Upload folder using huggingface_hub
Browse files- .gitattributes +3 -0
- added_tokens.json +3 -0
- chat_template.jinja +47 -0
- checkpoint-2000/added_tokens.json +3 -0
- checkpoint-2000/chat_template.jinja +47 -0
- checkpoint-2000/config.json +98 -0
- checkpoint-2000/generation_config.json +10 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/pytorch_model-00001-of-00002.bin +3 -0
- checkpoint-2000/pytorch_model-00002-of-00002.bin +3 -0
- checkpoint-2000/pytorch_model.bin.index.json +892 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/special_tokens_map.json +33 -0
- checkpoint-2000/tokenizer.json +3 -0
- checkpoint-2000/tokenizer.model +3 -0
- checkpoint-2000/tokenizer_config.json +0 -0
- checkpoint-2000/trainer_state.json +1434 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2250/added_tokens.json +3 -0
- checkpoint-2250/chat_template.jinja +47 -0
- checkpoint-2250/config.json +98 -0
- checkpoint-2250/generation_config.json +10 -0
- checkpoint-2250/optimizer.pt +3 -0
- checkpoint-2250/pytorch_model-00001-of-00002.bin +3 -0
- checkpoint-2250/pytorch_model-00002-of-00002.bin +3 -0
- checkpoint-2250/pytorch_model.bin.index.json +892 -0
- checkpoint-2250/rng_state.pth +3 -0
- checkpoint-2250/scheduler.pt +3 -0
- checkpoint-2250/special_tokens_map.json +33 -0
- checkpoint-2250/tokenizer.json +3 -0
- checkpoint-2250/tokenizer.model +3 -0
- checkpoint-2250/tokenizer_config.json +0 -0
- checkpoint-2250/trainer_state.json +1609 -0
- checkpoint-2250/training_args.bin +3 -0
- config.json +98 -0
- generation_config.json +10 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +892 -0
- runs/Jul19_18-09-32_192-222-58-77/events.out.tfevents.1752948573.192-222-58-77.5282.0 +3 -0
- runs/Jul19_18-11-11_192-222-58-77/events.out.tfevents.1752948671.192-222-58-77.5752.0 +3 -0
- runs/Jul19_18-22-00_192-222-58-77/events.out.tfevents.1752949320.192-222-58-77.7466.0 +3 -0
- runs/Jul19_18-58-05_192-222-58-77/events.out.tfevents.1752951485.192-222-58-77.13141.0 +3 -0
- runs/Jul19_19-53-53_192-222-58-77/events.out.tfevents.1752954833.192-222-58-77.21133.0 +3 -0
- special_tokens_map.json +33 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-2250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}
|
| 2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
| 3 |
+
{%- if messages[0]['content'] is string -%}
|
| 4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 5 |
+
|
| 6 |
+
' -%}
|
| 7 |
+
{%- else -%}
|
| 8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
| 9 |
+
|
| 10 |
+
' -%}
|
| 11 |
+
{%- endif -%}
|
| 12 |
+
{%- set loop_messages = messages[1:] -%}
|
| 13 |
+
{%- else -%}
|
| 14 |
+
{%- set first_user_prefix = "" -%}
|
| 15 |
+
{%- set loop_messages = messages -%}
|
| 16 |
+
{%- endif -%}
|
| 17 |
+
{%- for message in loop_messages -%}
|
| 18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 20 |
+
{%- endif -%}
|
| 21 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 22 |
+
{%- set role = "model" -%}
|
| 23 |
+
{%- else -%}
|
| 24 |
+
{%- set role = message['role'] -%}
|
| 25 |
+
{%- endif -%}
|
| 26 |
+
{{ '<start_of_turn>' + role + '
|
| 27 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 28 |
+
{%- if message['content'] is string -%}
|
| 29 |
+
{{ message['content'] | trim }}
|
| 30 |
+
{%- elif message['content'] is iterable -%}
|
| 31 |
+
{%- for item in message['content'] -%}
|
| 32 |
+
{%- if item['type'] == 'image' -%}
|
| 33 |
+
{{ '<start_of_image>' }}
|
| 34 |
+
{%- elif item['type'] == 'text' -%}
|
| 35 |
+
{{ item['text'] | trim }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
{%- else -%}
|
| 39 |
+
{{ raise_exception("Invalid content type") }}
|
| 40 |
+
{%- endif -%}
|
| 41 |
+
{{ '<end_of_turn>
|
| 42 |
+
' }}
|
| 43 |
+
{%- endfor -%}
|
| 44 |
+
{%- if add_generation_prompt -%}
|
| 45 |
+
{{'<start_of_turn>model
|
| 46 |
+
'}}
|
| 47 |
+
{%- endif -%}
|
checkpoint-2000/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
checkpoint-2000/chat_template.jinja
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}
|
| 2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
| 3 |
+
{%- if messages[0]['content'] is string -%}
|
| 4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 5 |
+
|
| 6 |
+
' -%}
|
| 7 |
+
{%- else -%}
|
| 8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
| 9 |
+
|
| 10 |
+
' -%}
|
| 11 |
+
{%- endif -%}
|
| 12 |
+
{%- set loop_messages = messages[1:] -%}
|
| 13 |
+
{%- else -%}
|
| 14 |
+
{%- set first_user_prefix = "" -%}
|
| 15 |
+
{%- set loop_messages = messages -%}
|
| 16 |
+
{%- endif -%}
|
| 17 |
+
{%- for message in loop_messages -%}
|
| 18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 20 |
+
{%- endif -%}
|
| 21 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 22 |
+
{%- set role = "model" -%}
|
| 23 |
+
{%- else -%}
|
| 24 |
+
{%- set role = message['role'] -%}
|
| 25 |
+
{%- endif -%}
|
| 26 |
+
{{ '<start_of_turn>' + role + '
|
| 27 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 28 |
+
{%- if message['content'] is string -%}
|
| 29 |
+
{{ message['content'] | trim }}
|
| 30 |
+
{%- elif message['content'] is iterable -%}
|
| 31 |
+
{%- for item in message['content'] -%}
|
| 32 |
+
{%- if item['type'] == 'image' -%}
|
| 33 |
+
{{ '<start_of_image>' }}
|
| 34 |
+
{%- elif item['type'] == 'text' -%}
|
| 35 |
+
{{ item['text'] | trim }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
{%- else -%}
|
| 39 |
+
{{ raise_exception("Invalid content type") }}
|
| 40 |
+
{%- endif -%}
|
| 41 |
+
{{ '<end_of_turn>
|
| 42 |
+
' }}
|
| 43 |
+
{%- endfor -%}
|
| 44 |
+
{%- if add_generation_prompt -%}
|
| 45 |
+
{{'<start_of_turn>model
|
| 46 |
+
'}}
|
| 47 |
+
{%- endif -%}
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"boi_token_index": 255999,
|
| 6 |
+
"eoi_token_index": 256000,
|
| 7 |
+
"eos_token_id": [
|
| 8 |
+
1,
|
| 9 |
+
106
|
| 10 |
+
],
|
| 11 |
+
"image_token_index": 262144,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"mm_tokens_per_image": 256,
|
| 14 |
+
"model_type": "gemma3",
|
| 15 |
+
"pad_token_id": 1,
|
| 16 |
+
"text_config": {
|
| 17 |
+
"_sliding_window_pattern": 6,
|
| 18 |
+
"attention_bias": false,
|
| 19 |
+
"attention_dropout": 0.0,
|
| 20 |
+
"attn_logit_softcapping": null,
|
| 21 |
+
"final_logit_softcapping": null,
|
| 22 |
+
"head_dim": 256,
|
| 23 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 24 |
+
"hidden_size": 2560,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 10240,
|
| 27 |
+
"layer_types": [
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"sliding_attention"
|
| 62 |
+
],
|
| 63 |
+
"max_position_embeddings": 131072,
|
| 64 |
+
"model_type": "gemma3_text",
|
| 65 |
+
"num_attention_heads": 8,
|
| 66 |
+
"num_hidden_layers": 34,
|
| 67 |
+
"num_key_value_heads": 4,
|
| 68 |
+
"query_pre_attn_scalar": 256,
|
| 69 |
+
"rms_norm_eps": 1e-06,
|
| 70 |
+
"rope_local_base_freq": 10000,
|
| 71 |
+
"rope_scaling": {
|
| 72 |
+
"factor": 8.0,
|
| 73 |
+
"rope_type": "linear"
|
| 74 |
+
},
|
| 75 |
+
"rope_theta": 1000000,
|
| 76 |
+
"sliding_window": 1024,
|
| 77 |
+
"torch_dtype": "bfloat16",
|
| 78 |
+
"use_cache": true,
|
| 79 |
+
"vocab_size": 262208
|
| 80 |
+
},
|
| 81 |
+
"torch_dtype": "bfloat16",
|
| 82 |
+
"transformers_version": "4.53.2",
|
| 83 |
+
"vision_config": {
|
| 84 |
+
"attention_dropout": 0.0,
|
| 85 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 86 |
+
"hidden_size": 1152,
|
| 87 |
+
"image_size": 896,
|
| 88 |
+
"intermediate_size": 4304,
|
| 89 |
+
"layer_norm_eps": 1e-06,
|
| 90 |
+
"model_type": "siglip_vision_model",
|
| 91 |
+
"num_attention_heads": 16,
|
| 92 |
+
"num_channels": 3,
|
| 93 |
+
"num_hidden_layers": 27,
|
| 94 |
+
"patch_size": 14,
|
| 95 |
+
"torch_dtype": "bfloat16",
|
| 96 |
+
"vision_use_head": false
|
| 97 |
+
}
|
| 98 |
+
}
|
checkpoint-2000/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
106
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"transformers_version": "4.53.2"
|
| 10 |
+
}
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c257ee3f55a321cc7c2b8435910507513e464462e0457ca91a226f95846327ea
|
| 3 |
+
size 15521442411
|
checkpoint-2000/pytorch_model-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ab64823b2ab704e9d3dc0ac86269f807cc5b67a2e532b2e1117cc8966d0af34
|
| 3 |
+
size 4961400895
|
checkpoint-2000/pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f47f8eb9ff79fbf2e771e52f14ab388cfddb1aac334298b0c642673eee983409
|
| 3 |
+
size 3639086660
|
checkpoint-2000/pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,892 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4300079472,
|
| 4 |
+
"total_size": 8600158944
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"language_model.lm_head.weight": "pytorch_model-00001-of-00002.bin",
|
| 8 |
+
"language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
| 9 |
+
"language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 10 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 11 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 12 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 13 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 14 |
+
"language_model.model.layers.0.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 15 |
+
"language_model.model.layers.0.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 16 |
+
"language_model.model.layers.0.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 17 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 18 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 19 |
+
"language_model.model.layers.0.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 20 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 21 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 22 |
+
"language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 23 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 24 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 25 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 26 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 27 |
+
"language_model.model.layers.1.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 28 |
+
"language_model.model.layers.1.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 29 |
+
"language_model.model.layers.1.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 30 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 31 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 32 |
+
"language_model.model.layers.1.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 33 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 34 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 35 |
+
"language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 36 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 37 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 38 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 39 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 40 |
+
"language_model.model.layers.10.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 41 |
+
"language_model.model.layers.10.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 42 |
+
"language_model.model.layers.10.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 43 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 44 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 45 |
+
"language_model.model.layers.10.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 46 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 47 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 48 |
+
"language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 49 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 50 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 51 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 52 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 53 |
+
"language_model.model.layers.11.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 54 |
+
"language_model.model.layers.11.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 55 |
+
"language_model.model.layers.11.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 56 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 57 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 58 |
+
"language_model.model.layers.11.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 59 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 60 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 61 |
+
"language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 62 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 63 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 64 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 65 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 66 |
+
"language_model.model.layers.12.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 67 |
+
"language_model.model.layers.12.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 68 |
+
"language_model.model.layers.12.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 69 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 70 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 71 |
+
"language_model.model.layers.12.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 72 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 73 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 74 |
+
"language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 75 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 76 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 77 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 78 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 79 |
+
"language_model.model.layers.13.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 80 |
+
"language_model.model.layers.13.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 81 |
+
"language_model.model.layers.13.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 82 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 83 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 84 |
+
"language_model.model.layers.13.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 85 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 86 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 87 |
+
"language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 88 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 89 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 90 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 91 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 92 |
+
"language_model.model.layers.14.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 93 |
+
"language_model.model.layers.14.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 94 |
+
"language_model.model.layers.14.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 95 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 96 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 97 |
+
"language_model.model.layers.14.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 98 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 99 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 100 |
+
"language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 101 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 102 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 103 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 104 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 105 |
+
"language_model.model.layers.15.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 106 |
+
"language_model.model.layers.15.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 107 |
+
"language_model.model.layers.15.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 108 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 109 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 110 |
+
"language_model.model.layers.15.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 111 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 112 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 113 |
+
"language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 114 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 115 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 116 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 117 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 118 |
+
"language_model.model.layers.16.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 119 |
+
"language_model.model.layers.16.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 120 |
+
"language_model.model.layers.16.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 121 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 122 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 123 |
+
"language_model.model.layers.16.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 124 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 125 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 126 |
+
"language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 127 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 128 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 129 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 130 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 131 |
+
"language_model.model.layers.17.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 132 |
+
"language_model.model.layers.17.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 133 |
+
"language_model.model.layers.17.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 134 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 135 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 136 |
+
"language_model.model.layers.17.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 137 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 138 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 139 |
+
"language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 140 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 141 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 142 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 143 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 144 |
+
"language_model.model.layers.18.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 145 |
+
"language_model.model.layers.18.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 146 |
+
"language_model.model.layers.18.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 147 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 148 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 149 |
+
"language_model.model.layers.18.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 150 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 151 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 152 |
+
"language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 153 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 154 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 155 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 156 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 157 |
+
"language_model.model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 158 |
+
"language_model.model.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 159 |
+
"language_model.model.layers.19.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 160 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 161 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 162 |
+
"language_model.model.layers.19.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 163 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 164 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 165 |
+
"language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 166 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 167 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 168 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 169 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 170 |
+
"language_model.model.layers.2.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 171 |
+
"language_model.model.layers.2.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 172 |
+
"language_model.model.layers.2.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 173 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 174 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 175 |
+
"language_model.model.layers.2.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 176 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 177 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 178 |
+
"language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 179 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 180 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 181 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 182 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 183 |
+
"language_model.model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 184 |
+
"language_model.model.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 185 |
+
"language_model.model.layers.20.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 186 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 187 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 188 |
+
"language_model.model.layers.20.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 189 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 190 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 191 |
+
"language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 192 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 193 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 194 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 195 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 196 |
+
"language_model.model.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 197 |
+
"language_model.model.layers.21.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 198 |
+
"language_model.model.layers.21.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 199 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 200 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 201 |
+
"language_model.model.layers.21.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 202 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 203 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 204 |
+
"language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 205 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 206 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 207 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 208 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 209 |
+
"language_model.model.layers.22.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 210 |
+
"language_model.model.layers.22.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 211 |
+
"language_model.model.layers.22.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 212 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 213 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 214 |
+
"language_model.model.layers.22.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 215 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 216 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 217 |
+
"language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 218 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 219 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 220 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 221 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 222 |
+
"language_model.model.layers.23.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 223 |
+
"language_model.model.layers.23.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 224 |
+
"language_model.model.layers.23.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 225 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 226 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 227 |
+
"language_model.model.layers.23.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 228 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 229 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 230 |
+
"language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 231 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 232 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 233 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 234 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 235 |
+
"language_model.model.layers.24.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 236 |
+
"language_model.model.layers.24.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 237 |
+
"language_model.model.layers.24.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 238 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 239 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 240 |
+
"language_model.model.layers.24.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 241 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 242 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 243 |
+
"language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 244 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 245 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 246 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 247 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 248 |
+
"language_model.model.layers.25.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 249 |
+
"language_model.model.layers.25.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 250 |
+
"language_model.model.layers.25.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 251 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 252 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 253 |
+
"language_model.model.layers.25.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 254 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 255 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 256 |
+
"language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 257 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 258 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 259 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 260 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 261 |
+
"language_model.model.layers.26.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 262 |
+
"language_model.model.layers.26.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 263 |
+
"language_model.model.layers.26.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 264 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 265 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 266 |
+
"language_model.model.layers.26.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 267 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 268 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 269 |
+
"language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 270 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 271 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 272 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 273 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 274 |
+
"language_model.model.layers.27.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 275 |
+
"language_model.model.layers.27.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 276 |
+
"language_model.model.layers.27.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 277 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 278 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 279 |
+
"language_model.model.layers.27.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 280 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 281 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 282 |
+
"language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 283 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 284 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 285 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 286 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 287 |
+
"language_model.model.layers.28.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 288 |
+
"language_model.model.layers.28.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 289 |
+
"language_model.model.layers.28.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 290 |
+
"language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 291 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 292 |
+
"language_model.model.layers.28.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 293 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 294 |
+
"language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 295 |
+
"language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 296 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 297 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 298 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 299 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 300 |
+
"language_model.model.layers.29.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 301 |
+
"language_model.model.layers.29.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 302 |
+
"language_model.model.layers.29.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 303 |
+
"language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 304 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 305 |
+
"language_model.model.layers.29.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 306 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 307 |
+
"language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 308 |
+
"language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 309 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 310 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 311 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 312 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 313 |
+
"language_model.model.layers.3.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 314 |
+
"language_model.model.layers.3.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 315 |
+
"language_model.model.layers.3.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 316 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 317 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 318 |
+
"language_model.model.layers.3.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 319 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 320 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 321 |
+
"language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 322 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 323 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 324 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 325 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 326 |
+
"language_model.model.layers.30.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 327 |
+
"language_model.model.layers.30.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 328 |
+
"language_model.model.layers.30.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 329 |
+
"language_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 330 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 331 |
+
"language_model.model.layers.30.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 332 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 333 |
+
"language_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 334 |
+
"language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 335 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 336 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 337 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 338 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 339 |
+
"language_model.model.layers.31.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 340 |
+
"language_model.model.layers.31.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 341 |
+
"language_model.model.layers.31.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 342 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 343 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 344 |
+
"language_model.model.layers.31.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 345 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 346 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 347 |
+
"language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 348 |
+
"language_model.model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 349 |
+
"language_model.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 350 |
+
"language_model.model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 351 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 352 |
+
"language_model.model.layers.32.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 353 |
+
"language_model.model.layers.32.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 354 |
+
"language_model.model.layers.32.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 355 |
+
"language_model.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 356 |
+
"language_model.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 357 |
+
"language_model.model.layers.32.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 358 |
+
"language_model.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 359 |
+
"language_model.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 360 |
+
"language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 361 |
+
"language_model.model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 362 |
+
"language_model.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 363 |
+
"language_model.model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 364 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 365 |
+
"language_model.model.layers.33.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 366 |
+
"language_model.model.layers.33.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 367 |
+
"language_model.model.layers.33.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 368 |
+
"language_model.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 369 |
+
"language_model.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 370 |
+
"language_model.model.layers.33.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 371 |
+
"language_model.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 372 |
+
"language_model.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 373 |
+
"language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 374 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 375 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 376 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 377 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 378 |
+
"language_model.model.layers.4.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 379 |
+
"language_model.model.layers.4.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 380 |
+
"language_model.model.layers.4.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 381 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 382 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 383 |
+
"language_model.model.layers.4.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 384 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 385 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 386 |
+
"language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 387 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 388 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 389 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 390 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 391 |
+
"language_model.model.layers.5.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 392 |
+
"language_model.model.layers.5.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 393 |
+
"language_model.model.layers.5.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 394 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 395 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 396 |
+
"language_model.model.layers.5.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 397 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 398 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 399 |
+
"language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 400 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 401 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 402 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 403 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 404 |
+
"language_model.model.layers.6.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 405 |
+
"language_model.model.layers.6.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 406 |
+
"language_model.model.layers.6.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 407 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 408 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 409 |
+
"language_model.model.layers.6.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 410 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 411 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 412 |
+
"language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 413 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 414 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 415 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 416 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 417 |
+
"language_model.model.layers.7.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 418 |
+
"language_model.model.layers.7.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 419 |
+
"language_model.model.layers.7.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 420 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 421 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 422 |
+
"language_model.model.layers.7.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 423 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 424 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 425 |
+
"language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 426 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 427 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 428 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 429 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 430 |
+
"language_model.model.layers.8.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 431 |
+
"language_model.model.layers.8.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 432 |
+
"language_model.model.layers.8.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 433 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 434 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 435 |
+
"language_model.model.layers.8.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 436 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 437 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 438 |
+
"language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 439 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 440 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 441 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 442 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 443 |
+
"language_model.model.layers.9.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 444 |
+
"language_model.model.layers.9.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 445 |
+
"language_model.model.layers.9.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 446 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 447 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 448 |
+
"language_model.model.layers.9.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 449 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 450 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 451 |
+
"language_model.model.norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 452 |
+
"multi_modal_projector.mm_input_projection_weight": "pytorch_model-00001-of-00002.bin",
|
| 453 |
+
"multi_modal_projector.mm_soft_emb_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 454 |
+
"vision_tower.vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00002.bin",
|
| 455 |
+
"vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
|
| 456 |
+
"vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
|
| 457 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 458 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 459 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 460 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 461 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 462 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 463 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 464 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 465 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 466 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 467 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 468 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 469 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 470 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 471 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 472 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 473 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 474 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 475 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 476 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 477 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 478 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 479 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 480 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 481 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 482 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 483 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 484 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 485 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 486 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 487 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 488 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 489 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 490 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 491 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 492 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 493 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 494 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 495 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 496 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 497 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 498 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 499 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 500 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 501 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 502 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 503 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 504 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 505 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 506 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 507 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 508 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 509 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 510 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 511 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 512 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 513 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 514 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 515 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 516 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 517 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 518 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 519 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 520 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 521 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 522 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 523 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 524 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 525 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 526 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 527 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 528 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 529 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 530 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 531 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 532 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 533 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 534 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 535 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 536 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 537 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 538 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 539 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 540 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 541 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 542 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 543 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 544 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 545 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 546 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 547 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 548 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 549 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 550 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 551 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 552 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 553 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 554 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 555 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 556 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 557 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 558 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 559 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 560 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 561 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 562 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 563 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 564 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 565 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 566 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 567 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 568 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 569 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 570 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 571 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 572 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 573 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 574 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 575 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 576 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 577 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 578 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 579 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 580 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 581 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 582 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 583 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 584 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 585 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 586 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 587 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 588 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 589 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 590 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 591 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 592 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 593 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 594 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 595 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 596 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 597 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 598 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 599 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 600 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 601 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 602 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 603 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 604 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 605 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 606 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 607 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 608 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 609 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 610 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 611 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 612 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 613 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 614 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 615 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 616 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 617 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 618 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 619 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 620 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 621 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 622 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 623 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 624 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 625 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 626 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 627 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 628 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 629 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 630 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 631 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 632 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 633 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 634 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 635 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 636 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 637 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 638 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 639 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 640 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 641 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 642 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 643 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 644 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 645 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 646 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 647 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 648 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 649 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 650 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 651 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 652 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 653 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 654 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 655 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 656 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 657 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 658 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 659 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 660 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 661 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 662 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 663 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 664 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 665 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 666 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 667 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 668 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 669 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 670 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 671 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 672 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 673 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 674 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 675 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 676 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 677 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 678 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 679 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 680 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 681 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 682 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 683 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 684 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 685 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 686 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 687 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 688 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 689 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 690 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 691 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 692 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 693 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 694 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 695 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 696 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 697 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 698 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 699 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 700 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 701 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 702 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 703 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 704 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 705 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 706 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 707 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 708 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 709 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 710 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 711 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 712 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 713 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 714 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 715 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 716 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 717 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 718 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 719 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 720 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 721 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 722 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 723 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 724 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 725 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 726 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 727 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 728 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 729 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 730 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 731 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 732 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 733 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 734 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 735 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 736 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 737 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 738 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 739 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 740 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 741 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 742 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 743 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 744 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 745 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 746 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 747 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 748 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 749 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 750 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 751 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 752 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 753 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 754 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 755 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 756 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 757 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 758 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 759 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 760 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 761 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 762 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 763 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 764 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 765 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 766 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 767 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 768 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 769 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 770 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 771 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 772 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 773 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 774 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 775 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 776 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 777 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 778 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 779 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 780 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 781 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 782 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 783 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 784 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 785 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 786 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 787 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 788 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 789 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 790 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 791 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 792 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 793 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 794 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 795 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 796 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 797 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 798 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 799 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 800 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 801 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 802 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 803 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 804 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 805 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 806 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 807 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 808 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 809 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 810 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 811 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 812 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 813 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 814 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 815 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 816 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 817 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 818 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 819 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 820 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 821 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 822 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 823 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 824 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 825 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 826 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 827 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 828 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 829 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 830 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 831 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 832 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 833 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 834 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 835 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 836 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 837 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 838 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 839 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 840 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 841 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 842 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 843 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 844 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 845 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 846 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 847 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 848 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 849 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 850 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 851 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 852 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 853 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 854 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 855 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 856 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 857 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 858 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 859 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 860 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 861 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 862 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 863 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 864 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 865 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 866 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 867 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 868 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 869 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 870 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 871 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 872 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 873 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 874 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 875 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 876 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 877 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 878 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 879 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 880 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 881 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 882 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 883 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 884 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 885 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 886 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 887 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 888 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 889 |
+
"vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 890 |
+
"vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin"
|
| 891 |
+
}
|
| 892 |
+
}
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
|
| 3 |
+
size 14645
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ca0fc272c32fcf91c2a9431065a9de09e224f79395cd68500e5ef0b588ea7a5
|
| 3 |
+
size 1465
|
checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"eoi_token": "<end_of_image>",
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"content": "<eos>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"image_token": "<image_soft_token>",
|
| 19 |
+
"pad_token": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
checkpoint-2000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c96fd7401f729829eb0636c0285020112e74ace07bedf404c4c2461911b20287
|
| 3 |
+
size 33384821
|
checkpoint-2000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
checkpoint-2000/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,1434 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.17787264318747775,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0008893632159373888,
|
| 14 |
+
"grad_norm": 68.5,
|
| 15 |
+
"learning_rate": 2.7e-06,
|
| 16 |
+
"loss": 8.8776,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0017787264318747777,
|
| 21 |
+
"grad_norm": 39.0,
|
| 22 |
+
"learning_rate": 5.7000000000000005e-06,
|
| 23 |
+
"loss": 7.711,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0026680896478121665,
|
| 28 |
+
"grad_norm": 29.375,
|
| 29 |
+
"learning_rate": 8.7e-06,
|
| 30 |
+
"loss": 5.7038,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0035574528637495554,
|
| 35 |
+
"grad_norm": 24.5,
|
| 36 |
+
"learning_rate": 1.1700000000000001e-05,
|
| 37 |
+
"loss": 4.746,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.004446816079686944,
|
| 42 |
+
"grad_norm": 22.625,
|
| 43 |
+
"learning_rate": 1.47e-05,
|
| 44 |
+
"loss": 4.1094,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.005336179295624333,
|
| 49 |
+
"grad_norm": 21.625,
|
| 50 |
+
"learning_rate": 1.77e-05,
|
| 51 |
+
"loss": 4.0746,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0062255425115617215,
|
| 56 |
+
"grad_norm": 25.25,
|
| 57 |
+
"learning_rate": 2.07e-05,
|
| 58 |
+
"loss": 3.8396,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.007114905727499111,
|
| 63 |
+
"grad_norm": 20.875,
|
| 64 |
+
"learning_rate": 2.37e-05,
|
| 65 |
+
"loss": 3.8629,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0080042689434365,
|
| 70 |
+
"grad_norm": 22.875,
|
| 71 |
+
"learning_rate": 2.6700000000000002e-05,
|
| 72 |
+
"loss": 3.9097,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.008893632159373888,
|
| 77 |
+
"grad_norm": 19.375,
|
| 78 |
+
"learning_rate": 2.97e-05,
|
| 79 |
+
"loss": 3.763,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.009782995375311278,
|
| 84 |
+
"grad_norm": 19.625,
|
| 85 |
+
"learning_rate": 2.9874418604651165e-05,
|
| 86 |
+
"loss": 4.1501,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.010672358591248666,
|
| 91 |
+
"grad_norm": 19.0,
|
| 92 |
+
"learning_rate": 2.9734883720930235e-05,
|
| 93 |
+
"loss": 3.9038,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.011561721807186055,
|
| 98 |
+
"grad_norm": 16.625,
|
| 99 |
+
"learning_rate": 2.9595348837209305e-05,
|
| 100 |
+
"loss": 4.0583,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.012451085023123443,
|
| 105 |
+
"grad_norm": 16.375,
|
| 106 |
+
"learning_rate": 2.9455813953488376e-05,
|
| 107 |
+
"loss": 3.5958,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.013340448239060833,
|
| 112 |
+
"grad_norm": 15.375,
|
| 113 |
+
"learning_rate": 2.9316279069767443e-05,
|
| 114 |
+
"loss": 3.9075,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.014229811454998222,
|
| 119 |
+
"grad_norm": 15.625,
|
| 120 |
+
"learning_rate": 2.9176744186046513e-05,
|
| 121 |
+
"loss": 3.9495,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.01511917467093561,
|
| 126 |
+
"grad_norm": 18.125,
|
| 127 |
+
"learning_rate": 2.9037209302325583e-05,
|
| 128 |
+
"loss": 3.3247,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.016008537886873,
|
| 133 |
+
"grad_norm": 18.75,
|
| 134 |
+
"learning_rate": 2.889767441860465e-05,
|
| 135 |
+
"loss": 3.6863,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.01689790110281039,
|
| 140 |
+
"grad_norm": 15.625,
|
| 141 |
+
"learning_rate": 2.875813953488372e-05,
|
| 142 |
+
"loss": 3.3097,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.017787264318747775,
|
| 147 |
+
"grad_norm": 14.3125,
|
| 148 |
+
"learning_rate": 2.861860465116279e-05,
|
| 149 |
+
"loss": 3.48,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.018676627534685165,
|
| 154 |
+
"grad_norm": 17.875,
|
| 155 |
+
"learning_rate": 2.847906976744186e-05,
|
| 156 |
+
"loss": 3.6216,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.019565990750622556,
|
| 161 |
+
"grad_norm": 15.4375,
|
| 162 |
+
"learning_rate": 2.833953488372093e-05,
|
| 163 |
+
"loss": 3.4751,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.020455353966559942,
|
| 168 |
+
"grad_norm": 14.75,
|
| 169 |
+
"learning_rate": 2.8199999999999998e-05,
|
| 170 |
+
"loss": 3.9,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.021344717182497332,
|
| 175 |
+
"grad_norm": 14.8125,
|
| 176 |
+
"learning_rate": 2.8060465116279068e-05,
|
| 177 |
+
"loss": 3.7454,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.02223408039843472,
|
| 182 |
+
"grad_norm": 15.6875,
|
| 183 |
+
"learning_rate": 2.7920930232558138e-05,
|
| 184 |
+
"loss": 3.5053,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.02312344361437211,
|
| 189 |
+
"grad_norm": 14.5,
|
| 190 |
+
"learning_rate": 2.778139534883721e-05,
|
| 191 |
+
"loss": 3.3656,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.0240128068303095,
|
| 196 |
+
"grad_norm": 13.6875,
|
| 197 |
+
"learning_rate": 2.764186046511628e-05,
|
| 198 |
+
"loss": 3.769,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.024902170046246886,
|
| 203 |
+
"grad_norm": 15.0625,
|
| 204 |
+
"learning_rate": 2.750232558139535e-05,
|
| 205 |
+
"loss": 3.5721,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.025791533262184276,
|
| 210 |
+
"grad_norm": 14.6875,
|
| 211 |
+
"learning_rate": 2.736279069767442e-05,
|
| 212 |
+
"loss": 3.6104,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.026680896478121666,
|
| 217 |
+
"grad_norm": 13.875,
|
| 218 |
+
"learning_rate": 2.722325581395349e-05,
|
| 219 |
+
"loss": 3.5904,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.027570259694059053,
|
| 224 |
+
"grad_norm": 13.8125,
|
| 225 |
+
"learning_rate": 2.7083720930232556e-05,
|
| 226 |
+
"loss": 3.5633,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.028459622909996443,
|
| 231 |
+
"grad_norm": 13.5625,
|
| 232 |
+
"learning_rate": 2.6944186046511626e-05,
|
| 233 |
+
"loss": 3.3366,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.02934898612593383,
|
| 238 |
+
"grad_norm": 14.3125,
|
| 239 |
+
"learning_rate": 2.6804651162790697e-05,
|
| 240 |
+
"loss": 3.6519,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.03023834934187122,
|
| 245 |
+
"grad_norm": 14.4375,
|
| 246 |
+
"learning_rate": 2.6665116279069767e-05,
|
| 247 |
+
"loss": 3.4482,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.03112771255780861,
|
| 252 |
+
"grad_norm": 13.9375,
|
| 253 |
+
"learning_rate": 2.6525581395348837e-05,
|
| 254 |
+
"loss": 3.3554,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.032017075773746,
|
| 259 |
+
"grad_norm": 14.5625,
|
| 260 |
+
"learning_rate": 2.6386046511627907e-05,
|
| 261 |
+
"loss": 3.4008,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.03290643898968339,
|
| 266 |
+
"grad_norm": 14.375,
|
| 267 |
+
"learning_rate": 2.6246511627906978e-05,
|
| 268 |
+
"loss": 3.3279,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.03379580220562078,
|
| 273 |
+
"grad_norm": 13.9375,
|
| 274 |
+
"learning_rate": 2.6106976744186048e-05,
|
| 275 |
+
"loss": 3.487,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.03468516542155817,
|
| 280 |
+
"grad_norm": 14.625,
|
| 281 |
+
"learning_rate": 2.5967441860465115e-05,
|
| 282 |
+
"loss": 3.2542,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.03557452863749555,
|
| 287 |
+
"grad_norm": 13.1875,
|
| 288 |
+
"learning_rate": 2.5827906976744185e-05,
|
| 289 |
+
"loss": 3.3328,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.03646389185343294,
|
| 294 |
+
"grad_norm": 13.25,
|
| 295 |
+
"learning_rate": 2.5688372093023255e-05,
|
| 296 |
+
"loss": 3.5205,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.03735325506937033,
|
| 301 |
+
"grad_norm": 11.9375,
|
| 302 |
+
"learning_rate": 2.5548837209302325e-05,
|
| 303 |
+
"loss": 3.4151,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.03824261828530772,
|
| 308 |
+
"grad_norm": 13.625,
|
| 309 |
+
"learning_rate": 2.5409302325581396e-05,
|
| 310 |
+
"loss": 3.1404,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.03913198150124511,
|
| 315 |
+
"grad_norm": 14.0625,
|
| 316 |
+
"learning_rate": 2.5269767441860466e-05,
|
| 317 |
+
"loss": 3.5277,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.040021344717182494,
|
| 322 |
+
"grad_norm": 13.1875,
|
| 323 |
+
"learning_rate": 2.5130232558139536e-05,
|
| 324 |
+
"loss": 3.1584,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.040910707933119884,
|
| 329 |
+
"grad_norm": 13.4375,
|
| 330 |
+
"learning_rate": 2.4990697674418606e-05,
|
| 331 |
+
"loss": 3.4669,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.041800071149057275,
|
| 336 |
+
"grad_norm": 14.5625,
|
| 337 |
+
"learning_rate": 2.4851162790697673e-05,
|
| 338 |
+
"loss": 3.2653,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.042689434364994665,
|
| 343 |
+
"grad_norm": 13.9375,
|
| 344 |
+
"learning_rate": 2.4711627906976743e-05,
|
| 345 |
+
"loss": 3.4219,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.043578797580932055,
|
| 350 |
+
"grad_norm": 12.875,
|
| 351 |
+
"learning_rate": 2.4572093023255814e-05,
|
| 352 |
+
"loss": 3.508,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.04446816079686944,
|
| 357 |
+
"grad_norm": 14.0625,
|
| 358 |
+
"learning_rate": 2.4432558139534884e-05,
|
| 359 |
+
"loss": 3.3343,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.04535752401280683,
|
| 364 |
+
"grad_norm": 13.75,
|
| 365 |
+
"learning_rate": 2.4293023255813954e-05,
|
| 366 |
+
"loss": 3.5054,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.04624688722874422,
|
| 371 |
+
"grad_norm": 15.25,
|
| 372 |
+
"learning_rate": 2.4153488372093024e-05,
|
| 373 |
+
"loss": 3.0298,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.04713625044468161,
|
| 378 |
+
"grad_norm": 13.75,
|
| 379 |
+
"learning_rate": 2.4013953488372095e-05,
|
| 380 |
+
"loss": 3.4306,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.048025613660619,
|
| 385 |
+
"grad_norm": 14.25,
|
| 386 |
+
"learning_rate": 2.3874418604651165e-05,
|
| 387 |
+
"loss": 3.1824,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.04891497687655639,
|
| 392 |
+
"grad_norm": 12.3125,
|
| 393 |
+
"learning_rate": 2.373488372093023e-05,
|
| 394 |
+
"loss": 3.211,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.04980434009249377,
|
| 399 |
+
"grad_norm": 13.75,
|
| 400 |
+
"learning_rate": 2.3595348837209302e-05,
|
| 401 |
+
"loss": 3.091,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.05069370330843116,
|
| 406 |
+
"grad_norm": 13.75,
|
| 407 |
+
"learning_rate": 2.3455813953488372e-05,
|
| 408 |
+
"loss": 3.234,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.05158306652436855,
|
| 413 |
+
"grad_norm": 13.75,
|
| 414 |
+
"learning_rate": 2.3316279069767442e-05,
|
| 415 |
+
"loss": 3.1404,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.05247242974030594,
|
| 420 |
+
"grad_norm": 13.25,
|
| 421 |
+
"learning_rate": 2.3176744186046513e-05,
|
| 422 |
+
"loss": 3.2191,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.05336179295624333,
|
| 427 |
+
"grad_norm": 12.625,
|
| 428 |
+
"learning_rate": 2.3037209302325583e-05,
|
| 429 |
+
"loss": 3.0968,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.054251156172180716,
|
| 434 |
+
"grad_norm": 13.5625,
|
| 435 |
+
"learning_rate": 2.2897674418604653e-05,
|
| 436 |
+
"loss": 3.1108,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.055140519388118106,
|
| 441 |
+
"grad_norm": 12.75,
|
| 442 |
+
"learning_rate": 2.2758139534883723e-05,
|
| 443 |
+
"loss": 3.028,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.056029882604055496,
|
| 448 |
+
"grad_norm": 12.375,
|
| 449 |
+
"learning_rate": 2.261860465116279e-05,
|
| 450 |
+
"loss": 3.1469,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.056919245819992886,
|
| 455 |
+
"grad_norm": 14.8125,
|
| 456 |
+
"learning_rate": 2.247906976744186e-05,
|
| 457 |
+
"loss": 3.1258,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.057808609035930276,
|
| 462 |
+
"grad_norm": 12.5625,
|
| 463 |
+
"learning_rate": 2.233953488372093e-05,
|
| 464 |
+
"loss": 3.1147,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.05869797225186766,
|
| 469 |
+
"grad_norm": 13.1875,
|
| 470 |
+
"learning_rate": 2.22e-05,
|
| 471 |
+
"loss": 3.0447,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.05958733546780505,
|
| 476 |
+
"grad_norm": 15.3125,
|
| 477 |
+
"learning_rate": 2.206046511627907e-05,
|
| 478 |
+
"loss": 3.1177,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.06047669868374244,
|
| 483 |
+
"grad_norm": 13.6875,
|
| 484 |
+
"learning_rate": 2.192093023255814e-05,
|
| 485 |
+
"loss": 3.2542,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.06136606189967983,
|
| 490 |
+
"grad_norm": 13.1875,
|
| 491 |
+
"learning_rate": 2.178139534883721e-05,
|
| 492 |
+
"loss": 3.188,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.06225542511561722,
|
| 497 |
+
"grad_norm": 13.625,
|
| 498 |
+
"learning_rate": 2.1641860465116282e-05,
|
| 499 |
+
"loss": 3.2298,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.06314478833155461,
|
| 504 |
+
"grad_norm": 14.0625,
|
| 505 |
+
"learning_rate": 2.150232558139535e-05,
|
| 506 |
+
"loss": 3.1127,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.064034151547492,
|
| 511 |
+
"grad_norm": 15.1875,
|
| 512 |
+
"learning_rate": 2.136279069767442e-05,
|
| 513 |
+
"loss": 3.1468,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.06492351476342939,
|
| 518 |
+
"grad_norm": 12.625,
|
| 519 |
+
"learning_rate": 2.122325581395349e-05,
|
| 520 |
+
"loss": 3.2763,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.06581287797936677,
|
| 525 |
+
"grad_norm": 13.875,
|
| 526 |
+
"learning_rate": 2.108372093023256e-05,
|
| 527 |
+
"loss": 3.051,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.06670224119530416,
|
| 532 |
+
"grad_norm": 13.9375,
|
| 533 |
+
"learning_rate": 2.094418604651163e-05,
|
| 534 |
+
"loss": 3.1937,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.06759160441124155,
|
| 539 |
+
"grad_norm": 13.3125,
|
| 540 |
+
"learning_rate": 2.08046511627907e-05,
|
| 541 |
+
"loss": 3.0506,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.06848096762717894,
|
| 546 |
+
"grad_norm": 12.625,
|
| 547 |
+
"learning_rate": 2.066511627906977e-05,
|
| 548 |
+
"loss": 2.975,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.06937033084311633,
|
| 553 |
+
"grad_norm": 12.75,
|
| 554 |
+
"learning_rate": 2.052558139534884e-05,
|
| 555 |
+
"loss": 2.9174,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.07025969405905372,
|
| 560 |
+
"grad_norm": 12.875,
|
| 561 |
+
"learning_rate": 2.0386046511627907e-05,
|
| 562 |
+
"loss": 3.0532,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.0711490572749911,
|
| 567 |
+
"grad_norm": 12.4375,
|
| 568 |
+
"learning_rate": 2.0246511627906977e-05,
|
| 569 |
+
"loss": 3.2092,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.0720384204909285,
|
| 574 |
+
"grad_norm": 12.625,
|
| 575 |
+
"learning_rate": 2.0106976744186048e-05,
|
| 576 |
+
"loss": 2.9702,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.07292778370686588,
|
| 581 |
+
"grad_norm": 14.0625,
|
| 582 |
+
"learning_rate": 1.9967441860465118e-05,
|
| 583 |
+
"loss": 3.0595,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.07381714692280328,
|
| 588 |
+
"grad_norm": 14.5,
|
| 589 |
+
"learning_rate": 1.9827906976744188e-05,
|
| 590 |
+
"loss": 3.0102,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.07470651013874066,
|
| 595 |
+
"grad_norm": 13.25,
|
| 596 |
+
"learning_rate": 1.968837209302326e-05,
|
| 597 |
+
"loss": 3.0725,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.07559587335467804,
|
| 602 |
+
"grad_norm": 13.6875,
|
| 603 |
+
"learning_rate": 1.954883720930233e-05,
|
| 604 |
+
"loss": 3.0679,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.07648523657061544,
|
| 609 |
+
"grad_norm": 13.1875,
|
| 610 |
+
"learning_rate": 1.94093023255814e-05,
|
| 611 |
+
"loss": 3.0764,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.07737459978655283,
|
| 616 |
+
"grad_norm": 14.5,
|
| 617 |
+
"learning_rate": 1.9269767441860466e-05,
|
| 618 |
+
"loss": 2.768,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.07826396300249022,
|
| 623 |
+
"grad_norm": 14.875,
|
| 624 |
+
"learning_rate": 1.9130232558139536e-05,
|
| 625 |
+
"loss": 3.2016,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.0791533262184276,
|
| 630 |
+
"grad_norm": 12.875,
|
| 631 |
+
"learning_rate": 1.8990697674418606e-05,
|
| 632 |
+
"loss": 3.0906,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.08004268943436499,
|
| 637 |
+
"grad_norm": 13.0,
|
| 638 |
+
"learning_rate": 1.8851162790697673e-05,
|
| 639 |
+
"loss": 3.1441,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.08093205265030239,
|
| 644 |
+
"grad_norm": 13.25,
|
| 645 |
+
"learning_rate": 1.8711627906976743e-05,
|
| 646 |
+
"loss": 2.9791,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.08182141586623977,
|
| 651 |
+
"grad_norm": 14.0625,
|
| 652 |
+
"learning_rate": 1.8572093023255814e-05,
|
| 653 |
+
"loss": 2.8393,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.08271077908217717,
|
| 658 |
+
"grad_norm": 13.1875,
|
| 659 |
+
"learning_rate": 1.8432558139534884e-05,
|
| 660 |
+
"loss": 2.9332,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.08360014229811455,
|
| 665 |
+
"grad_norm": 13.0625,
|
| 666 |
+
"learning_rate": 1.8293023255813954e-05,
|
| 667 |
+
"loss": 2.9787,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.08448950551405193,
|
| 672 |
+
"grad_norm": 15.375,
|
| 673 |
+
"learning_rate": 1.815348837209302e-05,
|
| 674 |
+
"loss": 2.8229,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.08537886872998933,
|
| 679 |
+
"grad_norm": 13.5625,
|
| 680 |
+
"learning_rate": 1.801395348837209e-05,
|
| 681 |
+
"loss": 2.8112,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.08626823194592671,
|
| 686 |
+
"grad_norm": 16.75,
|
| 687 |
+
"learning_rate": 1.787441860465116e-05,
|
| 688 |
+
"loss": 3.0131,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.08715759516186411,
|
| 693 |
+
"grad_norm": 13.9375,
|
| 694 |
+
"learning_rate": 1.773488372093023e-05,
|
| 695 |
+
"loss": 2.9496,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.08804695837780149,
|
| 700 |
+
"grad_norm": 15.0625,
|
| 701 |
+
"learning_rate": 1.7595348837209302e-05,
|
| 702 |
+
"loss": 3.0641,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.08893632159373888,
|
| 707 |
+
"grad_norm": 13.0,
|
| 708 |
+
"learning_rate": 1.7455813953488372e-05,
|
| 709 |
+
"loss": 2.8714,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.08982568480967627,
|
| 714 |
+
"grad_norm": 13.8125,
|
| 715 |
+
"learning_rate": 1.7316279069767442e-05,
|
| 716 |
+
"loss": 2.7792,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.09071504802561366,
|
| 721 |
+
"grad_norm": 13.875,
|
| 722 |
+
"learning_rate": 1.7176744186046512e-05,
|
| 723 |
+
"loss": 2.9472,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.09160441124155105,
|
| 728 |
+
"grad_norm": 14.0,
|
| 729 |
+
"learning_rate": 1.703720930232558e-05,
|
| 730 |
+
"loss": 2.5662,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.09249377445748844,
|
| 735 |
+
"grad_norm": 13.9375,
|
| 736 |
+
"learning_rate": 1.689767441860465e-05,
|
| 737 |
+
"loss": 2.82,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.09338313767342583,
|
| 742 |
+
"grad_norm": 13.875,
|
| 743 |
+
"learning_rate": 1.675813953488372e-05,
|
| 744 |
+
"loss": 2.8245,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.09427250088936322,
|
| 749 |
+
"grad_norm": 11.8125,
|
| 750 |
+
"learning_rate": 1.661860465116279e-05,
|
| 751 |
+
"loss": 2.8141,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.0951618641053006,
|
| 756 |
+
"grad_norm": 13.1875,
|
| 757 |
+
"learning_rate": 1.647906976744186e-05,
|
| 758 |
+
"loss": 2.8975,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.096051227321238,
|
| 763 |
+
"grad_norm": 14.625,
|
| 764 |
+
"learning_rate": 1.633953488372093e-05,
|
| 765 |
+
"loss": 2.7996,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.09694059053717538,
|
| 770 |
+
"grad_norm": 12.625,
|
| 771 |
+
"learning_rate": 1.62e-05,
|
| 772 |
+
"loss": 2.7679,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.09782995375311278,
|
| 777 |
+
"grad_norm": 14.0625,
|
| 778 |
+
"learning_rate": 1.606046511627907e-05,
|
| 779 |
+
"loss": 3.0057,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.09871931696905016,
|
| 784 |
+
"grad_norm": 13.6875,
|
| 785 |
+
"learning_rate": 1.5920930232558138e-05,
|
| 786 |
+
"loss": 2.5742,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.09960868018498754,
|
| 791 |
+
"grad_norm": 15.3125,
|
| 792 |
+
"learning_rate": 1.5781395348837208e-05,
|
| 793 |
+
"loss": 2.7903,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.10049804340092494,
|
| 798 |
+
"grad_norm": 14.8125,
|
| 799 |
+
"learning_rate": 1.564186046511628e-05,
|
| 800 |
+
"loss": 2.5664,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.10138740661686232,
|
| 805 |
+
"grad_norm": 13.8125,
|
| 806 |
+
"learning_rate": 1.550232558139535e-05,
|
| 807 |
+
"loss": 2.9392,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.10227676983279972,
|
| 812 |
+
"grad_norm": 13.9375,
|
| 813 |
+
"learning_rate": 1.536279069767442e-05,
|
| 814 |
+
"loss": 2.7105,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.1031661330487371,
|
| 819 |
+
"grad_norm": 14.5,
|
| 820 |
+
"learning_rate": 1.5223255813953489e-05,
|
| 821 |
+
"loss": 2.9472,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.10405549626467449,
|
| 826 |
+
"grad_norm": 13.4375,
|
| 827 |
+
"learning_rate": 1.508372093023256e-05,
|
| 828 |
+
"loss": 2.7698,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.10494485948061189,
|
| 833 |
+
"grad_norm": 13.125,
|
| 834 |
+
"learning_rate": 1.4944186046511628e-05,
|
| 835 |
+
"loss": 2.8998,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.10583422269654927,
|
| 840 |
+
"grad_norm": 14.125,
|
| 841 |
+
"learning_rate": 1.4804651162790698e-05,
|
| 842 |
+
"loss": 2.7952,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.10672358591248667,
|
| 847 |
+
"grad_norm": 14.875,
|
| 848 |
+
"learning_rate": 1.4665116279069768e-05,
|
| 849 |
+
"loss": 2.7689,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.10761294912842405,
|
| 854 |
+
"grad_norm": 13.375,
|
| 855 |
+
"learning_rate": 1.4525581395348837e-05,
|
| 856 |
+
"loss": 3.0368,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.10850231234436143,
|
| 861 |
+
"grad_norm": 14.5,
|
| 862 |
+
"learning_rate": 1.4386046511627907e-05,
|
| 863 |
+
"loss": 2.8113,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.10939167556029883,
|
| 868 |
+
"grad_norm": 13.25,
|
| 869 |
+
"learning_rate": 1.4246511627906977e-05,
|
| 870 |
+
"loss": 2.5883,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.11028103877623621,
|
| 875 |
+
"grad_norm": 14.25,
|
| 876 |
+
"learning_rate": 1.4106976744186048e-05,
|
| 877 |
+
"loss": 2.9207,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.11117040199217361,
|
| 882 |
+
"grad_norm": 12.9375,
|
| 883 |
+
"learning_rate": 1.3967441860465116e-05,
|
| 884 |
+
"loss": 2.8662,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.11205976520811099,
|
| 889 |
+
"grad_norm": 14.25,
|
| 890 |
+
"learning_rate": 1.3827906976744186e-05,
|
| 891 |
+
"loss": 2.8439,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.11294912842404838,
|
| 896 |
+
"grad_norm": 13.1875,
|
| 897 |
+
"learning_rate": 1.3688372093023257e-05,
|
| 898 |
+
"loss": 2.8322,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.11383849163998577,
|
| 903 |
+
"grad_norm": 13.6875,
|
| 904 |
+
"learning_rate": 1.3548837209302327e-05,
|
| 905 |
+
"loss": 2.8627,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.11472785485592316,
|
| 910 |
+
"grad_norm": 12.8125,
|
| 911 |
+
"learning_rate": 1.3409302325581395e-05,
|
| 912 |
+
"loss": 2.733,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.11561721807186055,
|
| 917 |
+
"grad_norm": 12.75,
|
| 918 |
+
"learning_rate": 1.3269767441860466e-05,
|
| 919 |
+
"loss": 2.7608,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.11650658128779794,
|
| 924 |
+
"grad_norm": 14.4375,
|
| 925 |
+
"learning_rate": 1.3130232558139536e-05,
|
| 926 |
+
"loss": 2.7633,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.11739594450373532,
|
| 931 |
+
"grad_norm": 13.875,
|
| 932 |
+
"learning_rate": 1.2990697674418606e-05,
|
| 933 |
+
"loss": 2.682,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.11828530771967272,
|
| 938 |
+
"grad_norm": 14.4375,
|
| 939 |
+
"learning_rate": 1.2851162790697675e-05,
|
| 940 |
+
"loss": 2.7205,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.1191746709356101,
|
| 945 |
+
"grad_norm": 12.6875,
|
| 946 |
+
"learning_rate": 1.2711627906976745e-05,
|
| 947 |
+
"loss": 2.7408,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.1200640341515475,
|
| 952 |
+
"grad_norm": 13.5,
|
| 953 |
+
"learning_rate": 1.2572093023255815e-05,
|
| 954 |
+
"loss": 3.0955,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.12095339736748488,
|
| 959 |
+
"grad_norm": 13.8125,
|
| 960 |
+
"learning_rate": 1.2432558139534885e-05,
|
| 961 |
+
"loss": 2.8928,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.12184276058342226,
|
| 966 |
+
"grad_norm": 12.5625,
|
| 967 |
+
"learning_rate": 1.2293023255813954e-05,
|
| 968 |
+
"loss": 2.7429,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.12273212379935966,
|
| 973 |
+
"grad_norm": 14.3125,
|
| 974 |
+
"learning_rate": 1.2153488372093024e-05,
|
| 975 |
+
"loss": 2.6795,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.12362148701529704,
|
| 980 |
+
"grad_norm": 13.125,
|
| 981 |
+
"learning_rate": 1.2013953488372094e-05,
|
| 982 |
+
"loss": 2.6802,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.12451085023123444,
|
| 987 |
+
"grad_norm": 13.8125,
|
| 988 |
+
"learning_rate": 1.1874418604651165e-05,
|
| 989 |
+
"loss": 2.6818,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.12540021344717184,
|
| 994 |
+
"grad_norm": 13.875,
|
| 995 |
+
"learning_rate": 1.1734883720930233e-05,
|
| 996 |
+
"loss": 2.5968,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.12628957666310922,
|
| 1001 |
+
"grad_norm": 13.75,
|
| 1002 |
+
"learning_rate": 1.1595348837209303e-05,
|
| 1003 |
+
"loss": 2.7026,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.1271789398790466,
|
| 1008 |
+
"grad_norm": 13.5625,
|
| 1009 |
+
"learning_rate": 1.1455813953488372e-05,
|
| 1010 |
+
"loss": 2.8092,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.128068303094984,
|
| 1015 |
+
"grad_norm": 13.9375,
|
| 1016 |
+
"learning_rate": 1.1316279069767442e-05,
|
| 1017 |
+
"loss": 2.6957,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.12895766631092137,
|
| 1022 |
+
"grad_norm": 14.0,
|
| 1023 |
+
"learning_rate": 1.117674418604651e-05,
|
| 1024 |
+
"loss": 2.8901,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.12984702952685878,
|
| 1029 |
+
"grad_norm": 14.3125,
|
| 1030 |
+
"learning_rate": 1.1037209302325581e-05,
|
| 1031 |
+
"loss": 2.6284,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.13073639274279616,
|
| 1036 |
+
"grad_norm": 13.875,
|
| 1037 |
+
"learning_rate": 1.0897674418604651e-05,
|
| 1038 |
+
"loss": 2.9493,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.13162575595873355,
|
| 1043 |
+
"grad_norm": 13.5625,
|
| 1044 |
+
"learning_rate": 1.0758139534883721e-05,
|
| 1045 |
+
"loss": 2.6665,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.13251511917467093,
|
| 1050 |
+
"grad_norm": 14.125,
|
| 1051 |
+
"learning_rate": 1.061860465116279e-05,
|
| 1052 |
+
"loss": 2.8124,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.13340448239060831,
|
| 1057 |
+
"grad_norm": 13.8125,
|
| 1058 |
+
"learning_rate": 1.047906976744186e-05,
|
| 1059 |
+
"loss": 2.8094,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.13429384560654573,
|
| 1064 |
+
"grad_norm": 14.3125,
|
| 1065 |
+
"learning_rate": 1.033953488372093e-05,
|
| 1066 |
+
"loss": 2.6246,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.1351832088224831,
|
| 1071 |
+
"grad_norm": 14.5625,
|
| 1072 |
+
"learning_rate": 1.02e-05,
|
| 1073 |
+
"loss": 2.8486,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.1360725720384205,
|
| 1078 |
+
"grad_norm": 13.625,
|
| 1079 |
+
"learning_rate": 1.0060465116279069e-05,
|
| 1080 |
+
"loss": 2.7712,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.13696193525435787,
|
| 1085 |
+
"grad_norm": 14.5625,
|
| 1086 |
+
"learning_rate": 9.92093023255814e-06,
|
| 1087 |
+
"loss": 2.7667,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.13785129847029526,
|
| 1092 |
+
"grad_norm": 14.375,
|
| 1093 |
+
"learning_rate": 9.78139534883721e-06,
|
| 1094 |
+
"loss": 2.6918,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.13874066168623267,
|
| 1099 |
+
"grad_norm": 14.1875,
|
| 1100 |
+
"learning_rate": 9.64186046511628e-06,
|
| 1101 |
+
"loss": 2.872,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.13963002490217005,
|
| 1106 |
+
"grad_norm": 14.375,
|
| 1107 |
+
"learning_rate": 9.502325581395348e-06,
|
| 1108 |
+
"loss": 2.9586,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.14051938811810744,
|
| 1113 |
+
"grad_norm": 13.8125,
|
| 1114 |
+
"learning_rate": 9.362790697674419e-06,
|
| 1115 |
+
"loss": 2.5803,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.14140875133404482,
|
| 1120 |
+
"grad_norm": 13.8125,
|
| 1121 |
+
"learning_rate": 9.223255813953489e-06,
|
| 1122 |
+
"loss": 2.72,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.1422981145499822,
|
| 1127 |
+
"grad_norm": 13.4375,
|
| 1128 |
+
"learning_rate": 9.083720930232559e-06,
|
| 1129 |
+
"loss": 2.7268,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.1431874777659196,
|
| 1134 |
+
"grad_norm": 14.0625,
|
| 1135 |
+
"learning_rate": 8.944186046511628e-06,
|
| 1136 |
+
"loss": 2.7176,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.144076840981857,
|
| 1141 |
+
"grad_norm": 15.125,
|
| 1142 |
+
"learning_rate": 8.804651162790698e-06,
|
| 1143 |
+
"loss": 2.6748,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.14496620419779438,
|
| 1148 |
+
"grad_norm": 15.25,
|
| 1149 |
+
"learning_rate": 8.665116279069768e-06,
|
| 1150 |
+
"loss": 2.7349,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.14585556741373176,
|
| 1155 |
+
"grad_norm": 15.0625,
|
| 1156 |
+
"learning_rate": 8.525581395348838e-06,
|
| 1157 |
+
"loss": 2.729,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.14674493062966915,
|
| 1162 |
+
"grad_norm": 14.5625,
|
| 1163 |
+
"learning_rate": 8.386046511627907e-06,
|
| 1164 |
+
"loss": 2.6542,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.14763429384560656,
|
| 1169 |
+
"grad_norm": 14.625,
|
| 1170 |
+
"learning_rate": 8.246511627906977e-06,
|
| 1171 |
+
"loss": 2.6102,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.14852365706154394,
|
| 1176 |
+
"grad_norm": 13.8125,
|
| 1177 |
+
"learning_rate": 8.106976744186047e-06,
|
| 1178 |
+
"loss": 2.7355,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.14941302027748132,
|
| 1183 |
+
"grad_norm": 14.1875,
|
| 1184 |
+
"learning_rate": 7.967441860465118e-06,
|
| 1185 |
+
"loss": 2.7689,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.1503023834934187,
|
| 1190 |
+
"grad_norm": 14.3125,
|
| 1191 |
+
"learning_rate": 7.827906976744186e-06,
|
| 1192 |
+
"loss": 2.7373,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.1511917467093561,
|
| 1197 |
+
"grad_norm": 15.25,
|
| 1198 |
+
"learning_rate": 7.688372093023256e-06,
|
| 1199 |
+
"loss": 2.7359,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.1520811099252935,
|
| 1204 |
+
"grad_norm": 15.0,
|
| 1205 |
+
"learning_rate": 7.548837209302326e-06,
|
| 1206 |
+
"loss": 2.6088,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.15297047314123088,
|
| 1211 |
+
"grad_norm": 14.4375,
|
| 1212 |
+
"learning_rate": 7.409302325581395e-06,
|
| 1213 |
+
"loss": 2.7727,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.15385983635716827,
|
| 1218 |
+
"grad_norm": 13.1875,
|
| 1219 |
+
"learning_rate": 7.269767441860465e-06,
|
| 1220 |
+
"loss": 2.8457,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.15474919957310565,
|
| 1225 |
+
"grad_norm": 14.0625,
|
| 1226 |
+
"learning_rate": 7.130232558139535e-06,
|
| 1227 |
+
"loss": 2.6671,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.15563856278904303,
|
| 1232 |
+
"grad_norm": 14.0,
|
| 1233 |
+
"learning_rate": 6.990697674418605e-06,
|
| 1234 |
+
"loss": 2.593,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.15652792600498044,
|
| 1239 |
+
"grad_norm": 13.6875,
|
| 1240 |
+
"learning_rate": 6.851162790697674e-06,
|
| 1241 |
+
"loss": 2.6174,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.15741728922091783,
|
| 1246 |
+
"grad_norm": 14.375,
|
| 1247 |
+
"learning_rate": 6.711627906976745e-06,
|
| 1248 |
+
"loss": 2.6143,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.1583066524368552,
|
| 1253 |
+
"grad_norm": 12.875,
|
| 1254 |
+
"learning_rate": 6.572093023255814e-06,
|
| 1255 |
+
"loss": 2.7958,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.1591960156527926,
|
| 1260 |
+
"grad_norm": 13.875,
|
| 1261 |
+
"learning_rate": 6.432558139534884e-06,
|
| 1262 |
+
"loss": 2.6567,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.16008537886872998,
|
| 1267 |
+
"grad_norm": 14.625,
|
| 1268 |
+
"learning_rate": 6.293023255813954e-06,
|
| 1269 |
+
"loss": 2.5427,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.1609747420846674,
|
| 1274 |
+
"grad_norm": 14.1875,
|
| 1275 |
+
"learning_rate": 6.153488372093024e-06,
|
| 1276 |
+
"loss": 2.6013,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.16186410530060477,
|
| 1281 |
+
"grad_norm": 14.8125,
|
| 1282 |
+
"learning_rate": 6.013953488372093e-06,
|
| 1283 |
+
"loss": 2.6624,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.16275346851654215,
|
| 1288 |
+
"grad_norm": 14.625,
|
| 1289 |
+
"learning_rate": 5.8744186046511635e-06,
|
| 1290 |
+
"loss": 2.6861,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.16364283173247954,
|
| 1295 |
+
"grad_norm": 12.875,
|
| 1296 |
+
"learning_rate": 5.734883720930233e-06,
|
| 1297 |
+
"loss": 2.7337,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.16453219494841692,
|
| 1302 |
+
"grad_norm": 13.25,
|
| 1303 |
+
"learning_rate": 5.595348837209303e-06,
|
| 1304 |
+
"loss": 2.532,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.16542155816435433,
|
| 1309 |
+
"grad_norm": 14.0625,
|
| 1310 |
+
"learning_rate": 5.4558139534883726e-06,
|
| 1311 |
+
"loss": 2.5045,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.16631092138029172,
|
| 1316 |
+
"grad_norm": 14.5625,
|
| 1317 |
+
"learning_rate": 5.316279069767443e-06,
|
| 1318 |
+
"loss": 2.8413,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.1672002845962291,
|
| 1323 |
+
"grad_norm": 14.8125,
|
| 1324 |
+
"learning_rate": 5.176744186046511e-06,
|
| 1325 |
+
"loss": 2.6274,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.16808964781216648,
|
| 1330 |
+
"grad_norm": 13.5625,
|
| 1331 |
+
"learning_rate": 5.0372093023255816e-06,
|
| 1332 |
+
"loss": 2.5649,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.16897901102810386,
|
| 1337 |
+
"grad_norm": 15.0625,
|
| 1338 |
+
"learning_rate": 4.897674418604651e-06,
|
| 1339 |
+
"loss": 2.7143,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.16986837424404128,
|
| 1344 |
+
"grad_norm": 15.125,
|
| 1345 |
+
"learning_rate": 4.758139534883721e-06,
|
| 1346 |
+
"loss": 2.642,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.17075773745997866,
|
| 1351 |
+
"grad_norm": 12.875,
|
| 1352 |
+
"learning_rate": 4.618604651162791e-06,
|
| 1353 |
+
"loss": 2.8059,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.17164710067591604,
|
| 1358 |
+
"grad_norm": 13.8125,
|
| 1359 |
+
"learning_rate": 4.479069767441861e-06,
|
| 1360 |
+
"loss": 2.6971,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.17253646389185343,
|
| 1365 |
+
"grad_norm": 13.6875,
|
| 1366 |
+
"learning_rate": 4.33953488372093e-06,
|
| 1367 |
+
"loss": 2.6398,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.1734258271077908,
|
| 1372 |
+
"grad_norm": 16.375,
|
| 1373 |
+
"learning_rate": 4.2000000000000004e-06,
|
| 1374 |
+
"loss": 2.9306,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.17431519032372822,
|
| 1379 |
+
"grad_norm": 13.8125,
|
| 1380 |
+
"learning_rate": 4.06046511627907e-06,
|
| 1381 |
+
"loss": 2.7713,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.1752045535396656,
|
| 1386 |
+
"grad_norm": 13.125,
|
| 1387 |
+
"learning_rate": 3.92093023255814e-06,
|
| 1388 |
+
"loss": 2.7845,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.17609391675560299,
|
| 1393 |
+
"grad_norm": 13.5,
|
| 1394 |
+
"learning_rate": 3.7813953488372095e-06,
|
| 1395 |
+
"loss": 2.5285,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.17698327997154037,
|
| 1400 |
+
"grad_norm": 14.75,
|
| 1401 |
+
"learning_rate": 3.6418604651162793e-06,
|
| 1402 |
+
"loss": 2.7907,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.17787264318747775,
|
| 1407 |
+
"grad_norm": 14.25,
|
| 1408 |
+
"learning_rate": 3.502325581395349e-06,
|
| 1409 |
+
"loss": 2.6383,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
}
|
| 1412 |
+
],
|
| 1413 |
+
"logging_steps": 10,
|
| 1414 |
+
"max_steps": 2250,
|
| 1415 |
+
"num_input_tokens_seen": 0,
|
| 1416 |
+
"num_train_epochs": 1,
|
| 1417 |
+
"save_steps": 500,
|
| 1418 |
+
"stateful_callbacks": {
|
| 1419 |
+
"TrainerControl": {
|
| 1420 |
+
"args": {
|
| 1421 |
+
"should_epoch_stop": false,
|
| 1422 |
+
"should_evaluate": false,
|
| 1423 |
+
"should_log": false,
|
| 1424 |
+
"should_save": true,
|
| 1425 |
+
"should_training_stop": false
|
| 1426 |
+
},
|
| 1427 |
+
"attributes": {}
|
| 1428 |
+
}
|
| 1429 |
+
},
|
| 1430 |
+
"total_flos": 1.2177004224e+17,
|
| 1431 |
+
"train_batch_size": 1,
|
| 1432 |
+
"trial_name": null,
|
| 1433 |
+
"trial_params": null
|
| 1434 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:450bc4d6d613e8730f0693919843828e1024b9940c5cce15e9d1fda91da1eccb
|
| 3 |
+
size 5777
|
checkpoint-2250/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
checkpoint-2250/chat_template.jinja
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}
|
| 2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
| 3 |
+
{%- if messages[0]['content'] is string -%}
|
| 4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 5 |
+
|
| 6 |
+
' -%}
|
| 7 |
+
{%- else -%}
|
| 8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
| 9 |
+
|
| 10 |
+
' -%}
|
| 11 |
+
{%- endif -%}
|
| 12 |
+
{%- set loop_messages = messages[1:] -%}
|
| 13 |
+
{%- else -%}
|
| 14 |
+
{%- set first_user_prefix = "" -%}
|
| 15 |
+
{%- set loop_messages = messages -%}
|
| 16 |
+
{%- endif -%}
|
| 17 |
+
{%- for message in loop_messages -%}
|
| 18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 20 |
+
{%- endif -%}
|
| 21 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 22 |
+
{%- set role = "model" -%}
|
| 23 |
+
{%- else -%}
|
| 24 |
+
{%- set role = message['role'] -%}
|
| 25 |
+
{%- endif -%}
|
| 26 |
+
{{ '<start_of_turn>' + role + '
|
| 27 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 28 |
+
{%- if message['content'] is string -%}
|
| 29 |
+
{{ message['content'] | trim }}
|
| 30 |
+
{%- elif message['content'] is iterable -%}
|
| 31 |
+
{%- for item in message['content'] -%}
|
| 32 |
+
{%- if item['type'] == 'image' -%}
|
| 33 |
+
{{ '<start_of_image>' }}
|
| 34 |
+
{%- elif item['type'] == 'text' -%}
|
| 35 |
+
{{ item['text'] | trim }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
{%- else -%}
|
| 39 |
+
{{ raise_exception("Invalid content type") }}
|
| 40 |
+
{%- endif -%}
|
| 41 |
+
{{ '<end_of_turn>
|
| 42 |
+
' }}
|
| 43 |
+
{%- endfor -%}
|
| 44 |
+
{%- if add_generation_prompt -%}
|
| 45 |
+
{{'<start_of_turn>model
|
| 46 |
+
'}}
|
| 47 |
+
{%- endif -%}
|
checkpoint-2250/config.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"boi_token_index": 255999,
|
| 6 |
+
"eoi_token_index": 256000,
|
| 7 |
+
"eos_token_id": [
|
| 8 |
+
1,
|
| 9 |
+
106
|
| 10 |
+
],
|
| 11 |
+
"image_token_index": 262144,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"mm_tokens_per_image": 256,
|
| 14 |
+
"model_type": "gemma3",
|
| 15 |
+
"pad_token_id": 1,
|
| 16 |
+
"text_config": {
|
| 17 |
+
"_sliding_window_pattern": 6,
|
| 18 |
+
"attention_bias": false,
|
| 19 |
+
"attention_dropout": 0.0,
|
| 20 |
+
"attn_logit_softcapping": null,
|
| 21 |
+
"final_logit_softcapping": null,
|
| 22 |
+
"head_dim": 256,
|
| 23 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 24 |
+
"hidden_size": 2560,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 10240,
|
| 27 |
+
"layer_types": [
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"sliding_attention"
|
| 62 |
+
],
|
| 63 |
+
"max_position_embeddings": 131072,
|
| 64 |
+
"model_type": "gemma3_text",
|
| 65 |
+
"num_attention_heads": 8,
|
| 66 |
+
"num_hidden_layers": 34,
|
| 67 |
+
"num_key_value_heads": 4,
|
| 68 |
+
"query_pre_attn_scalar": 256,
|
| 69 |
+
"rms_norm_eps": 1e-06,
|
| 70 |
+
"rope_local_base_freq": 10000,
|
| 71 |
+
"rope_scaling": {
|
| 72 |
+
"factor": 8.0,
|
| 73 |
+
"rope_type": "linear"
|
| 74 |
+
},
|
| 75 |
+
"rope_theta": 1000000,
|
| 76 |
+
"sliding_window": 1024,
|
| 77 |
+
"torch_dtype": "bfloat16",
|
| 78 |
+
"use_cache": true,
|
| 79 |
+
"vocab_size": 262208
|
| 80 |
+
},
|
| 81 |
+
"torch_dtype": "bfloat16",
|
| 82 |
+
"transformers_version": "4.53.2",
|
| 83 |
+
"vision_config": {
|
| 84 |
+
"attention_dropout": 0.0,
|
| 85 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 86 |
+
"hidden_size": 1152,
|
| 87 |
+
"image_size": 896,
|
| 88 |
+
"intermediate_size": 4304,
|
| 89 |
+
"layer_norm_eps": 1e-06,
|
| 90 |
+
"model_type": "siglip_vision_model",
|
| 91 |
+
"num_attention_heads": 16,
|
| 92 |
+
"num_channels": 3,
|
| 93 |
+
"num_hidden_layers": 27,
|
| 94 |
+
"patch_size": 14,
|
| 95 |
+
"torch_dtype": "bfloat16",
|
| 96 |
+
"vision_use_head": false
|
| 97 |
+
}
|
| 98 |
+
}
|
checkpoint-2250/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
106
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"transformers_version": "4.53.2"
|
| 10 |
+
}
|
checkpoint-2250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b5c47e57782824788a2e1dbaace909f6380e8812f418c7ed71cb7fdbfb70006
|
| 3 |
+
size 15521442411
|
checkpoint-2250/pytorch_model-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f04b0705a4d6390d5c4b7bc82c8de9a7ba47d6e9e99faf7c0c978b0fd5cdcef0
|
| 3 |
+
size 4961400895
|
checkpoint-2250/pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a8da446a664b41a559669ccd60dd81c8d67cfd6b5be576038bf305ced4d5827
|
| 3 |
+
size 3639086660
|
checkpoint-2250/pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,892 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4300079472,
|
| 4 |
+
"total_size": 8600158944
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"language_model.lm_head.weight": "pytorch_model-00001-of-00002.bin",
|
| 8 |
+
"language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
| 9 |
+
"language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 10 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 11 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 12 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 13 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 14 |
+
"language_model.model.layers.0.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 15 |
+
"language_model.model.layers.0.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 16 |
+
"language_model.model.layers.0.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 17 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 18 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 19 |
+
"language_model.model.layers.0.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 20 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 21 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 22 |
+
"language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 23 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 24 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 25 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 26 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 27 |
+
"language_model.model.layers.1.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 28 |
+
"language_model.model.layers.1.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 29 |
+
"language_model.model.layers.1.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 30 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 31 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 32 |
+
"language_model.model.layers.1.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 33 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 34 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 35 |
+
"language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 36 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 37 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 38 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 39 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 40 |
+
"language_model.model.layers.10.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 41 |
+
"language_model.model.layers.10.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 42 |
+
"language_model.model.layers.10.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 43 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 44 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 45 |
+
"language_model.model.layers.10.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 46 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 47 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 48 |
+
"language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 49 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 50 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 51 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 52 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 53 |
+
"language_model.model.layers.11.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 54 |
+
"language_model.model.layers.11.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 55 |
+
"language_model.model.layers.11.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 56 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 57 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 58 |
+
"language_model.model.layers.11.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 59 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 60 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 61 |
+
"language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 62 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 63 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 64 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 65 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 66 |
+
"language_model.model.layers.12.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 67 |
+
"language_model.model.layers.12.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 68 |
+
"language_model.model.layers.12.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 69 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 70 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 71 |
+
"language_model.model.layers.12.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 72 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 73 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 74 |
+
"language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 75 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 76 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 77 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 78 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 79 |
+
"language_model.model.layers.13.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 80 |
+
"language_model.model.layers.13.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 81 |
+
"language_model.model.layers.13.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 82 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 83 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 84 |
+
"language_model.model.layers.13.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 85 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 86 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 87 |
+
"language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 88 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 89 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 90 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 91 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 92 |
+
"language_model.model.layers.14.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 93 |
+
"language_model.model.layers.14.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 94 |
+
"language_model.model.layers.14.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 95 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 96 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 97 |
+
"language_model.model.layers.14.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 98 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 99 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 100 |
+
"language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 101 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 102 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 103 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 104 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 105 |
+
"language_model.model.layers.15.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 106 |
+
"language_model.model.layers.15.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 107 |
+
"language_model.model.layers.15.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 108 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 109 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 110 |
+
"language_model.model.layers.15.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 111 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 112 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 113 |
+
"language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 114 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 115 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 116 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 117 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 118 |
+
"language_model.model.layers.16.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 119 |
+
"language_model.model.layers.16.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 120 |
+
"language_model.model.layers.16.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 121 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 122 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 123 |
+
"language_model.model.layers.16.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 124 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 125 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 126 |
+
"language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 127 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 128 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 129 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 130 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 131 |
+
"language_model.model.layers.17.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 132 |
+
"language_model.model.layers.17.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 133 |
+
"language_model.model.layers.17.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 134 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 135 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 136 |
+
"language_model.model.layers.17.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 137 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 138 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 139 |
+
"language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 140 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 141 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 142 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 143 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 144 |
+
"language_model.model.layers.18.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 145 |
+
"language_model.model.layers.18.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 146 |
+
"language_model.model.layers.18.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 147 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 148 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 149 |
+
"language_model.model.layers.18.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 150 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 151 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 152 |
+
"language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 153 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 154 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 155 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 156 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 157 |
+
"language_model.model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 158 |
+
"language_model.model.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 159 |
+
"language_model.model.layers.19.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 160 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 161 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 162 |
+
"language_model.model.layers.19.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 163 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 164 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 165 |
+
"language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 166 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 167 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 168 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 169 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 170 |
+
"language_model.model.layers.2.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 171 |
+
"language_model.model.layers.2.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 172 |
+
"language_model.model.layers.2.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 173 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 174 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 175 |
+
"language_model.model.layers.2.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 176 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 177 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 178 |
+
"language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 179 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 180 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 181 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 182 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 183 |
+
"language_model.model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 184 |
+
"language_model.model.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 185 |
+
"language_model.model.layers.20.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 186 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 187 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 188 |
+
"language_model.model.layers.20.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 189 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 190 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 191 |
+
"language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 192 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 193 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 194 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 195 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 196 |
+
"language_model.model.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 197 |
+
"language_model.model.layers.21.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 198 |
+
"language_model.model.layers.21.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 199 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 200 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 201 |
+
"language_model.model.layers.21.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 202 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 203 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 204 |
+
"language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 205 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 206 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 207 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 208 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 209 |
+
"language_model.model.layers.22.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 210 |
+
"language_model.model.layers.22.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 211 |
+
"language_model.model.layers.22.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 212 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 213 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 214 |
+
"language_model.model.layers.22.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 215 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 216 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 217 |
+
"language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 218 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 219 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 220 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 221 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 222 |
+
"language_model.model.layers.23.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 223 |
+
"language_model.model.layers.23.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 224 |
+
"language_model.model.layers.23.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 225 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 226 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 227 |
+
"language_model.model.layers.23.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 228 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 229 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 230 |
+
"language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 231 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 232 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 233 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 234 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 235 |
+
"language_model.model.layers.24.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 236 |
+
"language_model.model.layers.24.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 237 |
+
"language_model.model.layers.24.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 238 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 239 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 240 |
+
"language_model.model.layers.24.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 241 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 242 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 243 |
+
"language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 244 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 245 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 246 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 247 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 248 |
+
"language_model.model.layers.25.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 249 |
+
"language_model.model.layers.25.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 250 |
+
"language_model.model.layers.25.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 251 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 252 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 253 |
+
"language_model.model.layers.25.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 254 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 255 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 256 |
+
"language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 257 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 258 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 259 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 260 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 261 |
+
"language_model.model.layers.26.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 262 |
+
"language_model.model.layers.26.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 263 |
+
"language_model.model.layers.26.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 264 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 265 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 266 |
+
"language_model.model.layers.26.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 267 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 268 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 269 |
+
"language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 270 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 271 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 272 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 273 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 274 |
+
"language_model.model.layers.27.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 275 |
+
"language_model.model.layers.27.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 276 |
+
"language_model.model.layers.27.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 277 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 278 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 279 |
+
"language_model.model.layers.27.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 280 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 281 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 282 |
+
"language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 283 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 284 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 285 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 286 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 287 |
+
"language_model.model.layers.28.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 288 |
+
"language_model.model.layers.28.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 289 |
+
"language_model.model.layers.28.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 290 |
+
"language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 291 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 292 |
+
"language_model.model.layers.28.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 293 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 294 |
+
"language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 295 |
+
"language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 296 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 297 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 298 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 299 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 300 |
+
"language_model.model.layers.29.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 301 |
+
"language_model.model.layers.29.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 302 |
+
"language_model.model.layers.29.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 303 |
+
"language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 304 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 305 |
+
"language_model.model.layers.29.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 306 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 307 |
+
"language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 308 |
+
"language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 309 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 310 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 311 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 312 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 313 |
+
"language_model.model.layers.3.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 314 |
+
"language_model.model.layers.3.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 315 |
+
"language_model.model.layers.3.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 316 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 317 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 318 |
+
"language_model.model.layers.3.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 319 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 320 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 321 |
+
"language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 322 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 323 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 324 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 325 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 326 |
+
"language_model.model.layers.30.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 327 |
+
"language_model.model.layers.30.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 328 |
+
"language_model.model.layers.30.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 329 |
+
"language_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 330 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 331 |
+
"language_model.model.layers.30.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 332 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 333 |
+
"language_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 334 |
+
"language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 335 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 336 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 337 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 338 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 339 |
+
"language_model.model.layers.31.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 340 |
+
"language_model.model.layers.31.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 341 |
+
"language_model.model.layers.31.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 342 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 343 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 344 |
+
"language_model.model.layers.31.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 345 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 346 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 347 |
+
"language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 348 |
+
"language_model.model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 349 |
+
"language_model.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 350 |
+
"language_model.model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 351 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 352 |
+
"language_model.model.layers.32.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 353 |
+
"language_model.model.layers.32.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 354 |
+
"language_model.model.layers.32.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 355 |
+
"language_model.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 356 |
+
"language_model.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 357 |
+
"language_model.model.layers.32.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 358 |
+
"language_model.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 359 |
+
"language_model.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 360 |
+
"language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 361 |
+
"language_model.model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 362 |
+
"language_model.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 363 |
+
"language_model.model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 364 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 365 |
+
"language_model.model.layers.33.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 366 |
+
"language_model.model.layers.33.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 367 |
+
"language_model.model.layers.33.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 368 |
+
"language_model.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 369 |
+
"language_model.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 370 |
+
"language_model.model.layers.33.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 371 |
+
"language_model.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 372 |
+
"language_model.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 373 |
+
"language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 374 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 375 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 376 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 377 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 378 |
+
"language_model.model.layers.4.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 379 |
+
"language_model.model.layers.4.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 380 |
+
"language_model.model.layers.4.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 381 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 382 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 383 |
+
"language_model.model.layers.4.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 384 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 385 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 386 |
+
"language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 387 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 388 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 389 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 390 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 391 |
+
"language_model.model.layers.5.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 392 |
+
"language_model.model.layers.5.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 393 |
+
"language_model.model.layers.5.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 394 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 395 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 396 |
+
"language_model.model.layers.5.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 397 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 398 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 399 |
+
"language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 400 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 401 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 402 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 403 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 404 |
+
"language_model.model.layers.6.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 405 |
+
"language_model.model.layers.6.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 406 |
+
"language_model.model.layers.6.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 407 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 408 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 409 |
+
"language_model.model.layers.6.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 410 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 411 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 412 |
+
"language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 413 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 414 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 415 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 416 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 417 |
+
"language_model.model.layers.7.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 418 |
+
"language_model.model.layers.7.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 419 |
+
"language_model.model.layers.7.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 420 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 421 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 422 |
+
"language_model.model.layers.7.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 423 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 424 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 425 |
+
"language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 426 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 427 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 428 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 429 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 430 |
+
"language_model.model.layers.8.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 431 |
+
"language_model.model.layers.8.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 432 |
+
"language_model.model.layers.8.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 433 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 434 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 435 |
+
"language_model.model.layers.8.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 436 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 437 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 438 |
+
"language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 439 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 440 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 441 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 442 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 443 |
+
"language_model.model.layers.9.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 444 |
+
"language_model.model.layers.9.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 445 |
+
"language_model.model.layers.9.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 446 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 447 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 448 |
+
"language_model.model.layers.9.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 449 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 450 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 451 |
+
"language_model.model.norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 452 |
+
"multi_modal_projector.mm_input_projection_weight": "pytorch_model-00001-of-00002.bin",
|
| 453 |
+
"multi_modal_projector.mm_soft_emb_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 454 |
+
"vision_tower.vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00002.bin",
|
| 455 |
+
"vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
|
| 456 |
+
"vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
|
| 457 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 458 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 459 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 460 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 461 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 462 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 463 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 464 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 465 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 466 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 467 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 468 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 469 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 470 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 471 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 472 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 473 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 474 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 475 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 476 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 477 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 478 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 479 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 480 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 481 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 482 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 483 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 484 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 485 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 486 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 487 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 488 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 489 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 490 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 491 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 492 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 493 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 494 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 495 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 496 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 497 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 498 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 499 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 500 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 501 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 502 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 503 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 504 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 505 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 506 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 507 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 508 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 509 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 510 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 511 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 512 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 513 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 514 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 515 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 516 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 517 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 518 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 519 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 520 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 521 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 522 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 523 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 524 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 525 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 526 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 527 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 528 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 529 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 530 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 531 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 532 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 533 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 534 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 535 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 536 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 537 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 538 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 539 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 540 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 541 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 542 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 543 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 544 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 545 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 546 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 547 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 548 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 549 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 550 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 551 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 552 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 553 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 554 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 555 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 556 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 557 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 558 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 559 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 560 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 561 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 562 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 563 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 564 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 565 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 566 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 567 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 568 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 569 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 570 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 571 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 572 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 573 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 574 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 575 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 576 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 577 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 578 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 579 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 580 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 581 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 582 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 583 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 584 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 585 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 586 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 587 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 588 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 589 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 590 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 591 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 592 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 593 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 594 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 595 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 596 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 597 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 598 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 599 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 600 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 601 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 602 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 603 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 604 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 605 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 606 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 607 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 608 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 609 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 610 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 611 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 612 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 613 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 614 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 615 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 616 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 617 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 618 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 619 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 620 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 621 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 622 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 623 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 624 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 625 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 626 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 627 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 628 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 629 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 630 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 631 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 632 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 633 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 634 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 635 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 636 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 637 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 638 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 639 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 640 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 641 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 642 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 643 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 644 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 645 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 646 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 647 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 648 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 649 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 650 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 651 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 652 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 653 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 654 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 655 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 656 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 657 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 658 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 659 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 660 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 661 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 662 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 663 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 664 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 665 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 666 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 667 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 668 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 669 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 670 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 671 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 672 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 673 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 674 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 675 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 676 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 677 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 678 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 679 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 680 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 681 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 682 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 683 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 684 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 685 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 686 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 687 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 688 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 689 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 690 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 691 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 692 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 693 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 694 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 695 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 696 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 697 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 698 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 699 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 700 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 701 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 702 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 703 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 704 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 705 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 706 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 707 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 708 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 709 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 710 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 711 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 712 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 713 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 714 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 715 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 716 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 717 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 718 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 719 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 720 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 721 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 722 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 723 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 724 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 725 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 726 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 727 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 728 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 729 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 730 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 731 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 732 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 733 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 734 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 735 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 736 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 737 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 738 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 739 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 740 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 741 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 742 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 743 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 744 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 745 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 746 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 747 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 748 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 749 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 750 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 751 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 752 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 753 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 754 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 755 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 756 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 757 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 758 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 759 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 760 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 761 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 762 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 763 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 764 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 765 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 766 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 767 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 768 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 769 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 770 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 771 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 772 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 773 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 774 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 775 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 776 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 777 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 778 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 779 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 780 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 781 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 782 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 783 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 784 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 785 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 786 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 787 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 788 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 789 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 790 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 791 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 792 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 793 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 794 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 795 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 796 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 797 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 798 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 799 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 800 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 801 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 802 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 803 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 804 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 805 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 806 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 807 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 808 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 809 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 810 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 811 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 812 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 813 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 814 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 815 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 816 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 817 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 818 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 819 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 820 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 821 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 822 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 823 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 824 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 825 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 826 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 827 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 828 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 829 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 830 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 831 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 832 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 833 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 834 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 835 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 836 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 837 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 838 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 839 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 840 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 841 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 842 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 843 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 844 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 845 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 846 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 847 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 848 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 849 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 850 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 851 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 852 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 853 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 854 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 855 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 856 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 857 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 858 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 859 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 860 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 861 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 862 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 863 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 864 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 865 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 866 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 867 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 868 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 869 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 870 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 871 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 872 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 873 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 874 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 875 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 876 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 877 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 878 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 879 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 880 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 881 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 882 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 883 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 884 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 885 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 886 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 887 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 888 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 889 |
+
"vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 890 |
+
"vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin"
|
| 891 |
+
}
|
| 892 |
+
}
|
checkpoint-2250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
|
| 3 |
+
size 14645
|
checkpoint-2250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8107951557eb1893d79401878cdac4d8aaa41acbc5a2794d774682f60c267db
|
| 3 |
+
size 1465
|
checkpoint-2250/special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"eoi_token": "<end_of_image>",
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"content": "<eos>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"image_token": "<image_soft_token>",
|
| 19 |
+
"pad_token": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
checkpoint-2250/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c96fd7401f729829eb0636c0285020112e74ace07bedf404c4c2461911b20287
|
| 3 |
+
size 33384821
|
checkpoint-2250/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
checkpoint-2250/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2250/trainer_state.json
ADDED
|
@@ -0,0 +1,1609 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2001067235859125,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2250,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0008893632159373888,
|
| 14 |
+
"grad_norm": 68.5,
|
| 15 |
+
"learning_rate": 2.7e-06,
|
| 16 |
+
"loss": 8.8776,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0017787264318747777,
|
| 21 |
+
"grad_norm": 39.0,
|
| 22 |
+
"learning_rate": 5.7000000000000005e-06,
|
| 23 |
+
"loss": 7.711,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0026680896478121665,
|
| 28 |
+
"grad_norm": 29.375,
|
| 29 |
+
"learning_rate": 8.7e-06,
|
| 30 |
+
"loss": 5.7038,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0035574528637495554,
|
| 35 |
+
"grad_norm": 24.5,
|
| 36 |
+
"learning_rate": 1.1700000000000001e-05,
|
| 37 |
+
"loss": 4.746,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.004446816079686944,
|
| 42 |
+
"grad_norm": 22.625,
|
| 43 |
+
"learning_rate": 1.47e-05,
|
| 44 |
+
"loss": 4.1094,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.005336179295624333,
|
| 49 |
+
"grad_norm": 21.625,
|
| 50 |
+
"learning_rate": 1.77e-05,
|
| 51 |
+
"loss": 4.0746,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0062255425115617215,
|
| 56 |
+
"grad_norm": 25.25,
|
| 57 |
+
"learning_rate": 2.07e-05,
|
| 58 |
+
"loss": 3.8396,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.007114905727499111,
|
| 63 |
+
"grad_norm": 20.875,
|
| 64 |
+
"learning_rate": 2.37e-05,
|
| 65 |
+
"loss": 3.8629,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0080042689434365,
|
| 70 |
+
"grad_norm": 22.875,
|
| 71 |
+
"learning_rate": 2.6700000000000002e-05,
|
| 72 |
+
"loss": 3.9097,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.008893632159373888,
|
| 77 |
+
"grad_norm": 19.375,
|
| 78 |
+
"learning_rate": 2.97e-05,
|
| 79 |
+
"loss": 3.763,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.009782995375311278,
|
| 84 |
+
"grad_norm": 19.625,
|
| 85 |
+
"learning_rate": 2.9874418604651165e-05,
|
| 86 |
+
"loss": 4.1501,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.010672358591248666,
|
| 91 |
+
"grad_norm": 19.0,
|
| 92 |
+
"learning_rate": 2.9734883720930235e-05,
|
| 93 |
+
"loss": 3.9038,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.011561721807186055,
|
| 98 |
+
"grad_norm": 16.625,
|
| 99 |
+
"learning_rate": 2.9595348837209305e-05,
|
| 100 |
+
"loss": 4.0583,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.012451085023123443,
|
| 105 |
+
"grad_norm": 16.375,
|
| 106 |
+
"learning_rate": 2.9455813953488376e-05,
|
| 107 |
+
"loss": 3.5958,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.013340448239060833,
|
| 112 |
+
"grad_norm": 15.375,
|
| 113 |
+
"learning_rate": 2.9316279069767443e-05,
|
| 114 |
+
"loss": 3.9075,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.014229811454998222,
|
| 119 |
+
"grad_norm": 15.625,
|
| 120 |
+
"learning_rate": 2.9176744186046513e-05,
|
| 121 |
+
"loss": 3.9495,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.01511917467093561,
|
| 126 |
+
"grad_norm": 18.125,
|
| 127 |
+
"learning_rate": 2.9037209302325583e-05,
|
| 128 |
+
"loss": 3.3247,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.016008537886873,
|
| 133 |
+
"grad_norm": 18.75,
|
| 134 |
+
"learning_rate": 2.889767441860465e-05,
|
| 135 |
+
"loss": 3.6863,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.01689790110281039,
|
| 140 |
+
"grad_norm": 15.625,
|
| 141 |
+
"learning_rate": 2.875813953488372e-05,
|
| 142 |
+
"loss": 3.3097,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.017787264318747775,
|
| 147 |
+
"grad_norm": 14.3125,
|
| 148 |
+
"learning_rate": 2.861860465116279e-05,
|
| 149 |
+
"loss": 3.48,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.018676627534685165,
|
| 154 |
+
"grad_norm": 17.875,
|
| 155 |
+
"learning_rate": 2.847906976744186e-05,
|
| 156 |
+
"loss": 3.6216,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.019565990750622556,
|
| 161 |
+
"grad_norm": 15.4375,
|
| 162 |
+
"learning_rate": 2.833953488372093e-05,
|
| 163 |
+
"loss": 3.4751,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.020455353966559942,
|
| 168 |
+
"grad_norm": 14.75,
|
| 169 |
+
"learning_rate": 2.8199999999999998e-05,
|
| 170 |
+
"loss": 3.9,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.021344717182497332,
|
| 175 |
+
"grad_norm": 14.8125,
|
| 176 |
+
"learning_rate": 2.8060465116279068e-05,
|
| 177 |
+
"loss": 3.7454,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.02223408039843472,
|
| 182 |
+
"grad_norm": 15.6875,
|
| 183 |
+
"learning_rate": 2.7920930232558138e-05,
|
| 184 |
+
"loss": 3.5053,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.02312344361437211,
|
| 189 |
+
"grad_norm": 14.5,
|
| 190 |
+
"learning_rate": 2.778139534883721e-05,
|
| 191 |
+
"loss": 3.3656,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.0240128068303095,
|
| 196 |
+
"grad_norm": 13.6875,
|
| 197 |
+
"learning_rate": 2.764186046511628e-05,
|
| 198 |
+
"loss": 3.769,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.024902170046246886,
|
| 203 |
+
"grad_norm": 15.0625,
|
| 204 |
+
"learning_rate": 2.750232558139535e-05,
|
| 205 |
+
"loss": 3.5721,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.025791533262184276,
|
| 210 |
+
"grad_norm": 14.6875,
|
| 211 |
+
"learning_rate": 2.736279069767442e-05,
|
| 212 |
+
"loss": 3.6104,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.026680896478121666,
|
| 217 |
+
"grad_norm": 13.875,
|
| 218 |
+
"learning_rate": 2.722325581395349e-05,
|
| 219 |
+
"loss": 3.5904,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.027570259694059053,
|
| 224 |
+
"grad_norm": 13.8125,
|
| 225 |
+
"learning_rate": 2.7083720930232556e-05,
|
| 226 |
+
"loss": 3.5633,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.028459622909996443,
|
| 231 |
+
"grad_norm": 13.5625,
|
| 232 |
+
"learning_rate": 2.6944186046511626e-05,
|
| 233 |
+
"loss": 3.3366,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.02934898612593383,
|
| 238 |
+
"grad_norm": 14.3125,
|
| 239 |
+
"learning_rate": 2.6804651162790697e-05,
|
| 240 |
+
"loss": 3.6519,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.03023834934187122,
|
| 245 |
+
"grad_norm": 14.4375,
|
| 246 |
+
"learning_rate": 2.6665116279069767e-05,
|
| 247 |
+
"loss": 3.4482,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.03112771255780861,
|
| 252 |
+
"grad_norm": 13.9375,
|
| 253 |
+
"learning_rate": 2.6525581395348837e-05,
|
| 254 |
+
"loss": 3.3554,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.032017075773746,
|
| 259 |
+
"grad_norm": 14.5625,
|
| 260 |
+
"learning_rate": 2.6386046511627907e-05,
|
| 261 |
+
"loss": 3.4008,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.03290643898968339,
|
| 266 |
+
"grad_norm": 14.375,
|
| 267 |
+
"learning_rate": 2.6246511627906978e-05,
|
| 268 |
+
"loss": 3.3279,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.03379580220562078,
|
| 273 |
+
"grad_norm": 13.9375,
|
| 274 |
+
"learning_rate": 2.6106976744186048e-05,
|
| 275 |
+
"loss": 3.487,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.03468516542155817,
|
| 280 |
+
"grad_norm": 14.625,
|
| 281 |
+
"learning_rate": 2.5967441860465115e-05,
|
| 282 |
+
"loss": 3.2542,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.03557452863749555,
|
| 287 |
+
"grad_norm": 13.1875,
|
| 288 |
+
"learning_rate": 2.5827906976744185e-05,
|
| 289 |
+
"loss": 3.3328,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.03646389185343294,
|
| 294 |
+
"grad_norm": 13.25,
|
| 295 |
+
"learning_rate": 2.5688372093023255e-05,
|
| 296 |
+
"loss": 3.5205,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.03735325506937033,
|
| 301 |
+
"grad_norm": 11.9375,
|
| 302 |
+
"learning_rate": 2.5548837209302325e-05,
|
| 303 |
+
"loss": 3.4151,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.03824261828530772,
|
| 308 |
+
"grad_norm": 13.625,
|
| 309 |
+
"learning_rate": 2.5409302325581396e-05,
|
| 310 |
+
"loss": 3.1404,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.03913198150124511,
|
| 315 |
+
"grad_norm": 14.0625,
|
| 316 |
+
"learning_rate": 2.5269767441860466e-05,
|
| 317 |
+
"loss": 3.5277,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.040021344717182494,
|
| 322 |
+
"grad_norm": 13.1875,
|
| 323 |
+
"learning_rate": 2.5130232558139536e-05,
|
| 324 |
+
"loss": 3.1584,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.040910707933119884,
|
| 329 |
+
"grad_norm": 13.4375,
|
| 330 |
+
"learning_rate": 2.4990697674418606e-05,
|
| 331 |
+
"loss": 3.4669,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.041800071149057275,
|
| 336 |
+
"grad_norm": 14.5625,
|
| 337 |
+
"learning_rate": 2.4851162790697673e-05,
|
| 338 |
+
"loss": 3.2653,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.042689434364994665,
|
| 343 |
+
"grad_norm": 13.9375,
|
| 344 |
+
"learning_rate": 2.4711627906976743e-05,
|
| 345 |
+
"loss": 3.4219,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.043578797580932055,
|
| 350 |
+
"grad_norm": 12.875,
|
| 351 |
+
"learning_rate": 2.4572093023255814e-05,
|
| 352 |
+
"loss": 3.508,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.04446816079686944,
|
| 357 |
+
"grad_norm": 14.0625,
|
| 358 |
+
"learning_rate": 2.4432558139534884e-05,
|
| 359 |
+
"loss": 3.3343,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.04535752401280683,
|
| 364 |
+
"grad_norm": 13.75,
|
| 365 |
+
"learning_rate": 2.4293023255813954e-05,
|
| 366 |
+
"loss": 3.5054,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.04624688722874422,
|
| 371 |
+
"grad_norm": 15.25,
|
| 372 |
+
"learning_rate": 2.4153488372093024e-05,
|
| 373 |
+
"loss": 3.0298,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.04713625044468161,
|
| 378 |
+
"grad_norm": 13.75,
|
| 379 |
+
"learning_rate": 2.4013953488372095e-05,
|
| 380 |
+
"loss": 3.4306,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.048025613660619,
|
| 385 |
+
"grad_norm": 14.25,
|
| 386 |
+
"learning_rate": 2.3874418604651165e-05,
|
| 387 |
+
"loss": 3.1824,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.04891497687655639,
|
| 392 |
+
"grad_norm": 12.3125,
|
| 393 |
+
"learning_rate": 2.373488372093023e-05,
|
| 394 |
+
"loss": 3.211,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.04980434009249377,
|
| 399 |
+
"grad_norm": 13.75,
|
| 400 |
+
"learning_rate": 2.3595348837209302e-05,
|
| 401 |
+
"loss": 3.091,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.05069370330843116,
|
| 406 |
+
"grad_norm": 13.75,
|
| 407 |
+
"learning_rate": 2.3455813953488372e-05,
|
| 408 |
+
"loss": 3.234,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.05158306652436855,
|
| 413 |
+
"grad_norm": 13.75,
|
| 414 |
+
"learning_rate": 2.3316279069767442e-05,
|
| 415 |
+
"loss": 3.1404,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.05247242974030594,
|
| 420 |
+
"grad_norm": 13.25,
|
| 421 |
+
"learning_rate": 2.3176744186046513e-05,
|
| 422 |
+
"loss": 3.2191,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.05336179295624333,
|
| 427 |
+
"grad_norm": 12.625,
|
| 428 |
+
"learning_rate": 2.3037209302325583e-05,
|
| 429 |
+
"loss": 3.0968,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.054251156172180716,
|
| 434 |
+
"grad_norm": 13.5625,
|
| 435 |
+
"learning_rate": 2.2897674418604653e-05,
|
| 436 |
+
"loss": 3.1108,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.055140519388118106,
|
| 441 |
+
"grad_norm": 12.75,
|
| 442 |
+
"learning_rate": 2.2758139534883723e-05,
|
| 443 |
+
"loss": 3.028,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.056029882604055496,
|
| 448 |
+
"grad_norm": 12.375,
|
| 449 |
+
"learning_rate": 2.261860465116279e-05,
|
| 450 |
+
"loss": 3.1469,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.056919245819992886,
|
| 455 |
+
"grad_norm": 14.8125,
|
| 456 |
+
"learning_rate": 2.247906976744186e-05,
|
| 457 |
+
"loss": 3.1258,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.057808609035930276,
|
| 462 |
+
"grad_norm": 12.5625,
|
| 463 |
+
"learning_rate": 2.233953488372093e-05,
|
| 464 |
+
"loss": 3.1147,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.05869797225186766,
|
| 469 |
+
"grad_norm": 13.1875,
|
| 470 |
+
"learning_rate": 2.22e-05,
|
| 471 |
+
"loss": 3.0447,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.05958733546780505,
|
| 476 |
+
"grad_norm": 15.3125,
|
| 477 |
+
"learning_rate": 2.206046511627907e-05,
|
| 478 |
+
"loss": 3.1177,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.06047669868374244,
|
| 483 |
+
"grad_norm": 13.6875,
|
| 484 |
+
"learning_rate": 2.192093023255814e-05,
|
| 485 |
+
"loss": 3.2542,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.06136606189967983,
|
| 490 |
+
"grad_norm": 13.1875,
|
| 491 |
+
"learning_rate": 2.178139534883721e-05,
|
| 492 |
+
"loss": 3.188,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.06225542511561722,
|
| 497 |
+
"grad_norm": 13.625,
|
| 498 |
+
"learning_rate": 2.1641860465116282e-05,
|
| 499 |
+
"loss": 3.2298,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.06314478833155461,
|
| 504 |
+
"grad_norm": 14.0625,
|
| 505 |
+
"learning_rate": 2.150232558139535e-05,
|
| 506 |
+
"loss": 3.1127,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.064034151547492,
|
| 511 |
+
"grad_norm": 15.1875,
|
| 512 |
+
"learning_rate": 2.136279069767442e-05,
|
| 513 |
+
"loss": 3.1468,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.06492351476342939,
|
| 518 |
+
"grad_norm": 12.625,
|
| 519 |
+
"learning_rate": 2.122325581395349e-05,
|
| 520 |
+
"loss": 3.2763,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.06581287797936677,
|
| 525 |
+
"grad_norm": 13.875,
|
| 526 |
+
"learning_rate": 2.108372093023256e-05,
|
| 527 |
+
"loss": 3.051,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.06670224119530416,
|
| 532 |
+
"grad_norm": 13.9375,
|
| 533 |
+
"learning_rate": 2.094418604651163e-05,
|
| 534 |
+
"loss": 3.1937,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.06759160441124155,
|
| 539 |
+
"grad_norm": 13.3125,
|
| 540 |
+
"learning_rate": 2.08046511627907e-05,
|
| 541 |
+
"loss": 3.0506,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.06848096762717894,
|
| 546 |
+
"grad_norm": 12.625,
|
| 547 |
+
"learning_rate": 2.066511627906977e-05,
|
| 548 |
+
"loss": 2.975,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.06937033084311633,
|
| 553 |
+
"grad_norm": 12.75,
|
| 554 |
+
"learning_rate": 2.052558139534884e-05,
|
| 555 |
+
"loss": 2.9174,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.07025969405905372,
|
| 560 |
+
"grad_norm": 12.875,
|
| 561 |
+
"learning_rate": 2.0386046511627907e-05,
|
| 562 |
+
"loss": 3.0532,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.0711490572749911,
|
| 567 |
+
"grad_norm": 12.4375,
|
| 568 |
+
"learning_rate": 2.0246511627906977e-05,
|
| 569 |
+
"loss": 3.2092,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.0720384204909285,
|
| 574 |
+
"grad_norm": 12.625,
|
| 575 |
+
"learning_rate": 2.0106976744186048e-05,
|
| 576 |
+
"loss": 2.9702,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.07292778370686588,
|
| 581 |
+
"grad_norm": 14.0625,
|
| 582 |
+
"learning_rate": 1.9967441860465118e-05,
|
| 583 |
+
"loss": 3.0595,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.07381714692280328,
|
| 588 |
+
"grad_norm": 14.5,
|
| 589 |
+
"learning_rate": 1.9827906976744188e-05,
|
| 590 |
+
"loss": 3.0102,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.07470651013874066,
|
| 595 |
+
"grad_norm": 13.25,
|
| 596 |
+
"learning_rate": 1.968837209302326e-05,
|
| 597 |
+
"loss": 3.0725,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.07559587335467804,
|
| 602 |
+
"grad_norm": 13.6875,
|
| 603 |
+
"learning_rate": 1.954883720930233e-05,
|
| 604 |
+
"loss": 3.0679,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.07648523657061544,
|
| 609 |
+
"grad_norm": 13.1875,
|
| 610 |
+
"learning_rate": 1.94093023255814e-05,
|
| 611 |
+
"loss": 3.0764,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.07737459978655283,
|
| 616 |
+
"grad_norm": 14.5,
|
| 617 |
+
"learning_rate": 1.9269767441860466e-05,
|
| 618 |
+
"loss": 2.768,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.07826396300249022,
|
| 623 |
+
"grad_norm": 14.875,
|
| 624 |
+
"learning_rate": 1.9130232558139536e-05,
|
| 625 |
+
"loss": 3.2016,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.0791533262184276,
|
| 630 |
+
"grad_norm": 12.875,
|
| 631 |
+
"learning_rate": 1.8990697674418606e-05,
|
| 632 |
+
"loss": 3.0906,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.08004268943436499,
|
| 637 |
+
"grad_norm": 13.0,
|
| 638 |
+
"learning_rate": 1.8851162790697673e-05,
|
| 639 |
+
"loss": 3.1441,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.08093205265030239,
|
| 644 |
+
"grad_norm": 13.25,
|
| 645 |
+
"learning_rate": 1.8711627906976743e-05,
|
| 646 |
+
"loss": 2.9791,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.08182141586623977,
|
| 651 |
+
"grad_norm": 14.0625,
|
| 652 |
+
"learning_rate": 1.8572093023255814e-05,
|
| 653 |
+
"loss": 2.8393,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.08271077908217717,
|
| 658 |
+
"grad_norm": 13.1875,
|
| 659 |
+
"learning_rate": 1.8432558139534884e-05,
|
| 660 |
+
"loss": 2.9332,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.08360014229811455,
|
| 665 |
+
"grad_norm": 13.0625,
|
| 666 |
+
"learning_rate": 1.8293023255813954e-05,
|
| 667 |
+
"loss": 2.9787,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.08448950551405193,
|
| 672 |
+
"grad_norm": 15.375,
|
| 673 |
+
"learning_rate": 1.815348837209302e-05,
|
| 674 |
+
"loss": 2.8229,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.08537886872998933,
|
| 679 |
+
"grad_norm": 13.5625,
|
| 680 |
+
"learning_rate": 1.801395348837209e-05,
|
| 681 |
+
"loss": 2.8112,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.08626823194592671,
|
| 686 |
+
"grad_norm": 16.75,
|
| 687 |
+
"learning_rate": 1.787441860465116e-05,
|
| 688 |
+
"loss": 3.0131,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.08715759516186411,
|
| 693 |
+
"grad_norm": 13.9375,
|
| 694 |
+
"learning_rate": 1.773488372093023e-05,
|
| 695 |
+
"loss": 2.9496,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.08804695837780149,
|
| 700 |
+
"grad_norm": 15.0625,
|
| 701 |
+
"learning_rate": 1.7595348837209302e-05,
|
| 702 |
+
"loss": 3.0641,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.08893632159373888,
|
| 707 |
+
"grad_norm": 13.0,
|
| 708 |
+
"learning_rate": 1.7455813953488372e-05,
|
| 709 |
+
"loss": 2.8714,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.08982568480967627,
|
| 714 |
+
"grad_norm": 13.8125,
|
| 715 |
+
"learning_rate": 1.7316279069767442e-05,
|
| 716 |
+
"loss": 2.7792,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.09071504802561366,
|
| 721 |
+
"grad_norm": 13.875,
|
| 722 |
+
"learning_rate": 1.7176744186046512e-05,
|
| 723 |
+
"loss": 2.9472,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.09160441124155105,
|
| 728 |
+
"grad_norm": 14.0,
|
| 729 |
+
"learning_rate": 1.703720930232558e-05,
|
| 730 |
+
"loss": 2.5662,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.09249377445748844,
|
| 735 |
+
"grad_norm": 13.9375,
|
| 736 |
+
"learning_rate": 1.689767441860465e-05,
|
| 737 |
+
"loss": 2.82,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.09338313767342583,
|
| 742 |
+
"grad_norm": 13.875,
|
| 743 |
+
"learning_rate": 1.675813953488372e-05,
|
| 744 |
+
"loss": 2.8245,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.09427250088936322,
|
| 749 |
+
"grad_norm": 11.8125,
|
| 750 |
+
"learning_rate": 1.661860465116279e-05,
|
| 751 |
+
"loss": 2.8141,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.0951618641053006,
|
| 756 |
+
"grad_norm": 13.1875,
|
| 757 |
+
"learning_rate": 1.647906976744186e-05,
|
| 758 |
+
"loss": 2.8975,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.096051227321238,
|
| 763 |
+
"grad_norm": 14.625,
|
| 764 |
+
"learning_rate": 1.633953488372093e-05,
|
| 765 |
+
"loss": 2.7996,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.09694059053717538,
|
| 770 |
+
"grad_norm": 12.625,
|
| 771 |
+
"learning_rate": 1.62e-05,
|
| 772 |
+
"loss": 2.7679,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.09782995375311278,
|
| 777 |
+
"grad_norm": 14.0625,
|
| 778 |
+
"learning_rate": 1.606046511627907e-05,
|
| 779 |
+
"loss": 3.0057,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.09871931696905016,
|
| 784 |
+
"grad_norm": 13.6875,
|
| 785 |
+
"learning_rate": 1.5920930232558138e-05,
|
| 786 |
+
"loss": 2.5742,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.09960868018498754,
|
| 791 |
+
"grad_norm": 15.3125,
|
| 792 |
+
"learning_rate": 1.5781395348837208e-05,
|
| 793 |
+
"loss": 2.7903,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.10049804340092494,
|
| 798 |
+
"grad_norm": 14.8125,
|
| 799 |
+
"learning_rate": 1.564186046511628e-05,
|
| 800 |
+
"loss": 2.5664,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.10138740661686232,
|
| 805 |
+
"grad_norm": 13.8125,
|
| 806 |
+
"learning_rate": 1.550232558139535e-05,
|
| 807 |
+
"loss": 2.9392,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.10227676983279972,
|
| 812 |
+
"grad_norm": 13.9375,
|
| 813 |
+
"learning_rate": 1.536279069767442e-05,
|
| 814 |
+
"loss": 2.7105,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.1031661330487371,
|
| 819 |
+
"grad_norm": 14.5,
|
| 820 |
+
"learning_rate": 1.5223255813953489e-05,
|
| 821 |
+
"loss": 2.9472,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.10405549626467449,
|
| 826 |
+
"grad_norm": 13.4375,
|
| 827 |
+
"learning_rate": 1.508372093023256e-05,
|
| 828 |
+
"loss": 2.7698,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.10494485948061189,
|
| 833 |
+
"grad_norm": 13.125,
|
| 834 |
+
"learning_rate": 1.4944186046511628e-05,
|
| 835 |
+
"loss": 2.8998,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.10583422269654927,
|
| 840 |
+
"grad_norm": 14.125,
|
| 841 |
+
"learning_rate": 1.4804651162790698e-05,
|
| 842 |
+
"loss": 2.7952,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.10672358591248667,
|
| 847 |
+
"grad_norm": 14.875,
|
| 848 |
+
"learning_rate": 1.4665116279069768e-05,
|
| 849 |
+
"loss": 2.7689,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.10761294912842405,
|
| 854 |
+
"grad_norm": 13.375,
|
| 855 |
+
"learning_rate": 1.4525581395348837e-05,
|
| 856 |
+
"loss": 3.0368,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.10850231234436143,
|
| 861 |
+
"grad_norm": 14.5,
|
| 862 |
+
"learning_rate": 1.4386046511627907e-05,
|
| 863 |
+
"loss": 2.8113,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.10939167556029883,
|
| 868 |
+
"grad_norm": 13.25,
|
| 869 |
+
"learning_rate": 1.4246511627906977e-05,
|
| 870 |
+
"loss": 2.5883,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.11028103877623621,
|
| 875 |
+
"grad_norm": 14.25,
|
| 876 |
+
"learning_rate": 1.4106976744186048e-05,
|
| 877 |
+
"loss": 2.9207,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.11117040199217361,
|
| 882 |
+
"grad_norm": 12.9375,
|
| 883 |
+
"learning_rate": 1.3967441860465116e-05,
|
| 884 |
+
"loss": 2.8662,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.11205976520811099,
|
| 889 |
+
"grad_norm": 14.25,
|
| 890 |
+
"learning_rate": 1.3827906976744186e-05,
|
| 891 |
+
"loss": 2.8439,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.11294912842404838,
|
| 896 |
+
"grad_norm": 13.1875,
|
| 897 |
+
"learning_rate": 1.3688372093023257e-05,
|
| 898 |
+
"loss": 2.8322,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.11383849163998577,
|
| 903 |
+
"grad_norm": 13.6875,
|
| 904 |
+
"learning_rate": 1.3548837209302327e-05,
|
| 905 |
+
"loss": 2.8627,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.11472785485592316,
|
| 910 |
+
"grad_norm": 12.8125,
|
| 911 |
+
"learning_rate": 1.3409302325581395e-05,
|
| 912 |
+
"loss": 2.733,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.11561721807186055,
|
| 917 |
+
"grad_norm": 12.75,
|
| 918 |
+
"learning_rate": 1.3269767441860466e-05,
|
| 919 |
+
"loss": 2.7608,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.11650658128779794,
|
| 924 |
+
"grad_norm": 14.4375,
|
| 925 |
+
"learning_rate": 1.3130232558139536e-05,
|
| 926 |
+
"loss": 2.7633,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.11739594450373532,
|
| 931 |
+
"grad_norm": 13.875,
|
| 932 |
+
"learning_rate": 1.2990697674418606e-05,
|
| 933 |
+
"loss": 2.682,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.11828530771967272,
|
| 938 |
+
"grad_norm": 14.4375,
|
| 939 |
+
"learning_rate": 1.2851162790697675e-05,
|
| 940 |
+
"loss": 2.7205,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.1191746709356101,
|
| 945 |
+
"grad_norm": 12.6875,
|
| 946 |
+
"learning_rate": 1.2711627906976745e-05,
|
| 947 |
+
"loss": 2.7408,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.1200640341515475,
|
| 952 |
+
"grad_norm": 13.5,
|
| 953 |
+
"learning_rate": 1.2572093023255815e-05,
|
| 954 |
+
"loss": 3.0955,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.12095339736748488,
|
| 959 |
+
"grad_norm": 13.8125,
|
| 960 |
+
"learning_rate": 1.2432558139534885e-05,
|
| 961 |
+
"loss": 2.8928,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.12184276058342226,
|
| 966 |
+
"grad_norm": 12.5625,
|
| 967 |
+
"learning_rate": 1.2293023255813954e-05,
|
| 968 |
+
"loss": 2.7429,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.12273212379935966,
|
| 973 |
+
"grad_norm": 14.3125,
|
| 974 |
+
"learning_rate": 1.2153488372093024e-05,
|
| 975 |
+
"loss": 2.6795,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.12362148701529704,
|
| 980 |
+
"grad_norm": 13.125,
|
| 981 |
+
"learning_rate": 1.2013953488372094e-05,
|
| 982 |
+
"loss": 2.6802,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.12451085023123444,
|
| 987 |
+
"grad_norm": 13.8125,
|
| 988 |
+
"learning_rate": 1.1874418604651165e-05,
|
| 989 |
+
"loss": 2.6818,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.12540021344717184,
|
| 994 |
+
"grad_norm": 13.875,
|
| 995 |
+
"learning_rate": 1.1734883720930233e-05,
|
| 996 |
+
"loss": 2.5968,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.12628957666310922,
|
| 1001 |
+
"grad_norm": 13.75,
|
| 1002 |
+
"learning_rate": 1.1595348837209303e-05,
|
| 1003 |
+
"loss": 2.7026,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.1271789398790466,
|
| 1008 |
+
"grad_norm": 13.5625,
|
| 1009 |
+
"learning_rate": 1.1455813953488372e-05,
|
| 1010 |
+
"loss": 2.8092,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.128068303094984,
|
| 1015 |
+
"grad_norm": 13.9375,
|
| 1016 |
+
"learning_rate": 1.1316279069767442e-05,
|
| 1017 |
+
"loss": 2.6957,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.12895766631092137,
|
| 1022 |
+
"grad_norm": 14.0,
|
| 1023 |
+
"learning_rate": 1.117674418604651e-05,
|
| 1024 |
+
"loss": 2.8901,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.12984702952685878,
|
| 1029 |
+
"grad_norm": 14.3125,
|
| 1030 |
+
"learning_rate": 1.1037209302325581e-05,
|
| 1031 |
+
"loss": 2.6284,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.13073639274279616,
|
| 1036 |
+
"grad_norm": 13.875,
|
| 1037 |
+
"learning_rate": 1.0897674418604651e-05,
|
| 1038 |
+
"loss": 2.9493,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.13162575595873355,
|
| 1043 |
+
"grad_norm": 13.5625,
|
| 1044 |
+
"learning_rate": 1.0758139534883721e-05,
|
| 1045 |
+
"loss": 2.6665,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.13251511917467093,
|
| 1050 |
+
"grad_norm": 14.125,
|
| 1051 |
+
"learning_rate": 1.061860465116279e-05,
|
| 1052 |
+
"loss": 2.8124,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.13340448239060831,
|
| 1057 |
+
"grad_norm": 13.8125,
|
| 1058 |
+
"learning_rate": 1.047906976744186e-05,
|
| 1059 |
+
"loss": 2.8094,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.13429384560654573,
|
| 1064 |
+
"grad_norm": 14.3125,
|
| 1065 |
+
"learning_rate": 1.033953488372093e-05,
|
| 1066 |
+
"loss": 2.6246,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.1351832088224831,
|
| 1071 |
+
"grad_norm": 14.5625,
|
| 1072 |
+
"learning_rate": 1.02e-05,
|
| 1073 |
+
"loss": 2.8486,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.1360725720384205,
|
| 1078 |
+
"grad_norm": 13.625,
|
| 1079 |
+
"learning_rate": 1.0060465116279069e-05,
|
| 1080 |
+
"loss": 2.7712,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.13696193525435787,
|
| 1085 |
+
"grad_norm": 14.5625,
|
| 1086 |
+
"learning_rate": 9.92093023255814e-06,
|
| 1087 |
+
"loss": 2.7667,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.13785129847029526,
|
| 1092 |
+
"grad_norm": 14.375,
|
| 1093 |
+
"learning_rate": 9.78139534883721e-06,
|
| 1094 |
+
"loss": 2.6918,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.13874066168623267,
|
| 1099 |
+
"grad_norm": 14.1875,
|
| 1100 |
+
"learning_rate": 9.64186046511628e-06,
|
| 1101 |
+
"loss": 2.872,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.13963002490217005,
|
| 1106 |
+
"grad_norm": 14.375,
|
| 1107 |
+
"learning_rate": 9.502325581395348e-06,
|
| 1108 |
+
"loss": 2.9586,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.14051938811810744,
|
| 1113 |
+
"grad_norm": 13.8125,
|
| 1114 |
+
"learning_rate": 9.362790697674419e-06,
|
| 1115 |
+
"loss": 2.5803,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.14140875133404482,
|
| 1120 |
+
"grad_norm": 13.8125,
|
| 1121 |
+
"learning_rate": 9.223255813953489e-06,
|
| 1122 |
+
"loss": 2.72,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.1422981145499822,
|
| 1127 |
+
"grad_norm": 13.4375,
|
| 1128 |
+
"learning_rate": 9.083720930232559e-06,
|
| 1129 |
+
"loss": 2.7268,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.1431874777659196,
|
| 1134 |
+
"grad_norm": 14.0625,
|
| 1135 |
+
"learning_rate": 8.944186046511628e-06,
|
| 1136 |
+
"loss": 2.7176,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.144076840981857,
|
| 1141 |
+
"grad_norm": 15.125,
|
| 1142 |
+
"learning_rate": 8.804651162790698e-06,
|
| 1143 |
+
"loss": 2.6748,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.14496620419779438,
|
| 1148 |
+
"grad_norm": 15.25,
|
| 1149 |
+
"learning_rate": 8.665116279069768e-06,
|
| 1150 |
+
"loss": 2.7349,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.14585556741373176,
|
| 1155 |
+
"grad_norm": 15.0625,
|
| 1156 |
+
"learning_rate": 8.525581395348838e-06,
|
| 1157 |
+
"loss": 2.729,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.14674493062966915,
|
| 1162 |
+
"grad_norm": 14.5625,
|
| 1163 |
+
"learning_rate": 8.386046511627907e-06,
|
| 1164 |
+
"loss": 2.6542,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.14763429384560656,
|
| 1169 |
+
"grad_norm": 14.625,
|
| 1170 |
+
"learning_rate": 8.246511627906977e-06,
|
| 1171 |
+
"loss": 2.6102,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.14852365706154394,
|
| 1176 |
+
"grad_norm": 13.8125,
|
| 1177 |
+
"learning_rate": 8.106976744186047e-06,
|
| 1178 |
+
"loss": 2.7355,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.14941302027748132,
|
| 1183 |
+
"grad_norm": 14.1875,
|
| 1184 |
+
"learning_rate": 7.967441860465118e-06,
|
| 1185 |
+
"loss": 2.7689,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.1503023834934187,
|
| 1190 |
+
"grad_norm": 14.3125,
|
| 1191 |
+
"learning_rate": 7.827906976744186e-06,
|
| 1192 |
+
"loss": 2.7373,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.1511917467093561,
|
| 1197 |
+
"grad_norm": 15.25,
|
| 1198 |
+
"learning_rate": 7.688372093023256e-06,
|
| 1199 |
+
"loss": 2.7359,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.1520811099252935,
|
| 1204 |
+
"grad_norm": 15.0,
|
| 1205 |
+
"learning_rate": 7.548837209302326e-06,
|
| 1206 |
+
"loss": 2.6088,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.15297047314123088,
|
| 1211 |
+
"grad_norm": 14.4375,
|
| 1212 |
+
"learning_rate": 7.409302325581395e-06,
|
| 1213 |
+
"loss": 2.7727,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.15385983635716827,
|
| 1218 |
+
"grad_norm": 13.1875,
|
| 1219 |
+
"learning_rate": 7.269767441860465e-06,
|
| 1220 |
+
"loss": 2.8457,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.15474919957310565,
|
| 1225 |
+
"grad_norm": 14.0625,
|
| 1226 |
+
"learning_rate": 7.130232558139535e-06,
|
| 1227 |
+
"loss": 2.6671,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.15563856278904303,
|
| 1232 |
+
"grad_norm": 14.0,
|
| 1233 |
+
"learning_rate": 6.990697674418605e-06,
|
| 1234 |
+
"loss": 2.593,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.15652792600498044,
|
| 1239 |
+
"grad_norm": 13.6875,
|
| 1240 |
+
"learning_rate": 6.851162790697674e-06,
|
| 1241 |
+
"loss": 2.6174,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.15741728922091783,
|
| 1246 |
+
"grad_norm": 14.375,
|
| 1247 |
+
"learning_rate": 6.711627906976745e-06,
|
| 1248 |
+
"loss": 2.6143,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.1583066524368552,
|
| 1253 |
+
"grad_norm": 12.875,
|
| 1254 |
+
"learning_rate": 6.572093023255814e-06,
|
| 1255 |
+
"loss": 2.7958,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.1591960156527926,
|
| 1260 |
+
"grad_norm": 13.875,
|
| 1261 |
+
"learning_rate": 6.432558139534884e-06,
|
| 1262 |
+
"loss": 2.6567,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.16008537886872998,
|
| 1267 |
+
"grad_norm": 14.625,
|
| 1268 |
+
"learning_rate": 6.293023255813954e-06,
|
| 1269 |
+
"loss": 2.5427,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.1609747420846674,
|
| 1274 |
+
"grad_norm": 14.1875,
|
| 1275 |
+
"learning_rate": 6.153488372093024e-06,
|
| 1276 |
+
"loss": 2.6013,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.16186410530060477,
|
| 1281 |
+
"grad_norm": 14.8125,
|
| 1282 |
+
"learning_rate": 6.013953488372093e-06,
|
| 1283 |
+
"loss": 2.6624,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.16275346851654215,
|
| 1288 |
+
"grad_norm": 14.625,
|
| 1289 |
+
"learning_rate": 5.8744186046511635e-06,
|
| 1290 |
+
"loss": 2.6861,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.16364283173247954,
|
| 1295 |
+
"grad_norm": 12.875,
|
| 1296 |
+
"learning_rate": 5.734883720930233e-06,
|
| 1297 |
+
"loss": 2.7337,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.16453219494841692,
|
| 1302 |
+
"grad_norm": 13.25,
|
| 1303 |
+
"learning_rate": 5.595348837209303e-06,
|
| 1304 |
+
"loss": 2.532,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.16542155816435433,
|
| 1309 |
+
"grad_norm": 14.0625,
|
| 1310 |
+
"learning_rate": 5.4558139534883726e-06,
|
| 1311 |
+
"loss": 2.5045,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.16631092138029172,
|
| 1316 |
+
"grad_norm": 14.5625,
|
| 1317 |
+
"learning_rate": 5.316279069767443e-06,
|
| 1318 |
+
"loss": 2.8413,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.1672002845962291,
|
| 1323 |
+
"grad_norm": 14.8125,
|
| 1324 |
+
"learning_rate": 5.176744186046511e-06,
|
| 1325 |
+
"loss": 2.6274,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.16808964781216648,
|
| 1330 |
+
"grad_norm": 13.5625,
|
| 1331 |
+
"learning_rate": 5.0372093023255816e-06,
|
| 1332 |
+
"loss": 2.5649,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.16897901102810386,
|
| 1337 |
+
"grad_norm": 15.0625,
|
| 1338 |
+
"learning_rate": 4.897674418604651e-06,
|
| 1339 |
+
"loss": 2.7143,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.16986837424404128,
|
| 1344 |
+
"grad_norm": 15.125,
|
| 1345 |
+
"learning_rate": 4.758139534883721e-06,
|
| 1346 |
+
"loss": 2.642,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.17075773745997866,
|
| 1351 |
+
"grad_norm": 12.875,
|
| 1352 |
+
"learning_rate": 4.618604651162791e-06,
|
| 1353 |
+
"loss": 2.8059,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.17164710067591604,
|
| 1358 |
+
"grad_norm": 13.8125,
|
| 1359 |
+
"learning_rate": 4.479069767441861e-06,
|
| 1360 |
+
"loss": 2.6971,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.17253646389185343,
|
| 1365 |
+
"grad_norm": 13.6875,
|
| 1366 |
+
"learning_rate": 4.33953488372093e-06,
|
| 1367 |
+
"loss": 2.6398,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.1734258271077908,
|
| 1372 |
+
"grad_norm": 16.375,
|
| 1373 |
+
"learning_rate": 4.2000000000000004e-06,
|
| 1374 |
+
"loss": 2.9306,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.17431519032372822,
|
| 1379 |
+
"grad_norm": 13.8125,
|
| 1380 |
+
"learning_rate": 4.06046511627907e-06,
|
| 1381 |
+
"loss": 2.7713,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.1752045535396656,
|
| 1386 |
+
"grad_norm": 13.125,
|
| 1387 |
+
"learning_rate": 3.92093023255814e-06,
|
| 1388 |
+
"loss": 2.7845,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.17609391675560299,
|
| 1393 |
+
"grad_norm": 13.5,
|
| 1394 |
+
"learning_rate": 3.7813953488372095e-06,
|
| 1395 |
+
"loss": 2.5285,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.17698327997154037,
|
| 1400 |
+
"grad_norm": 14.75,
|
| 1401 |
+
"learning_rate": 3.6418604651162793e-06,
|
| 1402 |
+
"loss": 2.7907,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.17787264318747775,
|
| 1407 |
+
"grad_norm": 14.25,
|
| 1408 |
+
"learning_rate": 3.502325581395349e-06,
|
| 1409 |
+
"loss": 2.6383,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.17876200640341516,
|
| 1414 |
+
"grad_norm": 13.4375,
|
| 1415 |
+
"learning_rate": 3.3627906976744185e-06,
|
| 1416 |
+
"loss": 2.62,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.17965136961935255,
|
| 1421 |
+
"grad_norm": 16.0,
|
| 1422 |
+
"learning_rate": 3.2232558139534883e-06,
|
| 1423 |
+
"loss": 2.6536,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.18054073283528993,
|
| 1428 |
+
"grad_norm": 13.3125,
|
| 1429 |
+
"learning_rate": 3.083720930232558e-06,
|
| 1430 |
+
"loss": 2.6178,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.1814300960512273,
|
| 1435 |
+
"grad_norm": 15.0,
|
| 1436 |
+
"learning_rate": 2.944186046511628e-06,
|
| 1437 |
+
"loss": 2.7065,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.1823194592671647,
|
| 1442 |
+
"grad_norm": 12.375,
|
| 1443 |
+
"learning_rate": 2.8046511627906977e-06,
|
| 1444 |
+
"loss": 2.6898,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.1832088224831021,
|
| 1449 |
+
"grad_norm": 14.0625,
|
| 1450 |
+
"learning_rate": 2.6651162790697675e-06,
|
| 1451 |
+
"loss": 2.5896,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.1840981856990395,
|
| 1456 |
+
"grad_norm": 15.4375,
|
| 1457 |
+
"learning_rate": 2.5255813953488374e-06,
|
| 1458 |
+
"loss": 2.6833,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.18498754891497687,
|
| 1463 |
+
"grad_norm": 15.5,
|
| 1464 |
+
"learning_rate": 2.386046511627907e-06,
|
| 1465 |
+
"loss": 2.7408,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.18587691213091426,
|
| 1470 |
+
"grad_norm": 13.375,
|
| 1471 |
+
"learning_rate": 2.246511627906977e-06,
|
| 1472 |
+
"loss": 2.7091,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.18676627534685167,
|
| 1477 |
+
"grad_norm": 14.1875,
|
| 1478 |
+
"learning_rate": 2.1069767441860464e-06,
|
| 1479 |
+
"loss": 2.4644,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.18765563856278905,
|
| 1484 |
+
"grad_norm": 14.625,
|
| 1485 |
+
"learning_rate": 1.967441860465116e-06,
|
| 1486 |
+
"loss": 2.7544,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.18854500177872643,
|
| 1491 |
+
"grad_norm": 14.625,
|
| 1492 |
+
"learning_rate": 1.8279069767441862e-06,
|
| 1493 |
+
"loss": 2.7613,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.18943436499466382,
|
| 1498 |
+
"grad_norm": 14.0625,
|
| 1499 |
+
"learning_rate": 1.6883720930232558e-06,
|
| 1500 |
+
"loss": 2.5281,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.1903237282106012,
|
| 1505 |
+
"grad_norm": 14.1875,
|
| 1506 |
+
"learning_rate": 1.5488372093023256e-06,
|
| 1507 |
+
"loss": 2.56,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.1912130914265386,
|
| 1512 |
+
"grad_norm": 14.0,
|
| 1513 |
+
"learning_rate": 1.4093023255813954e-06,
|
| 1514 |
+
"loss": 2.6563,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.192102454642476,
|
| 1519 |
+
"grad_norm": 14.0,
|
| 1520 |
+
"learning_rate": 1.2697674418604653e-06,
|
| 1521 |
+
"loss": 2.6377,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.19299181785841338,
|
| 1526 |
+
"grad_norm": 14.4375,
|
| 1527 |
+
"learning_rate": 1.1302325581395349e-06,
|
| 1528 |
+
"loss": 2.694,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.19388118107435076,
|
| 1533 |
+
"grad_norm": 14.5,
|
| 1534 |
+
"learning_rate": 9.906976744186047e-07,
|
| 1535 |
+
"loss": 2.6686,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.19477054429028814,
|
| 1540 |
+
"grad_norm": 14.0625,
|
| 1541 |
+
"learning_rate": 8.511627906976745e-07,
|
| 1542 |
+
"loss": 2.7232,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.19565990750622556,
|
| 1547 |
+
"grad_norm": 14.5625,
|
| 1548 |
+
"learning_rate": 7.116279069767442e-07,
|
| 1549 |
+
"loss": 2.7544,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.19654927072216294,
|
| 1554 |
+
"grad_norm": 13.5,
|
| 1555 |
+
"learning_rate": 5.72093023255814e-07,
|
| 1556 |
+
"loss": 2.6411,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.19743863393810032,
|
| 1561 |
+
"grad_norm": 13.1875,
|
| 1562 |
+
"learning_rate": 4.325581395348837e-07,
|
| 1563 |
+
"loss": 2.5296,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.1983279971540377,
|
| 1568 |
+
"grad_norm": 15.25,
|
| 1569 |
+
"learning_rate": 2.9302325581395347e-07,
|
| 1570 |
+
"loss": 2.5208,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.1992173603699751,
|
| 1575 |
+
"grad_norm": 13.125,
|
| 1576 |
+
"learning_rate": 1.5348837209302325e-07,
|
| 1577 |
+
"loss": 2.6465,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.2001067235859125,
|
| 1582 |
+
"grad_norm": 14.75,
|
| 1583 |
+
"learning_rate": 1.3953488372093025e-08,
|
| 1584 |
+
"loss": 2.7407,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
}
|
| 1587 |
+
],
|
| 1588 |
+
"logging_steps": 10,
|
| 1589 |
+
"max_steps": 2250,
|
| 1590 |
+
"num_input_tokens_seen": 0,
|
| 1591 |
+
"num_train_epochs": 1,
|
| 1592 |
+
"save_steps": 500,
|
| 1593 |
+
"stateful_callbacks": {
|
| 1594 |
+
"TrainerControl": {
|
| 1595 |
+
"args": {
|
| 1596 |
+
"should_epoch_stop": false,
|
| 1597 |
+
"should_evaluate": false,
|
| 1598 |
+
"should_log": false,
|
| 1599 |
+
"should_save": true,
|
| 1600 |
+
"should_training_stop": true
|
| 1601 |
+
},
|
| 1602 |
+
"attributes": {}
|
| 1603 |
+
}
|
| 1604 |
+
},
|
| 1605 |
+
"total_flos": 1.3699129752e+17,
|
| 1606 |
+
"train_batch_size": 1,
|
| 1607 |
+
"trial_name": null,
|
| 1608 |
+
"trial_params": null
|
| 1609 |
+
}
|
checkpoint-2250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:450bc4d6d613e8730f0693919843828e1024b9940c5cce15e9d1fda91da1eccb
|
| 3 |
+
size 5777
|
config.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"boi_token_index": 255999,
|
| 6 |
+
"eoi_token_index": 256000,
|
| 7 |
+
"eos_token_id": [
|
| 8 |
+
1,
|
| 9 |
+
106
|
| 10 |
+
],
|
| 11 |
+
"image_token_index": 262144,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"mm_tokens_per_image": 256,
|
| 14 |
+
"model_type": "gemma3",
|
| 15 |
+
"pad_token_id": 1,
|
| 16 |
+
"text_config": {
|
| 17 |
+
"_sliding_window_pattern": 6,
|
| 18 |
+
"attention_bias": false,
|
| 19 |
+
"attention_dropout": 0.0,
|
| 20 |
+
"attn_logit_softcapping": null,
|
| 21 |
+
"final_logit_softcapping": null,
|
| 22 |
+
"head_dim": 256,
|
| 23 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 24 |
+
"hidden_size": 2560,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 10240,
|
| 27 |
+
"layer_types": [
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"sliding_attention"
|
| 62 |
+
],
|
| 63 |
+
"max_position_embeddings": 131072,
|
| 64 |
+
"model_type": "gemma3_text",
|
| 65 |
+
"num_attention_heads": 8,
|
| 66 |
+
"num_hidden_layers": 34,
|
| 67 |
+
"num_key_value_heads": 4,
|
| 68 |
+
"query_pre_attn_scalar": 256,
|
| 69 |
+
"rms_norm_eps": 1e-06,
|
| 70 |
+
"rope_local_base_freq": 10000,
|
| 71 |
+
"rope_scaling": {
|
| 72 |
+
"factor": 8.0,
|
| 73 |
+
"rope_type": "linear"
|
| 74 |
+
},
|
| 75 |
+
"rope_theta": 1000000,
|
| 76 |
+
"sliding_window": 1024,
|
| 77 |
+
"torch_dtype": "bfloat16",
|
| 78 |
+
"use_cache": true,
|
| 79 |
+
"vocab_size": 262208
|
| 80 |
+
},
|
| 81 |
+
"torch_dtype": "bfloat16",
|
| 82 |
+
"transformers_version": "4.53.2",
|
| 83 |
+
"vision_config": {
|
| 84 |
+
"attention_dropout": 0.0,
|
| 85 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 86 |
+
"hidden_size": 1152,
|
| 87 |
+
"image_size": 896,
|
| 88 |
+
"intermediate_size": 4304,
|
| 89 |
+
"layer_norm_eps": 1e-06,
|
| 90 |
+
"model_type": "siglip_vision_model",
|
| 91 |
+
"num_attention_heads": 16,
|
| 92 |
+
"num_channels": 3,
|
| 93 |
+
"num_hidden_layers": 27,
|
| 94 |
+
"patch_size": 14,
|
| 95 |
+
"torch_dtype": "bfloat16",
|
| 96 |
+
"vision_use_head": false
|
| 97 |
+
}
|
| 98 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
106
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"transformers_version": "4.53.2"
|
| 10 |
+
}
|
pytorch_model-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f04b0705a4d6390d5c4b7bc82c8de9a7ba47d6e9e99faf7c0c978b0fd5cdcef0
|
| 3 |
+
size 4961400895
|
pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a8da446a664b41a559669ccd60dd81c8d67cfd6b5be576038bf305ced4d5827
|
| 3 |
+
size 3639086660
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,892 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4300079472,
|
| 4 |
+
"total_size": 8600158944
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"language_model.lm_head.weight": "pytorch_model-00001-of-00002.bin",
|
| 8 |
+
"language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
| 9 |
+
"language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 10 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 11 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 12 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 13 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 14 |
+
"language_model.model.layers.0.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 15 |
+
"language_model.model.layers.0.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 16 |
+
"language_model.model.layers.0.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 17 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 18 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 19 |
+
"language_model.model.layers.0.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 20 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 21 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 22 |
+
"language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 23 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 24 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 25 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 26 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 27 |
+
"language_model.model.layers.1.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 28 |
+
"language_model.model.layers.1.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 29 |
+
"language_model.model.layers.1.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 30 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 31 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 32 |
+
"language_model.model.layers.1.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 33 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 34 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 35 |
+
"language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 36 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 37 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 38 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 39 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 40 |
+
"language_model.model.layers.10.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 41 |
+
"language_model.model.layers.10.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 42 |
+
"language_model.model.layers.10.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 43 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 44 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 45 |
+
"language_model.model.layers.10.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 46 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 47 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 48 |
+
"language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 49 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 50 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 51 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 52 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 53 |
+
"language_model.model.layers.11.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 54 |
+
"language_model.model.layers.11.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 55 |
+
"language_model.model.layers.11.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 56 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 57 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 58 |
+
"language_model.model.layers.11.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 59 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 60 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 61 |
+
"language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 62 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 63 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 64 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 65 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 66 |
+
"language_model.model.layers.12.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 67 |
+
"language_model.model.layers.12.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 68 |
+
"language_model.model.layers.12.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 69 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 70 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 71 |
+
"language_model.model.layers.12.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 72 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 73 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 74 |
+
"language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 75 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 76 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 77 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 78 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 79 |
+
"language_model.model.layers.13.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 80 |
+
"language_model.model.layers.13.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 81 |
+
"language_model.model.layers.13.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 82 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 83 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 84 |
+
"language_model.model.layers.13.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 85 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 86 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 87 |
+
"language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 88 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 89 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 90 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 91 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 92 |
+
"language_model.model.layers.14.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 93 |
+
"language_model.model.layers.14.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 94 |
+
"language_model.model.layers.14.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 95 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 96 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 97 |
+
"language_model.model.layers.14.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 98 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 99 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 100 |
+
"language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 101 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 102 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 103 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 104 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 105 |
+
"language_model.model.layers.15.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 106 |
+
"language_model.model.layers.15.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 107 |
+
"language_model.model.layers.15.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 108 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 109 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 110 |
+
"language_model.model.layers.15.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 111 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 112 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 113 |
+
"language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 114 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 115 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 116 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 117 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 118 |
+
"language_model.model.layers.16.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 119 |
+
"language_model.model.layers.16.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 120 |
+
"language_model.model.layers.16.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 121 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 122 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 123 |
+
"language_model.model.layers.16.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 124 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 125 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 126 |
+
"language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 127 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 128 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 129 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 130 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 131 |
+
"language_model.model.layers.17.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 132 |
+
"language_model.model.layers.17.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 133 |
+
"language_model.model.layers.17.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 134 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 135 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 136 |
+
"language_model.model.layers.17.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 137 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 138 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 139 |
+
"language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 140 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 141 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 142 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 143 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 144 |
+
"language_model.model.layers.18.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 145 |
+
"language_model.model.layers.18.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 146 |
+
"language_model.model.layers.18.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 147 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 148 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 149 |
+
"language_model.model.layers.18.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 150 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 151 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 152 |
+
"language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 153 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 154 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 155 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 156 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 157 |
+
"language_model.model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 158 |
+
"language_model.model.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 159 |
+
"language_model.model.layers.19.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 160 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 161 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 162 |
+
"language_model.model.layers.19.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 163 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 164 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 165 |
+
"language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 166 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 167 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 168 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 169 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 170 |
+
"language_model.model.layers.2.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 171 |
+
"language_model.model.layers.2.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 172 |
+
"language_model.model.layers.2.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 173 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 174 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 175 |
+
"language_model.model.layers.2.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 176 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 177 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 178 |
+
"language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 179 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 180 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 181 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 182 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 183 |
+
"language_model.model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 184 |
+
"language_model.model.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 185 |
+
"language_model.model.layers.20.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 186 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 187 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 188 |
+
"language_model.model.layers.20.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 189 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 190 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 191 |
+
"language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 192 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 193 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 194 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 195 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 196 |
+
"language_model.model.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 197 |
+
"language_model.model.layers.21.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 198 |
+
"language_model.model.layers.21.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 199 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 200 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 201 |
+
"language_model.model.layers.21.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 202 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 203 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 204 |
+
"language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 205 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 206 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 207 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 208 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 209 |
+
"language_model.model.layers.22.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 210 |
+
"language_model.model.layers.22.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 211 |
+
"language_model.model.layers.22.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 212 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 213 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 214 |
+
"language_model.model.layers.22.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 215 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 216 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 217 |
+
"language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 218 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 219 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 220 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 221 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 222 |
+
"language_model.model.layers.23.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 223 |
+
"language_model.model.layers.23.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 224 |
+
"language_model.model.layers.23.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 225 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 226 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 227 |
+
"language_model.model.layers.23.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 228 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 229 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 230 |
+
"language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 231 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 232 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 233 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 234 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 235 |
+
"language_model.model.layers.24.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 236 |
+
"language_model.model.layers.24.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 237 |
+
"language_model.model.layers.24.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 238 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 239 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 240 |
+
"language_model.model.layers.24.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 241 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 242 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 243 |
+
"language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 244 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 245 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 246 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 247 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 248 |
+
"language_model.model.layers.25.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 249 |
+
"language_model.model.layers.25.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 250 |
+
"language_model.model.layers.25.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 251 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 252 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 253 |
+
"language_model.model.layers.25.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 254 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 255 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 256 |
+
"language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 257 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 258 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 259 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 260 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 261 |
+
"language_model.model.layers.26.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 262 |
+
"language_model.model.layers.26.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 263 |
+
"language_model.model.layers.26.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 264 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 265 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 266 |
+
"language_model.model.layers.26.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 267 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 268 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 269 |
+
"language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 270 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 271 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 272 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 273 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 274 |
+
"language_model.model.layers.27.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 275 |
+
"language_model.model.layers.27.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 276 |
+
"language_model.model.layers.27.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 277 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 278 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 279 |
+
"language_model.model.layers.27.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 280 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 281 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 282 |
+
"language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 283 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 284 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 285 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 286 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 287 |
+
"language_model.model.layers.28.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 288 |
+
"language_model.model.layers.28.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 289 |
+
"language_model.model.layers.28.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 290 |
+
"language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 291 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 292 |
+
"language_model.model.layers.28.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 293 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 294 |
+
"language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 295 |
+
"language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 296 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 297 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 298 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 299 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 300 |
+
"language_model.model.layers.29.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 301 |
+
"language_model.model.layers.29.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 302 |
+
"language_model.model.layers.29.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 303 |
+
"language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 304 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 305 |
+
"language_model.model.layers.29.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 306 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 307 |
+
"language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 308 |
+
"language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 309 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 310 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 311 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 312 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 313 |
+
"language_model.model.layers.3.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 314 |
+
"language_model.model.layers.3.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 315 |
+
"language_model.model.layers.3.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 316 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 317 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 318 |
+
"language_model.model.layers.3.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 319 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 320 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 321 |
+
"language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 322 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 323 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 324 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 325 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 326 |
+
"language_model.model.layers.30.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 327 |
+
"language_model.model.layers.30.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 328 |
+
"language_model.model.layers.30.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 329 |
+
"language_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 330 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 331 |
+
"language_model.model.layers.30.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 332 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 333 |
+
"language_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 334 |
+
"language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 335 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 336 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 337 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 338 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 339 |
+
"language_model.model.layers.31.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 340 |
+
"language_model.model.layers.31.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 341 |
+
"language_model.model.layers.31.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 342 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 343 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 344 |
+
"language_model.model.layers.31.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 345 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 346 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 347 |
+
"language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 348 |
+
"language_model.model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 349 |
+
"language_model.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 350 |
+
"language_model.model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 351 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 352 |
+
"language_model.model.layers.32.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 353 |
+
"language_model.model.layers.32.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 354 |
+
"language_model.model.layers.32.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 355 |
+
"language_model.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 356 |
+
"language_model.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 357 |
+
"language_model.model.layers.32.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 358 |
+
"language_model.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 359 |
+
"language_model.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 360 |
+
"language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 361 |
+
"language_model.model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 362 |
+
"language_model.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 363 |
+
"language_model.model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 364 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 365 |
+
"language_model.model.layers.33.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 366 |
+
"language_model.model.layers.33.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 367 |
+
"language_model.model.layers.33.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 368 |
+
"language_model.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 369 |
+
"language_model.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 370 |
+
"language_model.model.layers.33.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 371 |
+
"language_model.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 372 |
+
"language_model.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 373 |
+
"language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 374 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 375 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 376 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 377 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 378 |
+
"language_model.model.layers.4.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 379 |
+
"language_model.model.layers.4.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 380 |
+
"language_model.model.layers.4.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 381 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 382 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 383 |
+
"language_model.model.layers.4.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 384 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 385 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 386 |
+
"language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 387 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 388 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 389 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 390 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 391 |
+
"language_model.model.layers.5.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 392 |
+
"language_model.model.layers.5.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 393 |
+
"language_model.model.layers.5.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 394 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 395 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 396 |
+
"language_model.model.layers.5.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 397 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 398 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 399 |
+
"language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 400 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 401 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 402 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 403 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 404 |
+
"language_model.model.layers.6.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 405 |
+
"language_model.model.layers.6.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 406 |
+
"language_model.model.layers.6.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 407 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 408 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 409 |
+
"language_model.model.layers.6.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 410 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 411 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 412 |
+
"language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 413 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 414 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 415 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 416 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 417 |
+
"language_model.model.layers.7.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 418 |
+
"language_model.model.layers.7.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 419 |
+
"language_model.model.layers.7.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 420 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 421 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 422 |
+
"language_model.model.layers.7.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 423 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 424 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 425 |
+
"language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 426 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 427 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 428 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 429 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 430 |
+
"language_model.model.layers.8.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 431 |
+
"language_model.model.layers.8.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 432 |
+
"language_model.model.layers.8.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 433 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 434 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 435 |
+
"language_model.model.layers.8.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 436 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 437 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 438 |
+
"language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 439 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 440 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 441 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 442 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 443 |
+
"language_model.model.layers.9.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 444 |
+
"language_model.model.layers.9.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 445 |
+
"language_model.model.layers.9.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 446 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 447 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 448 |
+
"language_model.model.layers.9.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 449 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 450 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 451 |
+
"language_model.model.norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 452 |
+
"multi_modal_projector.mm_input_projection_weight": "pytorch_model-00001-of-00002.bin",
|
| 453 |
+
"multi_modal_projector.mm_soft_emb_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 454 |
+
"vision_tower.vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00002.bin",
|
| 455 |
+
"vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
|
| 456 |
+
"vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
|
| 457 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 458 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 459 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 460 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 461 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 462 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 463 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 464 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 465 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 466 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 467 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 468 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 469 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 470 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 471 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 472 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 473 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 474 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 475 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 476 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 477 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 478 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 479 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 480 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 481 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 482 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 483 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 484 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 485 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 486 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 487 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 488 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 489 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 490 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 491 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 492 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 493 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 494 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 495 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 496 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 497 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 498 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 499 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 500 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 501 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 502 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 503 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 504 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 505 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 506 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 507 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 508 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 509 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 510 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 511 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 512 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 513 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 514 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 515 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 516 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 517 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 518 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 519 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 520 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 521 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 522 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 523 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 524 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 525 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 526 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 527 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 528 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 529 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 530 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 531 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 532 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 533 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 534 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 535 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 536 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 537 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 538 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 539 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 540 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 541 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 542 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 543 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 544 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 545 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 546 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 547 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 548 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 549 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 550 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 551 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 552 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 553 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 554 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 555 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 556 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 557 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 558 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 559 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 560 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 561 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 562 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 563 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 564 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 565 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 566 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 567 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 568 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 569 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 570 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 571 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 572 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 573 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 574 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 575 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 576 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 577 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 578 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 579 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 580 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 581 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 582 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 583 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 584 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 585 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 586 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 587 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 588 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 589 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 590 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 591 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 592 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 593 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 594 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 595 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 596 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 597 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 598 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 599 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 600 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 601 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 602 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 603 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 604 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 605 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 606 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 607 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 608 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 609 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 610 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 611 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 612 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 613 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 614 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 615 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 616 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 617 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 618 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 619 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 620 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 621 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 622 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 623 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 624 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 625 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 626 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 627 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 628 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 629 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 630 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 631 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 632 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 633 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 634 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 635 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 636 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 637 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 638 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 639 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 640 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 641 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 642 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 643 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 644 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 645 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 646 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 647 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 648 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 649 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 650 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 651 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 652 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 653 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 654 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 655 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 656 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 657 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 658 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 659 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 660 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 661 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 662 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 663 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 664 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 665 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 666 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 667 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 668 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 669 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 670 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 671 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 672 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 673 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 674 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 675 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 676 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 677 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 678 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 679 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 680 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 681 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 682 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 683 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 684 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 685 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 686 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 687 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 688 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 689 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 690 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 691 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 692 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 693 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 694 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 695 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 696 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 697 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 698 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 699 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 700 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 701 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 702 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 703 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 704 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 705 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 706 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 707 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 708 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 709 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 710 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 711 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 712 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 713 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 714 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 715 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 716 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 717 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 718 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 719 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 720 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 721 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 722 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 723 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 724 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 725 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 726 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 727 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 728 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 729 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 730 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 731 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 732 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 733 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 734 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 735 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 736 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 737 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 738 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 739 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 740 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 741 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 742 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 743 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 744 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 745 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 746 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 747 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 748 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 749 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 750 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 751 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 752 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 753 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 754 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 755 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 756 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 757 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 758 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 759 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 760 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 761 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 762 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 763 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 764 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 765 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 766 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 767 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 768 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 769 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 770 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 771 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 772 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 773 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 774 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 775 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 776 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 777 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 778 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 779 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 780 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 781 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 782 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 783 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 784 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 785 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 786 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 787 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 788 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 789 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 790 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 791 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 792 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 793 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 794 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 795 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 796 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 797 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 798 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 799 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 800 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 801 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 802 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 803 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 804 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 805 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 806 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 807 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 808 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 809 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 810 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 811 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 812 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 813 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 814 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 815 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 816 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 817 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 818 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 819 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 820 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 821 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 822 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 823 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 824 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 825 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 826 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 827 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 828 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 829 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 830 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 831 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 832 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 833 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 834 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 835 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 836 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 837 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 838 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 839 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 840 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 841 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 842 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 843 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 844 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 845 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 846 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 847 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 848 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 849 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 850 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 851 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 852 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 853 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 854 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 855 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 856 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 857 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 858 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 859 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 860 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 861 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 862 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 863 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 864 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 865 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 866 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 867 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 868 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 869 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 870 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 871 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 872 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 873 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
| 874 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
| 875 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
| 876 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
| 877 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
| 878 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 879 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
| 880 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 881 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 882 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 883 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 884 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 885 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 886 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 887 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
| 888 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 889 |
+
"vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
| 890 |
+
"vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin"
|
| 891 |
+
}
|
| 892 |
+
}
|
runs/Jul19_18-09-32_192-222-58-77/events.out.tfevents.1752948573.192-222-58-77.5282.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ab15d22681300bde760c80739f60b3f24dca2dec9e2633a311add35e4b46a1a
|
| 3 |
+
size 6831
|
runs/Jul19_18-11-11_192-222-58-77/events.out.tfevents.1752948671.192-222-58-77.5752.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f815219a336c10c8d54977b8f1edc506fe23f9b90803182aab32b79cefb718a
|
| 3 |
+
size 17382
|
runs/Jul19_18-22-00_192-222-58-77/events.out.tfevents.1752949320.192-222-58-77.7466.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d24eacd957f7961b838c971fd999f09909f46a383cfa50ff1851e7f63f06dcc
|
| 3 |
+
size 46079
|
runs/Jul19_18-58-05_192-222-58-77/events.out.tfevents.1752951485.192-222-58-77.13141.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61e3cf3ad446dc28b8a408f94ca39dfef8d887cb8ced11f0c4bfc3cd05477456
|
| 3 |
+
size 54663
|
runs/Jul19_19-53-53_192-222-58-77/events.out.tfevents.1752954833.192-222-58-77.21133.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b5dbe3cdbec8d498a403f48d7e344f2b8c133b21c092282b057e3758449e146
|
| 3 |
+
size 9573
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"eoi_token": "<end_of_image>",
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"content": "<eos>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"image_token": "<image_soft_token>",
|
| 19 |
+
"pad_token": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c96fd7401f729829eb0636c0285020112e74ace07bedf404c4c2461911b20287
|
| 3 |
+
size 33384821
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:450bc4d6d613e8730f0693919843828e1024b9940c5cce15e9d1fda91da1eccb
|
| 3 |
+
size 5777
|