Hugging Face's logo

adityavipradas
/
sft_gemma

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
sft
Model card Files Metrics Community
adityavipradas commited on
Commit
0a10356
·
verified ·
1 Parent(s): 011b31d

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. adapter_config.json +39 -39
  2. adapter_model.safetensors +1 -1
  3. runs/Mar16_08-55-33_USNPB-4JL9TT3/events.out.tfevents.1742136967.USNPB-4JL9TT3.10312.0 +3 -0
  4. runs/Mar16_08-55-33_USNPB-4JL9TT3/events.out.tfevents.1742137156.USNPB-4JL9TT3.10312.1 +3 -0
  5. special_tokens_map.json +33 -33
  6. tokenizer_config.json +0 -0
  7. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -1,40 +1,40 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "google/gemma-3-1b-pt",
5
- "bias": "none",
6
- "eva_config": null,
7
- "exclude_modules": null,
8
- "fan_in_fan_out": false,
9
- "inference_mode": true,
10
- "init_lora_weights": true,
11
- "layer_replication": null,
12
- "layers_pattern": null,
13
- "layers_to_transform": null,
14
- "loftq_config": {},
15
- "lora_alpha": 16,
16
- "lora_bias": false,
17
- "lora_dropout": 0.05,
18
- "megatron_config": null,
19
- "megatron_core": "megatron.core",
20
- "modules_to_save": [
21
- "lm_head",
22
- "embed_tokens"
23
- ],
24
- "peft_type": "LORA",
25
- "r": 4,
26
- "rank_pattern": {},
27
- "revision": null,
28
- "target_modules": [
29
- "down_proj",
30
- "gate_proj",
31
- "up_proj",
32
- "q_proj",
33
- "o_proj",
34
- "k_proj",
35
- "v_proj"
36
- ],
37
- "task_type": "CAUSAL_LM",
38
- "use_dora": false,
39
- "use_rslora": true
40
  }
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-3-1b-pt",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": [
21
+ "lm_head",
22
+ "embed_tokens"
23
+ ],
24
+ "peft_type": "LORA",
25
+ "r": 4,
26
+ "rank_pattern": {},
27
+ "revision": null,
28
+ "target_modules": [
29
+ "v_proj",
30
+ "o_proj",
31
+ "down_proj",
32
+ "q_proj",
33
+ "gate_proj",
34
+ "k_proj",
35
+ "up_proj"
36
+ ],
37
+ "task_type": "CAUSAL_LM",
38
+ "use_dora": false,
39
+ "use_rslora": true
40
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b18cc864178cd947fa56b25483440c578d47ca602e9a845f653f64a220836c84
3
  size 2429014600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a451c18261d34ade7d3c621f7e4dd130c9b4a1c5f61c1da057f9a66b33d199
3
  size 2429014600
runs/Mar16_08-55-33_USNPB-4JL9TT3/events.out.tfevents.1742136967.USNPB-4JL9TT3.10312.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5cecc03bc8eda8e823952c72a220ed9e67f2c813581f164a95df56701f8bf95
3
+ size 6127
runs/Mar16_08-55-33_USNPB-4JL9TT3/events.out.tfevents.1742137156.USNPB-4JL9TT3.10312.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e864363a3f449187f52461f555b27056d6de5167d87b7a145c8873eeec44473a
3
+ size 7888
special_tokens_map.json CHANGED
@@ -1,33 +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
- }
 
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_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebb8ff2b22391ad9178b0efccaeec9eee9a096d80bbe02a8b05bd83d6faa2820
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79a151b6327956c32fc623508c04ba299ad0efd6257fe998db8f2c25a282d1a
3
  size 5624