Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6daad9e3fcbc2a922d4452b027e0e29a2762cae95ced4e90bb066bc222e85731
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dcd4bf98f605b65e08d571683b49e3e541142117a2f403b88d52b10ae3d40d6
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ae71d10a257a2fe948689384f7ea2e41047332795ff539d04c5d39248106224
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac079e6f776bec3b7bea2038e04b1c6576e41a3f74d24e7a86650a7211209de
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,87 @@
+{"current_steps": 1, "total_steps": 364, "loss": 1.5698, "lr": 5.405405405405406e-07, "epoch": 0.01910828025477707, "percentage": 0.27, "elapsed_time": "0:00:10", "remaining_time": "1:02:00"}
+{"current_steps": 2, "total_steps": 364, "loss": 1.5972, "lr": 1.0810810810810812e-06, "epoch": 0.03821656050955414, "percentage": 0.55, "elapsed_time": "0:00:14", "remaining_time": "0:44:12"}
+{"current_steps": 3, "total_steps": 364, "loss": 1.5254, "lr": 1.6216216216216219e-06, "epoch": 0.05732484076433121, "percentage": 0.82, "elapsed_time": "0:00:22", "remaining_time": "0:44:09"}
+{"current_steps": 4, "total_steps": 364, "loss": 1.5602, "lr": 2.1621621621621623e-06, "epoch": 0.07643312101910828, "percentage": 1.1, "elapsed_time": "0:00:27", "remaining_time": "0:41:31"}
+{"current_steps": 5, "total_steps": 364, "loss": 1.4957, "lr": 2.702702702702703e-06, "epoch": 0.09554140127388536, "percentage": 1.37, "elapsed_time": "0:00:32", "remaining_time": "0:39:03"}
+{"current_steps": 6, "total_steps": 364, "loss": 1.4258, "lr": 3.2432432432432437e-06, "epoch": 0.11464968152866242, "percentage": 1.65, "elapsed_time": "0:00:37", "remaining_time": "0:37:23"}
+{"current_steps": 7, "total_steps": 364, "loss": 1.2829, "lr": 3.7837837837837844e-06, "epoch": 0.1337579617834395, "percentage": 1.92, "elapsed_time": "0:00:41", "remaining_time": "0:35:12"}
+{"current_steps": 8, "total_steps": 364, "loss": 1.265, "lr": 4.324324324324325e-06, "epoch": 0.15286624203821655, "percentage": 2.2, "elapsed_time": "0:00:46", "remaining_time": "0:34:33"}
+{"current_steps": 9, "total_steps": 364, "loss": 1.2011, "lr": 4.864864864864866e-06, "epoch": 0.17197452229299362, "percentage": 2.47, "elapsed_time": "0:00:51", "remaining_time": "0:34:09"}
+{"current_steps": 10, "total_steps": 364, "loss": 1.1285, "lr": 5.405405405405406e-06, "epoch": 0.1910828025477707, "percentage": 2.75, "elapsed_time": "0:01:00", "remaining_time": "0:35:34"}
+{"current_steps": 11, "total_steps": 364, "loss": 1.0849, "lr": 5.945945945945947e-06, "epoch": 0.21019108280254778, "percentage": 3.02, "elapsed_time": "0:01:03", "remaining_time": "0:34:04"}
+{"current_steps": 12, "total_steps": 364, "loss": 1.0295, "lr": 6.486486486486487e-06, "epoch": 0.22929936305732485, "percentage": 3.3, "elapsed_time": "0:01:07", "remaining_time": "0:33:01"}
+{"current_steps": 13, "total_steps": 364, "loss": 1.0054, "lr": 7.027027027027028e-06, "epoch": 0.2484076433121019, "percentage": 3.57, "elapsed_time": "0:01:14", "remaining_time": "0:33:29"}
+{"current_steps": 14, "total_steps": 364, "loss": 0.9589, "lr": 7.567567567567569e-06, "epoch": 0.267515923566879, "percentage": 3.85, "elapsed_time": "0:01:19", "remaining_time": "0:32:56"}
+{"current_steps": 15, "total_steps": 364, "loss": 0.9881, "lr": 8.108108108108109e-06, "epoch": 0.28662420382165604, "percentage": 4.12, "elapsed_time": "0:01:23", "remaining_time": "0:32:23"}
+{"current_steps": 16, "total_steps": 364, "loss": 0.955, "lr": 8.64864864864865e-06, "epoch": 0.3057324840764331, "percentage": 4.4, "elapsed_time": "0:01:30", "remaining_time": "0:32:45"}
+{"current_steps": 17, "total_steps": 364, "loss": 0.9141, "lr": 9.189189189189191e-06, "epoch": 0.3248407643312102, "percentage": 4.67, "elapsed_time": "0:01:35", "remaining_time": "0:32:38"}
+{"current_steps": 18, "total_steps": 364, "loss": 0.9251, "lr": 9.729729729729732e-06, "epoch": 0.34394904458598724, "percentage": 4.95, "elapsed_time": "0:01:40", "remaining_time": "0:32:12"}
+{"current_steps": 19, "total_steps": 364, "loss": 0.9106, "lr": 1.027027027027027e-05, "epoch": 0.3630573248407643, "percentage": 5.22, "elapsed_time": "0:01:44", "remaining_time": "0:31:37"}
+{"current_steps": 20, "total_steps": 364, "loss": 0.8812, "lr": 1.0810810810810812e-05, "epoch": 0.3821656050955414, "percentage": 5.49, "elapsed_time": "0:01:51", "remaining_time": "0:31:57"}
+{"current_steps": 21, "total_steps": 364, "loss": 0.8684, "lr": 1.1351351351351352e-05, "epoch": 0.4012738853503185, "percentage": 5.77, "elapsed_time": "0:01:56", "remaining_time": "0:31:42"}
+{"current_steps": 22, "total_steps": 364, "loss": 0.8832, "lr": 1.1891891891891894e-05, "epoch": 0.42038216560509556, "percentage": 6.04, "elapsed_time": "0:02:01", "remaining_time": "0:31:30"}
+{"current_steps": 23, "total_steps": 364, "loss": 0.878, "lr": 1.2432432432432433e-05, "epoch": 0.4394904458598726, "percentage": 6.32, "elapsed_time": "0:02:05", "remaining_time": "0:31:06"}
+{"current_steps": 24, "total_steps": 364, "loss": 0.864, "lr": 1.2972972972972975e-05, "epoch": 0.4585987261146497, "percentage": 6.59, "elapsed_time": "0:02:11", "remaining_time": "0:31:05"}
+{"current_steps": 25, "total_steps": 364, "loss": 0.8365, "lr": 1.3513513513513515e-05, "epoch": 0.47770700636942676, "percentage": 6.87, "elapsed_time": "0:02:18", "remaining_time": "0:31:13"}
+{"current_steps": 26, "total_steps": 364, "loss": 0.8362, "lr": 1.4054054054054055e-05, "epoch": 0.4968152866242038, "percentage": 7.14, "elapsed_time": "0:02:23", "remaining_time": "0:31:04"}
+{"current_steps": 27, "total_steps": 364, "loss": 0.8495, "lr": 1.4594594594594596e-05, "epoch": 0.5159235668789809, "percentage": 7.42, "elapsed_time": "0:02:27", "remaining_time": "0:30:43"}
+{"current_steps": 28, "total_steps": 364, "loss": 0.8239, "lr": 1.5135135135135138e-05, "epoch": 0.535031847133758, "percentage": 7.69, "elapsed_time": "0:02:35", "remaining_time": "0:31:01"}
+{"current_steps": 29, "total_steps": 364, "loss": 0.8448, "lr": 1.5675675675675676e-05, "epoch": 0.554140127388535, "percentage": 7.97, "elapsed_time": "0:02:39", "remaining_time": "0:30:46"}
+{"current_steps": 30, "total_steps": 364, "loss": 0.8311, "lr": 1.6216216216216218e-05, "epoch": 0.5732484076433121, "percentage": 8.24, "elapsed_time": "0:02:43", "remaining_time": "0:30:18"}
+{"current_steps": 31, "total_steps": 364, "loss": 0.8207, "lr": 1.6756756756756757e-05, "epoch": 0.5923566878980892, "percentage": 8.52, "elapsed_time": "0:02:47", "remaining_time": "0:29:58"}
+{"current_steps": 32, "total_steps": 364, "loss": 0.8042, "lr": 1.72972972972973e-05, "epoch": 0.6114649681528662, "percentage": 8.79, "elapsed_time": "0:02:53", "remaining_time": "0:30:04"}
+{"current_steps": 33, "total_steps": 364, "loss": 0.809, "lr": 1.783783783783784e-05, "epoch": 0.6305732484076433, "percentage": 9.07, "elapsed_time": "0:02:58", "remaining_time": "0:29:46"}
+{"current_steps": 34, "total_steps": 364, "loss": 0.8475, "lr": 1.8378378378378383e-05, "epoch": 0.6496815286624203, "percentage": 9.34, "elapsed_time": "0:03:01", "remaining_time": "0:29:25"}
+{"current_steps": 35, "total_steps": 364, "loss": 0.795, "lr": 1.891891891891892e-05, "epoch": 0.6687898089171974, "percentage": 9.62, "elapsed_time": "0:03:06", "remaining_time": "0:29:13"}
+{"current_steps": 36, "total_steps": 364, "loss": 0.8243, "lr": 1.9459459459459463e-05, "epoch": 0.6878980891719745, "percentage": 9.89, "elapsed_time": "0:03:13", "remaining_time": "0:29:24"}
+{"current_steps": 37, "total_steps": 364, "loss": 0.8132, "lr": 2e-05, "epoch": 0.7070063694267515, "percentage": 10.16, "elapsed_time": "0:03:19", "remaining_time": "0:29:23"}
+{"current_steps": 38, "total_steps": 364, "loss": 0.8151, "lr": 1.9999538500851633e-05, "epoch": 0.7261146496815286, "percentage": 10.44, "elapsed_time": "0:03:24", "remaining_time": "0:29:11"}
+{"current_steps": 39, "total_steps": 364, "loss": 0.8062, "lr": 1.9998154046002822e-05, "epoch": 0.7452229299363057, "percentage": 10.71, "elapsed_time": "0:03:31", "remaining_time": "0:29:21"}
+{"current_steps": 40, "total_steps": 364, "loss": 0.8148, "lr": 1.9995846763238514e-05, "epoch": 0.7643312101910829, "percentage": 10.99, "elapsed_time": "0:03:36", "remaining_time": "0:29:10"}
+{"current_steps": 41, "total_steps": 364, "loss": 0.8219, "lr": 1.9992616865520515e-05, "epoch": 0.7834394904458599, "percentage": 11.26, "elapsed_time": "0:03:39", "remaining_time": "0:28:50"}
+{"current_steps": 42, "total_steps": 364, "loss": 0.8053, "lr": 1.9988464650967834e-05, "epoch": 0.802547770700637, "percentage": 11.54, "elapsed_time": "0:03:44", "remaining_time": "0:28:44"}
+{"current_steps": 43, "total_steps": 364, "loss": 0.8001, "lr": 1.9983390502829168e-05, "epoch": 0.821656050955414, "percentage": 11.81, "elapsed_time": "0:03:48", "remaining_time": "0:28:26"}
+{"current_steps": 44, "total_steps": 364, "loss": 0.8023, "lr": 1.9977394889447526e-05, "epoch": 0.8407643312101911, "percentage": 12.09, "elapsed_time": "0:03:52", "remaining_time": "0:28:10"}
+{"current_steps": 45, "total_steps": 364, "loss": 0.7922, "lr": 1.9970478364217e-05, "epoch": 0.8598726114649682, "percentage": 12.36, "elapsed_time": "0:03:56", "remaining_time": "0:27:56"}
+{"current_steps": 46, "total_steps": 364, "loss": 0.8043, "lr": 1.9962641565531694e-05, "epoch": 0.8789808917197452, "percentage": 12.64, "elapsed_time": "0:04:00", "remaining_time": "0:27:43"}
+{"current_steps": 47, "total_steps": 364, "loss": 0.8107, "lr": 1.9953885216726788e-05, "epoch": 0.8980891719745223, "percentage": 12.91, "elapsed_time": "0:04:06", "remaining_time": "0:27:43"}
+{"current_steps": 48, "total_steps": 364, "loss": 0.7702, "lr": 1.994421012601179e-05, "epoch": 0.9171974522292994, "percentage": 13.19, "elapsed_time": "0:04:10", "remaining_time": "0:27:30"}
+{"current_steps": 49, "total_steps": 364, "loss": 0.8117, "lr": 1.9933617186395917e-05, "epoch": 0.9363057324840764, "percentage": 13.46, "elapsed_time": "0:04:15", "remaining_time": "0:27:22"}
+{"current_steps": 50, "total_steps": 364, "loss": 0.7898, "lr": 1.99221073756057e-05, "epoch": 0.9554140127388535, "percentage": 13.74, "elapsed_time": "0:04:19", "remaining_time": "0:27:07"}
+{"current_steps": 51, "total_steps": 364, "loss": 0.8044, "lr": 1.990968175599471e-05, "epoch": 0.9745222929936306, "percentage": 14.01, "elapsed_time": "0:04:25", "remaining_time": "0:27:10"}
+{"current_steps": 52, "total_steps": 364, "loss": 0.7751, "lr": 1.9896341474445526e-05, "epoch": 0.9936305732484076, "percentage": 14.29, "elapsed_time": "0:04:29", "remaining_time": "0:26:56"}
+{"current_steps": 53, "total_steps": 364, "loss": 0.7185, "lr": 1.9882087762263857e-05, "epoch": 1.0127388535031847, "percentage": 14.56, "elapsed_time": "0:06:21", "remaining_time": "0:37:18"}
+{"current_steps": 54, "total_steps": 364, "loss": 0.6317, "lr": 1.9866921935064907e-05, "epoch": 1.0318471337579618, "percentage": 14.84, "elapsed_time": "0:06:26", "remaining_time": "0:36:59"}
+{"current_steps": 55, "total_steps": 364, "loss": 0.5979, "lr": 1.985084539265195e-05, "epoch": 1.0509554140127388, "percentage": 15.11, "elapsed_time": "0:06:31", "remaining_time": "0:36:40"}
+{"current_steps": 56, "total_steps": 364, "loss": 0.599, "lr": 1.983385961888711e-05, "epoch": 1.070063694267516, "percentage": 15.38, "elapsed_time": "0:06:37", "remaining_time": "0:36:23"}
+{"current_steps": 57, "total_steps": 364, "loss": 0.602, "lr": 1.9815966181554412e-05, "epoch": 1.089171974522293, "percentage": 15.66, "elapsed_time": "0:06:42", "remaining_time": "0:36:10"}
+{"current_steps": 58, "total_steps": 364, "loss": 0.6138, "lr": 1.9797166732215078e-05, "epoch": 1.10828025477707, "percentage": 15.93, "elapsed_time": "0:06:46", "remaining_time": "0:35:46"}
+{"current_steps": 59, "total_steps": 364, "loss": 0.5711, "lr": 1.977746300605507e-05, "epoch": 1.127388535031847, "percentage": 16.21, "elapsed_time": "0:06:52", "remaining_time": "0:35:34"}
+{"current_steps": 60, "total_steps": 364, "loss": 0.5927, "lr": 1.975685682172497e-05, "epoch": 1.1464968152866242, "percentage": 16.48, "elapsed_time": "0:06:57", "remaining_time": "0:35:15"}
+{"current_steps": 61, "total_steps": 364, "loss": 0.5961, "lr": 1.973535008117207e-05, "epoch": 1.1656050955414012, "percentage": 16.76, "elapsed_time": "0:07:03", "remaining_time": "0:35:05"}
+{"current_steps": 62, "total_steps": 364, "loss": 0.5776, "lr": 1.9712944769464864e-05, "epoch": 1.1847133757961783, "percentage": 17.03, "elapsed_time": "0:07:08", "remaining_time": "0:34:44"}
+{"current_steps": 63, "total_steps": 364, "loss": 0.5703, "lr": 1.9689642954609808e-05, "epoch": 1.2038216560509554, "percentage": 17.31, "elapsed_time": "0:07:12", "remaining_time": "0:34:25"}
+{"current_steps": 64, "total_steps": 364, "loss": 0.6179, "lr": 1.9665446787360444e-05, "epoch": 1.2229299363057324, "percentage": 17.58, "elapsed_time": "0:07:17", "remaining_time": "0:34:12"}
+{"current_steps": 65, "total_steps": 364, "loss": 0.5533, "lr": 1.9640358501018885e-05, "epoch": 1.2420382165605095, "percentage": 17.86, "elapsed_time": "0:07:24", "remaining_time": "0:34:02"}
+{"current_steps": 66, "total_steps": 364, "loss": 0.5839, "lr": 1.9614380411229693e-05, "epoch": 1.2611464968152866, "percentage": 18.13, "elapsed_time": "0:07:29", "remaining_time": "0:33:48"}
+{"current_steps": 67, "total_steps": 364, "loss": 0.5883, "lr": 1.9587514915766124e-05, "epoch": 1.2802547770700636, "percentage": 18.41, "elapsed_time": "0:07:34", "remaining_time": "0:33:34"}
+{"current_steps": 68, "total_steps": 364, "loss": 0.5448, "lr": 1.9559764494308838e-05, "epoch": 1.2993630573248407, "percentage": 18.68, "elapsed_time": "0:07:38", "remaining_time": "0:33:14"}
+{"current_steps": 69, "total_steps": 364, "loss": 0.5767, "lr": 1.9531131708217005e-05, "epoch": 1.3184713375796178, "percentage": 18.96, "elapsed_time": "0:07:42", "remaining_time": "0:32:58"}
+{"current_steps": 70, "total_steps": 364, "loss": 0.5755, "lr": 1.950161920029191e-05, "epoch": 1.3375796178343948, "percentage": 19.23, "elapsed_time": "0:07:49", "remaining_time": "0:32:52"}
+{"current_steps": 71, "total_steps": 364, "loss": 0.5469, "lr": 1.9471229694533003e-05, "epoch": 1.356687898089172, "percentage": 19.51, "elapsed_time": "0:07:53", "remaining_time": "0:32:33"}
+{"current_steps": 72, "total_steps": 364, "loss": 0.5784, "lr": 1.943996599588649e-05, "epoch": 1.3757961783439492, "percentage": 19.78, "elapsed_time": "0:08:01", "remaining_time": "0:32:32"}
+{"current_steps": 73, "total_steps": 364, "loss": 0.592, "lr": 1.940783098998643e-05, "epoch": 1.394904458598726, "percentage": 20.05, "elapsed_time": "0:08:06", "remaining_time": "0:32:17"}
+{"current_steps": 74, "total_steps": 364, "loss": 0.5365, "lr": 1.93748276428884e-05, "epoch": 1.4140127388535033, "percentage": 20.33, "elapsed_time": "0:08:11", "remaining_time": "0:32:04"}
+{"current_steps": 75, "total_steps": 364, "loss": 0.5772, "lr": 1.9340959000795707e-05, "epoch": 1.4331210191082802, "percentage": 20.6, "elapsed_time": "0:08:15", "remaining_time": "0:31:51"}
+{"current_steps": 76, "total_steps": 364, "loss": 0.5819, "lr": 1.9306228189778255e-05, "epoch": 1.4522292993630574, "percentage": 20.88, "elapsed_time": "0:08:22", "remaining_time": "0:31:42"}
+{"current_steps": 77, "total_steps": 364, "loss": 0.5574, "lr": 1.927063841548398e-05, "epoch": 1.4713375796178343, "percentage": 21.15, "elapsed_time": "0:08:25", "remaining_time": "0:31:24"}
+{"current_steps": 78, "total_steps": 364, "loss": 0.5665, "lr": 1.9234192962842996e-05, "epoch": 1.4904458598726116, "percentage": 21.43, "elapsed_time": "0:08:29", "remaining_time": "0:31:08"}
+{"current_steps": 79, "total_steps": 364, "loss": 0.6213, "lr": 1.9196895195764363e-05, "epoch": 1.5095541401273884, "percentage": 21.7, "elapsed_time": "0:08:34", "remaining_time": "0:30:55"}
+{"current_steps": 80, "total_steps": 364, "loss": 0.5928, "lr": 1.9158748556825637e-05, "epoch": 1.5286624203821657, "percentage": 21.98, "elapsed_time": "0:08:38", "remaining_time": "0:30:42"}
+{"current_steps": 81, "total_steps": 364, "loss": 0.6015, "lr": 1.9119756566955092e-05, "epoch": 1.5477707006369426, "percentage": 22.25, "elapsed_time": "0:08:43", "remaining_time": "0:30:28"}
+{"current_steps": 82, "total_steps": 364, "loss": 0.5937, "lr": 1.907992282510675e-05, "epoch": 1.5668789808917198, "percentage": 22.53, "elapsed_time": "0:08:47", "remaining_time": "0:30:13"}
+{"current_steps": 83, "total_steps": 364, "loss": 0.5835, "lr": 1.90392510079282e-05, "epoch": 1.5859872611464967, "percentage": 22.8, "elapsed_time": "0:08:51", "remaining_time": "0:29:59"}
+{"current_steps": 84, "total_steps": 364, "loss": 0.5785, "lr": 1.8997744869421248e-05, "epoch": 1.605095541401274, "percentage": 23.08, "elapsed_time": "0:08:55", "remaining_time": "0:29:46"}
+{"current_steps": 85, "total_steps": 364, "loss": 0.5773, "lr": 1.8955408240595396e-05, "epoch": 1.6242038216560508, "percentage": 23.35, "elapsed_time": "0:08:59", "remaining_time": "0:29:32"}
+{"current_steps": 86, "total_steps": 364, "loss": 0.6068, "lr": 1.891224502911428e-05, "epoch": 1.643312101910828, "percentage": 23.63, "elapsed_time": "0:09:04", "remaining_time": "0:29:21"}
+{"current_steps": 87, "total_steps": 364, "loss": 0.5602, "lr": 1.886825921893497e-05, "epoch": 1.662420382165605, "percentage": 23.9, "elapsed_time": "0:09:09", "remaining_time": "0:29:09"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c08e3b2808882d1c04e46a6f09a71bf2afbc980d27d8de980b93b15e7f00eff3
+size 7352