Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,38 @@ 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
+qwen2.5_full_sft/checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_full_sft/checkpoint-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_full_sft/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-1700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-2300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-2600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-2700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-2900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-3100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5_lora_sft/checkpoint-epoch-0-step-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen2.5_full_sft/checkpoint-1800/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
+}

qwen2.5_full_sft/checkpoint-1800/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2.5_full_sft/checkpoint-1800/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen2.5_full_sft/checkpoint-1800/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.3"
+}

qwen2.5_full_sft/checkpoint-1800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9904eb4590bab96c0e32ebaacec8f464b80a4002f8173710dcc5ba43d9c85d54
+size 3087467144

qwen2.5_full_sft/checkpoint-1800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c535555b2649e0f140566562a6c5aa2d6e07868ee86ab92a2566819c39b2f3
+size 4529806751

qwen2.5_full_sft/checkpoint-1800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

qwen2.5_full_sft/checkpoint-1800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733df5ab2cd0c3146afe5b3d08d71a3b9153092ba899be7222ec64beeefb18cf
+size 1465

qwen2.5_full_sft/checkpoint-1800/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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

qwen2.5_full_sft/checkpoint-1800/tokenizer.json

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

qwen2.5_full_sft/checkpoint-1800/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2.5_full_sft/checkpoint-1800/trainer_state.json

@@ -0,0 +1,1294 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3707279397567098,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0020595996653150544,
+      "grad_norm": 3.171875,
+      "learning_rate": 6.164383561643836e-07,
+      "loss": 0.9341,
+      "step": 10
+    },
+    {
+      "epoch": 0.004119199330630109,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.3013698630136986e-06,
+      "loss": 0.8822,
+      "step": 20
+    },
+    {
+      "epoch": 0.006178798995945163,
+      "grad_norm": 2.625,
+      "learning_rate": 1.9863013698630136e-06,
+      "loss": 0.9008,
+      "step": 30
+    },
+    {
+      "epoch": 0.008238398661260218,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.671232876712329e-06,
+      "loss": 0.8337,
+      "step": 40
+    },
+    {
+      "epoch": 0.010297998326575271,
+      "grad_norm": 2.21875,
+      "learning_rate": 3.356164383561644e-06,
+      "loss": 0.8392,
+      "step": 50
+    },
+    {
+      "epoch": 0.012357597991890326,
+      "grad_norm": 1.8046875,
+      "learning_rate": 4.0410958904109595e-06,
+      "loss": 0.8572,
+      "step": 60
+    },
+    {
+      "epoch": 0.01441719765720538,
+      "grad_norm": 1.9375,
+      "learning_rate": 4.726027397260274e-06,
+      "loss": 0.8535,
+      "step": 70
+    },
+    {
+      "epoch": 0.016476797322520435,
+      "grad_norm": 1.453125,
+      "learning_rate": 5.41095890410959e-06,
+      "loss": 0.8643,
+      "step": 80
+    },
+    {
+      "epoch": 0.01853639698783549,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.095890410958905e-06,
+      "loss": 0.8333,
+      "step": 90
+    },
+    {
+      "epoch": 0.020595996653150542,
+      "grad_norm": 1.265625,
+      "learning_rate": 6.78082191780822e-06,
+      "loss": 0.7985,
+      "step": 100
+    },
+    {
+      "epoch": 0.022655596318465598,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.465753424657535e-06,
+      "loss": 0.8222,
+      "step": 110
+    },
+    {
+      "epoch": 0.024715195983780653,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.150684931506851e-06,
+      "loss": 0.7686,
+      "step": 120
+    },
+    {
+      "epoch": 0.02677479564909571,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.835616438356165e-06,
+      "loss": 0.8005,
+      "step": 130
+    },
+    {
+      "epoch": 0.02883439531441076,
+      "grad_norm": 1.203125,
+      "learning_rate": 9.52054794520548e-06,
+      "loss": 0.7832,
+      "step": 140
+    },
+    {
+      "epoch": 0.030893994979725815,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.993630573248408e-06,
+      "loss": 0.7758,
+      "step": 150
+    },
+    {
+      "epoch": 0.03295359464504087,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.972399150743101e-06,
+      "loss": 0.7042,
+      "step": 160
+    },
+    {
+      "epoch": 0.035013194310355926,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.951167728237793e-06,
+      "loss": 0.7154,
+      "step": 170
+    },
+    {
+      "epoch": 0.03707279397567098,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.929936305732485e-06,
+      "loss": 0.744,
+      "step": 180
+    },
+    {
+      "epoch": 0.039132393640986037,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.908704883227176e-06,
+      "loss": 0.7538,
+      "step": 190
+    },
+    {
+      "epoch": 0.041191993306301085,
+      "grad_norm": 1.4140625,
+      "learning_rate": 9.88747346072187e-06,
+      "loss": 0.7344,
+      "step": 200
+    },
+    {
+      "epoch": 0.04325159297161614,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.866242038216562e-06,
+      "loss": 0.7408,
+      "step": 210
+    },
+    {
+      "epoch": 0.045311192636931195,
+      "grad_norm": 2.125,
+      "learning_rate": 9.845010615711253e-06,
+      "loss": 0.7133,
+      "step": 220
+    },
+    {
+      "epoch": 0.04737079230224625,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.823779193205945e-06,
+      "loss": 0.7584,
+      "step": 230
+    },
+    {
+      "epoch": 0.049430391967561306,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.802547770700639e-06,
+      "loss": 0.7208,
+      "step": 240
+    },
+    {
+      "epoch": 0.05148999163287636,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.78131634819533e-06,
+      "loss": 0.7483,
+      "step": 250
+    },
+    {
+      "epoch": 0.05354959129819142,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.760084925690022e-06,
+      "loss": 0.7419,
+      "step": 260
+    },
+    {
+      "epoch": 0.05560919096350647,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.738853503184714e-06,
+      "loss": 0.69,
+      "step": 270
+    },
+    {
+      "epoch": 0.05766879062882152,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.717622080679406e-06,
+      "loss": 0.6888,
+      "step": 280
+    },
+    {
+      "epoch": 0.059728390294136575,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.696390658174099e-06,
+      "loss": 0.7139,
+      "step": 290
+    },
+    {
+      "epoch": 0.06178798995945163,
+      "grad_norm": 1.3515625,
+      "learning_rate": 9.67515923566879e-06,
+      "loss": 0.7062,
+      "step": 300
+    },
+    {
+      "epoch": 0.06384758962476668,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.653927813163482e-06,
+      "loss": 0.7225,
+      "step": 310
+    },
+    {
+      "epoch": 0.06590718929008174,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.632696390658174e-06,
+      "loss": 0.7428,
+      "step": 320
+    },
+    {
+      "epoch": 0.06796678895539679,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.611464968152868e-06,
+      "loss": 0.6763,
+      "step": 330
+    },
+    {
+      "epoch": 0.07002638862071185,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.59023354564756e-06,
+      "loss": 0.6758,
+      "step": 340
+    },
+    {
+      "epoch": 0.0720859882860269,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.569002123142251e-06,
+      "loss": 0.7067,
+      "step": 350
+    },
+    {
+      "epoch": 0.07414558795134196,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.547770700636943e-06,
+      "loss": 0.7329,
+      "step": 360
+    },
+    {
+      "epoch": 0.07620518761665701,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.526539278131636e-06,
+      "loss": 0.7396,
+      "step": 370
+    },
+    {
+      "epoch": 0.07826478728197207,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.505307855626328e-06,
+      "loss": 0.7596,
+      "step": 380
+    },
+    {
+      "epoch": 0.08032438694728712,
+      "grad_norm": 1.375,
+      "learning_rate": 9.48407643312102e-06,
+      "loss": 0.7073,
+      "step": 390
+    },
+    {
+      "epoch": 0.08238398661260217,
+      "grad_norm": 1.984375,
+      "learning_rate": 9.462845010615711e-06,
+      "loss": 0.7241,
+      "step": 400
+    },
+    {
+      "epoch": 0.08444358627791723,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.441613588110405e-06,
+      "loss": 0.7105,
+      "step": 410
+    },
+    {
+      "epoch": 0.08650318594323228,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.420382165605097e-06,
+      "loss": 0.6821,
+      "step": 420
+    },
+    {
+      "epoch": 0.08856278560854734,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.399150743099788e-06,
+      "loss": 0.7379,
+      "step": 430
+    },
+    {
+      "epoch": 0.09062238527386239,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.37791932059448e-06,
+      "loss": 0.6849,
+      "step": 440
+    },
+    {
+      "epoch": 0.09268198493917745,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.356687898089174e-06,
+      "loss": 0.6898,
+      "step": 450
+    },
+    {
+      "epoch": 0.0947415846044925,
+      "grad_norm": 1.9453125,
+      "learning_rate": 9.335456475583865e-06,
+      "loss": 0.6911,
+      "step": 460
+    },
+    {
+      "epoch": 0.09680118426980755,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.314225053078557e-06,
+      "loss": 0.7164,
+      "step": 470
+    },
+    {
+      "epoch": 0.09886078393512261,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.292993630573249e-06,
+      "loss": 0.6855,
+      "step": 480
+    },
+    {
+      "epoch": 0.10092038360043766,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.271762208067942e-06,
+      "loss": 0.7093,
+      "step": 490
+    },
+    {
+      "epoch": 0.10297998326575272,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.250530785562634e-06,
+      "loss": 0.6891,
+      "step": 500
+    },
+    {
+      "epoch": 0.10503958293106777,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.229299363057326e-06,
+      "loss": 0.6962,
+      "step": 510
+    },
+    {
+      "epoch": 0.10709918259638283,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.208067940552017e-06,
+      "loss": 0.7039,
+      "step": 520
+    },
+    {
+      "epoch": 0.10915878226169788,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.186836518046711e-06,
+      "loss": 0.6919,
+      "step": 530
+    },
+    {
+      "epoch": 0.11121838192701294,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.165605095541403e-06,
+      "loss": 0.6784,
+      "step": 540
+    },
+    {
+      "epoch": 0.11327798159232799,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.144373673036094e-06,
+      "loss": 0.69,
+      "step": 550
+    },
+    {
+      "epoch": 0.11533758125764304,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.123142250530786e-06,
+      "loss": 0.7122,
+      "step": 560
+    },
+    {
+      "epoch": 0.1173971809229581,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.101910828025478e-06,
+      "loss": 0.7057,
+      "step": 570
+    },
+    {
+      "epoch": 0.11945678058827315,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.080679405520171e-06,
+      "loss": 0.6727,
+      "step": 580
+    },
+    {
+      "epoch": 0.12151638025358821,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.059447983014863e-06,
+      "loss": 0.6828,
+      "step": 590
+    },
+    {
+      "epoch": 0.12357597991890326,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.038216560509555e-06,
+      "loss": 0.7218,
+      "step": 600
+    },
+    {
+      "epoch": 0.1256355795842183,
+      "grad_norm": 1.171875,
+      "learning_rate": 9.016985138004246e-06,
+      "loss": 0.6701,
+      "step": 610
+    },
+    {
+      "epoch": 0.12769517924953336,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.99575371549894e-06,
+      "loss": 0.7289,
+      "step": 620
+    },
+    {
+      "epoch": 0.12975477891484843,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.974522292993632e-06,
+      "loss": 0.6545,
+      "step": 630
+    },
+    {
+      "epoch": 0.13181437858016348,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.953290870488323e-06,
+      "loss": 0.6697,
+      "step": 640
+    },
+    {
+      "epoch": 0.13387397824547853,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.932059447983015e-06,
+      "loss": 0.6964,
+      "step": 650
+    },
+    {
+      "epoch": 0.13593357791079358,
+      "grad_norm": 1.6328125,
+      "learning_rate": 8.910828025477709e-06,
+      "loss": 0.7249,
+      "step": 660
+    },
+    {
+      "epoch": 0.13799317757610866,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.8895966029724e-06,
+      "loss": 0.6914,
+      "step": 670
+    },
+    {
+      "epoch": 0.1400527772414237,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.868365180467092e-06,
+      "loss": 0.7196,
+      "step": 680
+    },
+    {
+      "epoch": 0.14211237690673875,
+      "grad_norm": 1.5,
+      "learning_rate": 8.847133757961784e-06,
+      "loss": 0.6761,
+      "step": 690
+    },
+    {
+      "epoch": 0.1441719765720538,
+      "grad_norm": 1.734375,
+      "learning_rate": 8.825902335456477e-06,
+      "loss": 0.6784,
+      "step": 700
+    },
+    {
+      "epoch": 0.14623157623736885,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.804670912951169e-06,
+      "loss": 0.7393,
+      "step": 710
+    },
+    {
+      "epoch": 0.14829117590268392,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.78343949044586e-06,
+      "loss": 0.6897,
+      "step": 720
+    },
+    {
+      "epoch": 0.15035077556799897,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.762208067940552e-06,
+      "loss": 0.6699,
+      "step": 730
+    },
+    {
+      "epoch": 0.15241037523331402,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.740976645435246e-06,
+      "loss": 0.6873,
+      "step": 740
+    },
+    {
+      "epoch": 0.15446997489862907,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.719745222929938e-06,
+      "loss": 0.661,
+      "step": 750
+    },
+    {
+      "epoch": 0.15652957456394415,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.69851380042463e-06,
+      "loss": 0.6918,
+      "step": 760
+    },
+    {
+      "epoch": 0.1585891742292592,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.677282377919321e-06,
+      "loss": 0.69,
+      "step": 770
+    },
+    {
+      "epoch": 0.16064877389457424,
+      "grad_norm": 1.375,
+      "learning_rate": 8.656050955414015e-06,
+      "loss": 0.7571,
+      "step": 780
+    },
+    {
+      "epoch": 0.1627083735598893,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.634819532908706e-06,
+      "loss": 0.7193,
+      "step": 790
+    },
+    {
+      "epoch": 0.16476797322520434,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.613588110403398e-06,
+      "loss": 0.6783,
+      "step": 800
+    },
+    {
+      "epoch": 0.16682757289051942,
+      "grad_norm": 1.375,
+      "learning_rate": 8.59235668789809e-06,
+      "loss": 0.6807,
+      "step": 810
+    },
+    {
+      "epoch": 0.16888717255583446,
+      "grad_norm": 1.2578125,
+      "learning_rate": 8.571125265392782e-06,
+      "loss": 0.6597,
+      "step": 820
+    },
+    {
+      "epoch": 0.1709467722211495,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.549893842887475e-06,
+      "loss": 0.691,
+      "step": 830
+    },
+    {
+      "epoch": 0.17300637188646456,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.528662420382167e-06,
+      "loss": 0.6266,
+      "step": 840
+    },
+    {
+      "epoch": 0.17506597155177964,
+      "grad_norm": 1.578125,
+      "learning_rate": 8.507430997876858e-06,
+      "loss": 0.7104,
+      "step": 850
+    },
+    {
+      "epoch": 0.17712557121709468,
+      "grad_norm": 1.8359375,
+      "learning_rate": 8.48619957537155e-06,
+      "loss": 0.7417,
+      "step": 860
+    },
+    {
+      "epoch": 0.17918517088240973,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.464968152866244e-06,
+      "loss": 0.6707,
+      "step": 870
+    },
+    {
+      "epoch": 0.18124477054772478,
+      "grad_norm": 1.75,
+      "learning_rate": 8.443736730360935e-06,
+      "loss": 0.6776,
+      "step": 880
+    },
+    {
+      "epoch": 0.18330437021303983,
+      "grad_norm": 1.3125,
+      "learning_rate": 8.422505307855627e-06,
+      "loss": 0.6576,
+      "step": 890
+    },
+    {
+      "epoch": 0.1853639698783549,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.401273885350319e-06,
+      "loss": 0.6838,
+      "step": 900
+    },
+    {
+      "epoch": 0.18742356954366995,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.380042462845012e-06,
+      "loss": 0.6616,
+      "step": 910
+    },
+    {
+      "epoch": 0.189483169208985,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.358811040339704e-06,
+      "loss": 0.6868,
+      "step": 920
+    },
+    {
+      "epoch": 0.19154276887430005,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.337579617834396e-06,
+      "loss": 0.667,
+      "step": 930
+    },
+    {
+      "epoch": 0.1936023685396151,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.316348195329087e-06,
+      "loss": 0.6805,
+      "step": 940
+    },
+    {
+      "epoch": 0.19566196820493018,
+      "grad_norm": 1.25,
+      "learning_rate": 8.295116772823781e-06,
+      "loss": 0.6723,
+      "step": 950
+    },
+    {
+      "epoch": 0.19772156787024522,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.273885350318473e-06,
+      "loss": 0.6739,
+      "step": 960
+    },
+    {
+      "epoch": 0.19978116753556027,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.252653927813164e-06,
+      "loss": 0.7014,
+      "step": 970
+    },
+    {
+      "epoch": 0.20184076720087532,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.231422505307856e-06,
+      "loss": 0.6908,
+      "step": 980
+    },
+    {
+      "epoch": 0.2039003668661904,
+      "grad_norm": 1.328125,
+      "learning_rate": 8.21019108280255e-06,
+      "loss": 0.6582,
+      "step": 990
+    },
+    {
+      "epoch": 0.20595996653150545,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.188959660297241e-06,
+      "loss": 0.6619,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2080195661968205,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.167728237791933e-06,
+      "loss": 0.6798,
+      "step": 1010
+    },
+    {
+      "epoch": 0.21007916586213554,
+      "grad_norm": 1.34375,
+      "learning_rate": 8.146496815286625e-06,
+      "loss": 0.6565,
+      "step": 1020
+    },
+    {
+      "epoch": 0.2121387655274506,
+      "grad_norm": 1.625,
+      "learning_rate": 8.125265392781318e-06,
+      "loss": 0.7176,
+      "step": 1030
+    },
+    {
+      "epoch": 0.21419836519276567,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.10403397027601e-06,
+      "loss": 0.6692,
+      "step": 1040
+    },
+    {
+      "epoch": 0.21625796485808071,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.082802547770702e-06,
+      "loss": 0.675,
+      "step": 1050
+    },
+    {
+      "epoch": 0.21831756452339576,
+      "grad_norm": 1.375,
+      "learning_rate": 8.061571125265393e-06,
+      "loss": 0.6989,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2203771641887108,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.040339702760087e-06,
+      "loss": 0.7133,
+      "step": 1070
+    },
+    {
+      "epoch": 0.2224367638540259,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.019108280254779e-06,
+      "loss": 0.7272,
+      "step": 1080
+    },
+    {
+      "epoch": 0.22449636351934094,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.99787685774947e-06,
+      "loss": 0.6684,
+      "step": 1090
+    },
+    {
+      "epoch": 0.22655596318465598,
+      "grad_norm": 1.328125,
+      "learning_rate": 7.976645435244162e-06,
+      "loss": 0.6895,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22861556284997103,
+      "grad_norm": 1.5078125,
+      "learning_rate": 7.955414012738854e-06,
+      "loss": 0.6859,
+      "step": 1110
+    },
+    {
+      "epoch": 0.23067516251528608,
+      "grad_norm": 1.6953125,
+      "learning_rate": 7.934182590233547e-06,
+      "loss": 0.723,
+      "step": 1120
+    },
+    {
+      "epoch": 0.23273476218060116,
+      "grad_norm": 1.265625,
+      "learning_rate": 7.912951167728239e-06,
+      "loss": 0.6883,
+      "step": 1130
+    },
+    {
+      "epoch": 0.2347943618459162,
+      "grad_norm": 1.390625,
+      "learning_rate": 7.89171974522293e-06,
+      "loss": 0.6653,
+      "step": 1140
+    },
+    {
+      "epoch": 0.23685396151123125,
+      "grad_norm": 1.6015625,
+      "learning_rate": 7.870488322717622e-06,
+      "loss": 0.7101,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2389135611765463,
+      "grad_norm": 1.4765625,
+      "learning_rate": 7.849256900212316e-06,
+      "loss": 0.6775,
+      "step": 1160
+    },
+    {
+      "epoch": 0.24097316084186135,
+      "grad_norm": 1.421875,
+      "learning_rate": 7.828025477707008e-06,
+      "loss": 0.651,
+      "step": 1170
+    },
+    {
+      "epoch": 0.24303276050717643,
+      "grad_norm": 1.34375,
+      "learning_rate": 7.8067940552017e-06,
+      "loss": 0.6951,
+      "step": 1180
+    },
+    {
+      "epoch": 0.24509236017249147,
+      "grad_norm": 1.59375,
+      "learning_rate": 7.785562632696391e-06,
+      "loss": 0.6685,
+      "step": 1190
+    },
+    {
+      "epoch": 0.24715195983780652,
+      "grad_norm": 1.625,
+      "learning_rate": 7.764331210191085e-06,
+      "loss": 0.7213,
+      "step": 1200
+    },
+    {
+      "epoch": 0.24921155950312157,
+      "grad_norm": 1.3671875,
+      "learning_rate": 7.743099787685776e-06,
+      "loss": 0.6925,
+      "step": 1210
+    },
+    {
+      "epoch": 0.2512711591684366,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.721868365180468e-06,
+      "loss": 0.6676,
+      "step": 1220
+    },
+    {
+      "epoch": 0.25333075883375167,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.70063694267516e-06,
+      "loss": 0.7241,
+      "step": 1230
+    },
+    {
+      "epoch": 0.2553903584990667,
+      "grad_norm": 1.3125,
+      "learning_rate": 7.679405520169853e-06,
+      "loss": 0.6648,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2574499581643818,
+      "grad_norm": 1.3359375,
+      "learning_rate": 7.658174097664545e-06,
+      "loss": 0.6936,
+      "step": 1250
+    },
+    {
+      "epoch": 0.25950955782969687,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.636942675159237e-06,
+      "loss": 0.6615,
+      "step": 1260
+    },
+    {
+      "epoch": 0.2615691574950119,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.615711252653929e-06,
+      "loss": 0.694,
+      "step": 1270
+    },
+    {
+      "epoch": 0.26362875716032697,
+      "grad_norm": 1.703125,
+      "learning_rate": 7.594479830148621e-06,
+      "loss": 0.721,
+      "step": 1280
+    },
+    {
+      "epoch": 0.265688356825642,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.573248407643314e-06,
+      "loss": 0.6581,
+      "step": 1290
+    },
+    {
+      "epoch": 0.26774795649095706,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.552016985138005e-06,
+      "loss": 0.6855,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2698075561562721,
+      "grad_norm": 1.5,
+      "learning_rate": 7.530785562632698e-06,
+      "loss": 0.6606,
+      "step": 1310
+    },
+    {
+      "epoch": 0.27186715582158716,
+      "grad_norm": 1.609375,
+      "learning_rate": 7.50955414012739e-06,
+      "loss": 0.6695,
+      "step": 1320
+    },
+    {
+      "epoch": 0.2739267554869022,
+      "grad_norm": 1.2265625,
+      "learning_rate": 7.4883227176220806e-06,
+      "loss": 0.6577,
+      "step": 1330
+    },
+    {
+      "epoch": 0.2759863551522173,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.467091295116773e-06,
+      "loss": 0.6765,
+      "step": 1340
+    },
+    {
+      "epoch": 0.27804595481753236,
+      "grad_norm": 1.359375,
+      "learning_rate": 7.445859872611465e-06,
+      "loss": 0.6688,
+      "step": 1350
+    },
+    {
+      "epoch": 0.2801055544828474,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.4246284501061575e-06,
+      "loss": 0.6831,
+      "step": 1360
+    },
+    {
+      "epoch": 0.28216515414816246,
+      "grad_norm": 1.3359375,
+      "learning_rate": 7.403397027600849e-06,
+      "loss": 0.6893,
+      "step": 1370
+    },
+    {
+      "epoch": 0.2842247538134775,
+      "grad_norm": 1.890625,
+      "learning_rate": 7.382165605095542e-06,
+      "loss": 0.7225,
+      "step": 1380
+    },
+    {
+      "epoch": 0.28628435347879255,
+      "grad_norm": 1.546875,
+      "learning_rate": 7.3609341825902335e-06,
+      "loss": 0.6909,
+      "step": 1390
+    },
+    {
+      "epoch": 0.2883439531441076,
+      "grad_norm": 1.6328125,
+      "learning_rate": 7.339702760084926e-06,
+      "loss": 0.6611,
+      "step": 1400
+    },
+    {
+      "epoch": 0.29040355280942265,
+      "grad_norm": 1.2734375,
+      "learning_rate": 7.318471337579618e-06,
+      "loss": 0.6339,
+      "step": 1410
+    },
+    {
+      "epoch": 0.2924631524747377,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.2972399150743105e-06,
+      "loss": 0.6755,
+      "step": 1420
+    },
+    {
+      "epoch": 0.2945227521400528,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7.276008492569002e-06,
+      "loss": 0.6666,
+      "step": 1430
+    },
+    {
+      "epoch": 0.29658235180536785,
+      "grad_norm": 1.53125,
+      "learning_rate": 7.254777070063695e-06,
+      "loss": 0.6508,
+      "step": 1440
+    },
+    {
+      "epoch": 0.2986419514706829,
+      "grad_norm": 1.5390625,
+      "learning_rate": 7.2335456475583865e-06,
+      "loss": 0.6862,
+      "step": 1450
+    },
+    {
+      "epoch": 0.30070155113599795,
+      "grad_norm": 1.359375,
+      "learning_rate": 7.212314225053078e-06,
+      "loss": 0.6958,
+      "step": 1460
+    },
+    {
+      "epoch": 0.302761150801313,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.191082802547771e-06,
+      "loss": 0.684,
+      "step": 1470
+    },
+    {
+      "epoch": 0.30482075046662804,
+      "grad_norm": 1.6640625,
+      "learning_rate": 7.169851380042463e-06,
+      "loss": 0.6716,
+      "step": 1480
+    },
+    {
+      "epoch": 0.3068803501319431,
+      "grad_norm": 1.5546875,
+      "learning_rate": 7.148619957537155e-06,
+      "loss": 0.6713,
+      "step": 1490
+    },
+    {
+      "epoch": 0.30893994979725814,
+      "grad_norm": 1.75,
+      "learning_rate": 7.127388535031847e-06,
+      "loss": 0.6657,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3109995494625732,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.1061571125265395e-06,
+      "loss": 0.6556,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3130591491278883,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.084925690021231e-06,
+      "loss": 0.6475,
+      "step": 1520
+    },
+    {
+      "epoch": 0.31511874879320334,
+      "grad_norm": 1.4140625,
+      "learning_rate": 7.063694267515924e-06,
+      "loss": 0.6739,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3171783484585184,
+      "grad_norm": 1.359375,
+      "learning_rate": 7.0424628450106156e-06,
+      "loss": 0.6792,
+      "step": 1540
+    },
+    {
+      "epoch": 0.31923794812383344,
+      "grad_norm": 1.40625,
+      "learning_rate": 7.021231422505308e-06,
+      "loss": 0.6637,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3212975477891485,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7e-06,
+      "loss": 0.6658,
+      "step": 1560
+    },
+    {
+      "epoch": 0.32335714745446353,
+      "grad_norm": 1.359375,
+      "learning_rate": 6.9787685774946925e-06,
+      "loss": 0.6189,
+      "step": 1570
+    },
+    {
+      "epoch": 0.3254167471197786,
+      "grad_norm": 1.640625,
+      "learning_rate": 6.957537154989384e-06,
+      "loss": 0.6709,
+      "step": 1580
+    },
+    {
+      "epoch": 0.32747634678509363,
+      "grad_norm": 1.4609375,
+      "learning_rate": 6.936305732484077e-06,
+      "loss": 0.688,
+      "step": 1590
+    },
+    {
+      "epoch": 0.3295359464504087,
+      "grad_norm": 1.515625,
+      "learning_rate": 6.9150743099787685e-06,
+      "loss": 0.6961,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3315955461157238,
+      "grad_norm": 1.578125,
+      "learning_rate": 6.893842887473461e-06,
+      "loss": 0.654,
+      "step": 1610
+    },
+    {
+      "epoch": 0.33365514578103883,
+      "grad_norm": 1.4453125,
+      "learning_rate": 6.872611464968153e-06,
+      "loss": 0.6655,
+      "step": 1620
+    },
+    {
+      "epoch": 0.3357147454463539,
+      "grad_norm": 1.546875,
+      "learning_rate": 6.8513800424628455e-06,
+      "loss": 0.6588,
+      "step": 1630
+    },
+    {
+      "epoch": 0.3377743451116689,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.830148619957537e-06,
+      "loss": 0.6371,
+      "step": 1640
+    },
+    {
+      "epoch": 0.339833944776984,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.80891719745223e-06,
+      "loss": 0.6723,
+      "step": 1650
+    },
+    {
+      "epoch": 0.341893544442299,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.7876857749469215e-06,
+      "loss": 0.6809,
+      "step": 1660
+    },
+    {
+      "epoch": 0.3439531441076141,
+      "grad_norm": 1.296875,
+      "learning_rate": 6.766454352441614e-06,
+      "loss": 0.6593,
+      "step": 1670
+    },
+    {
+      "epoch": 0.3460127437729291,
+      "grad_norm": 1.34375,
+      "learning_rate": 6.745222929936306e-06,
+      "loss": 0.6804,
+      "step": 1680
+    },
+    {
+      "epoch": 0.34807234343824417,
+      "grad_norm": 1.4296875,
+      "learning_rate": 6.7239915074309984e-06,
+      "loss": 0.6631,
+      "step": 1690
+    },
+    {
+      "epoch": 0.3501319431035593,
+      "grad_norm": 1.5859375,
+      "learning_rate": 6.70276008492569e-06,
+      "loss": 0.7134,
+      "step": 1700
+    },
+    {
+      "epoch": 0.3521915427688743,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.681528662420382e-06,
+      "loss": 0.6879,
+      "step": 1710
+    },
+    {
+      "epoch": 0.35425114243418937,
+      "grad_norm": 1.5,
+      "learning_rate": 6.6602972399150745e-06,
+      "loss": 0.6816,
+      "step": 1720
+    },
+    {
+      "epoch": 0.3563107420995044,
+      "grad_norm": 1.5859375,
+      "learning_rate": 6.639065817409766e-06,
+      "loss": 0.6591,
+      "step": 1730
+    },
+    {
+      "epoch": 0.35837034176481947,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.617834394904459e-06,
+      "loss": 0.6874,
+      "step": 1740
+    },
+    {
+      "epoch": 0.3604299414301345,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.5966029723991506e-06,
+      "loss": 0.6514,
+      "step": 1750
+    },
+    {
+      "epoch": 0.36248954109544956,
+      "grad_norm": 1.515625,
+      "learning_rate": 6.575371549893843e-06,
+      "loss": 0.6424,
+      "step": 1760
+    },
+    {
+      "epoch": 0.3645491407607646,
+      "grad_norm": 1.34375,
+      "learning_rate": 6.554140127388535e-06,
+      "loss": 0.6266,
+      "step": 1770
+    },
+    {
+      "epoch": 0.36660874042607966,
+      "grad_norm": 1.484375,
+      "learning_rate": 6.5329087048832275e-06,
+      "loss": 0.6608,
+      "step": 1780
+    },
+    {
+      "epoch": 0.3686683400913947,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.511677282377919e-06,
+      "loss": 0.6556,
+      "step": 1790
+    },
+    {
+      "epoch": 0.3707279397567098,
+      "grad_norm": 1.546875,
+      "learning_rate": 6.490445859872612e-06,
+      "loss": 0.6635,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.611802348040192e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2.5_full_sft/checkpoint-1800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3f2d9cedae7b7a6948879545ee242f546eeea69378ead1818fa3ffdc8adefc
+size 5841

qwen2.5_full_sft/checkpoint-1900/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
+}

qwen2.5_full_sft/checkpoint-1900/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2.5_full_sft/checkpoint-1900/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen2.5_full_sft/checkpoint-1900/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.3"
+}

qwen2.5_full_sft/checkpoint-1900/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc9fb52fba83255c7a6a0036f882b542741c513f7f806964c8e88f284abf31ee
+size 3087467144

qwen2.5_full_sft/checkpoint-1900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee92d2bc55a9d3471c2e045fc87897861d063f556d6f15c4d4d806826e62bc0c
+size 4529806751

qwen2.5_full_sft/checkpoint-1900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

qwen2.5_full_sft/checkpoint-1900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3caf84d473e9b3a883287b46cdcff87de7f9a21586cc11198f6a301f922a7a25
+size 1465

qwen2.5_full_sft/checkpoint-1900/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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

qwen2.5_full_sft/checkpoint-1900/tokenizer.json

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

qwen2.5_full_sft/checkpoint-1900/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2.5_full_sft/checkpoint-1900/trainer_state.json

@@ -0,0 +1,1364 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.39132393640986035,
+  "eval_steps": 500,
+  "global_step": 1900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0020595996653150544,
+      "grad_norm": 3.171875,
+      "learning_rate": 6.164383561643836e-07,
+      "loss": 0.9341,
+      "step": 10
+    },
+    {
+      "epoch": 0.004119199330630109,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.3013698630136986e-06,
+      "loss": 0.8822,
+      "step": 20
+    },
+    {
+      "epoch": 0.006178798995945163,
+      "grad_norm": 2.625,
+      "learning_rate": 1.9863013698630136e-06,
+      "loss": 0.9008,
+      "step": 30
+    },
+    {
+      "epoch": 0.008238398661260218,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.671232876712329e-06,
+      "loss": 0.8337,
+      "step": 40
+    },
+    {
+      "epoch": 0.010297998326575271,
+      "grad_norm": 2.21875,
+      "learning_rate": 3.356164383561644e-06,
+      "loss": 0.8392,
+      "step": 50
+    },
+    {
+      "epoch": 0.012357597991890326,
+      "grad_norm": 1.8046875,
+      "learning_rate": 4.0410958904109595e-06,
+      "loss": 0.8572,
+      "step": 60
+    },
+    {
+      "epoch": 0.01441719765720538,
+      "grad_norm": 1.9375,
+      "learning_rate": 4.726027397260274e-06,
+      "loss": 0.8535,
+      "step": 70
+    },
+    {
+      "epoch": 0.016476797322520435,
+      "grad_norm": 1.453125,
+      "learning_rate": 5.41095890410959e-06,
+      "loss": 0.8643,
+      "step": 80
+    },
+    {
+      "epoch": 0.01853639698783549,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.095890410958905e-06,
+      "loss": 0.8333,
+      "step": 90
+    },
+    {
+      "epoch": 0.020595996653150542,
+      "grad_norm": 1.265625,
+      "learning_rate": 6.78082191780822e-06,
+      "loss": 0.7985,
+      "step": 100
+    },
+    {
+      "epoch": 0.022655596318465598,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.465753424657535e-06,
+      "loss": 0.8222,
+      "step": 110
+    },
+    {
+      "epoch": 0.024715195983780653,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.150684931506851e-06,
+      "loss": 0.7686,
+      "step": 120
+    },
+    {
+      "epoch": 0.02677479564909571,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.835616438356165e-06,
+      "loss": 0.8005,
+      "step": 130
+    },
+    {
+      "epoch": 0.02883439531441076,
+      "grad_norm": 1.203125,
+      "learning_rate": 9.52054794520548e-06,
+      "loss": 0.7832,
+      "step": 140
+    },
+    {
+      "epoch": 0.030893994979725815,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.993630573248408e-06,
+      "loss": 0.7758,
+      "step": 150
+    },
+    {
+      "epoch": 0.03295359464504087,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.972399150743101e-06,
+      "loss": 0.7042,
+      "step": 160
+    },
+    {
+      "epoch": 0.035013194310355926,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.951167728237793e-06,
+      "loss": 0.7154,
+      "step": 170
+    },
+    {
+      "epoch": 0.03707279397567098,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.929936305732485e-06,
+      "loss": 0.744,
+      "step": 180
+    },
+    {
+      "epoch": 0.039132393640986037,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.908704883227176e-06,
+      "loss": 0.7538,
+      "step": 190
+    },
+    {
+      "epoch": 0.041191993306301085,
+      "grad_norm": 1.4140625,
+      "learning_rate": 9.88747346072187e-06,
+      "loss": 0.7344,
+      "step": 200
+    },
+    {
+      "epoch": 0.04325159297161614,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.866242038216562e-06,
+      "loss": 0.7408,
+      "step": 210
+    },
+    {
+      "epoch": 0.045311192636931195,
+      "grad_norm": 2.125,
+      "learning_rate": 9.845010615711253e-06,
+      "loss": 0.7133,
+      "step": 220
+    },
+    {
+      "epoch": 0.04737079230224625,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.823779193205945e-06,
+      "loss": 0.7584,
+      "step": 230
+    },
+    {
+      "epoch": 0.049430391967561306,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.802547770700639e-06,
+      "loss": 0.7208,
+      "step": 240
+    },
+    {
+      "epoch": 0.05148999163287636,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.78131634819533e-06,
+      "loss": 0.7483,
+      "step": 250
+    },
+    {
+      "epoch": 0.05354959129819142,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.760084925690022e-06,
+      "loss": 0.7419,
+      "step": 260
+    },
+    {
+      "epoch": 0.05560919096350647,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.738853503184714e-06,
+      "loss": 0.69,
+      "step": 270
+    },
+    {
+      "epoch": 0.05766879062882152,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.717622080679406e-06,
+      "loss": 0.6888,
+      "step": 280
+    },
+    {
+      "epoch": 0.059728390294136575,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.696390658174099e-06,
+      "loss": 0.7139,
+      "step": 290
+    },
+    {
+      "epoch": 0.06178798995945163,
+      "grad_norm": 1.3515625,
+      "learning_rate": 9.67515923566879e-06,
+      "loss": 0.7062,
+      "step": 300
+    },
+    {
+      "epoch": 0.06384758962476668,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.653927813163482e-06,
+      "loss": 0.7225,
+      "step": 310
+    },
+    {
+      "epoch": 0.06590718929008174,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.632696390658174e-06,
+      "loss": 0.7428,
+      "step": 320
+    },
+    {
+      "epoch": 0.06796678895539679,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.611464968152868e-06,
+      "loss": 0.6763,
+      "step": 330
+    },
+    {
+      "epoch": 0.07002638862071185,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.59023354564756e-06,
+      "loss": 0.6758,
+      "step": 340
+    },
+    {
+      "epoch": 0.0720859882860269,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.569002123142251e-06,
+      "loss": 0.7067,
+      "step": 350
+    },
+    {
+      "epoch": 0.07414558795134196,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.547770700636943e-06,
+      "loss": 0.7329,
+      "step": 360
+    },
+    {
+      "epoch": 0.07620518761665701,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.526539278131636e-06,
+      "loss": 0.7396,
+      "step": 370
+    },
+    {
+      "epoch": 0.07826478728197207,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.505307855626328e-06,
+      "loss": 0.7596,
+      "step": 380
+    },
+    {
+      "epoch": 0.08032438694728712,
+      "grad_norm": 1.375,
+      "learning_rate": 9.48407643312102e-06,
+      "loss": 0.7073,
+      "step": 390
+    },
+    {
+      "epoch": 0.08238398661260217,
+      "grad_norm": 1.984375,
+      "learning_rate": 9.462845010615711e-06,
+      "loss": 0.7241,
+      "step": 400
+    },
+    {
+      "epoch": 0.08444358627791723,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.441613588110405e-06,
+      "loss": 0.7105,
+      "step": 410
+    },
+    {
+      "epoch": 0.08650318594323228,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.420382165605097e-06,
+      "loss": 0.6821,
+      "step": 420
+    },
+    {
+      "epoch": 0.08856278560854734,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.399150743099788e-06,
+      "loss": 0.7379,
+      "step": 430
+    },
+    {
+      "epoch": 0.09062238527386239,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.37791932059448e-06,
+      "loss": 0.6849,
+      "step": 440
+    },
+    {
+      "epoch": 0.09268198493917745,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.356687898089174e-06,
+      "loss": 0.6898,
+      "step": 450
+    },
+    {
+      "epoch": 0.0947415846044925,
+      "grad_norm": 1.9453125,
+      "learning_rate": 9.335456475583865e-06,
+      "loss": 0.6911,
+      "step": 460
+    },
+    {
+      "epoch": 0.09680118426980755,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.314225053078557e-06,
+      "loss": 0.7164,
+      "step": 470
+    },
+    {
+      "epoch": 0.09886078393512261,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.292993630573249e-06,
+      "loss": 0.6855,
+      "step": 480
+    },
+    {
+      "epoch": 0.10092038360043766,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.271762208067942e-06,
+      "loss": 0.7093,
+      "step": 490
+    },
+    {
+      "epoch": 0.10297998326575272,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.250530785562634e-06,
+      "loss": 0.6891,
+      "step": 500
+    },
+    {
+      "epoch": 0.10503958293106777,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.229299363057326e-06,
+      "loss": 0.6962,
+      "step": 510
+    },
+    {
+      "epoch": 0.10709918259638283,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.208067940552017e-06,
+      "loss": 0.7039,
+      "step": 520
+    },
+    {
+      "epoch": 0.10915878226169788,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.186836518046711e-06,
+      "loss": 0.6919,
+      "step": 530
+    },
+    {
+      "epoch": 0.11121838192701294,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.165605095541403e-06,
+      "loss": 0.6784,
+      "step": 540
+    },
+    {
+      "epoch": 0.11327798159232799,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.144373673036094e-06,
+      "loss": 0.69,
+      "step": 550
+    },
+    {
+      "epoch": 0.11533758125764304,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.123142250530786e-06,
+      "loss": 0.7122,
+      "step": 560
+    },
+    {
+      "epoch": 0.1173971809229581,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.101910828025478e-06,
+      "loss": 0.7057,
+      "step": 570
+    },
+    {
+      "epoch": 0.11945678058827315,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.080679405520171e-06,
+      "loss": 0.6727,
+      "step": 580
+    },
+    {
+      "epoch": 0.12151638025358821,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.059447983014863e-06,
+      "loss": 0.6828,
+      "step": 590
+    },
+    {
+      "epoch": 0.12357597991890326,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.038216560509555e-06,
+      "loss": 0.7218,
+      "step": 600
+    },
+    {
+      "epoch": 0.1256355795842183,
+      "grad_norm": 1.171875,
+      "learning_rate": 9.016985138004246e-06,
+      "loss": 0.6701,
+      "step": 610
+    },
+    {
+      "epoch": 0.12769517924953336,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.99575371549894e-06,
+      "loss": 0.7289,
+      "step": 620
+    },
+    {
+      "epoch": 0.12975477891484843,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.974522292993632e-06,
+      "loss": 0.6545,
+      "step": 630
+    },
+    {
+      "epoch": 0.13181437858016348,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.953290870488323e-06,
+      "loss": 0.6697,
+      "step": 640
+    },
+    {
+      "epoch": 0.13387397824547853,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.932059447983015e-06,
+      "loss": 0.6964,
+      "step": 650
+    },
+    {
+      "epoch": 0.13593357791079358,
+      "grad_norm": 1.6328125,
+      "learning_rate": 8.910828025477709e-06,
+      "loss": 0.7249,
+      "step": 660
+    },
+    {
+      "epoch": 0.13799317757610866,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.8895966029724e-06,
+      "loss": 0.6914,
+      "step": 670
+    },
+    {
+      "epoch": 0.1400527772414237,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.868365180467092e-06,
+      "loss": 0.7196,
+      "step": 680
+    },
+    {
+      "epoch": 0.14211237690673875,
+      "grad_norm": 1.5,
+      "learning_rate": 8.847133757961784e-06,
+      "loss": 0.6761,
+      "step": 690
+    },
+    {
+      "epoch": 0.1441719765720538,
+      "grad_norm": 1.734375,
+      "learning_rate": 8.825902335456477e-06,
+      "loss": 0.6784,
+      "step": 700
+    },
+    {
+      "epoch": 0.14623157623736885,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.804670912951169e-06,
+      "loss": 0.7393,
+      "step": 710
+    },
+    {
+      "epoch": 0.14829117590268392,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.78343949044586e-06,
+      "loss": 0.6897,
+      "step": 720
+    },
+    {
+      "epoch": 0.15035077556799897,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.762208067940552e-06,
+      "loss": 0.6699,
+      "step": 730
+    },
+    {
+      "epoch": 0.15241037523331402,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.740976645435246e-06,
+      "loss": 0.6873,
+      "step": 740
+    },
+    {
+      "epoch": 0.15446997489862907,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.719745222929938e-06,
+      "loss": 0.661,
+      "step": 750
+    },
+    {
+      "epoch": 0.15652957456394415,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.69851380042463e-06,
+      "loss": 0.6918,
+      "step": 760
+    },
+    {
+      "epoch": 0.1585891742292592,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.677282377919321e-06,
+      "loss": 0.69,
+      "step": 770
+    },
+    {
+      "epoch": 0.16064877389457424,
+      "grad_norm": 1.375,
+      "learning_rate": 8.656050955414015e-06,
+      "loss": 0.7571,
+      "step": 780
+    },
+    {
+      "epoch": 0.1627083735598893,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.634819532908706e-06,
+      "loss": 0.7193,
+      "step": 790
+    },
+    {
+      "epoch": 0.16476797322520434,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.613588110403398e-06,
+      "loss": 0.6783,
+      "step": 800
+    },
+    {
+      "epoch": 0.16682757289051942,
+      "grad_norm": 1.375,
+      "learning_rate": 8.59235668789809e-06,
+      "loss": 0.6807,
+      "step": 810
+    },
+    {
+      "epoch": 0.16888717255583446,
+      "grad_norm": 1.2578125,
+      "learning_rate": 8.571125265392782e-06,
+      "loss": 0.6597,
+      "step": 820
+    },
+    {
+      "epoch": 0.1709467722211495,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.549893842887475e-06,
+      "loss": 0.691,
+      "step": 830
+    },
+    {
+      "epoch": 0.17300637188646456,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.528662420382167e-06,
+      "loss": 0.6266,
+      "step": 840
+    },
+    {
+      "epoch": 0.17506597155177964,
+      "grad_norm": 1.578125,
+      "learning_rate": 8.507430997876858e-06,
+      "loss": 0.7104,
+      "step": 850
+    },
+    {
+      "epoch": 0.17712557121709468,
+      "grad_norm": 1.8359375,
+      "learning_rate": 8.48619957537155e-06,
+      "loss": 0.7417,
+      "step": 860
+    },
+    {
+      "epoch": 0.17918517088240973,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.464968152866244e-06,
+      "loss": 0.6707,
+      "step": 870
+    },
+    {
+      "epoch": 0.18124477054772478,
+      "grad_norm": 1.75,
+      "learning_rate": 8.443736730360935e-06,
+      "loss": 0.6776,
+      "step": 880
+    },
+    {
+      "epoch": 0.18330437021303983,
+      "grad_norm": 1.3125,
+      "learning_rate": 8.422505307855627e-06,
+      "loss": 0.6576,
+      "step": 890
+    },
+    {
+      "epoch": 0.1853639698783549,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.401273885350319e-06,
+      "loss": 0.6838,
+      "step": 900
+    },
+    {
+      "epoch": 0.18742356954366995,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.380042462845012e-06,
+      "loss": 0.6616,
+      "step": 910
+    },
+    {
+      "epoch": 0.189483169208985,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.358811040339704e-06,
+      "loss": 0.6868,
+      "step": 920
+    },
+    {
+      "epoch": 0.19154276887430005,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.337579617834396e-06,
+      "loss": 0.667,
+      "step": 930
+    },
+    {
+      "epoch": 0.1936023685396151,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.316348195329087e-06,
+      "loss": 0.6805,
+      "step": 940
+    },
+    {
+      "epoch": 0.19566196820493018,
+      "grad_norm": 1.25,
+      "learning_rate": 8.295116772823781e-06,
+      "loss": 0.6723,
+      "step": 950
+    },
+    {
+      "epoch": 0.19772156787024522,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.273885350318473e-06,
+      "loss": 0.6739,
+      "step": 960
+    },
+    {
+      "epoch": 0.19978116753556027,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.252653927813164e-06,
+      "loss": 0.7014,
+      "step": 970
+    },
+    {
+      "epoch": 0.20184076720087532,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.231422505307856e-06,
+      "loss": 0.6908,
+      "step": 980
+    },
+    {
+      "epoch": 0.2039003668661904,
+      "grad_norm": 1.328125,
+      "learning_rate": 8.21019108280255e-06,
+      "loss": 0.6582,
+      "step": 990
+    },
+    {
+      "epoch": 0.20595996653150545,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.188959660297241e-06,
+      "loss": 0.6619,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2080195661968205,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.167728237791933e-06,
+      "loss": 0.6798,
+      "step": 1010
+    },
+    {
+      "epoch": 0.21007916586213554,
+      "grad_norm": 1.34375,
+      "learning_rate": 8.146496815286625e-06,
+      "loss": 0.6565,
+      "step": 1020
+    },
+    {
+      "epoch": 0.2121387655274506,
+      "grad_norm": 1.625,
+      "learning_rate": 8.125265392781318e-06,
+      "loss": 0.7176,
+      "step": 1030
+    },
+    {
+      "epoch": 0.21419836519276567,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.10403397027601e-06,
+      "loss": 0.6692,
+      "step": 1040
+    },
+    {
+      "epoch": 0.21625796485808071,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.082802547770702e-06,
+      "loss": 0.675,
+      "step": 1050
+    },
+    {
+      "epoch": 0.21831756452339576,
+      "grad_norm": 1.375,
+      "learning_rate": 8.061571125265393e-06,
+      "loss": 0.6989,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2203771641887108,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.040339702760087e-06,
+      "loss": 0.7133,
+      "step": 1070
+    },
+    {
+      "epoch": 0.2224367638540259,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.019108280254779e-06,
+      "loss": 0.7272,
+      "step": 1080
+    },
+    {
+      "epoch": 0.22449636351934094,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.99787685774947e-06,
+      "loss": 0.6684,
+      "step": 1090
+    },
+    {
+      "epoch": 0.22655596318465598,
+      "grad_norm": 1.328125,
+      "learning_rate": 7.976645435244162e-06,
+      "loss": 0.6895,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22861556284997103,
+      "grad_norm": 1.5078125,
+      "learning_rate": 7.955414012738854e-06,
+      "loss": 0.6859,
+      "step": 1110
+    },
+    {
+      "epoch": 0.23067516251528608,
+      "grad_norm": 1.6953125,
+      "learning_rate": 7.934182590233547e-06,
+      "loss": 0.723,
+      "step": 1120
+    },
+    {
+      "epoch": 0.23273476218060116,
+      "grad_norm": 1.265625,
+      "learning_rate": 7.912951167728239e-06,
+      "loss": 0.6883,
+      "step": 1130
+    },
+    {
+      "epoch": 0.2347943618459162,
+      "grad_norm": 1.390625,
+      "learning_rate": 7.89171974522293e-06,
+      "loss": 0.6653,
+      "step": 1140
+    },
+    {
+      "epoch": 0.23685396151123125,
+      "grad_norm": 1.6015625,
+      "learning_rate": 7.870488322717622e-06,
+      "loss": 0.7101,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2389135611765463,
+      "grad_norm": 1.4765625,
+      "learning_rate": 7.849256900212316e-06,
+      "loss": 0.6775,
+      "step": 1160
+    },
+    {
+      "epoch": 0.24097316084186135,
+      "grad_norm": 1.421875,
+      "learning_rate": 7.828025477707008e-06,
+      "loss": 0.651,
+      "step": 1170
+    },
+    {
+      "epoch": 0.24303276050717643,
+      "grad_norm": 1.34375,
+      "learning_rate": 7.8067940552017e-06,
+      "loss": 0.6951,
+      "step": 1180
+    },
+    {
+      "epoch": 0.24509236017249147,
+      "grad_norm": 1.59375,
+      "learning_rate": 7.785562632696391e-06,
+      "loss": 0.6685,
+      "step": 1190
+    },
+    {
+      "epoch": 0.24715195983780652,
+      "grad_norm": 1.625,
+      "learning_rate": 7.764331210191085e-06,
+      "loss": 0.7213,
+      "step": 1200
+    },
+    {
+      "epoch": 0.24921155950312157,
+      "grad_norm": 1.3671875,
+      "learning_rate": 7.743099787685776e-06,
+      "loss": 0.6925,
+      "step": 1210
+    },
+    {
+      "epoch": 0.2512711591684366,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.721868365180468e-06,
+      "loss": 0.6676,
+      "step": 1220
+    },
+    {
+      "epoch": 0.25333075883375167,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.70063694267516e-06,
+      "loss": 0.7241,
+      "step": 1230
+    },
+    {
+      "epoch": 0.2553903584990667,
+      "grad_norm": 1.3125,
+      "learning_rate": 7.679405520169853e-06,
+      "loss": 0.6648,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2574499581643818,
+      "grad_norm": 1.3359375,
+      "learning_rate": 7.658174097664545e-06,
+      "loss": 0.6936,
+      "step": 1250
+    },
+    {
+      "epoch": 0.25950955782969687,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.636942675159237e-06,
+      "loss": 0.6615,
+      "step": 1260
+    },
+    {
+      "epoch": 0.2615691574950119,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.615711252653929e-06,
+      "loss": 0.694,
+      "step": 1270
+    },
+    {
+      "epoch": 0.26362875716032697,
+      "grad_norm": 1.703125,
+      "learning_rate": 7.594479830148621e-06,
+      "loss": 0.721,
+      "step": 1280
+    },
+    {
+      "epoch": 0.265688356825642,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.573248407643314e-06,
+      "loss": 0.6581,
+      "step": 1290
+    },
+    {
+      "epoch": 0.26774795649095706,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.552016985138005e-06,
+      "loss": 0.6855,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2698075561562721,
+      "grad_norm": 1.5,
+      "learning_rate": 7.530785562632698e-06,
+      "loss": 0.6606,
+      "step": 1310
+    },
+    {
+      "epoch": 0.27186715582158716,
+      "grad_norm": 1.609375,
+      "learning_rate": 7.50955414012739e-06,
+      "loss": 0.6695,
+      "step": 1320
+    },
+    {
+      "epoch": 0.2739267554869022,
+      "grad_norm": 1.2265625,
+      "learning_rate": 7.4883227176220806e-06,
+      "loss": 0.6577,
+      "step": 1330
+    },
+    {
+      "epoch": 0.2759863551522173,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.467091295116773e-06,
+      "loss": 0.6765,
+      "step": 1340
+    },
+    {
+      "epoch": 0.27804595481753236,
+      "grad_norm": 1.359375,
+      "learning_rate": 7.445859872611465e-06,
+      "loss": 0.6688,
+      "step": 1350
+    },
+    {
+      "epoch": 0.2801055544828474,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.4246284501061575e-06,
+      "loss": 0.6831,
+      "step": 1360
+    },
+    {
+      "epoch": 0.28216515414816246,
+      "grad_norm": 1.3359375,
+      "learning_rate": 7.403397027600849e-06,
+      "loss": 0.6893,
+      "step": 1370
+    },
+    {
+      "epoch": 0.2842247538134775,
+      "grad_norm": 1.890625,
+      "learning_rate": 7.382165605095542e-06,
+      "loss": 0.7225,
+      "step": 1380
+    },
+    {
+      "epoch": 0.28628435347879255,
+      "grad_norm": 1.546875,
+      "learning_rate": 7.3609341825902335e-06,
+      "loss": 0.6909,
+      "step": 1390
+    },
+    {
+      "epoch": 0.2883439531441076,
+      "grad_norm": 1.6328125,
+      "learning_rate": 7.339702760084926e-06,
+      "loss": 0.6611,
+      "step": 1400
+    },
+    {
+      "epoch": 0.29040355280942265,
+      "grad_norm": 1.2734375,
+      "learning_rate": 7.318471337579618e-06,
+      "loss": 0.6339,
+      "step": 1410
+    },
+    {
+      "epoch": 0.2924631524747377,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.2972399150743105e-06,
+      "loss": 0.6755,
+      "step": 1420
+    },
+    {
+      "epoch": 0.2945227521400528,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7.276008492569002e-06,
+      "loss": 0.6666,
+      "step": 1430
+    },
+    {
+      "epoch": 0.29658235180536785,
+      "grad_norm": 1.53125,
+      "learning_rate": 7.254777070063695e-06,
+      "loss": 0.6508,
+      "step": 1440
+    },
+    {
+      "epoch": 0.2986419514706829,
+      "grad_norm": 1.5390625,
+      "learning_rate": 7.2335456475583865e-06,
+      "loss": 0.6862,
+      "step": 1450
+    },
+    {
+      "epoch": 0.30070155113599795,
+      "grad_norm": 1.359375,
+      "learning_rate": 7.212314225053078e-06,
+      "loss": 0.6958,
+      "step": 1460
+    },
+    {
+      "epoch": 0.302761150801313,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.191082802547771e-06,
+      "loss": 0.684,
+      "step": 1470
+    },
+    {
+      "epoch": 0.30482075046662804,
+      "grad_norm": 1.6640625,
+      "learning_rate": 7.169851380042463e-06,
+      "loss": 0.6716,
+      "step": 1480
+    },
+    {
+      "epoch": 0.3068803501319431,
+      "grad_norm": 1.5546875,
+      "learning_rate": 7.148619957537155e-06,
+      "loss": 0.6713,
+      "step": 1490
+    },
+    {
+      "epoch": 0.30893994979725814,
+      "grad_norm": 1.75,
+      "learning_rate": 7.127388535031847e-06,
+      "loss": 0.6657,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3109995494625732,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.1061571125265395e-06,
+      "loss": 0.6556,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3130591491278883,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.084925690021231e-06,
+      "loss": 0.6475,
+      "step": 1520
+    },
+    {
+      "epoch": 0.31511874879320334,
+      "grad_norm": 1.4140625,
+      "learning_rate": 7.063694267515924e-06,
+      "loss": 0.6739,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3171783484585184,
+      "grad_norm": 1.359375,
+      "learning_rate": 7.0424628450106156e-06,
+      "loss": 0.6792,
+      "step": 1540
+    },
+    {
+      "epoch": 0.31923794812383344,
+      "grad_norm": 1.40625,
+      "learning_rate": 7.021231422505308e-06,
+      "loss": 0.6637,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3212975477891485,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7e-06,
+      "loss": 0.6658,
+      "step": 1560
+    },
+    {
+      "epoch": 0.32335714745446353,
+      "grad_norm": 1.359375,
+      "learning_rate": 6.9787685774946925e-06,
+      "loss": 0.6189,
+      "step": 1570
+    },
+    {
+      "epoch": 0.3254167471197786,
+      "grad_norm": 1.640625,
+      "learning_rate": 6.957537154989384e-06,
+      "loss": 0.6709,
+      "step": 1580
+    },
+    {
+      "epoch": 0.32747634678509363,
+      "grad_norm": 1.4609375,
+      "learning_rate": 6.936305732484077e-06,
+      "loss": 0.688,
+      "step": 1590
+    },
+    {
+      "epoch": 0.3295359464504087,
+      "grad_norm": 1.515625,
+      "learning_rate": 6.9150743099787685e-06,
+      "loss": 0.6961,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3315955461157238,
+      "grad_norm": 1.578125,
+      "learning_rate": 6.893842887473461e-06,
+      "loss": 0.654,
+      "step": 1610
+    },
+    {
+      "epoch": 0.33365514578103883,
+      "grad_norm": 1.4453125,
+      "learning_rate": 6.872611464968153e-06,
+      "loss": 0.6655,
+      "step": 1620
+    },
+    {
+      "epoch": 0.3357147454463539,
+      "grad_norm": 1.546875,
+      "learning_rate": 6.8513800424628455e-06,
+      "loss": 0.6588,
+      "step": 1630
+    },
+    {
+      "epoch": 0.3377743451116689,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.830148619957537e-06,
+      "loss": 0.6371,
+      "step": 1640
+    },
+    {
+      "epoch": 0.339833944776984,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.80891719745223e-06,
+      "loss": 0.6723,
+      "step": 1650
+    },
+    {
+      "epoch": 0.341893544442299,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.7876857749469215e-06,
+      "loss": 0.6809,
+      "step": 1660
+    },
+    {
+      "epoch": 0.3439531441076141,
+      "grad_norm": 1.296875,
+      "learning_rate": 6.766454352441614e-06,
+      "loss": 0.6593,
+      "step": 1670
+    },
+    {
+      "epoch": 0.3460127437729291,
+      "grad_norm": 1.34375,
+      "learning_rate": 6.745222929936306e-06,
+      "loss": 0.6804,
+      "step": 1680
+    },
+    {
+      "epoch": 0.34807234343824417,
+      "grad_norm": 1.4296875,
+      "learning_rate": 6.7239915074309984e-06,
+      "loss": 0.6631,
+      "step": 1690
+    },
+    {
+      "epoch": 0.3501319431035593,
+      "grad_norm": 1.5859375,
+      "learning_rate": 6.70276008492569e-06,
+      "loss": 0.7134,
+      "step": 1700
+    },
+    {
+      "epoch": 0.3521915427688743,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.681528662420382e-06,
+      "loss": 0.6879,
+      "step": 1710
+    },
+    {
+      "epoch": 0.35425114243418937,
+      "grad_norm": 1.5,
+      "learning_rate": 6.6602972399150745e-06,
+      "loss": 0.6816,
+      "step": 1720
+    },
+    {
+      "epoch": 0.3563107420995044,
+      "grad_norm": 1.5859375,
+      "learning_rate": 6.639065817409766e-06,
+      "loss": 0.6591,
+      "step": 1730
+    },
+    {
+      "epoch": 0.35837034176481947,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.617834394904459e-06,
+      "loss": 0.6874,
+      "step": 1740
+    },
+    {
+      "epoch": 0.3604299414301345,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.5966029723991506e-06,
+      "loss": 0.6514,
+      "step": 1750
+    },
+    {
+      "epoch": 0.36248954109544956,
+      "grad_norm": 1.515625,
+      "learning_rate": 6.575371549893843e-06,
+      "loss": 0.6424,
+      "step": 1760
+    },
+    {
+      "epoch": 0.3645491407607646,
+      "grad_norm": 1.34375,
+      "learning_rate": 6.554140127388535e-06,
+      "loss": 0.6266,
+      "step": 1770
+    },
+    {
+      "epoch": 0.36660874042607966,
+      "grad_norm": 1.484375,
+      "learning_rate": 6.5329087048832275e-06,
+      "loss": 0.6608,
+      "step": 1780
+    },
+    {
+      "epoch": 0.3686683400913947,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.511677282377919e-06,
+      "loss": 0.6556,
+      "step": 1790
+    },
+    {
+      "epoch": 0.3707279397567098,
+      "grad_norm": 1.546875,
+      "learning_rate": 6.490445859872612e-06,
+      "loss": 0.6635,
+      "step": 1800
+    },
+    {
+      "epoch": 0.37278753942202486,
+      "grad_norm": 1.6875,
+      "learning_rate": 6.4692144373673036e-06,
+      "loss": 0.6808,
+      "step": 1810
+    },
+    {
+      "epoch": 0.3748471390873399,
+      "grad_norm": 1.546875,
+      "learning_rate": 6.447983014861996e-06,
+      "loss": 0.69,
+      "step": 1820
+    },
+    {
+      "epoch": 0.37690673875265496,
+      "grad_norm": 1.375,
+      "learning_rate": 6.426751592356688e-06,
+      "loss": 0.7151,
+      "step": 1830
+    },
+    {
+      "epoch": 0.37896633841797,
+      "grad_norm": 1.6328125,
+      "learning_rate": 6.4055201698513805e-06,
+      "loss": 0.6897,
+      "step": 1840
+    },
+    {
+      "epoch": 0.38102593808328505,
+      "grad_norm": 1.390625,
+      "learning_rate": 6.384288747346072e-06,
+      "loss": 0.6867,
+      "step": 1850
+    },
+    {
+      "epoch": 0.3830855377486001,
+      "grad_norm": 1.34375,
+      "learning_rate": 6.363057324840765e-06,
+      "loss": 0.6976,
+      "step": 1860
+    },
+    {
+      "epoch": 0.38514513741391515,
+      "grad_norm": 1.3203125,
+      "learning_rate": 6.3418259023354565e-06,
+      "loss": 0.6719,
+      "step": 1870
+    },
+    {
+      "epoch": 0.3872047370792302,
+      "grad_norm": 1.5390625,
+      "learning_rate": 6.320594479830149e-06,
+      "loss": 0.67,
+      "step": 1880
+    },
+    {
+      "epoch": 0.3892643367445453,
+      "grad_norm": 1.625,
+      "learning_rate": 6.299363057324841e-06,
+      "loss": 0.6491,
+      "step": 1890
+    },
+    {
+      "epoch": 0.39132393640986035,
+      "grad_norm": 1.3046875,
+      "learning_rate": 6.2781316348195334e-06,
+      "loss": 0.6766,
+      "step": 1900
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.7572926105638912e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2.5_full_sft/checkpoint-1900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3f2d9cedae7b7a6948879545ee242f546eeea69378ead1818fa3ffdc8adefc
+size 5841

qwen2.5_full_sft/checkpoint-2000/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
+}

qwen2.5_full_sft/checkpoint-2000/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2.5_full_sft/checkpoint-2000/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen2.5_full_sft/checkpoint-2000/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.3"
+}

qwen2.5_full_sft/checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c4c083fd1d173615719fd23f7ee30d83745785d3cd06d632b135223017b8ef
+size 3087467144

qwen2.5_full_sft/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef0e60b9a02eb545f028f607ca36b1b37844be5d79262c7d207ee5639a643c5
+size 4529806751

qwen2.5_full_sft/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

qwen2.5_full_sft/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a73f5b12499aef9b6990640b0574badd8fe8efa1a0847942e43bfd63f17a017
+size 1465

qwen2.5_full_sft/checkpoint-2000/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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

qwen2.5_full_sft/checkpoint-2000/tokenizer.json

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

qwen2.5_full_sft/checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2.5_full_sft/checkpoint-2000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4119199330630109,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0020595996653150544,
+      "grad_norm": 3.171875,
+      "learning_rate": 6.164383561643836e-07,
+      "loss": 0.9341,
+      "step": 10
+    },
+    {
+      "epoch": 0.004119199330630109,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.3013698630136986e-06,
+      "loss": 0.8822,
+      "step": 20
+    },
+    {
+      "epoch": 0.006178798995945163,
+      "grad_norm": 2.625,
+      "learning_rate": 1.9863013698630136e-06,
+      "loss": 0.9008,
+      "step": 30
+    },
+    {
+      "epoch": 0.008238398661260218,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.671232876712329e-06,
+      "loss": 0.8337,
+      "step": 40
+    },
+    {
+      "epoch": 0.010297998326575271,
+      "grad_norm": 2.21875,
+      "learning_rate": 3.356164383561644e-06,
+      "loss": 0.8392,
+      "step": 50
+    },
+    {
+      "epoch": 0.012357597991890326,
+      "grad_norm": 1.8046875,
+      "learning_rate": 4.0410958904109595e-06,
+      "loss": 0.8572,
+      "step": 60
+    },
+    {
+      "epoch": 0.01441719765720538,
+      "grad_norm": 1.9375,
+      "learning_rate": 4.726027397260274e-06,
+      "loss": 0.8535,
+      "step": 70
+    },
+    {
+      "epoch": 0.016476797322520435,
+      "grad_norm": 1.453125,
+      "learning_rate": 5.41095890410959e-06,
+      "loss": 0.8643,
+      "step": 80
+    },
+    {
+      "epoch": 0.01853639698783549,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.095890410958905e-06,
+      "loss": 0.8333,
+      "step": 90
+    },
+    {
+      "epoch": 0.020595996653150542,
+      "grad_norm": 1.265625,
+      "learning_rate": 6.78082191780822e-06,
+      "loss": 0.7985,
+      "step": 100
+    },
+    {
+      "epoch": 0.022655596318465598,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.465753424657535e-06,
+      "loss": 0.8222,
+      "step": 110
+    },
+    {
+      "epoch": 0.024715195983780653,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.150684931506851e-06,
+      "loss": 0.7686,
+      "step": 120
+    },
+    {
+      "epoch": 0.02677479564909571,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.835616438356165e-06,
+      "loss": 0.8005,
+      "step": 130
+    },
+    {
+      "epoch": 0.02883439531441076,
+      "grad_norm": 1.203125,
+      "learning_rate": 9.52054794520548e-06,
+      "loss": 0.7832,
+      "step": 140
+    },
+    {
+      "epoch": 0.030893994979725815,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.993630573248408e-06,
+      "loss": 0.7758,
+      "step": 150
+    },
+    {
+      "epoch": 0.03295359464504087,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.972399150743101e-06,
+      "loss": 0.7042,
+      "step": 160
+    },
+    {
+      "epoch": 0.035013194310355926,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.951167728237793e-06,
+      "loss": 0.7154,
+      "step": 170
+    },
+    {
+      "epoch": 0.03707279397567098,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.929936305732485e-06,
+      "loss": 0.744,
+      "step": 180
+    },
+    {
+      "epoch": 0.039132393640986037,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.908704883227176e-06,
+      "loss": 0.7538,
+      "step": 190
+    },
+    {
+      "epoch": 0.041191993306301085,
+      "grad_norm": 1.4140625,
+      "learning_rate": 9.88747346072187e-06,
+      "loss": 0.7344,
+      "step": 200
+    },
+    {
+      "epoch": 0.04325159297161614,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.866242038216562e-06,
+      "loss": 0.7408,
+      "step": 210
+    },
+    {
+      "epoch": 0.045311192636931195,
+      "grad_norm": 2.125,
+      "learning_rate": 9.845010615711253e-06,
+      "loss": 0.7133,
+      "step": 220
+    },
+    {
+      "epoch": 0.04737079230224625,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.823779193205945e-06,
+      "loss": 0.7584,
+      "step": 230
+    },
+    {
+      "epoch": 0.049430391967561306,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.802547770700639e-06,
+      "loss": 0.7208,
+      "step": 240
+    },
+    {
+      "epoch": 0.05148999163287636,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.78131634819533e-06,
+      "loss": 0.7483,
+      "step": 250
+    },
+    {
+      "epoch": 0.05354959129819142,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.760084925690022e-06,
+      "loss": 0.7419,
+      "step": 260
+    },
+    {
+      "epoch": 0.05560919096350647,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.738853503184714e-06,
+      "loss": 0.69,
+      "step": 270
+    },
+    {
+      "epoch": 0.05766879062882152,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.717622080679406e-06,
+      "loss": 0.6888,
+      "step": 280
+    },
+    {
+      "epoch": 0.059728390294136575,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.696390658174099e-06,
+      "loss": 0.7139,
+      "step": 290
+    },
+    {
+      "epoch": 0.06178798995945163,
+      "grad_norm": 1.3515625,
+      "learning_rate": 9.67515923566879e-06,
+      "loss": 0.7062,
+      "step": 300
+    },
+    {
+      "epoch": 0.06384758962476668,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.653927813163482e-06,
+      "loss": 0.7225,
+      "step": 310
+    },
+    {
+      "epoch": 0.06590718929008174,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.632696390658174e-06,
+      "loss": 0.7428,
+      "step": 320
+    },
+    {
+      "epoch": 0.06796678895539679,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.611464968152868e-06,
+      "loss": 0.6763,
+      "step": 330
+    },
+    {
+      "epoch": 0.07002638862071185,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.59023354564756e-06,
+      "loss": 0.6758,
+      "step": 340
+    },
+    {
+      "epoch": 0.0720859882860269,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.569002123142251e-06,
+      "loss": 0.7067,
+      "step": 350
+    },
+    {
+      "epoch": 0.07414558795134196,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.547770700636943e-06,
+      "loss": 0.7329,
+      "step": 360
+    },
+    {
+      "epoch": 0.07620518761665701,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.526539278131636e-06,
+      "loss": 0.7396,
+      "step": 370
+    },
+    {
+      "epoch": 0.07826478728197207,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.505307855626328e-06,
+      "loss": 0.7596,
+      "step": 380
+    },
+    {
+      "epoch": 0.08032438694728712,
+      "grad_norm": 1.375,
+      "learning_rate": 9.48407643312102e-06,
+      "loss": 0.7073,
+      "step": 390
+    },
+    {
+      "epoch": 0.08238398661260217,
+      "grad_norm": 1.984375,
+      "learning_rate": 9.462845010615711e-06,
+      "loss": 0.7241,
+      "step": 400
+    },
+    {
+      "epoch": 0.08444358627791723,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.441613588110405e-06,
+      "loss": 0.7105,
+      "step": 410
+    },
+    {
+      "epoch": 0.08650318594323228,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.420382165605097e-06,
+      "loss": 0.6821,
+      "step": 420
+    },
+    {
+      "epoch": 0.08856278560854734,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.399150743099788e-06,
+      "loss": 0.7379,
+      "step": 430
+    },
+    {
+      "epoch": 0.09062238527386239,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.37791932059448e-06,
+      "loss": 0.6849,
+      "step": 440
+    },
+    {
+      "epoch": 0.09268198493917745,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.356687898089174e-06,
+      "loss": 0.6898,
+      "step": 450
+    },
+    {
+      "epoch": 0.0947415846044925,
+      "grad_norm": 1.9453125,
+      "learning_rate": 9.335456475583865e-06,
+      "loss": 0.6911,
+      "step": 460
+    },
+    {
+      "epoch": 0.09680118426980755,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.314225053078557e-06,
+      "loss": 0.7164,
+      "step": 470
+    },
+    {
+      "epoch": 0.09886078393512261,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.292993630573249e-06,
+      "loss": 0.6855,
+      "step": 480
+    },
+    {
+      "epoch": 0.10092038360043766,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.271762208067942e-06,
+      "loss": 0.7093,
+      "step": 490
+    },
+    {
+      "epoch": 0.10297998326575272,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.250530785562634e-06,
+      "loss": 0.6891,
+      "step": 500
+    },
+    {
+      "epoch": 0.10503958293106777,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.229299363057326e-06,
+      "loss": 0.6962,
+      "step": 510
+    },
+    {
+      "epoch": 0.10709918259638283,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.208067940552017e-06,
+      "loss": 0.7039,
+      "step": 520
+    },
+    {
+      "epoch": 0.10915878226169788,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.186836518046711e-06,
+      "loss": 0.6919,
+      "step": 530
+    },
+    {
+      "epoch": 0.11121838192701294,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.165605095541403e-06,
+      "loss": 0.6784,
+      "step": 540
+    },
+    {
+      "epoch": 0.11327798159232799,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.144373673036094e-06,
+      "loss": 0.69,
+      "step": 550
+    },
+    {
+      "epoch": 0.11533758125764304,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.123142250530786e-06,
+      "loss": 0.7122,
+      "step": 560
+    },
+    {
+      "epoch": 0.1173971809229581,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.101910828025478e-06,
+      "loss": 0.7057,
+      "step": 570
+    },
+    {
+      "epoch": 0.11945678058827315,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.080679405520171e-06,
+      "loss": 0.6727,
+      "step": 580
+    },
+    {
+      "epoch": 0.12151638025358821,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.059447983014863e-06,
+      "loss": 0.6828,
+      "step": 590
+    },
+    {
+      "epoch": 0.12357597991890326,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.038216560509555e-06,
+      "loss": 0.7218,
+      "step": 600
+    },
+    {
+      "epoch": 0.1256355795842183,
+      "grad_norm": 1.171875,
+      "learning_rate": 9.016985138004246e-06,
+      "loss": 0.6701,
+      "step": 610
+    },
+    {
+      "epoch": 0.12769517924953336,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.99575371549894e-06,
+      "loss": 0.7289,
+      "step": 620
+    },
+    {
+      "epoch": 0.12975477891484843,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.974522292993632e-06,
+      "loss": 0.6545,
+      "step": 630
+    },
+    {
+      "epoch": 0.13181437858016348,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.953290870488323e-06,
+      "loss": 0.6697,
+      "step": 640
+    },
+    {
+      "epoch": 0.13387397824547853,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.932059447983015e-06,
+      "loss": 0.6964,
+      "step": 650
+    },
+    {
+      "epoch": 0.13593357791079358,
+      "grad_norm": 1.6328125,
+      "learning_rate": 8.910828025477709e-06,
+      "loss": 0.7249,
+      "step": 660
+    },
+    {
+      "epoch": 0.13799317757610866,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.8895966029724e-06,
+      "loss": 0.6914,
+      "step": 670
+    },
+    {
+      "epoch": 0.1400527772414237,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.868365180467092e-06,
+      "loss": 0.7196,
+      "step": 680
+    },
+    {
+      "epoch": 0.14211237690673875,
+      "grad_norm": 1.5,
+      "learning_rate": 8.847133757961784e-06,
+      "loss": 0.6761,
+      "step": 690
+    },
+    {
+      "epoch": 0.1441719765720538,
+      "grad_norm": 1.734375,
+      "learning_rate": 8.825902335456477e-06,
+      "loss": 0.6784,
+      "step": 700
+    },
+    {
+      "epoch": 0.14623157623736885,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.804670912951169e-06,
+      "loss": 0.7393,
+      "step": 710
+    },
+    {
+      "epoch": 0.14829117590268392,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.78343949044586e-06,
+      "loss": 0.6897,
+      "step": 720
+    },
+    {
+      "epoch": 0.15035077556799897,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.762208067940552e-06,
+      "loss": 0.6699,
+      "step": 730
+    },
+    {
+      "epoch": 0.15241037523331402,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.740976645435246e-06,
+      "loss": 0.6873,
+      "step": 740
+    },
+    {
+      "epoch": 0.15446997489862907,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.719745222929938e-06,
+      "loss": 0.661,
+      "step": 750
+    },
+    {
+      "epoch": 0.15652957456394415,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.69851380042463e-06,
+      "loss": 0.6918,
+      "step": 760
+    },
+    {
+      "epoch": 0.1585891742292592,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.677282377919321e-06,
+      "loss": 0.69,
+      "step": 770
+    },
+    {
+      "epoch": 0.16064877389457424,
+      "grad_norm": 1.375,
+      "learning_rate": 8.656050955414015e-06,
+      "loss": 0.7571,
+      "step": 780
+    },
+    {
+      "epoch": 0.1627083735598893,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.634819532908706e-06,
+      "loss": 0.7193,
+      "step": 790
+    },
+    {
+      "epoch": 0.16476797322520434,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.613588110403398e-06,
+      "loss": 0.6783,
+      "step": 800
+    },
+    {
+      "epoch": 0.16682757289051942,
+      "grad_norm": 1.375,
+      "learning_rate": 8.59235668789809e-06,
+      "loss": 0.6807,
+      "step": 810
+    },
+    {
+      "epoch": 0.16888717255583446,
+      "grad_norm": 1.2578125,
+      "learning_rate": 8.571125265392782e-06,
+      "loss": 0.6597,
+      "step": 820
+    },
+    {
+      "epoch": 0.1709467722211495,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.549893842887475e-06,
+      "loss": 0.691,
+      "step": 830
+    },
+    {
+      "epoch": 0.17300637188646456,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.528662420382167e-06,
+      "loss": 0.6266,
+      "step": 840
+    },
+    {
+      "epoch": 0.17506597155177964,
+      "grad_norm": 1.578125,
+      "learning_rate": 8.507430997876858e-06,
+      "loss": 0.7104,
+      "step": 850
+    },
+    {
+      "epoch": 0.17712557121709468,
+      "grad_norm": 1.8359375,
+      "learning_rate": 8.48619957537155e-06,
+      "loss": 0.7417,
+      "step": 860
+    },
+    {
+      "epoch": 0.17918517088240973,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.464968152866244e-06,
+      "loss": 0.6707,
+      "step": 870
+    },
+    {
+      "epoch": 0.18124477054772478,
+      "grad_norm": 1.75,
+      "learning_rate": 8.443736730360935e-06,
+      "loss": 0.6776,
+      "step": 880
+    },
+    {
+      "epoch": 0.18330437021303983,
+      "grad_norm": 1.3125,
+      "learning_rate": 8.422505307855627e-06,
+      "loss": 0.6576,
+      "step": 890
+    },
+    {
+      "epoch": 0.1853639698783549,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.401273885350319e-06,
+      "loss": 0.6838,
+      "step": 900
+    },
+    {
+      "epoch": 0.18742356954366995,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.380042462845012e-06,
+      "loss": 0.6616,
+      "step": 910
+    },
+    {
+      "epoch": 0.189483169208985,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.358811040339704e-06,
+      "loss": 0.6868,
+      "step": 920
+    },
+    {
+      "epoch": 0.19154276887430005,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.337579617834396e-06,
+      "loss": 0.667,
+      "step": 930
+    },
+    {
+      "epoch": 0.1936023685396151,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.316348195329087e-06,
+      "loss": 0.6805,
+      "step": 940
+    },
+    {
+      "epoch": 0.19566196820493018,
+      "grad_norm": 1.25,
+      "learning_rate": 8.295116772823781e-06,
+      "loss": 0.6723,
+      "step": 950
+    },
+    {
+      "epoch": 0.19772156787024522,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.273885350318473e-06,
+      "loss": 0.6739,
+      "step": 960
+    },
+    {
+      "epoch": 0.19978116753556027,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.252653927813164e-06,
+      "loss": 0.7014,
+      "step": 970
+    },
+    {
+      "epoch": 0.20184076720087532,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.231422505307856e-06,
+      "loss": 0.6908,
+      "step": 980
+    },
+    {
+      "epoch": 0.2039003668661904,
+      "grad_norm": 1.328125,
+      "learning_rate": 8.21019108280255e-06,
+      "loss": 0.6582,
+      "step": 990
+    },
+    {
+      "epoch": 0.20595996653150545,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.188959660297241e-06,
+      "loss": 0.6619,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2080195661968205,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.167728237791933e-06,
+      "loss": 0.6798,
+      "step": 1010
+    },
+    {
+      "epoch": 0.21007916586213554,
+      "grad_norm": 1.34375,
+      "learning_rate": 8.146496815286625e-06,
+      "loss": 0.6565,
+      "step": 1020
+    },
+    {
+      "epoch": 0.2121387655274506,
+      "grad_norm": 1.625,
+      "learning_rate": 8.125265392781318e-06,
+      "loss": 0.7176,
+      "step": 1030
+    },
+    {
+      "epoch": 0.21419836519276567,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.10403397027601e-06,
+      "loss": 0.6692,
+      "step": 1040
+    },
+    {
+      "epoch": 0.21625796485808071,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.082802547770702e-06,
+      "loss": 0.675,
+      "step": 1050
+    },
+    {
+      "epoch": 0.21831756452339576,
+      "grad_norm": 1.375,
+      "learning_rate": 8.061571125265393e-06,
+      "loss": 0.6989,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2203771641887108,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.040339702760087e-06,
+      "loss": 0.7133,
+      "step": 1070
+    },
+    {
+      "epoch": 0.2224367638540259,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.019108280254779e-06,
+      "loss": 0.7272,
+      "step": 1080
+    },
+    {
+      "epoch": 0.22449636351934094,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.99787685774947e-06,
+      "loss": 0.6684,
+      "step": 1090
+    },
+    {
+      "epoch": 0.22655596318465598,
+      "grad_norm": 1.328125,
+      "learning_rate": 7.976645435244162e-06,
+      "loss": 0.6895,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22861556284997103,
+      "grad_norm": 1.5078125,
+      "learning_rate": 7.955414012738854e-06,
+      "loss": 0.6859,
+      "step": 1110
+    },
+    {
+      "epoch": 0.23067516251528608,
+      "grad_norm": 1.6953125,
+      "learning_rate": 7.934182590233547e-06,
+      "loss": 0.723,
+      "step": 1120
+    },
+    {
+      "epoch": 0.23273476218060116,
+      "grad_norm": 1.265625,
+      "learning_rate": 7.912951167728239e-06,
+      "loss": 0.6883,
+      "step": 1130
+    },
+    {
+      "epoch": 0.2347943618459162,
+      "grad_norm": 1.390625,
+      "learning_rate": 7.89171974522293e-06,
+      "loss": 0.6653,
+      "step": 1140
+    },
+    {
+      "epoch": 0.23685396151123125,
+      "grad_norm": 1.6015625,
+      "learning_rate": 7.870488322717622e-06,
+      "loss": 0.7101,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2389135611765463,
+      "grad_norm": 1.4765625,
+      "learning_rate": 7.849256900212316e-06,
+      "loss": 0.6775,
+      "step": 1160
+    },
+    {
+      "epoch": 0.24097316084186135,
+      "grad_norm": 1.421875,
+      "learning_rate": 7.828025477707008e-06,
+      "loss": 0.651,
+      "step": 1170
+    },
+    {
+      "epoch": 0.24303276050717643,
+      "grad_norm": 1.34375,
+      "learning_rate": 7.8067940552017e-06,
+      "loss": 0.6951,
+      "step": 1180
+    },
+    {
+      "epoch": 0.24509236017249147,
+      "grad_norm": 1.59375,
+      "learning_rate": 7.785562632696391e-06,
+      "loss": 0.6685,
+      "step": 1190
+    },
+    {
+      "epoch": 0.24715195983780652,
+      "grad_norm": 1.625,
+      "learning_rate": 7.764331210191085e-06,
+      "loss": 0.7213,
+      "step": 1200
+    },
+    {
+      "epoch": 0.24921155950312157,
+      "grad_norm": 1.3671875,
+      "learning_rate": 7.743099787685776e-06,
+      "loss": 0.6925,
+      "step": 1210
+    },
+    {
+      "epoch": 0.2512711591684366,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.721868365180468e-06,
+      "loss": 0.6676,
+      "step": 1220
+    },
+    {
+      "epoch": 0.25333075883375167,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.70063694267516e-06,
+      "loss": 0.7241,
+      "step": 1230
+    },
+    {
+      "epoch": 0.2553903584990667,
+      "grad_norm": 1.3125,
+      "learning_rate": 7.679405520169853e-06,
+      "loss": 0.6648,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2574499581643818,
+      "grad_norm": 1.3359375,
+      "learning_rate": 7.658174097664545e-06,
+      "loss": 0.6936,
+      "step": 1250
+    },
+    {
+      "epoch": 0.25950955782969687,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.636942675159237e-06,
+      "loss": 0.6615,
+      "step": 1260
+    },
+    {
+      "epoch": 0.2615691574950119,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.615711252653929e-06,
+      "loss": 0.694,
+      "step": 1270
+    },
+    {
+      "epoch": 0.26362875716032697,
+      "grad_norm": 1.703125,
+      "learning_rate": 7.594479830148621e-06,
+      "loss": 0.721,
+      "step": 1280
+    },
+    {
+      "epoch": 0.265688356825642,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.573248407643314e-06,
+      "loss": 0.6581,
+      "step": 1290
+    },
+    {
+      "epoch": 0.26774795649095706,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.552016985138005e-06,
+      "loss": 0.6855,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2698075561562721,
+      "grad_norm": 1.5,
+      "learning_rate": 7.530785562632698e-06,
+      "loss": 0.6606,
+      "step": 1310
+    },
+    {
+      "epoch": 0.27186715582158716,
+      "grad_norm": 1.609375,
+      "learning_rate": 7.50955414012739e-06,
+      "loss": 0.6695,
+      "step": 1320
+    },
+    {
+      "epoch": 0.2739267554869022,
+      "grad_norm": 1.2265625,
+      "learning_rate": 7.4883227176220806e-06,
+      "loss": 0.6577,
+      "step": 1330
+    },
+    {
+      "epoch": 0.2759863551522173,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.467091295116773e-06,
+      "loss": 0.6765,
+      "step": 1340
+    },
+    {
+      "epoch": 0.27804595481753236,
+      "grad_norm": 1.359375,
+      "learning_rate": 7.445859872611465e-06,
+      "loss": 0.6688,
+      "step": 1350
+    },
+    {
+      "epoch": 0.2801055544828474,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.4246284501061575e-06,
+      "loss": 0.6831,
+      "step": 1360
+    },
+    {
+      "epoch": 0.28216515414816246,
+      "grad_norm": 1.3359375,
+      "learning_rate": 7.403397027600849e-06,
+      "loss": 0.6893,
+      "step": 1370
+    },
+    {
+      "epoch": 0.2842247538134775,
+      "grad_norm": 1.890625,
+      "learning_rate": 7.382165605095542e-06,
+      "loss": 0.7225,
+      "step": 1380
+    },
+    {
+      "epoch": 0.28628435347879255,
+      "grad_norm": 1.546875,
+      "learning_rate": 7.3609341825902335e-06,
+      "loss": 0.6909,
+      "step": 1390
+    },
+    {
+      "epoch": 0.2883439531441076,
+      "grad_norm": 1.6328125,
+      "learning_rate": 7.339702760084926e-06,
+      "loss": 0.6611,
+      "step": 1400
+    },
+    {
+      "epoch": 0.29040355280942265,
+      "grad_norm": 1.2734375,
+      "learning_rate": 7.318471337579618e-06,
+      "loss": 0.6339,
+      "step": 1410
+    },
+    {
+      "epoch": 0.2924631524747377,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.2972399150743105e-06,
+      "loss": 0.6755,
+      "step": 1420
+    },
+    {
+      "epoch": 0.2945227521400528,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7.276008492569002e-06,
+      "loss": 0.6666,
+      "step": 1430
+    },
+    {
+      "epoch": 0.29658235180536785,
+      "grad_norm": 1.53125,
+      "learning_rate": 7.254777070063695e-06,
+      "loss": 0.6508,
+      "step": 1440
+    },
+    {
+      "epoch": 0.2986419514706829,
+      "grad_norm": 1.5390625,
+      "learning_rate": 7.2335456475583865e-06,
+      "loss": 0.6862,
+      "step": 1450
+    },
+    {
+      "epoch": 0.30070155113599795,
+      "grad_norm": 1.359375,
+      "learning_rate": 7.212314225053078e-06,
+      "loss": 0.6958,
+      "step": 1460
+    },
+    {
+      "epoch": 0.302761150801313,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.191082802547771e-06,
+      "loss": 0.684,
+      "step": 1470
+    },
+    {
+      "epoch": 0.30482075046662804,
+      "grad_norm": 1.6640625,
+      "learning_rate": 7.169851380042463e-06,
+      "loss": 0.6716,
+      "step": 1480
+    },
+    {
+      "epoch": 0.3068803501319431,
+      "grad_norm": 1.5546875,
+      "learning_rate": 7.148619957537155e-06,
+      "loss": 0.6713,
+      "step": 1490
+    },
+    {
+      "epoch": 0.30893994979725814,
+      "grad_norm": 1.75,
+      "learning_rate": 7.127388535031847e-06,
+      "loss": 0.6657,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3109995494625732,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.1061571125265395e-06,
+      "loss": 0.6556,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3130591491278883,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.084925690021231e-06,
+      "loss": 0.6475,
+      "step": 1520
+    },
+    {
+      "epoch": 0.31511874879320334,
+      "grad_norm": 1.4140625,
+      "learning_rate": 7.063694267515924e-06,
+      "loss": 0.6739,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3171783484585184,
+      "grad_norm": 1.359375,
+      "learning_rate": 7.0424628450106156e-06,
+      "loss": 0.6792,
+      "step": 1540
+    },
+    {
+      "epoch": 0.31923794812383344,
+      "grad_norm": 1.40625,
+      "learning_rate": 7.021231422505308e-06,
+      "loss": 0.6637,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3212975477891485,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7e-06,
+      "loss": 0.6658,
+      "step": 1560
+    },
+    {
+      "epoch": 0.32335714745446353,
+      "grad_norm": 1.359375,
+      "learning_rate": 6.9787685774946925e-06,
+      "loss": 0.6189,
+      "step": 1570
+    },
+    {
+      "epoch": 0.3254167471197786,
+      "grad_norm": 1.640625,
+      "learning_rate": 6.957537154989384e-06,
+      "loss": 0.6709,
+      "step": 1580
+    },
+    {
+      "epoch": 0.32747634678509363,
+      "grad_norm": 1.4609375,
+      "learning_rate": 6.936305732484077e-06,
+      "loss": 0.688,
+      "step": 1590
+    },
+    {
+      "epoch": 0.3295359464504087,
+      "grad_norm": 1.515625,
+      "learning_rate": 6.9150743099787685e-06,
+      "loss": 0.6961,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3315955461157238,
+      "grad_norm": 1.578125,
+      "learning_rate": 6.893842887473461e-06,
+      "loss": 0.654,
+      "step": 1610
+    },
+    {
+      "epoch": 0.33365514578103883,
+      "grad_norm": 1.4453125,
+      "learning_rate": 6.872611464968153e-06,
+      "loss": 0.6655,
+      "step": 1620
+    },
+    {
+      "epoch": 0.3357147454463539,
+      "grad_norm": 1.546875,
+      "learning_rate": 6.8513800424628455e-06,
+      "loss": 0.6588,
+      "step": 1630
+    },
+    {
+      "epoch": 0.3377743451116689,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.830148619957537e-06,
+      "loss": 0.6371,
+      "step": 1640
+    },
+    {
+      "epoch": 0.339833944776984,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.80891719745223e-06,
+      "loss": 0.6723,
+      "step": 1650
+    },
+    {
+      "epoch": 0.341893544442299,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.7876857749469215e-06,
+      "loss": 0.6809,
+      "step": 1660
+    },
+    {
+      "epoch": 0.3439531441076141,
+      "grad_norm": 1.296875,
+      "learning_rate": 6.766454352441614e-06,
+      "loss": 0.6593,
+      "step": 1670
+    },
+    {
+      "epoch": 0.3460127437729291,
+      "grad_norm": 1.34375,
+      "learning_rate": 6.745222929936306e-06,
+      "loss": 0.6804,
+      "step": 1680
+    },
+    {
+      "epoch": 0.34807234343824417,
+      "grad_norm": 1.4296875,
+      "learning_rate": 6.7239915074309984e-06,
+      "loss": 0.6631,
+      "step": 1690
+    },
+    {
+      "epoch": 0.3501319431035593,
+      "grad_norm": 1.5859375,
+      "learning_rate": 6.70276008492569e-06,
+      "loss": 0.7134,
+      "step": 1700
+    },
+    {
+      "epoch": 0.3521915427688743,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.681528662420382e-06,
+      "loss": 0.6879,
+      "step": 1710
+    },
+    {
+      "epoch": 0.35425114243418937,
+      "grad_norm": 1.5,
+      "learning_rate": 6.6602972399150745e-06,
+      "loss": 0.6816,
+      "step": 1720
+    },
+    {
+      "epoch": 0.3563107420995044,
+      "grad_norm": 1.5859375,
+      "learning_rate": 6.639065817409766e-06,
+      "loss": 0.6591,
+      "step": 1730
+    },
+    {
+      "epoch": 0.35837034176481947,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.617834394904459e-06,
+      "loss": 0.6874,
+      "step": 1740
+    },
+    {
+      "epoch": 0.3604299414301345,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.5966029723991506e-06,
+      "loss": 0.6514,
+      "step": 1750
+    },
+    {
+      "epoch": 0.36248954109544956,
+      "grad_norm": 1.515625,
+      "learning_rate": 6.575371549893843e-06,
+      "loss": 0.6424,
+      "step": 1760
+    },
+    {
+      "epoch": 0.3645491407607646,
+      "grad_norm": 1.34375,
+      "learning_rate": 6.554140127388535e-06,
+      "loss": 0.6266,
+      "step": 1770
+    },
+    {
+      "epoch": 0.36660874042607966,
+      "grad_norm": 1.484375,
+      "learning_rate": 6.5329087048832275e-06,
+      "loss": 0.6608,
+      "step": 1780
+    },
+    {
+      "epoch": 0.3686683400913947,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.511677282377919e-06,
+      "loss": 0.6556,
+      "step": 1790
+    },
+    {
+      "epoch": 0.3707279397567098,
+      "grad_norm": 1.546875,
+      "learning_rate": 6.490445859872612e-06,
+      "loss": 0.6635,
+      "step": 1800
+    },
+    {
+      "epoch": 0.37278753942202486,
+      "grad_norm": 1.6875,
+      "learning_rate": 6.4692144373673036e-06,
+      "loss": 0.6808,
+      "step": 1810
+    },
+    {
+      "epoch": 0.3748471390873399,
+      "grad_norm": 1.546875,
+      "learning_rate": 6.447983014861996e-06,
+      "loss": 0.69,
+      "step": 1820
+    },
+    {
+      "epoch": 0.37690673875265496,
+      "grad_norm": 1.375,
+      "learning_rate": 6.426751592356688e-06,
+      "loss": 0.7151,
+      "step": 1830
+    },
+    {
+      "epoch": 0.37896633841797,
+      "grad_norm": 1.6328125,
+      "learning_rate": 6.4055201698513805e-06,
+      "loss": 0.6897,
+      "step": 1840
+    },
+    {
+      "epoch": 0.38102593808328505,
+      "grad_norm": 1.390625,
+      "learning_rate": 6.384288747346072e-06,
+      "loss": 0.6867,
+      "step": 1850
+    },
+    {
+      "epoch": 0.3830855377486001,
+      "grad_norm": 1.34375,
+      "learning_rate": 6.363057324840765e-06,
+      "loss": 0.6976,
+      "step": 1860
+    },
+    {
+      "epoch": 0.38514513741391515,
+      "grad_norm": 1.3203125,
+      "learning_rate": 6.3418259023354565e-06,
+      "loss": 0.6719,
+      "step": 1870
+    },
+    {
+      "epoch": 0.3872047370792302,
+      "grad_norm": 1.5390625,
+      "learning_rate": 6.320594479830149e-06,
+      "loss": 0.67,
+      "step": 1880
+    },
+    {
+      "epoch": 0.3892643367445453,
+      "grad_norm": 1.625,
+      "learning_rate": 6.299363057324841e-06,
+      "loss": 0.6491,
+      "step": 1890
+    },
+    {
+      "epoch": 0.39132393640986035,
+      "grad_norm": 1.3046875,
+      "learning_rate": 6.2781316348195334e-06,
+      "loss": 0.6766,
+      "step": 1900
+    },
+    {
+      "epoch": 0.3933835360751754,
+      "grad_norm": 1.4609375,
+      "learning_rate": 6.256900212314225e-06,
+      "loss": 0.6425,
+      "step": 1910
+    },
+    {
+      "epoch": 0.39544313574049045,
+      "grad_norm": 1.2421875,
+      "learning_rate": 6.235668789808918e-06,
+      "loss": 0.6416,
+      "step": 1920
+    },
+    {
+      "epoch": 0.3975027354058055,
+      "grad_norm": 1.390625,
+      "learning_rate": 6.2144373673036095e-06,
+      "loss": 0.7069,
+      "step": 1930
+    },
+    {
+      "epoch": 0.39956233507112054,
+      "grad_norm": 1.640625,
+      "learning_rate": 6.193205944798302e-06,
+      "loss": 0.6755,
+      "step": 1940
+    },
+    {
+      "epoch": 0.4016219347364356,
+      "grad_norm": 1.3046875,
+      "learning_rate": 6.171974522292994e-06,
+      "loss": 0.6896,
+      "step": 1950
+    },
+    {
+      "epoch": 0.40368153440175064,
+      "grad_norm": 1.34375,
+      "learning_rate": 6.1507430997876864e-06,
+      "loss": 0.6567,
+      "step": 1960
+    },
+    {
+      "epoch": 0.4057411340670657,
+      "grad_norm": 1.5078125,
+      "learning_rate": 6.129511677282378e-06,
+      "loss": 0.6335,
+      "step": 1970
+    },
+    {
+      "epoch": 0.4078007337323808,
+      "grad_norm": 1.5625,
+      "learning_rate": 6.10828025477707e-06,
+      "loss": 0.6613,
+      "step": 1980
+    },
+    {
+      "epoch": 0.40986033339769584,
+      "grad_norm": 1.3671875,
+      "learning_rate": 6.0870488322717625e-06,
+      "loss": 0.6833,
+      "step": 1990
+    },
+    {
+      "epoch": 0.4119199330630109,
+      "grad_norm": 1.515625,
+      "learning_rate": 6.065817409766454e-06,
+      "loss": 0.6645,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9036478551297434e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2.5_full_sft/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3f2d9cedae7b7a6948879545ee242f546eeea69378ead1818fa3ffdc8adefc
+size 5841

qwen2.5_lora_sft/checkpoint-epoch-0-step-100/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /root/autodl-tmp/Models/Qwen/Qwen2.5-Coder-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/root/autodl-tmp/Models/Qwen/Qwen2.5-Coder-1.5B-Instruct
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

qwen2.5_lora_sft/checkpoint-epoch-0-step-100/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/autodl-tmp/Models/Qwen/Qwen2.5-Coder-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen2.5_lora_sft/checkpoint-epoch-0-step-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bfe09863b800072ee24a26ca84e7b4dcce02c0889ea0f46060c8cbacfe63e16
+size 73911112

qwen2.5_lora_sft/checkpoint-epoch-0-step-100/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
+}