Add fine-tuned model

README.md

@@ -0,0 +1,7 @@
+---
+base_model: Qwen/Qwen3-4B
+library_name: peft
+---
+### Framework versions
+
+- PEFT 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ba407ab5763518863329293186a66066cded258d8f1dc63d2d08ba1450a2c81
+size 528550256

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf4233a05cc80d36da049c8c40877aa3b37dab8c9bc156c928f7b2ef5575305
+size 7032431

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1470 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 204,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004901960784313725,
+      "grad_norm": 2.6420116424560547,
+      "learning_rate": 1e-05,
+      "loss": 2.3906,
+      "step": 1
+    },
+    {
+      "epoch": 0.00980392156862745,
+      "grad_norm": 2.637878894805908,
+      "learning_rate": 9.950980392156863e-06,
+      "loss": 2.4164,
+      "step": 2
+    },
+    {
+      "epoch": 0.014705882352941176,
+      "grad_norm": 2.458621025085449,
+      "learning_rate": 9.901960784313727e-06,
+      "loss": 2.4651,
+      "step": 3
+    },
+    {
+      "epoch": 0.0196078431372549,
+      "grad_norm": 2.19918155670166,
+      "learning_rate": 9.852941176470589e-06,
+      "loss": 2.3703,
+      "step": 4
+    },
+    {
+      "epoch": 0.024509803921568627,
+      "grad_norm": 1.9437588453292847,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 2.2912,
+      "step": 5
+    },
+    {
+      "epoch": 0.029411764705882353,
+      "grad_norm": 1.7210766077041626,
+      "learning_rate": 9.754901960784315e-06,
+      "loss": 2.2819,
+      "step": 6
+    },
+    {
+      "epoch": 0.03431372549019608,
+      "grad_norm": 1.4723800420761108,
+      "learning_rate": 9.705882352941177e-06,
+      "loss": 2.2195,
+      "step": 7
+    },
+    {
+      "epoch": 0.0392156862745098,
+      "grad_norm": 1.3819530010223389,
+      "learning_rate": 9.65686274509804e-06,
+      "loss": 2.3104,
+      "step": 8
+    },
+    {
+      "epoch": 0.04411764705882353,
+      "grad_norm": 1.1695120334625244,
+      "learning_rate": 9.607843137254903e-06,
+      "loss": 2.2391,
+      "step": 9
+    },
+    {
+      "epoch": 0.049019607843137254,
+      "grad_norm": 1.0744879245758057,
+      "learning_rate": 9.558823529411766e-06,
+      "loss": 2.2186,
+      "step": 10
+    },
+    {
+      "epoch": 0.05392156862745098,
+      "grad_norm": 0.9573182463645935,
+      "learning_rate": 9.509803921568628e-06,
+      "loss": 2.1767,
+      "step": 11
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 0.8470582365989685,
+      "learning_rate": 9.46078431372549e-06,
+      "loss": 2.1134,
+      "step": 12
+    },
+    {
+      "epoch": 0.06372549019607843,
+      "grad_norm": 0.7953258752822876,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 2.0726,
+      "step": 13
+    },
+    {
+      "epoch": 0.06862745098039216,
+      "grad_norm": 0.7779842615127563,
+      "learning_rate": 9.362745098039216e-06,
+      "loss": 2.1264,
+      "step": 14
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 0.7064876556396484,
+      "learning_rate": 9.31372549019608e-06,
+      "loss": 2.0687,
+      "step": 15
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 0.67366623878479,
+      "learning_rate": 9.264705882352942e-06,
+      "loss": 2.0645,
+      "step": 16
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.6415592432022095,
+      "learning_rate": 9.215686274509804e-06,
+      "loss": 2.0479,
+      "step": 17
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 0.6055485010147095,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 2.0086,
+      "step": 18
+    },
+    {
+      "epoch": 0.09313725490196079,
+      "grad_norm": 0.6359033584594727,
+      "learning_rate": 9.11764705882353e-06,
+      "loss": 2.06,
+      "step": 19
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.6109209656715393,
+      "learning_rate": 9.068627450980392e-06,
+      "loss": 2.0204,
+      "step": 20
+    },
+    {
+      "epoch": 0.10294117647058823,
+      "grad_norm": 0.570789098739624,
+      "learning_rate": 9.019607843137256e-06,
+      "loss": 1.9773,
+      "step": 21
+    },
+    {
+      "epoch": 0.10784313725490197,
+      "grad_norm": 0.5694129467010498,
+      "learning_rate": 8.970588235294119e-06,
+      "loss": 1.9606,
+      "step": 22
+    },
+    {
+      "epoch": 0.11274509803921569,
+      "grad_norm": 0.5448282361030579,
+      "learning_rate": 8.921568627450982e-06,
+      "loss": 1.9954,
+      "step": 23
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.5157647132873535,
+      "learning_rate": 8.872549019607843e-06,
+      "loss": 1.9433,
+      "step": 24
+    },
+    {
+      "epoch": 0.12254901960784313,
+      "grad_norm": 0.5053679347038269,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 1.9264,
+      "step": 25
+    },
+    {
+      "epoch": 0.12745098039215685,
+      "grad_norm": 0.4856751263141632,
+      "learning_rate": 8.774509803921569e-06,
+      "loss": 1.8901,
+      "step": 26
+    },
+    {
+      "epoch": 0.1323529411764706,
+      "grad_norm": 0.49523958563804626,
+      "learning_rate": 8.725490196078433e-06,
+      "loss": 1.9636,
+      "step": 27
+    },
+    {
+      "epoch": 0.13725490196078433,
+      "grad_norm": 0.4699620008468628,
+      "learning_rate": 8.676470588235295e-06,
+      "loss": 1.9387,
+      "step": 28
+    },
+    {
+      "epoch": 0.14215686274509803,
+      "grad_norm": 0.4365707337856293,
+      "learning_rate": 8.627450980392157e-06,
+      "loss": 1.8187,
+      "step": 29
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 0.44944438338279724,
+      "learning_rate": 8.57843137254902e-06,
+      "loss": 1.8741,
+      "step": 30
+    },
+    {
+      "epoch": 0.15196078431372548,
+      "grad_norm": 0.4370705187320709,
+      "learning_rate": 8.529411764705883e-06,
+      "loss": 1.88,
+      "step": 31
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 0.44076773524284363,
+      "learning_rate": 8.480392156862745e-06,
+      "loss": 1.8911,
+      "step": 32
+    },
+    {
+      "epoch": 0.16176470588235295,
+      "grad_norm": 0.4040326476097107,
+      "learning_rate": 8.43137254901961e-06,
+      "loss": 1.7777,
+      "step": 33
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.40086352825164795,
+      "learning_rate": 8.382352941176472e-06,
+      "loss": 1.767,
+      "step": 34
+    },
+    {
+      "epoch": 0.1715686274509804,
+      "grad_norm": 0.38453346490859985,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.767,
+      "step": 35
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 0.3940694332122803,
+      "learning_rate": 8.284313725490198e-06,
+      "loss": 1.8315,
+      "step": 36
+    },
+    {
+      "epoch": 0.18137254901960784,
+      "grad_norm": 0.3779416084289551,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 1.759,
+      "step": 37
+    },
+    {
+      "epoch": 0.18627450980392157,
+      "grad_norm": 0.3650701344013214,
+      "learning_rate": 8.186274509803922e-06,
+      "loss": 1.7826,
+      "step": 38
+    },
+    {
+      "epoch": 0.19117647058823528,
+      "grad_norm": 0.3733120858669281,
+      "learning_rate": 8.137254901960784e-06,
+      "loss": 1.8012,
+      "step": 39
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.37932655215263367,
+      "learning_rate": 8.088235294117648e-06,
+      "loss": 1.8404,
+      "step": 40
+    },
+    {
+      "epoch": 0.20098039215686275,
+      "grad_norm": 0.3406783640384674,
+      "learning_rate": 8.03921568627451e-06,
+      "loss": 1.6991,
+      "step": 41
+    },
+    {
+      "epoch": 0.20588235294117646,
+      "grad_norm": 0.35015350580215454,
+      "learning_rate": 7.990196078431374e-06,
+      "loss": 1.7915,
+      "step": 42
+    },
+    {
+      "epoch": 0.2107843137254902,
+      "grad_norm": 0.34951597452163696,
+      "learning_rate": 7.941176470588236e-06,
+      "loss": 1.743,
+      "step": 43
+    },
+    {
+      "epoch": 0.21568627450980393,
+      "grad_norm": 0.3313625454902649,
+      "learning_rate": 7.892156862745098e-06,
+      "loss": 1.6831,
+      "step": 44
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": 0.3377585709095001,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 1.752,
+      "step": 45
+    },
+    {
+      "epoch": 0.22549019607843138,
+      "grad_norm": 0.33550116419792175,
+      "learning_rate": 7.794117647058825e-06,
+      "loss": 1.7306,
+      "step": 46
+    },
+    {
+      "epoch": 0.23039215686274508,
+      "grad_norm": 0.3151518702507019,
+      "learning_rate": 7.745098039215687e-06,
+      "loss": 1.6855,
+      "step": 47
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.9718700051307678,
+      "learning_rate": 7.69607843137255e-06,
+      "loss": 1.7545,
+      "step": 48
+    },
+    {
+      "epoch": 0.24019607843137256,
+      "grad_norm": 0.34166595339775085,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 1.7708,
+      "step": 49
+    },
+    {
+      "epoch": 0.24509803921568626,
+      "grad_norm": 0.32603785395622253,
+      "learning_rate": 7.598039215686275e-06,
+      "loss": 1.7277,
+      "step": 50
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.3403571844100952,
+      "learning_rate": 7.549019607843138e-06,
+      "loss": 1.668,
+      "step": 51
+    },
+    {
+      "epoch": 0.2549019607843137,
+      "grad_norm": 0.3319453299045563,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.6724,
+      "step": 52
+    },
+    {
+      "epoch": 0.25980392156862747,
+      "grad_norm": 0.302993506193161,
+      "learning_rate": 7.450980392156863e-06,
+      "loss": 1.647,
+      "step": 53
+    },
+    {
+      "epoch": 0.2647058823529412,
+      "grad_norm": 0.3261265754699707,
+      "learning_rate": 7.401960784313726e-06,
+      "loss": 1.6904,
+      "step": 54
+    },
+    {
+      "epoch": 0.2696078431372549,
+      "grad_norm": 0.3025933504104614,
+      "learning_rate": 7.352941176470589e-06,
+      "loss": 1.6523,
+      "step": 55
+    },
+    {
+      "epoch": 0.27450980392156865,
+      "grad_norm": 0.29569879174232483,
+      "learning_rate": 7.3039215686274515e-06,
+      "loss": 1.6773,
+      "step": 56
+    },
+    {
+      "epoch": 0.27941176470588236,
+      "grad_norm": 0.3351399600505829,
+      "learning_rate": 7.2549019607843145e-06,
+      "loss": 1.5811,
+      "step": 57
+    },
+    {
+      "epoch": 0.28431372549019607,
+      "grad_norm": 0.30577149987220764,
+      "learning_rate": 7.205882352941177e-06,
+      "loss": 1.6286,
+      "step": 58
+    },
+    {
+      "epoch": 0.28921568627450983,
+      "grad_norm": 0.2970532178878784,
+      "learning_rate": 7.15686274509804e-06,
+      "loss": 1.6368,
+      "step": 59
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.3181511461734772,
+      "learning_rate": 7.107843137254903e-06,
+      "loss": 1.6797,
+      "step": 60
+    },
+    {
+      "epoch": 0.29901960784313725,
+      "grad_norm": 0.29371798038482666,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 1.6058,
+      "step": 61
+    },
+    {
+      "epoch": 0.30392156862745096,
+      "grad_norm": 0.30722576379776,
+      "learning_rate": 7.009803921568628e-06,
+      "loss": 1.623,
+      "step": 62
+    },
+    {
+      "epoch": 0.3088235294117647,
+      "grad_norm": 0.29775312542915344,
+      "learning_rate": 6.96078431372549e-06,
+      "loss": 1.6263,
+      "step": 63
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 0.2881508469581604,
+      "learning_rate": 6.911764705882353e-06,
+      "loss": 1.6688,
+      "step": 64
+    },
+    {
+      "epoch": 0.31862745098039214,
+      "grad_norm": 0.28677794337272644,
+      "learning_rate": 6.862745098039216e-06,
+      "loss": 1.5994,
+      "step": 65
+    },
+    {
+      "epoch": 0.3235294117647059,
+      "grad_norm": 0.2931361794471741,
+      "learning_rate": 6.813725490196079e-06,
+      "loss": 1.6075,
+      "step": 66
+    },
+    {
+      "epoch": 0.3284313725490196,
+      "grad_norm": 0.29081669449806213,
+      "learning_rate": 6.764705882352942e-06,
+      "loss": 1.6084,
+      "step": 67
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.2896648645401001,
+      "learning_rate": 6.715686274509804e-06,
+      "loss": 1.6014,
+      "step": 68
+    },
+    {
+      "epoch": 0.3382352941176471,
+      "grad_norm": 0.27905285358428955,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.5465,
+      "step": 69
+    },
+    {
+      "epoch": 0.3431372549019608,
+      "grad_norm": 0.29267242550849915,
+      "learning_rate": 6.61764705882353e-06,
+      "loss": 1.596,
+      "step": 70
+    },
+    {
+      "epoch": 0.3480392156862745,
+      "grad_norm": 0.3017067611217499,
+      "learning_rate": 6.568627450980393e-06,
+      "loss": 1.6626,
+      "step": 71
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.2846944034099579,
+      "learning_rate": 6.519607843137256e-06,
+      "loss": 1.579,
+      "step": 72
+    },
+    {
+      "epoch": 0.35784313725490197,
+      "grad_norm": 0.28819096088409424,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 1.6125,
+      "step": 73
+    },
+    {
+      "epoch": 0.3627450980392157,
+      "grad_norm": 0.28067734837532043,
+      "learning_rate": 6.421568627450982e-06,
+      "loss": 1.5846,
+      "step": 74
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "grad_norm": 0.27532151341438293,
+      "learning_rate": 6.372549019607843e-06,
+      "loss": 1.5038,
+      "step": 75
+    },
+    {
+      "epoch": 0.37254901960784315,
+      "grad_norm": 0.27768000960350037,
+      "learning_rate": 6.323529411764706e-06,
+      "loss": 1.5085,
+      "step": 76
+    },
+    {
+      "epoch": 0.37745098039215685,
+      "grad_norm": 0.2905992567539215,
+      "learning_rate": 6.274509803921569e-06,
+      "loss": 1.5726,
+      "step": 77
+    },
+    {
+      "epoch": 0.38235294117647056,
+      "grad_norm": 0.30053502321243286,
+      "learning_rate": 6.225490196078432e-06,
+      "loss": 1.6256,
+      "step": 78
+    },
+    {
+      "epoch": 0.3872549019607843,
+      "grad_norm": 0.28900110721588135,
+      "learning_rate": 6.176470588235295e-06,
+      "loss": 1.6232,
+      "step": 79
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.2773635983467102,
+      "learning_rate": 6.1274509803921575e-06,
+      "loss": 1.5722,
+      "step": 80
+    },
+    {
+      "epoch": 0.39705882352941174,
+      "grad_norm": 0.2847748398780823,
+      "learning_rate": 6.07843137254902e-06,
+      "loss": 1.5998,
+      "step": 81
+    },
+    {
+      "epoch": 0.4019607843137255,
+      "grad_norm": 0.2789691984653473,
+      "learning_rate": 6.029411764705883e-06,
+      "loss": 1.5358,
+      "step": 82
+    },
+    {
+      "epoch": 0.4068627450980392,
+      "grad_norm": 0.27959495782852173,
+      "learning_rate": 5.980392156862746e-06,
+      "loss": 1.5554,
+      "step": 83
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 0.2851790487766266,
+      "learning_rate": 5.931372549019609e-06,
+      "loss": 1.55,
+      "step": 84
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.2878727316856384,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 1.5329,
+      "step": 85
+    },
+    {
+      "epoch": 0.4215686274509804,
+      "grad_norm": 0.27520549297332764,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 1.5172,
+      "step": 86
+    },
+    {
+      "epoch": 0.4264705882352941,
+      "grad_norm": 0.28156203031539917,
+      "learning_rate": 5.784313725490197e-06,
+      "loss": 1.5707,
+      "step": 87
+    },
+    {
+      "epoch": 0.43137254901960786,
+      "grad_norm": 0.2712784707546234,
+      "learning_rate": 5.735294117647059e-06,
+      "loss": 1.5178,
+      "step": 88
+    },
+    {
+      "epoch": 0.4362745098039216,
+      "grad_norm": 0.2686169743537903,
+      "learning_rate": 5.686274509803922e-06,
+      "loss": 1.5254,
+      "step": 89
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": 0.2874678373336792,
+      "learning_rate": 5.637254901960784e-06,
+      "loss": 1.484,
+      "step": 90
+    },
+    {
+      "epoch": 0.44607843137254904,
+      "grad_norm": 0.29158371686935425,
+      "learning_rate": 5.588235294117647e-06,
+      "loss": 1.5651,
+      "step": 91
+    },
+    {
+      "epoch": 0.45098039215686275,
+      "grad_norm": 0.2792781889438629,
+      "learning_rate": 5.5392156862745104e-06,
+      "loss": 1.511,
+      "step": 92
+    },
+    {
+      "epoch": 0.45588235294117646,
+      "grad_norm": 0.2733880877494812,
+      "learning_rate": 5.4901960784313735e-06,
+      "loss": 1.5253,
+      "step": 93
+    },
+    {
+      "epoch": 0.46078431372549017,
+      "grad_norm": 0.2775598168373108,
+      "learning_rate": 5.441176470588236e-06,
+      "loss": 1.5302,
+      "step": 94
+    },
+    {
+      "epoch": 0.46568627450980393,
+      "grad_norm": 0.2741158902645111,
+      "learning_rate": 5.392156862745098e-06,
+      "loss": 1.5037,
+      "step": 95
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.27771446108818054,
+      "learning_rate": 5.343137254901961e-06,
+      "loss": 1.5431,
+      "step": 96
+    },
+    {
+      "epoch": 0.47549019607843135,
+      "grad_norm": 0.2722872793674469,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 1.4893,
+      "step": 97
+    },
+    {
+      "epoch": 0.4803921568627451,
+      "grad_norm": 0.2785607576370239,
+      "learning_rate": 5.245098039215687e-06,
+      "loss": 1.524,
+      "step": 98
+    },
+    {
+      "epoch": 0.4852941176470588,
+      "grad_norm": 0.2822011709213257,
+      "learning_rate": 5.19607843137255e-06,
+      "loss": 1.527,
+      "step": 99
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.2763293981552124,
+      "learning_rate": 5.147058823529411e-06,
+      "loss": 1.5184,
+      "step": 100
+    },
+    {
+      "epoch": 0.4950980392156863,
+      "grad_norm": 0.28446826338768005,
+      "learning_rate": 5.098039215686274e-06,
+      "loss": 1.504,
+      "step": 101
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.28324395418167114,
+      "learning_rate": 5.049019607843137e-06,
+      "loss": 1.4969,
+      "step": 102
+    },
+    {
+      "epoch": 0.5049019607843137,
+      "grad_norm": 0.2684231698513031,
+      "learning_rate": 5e-06,
+      "loss": 1.4875,
+      "step": 103
+    },
+    {
+      "epoch": 0.5098039215686274,
+      "grad_norm": 0.28931769728660583,
+      "learning_rate": 4.9509803921568634e-06,
+      "loss": 1.5213,
+      "step": 104
+    },
+    {
+      "epoch": 0.5147058823529411,
+      "grad_norm": 0.2650238871574402,
+      "learning_rate": 4.901960784313726e-06,
+      "loss": 1.4841,
+      "step": 105
+    },
+    {
+      "epoch": 0.5196078431372549,
+      "grad_norm": 0.28261345624923706,
+      "learning_rate": 4.852941176470589e-06,
+      "loss": 1.5487,
+      "step": 106
+    },
+    {
+      "epoch": 0.5245098039215687,
+      "grad_norm": 0.27982214093208313,
+      "learning_rate": 4.803921568627452e-06,
+      "loss": 1.4709,
+      "step": 107
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 0.26446083188056946,
+      "learning_rate": 4.754901960784314e-06,
+      "loss": 1.4855,
+      "step": 108
+    },
+    {
+      "epoch": 0.5343137254901961,
+      "grad_norm": 0.26591673493385315,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 1.4878,
+      "step": 109
+    },
+    {
+      "epoch": 0.5392156862745098,
+      "grad_norm": 0.2831075191497803,
+      "learning_rate": 4.65686274509804e-06,
+      "loss": 1.5064,
+      "step": 110
+    },
+    {
+      "epoch": 0.5441176470588235,
+      "grad_norm": 0.279681533575058,
+      "learning_rate": 4.607843137254902e-06,
+      "loss": 1.4595,
+      "step": 111
+    },
+    {
+      "epoch": 0.5490196078431373,
+      "grad_norm": 0.25997674465179443,
+      "learning_rate": 4.558823529411765e-06,
+      "loss": 1.4882,
+      "step": 112
+    },
+    {
+      "epoch": 0.553921568627451,
+      "grad_norm": 0.2680943012237549,
+      "learning_rate": 4.509803921568628e-06,
+      "loss": 1.4864,
+      "step": 113
+    },
+    {
+      "epoch": 0.5588235294117647,
+      "grad_norm": 0.27307650446891785,
+      "learning_rate": 4.460784313725491e-06,
+      "loss": 1.4795,
+      "step": 114
+    },
+    {
+      "epoch": 0.5637254901960784,
+      "grad_norm": 0.27525004744529724,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 1.4962,
+      "step": 115
+    },
+    {
+      "epoch": 0.5686274509803921,
+      "grad_norm": 0.2800407409667969,
+      "learning_rate": 4.3627450980392164e-06,
+      "loss": 1.5018,
+      "step": 116
+    },
+    {
+      "epoch": 0.5735294117647058,
+      "grad_norm": 0.2746967375278473,
+      "learning_rate": 4.313725490196079e-06,
+      "loss": 1.4599,
+      "step": 117
+    },
+    {
+      "epoch": 0.5784313725490197,
+      "grad_norm": 0.28827792406082153,
+      "learning_rate": 4.264705882352942e-06,
+      "loss": 1.4819,
+      "step": 118
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.3010604977607727,
+      "learning_rate": 4.215686274509805e-06,
+      "loss": 1.5429,
+      "step": 119
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.2689879834651947,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 1.4515,
+      "step": 120
+    },
+    {
+      "epoch": 0.5931372549019608,
+      "grad_norm": 0.26634031534194946,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 1.4715,
+      "step": 121
+    },
+    {
+      "epoch": 0.5980392156862745,
+      "grad_norm": 0.27476969361305237,
+      "learning_rate": 4.068627450980392e-06,
+      "loss": 1.4765,
+      "step": 122
+    },
+    {
+      "epoch": 0.6029411764705882,
+      "grad_norm": 0.2860129177570343,
+      "learning_rate": 4.019607843137255e-06,
+      "loss": 1.527,
+      "step": 123
+    },
+    {
+      "epoch": 0.6078431372549019,
+      "grad_norm": 0.27090632915496826,
+      "learning_rate": 3.970588235294118e-06,
+      "loss": 1.4655,
+      "step": 124
+    },
+    {
+      "epoch": 0.6127450980392157,
+      "grad_norm": 0.2747662365436554,
+      "learning_rate": 3.92156862745098e-06,
+      "loss": 1.4132,
+      "step": 125
+    },
+    {
+      "epoch": 0.6176470588235294,
+      "grad_norm": 0.2632937729358673,
+      "learning_rate": 3.872549019607843e-06,
+      "loss": 1.4475,
+      "step": 126
+    },
+    {
+      "epoch": 0.6225490196078431,
+      "grad_norm": 0.26978743076324463,
+      "learning_rate": 3.8235294117647055e-06,
+      "loss": 1.4386,
+      "step": 127
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 0.27830275893211365,
+      "learning_rate": 3.774509803921569e-06,
+      "loss": 1.4767,
+      "step": 128
+    },
+    {
+      "epoch": 0.6323529411764706,
+      "grad_norm": 0.26617521047592163,
+      "learning_rate": 3.7254901960784316e-06,
+      "loss": 1.4527,
+      "step": 129
+    },
+    {
+      "epoch": 0.6372549019607843,
+      "grad_norm": 0.27568498253822327,
+      "learning_rate": 3.6764705882352946e-06,
+      "loss": 1.4512,
+      "step": 130
+    },
+    {
+      "epoch": 0.6421568627450981,
+      "grad_norm": 0.2786470353603363,
+      "learning_rate": 3.6274509803921573e-06,
+      "loss": 1.371,
+      "step": 131
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 0.2729642689228058,
+      "learning_rate": 3.57843137254902e-06,
+      "loss": 1.4207,
+      "step": 132
+    },
+    {
+      "epoch": 0.6519607843137255,
+      "grad_norm": 0.27308568358421326,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 1.437,
+      "step": 133
+    },
+    {
+      "epoch": 0.6568627450980392,
+      "grad_norm": 0.27915245294570923,
+      "learning_rate": 3.480392156862745e-06,
+      "loss": 1.454,
+      "step": 134
+    },
+    {
+      "epoch": 0.6617647058823529,
+      "grad_norm": 0.2963963449001312,
+      "learning_rate": 3.431372549019608e-06,
+      "loss": 1.463,
+      "step": 135
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.2843087911605835,
+      "learning_rate": 3.382352941176471e-06,
+      "loss": 1.482,
+      "step": 136
+    },
+    {
+      "epoch": 0.6715686274509803,
+      "grad_norm": 0.2734018564224243,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.4497,
+      "step": 137
+    },
+    {
+      "epoch": 0.6764705882352942,
+      "grad_norm": 0.27001234889030457,
+      "learning_rate": 3.2843137254901964e-06,
+      "loss": 1.4,
+      "step": 138
+    },
+    {
+      "epoch": 0.6813725490196079,
+      "grad_norm": 0.2916729152202606,
+      "learning_rate": 3.2352941176470594e-06,
+      "loss": 1.4657,
+      "step": 139
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.281105637550354,
+      "learning_rate": 3.1862745098039216e-06,
+      "loss": 1.4053,
+      "step": 140
+    },
+    {
+      "epoch": 0.6911764705882353,
+      "grad_norm": 0.26319730281829834,
+      "learning_rate": 3.1372549019607846e-06,
+      "loss": 1.4509,
+      "step": 141
+    },
+    {
+      "epoch": 0.696078431372549,
+      "grad_norm": 0.26468271017074585,
+      "learning_rate": 3.0882352941176476e-06,
+      "loss": 1.4158,
+      "step": 142
+    },
+    {
+      "epoch": 0.7009803921568627,
+      "grad_norm": 0.28249025344848633,
+      "learning_rate": 3.03921568627451e-06,
+      "loss": 1.4612,
+      "step": 143
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.26733994483947754,
+      "learning_rate": 2.990196078431373e-06,
+      "loss": 1.4322,
+      "step": 144
+    },
+    {
+      "epoch": 0.7107843137254902,
+      "grad_norm": 0.27187880873680115,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 1.4201,
+      "step": 145
+    },
+    {
+      "epoch": 0.7156862745098039,
+      "grad_norm": 0.2730119526386261,
+      "learning_rate": 2.8921568627450985e-06,
+      "loss": 1.4369,
+      "step": 146
+    },
+    {
+      "epoch": 0.7205882352941176,
+      "grad_norm": 0.2769201993942261,
+      "learning_rate": 2.843137254901961e-06,
+      "loss": 1.4098,
+      "step": 147
+    },
+    {
+      "epoch": 0.7254901960784313,
+      "grad_norm": 0.27176210284233093,
+      "learning_rate": 2.7941176470588237e-06,
+      "loss": 1.4273,
+      "step": 148
+    },
+    {
+      "epoch": 0.7303921568627451,
+      "grad_norm": 0.2792702913284302,
+      "learning_rate": 2.7450980392156867e-06,
+      "loss": 1.463,
+      "step": 149
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 0.2821847200393677,
+      "learning_rate": 2.696078431372549e-06,
+      "loss": 1.4451,
+      "step": 150
+    },
+    {
+      "epoch": 0.7401960784313726,
+      "grad_norm": 0.2684028446674347,
+      "learning_rate": 2.647058823529412e-06,
+      "loss": 1.4247,
+      "step": 151
+    },
+    {
+      "epoch": 0.7450980392156863,
+      "grad_norm": 0.26930952072143555,
+      "learning_rate": 2.598039215686275e-06,
+      "loss": 1.4359,
+      "step": 152
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.26983842253685,
+      "learning_rate": 2.549019607843137e-06,
+      "loss": 1.4202,
+      "step": 153
+    },
+    {
+      "epoch": 0.7549019607843137,
+      "grad_norm": 0.26508617401123047,
+      "learning_rate": 2.5e-06,
+      "loss": 1.3969,
+      "step": 154
+    },
+    {
+      "epoch": 0.7598039215686274,
+      "grad_norm": 0.27193331718444824,
+      "learning_rate": 2.450980392156863e-06,
+      "loss": 1.4476,
+      "step": 155
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 0.27425047755241394,
+      "learning_rate": 2.401960784313726e-06,
+      "loss": 1.3886,
+      "step": 156
+    },
+    {
+      "epoch": 0.7696078431372549,
+      "grad_norm": 0.2816329002380371,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 1.4008,
+      "step": 157
+    },
+    {
+      "epoch": 0.7745098039215687,
+      "grad_norm": 0.29589465260505676,
+      "learning_rate": 2.303921568627451e-06,
+      "loss": 1.419,
+      "step": 158
+    },
+    {
+      "epoch": 0.7794117647058824,
+      "grad_norm": 0.27863284945487976,
+      "learning_rate": 2.254901960784314e-06,
+      "loss": 1.4443,
+      "step": 159
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.2747310400009155,
+      "learning_rate": 2.2058823529411767e-06,
+      "loss": 1.3856,
+      "step": 160
+    },
+    {
+      "epoch": 0.7892156862745098,
+      "grad_norm": 0.2732672095298767,
+      "learning_rate": 2.1568627450980393e-06,
+      "loss": 1.455,
+      "step": 161
+    },
+    {
+      "epoch": 0.7941176470588235,
+      "grad_norm": 0.2707500159740448,
+      "learning_rate": 2.1078431372549023e-06,
+      "loss": 1.3619,
+      "step": 162
+    },
+    {
+      "epoch": 0.7990196078431373,
+      "grad_norm": 0.282505065202713,
+      "learning_rate": 2.058823529411765e-06,
+      "loss": 1.4465,
+      "step": 163
+    },
+    {
+      "epoch": 0.803921568627451,
+      "grad_norm": 0.3066253066062927,
+      "learning_rate": 2.0098039215686276e-06,
+      "loss": 1.3808,
+      "step": 164
+    },
+    {
+      "epoch": 0.8088235294117647,
+      "grad_norm": 0.2728064954280853,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 1.4077,
+      "step": 165
+    },
+    {
+      "epoch": 0.8137254901960784,
+      "grad_norm": 0.27442610263824463,
+      "learning_rate": 1.9117647058823528e-06,
+      "loss": 1.4288,
+      "step": 166
+    },
+    {
+      "epoch": 0.8186274509803921,
+      "grad_norm": 0.27505430579185486,
+      "learning_rate": 1.8627450980392158e-06,
+      "loss": 1.4404,
+      "step": 167
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.28002044558525085,
+      "learning_rate": 1.8137254901960786e-06,
+      "loss": 1.4569,
+      "step": 168
+    },
+    {
+      "epoch": 0.8284313725490197,
+      "grad_norm": 0.28254789113998413,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 1.3985,
+      "step": 169
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.26690635085105896,
+      "learning_rate": 1.715686274509804e-06,
+      "loss": 1.3983,
+      "step": 170
+    },
+    {
+      "epoch": 0.8382352941176471,
+      "grad_norm": 0.266835480928421,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.4371,
+      "step": 171
+    },
+    {
+      "epoch": 0.8431372549019608,
+      "grad_norm": 0.2698020935058594,
+      "learning_rate": 1.6176470588235297e-06,
+      "loss": 1.4008,
+      "step": 172
+    },
+    {
+      "epoch": 0.8480392156862745,
+      "grad_norm": 0.2694830894470215,
+      "learning_rate": 1.5686274509803923e-06,
+      "loss": 1.4214,
+      "step": 173
+    },
+    {
+      "epoch": 0.8529411764705882,
+      "grad_norm": 0.2650381028652191,
+      "learning_rate": 1.519607843137255e-06,
+      "loss": 1.4154,
+      "step": 174
+    },
+    {
+      "epoch": 0.8578431372549019,
+      "grad_norm": 0.2682033181190491,
+      "learning_rate": 1.4705882352941177e-06,
+      "loss": 1.4075,
+      "step": 175
+    },
+    {
+      "epoch": 0.8627450980392157,
+      "grad_norm": 0.26703158020973206,
+      "learning_rate": 1.4215686274509805e-06,
+      "loss": 1.4173,
+      "step": 176
+    },
+    {
+      "epoch": 0.8676470588235294,
+      "grad_norm": 0.30258509516716003,
+      "learning_rate": 1.3725490196078434e-06,
+      "loss": 1.3416,
+      "step": 177
+    },
+    {
+      "epoch": 0.8725490196078431,
+      "grad_norm": 0.27852076292037964,
+      "learning_rate": 1.323529411764706e-06,
+      "loss": 1.3871,
+      "step": 178
+    },
+    {
+      "epoch": 0.8774509803921569,
+      "grad_norm": 0.27530935406684875,
+      "learning_rate": 1.2745098039215686e-06,
+      "loss": 1.4311,
+      "step": 179
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.27785223722457886,
+      "learning_rate": 1.2254901960784314e-06,
+      "loss": 1.4504,
+      "step": 180
+    },
+    {
+      "epoch": 0.8872549019607843,
+      "grad_norm": 0.27995413541793823,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 1.4239,
+      "step": 181
+    },
+    {
+      "epoch": 0.8921568627450981,
+      "grad_norm": 0.265800416469574,
+      "learning_rate": 1.127450980392157e-06,
+      "loss": 1.405,
+      "step": 182
+    },
+    {
+      "epoch": 0.8970588235294118,
+      "grad_norm": 0.2827346920967102,
+      "learning_rate": 1.0784313725490197e-06,
+      "loss": 1.4551,
+      "step": 183
+    },
+    {
+      "epoch": 0.9019607843137255,
+      "grad_norm": 0.263273686170578,
+      "learning_rate": 1.0294117647058825e-06,
+      "loss": 1.402,
+      "step": 184
+    },
+    {
+      "epoch": 0.9068627450980392,
+      "grad_norm": 0.2674250602722168,
+      "learning_rate": 9.80392156862745e-07,
+      "loss": 1.3931,
+      "step": 185
+    },
+    {
+      "epoch": 0.9117647058823529,
+      "grad_norm": 0.2709958255290985,
+      "learning_rate": 9.313725490196079e-07,
+      "loss": 1.4266,
+      "step": 186
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.27474477887153625,
+      "learning_rate": 8.823529411764707e-07,
+      "loss": 1.4248,
+      "step": 187
+    },
+    {
+      "epoch": 0.9215686274509803,
+      "grad_norm": 0.2690979540348053,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.4278,
+      "step": 188
+    },
+    {
+      "epoch": 0.9264705882352942,
+      "grad_norm": 0.2708565294742584,
+      "learning_rate": 7.843137254901962e-07,
+      "loss": 1.3561,
+      "step": 189
+    },
+    {
+      "epoch": 0.9313725490196079,
+      "grad_norm": 0.26445382833480835,
+      "learning_rate": 7.352941176470589e-07,
+      "loss": 1.3754,
+      "step": 190
+    },
+    {
+      "epoch": 0.9362745098039216,
+      "grad_norm": 0.30714988708496094,
+      "learning_rate": 6.862745098039217e-07,
+      "loss": 1.4665,
+      "step": 191
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.2680458128452301,
+      "learning_rate": 6.372549019607843e-07,
+      "loss": 1.4568,
+      "step": 192
+    },
+    {
+      "epoch": 0.946078431372549,
+      "grad_norm": 0.2722586691379547,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 1.4348,
+      "step": 193
+    },
+    {
+      "epoch": 0.9509803921568627,
+      "grad_norm": 0.26564568281173706,
+      "learning_rate": 5.392156862745098e-07,
+      "loss": 1.3929,
+      "step": 194
+    },
+    {
+      "epoch": 0.9558823529411765,
+      "grad_norm": 0.2742433249950409,
+      "learning_rate": 4.901960784313725e-07,
+      "loss": 1.3456,
+      "step": 195
+    },
+    {
+      "epoch": 0.9607843137254902,
+      "grad_norm": 0.25368532538414,
+      "learning_rate": 4.4117647058823536e-07,
+      "loss": 1.4049,
+      "step": 196
+    },
+    {
+      "epoch": 0.9656862745098039,
+      "grad_norm": 0.2673678696155548,
+      "learning_rate": 3.921568627450981e-07,
+      "loss": 1.3833,
+      "step": 197
+    },
+    {
+      "epoch": 0.9705882352941176,
+      "grad_norm": 0.2712225914001465,
+      "learning_rate": 3.4313725490196084e-07,
+      "loss": 1.3855,
+      "step": 198
+    },
+    {
+      "epoch": 0.9754901960784313,
+      "grad_norm": 0.26563599705696106,
+      "learning_rate": 2.9411764705882356e-07,
+      "loss": 1.4003,
+      "step": 199
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.2685685157775879,
+      "learning_rate": 2.4509803921568627e-07,
+      "loss": 1.3914,
+      "step": 200
+    },
+    {
+      "epoch": 0.9852941176470589,
+      "grad_norm": 0.2729678153991699,
+      "learning_rate": 1.9607843137254904e-07,
+      "loss": 1.3564,
+      "step": 201
+    },
+    {
+      "epoch": 0.9901960784313726,
+      "grad_norm": 0.259825736284256,
+      "learning_rate": 1.4705882352941178e-07,
+      "loss": 1.3989,
+      "step": 202
+    },
+    {
+      "epoch": 0.9950980392156863,
+      "grad_norm": 0.27453508973121643,
+      "learning_rate": 9.803921568627452e-08,
+      "loss": 1.4024,
+      "step": 203
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2659491002559662,
+      "learning_rate": 4.901960784313726e-08,
+      "loss": 1.3704,
+      "step": 204
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4392527341842651,
+      "eval_runtime": 1.6144,
+      "eval_samples_per_second": 19.202,
+      "eval_steps_per_second": 2.478,
+      "step": 204
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.750879471599616e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}