Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</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
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.0.dev0"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c8b3408fa2f7004d95ebd1dfbc4269ebaf5c1d5e7e46af33162c7bf7faf944
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36b411f2517bb1a71d13458decd15972a3aeb03d90410cd57bc2c4e3cbe7df75
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05070bc4b789c29acbd0cf7f76db418fcbeb67dc7d35b244c886bbe6339904d
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f786a222db9baa582f1836841b632aa38ae363c84de9071f4cc9271a0d4ed3
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b901e2199f3929a25432ccdfbec1c0102955f54c99414f017f37fc2391c98c
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c4cb471f51c316a93206a706d17626478fc9a44b622652a02d5a04ce39fd91
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9489823ecae3ec59adf6453a70018c6accdedcc859429af157d49696aedc077
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c9056918201bb7f28dfe57ddd61813d27f3e00ed7996decb48912f08bd8cce
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c7cc03d8d516305946ff6aa6d2e0ccbbdc17c635fdba40ad155d5c430ebe94
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdb840309debeff15dbb44c8038be227d28487b676d97acec44e0102ebfb24d
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd64325fbc66c122cdf55c3b3b3ea70e2e12cb35eed4a55266ea02ae2aca76aa
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7a8cb7fc6bffbc74c19e9e3ed6f913684693fd499ffe4b639f600164572133
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8a267f68a70708af9b30b1d036ae8b4fded71c6b19540224a583cd967caf6f
+size 1094220288

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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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,
+  "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 +1,1357 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 189,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015873015873015872,
+      "grad_norm": 2.3323949793109238,
+      "learning_rate": 0.0,
+      "loss": 1.0469,
+      "step": 1
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 2.317201200688066,
+      "learning_rate": 3.125e-07,
+      "loss": 0.9931,
+      "step": 2
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 2.603689956679125,
+      "learning_rate": 6.25e-07,
+      "loss": 1.0188,
+      "step": 3
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 2.2583787301898592,
+      "learning_rate": 9.375000000000001e-07,
+      "loss": 0.9097,
+      "step": 4
+    },
+    {
+      "epoch": 0.07936507936507936,
+      "grad_norm": 2.197466891038096,
+      "learning_rate": 1.25e-06,
+      "loss": 1.0459,
+      "step": 5
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 2.1259963361099747,
+      "learning_rate": 1.5625e-06,
+      "loss": 0.9986,
+      "step": 6
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 2.0707820881041,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 0.9555,
+      "step": 7
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 1.870407527874291,
+      "learning_rate": 2.1875000000000002e-06,
+      "loss": 0.952,
+      "step": 8
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 1.8578085390534953,
+      "learning_rate": 2.5e-06,
+      "loss": 0.9993,
+      "step": 9
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 1.881148688458384,
+      "learning_rate": 2.8125e-06,
+      "loss": 0.9373,
+      "step": 10
+    },
+    {
+      "epoch": 0.1746031746031746,
+      "grad_norm": 1.6917769845914787,
+      "learning_rate": 3.125e-06,
+      "loss": 0.8839,
+      "step": 11
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.2541345576396532,
+      "learning_rate": 3.4375e-06,
+      "loss": 0.9909,
+      "step": 12
+    },
+    {
+      "epoch": 0.20634920634920634,
+      "grad_norm": 1.4038335670152517,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.9322,
+      "step": 13
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.363468897891553,
+      "learning_rate": 4.0625000000000005e-06,
+      "loss": 1.0934,
+      "step": 14
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 1.1331989679866032,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.977,
+      "step": 15
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.9899834287202586,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 1.0443,
+      "step": 16
+    },
+    {
+      "epoch": 0.2698412698412698,
+      "grad_norm": 1.155920523517074,
+      "learning_rate": 5e-06,
+      "loss": 0.9483,
+      "step": 17
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 1.2715867938274161,
+      "learning_rate": 5.3125e-06,
+      "loss": 1.0096,
+      "step": 18
+    },
+    {
+      "epoch": 0.30158730158730157,
+      "grad_norm": 0.9922231339593638,
+      "learning_rate": 5.625e-06,
+      "loss": 0.7463,
+      "step": 19
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 1.2551959582539625,
+      "learning_rate": 5.9375e-06,
+      "loss": 0.9226,
+      "step": 20
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.892951024999124,
+      "learning_rate": 6.25e-06,
+      "loss": 0.988,
+      "step": 21
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 1.4360539096520086,
+      "learning_rate": 6.5625e-06,
+      "loss": 1.0509,
+      "step": 22
+    },
+    {
+      "epoch": 0.36507936507936506,
+      "grad_norm": 1.1100051374669628,
+      "learning_rate": 6.875e-06,
+      "loss": 0.8728,
+      "step": 23
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.9630208551024003,
+      "learning_rate": 7.1875e-06,
+      "loss": 0.8352,
+      "step": 24
+    },
+    {
+      "epoch": 0.3968253968253968,
+      "grad_norm": 1.109963225007402,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.0289,
+      "step": 25
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.842175710243708,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.8616,
+      "step": 26
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.8255762742603932,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 0.7234,
+      "step": 27
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.8274507712792363,
+      "learning_rate": 8.4375e-06,
+      "loss": 0.9758,
+      "step": 28
+    },
+    {
+      "epoch": 0.4603174603174603,
+      "grad_norm": 0.7834224887700044,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.9056,
+      "step": 29
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.187020605300137,
+      "learning_rate": 9.0625e-06,
+      "loss": 0.9481,
+      "step": 30
+    },
+    {
+      "epoch": 0.49206349206349204,
+      "grad_norm": 1.0233176856791018,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.9194,
+      "step": 31
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 0.848791394024066,
+      "learning_rate": 9.6875e-06,
+      "loss": 0.8852,
+      "step": 32
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 0.8289281876622956,
+      "learning_rate": 1e-05,
+      "loss": 1.038,
+      "step": 33
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 0.7738330911179299,
+      "learning_rate": 9.999691920767945e-06,
+      "loss": 0.8374,
+      "step": 34
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.65004421093035,
+      "learning_rate": 9.998767721036901e-06,
+      "loss": 0.8242,
+      "step": 35
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.718229691257778,
+      "learning_rate": 9.997227514697568e-06,
+      "loss": 0.9693,
+      "step": 36
+    },
+    {
+      "epoch": 0.5873015873015873,
+      "grad_norm": 0.598178727036991,
+      "learning_rate": 9.99507149155218e-06,
+      "loss": 0.9843,
+      "step": 37
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 0.6896420594948925,
+      "learning_rate": 9.992299917291118e-06,
+      "loss": 0.848,
+      "step": 38
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 0.7218001479564617,
+      "learning_rate": 9.98891313346017e-06,
+      "loss": 0.9095,
+      "step": 39
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.673383804041238,
+      "learning_rate": 9.984911557418444e-06,
+      "loss": 0.7682,
+      "step": 40
+    },
+    {
+      "epoch": 0.6507936507936508,
+      "grad_norm": 0.9044903125501461,
+      "learning_rate": 9.980295682286924e-06,
+      "loss": 0.8388,
+      "step": 41
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.6528626470394925,
+      "learning_rate": 9.97506607688772e-06,
+      "loss": 0.9107,
+      "step": 42
+    },
+    {
+      "epoch": 0.6825396825396826,
+      "grad_norm": 0.5248039585149111,
+      "learning_rate": 9.969223385673958e-06,
+      "loss": 0.8307,
+      "step": 43
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 0.568338771820042,
+      "learning_rate": 9.962768328650367e-06,
+      "loss": 0.7523,
+      "step": 44
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.5429855696185105,
+      "learning_rate": 9.95570170128455e-06,
+      "loss": 0.8442,
+      "step": 45
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 0.5098426033492849,
+      "learning_rate": 9.94802437440896e-06,
+      "loss": 0.7962,
+      "step": 46
+    },
+    {
+      "epoch": 0.746031746031746,
+      "grad_norm": 0.6078990273192543,
+      "learning_rate": 9.939737294113585e-06,
+      "loss": 0.8969,
+      "step": 47
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.4709547244829324,
+      "learning_rate": 9.930841481629358e-06,
+      "loss": 0.8885,
+      "step": 48
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.54039591858629,
+      "learning_rate": 9.92133803320231e-06,
+      "loss": 0.7818,
+      "step": 49
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.4875170254753124,
+      "learning_rate": 9.91122811995848e-06,
+      "loss": 0.8193,
+      "step": 50
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 0.5005396928536703,
+      "learning_rate": 9.90051298775959e-06,
+      "loss": 0.8692,
+      "step": 51
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 0.40245216027036546,
+      "learning_rate": 9.88919395704952e-06,
+      "loss": 0.826,
+      "step": 52
+    },
+    {
+      "epoch": 0.8412698412698413,
+      "grad_norm": 0.5389952051377087,
+      "learning_rate": 9.877272422691583e-06,
+      "loss": 0.9318,
+      "step": 53
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.5638980417584056,
+      "learning_rate": 9.864749853796642e-06,
+      "loss": 0.7985,
+      "step": 54
+    },
+    {
+      "epoch": 0.873015873015873,
+      "grad_norm": 0.5506830661309166,
+      "learning_rate": 9.85162779354206e-06,
+      "loss": 0.7291,
+      "step": 55
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.48566023212019677,
+      "learning_rate": 9.837907858981536e-06,
+      "loss": 0.8802,
+      "step": 56
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 0.4725406192484581,
+      "learning_rate": 9.823591740845831e-06,
+      "loss": 0.8627,
+      "step": 57
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 0.5270784935436914,
+      "learning_rate": 9.808681203334416e-06,
+      "loss": 0.7976,
+      "step": 58
+    },
+    {
+      "epoch": 0.9365079365079365,
+      "grad_norm": 0.4795159174595573,
+      "learning_rate": 9.793178083898073e-06,
+      "loss": 0.8783,
+      "step": 59
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.42309628953003137,
+      "learning_rate": 9.777084293012448e-06,
+      "loss": 0.842,
+      "step": 60
+    },
+    {
+      "epoch": 0.9682539682539683,
+      "grad_norm": 0.464555539059811,
+      "learning_rate": 9.760401813942641e-06,
+      "loss": 0.7662,
+      "step": 61
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 0.5141212041737542,
+      "learning_rate": 9.743132702498785e-06,
+      "loss": 0.8688,
+      "step": 62
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5165788253828009,
+      "learning_rate": 9.725279086782719e-06,
+      "loss": 0.768,
+      "step": 63
+    },
+    {
+      "epoch": 1.0158730158730158,
+      "grad_norm": 0.576629868282963,
+      "learning_rate": 9.706843166925733e-06,
+      "loss": 0.7989,
+      "step": 64
+    },
+    {
+      "epoch": 1.0317460317460316,
+      "grad_norm": 0.4946943998511545,
+      "learning_rate": 9.687827214817433e-06,
+      "loss": 0.8261,
+      "step": 65
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 0.4987216606535057,
+      "learning_rate": 9.668233573825794e-06,
+      "loss": 0.8905,
+      "step": 66
+    },
+    {
+      "epoch": 1.0634920634920635,
+      "grad_norm": 0.45688977932466196,
+      "learning_rate": 9.64806465850836e-06,
+      "loss": 0.7327,
+      "step": 67
+    },
+    {
+      "epoch": 1.0793650793650793,
+      "grad_norm": 0.5226340006885853,
+      "learning_rate": 9.62732295431471e-06,
+      "loss": 0.7311,
+      "step": 68
+    },
+    {
+      "epoch": 1.0952380952380953,
+      "grad_norm": 0.6684025298786129,
+      "learning_rate": 9.606011017280166e-06,
+      "loss": 0.8971,
+      "step": 69
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5147703758608321,
+      "learning_rate": 9.5841314737108e-06,
+      "loss": 0.7652,
+      "step": 70
+    },
+    {
+      "epoch": 1.126984126984127,
+      "grad_norm": 0.5417227409614662,
+      "learning_rate": 9.56168701985981e-06,
+      "loss": 0.7999,
+      "step": 71
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.5016561221704748,
+      "learning_rate": 9.538680421595236e-06,
+      "loss": 0.8074,
+      "step": 72
+    },
+    {
+      "epoch": 1.1587301587301586,
+      "grad_norm": 0.4853528793957531,
+      "learning_rate": 9.515114514059127e-06,
+      "loss": 0.8135,
+      "step": 73
+    },
+    {
+      "epoch": 1.1746031746031746,
+      "grad_norm": 0.47765415470199357,
+      "learning_rate": 9.490992201318165e-06,
+      "loss": 0.7879,
+      "step": 74
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.46535342031003013,
+      "learning_rate": 9.466316456005783e-06,
+      "loss": 0.7762,
+      "step": 75
+    },
+    {
+      "epoch": 1.2063492063492063,
+      "grad_norm": 0.5033568814253909,
+      "learning_rate": 9.441090318955843e-06,
+      "loss": 0.7022,
+      "step": 76
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.4986643533291915,
+      "learning_rate": 9.415316898827923e-06,
+      "loss": 0.7349,
+      "step": 77
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 0.43657193718859494,
+      "learning_rate": 9.388999371724212e-06,
+      "loss": 0.8264,
+      "step": 78
+    },
+    {
+      "epoch": 1.253968253968254,
+      "grad_norm": 0.47617277777848616,
+      "learning_rate": 9.362140980798127e-06,
+      "loss": 0.8944,
+      "step": 79
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.4295219607791053,
+      "learning_rate": 9.334745035854646e-06,
+      "loss": 0.7588,
+      "step": 80
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.5225987407011279,
+      "learning_rate": 9.306814912942445e-06,
+      "loss": 0.8359,
+      "step": 81
+    },
+    {
+      "epoch": 1.3015873015873016,
+      "grad_norm": 0.4173684559568506,
+      "learning_rate": 9.278354053937848e-06,
+      "loss": 0.7804,
+      "step": 82
+    },
+    {
+      "epoch": 1.3174603174603174,
+      "grad_norm": 0.5238592049595157,
+      "learning_rate": 9.249365966120692e-06,
+      "loss": 0.8564,
+      "step": 83
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.4526393208745273,
+      "learning_rate": 9.219854221742106e-06,
+      "loss": 0.8102,
+      "step": 84
+    },
+    {
+      "epoch": 1.3492063492063493,
+      "grad_norm": 0.44471888761912887,
+      "learning_rate": 9.189822457584311e-06,
+      "loss": 0.7439,
+      "step": 85
+    },
+    {
+      "epoch": 1.3650793650793651,
+      "grad_norm": 0.43731884433734214,
+      "learning_rate": 9.159274374512444e-06,
+      "loss": 0.6592,
+      "step": 86
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.4377614076782124,
+      "learning_rate": 9.128213737018493e-06,
+      "loss": 0.806,
+      "step": 87
+    },
+    {
+      "epoch": 1.3968253968253967,
+      "grad_norm": 0.4027105033083121,
+      "learning_rate": 9.096644372757393e-06,
+      "loss": 0.8855,
+      "step": 88
+    },
+    {
+      "epoch": 1.4126984126984126,
+      "grad_norm": 0.571463019194369,
+      "learning_rate": 9.064570172075349e-06,
+      "loss": 0.7979,
+      "step": 89
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.4801097800367482,
+      "learning_rate": 9.031995087530403e-06,
+      "loss": 0.7992,
+      "step": 90
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.47255682704462587,
+      "learning_rate": 8.99892313340537e-06,
+      "loss": 0.6633,
+      "step": 91
+    },
+    {
+      "epoch": 1.4603174603174602,
+      "grad_norm": 0.4862492507086913,
+      "learning_rate": 8.96535838521314e-06,
+      "loss": 0.8033,
+      "step": 92
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 0.4794987734861929,
+      "learning_rate": 8.931304979194452e-06,
+      "loss": 0.8069,
+      "step": 93
+    },
+    {
+      "epoch": 1.492063492063492,
+      "grad_norm": 0.4658669415595415,
+      "learning_rate": 8.896767111808177e-06,
+      "loss": 0.7371,
+      "step": 94
+    },
+    {
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.5683125861447418,
+      "learning_rate": 8.861749039214177e-06,
+      "loss": 0.9145,
+      "step": 95
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.47857884026171116,
+      "learning_rate": 8.826255076748823e-06,
+      "loss": 0.8455,
+      "step": 96
+    },
+    {
+      "epoch": 1.5396825396825395,
+      "grad_norm": 0.429389167302876,
+      "learning_rate": 8.790289598393186e-06,
+      "loss": 0.7216,
+      "step": 97
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.522031534882144,
+      "learning_rate": 8.753857036234055e-06,
+      "loss": 0.8155,
+      "step": 98
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.5375692580431519,
+      "learning_rate": 8.716961879917734e-06,
+      "loss": 0.7373,
+      "step": 99
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.4277716225580266,
+      "learning_rate": 8.679608676096793e-06,
+      "loss": 0.8132,
+      "step": 100
+    },
+    {
+      "epoch": 1.6031746031746033,
+      "grad_norm": 0.9709114563751018,
+      "learning_rate": 8.641802027869774e-06,
+      "loss": 0.7952,
+      "step": 101
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.6722991060253756,
+      "learning_rate": 8.603546594213935e-06,
+      "loss": 0.8566,
+      "step": 102
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "grad_norm": 0.48227435877100366,
+      "learning_rate": 8.564847089411128e-06,
+      "loss": 0.8292,
+      "step": 103
+    },
+    {
+      "epoch": 1.6507936507936507,
+      "grad_norm": 0.43738769808282163,
+      "learning_rate": 8.525708282466839e-06,
+      "loss": 0.8424,
+      "step": 104
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.42758983764847835,
+      "learning_rate": 8.486134996522502e-06,
+      "loss": 0.8179,
+      "step": 105
+    },
+    {
+      "epoch": 1.6825396825396826,
+      "grad_norm": 0.6465752665836958,
+      "learning_rate": 8.446132108261136e-06,
+      "loss": 0.806,
+      "step": 106
+    },
+    {
+      "epoch": 1.6984126984126984,
+      "grad_norm": 0.5216064305348748,
+      "learning_rate": 8.405704547306379e-06,
+      "loss": 0.8041,
+      "step": 107
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.46284349128240304,
+      "learning_rate": 8.364857295615006e-06,
+      "loss": 0.8924,
+      "step": 108
+    },
+    {
+      "epoch": 1.7301587301587302,
+      "grad_norm": 0.48814352812138595,
+      "learning_rate": 8.323595386862985e-06,
+      "loss": 0.7929,
+      "step": 109
+    },
+    {
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.48088506678769916,
+      "learning_rate": 8.281923905825188e-06,
+      "loss": 0.7671,
+      "step": 110
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 0.4594586947272896,
+      "learning_rate": 8.23984798774876e-06,
+      "loss": 0.7366,
+      "step": 111
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.4673793179812366,
+      "learning_rate": 8.197372817720314e-06,
+      "loss": 0.7397,
+      "step": 112
+    },
+    {
+      "epoch": 1.7936507936507935,
+      "grad_norm": 0.6557346369623661,
+      "learning_rate": 8.154503630026955e-06,
+      "loss": 0.7262,
+      "step": 113
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.45128446254113314,
+      "learning_rate": 8.111245707511253e-06,
+      "loss": 0.7213,
+      "step": 114
+    },
+    {
+      "epoch": 1.8253968253968254,
+      "grad_norm": 0.41666335434637974,
+      "learning_rate": 8.067604380920228e-06,
+      "loss": 0.7952,
+      "step": 115
+    },
+    {
+      "epoch": 1.8412698412698414,
+      "grad_norm": 0.4407610683896587,
+      "learning_rate": 8.023585028248435e-06,
+      "loss": 0.8486,
+      "step": 116
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.5501977264080524,
+      "learning_rate": 7.979193074075216e-06,
+      "loss": 0.8911,
+      "step": 117
+    },
+    {
+      "epoch": 1.873015873015873,
+      "grad_norm": 0.459940871244406,
+      "learning_rate": 7.934433988896233e-06,
+      "loss": 0.6535,
+      "step": 118
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.46949896874504654,
+      "learning_rate": 7.889313288449323e-06,
+      "loss": 0.8232,
+      "step": 119
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.41110722374315695,
+      "learning_rate": 7.843836533034784e-06,
+      "loss": 0.7628,
+      "step": 120
+    },
+    {
+      "epoch": 1.9206349206349205,
+      "grad_norm": 0.47755036946919965,
+      "learning_rate": 7.798009326830167e-06,
+      "loss": 0.8003,
+      "step": 121
+    },
+    {
+      "epoch": 1.9365079365079365,
+      "grad_norm": 0.41342145123270885,
+      "learning_rate": 7.751837317199673e-06,
+      "loss": 0.8683,
+      "step": 122
+    },
+    {
+      "epoch": 1.9523809523809523,
+      "grad_norm": 0.4479867168170251,
+      "learning_rate": 7.705326193998207e-06,
+      "loss": 0.7552,
+      "step": 123
+    },
+    {
+      "epoch": 1.9682539682539684,
+      "grad_norm": 0.4549548876094008,
+      "learning_rate": 7.658481688870218e-06,
+      "loss": 0.7587,
+      "step": 124
+    },
+    {
+      "epoch": 1.9841269841269842,
+      "grad_norm": 0.4684989926335189,
+      "learning_rate": 7.611309574543373e-06,
+      "loss": 0.7607,
+      "step": 125
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4367513791425883,
+      "learning_rate": 7.563815664117173e-06,
+      "loss": 0.9146,
+      "step": 126
+    },
+    {
+      "epoch": 2.015873015873016,
+      "grad_norm": 0.7927149278076437,
+      "learning_rate": 7.5160058103465985e-06,
+      "loss": 0.7131,
+      "step": 127
+    },
+    {
+      "epoch": 2.0317460317460316,
+      "grad_norm": 0.5847918647965703,
+      "learning_rate": 7.467885904920864e-06,
+      "loss": 0.7578,
+      "step": 128
+    },
+    {
+      "epoch": 2.0476190476190474,
+      "grad_norm": 0.7836046335272314,
+      "learning_rate": 7.419461877737373e-06,
+      "loss": 0.8327,
+      "step": 129
+    },
+    {
+      "epoch": 2.0634920634920633,
+      "grad_norm": 2.1428241341527117,
+      "learning_rate": 7.370739696170971e-06,
+      "loss": 0.7441,
+      "step": 130
+    },
+    {
+      "epoch": 2.0793650793650795,
+      "grad_norm": 0.9566247813485141,
+      "learning_rate": 7.321725364338566e-06,
+      "loss": 0.6185,
+      "step": 131
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 0.5336099004301172,
+      "learning_rate": 7.272424922359246e-06,
+      "loss": 0.6455,
+      "step": 132
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 0.7132260718912609,
+      "learning_rate": 7.222844445609931e-06,
+      "loss": 0.7834,
+      "step": 133
+    },
+    {
+      "epoch": 2.126984126984127,
+      "grad_norm": 0.5749113101610002,
+      "learning_rate": 7.172990043976703e-06,
+      "loss": 0.7296,
+      "step": 134
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.5366676899164674,
+      "learning_rate": 7.122867861101868e-06,
+      "loss": 0.795,
+      "step": 135
+    },
+    {
+      "epoch": 2.1587301587301586,
+      "grad_norm": 0.44931031781346276,
+      "learning_rate": 7.072484073626872e-06,
+      "loss": 0.6875,
+      "step": 136
+    },
+    {
+      "epoch": 2.1746031746031744,
+      "grad_norm": 0.6709913679680917,
+      "learning_rate": 7.021844890431136e-06,
+      "loss": 0.7669,
+      "step": 137
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.5782700607354144,
+      "learning_rate": 6.970956551866925e-06,
+      "loss": 0.7273,
+      "step": 138
+    },
+    {
+      "epoch": 2.2063492063492065,
+      "grad_norm": 0.5008612890527109,
+      "learning_rate": 6.9198253289903515e-06,
+      "loss": 0.6634,
+      "step": 139
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.5733594756270326,
+      "learning_rate": 6.868457522788561e-06,
+      "loss": 0.7358,
+      "step": 140
+    },
+    {
+      "epoch": 2.238095238095238,
+      "grad_norm": 0.48532685396257946,
+      "learning_rate": 6.816859463403271e-06,
+      "loss": 0.659,
+      "step": 141
+    },
+    {
+      "epoch": 2.253968253968254,
+      "grad_norm": 0.5460096768726493,
+      "learning_rate": 6.765037509350685e-06,
+      "loss": 0.7585,
+      "step": 142
+    },
+    {
+      "epoch": 2.2698412698412698,
+      "grad_norm": 0.4827715321224934,
+      "learning_rate": 6.7129980467379265e-06,
+      "loss": 0.6664,
+      "step": 143
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.5417449745700821,
+      "learning_rate": 6.660747488476066e-06,
+      "loss": 0.663,
+      "step": 144
+    },
+    {
+      "epoch": 2.3015873015873014,
+      "grad_norm": 0.5672091588208017,
+      "learning_rate": 6.608292273489851e-06,
+      "loss": 0.6122,
+      "step": 145
+    },
+    {
+      "epoch": 2.317460317460317,
+      "grad_norm": 0.5264115445856029,
+      "learning_rate": 6.555638865924221e-06,
+      "loss": 0.7035,
+      "step": 146
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.5168486054014866,
+      "learning_rate": 6.502793754347721e-06,
+      "loss": 0.7598,
+      "step": 147
+    },
+    {
+      "epoch": 2.3492063492063493,
+      "grad_norm": 0.6085627519823247,
+      "learning_rate": 6.449763450952912e-06,
+      "loss": 0.6875,
+      "step": 148
+    },
+    {
+      "epoch": 2.365079365079365,
+      "grad_norm": 0.504951049632705,
+      "learning_rate": 6.396554490753848e-06,
+      "loss": 0.6839,
+      "step": 149
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.42239268629753335,
+      "learning_rate": 6.343173430780769e-06,
+      "loss": 0.8396,
+      "step": 150
+    },
+    {
+      "epoch": 2.3968253968253967,
+      "grad_norm": 0.5170870251352963,
+      "learning_rate": 6.289626849272062e-06,
+      "loss": 0.8013,
+      "step": 151
+    },
+    {
+      "epoch": 2.4126984126984126,
+      "grad_norm": 0.5408561718958109,
+      "learning_rate": 6.2359213448636104e-06,
+      "loss": 0.754,
+      "step": 152
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.42606389993166277,
+      "learning_rate": 6.182063535775634e-06,
+      "loss": 0.7662,
+      "step": 153
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.41021417431281776,
+      "learning_rate": 6.1280600589971225e-06,
+      "loss": 0.791,
+      "step": 154
+    },
+    {
+      "epoch": 2.4603174603174605,
+      "grad_norm": 0.4068459581892925,
+      "learning_rate": 6.073917569467934e-06,
+      "loss": 0.8066,
+      "step": 155
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.40243757072180364,
+      "learning_rate": 6.0196427392587085e-06,
+      "loss": 0.7061,
+      "step": 156
+    },
+    {
+      "epoch": 2.492063492063492,
+      "grad_norm": 0.5924677871750427,
+      "learning_rate": 5.96524225674865e-06,
+      "loss": 0.744,
+      "step": 157
+    },
+    {
+      "epoch": 2.507936507936508,
+      "grad_norm": 0.4344103520994765,
+      "learning_rate": 5.9107228258013085e-06,
+      "loss": 0.7076,
+      "step": 158
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "grad_norm": 0.4824828219676673,
+      "learning_rate": 5.856091164938451e-06,
+      "loss": 0.6534,
+      "step": 159
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.4197375023372333,
+      "learning_rate": 5.801354006512127e-06,
+      "loss": 0.6902,
+      "step": 160
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 0.4523354962317184,
+      "learning_rate": 5.746518095875033e-06,
+      "loss": 0.6996,
+      "step": 161
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.41073692830700287,
+      "learning_rate": 5.6915901905492586e-06,
+      "loss": 0.629,
+      "step": 162
+    },
+    {
+      "epoch": 2.5873015873015874,
+      "grad_norm": 0.5807356357914126,
+      "learning_rate": 5.6365770593935665e-06,
+      "loss": 0.5924,
+      "step": 163
+    },
+    {
+      "epoch": 2.6031746031746033,
+      "grad_norm": 0.5296154741304107,
+      "learning_rate": 5.581485481769231e-06,
+      "loss": 0.7197,
+      "step": 164
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.4462893254042338,
+      "learning_rate": 5.526322246704628e-06,
+      "loss": 0.8007,
+      "step": 165
+    },
+    {
+      "epoch": 2.634920634920635,
+      "grad_norm": 0.3974463949753287,
+      "learning_rate": 5.471094152058592e-06,
+      "loss": 0.6822,
+      "step": 166
+    },
+    {
+      "epoch": 2.6507936507936507,
+      "grad_norm": 0.46244966479154553,
+      "learning_rate": 5.415808003682717e-06,
+      "loss": 0.7318,
+      "step": 167
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.438557400530548,
+      "learning_rate": 5.360470614582661e-06,
+      "loss": 0.7147,
+      "step": 168
+    },
+    {
+      "epoch": 2.682539682539683,
+      "grad_norm": 0.5680373876053647,
+      "learning_rate": 5.305088804078559e-06,
+      "loss": 0.7357,
+      "step": 169
+    },
+    {
+      "epoch": 2.6984126984126986,
+      "grad_norm": 0.4556205137087138,
+      "learning_rate": 5.249669396964665e-06,
+      "loss": 0.6361,
+      "step": 170
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.44940699263796485,
+      "learning_rate": 5.1942192226683385e-06,
+      "loss": 0.7778,
+      "step": 171
+    },
+    {
+      "epoch": 2.7301587301587302,
+      "grad_norm": 0.47535854965434626,
+      "learning_rate": 5.138745114408427e-06,
+      "loss": 0.6008,
+      "step": 172
+    },
+    {
+      "epoch": 2.746031746031746,
+      "grad_norm": 0.5020715004802897,
+      "learning_rate": 5.083253908353193e-06,
+      "loss": 0.6696,
+      "step": 173
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.4715489187155987,
+      "learning_rate": 5.0277524427778986e-06,
+      "loss": 0.7846,
+      "step": 174
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.44938039077917374,
+      "learning_rate": 4.972247557222102e-06,
+      "loss": 0.7187,
+      "step": 175
+    },
+    {
+      "epoch": 2.7936507936507935,
+      "grad_norm": 0.536309868809644,
+      "learning_rate": 4.916746091646808e-06,
+      "loss": 0.6818,
+      "step": 176
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "grad_norm": 0.4238224566275176,
+      "learning_rate": 4.8612548855915755e-06,
+      "loss": 0.7252,
+      "step": 177
+    },
+    {
+      "epoch": 2.825396825396825,
+      "grad_norm": 0.5075369152051689,
+      "learning_rate": 4.805780777331662e-06,
+      "loss": 0.7461,
+      "step": 178
+    },
+    {
+      "epoch": 2.8412698412698414,
+      "grad_norm": 0.463068134108742,
+      "learning_rate": 4.750330603035336e-06,
+      "loss": 0.7141,
+      "step": 179
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.44910366292391646,
+      "learning_rate": 4.694911195921443e-06,
+      "loss": 0.7278,
+      "step": 180
+    },
+    {
+      "epoch": 2.873015873015873,
+      "grad_norm": 0.43362119780351166,
+      "learning_rate": 4.6395293854173395e-06,
+      "loss": 0.6069,
+      "step": 181
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.7285135499415637,
+      "learning_rate": 4.584191996317285e-06,
+      "loss": 0.6846,
+      "step": 182
+    },
+    {
+      "epoch": 2.9047619047619047,
+      "grad_norm": 0.49976201370002465,
+      "learning_rate": 4.528905847941411e-06,
+      "loss": 0.843,
+      "step": 183
+    },
+    {
+      "epoch": 2.9206349206349205,
+      "grad_norm": 0.47745344638517,
+      "learning_rate": 4.473677753295375e-06,
+      "loss": 0.6609,
+      "step": 184
+    },
+    {
+      "epoch": 2.9365079365079367,
+      "grad_norm": 0.4075892143069301,
+      "learning_rate": 4.418514518230769e-06,
+      "loss": 0.7133,
+      "step": 185
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.490679894902017,
+      "learning_rate": 4.363422940606435e-06,
+      "loss": 0.7483,
+      "step": 186
+    },
+    {
+      "epoch": 2.9682539682539684,
+      "grad_norm": 0.507751484260846,
+      "learning_rate": 4.308409809450742e-06,
+      "loss": 0.7635,
+      "step": 187
+    },
+    {
+      "epoch": 2.984126984126984,
+      "grad_norm": 0.5129728167302848,
+      "learning_rate": 4.253481904124968e-06,
+      "loss": 0.7353,
+      "step": 188
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.44280290900369257,
+      "learning_rate": 4.198645993487872e-06,
+      "loss": 0.6059,
+      "step": 189
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 47138450767872.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76762bc73f1e2fba3a83ca81b4ef3adb9e3eced24616582f4647171a7638edbf
+size 8081