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
+}

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": "4.51.3",
+  "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": "4.51.3"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0a1a0ef19972a300639a14682cd5bbbd5fad8397bea8fa6ae6f6f9cbeff6d8
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1acd3dfeba94ecce8c4d9eee7cf94d1f80250071a0f16e4a9eb7fa70ab1d572
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e00cccdcb8acd4cb417765ca1dec250e34a249b1e6f85e24ccbe02f7e96709
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7343909464b8d51a4c1fb1391b252293405d70cf180cce3ebe1648a0ae569f01
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec65ce119954a55e25b3b36fbd11cdea9e2c420ca7cbbb8db4ce145435a010b8
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3330e3f7a6b1fb624f3892b251ed2f754e9f3a3d91afd3a3adcf0fa5c152e5
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a7b3410bdf366e2e8d945e8d36f0be8c635e052e0a7816166fce77fada82cf
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2deb6daf4de400103731ddd21ee9e891f40fdef5e83d8812d8ba3766b321064e
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb446d54fd1a40ec6eff617b8dafc5b8fe84ad59c8be40454aaf6103d08c273
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec4b1a1c0b5f58b5f0d9893a3cc96b25b3dc273543368a732ab4e73cf3fa602
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e86580de378a8399bc88d975680f3c5c8a75be65e62be27050f4d333537c06f
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7208cfb863867868efed0395719e87a03c88d20b9e84176fb977b9739c8126
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a98994bb7ac111edc2141478167950dc56a9be2788307bac6b64a758d984653
+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 +1,241 @@
+{
+  "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 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.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').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        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- 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 +1,846 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 2.0672700448576804,
+      "learning_rate": 0.0,
+      "loss": 0.866,
+      "step": 1
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 2.2902360202645,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 1.043,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2.064587564315747,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.9479,
+      "step": 3
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 2.1456251662755625,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 1.0053,
+      "step": 4
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 2.118290312395124,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.0228,
+      "step": 5
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 1.9727110398188104,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.9994,
+      "step": 6
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 1.811780274017235,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.9832,
+      "step": 7
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 1.60280335465616,
+      "learning_rate": 5e-06,
+      "loss": 1.0057,
+      "step": 8
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 1.4946232465242921,
+      "learning_rate": 4.999302593030069e-06,
+      "loss": 1.0198,
+      "step": 9
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.219848341043154,
+      "learning_rate": 4.99721076122146e-06,
+      "loss": 0.9945,
+      "step": 10
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 1.0507879904789832,
+      "learning_rate": 4.99372567166064e-06,
+      "loss": 0.8896,
+      "step": 11
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.2565080469257828,
+      "learning_rate": 4.98884926876821e-06,
+      "loss": 0.9066,
+      "step": 12
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 1.3416635061508715,
+      "learning_rate": 4.982584273214061e-06,
+      "loss": 0.973,
+      "step": 13
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 1.1635476799198454,
+      "learning_rate": 4.974934180399447e-06,
+      "loss": 0.8802,
+      "step": 14
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.2273198837996009,
+      "learning_rate": 4.965903258506806e-06,
+      "loss": 0.9058,
+      "step": 15
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.9397916351800223,
+      "learning_rate": 4.955496546118439e-06,
+      "loss": 0.851,
+      "step": 16
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.8970172914695361,
+      "learning_rate": 4.943719849405347e-06,
+      "loss": 0.959,
+      "step": 17
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.8557735235888474,
+      "learning_rate": 4.930579738887827e-06,
+      "loss": 0.8591,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.8228693160594547,
+      "learning_rate": 4.9160835457696075e-06,
+      "loss": 0.9227,
+      "step": 19
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.9746558682735013,
+      "learning_rate": 4.900239357847582e-06,
+      "loss": 0.9185,
+      "step": 20
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.783405238430667,
+      "learning_rate": 4.883056014999423e-06,
+      "loss": 0.8853,
+      "step": 21
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 1.1560714233050355,
+      "learning_rate": 4.864543104251587e-06,
+      "loss": 0.837,
+      "step": 22
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.6779891999963303,
+      "learning_rate": 4.844710954430464e-06,
+      "loss": 0.9006,
+      "step": 23
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.6140368603132732,
+      "learning_rate": 4.823570630399665e-06,
+      "loss": 0.8713,
+      "step": 24
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.5959623784138675,
+      "learning_rate": 4.8011339268866505e-06,
+      "loss": 0.8573,
+      "step": 25
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.6645642684704514,
+      "learning_rate": 4.777413361902152e-06,
+      "loss": 0.9244,
+      "step": 26
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.5749254662708289,
+      "learning_rate": 4.752422169756048e-06,
+      "loss": 0.8214,
+      "step": 27
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.49471199829315,
+      "learning_rate": 4.726174293673612e-06,
+      "loss": 0.8501,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.49471199829315,
+      "learning_rate": 4.698684378016223e-06,
+      "loss": 0.7761,
+      "step": 29
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.8408225702174914,
+      "learning_rate": 4.669967760110908e-06,
+      "loss": 0.8702,
+      "step": 30
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 0.5019249070368396,
+      "learning_rate": 4.6400404616932505e-06,
+      "loss": 0.8376,
+      "step": 31
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.4303555090359822,
+      "learning_rate": 4.608919179968457e-06,
+      "loss": 0.8834,
+      "step": 32
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.446333451933402,
+      "learning_rate": 4.576621278295558e-06,
+      "loss": 0.8631,
+      "step": 33
+    },
+    {
+      "epoch": 1.1754385964912282,
+      "grad_norm": 0.4783577116779664,
+      "learning_rate": 4.543164776499945e-06,
+      "loss": 0.8283,
+      "step": 34
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.4079076293014929,
+      "learning_rate": 4.508568340819654e-06,
+      "loss": 0.8868,
+      "step": 35
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 0.40536005006600634,
+      "learning_rate": 4.472851273490985e-06,
+      "loss": 0.8674,
+      "step": 36
+    },
+    {
+      "epoch": 1.280701754385965,
+      "grad_norm": 0.4152500781803562,
+      "learning_rate": 4.436033501979299e-06,
+      "loss": 0.859,
+      "step": 37
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.4347010646426558,
+      "learning_rate": 4.398135567860972e-06,
+      "loss": 0.8254,
+      "step": 38
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 0.3788287405374111,
+      "learning_rate": 4.359178615362725e-06,
+      "loss": 0.7829,
+      "step": 39
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 0.4670693473167291,
+      "learning_rate": 4.319184379564716e-06,
+      "loss": 0.8918,
+      "step": 40
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.47835984972537143,
+      "learning_rate": 4.278175174273989e-06,
+      "loss": 0.8179,
+      "step": 41
+    },
+    {
+      "epoch": 1.456140350877193,
+      "grad_norm": 0.4499444593333873,
+      "learning_rate": 4.236173879575022e-06,
+      "loss": 0.7871,
+      "step": 42
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 0.3878622142611574,
+      "learning_rate": 4.1932039290643534e-06,
+      "loss": 0.7789,
+      "step": 43
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.3316720314372251,
+      "learning_rate": 4.149289296776369e-06,
+      "loss": 0.91,
+      "step": 44
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 0.36941265676632506,
+      "learning_rate": 4.104454483807579e-06,
+      "loss": 0.8607,
+      "step": 45
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 0.3620626145776103,
+      "learning_rate": 4.058724504646834e-06,
+      "loss": 0.7937,
+      "step": 46
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.3338291240702826,
+      "learning_rate": 4.012124873219094e-06,
+      "loss": 0.7815,
+      "step": 47
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.472336322290524,
+      "learning_rate": 3.964681588650562e-06,
+      "loss": 0.8394,
+      "step": 48
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 0.3420578655212163,
+      "learning_rate": 3.916421120763106e-06,
+      "loss": 0.8502,
+      "step": 49
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.38000589787590366,
+      "learning_rate": 3.8673703953060685e-06,
+      "loss": 0.8347,
+      "step": 50
+    },
+    {
+      "epoch": 1.7719298245614035,
+      "grad_norm": 0.3654714309302888,
+      "learning_rate": 3.817556778933697e-06,
+      "loss": 0.8581,
+      "step": 51
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 0.3918540158095545,
+      "learning_rate": 3.7670080639366e-06,
+      "loss": 0.8769,
+      "step": 52
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.35070825923075866,
+      "learning_rate": 3.7157524527357036e-06,
+      "loss": 0.7163,
+      "step": 53
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 0.35412184971484173,
+      "learning_rate": 3.663818542147409e-06,
+      "loss": 0.8756,
+      "step": 54
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 0.3580769918085387,
+      "learning_rate": 3.61123530742869e-06,
+      "loss": 0.8221,
+      "step": 55
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.33901277879515357,
+      "learning_rate": 3.5580320861110627e-06,
+      "loss": 0.8703,
+      "step": 56
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 0.3463865269661244,
+      "learning_rate": 3.5042385616324243e-06,
+      "loss": 0.8721,
+      "step": 57
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5122368904802833,
+      "learning_rate": 3.4498847467759e-06,
+      "loss": 0.8607,
+      "step": 58
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 0.32344238659596863,
+      "learning_rate": 3.3950009669249502e-06,
+      "loss": 0.7811,
+      "step": 59
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.35108823806290596,
+      "learning_rate": 3.3396178431440572e-06,
+      "loss": 0.9217,
+      "step": 60
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.30984522709441403,
+      "learning_rate": 3.283766275094454e-06,
+      "loss": 0.7985,
+      "step": 61
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 0.34747230260102224,
+      "learning_rate": 3.227477423794412e-06,
+      "loss": 0.7911,
+      "step": 62
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 0.3139893028606255,
+      "learning_rate": 3.1707826942337124e-06,
+      "loss": 0.8368,
+      "step": 63
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.32074434133002094,
+      "learning_rate": 3.1137137178519983e-06,
+      "loss": 0.8602,
+      "step": 64
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.33796734180843035,
+      "learning_rate": 3.056302334890786e-06,
+      "loss": 0.7477,
+      "step": 65
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.308432104905017,
+      "learning_rate": 2.9985805766289815e-06,
+      "loss": 0.808,
+      "step": 66
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.3123660916517458,
+      "learning_rate": 2.940580647511805e-06,
+      "loss": 0.7912,
+      "step": 67
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.3406699289606851,
+      "learning_rate": 2.8823349071831154e-06,
+      "loss": 0.857,
+      "step": 68
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 0.3063945394190306,
+      "learning_rate": 2.8238758524311316e-06,
+      "loss": 0.7817,
+      "step": 69
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.31851738409569996,
+      "learning_rate": 2.7652360990576457e-06,
+      "loss": 0.9036,
+      "step": 70
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.3145120103359264,
+      "learning_rate": 2.7064483636808314e-06,
+      "loss": 0.8149,
+      "step": 71
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 0.3050076260239972,
+      "learning_rate": 2.6475454454818072e-06,
+      "loss": 0.8372,
+      "step": 72
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.30681790274996473,
+      "learning_rate": 2.5885602079051354e-06,
+      "loss": 0.7604,
+      "step": 73
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 0.314110412232156,
+      "learning_rate": 2.529525560323462e-06,
+      "loss": 0.8005,
+      "step": 74
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.3236785830234266,
+      "learning_rate": 2.470474439676539e-06,
+      "loss": 0.8168,
+      "step": 75
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.359656431397916,
+      "learning_rate": 2.411439792094866e-06,
+      "loss": 0.8402,
+      "step": 76
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.32366656133415905,
+      "learning_rate": 2.3524545545181936e-06,
+      "loss": 0.8668,
+      "step": 77
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 0.3262664895219039,
+      "learning_rate": 2.2935516363191695e-06,
+      "loss": 0.8343,
+      "step": 78
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.3081673146324169,
+      "learning_rate": 2.234763900942355e-06,
+      "loss": 0.8084,
+      "step": 79
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 0.32923845454809364,
+      "learning_rate": 2.1761241475688697e-06,
+      "loss": 0.7564,
+      "step": 80
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.3103638917941097,
+      "learning_rate": 2.117665092816885e-06,
+      "loss": 0.7423,
+      "step": 81
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.32527138845292275,
+      "learning_rate": 2.059419352488196e-06,
+      "loss": 0.8292,
+      "step": 82
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 0.31114889374241994,
+      "learning_rate": 2.0014194233710193e-06,
+      "loss": 0.8229,
+      "step": 83
+    },
+    {
+      "epoch": 2.912280701754386,
+      "grad_norm": 0.3119716096545865,
+      "learning_rate": 1.9436976651092143e-06,
+      "loss": 0.829,
+      "step": 84
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.31910821914661397,
+      "learning_rate": 1.8862862821480023e-06,
+      "loss": 0.7703,
+      "step": 85
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 0.31035281270338383,
+      "learning_rate": 1.829217305766289e-06,
+      "loss": 0.8182,
+      "step": 86
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.31035281270338383,
+      "learning_rate": 1.772522576205589e-06,
+      "loss": 0.6834,
+      "step": 87
+    },
+    {
+      "epoch": 3.0350877192982457,
+      "grad_norm": 0.6381501820358972,
+      "learning_rate": 1.7162337249055478e-06,
+      "loss": 0.7985,
+      "step": 88
+    },
+    {
+      "epoch": 3.0701754385964914,
+      "grad_norm": 0.34108098057965985,
+      "learning_rate": 1.6603821568559436e-06,
+      "loss": 0.8813,
+      "step": 89
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.3119218127003693,
+      "learning_rate": 1.6049990330750508e-06,
+      "loss": 0.8332,
+      "step": 90
+    },
+    {
+      "epoch": 3.1403508771929824,
+      "grad_norm": 0.31753762794893836,
+      "learning_rate": 1.5501152532241003e-06,
+      "loss": 0.8085,
+      "step": 91
+    },
+    {
+      "epoch": 3.175438596491228,
+      "grad_norm": 0.26210667369890633,
+      "learning_rate": 1.495761438367577e-06,
+      "loss": 0.7937,
+      "step": 92
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.3412780118816683,
+      "learning_rate": 1.4419679138889379e-06,
+      "loss": 0.9124,
+      "step": 93
+    },
+    {
+      "epoch": 3.245614035087719,
+      "grad_norm": 0.3273535475843529,
+      "learning_rate": 1.3887646925713116e-06,
+      "loss": 0.771,
+      "step": 94
+    },
+    {
+      "epoch": 3.280701754385965,
+      "grad_norm": 0.301251838670515,
+      "learning_rate": 1.3361814578525922e-06,
+      "loss": 0.7657,
+      "step": 95
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 0.362998311924545,
+      "learning_rate": 1.2842475472642969e-06,
+      "loss": 0.8489,
+      "step": 96
+    },
+    {
+      "epoch": 3.3508771929824563,
+      "grad_norm": 0.29122608306651043,
+      "learning_rate": 1.2329919360634003e-06,
+      "loss": 0.8135,
+      "step": 97
+    },
+    {
+      "epoch": 3.3859649122807016,
+      "grad_norm": 0.29475940071935713,
+      "learning_rate": 1.182443221066303e-06,
+      "loss": 0.7059,
+      "step": 98
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.28973717877011734,
+      "learning_rate": 1.1326296046939334e-06,
+      "loss": 0.7342,
+      "step": 99
+    },
+    {
+      "epoch": 3.456140350877193,
+      "grad_norm": 0.30995625777137437,
+      "learning_rate": 1.083578879236895e-06,
+      "loss": 0.7411,
+      "step": 100
+    },
+    {
+      "epoch": 3.4912280701754383,
+      "grad_norm": 0.2859432013165172,
+      "learning_rate": 1.0353184113494386e-06,
+      "loss": 0.772,
+      "step": 101
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.30700142822195303,
+      "learning_rate": 9.878751267809069e-07,
+      "loss": 0.7557,
+      "step": 102
+    },
+    {
+      "epoch": 3.56140350877193,
+      "grad_norm": 0.27176920609301375,
+      "learning_rate": 9.412754953531664e-07,
+      "loss": 0.7729,
+      "step": 103
+    },
+    {
+      "epoch": 3.5964912280701755,
+      "grad_norm": 0.36537897752504017,
+      "learning_rate": 8.955455161924217e-07,
+      "loss": 0.7803,
+      "step": 104
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.32335411827201516,
+      "learning_rate": 8.507107032236323e-07,
+      "loss": 0.6832,
+      "step": 105
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.31630275273581865,
+      "learning_rate": 8.067960709356479e-07,
+      "loss": 0.7744,
+      "step": 106
+    },
+    {
+      "epoch": 3.7017543859649122,
+      "grad_norm": 0.3116184912362651,
+      "learning_rate": 7.638261204249783e-07,
+      "loss": 0.7719,
+      "step": 107
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.31857809248659025,
+      "learning_rate": 7.218248257260127e-07,
+      "loss": 0.8335,
+      "step": 108
+    },
+    {
+      "epoch": 3.7719298245614032,
+      "grad_norm": 0.28756539469934045,
+      "learning_rate": 6.808156204352845e-07,
+      "loss": 0.857,
+      "step": 109
+    },
+    {
+      "epoch": 3.807017543859649,
+      "grad_norm": 0.30352272859730434,
+      "learning_rate": 6.40821384637276e-07,
+      "loss": 0.8382,
+      "step": 110
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.31531467423763393,
+      "learning_rate": 6.018644321390288e-07,
+      "loss": 0.823,
+      "step": 111
+    },
+    {
+      "epoch": 3.8771929824561404,
+      "grad_norm": 0.2935691411718206,
+      "learning_rate": 5.639664980207024e-07,
+      "loss": 0.7658,
+      "step": 112
+    },
+    {
+      "epoch": 3.912280701754386,
+      "grad_norm": 0.3148692436878785,
+      "learning_rate": 5.271487265090163e-07,
+      "loss": 0.7759,
+      "step": 113
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.28756831417145856,
+      "learning_rate": 4.914316591803475e-07,
+      "loss": 0.7931,
+      "step": 114
+    },
+    {
+      "epoch": 3.982456140350877,
+      "grad_norm": 0.2919237741849252,
+      "learning_rate": 4.5683522350005505e-07,
+      "loss": 0.81,
+      "step": 115
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.4951765857412171,
+      "learning_rate": 4.23378721704443e-07,
+      "loss": 0.7612,
+      "step": 116
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 140,
+  "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": 52227047817216.0,
+  "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 sha256:2800624b036dea0ee57257a2aa781a9511f6ee015447129f0f6aa31a680e8d7f
+size 8081