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:a31243ce1a484490b7fe212ac74fa302187bcea3a7c779fae46588afb2eb748a
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb032d065d6bb98f7ec8f02526d60675b444a530b971aae5bd57e2e903a5536
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d55c71eb933b0845379b71e0fa3e8a4489b8f09cd074863c5ca1b81e8ea2d7
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2331e1acdb46bfe84c16e718cc227d95263de73ac55b58fdac53cf80fafd1ec
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:066f8777723a65fd69cef1f1941f23fbbee9522129fdf0e128b5b4c4bea8b1ce
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd5f26414cc0864b93baa8ecb6812e2af41cb3ac3f53cb812b0db11d7247706
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76bb883f90de2de0cac5e67f767ce8f710a1e13954adcb91aa07dc5af5b49e1e
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1a9856d25deda68455ce3bab715340e11110aed523e4e00a01f1b7c1c65c2a
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc8edd0c51e943038a185a44014f79981bb0bfc084e21a2fb03d7835d1b95ad1
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6000f8abfc13cb60fd888425ddbebf3dd723b8bd45c010fbabba2ac821f09f08
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb28c92f3976144eaac79707a3bdeef3386cdbb187f999c2e52258e574d37b28
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362e8b8af782e9e49ec7fd725773cf94312d35575292f36e1e11eece34c9ad85
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3e4b0c73d66af381e666dc224a4d7a666385f2f98810bbb6aabc3b8cafd0c3
+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 +1,643 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 87,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 2.067296788002129,
+      "learning_rate": 0.0,
+      "loss": 0.866,
+      "step": 1
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 2.290485750060095,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 1.043,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 1.8761831403153433,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.9406,
+      "step": 3
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 1.5348726385452636,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.9753,
+      "step": 4
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 2.451336617862282,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.9902,
+      "step": 5
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 3.321340013917274,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.9761,
+      "step": 6
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 2.813148280382836,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.9736,
+      "step": 7
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 1.5924965375006837,
+      "learning_rate": 5e-05,
+      "loss": 0.9838,
+      "step": 8
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 1.5690611350244767,
+      "learning_rate": 4.9993025930300686e-05,
+      "loss": 0.9958,
+      "step": 9
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.3166502579359358,
+      "learning_rate": 4.99721076122146e-05,
+      "loss": 0.9588,
+      "step": 10
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 1.136691779583638,
+      "learning_rate": 4.9937256716606394e-05,
+      "loss": 0.8503,
+      "step": 11
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.8350469358137226,
+      "learning_rate": 4.9888492687682096e-05,
+      "loss": 0.8724,
+      "step": 12
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 0.7872759895415901,
+      "learning_rate": 4.982584273214061e-05,
+      "loss": 0.9391,
+      "step": 13
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.7631657638189762,
+      "learning_rate": 4.9749341803994465e-05,
+      "loss": 0.8446,
+      "step": 14
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.6807894928709346,
+      "learning_rate": 4.965903258506806e-05,
+      "loss": 0.8727,
+      "step": 15
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.5683155258085846,
+      "learning_rate": 4.955496546118439e-05,
+      "loss": 0.8189,
+      "step": 16
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.7801939464768173,
+      "learning_rate": 4.9437198494053464e-05,
+      "loss": 0.9303,
+      "step": 17
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.5867664533954665,
+      "learning_rate": 4.9305797388878264e-05,
+      "loss": 0.83,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5567512617299766,
+      "learning_rate": 4.916083545769607e-05,
+      "loss": 0.8938,
+      "step": 19
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.5135799351938194,
+      "learning_rate": 4.9002393578475816e-05,
+      "loss": 0.8907,
+      "step": 20
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.5604879970565443,
+      "learning_rate": 4.883056014999423e-05,
+      "loss": 0.8582,
+      "step": 21
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.5008974828940795,
+      "learning_rate": 4.864543104251587e-05,
+      "loss": 0.8132,
+      "step": 22
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.5351207184045396,
+      "learning_rate": 4.8447109544304636e-05,
+      "loss": 0.8775,
+      "step": 23
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.48534815393327974,
+      "learning_rate": 4.823570630399665e-05,
+      "loss": 0.8478,
+      "step": 24
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.4766396695563186,
+      "learning_rate": 4.8011339268866505e-05,
+      "loss": 0.8363,
+      "step": 25
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.4856803005330466,
+      "learning_rate": 4.7774133619021514e-05,
+      "loss": 0.9035,
+      "step": 26
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.3964013618666619,
+      "learning_rate": 4.752422169756048e-05,
+      "loss": 0.8033,
+      "step": 27
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.48912255110703906,
+      "learning_rate": 4.726174293673612e-05,
+      "loss": 0.8316,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.48912255110703906,
+      "learning_rate": 4.698684378016222e-05,
+      "loss": 0.6913,
+      "step": 29
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.9512574190630522,
+      "learning_rate": 4.669967760110908e-05,
+      "loss": 0.7426,
+      "step": 30
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 0.5119153708536178,
+      "learning_rate": 4.6400404616932505e-05,
+      "loss": 0.705,
+      "step": 31
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.5326897543607073,
+      "learning_rate": 4.608919179968457e-05,
+      "loss": 0.7502,
+      "step": 32
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.7107030254650039,
+      "learning_rate": 4.576621278295558e-05,
+      "loss": 0.7215,
+      "step": 33
+    },
+    {
+      "epoch": 1.1754385964912282,
+      "grad_norm": 0.6935703731339729,
+      "learning_rate": 4.5431647764999455e-05,
+      "loss": 0.6888,
+      "step": 34
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.5468190267311956,
+      "learning_rate": 4.5085683408196535e-05,
+      "loss": 0.7342,
+      "step": 35
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 0.6166217447509906,
+      "learning_rate": 4.4728512734909844e-05,
+      "loss": 0.7456,
+      "step": 36
+    },
+    {
+      "epoch": 1.280701754385965,
+      "grad_norm": 0.9130217986036923,
+      "learning_rate": 4.436033501979299e-05,
+      "loss": 0.7106,
+      "step": 37
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.5281267490436047,
+      "learning_rate": 4.398135567860972e-05,
+      "loss": 0.693,
+      "step": 38
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 0.5213754312271124,
+      "learning_rate": 4.3591786153627247e-05,
+      "loss": 0.6418,
+      "step": 39
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 0.5481623741259232,
+      "learning_rate": 4.319184379564716e-05,
+      "loss": 0.7452,
+      "step": 40
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.6014133516410636,
+      "learning_rate": 4.2781751742739885e-05,
+      "loss": 0.686,
+      "step": 41
+    },
+    {
+      "epoch": 1.456140350877193,
+      "grad_norm": 0.44416005870003245,
+      "learning_rate": 4.2361738795750214e-05,
+      "loss": 0.6433,
+      "step": 42
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 0.46835862575073184,
+      "learning_rate": 4.193203929064353e-05,
+      "loss": 0.6381,
+      "step": 43
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.5015932878379395,
+      "learning_rate": 4.1492892967763686e-05,
+      "loss": 0.7615,
+      "step": 44
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 0.49117089644567374,
+      "learning_rate": 4.1044544838075794e-05,
+      "loss": 0.7258,
+      "step": 45
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 0.4310052429661563,
+      "learning_rate": 4.058724504646834e-05,
+      "loss": 0.6558,
+      "step": 46
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.46975098597348564,
+      "learning_rate": 4.012124873219094e-05,
+      "loss": 0.6587,
+      "step": 47
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.46564012035747604,
+      "learning_rate": 3.964681588650562e-05,
+      "loss": 0.7071,
+      "step": 48
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 0.4292070243922818,
+      "learning_rate": 3.916421120763106e-05,
+      "loss": 0.7292,
+      "step": 49
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.4700066192248402,
+      "learning_rate": 3.867370395306068e-05,
+      "loss": 0.7118,
+      "step": 50
+    },
+    {
+      "epoch": 1.7719298245614035,
+      "grad_norm": 0.41414590310746596,
+      "learning_rate": 3.817556778933698e-05,
+      "loss": 0.7187,
+      "step": 51
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 0.4934164034770572,
+      "learning_rate": 3.7670080639366004e-05,
+      "loss": 0.7425,
+      "step": 52
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.4258237994121863,
+      "learning_rate": 3.715752452735704e-05,
+      "loss": 0.5943,
+      "step": 53
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 0.5078698766882597,
+      "learning_rate": 3.6638185421474084e-05,
+      "loss": 0.7346,
+      "step": 54
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 0.44841215920564664,
+      "learning_rate": 3.61123530742869e-05,
+      "loss": 0.6742,
+      "step": 55
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.39580481306947396,
+      "learning_rate": 3.5580320861110625e-05,
+      "loss": 0.7273,
+      "step": 56
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 0.48313542261877046,
+      "learning_rate": 3.504238561632424e-05,
+      "loss": 0.732,
+      "step": 57
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8524767663864421,
+      "learning_rate": 3.4498847467759e-05,
+      "loss": 0.6104,
+      "step": 58
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 0.9497059015721913,
+      "learning_rate": 3.3950009669249497e-05,
+      "loss": 0.5313,
+      "step": 59
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 2.6382740891339025,
+      "learning_rate": 3.339617843144057e-05,
+      "loss": 0.6382,
+      "step": 60
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 2.9127895766727887,
+      "learning_rate": 3.2837662750944535e-05,
+      "loss": 0.557,
+      "step": 61
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 0.5994326492557629,
+      "learning_rate": 3.227477423794412e-05,
+      "loss": 0.5275,
+      "step": 62
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 0.7402586486266488,
+      "learning_rate": 3.170782694233712e-05,
+      "loss": 0.5685,
+      "step": 63
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.8114992716723906,
+      "learning_rate": 3.1137137178519985e-05,
+      "loss": 0.5608,
+      "step": 64
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.4638568586846813,
+      "learning_rate": 3.056302334890786e-05,
+      "loss": 0.5008,
+      "step": 65
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.5045959497131294,
+      "learning_rate": 2.9985805766289817e-05,
+      "loss": 0.5395,
+      "step": 66
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.5579563118760068,
+      "learning_rate": 2.9405806475118048e-05,
+      "loss": 0.5138,
+      "step": 67
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.5637466858166899,
+      "learning_rate": 2.882334907183115e-05,
+      "loss": 0.5698,
+      "step": 68
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 0.4578787068510027,
+      "learning_rate": 2.8238758524311314e-05,
+      "loss": 0.5291,
+      "step": 69
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.761131940332416,
+      "learning_rate": 2.7652360990576453e-05,
+      "loss": 0.6047,
+      "step": 70
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.5221912763262103,
+      "learning_rate": 2.7064483636808313e-05,
+      "loss": 0.5368,
+      "step": 71
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 0.469481484634673,
+      "learning_rate": 2.6475454454818073e-05,
+      "loss": 0.5374,
+      "step": 72
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.48764324851448193,
+      "learning_rate": 2.5885602079051353e-05,
+      "loss": 0.4709,
+      "step": 73
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 0.5222547729689572,
+      "learning_rate": 2.529525560323462e-05,
+      "loss": 0.5577,
+      "step": 74
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.48783850266999607,
+      "learning_rate": 2.470474439676539e-05,
+      "loss": 0.5425,
+      "step": 75
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.5489576835164317,
+      "learning_rate": 2.4114397920948657e-05,
+      "loss": 0.5442,
+      "step": 76
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.43701838993444003,
+      "learning_rate": 2.3524545545181933e-05,
+      "loss": 0.5711,
+      "step": 77
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 0.3981876016589946,
+      "learning_rate": 2.2935516363191693e-05,
+      "loss": 0.5559,
+      "step": 78
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.43288188752005125,
+      "learning_rate": 2.2347639009423553e-05,
+      "loss": 0.5459,
+      "step": 79
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 0.3879671575828641,
+      "learning_rate": 2.1761241475688695e-05,
+      "loss": 0.4994,
+      "step": 80
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.36710005595302997,
+      "learning_rate": 2.117665092816885e-05,
+      "loss": 0.4588,
+      "step": 81
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.4298634595452112,
+      "learning_rate": 2.059419352488196e-05,
+      "loss": 0.5301,
+      "step": 82
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 0.37298113858035087,
+      "learning_rate": 2.0014194233710193e-05,
+      "loss": 0.5323,
+      "step": 83
+    },
+    {
+      "epoch": 2.912280701754386,
+      "grad_norm": 0.4497970060495327,
+      "learning_rate": 1.9436976651092144e-05,
+      "loss": 0.564,
+      "step": 84
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.4115774413493238,
+      "learning_rate": 1.8862862821480025e-05,
+      "loss": 0.4881,
+      "step": 85
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 0.3499066739001436,
+      "learning_rate": 1.829217305766289e-05,
+      "loss": 0.5444,
+      "step": 86
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3499066739001436,
+      "learning_rate": 1.7725225762055887e-05,
+      "loss": 0.3119,
+      "step": 87
+    }
+  ],
+  "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": 39139677044736.0,
+  "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 sha256:3e7473c7405e26df8a55874b9462727752541cd2f5d83fefdcad86afb11468a3
+size 8081