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 sha256:6d33d8974b37863bd994fbb3d277592cfb1d894b318f16dac189a0a62f7d9252
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18a6e5c9c2f59c629e74c545347a548acab571525058f281af8690c238bd62a
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bac3f4a947710b06629b049e1ac6c92fa1f10b4f7f21a6752bb8828e6b4bf30
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de37b122f5b4ca0a48d03c1d36919fc64722f8f09ac2a3f492bf3043532cce8
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d2e8c177fcfa623032030be71943cd5a4764766b08ed2af352a4ea42ccc358
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12b7ea309ceeebf2bb483ff430a3ba36114ae320b6696b5e057566f0e6fbe12
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738c5188f1410f6dff7aa5933772bbc7a3344682361fa9e262e0049a7ba22cd1
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62cc6ffb9366a3bbcd8310614f8d350ffc34574e49c2d329a58e8f4b1aa3dd35
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50681a5c25c0066f892b99bf08bd7d9b664133e46844e7feb9d9407750aca3cb
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156aa3c63fa09ef87289a8244f79d4b45401fc942f1a963e0f7905b214279da0
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3281203e9738f5207abdf90a7192e14373a67159cc68ec96935564a80328a738
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72991993805608b85fae24734f1f17eac45e28bffd59549a6b96c3d13c66004
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb18d19f1b35d0de86f91b0f98583013bebf79d8d835e2744c003500bd80830e
+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 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.18066847335140018,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018066847335140017,
+      "grad_norm": 2.833585783869219,
+      "learning_rate": 0.0,
+      "loss": 0.8251,
+      "step": 1
+    },
+    {
+      "epoch": 0.0036133694670280035,
+      "grad_norm": 2.8814908232125855,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 0.8284,
+      "step": 2
+    },
+    {
+      "epoch": 0.005420054200542005,
+      "grad_norm": 2.8770896332736204,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.8426,
+      "step": 3
+    },
+    {
+      "epoch": 0.007226738934056007,
+      "grad_norm": 2.7937082319961015,
+      "learning_rate": 3.2142857142857143e-06,
+      "loss": 0.8378,
+      "step": 4
+    },
+    {
+      "epoch": 0.009033423667570008,
+      "grad_norm": 2.6064730264267317,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.8226,
+      "step": 5
+    },
+    {
+      "epoch": 0.01084010840108401,
+      "grad_norm": 2.08053811254878,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.8094,
+      "step": 6
+    },
+    {
+      "epoch": 0.012646793134598013,
+      "grad_norm": 1.4474261934350556,
+      "learning_rate": 6.428571428571429e-06,
+      "loss": 0.7737,
+      "step": 7
+    },
+    {
+      "epoch": 0.014453477868112014,
+      "grad_norm": 1.3829973165220981,
+      "learning_rate": 7.5e-06,
+      "loss": 0.7732,
+      "step": 8
+    },
+    {
+      "epoch": 0.016260162601626018,
+      "grad_norm": 1.286324724661706,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.7653,
+      "step": 9
+    },
+    {
+      "epoch": 0.018066847335140017,
+      "grad_norm": 2.3802925033552484,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 0.7502,
+      "step": 10
+    },
+    {
+      "epoch": 0.01987353206865402,
+      "grad_norm": 2.332362112237301,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.7352,
+      "step": 11
+    },
+    {
+      "epoch": 0.02168021680216802,
+      "grad_norm": 2.255275511725211,
+      "learning_rate": 1.1785714285714286e-05,
+      "loss": 0.7485,
+      "step": 12
+    },
+    {
+      "epoch": 0.023486901535682024,
+      "grad_norm": 1.862321465187453,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.7252,
+      "step": 13
+    },
+    {
+      "epoch": 0.025293586269196026,
+      "grad_norm": 1.7503296986837806,
+      "learning_rate": 1.3928571428571429e-05,
+      "loss": 0.7286,
+      "step": 14
+    },
+    {
+      "epoch": 0.02710027100271003,
+      "grad_norm": 1.3910078564328057,
+      "learning_rate": 1.5e-05,
+      "loss": 0.7179,
+      "step": 15
+    },
+    {
+      "epoch": 0.028906955736224028,
+      "grad_norm": 1.1447088267333418,
+      "learning_rate": 1.6071428571428572e-05,
+      "loss": 0.7019,
+      "step": 16
+    },
+    {
+      "epoch": 0.03071364046973803,
+      "grad_norm": 0.8309495264632762,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.6998,
+      "step": 17
+    },
+    {
+      "epoch": 0.032520325203252036,
+      "grad_norm": 0.7727537242977915,
+      "learning_rate": 1.8214285714285712e-05,
+      "loss": 0.6887,
+      "step": 18
+    },
+    {
+      "epoch": 0.03432700993676603,
+      "grad_norm": 0.8344364990521232,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 0.6834,
+      "step": 19
+    },
+    {
+      "epoch": 0.036133694670280034,
+      "grad_norm": 0.6823059422974896,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 0.6597,
+      "step": 20
+    },
+    {
+      "epoch": 0.037940379403794036,
+      "grad_norm": 0.6081366218483659,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.666,
+      "step": 21
+    },
+    {
+      "epoch": 0.03974706413730804,
+      "grad_norm": 0.5681526786044694,
+      "learning_rate": 2.25e-05,
+      "loss": 0.6549,
+      "step": 22
+    },
+    {
+      "epoch": 0.04155374887082204,
+      "grad_norm": 0.5770791293540624,
+      "learning_rate": 2.357142857142857e-05,
+      "loss": 0.6552,
+      "step": 23
+    },
+    {
+      "epoch": 0.04336043360433604,
+      "grad_norm": 0.5162292144131758,
+      "learning_rate": 2.464285714285714e-05,
+      "loss": 0.6604,
+      "step": 24
+    },
+    {
+      "epoch": 0.045167118337850046,
+      "grad_norm": 0.5490380070807557,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 0.6421,
+      "step": 25
+    },
+    {
+      "epoch": 0.04697380307136405,
+      "grad_norm": 0.4844741148097692,
+      "learning_rate": 2.6785714285714288e-05,
+      "loss": 0.6566,
+      "step": 26
+    },
+    {
+      "epoch": 0.04878048780487805,
+      "grad_norm": 0.4632816755153851,
+      "learning_rate": 2.7857142857142858e-05,
+      "loss": 0.6346,
+      "step": 27
+    },
+    {
+      "epoch": 0.05058717253839205,
+      "grad_norm": 0.47413499783511553,
+      "learning_rate": 2.892857142857143e-05,
+      "loss": 0.6372,
+      "step": 28
+    },
+    {
+      "epoch": 0.052393857271906055,
+      "grad_norm": 0.46848340364244656,
+      "learning_rate": 3e-05,
+      "loss": 0.6485,
+      "step": 29
+    },
+    {
+      "epoch": 0.05420054200542006,
+      "grad_norm": 0.4249862814563853,
+      "learning_rate": 2.9999731440137413e-05,
+      "loss": 0.649,
+      "step": 30
+    },
+    {
+      "epoch": 0.05600722673893405,
+      "grad_norm": 0.3741955197649565,
+      "learning_rate": 2.9998925770166232e-05,
+      "loss": 0.6379,
+      "step": 31
+    },
+    {
+      "epoch": 0.057813911472448055,
+      "grad_norm": 0.3881925801129848,
+      "learning_rate": 2.9997583018935875e-05,
+      "loss": 0.6262,
+      "step": 32
+    },
+    {
+      "epoch": 0.05962059620596206,
+      "grad_norm": 0.3922238715881848,
+      "learning_rate": 2.9995703234527553e-05,
+      "loss": 0.6364,
+      "step": 33
+    },
+    {
+      "epoch": 0.06142728093947606,
+      "grad_norm": 0.33920092930264795,
+      "learning_rate": 2.999328648425255e-05,
+      "loss": 0.6233,
+      "step": 34
+    },
+    {
+      "epoch": 0.06323396567299007,
+      "grad_norm": 0.38360312337448227,
+      "learning_rate": 2.999033285464982e-05,
+      "loss": 0.6291,
+      "step": 35
+    },
+    {
+      "epoch": 0.06504065040650407,
+      "grad_norm": 0.37438403307661106,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 0.6248,
+      "step": 36
+    },
+    {
+      "epoch": 0.06684733514001806,
+      "grad_norm": 0.3660585694043342,
+      "learning_rate": 2.9982815399736008e-05,
+      "loss": 0.6297,
+      "step": 37
+    },
+    {
+      "epoch": 0.06865401987353206,
+      "grad_norm": 0.3536480766826361,
+      "learning_rate": 2.9978251843609816e-05,
+      "loss": 0.6221,
+      "step": 38
+    },
+    {
+      "epoch": 0.07046070460704607,
+      "grad_norm": 0.4002479177979865,
+      "learning_rate": 2.9973151946516027e-05,
+      "loss": 0.6245,
+      "step": 39
+    },
+    {
+      "epoch": 0.07226738934056007,
+      "grad_norm": 0.3063169356732776,
+      "learning_rate": 2.996751589107167e-05,
+      "loss": 0.6123,
+      "step": 40
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.35680447479317984,
+      "learning_rate": 2.9961343879092512e-05,
+      "loss": 0.6186,
+      "step": 41
+    },
+    {
+      "epoch": 0.07588075880758807,
+      "grad_norm": 0.29028093811805317,
+      "learning_rate": 2.9954636131585845e-05,
+      "loss": 0.6117,
+      "step": 42
+    },
+    {
+      "epoch": 0.07768744354110207,
+      "grad_norm": 0.327087930172019,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 0.6116,
+      "step": 43
+    },
+    {
+      "epoch": 0.07949412827461608,
+      "grad_norm": 0.30051645313739944,
+      "learning_rate": 2.993961440992859e-05,
+      "loss": 0.6057,
+      "step": 44
+    },
+    {
+      "epoch": 0.08130081300813008,
+      "grad_norm": 0.32276337072694117,
+      "learning_rate": 2.993130097367553e-05,
+      "loss": 0.6129,
+      "step": 45
+    },
+    {
+      "epoch": 0.08310749774164408,
+      "grad_norm": 0.29149163779977444,
+      "learning_rate": 2.9922452877670775e-05,
+      "loss": 0.6145,
+      "step": 46
+    },
+    {
+      "epoch": 0.08491418247515808,
+      "grad_norm": 0.2848254537728177,
+      "learning_rate": 2.991307043874677e-05,
+      "loss": 0.6171,
+      "step": 47
+    },
+    {
+      "epoch": 0.08672086720867209,
+      "grad_norm": 0.2736548047269907,
+      "learning_rate": 2.9903153992869734e-05,
+      "loss": 0.6033,
+      "step": 48
+    },
+    {
+      "epoch": 0.08852755194218609,
+      "grad_norm": 0.3041549583089305,
+      "learning_rate": 2.989270389512756e-05,
+      "loss": 0.6108,
+      "step": 49
+    },
+    {
+      "epoch": 0.09033423667570009,
+      "grad_norm": 0.28826353495304036,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.6101,
+      "step": 50
+    },
+    {
+      "epoch": 0.0921409214092141,
+      "grad_norm": 0.28025059682410447,
+      "learning_rate": 2.9870204259931062e-05,
+      "loss": 0.6,
+      "step": 51
+    },
+    {
+      "epoch": 0.0939476061427281,
+      "grad_norm": 0.27249462262783575,
+      "learning_rate": 2.9858155528143256e-05,
+      "loss": 0.617,
+      "step": 52
+    },
+    {
+      "epoch": 0.0957542908762421,
+      "grad_norm": 0.3172471705535385,
+      "learning_rate": 2.9845574755794522e-05,
+      "loss": 0.6026,
+      "step": 53
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.24824194798422894,
+      "learning_rate": 2.9832462393376926e-05,
+      "loss": 0.5921,
+      "step": 54
+    },
+    {
+      "epoch": 0.0993676603432701,
+      "grad_norm": 0.3434388403796833,
+      "learning_rate": 2.9818818910417706e-05,
+      "loss": 0.6079,
+      "step": 55
+    },
+    {
+      "epoch": 0.1011743450767841,
+      "grad_norm": 0.30129494072287116,
+      "learning_rate": 2.9804644795462437e-05,
+      "loss": 0.6121,
+      "step": 56
+    },
+    {
+      "epoch": 0.10298102981029811,
+      "grad_norm": 0.29313587299072186,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.5974,
+      "step": 57
+    },
+    {
+      "epoch": 0.10478771454381211,
+      "grad_norm": 0.32928460639595075,
+      "learning_rate": 2.9774706718732255e-05,
+      "loss": 0.6061,
+      "step": 58
+    },
+    {
+      "epoch": 0.10659439927732611,
+      "grad_norm": 0.2680249584703676,
+      "learning_rate": 2.9758943828979444e-05,
+      "loss": 0.592,
+      "step": 59
+    },
+    {
+      "epoch": 0.10840108401084012,
+      "grad_norm": 0.34348625850914644,
+      "learning_rate": 2.9742652451236414e-05,
+      "loss": 0.5934,
+      "step": 60
+    },
+    {
+      "epoch": 0.1102077687443541,
+      "grad_norm": 0.28452776028596916,
+      "learning_rate": 2.972583316886451e-05,
+      "loss": 0.597,
+      "step": 61
+    },
+    {
+      "epoch": 0.1120144534778681,
+      "grad_norm": 0.3322182395606521,
+      "learning_rate": 2.9708486584128303e-05,
+      "loss": 0.6018,
+      "step": 62
+    },
+    {
+      "epoch": 0.11382113821138211,
+      "grad_norm": 0.30021383036006005,
+      "learning_rate": 2.9690613318173966e-05,
+      "loss": 0.6017,
+      "step": 63
+    },
+    {
+      "epoch": 0.11562782294489611,
+      "grad_norm": 0.276650237644649,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.6001,
+      "step": 64
+    },
+    {
+      "epoch": 0.11743450767841011,
+      "grad_norm": 0.5862319982197399,
+      "learning_rate": 2.9653289321469715e-05,
+      "loss": 0.5941,
+      "step": 65
+    },
+    {
+      "epoch": 0.11924119241192412,
+      "grad_norm": 0.26853876464603094,
+      "learning_rate": 2.9633839927216793e-05,
+      "loss": 0.5971,
+      "step": 66
+    },
+    {
+      "epoch": 0.12104787714543812,
+      "grad_norm": 0.2829683425685341,
+      "learning_rate": 2.9613866524691867e-05,
+      "loss": 0.5874,
+      "step": 67
+    },
+    {
+      "epoch": 0.12285456187895212,
+      "grad_norm": 0.2819305232851346,
+      "learning_rate": 2.9593369829102173e-05,
+      "loss": 0.6031,
+      "step": 68
+    },
+    {
+      "epoch": 0.12466124661246612,
+      "grad_norm": 0.27702734164669873,
+      "learning_rate": 2.957235057439301e-05,
+      "loss": 0.6047,
+      "step": 69
+    },
+    {
+      "epoch": 0.12646793134598014,
+      "grad_norm": 0.29063816468584863,
+      "learning_rate": 2.955080951322147e-05,
+      "loss": 0.6089,
+      "step": 70
+    },
+    {
+      "epoch": 0.12827461607949414,
+      "grad_norm": 0.3063448907538783,
+      "learning_rate": 2.9528747416929467e-05,
+      "loss": 0.582,
+      "step": 71
+    },
+    {
+      "epoch": 0.13008130081300814,
+      "grad_norm": 0.2996205495531954,
+      "learning_rate": 2.9506165075516148e-05,
+      "loss": 0.5989,
+      "step": 72
+    },
+    {
+      "epoch": 0.13188798554652212,
+      "grad_norm": 0.3741556351883678,
+      "learning_rate": 2.9483063297609577e-05,
+      "loss": 0.5978,
+      "step": 73
+    },
+    {
+      "epoch": 0.13369467028003612,
+      "grad_norm": 0.2987012098136024,
+      "learning_rate": 2.9459442910437798e-05,
+      "loss": 0.5894,
+      "step": 74
+    },
+    {
+      "epoch": 0.13550135501355012,
+      "grad_norm": 0.33060763601185644,
+      "learning_rate": 2.94353047597992e-05,
+      "loss": 0.5888,
+      "step": 75
+    },
+    {
+      "epoch": 0.13730803974706413,
+      "grad_norm": 0.2858723573255857,
+      "learning_rate": 2.941064971003224e-05,
+      "loss": 0.5843,
+      "step": 76
+    },
+    {
+      "epoch": 0.13911472448057813,
+      "grad_norm": 0.30513180176369226,
+      "learning_rate": 2.9385478643984484e-05,
+      "loss": 0.58,
+      "step": 77
+    },
+    {
+      "epoch": 0.14092140921409213,
+      "grad_norm": 0.3480721530294818,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 0.5909,
+      "step": 78
+    },
+    {
+      "epoch": 0.14272809394760613,
+      "grad_norm": 0.3098785903465462,
+      "learning_rate": 2.9333592086792113e-05,
+      "loss": 0.5987,
+      "step": 79
+    },
+    {
+      "epoch": 0.14453477868112014,
+      "grad_norm": 0.32360139759712253,
+      "learning_rate": 2.9306878453600382e-05,
+      "loss": 0.6078,
+      "step": 80
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.31681100648297805,
+      "learning_rate": 2.9279652519967105e-05,
+      "loss": 0.5928,
+      "step": 81
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.33637175342033093,
+      "learning_rate": 2.9251915260798024e-05,
+      "loss": 0.5851,
+      "step": 82
+    },
+    {
+      "epoch": 0.14995483288166214,
+      "grad_norm": 0.32126065455334785,
+      "learning_rate": 2.9223667669308395e-05,
+      "loss": 0.595,
+      "step": 83
+    },
+    {
+      "epoch": 0.15176151761517614,
+      "grad_norm": 0.28162115413110317,
+      "learning_rate": 2.9194910756987464e-05,
+      "loss": 0.5886,
+      "step": 84
+    },
+    {
+      "epoch": 0.15356820234869015,
+      "grad_norm": 0.2927832038468001,
+      "learning_rate": 2.9165645553562215e-05,
+      "loss": 0.5919,
+      "step": 85
+    },
+    {
+      "epoch": 0.15537488708220415,
+      "grad_norm": 0.2842368528997179,
+      "learning_rate": 2.9135873106960525e-05,
+      "loss": 0.5907,
+      "step": 86
+    },
+    {
+      "epoch": 0.15718157181571815,
+      "grad_norm": 0.3044892933421028,
+      "learning_rate": 2.9105594483273603e-05,
+      "loss": 0.5932,
+      "step": 87
+    },
+    {
+      "epoch": 0.15898825654923215,
+      "grad_norm": 0.2787616554815814,
+      "learning_rate": 2.9074810766717865e-05,
+      "loss": 0.5972,
+      "step": 88
+    },
+    {
+      "epoch": 0.16079494128274616,
+      "grad_norm": 0.31536931569551113,
+      "learning_rate": 2.904352305959606e-05,
+      "loss": 0.5941,
+      "step": 89
+    },
+    {
+      "epoch": 0.16260162601626016,
+      "grad_norm": 0.2812317162219802,
+      "learning_rate": 2.9011732482257835e-05,
+      "loss": 0.5858,
+      "step": 90
+    },
+    {
+      "epoch": 0.16440831074977416,
+      "grad_norm": 0.3243626162570077,
+      "learning_rate": 2.89794401730596e-05,
+      "loss": 0.5839,
+      "step": 91
+    },
+    {
+      "epoch": 0.16621499548328816,
+      "grad_norm": 0.31149750778219104,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 0.5879,
+      "step": 92
+    },
+    {
+      "epoch": 0.16802168021680217,
+      "grad_norm": 0.2799988189260621,
+      "learning_rate": 2.8913355002297367e-05,
+      "loss": 0.5939,
+      "step": 93
+    },
+    {
+      "epoch": 0.16982836495031617,
+      "grad_norm": 0.3659704073921071,
+      "learning_rate": 2.887956450710995e-05,
+      "loss": 0.594,
+      "step": 94
+    },
+    {
+      "epoch": 0.17163504968383017,
+      "grad_norm": 0.3155038381999107,
+      "learning_rate": 2.8845277012730963e-05,
+      "loss": 0.5857,
+      "step": 95
+    },
+    {
+      "epoch": 0.17344173441734417,
+      "grad_norm": 0.28670310893186607,
+      "learning_rate": 2.8810493746926364e-05,
+      "loss": 0.5854,
+      "step": 96
+    },
+    {
+      "epoch": 0.17524841915085818,
+      "grad_norm": 0.3027782704454321,
+      "learning_rate": 2.87752159552147e-05,
+      "loss": 0.5913,
+      "step": 97
+    },
+    {
+      "epoch": 0.17705510388437218,
+      "grad_norm": 0.29488509286302705,
+      "learning_rate": 2.87394449008225e-05,
+      "loss": 0.5842,
+      "step": 98
+    },
+    {
+      "epoch": 0.17886178861788618,
+      "grad_norm": 0.3023043372178035,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.5971,
+      "step": 99
+    },
+    {
+      "epoch": 0.18066847335140018,
+      "grad_norm": 0.2920343922477137,
+      "learning_rate": 2.8666428145170385e-05,
+      "loss": 0.5703,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 553,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 115440686923776.0,
+  "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 sha256:31b94bc32b72481dea07dafd0a99d0fdd55f6b30b080ca417d5bcaa9c387fdcc
+size 8017