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:d2d079da1480e9bb0816b794eae451f7bb2061277ed93b9bca8d8530ebf5cd37
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1b634f263cced880189b8b692e9d406dc06dacef579b4d4ba2ac73638dfc65
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f2f138fd286d361e7a4bf33fbbf19f0f2cbf1abe42b45287606411705162aa
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97550d9f948192ee2bb005f7f9a32447da13f299df2e8203048d13cd81fb760
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f55dea4092fb354d9d5601a7962ba28402c553d9fe8129632424995033df59
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6c3269a3ef6ee399362614269488a8bc97a0f7887d99af13ebc1cf98ebcd8d
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:129497ad2c178e62e2748b0920aea46dc86d6a29465c34d96139d3a07b59c8a0
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4f1024eedb6857662c511f817597ec6f1afb81ca61b13303752904f94eabe4
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f302f1c6ac205fa5b1914e0bd60c0c0d3d16dc604a39043dac962195ddb78a0
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbfb057bf2675d7ad6a6815eabca164f04aa9ce6959c6b743c62aec171d208ae
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:639087f454450823afe5a25905ebb18ccb29d2252e2b3ef6870facd094ee8754
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:038723d56a2f840886720075f350facb98b3a9b70c41fb1bdbc02b87752d7301
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa1486c4206141fa8602be8f926c9393757ca7a33863e5f1a9035dacbb20b57e
+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": 2.0673206864963745,
+      "learning_rate": 0.0,
+      "loss": 0.866,
+      "step": 1
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 2.2904017321663805,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.043,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2.0447321324197216,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.9475,
+      "step": 3
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 2.0529204396049754,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.0014,
+      "step": 4
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.7712528364581102,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.0106,
+      "step": 5
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 1.6084257489099159,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.9839,
+      "step": 6
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 1.297162576557966,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.9657,
+      "step": 7
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 1.1800839775732233,
+      "learning_rate": 1e-05,
+      "loss": 0.9877,
+      "step": 8
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 2.58503727715984,
+      "learning_rate": 9.998605186060138e-06,
+      "loss": 1.0058,
+      "step": 9
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.9905581538828991,
+      "learning_rate": 9.99442152244292e-06,
+      "loss": 0.9806,
+      "step": 10
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 1.7663566292058208,
+      "learning_rate": 9.98745134332128e-06,
+      "loss": 0.8723,
+      "step": 11
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.9849427419494283,
+      "learning_rate": 9.97769853753642e-06,
+      "loss": 0.8957,
+      "step": 12
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 1.89266227591124,
+      "learning_rate": 9.965168546428122e-06,
+      "loss": 0.9647,
+      "step": 13
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 1.8081246447916168,
+      "learning_rate": 9.949868360798893e-06,
+      "loss": 0.8717,
+      "step": 14
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.392291810733737,
+      "learning_rate": 9.931806517013612e-06,
+      "loss": 0.8962,
+      "step": 15
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.8888737579943786,
+      "learning_rate": 9.910993092236878e-06,
+      "loss": 0.8384,
+      "step": 16
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.8429446940790654,
+      "learning_rate": 9.887439698810694e-06,
+      "loss": 0.9464,
+      "step": 17
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.7079931791287907,
+      "learning_rate": 9.861159477775653e-06,
+      "loss": 0.8448,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.7999325220892067,
+      "learning_rate": 9.832167091539215e-06,
+      "loss": 0.9085,
+      "step": 19
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.7767778908475649,
+      "learning_rate": 9.800478715695165e-06,
+      "loss": 0.9029,
+      "step": 20
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.8330149692892203,
+      "learning_rate": 9.766112029998847e-06,
+      "loss": 0.8696,
+      "step": 21
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.8914727119553612,
+      "learning_rate": 9.729086208503174e-06,
+      "loss": 0.8225,
+      "step": 22
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.7791831408718177,
+      "learning_rate": 9.689421908860928e-06,
+      "loss": 0.8873,
+      "step": 23
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.6266323636808694,
+      "learning_rate": 9.64714126079933e-06,
+      "loss": 0.8572,
+      "step": 24
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.5575224010810581,
+      "learning_rate": 9.602267853773301e-06,
+      "loss": 0.8441,
+      "step": 25
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.49845686934126004,
+      "learning_rate": 9.554826723804304e-06,
+      "loss": 0.91,
+      "step": 26
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.7453493090030026,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.8084,
+      "step": 27
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.5443473972197154,
+      "learning_rate": 9.452348587347224e-06,
+      "loss": 0.8378,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5443473972197154,
+      "learning_rate": 9.397368756032445e-06,
+      "loss": 0.7501,
+      "step": 29
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.9845706600468573,
+      "learning_rate": 9.339935520221816e-06,
+      "loss": 0.8382,
+      "step": 30
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 0.5543964617569102,
+      "learning_rate": 9.280080923386501e-06,
+      "loss": 0.8038,
+      "step": 31
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.46973363226646997,
+      "learning_rate": 9.217838359936914e-06,
+      "loss": 0.85,
+      "step": 32
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.4180544535801267,
+      "learning_rate": 9.153242556591115e-06,
+      "loss": 0.8262,
+      "step": 33
+    },
+    {
+      "epoch": 1.1754385964912282,
+      "grad_norm": 0.4280159609659819,
+      "learning_rate": 9.08632955299989e-06,
+      "loss": 0.7898,
+      "step": 34
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.42159793205260626,
+      "learning_rate": 9.017136681639307e-06,
+      "loss": 0.848,
+      "step": 35
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 0.4166802767788711,
+      "learning_rate": 8.94570254698197e-06,
+      "loss": 0.835,
+      "step": 36
+    },
+    {
+      "epoch": 1.280701754385965,
+      "grad_norm": 0.45491764527405454,
+      "learning_rate": 8.872067003958597e-06,
+      "loss": 0.8228,
+      "step": 37
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.36795922123966324,
+      "learning_rate": 8.796271135721944e-06,
+      "loss": 0.7929,
+      "step": 38
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 0.3812747318226063,
+      "learning_rate": 8.71835723072545e-06,
+      "loss": 0.7479,
+      "step": 39
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 0.4380736294941453,
+      "learning_rate": 8.638368759129433e-06,
+      "loss": 0.854,
+      "step": 40
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.42681263426801547,
+      "learning_rate": 8.556350348547978e-06,
+      "loss": 0.783,
+      "step": 41
+    },
+    {
+      "epoch": 1.456140350877193,
+      "grad_norm": 0.3869060589821296,
+      "learning_rate": 8.472347759150044e-06,
+      "loss": 0.7519,
+      "step": 42
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 0.349033312619947,
+      "learning_rate": 8.386407858128707e-06,
+      "loss": 0.7401,
+      "step": 43
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.47432293998540326,
+      "learning_rate": 8.298578593552737e-06,
+      "loss": 0.8744,
+      "step": 44
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 0.34747605992665864,
+      "learning_rate": 8.208908967615159e-06,
+      "loss": 0.8284,
+      "step": 45
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 0.33836969242748544,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.761,
+      "step": 46
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.34153910165257595,
+      "learning_rate": 8.024249746438189e-06,
+      "loss": 0.7503,
+      "step": 47
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3518085425244518,
+      "learning_rate": 7.929363177301124e-06,
+      "loss": 0.806,
+      "step": 48
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 0.3201003712741555,
+      "learning_rate": 7.832842241526212e-06,
+      "loss": 0.8157,
+      "step": 49
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.44685942068174817,
+      "learning_rate": 7.734740790612137e-06,
+      "loss": 0.805,
+      "step": 50
+    },
+    {
+      "epoch": 1.7719298245614035,
+      "grad_norm": 0.36470984754663527,
+      "learning_rate": 7.635113557867395e-06,
+      "loss": 0.8212,
+      "step": 51
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 0.3804494373810331,
+      "learning_rate": 7.5340161278732e-06,
+      "loss": 0.8411,
+      "step": 52
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.35072655343818854,
+      "learning_rate": 7.431504905471407e-06,
+      "loss": 0.6893,
+      "step": 53
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 0.37510634573201984,
+      "learning_rate": 7.327637084294818e-06,
+      "loss": 0.8318,
+      "step": 54
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 0.36084870946004954,
+      "learning_rate": 7.22247061485738e-06,
+      "loss": 0.7873,
+      "step": 55
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.3554099591869526,
+      "learning_rate": 7.1160641722221255e-06,
+      "loss": 0.8339,
+      "step": 56
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 0.35408911917355423,
+      "learning_rate": 7.008477123264849e-06,
+      "loss": 0.8398,
+      "step": 57
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5096432648647283,
+      "learning_rate": 6.8997694935518e-06,
+      "loss": 0.8045,
+      "step": 58
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 0.37475991102238737,
+      "learning_rate": 6.7900019338499005e-06,
+      "loss": 0.729,
+      "step": 59
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.3972878307760745,
+      "learning_rate": 6.6792356862881144e-06,
+      "loss": 0.8575,
+      "step": 60
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.3262352261724935,
+      "learning_rate": 6.567532550188908e-06,
+      "loss": 0.7472,
+      "step": 61
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 0.3424287596496662,
+      "learning_rate": 6.454954847588824e-06,
+      "loss": 0.7363,
+      "step": 62
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 0.3371272655759515,
+      "learning_rate": 6.341565388467425e-06,
+      "loss": 0.7783,
+      "step": 63
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.33141142769946547,
+      "learning_rate": 6.227427435703997e-06,
+      "loss": 0.7991,
+      "step": 64
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.34200209272644433,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.6939,
+      "step": 65
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.3295251118618366,
+      "learning_rate": 5.997161153257963e-06,
+      "loss": 0.7493,
+      "step": 66
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.3257402952640206,
+      "learning_rate": 5.88116129502361e-06,
+      "loss": 0.7354,
+      "step": 67
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.3468262089051018,
+      "learning_rate": 5.764669814366231e-06,
+      "loss": 0.7993,
+      "step": 68
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 0.29791562249569503,
+      "learning_rate": 5.647751704862263e-06,
+      "loss": 0.7275,
+      "step": 69
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.31732061287253815,
+      "learning_rate": 5.530472198115291e-06,
+      "loss": 0.8358,
+      "step": 70
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.3211536541824813,
+      "learning_rate": 5.412896727361663e-06,
+      "loss": 0.7616,
+      "step": 71
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 0.3031380817210058,
+      "learning_rate": 5.2950908909636144e-06,
+      "loss": 0.7742,
+      "step": 72
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.3178438171935809,
+      "learning_rate": 5.177120415810271e-06,
+      "loss": 0.7036,
+      "step": 73
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 0.32137565688435116,
+      "learning_rate": 5.059051120646924e-06,
+      "loss": 0.7506,
+      "step": 74
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.34182497608608436,
+      "learning_rate": 4.940948879353078e-06,
+      "loss": 0.7612,
+      "step": 75
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.49331678469706836,
+      "learning_rate": 4.822879584189732e-06,
+      "loss": 0.7772,
+      "step": 76
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.32578460424312694,
+      "learning_rate": 4.704909109036387e-06,
+      "loss": 0.7999,
+      "step": 77
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 0.3213450270788892,
+      "learning_rate": 4.587103272638339e-06,
+      "loss": 0.7784,
+      "step": 78
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.32173299291318835,
+      "learning_rate": 4.46952780188471e-06,
+      "loss": 0.7544,
+      "step": 79
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 0.2951701970822717,
+      "learning_rate": 4.352248295137739e-06,
+      "loss": 0.7091,
+      "step": 80
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.30244163280128544,
+      "learning_rate": 4.23533018563377e-06,
+      "loss": 0.6826,
+      "step": 81
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.3396096678073034,
+      "learning_rate": 4.118838704976392e-06,
+      "loss": 0.7664,
+      "step": 82
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 0.3029269615782617,
+      "learning_rate": 4.002838846742039e-06,
+      "loss": 0.7641,
+      "step": 83
+    },
+    {
+      "epoch": 2.912280701754386,
+      "grad_norm": 0.34338823718992795,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.7728,
+      "step": 84
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.2938721437198324,
+      "learning_rate": 3.7725725642960047e-06,
+      "loss": 0.7117,
+      "step": 85
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 0.3085593380963007,
+      "learning_rate": 3.658434611532578e-06,
+      "loss": 0.767,
+      "step": 86
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3085593380963007,
+      "learning_rate": 3.545045152411178e-06,
+      "loss": 0.6125,
+      "step": 87
+    },
+    {
+      "epoch": 3.0350877192982457,
+      "grad_norm": 0.5571040712543199,
+      "learning_rate": 3.4324674498110956e-06,
+      "loss": 0.7249,
+      "step": 88
+    },
+    {
+      "epoch": 3.0701754385964914,
+      "grad_norm": 0.4197147770164601,
+      "learning_rate": 3.3207643137118872e-06,
+      "loss": 0.7946,
+      "step": 89
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.32254405544164744,
+      "learning_rate": 3.2099980661501016e-06,
+      "loss": 0.7595,
+      "step": 90
+    },
+    {
+      "epoch": 3.1403508771929824,
+      "grad_norm": 0.37912618459203973,
+      "learning_rate": 3.1002305064482006e-06,
+      "loss": 0.7302,
+      "step": 91
+    },
+    {
+      "epoch": 3.175438596491228,
+      "grad_norm": 0.425878207604886,
+      "learning_rate": 2.991522876735154e-06,
+      "loss": 0.7247,
+      "step": 92
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.4309388403995281,
+      "learning_rate": 2.8839358277778758e-06,
+      "loss": 0.824,
+      "step": 93
+    },
+    {
+      "epoch": 3.245614035087719,
+      "grad_norm": 0.3218605427039408,
+      "learning_rate": 2.7775293851426233e-06,
+      "loss": 0.7006,
+      "step": 94
+    },
+    {
+      "epoch": 3.280701754385965,
+      "grad_norm": 0.2845528469845822,
+      "learning_rate": 2.6723629157051844e-06,
+      "loss": 0.6961,
+      "step": 95
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 0.41125431712555316,
+      "learning_rate": 2.5684950945285937e-06,
+      "loss": 0.7666,
+      "step": 96
+    },
+    {
+      "epoch": 3.3508771929824563,
+      "grad_norm": 0.3357613909767992,
+      "learning_rate": 2.4659838721268005e-06,
+      "loss": 0.7407,
+      "step": 97
+    },
+    {
+      "epoch": 3.3859649122807016,
+      "grad_norm": 0.3101463097467026,
+      "learning_rate": 2.364886442132606e-06,
+      "loss": 0.6439,
+      "step": 98
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.31823397426684447,
+      "learning_rate": 2.265259209387867e-06,
+      "loss": 0.6643,
+      "step": 99
+    },
+    {
+      "epoch": 3.456140350877193,
+      "grad_norm": 0.3243150976858008,
+      "learning_rate": 2.16715775847379e-06,
+      "loss": 0.6661,
+      "step": 100
+    },
+    {
+      "epoch": 3.4912280701754383,
+      "grad_norm": 0.32784635844078874,
+      "learning_rate": 2.0706368226988772e-06,
+      "loss": 0.6998,
+      "step": 101
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.3487612159161503,
+      "learning_rate": 1.9757502535618137e-06,
+      "loss": 0.6876,
+      "step": 102
+    },
+    {
+      "epoch": 3.56140350877193,
+      "grad_norm": 0.29203671158252864,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.7013,
+      "step": 103
+    },
+    {
+      "epoch": 3.5964912280701755,
+      "grad_norm": 0.348040537288868,
+      "learning_rate": 1.7910910323848435e-06,
+      "loss": 0.6935,
+      "step": 104
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.3230772650485642,
+      "learning_rate": 1.7014214064472646e-06,
+      "loss": 0.616,
+      "step": 105
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.30004091482464185,
+      "learning_rate": 1.6135921418712959e-06,
+      "loss": 0.6941,
+      "step": 106
+    },
+    {
+      "epoch": 3.7017543859649122,
+      "grad_norm": 0.3237623734694473,
+      "learning_rate": 1.5276522408499567e-06,
+      "loss": 0.6971,
+      "step": 107
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.35286509187095205,
+      "learning_rate": 1.4436496514520253e-06,
+      "loss": 0.76,
+      "step": 108
+    },
+    {
+      "epoch": 3.7719298245614032,
+      "grad_norm": 0.3113387000491033,
+      "learning_rate": 1.361631240870569e-06,
+      "loss": 0.7823,
+      "step": 109
+    },
+    {
+      "epoch": 3.807017543859649,
+      "grad_norm": 0.31180727979378736,
+      "learning_rate": 1.281642769274552e-06,
+      "loss": 0.7433,
+      "step": 110
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.3039468663249765,
+      "learning_rate": 1.2037288642780575e-06,
+      "loss": 0.7469,
+      "step": 111
+    },
+    {
+      "epoch": 3.8771929824561404,
+      "grad_norm": 0.31170431993009845,
+      "learning_rate": 1.1279329960414047e-06,
+      "loss": 0.687,
+      "step": 112
+    },
+    {
+      "epoch": 3.912280701754386,
+      "grad_norm": 0.2979483246464743,
+      "learning_rate": 1.0542974530180327e-06,
+      "loss": 0.702,
+      "step": 113
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.2806612442551802,
+      "learning_rate": 9.82863318360695e-07,
+      "loss": 0.7217,
+      "step": 114
+    },
+    {
+      "epoch": 3.982456140350877,
+      "grad_norm": 0.3064545089842091,
+      "learning_rate": 9.136704470001101e-07,
+      "loss": 0.737,
+      "step": 115
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.533265253763801,
+      "learning_rate": 8.46757443408886e-07,
+      "loss": 0.6768,
+      "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 sha256:5a3db2c7cd60fa4bf7f25cb7dfb3ac9065581183a5662472cad50b39d049a967
+size 8081