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 sha256:2eb5c46e6a35584b347a1eea9936d9cffaef1ec649a3618f8ed957c76deb789b
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6398a83b00191d90d766a953e9401318253210cffd2935e7daae8ad72509134
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b5982009e7f03e313575d88c048c1a3ed490573a3ebb561807dbaaea7c6dca
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79289e16c3c58872e28897cb52406e95852d0b2e5516be6c93954c121dc14753
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f7c8c27f8ccc85a00fbcd1aab3754bdd7c22185884b46ee1befa7f5605bb6c
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341cc7eefbbea7dfdda57ad2fda9cbe946288b08ab65f6c4ad1946c49aaa880b
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305e03afe476939bc9b02b63338b9bf07b7f10400e3cfa807822be7d69a81c08
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b001f05e0191530d0c54f3581ee8c7227a5a7f4eed3a7320e3f0703ec5535777
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a4499873f4d8938f07a54879eccfb4a21f39b645a5b2cb05ed92c0d3c6d302
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0261fb7d7e5c366d1b87a4386f488125f142df60a85ab036b856aec9bc4a76ec
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f57ee96753cdf8a1c9661214ffd8c03074ea559d7f0fa8a63d989aa2e5e6879
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d324d22d9e9f0eac40dae11297fc6792f3b8e2b2fd496da83a8ab8b9f368d24
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c55e1b421c23d7795004a029b0e93f23f7f9d8b791d0114be7965030a4f5f0
+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 +1,832 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 114,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017543859649122806,
+      "grad_norm": 2.256555232517452,
+      "learning_rate": 0.0,
+      "loss": 0.8483,
+      "step": 1
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 2.205270245564155,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 0.8765,
+      "step": 2
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 2.361805594728836,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 1.0209,
+      "step": 3
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 2.481606951567156,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.062,
+      "step": 4
+    },
+    {
+      "epoch": 0.08771929824561403,
+      "grad_norm": 1.923229005445868,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.8564,
+      "step": 5
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2.1103374249725833,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0082,
+      "step": 6
+    },
+    {
+      "epoch": 0.12280701754385964,
+      "grad_norm": 1.9672661474560547,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.9978,
+      "step": 7
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 1.810080319596374,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.9468,
+      "step": 8
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 2.2501314657852776,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.9614,
+      "step": 9
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.3827469830753207,
+      "learning_rate": 6e-06,
+      "loss": 0.9873,
+      "step": 10
+    },
+    {
+      "epoch": 0.19298245614035087,
+      "grad_norm": 1.5862884873258083,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0305,
+      "step": 11
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 1.57454716689858,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.9006,
+      "step": 12
+    },
+    {
+      "epoch": 0.22807017543859648,
+      "grad_norm": 1.5638780668313408,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.936,
+      "step": 13
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 1.5588053318143216,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.9131,
+      "step": 14
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 1.2968184983553472,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.9716,
+      "step": 15
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 1.3213006637878912,
+      "learning_rate": 1e-05,
+      "loss": 0.922,
+      "step": 16
+    },
+    {
+      "epoch": 0.2982456140350877,
+      "grad_norm": 1.4807190056139585,
+      "learning_rate": 9.999661540018812e-06,
+      "loss": 1.0189,
+      "step": 17
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 1.7897441321489662,
+      "learning_rate": 9.99864620589731e-06,
+      "loss": 0.903,
+      "step": 18
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.1554720466501127,
+      "learning_rate": 9.99695413509548e-06,
+      "loss": 0.9231,
+      "step": 19
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.0430048166465928,
+      "learning_rate": 9.994585556692624e-06,
+      "loss": 0.9584,
+      "step": 20
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.8734173643171832,
+      "learning_rate": 9.991540791356342e-06,
+      "loss": 0.8954,
+      "step": 21
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 0.8505715098348454,
+      "learning_rate": 9.987820251299121e-06,
+      "loss": 0.7634,
+      "step": 22
+    },
+    {
+      "epoch": 0.40350877192982454,
+      "grad_norm": 0.932431362896424,
+      "learning_rate": 9.98342444022253e-06,
+      "loss": 0.8972,
+      "step": 23
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.994313791348145,
+      "learning_rate": 9.978353953249023e-06,
+      "loss": 0.7951,
+      "step": 24
+    },
+    {
+      "epoch": 0.43859649122807015,
+      "grad_norm": 0.8497211408850255,
+      "learning_rate": 9.972609476841368e-06,
+      "loss": 0.9234,
+      "step": 25
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 0.9190618422149534,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 0.8877,
+      "step": 26
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.8415994406297493,
+      "learning_rate": 9.959101757706308e-06,
+      "loss": 0.8086,
+      "step": 27
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.742782382735312,
+      "learning_rate": 9.951340343707852e-06,
+      "loss": 0.8769,
+      "step": 28
+    },
+    {
+      "epoch": 0.5087719298245614,
+      "grad_norm": 0.6160964124153906,
+      "learning_rate": 9.942908597485558e-06,
+      "loss": 0.8978,
+      "step": 29
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.5976609614605858,
+      "learning_rate": 9.933807660562898e-06,
+      "loss": 0.7837,
+      "step": 30
+    },
+    {
+      "epoch": 0.543859649122807,
+      "grad_norm": 0.5560568208246192,
+      "learning_rate": 9.924038765061042e-06,
+      "loss": 0.8396,
+      "step": 31
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.5836679513268156,
+      "learning_rate": 9.913603233532067e-06,
+      "loss": 0.7701,
+      "step": 32
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.7645333976719451,
+      "learning_rate": 9.902502478779897e-06,
+      "loss": 0.8688,
+      "step": 33
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.7612685741039715,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 0.9675,
+      "step": 34
+    },
+    {
+      "epoch": 0.6140350877192983,
+      "grad_norm": 0.6672122472693547,
+      "learning_rate": 9.878311400921072e-06,
+      "loss": 0.8122,
+      "step": 35
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.6198318849807769,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.8276,
+      "step": 36
+    },
+    {
+      "epoch": 0.6491228070175439,
+      "grad_norm": 0.5915273774198798,
+      "learning_rate": 9.851478631379982e-06,
+      "loss": 0.862,
+      "step": 37
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.7597701986857002,
+      "learning_rate": 9.83707609731432e-06,
+      "loss": 0.8755,
+      "step": 38
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.6165755211119401,
+      "learning_rate": 9.822018700574696e-06,
+      "loss": 0.898,
+      "step": 39
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.546722974197266,
+      "learning_rate": 9.806308479691595e-06,
+      "loss": 0.8637,
+      "step": 40
+    },
+    {
+      "epoch": 0.7192982456140351,
+      "grad_norm": 0.5624327518167074,
+      "learning_rate": 9.789947561577445e-06,
+      "loss": 0.8685,
+      "step": 41
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.5747062370239466,
+      "learning_rate": 9.77293816123866e-06,
+      "loss": 0.8039,
+      "step": 42
+    },
+    {
+      "epoch": 0.7543859649122807,
+      "grad_norm": 0.5540954371595526,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.8365,
+      "step": 43
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.5678372679311994,
+      "learning_rate": 9.736983212571646e-06,
+      "loss": 0.7528,
+      "step": 44
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.5498130339645014,
+      "learning_rate": 9.718042531967918e-06,
+      "loss": 0.8692,
+      "step": 45
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.723915088763488,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.8465,
+      "step": 46
+    },
+    {
+      "epoch": 0.8245614035087719,
+      "grad_norm": 0.5693533968278255,
+      "learning_rate": 9.678247579197658e-06,
+      "loss": 0.8505,
+      "step": 47
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.444847109914399,
+      "learning_rate": 9.657398694630713e-06,
+      "loss": 0.8346,
+      "step": 48
+    },
+    {
+      "epoch": 0.8596491228070176,
+      "grad_norm": 0.5481527250136425,
+      "learning_rate": 9.635919272833938e-06,
+      "loss": 0.9264,
+      "step": 49
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.4850156760944371,
+      "learning_rate": 9.613812221777212e-06,
+      "loss": 0.6667,
+      "step": 50
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.5196718609108957,
+      "learning_rate": 9.591080534401371e-06,
+      "loss": 0.8957,
+      "step": 51
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.5280436158388971,
+      "learning_rate": 9.567727288213005e-06,
+      "loss": 0.8639,
+      "step": 52
+    },
+    {
+      "epoch": 0.9298245614035088,
+      "grad_norm": 0.5997684565130753,
+      "learning_rate": 9.543755644867823e-06,
+      "loss": 0.8164,
+      "step": 53
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.5103541862955409,
+      "learning_rate": 9.519168849742603e-06,
+      "loss": 0.7713,
+      "step": 54
+    },
+    {
+      "epoch": 0.9649122807017544,
+      "grad_norm": 0.5148641741360179,
+      "learning_rate": 9.493970231495836e-06,
+      "loss": 0.8101,
+      "step": 55
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.46692510221358374,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 0.8216,
+      "step": 56
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.666709235115788,
+      "learning_rate": 9.441751253965022e-06,
+      "loss": 0.7334,
+      "step": 57
+    },
+    {
+      "epoch": 1.0175438596491229,
+      "grad_norm": 0.5936450769507504,
+      "learning_rate": 9.414737964294636e-06,
+      "loss": 0.8429,
+      "step": 58
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.5402515184573428,
+      "learning_rate": 9.38712698977291e-06,
+      "loss": 0.7318,
+      "step": 59
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.9071602417358279,
+      "learning_rate": 9.358922068483813e-06,
+      "loss": 0.8178,
+      "step": 60
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 0.5181420637496472,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.6926,
+      "step": 61
+    },
+    {
+      "epoch": 1.087719298245614,
+      "grad_norm": 0.516304628920244,
+      "learning_rate": 9.30074573947683e-06,
+      "loss": 0.7764,
+      "step": 62
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.6092031389895063,
+      "learning_rate": 9.27078220790263e-06,
+      "loss": 0.804,
+      "step": 63
+    },
+    {
+      "epoch": 1.1228070175438596,
+      "grad_norm": 0.5739882837391556,
+      "learning_rate": 9.24024048078213e-06,
+      "loss": 0.7961,
+      "step": 64
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.4850959044650596,
+      "learning_rate": 9.209124692976287e-06,
+      "loss": 0.719,
+      "step": 65
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.5269909739571422,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.7205,
+      "step": 66
+    },
+    {
+      "epoch": 1.1754385964912282,
+      "grad_norm": 0.5314922201966987,
+      "learning_rate": 9.145187862775208e-06,
+      "loss": 0.7181,
+      "step": 67
+    },
+    {
+      "epoch": 1.1929824561403508,
+      "grad_norm": 0.4899793932301242,
+      "learning_rate": 9.112375476403313e-06,
+      "loss": 0.7646,
+      "step": 68
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.5480170596915535,
+      "learning_rate": 9.079006340220862e-06,
+      "loss": 0.8132,
+      "step": 69
+    },
+    {
+      "epoch": 1.2280701754385965,
+      "grad_norm": 0.5344703713427396,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.7621,
+      "step": 70
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 0.5142366314984944,
+      "learning_rate": 9.01061596377522e-06,
+      "loss": 0.8121,
+      "step": 71
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.5877062225708843,
+      "learning_rate": 8.97560398247424e-06,
+      "loss": 0.7764,
+      "step": 72
+    },
+    {
+      "epoch": 1.280701754385965,
+      "grad_norm": 0.5275593499501555,
+      "learning_rate": 8.94005376803361e-06,
+      "loss": 0.7774,
+      "step": 73
+    },
+    {
+      "epoch": 1.2982456140350878,
+      "grad_norm": 0.49685789720182055,
+      "learning_rate": 8.903970133383297e-06,
+      "loss": 0.6981,
+      "step": 74
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.475321792037016,
+      "learning_rate": 8.867357963669821e-06,
+      "loss": 0.8256,
+      "step": 75
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.4843848014144311,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.7196,
+      "step": 76
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 1.496794429410156,
+      "learning_rate": 8.792567916744346e-06,
+      "loss": 0.6912,
+      "step": 77
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.6153325721376482,
+      "learning_rate": 8.754400164907496e-06,
+      "loss": 0.811,
+      "step": 78
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 0.6721942051923293,
+      "learning_rate": 8.715724127386971e-06,
+      "loss": 0.7933,
+      "step": 79
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 0.5030720500009336,
+      "learning_rate": 8.676545040299145e-06,
+      "loss": 0.743,
+      "step": 80
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.5538931248913758,
+      "learning_rate": 8.636868207865244e-06,
+      "loss": 0.767,
+      "step": 81
+    },
+    {
+      "epoch": 1.4385964912280702,
+      "grad_norm": 0.5337323807177417,
+      "learning_rate": 8.596699001693257e-06,
+      "loss": 0.7524,
+      "step": 82
+    },
+    {
+      "epoch": 1.456140350877193,
+      "grad_norm": 0.5308647219753817,
+      "learning_rate": 8.556042860050686e-06,
+      "loss": 0.6872,
+      "step": 83
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.47526293846704515,
+      "learning_rate": 8.51490528712831e-06,
+      "loss": 0.6151,
+      "step": 84
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 0.5167817753474783,
+      "learning_rate": 8.473291852294986e-06,
+      "loss": 0.7717,
+      "step": 85
+    },
+    {
+      "epoch": 1.5087719298245614,
+      "grad_norm": 0.581779409307219,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.7539,
+      "step": 86
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.46750024633090104,
+      "learning_rate": 8.388659995728662e-06,
+      "loss": 0.8867,
+      "step": 87
+    },
+    {
+      "epoch": 1.543859649122807,
+      "grad_norm": 0.7775428447931367,
+      "learning_rate": 8.345653031794292e-06,
+      "loss": 0.7715,
+      "step": 88
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 0.45420868791461705,
+      "learning_rate": 8.302193119995038e-06,
+      "loss": 0.8097,
+      "step": 89
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.5734514921428913,
+      "learning_rate": 8.258286144107277e-06,
+      "loss": 0.7128,
+      "step": 90
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 0.5283496931762547,
+      "learning_rate": 8.213938048432697e-06,
+      "loss": 0.7471,
+      "step": 91
+    },
+    {
+      "epoch": 1.6140350877192984,
+      "grad_norm": 0.9000918883180169,
+      "learning_rate": 8.16915483699355e-06,
+      "loss": 0.7585,
+      "step": 92
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.42473651420290276,
+      "learning_rate": 8.123942572719801e-06,
+      "loss": 0.6968,
+      "step": 93
+    },
+    {
+      "epoch": 1.6491228070175439,
+      "grad_norm": 0.4566134251259284,
+      "learning_rate": 8.078307376628292e-06,
+      "loss": 0.703,
+      "step": 94
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5418186278604009,
+      "learning_rate": 8.032255426994069e-06,
+      "loss": 0.8007,
+      "step": 95
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.5733519308896541,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 0.7076,
+      "step": 96
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 0.5094945171963646,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.8732,
+      "step": 97
+    },
+    {
+      "epoch": 1.719298245614035,
+      "grad_norm": 0.4620218725432511,
+      "learning_rate": 7.891661680839932e-06,
+      "loss": 0.7513,
+      "step": 98
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 1.7222136001410835,
+      "learning_rate": 7.84400561551426e-06,
+      "loss": 0.7866,
+      "step": 99
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "grad_norm": 0.485528858744073,
+      "learning_rate": 7.795964517353734e-06,
+      "loss": 0.7314,
+      "step": 100
+    },
+    {
+      "epoch": 1.7719298245614035,
+      "grad_norm": 0.5534357225495664,
+      "learning_rate": 7.747544890354031e-06,
+      "loss": 0.8004,
+      "step": 101
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.4372744352751169,
+      "learning_rate": 7.698753289757565e-06,
+      "loss": 0.7979,
+      "step": 102
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 0.5308017997290465,
+      "learning_rate": 7.649596321166024e-06,
+      "loss": 0.8179,
+      "step": 103
+    },
+    {
+      "epoch": 1.8245614035087718,
+      "grad_norm": 0.4838905935160564,
+      "learning_rate": 7.600080639646077e-06,
+      "loss": 0.6699,
+      "step": 104
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.4911437146733649,
+      "learning_rate": 7.550212948828377e-06,
+      "loss": 0.6439,
+      "step": 105
+    },
+    {
+      "epoch": 1.8596491228070176,
+      "grad_norm": 0.6771983179775685,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.8343,
+      "step": 106
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 0.5801932125189808,
+      "learning_rate": 7.449448591190436e-06,
+      "loss": 0.7647,
+      "step": 107
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.4957701647602047,
+      "learning_rate": 7.398565566251232e-06,
+      "loss": 0.786,
+      "step": 108
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 0.5454933024553883,
+      "learning_rate": 7.347357813929455e-06,
+      "loss": 0.7003,
+      "step": 109
+    },
+    {
+      "epoch": 1.9298245614035088,
+      "grad_norm": 0.5365025981976435,
+      "learning_rate": 7.295832266935059e-06,
+      "loss": 0.8062,
+      "step": 110
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.4783223450378368,
+      "learning_rate": 7.243995901002312e-06,
+      "loss": 0.8047,
+      "step": 111
+    },
+    {
+      "epoch": 1.9649122807017543,
+      "grad_norm": 0.5409575330711582,
+      "learning_rate": 7.191855733945388e-06,
+      "loss": 0.7754,
+      "step": 112
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 0.5248042146794984,
+      "learning_rate": 7.1394188247082715e-06,
+      "loss": 0.8502,
+      "step": 113
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6120193413387582,
+      "learning_rate": 7.08669227240909e-06,
+      "loss": 0.7556,
+      "step": 114
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 285,
+  "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": 26112855638016.0,
+  "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 sha256:500a0c487f3ed048130f19df6cf26d355285f45b7f94f5d1f95a37b6bd9ace10
+size 8081