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:ff787e21828ddbdaa8de757e826e9def3a86c5a35c1e924fbda1f6b4402c9ed3
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f700603be76913f3bdb9339fee388f1f91dfee8b26101de16b53445cabdb9a4c
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a1719170b980ce29292de5f1e6a6a1de462173d7283ab5877b3e6706aab9e36
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b49d3d0b12ab35b761aa4f36e3a6d8405b8dc91c3de9a5c3cb98470777c170
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d51e67029cd78d41a8cd238286817fb009120709154c3144c6d1ee512625430
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8c3586986ab1fa100845be1618201c32c54efe29c398aa7e2250320ec3298a
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38325900263a75417e7118fb04911cb911f474a8faf6eaa762cb9e7a072d2576
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d3afd8b62d57aedc7efe3404216f682efb5f3b08517ce73a6781b935612f13
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e71c4b3eb25e8a756a05139d340402b700cf08256250d31f6e2241ed7130f1
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3418dad61114e52cc632f75512f39407b9c3f8fe6948ffe5d58622cf169951
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e934e565bd1a7e48f3e22efd5c416f860ca3a31633b8c202780ac55d39eb0f0f
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:588a3e4c9e37afabe1a39374f56b2acb11656ab5736d8481dba651b26445d170
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0f28e56c0f5f12c867e22a858e67500cd0533cffc97f7d98f3ec16a88d58c6
+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": 2.067214871055153,
+      "learning_rate": 0.0,
+      "loss": 0.866,
+      "step": 1
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 2.2902974488934356,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.043,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 1.8959065809264741,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.9429,
+      "step": 3
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 1.7531397239789308,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.9852,
+      "step": 4
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.9134009040538502,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.9898,
+      "step": 5
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 2.4981051959996017,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.9729,
+      "step": 6
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 2.1259191076410326,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 0.9501,
+      "step": 7
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 2.6083028457024127,
+      "learning_rate": 3e-05,
+      "loss": 0.9957,
+      "step": 8
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 2.2174618708678193,
+      "learning_rate": 2.999581555818041e-05,
+      "loss": 1.003,
+      "step": 9
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.310512297596868,
+      "learning_rate": 2.9983264567328756e-05,
+      "loss": 0.9666,
+      "step": 10
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 1.0417774774374975,
+      "learning_rate": 2.9962354029963835e-05,
+      "loss": 0.8532,
+      "step": 11
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.096319575622801,
+      "learning_rate": 2.9933095612609253e-05,
+      "loss": 0.8722,
+      "step": 12
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 1.051828485887936,
+      "learning_rate": 2.989550563928436e-05,
+      "loss": 0.94,
+      "step": 13
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.7880955122292899,
+      "learning_rate": 2.9849605082396678e-05,
+      "loss": 0.8454,
+      "step": 14
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.6655179120990646,
+      "learning_rate": 2.9795419551040836e-05,
+      "loss": 0.8716,
+      "step": 15
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.6709188694271632,
+      "learning_rate": 2.973297927671063e-05,
+      "loss": 0.8177,
+      "step": 16
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.7681555199843141,
+      "learning_rate": 2.966231909643208e-05,
+      "loss": 0.9286,
+      "step": 17
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.6474330407996667,
+      "learning_rate": 2.958347843332696e-05,
+      "loss": 0.8274,
+      "step": 18
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5325702575478014,
+      "learning_rate": 2.949650127461764e-05,
+      "loss": 0.8929,
+      "step": 19
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.5849013227799386,
+      "learning_rate": 2.940143614708549e-05,
+      "loss": 0.891,
+      "step": 20
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.6549654089627338,
+      "learning_rate": 2.9298336089996538e-05,
+      "loss": 0.8568,
+      "step": 21
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.5258630198755742,
+      "learning_rate": 2.9187258625509518e-05,
+      "loss": 0.8109,
+      "step": 22
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.4998629934118094,
+      "learning_rate": 2.906826572658278e-05,
+      "loss": 0.875,
+      "step": 23
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.42855717754389155,
+      "learning_rate": 2.8941423782397987e-05,
+      "loss": 0.8454,
+      "step": 24
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.50628059004859,
+      "learning_rate": 2.8806803561319903e-05,
+      "loss": 0.8334,
+      "step": 25
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.5060863985075719,
+      "learning_rate": 2.866448017141291e-05,
+      "loss": 0.8989,
+      "step": 26
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.8609761967398525,
+      "learning_rate": 2.8514533018536286e-05,
+      "loss": 0.7991,
+      "step": 27
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.48863408976007106,
+      "learning_rate": 2.835704576204167e-05,
+      "loss": 0.8282,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.48863408976007106,
+      "learning_rate": 2.8192106268097336e-05,
+      "loss": 0.7073,
+      "step": 29
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.9713567127839504,
+      "learning_rate": 2.801980656066545e-05,
+      "loss": 0.7714,
+      "step": 30
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 0.4951617245737733,
+      "learning_rate": 2.78402427701595e-05,
+      "loss": 0.7343,
+      "step": 31
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.561308739752077,
+      "learning_rate": 2.7653515079810744e-05,
+      "loss": 0.7805,
+      "step": 32
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.6696065745196884,
+      "learning_rate": 2.7459727669773344e-05,
+      "loss": 0.7562,
+      "step": 33
+    },
+    {
+      "epoch": 1.1754385964912282,
+      "grad_norm": 0.574338497323505,
+      "learning_rate": 2.725898865899967e-05,
+      "loss": 0.7163,
+      "step": 34
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.5954448022407949,
+      "learning_rate": 2.705141004491792e-05,
+      "loss": 0.7716,
+      "step": 35
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 0.4473898865990269,
+      "learning_rate": 2.6837107640945904e-05,
+      "loss": 0.7742,
+      "step": 36
+    },
+    {
+      "epoch": 1.280701754385965,
+      "grad_norm": 0.7727798282627385,
+      "learning_rate": 2.6616201011875792e-05,
+      "loss": 0.744,
+      "step": 37
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.5121520923399718,
+      "learning_rate": 2.638881340716583e-05,
+      "loss": 0.7212,
+      "step": 38
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 0.4705537944247171,
+      "learning_rate": 2.6155071692176348e-05,
+      "loss": 0.674,
+      "step": 39
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 0.571084271601031,
+      "learning_rate": 2.5915106277388293e-05,
+      "loss": 0.7776,
+      "step": 40
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.5850344726559537,
+      "learning_rate": 2.566905104564393e-05,
+      "loss": 0.7177,
+      "step": 41
+    },
+    {
+      "epoch": 1.456140350877193,
+      "grad_norm": 0.4332588522858084,
+      "learning_rate": 2.541704327745013e-05,
+      "loss": 0.6776,
+      "step": 42
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 0.4393188232149638,
+      "learning_rate": 2.5159223574386117e-05,
+      "loss": 0.6675,
+      "step": 43
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.4979789836021164,
+      "learning_rate": 2.489573578065821e-05,
+      "loss": 0.8005,
+      "step": 44
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 0.45732271681245434,
+      "learning_rate": 2.4626726902845477e-05,
+      "loss": 0.7579,
+      "step": 45
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 0.45795659974157954,
+      "learning_rate": 2.4352347027881003e-05,
+      "loss": 0.6847,
+      "step": 46
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.3706866470068484,
+      "learning_rate": 2.4072749239314565e-05,
+      "loss": 0.6851,
+      "step": 47
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3822700465065106,
+      "learning_rate": 2.3788089531903372e-05,
+      "loss": 0.7357,
+      "step": 48
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 0.4388840978268458,
+      "learning_rate": 2.3498526724578637e-05,
+      "loss": 0.7545,
+      "step": 49
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.5096281415627839,
+      "learning_rate": 2.320422237183641e-05,
+      "loss": 0.7449,
+      "step": 50
+    },
+    {
+      "epoch": 1.7719298245614035,
+      "grad_norm": 0.4149064055586781,
+      "learning_rate": 2.2905340673602184e-05,
+      "loss": 0.7481,
+      "step": 51
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 0.45646999516691433,
+      "learning_rate": 2.26020483836196e-05,
+      "loss": 0.7732,
+      "step": 52
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.45834783579018146,
+      "learning_rate": 2.229451471641422e-05,
+      "loss": 0.6229,
+      "step": 53
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 0.47503100724025626,
+      "learning_rate": 2.198291125288445e-05,
+      "loss": 0.7608,
+      "step": 54
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 0.4978417847863162,
+      "learning_rate": 2.166741184457214e-05,
+      "loss": 0.7096,
+      "step": 55
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.3815502550665043,
+      "learning_rate": 2.1348192516666376e-05,
+      "loss": 0.7613,
+      "step": 56
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 0.5283326744530167,
+      "learning_rate": 2.1025431369794546e-05,
+      "loss": 0.7659,
+      "step": 57
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7991429287166618,
+      "learning_rate": 2.0699308480655397e-05,
+      "loss": 0.6749,
+      "step": 58
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 0.7075576798543697,
+      "learning_rate": 2.03700058015497e-05,
+      "loss": 0.6011,
+      "step": 59
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.6128577868137788,
+      "learning_rate": 2.0037707058864343e-05,
+      "loss": 0.7135,
+      "step": 60
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 2.7353412863881106,
+      "learning_rate": 1.9702597650566723e-05,
+      "loss": 0.6262,
+      "step": 61
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 1.436411571175325,
+      "learning_rate": 1.936486454276647e-05,
+      "loss": 0.6019,
+      "step": 62
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 0.7724991117675305,
+      "learning_rate": 1.9024696165402272e-05,
+      "loss": 0.6402,
+      "step": 63
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.8129381352505199,
+      "learning_rate": 1.8682282307111988e-05,
+      "loss": 0.6407,
+      "step": 64
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.4291210901719085,
+      "learning_rate": 1.8337814009344716e-05,
+      "loss": 0.5708,
+      "step": 65
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.4866938146227632,
+      "learning_rate": 1.7991483459773887e-05,
+      "loss": 0.612,
+      "step": 66
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.501246587872298,
+      "learning_rate": 1.7643483885070827e-05,
+      "loss": 0.588,
+      "step": 67
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.6083185314221561,
+      "learning_rate": 1.729400944309869e-05,
+      "loss": 0.6506,
+      "step": 68
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 0.47109461910264055,
+      "learning_rate": 1.6943255114586788e-05,
+      "loss": 0.6001,
+      "step": 69
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.9612069814317359,
+      "learning_rate": 1.659141659434587e-05,
+      "loss": 0.6855,
+      "step": 70
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.4415318960259018,
+      "learning_rate": 1.623869018208499e-05,
+      "loss": 0.6185,
+      "step": 71
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 0.5141343063620322,
+      "learning_rate": 1.5885272672890842e-05,
+      "loss": 0.625,
+      "step": 72
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.5270279056557339,
+      "learning_rate": 1.553136124743081e-05,
+      "loss": 0.5617,
+      "step": 73
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 0.466590856309372,
+      "learning_rate": 1.517715336194077e-05,
+      "loss": 0.6277,
+      "step": 74
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.43235236729979676,
+      "learning_rate": 1.4822846638059234e-05,
+      "loss": 0.6195,
+      "step": 75
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.491374794528347,
+      "learning_rate": 1.4468638752569193e-05,
+      "loss": 0.6175,
+      "step": 76
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.4192646842845411,
+      "learning_rate": 1.411472732710916e-05,
+      "loss": 0.6506,
+      "step": 77
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 0.40467023638867167,
+      "learning_rate": 1.3761309817915017e-05,
+      "loss": 0.637,
+      "step": 78
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.43210383757416787,
+      "learning_rate": 1.340858340565413e-05,
+      "loss": 0.623,
+      "step": 79
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 0.3261551587036006,
+      "learning_rate": 1.3056744885413216e-05,
+      "loss": 0.5767,
+      "step": 80
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.3518292750647773,
+      "learning_rate": 1.2705990556901311e-05,
+      "loss": 0.5364,
+      "step": 81
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.40707731514091194,
+      "learning_rate": 1.2356516114929176e-05,
+      "loss": 0.6132,
+      "step": 82
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 0.3942472555532828,
+      "learning_rate": 1.2008516540226115e-05,
+      "loss": 0.6193,
+      "step": 83
+    },
+    {
+      "epoch": 2.912280701754386,
+      "grad_norm": 0.44241351169227155,
+      "learning_rate": 1.1662185990655285e-05,
+      "loss": 0.6401,
+      "step": 84
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.3874748773873833,
+      "learning_rate": 1.1317717692888014e-05,
+      "loss": 0.5637,
+      "step": 85
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 0.34302393254475577,
+      "learning_rate": 1.0975303834597734e-05,
+      "loss": 0.6325,
+      "step": 86
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.34302393254475577,
+      "learning_rate": 1.0635135457233533e-05,
+      "loss": 0.4186,
+      "step": 87
+    },
+    {
+      "epoch": 3.0350877192982457,
+      "grad_norm": 0.9844351160592908,
+      "learning_rate": 1.0297402349433286e-05,
+      "loss": 0.5259,
+      "step": 88
+    },
+    {
+      "epoch": 3.0701754385964914,
+      "grad_norm": 0.9168409207310226,
+      "learning_rate": 9.96229294113566e-06,
+      "loss": 0.5808,
+      "step": 89
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.4844166706459174,
+      "learning_rate": 9.629994198450305e-06,
+      "loss": 0.5523,
+      "step": 90
+    },
+    {
+      "epoch": 3.1403508771929824,
+      "grad_norm": 1.1469572697445642,
+      "learning_rate": 9.300691519344602e-06,
+      "loss": 0.5111,
+      "step": 91
+    },
+    {
+      "epoch": 3.175438596491228,
+      "grad_norm": 1.1765186720119694,
+      "learning_rate": 8.974568630205462e-06,
+      "loss": 0.5249,
+      "step": 92
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.8176252024624937,
+      "learning_rate": 8.651807483333627e-06,
+      "loss": 0.5864,
+      "step": 93
+    },
+    {
+      "epoch": 3.245614035087719,
+      "grad_norm": 0.5279006826410574,
+      "learning_rate": 8.332588155427869e-06,
+      "loss": 0.496,
+      "step": 94
+    },
+    {
+      "epoch": 3.280701754385965,
+      "grad_norm": 0.6870894874287676,
+      "learning_rate": 8.017088747115554e-06,
+      "loss": 0.4908,
+      "step": 95
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 0.8638224803482439,
+      "learning_rate": 7.70548528358578e-06,
+      "loss": 0.5443,
+      "step": 96
+    },
+    {
+      "epoch": 3.3508771929824563,
+      "grad_norm": 0.6334251823605639,
+      "learning_rate": 7.397951616380401e-06,
+      "loss": 0.5157,
+      "step": 97
+    },
+    {
+      "epoch": 3.3859649122807016,
+      "grad_norm": 0.5006252100198026,
+      "learning_rate": 7.094659326397818e-06,
+      "loss": 0.4591,
+      "step": 98
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.580855649746264,
+      "learning_rate": 6.795777628163599e-06,
+      "loss": 0.4592,
+      "step": 99
+    },
+    {
+      "epoch": 3.456140350877193,
+      "grad_norm": 0.4864958551783637,
+      "learning_rate": 6.50147327542137e-06,
+      "loss": 0.4456,
+      "step": 100
+    },
+    {
+      "epoch": 3.4912280701754383,
+      "grad_norm": 0.4386151451501962,
+      "learning_rate": 6.211910468096631e-06,
+      "loss": 0.4912,
+      "step": 101
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.5204884142263023,
+      "learning_rate": 5.927250760685441e-06,
+      "loss": 0.4882,
+      "step": 102
+    },
+    {
+      "epoch": 3.56140350877193,
+      "grad_norm": 0.4591459898899543,
+      "learning_rate": 5.647652972118998e-06,
+      "loss": 0.5029,
+      "step": 103
+    },
+    {
+      "epoch": 3.5964912280701755,
+      "grad_norm": 0.46162973899727977,
+      "learning_rate": 5.37327309715453e-06,
+      "loss": 0.4663,
+      "step": 104
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.4860430732891522,
+      "learning_rate": 5.104264219341793e-06,
+      "loss": 0.4381,
+      "step": 105
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.4382286914097587,
+      "learning_rate": 4.840776425613887e-06,
+      "loss": 0.4718,
+      "step": 106
+    },
+    {
+      "epoch": 3.7017543859649122,
+      "grad_norm": 0.3669218088879972,
+      "learning_rate": 4.5829567225498696e-06,
+      "loss": 0.4853,
+      "step": 107
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.4914583934045724,
+      "learning_rate": 4.330948954356076e-06,
+      "loss": 0.5486,
+      "step": 108
+    },
+    {
+      "epoch": 3.7719298245614032,
+      "grad_norm": 0.4105131971302891,
+      "learning_rate": 4.084893722611706e-06,
+      "loss": 0.5743,
+      "step": 109
+    },
+    {
+      "epoch": 3.807017543859649,
+      "grad_norm": 0.4293923567900349,
+      "learning_rate": 3.844928307823655e-06,
+      "loss": 0.5066,
+      "step": 110
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.42234992523360537,
+      "learning_rate": 3.6111865928341723e-06,
+      "loss": 0.5164,
+      "step": 111
+    },
+    {
+      "epoch": 3.8771929824561404,
+      "grad_norm": 0.3550274138683157,
+      "learning_rate": 3.3837989881242142e-06,
+      "loss": 0.4636,
+      "step": 112
+    },
+    {
+      "epoch": 3.912280701754386,
+      "grad_norm": 0.3696171628607218,
+      "learning_rate": 3.162892359054098e-06,
+      "loss": 0.4773,
+      "step": 113
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.3651667188910503,
+      "learning_rate": 2.948589955082085e-06,
+      "loss": 0.5031,
+      "step": 114
+    },
+    {
+      "epoch": 3.982456140350877,
+      "grad_norm": 0.33560060580788487,
+      "learning_rate": 2.74101134100033e-06,
+      "loss": 0.5182,
+      "step": 115
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6522055904321776,
+      "learning_rate": 2.540272330226658e-06,
+      "loss": 0.4388,
+      "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:c26b6109cfcaba35fc47a81fb83c06213e652d23ee9784a304320c3403a357d2
+size 8081