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:c66edf0390bb21ae2a3dc53d6af49ddb8dde9718a4b1c6ef1e820aa22d89153b
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0337a09c934ebe39c9a6989791cc3734b1936133b660e78c7cb0c9fadd70caec
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2edd70a6b1ed0e792160eba761e3e382cd9b71f407604cc9b50536e54d252416
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0cf3e42c6af3df8af158eaf97adc86c22be773048ab52c269adb75ad3bc39fe
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75474e30f9f11ea4393fcc5e7f0b7fd2cb43a229478e8f2a604af8b34ded2f04
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ad236a1942c03aa8db148ba0b60e67b5c8e87a7948e55a6a0363034f3942e0
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fbe5c92a3e14d8d60fbc4bab5fdb7f9ea3abf7d6dc9f1341cc6acdb88ad4927
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97191fb2e4bcc5cd85ad7ba3c53db9b8551fcc2caf672298fc489afbdf073f4
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81d5b3e7a587f6623730cec15f9bf026e3892da1b847af23938e7c41ae4ea4a
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d707a9a31cacc8e42cf3e027a3b20db7b99a02f3578b5533154871be83173153
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c33f8f7da5d206fcad1cbb6fad381d3f6e477080cc25f0181eb2c9109539a5
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bea3a915fb9676c0a3fcb98e560553f0c7468e34f2b6af03196f1cb3b279aae
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a60628f974a57a4b5fd2e8c90a4d67421c00ec3553ab9019386ebe97dba376
+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 +1,524 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.028985507246376812,
+      "grad_norm": 11.274454167048727,
+      "learning_rate": 0.0,
+      "loss": 0.6357,
+      "step": 1
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "grad_norm": 10.143348640958312,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.6666,
+      "step": 2
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 9.086409087474683,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.6451,
+      "step": 3
+    },
+    {
+      "epoch": 0.11594202898550725,
+      "grad_norm": 8.70666602748876,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.6048,
+      "step": 4
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 8.976482480167713,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.5937,
+      "step": 5
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 6.543196052759934,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.4943,
+      "step": 6
+    },
+    {
+      "epoch": 0.2028985507246377,
+      "grad_norm": 7.511256155710179,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.4247,
+      "step": 7
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 3.274069972289533,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.302,
+      "step": 8
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 5.507527578193957,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.2751,
+      "step": 9
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 3.651481150079746,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.2311,
+      "step": 10
+    },
+    {
+      "epoch": 0.3188405797101449,
+      "grad_norm": 2.9570009811876314,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.2133,
+      "step": 11
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 2.5680951348234355,
+      "learning_rate": 1e-05,
+      "loss": 0.2021,
+      "step": 12
+    },
+    {
+      "epoch": 0.37681159420289856,
+      "grad_norm": 2.4726534615132394,
+      "learning_rate": 9.997020702755353e-06,
+      "loss": 0.2086,
+      "step": 13
+    },
+    {
+      "epoch": 0.4057971014492754,
+      "grad_norm": 2.0168121750509207,
+      "learning_rate": 9.98808636150624e-06,
+      "loss": 0.1844,
+      "step": 14
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 1.988964439347895,
+      "learning_rate": 9.973207623475964e-06,
+      "loss": 0.1561,
+      "step": 15
+    },
+    {
+      "epoch": 0.463768115942029,
+      "grad_norm": 1.703404936865681,
+      "learning_rate": 9.952402219937817e-06,
+      "loss": 0.1561,
+      "step": 16
+    },
+    {
+      "epoch": 0.4927536231884058,
+      "grad_norm": 1.4224019007386586,
+      "learning_rate": 9.925694945084369e-06,
+      "loss": 0.1359,
+      "step": 17
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 1.390079768168245,
+      "learning_rate": 9.893117626479778e-06,
+      "loss": 0.1422,
+      "step": 18
+    },
+    {
+      "epoch": 0.5507246376811594,
+      "grad_norm": 1.363268530198362,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.1448,
+      "step": 19
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 1.2167507253689909,
+      "learning_rate": 9.810515099218004e-06,
+      "loss": 0.1276,
+      "step": 20
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 1.1574568817316992,
+      "learning_rate": 9.76058832955357e-06,
+      "loss": 0.1177,
+      "step": 21
+    },
+    {
+      "epoch": 0.6376811594202898,
+      "grad_norm": 1.2101868179533353,
+      "learning_rate": 9.704988276811883e-06,
+      "loss": 0.1086,
+      "step": 22
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.1144422829365617,
+      "learning_rate": 9.643781200626512e-06,
+      "loss": 0.1291,
+      "step": 23
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 1.2450794816372637,
+      "learning_rate": 9.577040042626832e-06,
+      "loss": 0.1183,
+      "step": 24
+    },
+    {
+      "epoch": 0.7246376811594203,
+      "grad_norm": 1.2167862630409976,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.1213,
+      "step": 25
+    },
+    {
+      "epoch": 0.7536231884057971,
+      "grad_norm": 1.248557822116599,
+      "learning_rate": 9.427280128266049e-06,
+      "loss": 0.1177,
+      "step": 26
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 1.113733087204506,
+      "learning_rate": 9.344439843625034e-06,
+      "loss": 0.1152,
+      "step": 27
+    },
+    {
+      "epoch": 0.8115942028985508,
+      "grad_norm": 1.1038118432089006,
+      "learning_rate": 9.256422207921757e-06,
+      "loss": 0.1246,
+      "step": 28
+    },
+    {
+      "epoch": 0.8405797101449275,
+      "grad_norm": 1.100623510584588,
+      "learning_rate": 9.163332113436031e-06,
+      "loss": 0.1184,
+      "step": 29
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 1.0179727735610475,
+      "learning_rate": 9.065280497392663e-06,
+      "loss": 0.1096,
+      "step": 30
+    },
+    {
+      "epoch": 0.8985507246376812,
+      "grad_norm": 1.2701457238654967,
+      "learning_rate": 8.962384209755453e-06,
+      "loss": 0.1195,
+      "step": 31
+    },
+    {
+      "epoch": 0.927536231884058,
+      "grad_norm": 1.1294896292998675,
+      "learning_rate": 8.854765873974898e-06,
+      "loss": 0.1105,
+      "step": 32
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 1.1171814840270677,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.1175,
+      "step": 33
+    },
+    {
+      "epoch": 0.9855072463768116,
+      "grad_norm": 0.9886273247393406,
+      "learning_rate": 8.625881535716883e-06,
+      "loss": 0.1058,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9886273247393406,
+      "learning_rate": 8.504888299030748e-06,
+      "loss": 0.1001,
+      "step": 35
+    },
+    {
+      "epoch": 1.0289855072463767,
+      "grad_norm": 1.5562818130049305,
+      "learning_rate": 8.379718220723772e-06,
+      "loss": 0.0727,
+      "step": 36
+    },
+    {
+      "epoch": 1.0579710144927537,
+      "grad_norm": 0.8147596643901716,
+      "learning_rate": 8.250520468343722e-06,
+      "loss": 0.0871,
+      "step": 37
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 0.785533808227011,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.0752,
+      "step": 38
+    },
+    {
+      "epoch": 1.1159420289855073,
+      "grad_norm": 1.067197574454516,
+      "learning_rate": 7.980662427346127e-06,
+      "loss": 0.0862,
+      "step": 39
+    },
+    {
+      "epoch": 1.144927536231884,
+      "grad_norm": 1.0067934230612672,
+      "learning_rate": 7.84032373365578e-06,
+      "loss": 0.0928,
+      "step": 40
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 1.027473082943366,
+      "learning_rate": 7.696600172495997e-06,
+      "loss": 0.0757,
+      "step": 41
+    },
+    {
+      "epoch": 1.2028985507246377,
+      "grad_norm": 0.9703955436663084,
+      "learning_rate": 7.5496630219506805e-06,
+      "loss": 0.0621,
+      "step": 42
+    },
+    {
+      "epoch": 1.2318840579710144,
+      "grad_norm": 0.9885265576714246,
+      "learning_rate": 7.399687389798933e-06,
+      "loss": 0.0855,
+      "step": 43
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 0.9758981949816004,
+      "learning_rate": 7.246852004835807e-06,
+      "loss": 0.084,
+      "step": 44
+    },
+    {
+      "epoch": 1.289855072463768,
+      "grad_norm": 0.9024594434416954,
+      "learning_rate": 7.091339003877826e-06,
+      "loss": 0.0767,
+      "step": 45
+    },
+    {
+      "epoch": 1.318840579710145,
+      "grad_norm": 0.830224350365886,
+      "learning_rate": 6.933333714707094e-06,
+      "loss": 0.0806,
+      "step": 46
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 0.8475268092069895,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.0686,
+      "step": 47
+    },
+    {
+      "epoch": 1.3768115942028984,
+      "grad_norm": 0.8152669559501473,
+      "learning_rate": 6.6106022089924535e-06,
+      "loss": 0.0913,
+      "step": 48
+    },
+    {
+      "epoch": 1.4057971014492754,
+      "grad_norm": 0.8455140548788239,
+      "learning_rate": 6.4462605976828395e-06,
+      "loss": 0.0746,
+      "step": 49
+    },
+    {
+      "epoch": 1.434782608695652,
+      "grad_norm": 0.817492348372533,
+      "learning_rate": 6.280195450287736e-06,
+      "loss": 0.0976,
+      "step": 50
+    },
+    {
+      "epoch": 1.463768115942029,
+      "grad_norm": 0.880952546066598,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.0833,
+      "step": 51
+    },
+    {
+      "epoch": 1.4927536231884058,
+      "grad_norm": 0.8489601481147181,
+      "learning_rate": 5.943687977264584e-06,
+      "loss": 0.0784,
+      "step": 52
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 0.8142122839258903,
+      "learning_rate": 5.773646673951406e-06,
+      "loss": 0.0838,
+      "step": 53
+    },
+    {
+      "epoch": 1.5507246376811594,
+      "grad_norm": 0.8922929202950094,
+      "learning_rate": 5.6026834012766155e-06,
+      "loss": 0.0828,
+      "step": 54
+    },
+    {
+      "epoch": 1.5797101449275361,
+      "grad_norm": 0.7122624377371234,
+      "learning_rate": 5.4310018994030974e-06,
+      "loss": 0.0797,
+      "step": 55
+    },
+    {
+      "epoch": 1.608695652173913,
+      "grad_norm": 0.9217981197726534,
+      "learning_rate": 5.258806764421048e-06,
+      "loss": 0.0772,
+      "step": 56
+    },
+    {
+      "epoch": 1.6376811594202898,
+      "grad_norm": 0.9257391753751778,
+      "learning_rate": 5.0863032045269435e-06,
+      "loss": 0.0766,
+      "step": 57
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.8307688279849595,
+      "learning_rate": 4.913696795473058e-06,
+      "loss": 0.0818,
+      "step": 58
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.9173954819802914,
+      "learning_rate": 4.741193235578953e-06,
+      "loss": 0.0927,
+      "step": 59
+    },
+    {
+      "epoch": 1.7246376811594204,
+      "grad_norm": 0.8708594385417067,
+      "learning_rate": 4.568998100596903e-06,
+      "loss": 0.0665,
+      "step": 60
+    },
+    {
+      "epoch": 1.7536231884057971,
+      "grad_norm": 0.8126974465329198,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.0839,
+      "step": 61
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 0.853158086441921,
+      "learning_rate": 4.226353326048594e-06,
+      "loss": 0.0773,
+      "step": 62
+    },
+    {
+      "epoch": 1.8115942028985508,
+      "grad_norm": 0.8525307891771787,
+      "learning_rate": 4.056312022735417e-06,
+      "loss": 0.0809,
+      "step": 63
+    },
+    {
+      "epoch": 1.8405797101449275,
+      "grad_norm": 1.0467111292284437,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.0782,
+      "step": 64
+    },
+    {
+      "epoch": 1.8695652173913042,
+      "grad_norm": 0.9286296034389645,
+      "learning_rate": 3.7198045497122647e-06,
+      "loss": 0.0774,
+      "step": 65
+    },
+    {
+      "epoch": 1.8985507246376812,
+      "grad_norm": 0.7656482475139829,
+      "learning_rate": 3.553739402317162e-06,
+      "loss": 0.0767,
+      "step": 66
+    },
+    {
+      "epoch": 1.927536231884058,
+      "grad_norm": 0.7766347569440668,
+      "learning_rate": 3.389397791007548e-06,
+      "loss": 0.0984,
+      "step": 67
+    },
+    {
+      "epoch": 1.9565217391304348,
+      "grad_norm": 0.7336465690307817,
+      "learning_rate": 3.226975564787322e-06,
+      "loss": 0.074,
+      "step": 68
+    },
+    {
+      "epoch": 1.9855072463768115,
+      "grad_norm": 0.795203124951574,
+      "learning_rate": 3.0666662852929063e-06,
+      "loss": 0.0785,
+      "step": 69
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.2688010574239046,
+      "learning_rate": 2.9086609961221758e-06,
+      "loss": 0.0659,
+      "step": 70
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 102,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 6977636007936.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534bc8e474028dbf459153f9e2e4d91c0f9abbba10a638ebb072d0c0a02971de
+size 7608