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:e903fb29cd9b5aa41b02957c4e10aa227b89146b7d28def7579c35ebf364a247
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f055d0afd647cffd51175e4462a18d77aa7a0df6256747e5138c7de12d1535e
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3ca297dab1554c427d7de9957b6e47ef958e698943134d8be97805e046c921
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d131e5ecffdd7e037a2f76629f966e2310f7cb81ec9c804f6eddc32970cca84
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1777048cd2b2fc628541968a305ca0645d1735e14fca055182c0f91593b1b305
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39955f9cf62f01346f018a7df2822768723e0d70d4a42f37796eaefb6b64dddc
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ca8df9a30a59e456b74e3d3990ad70a42935f43e1350022eda042fb68d6d6b
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec49870caabae1a36fe12a73c5a02c8dd85a57d8673f04fe4d053fe042aa98a2
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c30083b10bde21188b999e70019ea6d7d80b804e4ba907985ebaf04892519a2
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b606c761a5bfba45e97af8dc793ed088b90bddb25bbc94ff122760ce6fcc5bfa
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11648c9eed5f4c2b8c962fe8f4d5db3ee67d732e315581f4a87a67339315b6e5
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83e53f5c048f959ec16e2d7a146d436c98d4c85b449a45c87e67fd7beb459c4
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d771050f4c2a1e61623bf92329a0d7c385db7bc5a9f20a9d5be9d0285ab057da
+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 +1,475 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015873015873015872,
+      "grad_norm": 2.355871594757968,
+      "learning_rate": 0.0,
+      "loss": 1.0469,
+      "step": 1
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 2.29666205825573,
+      "learning_rate": 1.5625e-06,
+      "loss": 0.9929,
+      "step": 2
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 2.535252155158116,
+      "learning_rate": 3.125e-06,
+      "loss": 1.0185,
+      "step": 3
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 2.106429965859871,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 0.9046,
+      "step": 4
+    },
+    {
+      "epoch": 0.07936507936507936,
+      "grad_norm": 1.7754252196610092,
+      "learning_rate": 6.25e-06,
+      "loss": 1.0312,
+      "step": 5
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 1.5212254656019404,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.9741,
+      "step": 6
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 1.2286700272250457,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.924,
+      "step": 7
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 1.239763672997659,
+      "learning_rate": 1.09375e-05,
+      "loss": 0.9112,
+      "step": 8
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 1.7804807603399884,
+      "learning_rate": 1.25e-05,
+      "loss": 0.9631,
+      "step": 9
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 1.6096276860914913,
+      "learning_rate": 1.4062500000000001e-05,
+      "loss": 0.8914,
+      "step": 10
+    },
+    {
+      "epoch": 0.1746031746031746,
+      "grad_norm": 1.4685478602306294,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.8313,
+      "step": 11
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.797675338951107,
+      "learning_rate": 1.71875e-05,
+      "loss": 0.9572,
+      "step": 12
+    },
+    {
+      "epoch": 0.20634920634920634,
+      "grad_norm": 1.5020710264445867,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.8929,
+      "step": 13
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.389913325647765,
+      "learning_rate": 2.0312500000000002e-05,
+      "loss": 1.0575,
+      "step": 14
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 1.0364172775494112,
+      "learning_rate": 2.1875e-05,
+      "loss": 0.9367,
+      "step": 15
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 1.1754008678466592,
+      "learning_rate": 2.34375e-05,
+      "loss": 1.0082,
+      "step": 16
+    },
+    {
+      "epoch": 0.2698412698412698,
+      "grad_norm": 1.0227204004003465,
+      "learning_rate": 2.5e-05,
+      "loss": 0.9148,
+      "step": 17
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 1.0820292890536618,
+      "learning_rate": 2.6562500000000002e-05,
+      "loss": 0.9748,
+      "step": 18
+    },
+    {
+      "epoch": 0.30158730158730157,
+      "grad_norm": 0.945837076799249,
+      "learning_rate": 2.8125000000000003e-05,
+      "loss": 0.7132,
+      "step": 19
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 1.0248571882025115,
+      "learning_rate": 2.96875e-05,
+      "loss": 0.8881,
+      "step": 20
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.7825673389448284,
+      "learning_rate": 3.125e-05,
+      "loss": 0.9596,
+      "step": 21
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 0.9610289643147956,
+      "learning_rate": 3.2812500000000005e-05,
+      "loss": 1.0261,
+      "step": 22
+    },
+    {
+      "epoch": 0.36507936507936506,
+      "grad_norm": 0.9669319262880848,
+      "learning_rate": 3.4375e-05,
+      "loss": 0.8504,
+      "step": 23
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.7449356400588687,
+      "learning_rate": 3.59375e-05,
+      "loss": 0.8124,
+      "step": 24
+    },
+    {
+      "epoch": 0.3968253968253968,
+      "grad_norm": 0.83693613965816,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.0061,
+      "step": 25
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.732383235323442,
+      "learning_rate": 3.90625e-05,
+      "loss": 0.8433,
+      "step": 26
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.7794935876422098,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 0.7042,
+      "step": 27
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.7604958575268047,
+      "learning_rate": 4.21875e-05,
+      "loss": 0.9629,
+      "step": 28
+    },
+    {
+      "epoch": 0.4603174603174603,
+      "grad_norm": 0.6984385536231642,
+      "learning_rate": 4.375e-05,
+      "loss": 0.8909,
+      "step": 29
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.7941140442495155,
+      "learning_rate": 4.5312500000000004e-05,
+      "loss": 0.9318,
+      "step": 30
+    },
+    {
+      "epoch": 0.49206349206349204,
+      "grad_norm": 0.7485507149365567,
+      "learning_rate": 4.6875e-05,
+      "loss": 0.9032,
+      "step": 31
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 0.7312955579208906,
+      "learning_rate": 4.8437500000000005e-05,
+      "loss": 0.8793,
+      "step": 32
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 0.728955139017027,
+      "learning_rate": 5e-05,
+      "loss": 1.0292,
+      "step": 33
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 0.6223071714803796,
+      "learning_rate": 4.999845960383972e-05,
+      "loss": 0.829,
+      "step": 34
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.7081482857388056,
+      "learning_rate": 4.999383860518451e-05,
+      "loss": 0.821,
+      "step": 35
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.7021438050343367,
+      "learning_rate": 4.998613757348784e-05,
+      "loss": 0.9658,
+      "step": 36
+    },
+    {
+      "epoch": 0.5873015873015873,
+      "grad_norm": 0.6005545292155794,
+      "learning_rate": 4.9975357457760896e-05,
+      "loss": 0.9805,
+      "step": 37
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 0.66159765943155,
+      "learning_rate": 4.9961499586455584e-05,
+      "loss": 0.8479,
+      "step": 38
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 0.6859851915992995,
+      "learning_rate": 4.994456566730085e-05,
+      "loss": 0.9104,
+      "step": 39
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.5770937588145084,
+      "learning_rate": 4.9924557787092216e-05,
+      "loss": 0.7705,
+      "step": 40
+    },
+    {
+      "epoch": 0.6507936507936508,
+      "grad_norm": 0.5587380636863567,
+      "learning_rate": 4.990147841143462e-05,
+      "loss": 0.8406,
+      "step": 41
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5939117737515469,
+      "learning_rate": 4.9875330384438604e-05,
+      "loss": 0.9143,
+      "step": 42
+    },
+    {
+      "epoch": 0.6825396825396826,
+      "grad_norm": 0.5421902034671652,
+      "learning_rate": 4.984611692836979e-05,
+      "loss": 0.8323,
+      "step": 43
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 0.5523631282552526,
+      "learning_rate": 4.9813841643251836e-05,
+      "loss": 0.7557,
+      "step": 44
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.5991896816540728,
+      "learning_rate": 4.977850850642275e-05,
+      "loss": 0.8471,
+      "step": 45
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 0.6364621652121066,
+      "learning_rate": 4.97401218720448e-05,
+      "loss": 0.8013,
+      "step": 46
+    },
+    {
+      "epoch": 0.746031746031746,
+      "grad_norm": 0.5534873919742207,
+      "learning_rate": 4.969868647056792e-05,
+      "loss": 0.8996,
+      "step": 47
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.5035034360883922,
+      "learning_rate": 4.965420740814679e-05,
+      "loss": 0.8944,
+      "step": 48
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.5729489774574688,
+      "learning_rate": 4.9606690166011546e-05,
+      "loss": 0.7887,
+      "step": 49
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.6004405465949967,
+      "learning_rate": 4.95561405997924e-05,
+      "loss": 0.831,
+      "step": 50
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 0.725673276310606,
+      "learning_rate": 4.9502564938797946e-05,
+      "loss": 0.8849,
+      "step": 51
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 0.4990176056299948,
+      "learning_rate": 4.9445969785247595e-05,
+      "loss": 0.8298,
+      "step": 52
+    },
+    {
+      "epoch": 0.8412698412698413,
+      "grad_norm": 0.6071056927514447,
+      "learning_rate": 4.938636211345792e-05,
+      "loss": 0.944,
+      "step": 53
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.6345636016627114,
+      "learning_rate": 4.932374926898321e-05,
+      "loss": 0.8069,
+      "step": 54
+    },
+    {
+      "epoch": 0.873015873015873,
+      "grad_norm": 0.6333202856879505,
+      "learning_rate": 4.9258138967710306e-05,
+      "loss": 0.7373,
+      "step": 55
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.5152048396222051,
+      "learning_rate": 4.918953929490768e-05,
+      "loss": 0.8855,
+      "step": 56
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 0.5806639114473304,
+      "learning_rate": 4.9117958704229154e-05,
+      "loss": 0.8731,
+      "step": 57
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 0.6001547400645247,
+      "learning_rate": 4.904340601667208e-05,
+      "loss": 0.816,
+      "step": 58
+    },
+    {
+      "epoch": 0.9365079365079365,
+      "grad_norm": 0.470270082255384,
+      "learning_rate": 4.8965890419490354e-05,
+      "loss": 0.8847,
+      "step": 59
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.5015222585808989,
+      "learning_rate": 4.8885421465062236e-05,
+      "loss": 0.8507,
+      "step": 60
+    },
+    {
+      "epoch": 0.9682539682539683,
+      "grad_norm": 0.48808541077856465,
+      "learning_rate": 4.88020090697132e-05,
+      "loss": 0.774,
+      "step": 61
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 0.5837250225569859,
+      "learning_rate": 4.871566351249393e-05,
+      "loss": 0.8844,
+      "step": 62
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5121395435398158,
+      "learning_rate": 4.86263954339136e-05,
+      "loss": 0.7565,
+      "step": 63
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 315,
+  "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": 15539903594496.0,
+  "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 sha256:8f9800f202a2235e80940555255ee5d0a4a8197ca429c38110d4a4660b7d76fd
+size 7672