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:f013353a152dbf740e3e40426d0fb57cc95375d55ea6b6182108d06065c572bd
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d3d9b67356ea363e3a7a9523576ea32abcd7e28838c310ce4336ea0a557eca
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4912811e9c111d27eac5c7012a4b319e07721adf6852cdc97a3b30d730473050
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98059abc91d23be0af1fc426b2bc80cc2260e5c8b37a142172dd53b9603ca654
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8bb39b9b2190474281ac1372a5604a08ff42b453c6ff2878a7b065add9c107
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa26f0136f17c19119c87035c1f286a5070ce861db17cfadf7344e6cf81afa6
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3b6b9c30dca23c1a00dc7d6835db91b9d55b87aacf7024d0e77e0d324f6ef8
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ade185dc44449498f3626f012c12761a1f9bbe457c4ca693114a277972af68
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b269f3e124257c30c2196585d64ed14c5e29732c632dfec180c928f24115cf0
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7a3b28bbcdea0ef5b87fdc5d2886267f58cddd444bcb3b360dcf99dadf1bd5
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6070214e8e4cb86731de70ec40cba1bc1f1ff86e649a83ca3a97b8908d7b5e4
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f931b89827bb6d52d73ba29c396c670742a1657340c5e68f3aaf89ae10104aa4
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cec5bd377b2c4c04a6722309371d27e51ddc5e0f4a2baf3fd4953207bf6d35af
+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 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.18066847335140018,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018066847335140017,
+      "grad_norm": 2.833710603673153,
+      "learning_rate": 0.0,
+      "loss": 0.8251,
+      "step": 1
+    },
+    {
+      "epoch": 0.0036133694670280035,
+      "grad_norm": 2.881526090787093,
+      "learning_rate": 1.7857142857142858e-07,
+      "loss": 0.8284,
+      "step": 2
+    },
+    {
+      "epoch": 0.005420054200542005,
+      "grad_norm": 2.892351545715412,
+      "learning_rate": 3.5714285714285716e-07,
+      "loss": 0.8432,
+      "step": 3
+    },
+    {
+      "epoch": 0.007226738934056007,
+      "grad_norm": 2.854997748052911,
+      "learning_rate": 5.357142857142857e-07,
+      "loss": 0.8398,
+      "step": 4
+    },
+    {
+      "epoch": 0.009033423667570008,
+      "grad_norm": 2.800194786509123,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.8302,
+      "step": 5
+    },
+    {
+      "epoch": 0.01084010840108401,
+      "grad_norm": 2.7703722030307465,
+      "learning_rate": 8.928571428571429e-07,
+      "loss": 0.8306,
+      "step": 6
+    },
+    {
+      "epoch": 0.012646793134598013,
+      "grad_norm": 2.7419868468578503,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 0.813,
+      "step": 7
+    },
+    {
+      "epoch": 0.014453477868112014,
+      "grad_norm": 2.782799904203301,
+      "learning_rate": 1.25e-06,
+      "loss": 0.8215,
+      "step": 8
+    },
+    {
+      "epoch": 0.016260162601626018,
+      "grad_norm": 2.657957788320578,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.8192,
+      "step": 9
+    },
+    {
+      "epoch": 0.018066847335140017,
+      "grad_norm": 2.599128638584182,
+      "learning_rate": 1.6071428571428574e-06,
+      "loss": 0.8146,
+      "step": 10
+    },
+    {
+      "epoch": 0.01987353206865402,
+      "grad_norm": 2.2653416227389065,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 0.8023,
+      "step": 11
+    },
+    {
+      "epoch": 0.02168021680216802,
+      "grad_norm": 2.132529562690701,
+      "learning_rate": 1.9642857142857144e-06,
+      "loss": 0.813,
+      "step": 12
+    },
+    {
+      "epoch": 0.023486901535682024,
+      "grad_norm": 2.183869626490225,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.8047,
+      "step": 13
+    },
+    {
+      "epoch": 0.025293586269196026,
+      "grad_norm": 2.038470938805882,
+      "learning_rate": 2.321428571428572e-06,
+      "loss": 0.8006,
+      "step": 14
+    },
+    {
+      "epoch": 0.02710027100271003,
+      "grad_norm": 1.4549601698726884,
+      "learning_rate": 2.5e-06,
+      "loss": 0.7864,
+      "step": 15
+    },
+    {
+      "epoch": 0.028906955736224028,
+      "grad_norm": 1.4204350596775097,
+      "learning_rate": 2.6785714285714285e-06,
+      "loss": 0.7795,
+      "step": 16
+    },
+    {
+      "epoch": 0.03071364046973803,
+      "grad_norm": 1.3806667810715707,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.7872,
+      "step": 17
+    },
+    {
+      "epoch": 0.032520325203252036,
+      "grad_norm": 1.274491626508539,
+      "learning_rate": 3.0357142857142856e-06,
+      "loss": 0.7795,
+      "step": 18
+    },
+    {
+      "epoch": 0.03432700993676603,
+      "grad_norm": 1.216777658487583,
+      "learning_rate": 3.2142857142857147e-06,
+      "loss": 0.773,
+      "step": 19
+    },
+    {
+      "epoch": 0.036133694670280034,
+      "grad_norm": 1.0495765967682895,
+      "learning_rate": 3.3928571428571435e-06,
+      "loss": 0.743,
+      "step": 20
+    },
+    {
+      "epoch": 0.037940379403794036,
+      "grad_norm": 1.1207660747477255,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.7403,
+      "step": 21
+    },
+    {
+      "epoch": 0.03974706413730804,
+      "grad_norm": 1.2817143165080294,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.7296,
+      "step": 22
+    },
+    {
+      "epoch": 0.04155374887082204,
+      "grad_norm": 1.3509916465584577,
+      "learning_rate": 3.928571428571429e-06,
+      "loss": 0.7302,
+      "step": 23
+    },
+    {
+      "epoch": 0.04336043360433604,
+      "grad_norm": 1.2332702771542092,
+      "learning_rate": 4.107142857142857e-06,
+      "loss": 0.7359,
+      "step": 24
+    },
+    {
+      "epoch": 0.045167118337850046,
+      "grad_norm": 0.9471118008485697,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.7129,
+      "step": 25
+    },
+    {
+      "epoch": 0.04697380307136405,
+      "grad_norm": 0.7486583362489228,
+      "learning_rate": 4.464285714285715e-06,
+      "loss": 0.7275,
+      "step": 26
+    },
+    {
+      "epoch": 0.04878048780487805,
+      "grad_norm": 0.6717818173905871,
+      "learning_rate": 4.642857142857144e-06,
+      "loss": 0.7021,
+      "step": 27
+    },
+    {
+      "epoch": 0.05058717253839205,
+      "grad_norm": 0.7950859243166388,
+      "learning_rate": 4.821428571428572e-06,
+      "loss": 0.6997,
+      "step": 28
+    },
+    {
+      "epoch": 0.052393857271906055,
+      "grad_norm": 0.8884910173051872,
+      "learning_rate": 5e-06,
+      "loss": 0.7086,
+      "step": 29
+    },
+    {
+      "epoch": 0.05420054200542006,
+      "grad_norm": 0.9673224881715593,
+      "learning_rate": 4.999955240022903e-06,
+      "loss": 0.7067,
+      "step": 30
+    },
+    {
+      "epoch": 0.05600722673893405,
+      "grad_norm": 0.9034786964026056,
+      "learning_rate": 4.999820961694372e-06,
+      "loss": 0.6936,
+      "step": 31
+    },
+    {
+      "epoch": 0.057813911472448055,
+      "grad_norm": 0.662557988289521,
+      "learning_rate": 4.999597169822646e-06,
+      "loss": 0.6811,
+      "step": 32
+    },
+    {
+      "epoch": 0.05962059620596206,
+      "grad_norm": 0.5043328133424003,
+      "learning_rate": 4.999283872421259e-06,
+      "loss": 0.6911,
+      "step": 33
+    },
+    {
+      "epoch": 0.06142728093947606,
+      "grad_norm": 0.5806752340113361,
+      "learning_rate": 4.998881080708759e-06,
+      "loss": 0.6766,
+      "step": 34
+    },
+    {
+      "epoch": 0.06323396567299007,
+      "grad_norm": 0.572041040601822,
+      "learning_rate": 4.998388809108304e-06,
+      "loss": 0.6815,
+      "step": 35
+    },
+    {
+      "epoch": 0.06504065040650407,
+      "grad_norm": 0.49944539615671646,
+      "learning_rate": 4.997807075247147e-06,
+      "loss": 0.6752,
+      "step": 36
+    },
+    {
+      "epoch": 0.06684733514001806,
+      "grad_norm": 0.5564450644413174,
+      "learning_rate": 4.997135899956002e-06,
+      "loss": 0.6781,
+      "step": 37
+    },
+    {
+      "epoch": 0.06865401987353206,
+      "grad_norm": 0.4421624128151595,
+      "learning_rate": 4.996375307268303e-06,
+      "loss": 0.6708,
+      "step": 38
+    },
+    {
+      "epoch": 0.07046070460704607,
+      "grad_norm": 0.4865410430073666,
+      "learning_rate": 4.995525324419338e-06,
+      "loss": 0.6706,
+      "step": 39
+    },
+    {
+      "epoch": 0.07226738934056007,
+      "grad_norm": 0.3765775514297677,
+      "learning_rate": 4.994585981845278e-06,
+      "loss": 0.659,
+      "step": 40
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.3548944502238461,
+      "learning_rate": 4.993557313182086e-06,
+      "loss": 0.6664,
+      "step": 41
+    },
+    {
+      "epoch": 0.07588075880758807,
+      "grad_norm": 0.36293566558445617,
+      "learning_rate": 4.992439355264308e-06,
+      "loss": 0.656,
+      "step": 42
+    },
+    {
+      "epoch": 0.07768744354110207,
+      "grad_norm": 0.3975630575488288,
+      "learning_rate": 4.9912321481237616e-06,
+      "loss": 0.6566,
+      "step": 43
+    },
+    {
+      "epoch": 0.07949412827461608,
+      "grad_norm": 0.37034479741196286,
+      "learning_rate": 4.989935734988098e-06,
+      "loss": 0.6492,
+      "step": 44
+    },
+    {
+      "epoch": 0.08130081300813008,
+      "grad_norm": 0.35041438533218666,
+      "learning_rate": 4.988550162279255e-06,
+      "loss": 0.6557,
+      "step": 45
+    },
+    {
+      "epoch": 0.08310749774164408,
+      "grad_norm": 0.3929751461483523,
+      "learning_rate": 4.9870754796117956e-06,
+      "loss": 0.658,
+      "step": 46
+    },
+    {
+      "epoch": 0.08491418247515808,
+      "grad_norm": 0.3228131120122744,
+      "learning_rate": 4.985511739791129e-06,
+      "loss": 0.6595,
+      "step": 47
+    },
+    {
+      "epoch": 0.08672086720867209,
+      "grad_norm": 0.32669811901998275,
+      "learning_rate": 4.983858998811622e-06,
+      "loss": 0.6464,
+      "step": 48
+    },
+    {
+      "epoch": 0.08852755194218609,
+      "grad_norm": 0.2958192972688314,
+      "learning_rate": 4.982117315854594e-06,
+      "loss": 0.6508,
+      "step": 49
+    },
+    {
+      "epoch": 0.09033423667570009,
+      "grad_norm": 0.29517256658089447,
+      "learning_rate": 4.980286753286196e-06,
+      "loss": 0.6493,
+      "step": 50
+    },
+    {
+      "epoch": 0.0921409214092141,
+      "grad_norm": 0.28707888927411485,
+      "learning_rate": 4.978367376655177e-06,
+      "loss": 0.639,
+      "step": 51
+    },
+    {
+      "epoch": 0.0939476061427281,
+      "grad_norm": 0.2839510706729385,
+      "learning_rate": 4.976359254690543e-06,
+      "loss": 0.6577,
+      "step": 52
+    },
+    {
+      "epoch": 0.0957542908762421,
+      "grad_norm": 0.2652433955956874,
+      "learning_rate": 4.974262459299088e-06,
+      "loss": 0.6408,
+      "step": 53
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.26894761764637504,
+      "learning_rate": 4.9720770655628216e-06,
+      "loss": 0.6323,
+      "step": 54
+    },
+    {
+      "epoch": 0.0993676603432701,
+      "grad_norm": 0.3393488396315471,
+      "learning_rate": 4.969803151736285e-06,
+      "loss": 0.6443,
+      "step": 55
+    },
+    {
+      "epoch": 0.1011743450767841,
+      "grad_norm": 0.2936280995299213,
+      "learning_rate": 4.967440799243739e-06,
+      "loss": 0.6504,
+      "step": 56
+    },
+    {
+      "epoch": 0.10298102981029811,
+      "grad_norm": 0.5048572168975388,
+      "learning_rate": 4.964990092676263e-06,
+      "loss": 0.6358,
+      "step": 57
+    },
+    {
+      "epoch": 0.10478771454381211,
+      "grad_norm": 0.253534540909337,
+      "learning_rate": 4.962451119788709e-06,
+      "loss": 0.6434,
+      "step": 58
+    },
+    {
+      "epoch": 0.10659439927732611,
+      "grad_norm": 0.24450647410382542,
+      "learning_rate": 4.959823971496575e-06,
+      "loss": 0.6287,
+      "step": 59
+    },
+    {
+      "epoch": 0.10840108401084012,
+      "grad_norm": 0.24318659934415682,
+      "learning_rate": 4.957108741872736e-06,
+      "loss": 0.6298,
+      "step": 60
+    },
+    {
+      "epoch": 0.1102077687443541,
+      "grad_norm": 0.26159880879938346,
+      "learning_rate": 4.954305528144085e-06,
+      "loss": 0.6338,
+      "step": 61
+    },
+    {
+      "epoch": 0.1120144534778681,
+      "grad_norm": 0.25390256208872614,
+      "learning_rate": 4.9514144306880506e-06,
+      "loss": 0.6392,
+      "step": 62
+    },
+    {
+      "epoch": 0.11382113821138211,
+      "grad_norm": 0.2557236984724456,
+      "learning_rate": 4.948435553028994e-06,
+      "loss": 0.6381,
+      "step": 63
+    },
+    {
+      "epoch": 0.11562782294489611,
+      "grad_norm": 0.24995746272587419,
+      "learning_rate": 4.9453690018345144e-06,
+      "loss": 0.6358,
+      "step": 64
+    },
+    {
+      "epoch": 0.11743450767841011,
+      "grad_norm": 0.24266667399842143,
+      "learning_rate": 4.942214886911619e-06,
+      "loss": 0.6309,
+      "step": 65
+    },
+    {
+      "epoch": 0.11924119241192412,
+      "grad_norm": 0.2614760212116958,
+      "learning_rate": 4.938973321202799e-06,
+      "loss": 0.6324,
+      "step": 66
+    },
+    {
+      "epoch": 0.12104787714543812,
+      "grad_norm": 0.23803026874912583,
+      "learning_rate": 4.935644420781978e-06,
+      "loss": 0.6228,
+      "step": 67
+    },
+    {
+      "epoch": 0.12285456187895212,
+      "grad_norm": 0.23755765861041625,
+      "learning_rate": 4.932228304850363e-06,
+      "loss": 0.6387,
+      "step": 68
+    },
+    {
+      "epoch": 0.12466124661246612,
+      "grad_norm": 0.23843258528052497,
+      "learning_rate": 4.9287250957321685e-06,
+      "loss": 0.6401,
+      "step": 69
+    },
+    {
+      "epoch": 0.12646793134598014,
+      "grad_norm": 0.26210939608771777,
+      "learning_rate": 4.925134918870245e-06,
+      "loss": 0.6458,
+      "step": 70
+    },
+    {
+      "epoch": 0.12827461607949414,
+      "grad_norm": 0.32756867637738996,
+      "learning_rate": 4.921457902821578e-06,
+      "loss": 0.6164,
+      "step": 71
+    },
+    {
+      "epoch": 0.13008130081300814,
+      "grad_norm": 0.23025066317701987,
+      "learning_rate": 4.917694179252692e-06,
+      "loss": 0.6343,
+      "step": 72
+    },
+    {
+      "epoch": 0.13188798554652212,
+      "grad_norm": 0.2342725143215051,
+      "learning_rate": 4.9138438829349296e-06,
+      "loss": 0.633,
+      "step": 73
+    },
+    {
+      "epoch": 0.13369467028003612,
+      "grad_norm": 0.25602275015410886,
+      "learning_rate": 4.909907151739634e-06,
+      "loss": 0.6247,
+      "step": 74
+    },
+    {
+      "epoch": 0.13550135501355012,
+      "grad_norm": 0.27962135134351895,
+      "learning_rate": 4.9058841266332005e-06,
+      "loss": 0.6226,
+      "step": 75
+    },
+    {
+      "epoch": 0.13730803974706413,
+      "grad_norm": 0.2577599322141621,
+      "learning_rate": 4.901774951672041e-06,
+      "loss": 0.618,
+      "step": 76
+    },
+    {
+      "epoch": 0.13911472448057813,
+      "grad_norm": 0.25384048802645065,
+      "learning_rate": 4.897579773997415e-06,
+      "loss": 0.6122,
+      "step": 77
+    },
+    {
+      "epoch": 0.14092140921409213,
+      "grad_norm": 0.25252662487176686,
+      "learning_rate": 4.893298743830168e-06,
+      "loss": 0.625,
+      "step": 78
+    },
+    {
+      "epoch": 0.14272809394760613,
+      "grad_norm": 0.2581525435101277,
+      "learning_rate": 4.8889320144653525e-06,
+      "loss": 0.6345,
+      "step": 79
+    },
+    {
+      "epoch": 0.14453477868112014,
+      "grad_norm": 0.2559916652692462,
+      "learning_rate": 4.884479742266731e-06,
+      "loss": 0.6432,
+      "step": 80
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.2633785753789179,
+      "learning_rate": 4.879942086661185e-06,
+      "loss": 0.625,
+      "step": 81
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.25653911708344745,
+      "learning_rate": 4.875319210133004e-06,
+      "loss": 0.6185,
+      "step": 82
+    },
+    {
+      "epoch": 0.14995483288166214,
+      "grad_norm": 0.2508750960975656,
+      "learning_rate": 4.870611278218066e-06,
+      "loss": 0.6301,
+      "step": 83
+    },
+    {
+      "epoch": 0.15176151761517614,
+      "grad_norm": 0.2561874287228457,
+      "learning_rate": 4.865818459497911e-06,
+      "loss": 0.6222,
+      "step": 84
+    },
+    {
+      "epoch": 0.15356820234869015,
+      "grad_norm": 0.2353115985430909,
+      "learning_rate": 4.860940925593703e-06,
+      "loss": 0.6238,
+      "step": 85
+    },
+    {
+      "epoch": 0.15537488708220415,
+      "grad_norm": 0.24543988420919832,
+      "learning_rate": 4.855978851160088e-06,
+      "loss": 0.6243,
+      "step": 86
+    },
+    {
+      "epoch": 0.15718157181571815,
+      "grad_norm": 0.23980236271661898,
+      "learning_rate": 4.850932413878934e-06,
+      "loss": 0.6264,
+      "step": 87
+    },
+    {
+      "epoch": 0.15898825654923215,
+      "grad_norm": 0.23746967391567278,
+      "learning_rate": 4.845801794452978e-06,
+      "loss": 0.6308,
+      "step": 88
+    },
+    {
+      "epoch": 0.16079494128274616,
+      "grad_norm": 0.2438060428432456,
+      "learning_rate": 4.8405871765993435e-06,
+      "loss": 0.6256,
+      "step": 89
+    },
+    {
+      "epoch": 0.16260162601626016,
+      "grad_norm": 0.2504401843691212,
+      "learning_rate": 4.8352887470429726e-06,
+      "loss": 0.6193,
+      "step": 90
+    },
+    {
+      "epoch": 0.16440831074977416,
+      "grad_norm": 0.22268738858248663,
+      "learning_rate": 4.829906695509934e-06,
+      "loss": 0.6175,
+      "step": 91
+    },
+    {
+      "epoch": 0.16621499548328816,
+      "grad_norm": 0.2560623721447496,
+      "learning_rate": 4.824441214720629e-06,
+      "loss": 0.6207,
+      "step": 92
+    },
+    {
+      "epoch": 0.16802168021680217,
+      "grad_norm": 0.23139572900738714,
+      "learning_rate": 4.8188925003828945e-06,
+      "loss": 0.6276,
+      "step": 93
+    },
+    {
+      "epoch": 0.16982836495031617,
+      "grad_norm": 0.2394430562047215,
+      "learning_rate": 4.813260751184992e-06,
+      "loss": 0.6254,
+      "step": 94
+    },
+    {
+      "epoch": 0.17163504968383017,
+      "grad_norm": 0.23489365258879913,
+      "learning_rate": 4.8075461687884935e-06,
+      "loss": 0.6184,
+      "step": 95
+    },
+    {
+      "epoch": 0.17344173441734417,
+      "grad_norm": 0.2390908704544338,
+      "learning_rate": 4.801748957821061e-06,
+      "loss": 0.6164,
+      "step": 96
+    },
+    {
+      "epoch": 0.17524841915085818,
+      "grad_norm": 0.2250588188582116,
+      "learning_rate": 4.795869325869117e-06,
+      "loss": 0.623,
+      "step": 97
+    },
+    {
+      "epoch": 0.17705510388437218,
+      "grad_norm": 0.21860584575831038,
+      "learning_rate": 4.7899074834704165e-06,
+      "loss": 0.6173,
+      "step": 98
+    },
+    {
+      "epoch": 0.17886178861788618,
+      "grad_norm": 0.24617787352480855,
+      "learning_rate": 4.783863644106502e-06,
+      "loss": 0.6291,
+      "step": 99
+    },
+    {
+      "epoch": 0.18066847335140018,
+      "grad_norm": 0.21802652765301336,
+      "learning_rate": 4.777738024195065e-06,
+      "loss": 0.603,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 553,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 115440686923776.0,
+  "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 sha256:862cf87b1e05c0e1fb9e771f81ab56a7c4bd43704732a82920faf23e31b14aea
+size 8017