Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a9621d627d4b69570f9471e368771d7548798ba88f3c0eb317ce150d9a3d70
+oid sha256:d98edc3d2ca1aec91433e9987eee768c36fddb0d2cde139c9b53415ce830ce40
 size 1192135096

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b535e39d606564233a120331ad9e0121c45ae5b345ddc807d5c8a7366d4e1002
+oid sha256:9069b63adcfe2746e98414c2c83d0ddd2f1f9d6d20a61a295651cba33be78589
 size 2384459962

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf649bac0f2cfebbcf7fed3fb87fad328f4aea97a5892dffe764f4191f92f88c
+oid sha256:3062b0a02968eef37b0d0a0387798ef4cd562c0a577e5e8055c6181ccd441515
 size 1064

special_tokens_map.json

@@ -15,11 +15,11 @@
     "<|video_pad|>"
   ],
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|im_end|>"
+  "pad_token": "<|endoftext|>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:574de68a0f63f2004784a421c7d42c2b2786c05cb38542d2ed3525757a1f7fde
+size 11422932

tokenizer_config.json

@@ -229,11 +229,11 @@
   "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|>",
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,
-  "pad_token": "<|im_end|>",
+  "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

trainer_state.json

@@ -2,100 +2,151 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9984,
-  "eval_steps": 500,
-  "global_step": 312,
+  "epoch": 0.9994666666666666,
+  "eval_steps": 100,
+  "global_step": 937,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.08,
-      "grad_norm": 6.90625,
-      "learning_rate": 4.615384615384616e-05,
-      "loss": 0.9872,
-      "step": 25
+      "epoch": 0.10666666666666667,
+      "grad_norm": 6.6875,
+      "learning_rate": 4.471718249733191e-05,
+      "loss": 1.2181,
+      "step": 100
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "eval_loss": 1.4656692743301392,
+      "eval_runtime": 128.3122,
+      "eval_samples_per_second": 44.703,
+      "eval_steps_per_second": 5.588,
+      "step": 100
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 6.5625,
+      "learning_rate": 3.938100320170758e-05,
+      "loss": 1.1539,
+      "step": 200
     },
     {
-      "epoch": 0.16,
-      "grad_norm": 7.0,
-      "learning_rate": 4.21474358974359e-05,
-      "loss": 0.9209,
-      "step": 50
+      "epoch": 0.21333333333333335,
+      "eval_loss": 1.4585195779800415,
+      "eval_runtime": 128.2644,
+      "eval_samples_per_second": 44.72,
+      "eval_steps_per_second": 5.59,
+      "step": 200
     },
     {
-      "epoch": 0.24,
-      "grad_norm": 6.90625,
-      "learning_rate": 3.814102564102564e-05,
-      "loss": 0.866,
-      "step": 75
+      "epoch": 0.32,
+      "grad_norm": 5.625,
+      "learning_rate": 3.4044823906083245e-05,
+      "loss": 1.1353,
+      "step": 300
     },
     {
       "epoch": 0.32,
-      "grad_norm": 6.09375,
-      "learning_rate": 3.4134615384615386e-05,
-      "loss": 0.8653,
-      "step": 100
+      "eval_loss": 1.4478052854537964,
+      "eval_runtime": 128.1523,
+      "eval_samples_per_second": 44.759,
+      "eval_steps_per_second": 5.595,
+      "step": 300
     },
     {
-      "epoch": 0.4,
-      "grad_norm": 7.09375,
-      "learning_rate": 3.012820512820513e-05,
-      "loss": 0.8149,
-      "step": 125
+      "epoch": 0.4266666666666667,
+      "grad_norm": 5.8125,
+      "learning_rate": 2.8708644610458914e-05,
+      "loss": 1.133,
+      "step": 400
     },
     {
-      "epoch": 0.48,
-      "grad_norm": 7.40625,
-      "learning_rate": 2.6121794871794876e-05,
-      "loss": 0.8612,
-      "step": 150
+      "epoch": 0.4266666666666667,
+      "eval_loss": 1.4380828142166138,
+      "eval_runtime": 128.2602,
+      "eval_samples_per_second": 44.722,
+      "eval_steps_per_second": 5.59,
+      "step": 400
     },
     {
-      "epoch": 0.56,
-      "grad_norm": 7.3125,
-      "learning_rate": 2.2115384615384616e-05,
-      "loss": 0.8275,
-      "step": 175
+      "epoch": 0.5333333333333333,
+      "grad_norm": 5.4375,
+      "learning_rate": 2.337246531483458e-05,
+      "loss": 1.1229,
+      "step": 500
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 1.4234306812286377,
+      "eval_runtime": 128.3478,
+      "eval_samples_per_second": 44.691,
+      "eval_steps_per_second": 5.586,
+      "step": 500
     },
     {
       "epoch": 0.64,
-      "grad_norm": 7.0625,
-      "learning_rate": 1.810897435897436e-05,
-      "loss": 0.8186,
-      "step": 200
+      "grad_norm": 5.71875,
+      "learning_rate": 1.8036286019210247e-05,
+      "loss": 1.1073,
+      "step": 600
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.4192696809768677,
+      "eval_runtime": 128.1918,
+      "eval_samples_per_second": 44.745,
+      "eval_steps_per_second": 5.593,
+      "step": 600
     },
     {
-      "epoch": 0.72,
-      "grad_norm": 6.96875,
-      "learning_rate": 1.4102564102564104e-05,
-      "loss": 0.8048,
-      "step": 225
+      "epoch": 0.7466666666666667,
+      "grad_norm": 6.4375,
+      "learning_rate": 1.2700106723585914e-05,
+      "loss": 1.1053,
+      "step": 700
     },
     {
-      "epoch": 0.8,
-      "grad_norm": 6.625,
-      "learning_rate": 1.0096153846153847e-05,
-      "loss": 0.8237,
-      "step": 250
+      "epoch": 0.7466666666666667,
+      "eval_loss": 1.4158320426940918,
+      "eval_runtime": 128.2181,
+      "eval_samples_per_second": 44.736,
+      "eval_steps_per_second": 5.592,
+      "step": 700
     },
     {
-      "epoch": 0.88,
-      "grad_norm": 7.75,
-      "learning_rate": 6.08974358974359e-06,
-      "loss": 0.8544,
-      "step": 275
+      "epoch": 0.8533333333333334,
+      "grad_norm": 6.03125,
+      "learning_rate": 7.363927427961579e-06,
+      "loss": 1.1059,
+      "step": 800
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "eval_loss": 1.4143309593200684,
+      "eval_runtime": 128.2757,
+      "eval_samples_per_second": 44.716,
+      "eval_steps_per_second": 5.59,
+      "step": 800
     },
     {
       "epoch": 0.96,
-      "grad_norm": 7.15625,
-      "learning_rate": 2.0833333333333334e-06,
-      "loss": 0.8185,
-      "step": 300
+      "grad_norm": 5.75,
+      "learning_rate": 2.0277481323372464e-06,
+      "loss": 1.1033,
+      "step": 900
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 1.413725733757019,
+      "eval_runtime": 128.2264,
+      "eval_samples_per_second": 44.733,
+      "eval_steps_per_second": 5.592,
+      "step": 900
     }
   ],
-  "logging_steps": 25,
-  "max_steps": 312,
+  "logging_steps": 100,
+  "max_steps": 937,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -111,7 +162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3377377597980672.0,
+  "total_flos": 2.0285915444281344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc44085ea5aec9b20c61210d797707f5d128a458b13bba0602952888ce6f88d
+oid sha256:9e22a09f7d57eefb94c0225ca0ecccdde6d19aff2eb73e7914dd16e4c7c4bc5f
 size 5304