Model save

README.md

@@ -1,19 +1,14 @@
 ---
-base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: HuggingFaceH4/Bespoke-Stratos-17k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill
 tags:
 - generated_from_trainer
-- open-r1
-- trl
-- sft
 licence: license
 ---
 
 # Model Card for Qwen2.5-1.5B-Open-R1-Distill
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
+This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,7 +24,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/2741919970-hustvl/huggingface/runs/8v0s3ur8) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/2741919970-hustvl/huggingface/runs/kmc58nu5) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,13 +1,8 @@
 {
-    "eval_loss": 0.7947947978973389,
-    "eval_runtime": 27.9803,
-    "eval_samples": 100,
-    "eval_samples_per_second": 9.185,
-    "eval_steps_per_second": 1.179,
-    "total_flos": 76959556042752.0,
-    "train_loss": 0.8068137678457665,
-    "train_runtime": 18078.9101,
+    "total_flos": 0.0,
+    "train_loss": 0.984842965855427,
+    "train_runtime": 39952.7795,
     "train_samples": 16610,
-    "train_samples_per_second": 2.392,
-    "train_steps_per_second": 0.075
+    "train_samples_per_second": 3.298,
+    "train_steps_per_second": 0.103
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02c925bf03bb323f85ea2ca3bbbcc6277a912ae0dd38ad8ed4a857b8d2a6d51
+size 2687651730

special_tokens_map.json

@@ -1,25 +1,24 @@
 {
-  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|im_end|>"
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:d4c0d99d84af59e9126913fafe5210822963e9a3065ee43e6833b358b0c2f825
+size 3564303

tokenizer_config.json

@@ -1,8 +1,9 @@
 {
   "add_bos_token": false,
+  "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "151643": {
+    "0": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
@@ -10,199 +11,206 @@
       "single_word": false,
       "special": true
     },
-    "151644": {
-      "content": "<|im_start|>",
+    "1": {
+      "content": "<|padding|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "151645": {
-      "content": "<|im_end|>",
+    "50254": {
+      "content": "                        ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151646": {
-      "content": "<|object_ref_start|>",
+    "50255": {
+      "content": "                       ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151647": {
-      "content": "<|object_ref_end|>",
+    "50256": {
+      "content": "                      ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151648": {
-      "content": "<|box_start|>",
+    "50257": {
+      "content": "                     ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151649": {
-      "content": "<|box_end|>",
+    "50258": {
+      "content": "                    ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151650": {
-      "content": "<|quad_start|>",
+    "50259": {
+      "content": "                   ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151651": {
-      "content": "<|quad_end|>",
+    "50260": {
+      "content": "                  ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151652": {
-      "content": "<|vision_start|>",
+    "50261": {
+      "content": "                 ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151653": {
-      "content": "<|vision_end|>",
+    "50262": {
+      "content": "                ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151654": {
-      "content": "<|vision_pad|>",
+    "50263": {
+      "content": "               ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151655": {
-      "content": "<|image_pad|>",
+    "50264": {
+      "content": "              ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151656": {
-      "content": "<|video_pad|>",
+    "50265": {
+      "content": "             ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "151657": {
-      "content": "<tool_call>",
+    "50266": {
+      "content": "            ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "151658": {
-      "content": "</tool_call>",
+    "50267": {
+      "content": "           ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "151659": {
-      "content": "<|fim_prefix|>",
+    "50268": {
+      "content": "          ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "151660": {
-      "content": "<|fim_middle|>",
+    "50269": {
+      "content": "         ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "151661": {
-      "content": "<|fim_suffix|>",
+    "50270": {
+      "content": "        ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "151662": {
-      "content": "<|fim_pad|>",
+    "50271": {
+      "content": "       ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "151663": {
-      "content": "<|repo_name|>",
+    "50272": {
+      "content": "      ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "151664": {
-      "content": "<|file_sep|>",
+    "50273": {
+      "content": "     ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
       "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    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\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    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) 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{%- endif %}\n",
+  "bos_token": "<|endoftext|>",
+  "chat_template": "\n{%- if tools %}\n    <|im_start|>system\n    {%- if messages[0]['role'] == 'system' %}\n        {{ messages[0]['content'] }}\n    {%- else %}\n        You are Mamba. You are a helpful assistant.\n    {%- endif %}\n    <|im_end|>\n    <|im_start|>system\n    # Tools\n    \n    You may call one or more functions to assist with the user query.\n    You are provided with function signatures within <tools></tools> XML tags:\n    <tools>\n    {%- for tool in tools %}\n        {{ tool | tojson }}\n    {%- endfor %}\n    </tools>\n    \n    For 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>\n    <|im_end|>\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        <|im_start|>system\n        {{ messages[0]['content'] }}\n        <|im_end|>\n    {%- else %}\n        <|im_start|>system\n        You are Mamba. You are a helpful assistant.\n        <|im_end|>\n    {%- endif %}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        <|im_start|>{{ message.role }}\n        {{ message.content }}\n        <|im_end|>\n    {%- elif message.role == \"assistant\" %}\n        <|im_start|>assistant\n        {%- if message.content %}\n            {{ message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            <tool_call>\n            {\"name\": \"{{ tool_call.name }}\", \"arguments\": {{ tool_call.arguments | tojson }}}\n            </tool_call>\n        {%- endfor %}\n        <|im_end|>\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.index0 == 0 or messages[loop.index0 - 1].role != \"tool\" %}\n            <|im_start|>user\n        {%- endif %}\n        <tool_response>\n        {{ message.content }}\n        </tool_response>\n        {%- if loop.last or messages[loop.index0 + 1].role != \"tool\" %}\n            <|im_end|>\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n    <|im_start|>assistant\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
+  "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
-  "model_max_length": 131072,
-  "pad_token": "<|im_end|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 76959556042752.0,
-    "train_loss": 0.8068137678457665,
-    "train_runtime": 18078.9101,
+    "total_flos": 0.0,
+    "train_loss": 0.984842965855427,
+    "train_runtime": 39952.7795,
     "train_samples": 16610,
-    "train_samples_per_second": 2.392,
-    "train_steps_per_second": 0.075
+    "train_samples_per_second": 3.298,
+    "train_steps_per_second": 0.103
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d60e2086dd88927d46a3ffa1d5ec1ab404d991d69e1288db51a9e380ef723a6
-size 8632
+oid sha256:0e9f85f84709485ec288fc5261a93449e11063558dfd5d1855dd1fb849067490
+size 8376