Model save

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: Qwen/Qwen2.5-Math-7B
+base_model: Qwen/Qwen2.5-7B-Instruct
 library_name: transformers
 model_name: Qwen2.5-7B-Open-R1-Distill-mixed
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-7B-Open-R1-Distill-mixed
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B).
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -27,7 +27,7 @@ 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/jjh233/huggingface/runs/4ee21rto) 
+[<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/jjh233/huggingface/runs/qx8bei0j) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 9.05303086676834,
-    "train_runtime": 99277.474,
+    "train_loss": 1.4448112659087413,
+    "train_runtime": 91860.5158,
     "train_samples": 16610,
-    "train_samples_per_second": 0.218,
-    "train_steps_per_second": 0.027
+    "train_samples_per_second": 0.235,
+    "train_steps_per_second": 0.029
 }

config.json

@@ -1,16 +1,16 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-Math-7B",
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
+  "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 3584,
   "initializer_range": 0.02,
   "intermediate_size": 18944,
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 32768,
   "max_window_layers": 28,
   "model_type": "qwen2",
   "num_attention_heads": 28,
@@ -18,13 +18,12 @@
   "num_key_value_heads": 4,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000,
-  "sliding_window": 4096,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0.dev0",
   "use_cache": false,
-  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

generation_config.json

@@ -1,6 +1,14 @@
 {
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
   "transformers_version": "4.49.0.dev0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2177467f63bc5aaf9de4c301ab72af7adc904148d9b4cdf899d3504f907c3f6
+oid sha256:92aed972beb5efc162e81cc18cdc5b53fcb17ef4008e0413598dd0c72f6065d2
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07daa14da790d0628aeeac16c6e30c981612031c50e40d9bb0059723ef5cdce7
+oid sha256:3ed30defca2c386ff61e8ba0ad1dd3ab3b94de98d62978721f07fab5888b6c9f
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21c9b61a1843f674c3ec29013f216f2f33be3bc35548f1ad6527f3becea389b3
+oid sha256:890e40b6ecfcf0b27cc96e67434473231bf9d6ef8c08a4ee40bfe963e27abb0d
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a42786061c92654b2876018ac9898c04f5cd4fc8254b88f5dcd90a396268cc1
+oid sha256:cd4d107cb11585b17c4f3c92913dabf9e81ede449f5246e183ada044ed181fd2
 size 1089994880

results/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/results_2025-02-10T16-08-09.207705.json

@@ -0,0 +1,98 @@
+{
+  "config_general": {
+    "lighteval_sha": "?",
+    "num_fewshot_seeds": 1,
+    "override_batch_size": -1,
+    "max_samples": null,
+    "job_id": 0,
+    "start_time": 627433.20374781,
+    "end_time": 627650.868866556,
+    "total_evaluation_time_secondes": "217.66511874599382",
+    "model_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+    "model_sha": "",
+    "model_dtype": null,
+    "model_size": null
+  },
+  "results": {
+    "custom|aime24|1": {
+      "extractive_match": 0.2,
+      "extractive_match_stderr": 0.07427813527082075
+    },
+    "all": {
+      "extractive_match": 0.2,
+      "extractive_match_stderr": 0.07427813527082075
+    }
+  },
+  "versions": {
+    "custom|aime24|1": 1
+  },
+  "config_tasks": {
+    "custom|aime24": {
+      "name": "aime24",
+      "prompt_function": "aime_prompt_fn",
+      "hf_repo": "HuggingFaceH4/aime_2024",
+      "hf_subset": "default",
+      "metric": [
+        {
+          "metric_name": "extractive_match",
+          "higher_is_better": true,
+          "category": "3",
+          "use_case": "1",
+          "sample_level_fn": "sample_level_fn",
+          "corpus_level_fn": "mean"
+        }
+      ],
+      "hf_revision": null,
+      "hf_filter": null,
+      "hf_avail_splits": [
+        "train"
+      ],
+      "trust_dataset": false,
+      "evaluation_splits": [
+        "train"
+      ],
+      "few_shots_split": null,
+      "few_shots_select": null,
+      "generation_size": 32768,
+      "generation_grammar": null,
+      "stop_sequence": [],
+      "num_samples": null,
+      "suite": [
+        "custom"
+      ],
+      "original_num_docs": 30,
+      "effective_num_docs": 30,
+      "must_remove_duplicate_docs": false,
+      "version": 1
+    }
+  },
+  "summary_tasks": {
+    "custom|aime24|1": {
+      "hashes": {
+        "hash_examples": "18ca0099f8d8f826",
+        "hash_full_prompts": "558d24d97c0a0742",
+        "hash_input_tokens": "4637fbc1de5f6656",
+        "hash_cont_tokens": "78ccf84b49581fa6"
+      },
+      "truncated": 0,
+      "non_truncated": 30,
+      "padded": 0,
+      "non_padded": 30,
+      "effective_few_shots": -1.0,
+      "num_truncated_few_shots": 30
+    }
+  },
+  "summary_general": {
+    "hashes": {
+      "hash_examples": "c4769936f28d3d77",
+      "hash_full_prompts": "a1a733ebec6ebc6d",
+      "hash_input_tokens": "a8ff12512b74af64",
+      "hash_cont_tokens": "fd258a745d12f011"
+    },
+    "truncated": 0,
+    "non_truncated": 30,
+    "padded": 0,
+    "non_padded": 30,
+    "num_truncated_few_shots": 30
+  }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -195,13 +195,13 @@
     "<|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        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\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\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|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",
+  "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",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|im_end|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 9.05303086676834,
-    "train_runtime": 99277.474,
+    "train_loss": 1.4448112659087413,
+    "train_runtime": 91860.5158,
     "train_samples": 16610,
-    "train_samples_per_second": 0.218,
-    "train_steps_per_second": 0.027
+    "train_samples_per_second": 0.235,
+    "train_steps_per_second": 0.029
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f311f0d076b6ff826d0428e10fb588767bf2c8f02c04ed19ff6db52a7decaa6
-size 6008
+oid sha256:2c61a9db7fca493e3e063521152d4de1a0e5c8a089eb36a2528d0b0d1d0294e9
+size 5944