Model save

.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

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: transformers
+model_name: Qwen2.5-1.5B-Open-R1-Distill
+tags:
+- generated_from_trainer
+- 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).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="howey/Qwen2.5-1.5B-Open-R1-Distill", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+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/hhy-tue/huggingface/runs/1od5dss7) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.14.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 6.966137809639834e+17,
+    "train_loss": 0.8737344685390857,
+    "train_runtime": 458.8599,
+    "train_samples": 16610,
+    "train_samples_per_second": 47.095,
+    "train_steps_per_second": 0.368
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b47b3d8fe71955dce6e32b963334645ad576b8c60b112c9cb3e0f4d8b7e7322
+size 3087467144

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 6.966137809639834e+17,
+    "train_loss": 0.8737344685390857,
+    "train_runtime": 458.8599,
+    "train_samples": 16610,
+    "train_samples_per_second": 47.095,
+    "train_steps_per_second": 0.368
+}

trainer_state.json

@@ -0,0 +1,281 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 169,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.029585798816568046,
+      "grad_norm": 716.0,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 1.1003,
+      "step": 5
+    },
+    {
+      "epoch": 0.05917159763313609,
+      "grad_norm": 564.0,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 1.0845,
+      "step": 10
+    },
+    {
+      "epoch": 0.08875739644970414,
+      "grad_norm": 484.0,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 1.0317,
+      "step": 15
+    },
+    {
+      "epoch": 0.11834319526627218,
+      "grad_norm": 408.0,
+      "learning_rate": 1.9980782984658682e-05,
+      "loss": 0.9659,
+      "step": 20
+    },
+    {
+      "epoch": 0.14792899408284024,
+      "grad_norm": 336.0,
+      "learning_rate": 1.9863613034027224e-05,
+      "loss": 0.9174,
+      "step": 25
+    },
+    {
+      "epoch": 0.17751479289940827,
+      "grad_norm": 332.0,
+      "learning_rate": 1.9641197940012136e-05,
+      "loss": 0.8886,
+      "step": 30
+    },
+    {
+      "epoch": 0.20710059171597633,
+      "grad_norm": 326.0,
+      "learning_rate": 1.9315910880512792e-05,
+      "loss": 0.8835,
+      "step": 35
+    },
+    {
+      "epoch": 0.23668639053254437,
+      "grad_norm": 320.0,
+      "learning_rate": 1.8891222681391853e-05,
+      "loss": 0.8857,
+      "step": 40
+    },
+    {
+      "epoch": 0.26627218934911245,
+      "grad_norm": 302.0,
+      "learning_rate": 1.8371664782625287e-05,
+      "loss": 0.8715,
+      "step": 45
+    },
+    {
+      "epoch": 0.2958579881656805,
+      "grad_norm": 310.0,
+      "learning_rate": 1.7762780887657576e-05,
+      "loss": 0.8628,
+      "step": 50
+    },
+    {
+      "epoch": 0.3254437869822485,
+      "grad_norm": 320.0,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.8537,
+      "step": 55
+    },
+    {
+      "epoch": 0.35502958579881655,
+      "grad_norm": 320.0,
+      "learning_rate": 1.6303906161279554e-05,
+      "loss": 0.8655,
+      "step": 60
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 314.0,
+      "learning_rate": 1.5469481581224274e-05,
+      "loss": 0.8395,
+      "step": 65
+    },
+    {
+      "epoch": 0.41420118343195267,
+      "grad_norm": 298.0,
+      "learning_rate": 1.4576697415156818e-05,
+      "loss": 0.8424,
+      "step": 70
+    },
+    {
+      "epoch": 0.4437869822485207,
+      "grad_norm": 302.0,
+      "learning_rate": 1.3635079705638298e-05,
+      "loss": 0.8554,
+      "step": 75
+    },
+    {
+      "epoch": 0.47337278106508873,
+      "grad_norm": 314.0,
+      "learning_rate": 1.2654675551080724e-05,
+      "loss": 0.8377,
+      "step": 80
+    },
+    {
+      "epoch": 0.5029585798816568,
+      "grad_norm": 306.0,
+      "learning_rate": 1.164594590280734e-05,
+      "loss": 0.8422,
+      "step": 85
+    },
+    {
+      "epoch": 0.5325443786982249,
+      "grad_norm": 302.0,
+      "learning_rate": 1.0619653946285948e-05,
+      "loss": 0.8428,
+      "step": 90
+    },
+    {
+      "epoch": 0.5621301775147929,
+      "grad_norm": 326.0,
+      "learning_rate": 9.586750257511868e-06,
+      "loss": 0.8517,
+      "step": 95
+    },
+    {
+      "epoch": 0.591715976331361,
+      "grad_norm": 304.0,
+      "learning_rate": 8.558255959926533e-06,
+      "loss": 0.8264,
+      "step": 100
+    },
+    {
+      "epoch": 0.591715976331361,
+      "eval_loss": 0.863949179649353,
+      "eval_runtime": 0.7733,
+      "eval_samples_per_second": 165.529,
+      "eval_steps_per_second": 5.173,
+      "step": 100
+    },
+    {
+      "epoch": 0.621301775147929,
+      "grad_norm": 306.0,
+      "learning_rate": 7.545145128592009e-06,
+      "loss": 0.8314,
+      "step": 105
+    },
+    {
+      "epoch": 0.650887573964497,
+      "grad_norm": 310.0,
+      "learning_rate": 6.558227696373617e-06,
+      "loss": 0.8447,
+      "step": 110
+    },
+    {
+      "epoch": 0.6804733727810651,
+      "grad_norm": 304.0,
+      "learning_rate": 5.608034111526298e-06,
+      "loss": 0.841,
+      "step": 115
+    },
+    {
+      "epoch": 0.7100591715976331,
+      "grad_norm": 306.0,
+      "learning_rate": 4.704702977392914e-06,
+      "loss": 0.8296,
+      "step": 120
+    },
+    {
+      "epoch": 0.7396449704142012,
+      "grad_norm": 316.0,
+      "learning_rate": 3.857872873103322e-06,
+      "loss": 0.8332,
+      "step": 125
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 310.0,
+      "learning_rate": 3.0765795095517026e-06,
+      "loss": 0.8342,
+      "step": 130
+    },
+    {
+      "epoch": 0.7988165680473372,
+      "grad_norm": 326.0,
+      "learning_rate": 2.369159318001937e-06,
+      "loss": 0.8397,
+      "step": 135
+    },
+    {
+      "epoch": 0.8284023668639053,
+      "grad_norm": 312.0,
+      "learning_rate": 1.743160500034443e-06,
+      "loss": 0.8296,
+      "step": 140
+    },
+    {
+      "epoch": 0.8579881656804734,
+      "grad_norm": 312.0,
+      "learning_rate": 1.2052624879351105e-06,
+      "loss": 0.8377,
+      "step": 145
+    },
+    {
+      "epoch": 0.8875739644970414,
+      "grad_norm": 302.0,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.8471,
+      "step": 150
+    },
+    {
+      "epoch": 0.9171597633136095,
+      "grad_norm": 320.0,
+      "learning_rate": 4.1572517541747294e-07,
+      "loss": 0.8428,
+      "step": 155
+    },
+    {
+      "epoch": 0.9467455621301775,
+      "grad_norm": 302.0,
+      "learning_rate": 1.7251026952640583e-07,
+      "loss": 0.8416,
+      "step": 160
+    },
+    {
+      "epoch": 0.9763313609467456,
+      "grad_norm": 290.0,
+      "learning_rate": 3.4155069933301535e-08,
+      "loss": 0.8245,
+      "step": 165
+    },
+    {
+      "epoch": 1.0,
+      "step": 169,
+      "total_flos": 6.966137809639834e+17,
+      "train_loss": 0.8737344685390857,
+      "train_runtime": 458.8599,
+      "train_samples_per_second": 47.095,
+      "train_steps_per_second": 0.368
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 169,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.966137809639834e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b7be9ec9c06f7731fa941f5ee3877849a8e411cd2ad4a7027d2bb15d29e3d4b
+size 6008