From 0aa83b89c8a4109bbd37805715fc755169bf294c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 16 Jun 2026 04:58:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: harsha070/expfinal-qwen-mbpp-s42-lambda-0p0 Source: Original Platform --- .gitattributes | 36 ++ README.md | 67 ++++ chat_template.jinja | 54 +++ completions/completions_00010.parquet | 3 + completions/completions_00020.parquet | 3 + completions/completions_00030.parquet | 3 + completions/completions_00040.parquet | 3 + completions/completions_00050.parquet | 3 + completions/completions_00060.parquet | 3 + completions/completions_00070.parquet | 3 + completions/completions_00080.parquet | 3 + completions/completions_00090.parquet | 3 + completions/completions_00100.parquet | 3 + completions/completions_00110.parquet | 3 + completions/completions_00120.parquet | 3 + completions/completions_00130.parquet | 3 + completions/completions_00140.parquet | 3 + completions/completions_00150.parquet | 3 + completions/completions_00160.parquet | 3 + config.json | 69 ++++ generation_config.json | 13 + last-checkpoint/chat_template.jinja | 54 +++ last-checkpoint/config.json | 69 ++++ last-checkpoint/generation_config.json | 13 + last-checkpoint/model.safetensors | 3 + last-checkpoint/tokenizer.json | 3 + last-checkpoint/tokenizer_config.json | 30 ++ last-checkpoint/trainer_state.json | 482 +++++++++++++++++++++++++ last-checkpoint/training_args.bin | 3 + model.safetensors | 3 + tokenizer.json | 3 + tokenizer_config.json | 30 ++ training_args.bin | 3 + 33 files changed, 983 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 completions/completions_00010.parquet create mode 100644 completions/completions_00020.parquet create mode 100644 completions/completions_00030.parquet create mode 100644 completions/completions_00040.parquet create mode 100644 completions/completions_00050.parquet create mode 100644 completions/completions_00060.parquet create mode 100644 completions/completions_00070.parquet create mode 100644 completions/completions_00080.parquet create mode 100644 completions/completions_00090.parquet create mode 100644 completions/completions_00100.parquet create mode 100644 completions/completions_00110.parquet create mode 100644 completions/completions_00120.parquet create mode 100644 completions/completions_00130.parquet create mode 100644 completions/completions_00140.parquet create mode 100644 completions/completions_00150.parquet create mode 100644 completions/completions_00160.parquet create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 last-checkpoint/chat_template.jinja create mode 100644 last-checkpoint/config.json create mode 100644 last-checkpoint/generation_config.json create mode 100644 last-checkpoint/model.safetensors create mode 100644 last-checkpoint/tokenizer.json create mode 100644 last-checkpoint/tokenizer_config.json create mode 100644 last-checkpoint/trainer_state.json create mode 100644 last-checkpoint/training_args.bin create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 training_args.bin diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fa998c5 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: harsha070/sft-warmup-qwen-v1 +library_name: transformers +model_name: expfinal-qwen-mbpp-s42-lambda-0p0 +tags: +- generated_from_trainer +- grpo +- trl +licence: license +--- + +# Model Card for expfinal-qwen-mbpp-s42-lambda-0p0 + +This model is a fine-tuned version of [harsha070/sft-warmup-qwen-v1](https://huggingface.co/harsha070/sft-warmup-qwen-v1). +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="harsha070/expfinal-qwen-mbpp-s42-lambda-0p0", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + +[Visualize in Weights & Biases](https://wandb.ai/models-self5933/obfuscation-early-warning/runs/v5edfncc) + + + +This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). + +### Framework versions + +- TRL: 1.3.0 +- Transformers: 5.7.0 +- Pytorch: 2.11.0 +- Datasets: 4.8.5 +- Tokenizers: 0.22.2 + +## Citations + +Cite GRPO as: + +```bibtex +@article{shao2024deepseekmath, + title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, + author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, + year = 2024, + eprint = {arXiv:2402.03300}, +} +``` + +Cite TRL as: + +```bibtex +@software{vonwerra2020trl, + title = {{TRL: Transformers Reinforcement Learning}}, + author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin}, + license = {Apache-2.0}, + url = {https://github.com/huggingface/trl}, + year = {2020} +} +``` \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\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 XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/completions/completions_00010.parquet b/completions/completions_00010.parquet new file mode 100644 index 0000000..cc9c1ac --- /dev/null +++ b/completions/completions_00010.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbc76d485fd0640b155715f10c54e062c47e16d028a433c04dcab1da16bef16b +size 19054 diff --git a/completions/completions_00020.parquet b/completions/completions_00020.parquet new file mode 100644 index 0000000..e6f0961 --- /dev/null +++ b/completions/completions_00020.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7595b59c0e45512a666b702a95ac8817a447d4041a09793d8c4a968ddbf17fd9 +size 19060 diff --git a/completions/completions_00030.parquet b/completions/completions_00030.parquet new file mode 100644 index 0000000..bc62fbb --- /dev/null +++ b/completions/completions_00030.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de91d43dfdd8408746d32186d55a13f4d9b0310d946f32651ddbd7cf253b4fb7 +size 18232 diff --git a/completions/completions_00040.parquet b/completions/completions_00040.parquet new file mode 100644 index 0000000..380e84d --- /dev/null +++ b/completions/completions_00040.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826bb48be565c377bb64de1e0688b0b4c71721ab76688f819cb2c95a50e63863 +size 19256 diff --git a/completions/completions_00050.parquet b/completions/completions_00050.parquet new file mode 100644 index 0000000..45c5620 --- /dev/null +++ b/completions/completions_00050.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827ad260db9247a389559e67e4016abda1c4ed4931a325e5237d10229587eaa0 +size 18962 diff --git a/completions/completions_00060.parquet b/completions/completions_00060.parquet new file mode 100644 index 0000000..b6d3d3d --- /dev/null +++ b/completions/completions_00060.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:511f7d9b092ac8f8cfb8cc4f4046fa95673c629f4e04922c37d64d5ed453ee8d +size 16945 diff --git a/completions/completions_00070.parquet b/completions/completions_00070.parquet new file mode 100644 index 0000000..9fb9fc3 --- /dev/null +++ b/completions/completions_00070.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf7818fb11ac62e82f38e6a646b81649a724cf6660b7a9a5617636ea766087d +size 17896 diff --git a/completions/completions_00080.parquet b/completions/completions_00080.parquet new file mode 100644 index 0000000..5695477 --- /dev/null +++ b/completions/completions_00080.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e13180d57fe71677d97394b97359f6f91662d2569509975ddd369f603510ffee +size 17608 diff --git a/completions/completions_00090.parquet b/completions/completions_00090.parquet new file mode 100644 index 0000000..b25466a --- /dev/null +++ b/completions/completions_00090.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc1d870b788698195912cbaaad5171c08e1525806a6a22b4c55b62c82f6d013b +size 16040 diff --git a/completions/completions_00100.parquet b/completions/completions_00100.parquet new file mode 100644 index 0000000..6018c72 --- /dev/null +++ b/completions/completions_00100.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5626a4822ba10a732b1e426d01e4f629a29d14c56df1a26cc5cc137a1431289 +size 18379 diff --git a/completions/completions_00110.parquet b/completions/completions_00110.parquet new file mode 100644 index 0000000..1993fe2 --- /dev/null +++ b/completions/completions_00110.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c46a71e799942190ec77c11e673e6fa80413246f6e99cd132f59cc514bec2547 +size 18650 diff --git a/completions/completions_00120.parquet b/completions/completions_00120.parquet new file mode 100644 index 0000000..fe1fe0b --- /dev/null +++ b/completions/completions_00120.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0edb1defb212f3dee8ef9af9bea31ca469271013ad1adb0682ad0854b06c37c1 +size 17250 diff --git a/completions/completions_00130.parquet b/completions/completions_00130.parquet new file mode 100644 index 0000000..3ab8024 --- /dev/null +++ b/completions/completions_00130.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a8c82b842058697f48442f22899cbb19c2065e2b9790985a3b94099f197e1d +size 16983 diff --git a/completions/completions_00140.parquet b/completions/completions_00140.parquet new file mode 100644 index 0000000..bd81e75 --- /dev/null +++ b/completions/completions_00140.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c340c4dc7c4a16bee1b744271934fa158d9c26e5d9ce4c708bf7b2cb6d5015bd +size 16791 diff --git a/completions/completions_00150.parquet b/completions/completions_00150.parquet new file mode 100644 index 0000000..b1f4e71 --- /dev/null +++ b/completions/completions_00150.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b2b305023df8ba192ff0d9ef22e7ab42504202a26efd150a9192d837adf1ee +size 16827 diff --git a/completions/completions_00160.parquet b/completions/completions_00160.parquet new file mode 100644 index 0000000..40db249 --- /dev/null +++ b/completions/completions_00160.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:804fa87a96311fb60fc71585b0f16003713e44ee47ec8e0214cabeedc771900d +size 17839 diff --git a/config.json b/config.json new file mode 100644 index 0000000..64c100d --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 70, + "model_type": "qwen2", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..aaf8639 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "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": "5.7.0" +} diff --git a/last-checkpoint/chat_template.jinja b/last-checkpoint/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/last-checkpoint/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\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 XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/last-checkpoint/config.json b/last-checkpoint/config.json new file mode 100644 index 0000000..64c100d --- /dev/null +++ b/last-checkpoint/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 70, + "model_type": "qwen2", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/last-checkpoint/generation_config.json b/last-checkpoint/generation_config.json new file mode 100644 index 0000000..aaf8639 --- /dev/null +++ b/last-checkpoint/generation_config.json @@ -0,0 +1,13 @@ +{ + "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": "5.7.0" +} diff --git a/last-checkpoint/model.safetensors b/last-checkpoint/model.safetensors new file mode 100644 index 0000000..0a4c06a --- /dev/null +++ b/last-checkpoint/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94887323c99ef1d5a14a3a3bad2299ac61ee1ac32fc8cb5f292ff4ca3cd9210d +size 6171927112 diff --git a/last-checkpoint/tokenizer.json b/last-checkpoint/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/last-checkpoint/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/last-checkpoint/tokenizer_config.json b/last-checkpoint/tokenizer_config.json new file mode 100644 index 0000000..770e41d --- /dev/null +++ b/last-checkpoint/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/last-checkpoint/trainer_state.json b/last-checkpoint/trainer_state.json new file mode 100644 index 0000000..0f2e554 --- /dev/null +++ b/last-checkpoint/trainer_state.json @@ -0,0 +1,482 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0666666666666667, + "eval_steps": 500, + "global_step": 160, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.7375, + "completions/max_length": 512.0, + "completions/max_terminated_length": 424.3, + "completions/mean_length": 490.4875, + "completions/mean_terminated_length": 405.65333557128906, + "completions/min_length": 428.2, + "completions/min_terminated_length": 377.0, + "entropy": 0.25217165537178515, + "epoch": 0.06666666666666667, + "frac_reward_zero_std": 0.4, + "grad_norm": 1.5703125, + "kl": 0.0473901923673111, + "learning_rate": 9.4375e-06, + "loss": -0.0006930597126483917, + "num_tokens": 52107.0, + "reward": 0.675, + "reward_std": 0.399344927072525, + "rewards/JointRewardFunction/mean": 0.675, + "rewards/JointRewardFunction/std": 0.39934495091438293, + "step": 10, + "step_time": 22.542225440999847 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.8625, + "completions/max_length": 512.0, + "completions/max_terminated_length": 284.7, + "completions/mean_length": 504.1875, + "completions/mean_terminated_length": 272.675, + "completions/min_length": 467.3, + "completions/min_terminated_length": 262.5, + "entropy": 0.202899154368788, + "epoch": 0.13333333333333333, + "frac_reward_zero_std": 0.55, + "grad_norm": 1.546875, + "kl": 0.09602957724127918, + "learning_rate": 8.8125e-06, + "loss": -1.602950505912304e-05, + "num_tokens": 106202.0, + "reward": 0.7, + "reward_std": 0.3110164314508438, + "rewards/JointRewardFunction/mean": 0.7, + "rewards/JointRewardFunction/std": 0.3110164374113083, + "step": 20, + "step_time": 23.115930349700285 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.8625, + "completions/max_length": 512.0, + "completions/max_terminated_length": 228.9, + "completions/mean_length": 495.1875, + "completions/mean_terminated_length": 212.45, + "completions/min_length": 461.5, + "completions/min_terminated_length": 205.5, + "entropy": 0.21361660687252879, + "epoch": 0.2, + "frac_reward_zero_std": 0.65, + "grad_norm": 1.6640625, + "kl": 0.09101211386732758, + "learning_rate": 8.1875e-06, + "loss": 0.0017554668709635734, + "num_tokens": 157233.0, + "reward": 0.8625, + "reward_std": 0.2857582807540894, + "rewards/JointRewardFunction/mean": 0.8625, + "rewards/JointRewardFunction/std": 0.28575828671455383, + "step": 30, + "step_time": 22.91968024349999 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.9375, + "completions/max_length": 512.0, + "completions/max_terminated_length": 141.1, + "completions/mean_length": 506.8625, + "completions/mean_terminated_length": 132.6, + "completions/min_length": 482.5, + "completions/min_terminated_length": 124.1, + "entropy": 0.1852631143294275, + "epoch": 0.26666666666666666, + "frac_reward_zero_std": 0.55, + "grad_norm": 1.90625, + "kl": 0.08399276400450617, + "learning_rate": 7.5625e-06, + "loss": 0.000752098485827446, + "num_tokens": 211094.0, + "reward": 0.7875, + "reward_std": 0.35561010539531707, + "rewards/JointRewardFunction/mean": 0.7875, + "rewards/JointRewardFunction/std": 0.35561011731624603, + "step": 40, + "step_time": 23.1765345180007 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.7375, + "completions/max_length": 512.0, + "completions/max_terminated_length": 379.3, + "completions/mean_length": 490.375, + "completions/mean_terminated_length": 355.89500122070314, + "completions/min_length": 437.5, + "completions/min_terminated_length": 335.1, + "entropy": 0.20920381098985671, + "epoch": 0.3333333333333333, + "frac_reward_zero_std": 0.65, + "grad_norm": 1.671875, + "kl": 0.08546415464952588, + "learning_rate": 6.9375e-06, + "loss": 0.002159162983298302, + "num_tokens": 263040.0, + "reward": 0.8625, + "reward_std": 0.2857582807540894, + "rewards/JointRewardFunction/mean": 0.8625, + "rewards/JointRewardFunction/std": 0.28575828671455383, + "step": 50, + "step_time": 23.374498161900373 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.525, + "completions/max_length": 512.0, + "completions/max_terminated_length": 472.5, + "completions/mean_length": 468.2875, + "completions/mean_terminated_length": 420.48833923339845, + "completions/min_length": 354.2, + "completions/min_terminated_length": 354.2, + "entropy": 0.2077056860551238, + "epoch": 0.4, + "frac_reward_zero_std": 0.75, + "grad_norm": 1.4609375, + "kl": 0.09320587411057205, + "learning_rate": 6.3125e-06, + "loss": -0.0018056023865938187, + "num_tokens": 313903.0, + "reward": 0.8625, + "reward_std": 0.21504760384559632, + "rewards/JointRewardFunction/mean": 0.8625, + "rewards/JointRewardFunction/std": 0.2150476098060608, + "step": 60, + "step_time": 23.37301885729976 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.6625, + "completions/max_length": 512.0, + "completions/max_terminated_length": 405.9, + "completions/mean_length": 482.5875, + "completions/mean_terminated_length": 375.9566711425781, + "completions/min_length": 381.3, + "completions/min_terminated_length": 330.1, + "entropy": 0.2098280948586762, + "epoch": 0.4666666666666667, + "frac_reward_zero_std": 0.5, + "grad_norm": 1.2734375, + "kl": 0.07904624061193317, + "learning_rate": 5.6875e-06, + "loss": 0.002197714149951935, + "num_tokens": 366306.0, + "reward": 0.7875, + "reward_std": 0.35561010539531707, + "rewards/JointRewardFunction/mean": 0.7875, + "rewards/JointRewardFunction/std": 0.35561011731624603, + "step": 70, + "step_time": 23.226104836099694 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.475, + "completions/max_length": 512.0, + "completions/max_terminated_length": 476.6, + "completions/mean_length": 462.95, + "completions/mean_terminated_length": 421.48095703125, + "completions/min_length": 355.3, + "completions/min_terminated_length": 355.3, + "entropy": 0.23389623733237386, + "epoch": 0.5333333333333333, + "frac_reward_zero_std": 0.55, + "grad_norm": 1.421875, + "kl": 1.7520212520845235, + "learning_rate": 5.0625e-06, + "loss": 0.014839766919612885, + "num_tokens": 417014.0, + "reward": 0.825, + "reward_std": 0.3429849535226822, + "rewards/JointRewardFunction/mean": 0.825, + "rewards/JointRewardFunction/std": 0.34298495948314667, + "step": 80, + "step_time": 23.28830157520024 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.6125, + "completions/max_length": 512.0, + "completions/max_terminated_length": 400.4, + "completions/mean_length": 469.4375, + "completions/mean_terminated_length": 354.97833557128905, + "completions/min_length": 361.2, + "completions/min_terminated_length": 310.0, + "entropy": 0.23284959373995662, + "epoch": 0.6, + "frac_reward_zero_std": 0.8, + "grad_norm": 0.00860595703125, + "kl": 0.09338290304876865, + "learning_rate": 4.4375e-06, + "loss": -0.00816301703453064, + "num_tokens": 468717.0, + "reward": 0.775, + "reward_std": 0.2112731784582138, + "rewards/JointRewardFunction/mean": 0.775, + "rewards/JointRewardFunction/std": 0.2112731844186783, + "step": 90, + "step_time": 23.190502532400387 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.7125, + "completions/max_length": 512.0, + "completions/max_terminated_length": 375.5, + "completions/mean_length": 486.9625, + "completions/mean_terminated_length": 343.10833435058595, + "completions/min_length": 421.6, + "completions/min_terminated_length": 319.2, + "entropy": 0.23229737337678671, + "epoch": 0.6666666666666666, + "frac_reward_zero_std": 0.45, + "grad_norm": 2.265625, + "kl": 0.10509764784947037, + "learning_rate": 3.8125e-06, + "loss": 0.012743420898914337, + "num_tokens": 522558.0, + "reward": 0.7, + "reward_std": 0.3737070143222809, + "rewards/JointRewardFunction/mean": 0.7, + "rewards/JointRewardFunction/std": 0.37370702624320984, + "step": 100, + "step_time": 23.302893278999363 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5625, + "completions/max_length": 512.0, + "completions/max_terminated_length": 470.8, + "completions/mean_length": 468.9, + "completions/mean_terminated_length": 418.7083374023438, + "completions/min_length": 370.4, + "completions/min_terminated_length": 370.4, + "entropy": 0.21385292476043105, + "epoch": 0.7333333333333333, + "frac_reward_zero_std": 0.8, + "grad_norm": 1.65625, + "kl": 0.10132698961533607, + "learning_rate": 3.1875e-06, + "loss": 0.004469546675682068, + "num_tokens": 573018.0, + "reward": 0.8625, + "reward_std": 0.22768060266971588, + "rewards/JointRewardFunction/mean": 0.8625, + "rewards/JointRewardFunction/std": 0.22768060266971588, + "step": 110, + "step_time": 23.21463985899991 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.475, + "completions/max_length": 512.0, + "completions/max_terminated_length": 498.2, + "completions/mean_length": 464.075, + "completions/mean_terminated_length": 425.3933380126953, + "completions/min_length": 350.8, + "completions/min_terminated_length": 350.8, + "entropy": 0.24488159762695433, + "epoch": 0.8, + "frac_reward_zero_std": 0.6, + "grad_norm": 1.1953125, + "kl": 0.11085290028713643, + "learning_rate": 2.5625e-06, + "loss": 0.007788118720054626, + "num_tokens": 622408.0, + "reward": 0.85, + "reward_std": 0.3265853762626648, + "rewards/JointRewardFunction/mean": 0.85, + "rewards/JointRewardFunction/std": 0.3265853762626648, + "step": 120, + "step_time": 23.28342122000013 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.575, + "completions/max_length": 512.0, + "completions/max_terminated_length": 386.7, + "completions/mean_length": 473.75, + "completions/mean_terminated_length": 338.4150054931641, + "completions/min_length": 396.3, + "completions/min_terminated_length": 293.9, + "entropy": 0.20693162837997078, + "epoch": 0.8666666666666667, + "frac_reward_zero_std": 0.7, + "grad_norm": 0.0274658203125, + "kl": 0.1018260810058564, + "learning_rate": 1.9375e-06, + "loss": 0.004177199304103851, + "num_tokens": 674560.0, + "reward": 0.7125, + "reward_std": 0.28489942848682404, + "rewards/JointRewardFunction/mean": 0.7125, + "rewards/JointRewardFunction/std": 0.284899440407753, + "step": 130, + "step_time": 23.369472190498527 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5625, + "completions/max_length": 512.0, + "completions/max_terminated_length": 474.9, + "completions/mean_length": 473.4625, + "completions/mean_terminated_length": 436.53857421875, + "completions/min_length": 387.5, + "completions/min_terminated_length": 387.5, + "entropy": 0.21715571610257028, + "epoch": 0.9333333333333333, + "frac_reward_zero_std": 0.75, + "grad_norm": 2.65625, + "kl": 0.09930992983281613, + "learning_rate": 1.3125000000000001e-06, + "loss": -0.003046867996454239, + "num_tokens": 725069.0, + "reward": 0.8625, + "reward_std": 0.22220884561538695, + "rewards/JointRewardFunction/mean": 0.8625, + "rewards/JointRewardFunction/std": 0.22220885157585143, + "step": 140, + "step_time": 23.435090316800597 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.525, + "completions/max_length": 512.0, + "completions/max_terminated_length": 465.8, + "completions/mean_length": 467.0125, + "completions/mean_terminated_length": 418.62000427246096, + "completions/min_length": 369.5, + "completions/min_terminated_length": 369.5, + "entropy": 0.23989124922081828, + "epoch": 1.0, + "frac_reward_zero_std": 0.75, + "grad_norm": 0.031982421875, + "kl": 0.11200284436345101, + "learning_rate": 6.875000000000001e-07, + "loss": 0.0012525198981165886, + "num_tokens": 774742.0, + "reward": 0.9125, + "reward_std": 0.16875659823417663, + "rewards/JointRewardFunction/mean": 0.9125, + "rewards/JointRewardFunction/std": 0.1687566041946411, + "step": 150, + "step_time": 23.458841795299485 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.475, + "completions/max_length": 512.0, + "completions/max_terminated_length": 451.2, + "completions/mean_length": 453.7375, + "completions/mean_terminated_length": 395.75953063964846, + "completions/min_length": 338.2, + "completions/min_terminated_length": 338.2, + "entropy": 0.24999441923573612, + "epoch": 1.0666666666666667, + "frac_reward_zero_std": 0.85, + "grad_norm": 0.0250244140625, + "kl": 0.10539310625754297, + "learning_rate": 6.250000000000001e-08, + "loss": 0.012749123573303222, + "num_tokens": 822957.0, + "reward": 0.8625, + "reward_std": 0.1759178400039673, + "rewards/JointRewardFunction/mean": 0.8625, + "rewards/JointRewardFunction/std": 0.17591784596443177, + "step": 160, + "step_time": 23.16400302819966 + } + ], + "logging_steps": 10, + "max_steps": 160, + "num_input_tokens_seen": 822957, + "num_train_epochs": 2, + "save_steps": 10, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/last-checkpoint/training_args.bin b/last-checkpoint/training_args.bin new file mode 100644 index 0000000..150503a --- /dev/null +++ b/last-checkpoint/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826637f41ec8cfa7e08ea7c1254ad24a7fe46492afd59522ca1fccd468f245a7 +size 7249 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..0a4c06a --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94887323c99ef1d5a14a3a3bad2299ac61ee1ac32fc8cb5f292ff4ca3cd9210d +size 6171927112 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..770e41d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..150503a --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826637f41ec8cfa7e08ea7c1254ad24a7fe46492afd59522ca1fccd468f245a7 +size 7249