From 9dc0196201c4faa34c170ff508fe7248287194bc Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 16 Jun 2026 08:03:16 +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-0p25 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..6ec6007 --- /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-0p25 +tags: +- generated_from_trainer +- trl +- grpo +licence: license +--- + +# Model Card for expfinal-qwen-mbpp-s42-lambda-0p25 + +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-0p25", 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/gm3e1a5v) + + + +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..bad23cc --- /dev/null +++ b/completions/completions_00010.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ec43cbcc4049469c8d8ed147d69642670532465e9b3a5bc1c718dab7a8ea51 +size 15427 diff --git a/completions/completions_00020.parquet b/completions/completions_00020.parquet new file mode 100644 index 0000000..9621869 --- /dev/null +++ b/completions/completions_00020.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbac651203da4456e98922a452894754f7141f941c573acfe2ec2ff4857a31ef +size 13084 diff --git a/completions/completions_00030.parquet b/completions/completions_00030.parquet new file mode 100644 index 0000000..5e7dbfc --- /dev/null +++ b/completions/completions_00030.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96620b9645eaccce84afb8c1cd55b692f0b750cd32e33a386242811264a90f52 +size 14756 diff --git a/completions/completions_00040.parquet b/completions/completions_00040.parquet new file mode 100644 index 0000000..d286d5d --- /dev/null +++ b/completions/completions_00040.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4bce7b25f0c05f01cbc235049c838513243a3f65edcafea7029a9b663a66016 +size 13719 diff --git a/completions/completions_00050.parquet b/completions/completions_00050.parquet new file mode 100644 index 0000000..3ad31f8 --- /dev/null +++ b/completions/completions_00050.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26afd72f160676f36edd857a9a29c552969933b58c0e41abea2ac456e45874e8 +size 13841 diff --git a/completions/completions_00060.parquet b/completions/completions_00060.parquet new file mode 100644 index 0000000..830849e --- /dev/null +++ b/completions/completions_00060.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae78dc9b9cd88c9acdfdc44d5f98064877f0189f9c693351f200fa24189bc565 +size 13541 diff --git a/completions/completions_00070.parquet b/completions/completions_00070.parquet new file mode 100644 index 0000000..cc3dedf --- /dev/null +++ b/completions/completions_00070.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9273bff550305db3d0a27eb6f19baae42a11e96024c6b577969ef3f37dc59241 +size 14092 diff --git a/completions/completions_00080.parquet b/completions/completions_00080.parquet new file mode 100644 index 0000000..1553e35 --- /dev/null +++ b/completions/completions_00080.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e846b2d4c85098e7f1e41fb09d660f47f541902bce73a8f619efd4f2cfccf66d +size 14668 diff --git a/completions/completions_00090.parquet b/completions/completions_00090.parquet new file mode 100644 index 0000000..38f8be6 --- /dev/null +++ b/completions/completions_00090.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac0a2276c2e46ff8a342959268a739a655605642e897ad3f889456489418a0e +size 14579 diff --git a/completions/completions_00100.parquet b/completions/completions_00100.parquet new file mode 100644 index 0000000..c93d10e --- /dev/null +++ b/completions/completions_00100.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a95d78dc9cfb50b4b303323c655fa3d32ccb009fc56852683a4dbecb38b367ee +size 13899 diff --git a/completions/completions_00110.parquet b/completions/completions_00110.parquet new file mode 100644 index 0000000..74e3e8c --- /dev/null +++ b/completions/completions_00110.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb0b22417b4f0a54330ab1955a3301c71fd7bc1c7541dac15da5124416ebf84 +size 15811 diff --git a/completions/completions_00120.parquet b/completions/completions_00120.parquet new file mode 100644 index 0000000..3b05d43 --- /dev/null +++ b/completions/completions_00120.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f63d8b15223b2955c10b74ee5badaa799bf85bcb07902d3946506e7afe4d159 +size 15727 diff --git a/completions/completions_00130.parquet b/completions/completions_00130.parquet new file mode 100644 index 0000000..e45030a --- /dev/null +++ b/completions/completions_00130.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1817d910b73c7e42a51fcdb38ac1816f98efdf1bfa2f714b9da1e0576504564 +size 12840 diff --git a/completions/completions_00140.parquet b/completions/completions_00140.parquet new file mode 100644 index 0000000..d593919 --- /dev/null +++ b/completions/completions_00140.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6832d6faa5eec6b2020d5917a02326bacdc76486c41650185c4898f41f84ed87 +size 11624 diff --git a/completions/completions_00150.parquet b/completions/completions_00150.parquet new file mode 100644 index 0000000..eaeffb6 --- /dev/null +++ b/completions/completions_00150.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d4b8fdcda57e47d0cd96d6d889287277faffc32e76a0ed33b23f61840d22003 +size 14016 diff --git a/completions/completions_00160.parquet b/completions/completions_00160.parquet new file mode 100644 index 0000000..65e61aa --- /dev/null +++ b/completions/completions_00160.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db2e72da9d9d0336cf0c1ab02a964f6e645871f012a600c852a7d10f2b8a968 +size 13955 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..9eb6dea --- /dev/null +++ b/last-checkpoint/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445184cfe8c9bc43ab65cca3d906547483b0194ed77777df583b30815b629be6 +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..b0a1509 --- /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": 0.1125, + "completions/max_length": 461.2, + "completions/max_terminated_length": 447.5, + "completions/mean_length": 376.325, + "completions/mean_terminated_length": 362.7201232910156, + "completions/min_length": 279.3, + "completions/min_terminated_length": 279.3, + "entropy": 0.2633976127021015, + "epoch": 0.06666666666666667, + "frac_reward_zero_std": 0.15, + "grad_norm": 2.515625, + "kl": 0.06368143780127866, + "learning_rate": 9.4375e-06, + "loss": 0.013505807518959046, + "num_tokens": 42974.0, + "reward": 0.83304443359375, + "reward_std": 0.4131676867604256, + "rewards/JointRewardFunction/mean": 0.83304443359375, + "rewards/JointRewardFunction/std": 0.4131676971912384, + "step": 10, + "step_time": 20.514270653799578 + }, + { + "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": 0.0625, + "completions/max_length": 409.6, + "completions/max_terminated_length": 384.0, + "completions/mean_length": 317.925, + "completions/mean_terminated_length": 308.6857147216797, + "completions/min_length": 249.7, + "completions/min_terminated_length": 249.7, + "entropy": 0.18158590691164136, + "epoch": 0.13333333333333333, + "frac_reward_zero_std": 0.25, + "grad_norm": 3.421875, + "kl": 0.1635891743004322, + "learning_rate": 8.8125e-06, + "loss": 0.009117365628480912, + "num_tokens": 82168.0, + "reward": 1.0664794921875, + "reward_std": 0.29466880708932874, + "rewards/JointRewardFunction/mean": 1.0664794921875, + "rewards/JointRewardFunction/std": 0.29466880932450296, + "step": 20, + "step_time": 19.10480176490073 + }, + { + "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": 0.05, + "completions/max_length": 406.0, + "completions/max_terminated_length": 389.9, + "completions/mean_length": 295.1375, + "completions/mean_terminated_length": 285.5047637939453, + "completions/min_length": 206.6, + "completions/min_terminated_length": 206.6, + "entropy": 0.21663210522383453, + "epoch": 0.2, + "frac_reward_zero_std": 0.25, + "grad_norm": 2.5625, + "kl": 0.18388604540377856, + "learning_rate": 8.1875e-06, + "loss": -0.01458892971277237, + "num_tokens": 117195.0, + "reward": 1.017388916015625, + "reward_std": 0.4210638031363487, + "rewards/JointRewardFunction/mean": 1.017388916015625, + "rewards/JointRewardFunction/std": 0.4210638180375099, + "step": 30, + "step_time": 19.004520852699535 + }, + { + "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": 0.125, + "completions/max_length": 453.9, + "completions/max_terminated_length": 431.6, + "completions/mean_length": 362.6625, + "completions/mean_terminated_length": 344.75762634277345, + "completions/min_length": 264.3, + "completions/min_terminated_length": 264.3, + "entropy": 0.2015760915353894, + "epoch": 0.26666666666666666, + "frac_reward_zero_std": 0.15, + "grad_norm": 2.484375, + "kl": 0.17142300652340053, + "learning_rate": 7.5625e-06, + "loss": 0.021102146804332735, + "num_tokens": 159520.0, + "reward": 1.040948486328125, + "reward_std": 0.31338895484805107, + "rewards/JointRewardFunction/mean": 1.040948486328125, + "rewards/JointRewardFunction/std": 0.31338896676898004, + "step": 40, + "step_time": 20.873488509700472 + }, + { + "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": 0.025, + "completions/max_length": 410.2, + "completions/max_terminated_length": 389.0, + "completions/mean_length": 307.825, + "completions/mean_terminated_length": 303.1875030517578, + "completions/min_length": 237.3, + "completions/min_terminated_length": 237.3, + "entropy": 0.22014566687867046, + "epoch": 0.3333333333333333, + "frac_reward_zero_std": 0.35, + "grad_norm": 0.014892578125, + "kl": 0.22832224890589714, + "learning_rate": 6.9375e-06, + "loss": 0.039792636036872865, + "num_tokens": 196862.0, + "reward": 1.0728515625, + "reward_std": 0.32390306144952774, + "rewards/JointRewardFunction/mean": 1.0728515625, + "rewards/JointRewardFunction/std": 0.3239030599594116, + "step": 50, + "step_time": 19.236986151600284 + }, + { + "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": 0.025, + "completions/max_length": 397.9, + "completions/max_terminated_length": 383.6, + "completions/mean_length": 315.625, + "completions/mean_terminated_length": 310.5375, + "completions/min_length": 221.9, + "completions/min_terminated_length": 221.9, + "entropy": 0.19608328267931938, + "epoch": 0.4, + "frac_reward_zero_std": 0.35, + "grad_norm": 1.8203125, + "kl": 0.2169005206786096, + "learning_rate": 6.3125e-06, + "loss": 0.017893573641777037, + "num_tokens": 235512.0, + "reward": 1.103521728515625, + "reward_std": 0.26875718161463735, + "rewards/JointRewardFunction/mean": 1.103521728515625, + "rewards/JointRewardFunction/std": 0.26875719204545023, + "step": 60, + "step_time": 18.723443715600297 + }, + { + "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": 0.075, + "completions/max_length": 438.1, + "completions/max_terminated_length": 423.8, + "completions/mean_length": 340.4875, + "completions/mean_terminated_length": 326.67738342285156, + "completions/min_length": 246.7, + "completions/min_terminated_length": 246.7, + "entropy": 0.17470104116946458, + "epoch": 0.4666666666666667, + "frac_reward_zero_std": 0.45, + "grad_norm": 1.90625, + "kl": 0.17606046590954066, + "learning_rate": 5.6875e-06, + "loss": 0.012082196772098541, + "num_tokens": 276547.0, + "reward": 1.0309814453125, + "reward_std": 0.3187349811196327, + "rewards/JointRewardFunction/mean": 1.0309814453125, + "rewards/JointRewardFunction/std": 0.31873499751091006, + "step": 70, + "step_time": 20.5276982866013 + }, + { + "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": 0.0125, + "completions/max_length": 441.0, + "completions/max_terminated_length": 439.9, + "completions/mean_length": 336.4, + "completions/mean_terminated_length": 334.3732147216797, + "completions/min_length": 238.0, + "completions/min_terminated_length": 238.0, + "entropy": 0.18340560160577296, + "epoch": 0.5333333333333333, + "frac_reward_zero_std": 0.7, + "grad_norm": 0.04248046875, + "kl": 0.1858743063174188, + "learning_rate": 5.0625e-06, + "loss": -0.010596746206283569, + "num_tokens": 317131.0, + "reward": 1.1973876953125, + "reward_std": 0.14741100370883942, + "rewards/JointRewardFunction/mean": 1.1973876953125, + "rewards/JointRewardFunction/std": 0.1474110044538975, + "step": 80, + "step_time": 20.424764195699574 + }, + { + "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": 0.0625, + "completions/max_length": 422.6, + "completions/max_terminated_length": 411.2, + "completions/mean_length": 319.8375, + "completions/mean_terminated_length": 309.8089294433594, + "completions/min_length": 222.4, + "completions/min_terminated_length": 222.4, + "entropy": 0.17013722923584282, + "epoch": 0.6, + "frac_reward_zero_std": 0.45, + "grad_norm": 1.75, + "kl": 0.22596123907715082, + "learning_rate": 4.4375e-06, + "loss": 0.0059959739446640015, + "num_tokens": 356866.0, + "reward": 1.0788330078125, + "reward_std": 0.2970864400267601, + "rewards/JointRewardFunction/mean": 1.0788330078125, + "rewards/JointRewardFunction/std": 0.29708646088838575, + "step": 90, + "step_time": 19.734197501099334 + }, + { + "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": 0.05, + "completions/max_length": 397.6, + "completions/max_terminated_length": 372.7, + "completions/mean_length": 300.6, + "completions/mean_terminated_length": 287.1, + "completions/min_length": 220.5, + "completions/min_terminated_length": 220.5, + "entropy": 0.18155792271718382, + "epoch": 0.6666666666666666, + "frac_reward_zero_std": 0.95, + "grad_norm": 0.0279541015625, + "kl": 0.23375053312629462, + "learning_rate": 3.8125e-06, + "loss": 8.478660020045936e-05, + "num_tokens": 395798.0, + "reward": 1.1875, + "reward_std": 0.08880758583545685, + "rewards/JointRewardFunction/mean": 1.1875, + "rewards/JointRewardFunction/std": 0.08880758583545685, + "step": 100, + "step_time": 18.690151827099545 + }, + { + "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": 0.0375, + "completions/max_length": 459.3, + "completions/max_terminated_length": 430.1, + "completions/mean_length": 335.3875, + "completions/mean_terminated_length": 328.3857177734375, + "completions/min_length": 243.9, + "completions/min_terminated_length": 243.9, + "entropy": 0.1711413566954434, + "epoch": 0.7333333333333333, + "frac_reward_zero_std": 0.65, + "grad_norm": 1.4140625, + "kl": 0.18389353882521392, + "learning_rate": 3.1875e-06, + "loss": 0.0026162829250097274, + "num_tokens": 435577.0, + "reward": 1.116802978515625, + "reward_std": 0.22371026836335658, + "rewards/JointRewardFunction/mean": 1.116802978515625, + "rewards/JointRewardFunction/std": 0.2237102746963501, + "step": 110, + "step_time": 21.052574327701223 + }, + { + "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": 0.0625, + "completions/max_length": 380.6, + "completions/max_terminated_length": 371.3, + "completions/mean_length": 303.3, + "completions/mean_terminated_length": 292.425, + "completions/min_length": 222.7, + "completions/min_terminated_length": 222.7, + "entropy": 0.19935499429702758, + "epoch": 0.8, + "frac_reward_zero_std": 0.55, + "grad_norm": 1.59375, + "kl": 0.19222176214680076, + "learning_rate": 2.5625e-06, + "loss": 0.01612665057182312, + "num_tokens": 472105.0, + "reward": 1.0654541015625, + "reward_std": 0.28345242142677307, + "rewards/JointRewardFunction/mean": 1.0654541015625, + "rewards/JointRewardFunction/std": 0.28345243632793427, + "step": 120, + "step_time": 18.070694422099404 + }, + { + "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": 0.1125, + "completions/max_length": 451.0, + "completions/max_terminated_length": 385.2, + "completions/mean_length": 331.925, + "completions/mean_terminated_length": 312.57203063964846, + "completions/min_length": 237.9, + "completions/min_terminated_length": 237.9, + "entropy": 0.1600348782725632, + "epoch": 0.8666666666666667, + "frac_reward_zero_std": 0.45, + "grad_norm": 2.390625, + "kl": 0.18412442253902556, + "learning_rate": 1.9375e-06, + "loss": 0.01880526840686798, + "num_tokens": 512911.0, + "reward": 1.0941162109375, + "reward_std": 0.313115157186985, + "rewards/JointRewardFunction/mean": 1.0941162109375, + "rewards/JointRewardFunction/std": 0.31311516016721724, + "step": 130, + "step_time": 20.829227783899295 + }, + { + "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": 0.0, + "completions/max_length": 361.2, + "completions/max_terminated_length": 361.2, + "completions/mean_length": 285.1, + "completions/mean_terminated_length": 285.1, + "completions/min_length": 226.3, + "completions/min_terminated_length": 226.3, + "entropy": 0.18776001809164883, + "epoch": 0.9333333333333333, + "frac_reward_zero_std": 0.75, + "grad_norm": 0.038818359375, + "kl": 0.2174981951713562, + "learning_rate": 1.3125000000000001e-06, + "loss": 0.00478580966591835, + "num_tokens": 548351.0, + "reward": 1.18388671875, + "reward_std": 0.18575088679790497, + "rewards/JointRewardFunction/mean": 1.18388671875, + "rewards/JointRewardFunction/std": 0.1857508897781372, + "step": 140, + "step_time": 17.17216874960086 + }, + { + "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": 0.0375, + "completions/max_length": 431.1, + "completions/max_terminated_length": 389.6, + "completions/mean_length": 295.625, + "completions/mean_terminated_length": 285.92440643310545, + "completions/min_length": 217.1, + "completions/min_terminated_length": 217.1, + "entropy": 0.19556321045383812, + "epoch": 1.0, + "frac_reward_zero_std": 0.6, + "grad_norm": 1.984375, + "kl": 0.22088080924004316, + "learning_rate": 6.875000000000001e-07, + "loss": 0.03738939166069031, + "num_tokens": 584313.0, + "reward": 1.14267578125, + "reward_std": 0.25464810580015185, + "rewards/JointRewardFunction/mean": 1.14267578125, + "rewards/JointRewardFunction/std": 0.2546481089666486, + "step": 150, + "step_time": 20.206593494599836 + }, + { + "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": 0.0125, + "completions/max_length": 372.0, + "completions/max_terminated_length": 365.0, + "completions/mean_length": 278.375, + "completions/mean_terminated_length": 276.0125, + "completions/min_length": 212.7, + "completions/min_terminated_length": 212.7, + "entropy": 0.19452018961310386, + "epoch": 1.0666666666666667, + "frac_reward_zero_std": 0.55, + "grad_norm": 2.03125, + "kl": 0.2295491287484765, + "learning_rate": 6.250000000000001e-08, + "loss": -0.003883980959653854, + "num_tokens": 618499.0, + "reward": 1.161102294921875, + "reward_std": 0.1998678043484688, + "rewards/JointRewardFunction/mean": 1.161102294921875, + "rewards/JointRewardFunction/std": 0.19986780881881713, + "step": 160, + "step_time": 17.52442454840075 + } + ], + "logging_steps": 10, + "max_steps": 160, + "num_input_tokens_seen": 618499, + "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..1db9a4f --- /dev/null +++ b/last-checkpoint/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd54c42cca96a218cec23fd7b18a28bd3cfc9a58f782c35554e1f9a8899e176d +size 7249 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..9eb6dea --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445184cfe8c9bc43ab65cca3d906547483b0194ed77777df583b30815b629be6 +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..1db9a4f --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd54c42cca96a218cec23fd7b18a28bd3cfc9a58f782c35554e1f9a8899e176d +size 7249