From de5c08a12c07624674aff76f439d40ef2c95f642 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 16 Jun 2026 07:40:17 +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-island-s42-lambda-0p75 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..7f11250 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Qwen/Qwen2.5-3B-Instruct +library_name: transformers +model_name: expfinal-qwen-island-s42-lambda-0p75 +tags: +- generated_from_trainer +- trl +- grpo +licence: license +--- + +# Model Card for expfinal-qwen-island-s42-lambda-0p75 + +This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-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="harsha070/expfinal-qwen-island-s42-lambda-0p75", 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/9b5b5fg9) + + + +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..a59148e --- /dev/null +++ b/completions/completions_00010.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1adff6d35ca30e9962cfdc1c1a90e165246b8aa4ae1f3cc0903795cf5d53bbb3 +size 15462 diff --git a/completions/completions_00020.parquet b/completions/completions_00020.parquet new file mode 100644 index 0000000..e037ef7 --- /dev/null +++ b/completions/completions_00020.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f2cf42000b2f499fc751d25154e7eb0e02911870139c33060bbd44f40b0331b +size 13294 diff --git a/completions/completions_00030.parquet b/completions/completions_00030.parquet new file mode 100644 index 0000000..a13f2da --- /dev/null +++ b/completions/completions_00030.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:903994d208b45c7bf1f7a6777ab29bb26cb72fed06baac7937cd5d204cab2df2 +size 22318 diff --git a/completions/completions_00040.parquet b/completions/completions_00040.parquet new file mode 100644 index 0000000..5513833 --- /dev/null +++ b/completions/completions_00040.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc225f17db7d00fb6abcb05ee14e8d81930467f09b934bc162f6516b3c39ea0 +size 19068 diff --git a/completions/completions_00050.parquet b/completions/completions_00050.parquet new file mode 100644 index 0000000..5ff64a7 --- /dev/null +++ b/completions/completions_00050.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700c7127efef7e4ad8ef4886387afda5fcc7cbcfb915398d26f592985a491535 +size 15660 diff --git a/completions/completions_00060.parquet b/completions/completions_00060.parquet new file mode 100644 index 0000000..72d3b65 --- /dev/null +++ b/completions/completions_00060.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1b58202738ca184a499b6071fc4a0e000a722ecc7612829b6bfb84a27ea8a94 +size 20592 diff --git a/completions/completions_00070.parquet b/completions/completions_00070.parquet new file mode 100644 index 0000000..197a7fb --- /dev/null +++ b/completions/completions_00070.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81bab122c0f2aee8cd4493881883d269d5fbaca859df7a444662a11b671f2f15 +size 15758 diff --git a/completions/completions_00080.parquet b/completions/completions_00080.parquet new file mode 100644 index 0000000..efb1cb9 --- /dev/null +++ b/completions/completions_00080.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee487fe2973939aa229c70f517e7cddbd1b7cacf03aa5f7c1bddc0b189d95cb +size 15033 diff --git a/completions/completions_00090.parquet b/completions/completions_00090.parquet new file mode 100644 index 0000000..600b7ca --- /dev/null +++ b/completions/completions_00090.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b272d026125dc2244cb38f4b0e770b71985c86d3deca9047cd3616897829448 +size 18720 diff --git a/completions/completions_00100.parquet b/completions/completions_00100.parquet new file mode 100644 index 0000000..a26f5f0 --- /dev/null +++ b/completions/completions_00100.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc320191cbea05160197d9e8c920cb0f9850a7402ad2ef668e0d6acd2e17a47 +size 13283 diff --git a/completions/completions_00110.parquet b/completions/completions_00110.parquet new file mode 100644 index 0000000..a2f7de6 --- /dev/null +++ b/completions/completions_00110.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:714bcbdced8e4d38e99125c1fe6053d350a51448877fafa622702b5ef044da57 +size 15580 diff --git a/completions/completions_00120.parquet b/completions/completions_00120.parquet new file mode 100644 index 0000000..910364a --- /dev/null +++ b/completions/completions_00120.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e4f0c26d61f85db75700093b7cedd13aa3f55ac334581f184fc60acb107033 +size 20100 diff --git a/completions/completions_00130.parquet b/completions/completions_00130.parquet new file mode 100644 index 0000000..bde2ecf --- /dev/null +++ b/completions/completions_00130.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7eb952f5a2de3db51855a86f396224a189ee940c510347fc1f43497570c0d2a +size 17732 diff --git a/completions/completions_00140.parquet b/completions/completions_00140.parquet new file mode 100644 index 0000000..349936f --- /dev/null +++ b/completions/completions_00140.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7803a897216d4a7dd3209f81c0a6cdf59dedf88e34aa1f3d867f5a19b0ad4381 +size 11083 diff --git a/completions/completions_00150.parquet b/completions/completions_00150.parquet new file mode 100644 index 0000000..aa03784 --- /dev/null +++ b/completions/completions_00150.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a4ced60b5878ee47f7ad975317234ff93381b5cbf79e6d041f87266b9d2e24 +size 16206 diff --git a/completions/completions_00160.parquet b/completions/completions_00160.parquet new file mode 100644 index 0000000..9961853 --- /dev/null +++ b/completions/completions_00160.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5946aa10869aea755491362fcef6a83fe28da550db1586e54355a991d7da338a +size 15264 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..e80cb84 --- /dev/null +++ b/last-checkpoint/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b6936f0e5ca14f4d6360795d02b25c43457a020c930e833bc09e83abd68971 +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..c7d45b1 --- /dev/null +++ b/last-checkpoint/trainer_state.json @@ -0,0 +1,482 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.28, + "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": 0.15, + "completions/max_length": 920.8, + "completions/max_terminated_length": 815.0, + "completions/mean_length": 575.9125, + "completions/mean_terminated_length": 512.0958465576172, + "completions/min_length": 250.5, + "completions/min_terminated_length": 250.5, + "entropy": 1.1609928414225579, + "epoch": 0.08, + "frac_reward_zero_std": 0.225, + "grad_norm": 4.6875, + "kl": 0.13114853966326337, + "learning_rate": 9.4375e-06, + "loss": 0.012817811965942384, + "num_tokens": 66717.0, + "reward": 0.730865478515625, + "reward_std": 0.7215771168470383, + "rewards/JointRewardFunction/mean": 0.730865478515625, + "rewards/JointRewardFunction/std": 0.7215771168470383, + "step": 10, + "step_time": 38.070080343699374 + }, + { + "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": 391.7, + "completions/max_terminated_length": 391.7, + "completions/mean_length": 177.925, + "completions/mean_terminated_length": 177.925, + "completions/min_length": 49.9, + "completions/min_terminated_length": 49.9, + "entropy": 2.0190576702356338, + "epoch": 0.16, + "frac_reward_zero_std": 0.1, + "grad_norm": 17.375, + "kl": 1.693755827844143, + "learning_rate": 8.8125e-06, + "loss": 0.07697797417640687, + "num_tokens": 101595.0, + "reward": 0.496136474609375, + "reward_std": 0.7558781564235687, + "rewards/JointRewardFunction/mean": 0.496136474609375, + "rewards/JointRewardFunction/std": 0.7558781564235687, + "step": 20, + "step_time": 18.131606991801892 + }, + { + "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": 0.175, + "completions/max_length": 988.7, + "completions/max_terminated_length": 802.5, + "completions/mean_length": 531.1125, + "completions/mean_terminated_length": 433.47263793945314, + "completions/min_length": 180.2, + "completions/min_terminated_length": 180.2, + "entropy": 1.3736804876476527, + "epoch": 0.24, + "frac_reward_zero_std": 0.225, + "grad_norm": 4.4375, + "kl": 0.4292584811337292, + "learning_rate": 8.1875e-06, + "loss": 0.12034453153610229, + "num_tokens": 164528.0, + "reward": 0.727508544921875, + "reward_std": 0.5448802873492241, + "rewards/JointRewardFunction/mean": 0.727508544921875, + "rewards/JointRewardFunction/std": 0.5448802877217531, + "step": 30, + "step_time": 42.41746253830024 + }, + { + "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": 926.7, + "completions/max_terminated_length": 754.3, + "completions/mean_length": 494.75, + "completions/mean_terminated_length": 441.88750610351565, + "completions/min_length": 215.1, + "completions/min_terminated_length": 215.1, + "entropy": 1.0656868401914834, + "epoch": 0.32, + "frac_reward_zero_std": 0.25, + "grad_norm": 5.125, + "kl": 0.3164741122163832, + "learning_rate": 7.5625e-06, + "loss": 0.0320564866065979, + "num_tokens": 224682.0, + "reward": 0.874420166015625, + "reward_std": 0.6246562719345092, + "rewards/JointRewardFunction/mean": 0.874420166015625, + "rewards/JointRewardFunction/std": 0.6246562749147415, + "step": 40, + "step_time": 39.87609361880059 + }, + { + "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": 629.9, + "completions/max_terminated_length": 629.9, + "completions/mean_length": 327.525, + "completions/mean_terminated_length": 327.525, + "completions/min_length": 114.7, + "completions/min_terminated_length": 114.7, + "entropy": 1.2003333028405905, + "epoch": 0.4, + "frac_reward_zero_std": 0.2, + "grad_norm": 7.5, + "kl": 0.43942997977137566, + "learning_rate": 6.9375e-06, + "loss": 0.022251369059085847, + "num_tokens": 271714.0, + "reward": 1.063922119140625, + "reward_std": 0.6383892238140106, + "rewards/JointRewardFunction/mean": 1.063922119140625, + "rewards/JointRewardFunction/std": 0.6383892357349396, + "step": 50, + "step_time": 27.557733834501413 + }, + { + "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": 641.7, + "completions/max_terminated_length": 590.3, + "completions/mean_length": 302.5, + "completions/mean_terminated_length": 293.0178588867187, + "completions/min_length": 102.5, + "completions/min_terminated_length": 102.5, + "entropy": 1.3896781962364912, + "epoch": 0.48, + "frac_reward_zero_std": 0.225, + "grad_norm": 4.375, + "kl": 0.5564426928758621, + "learning_rate": 6.3125e-06, + "loss": -0.0015912272036075592, + "num_tokens": 316254.0, + "reward": 0.9928466796875, + "reward_std": 0.6274125874042511, + "rewards/JointRewardFunction/mean": 0.9928466796875, + "rewards/JointRewardFunction/std": 0.6274125933647156, + "step": 60, + "step_time": 28.0631938617993 + }, + { + "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": 586.9, + "completions/max_terminated_length": 586.9, + "completions/mean_length": 294.55, + "completions/mean_terminated_length": 294.55, + "completions/min_length": 114.6, + "completions/min_terminated_length": 114.6, + "entropy": 1.4918637625873088, + "epoch": 0.56, + "frac_reward_zero_std": 0.25, + "grad_norm": 5.15625, + "kl": 0.5497013371437788, + "learning_rate": 5.6875e-06, + "loss": 0.047078275680541994, + "num_tokens": 360274.0, + "reward": 1.1190673828125, + "reward_std": 0.609263214468956, + "rewards/JointRewardFunction/mean": 1.1190673828125, + "rewards/JointRewardFunction/std": 0.609263226389885, + "step": 70, + "step_time": 26.138083929998174 + }, + { + "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": 847.5, + "completions/max_terminated_length": 678.8, + "completions/mean_length": 365.3375, + "completions/mean_terminated_length": 321.4898880004883, + "completions/min_length": 90.4, + "completions/min_terminated_length": 90.4, + "entropy": 1.5532763354480266, + "epoch": 0.64, + "frac_reward_zero_std": 0.175, + "grad_norm": 5.78125, + "kl": 0.4981705164536834, + "learning_rate": 5.0625e-06, + "loss": 0.11404727697372437, + "num_tokens": 410115.0, + "reward": 0.9597900390625, + "reward_std": 0.6095708787441254, + "rewards/JointRewardFunction/mean": 0.9597900390625, + "rewards/JointRewardFunction/std": 0.6095708817243576, + "step": 80, + "step_time": 36.49904953569931 + }, + { + "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": 732.5, + "completions/max_terminated_length": 677.8, + "completions/mean_length": 299.875, + "completions/mean_terminated_length": 282.1875030517578, + "completions/min_length": 96.0, + "completions/min_terminated_length": 96.0, + "entropy": 1.4728075489401817, + "epoch": 0.72, + "frac_reward_zero_std": 0.225, + "grad_norm": 3.5625, + "kl": 0.4925263602286577, + "learning_rate": 4.4375e-06, + "loss": 0.054662787914276124, + "num_tokens": 454725.0, + "reward": 1.019183349609375, + "reward_std": 0.61219422519207, + "rewards/JointRewardFunction/mean": 1.019183349609375, + "rewards/JointRewardFunction/std": 0.6121942341327667, + "step": 90, + "step_time": 31.705154634100108 + }, + { + "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": 760.6, + "completions/max_terminated_length": 660.6, + "completions/mean_length": 352.475, + "completions/mean_terminated_length": 312.0821502685547, + "completions/min_length": 105.0, + "completions/min_terminated_length": 105.0, + "entropy": 1.3954405788332225, + "epoch": 0.8, + "frac_reward_zero_std": 0.125, + "grad_norm": 5.78125, + "kl": 0.4322750365361571, + "learning_rate": 3.8125e-06, + "loss": 0.009273938834667206, + "num_tokens": 503589.0, + "reward": 0.9172119140625, + "reward_std": 0.6775627821683884, + "rewards/JointRewardFunction/mean": 0.9172119140625, + "rewards/JointRewardFunction/std": 0.6775627851486206, + "step": 100, + "step_time": 33.002576629400934 + }, + { + "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": 687.7, + "completions/max_terminated_length": 653.3, + "completions/mean_length": 315.025, + "completions/mean_terminated_length": 306.5357147216797, + "completions/min_length": 97.6, + "completions/min_terminated_length": 97.6, + "entropy": 1.4698836095631123, + "epoch": 0.88, + "frac_reward_zero_std": 0.275, + "grad_norm": 8.125, + "kl": 0.4709475075826049, + "learning_rate": 3.1875e-06, + "loss": 0.09247303009033203, + "num_tokens": 549335.0, + "reward": 0.997833251953125, + "reward_std": 0.6001621454954147, + "rewards/JointRewardFunction/mean": 0.997833251953125, + "rewards/JointRewardFunction/std": 0.6001621544361114, + "step": 110, + "step_time": 30.22435642040182 + }, + { + "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": 865.7, + "completions/max_terminated_length": 724.8, + "completions/mean_length": 377.4125, + "completions/mean_terminated_length": 342.6226211547852, + "completions/min_length": 102.6, + "completions/min_terminated_length": 102.6, + "entropy": 1.4377100937068463, + "epoch": 0.96, + "frac_reward_zero_std": 0.225, + "grad_norm": 3.15625, + "kl": 0.4150696059688926, + "learning_rate": 2.5625e-06, + "loss": -0.021556401252746583, + "num_tokens": 599900.0, + "reward": 1.0236083984375, + "reward_std": 0.6392961710691452, + "rewards/JointRewardFunction/mean": 1.0236083984375, + "rewards/JointRewardFunction/std": 0.6392962068319321, + "step": 120, + "step_time": 37.14680036250138 + }, + { + "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": 698.9, + "completions/max_terminated_length": 598.9, + "completions/mean_length": 299.0125, + "completions/mean_terminated_length": 260.36726531982424, + "completions/min_length": 72.3, + "completions/min_terminated_length": 72.3, + "entropy": 1.3930659301578998, + "epoch": 1.04, + "frac_reward_zero_std": 0.2, + "grad_norm": 5.71875, + "kl": 0.48926177779212593, + "learning_rate": 1.9375e-06, + "loss": 0.016721364855766297, + "num_tokens": 644439.0, + "reward": 0.972833251953125, + "reward_std": 0.6092687845230103, + "rewards/JointRewardFunction/mean": 0.972833251953125, + "rewards/JointRewardFunction/std": 0.6092687904834747, + "step": 130, + "step_time": 30.47871646400163 + }, + { + "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": 623.9, + "completions/max_terminated_length": 623.9, + "completions/mean_length": 286.925, + "completions/mean_terminated_length": 286.925, + "completions/min_length": 71.1, + "completions/min_terminated_length": 71.1, + "entropy": 1.4094880308955908, + "epoch": 1.12, + "frac_reward_zero_std": 0.35, + "grad_norm": 10.8125, + "kl": 0.4836927611380816, + "learning_rate": 1.3125000000000001e-06, + "loss": 0.08277995586395263, + "num_tokens": 688041.0, + "reward": 1.046673583984375, + "reward_std": 0.5450149297714233, + "rewards/JointRewardFunction/mean": 1.046673583984375, + "rewards/JointRewardFunction/std": 0.5450149476528168, + "step": 140, + "step_time": 27.556023125701177 + }, + { + "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": 781.7, + "completions/max_terminated_length": 652.2, + "completions/mean_length": 349.275, + "completions/mean_terminated_length": 317.290478515625, + "completions/min_length": 88.2, + "completions/min_terminated_length": 88.2, + "entropy": 1.334358724579215, + "epoch": 1.2, + "frac_reward_zero_std": 0.15, + "grad_norm": 5.9375, + "kl": 0.44102346180006863, + "learning_rate": 6.875000000000001e-07, + "loss": 0.12827397584915162, + "num_tokens": 736559.0, + "reward": 0.999505615234375, + "reward_std": 0.6881234139204025, + "rewards/JointRewardFunction/mean": 0.999505615234375, + "rewards/JointRewardFunction/std": 0.6881234139204025, + "step": 150, + "step_time": 33.79141057000161 + }, + { + "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": 678.4, + "completions/max_terminated_length": 558.1, + "completions/mean_length": 299.375, + "completions/mean_terminated_length": 261.2517883300781, + "completions/min_length": 71.7, + "completions/min_terminated_length": 71.7, + "entropy": 1.3799165710806847, + "epoch": 1.28, + "frac_reward_zero_std": 0.175, + "grad_norm": 7.21875, + "kl": 0.4770205244421959, + "learning_rate": 6.250000000000001e-08, + "loss": 0.08484221696853637, + "num_tokens": 781411.0, + "reward": 0.87017822265625, + "reward_std": 0.6314140051603317, + "rewards/JointRewardFunction/mean": 0.87017822265625, + "rewards/JointRewardFunction/std": 0.6314140141010285, + "step": 160, + "step_time": 30.14368499219854 + } + ], + "logging_steps": 10, + "max_steps": 160, + "num_input_tokens_seen": 781411, + "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..39b7889 --- /dev/null +++ b/last-checkpoint/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097ba1449d336ba5ce121ddd53380281d14f6040068d1d8375eaa4b8f24c83b8 +size 7249 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..e80cb84 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b6936f0e5ca14f4d6360795d02b25c43457a020c930e833bc09e83abd68971 +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..39b7889 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097ba1449d336ba5ce121ddd53380281d14f6040068d1d8375eaa4b8f24c83b8 +size 7249