Proactive-Interactive-R1/Proactive-Interactive-R1-SFT-7B

1---2library_name: transformers3license: apache-2.04base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B5tags:6- llama-factory7- full8- generated_from_trainer9model-index:10- name: Proactive-Interactive-R1-SFT-7B11  results: []12datasets:13- Proactive-Interactive-R1/Reasoning-While-Asking-SFT-Dataset14language:15- en16---17 18<!-- This model card has been generated automatically according to the information the Trainer had access to. You19should probably proofread and complete it, then remove this comment. -->20 21# Proactive-Interactive-R1-SFT-7B22 23This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) on the Reasoning-While-Asking-SFT-Dataset dataset.24 25## Model description26 27More information needed28 29## Intended uses & limitations30 31More information needed32 33## Training and evaluation data34 35More information needed36 37## Training procedure38 39### Training hyperparameters40 41The following hyperparameters were used during training:42- max_samples: 400043- learning_rate: 1e-0544- train_batch_size: 845- eval_batch_size: 846- seed: 4247- distributed_type: multi-GPU48- num_devices: 449- total_train_batch_size: 3250- total_eval_batch_size: 3251- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments52- lr_scheduler_type: cosine53- lr_scheduler_warmup_ratio: 0.0354- num_epochs: 355 56### Training results57 58 59 60### Framework versions61 62- Transformers 4.55.063- Pytorch 2.8.0+cu12864- Datasets 3.6.065- Tokenizers 0.21.1