| base_model: Qwen/Qwen2-Math-7B | |
| library_name: peft | |
| license: other | |
| tags: | |
| - llama-factory | |
| - lora | |
| - unsloth | |
| - generated_from_trainer | |
| model-index: | |
| - name: save | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # save | |
| This model is a fine-tuned version of [Qwen/Qwen2-Math-7B](https://huggingface.co/Qwen/Qwen2-Math-7B) on the Pretrain_Basic_low dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.4874 | |
| ## Model description | |
| More information needed | |
| ## Intended uses & limitations | |
| More information needed | |
| ## Training and evaluation data | |
| More information needed | |
| ## Training procedure | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 5e-05 | |
| - train_batch_size: 4 | |
| - eval_batch_size: 4 | |
| - seed: 42 | |
| - gradient_accumulation_steps: 4 | |
| - total_train_batch_size: 16 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: cosine | |
| - lr_scheduler_warmup_steps: 300 | |
| - num_epochs: 1.0 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:------:|:----:|:---------------:| | |
| | 0.4953 | 0.4333 | 500 | 0.4938 | | |
| | 0.4909 | 0.8666 | 1000 | 0.4874 | | |
| ### Framework versions | |
| - PEFT 0.12.0 | |
| - Transformers 4.43.4 | |
| - Pytorch 2.3.1+cu121 | |
| - Datasets 2.20.0 | |
| - Tokenizers 0.19.1 |