| base_model: NousResearch/Llama-2-7b-hf | |
| library_name: peft | |
| tags: | |
| - trl | |
| - sft | |
| - generated_from_trainer | |
| model-index: | |
| - name: Cold-Again-LLama-2-7B | |
| 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. --> | |
| # Cold-Again-LLama-2-7B | |
| This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset. | |
| It achieves the following results on the evaluation set: | |
| - eval_loss: 1.3661 | |
| - eval_runtime: 90.0594 | |
| - eval_samples_per_second: 1.11 | |
| - eval_steps_per_second: 0.044 | |
| - epoch: 5.76 | |
| - step: 36 | |
| ## 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: 0.0001 | |
| - train_batch_size: 16 | |
| - eval_batch_size: 32 | |
| - seed: 42 | |
| - gradient_accumulation_steps: 4 | |
| - total_train_batch_size: 64 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - lr_scheduler_warmup_ratio: 0.03 | |
| - num_epochs: 10 | |
| ### Framework versions | |
| - PEFT 0.12.0 | |
| - Transformers 4.43.3 | |
| - Pytorch 2.3.1+cu121 | |
| - Datasets 2.17.0 | |
| - Tokenizers 0.19.1 |