| license: apache-2.0 | |
| base_model: PY007/TinyLlama-1.1B-Chat-v0.3 | |
| tags: | |
| - generated_from_trainer | |
| model-index: | |
| - name: megachat | |
| 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. --> | |
| # megachat | |
| This model is a fine-tuned version of [PY007/TinyLlama-1.1B-Chat-v0.3](https://huggingface.co/PY007/TinyLlama-1.1B-Chat-v0.3) on an unknown dataset. | |
| ## 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: 0.0002 | |
| - train_batch_size: 1 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - gradient_accumulation_steps: 4 | |
| - total_train_batch_size: 4 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: cosine | |
| - training_steps: 2000 | |
| ### Training results | |
| ### Framework versions | |
| - Transformers 4.34.0 | |
| - Pytorch 2.1.0+cu121 | |
| - Datasets 2.14.5 | |
| - Tokenizers 0.14.1 | |
| # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) | |
| Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_w95__megachat) | |
| | Metric | Value | | |
| |-----------------------|---------------------------| | |
| | Avg. | 30.38 | | |
| | ARC (25-shot) | 30.8 | | |
| | HellaSwag (10-shot) | 54.35 | | |
| | MMLU (5-shot) | 25.55 | | |
| | TruthfulQA (0-shot) | 39.85 | | |
| | Winogrande (5-shot) | 56.99 | | |
| | GSM8K (5-shot) | 0.99 | | |
| | DROP (3-shot) | 4.16 | | |