| | --- |
| | language: |
| | - en |
| | base_model: meta/instruction |
| | tags: |
| | - hih |
| | - generated_from_trainer |
| | datasets: |
| | - rajj0/AbstractAI |
| | model-index: |
| | - name: AbstractAI-LLaMA-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. --> |
| |
|
| | # AbstractAI-LLaMA-7b |
| |
|
| | This model is a fine-tuned version of [meta/instruction](https://huggingface.co/meta/instruction) on the AbstractAI dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 1.6270 |
| |
|
| | ## 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: 4 |
| | - eval_batch_size: 8 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: constant |
| | - lr_scheduler_warmup_ratio: 0.03 |
| | - num_epochs: 1 |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:-----:|:----:|:---------------:| |
| | | 1.7854 | 0.24 | 20 | 1.7964 | |
| | | 1.6215 | 0.49 | 40 | 1.6849 | |
| | | 1.6423 | 0.73 | 60 | 1.6501 | |
| | | 1.5844 | 0.98 | 80 | 1.6270 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.35.0.dev0 |
| | - Pytorch 2.0.1+cu117 |
| | - Datasets 2.14.4 |
| | - Tokenizers 0.14.0 |
| | |
