--- license: other library_name: peft tags: - generated_from_trainer base_model: facebook/opt-1.3b model-index: - name: opt-1.3b_IA3_627_lr5e-05_bs4_epoch5_wd0.01 results: [] --- # opt-1.3b_IA3_627_lr5e-05_bs4_epoch5_wd0.01 This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co./facebook/opt-1.3b) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 3.4045 ## 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 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 3.676 | 1.0 | 157 | 3.4596 | | 3.6527 | 2.0 | 314 | 3.4477 | | 3.6205 | 3.0 | 471 | 3.4289 | | 3.6168 | 4.0 | 628 | 3.4106 | | 3.6125 | 5.0 | 785 | 3.4045 | ### Framework versions - PEFT 0.7.1 - Transformers 4.36.2 - Pytorch 2.0.1 - Datasets 2.16.1 - Tokenizers 0.15.0