| --- |
| base_model: kaizerBox/retnet-summarization_small |
| tags: |
| - generated_from_trainer |
| datasets: |
| - xsum |
| model-index: |
| - name: retnet-summarization_small |
| 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. --> |
|
|
| # retnet-summarization_small |
| |
| This model is a fine-tuned version of [kaizerBox/retnet-summarization_small](https://huggingface.co/kaizerBox/retnet-summarization_small) on the xsum dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 4.1299 |
| |
| ## 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: 0.001 |
| - train_batch_size: 10 |
| - eval_batch_size: 10 |
| - seed: 42 |
| - gradient_accumulation_steps: 4 |
| - total_train_batch_size: 40 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 10 |
| - num_epochs: 3 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:-----:|:---------------:| |
| | 4.3711 | 1.0 | 4610 | 4.1533 | |
| | 4.3448 | 2.0 | 9220 | 4.1370 | |
| | 4.3247 | 3.0 | 13830 | 4.1299 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.35.2 |
| - Pytorch 2.1.0+cu118 |
| - Datasets 2.15.0 |
| - Tokenizers 0.15.0 |
| |
