metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: facebook/bart-large
model-index:
- name: bart-finetuned-lyrlen-128-special_tokens
results: []
bart-finetuned-lyrlen-128-special_tokens
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9389
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2828 | 0.33 | 500 | 3.0015 |
| 3.0513 | 0.67 | 1000 | 2.9361 |
| 2.9573 | 1.0 | 1500 | 2.9111 |
| 2.8841 | 1.33 | 2000 | 2.9007 |
| 2.8352 | 1.67 | 2500 | 2.9764 |
| 2.7897 | 2.0 | 3000 | 2.9606 |
| 2.7511 | 2.33 | 3500 | 2.9490 |
| 2.7284 | 2.67 | 4000 | 2.9458 |
| 2.7167 | 3.0 | 4500 | 2.9470 |
| 2.7226 | 3.33 | 5000 | 2.9418 |
| 2.6823 | 3.67 | 5500 | 2.9317 |
| 2.6445 | 4.0 | 6000 | 2.9389 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2