metadata
base_model: facebook/bart-base
library_name: transformers
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: BART-Firefox-Simplification-Advanced
results: []
BART-Firefox-Simplification-Advanced
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0459
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: 2.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 71
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.3573 | 1.0 | 90 | 2.3117 |
| 2.3048 | 2.0 | 180 | 2.1491 |
| 2.0601 | 3.0 | 270 | 2.1264 |
| 1.9078 | 4.0 | 360 | 2.0917 |
| 1.7892 | 5.0 | 450 | 2.0459 |
| 1.6796 | 6.0 | 540 | 2.0607 |
| 1.658 | 7.0 | 630 | 2.0635 |
| 1.6285 | 8.0 | 720 | 2.0640 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu126
- Datasets 3.0.1
- Tokenizers 0.21.0