|
---
|
|
base_model: facebook/bart-base
|
|
library_name: transformers
|
|
license: apache-2.0
|
|
tags:
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: BART-Firefox-Simplification
|
|
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. -->
|
|
|
|
# BART-Firefox-Simplification
|
|
|
|
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 1.8845
|
|
|
|
## 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: 317
|
|
- num_epochs: 15
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:-----:|:----:|:---------------:|
|
|
| 2.9105 | 1.0 | 212 | 2.6066 |
|
|
| 2.5528 | 2.0 | 424 | 2.2820 |
|
|
| 2.2435 | 3.0 | 636 | 2.1249 |
|
|
| 2.0536 | 4.0 | 848 | 2.0488 |
|
|
| 1.8914 | 5.0 | 1060 | 2.0239 |
|
|
| 1.8098 | 6.0 | 1272 | 1.9841 |
|
|
| 1.7267 | 7.0 | 1484 | 1.9589 |
|
|
| 1.6515 | 8.0 | 1696 | 1.9342 |
|
|
| 1.5856 | 9.0 | 1908 | 1.9000 |
|
|
| 1.5154 | 10.0 | 2120 | 1.9103 |
|
|
| 1.457 | 11.0 | 2332 | 1.9085 |
|
|
| 1.4072 | 12.0 | 2544 | 1.8845 |
|
|
| 1.369 | 13.0 | 2756 | 1.8903 |
|
|
| 1.3603 | 14.0 | 2968 | 1.8887 |
|
|
| 1.3215 | 15.0 | 3180 | 1.8869 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.48.3
|
|
- Pytorch 2.6.0+cu126
|
|
- Datasets 3.0.1
|
|
- Tokenizers 0.21.0
|
|
|
