metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
datasets:
- arrow
model-index:
- name: LexLM_BART_fixed_V1
results: []
LexLM_BART_fixed_V1
This model is a fine-tuned version of facebook/bart-large on the arrow dataset. It achieves the following results on the evaluation set:
- Loss: 2.0971
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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.3227 | 1.0 | 69 | 2.3943 |
| 2.4403 | 2.0 | 138 | 2.1996 |
| 2.1857 | 3.0 | 207 | 2.1211 |
| 2.0354 | 4.0 | 276 | 2.0916 |
| 1.9175 | 5.0 | 345 | 2.0698 |
| 1.8048 | 6.0 | 414 | 2.0523 |
| 1.723 | 7.0 | 483 | 2.0462 |
| 1.6439 | 8.0 | 552 | 2.0653 |
| 1.5745 | 9.0 | 621 | 2.0608 |
| 1.5017 | 10.0 | 690 | 2.0902 |
| 1.44 | 11.0 | 759 | 2.0821 |
| 1.3828 | 12.0 | 828 | 2.0971 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.19.1