metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
datasets:
- arrow
model-index:
- name: LexLM_Longformer_BART_dependent_V1
results: []
LexLM_Longformer_BART_dependent_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: 2.0539
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 |
|---|---|---|---|
| 4.0359 | 1.0 | 69 | 2.3610 |
| 2.4398 | 2.0 | 138 | 2.1621 |
| 2.1751 | 3.0 | 207 | 2.0922 |
| 2.0243 | 4.0 | 276 | 2.0552 |
| 1.9034 | 5.0 | 345 | 2.0431 |
| 1.7928 | 6.0 | 414 | 2.0213 |
| 1.7052 | 7.0 | 483 | 2.0268 |
| 1.6214 | 8.0 | 552 | 2.0360 |
| 1.5587 | 9.0 | 621 | 2.0258 |
| 1.4833 | 10.0 | 690 | 2.0615 |
| 1.421 | 11.0 | 759 | 2.0539 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.19.1