|
--- |
|
license: apache-2.0 |
|
base_model: facebook/bart-large |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- arrow |
|
model-index: |
|
- name: LexLM_Longformer_BART_fixed_V1 |
|
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. --> |
|
|
|
# LexLM_Longformer_BART_fixed_V1 |
|
|
|
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the arrow dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.1670 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 5.1435 | 1.0 | 69 | 2.4906 | |
|
| 2.5078 | 2.0 | 138 | 2.2599 | |
|
| 2.2506 | 3.0 | 207 | 2.1843 | |
|
| 2.0946 | 4.0 | 276 | 2.1453 | |
|
| 1.966 | 5.0 | 345 | 2.1326 | |
|
| 1.8557 | 6.0 | 414 | 2.1124 | |
|
| 1.7708 | 7.0 | 483 | 2.1070 | |
|
| 1.685 | 8.0 | 552 | 2.0991 | |
|
| 1.617 | 9.0 | 621 | 2.1086 | |
|
| 1.5477 | 10.0 | 690 | 2.1347 | |
|
| 1.4844 | 11.0 | 759 | 2.1264 | |
|
| 1.4307 | 12.0 | 828 | 2.1426 | |
|
| 1.3789 | 13.0 | 897 | 2.1670 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.19.1 |
|
|
