metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bartL_3
results: []
bartL_3
This model is a fine-tuned version of facebook/bart-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.8209
- Rouge1: 0.1782
- Rouge2: 0.0368
- Rougel: 0.1349
- Rougelsum: 0.1349
- Gen Len: 20.0
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 1515
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.283 | 1.0 | 317 | 2.7342 | 0.1742 | 0.0364 | 0.128 | 0.1283 | 20.0 |
| 2.6366 | 2.0 | 634 | 2.7466 | 0.1838 | 0.0448 | 0.139 | 0.1394 | 20.0 |
| 2.2437 | 3.0 | 951 | 2.7819 | 0.1691 | 0.0374 | 0.1277 | 0.1278 | 20.0 |
| 1.9957 | 4.0 | 1268 | 2.8209 | 0.1782 | 0.0368 | 0.1349 | 0.1349 | 20.0 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.1