metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_keras_callback
model-index:
- name: iguerrasevillano/BART-summ-v1
results: []
iguerrasevillano/BART-summ-v1
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.8770
- Validation Loss: 3.5305
- Train Rouge1: 26.4536
- Train Rouge2: 8.0238
- Train Rougel: 21.3939
- Train Rougelsum: 21.0272
- Train Gen Len: 20.0
- Epoch: 3
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|---|---|---|---|---|---|---|---|
| 3.9333 | 3.5188 | 26.6086 | 6.7680 | 20.7580 | 20.5472 | 20.0 | 0 |
| 3.3063 | 3.5640 | 27.2760 | 6.7716 | 21.4322 | 20.8327 | 20.0 | 1 |
| 3.0764 | 3.5048 | 27.4389 | 7.4962 | 21.7549 | 21.5366 | 20.0 | 2 |
| 2.8770 | 3.5305 | 26.4536 | 8.0238 | 21.3939 | 21.0272 | 20.0 | 3 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.1