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: 2.8544
- Validation Loss: 3.5359
- Train Rouge1: 31.2594
- Train Rouge2: 8.1428
- Train Rougel: 22.0263
- Train Rougelsum: 23.4245
- Train Gen Len: 43.0
- Epoch: 2
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 |
|---|---|---|---|---|---|---|---|
| 3.3082 | 3.5055 | 33.4698 | 11.4810 | 25.8186 | 26.5162 | 43.625 | 0 |
| 3.0832 | 3.4774 | 31.7424 | 10.0784 | 23.7737 | 24.7615 | 42.625 | 1 |
| 2.8544 | 3.5359 | 31.2594 | 8.1428 | 22.0263 | 23.4245 | 43.0 | 2 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.1