metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_keras_callback
model-index:
- name: hasan-mr/t5-small-finetuned-xsum
results: []
hasan-mr/t5-small-finetuned-xsum
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.4714
- Validation Loss: 2.3108
- Train Rouge1: 19.8577
- Train Rouge2: 9.8769
- Train Rougel: 16.9223
- Train Rougelsum: 18.4092
- Train Gen Len: 19.0
- 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 |
|---|---|---|---|---|---|---|---|
| 2.7851 | 2.5023 | 15.0390 | 5.8132 | 12.5782 | 13.5865 | 19.0 | 0 |
| 2.6216 | 2.4086 | 19.5309 | 9.3236 | 16.5987 | 17.9409 | 19.0 | 1 |
| 2.5328 | 2.3538 | 19.7729 | 9.7316 | 16.9347 | 18.2866 | 19.0 | 2 |
| 2.4714 | 2.3108 | 19.8577 | 9.8769 | 16.9223 | 18.4092 | 19.0 | 3 |
Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1