metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: alexrink/t5-small-finetuned-xsum
results: []
alexrink/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: 5.6399
- Validation Loss: 6.0028
- Epoch: 19
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': 0.2, '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 | Epoch |
|---|---|---|
| 11.4991 | 6.9902 | 0 |
| 6.5958 | 6.2502 | 1 |
| 6.1443 | 6.1638 | 2 |
| 5.9379 | 6.0765 | 3 |
| 5.7739 | 5.9393 | 4 |
| 5.7033 | 6.0061 | 5 |
| 5.7070 | 5.9305 | 6 |
| 5.7000 | 5.9698 | 7 |
| 5.6888 | 5.9223 | 8 |
| 5.6657 | 5.9773 | 9 |
| 5.6827 | 5.9734 | 10 |
| 5.6380 | 5.9428 | 11 |
| 5.6532 | 5.9799 | 12 |
| 5.6617 | 5.9974 | 13 |
| 5.6402 | 5.9563 | 14 |
| 5.6710 | 5.9926 | 15 |
| 5.6999 | 5.9764 | 16 |
| 5.6573 | 5.9557 | 17 |
| 5.6297 | 5.9678 | 18 |
| 5.6399 | 6.0028 | 19 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.9.0
- Tokenizers 0.13.2