<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
hienbm/t5-small-complex-compound-to-simple
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: 2.9532
- Validation Loss: 2.8327
- Train Rouge1: 7.3022
- Train Rouge2: 2.5014
- Train Rougel: 6.2732
- Train Rougelsum: 6.8445
- Train Gen Len: 19.0
- Train Lr: 1e-04
- Epoch: 4
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': 'AdamW', 'weight_decay': 0.01, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Train Lr | Epoch |
|---|---|---|---|---|---|---|---|---|
| 3.3185 | 2.9178 | 6.0379 | 1.7784 | 5.1240 | 5.6647 | 19.0 | 1e-04 | 0 |
| 3.1137 | 2.8751 | 5.6140 | 1.5822 | 4.8464 | 5.2866 | 19.0 | 1e-04 | 1 |
| 3.0477 | 2.8522 | 5.7262 | 1.6938 | 4.9663 | 5.4112 | 19.0 | 1e-04 | 2 |
| 2.9955 | 2.8358 | 6.6081 | 2.1450 | 5.7088 | 6.2191 | 19.0 | 1e-04 | 3 |
| 2.9532 | 2.8327 | 7.3022 | 2.5014 | 6.2732 | 6.8445 | 19.0 | 1e-04 | 4 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.13.0
- Datasets 2.13.1
- Tokenizers 0.13.3
