<!-- 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. -->
LucaReggiani/t5-small-nlpfinalproject55-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: 3.1996
- Validation Loss: 3.0509
- Train Rouge1: 21.8691
- Train Rouge2: 5.0380
- Train Rougel: 17.3737
- Train Rougelsum: 17.3666
- Train Gen Len: 18.62
- Epoch: 9
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': 'SGD', 'weight_decay': None, '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': 0.01, 'momentum': 0.9, 'nesterov': False}
- training_precision: float32
Training results
Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
---|---|---|---|---|---|---|---|
3.8269 | 3.3077 | 18.3354 | 2.6346 | 14.6819 | 14.5948 | 18.56 | 0 |
3.6784 | 3.2525 | 20.0886 | 2.8244 | 15.8006 | 15.8320 | 17.89 | 1 |
3.5221 | 3.1223 | 20.4536 | 3.7761 | 15.5971 | 15.5748 | 18.5 | 2 |
3.3981 | 3.1003 | 22.0145 | 4.8444 | 17.1468 | 17.1329 | 18.01 | 3 |
3.3380 | 3.0591 | 21.8603 | 4.4109 | 16.9049 | 16.9147 | 18.45 | 4 |
3.3200 | 3.1147 | 21.5178 | 4.7155 | 17.4288 | 17.4466 | 18.78 | 5 |
3.3745 | 3.0972 | 22.3848 | 4.4307 | 17.2203 | 17.2453 | 18.14 | 6 |
3.2990 | 3.0936 | 23.0953 | 4.6457 | 18.0523 | 18.0075 | 17.73 | 7 |
3.2382 | 3.0578 | 23.0047 | 5.2161 | 18.0230 | 18.0116 | 18.46 | 8 |
3.1996 | 3.0509 | 21.8691 | 5.0380 | 17.3737 | 17.3666 | 18.62 | 9 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.9.0
- Tokenizers 0.13.2