<!-- 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. -->
nlewins/mt5-small-finetuned-ceb-to-en-tfX
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5927
- Validation Loss: 3.9934
- Train Bleu: 10.0888
- Train Gen Len: 32.4741
- Epoch: 16
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': 1e-04, '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 Bleu | Train Gen Len | Epoch |
---|---|---|---|---|
1.1257 | 3.4180 | 9.2258 | 34.9759 | 0 |
1.0746 | 3.4744 | 9.0599 | 34.4333 | 1 |
1.0318 | 3.4972 | 8.4820 | 36.3167 | 2 |
0.9940 | 3.5171 | 8.8382 | 34.5167 | 3 |
0.9592 | 3.5706 | 9.2122 | 33.3926 | 4 |
0.9204 | 3.6009 | 9.1170 | 35.0278 | 5 |
0.8846 | 3.6195 | 8.8953 | 35.3463 | 6 |
0.8452 | 3.6851 | 9.6623 | 32.4241 | 7 |
0.8165 | 3.6549 | 9.5994 | 33.5389 | 8 |
0.7849 | 3.7170 | 9.6300 | 34.2130 | 9 |
0.7493 | 3.7729 | 9.7413 | 32.8963 | 10 |
0.7251 | 3.8037 | 9.9866 | 32.0574 | 11 |
0.6969 | 3.8562 | 9.8795 | 33.6519 | 12 |
0.6712 | 3.8593 | 10.1822 | 33.75 | 13 |
0.6432 | 3.9431 | 10.2341 | 32.9259 | 14 |
0.6101 | 3.9601 | 10.1144 | 32.7981 | 15 |
0.5927 | 3.9934 | 10.0888 | 32.4741 | 16 |
Framework versions
- Transformers 4.33.3
- TensorFlow 2.14.0
- Datasets 2.14.5
- Tokenizers 0.13.3