<!-- 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. -->
mpham8/opus-mt-en-ROMANCE-finetuned-bam-to-fr-finetuned-bam-to-fr
This model is a fine-tuned version of mpham8/opus-mt-en-ROMANCE-finetuned-bam-to-fr on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6934
- Validation Loss: 0.2646
- Train Bleu: 70.9478
- Train Gen Len: 33.9867
- Epoch: 42
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 Bleu | Train Gen Len | Epoch |
|---|---|---|---|---|
| 2.4912 | 2.1490 | 6.4538 | 63.9433 | 0 |
| 2.2855 | 1.9357 | 8.9654 | 60.2427 | 1 |
| 2.1392 | 1.7827 | 9.9592 | 67.304 | 2 |
| 2.0250 | 1.6539 | 12.8260 | 72.8733 | 3 |
| 1.9288 | 1.5578 | 15.3897 | 60.79 | 4 |
| 1.8478 | 1.4682 | 14.8011 | 75.0593 | 5 |
| 1.7759 | 1.3935 | 16.6727 | 68.5527 | 6 |
| 1.7119 | 1.3223 | 19.7720 | 64.2227 | 7 |
| 1.6536 | 1.2601 | 20.9468 | 68.9367 | 8 |
| 1.5997 | 1.2059 | 20.5827 | 72.6047 | 9 |
| 1.5509 | 1.1463 | 19.0189 | 63.5927 | 10 |
| 1.5020 | 1.0996 | 23.1860 | 58.4813 | 11 |
| 1.4594 | 1.0486 | 26.1471 | 48.928 | 12 |
| 1.4189 | 1.0032 | 29.5029 | 46.51 | 13 |
| 1.3797 | 0.9643 | 28.5808 | 51.1693 | 14 |
| 1.3424 | 0.9228 | 31.3484 | 44.4947 | 15 |
| 1.3069 | 0.8842 | 32.6825 | 43.118 | 16 |
| 1.2721 | 0.8469 | 34.1900 | 39.7847 | 17 |
| 1.2400 | 0.8131 | 37.7316 | 37.6427 | 18 |
| 1.2089 | 0.7768 | 38.1373 | 39.624 | 19 |
| 1.1777 | 0.7420 | 39.2405 | 38.632 | 20 |
| 1.1491 | 0.7107 | 41.4665 | 39.07 | 21 |
| 1.1201 | 0.6841 | 42.0981 | 37.5293 | 22 |
| 1.0935 | 0.6517 | 44.3574 | 37.2947 | 23 |
| 1.0662 | 0.6261 | 44.9906 | 36.896 | 24 |
| 1.0406 | 0.5984 | 44.4437 | 38.0973 | 25 |
| 1.0155 | 0.5733 | 46.5144 | 38.4787 | 26 |
| 0.9921 | 0.5473 | 49.0599 | 36.1127 | 27 |
| 0.9694 | 0.5221 | 48.0559 | 35.8107 | 28 |
| 0.9451 | 0.4991 | 50.8444 | 36.3347 | 29 |
| 0.9230 | 0.4764 | 54.6054 | 36.1353 | 30 |
| 0.9013 | 0.4551 | 55.3687 | 35.1893 | 31 |
| 0.8796 | 0.4334 | 56.5136 | 35.306 | 32 |
| 0.8584 | 0.4142 | 57.7579 | 34.8267 | 33 |
| 0.8389 | 0.3952 | 60.2306 | 34.3993 | 34 |
| 0.8183 | 0.3756 | 61.8027 | 34.33 | 35 |
| 0.7991 | 0.3579 | 63.0070 | 34.856 | 36 |
| 0.7813 | 0.3435 | 64.1917 | 34.7053 | 37 |
| 0.7627 | 0.3228 | 65.5474 | 34.3607 | 38 |
| 0.7457 | 0.3107 | 66.7479 | 34.4573 | 39 |
| 0.7271 | 0.2929 | 68.3215 | 34.0347 | 40 |
| 0.7106 | 0.2778 | 69.6132 | 34.7493 | 41 |
| 0.6934 | 0.2646 | 70.9478 | 33.9867 | 42 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.9.0
- Tokenizers 0.13.2
