<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Tn-En_update
This model is a fine-tuned version of Helsinki-NLP/opus-mt-tn-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2371
- Bleu: 41.6029
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:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Bleu | Validation Loss |
|---|---|---|---|---|
| 2.1976 | 1.0 | 7554 | 26.8684 | 2.1137 |
| 1.871 | 2.0 | 15108 | 30.6829 | 1.8089 |
| 1.7084 | 3.0 | 22662 | 33.3106 | 1.6236 |
| 1.5871 | 4.0 | 30216 | 36.3656 | 1.5039 |
| 1.4967 | 5.0 | 37770 | 37.2840 | 1.4182 |
| 1.429 | 6.0 | 45324 | 38.9794 | 1.3521 |
| 1.3629 | 7.0 | 52878 | 40.2757 | 1.2992 |
| 1.3444 | 8.0 | 60432 | 40.9979 | 1.2632 |
| 1.3069 | 9.0 | 67986 | 41.3006 | 1.2438 |
| 1.2745 | 10.0 | 75540 | 41.5511 | 1.2371 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
