m2m100-lg-to-en-v5
This model is a fine-tuned version of MubarakB/m2m100-lg-to-en-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5196
- Bleu: 0.1371
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 2.6476 | 1.0 | 237 | 0.7225 | 0.3822 |
| 0.5312 | 2.0 | 474 | 0.5011 | 0.0973 |
| 0.4211 | 3.0 | 711 | 0.4924 | 0.3545 |
| 0.4015 | 4.0 | 948 | 0.4957 | 0.1006 |
| 0.3431 | 5.0 | 1185 | 0.5096 | 0.1953 |
| 0.2992 | 6.0 | 1422 | 0.5196 | 0.1371 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1