Transformer_MT
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-hi on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2471
- Bleu: 0.4736
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| No log | 2.53 | 200 | 2.4508 | 0.1996 |
| No log | 5.06 | 400 | 2.3803 | 0.3002 |
| 2.49 | 7.59 | 600 | 2.3398 | 0.4351 |
| 2.49 | 10.13 | 800 | 2.3148 | 0.3753 |
| 2.3247 | 12.66 | 1000 | 2.2919 | 0.4252 |
| 2.3247 | 15.19 | 1200 | 2.2747 | 0.4268 |
| 2.3247 | 17.72 | 1400 | 2.2633 | 0.4506 |
| 2.2349 | 20.25 | 1600 | 2.2563 | 0.4861 |
| 2.2349 | 22.78 | 1800 | 2.2486 | 0.4783 |
| 2.1924 | 25.32 | 2000 | 2.2471 | 0.4736 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0