metadata
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: german-spanglish
results: []
german-spanglish
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1288
- Bleu: 3.4941
- Gen Len: 13.975
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: 16
- 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 | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.7115 | 1.0 | 10 | 2.3293 | 0.9472 | 14.325 |
| 2.6497 | 2.0 | 20 | 2.2775 | 2.3123 | 14.15 |
| 2.6046 | 3.0 | 30 | 2.2373 | 2.3261 | 14.075 |
| 2.5411 | 4.0 | 40 | 2.2051 | 2.3386 | 14.05 |
| 2.5299 | 5.0 | 50 | 2.1819 | 2.3366 | 14.125 |
| 2.5496 | 6.0 | 60 | 2.1625 | 2.3345 | 14.175 |
| 2.5261 | 7.0 | 70 | 2.1473 | 3.0654 | 14.075 |
| 2.4913 | 8.0 | 80 | 2.1372 | 3.4941 | 13.975 |
| 2.4596 | 9.0 | 90 | 2.1310 | 3.4941 | 13.975 |
| 2.4372 | 10.0 | 100 | 2.1288 | 3.4941 | 13.975 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1