bidirection_translate_model_fixed_v0.4
This model is a fine-tuned version of gshields/bidirection_translate_model_error_v0.4 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8249
- Bleu: 25.2648
- Gen Len: 9.9333
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 8 | 2.8372 | 24.625 | 10.2667 |
| No log | 2.0 | 16 | 2.8249 | 25.2648 | 9.9333 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3