metadata
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: translation_model
results: []
translation_model
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8461
- Bleu: 1.3828
- Gen Len: 18.0112
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.1283 | 1.0 | 4674 | 1.8698 | 1.3343 | 18.024 |
| 2.1211 | 2.0 | 9348 | 1.8516 | 1.3656 | 18.0194 |
| 2.1063 | 3.0 | 14022 | 1.8461 | 1.3828 | 18.0112 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1