metadata
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: my_awesome_opus_books_model
results: []
my_awesome_opus_books_model
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1992
- Bleu: 28.3023
- Gen Len: 19.2462
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.2241 | 1.0 | 5000 | 0.2021 | 27.6962 | 19.0758 |
| 0.192 | 2.0 | 10000 | 0.2011 | 27.6422 | 19.1986 |
| 0.1711 | 3.0 | 15000 | 0.2014 | 27.7687 | 19.2298 |
| 0.1516 | 4.0 | 20000 | 0.1999 | 28.0588 | 19.2006 |
| 0.1362 | 5.0 | 25000 | 0.1992 | 28.3023 | 19.2462 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1