my_awesome_opus_books_model
This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 6.4338
- Bleu: 0.0654
- Gen Len: 19.0
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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
No log | 1.0 | 4 | 7.6017 | 0.2472 | 19.0 |
No log | 2.0 | 8 | 7.2626 | 0.2544 | 19.0 |
No log | 3.0 | 12 | 7.1078 | 0.2397 | 19.0 |
No log | 4.0 | 16 | 6.8611 | 0.1494 | 19.0 |
No log | 5.0 | 20 | 6.7383 | 0.1375 | 19.0 |
No log | 6.0 | 24 | 6.6216 | 0.0553 | 19.0 |
No log | 7.0 | 28 | 6.5373 | 0.0555 | 19.0 |
No log | 8.0 | 32 | 6.4807 | 0.0534 | 19.0 |
No log | 9.0 | 36 | 6.4465 | 0.0654 | 19.0 |
No log | 10.0 | 40 | 6.4338 | 0.0654 | 19.0 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 1