my_first_translator_with_flan_t5_small
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0731
- Bleu: 9.6394
- Gen Len: 19.7632
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 67 | 2.2736 | 10.1762 | 19.6842 |
| No log | 2.0 | 134 | 2.1891 | 9.7753 | 19.718 |
| No log | 3.0 | 201 | 2.1426 | 9.3646 | 19.7444 |
| No log | 4.0 | 268 | 2.1094 | 9.244 | 19.7594 |
| No log | 5.0 | 335 | 2.0922 | 9.4982 | 19.7444 |
| No log | 6.0 | 402 | 2.0810 | 9.5297 | 19.7556 |
| No log | 7.0 | 469 | 2.0752 | 9.6427 | 19.7632 |
| 2.555 | 8.0 | 536 | 2.0731 | 9.6394 | 19.7632 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.6.0+cpu
- Datasets 3.2.0
- Tokenizers 0.21.0