my_French_Dyula_t5_small_model
This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8634
- Bleu: 0.006
- Gen Len: 15.3039
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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 | 253 | 2.9381 | 0.0037 | 15.5806 |
| 3.1498 | 2.0 | 506 | 2.9202 | 0.0039 | 15.5221 |
| 3.1498 | 3.0 | 759 | 2.9053 | 0.0047 | 15.4942 |
| 3.1228 | 4.0 | 1012 | 2.8931 | 0.0047 | 15.6193 |
| 3.1228 | 5.0 | 1265 | 2.8840 | 0.0049 | 15.3963 |
| 3.1021 | 6.0 | 1518 | 2.8759 | 0.0049 | 15.412 |
| 3.1021 | 7.0 | 1771 | 2.8705 | 0.0051 | 15.3651 |
| 3.0913 | 8.0 | 2024 | 2.8665 | 0.0052 | 15.3372 |
| 3.0913 | 9.0 | 2277 | 2.8641 | 0.006 | 15.3338 |
| 3.0785 | 10.0 | 2530 | 2.8634 | 0.006 | 15.3039 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1