metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: t5-small-finetuned-en-to-fr
results: []
t5-small-finetuned-en-to-fr
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0063
- Bleu: 42.1181
- Gen Len: 8.6667
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 1 | 2.6488 | 21.9728 | 9.0 |
| No log | 2.0 | 2 | 2.5827 | 21.9728 | 9.0 |
| No log | 3.0 | 3 | 2.5204 | 21.9728 | 9.0 |
| No log | 4.0 | 4 | 2.4619 | 31.7783 | 9.0 |
| No log | 5.0 | 5 | 2.4063 | 31.7783 | 9.0 |
| No log | 6.0 | 6 | 2.3545 | 31.7783 | 9.0 |
| No log | 7.0 | 7 | 2.3044 | 32.857 | 9.0 |
| No log | 8.0 | 8 | 2.2592 | 32.857 | 9.0 |
| No log | 9.0 | 9 | 2.2182 | 32.857 | 9.0 |
| No log | 10.0 | 10 | 2.1816 | 32.857 | 9.0 |
| No log | 11.0 | 11 | 2.1476 | 32.857 | 9.0 |
| No log | 12.0 | 12 | 2.1175 | 32.857 | 9.0 |
| No log | 13.0 | 13 | 2.0914 | 32.857 | 9.0 |
| No log | 14.0 | 14 | 2.0696 | 32.857 | 9.0 |
| No log | 15.0 | 15 | 2.0510 | 44.7214 | 8.3333 |
| No log | 16.0 | 16 | 2.0357 | 44.7214 | 8.3333 |
| No log | 17.0 | 17 | 2.0238 | 44.7214 | 8.3333 |
| No log | 18.0 | 18 | 2.0150 | 44.7214 | 8.3333 |
| No log | 19.0 | 19 | 2.0092 | 44.7214 | 8.3333 |
| No log | 20.0 | 20 | 2.0063 | 42.1181 | 8.6667 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.0.1
- Datasets 2.13.0
- Tokenizers 0.13.2