metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- kde4
model-index:
- name: google-t5base-finetuned-iswlt2017-en-to-fr
results: []
google-t5base-finetuned-iswlt2017-en-to-fr
This model is a fine-tuned version of t5-base on the kde4 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7606
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9744 | 1.0 | 5912 | 0.8201 |
| 0.8671 | 2.0 | 11824 | 0.7727 |
| 0.8578 | 3.0 | 17736 | 0.7606 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.13.3