metadata
library_name: transformers
license: apache-2.0
base_model: google-t5/t5-base
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: elvish-translator-quenya-t5-base
results: []
elvish-translator-quenya-t5-base
This model is a fine-tuned version of google-t5/t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4619
- Bleu: 0.3386
- Gen Len: 14.3889
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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|---|
| 4.5969 | 1.0 | 144 | 4.0271 | 0.1511 | 14.5278 |
| 4.1388 | 2.0 | 288 | 3.8283 | 0.1435 | 15.3819 |
| 3.9458 | 3.0 | 432 | 3.7158 | 0.2337 | 13.2639 |
| 3.808 | 4.0 | 576 | 3.6417 | 0.2594 | 14.0278 |
| 3.7546 | 5.0 | 720 | 3.5761 | 0.295 | 14.7639 |
| 3.6707 | 6.0 | 864 | 3.5284 | 0.2913 | 15.2986 |
| 3.6004 | 7.0 | 1008 | 3.4973 | 0.3018 | 14.9861 |
| 3.5505 | 8.0 | 1152 | 3.4758 | 0.3043 | 14.7431 |
| 3.5129 | 9.0 | 1296 | 3.4659 | 0.3296 | 14.4792 |
| 3.5232 | 10.0 | 1440 | 3.4619 | 0.3386 | 14.3889 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.2.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1