metadata
library_name: transformers
license: apache-2.0
base_model: google-t5/t5-base
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: t5-base-spanish-yoremnokki
results: []
t5-base-spanish-yoremnokki
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: 1.7824
- Bleu: 12.9294
- Gen Len: 14.0092
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 3.4916 | 0.9994 | 846 | 2.3536 | 0.21 | 14.4369 |
| 2.4194 | 2.0 | 1693 | 2.0655 | 2.0366 | 13.9808 |
| 2.1821 | 2.9994 | 2539 | 1.9102 | 7.286 | 14.0406 |
| 2.1132 | 4.0 | 3386 | 1.8290 | 12.0392 | 14.003 |
| 2.0125 | 4.9994 | 4232 | 1.7935 | 12.8393 | 14.01 |
| 1.9896 | 5.9965 | 5076 | 1.7824 | 12.9294 | 14.0092 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1