metadata
license: apache-2.0
base_model: google/flan-t5-small
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: flan-t5-small-proverb-es-classification-neg-trigrams-sentences
results: []
flan-t5-small-proverb-es-classification-neg-trigrams-sentences
This model is a fine-tuned version of google/flan-t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0415
- F1: 94.7024
- Gen Len: 7.5583
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: 0.0003
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Gen Len |
|---|---|---|---|---|---|
| 0.0469 | 1.0 | 1466 | 0.0261 | 91.8196 | 7.5107 |
| 0.0247 | 2.0 | 2932 | 0.0230 | 93.6082 | 7.5334 |
| 0.018 | 3.0 | 4398 | 0.0208 | 93.6748 | 7.5418 |
| 0.0128 | 4.0 | 5864 | 0.0220 | 94.0879 | 7.5522 |
| 0.0091 | 5.0 | 7330 | 0.0274 | 94.2632 | 7.5656 |
| 0.0066 | 6.0 | 8796 | 0.0280 | 94.2282 | 7.5629 |
| 0.0049 | 7.0 | 10262 | 0.0345 | 94.6363 | 7.5491 |
| 0.0033 | 8.0 | 11728 | 0.0399 | 94.5434 | 7.5606 |
| 0.0029 | 9.0 | 13194 | 0.0412 | 94.6728 | 7.5510 |
| 0.0021 | 10.0 | 14660 | 0.0415 | 94.7024 | 7.5583 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.19.1