metadata
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
model-index:
- name: ingredient_prune
results: []
ingredient_prune
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2171
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 38.6247 | 0.18 | 10 | 28.2426 |
| 26.1854 | 0.36 | 20 | 20.2002 |
| 19.6623 | 0.55 | 30 | 13.6317 |
| 13.5288 | 0.73 | 40 | 6.1384 |
| 7.0646 | 0.91 | 50 | 4.3907 |
| 4.6726 | 1.09 | 60 | 4.1267 |
| 4.2044 | 1.27 | 70 | 3.8144 |
| 3.9212 | 1.45 | 80 | 3.4817 |
| 3.6409 | 1.64 | 90 | 2.9574 |
| 3.2497 | 1.82 | 100 | 2.0126 |
| 2.8668 | 2.0 | 110 | 1.5548 |
| 2.5591 | 2.18 | 120 | 1.3483 |
| 2.2817 | 2.36 | 130 | 0.9596 |
| 2.0322 | 2.55 | 140 | 0.7737 |
| 1.7896 | 2.73 | 150 | 0.6418 |
| 1.5978 | 2.91 | 160 | 0.5350 |
| 1.4263 | 3.09 | 170 | 0.4166 |
| 1.3053 | 3.27 | 180 | 0.3914 |
| 1.1636 | 3.45 | 190 | 0.3543 |
| 1.0639 | 3.64 | 200 | 0.3054 |
| 1.0036 | 3.82 | 210 | 0.2860 |
| 0.9076 | 4.0 | 220 | 0.2683 |
| 0.8769 | 4.18 | 230 | 0.2524 |
| 0.8282 | 4.36 | 240 | 0.2333 |
| 0.8092 | 4.55 | 250 | 0.2233 |
| 0.771 | 4.73 | 260 | 0.2198 |
| 0.7718 | 4.91 | 270 | 0.2171 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2