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: 0.3196
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 |
|---|---|---|---|
| 40.04 | 0.18 | 10 | 30.2044 |
| 28.2106 | 0.36 | 20 | 22.6394 |
| 22.4239 | 0.55 | 30 | 16.8570 |
| 17.149 | 0.73 | 40 | 10.1178 |
| 11.379 | 0.91 | 50 | 5.1010 |
| 6.6773 | 1.09 | 60 | 4.7149 |
| 5.0559 | 1.27 | 70 | 4.4758 |
| 4.6474 | 1.45 | 80 | 4.2656 |
| 4.3934 | 1.64 | 90 | 3.9831 |
| 4.1421 | 1.82 | 100 | 3.6196 |
| 3.9066 | 2.0 | 110 | 3.0985 |
| 3.5465 | 2.18 | 120 | 2.4730 |
| 3.1722 | 2.36 | 130 | 1.8153 |
| 2.8787 | 2.55 | 140 | 1.5002 |
| 2.564 | 2.73 | 150 | 1.1748 |
| 2.296 | 2.91 | 160 | 0.9380 |
| 2.135 | 3.09 | 170 | 0.7860 |
| 1.9049 | 3.27 | 180 | 0.6740 |
| 1.7388 | 3.45 | 190 | 0.5633 |
| 1.5868 | 3.64 | 200 | 0.4853 |
| 1.5128 | 3.82 | 210 | 0.4449 |
| 1.3889 | 4.0 | 220 | 0.4066 |
| 1.3273 | 4.18 | 230 | 0.3800 |
| 1.2965 | 4.36 | 240 | 0.3589 |
| 1.1939 | 4.55 | 250 | 0.3389 |
| 1.2203 | 4.73 | 260 | 0.3254 |
| 1.1422 | 4.91 | 270 | 0.3196 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2