google-flan-t5-small-modified_v2
This model is a fine-tuned version of google/flan-t5-small on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 1.3020
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: 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 |
|---|---|---|---|
| No log | 1.0 | 250 | 3.7751 |
| 4.3074 | 2.0 | 500 | 2.1221 |
| 4.3074 | 3.0 | 750 | 1.7130 |
| 2.5366 | 4.0 | 1000 | 1.5271 |
| 2.5366 | 5.0 | 1250 | 1.4301 |
| 2.0483 | 6.0 | 1500 | 1.3643 |
| 2.0483 | 7.0 | 1750 | 1.3389 |
| 1.8774 | 8.0 | 2000 | 1.3123 |
| 1.8774 | 9.0 | 2250 | 1.3067 |
| 1.7724 | 10.0 | 2500 | 1.3020 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3