flan-t5-small-gigatrue-AU-D-456
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5591
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: 256
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1476 | 0.2030 | 3000 | 2.6159 |
| 3.0318 | 0.4059 | 6000 | 2.5882 |
| 3.0079 | 0.6089 | 9000 | 2.5750 |
| 3.0 | 0.8119 | 12000 | 2.5675 |
| 2.9932 | 1.0148 | 15000 | 2.5650 |
| 2.9891 | 1.2178 | 18000 | 2.5632 |
| 2.9869 | 1.4207 | 21000 | 2.5603 |
| 2.9846 | 1.6237 | 24000 | 2.5608 |
| 2.9831 | 1.8267 | 27000 | 2.5591 |
| 2.9832 | 2.0296 | 30000 | 2.5592 |
| 2.9811 | 2.2326 | 33000 | 2.5591 |
| 2.9841 | 2.4356 | 36000 | 2.5594 |
| 2.9836 | 2.6385 | 39000 | 2.5589 |
| 2.9827 | 2.8415 | 42000 | 2.5591 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1
- Datasets 3.2.0
- Tokenizers 0.20.3