flan-t5-small-gigatrue-AU
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: 2.3317
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 |
|---|---|---|---|
| 2.7986 | 0.2030 | 3000 | 2.3800 |
| 2.7128 | 0.4059 | 6000 | 2.3597 |
| 2.691 | 0.6089 | 9000 | 2.3485 |
| 2.6832 | 0.8119 | 12000 | 2.3407 |
| 2.6763 | 1.0148 | 15000 | 2.3388 |
| 2.6714 | 1.2178 | 18000 | 2.3344 |
| 2.6693 | 1.4207 | 21000 | 2.3336 |
| 2.6672 | 1.6237 | 24000 | 2.3340 |
| 2.6654 | 1.8267 | 27000 | 2.3320 |
| 2.6655 | 2.0296 | 30000 | 2.3318 |
| 2.6628 | 2.2326 | 33000 | 2.3321 |
| 2.666 | 2.4356 | 36000 | 2.3318 |
| 2.6666 | 2.6385 | 39000 | 2.3315 |
| 2.665 | 2.8415 | 42000 | 2.3317 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1
- Datasets 3.2.0
- Tokenizers 0.20.3