flan-t5-small-gigatrue
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: 2.1229
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 |
|---|---|---|---|
| 2.5659 | 0.2030 | 3000 | 2.1724 |
| 2.4802 | 0.4059 | 6000 | 2.1500 |
| 2.4581 | 0.6089 | 9000 | 2.1390 |
| 2.4493 | 0.8119 | 12000 | 2.1325 |
| 2.4436 | 1.0148 | 15000 | 2.1282 |
| 2.4398 | 1.2178 | 18000 | 2.1255 |
| 2.437 | 1.4207 | 21000 | 2.1246 |
| 2.434 | 1.6237 | 24000 | 2.1246 |
| 2.4337 | 1.8267 | 27000 | 2.1226 |
| 2.4337 | 2.0296 | 30000 | 2.1228 |
| 2.4314 | 2.2326 | 33000 | 2.1234 |
| 2.4332 | 2.4356 | 36000 | 2.1232 |
| 2.4327 | 2.6385 | 39000 | 2.1230 |
| 2.4329 | 2.8415 | 42000 | 2.1229 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1
- Datasets 3.2.0
- Tokenizers 0.20.3