flan-t5-small-gigatrue-layercut-D456
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: 2.3793
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 |
|---|---|---|---|
| 2.9647 | 0.2030 | 3000 | 2.4360 |
| 2.8457 | 0.4059 | 6000 | 2.4086 |
| 2.8198 | 0.6089 | 9000 | 2.3927 |
| 2.8105 | 0.8119 | 12000 | 2.3875 |
| 2.804 | 1.0148 | 15000 | 2.3839 |
| 2.8004 | 1.2178 | 18000 | 2.3827 |
| 2.7983 | 1.4207 | 21000 | 2.3792 |
| 2.7954 | 1.6237 | 24000 | 2.3809 |
| 2.7946 | 1.8267 | 27000 | 2.3793 |
| 2.7941 | 2.0296 | 30000 | 2.3794 |
| 2.7934 | 2.2326 | 33000 | 2.3798 |
| 2.7954 | 2.4356 | 36000 | 2.3792 |
| 2.7945 | 2.6385 | 39000 | 2.3791 |
| 2.794 | 2.8415 | 42000 | 2.3793 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1
- Datasets 3.2.0
- Tokenizers 0.20.3