flan-t5-small-gigatrue-AI
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: 2.2957
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 |
|---|---|---|---|
| 2.7717 | 0.2030 | 3000 | 2.3464 |
| 2.6786 | 0.4059 | 6000 | 2.3242 |
| 2.6556 | 0.6089 | 9000 | 2.3117 |
| 2.6474 | 0.8119 | 12000 | 2.3046 |
| 2.6412 | 1.0148 | 15000 | 2.3025 |
| 2.6352 | 1.2178 | 18000 | 2.2994 |
| 2.6334 | 1.4207 | 21000 | 2.2974 |
| 2.6313 | 1.6237 | 24000 | 2.2974 |
| 2.629 | 1.8267 | 27000 | 2.2972 |
| 2.6292 | 2.0296 | 30000 | 2.2963 |
| 2.6262 | 2.2326 | 33000 | 2.2963 |
| 2.6296 | 2.4356 | 36000 | 2.2964 |
| 2.63 | 2.6385 | 39000 | 2.2954 |
| 2.6285 | 2.8415 | 42000 | 2.2957 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1
- Datasets 3.2.0
- Tokenizers 0.20.3