NLPGroupProject-Finetune-FNet
This model is a fine-tuned version of google/fnet-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1397
- Accuracy: 0.661
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- 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 | Accuracy |
|---|---|---|---|---|
| 1.2489 | 0.25 | 500 | 1.1166 | 0.601 |
| 1.0966 | 0.5 | 1000 | 0.9805 | 0.6 |
| 1.0379 | 0.75 | 1500 | 1.0110 | 0.624 |
| 0.9708 | 1.0 | 2000 | 0.9348 | 0.633 |
| 0.891 | 1.25 | 2500 | 1.1107 | 0.622 |
| 0.948 | 1.5 | 3000 | 1.0165 | 0.656 |
| 0.9148 | 1.75 | 3500 | 1.0472 | 0.655 |
| 0.969 | 2.0 | 4000 | 1.0291 | 0.65 |
| 0.855 | 2.25 | 4500 | 1.2743 | 0.635 |
| 0.8445 | 2.5 | 5000 | 1.1520 | 0.655 |
| 0.8057 | 2.75 | 5500 | 1.1107 | 0.662 |
| 0.7467 | 3.0 | 6000 | 1.1397 | 0.661 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1