Funnel-finetuned-stationary-update
This model is a fine-tuned version of funnel-transformer/small-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6506
- Accuracy: 0.8267
- F1: 0.8212
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6307 | 1.0 | 38 | 0.5364 | 0.6667 | 0.5333 |
| 0.5143 | 2.0 | 76 | 0.4769 | 0.6667 | 0.5333 |
| 0.4497 | 3.0 | 114 | 0.5060 | 0.7567 | 0.7270 |
| 0.398 | 4.0 | 152 | 0.5025 | 0.8167 | 0.8082 |
| 0.3168 | 5.0 | 190 | 0.4550 | 0.8033 | 0.8072 |
| 0.2705 | 6.0 | 228 | 0.5615 | 0.8133 | 0.8034 |
| 0.2016 | 7.0 | 266 | 0.5831 | 0.83 | 0.8213 |
| 0.1492 | 8.0 | 304 | 0.6144 | 0.83 | 0.8243 |
| 0.1184 | 9.0 | 342 | 0.6269 | 0.82 | 0.8150 |
| 0.0935 | 10.0 | 380 | 0.6506 | 0.8267 | 0.8212 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0