checkpoint-finetuned-stationary-update
This model is a fine-tuned version of google/electra-base-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6818
- Accuracy: 0.8067
- F1: 0.8027
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 |
|---|---|---|---|---|---|
| 0.5971 | 1.0 | 38 | 0.5642 | 0.72 | 0.6533 |
| 0.4759 | 2.0 | 76 | 0.4484 | 0.7633 | 0.7670 |
| 0.3768 | 3.0 | 114 | 0.4491 | 0.8033 | 0.7924 |
| 0.2983 | 4.0 | 152 | 0.4333 | 0.82 | 0.8175 |
| 0.2111 | 5.0 | 190 | 0.5193 | 0.8067 | 0.7990 |
| 0.1627 | 6.0 | 228 | 0.5407 | 0.8133 | 0.8101 |
| 0.1285 | 7.0 | 266 | 0.6347 | 0.7933 | 0.7823 |
| 0.0966 | 8.0 | 304 | 0.6961 | 0.8067 | 0.7973 |
| 0.0879 | 9.0 | 342 | 0.6972 | 0.8133 | 0.8042 |
| 0.0673 | 10.0 | 380 | 0.6818 | 0.8067 | 0.8027 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0