Albert-finetuned-stationary-update
This model is a fine-tuned version of albert-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7542
- Accuracy: 0.5967
- F1: 0.5862
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 |
|---|---|---|---|---|---|
| 0.3976 | 1.0 | 38 | 0.8830 | 0.6033 | 0.5849 |
| 0.3105 | 2.0 | 76 | 0.9030 | 0.63 | 0.5876 |
| 0.2256 | 3.0 | 114 | 1.2156 | 0.6333 | 0.6366 |
| 0.1788 | 4.0 | 152 | 1.3055 | 0.6 | 0.5857 |
| 0.161 | 5.0 | 190 | 1.2205 | 0.59 | 0.5808 |
| 0.1304 | 6.0 | 228 | 1.5496 | 0.5933 | 0.5804 |
| 0.1046 | 7.0 | 266 | 1.6266 | 0.59 | 0.5915 |
| 0.0966 | 8.0 | 304 | 1.6807 | 0.6033 | 0.5971 |
| 0.0649 | 9.0 | 342 | 1.7279 | 0.5967 | 0.5831 |
| 0.0697 | 10.0 | 380 | 1.7542 | 0.5967 | 0.5862 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0