lenate_model_12_albert-base-v2
This model is a fine-tuned version of albert/albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5494
- Accuracy: 0.7622
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 355 | 0.6467 | 0.7212 |
| 0.7746 | 2.0 | 710 | 0.5847 | 0.7241 |
| 0.5448 | 3.0 | 1065 | 0.5494 | 0.7622 |
| 0.5448 | 4.0 | 1420 | 0.6416 | 0.7368 |
| 0.3705 | 5.0 | 1775 | 0.6439 | 0.7735 |
| 0.2112 | 6.0 | 2130 | 0.8791 | 0.7643 |
| 0.2112 | 7.0 | 2485 | 1.1350 | 0.7657 |
| 0.1012 | 8.0 | 2840 | 1.3247 | 0.7721 |
| 0.0294 | 9.0 | 3195 | 1.4469 | 0.7699 |
| 0.0112 | 10.0 | 3550 | 1.4783 | 0.7699 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2