<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
CR_ALBERT_5E
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3540
- Accuracy: 0.9267
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5091 | 0.33 | 50 | 0.3616 | 0.86 |
| 0.327 | 0.66 | 100 | 0.2728 | 0.9067 |
| 0.2836 | 0.99 | 150 | 0.2753 | 0.9133 |
| 0.1985 | 1.32 | 200 | 0.3048 | 0.9067 |
| 0.2098 | 1.66 | 250 | 0.2365 | 0.9267 |
| 0.2203 | 1.99 | 300 | 0.2369 | 0.9133 |
| 0.1491 | 2.32 | 350 | 0.3029 | 0.9267 |
| 0.1527 | 2.65 | 400 | 0.2475 | 0.9333 |
| 0.1327 | 2.98 | 450 | 0.1993 | 0.9533 |
| 0.0848 | 3.31 | 500 | 0.2112 | 0.9467 |
| 0.0857 | 3.64 | 550 | 0.2498 | 0.9467 |
| 0.089 | 3.97 | 600 | 0.3246 | 0.9333 |
| 0.0613 | 4.3 | 650 | 0.2834 | 0.9267 |
| 0.0355 | 4.64 | 700 | 0.3557 | 0.9333 |
| 0.0479 | 4.97 | 750 | 0.3540 | 0.9267 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.3.2
- Tokenizers 0.13.1
