<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
xinyixiuxiu/albert-base-v2-SST2-finetuned-try
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2727
- Train Accuracy: 0.8880
- Validation Loss: 0.4356
- Validation Accuracy: 0.8349
- Epoch: 3
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:
- optimizer: {'name': 'Adam', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.6649 | 0.5880 | 0.5779 | 0.7534 | 0 |
| 0.4569 | 0.8060 | 0.3749 | 0.8658 | 1 |
| 0.3264 | 0.8730 | 0.3876 | 0.8429 | 2 |
| 0.2727 | 0.8880 | 0.4356 | 0.8349 | 3 |
Framework versions
- Transformers 4.21.1
- TensorFlow 2.7.0
- Datasets 2.10.1
- Tokenizers 0.12.1
