albert-large-v2_cls_sst2
This model is a fine-tuned version of albert-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3582
- Accuracy: 0.9300
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: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 433 | 0.3338 | 0.8933 |
| 0.3977 | 2.0 | 866 | 0.2406 | 0.9197 |
| 0.2954 | 3.0 | 1299 | 0.2865 | 0.9278 |
| 0.2196 | 4.0 | 1732 | 0.3251 | 0.9243 |
| 0.1105 | 5.0 | 2165 | 0.3582 | 0.9300 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1