my_awesome_model_lite
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: 0.3163
- Accuracy: 0.8693
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3342 | 1.0 | 2599 | 0.3106 | 0.8419 |
| 0.3038 | 2.0 | 5198 | 0.2729 | 0.8622 |
| 0.2683 | 3.0 | 7797 | 0.2728 | 0.8596 |
| 0.2358 | 4.0 | 10396 | 0.2717 | 0.8690 |
| 0.1948 | 5.0 | 12995 | 0.3163 | 0.8693 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3