distilbert-base-uncased__sst5__all-train
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3757
- Accuracy: 0.5045
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: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2492 | 1.0 | 534 | 1.1163 | 0.4991 |
| 0.9937 | 2.0 | 1068 | 1.1232 | 0.5122 |
| 0.7867 | 3.0 | 1602 | 1.2097 | 0.5045 |
| 0.595 | 4.0 | 2136 | 1.3757 | 0.5045 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.1+cu102
- Datasets 1.17.0
- Tokenizers 0.10.3