distilbert_sa_GLUE_Experiment_logit_kd_wnli_256
This model is a fine-tuned version of distilbert-base-uncased on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.3436
- Accuracy: 0.5634
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- distributed_type: multi-GPU
- 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 |
|---|---|---|---|---|
| 0.3511 | 1.0 | 3 | 0.3436 | 0.5634 |
| 0.3479 | 2.0 | 6 | 0.3457 | 0.5634 |
| 0.3474 | 3.0 | 9 | 0.3462 | 0.5634 |
| 0.3477 | 4.0 | 12 | 0.3442 | 0.5634 |
| 0.3486 | 5.0 | 15 | 0.3442 | 0.5634 |
| 0.3479 | 6.0 | 18 | 0.3455 | 0.5634 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2