distilbert_sa_GLUE_Experiment_logit_kd_data_aug_rte_256
This model is a fine-tuned version of distilbert-base-uncased on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.5461
- Accuracy: 0.4982
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 |
|---|---|---|---|---|
| 0.3321 | 1.0 | 568 | 0.5461 | 0.4982 |
| 0.288 | 2.0 | 1136 | 0.5692 | 0.4910 |
| 0.2847 | 3.0 | 1704 | 0.5578 | 0.4982 |
| 0.283 | 4.0 | 2272 | 0.5487 | 0.4946 |
| 0.2822 | 5.0 | 2840 | 0.5564 | 0.4982 |
| 0.2813 | 6.0 | 3408 | 0.5508 | 0.5235 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2