distilbert_sa_GLUE_Experiment_logit_kd_data_aug_qnli_96
This model is a fine-tuned version of distilbert-base-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.4386
- Accuracy: 0.5578
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 |
|---|---|---|---|---|
| 0.3496 | 1.0 | 16604 | 0.4386 | 0.5578 |
| 0.3031 | 2.0 | 33208 | 0.4636 | 0.5607 |
| 0.281 | 3.0 | 49812 | 0.4565 | 0.5576 |
| 0.2682 | 4.0 | 66416 | 0.4627 | 0.5647 |
| 0.2596 | 5.0 | 83020 | 0.4572 | 0.5768 |
| 0.2533 | 6.0 | 99624 | 0.4660 | 0.5753 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.