distilbert_sa_GLUE_Experiment_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: 0.9096
- Accuracy: 0.5702
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 |
---|---|---|---|---|
0.5397 | 1.0 | 16604 | 0.9096 | 0.5702 |
0.3675 | 2.0 | 33208 | 1.0680 | 0.5596 |
0.2735 | 3.0 | 49812 | 1.1893 | 0.5653 |
0.2174 | 4.0 | 66416 | 1.2806 | 0.5643 |
0.1795 | 5.0 | 83020 | 1.4118 | 0.5649 |
0.1514 | 6.0 | 99624 | 1.4578 | 0.5662 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 3
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.