| language: en | |
| license: mit | |
| tags: | |
| - deberta-v1 | |
| - deberta-mnli | |
| tasks: mnli | |
| thumbnail: https://huggingface.co./front/thumbnails/microsoft.png | |
| pipeline_tag: zero-shot-classification | |
| base_model: microsoft/deberta-v3-large | |
| This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co./microsoft/deberta-v3-large) on the GLUE MNLI dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.4103 | |
| - Accuracy: 0.9175 | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 6e-06 | |
| - train_batch_size: 8 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - lr_scheduler_warmup_steps: 50 | |
| - num_epochs: 2.0 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | | |
| |:-------------:|:-----:|:-----:|:---------------:|:--------:| | |
| | 0.3631 | 1.0 | 49088 | 0.3129 | 0.9130 | | |
| | 0.2267 | 2.0 | 98176 | 0.4157 | 0.9153 | | |
| ### Framework versions | |
| - Transformers 4.13.0.dev0 | |
| - Pytorch 1.10.0 | |
| - Datasets 1.15.2.dev0 | |
| - Tokenizers 0.10.3 | |