autoevaluate/binary-classification-not-evaluated

1---2license: apache-2.03tags:4- generated_from_trainer5datasets:6- glue7---8 9<!-- This model card has been generated automatically according to the information the Trainer had access to. You10should probably proofread and complete it, then remove this comment. -->11 12# binary-classification13 14This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.15It achieves the following results on the evaluation set:16 17- Loss: 0.300918- Accuracy: 0.896819 20## Model description21 22More information needed23 24## Intended uses & limitations25 26More information needed27 28## Training and evaluation data29 30More information needed31 32## Training procedure33 34### Training hyperparameters35 36The following hyperparameters were used during training:37- learning_rate: 2e-0538- train_batch_size: 1639- eval_batch_size: 1640- seed: 4241- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0842- lr_scheduler_type: linear43- num_epochs: 144 45### Training results46 47| Training Loss | Epoch | Step | Validation Loss | Accuracy |48|:-------------:|:-----:|:----:|:---------------:|:--------:|49| 0.175         | 1.0   | 4210 | 0.3009          | 0.8968   |50 51 52### Framework versions53 54- Transformers 4.19.255- Pytorch 1.11.0+cu11356- Datasets 2.2.257- Tokenizers 0.12.158