--- license: apache-2.0 tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: albert-xlarge-v2-finetuned-wnli results: - task: name: Text Classification type: text-classification dataset: name: glue type: glue args: wnli metrics: - name: Accuracy type: accuracy value: 0.5774647887323944 --- # albert-xlarge-v2-finetuned-wnli This model is a fine-tuned version of [albert-xlarge-v2](https://huggingface.co/albert-xlarge-v2) on the glue dataset. It achieves the following results on the evaluation set: - Loss: 0.6986 - Accuracy: 0.5775 ## 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: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 40 | 0.6827 | 0.5634 | | No log | 2.0 | 80 | 0.7022 | 0.5634 | | No log | 3.0 | 120 | 0.6865 | 0.5493 | | No log | 4.0 | 160 | 0.7093 | 0.5070 | | No log | 5.0 | 200 | 0.6986 | 0.5775 | ### Framework versions - Transformers 4.15.0 - Pytorch 1.10.0+cu111 - Datasets 1.18.0 - Tokenizers 0.10.3