bert-base-uncased-sst2

This model is a fine-tuned version of bert-base-cased on the SST-2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2671
• Accuracy: 0.9289

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 8