bert-large-cased-bn-adapter-3.17M-snli-model2

This model is a fine-tuned version of bert-large-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7747
• Accuracy: 0.731

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: 64
• eval_batch_size: 64
• seed: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4017	1.0	8584	0.3327	0.8763
0.3769	2.0	17168	0.3069	0.8881
0.3641	3.0	25752	0.3005	0.8895

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0