bert-base-uncased-finetuned-clinc_oos

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

• Loss: 0.7744
• Accuracy: {'accuracy': 0.932258064516129}
• F1: {'f1': 0.9301680056033511}

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
4.2947	1.0	954	2.1707	{'accuracy': 0.8312903225806452}	{'f1': 0.8144079203282508}
1.7379	2.0	1908	1.0298	{'accuracy': 0.9209677419354839}	{'f1': 0.9177062984730477}
0.8752	3.0	2862	0.7744	{'accuracy': 0.932258064516129}	{'f1': 0.9301680056033511}

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.0