bert-base-uncased-fine-tuned-on-clinc_oos-dataset

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: 1.2811
• Accuracy Score: 0.9239
• F1 Score: 0.9213

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: 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 Score	F1 Score
4.4271	1.0	239	3.5773	0.6116	0.5732
3.0415	2.0	478	2.4076	0.8390	0.8241
2.1182	3.0	717	1.7324	0.8994	0.8934
1.5897	4.0	956	1.3863	0.9210	0.9171
1.3458	5.0	1195	1.2811	0.9239	0.9213

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1