distilbert-base-uncased-finetuned-clinc_oos

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

• Loss: 0.6012
• Accuracy: {'accuracy': 0.9248387096774193}
• F1: {'f1': 0.924017622321749}

Model Training Details

Parameter	Value
Task	text-classification
Base Model Name	distilbert-base-uncased
Dataset Name	clinc_oos
Dataset Config	plus
Batch Size	16
Number of Epochs	3
Learning Rate	0.00002

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
4.3563	1.0	954	2.0254	{'accuracy': 0.8274193548387097}	{'f1': 0.8157244857086648}
1.5387	2.0	1908	0.8120	{'accuracy': 0.9129032258064517}	{'f1': 0.9118433401777696}
0.6711	3.0	2862	0.6012	{'accuracy': 0.9248387096774193}	{'f1': 0.924017622321749}

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3