distilbert-base-uncased-distilled-clinc

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: 1.5565
• Accuracy: 0.8265

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: 48
• eval_batch_size: 48
• 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
3.2743	1.0	318	2.5809	0.7310
2.2148	2.0	636	1.7909	0.8071
1.7065	3.0	954	1.5565	0.8265

Framework versions

• Transformers 4.21.0.dev0
• Pytorch 1.12.0
• Datasets 2.3.2
• Tokenizers 0.12.1