distilbert-base-uncased-finetuned-clinc

This model is a fine-tuned version of patnelt60/distilbert-base-uncased-finetuned-clinc on the clinc_oos dataset. It achieves the following results on the evaluation set:

• Loss: 0.1904
• Accuracy: 0.9268

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: 384
• eval_batch_size: 384
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	0.4572	0.8619
No log	2.0	80	0.3775	0.8881
No log	3.0	120	0.3184	0.9013
No log	4.0	160	0.2753	0.9110
No log	5.0	200	0.2441	0.9187
No log	6.0	240	0.2224	0.9232
No log	7.0	280	0.2073	0.9248
0.3426	8.0	320	0.1982	0.9268
0.3426	9.0	360	0.1923	0.9265
0.3426	10.0	400	0.1904	0.9268

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0
• Datasets 2.14.6
• Tokenizers 0.13.3