distilbert-base-uncased-distilled-clinc2

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

• Loss: 0.2271
• Accuracy: 0.9565

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: 0.0002134538968230803
• train_batch_size: 192
• eval_batch_size: 48
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1.7007007109718952e-07
• lr_scheduler_type: linear
• num_epochs: 13

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	80	0.4718	0.8939
No log	2.0	160	0.2975	0.9361
No log	3.0	240	0.2616	0.9494
0.5682	4.0	320	0.2531	0.9465
0.5682	5.0	400	0.2412	0.9523
0.5682	6.0	480	0.2452	0.9474
0.5682	7.0	560	0.2388	0.9503
0.1756	8.0	640	0.2342	0.9523
0.1756	9.0	720	0.2289	0.9542
0.1756	10.0	800	0.2290	0.9545
0.1756	11.0	880	0.2261	0.9558
0.1648	12.0	960	0.2267	0.9558
0.1648	13.0	1040	0.2271	0.9565

Framework versions

• Transformers 4.44.2
• Pytorch 2.2.2+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1