distilbert-base-uncased-finetuned-clinc

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: nan
• Accuracy: 0.9410

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: 192
• eval_batch_size: 192
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	80	nan	0.4606
No log	2.0	160	nan	0.7219
No log	3.0	240	nan	0.8071
No log	4.0	320	nan	0.8626
No log	5.0	400	nan	0.8858
No log	6.0	480	nan	0.9103
0.0	7.0	560	nan	0.9216
0.0	8.0	640	nan	0.9268
0.0	9.0	720	nan	0.9294
0.0	10.0	800	nan	0.9345
0.0	11.0	880	nan	0.9345
0.0	12.0	960	nan	0.9387
0.0	13.0	1040	nan	0.9390
0.0	14.0	1120	nan	0.9403
0.0	15.0	1200	nan	0.9419
0.0	16.0	1280	nan	0.9406
0.0	17.0	1360	nan	0.94
0.0	18.0	1440	nan	0.9403
0.0	19.0	1520	nan	0.9413
0.0	20.0	1600	nan	0.9410

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2