interview_classifier

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0840
• Accuracy: 0.9682

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: 2
• eval_batch_size: 2
• 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	79	2.2062	0.2739
No log	2.0	158	2.0045	0.4076
No log	3.0	237	1.6355	0.5414
No log	4.0	316	1.2068	0.6624
No log	5.0	395	0.7999	0.8408
No log	6.0	474	0.5501	0.8917
1.5743	7.0	553	0.3843	0.9299
1.5743	8.0	632	0.2837	0.9427
1.5743	9.0	711	0.2162	0.9554
1.5743	10.0	790	0.1692	0.9682
1.5743	11.0	869	0.1464	0.9682
1.5743	12.0	948	0.1195	0.9682
0.2976	13.0	1027	0.1085	0.9682
0.2976	14.0	1106	0.0934	0.9682
0.2976	15.0	1185	0.0940	0.9682
0.2976	16.0	1264	0.0869	0.9682
0.2976	17.0	1343	0.0844	0.9682
0.2976	18.0	1422	0.0844	0.9682
0.1102	19.0	1501	0.0822	0.9682
0.1102	20.0	1580	0.0840	0.9682

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1