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: 0.5073
• Accuracy: 0.9444

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: 1e-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	54	2.2473	0.1019
No log	2.0	108	2.1669	0.5370
No log	3.0	162	2.0159	0.5370
No log	4.0	216	1.8393	0.5556
No log	5.0	270	1.6508	0.6667
No log	6.0	324	1.4806	0.7037
No log	7.0	378	1.3298	0.7593
No log	8.0	432	1.1826	0.8241
No log	9.0	486	1.0571	0.8611
1.7901	10.0	540	0.9303	0.8611
1.7901	11.0	594	0.8432	0.8889
1.7901	12.0	648	0.7697	0.9259
1.7901	13.0	702	0.6979	0.9352
1.7901	14.0	756	0.6440	0.9352
1.7901	15.0	810	0.6008	0.9352
1.7901	16.0	864	0.5666	0.9444
1.7901	17.0	918	0.5383	0.9444
1.7901	18.0	972	0.5220	0.9444
0.7773	19.0	1026	0.5114	0.9444
0.7773	20.0	1080	0.5073	0.9444

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1