job-salary-classifier

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

• Loss: 0.2494
• F1: 0.6873
• Roc Auc: 0.8006
• Accuracy: 0.6494

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
No log	1.0	39	0.3015	0.4057	0.6299	0.2792
No log	2.0	78	0.2932	0.5674	0.7286	0.5195
No log	3.0	117	0.2666	0.6494	0.7669	0.5714
No log	4.0	156	0.2524	0.7010	0.8084	0.6623
No log	5.0	195	0.2509	0.6990	0.8058	0.6558
No log	6.0	234	0.2497	0.7103	0.8130	0.6688
No log	7.0	273	0.2494	0.6873	0.8006	0.6494

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0