bert-cvs-estimation-years-experience

This model is a fine-tuned version of jhonparra18/bert-base-cased-cv-studio_name-medium on the None dataset. It achieves the following results on the evaluation set:

• Loss: 9.4494
• Mse: 9.4494
• Mae: 2.0686
• R2: 0.4131
• Accuracy: 0.2586

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 20
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	R2	Accuracy
No log	10.34	300	10.5131	10.5131	2.2140	0.3470	0.2759
3.3802	20.69	600	9.1915	9.1915	2.0780	0.4291	0.2759
3.3802	31.03	900	8.8261	8.8261	1.9359	0.4518	0.2931
0.1613	41.38	1200	9.4494	9.4494	2.0686	0.4131	0.2586

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.0+cu102
• Datasets 2.4.0
• Tokenizers 0.12.1