heladepdet-bert-finetuned-regression

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

• Loss: 0.6639
• Mse: 0.6639

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Mse
1.4680	0.2867	250	0.9677	0.9677
0.8882	0.5734	500	0.7899	0.7899
0.7866	0.8601	750	0.7758	0.7758
0.7515	1.1468	1000	0.7578	0.7578
0.7517	1.4335	1250	0.7260	0.7260
0.7112	1.7202	1500	0.7218	0.7218
0.7080	2.0069	1750	0.6934	0.6934
0.6909	2.2936	2000	0.6857	0.6857
0.6876	2.5803	2250	0.6841	0.6841
0.6578	2.8670	2500	0.6750	0.6750
0.7028	3.1537	2750	0.6668	0.6668
0.6558	3.4404	3000	0.6734	0.6734
0.6618	3.7271	3250	0.6646	0.6646
0.6546	4.0138	3500	0.6613	0.6613
0.6457	4.3005	3750	0.6693	0.6693
0.6672	4.5872	4000	0.6639	0.6639
0.6495	4.8739	4250	0.6639	0.6639

Framework versions

• PEFT 0.18.1
• Transformers 5.2.0
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.2