Regression_bert_2

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.8766
• Mse: 3.8766
• Mae: 1.3858
• R2: -1.0002
• Accuracy: 0.5714

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	R2	Accuracy
No log	1.0	1	3.5920	3.5920	1.5846	-2.3703	0.2857
No log	2.0	2	3.3981	3.3981	1.5187	-2.1884	0.2857
No log	3.0	3	3.2200	3.2200	1.4559	-2.0213	0.2857
No log	4.0	4	3.0496	3.0496	1.3924	-1.8614	0.4286
No log	5.0	5	2.8847	2.8847	1.3402	-1.7067	0.4286
No log	6.0	6	2.7261	2.7261	1.2955	-1.5579	0.4286
No log	7.0	7	2.5772	2.5772	1.2590	-1.4182	0.4286
No log	8.0	8	2.4361	2.4361	1.2302	-1.2858	0.4286
No log	9.0	9	2.3055	2.3055	1.2027	-1.1632	0.4286
No log	10.0	10	2.1844	2.1844	1.1765	-1.0496	0.4286
No log	11.0	11	2.0725	2.0725	1.1546	-0.9446	0.4286
No log	12.0	12	1.9723	1.9723	1.1457	-0.8506	0.4286
No log	13.0	13	1.8851	1.8851	1.1381	-0.7688	0.4286
No log	14.0	14	1.8103	1.8103	1.1315	-0.6985	0.2857
No log	15.0	15	1.7472	1.7472	1.1258	-0.6394	0.2857
No log	16.0	16	1.6959	1.6959	1.1211	-0.5912	0.2857
No log	17.0	17	1.6558	1.6558	1.1174	-0.5536	0.2857
No log	18.0	18	1.6262	1.6262	1.1146	-0.5259	0.2857
No log	19.0	19	1.6067	1.6067	1.1128	-0.5076	0.2857
No log	20.0	20	1.5970	1.5970	1.1118	-0.4984	0.2857

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2