bert-petco-text_content-ctr

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

• Loss: 0.0034
• Mse: 0.0034
• Rmse: 0.0586
• Mae: 0.0408
• R2: 0.4036
• Accuracy: 0.6833

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	Rmse	Mae	R2	Accuracy
0.0239	1.0	15	0.0049	0.0049	0.0701	0.0519	0.1473	0.5833
0.0095	2.0	30	0.0047	0.0047	0.0688	0.0537	0.1774	0.5667
0.0071	3.0	45	0.0057	0.0057	0.0756	0.0643	0.0065	0.4
0.0062	4.0	60	0.0046	0.0046	0.0675	0.0544	0.2089	0.5
0.0058	5.0	75	0.0048	0.0048	0.0692	0.0495	0.1682	0.6833
0.0048	6.0	90	0.0046	0.0046	0.0678	0.0543	0.2014	0.5
0.0042	7.0	105	0.0039	0.0039	0.0621	0.0465	0.3295	0.6833
0.0034	8.0	120	0.0038	0.0038	0.0617	0.0444	0.3382	0.6667
0.0031	9.0	135	0.0040	0.0040	0.0630	0.0462	0.3106	0.6667
0.0037	10.0	150	0.0040	0.0040	0.0629	0.0439	0.3140	0.7167
0.0028	11.0	165	0.0041	0.0041	0.0638	0.0439	0.2942	0.6833
0.0027	12.0	180	0.0041	0.0041	0.0642	0.0447	0.2854	0.7167
0.0026	13.0	195	0.0036	0.0036	0.0598	0.0422	0.3788	0.7
0.0025	14.0	210	0.0034	0.0034	0.0587	0.0420	0.4021	0.6833
0.002	15.0	225	0.0034	0.0034	0.0586	0.0408	0.4036	0.6833
0.0022	16.0	240	0.0037	0.0037	0.0607	0.0420	0.3610	0.7
0.0019	17.0	255	0.0037	0.0037	0.0607	0.0416	0.3595	0.7167
0.0018	18.0	270	0.0037	0.0037	0.0612	0.0423	0.3493	0.6833
0.0018	19.0	285	0.0036	0.0036	0.0597	0.0409	0.3804	0.7167
0.0019	20.0	300	0.0035	0.0035	0.0589	0.0407	0.3967	0.6667

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2