bert-petco-fullemailbody-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: 0.0024
• Mse: 0.0024
• Rmse: 0.0487
• Mae: 0.0369
• R2: 0.3917

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: 1e-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
0.0259	1.0	15	0.0045	0.0045	0.0671	0.0558	-0.1551
0.0131	2.0	30	0.0042	0.0042	0.0645	0.0501	-0.0669
0.0114	3.0	45	0.0037	0.0037	0.0609	0.0514	0.0488
0.0118	4.0	60	0.0033	0.0033	0.0576	0.0446	0.1471
0.0097	5.0	75	0.0036	0.0036	0.0599	0.0460	0.0790
0.0095	6.0	90	0.0037	0.0037	0.0606	0.0462	0.0568
0.0086	7.0	105	0.0040	0.0040	0.0629	0.0485	-0.0177
0.0083	8.0	120	0.0026	0.0026	0.0513	0.0392	0.3232
0.0077	9.0	135	0.0035	0.0035	0.0595	0.0445	0.0915
0.0067	10.0	150	0.0037	0.0037	0.0606	0.0462	0.0561
0.0066	11.0	165	0.0025	0.0025	0.0503	0.0394	0.3499
0.0066	12.0	180	0.0034	0.0034	0.0580	0.0475	0.1355
0.0046	13.0	195	0.0024	0.0024	0.0487	0.0369	0.3917
0.0052	14.0	210	0.0035	0.0035	0.0587	0.0454	0.1137
0.0049	15.0	225	0.0032	0.0032	0.0567	0.0438	0.1753
0.0041	16.0	240	0.0034	0.0034	0.0581	0.0445	0.1321
0.0039	17.0	255	0.0030	0.0030	0.0548	0.0412	0.2277
0.0042	18.0	270	0.0036	0.0036	0.0603	0.0465	0.0676
0.0035	19.0	285	0.0036	0.0036	0.0601	0.0461	0.0719
0.0031	20.0	300	0.0033	0.0033	0.0574	0.0435	0.1548

Framework versions

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