bert-petco-emailbody-ctr

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

• Loss: 0.0143
• Mse: 0.0143
• Rmse: 0.1197
• Mae: 0.0727
• R2: 0.7276

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
0.1187	1.0	16	0.0474	0.0474	0.2176	0.0906	0.0990
0.1042	2.0	32	0.0447	0.0447	0.2115	0.1415	0.1490
0.0641	3.0	48	0.0315	0.0315	0.1774	0.0966	0.4012
0.0562	4.0	64	0.0278	0.0278	0.1667	0.0902	0.4716
0.0498	5.0	80	0.0278	0.0278	0.1669	0.0914	0.4702
0.0318	6.0	96	0.0229	0.0229	0.1512	0.0991	0.5652
0.0239	7.0	112	0.0275	0.0275	0.1658	0.1025	0.4770
0.0117	8.0	128	0.0513	0.0513	0.2264	0.0946	0.0248
0.0137	9.0	144	0.0371	0.0371	0.1926	0.0867	0.2940
0.0125	10.0	160	0.0287	0.0287	0.1694	0.0769	0.4538
0.0077	11.0	176	0.0332	0.0332	0.1821	0.0803	0.3691
0.0049	12.0	192	0.0225	0.0225	0.1501	0.0970	0.5715
0.0074	13.0	208	0.0185	0.0185	0.1360	0.0822	0.6482
0.0046	14.0	224	0.0214	0.0214	0.1464	0.0734	0.5923
0.005	15.0	240	0.0152	0.0152	0.1234	0.0730	0.7104
0.0059	16.0	256	0.0143	0.0143	0.1197	0.0727	0.7276
0.005	17.0	272	0.0249	0.0249	0.1577	0.0744	0.5271
0.0042	18.0	288	0.0267	0.0267	0.1635	0.0762	0.4911
0.0039	19.0	304	0.0283	0.0283	0.1683	0.0776	0.4609
0.0045	20.0	320	0.0274	0.0274	0.1654	0.0756	0.4795

Framework versions

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