bert-base-uncased-finetuned-dob

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: 0.0005

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
2.218	1.0	20	0.9998
0.5247	2.0	40	0.1072
0.0813	3.0	60	0.0406
0.0421	4.0	80	0.0351
0.0339	5.0	100	0.0286
0.0249	6.0	120	0.0064
0.0109	7.0	140	0.0022
0.0039	8.0	160	0.0016
0.0026	9.0	180	0.0013
0.0022	10.0	200	0.0011
0.002	11.0	220	0.0010
0.0017	12.0	240	0.0009
0.0015	13.0	260	0.0009
0.0014	14.0	280	0.0008
0.0013	15.0	300	0.0007
0.0013	16.0	320	0.0007
0.0012	17.0	340	0.0007
0.0011	18.0	360	0.0006
0.001	19.0	380	0.0006
0.001	20.0	400	0.0006
0.0009	21.0	420	0.0006
0.0009	22.0	440	0.0006
0.0009	23.0	460	0.0006
0.0009	24.0	480	0.0005
0.0008	25.0	500	0.0005
0.0008	26.0	520	0.0005
0.0008	27.0	540	0.0005
0.0008	28.0	560	0.0005
0.0008	29.0	580	0.0005
0.0008	30.0	600	0.0005

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1