bert-base-uncased-issues-128

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: 1.2463

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss
2.0991	1.0	291	1.6924
1.6398	2.0	582	1.4293
1.4878	3.0	873	1.3899
1.3995	4.0	1164	1.3814
1.3413	5.0	1455	1.1986
1.2802	6.0	1746	1.2751
1.2394	7.0	2037	1.2610
1.1993	8.0	2328	1.2118
1.1655	9.0	2619	1.1882
1.1406	10.0	2910	1.2225
1.129	11.0	3201	1.2082
1.104	12.0	3492	1.1654
1.0825	13.0	3783	1.2517
1.0739	14.0	4074	1.1687
1.0627	15.0	4365	1.1212
1.0623	16.0	4656	1.2463

Framework versions

• Transformers 4.16.2
• Pytorch 2.0.1+cu118
• Datasets 1.16.1
• Tokenizers 0.14.1