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: 1.2484

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
2.099	1.0	291	1.6869
1.6375	2.0	582	1.4308
1.4841	3.0	873	1.3859
1.397	4.0	1164	1.3731
1.3394	5.0	1455	1.1839
1.2819	6.0	1746	1.2912
1.2403	7.0	2037	1.2614
1.1983	8.0	2328	1.2071
1.1653	9.0	2619	1.1822
1.1407	10.0	2910	1.2134
1.1275	11.0	3201	1.2029
1.1064	12.0	3492	1.1685
1.0799	13.0	3783	1.2484
1.0776	14.0	4074	1.1658
1.0634	15.0	4365	1.1192
1.0607	16.0	4656	1.2484

Framework versions

• Transformers 4.16.2
• Pytorch 1.12.1
• Datasets 2.8.0
• Tokenizers 0.10.3