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: 1.2330

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
2.1035	1.0	291	1.7061
1.6317	2.0	582	1.5071
1.4971	3.0	873	1.3600
1.3955	4.0	1164	1.3393
1.3299	5.0	1455	1.2405
1.2871	6.0	1746	1.3681
1.2325	7.0	2037	1.2985
1.2023	8.0	2328	1.3442
1.1691	9.0	2619	1.2195
1.1434	10.0	2910	1.1827
1.1251	11.0	3201	1.1261
1.1113	12.0	3492	1.1707
1.0868	13.0	3783	1.2133
1.0749	14.0	4074	1.2199
1.0725	15.0	4365	1.2171
1.0609	16.0	4656	1.2330

Framework versions

• Transformers 4.42.4
• Pytorch 2.2.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1