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: 0.1675

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
0.239	1.0	291	0.2306
0.1865	2.0	582	0.1971
0.169	3.0	873	0.1918
0.1603	4.0	1164	0.1875
0.1536	5.0	1455	0.1567
0.1461	6.0	1746	0.1755
0.1411	7.0	2037	0.1719
0.1374	8.0	2328	0.1658
0.1341	9.0	2619	0.1594
0.1302	10.0	2910	0.1666
0.1284	11.0	3201	0.1634
0.1264	12.0	3492	0.1588
0.1238	13.0	3783	0.1690
0.1237	14.0	4074	0.1558
0.1218	15.0	4365	0.1523
0.1213	16.0	4656	0.1675

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1
• Datasets 2.13.0
• Tokenizers 0.13.3