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: 0.1598

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
0.2394	1.0	291	0.2312
0.1858	2.0	582	0.1863
0.1687	3.0	873	0.1948
0.1602	4.0	1164	0.1948
0.1537	5.0	1455	0.1678
0.1467	6.0	1746	0.1805
0.1406	7.0	2037	0.1641
0.1382	8.0	2328	0.1770
0.1354	9.0	2619	0.1724
0.1312	10.0	2910	0.1679
0.1284	11.0	3201	0.1709
0.1262	12.0	3492	0.1549
0.1252	13.0	3783	0.1559
0.1239	14.0	4074	0.1441
0.1217	15.0	4365	0.1673
0.1225	16.0	4656	0.1598

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1
• Datasets 2.13.1
• Tokenizers 0.13.3