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: 1.2540

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
2.0981	1.0	291	1.6917
1.6493	2.0	582	1.4357
1.4831	3.0	873	1.3923
1.3957	4.0	1164	1.4056
1.3339	5.0	1455	1.1944
1.2936	6.0	1746	1.2888
1.2458	7.0	2037	1.2715
1.2004	8.0	2328	1.1992
1.1785	9.0	2619	1.1726
1.1389	10.0	2910	1.2157
1.1313	11.0	3201	1.1977
1.0935	12.0	3492	1.1794
1.0826	13.0	3783	1.2260
1.0729	14.0	4074	1.1549
1.0599	15.0	4365	1.1269
1.0538	16.0	4656	1.2540

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.2
• Datasets 1.16.1
• Tokenizers 0.10.3