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: 1.1691

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
2.1115	1.0	291	1.6930
1.6354	2.0	582	1.3670
1.4808	3.0	873	1.4257
1.393	4.0	1164	1.4305
1.3415	5.0	1455	1.2622
1.2873	6.0	1746	1.3074
1.2302	7.0	2037	1.2133
1.2132	8.0	2328	1.2650
1.1793	9.0	2619	1.2654
1.148	10.0	2910	1.2179
1.127	11.0	3201	1.2638
1.0989	12.0	3492	1.1541
1.0961	13.0	3783	1.1539
1.0793	14.0	4074	1.0733
1.066	15.0	4365	1.2453
1.0672	16.0	4656	1.1691

Framework versions

• Transformers 4.37.1
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1