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: 1.2430

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss
2.1051	1.0	291	1.6955
1.6311	2.0	582	1.5132
1.4968	3.0	873	1.3491
1.394	4.0	1164	1.3301
1.3309	5.0	1455	1.2343
1.2833	6.0	1746	1.3496
1.2305	7.0	2037	1.2995
1.2018	8.0	2328	1.3417
1.1667	9.0	2619	1.2182
1.1388	10.0	2910	1.1757
1.1281	11.0	3201	1.1448
1.1094	12.0	3492	1.1833
1.0896	13.0	3783	1.2279
1.0761	14.0	4074	1.2065
1.0718	15.0	4365	1.2319
1.0644	16.0	4656	1.2430

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3