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: 1.2424

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 OptimizerNames.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
2.1055	1.0	291	1.6939
1.632	2.0	582	1.5164
1.4954	3.0	873	1.3612
1.3933	4.0	1164	1.3272
1.3289	5.0	1455	1.2318
1.2831	6.0	1746	1.3718
1.232	7.0	2037	1.2933
1.2032	8.0	2328	1.3472
1.1671	9.0	2619	1.2276
1.1403	10.0	2910	1.1774
1.1288	11.0	3201	1.1312
1.1083	12.0	3492	1.1874
1.0876	13.0	3783	1.2156
1.0757	14.0	4074	1.2056
1.0729	15.0	4365	1.2197
1.0636	16.0	4656	1.2424

Framework versions

• Transformers 4.46.1
• Pytorch 2.4.0
• Datasets 3.0.2
• Tokenizers 0.20.1