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: 1.2336

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
2.1005	1.0	291	1.6951
1.6354	2.0	582	1.5200
1.499	3.0	873	1.3495
1.3951	4.0	1164	1.3253
1.3294	5.0	1455	1.2449
1.2879	6.0	1746	1.3726
1.2343	7.0	2037	1.3026
1.2019	8.0	2328	1.3469
1.1691	9.0	2619	1.2174
1.1415	10.0	2910	1.1816
1.1263	11.0	3201	1.1311
1.1114	12.0	3492	1.1781
1.0896	13.0	3783	1.2231
1.0751	14.0	4074	1.2109
1.0723	15.0	4365	1.2206
1.0619	16.0	4656	1.2336

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.0+cu118
• Datasets 3.2.0
• Tokenizers 0.21.0