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: 1.2311

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
2.1008	1.0	291	1.7013
1.6347	2.0	582	1.5253
1.4976	3.0	873	1.3564
1.3963	4.0	1164	1.3459
1.3333	5.0	1455	1.2349
1.2849	6.0	1746	1.3587
1.2319	7.0	2037	1.3066
1.2078	8.0	2328	1.3463
1.167	9.0	2619	1.2071
1.1417	10.0	2910	1.1766
1.1259	11.0	3201	1.1292
1.1097	12.0	3492	1.1873
1.0884	13.0	3783	1.2220
1.0792	14.0	4074	1.2137
1.0741	15.0	4365	1.2251
1.0624	16.0	4656	1.2311

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.1