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: 1.2388

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
2.0959	1.0	291	1.6893
1.6328	2.0	582	1.5211
1.4921	3.0	873	1.3554
1.4011	4.0	1164	1.3424
1.3351	5.0	1455	1.2614
1.2718	6.0	1746	1.3491
1.2216	7.0	2037	1.2867
1.206	8.0	2328	1.3365
1.1781	9.0	2619	1.2072
1.1338	10.0	2910	1.1643
1.1288	11.0	3201	1.1396
1.1012	12.0	3492	1.1911
1.0915	13.0	3783	1.2163
1.0746	14.0	4074	1.2091
1.0731	15.0	4365	1.2164
1.0491	16.0	4656	1.2388

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0