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: 1.2222

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
2.0987	1.0	291	1.6985
1.6308	2.0	582	1.5183
1.4968	3.0	873	1.3575
1.3963	4.0	1164	1.3388
1.3329	5.0	1455	1.2376
1.2854	6.0	1746	1.3704
1.2359	7.0	2037	1.2990
1.2064	8.0	2328	1.3360
1.1628	9.0	2619	1.2264
1.1406	10.0	2910	1.1664
1.1286	11.0	3201	1.1303
1.1123	12.0	3492	1.1831
1.0896	13.0	3783	1.2102
1.0764	14.0	4074	1.2081
1.0716	15.0	4365	1.2217
1.06	16.0	4656	1.2222

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1