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: 1.2377

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
2.1027	1.0	291	1.6979
1.634	2.0	582	1.5218
1.4939	3.0	873	1.3492
1.3985	4.0	1164	1.3259
1.3368	5.0	1455	1.2550
1.2702	6.0	1746	1.3513
1.2206	7.0	2037	1.2973
1.2052	8.0	2328	1.3334
1.1765	9.0	2619	1.2212
1.1321	10.0	2910	1.1668
1.1282	11.0	3201	1.1422
1.1004	12.0	3492	1.1982
1.0897	13.0	3783	1.2257
1.0749	14.0	4074	1.2107
1.0715	15.0	4365	1.2169
1.0492	16.0	4656	1.2377

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.2+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0