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: 1.2379

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
2.101	1.0	291	1.7121
1.6363	2.0	582	1.5069
1.4979	3.0	873	1.3612
1.3964	4.0	1164	1.3421
1.3323	5.0	1455	1.2287
1.288	6.0	1746	1.3609
1.2321	7.0	2037	1.3087
1.2018	8.0	2328	1.3420
1.167	9.0	2619	1.2250
1.1402	10.0	2910	1.1748
1.126	11.0	3201	1.1265
1.1109	12.0	3492	1.1797
1.0865	13.0	3783	1.2223
1.0747	14.0	4074	1.2107
1.0707	15.0	4365	1.2308
1.061	16.0	4656	1.2379

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1