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: 1.2464

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
2.0986	1.0	291	1.6928
1.6392	2.0	582	1.4295
1.4873	3.0	873	1.3904
1.3995	4.0	1164	1.3811
1.341	5.0	1455	1.1973
1.2807	6.0	1746	1.2738
1.2394	7.0	2037	1.2633
1.1993	8.0	2328	1.2103
1.1656	9.0	2619	1.1839
1.1403	10.0	2910	1.2228
1.1289	11.0	3201	1.2081
1.104	12.0	3492	1.1652
1.0823	13.0	3783	1.2508
1.0736	14.0	4074	1.1687
1.0625	15.0	4365	1.1168
1.0626	16.0	4656	1.2464

Framework versions

• Transformers 4.30.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.13.3