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: 1.2314

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: 64
• eval_batch_size: 16
• 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
2.193	1.0	146	1.7004
1.7081	2.0	292	1.4895
1.5458	3.0	438	1.4427
1.4715	4.0	584	1.4081
1.3944	5.0	730	1.3163
1.3396	6.0	876	1.3200
1.2945	7.0	1022	1.2785
1.2652	8.0	1168	1.2473
1.2332	9.0	1314	1.2321
1.2042	10.0	1460	1.2162
1.204	11.0	1606	1.1781
1.1866	12.0	1752	1.2211
1.1592	13.0	1898	1.2801
1.1503	14.0	2044	1.1768
1.1268	15.0	2190	1.1657
1.1521	16.0	2336	1.2314

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0
• Datasets 2.2.3.dev0
• Tokenizers 0.12.1