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: 1.1663

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
2.1124	1.0	291	1.6330
1.6254	2.0	582	1.5264
1.4981	3.0	873	1.4292
1.4031	4.0	1164	1.3636
1.3311	5.0	1455	1.2945
1.2789	6.0	1746	1.2382
1.2376	7.0	2037	1.2670
1.2049	8.0	2328	1.2065
1.1789	9.0	2619	1.1641
1.1466	10.0	2910	1.1732
1.1331	11.0	3201	1.1338
1.088	12.0	3492	1.2339
1.0916	13.0	3783	1.1853
1.0755	14.0	4074	1.1018
1.058	15.0	4365	1.2024
1.0536	16.0	4656	1.1663

Framework versions

• Transformers 4.20.1
• Pytorch 1.10.0+cu102
• Datasets 2.3.2
• Tokenizers 0.12.1