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: 1.2526

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.1071	1.0	291	1.6964
1.6421	2.0	582	1.4279
1.4853	3.0	873	1.3924
1.4014	4.0	1164	1.3701
1.3388	5.0	1455	1.1944
1.283	6.0	1746	1.2795
1.2394	7.0	2037	1.2671
1.2014	8.0	2328	1.2084
1.1668	9.0	2619	1.1783
1.14	10.0	2910	1.2076
1.1277	11.0	3201	1.2081
1.1053	12.0	3492	1.1628
1.0819	13.0	3783	1.2544
1.0763	14.0	4074	1.1695
1.0634	15.0	4365	1.1157
1.0637	16.0	4656	1.2526

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1