Edit model card

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: 1.2620

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
2.0973 1.0 291 1.7221
1.6473 2.0 582 1.4317
1.4839 3.0 873 1.3902
1.3942 4.0 1164 1.3860
1.3345 5.0 1455 1.1929
1.2933 6.0 1746 1.2842
1.2457 7.0 2037 1.2714
1.2002 8.0 2328 1.1975
1.1833 9.0 2619 1.1701
1.1412 10.0 2910 1.2135
1.1316 11.0 3201 1.1978
1.0989 12.0 3492 1.1710
1.0832 13.0 3783 1.2304
1.0727 14.0 4074 1.1565
1.0591 15.0 4365 1.1271
1.0535 16.0 4656 1.2620

Framework versions

  • Transformers 4.22.2
  • Pytorch 1.10.0
  • Datasets 2.7.1
  • Tokenizers 0.12.1
Downloads last month
0