bert-31

This model is a fine-tuned version of hung200504/bert-21 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 9.6564

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: 3e-06
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
10.8389 0.09 5 11.6872
10.6506 0.18 10 11.3129
9.9367 0.27 15 10.9748
9.7504 0.36 20 10.6767
9.4789 0.45 25 10.4164
9.3145 0.55 30 10.1941
8.4653 0.64 35 10.0120
8.9579 0.73 40 9.8679
8.3746 0.82 45 9.7613
8.3205 0.91 50 9.6904
8.0754 1.0 55 9.6564

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.1
Downloads last month
4
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for hung200504/bert-31

Finetuned
hung200504/bert-21
Finetuned
(1)
this model