Edit model card

bert_uncased_L-6_H-768_A-12-QAT

This model is a fine-tuned version of google/bert_uncased_L-6_H-768_A-12 on the glue dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4989
  • Accuracy: 0.8303

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: 6e-05
  • train_batch_size: 128
  • eval_batch_size: 128
  • seed: 33
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 7
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3055 1.0 8 0.4989 0.8303
0.192 2.0 16 0.4659 0.8108
0.0994 3.0 24 0.5389 0.8177
0.0324 4.0 32 0.7313 0.8096
0.0164 5.0 40 0.6689 0.8211
0.0137 6.0 48 0.7148 0.8154
0.0041 7.0 56 0.7339 0.8177

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
4
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for jysh1023/bert_uncased_L-6_H-768_A-12-QAT

Finetuned
(4)
this model

Dataset used to train jysh1023/bert_uncased_L-6_H-768_A-12-QAT

Evaluation results