bert_distillation_0 / README.md
masterkristall's picture
End of training
8cde844
metadata
license: apache-2.0
base_model: google/bert_uncased_L-2_H-128_A-2
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_distillation_0
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          config: sst2
          split: validation
          args: sst2
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8302752293577982

bert_distillation_0

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the glue dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1784
  • 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: 0.0001
  • train_batch_size: 128
  • eval_batch_size: 128
  • seed: 2023
  • 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
1.2697 1.0 527 1.0445 0.8200
0.6784 2.0 1054 1.0168 0.8177
0.5206 3.0 1581 1.1356 0.8108
0.4383 4.0 2108 1.1437 0.8280
0.3844 5.0 2635 1.1687 0.8268
0.3547 6.0 3162 1.1784 0.8303
0.3373 7.0 3689 1.2045 0.8280

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0