metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - augmented_glue_sst2
metrics:
  - accuracy
model-index:
  - name: miny-bert-aug-sst2-distilled
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: augmented_glue_sst2
          type: augmented_glue_sst2
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9128440366972477

miny-bert-aug-sst2-distilled

This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 on the augmented_glue_sst2 dataset. It achieves the following results on the evaluation set:

Loss: 0.2643
Accuracy: 0.9128

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
0.602	1.0	6227	0.3389	0.9186
0.4195	2.0	12454	0.2989	0.9151
0.3644	3.0	18681	0.2794	0.9117
0.3304	4.0	24908	0.2793	0.9106
0.3066	5.0	31135	0.2659	0.9186
0.2881	6.0	37362	0.2668	0.9140
0.2754	7.0	43589	0.2643	0.9128

Framework versions

Transformers 4.16.2
Pytorch 1.10.0+cu111
Datasets 1.18.3
Tokenizers 0.11.0