metadata

language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: distilbert_add_GLUE_Experiment_logit_kd_qnli_96
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE QNLI
          type: glue
          config: qnli
          split: validation
          args: qnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.580633351638294

distilbert_add_GLUE_Experiment_logit_kd_qnli_96

This model is a fine-tuned version of distilbert-base-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.3984
Accuracy: 0.5806

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: 256
eval_batch_size: 256
seed: 10
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4153	1.0	410	0.4114	0.5054
0.4152	2.0	820	0.4115	0.5054
0.4129	3.0	1230	0.4020	0.5686
0.3995	4.0	1640	0.3984	0.5806
0.3934	5.0	2050	0.3992	0.5794
0.3888	6.0	2460	0.4024	0.5810
0.385	7.0	2870	0.4105	0.5675
0.3808	8.0	3280	0.4050	0.5777
0.3768	9.0	3690	0.4074	0.5722

Framework versions

Transformers 4.26.0
Pytorch 1.14.0a0+410ce96
Datasets 2.9.0
Tokenizers 0.13.2