metadata

language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: distilbert_sa_GLUE_Experiment_logit_kd_wnli_96
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE WNLI
          type: glue
          config: wnli
          split: validation
          args: wnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5633802816901409

distilbert_sa_GLUE_Experiment_logit_kd_wnli_96

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

Loss: 0.3441
Accuracy: 0.5634

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
0.348	1.0	3	0.3451	0.5634
0.3477	2.0	6	0.3447	0.5634
0.3467	3.0	9	0.3445	0.5634
0.3473	4.0	12	0.3442	0.5634
0.3474	5.0	15	0.3441	0.5634
0.3476	6.0	18	0.3443	0.5634
0.3477	7.0	21	0.3446	0.5634
0.347	8.0	24	0.3449	0.5634
0.3477	9.0	27	0.3451	0.5634
0.3472	10.0	30	0.3453	0.5634

Framework versions

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