gokuls's picture
End of training
e69c81b
metadata
language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: mobilebert_add_GLUE_Experiment_mrpc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MRPC
          type: glue
          config: mrpc
          split: validation
          args: mrpc
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6838235294117647
          - name: F1
            type: f1
            value: 0.8122270742358079

mobilebert_add_GLUE_Experiment_mrpc

This model is a fine-tuned version of google/mobilebert-uncased on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6197
  • Accuracy: 0.6838
  • F1: 0.8122
  • Combined Score: 0.7480

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: 128
  • eval_batch_size: 128
  • 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

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Combined Score
0.6387 1.0 29 0.6245 0.6838 0.8122 0.7480
0.6307 2.0 58 0.6234 0.6838 0.8122 0.7480
0.6307 3.0 87 0.6233 0.6838 0.8122 0.7480
0.6295 4.0 116 0.6231 0.6838 0.8122 0.7480
0.6261 5.0 145 0.6197 0.6838 0.8122 0.7480
0.6147 6.0 174 0.6344 0.6838 0.8122 0.7480
0.6209 7.0 203 0.6398 0.6838 0.8122 0.7480
0.6007 8.0 232 0.6338 0.6324 0.7517 0.6920
0.5795 9.0 261 0.6377 0.625 0.7429 0.6839
0.5712 10.0 290 0.6290 0.6814 0.8036 0.7425

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.14.0a0+410ce96
  • Datasets 2.8.0
  • Tokenizers 0.13.2