pszemraj's picture
Update README.md
5ee7d52
|
raw
history blame
2.65 kB
metadata
language:
  - en
license: mit
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - matthews_correlation
model-index:
  - name: deberta-v3-xsmall-CoLA
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE COLA
          type: glue
          config: cola
          split: validation
          args: cola
        metrics:
          - name: Matthews Correlation
            type: matthews_correlation
            value: 0.5894856058137782
widget:
  - text: The cat sat on the mat.
    example_title: Correct grammatical sentence
  - text: Me and my friend going to the store.
    example_title: Incorrect subject-verb agreement
  - text: I ain't got no money.
    example_title: Incorrect verb conjugation and double negative
  - text: She don't like pizza no more.
    example_title: Incorrect verb conjugation and double negative
  - text: They is arriving tomorrow.
    example_title: Incorrect verb conjugation

deberta-v3-xsmall-CoLA

This model is a fine-tuned version of microsoft/deberta-v3-xsmall on the GLUE COLA dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4237
  • Matthews Correlation: 0.5895

Model description

Trying to find a decent optimum between accuracy/quality and inference speed.

{
    "epoch": 3.0,
    "eval_loss": 0.423,
    "eval_matthews_correlation": 0.589,
    "eval_runtime": 5.0422,
    "eval_samples": 1043,
    "eval_samples_per_second": 206.853,
    "eval_steps_per_second": 51.763
}

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: 32
  • eval_batch_size: 4
  • seed: 16105
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Matthews Correlation
0.3945 1.0 67 0.4323 0.5778
0.3214 2.0 134 0.4237 0.5895
0.3059 3.0 201 0.4636 0.5795

Framework versions

  • Transformers 4.27.0.dev0
  • Pytorch 1.13.1+cu117
  • Datasets 2.8.0
  • Tokenizers 0.13.1