metamath's picture
Training complete
5d03612 verified
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - clinc_oos
metrics:
  - accuracy
model-index:
  - name: distilbert-base-uncased-distilled-optim-clinc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: clinc_oos
          type: clinc_oos
          config: plus
          split: validation
          args: plus
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9448387096774193

distilbert-base-uncased-distilled-optim-clinc

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

  • Loss: 0.3314
  • Accuracy: 0.9448

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: 2e-05
  • train_batch_size: 48
  • eval_batch_size: 48
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 318 2.1746 0.7242
2.5724 2.0 636 1.1166 0.8623
2.5724 3.0 954 0.6319 0.9155
0.9951 4.0 1272 0.4582 0.9306
0.4397 5.0 1590 0.3865 0.9394
0.4397 6.0 1908 0.3583 0.9419
0.2978 7.0 2226 0.3445 0.9429
0.251 8.0 2544 0.3394 0.9426
0.251 9.0 2862 0.3334 0.9445
0.233 10.0 3180 0.3314 0.9448

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.1+cu118
  • Datasets 2.16.1
  • Tokenizers 0.15.0