wooseok0303's picture
Training complete
d77eb18 verified
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: distilbert-base-uncased-distilled-clinc
    results: []

distilbert-base-uncased-distilled-clinc

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

  • Loss: 0.3033
  • Accuracy: 0.9442

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
2.6145 1.0 318 1.8929 0.7213
1.4633 2.0 636 0.9656 0.8677
0.7728 3.0 954 0.5575 0.9103
0.4641 4.0 1272 0.4082 0.9306
0.3342 5.0 1590 0.3504 0.9371
0.2786 6.0 1908 0.3256 0.9432
0.2514 7.0 2226 0.3150 0.9435
0.2365 8.0 2544 0.3096 0.9413
0.2275 9.0 2862 0.3055 0.9445
0.224 10.0 3180 0.3033 0.9442

Framework versions

  • Transformers 4.36.2
  • Pytorch 1.13.1+cu116
  • Datasets 2.16.2.dev0
  • Tokenizers 0.15.0