initial-dq-model / README.md
lucafrost's picture
update model card README.md
e79a3b2
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: initial-dq-model
    results: []

initial-dq-model

This model is a fine-tuned version of distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1677
  • Precision: 0.7763
  • Recall: 0.9380
  • F1: 0.8495
  • Accuracy: 0.9423

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.2251 1.0 1220 0.1768 0.7481 0.9264 0.8277 0.9378
0.186 2.0 2440 0.1677 0.7763 0.9380 0.8495 0.9423

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.10.2+cu113
  • Datasets 2.8.0
  • Tokenizers 0.13.2