nlp_til3 / README.md
casual's picture
End of training
14d0b83 verified
|
raw
history blame
2.33 kB
metadata
license: apache-2.0
base_model: casual/nlp_til2
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: nlp_til3
    results: []

nlp_til3

This model is a fine-tuned version of casual/nlp_til2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0052
  • Precision: 0.9899
  • Recall: 0.9919
  • F1: 0.9909
  • Accuracy: 0.9983

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: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 219 0.0192 0.9571 0.9614 0.9592 0.9931
No log 2.0 438 0.0176 0.9607 0.9696 0.9652 0.9940
0.0238 3.0 657 0.0142 0.9702 0.9692 0.9697 0.9948
0.0238 4.0 876 0.0105 0.9764 0.9744 0.9754 0.9958
0.0201 5.0 1095 0.0093 0.9839 0.9804 0.9822 0.9969
0.0201 6.0 1314 0.0080 0.9832 0.9878 0.9855 0.9974
0.0147 7.0 1533 0.0078 0.9850 0.9858 0.9854 0.9975
0.0147 8.0 1752 0.0071 0.9835 0.9892 0.9863 0.9976
0.0147 9.0 1971 0.0053 0.9899 0.9911 0.9905 0.9983
0.0106 10.0 2190 0.0052 0.9899 0.9919 0.9909 0.9983

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.19.1
  • Tokenizers 0.19.1