Edit model card

0322_cosmetic3_kcelectra

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

  • Loss: 0.3637
  • Accuracy: 0.8700
  • F1: 0.8703
  • Precision: 0.8789
  • Recall: 0.8700

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.4536 1.0 277 0.3556 0.8768 0.8734 0.8873 0.8768
0.2608 2.0 554 0.5060 0.8261 0.8252 0.8415 0.8261
0.1171 3.0 831 0.5406 0.8623 0.8571 0.8768 0.8623
0.1393 4.0 1108 0.5734 0.8768 0.8752 0.8862 0.8768
0.2115 5.0 1385 0.6661 0.8913 0.8915 0.8924 0.8913
0.0939 6.0 1662 0.5506 0.9058 0.9054 0.9057 0.9058
0.1122 7.0 1939 0.6672 0.8986 0.8985 0.8987 0.8986
0.2413 8.0 2216 0.7136 0.8949 0.8949 0.8950 0.8949
0.001 9.0 2493 0.6689 0.9058 0.9058 0.9058 0.9058
0.0013 10.0 2770 0.6764 0.9094 0.9094 0.9094 0.9094

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2
Downloads last month
4
Safetensors
Model size
109M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for BKforKorea/0322_cosmetic3_kcelectra

Finetuned
(4)
this model