Kuwon/chkpt

1---2base_model: monologg/koelectra-small-v3-discriminator3tags:4- generated_from_trainer5datasets:6- generator7metrics:8- accuracy9- f110- precision11- recall12model-index:13- name: chkpt14  results:15  - task:16      name: Text Classification17      type: text-classification18    dataset:19      name: generator20      type: generator21      config: default22      split: train23      args: default24    metrics:25    - name: Accuracy26      type: accuracy27      value: 0.882608695652173928    - name: F129      type: f130      value: 0.827573049502962231    - name: Precision32      type: precision33      value: 0.778998109640831734    - name: Recall35      type: recall36      value: 0.882608695652173937---38 39<!-- This model card has been generated automatically according to the information the Trainer had access to. You40should probably proofread and complete it, then remove this comment. -->41 42# chkpt43 44This model is a fine-tuned version of [monologg/koelectra-small-v3-discriminator](https://huggingface.co/monologg/koelectra-small-v3-discriminator) on the generator dataset.45It achieves the following results on the evaluation set:46- Loss: 1.281547- Accuracy: 0.882648- F1: 0.827649- Precision: 0.779050- Recall: 0.882651 52## Model description53 54More information needed55 56## Intended uses & limitations57 58More information needed59 60## Training and evaluation data61 62More information needed63 64## Training procedure65 66### Training hyperparameters67 68The following hyperparameters were used during training:69- learning_rate: 5e-0570- train_batch_size: 3271- eval_batch_size: 12872- seed: 4273- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0874- lr_scheduler_type: linear75- num_epochs: 176 77### Training results78 79| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |80|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|81| No log        | 1.0   | 29   | 1.2815          | 0.8826   | 0.8276 | 0.7790    | 0.8826 |82 83 84### Framework versions85 86- Transformers 4.35.287- Pytorch 2.1.188- Datasets 2.15.089- Tokenizers 0.15.090