AptaArkana's picture
Model save
c6ef744 verified
metadata
license: apache-2.0
base_model: Toshifumi/distilbert-base-multilingual-cased-finetuned-emotion
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: indonesian-emotion-distilbert-base-cased-finetuned
    results: []

indonesian-emotion-distilbert-base-cased-finetuned

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

  • Loss: 0.3309
  • Accuracy: 0.9299
  • Precision: 0.9299
  • Recall: 0.9299
  • F1: 0.9299

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: 1e-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
  • lr_scheduler_warmup_ratio: 0.01
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
0.2189 1.0 2747 0.2818 0.9179 0.9179 0.9179 0.9179
0.1878 2.0 5494 0.2642 0.9207 0.9207 0.9207 0.9207
0.1569 3.0 8241 0.2835 0.9273 0.9273 0.9273 0.9273
0.1379 4.0 10988 0.3153 0.9274 0.9274 0.9274 0.9274
0.1125 5.0 13735 0.3309 0.9299 0.9299 0.9299 0.9299

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2