Edit model card

Visualize in Weights & Biases

22best_berita_bert_model_fold_2

This model is a fine-tuned version of ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2522
  • Accuracy: 0.8349
  • Precision: 0.8373
  • Recall: 0.8357
  • F1: 0.8333

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
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
No log 1.0 106 0.6551 0.7264 0.7745 0.7082 0.7121
No log 2.0 212 0.9467 0.6934 0.7488 0.7142 0.6839
No log 3.0 318 0.8995 0.8113 0.8139 0.8146 0.8111
No log 4.0 424 1.1543 0.7972 0.8169 0.7986 0.7936
0.3548 5.0 530 1.1540 0.8208 0.8223 0.8148 0.8169
0.3548 6.0 636 1.3006 0.8255 0.8431 0.8261 0.8225
0.3548 7.0 742 1.2421 0.8255 0.8328 0.8265 0.8240
0.3548 8.0 848 1.2522 0.8349 0.8373 0.8357 0.8333
0.3548 9.0 954 1.2637 0.8302 0.8330 0.8308 0.8285
0.0125 10.0 1060 1.2667 0.8302 0.8330 0.8308 0.8285

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
2
Safetensors
Model size
111M 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 choiruzzia/22best_berita_bert_model_fold_2