intanm's picture
Update README.md
98ce6c2
metadata
license: mit
tags:
  - generated_from_trainer
model-index:
  - name: mlm-20230513-indobert-large-p1-002-pt2
    results: []
datasets:
  - intanm/indonesian_financial_statements

mlm-20230513-indobert-large-p1-002-pt2

This model is a fine-tuned version of intanm/mlm-20230513-indobert-large-p1-002-pt1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7799

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: 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
No log 1.0 284 2.0189
1.7946 2.0 568 2.0046
1.7946 3.0 852 1.9715
1.5453 4.0 1136 1.9322
1.5453 5.0 1420 1.8302
1.4321 6.0 1704 1.8689
1.4321 7.0 1988 1.8075
1.4267 8.0 2272 1.7632
1.4812 9.0 2556 1.7812
1.4812 10.0 2840 1.7886

Framework versions

  • Transformers 4.29.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3