mlm-20230416-003-1 / README.md
intanm's picture
Update README.md
c0371b9
metadata
license: mit
tags:
  - generated_from_trainer
model-index:
  - name: mlm-20230416-003-1
    results: []
datasets:
  - intanm/financial_news_id_v1.0

mlm-20230416-003-1

This model is a fine-tuned version of indobenchmark/indobert-base-p1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.3201

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: 20

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 330 4.2545
5.0912 2.0 660 3.6314
5.0912 3.0 990 3.2435
3.7016 4.0 1320 3.0558
3.22 5.0 1650 2.9062
3.22 6.0 1980 2.8126
2.946 7.0 2310 2.6621
2.7682 8.0 2640 2.5513
2.7682 9.0 2970 2.5651
2.624 10.0 3300 2.5347
2.5466 11.0 3630 2.4664
2.5466 12.0 3960 2.4375
2.4496 13.0 4290 2.4663
2.395 14.0 4620 2.3948
2.395 15.0 4950 2.4003
2.3377 16.0 5280 2.3072
2.2881 17.0 5610 2.3502
2.2881 18.0 5940 2.3236
2.2659 19.0 6270 2.3138
2.2419 20.0 6600 2.3359

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3