Hugging Face's logo

muhammadravi251001
/
fine-tuned-DatasetQAS-IDK-MRC-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05

Question Answering
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
fine-tuned-DatasetQAS-IDK-MRC-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05 / README.md
muhammadravi251001's picture
muhammadravi251001
update model card README.md
03c7c28
preview code
|
raw
history blame
2.88 kB
metadata
license: mit
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: >-
      fine-tuned-DatasetQAS-IDK-MRC-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05
    results: []

fine-tuned-DatasetQAS-IDK-MRC-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05

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

  • Loss: 1.1096
  • Exact Match: 63.3508
  • F1: 69.1464

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 128
  • 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 Exact Match F1
6.2958 0.49 36 2.4489 50.0 50.0
3.6359 0.98 72 1.9610 49.8691 49.8691
2.1589 1.47 108 1.8244 48.9529 49.9787
2.1589 1.96 144 1.7041 49.7382 51.8819
1.9535 2.46 180 1.5846 51.0471 56.3706
1.731 2.95 216 1.4596 54.0576 58.8577
1.5809 3.44 252 1.3590 56.1518 61.7069
1.5809 3.93 288 1.3205 56.2827 61.9772
1.4244 4.42 324 1.2688 55.8901 61.8344
1.2687 4.91 360 1.2379 58.9005 64.5444
1.2687 5.4 396 1.1637 62.4346 67.9125
1.1989 5.89 432 1.1675 60.7330 66.2963
1.1131 6.38 468 1.1321 62.5654 68.1655
1.0568 6.87 504 1.1155 62.9581 68.6094
1.0568 7.37 540 1.0895 64.1361 69.6097
1.0099 7.86 576 1.1013 63.2199 69.0324
0.9784 8.35 612 1.1117 63.8743 69.3380
0.9784 8.84 648 1.1096 63.3508 69.1464

Framework versions

  • Transformers 4.27.4
  • Pytorch 1.13.1+cu117
  • Datasets 2.2.0
  • Tokenizers 0.13.2