en_massive_syn / README.md
Ranjit's picture
End of training
88eaf5c
metadata
base_model: xxxxxxxxx
tags:
  - generated_from_trainer
datasets:
  - AmazonScience/massive
metrics:
  - f1
model-index:
  - name: massive_indo
    results: []

massive_indo

This model is a fine-tuned version of xxxxxxxxx on the massive dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6572
  • F1: 0.9265

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: 32
  • eval_batch_size: 32
  • 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 F1
4.6759 0.7 100 4.5686 0.0756
4.1696 1.41 200 4.1337 0.1459
3.7162 2.11 300 3.7519 0.2513
3.3933 2.82 400 3.4123 0.3291
3.0368 3.52 500 3.0874 0.4287
2.7163 4.23 600 2.7851 0.5446
2.4295 4.93 700 2.5342 0.5967
2.192 5.63 800 2.2814 0.6738
1.9818 6.34 900 2.0643 0.7221
1.7487 7.04 1000 1.8860 0.7589
1.6227 7.75 1100 1.7132 0.8021
1.4186 8.45 1200 1.5550 0.8249
1.2316 9.15 1300 1.4266 0.8378
1.1508 9.86 1400 1.3024 0.8547
1.0137 10.56 1500 1.1962 0.8708
0.9242 11.27 1600 1.1050 0.8807
0.877 11.97 1700 1.0273 0.8908
0.7244 12.68 1800 0.9580 0.8946
0.7141 13.38 1900 0.8928 0.9016
0.6071 14.08 2000 0.8448 0.9128
0.6166 14.79 2100 0.7980 0.9112
0.6017 15.49 2200 0.7613 0.9175
0.5192 16.2 2300 0.7300 0.9204
0.4669 16.9 2400 0.7112 0.9172
0.4539 17.61 2500 0.6872 0.9247
0.438 18.31 2600 0.6698 0.9248
0.4435 19.01 2700 0.6612 0.9256
0.4141 19.72 2800 0.6572 0.9265

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1+cu118
  • Tokenizers 0.13.3