test_2 / README.md
Ranjit's picture
End of training
95b612b
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: 0.6866
  • F1: 0.8161

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: 3

Training results

Training Loss Epoch Step Validation Loss F1
2.0824 0.11 2000 1.6825 0.3184
1.2059 0.22 4000 1.1052 0.5593
0.8955 0.33 6000 0.8835 0.6588
0.7748 0.44 8000 0.8215 0.6894
0.6839 0.54 10000 0.7765 0.7234
0.6299 0.65 12000 0.7514 0.7600
0.5778 0.76 14000 0.6906 0.7707
0.533 0.87 16000 0.6867 0.7771
0.4877 0.98 18000 0.6850 0.7861
0.4114 1.09 20000 0.6757 0.7907
0.3815 1.2 22000 0.6798 0.7956
0.3785 1.31 24000 0.6809 0.7987
0.3645 1.42 26000 0.6739 0.8033
0.3347 1.53 28000 0.6768 0.8037
0.3345 1.63 30000 0.6457 0.8087
0.3254 1.74 32000 0.6721 0.8055
0.3131 1.85 34000 0.6542 0.8125
0.3072 1.96 36000 0.6652 0.8070
0.2343 2.07 38000 0.6754 0.8143
0.2323 2.18 40000 0.6790 0.8167
0.232 2.29 42000 0.6967 0.8101
0.2171 2.4 44000 0.6999 0.8116
0.215 2.51 46000 0.6927 0.8095
0.2136 2.62 48000 0.6917 0.8155
0.2008 2.72 50000 0.6837 0.8137
0.1997 2.83 52000 0.6925 0.8140
0.1926 2.94 54000 0.6866 0.8161

Framework versions

  • Transformers 4.34.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.0