Edit model card

MLMA_lab9

This model is a fine-tuned version of microsoft/biogpt on the ncbi_disease dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3328
  • Precision: 0.1239
  • Recall: 0.0178
  • F1: 0.0311
  • Accuracy: 0.9177

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: 0.0001
  • 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 Precision Recall F1 Accuracy
0.2903 1.0 680 0.3328 0.1239 0.0178 0.0311 0.9177
0.2907 2.0 1360 0.3328 0.1239 0.0178 0.0311 0.9177
0.2885 3.0 2040 0.3328 0.1239 0.0178 0.0311 0.9177
0.2861 4.0 2720 0.3328 0.1239 0.0178 0.0311 0.9177
0.2948 5.0 3400 0.3328 0.1239 0.0178 0.0311 0.9177
0.2881 6.0 4080 0.3328 0.1239 0.0178 0.0311 0.9177
0.292 7.0 4760 0.3328 0.1239 0.0178 0.0311 0.9177
0.2882 8.0 5440 0.3328 0.1239 0.0178 0.0311 0.9177
0.2905 9.0 6120 0.3328 0.1239 0.0178 0.0311 0.9177
0.2881 10.0 6800 0.3328 0.1239 0.0178 0.0311 0.9177

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3
Downloads last month
1

Dataset used to train daijin219/MLMA_lab9_1

Evaluation results