VampeeHuntee's picture
End of training
009cfdd verified
metadata
language:
  - vi
base_model: vinai/phobert-base
tags:
  - generated_from_trainer
model-index:
  - name: phobert-base_baseline_words
    results: []

phobert-base_baseline_words

This model is a fine-tuned version of vinai/phobert-base on the covid19_ner dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0829
  • Patient Id: 0.9848
  • Name: 0.9421
  • Gender: 0.9570
  • Age: 0.9766
  • Job: 0.8095
  • Location: 0.9448
  • Organization: 0.9078
  • Date: 0.9869
  • Symptom And Disease: 0.8923
  • Transportation: 0.9943
  • F1 Macro: 0.9396
  • F1 Micro: 0.9498

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: 5

Training results

Training Loss Epoch Step Validation Loss Patient Id Name Gender Age Job Location Organization Date Symptom And Disease Transportation F1 Macro F1 Micro
0.2964 1.0 629 0.1215 0.9689 0.9534 0.9107 0.8987 0.5357 0.9350 0.8368 0.9856 0.8584 0.9667 0.8850 0.9251
0.068 2.0 1258 0.0890 0.9844 0.9479 0.9487 0.9723 0.6167 0.9377 0.8815 0.9860 0.8835 0.9886 0.9147 0.9409
0.0441 3.0 1887 0.0847 0.9828 0.9446 0.9554 0.9737 0.7570 0.9445 0.9062 0.9874 0.8909 0.9943 0.9337 0.9482
0.0327 4.0 2516 0.0859 0.9859 0.9449 0.9570 0.9765 0.7778 0.9451 0.9062 0.9874 0.8914 0.9943 0.9366 0.9495
0.0259 5.0 3145 0.0829 0.9848 0.9421 0.9570 0.9766 0.8095 0.9448 0.9078 0.9869 0.8923 0.9943 0.9396 0.9498

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.1.2
  • Datasets 2.19.2
  • Tokenizers 0.19.1