AptaArkana's picture
Training complete
621c1fe verified
|
raw
history blame
2.26 kB
metadata
license: afl-3.0
base_model: Davlan/bert-base-multilingual-cased-ner-hrl
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: belajarner_bert_case
    results: []

belajarner_bert_case

This model is a fine-tuned version of Davlan/bert-base-multilingual-cased-ner-hrl on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3367
  • Precision: 0.8139
  • Recall: 0.8422
  • F1: 0.8278
  • Accuracy: 0.9420

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: 8

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.2503 1.0 1567 0.2331 0.7484 0.8148 0.7802 0.9294
0.1645 2.0 3134 0.2307 0.7987 0.8158 0.8072 0.9363
0.1097 3.0 4701 0.2588 0.7764 0.8334 0.8039 0.9360
0.0822 4.0 6268 0.2624 0.8056 0.8389 0.8219 0.9409
0.061 5.0 7835 0.2927 0.8183 0.8275 0.8229 0.9414
0.0407 6.0 9402 0.3156 0.8021 0.8350 0.8182 0.9399
0.0315 7.0 10969 0.3257 0.8102 0.8381 0.8239 0.9413
0.0238 8.0 12536 0.3367 0.8139 0.8422 0.8278 0.9420

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2