distilbert_system_A / README.md
doomnova's picture
Update README.md
aed89f8
metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: distilbert_system_A
    results: []
datasets:
  - Babelscape/multinerd
language:
  - en

distilbert_system_A

This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0547
  • Precision: 0.8996
  • Recall: 0.9132
  • F1: 0.9063
  • Accuracy: 0.9850

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: 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 Precision Recall F1 Accuracy
0.0278 1.0 8205 0.0434 0.8992 0.8977 0.8984 0.9843
0.0161 2.0 16410 0.0477 0.9067 0.9065 0.9066 0.9851
0.0097 3.0 24615 0.0547 0.8996 0.9132 0.9063 0.9850

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0