ekaterinatao's picture
Model save
a3119a7 verified
metadata
base_model: DeepPavlov/rubert-base-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: nerel-bio-rubert-base
    results: []

nerel-bio-rubert-base

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

  • Loss: 0.6122
  • Precision: 0.7873
  • Recall: 0.7882
  • F1: 0.7878
  • Accuracy: 0.8601

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: 6
  • eval_batch_size: 6
  • seed: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 102 1.1211 0.6196 0.5809 0.5996 0.7125
No log 2.0 204 0.6800 0.7333 0.7165 0.7248 0.8137
No log 3.0 306 0.5985 0.7445 0.7488 0.7466 0.8303
No log 4.0 408 0.5673 0.7608 0.7622 0.7615 0.8402
0.7954 5.0 510 0.5665 0.7751 0.7702 0.7726 0.8485
0.7954 6.0 612 0.5934 0.7826 0.7742 0.7784 0.8544
0.7954 7.0 714 0.5804 0.7795 0.7751 0.7773 0.8527
0.7954 8.0 816 0.6075 0.7839 0.7878 0.7858 0.8577
0.7954 9.0 918 0.6139 0.7887 0.7889 0.7888 0.8614
0.1024 10.0 1020 0.6122 0.7873 0.7882 0.7878 0.8601

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2