Gaivoronsky's picture
Pushing Data-Lab/rubert-base-cased-conversational_ner-v2 model to Hugging Face Hub
b1ad351
|
raw
history blame
1.81 kB
metadata
base_model: DeepPavlov/rubert-base-cased-conversational
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: rubert-base-cased-conversational_ner-v2
    results: []

rubert-base-cased-conversational_ner-v2

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

  • Loss: 0.1045
  • Precision: 0.9259
  • Recall: 0.9375
  • F1: 0.9317
  • Accuracy: 0.9781

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: 3

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 40 0.3025 0.6627 0.6875 0.6748 0.9103
No log 2.0 80 0.1169 0.8276 0.9 0.8623 0.9694
No log 3.0 120 0.1045 0.9259 0.9375 0.9317 0.9781

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.13.3