gec_uk_seq2tag / README.md
BonySmoke's picture
Add SPELLCHECKER
fbe32a8 verified
metadata
base_model: youscan/ukr-roberta-base
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: gec_uk_seq2tag
    results: []

gec_uk_seq2tag

This model is a fine-tuned version of youscan/ukr-roberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2885
  • Precision: 0.5978
  • Recall: 0.4263
  • F1: 0.4977
  • Accuracy: 0.9550

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: 16
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 202 0.3200 0.5468 0.3189 0.4028 0.9493
No log 2.0 405 0.2860 0.5904 0.3765 0.4598 0.9539
0.3194 3.0 608 0.2843 0.5733 0.4437 0.5002 0.9538
0.3194 4.0 811 0.2885 0.5978 0.4263 0.4977 0.9550

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.1.2
  • Datasets 2.17.1
  • Tokenizers 0.15.1