bert128b128l / README.md
IvashinMaxim's picture
End of training
fada834 verified
metadata
license: mit
base_model: cointegrated/rubert-tiny2
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: bert128b128l
    results: []

bert128b128l

This model is a fine-tuned version of cointegrated/rubert-tiny2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1041
  • Accuracy: 0.5639

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: 1e-05
  • train_batch_size: 128
  • eval_batch_size: 128
  • 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 Accuracy
1.3571 1.0 1407 1.2302 0.5070
1.1759 2.0 2814 1.1297 0.552
1.1233 3.0 4221 1.1041 0.5639

Framework versions

  • Transformers 4.41.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1