Shakhovak's picture
End of training
4baed4d verified
metadata
library_name: transformers
license: mit
base_model: cointegrated/rubert-tiny2
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: ruBertTiny_attr_name_add
    results: []

ruBertTiny_attr_name_add

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: 0.3449
  • Accuracy: 0.8675

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5287 0.2739 10000 0.4472 0.7949
0.4568 0.5478 20000 0.4204 0.8120
0.4206 0.8217 30000 0.4116 0.7991
0.3907 1.0956 40000 0.3951 0.8291
0.3641 1.3695 50000 0.3851 0.8504
0.3532 1.6434 60000 0.3576 0.8333
0.3465 1.9173 70000 0.3509 0.8504
0.323 2.1912 80000 0.3523 0.8547
0.3099 2.4651 90000 0.3477 0.8632
0.3102 2.7391 100000 0.3449 0.8675

Framework versions

  • Transformers 4.44.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1