sibstrider's picture
End of training
4b6bf18 verified
|
raw
history blame
1.66 kB
metadata
license: mit
base_model: cointegrated/rubert-tiny2
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: rubert-tiny2-finetuned-classification
    results: []

rubert-tiny2-finetuned-classification

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: 0.4803
  • Accuracy: 0.8857

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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 138 0.6689 0.8571
No log 2.0 276 0.5727 0.8653
No log 3.0 414 0.5141 0.8694
0.6234 4.0 552 0.4879 0.8816
0.6234 5.0 690 0.4803 0.8857

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cpu
  • Datasets 2.16.1
  • Tokenizers 0.15.0