BulBERT-ct21-5pochs / README.md
mor40's picture
Training complete
8f53db8
metadata
base_model: mor40/BulBERT-chitanka-model
tags:
  - generated_from_trainer
datasets:
  - bgglue
metrics:
  - accuracy
model-index:
  - name: BulBERT-ct21-5pochs
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: bgglue
          type: bgglue
          config: ct21t1
          split: validation
          args: ct21t1
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.84

BulBERT-ct21-5pochs

This model is a fine-tuned version of mor40/BulBERT-chitanka-model on the bgglue dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0051
  • Accuracy: 0.84

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: 32
  • eval_batch_size: 32
  • 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 1.0 163 0.4891 0.7743
No log 2.0 326 0.5475 0.8257
No log 3.0 489 0.7889 0.82
0.288 4.0 652 0.9438 0.8286
0.288 5.0 815 1.0051 0.84

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.1