dliladar's picture
End of training
19f1e82 verified
metadata
license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - recall
  - precision
model-index:
  - name: multilingual_model_v02
    results: []

multilingual_model_v02

This model is a fine-tuned version of bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3359
  • Accuracy: 0.8707
  • F1 Score: 0.7728
  • Recall: 0.8527
  • Precision: 0.7066

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: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Score Recall Precision
No log 1.0 219 0.3391 0.8707 0.7728 0.8527 0.7066
No log 2.0 438 0.3377 0.8707 0.7728 0.8527 0.7066
0.3688 3.0 657 0.3359 0.8707 0.7728 0.8527 0.7066

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1