results / README.md
MateiCv's picture
End of training
0f40d77
metadata
license: apache-2.0
base_model: distilbert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: results
    results: []

results

This model is a fine-tuned version of distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5702
  • Accuracy: 0.7894
  • Precision: 0.7913
  • Recall: 0.7040
  • F1: 0.7144
  • Hamming Loss: 0.2106

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: 16
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 8

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1 Hamming Loss
1.435 1.0 1744 1.2662 0.5627 0.6403 0.4392 0.4707 0.4373
1.19 2.0 3488 1.0175 0.6358 0.6749 0.5311 0.5571 0.3642
0.9496 3.0 5232 0.8298 0.6934 0.7166 0.5916 0.6132 0.3066
0.8226 4.0 6976 0.7224 0.7306 0.7447 0.6371 0.6561 0.2694
0.7113 5.0 8720 0.6609 0.7514 0.7628 0.6583 0.6742 0.2486
0.6497 6.0 10464 0.6153 0.7724 0.7717 0.6904 0.6980 0.2276
0.5997 7.0 12208 0.5822 0.7863 0.7945 0.6967 0.7105 0.2137
0.571 8.0 13952 0.5702 0.7894 0.7913 0.7040 0.7144 0.2106

Framework versions

  • Transformers 4.32.0
  • Pytorch 2.0.1+cu118
  • Tokenizers 0.13.3