DrishtiSharma's picture
Woohoo! Drishti :)
4486ade
metadata
license: apache-2.0
base_model: distilbert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: distilbert-base-multilingual-cased-language-detection-fp16-false-bs-32
    results: []

distilbert-base-multilingual-cased-language-detection-fp16-false-bs-32

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

  • Loss: 0.0040
  • Accuracy: 0.9992
  • Weighted f1: 0.9992
  • Micro f1: 0.9992
  • Macro f1: 0.9992
  • Weighted recall: 0.9992
  • Micro recall: 0.9992
  • Macro recall: 0.9992
  • Weighted precision: 0.9992
  • Micro precision: 0.9992
  • Macro precision: 0.9992

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 Weighted f1 Micro f1 Macro f1 Weighted recall Micro recall Macro recall Weighted precision Micro precision Macro precision
0.1131 1.0 329 0.0040 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992
0.0058 2.0 658 0.0063 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9993 0.9992 0.9992 0.9992
0.0013 3.0 987 0.0061 0.9985 0.9985 0.9985 0.9984 0.9985 0.9985 0.9985 0.9985 0.9985 0.9984
0.0003 4.0 1316 0.0036 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992
0.0002 5.0 1645 0.0037 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992 0.9992

Framework versions

  • Transformers 4.33.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4.dev0
  • Tokenizers 0.13.3