brand-safety-classifier

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

  • Loss: 2.3403
  • Accuracy: 0.5726

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: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 119 2.9720 0.2989
No log 2.0 238 2.2252 0.5179
No log 3.0 357 1.7828 0.5663
No log 4.0 476 1.5521 0.5789
2.2394 5.0 595 1.4689 0.5832
2.2394 6.0 714 1.4107 0.5958
2.2394 7.0 833 1.4512 0.5937
2.2394 8.0 952 1.4819 0.5747
0.7869 9.0 1071 1.4911 0.5832
0.7869 10.0 1190 1.5625 0.5768
0.7869 11.0 1309 1.5715 0.5768
0.7869 12.0 1428 1.6383 0.5789
0.3286 13.0 1547 1.6635 0.5811
0.3286 14.0 1666 1.7684 0.5621
0.3286 15.0 1785 1.8133 0.5684
0.3286 16.0 1904 1.8770 0.5705
0.1571 17.0 2023 1.8929 0.5916
0.1571 18.0 2142 1.9210 0.5811
0.1571 19.0 2261 1.9451 0.5895
0.1571 20.0 2380 2.0018 0.5726
0.1571 21.0 2499 1.9992 0.5768
0.0924 22.0 2618 2.0863 0.5768
0.0924 23.0 2737 2.1038 0.5811
0.0924 24.0 2856 2.1313 0.5747
0.0924 25.0 2975 2.1055 0.5726
0.0752 26.0 3094 2.1162 0.5705
0.0752 27.0 3213 2.1612 0.5705
0.0752 28.0 3332 2.1885 0.5768
0.0752 29.0 3451 2.1585 0.5642
0.0616 30.0 3570 2.2013 0.5768
0.0616 31.0 3689 2.1932 0.5768
0.0616 32.0 3808 2.2058 0.5726
0.0616 33.0 3927 2.2331 0.5705
0.0583 34.0 4046 2.2470 0.5663
0.0583 35.0 4165 2.2558 0.5747
0.0583 36.0 4284 2.2560 0.5747
0.0583 37.0 4403 2.2577 0.5768
0.0483 38.0 4522 2.2817 0.5726
0.0483 39.0 4641 2.2795 0.5789
0.0483 40.0 4760 2.2845 0.5811
0.0483 41.0 4879 2.3065 0.5789
0.0483 42.0 4998 2.3018 0.5747
0.0474 43.0 5117 2.3147 0.5789
0.0474 44.0 5236 2.3279 0.5768
0.0474 45.0 5355 2.3330 0.5768
0.0474 46.0 5474 2.3449 0.5726
0.0422 47.0 5593 2.3433 0.5789
0.0422 48.0 5712 2.3418 0.5726
0.0422 49.0 5831 2.3411 0.5747
0.0422 50.0 5950 2.3403 0.5726

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.4.0
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
67M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for Mukalingam0813/brand-safety-classifier

Finetuned
(7189)
this model