xshubhamx's picture
Upload README.md with huggingface_hub
fdae43f verified
|
raw
history blame
6.02 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
base_model: facebook/bart-large
metrics:
  - accuracy
  - precision
  - recall
model-index:
  - name: bart-large-lora-no-grad
    results: []

bart-large-lora-no-grad

This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8724
  • Accuracy: 0.8428
  • Precision: 0.8414
  • Recall: 0.8428
  • Precision Macro: 0.8149
  • Recall Macro: 0.7856
  • Macro Fpr: 0.0144
  • Weighted Fpr: 0.0138
  • Weighted Specificity: 0.9778
  • Macro Specificity: 0.9876
  • Weighted Sensitivity: 0.8366
  • Macro Sensitivity: 0.7856
  • F1 Micro: 0.8366
  • F1 Macro: 0.7922
  • F1 Weighted: 0.8329

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall Precision Macro Recall Macro Macro Fpr Weighted Fpr Weighted Specificity Macro Specificity Weighted Sensitivity Macro Sensitivity F1 Micro F1 Macro F1 Weighted
1.3548 1.0 643 0.7811 0.7568 0.7272 0.7568 0.4206 0.4734 0.0234 0.0224 0.9682 0.9817 0.7568 0.4734 0.7568 0.4364 0.7359
0.7738 2.0 1286 0.6572 0.7893 0.7848 0.7893 0.6529 0.5639 0.0196 0.0187 0.9732 0.9842 0.7893 0.5639 0.7893 0.5618 0.7783
0.6874 3.0 1929 0.6485 0.8009 0.7994 0.8009 0.6224 0.6498 0.0179 0.0174 0.9767 0.9852 0.8009 0.6498 0.8009 0.6248 0.7948
0.502 4.0 2572 0.6912 0.8257 0.8216 0.8257 0.7661 0.7399 0.0158 0.0149 0.9738 0.9866 0.8257 0.7399 0.8257 0.7393 0.8182
0.4443 5.0 3215 0.6655 0.8350 0.8324 0.8350 0.7584 0.7344 0.0146 0.0139 0.9781 0.9875 0.8350 0.7344 0.8350 0.7352 0.8308
0.3903 6.0 3858 0.7269 0.8304 0.8288 0.8304 0.7500 0.7407 0.0149 0.0144 0.9789 0.9873 0.8304 0.7407 0.8304 0.7363 0.8261
0.3398 7.0 4501 0.8292 0.8218 0.8264 0.8218 0.8274 0.7793 0.0161 0.0152 0.9752 0.9865 0.8218 0.7793 0.8218 0.7883 0.8163
0.2818 8.0 5144 0.8360 0.8218 0.8240 0.8218 0.8251 0.7683 0.0159 0.0152 0.9767 0.9866 0.8218 0.7683 0.8218 0.7744 0.8178
0.2572 9.0 5787 0.8456 0.8342 0.8328 0.8342 0.7999 0.7735 0.0146 0.0140 0.9787 0.9875 0.8342 0.7735 0.8342 0.7768 0.8310
0.2594 10.0 6430 0.8724 0.8428 0.8414 0.8428 0.8149 0.7891 0.0138 0.0132 0.9790 0.9881 0.8428 0.7891 0.8428 0.7955 0.8396
0.208 11.0 7073 0.9797 0.8335 0.8339 0.8335 0.8092 0.7870 0.0148 0.0141 0.9774 0.9874 0.8335 0.7870 0.8335 0.7896 0.8303
0.1786 12.0 7716 1.0180 0.8311 0.8323 0.8311 0.8100 0.7846 0.0149 0.0143 0.9777 0.9873 0.8311 0.7846 0.8311 0.7906 0.8285
0.1556 13.0 8359 1.0392 0.8358 0.8335 0.8358 0.8040 0.7830 0.0146 0.0138 0.9773 0.9875 0.8358 0.7830 0.8358 0.7876 0.8321
0.1419 14.0 9002 1.0568 0.8381 0.8362 0.8381 0.8110 0.7855 0.0143 0.0136 0.9779 0.9877 0.8381 0.7855 0.8381 0.7917 0.8349
0.1251 15.0 9645 1.0593 0.8366 0.8350 0.8366 0.8149 0.7856 0.0144 0.0138 0.9778 0.9876 0.8366 0.7856 0.8366 0.7922 0.8329

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.19.0
  • Tokenizers 0.15.1