Hugging Face's logo

adasgaleus
/
BIM-0.75

Token Classification
Transformers
Safetensors
bert
generated_from_trainer
Inference Endpoints
Model card Files Community
BIM-0.75 / README.md
adasgaleus's picture
adasgaleus
End of training
d4f3319 verified
preview code
|
raw history blame contribute delete
No virus
6.89 kB
metadata
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: 20240327180321_happy_vaswani
    results: []

20240327180321_happy_vaswani

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

  • Loss: 0.0288
  • Precision: 0.9791
  • Recall: 0.9836
  • F1: 0.9813
  • Accuracy: 0.9908

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: 0.0005
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 69
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 350
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.0627 0.09 300 0.0535 0.9603 0.9629 0.9616 0.9809
0.0571 0.17 600 0.0485 0.9625 0.9685 0.9655 0.9827
0.0523 0.26 900 0.0451 0.9639 0.9721 0.9680 0.9840
0.0498 0.35 1200 0.0452 0.9659 0.9700 0.9680 0.9841
0.0498 0.44 1500 0.0440 0.9675 0.9717 0.9696 0.9849
0.0487 0.52 1800 0.0429 0.9674 0.9714 0.9694 0.9848
0.0485 0.61 2100 0.0431 0.9668 0.9733 0.9700 0.9850
0.0468 0.7 2400 0.0410 0.9672 0.9745 0.9709 0.9855
0.0469 0.78 2700 0.0412 0.9671 0.9754 0.9713 0.9857
0.0473 0.87 3000 0.0419 0.9678 0.9731 0.9704 0.9853
0.0455 0.96 3300 0.0415 0.9674 0.9756 0.9715 0.9857
0.0417 1.04 3600 0.0404 0.9674 0.9763 0.9718 0.9859
0.0428 1.13 3900 0.0410 0.9683 0.9755 0.9719 0.9860
0.0421 1.22 4200 0.0400 0.9691 0.9750 0.9721 0.9861
0.0412 1.31 4500 0.0403 0.9681 0.9763 0.9722 0.9861
0.0411 1.39 4800 0.0384 0.9706 0.9764 0.9735 0.9869
0.0401 1.48 5100 0.0381 0.9697 0.9772 0.9734 0.9867
0.0399 1.57 5400 0.0373 0.9711 0.9759 0.9735 0.9869
0.0398 1.65 5700 0.0367 0.9703 0.9780 0.9742 0.9871
0.0393 1.74 6000 0.0374 0.9687 0.9783 0.9735 0.9869
0.039 1.83 6300 0.0359 0.9709 0.9781 0.9745 0.9873
0.0386 1.92 6600 0.0361 0.9711 0.9780 0.9746 0.9873
0.0376 2.0 6900 0.0362 0.9717 0.9784 0.9750 0.9876
0.0346 2.09 7200 0.0359 0.9712 0.9790 0.9751 0.9876
0.0344 2.18 7500 0.0345 0.9730 0.9785 0.9757 0.9880
0.0335 2.26 7800 0.0340 0.9725 0.9789 0.9757 0.9880
0.0337 2.35 8100 0.0344 0.9722 0.9795 0.9758 0.9880
0.0336 2.44 8400 0.0344 0.9721 0.9806 0.9763 0.9883
0.033 2.53 8700 0.0342 0.9734 0.9792 0.9763 0.9883
0.0331 2.61 9000 0.0345 0.9736 0.9792 0.9764 0.9883
0.0329 2.7 9300 0.0331 0.9727 0.9808 0.9767 0.9884
0.032 2.79 9600 0.0332 0.9731 0.9808 0.9769 0.9886
0.0323 2.87 9900 0.0321 0.9740 0.9808 0.9774 0.9888
0.0314 2.96 10200 0.0322 0.9748 0.9805 0.9776 0.9889
0.0275 3.05 10500 0.0327 0.9750 0.9800 0.9775 0.9888
0.0275 3.13 10800 0.0330 0.9736 0.9810 0.9773 0.9888
0.0272 3.22 11100 0.0321 0.9753 0.9816 0.9784 0.9893
0.0272 3.31 11400 0.0319 0.9749 0.9810 0.9779 0.9891
0.0269 3.4 11700 0.0305 0.9758 0.9810 0.9784 0.9893
0.027 3.48 12000 0.0303 0.9762 0.9814 0.9788 0.9895
0.0267 3.57 12300 0.0300 0.9764 0.9819 0.9792 0.9897
0.0263 3.66 12600 0.0297 0.9766 0.9818 0.9792 0.9898
0.0261 3.74 12900 0.0296 0.9766 0.9824 0.9795 0.9899
0.0255 3.83 13200 0.0294 0.9775 0.9827 0.9801 0.9902
0.0254 3.92 13500 0.0289 0.9774 0.9828 0.9801 0.9902
0.0234 4.01 13800 0.0302 0.9775 0.9826 0.9801 0.9901
0.0207 4.09 14100 0.0303 0.9773 0.9823 0.9798 0.9900
0.0205 4.18 14400 0.0299 0.9779 0.9825 0.9802 0.9903
0.0205 4.27 14700 0.0296 0.9781 0.9828 0.9804 0.9903
0.0205 4.35 15000 0.0291 0.9785 0.9831 0.9808 0.9906
0.0201 4.44 15300 0.0294 0.9781 0.9830 0.9805 0.9904
0.0198 4.53 15600 0.0290 0.9784 0.9831 0.9807 0.9905
0.0199 4.62 15900 0.0293 0.9781 0.9835 0.9808 0.9905
0.0199 4.7 16200 0.0291 0.9789 0.9835 0.9812 0.9907
0.0195 4.79 16500 0.0293 0.9788 0.9835 0.9811 0.9907
0.0196 4.88 16800 0.0290 0.9787 0.9835 0.9811 0.9907
0.0196 4.96 17100 0.0288 0.9791 0.9836 0.9813 0.9908

Framework versions

  • Transformers 4.39.1
  • Pytorch 2.2.0a0+6a974be
  • Datasets 2.18.0
  • Tokenizers 0.15.2