Hugging Face's logo

SharonTudi
/
DIALOGUE_one

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DIALOGUE_one / README.md
SharonTudi's picture
SharonTudi
End of training
979ce38 verified
preview code
|
raw
history blame
5.83 kB
metadata
license: apache-2.0
base_model: bert-base-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: DIALOGUE_one
    results: []

DIALOGUE_one

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

  • Loss: 1.4205
  • Precision: 0.7375
  • Recall: 0.7368
  • F1: 0.7345
  • Accuracy: 0.7368

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: 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: 30

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
1.2687 0.62 30 1.0661 0.7208 0.6184 0.6068 0.6184
0.7981 1.25 60 0.6953 0.8047 0.7895 0.7941 0.7895
0.5436 1.88 90 0.5773 0.8362 0.7632 0.7502 0.7632
0.4194 2.5 120 0.5654 0.7821 0.7632 0.7620 0.7632
0.3344 3.12 150 0.6244 0.7686 0.7632 0.7634 0.7632
0.2455 3.75 180 0.5157 0.8687 0.8421 0.8422 0.8421
0.2549 4.38 210 0.6403 0.8533 0.8289 0.8298 0.8289
0.1941 5.0 240 0.8651 0.7571 0.75 0.7461 0.75
0.1621 5.62 270 0.7141 0.7793 0.7763 0.7765 0.7763
0.1514 6.25 300 0.5450 0.8961 0.8684 0.8698 0.8684
0.0772 6.88 330 0.8617 0.7966 0.7895 0.7923 0.7895
0.065 7.5 360 0.7816 0.7632 0.7632 0.7618 0.7632
0.0676 8.12 390 0.7294 0.7947 0.7895 0.7918 0.7895
0.048 8.75 420 0.8226 0.8417 0.8421 0.8400 0.8421
0.0377 9.38 450 1.1197 0.7021 0.7105 0.7030 0.7105
0.0175 10.0 480 1.1080 0.7892 0.7895 0.7811 0.7895
0.0169 10.62 510 1.1289 0.7337 0.7368 0.7331 0.7368
0.0028 11.25 540 1.1263 0.7243 0.7237 0.7184 0.7237
0.0023 11.88 570 1.2298 0.7103 0.7105 0.7042 0.7105
0.0019 12.5 600 1.2863 0.7103 0.7105 0.7042 0.7105
0.0017 13.12 630 1.2531 0.7375 0.7368 0.7345 0.7368
0.0016 13.75 660 1.3108 0.7103 0.7105 0.7042 0.7105
0.0015 14.38 690 1.3185 0.7375 0.7368 0.7345 0.7368
0.0014 15.0 720 1.3296 0.7375 0.7368 0.7345 0.7368
0.0012 15.62 750 1.3296 0.7375 0.7368 0.7345 0.7368
0.0012 16.25 780 1.3300 0.7375 0.7368 0.7345 0.7368
0.0012 16.88 810 1.2730 0.7677 0.7632 0.7640 0.7632
0.0011 17.5 840 1.2823 0.7677 0.7632 0.7640 0.7632
0.0011 18.12 870 1.3328 0.7375 0.7368 0.7345 0.7368
0.001 18.75 900 1.3341 0.7375 0.7368 0.7345 0.7368
0.001 19.38 930 1.3587 0.7375 0.7368 0.7345 0.7368
0.0009 20.0 960 1.3728 0.7375 0.7368 0.7345 0.7368
0.0009 20.62 990 1.3904 0.7375 0.7368 0.7345 0.7368
0.0008 21.25 1020 1.3928 0.7375 0.7368 0.7345 0.7368
0.0008 21.88 1050 1.3913 0.7375 0.7368 0.7345 0.7368
0.0008 22.5 1080 1.3853 0.7375 0.7368 0.7345 0.7368
0.0008 23.12 1110 1.3900 0.7375 0.7368 0.7345 0.7368
0.0008 23.75 1140 1.3935 0.7375 0.7368 0.7345 0.7368
0.0007 24.38 1170 1.4068 0.7375 0.7368 0.7345 0.7368
0.0008 25.0 1200 1.4144 0.7375 0.7368 0.7345 0.7368
0.0008 25.62 1230 1.4106 0.7375 0.7368 0.7345 0.7368
0.0008 26.25 1260 1.4165 0.7375 0.7368 0.7345 0.7368
0.0007 26.88 1290 1.4207 0.7375 0.7368 0.7345 0.7368
0.0007 27.5 1320 1.4236 0.7375 0.7368 0.7345 0.7368
0.0007 28.12 1350 1.4281 0.7375 0.7368 0.7345 0.7368
0.0007 28.75 1380 1.4204 0.7375 0.7368 0.7345 0.7368
0.0007 29.38 1410 1.4213 0.7375 0.7368 0.7345 0.7368
0.0007 30.0 1440 1.4205 0.7375 0.7368 0.7345 0.7368

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0