Hugging Face's logo

SharonTudi
/
CONTEXT_one

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
CONTEXT_one / README.md
SharonTudi's picture
SharonTudi
End of training
0399e96 verified
preview code
|
raw
history blame
5.85 kB
metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: CONTEXT_one
    results: []

CONTEXT_one

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

  • Loss: 1.1031
  • Precision: 0.8202
  • Recall: 0.8158
  • F1: 0.8134
  • Accuracy: 0.8158

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
1.3141 0.62 30 1.1728 0.4060 0.4868 0.4214 0.4868
0.8655 1.25 60 0.8567 0.7238 0.7237 0.7207 0.7237
0.6189 1.88 90 0.6433 0.7395 0.7368 0.7361 0.7368
0.4575 2.5 120 0.6314 0.7661 0.7632 0.7625 0.7632
0.3123 3.12 150 0.6091 0.7636 0.7632 0.7621 0.7632
0.215 3.75 180 0.6095 0.7769 0.7763 0.7758 0.7763
0.2901 4.38 210 0.6833 0.7409 0.7368 0.7367 0.7368
0.2169 5.0 240 0.6651 0.8354 0.8289 0.8285 0.8289
0.1721 5.62 270 0.6578 0.8530 0.8421 0.8416 0.8421
0.2103 6.25 300 0.7525 0.7506 0.75 0.7481 0.75
0.1021 6.88 330 0.6357 0.8725 0.8684 0.8681 0.8684
0.1115 7.5 360 1.0796 0.7510 0.75 0.7452 0.75
0.05 8.12 390 0.6933 0.8444 0.8289 0.8264 0.8289
0.0419 8.75 420 0.7248 0.8295 0.8158 0.8135 0.8158
0.0521 9.38 450 1.0193 0.7867 0.7895 0.7848 0.7895
0.0197 10.0 480 0.7878 0.7867 0.7895 0.7848 0.7895
0.0165 10.62 510 1.3815 0.7232 0.7105 0.6969 0.7105
0.0321 11.25 540 0.9198 0.7867 0.7895 0.7848 0.7895
0.0202 11.88 570 0.9919 0.8044 0.8026 0.7993 0.8026
0.0046 12.5 600 1.1230 0.7622 0.7632 0.7528 0.7632
0.0044 13.12 630 0.8484 0.8579 0.8553 0.8551 0.8553
0.0019 13.75 660 1.0979 0.7925 0.7895 0.7855 0.7895
0.0018 14.38 690 1.3561 0.7480 0.75 0.7438 0.75
0.0021 15.0 720 1.0228 0.8006 0.8026 0.7991 0.8026
0.0014 15.62 750 0.9298 0.8422 0.8421 0.8413 0.8421
0.0014 16.25 780 0.9537 0.8276 0.8289 0.8274 0.8289
0.0012 16.88 810 0.9708 0.8276 0.8289 0.8274 0.8289
0.0013 17.5 840 1.0009 0.8276 0.8289 0.8274 0.8289
0.0011 18.12 870 0.9999 0.8037 0.8026 0.7997 0.8026
0.0011 18.75 900 0.9871 0.8037 0.8026 0.7997 0.8026
0.001 19.38 930 0.9885 0.8276 0.8289 0.8274 0.8289
0.001 20.0 960 1.0078 0.8276 0.8289 0.8274 0.8289
0.0009 20.62 990 1.0204 0.8037 0.8026 0.7997 0.8026
0.0008 21.25 1020 1.0312 0.8037 0.8026 0.7997 0.8026
0.0008 21.88 1050 1.0438 0.8037 0.8026 0.7997 0.8026
0.0008 22.5 1080 1.0647 0.8037 0.8026 0.7997 0.8026
0.0008 23.12 1110 1.0633 0.8202 0.8158 0.8134 0.8158
0.0007 23.75 1140 1.0661 0.8202 0.8158 0.8134 0.8158
0.0008 24.38 1170 1.0871 0.8202 0.8158 0.8134 0.8158
0.0007 25.0 1200 1.0965 0.8202 0.8158 0.8134 0.8158
0.0007 25.62 1230 1.0893 0.8202 0.8158 0.8134 0.8158
0.0007 26.25 1260 1.0935 0.8202 0.8158 0.8134 0.8158
0.0007 26.88 1290 1.0942 0.8202 0.8158 0.8134 0.8158
0.0007 27.5 1320 1.0949 0.8202 0.8158 0.8134 0.8158
0.0007 28.12 1350 1.0937 0.8202 0.8158 0.8134 0.8158
0.0007 28.75 1380 1.0986 0.8202 0.8158 0.8134 0.8158
0.0007 29.38 1410 1.1030 0.8202 0.8158 0.8134 0.8158
0.0007 30.0 1440 1.1031 0.8202 0.8158 0.8134 0.8158

Framework versions

  • Transformers 4.37.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1