CoolFace
Modelpublic

popkek00/fall-detection-ft

sourceHugging Faceupdated 5mo agoView on Hugging Face
0likes14downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

fall-detection-ft

This model is a fine-tuned version of popkek00/trainer_output on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5574
  • Accuracy: 0.7395
  • F1: 0.8437

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
  • trainbatchsize: 128
  • evalbatchsize: 128
  • seed: 42
  • optimizer: Use adamwtorchfused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lrschedulertype: linear
  • lrschedulerwarmup_ratio: 0.1
  • num_epochs: 15

Training results

Training LossEpochStepValidation LossAccuracyF1
0.57341.0420.59550.71110.8310
0.59982.0840.61130.69390.8116
0.57253.01260.55740.73950.8437
0.51454.01680.54870.74630.8371
0.54275.02100.53890.73800.8344
0.4996.02520.55320.72460.8045
0.48377.02940.60000.68260.7599
0.49658.03360.57120.70810.7921
0.45059.03780.66170.63470.7182
0.453310.04200.71540.61680.6784
0.458811.04620.64550.65490.7331
0.425112.05040.68850.60930.6713
0.414313.05460.65690.62650.7007
0.403114.05880.71440.59360.6574
0.401115.06300.69770.60330.6696

Framework versions

  • Transformers 4.57.6
  • Pytorch 2.10.0+cu128
  • Datasets 4.8.4
  • Tokenizers 0.22.2