CoolFace
Modelpublic

pcam-interpretability/dino-vits16-val07869-vit-test

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes
Model Card

dino-vits16

Best Validation Accuracy: 0.7869

Metadata

  • Model Name: dino-vits16
  • Optimizer: adamw
  • Scheduler: cosine
  • Weight Decay: 0.05
  • Warmup Epochs: 5
  • Patience: 7
  • Amp: True
  • Seed: 42
  • Batch Size: 352
  • Initial Lr: 0.0006875
  • Total Epochs Ran: 1
  • Early Stopped: False
  • Training Time Seconds: 571.8525235652924
  • Num Parameters: 21666049
  • Device: NVIDIA A100-SXM4-40GB
  • Run Id: vit-test

Training Configuration

  • Epochs: 1
  • Batch size: 352
  • Learning rate (initial): 0.0006875

Training Logs (Per Epoch)

EpochTrain LossTrain AccVal LossVal AccLR
10.52840.77830.42720.78690.000137