CoolFace
Modelpublic

pcam-interpretability/dino-vits16-val08483-vit-tuned-sota

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

dino-vits16

Best Validation Accuracy: 0.8483

Metadata

  • —Model Name: dino-vits16
  • —Optimizer: adamw
  • —Scheduler: cosine
  • —Weight Decay: 0.001
  • —Warmup Epochs: 10
  • —Patience: 10
  • —Amp: True
  • —Seed: 42
  • —Batch Size: 352
  • —Initial Lr: 0.001
  • —Total Epochs Ran: 17
  • —Early Stopped: True
  • —Training Time Seconds: 9935.389509916306
  • —Num Parameters: 21666049
  • —Device: NVIDIA A100-SXM4-40GB
  • —Run Id: vit-tuned-sota

Training Configuration

  • —Epochs: 17
  • —Batch size: 352
  • —Learning rate (initial): 0.001

Training Logs (Per Epoch)

EpochTrain LossTrain AccVal LossVal AccLR
10.57600.73940.49600.74630.000100
20.42350.80450.41660.79990.000200
30.39900.81910.42400.79020.000300
40.38270.82730.35520.83080.000400
50.37450.83150.39660.80940.000500
60.37160.83280.42550.79250.000600
70.36320.83750.33600.84830.000700
80.36030.83970.41310.79900.000800
90.35620.84180.36420.82950.000900
100.35050.84420.38850.80940.001000
110.34320.84900.41650.79990.001000
120.33810.85140.37540.82930.001000
130.33340.85360.36110.83450.000999
140.32920.85570.42040.81090.000998
150.32050.85980.36870.83430.000996
16nan0.85880.38620.82300.000994
170.31470.86360.37940.83280.000991