benchmark supervised again

newsearch.py

@@ -27,12 +27,12 @@ learning_rate_values = [1e-3]
 # learning_rate_values = [5e-4]
 
 # alpha_values = [0, .25, 0.5, 0.75, 1]  # alpha = 0 is unsupervised. alpha = 1 is supervised.
-alpha_values = [0]
+alpha_values = [1.0]
 # widths = [2**k for k in range(4, 13)]
 # depths = [1, 2, 4, 8, 16]
 widths, depths = [512], [4]
 
-batch_size_values = [64, 256, 1024]
+batch_size_values = [256]
 max_epochs_values = [100]
 seeds = list(range(21, 1992))
 optimizers = [
@@ -73,7 +73,7 @@ for idx, params in enumerate(search_params):
 python newmain.py fit \
 --seed_everything {s} \
 --data.batch_size {bs} \
---data.train_size 50000 \
+--data.train_size 0 \
 --data.val_size 10000 \
 --model.alpha {a} \
 --model.width {w} \
@@ -90,13 +90,13 @@ python newmain.py fit \
 --trainer.callbacks.init_args.save_interval 0 \
 --optimizer torch.optim.{opt} \
 --optimizer.init_args.lr {lr} \
---trainer.callbacks+ lightning.pytorch.callbacks.LearningRateFinder \
---lr_scheduler lightning.pytorch.cli.ReduceLROnPlateau \
---lr_scheduler.init_args.monitor hp_metric \
---lr_scheduler.init_args.factor 0.05 \
---lr_scheduler.init_args.patience 5 \
---lr_scheduler.init_args.cooldown 10 \
---lr_scheduler.init_args.verbose true
+--trainer.callbacks+ lightning.pytorch.callbacks.LearningRateFinder
+# --lr_scheduler lightning.pytorch.cli.ReduceLROnPlateau \
+# --lr_scheduler.init_args.monitor hp_metric \
+# --lr_scheduler.init_args.factor 0.05 \
+# --lr_scheduler.init_args.patience 5 \
+# --lr_scheduler.init_args.cooldown 10 \
+# --lr_scheduler.init_args.verbose true
 """
     # job_name = f"color2_{bs}_{a}_{lr:2.2e}"
     # job_plugin.run(cmd, machine=Machine.T4, name=job_name)