Environment:
	Python: 3.10.11
	PyTorch: 2.0.1
	Torchvision: 0.15.2
	CUDA: 11.7
	CUDNN: 8500
	NumPy: 1.24.3
	PIL: 9.4.0
	Testing environment: [1]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: PACS
	holdout_fraction: 0.2
	hparams: {
    "resnet18": false,
    "resnet_dropout": 0,
    "nonlinear_classifier": false,
    "data_augmentation": true,
    "clip_backbone": "ViT-B/32",
    "student_model": "resnet",
    "SMA": true,
    "batch_size": 32
}
	hparams_seed: 0
	output_dir: sweep/ablation3/outputs/89f336e9c3fd2d1b94542700e3eecd25
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 8966537
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	trial_seed: 1
	uda_holdout_fraction: 0
	visualize: False
Not saving models
HParams:
	SMA: True
	batch_size: 32
	class_balanced: False
	clip_backbone: ViT-B/32
	data_augmentation: True
	lambda1: 0.5
	lambda2: 0.5
	last_k_epoch: 0.25
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3
	weight_decay: 0.0
	worst_case_p: 0.3333333333333333
using augment transform
using normal transform
using augment transform
using augment transform
using device:  cuda
Using ViT-B/32...
constructing student model
using resnet 50
Using SMA
n_steps 5001
checkpoint_freq 300
agg_test_acc  agg_val_acc   env0_in_acc   env0_out_acc  env1_in_acc   env1_out_acc  env2_in_acc   env2_out_acc  env3_in_acc   env3_out_acc  epoch         loss          mem_gb        step          step_time    
0.1085893791  0.1264685771  0.1677852349  0.1613691932  0.1103411514  0.1068376068  0.0553892216  0.0868263473  0.1574427481  0.1312101911  0.0000000000  7.2505226135  2.3338298798  0             1.6455798149 
0.8102937688  0.9610929354  0.9823062843  0.9462102689  0.8150319829  0.8055555556  0.9977544910  0.9880239521  0.9583333333  0.9490445860  7.1856287425  1.7426375089  2.5990204811  300           0.1597740444 
0.8383175692  0.9688281758  0.9963392312  0.9608801956  0.8347547974  0.8418803419  0.9992514970  0.9940119760  0.9761450382  0.9515923567  14.371257485  0.7697945485  2.5990204811  600           0.1818960730 
0.8463201388  0.9697116937  0.9981696156  0.9584352078  0.8443496802  0.8482905983  0.9992514970  0.9940119760  0.9809160305  0.9566878981  21.556886227  0.6623307681  2.5990204811  900           0.1817959507 
0.8455160093  0.9641798206  0.9981696156  0.9486552567  0.8470149254  0.8440170940  1.0000000000  0.9910179641  0.9869592875  0.9528662420  28.742514970  0.6241131635  2.5990204811  1200          0.1820103049 
0.8471197124  0.9745214441  0.9957291031  0.9682151589  0.8459488273  0.8482905983  1.0000000000  0.9910179641  0.9914122137  0.9643312102  35.928143712  0.5983288038  2.5990204811  1500          0.1816600545 
0.8433838131  0.9732818197  0.9981696156  0.9657701711  0.8427505330  0.8440170940  0.9992514970  0.9910179641  0.9904580153  0.9630573248  43.113772455  0.5797016638  2.5990204811  1800          0.1812800988 
0.8465889413  0.9693555872  0.9993898719  0.9535452323  0.8427505330  0.8504273504  0.9985029940  0.9940119760  0.9907760814  0.9605095541  50.299401197  0.5578673741  2.5990204811  2100          0.1900016061 
0.8465889413  0.9699875750  0.9993898719  0.9584352078  0.8427505330  0.8504273504  0.9992514970  0.9910179641  0.9923664122  0.9605095541  57.485029940  0.5513244921  2.5990204811  2400          0.1875157841 
0.8447209917  0.9777913374  1.0000000000  0.9682151589  0.8411513859  0.8482905983  1.0000000000  0.9970059880  0.9930025445  0.9681528662  64.670658682  0.5352974822  2.5990204811  2700          0.1848883120 
0.8423177150  0.9704122035  0.9993898719  0.9584352078  0.8406183369  0.8440170940  1.0000000000  0.9910179641  0.9961832061  0.9617834395  71.856287425  0.5155236652  2.5990204811  3000          0.1854799461 
0.8404474874  0.9780428674  0.9993898719  0.9608801956  0.8411513859  0.8397435897  1.0000000000  1.0000000000  0.9958651399  0.9732484076  79.041916167  0.5174602080  2.5990204811  3300          0.1820259110 
0.8455205652  0.9698730889  1.0000000000  0.9559902200  0.8427505330  0.8482905983  1.0000000000  0.9880239521  0.9958651399  0.9656050955  86.227544910  0.5096665039  2.5990204811  3600          0.1801805162 
0.8449852382  0.9765517130  0.9987797437  0.9657701711  0.8438166311  0.8461538462  1.0000000000  0.9970059880  0.9968193384  0.9668789809  93.413173652  0.4123672923  5.3941302299  3900          0.1948269494 
0.8455205652  0.9750948196  1.0000000000  0.9682151589  0.8427505330  0.8482905983  1.0000000000  0.9940119760  0.9961832061  0.9630573248  100.59880239  0.2858877290  5.3941302299  4200          0.2081159790 
0.8420489125  0.9764831911  1.0000000000  0.9706601467  0.8422174840  0.8418803419  1.0000000000  0.9970059880  0.9965012723  0.9617834395  107.78443113  0.2686382631  5.3941302299  4500          0.2131169017 
0.8428484861  0.9735919620  1.0000000000  0.9633251834  0.8438166311  0.8418803419  1.0000000000  0.9880239521  0.9961832061  0.9694267516  114.97005988  0.2553541904  5.3941302299  4800          0.2161566901 
0.8436503376  0.9695169824  1.0000000000  0.9511002445  0.8432835821  0.8440170940  1.0000000000  0.9880239521  0.9974554707  0.9694267516  119.76047904  0.2532947955  5.3941302299  5000          0.2139474165 
