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: [3]
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/00542f9600a4b2cf6c7ef4b54ce4e5a3
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 360901255
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	trial_seed: 2
	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 augment transform
using augment transform
using normal 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    
0.2493636650  0.1451245837  0.1092129347  0.1100244499  0.1503198294  0.1666666667  0.1489520958  0.1586826347  0.2490458015  0.2496815287  0.0000000000  6.5833616257  2.3338298798  0             1.9102880955 
0.7574812398  0.9655277972  0.9847467968  0.9559902200  0.9776119403  0.9465811966  0.9992514970  0.9940119760  0.7544529262  0.7605095541  7.1856287425  1.7407022539  2.5978608131  300           0.1588927738 
0.7598691671  0.9727530496  0.9945088469  0.9584352078  0.9920042644  0.9658119658  0.9992514970  0.9940119760  0.7554071247  0.7643312102  14.371257485  0.6300510843  2.5978608131  600           0.1802951797 
0.7706866579  0.9778260332  0.9993898719  0.9706601467  0.9946695096  0.9658119658  0.9992514970  0.9970059880  0.7719465649  0.7694267516  21.556886227  0.5400535656  2.5978608131  900           0.1806343198 
0.7854888896  0.9738917977  0.9987797437  0.9584352078  0.9968017058  0.9722222222  0.9992514970  0.9910179641  0.7824427481  0.7885350318  28.742514970  0.5058576150  2.5978608131  1200          0.1819252682 
0.7931289602  0.9775177975  0.9987797437  0.9633251834  0.9978678038  0.9722222222  1.0000000000  0.9970059880  0.7875318066  0.7987261146  35.928143712  0.4750808327  2.5978608131  1500          0.1820433633 
0.7991770794  0.9789422990  0.9987797437  0.9633251834  0.9989339019  0.9764957265  1.0000000000  0.9970059880  0.7919847328  0.8063694268  43.113772455  0.4595004830  2.5978608131  1800          0.1820845819 
0.8020421059  0.9833030319  0.9993898719  0.9755501222  0.9984008529  0.9743589744  0.9992514970  1.0000000000  0.7938931298  0.8101910828  50.299401197  0.4499690199  2.5978608131  2100          0.1809531029 
0.8128636485  0.9822022827  0.9993898719  0.9731051345  0.9989339019  0.9764957265  1.0000000000  0.9970059880  0.8040712468  0.8216560510  57.485029940  0.4402344431  2.5978608131  2400          0.1818238831 
0.8184322373  0.9803668004  0.9981696156  0.9633251834  0.9989339019  0.9807692308  1.0000000000  0.9970059880  0.8113867684  0.8254777070  64.670658682  0.4193005152  2.5978608131  2700          0.1828286958 
0.8219333961  0.9829145334  0.9993898719  0.9731051345  0.9994669510  0.9786324786  0.9992514970  0.9970059880  0.8145674300  0.8292993631  71.856287425  0.4116000135  2.5978608131  3000          0.1816678762 
0.8241590489  0.9758455418  1.0000000000  0.9608801956  0.9994669510  0.9786324786  1.0000000000  0.9880239521  0.8202926209  0.8280254777  79.041916167  0.4151692338  2.5978608131  3300          0.1817745233 
0.8262264789  0.9837295293  1.0000000000  0.9755501222  0.9984008529  0.9786324786  0.9992514970  0.9970059880  0.8244274809  0.8280254777  86.227544910  0.4025566121  2.5978608131  3600          0.1822033469 
0.8281373069  0.9845220429  1.0000000000  0.9706601467  0.9994669510  0.9829059829  1.0000000000  1.0000000000  0.8244274809  0.8318471338  93.413173652  0.3547059937  5.3948016167  3900          0.1962821420 
0.8284553731  0.9853370388  1.0000000000  0.9731051345  1.0000000000  0.9829059829  1.0000000000  1.0000000000  0.8250636132  0.8318471338  100.59880239  0.2661113283  5.3948016167  4200          0.2100785422 
0.8282955296  0.9877820266  1.0000000000  0.9804400978  1.0000000000  0.9829059829  1.0000000000  1.0000000000  0.8260178117  0.8305732484  107.78443113  0.2469091148  5.3948016167  4500          0.2114084148 
0.8282947193  0.9840152826  0.9993898719  0.9755501222  0.9984008529  0.9764957265  1.0000000000  1.0000000000  0.8272900763  0.8292993631  114.97005988  0.2312469126  5.3948016167  4800          0.2126704788 
0.8294087612  0.9843390348  1.0000000000  0.9731051345  1.0000000000  0.9829059829  1.0000000000  0.9970059880  0.8282442748  0.8305732484  119.76047904  0.2217393868  5.3948016167  5000          0.2145333028 
