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: TerraIncognita
	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: 1
	output_dir: sweep/ablation3/outputs/3006832643bc6de5cd8bdadf68836b19
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 50399791
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	trial_seed: 0
	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: 0.6880433961757358
	lambda2: 0.9840350138898164
	last_k_epoch: 0.33648211095401626
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3.599417945900826
	weight_decay: 0.0001
	worst_case_p: 0.25
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    
0.1930684000  0.1822530687  0.0672291062  0.0485232068  0.3311079728  0.3420647149  0.1479848866  0.1561712846  0.2041640110  0.1819727891  0.0000000000  5.3498301506  2.0074815750  0             1.4178915024 
0.3078293617  0.7045933469  0.7347745848  0.7162447257  0.7691616382  0.7791474063  0.6246851385  0.6183879093  0.3137879754  0.3018707483  3.0226700252  2.8646243318  2.2567677498  300           0.1600086999 
0.3333295394  0.8029773581  0.8642235697  0.8649789030  0.8261651046  0.8222907036  0.7437027708  0.7216624685  0.3452305078  0.3214285714  6.0453400504  2.4677830521  2.2567677498  600           0.1802877402 
0.3521372856  0.8167618336  0.8966517269  0.8723628692  0.8443959430  0.8335901387  0.7660579345  0.7443324937  0.3641385171  0.3401360544  9.0680100756  2.3160951591  2.2567677498  900           0.1782109276 
0.3556435160  0.8356432669  0.9090429739  0.8892405063  0.8585184234  0.8582434515  0.7953400504  0.7594458438  0.3685999575  0.3426870748  12.090680100  2.2032074463  2.2567677498  1200          0.1816940395 
0.3564935851  0.8471844779  0.9224887951  0.9029535865  0.8739247657  0.8715973292  0.8186397985  0.7670025189  0.3694497557  0.3435374150  15.113350125  2.0761621050  2.2567677498  1500          0.1814597138 
0.3594678788  0.8614446461  0.9346163986  0.9135021097  0.8806008473  0.8710837185  0.8441435768  0.7997481108  0.3753983429  0.3435374150  18.136020151  1.9849351470  2.2567677498  1800          0.1791122413 
0.3656321673  0.8686910730  0.9456894279  0.9166666667  0.8892027218  0.8808423215  0.8605163728  0.8085642317  0.3775228383  0.3537414966  21.158690176  1.9165676494  2.2567677498  2100          0.1799110619 
0.3675447551  0.8755395566  0.9525441603  0.9293248945  0.8948517140  0.8849512070  0.8828715365  0.8123425693  0.3796473338  0.3554421769  24.181360201  1.8175585838  2.2567677498  2400          0.1830024807 
0.3724319076  0.8879261572  0.9567624572  0.9367088608  0.9025548851  0.9008731382  0.8929471033  0.8261964736  0.3868706182  0.3579931973  27.204030226  1.7603491982  2.2567677498  2700          0.1791801667 
0.3777453140  0.8952468822  0.9615080411  0.9451476793  0.9116703043  0.8967642527  0.8986146096  0.8438287154  0.3906947100  0.3647959184  30.226700251  1.6791175421  2.2567677498  3000          0.1791049552 
0.3797638556  0.8912533229  0.9662536251  0.9419831224  0.9134677109  0.8967642527  0.9124685139  0.8350125945  0.3938814532  0.3656462585  33.249370277  1.6541690735  2.2567677498  3300          0.1780541547 
0.3853956654  0.9010854214  0.9694173477  0.9388185654  0.9179612274  0.9054956343  0.9171914358  0.8589420655  0.3991926917  0.3715986395  36.272040302  1.2634231933  5.3975014687  3600          0.2172813892 
0.3858208355  0.9052942025  0.9694173477  0.9451476793  0.9210424958  0.9054956343  0.9209697733  0.8652392947  0.3991926917  0.3724489796  39.294710327  1.1811220137  5.3975014687  3900          0.2212012458 
0.3867763165  0.9048277201  0.9720537833  0.9430379747  0.9237386057  0.9162814587  0.9304156171  0.8551637280  0.4028043340  0.3707482993  42.317380352  1.1689512904  5.3975014687  4200          0.2210338767 
0.3902830888  0.9090457115  0.9760084366  0.9504219409  0.9265631018  0.9152542373  0.9272670025  0.8614609572  0.4055661780  0.3750000000  45.340050377  1.1472170222  5.3975014687  4500          0.2190846165 
0.3911328870  0.9163203849  0.9781175850  0.9535864979  0.9268198742  0.9162814587  0.9313602015  0.8790931990  0.4072657744  0.3750000000  48.362720403  1.1376241601  5.3975014687  4800          0.2183295576 
0.3915577861  0.9166038045  0.9757447930  0.9556962025  0.9290024393  0.9162814587  0.9363979849  0.8778337531  0.4081155726  0.3750000000  50.377833753  1.1240961701  5.3975014687  5000          0.2179115677 
