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: 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: 4
	output_dir: sweep/ablation3/outputs/72f25ce0afe2606439a34dcf98c9b4bf
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 226729564
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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: 0.5122476832929141
	lambda2: 0.9892716333303577
	last_k_epoch: 0.2899069879248226
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.19589595208549
	weight_decay: 0.0001
	worst_case_p: 0.3
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    
0.0048789718  0.1381078220  0.0195096230  0.0263713080  0.0051354474  0.0046224961  0.1923803526  0.2178841310  0.1665604419  0.1700680272  0.0000000000  4.8746347427  2.1692652702  0             1.4388921261 
0.2383000586  0.6337952980  0.7418929607  0.7035864979  0.2382847606  0.2383153570  0.5931989924  0.5591939547  0.6144040790  0.6386054422  3.0226700252  2.6220733905  2.4381909370  300           0.1617119535 
0.2489561450  0.7582387255  0.8528868969  0.8449367089  0.2590833226  0.2388289676  0.7540931990  0.7052896725  0.7176545570  0.7244897959  6.0453400504  2.1960663148  2.4381909370  600           0.1785713180 
0.2971685207  0.7850198713  0.8921697864  0.8670886076  0.3031197843  0.2912172573  0.7742443325  0.7430730479  0.7597195666  0.7448979592  9.0680100756  2.0308102465  2.4381909370  900           0.1864767536 
0.3202151928  0.8121847632  0.9103611917  0.8902953586  0.3281550905  0.3122752953  0.8057304786  0.7732997481  0.7841512641  0.7729591837  12.090680100  1.8917909332  2.4381909370  1200          0.1813209573 
0.3432619967  0.8172761216  0.9259161613  0.8881856540  0.3511362177  0.3353877761  0.8378463476  0.7770780856  0.8068833652  0.7865646259  15.113350125  1.7953421032  2.4381909370  1500          0.1808424266 
0.3612374145  0.8341435371  0.9414711310  0.9008438819  0.3660290153  0.3564458141  0.8520151134  0.8022670025  0.8336520076  0.7993197279  18.136020151  1.6932085264  2.4381909370  1800          0.1850500393 
0.3743336956  0.8468703424  0.9493804376  0.9082278481  0.3783540891  0.3703133025  0.8655541562  0.8211586902  0.8449118334  0.8112244898  21.158690176  1.6288379117  2.4381909370  2100          0.1873852118 
0.3811386250  0.8573148969  0.9559715265  0.9187763713  0.3847733984  0.3775038521  0.8809823678  0.8249370277  0.8578712556  0.8282312925  24.181360201  1.5298764571  2.4381909370  2400          0.1886711017 
0.3849904744  0.8634075055  0.9543896652  0.9240506329  0.3883682116  0.3816127375  0.8932619647  0.8387909320  0.8655194391  0.8273809524  27.204030226  1.4858742261  2.4381909370  2700          0.1868398960 
0.3906397962  0.8706300418  0.9612443976  0.9240506329  0.3945307485  0.3867488444  0.8989294710  0.8400503778  0.8742298704  0.8477891156  30.226700251  1.4218451718  2.4381909370  3000          0.1885067217 
0.3930791997  0.8806693768  0.9667809122  0.9377637131  0.3983823341  0.3877760657  0.9124685139  0.8539042821  0.8831527512  0.8503401361  33.249370277  1.3902500769  2.4381909370  3300          0.1875481025 
0.3949409313  0.8786959594  0.9702082784  0.9377637131  0.4000513545  0.3898305085  0.9244332494  0.8513853904  0.8886764393  0.8469387755  36.272040302  1.3334263082  5.3977379799  3600          0.1918067853 
0.3929507805  0.8841963421  0.9696809913  0.9419831224  0.3986391064  0.3872624551  0.9256926952  0.8551637280  0.8946250266  0.8554421769  39.294710327  1.0585742996  5.3977379799  3900          0.2205007656 
0.3930792327  0.8908197479  0.9733720011  0.9504219409  0.3978687893  0.3882896764  0.9345088161  0.8589420655  0.9007860633  0.8630952381  42.317380352  1.0291934643  5.3977379799  4200          0.2173496588 
0.3918594650  0.8915591874  0.9749538624  0.9409282700  0.3969700860  0.3867488444  0.9341939547  0.8740554156  0.9033354578  0.8596938776  45.340050377  1.0047278710  5.3977379799  4500          0.2185695076 
0.3895482829  0.8928974865  0.9746902188  0.9440928270  0.3959429965  0.3831535696  0.9373425693  0.8740554156  0.9071595496  0.8605442177  48.362720403  0.9977960992  5.3977379799  4800          0.2159968980 
0.3889704791  0.8960621248  0.9802267335  0.9472573840  0.3958146103  0.3821263482  0.9370277078  0.8778337531  0.9145952836  0.8630952381  50.377833753  0.9853373808  5.3977379799  5000          0.2145549524 
