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: 4
	output_dir: sweep/ablation3/outputs/9e3f9ccae9f546ca46927b7e2e127be5
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1284248858
	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: 0.8001163740830898
	lambda2: 0.7340462818445315
	last_k_epoch: 0.3149495809125332
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.8284464949429635
	weight_decay: 1e-06
	worst_case_p: 0.2
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    
0.1289991458  0.0598883531  0.0160822568  0.0242616034  0.0249069200  0.0256805342  0.1549118388  0.1297229219  0.1253452305  0.1326530612  0.0000000000  5.3987855911  1.7946186066  0             1.4950428009 
0.2062486721  0.5925965045  0.6016345900  0.6118143460  0.7198613429  0.7226502311  0.4852015113  0.4433249370  0.2041640110  0.2083333333  3.0226700252  2.9983913652  2.0937752724  300           0.1536165659 
0.2820121355  0.7236005272  0.7969944635  0.7805907173  0.7718577481  0.7781201849  0.6700251889  0.6120906801  0.2766093053  0.2874149660  6.0453400504  2.6133043996  2.0937752724  600           0.1778554519 
0.3074082563  0.7590826399  0.8423411548  0.8090717300  0.8060084735  0.7981510015  0.7213476071  0.6700251889  0.3010410028  0.3137755102  9.0680100756  2.4597343143  2.0937752724  900           0.1750255084 
0.3197330396  0.7940916214  0.8621144213  0.8607594937  0.8211580434  0.8212634823  0.7374055416  0.7002518892  0.3171871680  0.3222789116  12.090680100  2.3746446208  2.0937752724  1200          0.1782811006 
0.3416226591  0.8131673612  0.8832059056  0.8808016878  0.8325844139  0.8294812532  0.7632241814  0.7292191436  0.3380072233  0.3452380952  15.113350125  2.2888309407  2.0937752724  1500          0.1803485044 
0.3615994197  0.8149939206  0.8974426575  0.8691983122  0.8433688535  0.8402670776  0.7931360202  0.7355163728  0.3575525813  0.3656462585  18.136020151  2.2429383965  2.0937752724  1800          0.1770276419 
0.3749861798  0.8334913032  0.9111521223  0.8976793249  0.8589035820  0.8433487417  0.8113979849  0.7594458438  0.3766730402  0.3732993197  21.158690176  2.1653985190  2.0937752724  2100          0.1729315424 
0.3802987732  0.8398035017  0.9238070129  0.8924050633  0.8671202979  0.8448895737  0.8189546599  0.7821158690  0.3830465264  0.3775510204  24.181360201  2.1097139561  2.0937752724  2400          0.1675501919 
0.3925184157  0.8524067420  0.9298708147  0.9082278481  0.8752086276  0.8618387262  0.8479219144  0.7871536524  0.3955810495  0.3894557823  27.204030226  2.0236642957  2.0937752724  2700          0.1690099621 
0.4013375106  0.8584248053  0.9409438439  0.9219409283  0.8807292335  0.8649203903  0.8548488665  0.7884130982  0.4055661780  0.3971088435  30.226700251  1.9845891571  2.0937752724  3000          0.1701003512 
0.4078188475  0.8634507295  0.9496440812  0.9219409283  0.8877904737  0.8762198254  0.8608312343  0.7921914358  0.4134268111  0.4022108844  33.249370277  1.9171506429  2.0937752724  3300          0.1672891823 
0.4150451128  0.8705044221  0.9517532296  0.9282700422  0.8924123764  0.8746789933  0.8709068010  0.8085642317  0.4185256002  0.4115646259  36.272040302  1.5619762743  5.4010052681  3600          0.1905226787 
0.4199336201  0.8748383551  0.9533350910  0.9293248945  0.9002439338  0.8803287108  0.8847607053  0.8148614610  0.4214998938  0.4183673469  39.294710327  1.3069226837  5.4010052681  3900          0.2109381636 
0.4209966808  0.8746159565  0.9638808331  0.9272151899  0.8993452305  0.8767334361  0.8913727960  0.8198992443  0.4210749947  0.4209183673  42.317380352  1.2757210362  5.4010052681  4200          0.2155715179 
0.4217394413  0.8842817207  0.9612443976  0.9367088608  0.9037103608  0.8823831536  0.8875944584  0.8337531486  0.4251115360  0.4183673469  45.340050377  1.2485333796  5.4010052681  4500          0.2151358700 
0.4253527094  0.8844658602  0.9654626944  0.9293248945  0.9082038773  0.8890600924  0.8976700252  0.8350125945  0.4272360314  0.4234693878  48.362720403  1.2351800227  5.4010052681  4800          0.2197323012 
0.4248213145  0.8856625929  0.9651990509  0.9398734177  0.9057645397  0.8808423215  0.9008186398  0.8362720403  0.4270235819  0.4226190476  50.377833753  1.2304949147  5.4010052681  5000          0.2176326561 
