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: [2]
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: 3
	output_dir: sweep/ablation3/outputs/25c26ead66f9f9e8e85523d2cd151ee7
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 823278103
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	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: 0.5694511041907044
	lambda2: 0.6621108818243455
	last_k_epoch: 0.20248994529588413
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.502579147595572
	weight_decay: 0.0001
	worst_case_p: 0.2
using augment transform
using augment transform
using normal 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    
0.0768261964  0.0389860163  0.0392828895  0.0379746835  0.0404416485  0.0364663585  0.0856423174  0.0680100756  0.0380284682  0.0425170068  0.0000000000  5.4959268570  1.7946186066  0             1.5236179829 
0.3454030225  0.5800172924  0.6490904297  0.6708860759  0.5896777507  0.5819209040  0.3419395466  0.3488664987  0.4896961972  0.4872448980  3.0226700252  3.0309624306  2.0947899818  300           0.1511705589 
0.3487090678  0.7283812933  0.8083311363  0.8006329114  0.7522146617  0.7416538264  0.3598866499  0.3375314861  0.6443594646  0.6428571429  6.0453400504  2.5982926647  2.0947899818  600           0.1754411642 
0.3773614608  0.7670983252  0.8375955708  0.8280590717  0.7923995378  0.7853107345  0.3781486146  0.3765743073  0.6934353091  0.6879251701  9.0680100756  2.4699455794  2.0947899818  900           0.1745564214 
0.4096347605  0.7855715753  0.8660690746  0.8481012658  0.8151238927  0.7858243451  0.4086901763  0.4105793451  0.7233906947  0.7227891156  12.090680100  2.3830858541  2.0947899818  1200          0.1744795076 
0.4305730476  0.8010913815  0.8805694701  0.8512658228  0.8264218770  0.8156137648  0.4291561713  0.4319899244  0.7429360527  0.7363945578  15.113350125  2.2993529129  2.0947899818  1500          0.1759752186 
0.4384445842  0.8114334134  0.8916424993  0.8734177215  0.8379766337  0.8202362609  0.4461586902  0.4307304786  0.7665179520  0.7406462585  18.136020151  2.2226274061  2.0947899818  1800          0.1792468405 
0.4543450879  0.8246868677  0.9069338255  0.8860759494  0.8513287970  0.8294812532  0.4590680101  0.4496221662  0.7862757595  0.7585034014  21.158690176  2.1587468791  2.0947899818  2100          0.1754200141 
0.4576511333  0.8331653747  0.9143158450  0.8860759494  0.8609577609  0.8438623523  0.4644206549  0.4508816121  0.8077331634  0.7695578231  24.181360201  2.0961992824  2.0947899818  2400          0.1735491904 
0.4664672542  0.8390266697  0.9238070129  0.8913502110  0.8726409038  0.8536209553  0.4770151134  0.4559193955  0.8138942001  0.7721088435  27.204030226  2.0581363277  2.0947899818  2700          0.1859368022 
0.4762279595  0.8489108890  0.9290798840  0.8987341772  0.8746950828  0.8520801233  0.4852015113  0.4672544081  0.8219672828  0.7959183673  30.226700251  1.9917116884  2.0947899818  3000          0.1748213196 
0.4811083121  0.8582550498  0.9380437648  0.9113924051  0.8798305302  0.8623523369  0.4924433249  0.4697732997  0.8408752921  0.8010204082  33.249370277  1.9145325069  2.0947899818  3300          0.1773682761 
0.4927581862  0.8647821468  0.9364619035  0.9103375527  0.8843240467  0.8710837185  0.5018891688  0.4836272040  0.8534098152  0.8129251701  36.272040302  1.8641886028  2.0947899818  3600          0.1799043830 
0.5009445841  0.8670005620  0.9483258634  0.9156118143  0.8933110797  0.8741653826  0.5119647355  0.4899244332  0.8527724665  0.8112244898  39.294710327  1.8225777300  2.0947899818  3900          0.1773973624 
0.5062972290  0.8768761625  0.9530714474  0.9261603376  0.8983181410  0.8787878788  0.5176322418  0.4949622166  0.8684937327  0.8256802721  42.317380352  1.3336116018  5.4006600380  4200          0.2079573472 
0.5125944582  0.8791274606  0.9612443976  0.9229957806  0.8985749133  0.8870056497  0.5251889169  0.5000000000  0.8765668154  0.8273809524  45.340050377  1.0834329134  5.4006600380  4500          0.2184137265 
0.5188916874  0.8882649642  0.9615080411  0.9335443038  0.9060213121  0.8911145352  0.5314861461  0.5062972292  0.8765668154  0.8401360544  48.362720403  1.0637870292  5.4006600380  4800          0.2181122684 
0.5201511332  0.8864641922  0.9673081993  0.9314345992  0.9085890358  0.8818695429  0.5352644836  0.5050377834  0.8833652008  0.8460884354  50.377833753  1.0341105589  5.4006600380  5000          0.2214493191 
