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: 4
	output_dir: sweep/ablation3/outputs/f7fbee3ac17f33407140db1297014e65
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1675575450
	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: 0.5122476832929141
	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 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    
0.0292821159  0.0864823112  0.1175850250  0.1086497890  0.1116959815  0.1201848998  0.0321158690  0.0264483627  0.0359039728  0.0306122449  0.0000000000  5.3150649071  2.1692652702  0             1.4358806610 
0.4090050376  0.7097622869  0.8020036910  0.7837552743  0.7651816665  0.7621982537  0.4137279597  0.4042821159  0.5876354366  0.5833333333  3.0226700252  2.6919365486  2.4363102913  300           0.1606324307 
0.4828400501  0.7776066403  0.8636962826  0.8470464135  0.8180767749  0.8038007191  0.4858312343  0.4798488665  0.7076694285  0.6819727891  6.0453400504  2.2767418448  2.4363102913  600           0.1772563052 
0.4985831232  0.8049106064  0.9000790931  0.8723628692  0.8360508409  0.8238315357  0.5047229219  0.4924433249  0.7374123646  0.7185374150  9.0680100756  2.1201759132  2.4363102913  900           0.1844600248 
0.5297544078  0.8268592313  0.9211705774  0.8860759494  0.8520991141  0.8376990241  0.5368387909  0.5226700252  0.7786275760  0.7568027211  12.090680100  1.9988057240  2.4363102913  1200          0.1846655679 
0.5530541559  0.8480206006  0.9330345373  0.9050632911  0.8693028630  0.8541345660  0.5632871537  0.5428211587  0.8017845762  0.7848639456  15.113350125  1.8889023817  2.4363102913  1500          0.1892713126 
0.5662783372  0.8503067608  0.9409438439  0.8997890295  0.8770060342  0.8628659476  0.5771410579  0.5554156171  0.8226046314  0.7882653061  18.136020151  1.8241245612  2.4363102913  1800          0.1859438189 
0.5733627201  0.8619753107  0.9480622199  0.9135021097  0.8838105020  0.8680020544  0.5824937028  0.5642317380  0.8315275122  0.8044217687  21.158690176  1.7349533192  2.4363102913  2100          0.1904362909 
0.5812342566  0.8701261326  0.9496440812  0.9219409283  0.8910001284  0.8721109399  0.5906801008  0.5717884131  0.8427873380  0.8163265306  24.181360201  1.6676834524  2.4363102913  2400          0.1903457260 
0.5881612088  0.8732005656  0.9593988927  0.9272151899  0.9021697265  0.8777606574  0.5957178841  0.5806045340  0.8568090079  0.8146258503  27.204030226  1.6010803449  2.4363102913  2700          0.1846177038 
0.5911523927  0.8780228582  0.9636171896  0.9208860759  0.9038387470  0.8849512070  0.6004408060  0.5818639798  0.8655194391  0.8282312925  30.226700251  1.5633946105  2.4363102913  3000          0.1803074948 
0.5954030224  0.8813033568  0.9678354864  0.9240506329  0.9115419181  0.8916281459  0.6064231738  0.5843828715  0.8731676227  0.8282312925  33.249370277  1.5171258156  2.4363102913  3300          0.1789971344 
0.5980793448  0.8912620161  0.9694173477  0.9367088608  0.9142380280  0.8977914741  0.6092569270  0.5869017632  0.8803909072  0.8392857143  36.272040302  1.4647159537  5.3955407143  3600          0.1878803913 
0.5949307302  0.8923111907  0.9683627735  0.9398734177  0.9168057517  0.8952234206  0.6079974811  0.5818639798  0.8878266412  0.8418367347  39.294710327  1.1312996362  5.3955407143  3900          0.2162397575 
0.5987090677  0.8931523205  0.9736356446  0.9388185654  0.9180896136  0.8962506420  0.6092569270  0.5881612091  0.8893137880  0.8443877551  42.317380352  1.0983196425  5.3955407143  4200          0.2174106860 
0.5998110828  0.9025897123  0.9749538624  0.9451476793  0.9243805367  0.9029275809  0.6127204030  0.5869017632  0.8999362651  0.8596938776  45.340050377  1.0865635620  5.3955407143  4500          0.2207611179 
0.6002833750  0.8985440773  0.9765357237  0.9430379747  0.9218128129  0.9039548023  0.6149244332  0.5856423174  0.8984491183  0.8486394558  48.362720403  1.0735256288  5.3955407143  4800          0.2209606210 
0.5982367755  0.9025605279  0.9791721592  0.9472573840  0.9283605084  0.9049820236  0.6146095718  0.5818639798  0.8999362651  0.8554421769  50.377833753  1.0640276381  5.3955407143  5000          0.2180345285 
