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/2390e3a47c7c3a07515e45b9c659988e
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1661109697
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	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: 0.7010166027828918
	lambda2: 0.6269010951324223
	last_k_epoch: 0.38851977780027735
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.131347198605345
	weight_decay: 1e-06
	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    
0.1421599496  0.1633997679  0.1323490641  0.1413502110  0.2119655925  0.2110939908  0.1382241814  0.1460957179  0.1298066709  0.1377551020  0.0000000000  4.9548702240  2.1692652702  0             1.6075546741 
0.3605163726  0.6845628840  0.7595570788  0.7436708861  0.7475927590  0.7411402157  0.3608312343  0.3602015113  0.5670278309  0.5688775510  3.0226700252  2.6923498130  2.4381909370  300           0.1634800458 
0.4998425690  0.7997051070  0.8808331136  0.8618143460  0.8298883040  0.8289676425  0.5059823678  0.4937027708  0.7199915020  0.7083333333  6.0453400504  2.3114609965  2.4381909370  600           0.1876506265 
0.5403022667  0.8292288758  0.9082520432  0.8945147679  0.8522275003  0.8423215203  0.5465994962  0.5340050378  0.7584448693  0.7508503401  9.0680100756  2.1649421910  2.4381909370  900           0.1870902403 
0.5642317378  0.8430478360  0.9216978645  0.9050632911  0.8666067531  0.8613251156  0.5717884131  0.5566750630  0.7890376036  0.7627551020  12.090680100  2.0547635194  2.4381909370  1200          0.1854131897 
0.5839105791  0.8552997207  0.9346163986  0.9145569620  0.8827834125  0.8690292758  0.5859571788  0.5818639798  0.8100701083  0.7823129252  15.113350125  1.9830904746  2.4381909370  1500          0.1826574755 
0.5958753146  0.8714522802  0.9417347746  0.9272151899  0.8888175632  0.8818695429  0.5985516373  0.5931989924  0.8289781177  0.8052721088  18.136020151  1.8747632666  2.4381909370  1800          0.1896727180 
0.6002833750  0.8767778454  0.9554442394  0.9367088608  0.8922839902  0.8849512070  0.6023299748  0.5982367758  0.8374760994  0.8086734694  21.158690176  1.7739458176  2.4381909370  2100          0.1869547311 
0.6028022667  0.8825591887  0.9567624572  0.9293248945  0.9008858647  0.8952234206  0.6061083123  0.5994962217  0.8529849161  0.8231292517  24.181360201  1.7413330750  2.4381909370  2400          0.1851975481 
0.6097292188  0.8861932839  0.9609807540  0.9398734177  0.9052509950  0.8972778634  0.6098866499  0.6095717884  0.8608455492  0.8214285714  27.204030226  1.6785018325  2.4381909370  2700          0.1883452145 
0.6139798486  0.8942277385  0.9665172687  0.9430379747  0.9129541661  0.9003595275  0.6120906801  0.6158690176  0.8661567878  0.8392857143  30.226700251  1.6694844166  2.4381909370  3000          0.1871299100 
0.6158690173  0.8957060775  0.9717901397  0.9419831224  0.9159070484  0.9075500770  0.6120906801  0.6196473552  0.8791162099  0.8375850340  33.249370277  1.3068508303  5.3981270790  3300          0.2166183662 
0.6152392944  0.8954539603  0.9654626944  0.9388185654  0.9177044550  0.9116589625  0.6133501259  0.6171284635  0.8769917145  0.8358843537  36.272040302  1.1794701231  5.3981270790  3600          0.2240770213 
0.6147670022  0.9004939337  0.9741629317  0.9493670886  0.9215560406  0.9085772984  0.6111460957  0.6183879093  0.8899511366  0.8435374150  39.294710327  1.1675893978  5.3981270790  3900          0.2216332785 
0.6169710324  0.9007370065  0.9738992882  0.9440928270  0.9247656952  0.9162814587  0.6142947103  0.6196473552  0.8882515403  0.8418367347  42.317380352  1.1521789761  5.3981270790  4200          0.2207272808 
0.6155541559  0.9020655037  0.9765357237  0.9419831224  0.9248940814  0.9121725732  0.6139798489  0.6171284635  0.8908009348  0.8520408163  45.340050377  1.1438089410  5.3981270790  4500          0.2220407041 
0.6166561710  0.9092302356  0.9775902979  0.9525316456  0.9286172808  0.9214175655  0.6136649874  0.6196473552  0.9035479074  0.8537414966  48.362720403  1.1408966394  5.3981270790  4800          0.2211563587 
0.6171284632  0.9062255268  0.9770630108  0.9430379747  0.9319553216  0.9167950693  0.6158690176  0.6183879093  0.8995113661  0.8588435374  50.377833753  1.1389623761  5.3981270790  5000          0.2198789048 
