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: 3
	output_dir: sweep/ablation3/outputs/c946fba87e2e8763ab9a5b215bad2110
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 323958112
	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: 0.5694511041907044
	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 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    
0.1655002778  0.0902271084  0.0664381756  0.0537974684  0.1676723585  0.1633281972  0.0598236776  0.0629722922  0.1474399830  0.1539115646  0.0000000000  4.3168826103  1.7946186066  0             1.8798606396 
0.4129160193  0.5886874511  0.6187714210  0.6075949367  0.4200795994  0.4057524397  0.5875314861  0.5428211587  0.6127044827  0.6156462585  3.0226700252  2.7610267766  2.0937752724  300           0.1514594213 
0.3941063881  0.7208699960  0.8307408384  0.8027426160  0.3988958788  0.3893168978  0.7156801008  0.6863979849  0.7036328872  0.6734693878  6.0453400504  2.3782976421  2.0937752724  600           0.1745585267 
0.4003975420  0.7543856650  0.8481413129  0.8259493671  0.4078829118  0.3929121726  0.7421284635  0.7229219144  0.7295517315  0.7142857143  9.0680100756  2.2612061524  2.0937752724  900           0.1794916558 
0.4102840036  0.7781023906  0.8758238861  0.8523206751  0.4163564001  0.4042116076  0.7755037783  0.7455919395  0.7660930529  0.7363945578  12.090680100  2.1692601375  2.0937752724  1200          0.1777519957 
0.4069458639  0.8145098523  0.9035064593  0.8871308017  0.4112209526  0.4026707756  0.8025818640  0.7783375315  0.7932865944  0.7780612245  15.113350125  2.1094112420  2.0937752724  1500          0.1725509501 
0.4018742139  0.8162320059  0.9195887161  0.8829113924  0.4072409809  0.3965074474  0.8202141058  0.7758186398  0.8041215211  0.7899659864  18.136020151  2.0173011847  2.0937752724  1800          0.1774135550 
0.3953901510  0.8332141811  0.9364619035  0.9103375527  0.4030042367  0.3877760657  0.8403652393  0.7984886650  0.8234544296  0.7908163265  21.158690176  1.9555121664  2.0937752724  2100          0.1798448420 
0.3890987334  0.8387038814  0.9475349328  0.9124472574  0.3981255617  0.3800719055  0.8573677582  0.8060453401  0.8379009985  0.7976190476  24.181360201  1.8817861315  2.0937752724  2400          0.1772490430 
0.3901900489  0.8514628967  0.9520168732  0.9135021097  0.3997945821  0.3805855162  0.8734256927  0.8211586902  0.8521351179  0.8197278912  27.204030226  1.8200487951  2.0937752724  2700          0.1767411749 
0.3910245592  0.8628873094  0.9538623781  0.9293248945  0.4014636025  0.3805855162  0.8816120907  0.8413098237  0.8674314850  0.8180272109  30.226700251  1.7719194325  2.0937752724  3000          0.1772449883 
0.3942344776  0.8675801903  0.9593988927  0.9335443038  0.4037745539  0.3846944016  0.8935768262  0.8350125945  0.8769917145  0.8341836735  33.249370277  1.7122436110  2.0937752724  3300          0.1746671645 
0.3960961102  0.8706445020  0.9667809122  0.9377637131  0.4069842085  0.3852080123  0.9102644836  0.8450881612  0.8791162099  0.8290816327  36.272040302  1.6356577802  2.0937752724  3600          0.1727453343 
0.4014245326  0.8840171081  0.9680991300  0.9440928270  0.4114777250  0.3913713405  0.9096347607  0.8627204030  0.8899511366  0.8452380952  39.294710327  1.6018669538  2.0937752724  3900          0.1751649070 
0.4031579109  0.8800703546  0.9723174268  0.9377637131  0.4123764283  0.3939393939  0.9175062972  0.8614609572  0.8910133843  0.8409863946  42.317380352  1.2051373786  5.3984646797  4200          0.2096936806 
0.4039282280  0.8886671236  0.9749538624  0.9504219409  0.4139170625  0.3939393939  0.9241183879  0.8652392947  0.9041852560  0.8503401361  45.340050377  0.9905494416  5.3984646797  4500          0.2244281650 
0.4055973474  0.8900161864  0.9775902979  0.9493670886  0.4157144691  0.3954802260  0.9294710327  0.8652392947  0.9063097514  0.8554421769  48.362720403  0.9714043506  5.3984646797  4800          0.2201147143 
0.4063034714  0.8934214060  0.9770630108  0.9546413502  0.4171267172  0.3954802260  0.9282115869  0.8778337531  0.9082217973  0.8477891156  50.377833753  0.9634314275  5.3984646797  5000          0.2201823390 
