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: 0
	output_dir: sweep/ablation3/outputs/a3fcbe71c5c8af4e4b72b06d9398957a
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 2033330553
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	trial_seed: 1
	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: 0.5
	lambda2: 0.5
	last_k_epoch: 0.25
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3
	weight_decay: 0.0
	worst_case_p: 0.3333333333333333
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    
0.1695528966  0.3013789526  0.2135512787  0.1898734177  0.4990371036  0.4838212635  0.1627833753  0.1763224181  0.2207350754  0.2304421769  0.0000000000  4.7260918617  2.3339076042  0             1.4711163044 
0.4877204028  0.7551066015  0.8325863433  0.8386075949  0.7961227372  0.7966101695  0.4867758186  0.4886649874  0.6543445932  0.6301020408  3.0226700252  2.4700033879  2.5991368294  300           0.1609392222 
0.5606108310  0.8181446781  0.9000790931  0.8924050633  0.8408011298  0.8392398562  0.5506926952  0.5705289673  0.7671553006  0.7227891156  6.0453400504  2.0741926996  2.5991368294  600           0.1821977448 
0.5716309821  0.8322116313  0.9227524387  0.9008438819  0.8622416228  0.8525937339  0.5651763224  0.5780856423  0.7988102826  0.7431972789  9.0680100756  1.9176788783  2.5991368294  900           0.1877490838 
0.5861146093  0.8495200968  0.9332981809  0.9092827004  0.8734112210  0.8705701079  0.5765113350  0.5957178841  0.8160186956  0.7687074830  12.090680100  1.7925690711  2.5991368294  1200          0.1847863603 
0.5920969770  0.8618734609  0.9467440021  0.9229957806  0.8840672744  0.8777606574  0.5859571788  0.5982367758  0.8285532186  0.7848639456  15.113350125  1.6962751492  2.5991368294  1500          0.1864593244 
0.6057934506  0.8703682435  0.9559715265  0.9261603376  0.8943381692  0.8839239856  0.5982367758  0.6133501259  0.8457616316  0.8010204082  18.136020151  1.5883716706  2.5991368294  1800          0.1862828422 
0.6131926949  0.8754493482  0.9596625363  0.9388185654  0.9006290923  0.8890600924  0.6042191436  0.6221662469  0.8572339069  0.7984693878  21.158690176  1.5192104185  2.5991368294  2100          0.1892810750 
0.6171284632  0.8782987033  0.9675718429  0.9398734177  0.9031968160  0.8906009245  0.6083123426  0.6259445844  0.8608455492  0.8044217687  24.181360201  1.4816637993  2.5991368294  2400          0.1896513883 
0.6209068007  0.8827862457  0.9723174268  0.9398734177  0.9107716010  0.8947098100  0.6083123426  0.6335012594  0.8689186318  0.8137755102  27.204030226  1.4573592997  2.5991368294  2700          0.1856651743 
0.6194899241  0.8863080977  0.9720537833  0.9504219409  0.9107716010  0.8972778634  0.6067380353  0.6322418136  0.8786913108  0.8112244898  30.226700251  1.4319043871  2.5991368294  3000          0.1871579639 
0.6213790929  0.8873717347  0.9707355655  0.9430379747  0.9205289511  0.9019003595  0.6067380353  0.6360201511  0.8863394944  0.8171768707  33.249370277  1.3982205908  2.5991368294  3300          0.1889415948 
0.6237405538  0.8932549830  0.9773266544  0.9514767932  0.9204005649  0.9060092450  0.6089420655  0.6385390428  0.8925005311  0.8222789116  36.272040302  1.3867935729  2.5991368294  3600          0.1866787187 
0.6231108309  0.8958465432  0.9762720801  0.9493670886  0.9245089228  0.9090909091  0.6114609572  0.6347607053  0.8967495220  0.8290816327  39.294710327  1.1881802434  5.3942589760  3900          0.2010225487 
0.6232682617  0.8998040333  0.9791721592  0.9535864979  0.9281037360  0.9090909091  0.6105163728  0.6360201511  0.9048226046  0.8367346939  42.317380352  0.9635786364  5.3942589760  4200          0.2191483458 
0.6210642314  0.8993991331  0.9794358028  0.9525316456  0.9316985492  0.9106317411  0.6086272040  0.6335012594  0.9067346505  0.8350340136  45.340050377  0.9486768959  5.3942589760  4500          0.2208470559 
0.6210642314  0.9078406330  0.9799630899  0.9556962025  0.9351649762  0.9183359014  0.6098866499  0.6322418136  0.9122583386  0.8494897959  48.362720403  0.9347457832  5.3942589760  4800          0.2223117765 
0.6198047856  0.9105444363  0.9804903770  0.9535864979  0.9350365901  0.9209039548  0.6098866499  0.6297229219  0.9145952836  0.8571428571  50.377833753  0.9398678714  5.3942589760  5000          0.2216387105 
