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: VLCS
	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/6f9607d4edd2681c223a7d7fda80c3c2
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1748988132
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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: 0.6171767606394463
	lambda2: 0.5293911814442921
	last_k_epoch: 0.3102645027326114
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.022572617872769
	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    
0.3560833055  0.4006014727  0.5167844523  0.5053003534  0.3581176471  0.3540489642  0.3084539223  0.3231707317  0.3335801555  0.3733333333  0.0000000000  3.9346375465  1.7945408821  0             1.4872591496 
0.6698025919  0.9026385122  1.0000000000  1.0000000000  0.6785882353  0.6610169492  0.8796648896  0.8338414634  0.9285449833  0.8740740741  8.4805653710  1.6155315659  2.0919981003  300           0.1480032142 
0.6521533175  0.9151372593  1.0000000000  0.9964664311  0.6527058824  0.6516007533  0.9188880427  0.8704268293  0.9581636431  0.8785185185  16.961130742  1.1696124057  2.0919981003  600           0.1664166594 
0.6486230195  0.9108534109  1.0000000000  0.9929328622  0.6494117647  0.6478342750  0.9459253618  0.8551829268  0.9696408738  0.8844444444  25.441696113  0.9581545484  2.0919981003  900           0.1713556822 
0.6483881685  0.9163999330  1.0000000000  0.9929328622  0.6470588235  0.6497175141  0.9619192688  0.8673780488  0.9766753054  0.8888888889  33.922261484  0.8429572759  2.0919981003  1200          0.1718329167 
0.6479180234  0.9153417642  1.0000000000  1.0000000000  0.6442352941  0.6516007533  0.9699162224  0.8719512195  0.9855609034  0.8740740741  42.402826855  0.8065320039  2.0919981003  1500          0.1705058908 
0.6465058156  0.9157354709  1.0000000000  1.0000000000  0.6432941176  0.6497175141  0.9786747906  0.8612804878  0.9877823029  0.8859259259  50.883392226  0.7730487061  2.0919981003  1800          0.1680398806 
0.6467415528  0.9081092557  1.0000000000  0.9964664311  0.6418823529  0.6516007533  0.9828636710  0.8582317073  0.9929655683  0.8696296296  59.363957597  0.7698834580  2.0919981003  2100          0.1726513886 
0.6467415528  0.9103033722  1.0000000000  1.0000000000  0.6418823529  0.6516007533  0.9859101295  0.8612804878  0.9925953351  0.8696296296  67.844522968  0.7909703432  2.0919981003  2400          0.1705734928 
0.6453289019  0.9117133391  1.0000000000  1.0000000000  0.6428235294  0.6478342750  0.9904798172  0.8536585366  0.9944465013  0.8814814815  76.325088339  0.7518918802  2.0919981003  2700          0.1669949659 
0.6486243489  0.9147907254  1.0000000000  1.0000000000  0.6437647059  0.6534839925  0.9923838538  0.8658536585  0.9948167345  0.8785185185  84.805653710  0.7312210073  2.0919981003  3000          0.1695365175 
0.6486243489  0.9135699603  1.0000000000  0.9964664311  0.6437647059  0.6534839925  0.9923838538  0.8612804878  0.9962976675  0.8829629630  93.286219081  0.7345948841  2.0919981003  3300          0.1691022595 
0.6498012626  0.9077341159  1.0000000000  1.0000000000  0.6442352941  0.6553672316  0.9965727342  0.8506097561  0.9962976675  0.8725925926  101.76678445  0.5448716307  5.3990297318  3600          0.1918641472 
0.6505071449  0.9139164943  1.0000000000  0.9929328622  0.6456470588  0.6553672316  0.9958111196  0.8658536585  0.9959274343  0.8829629630  110.24734982  0.3363975751  5.3990297318  3900          0.2122106632 
0.6514487645  0.9100416556  1.0000000000  0.9964664311  0.6456470588  0.6572504708  0.9935262757  0.8536585366  0.9966679008  0.8800000000  118.72791519  0.3218401911  5.3990297318  4200          0.2154400706 
0.6519193527  0.9115946517  1.0000000000  0.9964664311  0.6465882353  0.6572504708  0.9950495050  0.8612804878  0.9988893003  0.8770370370  127.20848056  0.3129361084  5.3990297318  4500          0.2141154536 
0.6519189096  0.9197146941  1.0000000000  1.0000000000  0.6484705882  0.6553672316  0.9973343488  0.8643292683  0.9966679008  0.8948148148  135.68904593  0.3086352344  5.3990297318  4800          0.2188898691 
0.6521542037  0.9127868109  1.0000000000  1.0000000000  0.6489411765  0.6553672316  0.9977151561  0.8628048780  0.9981488338  0.8755555556  141.34275618  0.3011629529  5.3990297318  5000          0.2173936510 
