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: [0]
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/88efd83176bc20c26a9388b7160af7e7
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1680235961
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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: 0.8001163740830898
	lambda2: 0.7340462818445315
	last_k_epoch: 0.3149495809125332
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.8284464949429635
	weight_decay: 1e-06
	worst_case_p: 0.2
using normal transform
using augment 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    
0.3471731447  0.2063677088  0.3480565371  0.3462897527  0.1317647059  0.1506591337  0.2254379284  0.2210365854  0.2428730100  0.2474074074  0.0000000000  4.1073994637  1.7945408821  0             1.6431519985 
0.9717314483  0.7958273363  0.9752650177  0.9681978799  0.7378823529  0.7401129944  0.8537699924  0.7881097561  0.9059607553  0.8592592593  8.4805653710  2.1519953426  2.0945272446  300           0.6360901038 
0.9836572433  0.7978026449  0.9849823322  0.9823321555  0.7797647059  0.7401129944  0.8872810358  0.7881097561  0.9200296187  0.8651851852  16.961130742  1.5814259795  2.0945272446  600           0.6278496575 
0.9849823317  0.7981155102  0.9840989399  0.9858657244  0.7896470588  0.7288135593  0.9093678599  0.8018292683  0.9400222140  0.8637037037  25.441696113  1.4675571942  2.0945272446  900           0.6218268657 
0.9840989394  0.8073569960  0.9823321555  0.9858657244  0.8009411765  0.7401129944  0.9299314547  0.8064024390  0.9518696779  0.8755555556  33.922261484  1.4160367091  2.0945272446  1200          0.6157317909 
0.9858657239  0.8100193808  0.9823321555  0.9893992933  0.8150588235  0.7269303202  0.9424980960  0.8216463415  0.9629766753  0.8814814815  42.402826855  1.3446460168  2.0945272446  1500          0.6271435372 
0.9858657239  0.8263132401  0.9823321555  0.9893992933  0.8249411765  0.7683615819  0.9550647372  0.8231707317  0.9637171418  0.8874074074  50.883392226  1.2913312417  2.0945272446  1800          0.6387901028 
0.9854240278  0.8171279069  0.9814487633  0.9893992933  0.8352941176  0.7645951036  0.9649657273  0.8201219512  0.9748241392  0.8666666667  59.363957597  1.2194682312  2.0945272446  2100          0.6410525393 
0.9854240278  0.8161894133  0.9814487633  0.9893992933  0.8423529412  0.7589453861  0.9672505712  0.8155487805  0.9777860052  0.8740740741  67.844522968  1.1887334945  2.0945272446  2400          0.6274791940 
0.9854240278  0.8185389328  0.9814487633  0.9893992933  0.8545882353  0.7570621469  0.9748667174  0.8170731707  0.9837097371  0.8814814815  76.325088339  1.1417865670  2.0945272446  2700          0.6218346063 
0.9854240278  0.8168938672  0.9814487633  0.9893992933  0.8644705882  0.7627118644  0.9775323686  0.8094512195  0.9833395039  0.8785185185  84.805653710  1.1110561365  2.0945272446  3000          0.6506975444 
0.9849823317  0.8169081701  0.9805653710  0.9893992933  0.8757647059  0.7627118644  0.9836252856  0.8109756098  0.9896334691  0.8770370370  93.286219081  1.0970584412  2.0945272446  3300          0.6458533025 
0.9854240278  0.8139964859  0.9814487633  0.9893992933  0.8804705882  0.7419962335  0.9870525514  0.8155487805  0.9888930026  0.8844444444  101.76678445  0.8305944330  5.4002408981  3600          0.6450779088 
0.9858657239  0.8109916732  0.9823321555  0.9893992933  0.8790588235  0.7344632768  0.9874333587  0.8155487805  0.9903739356  0.8829629630  110.24734982  0.6129742654  5.4002408981  3900          0.6418224740 
0.9863074200  0.8124413718  0.9832155477  0.9893992933  0.8814117647  0.7570621469  0.9878141660  0.7987804878  0.9896334691  0.8814814815  118.72791519  0.5874259207  5.4002408981  4200          0.6377238798 
0.9867491161  0.8120201182  0.9840989399  0.9893992933  0.8960000000  0.7495291902  0.9897182026  0.8109756098  0.9937060348  0.8755555556  127.20848056  0.5684942856  5.4002408981  4500          0.6339814615 
0.9867491161  0.8125477442  0.9840989399  0.9893992933  0.8941176471  0.7514124294  0.9866717441  0.8003048780  0.9914846353  0.8859259259  135.68904593  0.5556398891  5.4002408981  4800          0.6420218380 
0.9867491161  0.8109334025  0.9840989399  0.9893992933  0.8978823529  0.7419962335  0.9908606245  0.8048780488  0.9922251018  0.8859259259  141.34275618  0.5454029514  5.4002408981  5000          0.6376659870 
