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/21bd23666db0cd927e579b4f894d3f18
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 315420026
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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 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    
0.1165002769  0.3954217671  0.6033568905  0.5865724382  0.1068235294  0.1261770245  0.3282559025  0.3048780488  0.2984079970  0.2948148148  0.0000000000  5.2559404373  1.7945408821  0             1.5267817974 
0.6203784200  0.8817294003  0.9991166078  0.9964664311  0.6324705882  0.6082862524  0.8697638995  0.7835365854  0.9100333210  0.8651851852  8.4805653710  2.0641412902  2.0945272446  300           0.1426240158 
0.6601555331  0.8970051724  1.0000000000  0.9929328622  0.6592941176  0.6610169492  0.9108910891  0.8003048780  0.9378008145  0.8977777778  16.961130742  1.2710676273  2.0945272446  600           0.1688076790 
0.6500343411  0.8986868947  1.0000000000  0.9929328622  0.6541176471  0.6459510358  0.9367859863  0.8216463415  0.9514994447  0.8814814815  25.441696113  1.1038836604  2.0945272446  900           0.1695822899 
0.6439149216  0.8946218541  1.0000000000  0.9929328622  0.6494117647  0.6384180791  0.9474485910  0.8094512195  0.9648278415  0.8814814815  33.922261484  0.9858492311  2.0945272446  1200          0.1685229532 
0.6399140354  0.9023338868  1.0000000000  0.9964664311  0.6451764706  0.6346516008  0.9569687738  0.8216463415  0.9696408738  0.8888888889  42.402826855  0.9332316760  2.0945272446  1500          0.1667083414 
0.6375610942  0.8994896113  1.0000000000  1.0000000000  0.6404705882  0.6346516008  0.9706778370  0.8140243902  0.9737134395  0.8844444444  50.883392226  0.9126910245  2.0945272446  1800          0.1673660429 
0.6377963883  0.8984447453  1.0000000000  1.0000000000  0.6409411765  0.6346516008  0.9725818736  0.8079268293  0.9822288041  0.8874074074  59.363957597  0.8752691972  2.0945272446  2100          0.1739978504 
0.6389737451  0.9014220111  1.0000000000  1.0000000000  0.6395294118  0.6384180791  0.9786747906  0.8094512195  0.9811181044  0.8948148148  67.844522968  0.8643633914  2.0945272446  2400          0.1744641892 
0.6387384510  0.8989385724  1.0000000000  1.0000000000  0.6390588235  0.6384180791  0.9836252856  0.8079268293  0.9837097371  0.8888888889  76.325088339  0.8487007582  2.0945272446  2700          0.1728387380 
0.6385031569  0.9030322189  1.0000000000  1.0000000000  0.6385882353  0.6384180791  0.9859101295  0.8231707317  0.9866716031  0.8859259259  84.805653710  0.8454787882  2.0945272446  3000          0.1722095680 
0.6394443333  0.8997789335  1.0000000000  0.9964664311  0.6404705882  0.6384180791  0.9847677075  0.8125000000  0.9896334691  0.8903703704  93.286219081  0.8289518791  2.0945272446  3300          0.1756464839 
0.6396796275  0.9030036131  1.0000000000  1.0000000000  0.6409411765  0.6384180791  0.9840060929  0.8201219512  0.9903739356  0.8888888889  101.76678445  0.6202268063  5.4002408981  3600          0.2022406173 
0.6413271294  0.8970347784  1.0000000000  1.0000000000  0.6423529412  0.6403013183  0.9889565880  0.8155487805  0.9900037023  0.8755555556  110.24734982  0.4278091492  5.4002408981  3900          0.2218412701 
0.6415624235  0.8979795239  1.0000000000  1.0000000000  0.6428235294  0.6403013183  0.9881949733  0.8109756098  0.9922251018  0.8829629630  118.72791519  0.4048662941  5.4002408981  4200          0.2199028055 
0.6410918353  0.9005344773  1.0000000000  1.0000000000  0.6418823529  0.6403013183  0.9889565880  0.8201219512  0.9892632358  0.8814814815  127.20848056  0.3928043669  5.4002408981  4500          0.2214268057 
0.6408565412  0.8995182171  1.0000000000  1.0000000000  0.6414117647  0.6403013183  0.9904798172  0.8170731707  0.9896334691  0.8814814815  135.68904593  0.3870112250  5.4002408981  4800          0.2174553307 
0.6408565412  0.9015221316  1.0000000000  1.0000000000  0.6414117647  0.6403013183  0.9893373953  0.8201219512  0.9914846353  0.8844444444  141.34275618  0.3730780995  5.4002408981  5000          0.2165768301 
