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: [3]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: PACS
	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: 1
	output_dir: sweep/ablation3/outputs/ef4b221a35d53a054b488b0b483cdf4a
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1709129321
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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: 0.7819049321936025
	lambda2: 0.9075316444347157
	last_k_epoch: 0.25491468830584113
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.907263233121133
	weight_decay: 1e-06
	worst_case_p: 0.25
using augment transform
using augment transform
using augment transform
using normal 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    
0.0824334289  0.1538840276  0.1995118975  0.1589242054  0.1380597015  0.1111111111  0.1901197605  0.1916167665  0.0795165394  0.0853503185  0.0000000000  9.4587650299  2.0074062347  0             1.5215206146 
0.7512757083  0.9562573072  0.9743746187  0.9388753056  0.9808102345  0.9508547009  0.9955089820  0.9790419162  0.7471374046  0.7554140127  7.1856287425  3.0898574118  2.2566514015  300           0.1506683048 
0.8122234644  0.9718353084  0.9902379500  0.9535452323  0.9888059701  0.9679487179  0.9992514970  0.9940119760  0.8091603053  0.8152866242  14.371257485  1.0893907748  2.2566514015  600           0.1762129362 
0.8006059460  0.9754837906  0.9957291031  0.9657701711  0.9946695096  0.9636752137  1.0000000000  0.9970059880  0.7986641221  0.8025477707  21.556886227  0.9365320230  2.2566514015  900           0.1781246360 
0.8080861732  0.9732822922  0.9957291031  0.9608801956  0.9925373134  0.9679487179  1.0000000000  0.9910179641  0.8047073791  0.8114649682  28.742514970  0.8467706195  2.2566514015  1200          0.1748030066 
0.8109520101  0.9739340616  0.9938987187  0.9559902200  0.9968017058  0.9658119658  0.9992514970  1.0000000000  0.8053435115  0.8165605096  35.928143712  0.8178031556  2.2566514015  1500          0.1734907921 
0.8157254335  0.9724672963  0.9963392312  0.9584352078  0.9968017058  0.9679487179  1.0000000000  0.9910179641  0.8110687023  0.8203821656  43.113772455  0.7615144811  2.2566514015  1800          0.1728155454 
0.8128587863  0.9754993072  0.9981696156  0.9559902200  0.9978678038  0.9764957265  1.0000000000  0.9940119760  0.8117048346  0.8140127389  50.299401197  0.7651652601  2.2566514015  2100          0.1730092533 
0.8173157643  0.9742578138  0.9975594875  0.9535452323  0.9978678038  0.9722222222  1.0000000000  0.9970059880  0.8142493639  0.8203821656  57.485029940  0.7386737316  2.2566514015  2400          0.1730211488 
0.8184281855  0.9743605591  1.0000000000  0.9559902200  0.9978678038  0.9700854701  1.0000000000  0.9970059880  0.8177480916  0.8191082803  64.670658682  0.7393937103  2.2566514015  2700          0.1725659696 
0.8203382032  0.9767028016  0.9987797437  0.9608801956  0.9968017058  0.9722222222  1.0000000000  0.9970059880  0.8190203562  0.8216560510  71.856287425  0.7056712358  2.2566514015  3000          0.1713924305 
0.8238393620  0.9770265538  0.9993898719  0.9584352078  0.9973347548  0.9786324786  1.0000000000  0.9940119760  0.8222010178  0.8254777070  79.041916167  0.7079980859  2.2566514015  3300          0.1712365119 
0.8287734392  0.9781273030  0.9987797437  0.9608801956  0.9994669510  0.9764957265  0.9992514970  0.9970059880  0.8256997455  0.8318471338  86.227544910  0.7003124973  2.2566514015  3600          0.1696365841 
0.8298858604  0.9738917977  0.9993898719  0.9584352078  0.9968017058  0.9722222222  1.0000000000  0.9910179641  0.8291984733  0.8305732484  93.413173652  0.5917644808  5.3973727226  3900          0.1922775944 
0.8289292309  0.9747067936  0.9981696156  0.9608801956  1.0000000000  0.9722222222  1.0000000000  0.9910179641  0.8311068702  0.8267515924  100.59880239  0.4371991420  5.3973727226  4200          0.2082353330 
0.8302023059  0.9735032992  0.9981696156  0.9559902200  0.9989339019  0.9764957265  1.0000000000  0.9880239521  0.8323791349  0.8280254777  107.78443113  0.3928085157  5.3973727226  4500          0.2072862450 
0.8311573147  0.9834437760  0.9987797437  0.9755501222  0.9989339019  0.9807692308  1.0000000000  0.9940119760  0.8330152672  0.8292993631  114.97005988  0.3666641771  5.3973727226  4800          0.2073588141 
0.8319532905  0.9747870565  0.9993898719  0.9559902200  0.9994669510  0.9743589744  1.0000000000  0.9940119760  0.8333333333  0.8305732484  119.76047904  0.3564499485  5.3973727226  5000          0.2097312760 
