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: 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: 2
	output_dir: sweep/ablation3/outputs/146b080d3de9fd2295bb71526c368290
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1199454330
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	trial_seed: 2
	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: 0.8194577311903198
	lambda2: 0.5954971958468116
	last_k_epoch: 0.2502561813215683
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.3092434210820203
	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    
0.0784190827  0.0831432424  0.0500922752  0.0559071730  0.0822955450  0.0826913200  0.1029596977  0.1108312343  0.0777565328  0.0790816327  0.0000000000  4.3288955688  2.0074815750  0             1.5107975006 
0.2041214668  0.5877015664  0.5141049301  0.5063291139  0.7262806522  0.7026194145  0.5607682620  0.5541561713  0.2084130019  0.1998299320  3.0226700252  2.8187579433  2.2552723885  300           0.1521622729 
0.3179264056  0.7581509730  0.8281044028  0.8270042194  0.8012581846  0.7812018490  0.7040302267  0.6662468514  0.3161249203  0.3197278912  6.0453400504  2.4079821495  2.2552723885  600           0.1853801870 
0.3246199211  0.7990612943  0.8665963617  0.8343881857  0.8309153935  0.8197226502  0.7632241814  0.7430730479  0.3252602507  0.3239795918  9.0680100756  2.2580532598  2.2552723885  900           0.1818806394 
0.3397076324  0.8163037591  0.8963880833  0.8628691983  0.8517139556  0.8366718028  0.7858942065  0.7493702771  0.3435309114  0.3358843537  12.090680100  2.1673327974  2.2552723885  1200          0.1828970734 
0.3553286354  0.8291326624  0.9071974690  0.8765822785  0.8612145333  0.8412942989  0.8110831234  0.7695214106  0.3560654345  0.3545918367  15.113350125  2.0792809423  2.2552723885  1500          0.1775519482 
0.3587286411  0.8404258771  0.9264434485  0.8871308017  0.8727692900  0.8495120699  0.8384760705  0.7846347607  0.3603144253  0.3571428571  18.136020151  1.9859093444  2.2552723885  1800          0.1826685603 
0.3615977938  0.8509534182  0.9340891115  0.8902953586  0.8803440750  0.8602978942  0.8561083123  0.8022670025  0.3626513703  0.3605442177  21.158690176  1.9282385329  2.2552723885  2100          0.1811426902 
0.3649980704  0.8585293163  0.9422620617  0.9008438819  0.8890743356  0.8649203903  0.8680730479  0.8098236776  0.3660505630  0.3639455782  24.181360201  1.8215360737  2.2552723885  2400          0.1824809575 
0.3731795457  0.8675402049  0.9499077248  0.8997890295  0.8948517140  0.8715973292  0.8825566751  0.8312342569  0.3756107924  0.3707482993  27.204030226  1.7927262310  2.2552723885  2700          0.1826790102 
0.3795554708  0.8712310342  0.9522805167  0.9177215190  0.9001155476  0.8685156651  0.8960957179  0.8274559194  0.3807095815  0.3784013605  30.226700251  1.7304403381  2.2552723885  3000          0.1825350070 
0.3874193557  0.8824931667  0.9591352491  0.9177215190  0.9058929259  0.8834103749  0.9011335013  0.8463476071  0.3862332696  0.3886054422  33.249370277  1.6826767095  2.2552723885  3300          0.1841286548 
0.3949642953  0.8858248604  0.9612443976  0.9229957806  0.9129541661  0.8931689779  0.9030226700  0.8413098237  0.3919694073  0.3979591837  36.272040302  1.6842021497  2.2552723885  3600          0.1846599325 
0.4002774307  0.8871467451  0.9644081202  0.9282700422  0.9120554628  0.8906009245  0.9090050378  0.8425692695  0.3966432972  0.4039115646  39.294710327  1.5040074305  5.3961586952  3900          0.2021795400 
0.4033590330  0.8930149487  0.9630899025  0.9272151899  0.9183463859  0.8916281459  0.9190806045  0.8602015113  0.3994051413  0.4073129252  42.317380352  1.2490296594  5.3961586952  4200          0.2227302869 
0.4058024738  0.8942162095  0.9654626944  0.9377637131  0.9214276544  0.8972778634  0.9187657431  0.8476070529  0.4034416826  0.4081632653  45.340050377  1.2225163325  5.3961586952  4500          0.2246922731 
0.4098406410  0.8966712444  0.9644081202  0.9272151899  0.9266914880  0.8988186954  0.9184508816  0.8639798489  0.4064159762  0.4132653061  48.362720403  1.2083224094  5.3961586952  4800          0.2214876580 
0.4083526812  0.8987651773  0.9704719220  0.9303797468  0.9246373090  0.8906009245  0.9260075567  0.8753148615  0.4059910771  0.4107142857  50.377833753  1.2014667469  5.3961586952  5000          0.2239432395 
