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: 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: 4
	output_dir: sweep/ablation3/outputs/9d62a3fec3c16aa12dfc3d6dc26b0410
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1002587461
	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    
0.0119973113  0.1099349139  0.0123912470  0.0116033755  0.0124534600  0.0107858243  0.2216624685  0.1889168766  0.1272572764  0.1301020408  0.0000000000  5.5783910751  1.7946186066  0             1.5708854198 
0.1957831492  0.4924969926  0.1805958344  0.2109704641  0.5530876878  0.5608628659  0.4363979849  0.4030226700  0.4986190780  0.5136054422  3.0226700252  3.0136741749  2.0937752724  300           0.1572283928 
0.1852353212  0.6297150031  0.1753229634  0.1951476793  0.7475927590  0.7575757576  0.5856423174  0.5516372796  0.5954960697  0.5799319728  6.0453400504  2.6454025944  2.0937752724  600           0.1744790634 
0.2089668565  0.6650934361  0.1953598735  0.2225738397  0.7735267685  0.7683615819  0.6344458438  0.6095717884  0.6532823454  0.6173469388  9.0680100756  2.5569549266  2.0937752724  900           0.1773097150 
0.2262367607  0.7010066603  0.2204060111  0.2320675105  0.7956091925  0.7986646122  0.6841939547  0.6385390428  0.6813256851  0.6658163265  12.090680100  2.4737771177  2.0937752724  1200          0.1766162848 
0.2429803512  0.7184155918  0.2370155550  0.2489451477  0.8074207215  0.8079096045  0.7115869018  0.6687657431  0.7055449331  0.6785714286  15.113350125  2.4211462180  2.0937752724  1500          0.1743654784 
0.2762038887  0.7348503460  0.2697073557  0.2827004219  0.8256515599  0.8305084746  0.7317380353  0.6750629723  0.7350754196  0.6989795918  18.136020151  2.3828532918  2.0937752724  1800          0.1787762674 
0.2976940365  0.7511014885  0.2884260480  0.3069620253  0.8348953653  0.8192090395  0.7455919395  0.7002518892  0.7507966858  0.7338435374  21.158690176  2.3000263127  2.0937752724  2100          0.1761722533 
0.3065266518  0.7605420485  0.3018718692  0.3111814346  0.8459365772  0.8299948639  0.7786523929  0.7254408060  0.7597195666  0.7261904762  24.181360201  2.2717801654  2.0937752724  2400          0.1746286623 
0.3172053281  0.7814964473  0.3147904034  0.3196202532  0.8510720247  0.8371854135  0.7899874055  0.7607052897  0.7714042915  0.7465986395  27.204030226  2.2272297215  2.0937752724  2700          0.1768560163 
0.3314445830  0.7841428197  0.3242815713  0.3386075949  0.8594171267  0.8505392912  0.8038413098  0.7518891688  0.7894625027  0.7500000000  30.226700251  2.1975950225  2.0937752724  3000          0.1736013746 
0.3385636542  0.7904872734  0.3332454521  0.3438818565  0.8668635255  0.8428351310  0.8202141058  0.7556675063  0.7990227321  0.7729591837  33.249370277  2.1232680849  2.0937752724  3300          0.1757782586 
0.3380366452  0.8031318044  0.3300817295  0.3459915612  0.8752086276  0.8572162301  0.8198992443  0.7758186398  0.8166560442  0.7763605442  36.272040302  1.7448994946  5.4010052681  3600          0.2021418039 
0.3384325277  0.8051865123  0.3277089375  0.3491561181  0.8780331236  0.8649203903  0.8284005038  0.7632241814  0.8266411727  0.7874149660  39.294710327  1.3749941031  5.4010052681  3900          0.2227818640 
0.3393552801  0.8260600277  0.3295544424  0.3491561181  0.8811143921  0.8875192604  0.8510705290  0.7921914358  0.8408752921  0.7984693878  42.317380352  1.3203047089  5.4010052681  4200          0.2234992822 
0.3392234583  0.8209772036  0.3292907988  0.3491561181  0.8859930671  0.8705701079  0.8589420655  0.7921914358  0.8474612280  0.8001700680  45.340050377  1.2927171167  5.4010052681  4500          0.2225646496 
0.3427827854  0.8287378567  0.3353546006  0.3502109705  0.8859930671  0.8762198254  0.8655541562  0.8098236776  0.8565965583  0.8001700680  48.362720403  1.2746760595  5.4010052681  4800          0.2209533715 
0.3450240337  0.8265762027  0.3377273926  0.3523206751  0.8880472461  0.8680020544  0.8784634761  0.8073047859  0.8546845124  0.8044217687  50.377833753  1.2531310266  5.4010052681  5000          0.2208880472 
