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: 2
	output_dir: sweep/ablation3/outputs/b616f60da298d5c65ddc22260da010ba
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1361661792
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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 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    
0.0201702614  0.0721604121  0.0287371474  0.0116033755  0.1805109770  0.1813045711  0.0151133501  0.0088161209  0.0286806883  0.0263605442  0.0000000000  4.9409561157  2.0074815750  0             1.5276277065 
0.1525385147  0.6358148241  0.1479040337  0.1571729958  0.7240980870  0.7195685670  0.5884760705  0.5705289673  0.5991077119  0.6173469388  3.0226700252  2.8222499037  2.2552723885  300           0.1494398530 
0.2019789118  0.7016327528  0.1919325073  0.2120253165  0.8015149570  0.7817154597  0.6775818640  0.6624685139  0.6715530062  0.6607142857  6.0453400504  2.4742303467  2.2552723885  600           0.1797171664 
0.2503630660  0.7346405484  0.2465067229  0.2542194093  0.8207728848  0.8007190550  0.7147355164  0.6889168766  0.6983216486  0.7142857143  9.0680100756  2.3658410978  2.2552723885  900           0.1790752045 
0.2416610210  0.7609683104  0.2428157132  0.2405063291  0.8311721659  0.8176682075  0.7465365239  0.7254408060  0.7344380710  0.7397959184  12.090680100  2.2925774598  2.2552723885  1200          0.1763866782 
0.2555034200  0.7657420057  0.2620616926  0.2489451477  0.8395172679  0.8222907036  0.7701511335  0.7317380353  0.7590822180  0.7431972789  15.113350125  2.2334542457  2.2552723885  1500          0.1792078964 
0.2606451646  0.7839607647  0.2670709201  0.2542194093  0.8572345616  0.8284540318  0.7909319899  0.7632241814  0.7805396218  0.7602040816  18.136020151  2.1692970641  2.2552723885  1800          0.1820082100 
0.2587995206  0.7945397628  0.2644344846  0.2531645570  0.8663499807  0.8330765280  0.8016372796  0.7707808564  0.7932865944  0.7797619048  21.158690176  2.1000889921  2.2552723885  2100          0.1786793407 
0.2623591258  0.8061784916  0.2683891379  0.2563291139  0.8762357170  0.8443759630  0.8249370277  0.7858942065  0.8060335670  0.7882653061  24.181360201  2.0594247552  2.2552723885  2400          0.1811459597 
0.2736974672  0.8176888552  0.2784075929  0.2689873418  0.8809860059  0.8551617874  0.8337531486  0.7909319899  0.8215423837  0.8069727891  27.204030226  1.9937793350  2.2552723885  2700          0.1778921342 
0.2922873969  0.8263742852  0.2923807013  0.2921940928  0.8863782257  0.8577298408  0.8510705290  0.8161209068  0.8308901636  0.8052721088  30.226700251  1.9664845951  2.2552723885  3000          0.1828173510 
0.3032299949  0.8305405744  0.3037173741  0.3027426160  0.8913852869  0.8592706728  0.8598866499  0.8236775819  0.8387507967  0.8086734694  33.249370277  1.9014620554  2.2552723885  3300          0.1817088993 
0.3129864750  0.8317342326  0.3105721065  0.3154008439  0.8948517140  0.8669748331  0.8819269521  0.8136020151  0.8548969620  0.8146258503  36.272040302  1.8434993215  2.2552723885  3600          0.1813597735 
0.3189191503  0.8441003488  0.3171631954  0.3206751055  0.8984465272  0.8787878788  0.8812972292  0.8312342569  0.8674314850  0.8222789116  39.294710327  1.5819323552  5.3961586952  3900          0.2021731814 
0.3182599023  0.8412843294  0.3168995518  0.3196202532  0.8998587752  0.8767334361  0.8942065491  0.8324937028  0.8704057786  0.8146258503  42.317380352  1.2826288033  5.3961586952  4200          0.2213339170 
0.3158864151  0.8475358986  0.3174268389  0.3143459916  0.9103864424  0.8741653826  0.8875944584  0.8274559194  0.8725302741  0.8409863946  45.340050377  1.2463720274  5.3961586952  4500          0.2171904023 
0.3131177406  0.8550431732  0.3150540469  0.3111814346  0.9089741944  0.8844375963  0.9011335013  0.8337531486  0.8803909072  0.8469387755  48.362720403  1.2367683880  5.3961586952  4800          0.2215138555 
0.3112719576  0.8538656372  0.3134721856  0.3090717300  0.9126973938  0.8777606574  0.9061712846  0.8539042821  0.8823029530  0.8299319728  50.377833753  1.2217910814  5.3961586952  5000          0.2209971535 
