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: 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: 1
	output_dir: sweep/ablation3/outputs/1487078cb9d4d3559f4e1ccffa859d33
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 876823002
	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: 0.6880433961757358
	lambda2: 0.9840350138898164
	last_k_epoch: 0.33648211095401626
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3.599417945900826
	weight_decay: 0.0001
	worst_case_p: 0.25
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    
0.0403797963  0.0739460442  0.0495649881  0.0548523207  0.0442932340  0.0364663585  0.1067380353  0.1083123426  0.0480135968  0.0586734694  0.0000000000  6.4993705750  2.0074815750  0             1.4715566635 
0.4443095739  0.6554776113  0.7764302663  0.7816455696  0.4340736937  0.4545454545  0.6076826196  0.5793450882  0.6137667304  0.6054421769  3.0226700252  2.8420045590  2.2580189705  300           0.1563447873 
0.3573222293  0.7547583220  0.8544687582  0.8565400844  0.3489536526  0.3656908064  0.7301637280  0.7002518892  0.7063947313  0.7074829932  6.0453400504  2.4554671613  2.2580189705  600           0.1800398962 
0.3817814462  0.7816866544  0.8876878460  0.8702531646  0.3721915522  0.3913713405  0.7540931990  0.7418136020  0.7486721904  0.7329931973  9.0680100756  2.3235009948  2.2580189705  900           0.1846426519 
0.4149716490  0.7926083768  0.9008700237  0.8902953586  0.4015919887  0.4283513097  0.7729848866  0.7443324937  0.7673677502  0.7431972789  12.090680100  2.2141102286  2.2580189705  1200          0.1835472353 
0.4253717873  0.8055971825  0.9135249143  0.8997890295  0.4090383875  0.4417051875  0.8079345088  0.7670025189  0.7782026769  0.7500000000  15.113350125  2.1392543685  2.2580189705  1500          0.1827649522 
0.4327542237  0.8150443459  0.9253888742  0.9082278481  0.4202079856  0.4453004622  0.8142317380  0.7732997481  0.8049713193  0.7636054422  18.136020151  2.0631362172  2.2580189705  1800          0.1799334606 
0.4407147937  0.8303114348  0.9314526760  0.9177215190  0.4263705225  0.4550590652  0.8362720403  0.7934508816  0.8202676864  0.7797619048  21.158690176  1.9838386452  2.2580189705  2100          0.1825985487 
0.4405221814  0.8405767554  0.9443712101  0.9303797468  0.4264989087  0.4545454545  0.8523299748  0.8047858942  0.8370512003  0.7865646259  24.181360201  1.8972676194  2.2580189705  2400          0.1827743737 
0.4401370229  0.8453164420  0.9543896652  0.9314345992  0.4257285916  0.4545454545  0.8633501259  0.8060453401  0.8429997876  0.7984693878  27.204030226  1.8059105913  2.2580189705  2700          0.1838217258 
0.4402652442  0.8600742343  0.9588716056  0.9314345992  0.4285530877  0.4519774011  0.8709068010  0.8350125945  0.8542596133  0.8137755102  30.226700251  1.7488603135  2.2580189705  3000          0.1847188083 
0.4430899051  0.8645664621  0.9625626153  0.9377637131  0.4316343561  0.4545454545  0.8850755668  0.8413098237  0.8655194391  0.8146258503  33.249370277  1.6995594621  2.2580189705  3300          0.1789968220 
0.4413566586  0.8608202804  0.9654626944  0.9356540084  0.4286814739  0.4540318439  0.8979848866  0.8236775819  0.8697684300  0.8231292517  36.272040302  1.2506410368  5.3968758583  3600          0.2178555242 
0.4386602850  0.8710068833  0.9675718429  0.9345991561  0.4273976120  0.4499229584  0.9052267003  0.8450881612  0.8712555768  0.8333333333  39.294710327  1.1632485799  5.3968758583  3900          0.2247270083 
0.4383394184  0.8772786445  0.9728447139  0.9440928270  0.4252150469  0.4514637904  0.9061712846  0.8476070529  0.8829403017  0.8401360544  42.317380352  1.1387992299  5.3968758583  4200          0.2239049927 
0.4369271374  0.8697258827  0.9720537833  0.9451476793  0.4229040955  0.4509501798  0.9121536524  0.8400503778  0.8895262375  0.8239795918  45.340050377  1.1236352106  5.3968758583  4500          0.2224497565 
0.4363493336  0.8819286600  0.9720537833  0.9504219409  0.4227757093  0.4499229584  0.9130982368  0.8501259446  0.8922880816  0.8452380952  48.362720403  1.1082641890  5.3968758583  4800          0.2236537679 
0.4353863383  0.8869557338  0.9752175059  0.9504219409  0.4223905508  0.4483821263  0.9215994962  0.8677581864  0.8912258339  0.8426870748  50.377833753  1.0907868168  5.3968758583  5000          0.2190677691 
