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: 1
	output_dir: sweep/ablation3/outputs/5ca2c33cf9bf66fe89d1639b6efafa96
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1843587644
	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: 0.6880433961757358
	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 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    
0.0764665033  0.1978953836  0.0780384920  0.0748945148  0.2681987418  0.2881355932  0.1237405542  0.1448362720  0.1848311026  0.1607142857  0.0000000000  5.4452166557  2.0074815750  0             1.6846721172 
0.0742260893  0.6257246391  0.0693382547  0.0791139241  0.7154962126  0.6913199795  0.6183879093  0.5957178841  0.6020820055  0.5901360544  3.0226700252  2.8539369893  2.2545704842  300           0.1517148042 
0.3379063530  0.7347156309  0.3182177696  0.3575949367  0.8092181281  0.8027734977  0.7008816121  0.6989924433  0.7040577863  0.7023809524  6.0453400504  2.5229611222  2.2545704842  600           0.1799482203 
0.3313127612  0.7514267394  0.3240179278  0.3386075949  0.8370779304  0.8325629173  0.7471662469  0.7040302267  0.7352878691  0.7176870748  9.0680100756  2.4098542507  2.2545704842  900           0.1787317053 
0.3455511817  0.7688400570  0.3398365410  0.3512658228  0.8472204391  0.8341037494  0.7751889169  0.7292191436  0.7607818143  0.7431972789  12.090680100  2.3323331185  2.2545704842  1200          0.1798982207 
0.3640085944  0.7895777077  0.3588188769  0.3691983122  0.8544100655  0.8402670776  0.8032115869  0.7682619647  0.7854259613  0.7602040816  15.113350125  2.2459206796  2.2545704842  1500          0.1777504047 
0.3853669204  0.8039386605  0.3772739257  0.3934599156  0.8680190012  0.8520801233  0.8353274559  0.7833753149  0.8060335670  0.7763605442  18.136020151  2.1833715097  2.2545704842  1800          0.1794064172 
0.3939364484  0.8109407084  0.3859741629  0.4018987342  0.8727692900  0.8638931690  0.8387909320  0.7959697733  0.8211174846  0.7729591837  21.158690176  2.1199537627  2.2545704842  2100          0.1794189040 
0.4058017988  0.8197061373  0.3991563406  0.4124472574  0.8803440750  0.8638931690  0.8517002519  0.8010075567  0.8364138517  0.7942176871  24.181360201  2.0629190119  2.2545704842  2400          0.1779323737 
0.4177991101  0.8293571220  0.4115475877  0.4240506329  0.8850943638  0.8680020544  0.8633501259  0.8198992443  0.8504355216  0.8001700680  27.204030226  1.9519895530  2.2545704842  2700          0.1809670854 
0.4218860023  0.8330268335  0.4165568152  0.4272151899  0.8912569008  0.8757062147  0.8825566751  0.8274559194  0.8629700446  0.7959183673  30.226700251  1.9067877368  2.2545704842  3000          0.1784388534 
0.4275548949  0.8467216850  0.4236751911  0.4314345992  0.8953652587  0.8849512070  0.8938916877  0.8312342569  0.8676439346  0.8239795918  33.249370277  1.8775730737  2.2545704842  3300          0.1809740392 
0.4220176850  0.8474222407  0.4178750330  0.4261603376  0.8992168443  0.8844375963  0.9014483627  0.8261964736  0.8774166136  0.8316326531  36.272040302  1.3041357350  5.3973717690  3600          0.2178064394 
0.4200400803  0.8482042024  0.4160295281  0.4240506329  0.9073051740  0.8936825886  0.9118387909  0.8337531486  0.8846398980  0.8171768707  39.294710327  1.2143805635  5.3973717690  3900          0.2215515526 
0.4180626146  0.8559344066  0.4131294490  0.4229957806  0.9026832713  0.8911145352  0.9193954660  0.8476070529  0.8910133843  0.8290816327  42.317380352  1.1911496272  5.3973717690  4200          0.2208288701 
0.4142392268  0.8618680747  0.4097020828  0.4187763713  0.9112851457  0.8916281459  0.9134130982  0.8589420655  0.8935627788  0.8350340136  45.340050377  1.1733624033  5.3973717690  4500          0.2164534354 
0.4123935829  0.8651528060  0.4070656472  0.4177215190  0.9116703043  0.8998459168  0.9228589421  0.8639798489  0.9039728065  0.8316326531  48.362720403  1.1529412357  5.3973717690  4800          0.2195168718 
0.4116025132  0.8660694640  0.4065383601  0.4166666667  0.9157786622  0.8952234206  0.9209697733  0.8526448363  0.9052475037  0.8503401361  50.377833753  1.1482116115  5.3973717690  5000          0.2208131361 
