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: 3
	output_dir: sweep/ablation3/outputs/03a4cb024db0c6f743c27aa5aa3e7f63
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 297235714
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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: 0.7010166027828918
	lambda2: 0.6269010951324223
	last_k_epoch: 0.38851977780027735
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.131347198605345
	weight_decay: 1e-06
	worst_case_p: 0.3
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    
0.0444171295  0.0500870953  0.0651199578  0.0643459916  0.0472461163  0.0405752440  0.0456549118  0.0453400504  0.0412152114  0.0476190476  0.0000000000  4.7754507065  2.1692652702  0             1.4303689003 
0.2175117497  0.6764436437  0.7540205642  0.7510548523  0.7490050071  0.7467899332  0.5415617128  0.5314861461  0.2164860846  0.2185374150  3.0226700252  2.6925710940  2.4375615120  300           0.1604085445 
0.3721172980  0.7897671730  0.8602689164  0.8449367089  0.8161509822  0.8253723677  0.7292191436  0.6989924433  0.3734862970  0.3707482993  6.0453400504  2.2616455917  2.4375615120  600           0.1817232164 
0.3866746984  0.8171134510  0.8998154495  0.8734177215  0.8390037232  0.8335901387  0.7714105793  0.7443324937  0.3881453155  0.3852040816  9.0680100756  2.1120783035  2.4375615120  900           0.1830672439 
0.3843380244  0.8316209999  0.9193250725  0.8902953586  0.8524842727  0.8438623523  0.7953400504  0.7607052897  0.3826216274  0.3860544218  12.090680100  2.0034848173  2.4375615120  1200          0.1857649271 
0.3996381852  0.8453649085  0.9327708938  0.9018987342  0.8651945051  0.8520801233  0.8221032746  0.7821158690  0.4013171872  0.3979591837  15.113350125  1.9147055308  2.4375615120  1500          0.1822626265 
0.4119643234  0.8542372808  0.9417347746  0.9282700422  0.8768776480  0.8649203903  0.8391057935  0.7695214106  0.4132143616  0.4107142857  18.136020151  1.7997901396  2.4375615120  1800          0.1854969629 
0.4220594705  0.8716254389  0.9522805167  0.9282700422  0.8845808191  0.8793014895  0.8548488665  0.8073047859  0.4214998938  0.4226190476  21.158690176  1.7085815044  2.4375615120  2100          0.1860131812 
0.4259906000  0.8755948185  0.9554442394  0.9356540084  0.8922839902  0.8787878788  0.8759445844  0.8123425693  0.4268111324  0.4251700680  24.181360201  1.6523025997  2.4375615120  2400          0.1858883023 
0.4303479835  0.8895675003  0.9617716847  0.9398734177  0.9013994094  0.8875192604  0.8853904282  0.8413098237  0.4287231782  0.4319727891  27.204030226  1.6290002370  2.4375615120  2700          0.1818620491 
0.4361927847  0.8884976787  0.9673081993  0.9419831224  0.9028116575  0.8859784284  0.8942065491  0.8375314861  0.4327597196  0.4396258503  30.226700251  1.5955410179  2.4375615120  3000          0.1838714242 
0.4339609806  0.8954606860  0.9662536251  0.9430379747  0.9082038773  0.8957370313  0.9005037783  0.8476070529  0.4316974719  0.4362244898  33.249370277  1.2722707506  5.3968682289  3300          0.2117981132 
0.4303479835  0.8993727703  0.9694173477  0.9419831224  0.9119270766  0.9060092450  0.9184508816  0.8501259446  0.4287231782  0.4319727891  36.272040302  1.1549120927  5.3968682289  3600          0.2212795830 
0.4272663812  0.8955047042  0.9691537042  0.9462025316  0.9134677109  0.8952234206  0.9149874055  0.8450881612  0.4259613342  0.4285714286  39.294710327  1.1378753161  5.3968682289  3900          0.2215091308 
0.4252467556  0.9035487769  0.9746902188  0.9483122363  0.9166773655  0.9008731382  0.9241183879  0.8614609572  0.4261737837  0.4243197279  42.317380352  1.1265730043  5.3968682289  4200          0.2202346651 
0.4258846462  0.9015158649  0.9752175059  0.9451476793  0.9239953781  0.9054956343  0.9275818640  0.8539042821  0.4257488846  0.4260204082  45.340050377  1.1149761162  5.3968682289  4500          0.2189453499 
0.4239715164  0.9116986912  0.9754811495  0.9620253165  0.9246373090  0.9090909091  0.9285264484  0.8639798489  0.4253239856  0.4226190476  48.362720403  1.1036576074  5.3968682289  4800          0.2202799797 
0.4253535223  0.9123950234  0.9783812286  0.9493670886  0.9229682886  0.9162814587  0.9329345088  0.8715365239  0.4246866369  0.4260204082  50.377833753  1.1041329360  5.3968682289  5000          0.2218466258 
