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: [2]
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/410ceaaae6a33404243fabddfd40cd92
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 774609317
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	trial_seed: 1
	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: 0.8610090196552951
	lambda2: 0.5777772877463595
	last_k_epoch: 0.32350558703299503
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.866557071912062
	weight_decay: 0.0001
	worst_case_p: 0.25
using augment transform
using augment transform
using normal 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    
0.1157115868  0.0455178125  0.0268916425  0.0221518987  0.0178456798  0.0174627632  0.1142947103  0.1171284635  0.1055874230  0.0969387755  0.0000000000  5.0569295883  2.0074815750  0             1.4552960396 
0.3565806044  0.6841696543  0.8064856314  0.7869198312  0.7424573116  0.7349768875  0.3542191436  0.3589420655  0.5476949225  0.5306122449  3.0226700252  2.9242291864  2.2580189705  300           0.1541874353 
0.4474181358  0.7746384024  0.8700237279  0.8554852321  0.8110155347  0.8043143297  0.4540302267  0.4408060453  0.6859995751  0.6641156463  6.0453400504  2.5693479586  2.2580189705  600           0.1768421181 
0.4713476068  0.7987527513  0.8892697074  0.8786919831  0.8366927719  0.8279404212  0.4704030227  0.4722921914  0.7289143828  0.6896258503  9.0680100756  2.4347912788  2.2580189705  900           0.1775316644 
0.4905541559  0.8130185390  0.9069338255  0.8902953586  0.8508152523  0.8387262455  0.4861460957  0.4949622166  0.7546207776  0.7100340136  12.090680100  2.3273555879  2.2580189705  1200          0.1792945949 
0.5077141055  0.8319671709  0.9190614289  0.9040084388  0.8623700090  0.8546481767  0.5040931990  0.5113350126  0.7773528787  0.7372448980  15.113350125  2.2346732446  2.2580189705  1500          0.1772869682 
0.5231423171  0.8390688182  0.9264434485  0.9092827004  0.8721273591  0.8613251156  0.5198362720  0.5264483627  0.7964733376  0.7465986395  18.136020151  2.1545212781  2.2580189705  1800          0.1797080763 
0.5393576823  0.8409612677  0.9354073293  0.9103375527  0.8766208756  0.8659476117  0.5371536524  0.5415617128  0.8068833652  0.7465986395  21.158690176  2.0927884169  2.2580189705  2100          0.1890578365 
0.5459697730  0.8577581017  0.9430529924  0.9251054852  0.8889459494  0.8777606574  0.5491183879  0.5428211587  0.8196303378  0.7704081633  24.181360201  2.0231723050  2.2580189705  2400          0.1847908227 
0.5508501257  0.8630135170  0.9480622199  0.9272151899  0.8972910515  0.8854648177  0.5601385390  0.5415617128  0.8270660718  0.7763605442  27.204030226  1.9427048389  2.2580189705  2700          0.1822106274 
0.5562027705  0.8669214229  0.9554442394  0.9251054852  0.8970342791  0.8941961993  0.5645465995  0.5478589421  0.8466114298  0.7814625850  30.226700251  1.8932232149  2.2580189705  3000          0.1830945961 
0.5590365236  0.8738056492  0.9625626153  0.9324894515  0.9051226088  0.8947098100  0.5664357683  0.5516372796  0.8485234757  0.7942176871  33.249370277  1.8606077262  2.2580189705  3300          0.1811539658 
0.5606108310  0.8762742024  0.9601898234  0.9345991561  0.9096161253  0.8983050847  0.5683249370  0.5528967254  0.8540471638  0.7959183673  36.272040302  1.4900330440  5.3947548866  3600          0.2067180443 
0.5606108310  0.8849821160  0.9630899025  0.9377637131  0.9103864424  0.8983050847  0.5632871537  0.5579345088  0.8612704483  0.8188775510  39.294710327  1.3029451561  5.3947548866  3900          0.2194953243 
0.5634445841  0.8849401886  0.9670445558  0.9377637131  0.9156502760  0.9049820236  0.5639168766  0.5629722922  0.8674314850  0.8120748299  42.317380352  1.2771852628  5.3947548866  4200          0.2191480486 
0.5632871534  0.8854706664  0.9717901397  0.9451476793  0.9132109385  0.9034411916  0.5636020151  0.5629722922  0.8744423199  0.8078231293  45.340050377  1.2577261206  5.3947548866  4500          0.2210350251 
0.5615554153  0.8805300273  0.9651990509  0.9398734177  0.9221979715  0.8998459168  0.5626574307  0.5604534005  0.8812407053  0.8018707483  48.362720403  1.2522702475  5.3947548866  4800          0.2237761339 
0.5631297226  0.8857464563  0.9680991300  0.9388185654  0.9228399024  0.9054956343  0.5632871537  0.5629722922  0.8803909072  0.8129251701  50.377833753  1.2409236455  5.3947548866  5000          0.2222862148 
