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/d668b8885b57bf6324a55aec5fb4e9cc
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1891329785
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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: 0.7819049321936025
	lambda2: 0.9075316444347157
	last_k_epoch: 0.25491468830584113
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.907263233121133
	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    
0.0801587646  0.0765886650  0.0759293435  0.0843881857  0.0751059186  0.0801232666  0.0698992443  0.0680100756  0.1051625239  0.0816326531  0.0000000000  5.7006053925  2.0074815750  0             1.4103384018 
0.3168113924  0.6104248929  0.3023991563  0.3312236287  0.7506740275  0.7380585516  0.5085012594  0.5251889169  0.5831739962  0.5680272109  3.0226700252  2.9255980945  2.2580189705  300           0.1543072112 
0.1793027851  0.6860693696  0.1676773003  0.1909282700  0.7956091925  0.7776065742  0.6646725441  0.6675062972  0.6558317400  0.6130952381  6.0453400504  2.5791983318  2.2580189705  600           0.1772648064 
0.1822032813  0.7259797399  0.1703137358  0.1940928270  0.8139684170  0.8043143297  0.7084382872  0.7078085642  0.7142553644  0.6658163265  9.0680100756  2.4706064566  2.2580189705  900           0.1787939739 
0.2137127185  0.7423935788  0.2027418930  0.2246835443  0.8338682758  0.8104776579  0.7452770781  0.7304785894  0.7374123646  0.6862244898  12.090680100  2.3664022549  2.2580189705  1200          0.1835011721 
0.2432451072  0.7625655121  0.2291062484  0.2573839662  0.8469636667  0.8248587571  0.7654282116  0.7468513854  0.7669428511  0.7159863946  15.113350125  2.3083597533  2.2580189705  1500          0.1841685939 
0.2885980558  0.7784780065  0.2723437912  0.3048523207  0.8563358583  0.8412942989  0.7871536524  0.7594458438  0.7892500531  0.7346938776  18.136020151  2.2447149857  2.2580189705  1800          0.1803237335 
0.3263035337  0.7987994591  0.3139994727  0.3386075949  0.8649377327  0.8546481767  0.8051007557  0.7934508816  0.8011472275  0.7482993197  21.158690176  2.1985592421  2.2580189705  2100          0.1812107380 
0.3531983744  0.8085722469  0.3435275508  0.3628691983  0.8754653999  0.8695428865  0.8176952141  0.7959697733  0.8211174846  0.7602040816  24.181360201  2.1190336645  2.2580189705  2400          0.1844681334 
0.3653277855  0.8189955178  0.3540732929  0.3765822785  0.8808576197  0.8695428865  0.8378463476  0.8110831234  0.8330146590  0.7763605442  27.204030226  2.0605720850  2.2580189705  2700          0.1809721494 
0.3856318155  0.8298073861  0.3683100448  0.4029535865  0.8852227500  0.8762198254  0.8469773300  0.8249370277  0.8404503930  0.7882653061  30.226700251  2.0009030370  2.2580189705  3000          0.1835262609 
0.4015843363  0.8240362725  0.3843923016  0.4187763713  0.8925407626  0.8715973292  0.8693324937  0.8198992443  0.8502230720  0.7806122449  33.249370277  1.9655221291  2.2580189705  3300          0.1854048745 
0.4143725782  0.8473955245  0.3983654100  0.4303797468  0.8981897548  0.8854648177  0.8797229219  0.8463476071  0.8629700446  0.8103741497  36.272040302  1.8848868752  2.2580189705  3600          0.1833633812 
0.4160862613  0.8427058259  0.4017927762  0.4303797468  0.9052509950  0.8890600924  0.8913727960  0.8312342569  0.8633949437  0.8078231293  39.294710327  1.5851047516  5.3968758583  3900          0.2024616814 
0.4178003616  0.8468983011  0.4020564197  0.4335443038  0.9060213121  0.8864920390  0.8926322418  0.8438287154  0.8776290631  0.8103741497  42.317380352  1.2877654680  5.3968758583  4200          0.2248169017 
0.4180642832  0.8579310386  0.4004745584  0.4356540084  0.9128257799  0.8849512070  0.9001889169  0.8614609572  0.8780539622  0.8273809524  45.340050377  1.2553634465  5.3968758583  4500          0.2249697598 
0.4168776091  0.8551407013  0.4002109148  0.4335443038  0.9116703043  0.8952234206  0.9020780856  0.8564231738  0.8835776503  0.8137755102  48.362720403  1.2389492130  5.3968758583  4800          0.2255577970 
0.4142406174  0.8594022006  0.3991563406  0.4293248945  0.9141096418  0.8885464818  0.9058564232  0.8639798489  0.8854896962  0.8256802721  50.377833753  1.2202367908  5.3968758583  5000          0.2257995009 
