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: 1
	output_dir: sweep/ablation3/outputs/b769fc02c876ff230eeda79b40aece25
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 251496496
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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 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    
0.1021137103  0.0640656234  0.0181914052  0.0348101266  0.0558479908  0.0503338469  0.1253148615  0.1070528967  0.1047376248  0.0994897959  0.0000000000  5.8150386810  2.0074815750  0             1.4164915085 
0.3313139786  0.6903878920  0.7732665436  0.7436708861  0.7560662473  0.7519260401  0.5573047859  0.5755667506  0.3326959847  0.3299319728  3.0226700252  2.9168049145  2.2580189705  300           0.1577409856 
0.4088832631  0.7915837865  0.8563142631  0.8523206751  0.8192322506  0.8032871084  0.7096977330  0.7191435768  0.4087529212  0.4090136054  6.0453400504  2.4858336369  2.2580189705  600           0.1731762632 
0.4184486412  0.8129711756  0.8855786976  0.8765822785  0.8357940686  0.8217770930  0.7500000000  0.7405541562  0.4117272148  0.4251700680  9.0680100756  2.3631005418  2.2580189705  900           0.1775484769 
0.4344918335  0.8383898550  0.9087793303  0.8892405063  0.8491462319  0.8412942989  0.7792821159  0.7846347607  0.4336095177  0.4353741497  12.090680100  2.2340488176  2.2580189705  1200          0.1771015414 
0.4360852051  0.8461001155  0.9230160823  0.8955696203  0.8667351393  0.8505392912  0.8123425693  0.7921914358  0.4367962609  0.4353741497  15.113350125  2.1558827376  2.2580189705  1500          0.1786045726 
0.4422484097  0.8575815365  0.9348800422  0.9029535865  0.8728976762  0.8561890087  0.8340680101  0.8136020151  0.4423199490  0.4421768707  18.136020151  2.0398246662  2.2580189705  1800          0.1763222202 
0.4437366404  0.8698587569  0.9446348537  0.9187763713  0.8840672744  0.8746789933  0.8403652393  0.8161209068  0.4418950499  0.4455782313  21.158690176  1.9418590132  2.2580189705  2100          0.1730982010 
0.4444821107  0.8768678158  0.9462167150  0.9251054852  0.8903581975  0.8793014895  0.8642947103  0.8261964736  0.4374336095  0.4515306122  24.181360201  1.8844850079  2.2580189705  2400          0.1711865671 
0.4452256841  0.8820782206  0.9557078829  0.9303797468  0.8983181410  0.8808423215  0.8671284635  0.8350125945  0.4389207563  0.4515306122  27.204030226  1.8205841204  2.2580189705  2700          0.1699723879 
0.4422494936  0.8875679783  0.9599261798  0.9335443038  0.9030684298  0.8916281459  0.8850755668  0.8375314861  0.4389207563  0.4455782313  30.226700251  1.7629187779  2.2580189705  3000          0.1738774848 
0.4408680296  0.8861344931  0.9651990509  0.9229957806  0.9083322634  0.8890600924  0.8957808564  0.8463476071  0.4378585086  0.4438775510  33.249370277  1.7271724021  2.2580189705  3300          0.1740657743 
0.4404431305  0.8949272368  0.9654626944  0.9356540084  0.9170625241  0.8952234206  0.8986146096  0.8539042821  0.4370087104  0.4438775510  36.272040302  1.7568602649  2.2580189705  3600          0.1712835749 
0.4403377187  0.9004190278  0.9694173477  0.9409282700  0.9184747721  0.9013867488  0.9061712846  0.8589420655  0.4342468664  0.4464285714  39.294710327  1.4817857714  5.3968758583  3900          0.1955081789 
0.4375753327  0.8994593888  0.9694173477  0.9430379747  0.9198870202  0.9039548023  0.9178211587  0.8513853904  0.4304227746  0.4447278912  42.317380352  1.2525913858  5.3968758583  4200          0.2100244602 
0.4333236320  0.9023540776  0.9720537833  0.9398734177  0.9272050327  0.9044684129  0.9203400504  0.8627204030  0.4304227746  0.4362244898  45.340050377  1.2256728240  5.3968758583  4500          0.2112415059 
0.4359806062  0.9057807977  0.9733720011  0.9388185654  0.9268198742  0.9044684129  0.9212846348  0.8740554156  0.4314850223  0.4404761905  48.362720403  1.2058456190  5.3968758583  4800          0.2092176000 
0.4348118627  0.9089326930  0.9746902188  0.9398734177  0.9275901913  0.9090909091  0.9294710327  0.8778337531  0.4299978755  0.4396258503  50.377833753  1.2042470145  5.3968758583  5000          0.2106066227 
