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: 1
	output_dir: sweep/ablation3/outputs/fc5f78def51a7b8260da15d7c346ad90
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1101720297
	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: 0.7819049321936025
	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 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    
0.0503778337  0.1916497209  0.4123385183  0.4166666667  0.0190011555  0.0179763739  0.0541561713  0.0465994962  0.1595496070  0.1403061224  0.0000000000  4.6929593086  2.0074815750  0             1.5193722248 
0.4374999998  0.7130394187  0.8033219088  0.7784810127  0.7741686994  0.7832562917  0.4417506297  0.4332493703  0.6080305927  0.5773809524  3.0226700252  2.9717208131  2.2580189705  300           0.1522484803 
0.4806360199  0.7773159624  0.8542051147  0.8523206751  0.8074207215  0.8002054443  0.4776448363  0.4836272040  0.7110686212  0.6794217687  6.0453400504  2.5908955661  2.2580189705  600           0.1775298866 
0.5051952139  0.7978316697  0.8803058265  0.8670886076  0.8270638079  0.8274268105  0.4952770781  0.5151133501  0.7420862545  0.6989795918  9.0680100756  2.4549876750  2.2580189705  900           0.1806639250 
0.5229848864  0.8157756251  0.9045610335  0.8881856540  0.8451662601  0.8397534669  0.5107052897  0.5352644836  0.7629063098  0.7193877551  12.090680100  2.3360986722  2.2580189705  1200          0.1807839632 
0.5362090677  0.8267317297  0.9240706565  0.8987341772  0.8554371550  0.8459167951  0.5270780856  0.5453400504  0.7854259613  0.7355442177  15.113350125  2.2640900819  2.2580189705  1500          0.1819512208 
0.5393576823  0.8445260091  0.9253888742  0.9113924051  0.8667351393  0.8577298408  0.5308564232  0.5478589421  0.8007223284  0.7644557823  18.136020151  2.1664469333  2.2580189705  1800          0.1805701645 
0.5451826194  0.8502272900  0.9388346955  0.9240506329  0.8763641032  0.8613251156  0.5374685139  0.5528967254  0.8149564478  0.7653061224  21.158690176  2.0889542357  2.2580189705  2100          0.1812351704 
0.5535264481  0.8542162755  0.9485895070  0.9177215190  0.8825266401  0.8762198254  0.5440806045  0.5629722922  0.8264287232  0.7687074830  24.181360201  2.0321118367  2.2580189705  2400          0.1815228526 
0.5562027705  0.8678914972  0.9501713683  0.9388185654  0.8883040185  0.8808423215  0.5481738035  0.5642317380  0.8406628426  0.7840136054  27.204030226  1.9630326235  2.2580189705  2700          0.1796337223 
0.5569899242  0.8690268375  0.9549169523  0.9335443038  0.8944665554  0.8818695429  0.5510075567  0.5629722922  0.8449118334  0.7916666667  30.226700251  1.9019354828  2.2580189705  3000          0.1839951952 
0.5606108310  0.8730654072  0.9564988136  0.9335443038  0.8998587752  0.8880328711  0.5557304786  0.5654911839  0.8542596133  0.7976190476  33.249370277  1.8621361005  2.2580189705  3300          0.1821579695 
0.5636020148  0.8800399234  0.9638808331  0.9377637131  0.9028116575  0.8936825886  0.5579345088  0.5692695214  0.8623326960  0.8086734694  36.272040302  1.8083972446  2.2580189705  3600          0.1821053227 
0.5631297226  0.8849194571  0.9665172687  0.9440928270  0.9076903325  0.8900873138  0.5607682620  0.5654911839  0.8693435309  0.8205782313  39.294710327  1.5546934060  5.3968758583  3900          0.2052645588 
0.5654911836  0.8875607673  0.9696809913  0.9409282700  0.9126973938  0.8952234206  0.5629722922  0.5680100756  0.8782664117  0.8265306122  42.317380352  1.3062293220  5.3968758583  4200          0.2211189119 
0.5648614607  0.8861257047  0.9704719220  0.9430379747  0.9142380280  0.9024139702  0.5642317380  0.5654911839  0.8757170172  0.8129251701  45.340050377  1.2727744687  5.3968758583  4500          0.2205679512 
0.5656486143  0.8915977836  0.9731083575  0.9462025316  0.9169341379  0.9003595275  0.5658060453  0.5654911839  0.8816656044  0.8282312925  48.362720403  1.2563131909  5.3968758583  4800          0.2185574150 
0.5667506294  0.8894737825  0.9680991300  0.9430379747  0.9174476826  0.9039548023  0.5667506297  0.5667506297  0.8935627788  0.8214285714  50.377833753  1.2391728050  5.3968758583  5000          0.2141877615 
