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: [1]
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/fdddf2672eb85867b1b41b946f5afa27
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 2023135340
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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 normal 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    
0.1536238632  0.1132161613  0.1067756393  0.0907172996  0.1547053537  0.1525423729  0.1051637280  0.1171284635  0.1298066709  0.1318027211  0.0000000000  5.4299955368  2.0074815750  0             1.6032299995 
0.2426656505  0.6388656168  0.7861850778  0.7552742616  0.2398253948  0.2455059065  0.5913098237  0.5856423174  0.6063309964  0.5756802721  3.0226700252  2.8494422388  2.2545704842  300           0.1576826652 
0.3191885319  0.7338836732  0.8600052729  0.8491561181  0.3194248299  0.3189522342  0.6936397985  0.6977329975  0.7032079881  0.6547619048  6.0453400504  2.4461318318  2.2545704842  600           0.1769780525 
0.3577070252  0.7709584634  0.8932243607  0.8744725738  0.3553729619  0.3600410889  0.7301637280  0.7292191436  0.7410240068  0.7091836735  9.0680100756  2.3126484172  2.2545704842  900           0.1839849798 
0.3913464478  0.7905921482  0.9095702610  0.8881856540  0.3877262807  0.3949666153  0.7748740554  0.7531486146  0.7692797960  0.7304421769  12.090680100  2.2063459575  2.2545704842  1200          0.1822413635 
0.4094501858  0.8093180318  0.9256525178  0.9008438819  0.4039029400  0.4149974319  0.7950251889  0.7745591940  0.7981729339  0.7525510204  15.113350125  2.1346976380  2.2545704842  1500          0.1812078985 
0.4160624370  0.8129813386  0.9330345373  0.9071729958  0.4114777250  0.4206471495  0.8211586902  0.7758186398  0.8175058424  0.7559523810  18.136020151  2.0296789229  2.2545704842  1800          0.1760209934 
0.4169612722  0.8281374456  0.9427893488  0.9135021097  0.4112209526  0.4227015922  0.8353274559  0.8073047859  0.8213299341  0.7636054422  21.158690176  1.9542681770  2.2545704842  2100          0.1778406644 
0.4231241718  0.8443123902  0.9506986554  0.9198312236  0.4178970343  0.4283513097  0.8482367758  0.8324937028  0.8398130444  0.7806122449  24.181360201  1.8957101921  2.2545704842  2400          0.1818265669 
0.4277463712  0.8544734979  0.9564988136  0.9303797468  0.4225189370  0.4329738059  0.8658690176  0.8362720403  0.8497981729  0.7967687075  27.204030226  1.8333550179  2.2545704842  2700          0.1797808274 
0.4321118312  0.8624138920  0.9586079620  0.9335443038  0.4261137502  0.4381099127  0.8806675063  0.8501259446  0.8529849161  0.8035714286  30.226700251  1.7816855597  2.2545704842  3000          0.1763598506 
0.4350649113  0.8587932880  0.9654626944  0.9377637131  0.4289382462  0.4411915768  0.8875944584  0.8324937028  0.8638198428  0.8061224490  33.249370277  1.7242845333  2.2545704842  3300          0.1771869683 
0.4394304043  0.8678782056  0.9694173477  0.9388185654  0.4320195147  0.4468412943  0.8992443325  0.8450881612  0.8682812832  0.8197278912  36.272040302  1.6755007080  2.2545704842  3600          0.1802752781 
0.4367340636  0.8728692645  0.9686264171  0.9356540084  0.4302221081  0.4432460195  0.9061712846  0.8564231738  0.8772041640  0.8265306122  39.294710327  1.4242519049  5.3973717690  3900          0.2069439586 
0.4319191530  0.8790515172  0.9680991300  0.9377637131  0.4272692258  0.4365690806  0.9184508816  0.8677581864  0.8786913108  0.8316326531  42.317380352  1.2162783480  5.3973717690  4200          0.2229065156 
0.4302500667  0.8821051465  0.9728447139  0.9398734177  0.4249582745  0.4355418593  0.9124685139  0.8816120907  0.8878266412  0.8248299320  45.340050377  1.1878909210  5.3973717690  4500          0.2210038924 
0.4287735596  0.8786316748  0.9728447139  0.9398734177  0.4230324817  0.4345146379  0.9228589421  0.8652392947  0.8897386871  0.8307823129  48.362720403  1.1730769090  5.3973717690  4800          0.2238383412 
0.4263982503  0.8816025647  0.9746902188  0.9356540084  0.4208499165  0.4319465845  0.9203400504  0.8690176322  0.8986615679  0.8401360544  50.377833753  1.1560743076  5.3973717690  5000          0.2197561145 
