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: PACS
	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/a3812659e0af95baa28ba00e97fae8e7
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1603835918
	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: 0.8610090196552951
	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 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    
0.1809364920  0.1555167411  0.1641244661  0.1540342298  0.1924307036  0.1688034188  0.1242514970  0.1437125749  0.1797073791  0.1821656051  0.0000000000  7.6426801682  2.0074062347  0             1.5852115154 
0.7398156023  0.9554845752  0.9725442343  0.9339853301  0.9738805970  0.9444444444  0.9977544910  0.9880239521  0.7395038168  0.7401273885  7.1856287425  2.6079753488  2.2544541359  300           0.1489051867 
0.7788038277  0.9668270711  0.9896278218  0.9462102689  0.9893390192  0.9572649573  1.0000000000  0.9970059880  0.7779898219  0.7796178344  14.371257485  0.9462475175  2.2544541359  600           0.1675174443 
0.7889876173  0.9718353084  0.9957291031  0.9535452323  0.9904051173  0.9679487179  1.0000000000  0.9940119760  0.7894402036  0.7885350318  21.556886227  0.8483284718  2.2544541359  900           0.1696212101 
0.7934421642  0.9759327704  0.9945088469  0.9731051345  0.9936034115  0.9636752137  1.0000000000  0.9910179641  0.7958015267  0.7910828025  28.742514970  0.7749769430  2.2544541359  1200          0.1696690146 
0.8049030806  0.9779218126  0.9957291031  0.9559902200  0.9946695096  0.9807692308  1.0000000000  0.9970059880  0.8021628499  0.8076433121  35.928143712  0.7415273351  2.2544541359  1500          0.1701583743 
0.8109487687  0.9682740549  0.9969493594  0.9535452323  0.9973347548  0.9572649573  1.0000000000  0.9940119760  0.8104325700  0.8114649682  43.113772455  0.7099813759  2.2544541359  1800          0.1685988283 
0.8160418790  0.9759102881  0.9975594875  0.9657701711  0.9978678038  0.9679487179  0.9992514970  0.9940119760  0.8142493639  0.8178343949  50.299401197  0.6935196089  2.2544541359  2100          0.1691777833 
0.8228851635  0.9733625551  0.9981696156  0.9559902200  0.9957356077  0.9700854701  1.0000000000  0.9940119760  0.8202926209  0.8254777070  57.485029940  0.6838746135  2.2544541359  2400          0.1698043688 
0.8225670974  0.9793687964  0.9969493594  0.9633251834  0.9978678038  0.9807692308  1.0000000000  0.9940119760  0.8196564885  0.8254777070  64.670658682  0.6435021378  2.2544541359  2700          0.1684944288 
0.8219293443  0.9763367855  0.9993898719  0.9657701711  0.9994669510  0.9722222222  1.0000000000  0.9910179641  0.8209287532  0.8229299363  71.856287425  0.6633704368  2.2544541359  3000          0.1686132161 
0.8239983951  0.9759102881  0.9993898719  0.9657701711  0.9968017058  0.9679487179  1.0000000000  0.9940119760  0.8225190840  0.8254777070  79.041916167  0.6337725675  2.2544541359  3300          0.1676280292 
0.8244763047  0.9791702718  1.0000000000  0.9755501222  0.9994669510  0.9679487179  0.9992514970  0.9940119760  0.8222010178  0.8267515924  86.227544910  0.4873780367  5.3987078667  3600          0.1953577193 
0.8230433862  0.9792505346  0.9993898719  0.9706601467  0.9989339019  0.9700854701  1.0000000000  0.9970059880  0.8218829517  0.8242038217  93.413173652  0.3696890382  5.3987078667  3900          0.2063904675 
0.8227236994  0.9769462910  0.9987797437  0.9633251834  0.9978678038  0.9764957265  1.0000000000  0.9910179641  0.8237913486  0.8216560510  100.59880239  0.3412042694  5.3987078667  4200          0.2066080221 
0.8227236994  0.9749278006  1.0000000000  0.9559902200  1.0000000000  0.9807692308  1.0000000000  0.9880239521  0.8237913486  0.8216560510  107.78443113  0.3216404198  5.3987078667  4500          0.2070182681 
0.8236778978  0.9779442950  0.9987797437  0.9633251834  0.9989339019  0.9764957265  0.9992514970  0.9940119760  0.8256997455  0.8216560510  114.97005988  0.3121889671  5.3987078667  4800          0.2089738901 
0.8238369309  0.9841335444  0.9993898719  0.9682151589  0.9984008529  0.9871794872  1.0000000000  0.9970059880  0.8260178117  0.8216560510  119.76047904  0.3017792147  5.3987078667  5000          0.2115355659 
