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: 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: 1
	output_dir: sweep/ablation3/outputs/ca679a21053358d142be5f00245692ac
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 219593590
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	trial_seed: 0
	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: 0.6880433961757358
	lambda2: 0.9840350138898164
	last_k_epoch: 0.33648211095401626
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3.599417945900826
	weight_decay: 0.0001
	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    
0.1070359281  0.1064697250  0.1415497254  0.1075794621  0.0991471215  0.1239316239  0.1032934132  0.1107784431  0.0836513995  0.0878980892  0.0000000000  10.250308036  2.0074062347  0             1.5734322071 
0.9812874247  0.9515178891  0.9780353874  0.9584352078  0.9701492537  0.9572649573  0.9895209581  0.9730538922  0.9516539440  0.9388535032  7.1856287425  3.4525422351  2.2566514015  300           0.1522613867 
0.9925149696  0.9602774670  0.9914582062  0.9511002445  0.9914712154  0.9679487179  0.9940119760  0.9910179641  0.9713740458  0.9617834395  14.371257485  1.3648333667  2.2566514015  600           0.1744438410 
0.9928892211  0.9641469185  0.9938987187  0.9682151589  0.9914712154  0.9700854701  0.9947604790  0.9910179641  0.9726463104  0.9541401274  21.556886227  1.1987496698  2.2566514015  900           0.1717449458 
0.9895209576  0.9662357998  0.9975594875  0.9706601467  0.9952025586  0.9700854701  0.9940119760  0.9850299401  0.9780534351  0.9579617834  28.742514970  1.0703049592  2.2566514015  1200          0.1726345126 
0.9876497001  0.9652359645  0.9951189750  0.9608801956  0.9984008529  0.9679487179  0.9932634731  0.9820359281  0.9802798982  0.9668789809  35.928143712  0.9969424166  2.2566514015  1500          0.1730833793 
0.9887724546  0.9643866699  0.9951189750  0.9706601467  0.9962686567  0.9658119658  0.9925149701  0.9850299401  0.9834605598  0.9566878981  43.113772455  0.9718548328  2.2566514015  1800          0.1733709073 
0.9895209576  0.9635716740  0.9975594875  0.9682151589  0.9984008529  0.9658119658  0.9940119760  0.9850299401  0.9844147583  0.9566878981  50.299401197  0.9409453470  2.2566514015  2100          0.1734719992 
0.9895209576  0.9687971803  0.9993898719  0.9706601467  0.9978678038  0.9764957265  0.9940119760  0.9850299401  0.9882315522  0.9592356688  57.485029940  0.9571083540  2.2566514015  2400          0.1729472136 
0.9895209576  0.9727901036  0.9987797437  0.9682151589  0.9984008529  0.9743589744  0.9940119760  0.9850299401  0.9850508906  0.9757961783  64.670658682  0.8902132603  2.2566514015  2700          0.1726002645 
0.9891467061  0.9711258507  0.9975594875  0.9657701711  0.9978678038  0.9743589744  0.9932634731  0.9850299401  0.9882315522  0.9732484076  71.856287425  0.8710161904  2.2566514015  3000          0.1723129535 
0.9887724546  0.9678179585  0.9993898719  0.9682151589  0.9984008529  0.9658119658  0.9925149701  0.9850299401  0.9898218830  0.9694267516  79.041916167  0.8650715522  2.2566514015  3300          0.1734622804 
0.9891467061  0.9658112467  0.9975594875  0.9511002445  0.9994669510  0.9743589744  0.9932634731  0.9850299401  0.9904580153  0.9719745223  86.227544910  0.6321024716  5.3973727226  3600          0.2109719348 
0.9910179636  0.9680849673  0.9993898719  0.9608801956  0.9984008529  0.9764957265  0.9940119760  0.9880239521  0.9904580153  0.9668789809  93.413173652  0.5288467063  5.3973727226  3900          0.2106472381 
0.9898952091  0.9738241998  0.9993898719  0.9755501222  0.9989339019  0.9764957265  0.9917664671  0.9880239521  0.9898218830  0.9694267516  100.59880239  0.4922853063  5.3973727226  4200          0.2086342160 
0.9898952091  0.9748447239  0.9993898719  0.9731051345  0.9984008529  0.9743589744  0.9917664671  0.9880239521  0.9910941476  0.9770700637  107.78443113  0.4683436635  5.3973727226  4500          0.2079752501 
0.9898952091  0.9698862264  1.0000000000  0.9633251834  0.9994669510  0.9743589744  0.9917664671  0.9880239521  0.9901399491  0.9719745223  114.97005988  0.4566504087  5.3973727226  4800          0.2092624029 
0.9895209576  0.9739748159  0.9987797437  0.9755501222  0.9989339019  0.9807692308  0.9910179641  0.9880239521  0.9923664122  0.9656050955  119.76047904  0.4421515764  5.3973727226  5000          0.2114854741 
