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: 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/0840cfb66c9c3cf1138e328a5f2a97a3
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1527481883
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	trial_seed: 2
	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: 0.6109302038716249
	lambda2: 0.5117744391412766
	last_k_epoch: 0.31317984427858747
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.002688876693512
	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    
0.1368797040  0.2143545745  0.2019524100  0.2322738386  0.1305970149  0.1431623932  0.1863772455  0.2005988024  0.2216921120  0.2101910828  0.0000000000  7.9841814041  2.0074062347  0             1.4438796043 
0.8204535924  0.9585911288  0.9749847468  0.9535452323  0.8054371002  0.8354700855  0.9970059880  0.9910179641  0.9564249364  0.9312101911  7.1856287425  2.1257478734  2.2566514015  300           0.1509109775 
0.8436617276  0.9655113733  0.9938987187  0.9657701711  0.8326226013  0.8547008547  0.9992514970  0.9970059880  0.9774173028  0.9337579618  14.371257485  0.9423903028  2.2566514015  600           0.1711918028 
0.8543363763  0.9692987684  0.9975594875  0.9682151589  0.8411513859  0.8675213675  1.0000000000  0.9970059880  0.9825063613  0.9426751592  21.556886227  0.8132563462  2.2566514015  900           0.1716028134 
0.8556689989  0.9689426619  0.9987797437  0.9633251834  0.8438166311  0.8675213675  1.0000000000  0.9970059880  0.9866412214  0.9464968153  28.742514970  0.7706967843  2.2566514015  1200          0.1722210018 
0.8551359499  0.9674857685  0.9993898719  0.9657701711  0.8427505330  0.8675213675  1.0000000000  0.9940119760  0.9872773537  0.9426751592  35.928143712  0.7515438407  2.2566514015  1500          0.1700381303 
0.8532680002  0.9691842823  1.0000000000  0.9657701711  0.8411513859  0.8653846154  0.9992514970  0.9940119760  0.9901399491  0.9477707006  43.113772455  0.7169131677  2.2566514015  1800          0.1702280998 
0.8551336719  0.9726272741  1.0000000000  0.9731051345  0.8448827292  0.8653846154  1.0000000000  0.9970059880  0.9904580153  0.9477707006  50.299401197  0.6737046880  2.2566514015  2100          0.1711440309 
0.8567328190  0.9692645074  0.9981696156  0.9706601467  0.8480810235  0.8653846154  1.0000000000  0.9970059880  0.9917302799  0.9401273885  57.485029940  0.6758598002  2.2566514015  2400          0.1713869977 
0.8554001964  0.9621026425  1.0000000000  0.9559902200  0.8454157783  0.8653846154  1.0000000000  0.9940119760  0.9930025445  0.9363057325  64.670658682  0.6476881408  2.2566514015  2700          0.1702986105 
0.8580722756  0.9720196375  0.9987797437  0.9755501222  0.8443496802  0.8717948718  1.0000000000  0.9940119760  0.9933206107  0.9464968153  71.856287425  0.6452976405  2.2566514015  3000          0.1711400096 
0.8580699976  0.9649379978  1.0000000000  0.9657701711  0.8464818763  0.8696581197  1.0000000000  0.9940119760  0.9955470738  0.9350318471  79.041916167  0.6362545755  2.2566514015  3300          0.1690801167 
0.8607397987  0.9712046416  0.9993898719  0.9731051345  0.8475479744  0.8739316239  0.9992514970  0.9940119760  0.9961832061  0.9464968153  86.227544910  0.5007376409  5.3973727226  3600          0.1894839756 
0.8628742729  0.9743943098  1.0000000000  0.9682151589  0.8496801706  0.8760683761  1.0000000000  0.9970059880  0.9942748092  0.9579617834  93.413173652  0.3525913780  5.3973727226  3900          0.2051308076 
0.8676808262  0.9737181513  1.0000000000  0.9755501222  0.8507462687  0.8846153846  1.0000000000  0.9940119760  0.9977735369  0.9515923567  100.59880239  0.3273624021  5.3973727226  4200          0.2069633603 
0.8676808262  0.9713876497  1.0000000000  0.9706601467  0.8507462687  0.8846153846  1.0000000000  0.9970059880  0.9958651399  0.9464968153  107.78443113  0.3063679378  5.3973727226  4500          0.2069178128 
0.8682138752  0.9745331473  1.0000000000  0.9779951100  0.8518123667  0.8846153846  1.0000000000  0.9940119760  0.9965012723  0.9515923567  114.97005988  0.2972276095  5.3973727226  4800          0.2126119192 
0.8682138752  0.9696332621  1.0000000000  0.9731051345  0.8518123667  0.8846153846  1.0000000000  0.9880239521  0.9945928753  0.9477707006  119.76047904  0.2917628384  5.3973727226  5000          0.2127524829 
