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: 2
	output_dir: sweep/ablation3/outputs/ddac35fe96d69de22ede133af42addcf
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 535506236
	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: 0.5439617198173775
	lambda2: 0.5509403872292429
	last_k_epoch: 0.38252238504986713
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.920147743151585
	weight_decay: 1e-06
	worst_case_p: 0.3
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    
0.0911826793  0.1144726199  0.1086028066  0.0855745721  0.0794243070  0.0811965812  0.1669161677  0.1766467066  0.0931933842  0.0891719745  0.0000000000  7.4674644470  2.1691875458  0             1.4921722412 
0.8232040400  0.9664610550  0.9871873093  0.9511002445  0.9829424307  0.9572649573  0.9992514970  0.9910179641  0.8196564885  0.8267515924  7.1856287425  1.9898717322  2.4361939430  300           0.1519474173 
0.8150868701  0.9741775510  0.9957291031  0.9584352078  0.9952025586  0.9700854701  0.9985029940  0.9940119760  0.8136132316  0.8165605096  14.371257485  0.7170461359  2.4361939430  600           0.1730886825 
0.8091994048  0.9744857866  0.9951189750  0.9657701711  0.9952025586  0.9636752137  0.9992514970  0.9940119760  0.8069338422  0.8114649682  21.556886227  0.6150765816  2.4361939430  900           0.1749614779 
0.8106315129  0.9751980373  0.9975594875  0.9657701711  0.9978678038  0.9658119658  0.9992514970  0.9940119760  0.8085241730  0.8127388535  28.742514970  0.5621805596  2.4361939430  1200          0.1757616051 
0.8177936739  0.9787592909  0.9975594875  0.9657701711  0.9994669510  0.9764957265  1.0000000000  0.9940119760  0.8139312977  0.8216560510  35.928143712  0.5474189858  2.4361939430  1500          0.1743855516 
0.8235212958  0.9769687733  0.9987797437  0.9706601467  1.0000000000  0.9722222222  1.0000000000  0.9880239521  0.8215648855  0.8254777070  43.113772455  0.5087522943  2.4361939430  1800          0.1740086850 
0.8252730908  0.9776585417  0.9993898719  0.9633251834  0.9994669510  0.9786324786  1.0000000000  0.9910179641  0.8212468193  0.8292993631  50.299401197  0.5012370036  2.4361939430  2100          0.1739453991 
0.8227261304  0.9763143031  1.0000000000  0.9584352078  1.0000000000  0.9764957265  1.0000000000  0.9940119760  0.8199745547  0.8254777070  57.485029940  0.4824032647  2.4361939430  2400          0.1740659968 
0.8276610180  0.9778640321  0.9993898719  0.9682151589  0.9994669510  0.9743589744  1.0000000000  0.9910179641  0.8222010178  0.8331210191  64.670658682  0.4697920298  2.4361939430  2700          0.1733980759 
0.8271822981  0.9859690267  1.0000000000  0.9779951100  0.9994669510  0.9829059829  1.0000000000  0.9970059880  0.8237913486  0.8305732484  71.856287425  0.4661454728  2.4361939430  3000          0.1736013683 
0.8271806774  0.9784510553  0.9993898719  0.9584352078  1.0000000000  0.9829059829  1.0000000000  0.9940119760  0.8263358779  0.8280254777  79.041916167  0.4183369564  5.3991427422  3300          0.1961844881 
0.8281373069  0.9817913018  0.9993898719  0.9633251834  0.9989339019  0.9850427350  1.0000000000  0.9970059880  0.8244274809  0.8318471338  86.227544910  0.3376172744  5.3991427422  3600          0.2065683158 
0.8281373069  0.9768435458  0.9993898719  0.9608801956  0.9989339019  0.9786324786  1.0000000000  0.9910179641  0.8244274809  0.8318471338  93.413173652  0.3090471417  5.3991427422  3900          0.2056972750 
0.8292505385  0.9822402816  0.9993898719  0.9706601467  1.0000000000  0.9850427350  1.0000000000  0.9910179641  0.8266539440  0.8318471338  100.59880239  0.2917501462  5.3991427422  4200          0.2067429145 
0.8298874811  0.9797150310  0.9993898719  0.9682151589  1.0000000000  0.9829059829  1.0000000000  0.9880239521  0.8266539440  0.8331210191  107.78443113  0.2755714957  5.3991427422  4500          0.2088622840 
0.8290923158  0.9746040484  1.0000000000  0.9584352078  0.9994669510  0.9743589744  1.0000000000  0.9910179641  0.8250636132  0.8331210191  114.97005988  0.2669844417  5.3991427422  4800          0.2106324871 
0.8292513488  0.9776585417  1.0000000000  0.9633251834  0.9994669510  0.9786324786  1.0000000000  0.9910179641  0.8253816794  0.8331210191  119.76047904  0.2571268317  5.3991427422  5000          0.2142299616 
