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/1a71b9c1f88ac6231b15bbbba5b9e01f
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 120418156
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	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 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    
0.1130239520  0.1638623889  0.1732763880  0.1662591687  0.1545842217  0.1431623932  0.1332335329  0.0928143713  0.1711195929  0.1821656051  0.0000000000  9.9556674957  2.0074062347  0             1.4710354805 
0.9880239516  0.9425050254  0.9786455156  0.9437652812  0.9770788913  0.9487179487  0.9910179641  0.9850299401  0.9545165394  0.9350318471  7.1856287425  3.1098899138  2.2544541359  300           0.1494296543 
0.9880239516  0.9571201908  0.9902379500  0.9535452323  0.9909381663  0.9636752137  0.9910179641  0.9850299401  0.9685114504  0.9541401274  14.371257485  1.3513227409  2.2544541359  600           0.1702043382 
0.9910179636  0.9572365459  0.9969493594  0.9559902200  0.9962686567  0.9679487179  0.9940119760  0.9880239521  0.9681933842  0.9477707006  21.556886227  1.1748770934  2.2544541359  900           0.1684887608 
0.9876497001  0.9519561652  0.9969493594  0.9486552567  0.9952025586  0.9658119658  0.9902694611  0.9850299401  0.9748727735  0.9414012739  28.742514970  1.0931498007  2.2544541359  1200          0.1693497841 
0.9880239516  0.9608526738  0.9981696156  0.9608801956  0.9973347548  0.9700854701  0.9910179641  0.9850299401  0.9783715013  0.9515923567  35.928143712  1.0384223594  2.2544541359  1500          0.1687207230 
0.9872754486  0.9636880291  0.9963392312  0.9706601467  0.9952025586  0.9700854701  0.9895209581  0.9850299401  0.9818702290  0.9503184713  43.113772455  0.9920191755  2.2544541359  1800          0.1696187274 
0.9902694606  0.9608733249  0.9993898719  0.9584352078  0.9968017058  0.9636752137  0.9895209581  0.9910179641  0.9802798982  0.9605095541  50.299401197  0.9688083603  2.2544541359  2100          0.1707473540 
0.9910179636  0.9597157946  0.9981696156  0.9608801956  0.9973347548  0.9679487179  0.9910179641  0.9910179641  0.9793256997  0.9503184713  57.485029940  0.9586404552  2.2544541359  2400          0.1757763457 
0.9906437121  0.9624142191  0.9981696156  0.9511002445  0.9968017058  0.9743589744  0.9902694611  0.9910179641  0.9869592875  0.9617834395  64.670658682  0.9104422275  2.2544541359  2700          0.1745011719 
0.9906437121  0.9588323145  0.9969493594  0.9535452323  0.9989339019  0.9700854701  0.9902694611  0.9910179641  0.9863231552  0.9528662420  71.856287425  0.8921007254  2.2544541359  3000          0.1734415714 
0.9891467061  0.9600583290  0.9993898719  0.9559902200  0.9994669510  0.9636752137  0.9902694611  0.9880239521  0.9837786260  0.9605095541  79.041916167  0.8929673787  2.2544541359  3300          0.1716478229 
0.9891467061  0.9605993125  0.9987797437  0.9584352078  0.9984008529  0.9679487179  0.9902694611  0.9880239521  0.9866412214  0.9554140127  86.227544910  0.8797761351  2.2544541359  3600          0.1681959907 
0.9887724546  0.9657220737  1.0000000000  0.9584352078  0.9994669510  0.9807692308  0.9895209581  0.9880239521  0.9891857506  0.9579617834  93.413173652  0.7004630729  5.3972430229  3900          0.1911383168 
0.9891467061  0.9603595611  0.9987797437  0.9559902200  0.9989339019  0.9722222222  0.9902694611  0.9880239521  0.9866412214  0.9528662420  100.59880239  0.5083118390  5.3972430229  4200          0.2081788143 
0.9895209576  0.9604965673  0.9993898719  0.9559902200  0.9994669510  0.9700854701  0.9910179641  0.9880239521  0.9863231552  0.9554140127  107.78443113  0.4746136772  5.3972430229  4500          0.2069791500 
0.9898952091  0.9622771752  0.9993898719  0.9608801956  0.9994669510  0.9743589744  0.9917664671  0.9880239521  0.9891857506  0.9515923567  114.97005988  0.4564729680  5.3972430229  4800          0.2106049935 
0.9895209576  0.9630100393  0.9993898719  0.9682151589  0.9989339019  0.9679487179  0.9910179641  0.9880239521  0.9863231552  0.9528662420  119.76047904  0.4345259507  5.3972430229  5000          0.2144151711 
