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: [0]
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/7e7e9d9a96a60a73d05e4fd638102294
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 881650978
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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 normal transform
using augment 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    
0.1450486386  0.1070409782  0.1336180598  0.1564792176  0.1231343284  0.1111111111  0.1279940120  0.0928143713  0.1211832061  0.1171974522  0.0000000000  7.4371275902  2.0074062347  0             1.4214603901 
0.9203066747  0.9646624381  0.9188529591  0.9217603912  0.9840085288  0.9594017094  0.9977544910  0.9970059880  0.9653307888  0.9375796178  7.1856287425  2.2971944302  2.2566514015  300           0.1501790841 
0.9407705809  0.9696463241  0.9328859060  0.9486552567  0.9920042644  0.9700854701  0.9992514970  1.0000000000  0.9758269720  0.9388535032  14.371257485  0.9358120735  2.2566514015  600           0.1681601469 
0.9386306572  0.9699222055  0.9334960342  0.9437652812  0.9973347548  0.9700854701  1.0000000000  0.9970059880  0.9802798982  0.9426751592  21.556886227  0.7958752512  2.2566514015  900           0.1648488990 
0.9371030993  0.9712097007  0.9328859060  0.9413202934  0.9941364606  0.9764957265  1.0000000000  0.9970059880  0.9837786260  0.9401273885  28.742514970  0.7382920140  2.2566514015  1200          0.1641581551 
0.9407683433  0.9748924816  0.9353264185  0.9462102689  0.9962686567  0.9743589744  1.0000000000  1.0000000000  0.9901399491  0.9503184713  35.928143712  0.6986268496  2.2566514015  1500          0.1645281021 
0.9374059257  0.9748943506  0.9359365467  0.9388753056  0.9994669510  0.9786324786  1.0000000000  0.9970059880  0.9891857506  0.9490445860  43.113772455  0.7220052152  2.2566514015  1800          0.1630983671 
0.9319102973  0.9767416114  0.9298352654  0.9339853301  0.9994669510  0.9786324786  1.0000000000  1.0000000000  0.9923664122  0.9515923567  50.299401197  0.6279255249  2.2566514015  2100          0.1643898455 
0.9334378552  0.9763188520  0.9304453935  0.9364303178  0.9994669510  0.9829059829  0.9992514970  0.9970059880  0.9936386768  0.9490445860  57.485029940  0.6135608706  2.2566514015  2400          0.1641068427 
0.9340502210  0.9754541162  0.9292251373  0.9388753056  0.9984008529  0.9722222222  1.0000000000  1.0000000000  0.9930025445  0.9541401274  64.670658682  0.5968855212  2.2566514015  2700          0.1628670049 
0.9343552850  0.9768804866  0.9298352654  0.9388753056  0.9989339019  0.9807692308  1.0000000000  0.9970059880  0.9923664122  0.9528662420  71.856287425  0.6318447761  2.2566514015  3000          0.1633164064 
0.9337451569  0.9753189790  0.9286150092  0.9388753056  0.9989339019  0.9786324786  1.0000000000  0.9970059880  0.9939567430  0.9503184713  79.041916167  0.6184249085  2.2566514015  3300          0.1632559903 
0.9325249007  0.9777414844  0.9261744966  0.9388753056  0.9978678038  0.9829059829  1.0000000000  1.0000000000  0.9958651399  0.9503184713  86.227544910  0.4746782583  5.3973727226  3600          0.1862445323 
0.9340524586  0.9802911241  0.9267846248  0.9413202934  0.9994669510  0.9871794872  1.0000000000  0.9970059880  0.9945928753  0.9566878981  93.413173652  0.3312953252  5.3973727226  3900          0.2022736287 
0.9322198366  0.9761818458  0.9255643685  0.9388753056  0.9994669510  0.9850427350  1.0000000000  0.9970059880  0.9933206107  0.9464968153  100.59880239  0.3032931529  5.3973727226  4200          0.2041913040 
0.9300799129  0.9754578542  0.9261744966  0.9339853301  0.9989339019  0.9807692308  1.0000000000  0.9940119760  0.9955470738  0.9515923567  107.78443113  0.2868876407  5.3973727226  4500          0.2029229283 
0.9282472909  0.9771662399  0.9249542404  0.9315403423  0.9984008529  0.9786324786  1.0000000000  1.0000000000  0.9936386768  0.9528662420  114.97005988  0.2757541095  5.3973727226  4800          0.2033176176 
0.9288574190  0.9787413574  0.9261744966  0.9315403423  0.9989339019  0.9871794872  1.0000000000  1.0000000000  0.9958651399  0.9490445860  119.76047904  0.2668476821  5.3973727226  5000          0.2027179480 
