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: VLCS
	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/18c8cc1a3fc909c8bdf9ba28a821e46a
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 227287722
	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    
0.2531468847  0.1251484372  0.0768551237  0.0883392226  0.1364705882  0.1374764595  0.2425742574  0.2637195122  0.1710477601  0.1496296296  0.0000000000  6.4103975296  2.0073552132  0             1.6994345188 
0.7807571560  0.8574643331  1.0000000000  0.9929328622  0.7618823529  0.7231638418  0.7932216299  0.7682926829  0.9007774898  0.8562962963  8.4805653710  1.9766150570  2.2565736771  300           0.6088487339 
0.7868547170  0.8858840759  1.0000000000  1.0000000000  0.8023529412  0.7702448211  0.7932216299  0.7804878049  0.9485375787  0.8874074074  16.961130742  1.3617874126  2.2565736771  600           0.6164279517 
0.7881881231  0.8813559319  1.0000000000  1.0000000000  0.8310588235  0.7551789077  0.7943640518  0.7820121951  0.9659385413  0.8888888889  25.441696113  1.2030535054  2.2565736771  900           0.6217817187 
0.7811391243  0.8828374134  1.0000000000  1.0000000000  0.8583529412  0.7551789077  0.7909367860  0.7713414634  0.9689004073  0.8933333333  33.922261484  1.0979820246  2.2565736771  1200          0.6398873361 
0.7792339268  0.8853902487  1.0000000000  1.0000000000  0.8771764706  0.7702448211  0.7901751714  0.7682926829  0.9788967049  0.8859259259  42.402826855  1.0057966989  2.2565736771  1500          0.6331557139 
0.7735200756  0.8866457415  1.0000000000  1.0000000000  0.8997647059  0.7740112994  0.7833206398  0.7637195122  0.9866716031  0.8859259259  50.883392226  0.9634986377  2.2565736771  1800          0.6345185288 
0.7700904878  0.8861100646  1.0000000000  1.0000000000  0.9209411765  0.7664783427  0.7825590251  0.7576219512  0.9896334691  0.8918518519  59.363957597  0.9354014232  2.2565736771  2100          0.6260081212 
0.7721866695  0.8881272230  1.0000000000  1.0000000000  0.9331764706  0.7740112994  0.7821782178  0.7621951220  0.9922251018  0.8903703704  67.844522968  0.9264647951  2.2565736771  2400          0.6253091025 
0.7714256354  0.8899686124  1.0000000000  1.0000000000  0.9369411765  0.7721280603  0.7791317593  0.7637195122  0.9933358016  0.8977777778  76.325088339  0.9053154383  2.2565736771  2700          0.6254944237 
0.7721872500  0.8888888886  1.0000000000  1.0000000000  0.9472941176  0.7777777778  0.7806549886  0.7637195122  0.9940762680  0.8888888889  84.805653710  0.8921155473  2.2565736771  3000          0.6218754586 
0.7710442476  0.8854823182  1.0000000000  1.0000000000  0.9623529412  0.7645951036  0.7798933740  0.7621951220  0.9937060348  0.8918518519  93.286219081  0.9593484308  2.2565736771  3300          0.6203070203 
0.7721878305  0.8902783006  1.0000000000  1.0000000000  0.9614117647  0.7834274953  0.7791317593  0.7652439024  0.9951869678  0.8874074074  101.76678445  0.5187553979  5.3972864151  3600          0.6381814830 
0.7708538439  0.8870056494  1.0000000000  1.0000000000  0.9661176471  0.7721280603  0.7795125666  0.7621951220  0.9951869678  0.8888888889  110.24734982  0.4436527228  5.3972864151  3900          0.6114315271 
0.7702826329  0.8860179951  1.0000000000  1.0000000000  0.9684705882  0.7721280603  0.7783701447  0.7621951220  0.9959274343  0.8859259259  118.72791519  0.4221327283  5.3972864151  4200          0.6524481376 
0.7681870317  0.8866457415  1.0000000000  1.0000000000  0.9712941176  0.7740112994  0.7772277228  0.7591463415  0.9944465013  0.8859259259  127.20848056  0.4039267716  5.3972864151  4500          0.6265847341 
0.7678068049  0.8866038917  1.0000000000  1.0000000000  0.9712941176  0.7664783427  0.7749428789  0.7606707317  0.9966679008  0.8933333333  135.68904593  0.3955788910  5.3972864151  4800          0.6269856819 
0.7672355940  0.8919857708  1.0000000000  1.0000000000  0.9698823529  0.7796610169  0.7738004570  0.7606707317  0.9955572010  0.8962962963  141.34275618  0.3920937628  5.3972864151  5000          0.6317354345 
