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: TerraIncognita
	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/7ad891da63d5e55d0ea3ec5ac7cda7ce
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1148249373
	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    
0.0308564232  0.0673172756  0.0224097021  0.0295358650  0.1160611118  0.0975860298  0.0302267003  0.0314861461  0.0713830465  0.0748299320  0.0000000000  6.3735694885  2.0074815750  0             1.4535391331 
0.3154911837  0.6122147293  0.5304508305  0.5348101266  0.7319296444  0.7380585516  0.3400503778  0.2909319899  0.5659655832  0.5637755102  3.0226700252  2.9587658000  2.2580189705  300           0.1561009908 
0.4617443323  0.7831382711  0.8660690746  0.8544303797  0.8129413275  0.8079096045  0.4801637280  0.4433249370  0.7127682175  0.6870748299  6.0453400504  2.5661182356  2.2580189705  600           0.1783310715 
0.4927581862  0.8102526130  0.8890060638  0.8776371308  0.8372063166  0.8294812532  0.5119647355  0.4735516373  0.7493095390  0.7236394558  9.0680100756  2.4160889602  2.2580189705  900           0.1807724261 
0.5248740552  0.8338882133  0.9132612708  0.8987341772  0.8485043009  0.8520801233  0.5421914358  0.5075566751  0.7779902273  0.7508503401  12.090680100  2.2954505404  2.2580189705  1200          0.1773097658 
0.5338476068  0.8426449150  0.9277616662  0.9103375527  0.8617280781  0.8582434515  0.5488035264  0.5188916877  0.7907371999  0.7593537415  15.113350125  2.2156249440  2.2580189705  1500          0.1809260257 
0.5483312340  0.8610799362  0.9433166359  0.9240506329  0.8719989729  0.8726245506  0.5563602015  0.5403022670  0.8147439983  0.7865646259  18.136020151  2.1341919533  2.2580189705  1800          0.1807853357 
0.5678526446  0.8679288747  0.9464803586  0.9219409283  0.8811143921  0.8782742681  0.5676952141  0.5680100756  0.8300403654  0.8035714286  21.158690176  2.0539259382  2.2580189705  2100          0.1814777978 
0.5850125942  0.8744769631  0.9551805958  0.9335443038  0.8880472461  0.8854648177  0.5793450882  0.5906801008  0.8410877417  0.8044217687  24.181360201  1.9663081177  2.2580189705  2400          0.1797052256 
0.5927267000  0.8778265944  0.9591352491  0.9282700422  0.8951084863  0.8880328711  0.5897355164  0.5957178841  0.8502230720  0.8171768707  27.204030226  1.8911759722  2.2580189705  2700          0.1770286218 
0.5961901760  0.8853921023  0.9601898234  0.9345991561  0.8961355758  0.8941961993  0.5941435768  0.5982367758  0.8572339069  0.8273809524  30.226700251  1.8524977974  2.2580189705  3000          0.1767054526 
0.6009130979  0.8904158001  0.9644081202  0.9419831224  0.9066632430  0.8993323061  0.5972921914  0.6045340050  0.8667941364  0.8299319728  33.249370277  1.7773209508  2.2580189705  3300          0.1788756744 
0.6031171282  0.8887186525  0.9704719220  0.9430379747  0.9097445115  0.8957370313  0.5991813602  0.6070528967  0.8750796686  0.8273809524  36.272040302  1.3214273564  5.3968758583  3600          0.2144026017 
0.5996536521  0.8891969754  0.9707355655  0.9335443038  0.9170625241  0.9024139702  0.5960327456  0.6032745592  0.8818780540  0.8316326531  39.294710327  1.2334176572  5.3968758583  3900          0.2160098052 
0.5993387906  0.8997374161  0.9720537833  0.9472573840  0.9170625241  0.9101181305  0.5966624685  0.6020151134  0.8850647971  0.8418367347  42.317380352  1.2085868537  5.3968758583  4200          0.2177396003 
0.6005982365  0.9000520264  0.9723174268  0.9514767932  0.9196302478  0.9034411916  0.5954030227  0.6057934509  0.8908009348  0.8452380952  45.340050377  1.1946645367  5.3968758583  4500          0.2167380953 
0.5994962214  0.8994390814  0.9749538624  0.9462025316  0.9221979715  0.9085772984  0.5957178841  0.6032745592  0.8944125770  0.8435374150  48.362720403  1.1807531599  5.3968758583  4800          0.2160905568 
0.6012279594  0.9038768736  0.9778539415  0.9472573840  0.9241237643  0.9106317411  0.5954030227  0.6070528967  0.9026981092  0.8537414966  50.377833753  1.1752115357  5.3968758583  5000          0.2186953318 
