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: OfficeHome
	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/2a4214f0e9e824e334c14a60845c2c5f
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1529454978
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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: 0.7419102898692578
	lambda2: 0.5215383105176172
	last_k_epoch: 0.23762453204831346
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.9748462276330736
	weight_decay: 1e-06
	worst_case_p: 0.3
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    
0.0154564855  0.0182047768  0.0144181256  0.0164948454  0.0105956472  0.0080183276  0.0267454955  0.0259301015  0.0129087780  0.0206659013  0.0000000000  9.6051654816  2.1706647873  0             1.4191663265 
0.6027891320  0.7652392877  0.5890834192  0.6164948454  0.7817869416  0.6849942726  0.8814752252  0.8162344983  0.8511187608  0.7944890930  4.9433573635  5.5246874722  2.4384436607  300           0.3048024853 
0.6857347614  0.8225512662  0.6745623069  0.6969072165  0.8774341352  0.7296678121  0.9451013514  0.8883878241  0.9371772806  0.8495981630  9.8867147271  2.8163484144  2.4384436607  600           0.3125637023 
0.7063416392  0.8423573048  0.6972193615  0.7154639175  0.9115120275  0.7628865979  0.9687500000  0.8996617813  0.9581181870  0.8645235362  14.830072090  2.1321444515  2.4384436607  900           0.3001081761 
0.7109802835  0.8408437003  0.6982492276  0.7237113402  0.9407216495  0.7674684994  0.9760698198  0.8962795941  0.9672977625  0.8587830080  19.773429454  1.8008988750  2.4384436607  1200          0.2989237165 
0.7169041372  0.8556609187  0.7059732235  0.7278350515  0.9501718213  0.7915234822  0.9817004505  0.9109357384  0.9770510614  0.8645235362  24.716786817  1.6119082006  2.4384436607  1500          0.2890739266 
0.7199969207  0.8534208106  0.7059732235  0.7340206186  0.9593356243  0.7903780069  0.9873310811  0.9019165727  0.9833620195  0.8679678530  29.660144181  1.5106821581  2.4384436607  1800          0.2923592122 
0.7243770368  0.8564264331  0.7085478888  0.7402061856  0.9667812142  0.7823596793  0.9881756757  0.9120631342  0.9859437751  0.8748564868  34.603501544  1.4118799325  2.4384436607  2100          0.2971847757 
0.7274676969  0.8567693580  0.7126673532  0.7422680412  0.9684994273  0.7892325315  0.9895833333  0.9177001127  0.9888123924  0.8633754305  39.546858908  1.3704218582  2.4384436607  2400          0.2956024488 
0.7284975630  0.8567806450  0.7147270855  0.7422680412  0.9713631157  0.7835051546  0.9904279279  0.9165727170  0.9908204246  0.8702640643  44.490216271  1.3074366458  2.4384436607  2700          0.2902728446 
0.7303008904  0.8643775919  0.7162718847  0.7443298969  0.9753722795  0.7949599084  0.9918355856  0.9244644870  0.9899598394  0.8737083812  49.433573635  1.2663538114  2.4384436607  3000          0.3059918475 
0.7297859574  0.8583027957  0.7152420185  0.7443298969  0.9802405498  0.7857961054  0.9935247748  0.9177001127  0.9934021801  0.8714121699  54.376930999  1.2460268005  2.4384436607  3300          0.3064459697 
0.7326202126  0.8663109344  0.7167868177  0.7484536082  0.9782359679  0.7961053837  0.9943693694  0.9210822999  0.9936890419  0.8817451206  59.320288362  1.2015164681  2.4384436607  3600          0.2949263446 
0.7313318183  0.8602092911  0.7162718847  0.7463917526  0.9782359679  0.7949599084  0.9929617117  0.9177001127  0.9948364888  0.8679678530  64.263645726  1.1480952561  5.4016346931  3900          0.3155140146 
0.7336511404  0.8666538593  0.7167868177  0.7505154639  0.9808132875  0.8029782360  0.9952139640  0.9267192785  0.9948364888  0.8702640643  69.207003089  0.9733719852  5.4016346931  4200          0.3104914649 
0.7349395348  0.8663047972  0.7173017508  0.7525773196  0.9813860252  0.8041237113  0.9952139640  0.9210822999  0.9945496271  0.8737083812  74.150360453  0.9054548796  5.4016346931  4500          0.3075884136 
0.7341650118  0.8590526394  0.7198764161  0.7484536082  0.9831042383  0.7880870561  0.9940878378  0.9199549042  0.9945496271  0.8691159587  79.093717816  0.8589602174  5.4016346931  4800          0.3055888812 
0.7346799448  0.8605711724  0.7209062822  0.7484536082  0.9828178694  0.8041237113  0.9957770270  0.9199549042  0.9945496271  0.8576349024  82.389289392  0.8349730891  5.4016346931  5000          0.2953533018 
