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: 4
	output_dir: sweep/ablation3/outputs/9d87ee48560f9f3c4429273a244d4cfa
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1531745150
	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: 0.8001163740830898
	lambda2: 0.7340462818445315
	last_k_epoch: 0.3149495809125332
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.8284464949429635
	weight_decay: 1e-06
	worst_case_p: 0.2
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    
0.0108199645  0.0140941112  0.0092687951  0.0123711340  0.0140320733  0.0229095074  0.0090090090  0.0078917700  0.0083189902  0.0114810563  0.0000000000  9.9865512848  1.7954735756  0             1.5806543827 
0.5834706485  0.6963796377  0.5669412976  0.6000000000  0.6847079038  0.5830469645  0.7942004505  0.7621195039  0.7897303500  0.7439724455  4.9433573635  6.5992130367  2.0943040848  300           0.3000016618 
0.6504459211  0.8013660712  0.6349124614  0.6659793814  0.8582474227  0.7147766323  0.9104729730  0.8500563698  0.9061962134  0.8392652124  9.8867147271  3.7603827651  2.0943040848  600           0.3065497160 
0.6658939128  0.8168996042  0.6658084449  0.6659793814  0.9034936999  0.7308132875  0.9473536036  0.8737316798  0.9411933448  0.8461538462  14.830072090  2.8978910955  2.0943040848  900           0.3009998417 
0.6834111923  0.8374873728  0.6822863028  0.6845360825  0.9332760596  0.7697594502  0.9687500000  0.8816234498  0.9595524957  0.8610792193  19.773429454  2.4063974726  2.0943040848  1200          0.2999629879 
0.6955184895  0.8382174940  0.6941297631  0.6969072165  0.9493127148  0.7617411226  0.9774774775  0.8883878241  0.9730349971  0.8645235362  24.716786817  2.1254083327  2.0943040848  1500          0.3058430155 
0.7004146004  0.8488173224  0.6956745623  0.7051546392  0.9610538373  0.7777777778  0.9842342342  0.9052987599  0.9816408491  0.8633754305  29.660144181  1.9244212580  2.0943040848  1800          0.2950209300 
0.7071151005  0.8534467810  0.6967044284  0.7175257732  0.9659221077  0.7835051546  0.9853603604  0.8985343856  0.9833620195  0.8783008037  34.603501544  1.7836411023  2.0943040848  2100          0.2962009231 
0.7112366884  0.8553369502  0.7008238929  0.7216494845  0.9670675830  0.7869415808  0.9893018018  0.9019165727  0.9856569134  0.8771526980  39.546858908  1.6867762677  2.0943040848  2400          0.2975226307 
0.7127814875  0.8507737837  0.7039134912  0.7216494845  0.9733676976  0.7938144330  0.9909909910  0.8962795941  0.9905335628  0.8622273249  44.490216271  1.6376915157  2.0943040848  2700          0.2957640266 
0.7153561528  0.8663255071  0.7090628218  0.7216494845  0.9733676976  0.8041237113  0.9915540541  0.9177001127  0.9890992542  0.8771526980  49.433573635  1.5649596481  2.0943040848  3000          0.3082859619 
0.7158710859  0.8610349604  0.7100926880  0.7216494845  0.9768041237  0.8064146621  0.9912725225  0.9064261556  0.9893861159  0.8702640643  54.376930999  1.5074371354  2.0943040848  3300          0.2864597972 
0.7166424238  0.8659445587  0.7136972194  0.7195876289  0.9808132875  0.8018327606  0.9940878378  0.9177001127  0.9931153184  0.8783008037  59.320288362  1.4144697555  5.4026646614  3600          0.2839140193 
0.7189606842  0.8651730177  0.7162718847  0.7216494845  0.9773768614  0.8098510882  0.9923986486  0.9177001127  0.9931153184  0.8679678530  64.263645726  1.2044555271  5.4026646614  3900          0.2965361762 
0.7189606842  0.8644076140  0.7162718847  0.7216494845  0.9825315006  0.8098510882  0.9940878378  0.9177001127  0.9942627653  0.8656716418  69.207003089  1.1253918715  5.4026646614  4200          0.2994772887 
0.7207640117  0.8591102746  0.7178166838  0.7237113402  0.9831042383  0.8029782360  0.9935247748  0.9086809470  0.9931153184  0.8656716418  74.150360453  1.0684822005  5.4026646614  4500          0.2914460953 
0.7225673391  0.8648224235  0.7193614830  0.7257731959  0.9790950745  0.7949599084  0.9926801802  0.9143179256  0.9942627653  0.8851894374  79.093717816  1.0213649480  5.4026646614  4800          0.2963564070 
0.7235982669  0.8629132979  0.7193614830  0.7278350515  0.9819587629  0.7892325315  0.9952139640  0.9143179256  0.9939759036  0.8851894374  82.389289392  0.9942851448  5.4026646614  5000          0.2820615995 
