SoftTeacher Custom object-detection dataset support

Hello, has anyone successfully trained a custom dataset for object detection? I've tried a number of things that I've found in the Issues for this repo and the instructions in the MMDetection custom dataset instructions, but am still seeing strange results in the model training/evaluation, such as:

mmdet.ssod - ERROR - The testing results of the whole dataset is empty

and

2022-04-05 20:01:28,871 - mmdet.ssod - INFO - Iter [1200/7200] lr: 1.000e-04, eta: 3:58:30, time: 2.171, data_time: 0.120, memory: 26676, ema_momentum: 0.9990, sup_loss_rpn_cls: 0.0001, sup_loss_rpn_bbox: 0.0000, sup_loss_cls: 0.0000, sup_acc: 100.0000, sup_loss_bbox: 0.0000, unsup_loss_rpn_cls: 0.0002, unsup_loss_rpn_bbox: 0.0000, unsup_loss_cls: 0.0000, unsup_acc: 100.0000, unsup_loss_bbox: 0.0000, loss: 0.0003

and

[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 200/200, 9.5 task/s, elapsed: 21s, ETA:     0s2022-04-05 21:43:42,839 - mmdet.ssod - INFO - Evaluating bbox...
Loading and preparing results...
DONE (t=0.02s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=0.98s).
Accumulating evaluation results...
DONE (t=0.19s).
2022-04-05 21:43:44,086 - mmdet.ssod - INFO - 
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=1000 ] = 0.000
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=1000 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=300 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=1000 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = -1.000

Appreciate any clues about this! If there is a set of concrete instructions on how to train a custom dataset, that would be super helpful