Issue with scripts/evaluate_pretrained_model.sh - Stuck at "Rate 0.000 tasks/s, ETA 5555555.556 hours"

[yvfengZhong]

Hello,

I've encountered an issue while trying to run the scripts/evaluate_pretrained_model.sh script as instructed in the TRAINING_README.md file.

python -m training.offline.online_eval --shuffle --eval_subset minival --output_basedir tmp_log \
 --test_augmentation --task_type ObjectNavType \
 --input_sensors raw_navigation_camera raw_manipulation_camera last_actions an_object_is_in_hand \
 nav_task_relevant_object_bbox manip_task_relevant_object_bbox nav_accurate_object_bbox manip_accurate_object_bbox \
 --house_set objaverse --wandb_logging False --num_workers 2 \
 --gpu_devices 0 --training_run_id SigLIP-ViTb-3-double-det-CHORES-S --local_checkpoint_dir $CKPT_DIR

However, the script seems to be stuck and continuously outputs the following message:
Rate 0.000 tasks/s, ETA 5555555.556 hours

This appears to indicate that the script is not processing any tasks. I would appreciate any guidance on how to resolve this issue.
Thank you for your help!

[yvfengZhong]

Specifically, when the code reaches

spoc-robot-training/online_evaluation/online_evaluator_worker.py

Line 484 in 1efeeaa

task = self.task_sampler.next_task()

, it unexpectedly jumps to

spoc-robot-training/online_evaluation/online_evaluator.py

Line 531 in 1efeeaa

new_found_results = self.accumulate_results(results_queue, task_type_to_results_list)

instead of continuing to

spoc-robot-training/online_evaluation/online_evaluator_worker.py

Line 503 in 1efeeaa

sample_result = self.evaluate_on_task(task=task, agent=agent, worker_id=self.worker_id)

.

Additionally, the variable new_found_results remains 0 throughout, which might be related to the issue.

[zzee-glitch]

Hello, can you download the pre-trained model? If possible, can you share it? I can’t seem to download it here. Thank you

[shonnon-zxs]

Have you solved this problem?