Stack Overflow
Stack Overflow

Questions tagged [ray-tune]

72 questions
1
vote
1 answer

How can I sync the complete `local_dir` (`~/ray_results`) with the head node?

I am creating custom result files in my jobs and want to sync them from the worker nodes to the head nodes (To rsync them down to my local computer later on). I tried to write them all into the local_dir e.g. ~./ray_results but unfortunately it…
Denis
  • 13
  • 2
0
votes
0 answers

Ray Tune Hyperparamter Optimization with XGBoost - TuneNoNextExecutorEventError| RayActorError

I simply would like to tune my XGBoost with Ray Tune locally. However, my "actor" always dies unexpectedly before the ray trail could even start. I tried different code variants and also checked memory consumption/availability (I have 48 CPUs and…
Carsten
  • 35
  • 7
0
votes
0 answers

How train model using tensorflow and rayTune then upload best model and its log to S3

I'm using raytune to do hyperparameter optimization with tensorflow model. What I want to do is after training, upload model.h5 and its training log upto S3. My code is something like this: tuner = tuner.Tuner( tune.with_resources(), …
haneulkim
  • 4,406
  • 9
  • 38
  • 80
0
votes
0 answers

Does the BayesOptSearch algorithm support discrete hyperparameter spaces in Ray Tune?

I am writing an example using Ray Tune with BayesOptSearch algorithm. However, I got an error at line "results = tuner.fit()" presents BayesOpt does not support parameters of type Categorical I am running Ray 2.5.1 on Ubuntu. The problem may be…
James Xue
  • 1
  • 1
0
votes
0 answers

How to integrate tf.data.dataset with rayTune for distributed training

Using tensorflow-cpu==2.9.3, petastorm==0.12.1 on python 3.7 I've created tf.data.Dataset using petastorm for train and validation dataset. ds_train (DatasetV1Adapter; think this is old version of tf.data.dataset) ds_valid (DatasetV1Adapter) First…
haneulkim
  • 4,406
  • 9
  • 38
  • 80
0
votes
0 answers

Setting initial iterations in Ray Tune's implementation of BOHB

I am trying to use Ray Tune's implementation of BOHB to hyperparameter tune a PPO model. If I set the amount of iterations to e.g. 100 it works fine - however it already samples new hyperparameter values after only one iteration of a sample.…
Jakob Sejten
  • 31
  • 2
0
votes
0 answers

How can I set or limit the number of cores that a trial is allowed to use?

I am trying to run a trial in RayTune, for which I want to test how the number of cores I throw at the problem affects calculation times. I tried ray.init(num_cpus=foo), but it just utilises all cores on the machine nonetheless, regardless of the…
user18259592
  • 25
  • 3
0
votes
0 answers

Using Ray Tune to tune number of hidden layers in Keras

Is there any way to treat number of layers in a model as a hyperparameter in ray tune? in THIS example, I want to add a set to param_space to tune number of hidden layers like any other hyperparameter. How can I do it? import argparse import…
Amir
  • 29
  • 4
0
votes
0 answers

Problems with ray tune in combination with mlflow and keras (tensorflow)

I am using ray tune now for a while and it is really good! But when combining it with mlflow and keras callbacks, I have encountered problems. My Settings: Windows tensorflow==2.11.0 ray==2.3.0 mlflow==2.2.1 I am using it with a tune_trainable…
Patrick
  • 11
  • 2
0
votes
0 answers

How can I pass a callback to Ray Tune but using TuneSearchCV?

I am using Ray Tune's TuneSearchCV to perform a model hyperparameter search. I would like to register a callback (in this case to simply print some extra metrics). I have no problem writing the callback (see…
jtlz2
  • 7,700
  • 9
  • 64
  • 114
0
votes
0 answers

Ray-Tune with Optuna and tune.sample_from

I'm trying to run OptunaSearch with a config that looks like this config = {"algorithm": tune.choice(list(search_space.keys())), "params": tune.sample_from(lambda spec: search_space[spec.config.algorithm]['params'])} Where the…
Rodrigo A
  • 657
  • 7
  • 23
0
votes
1 answer

How to manually log to Ray Train's internal Tensorboard logger?

Ray Train automatically stores various things to Tensorboard. In addition, I want to log custom histograms, images, PR curves, scalars, etc. How do I access Ray Train's internal TBXLogger so that I can log additional things?
crypdick
  • 16,152
  • 7
  • 51
  • 74
0
votes
0 answers

How to reduce space during the ray/pytorch HPO process?

Could I ask, When I run pytorch lightning with ray HPO it creates a lot of directories like…
Slowat_Kela
  • 1,377
  • 2
  • 22
  • 60
0
votes
0 answers

How to load trials results for hyperparameter_search

I run 100 trials for hyperparameters tuning of a transformers as following: trainer = Trainer(...) best_trial = trainer.hyperparameter_search(direction="maximize", backend='ray', …
LearnToGrow
  • 1,656
  • 6
  • 30
  • 53
1 2
3
4 5