[CLI] segfaults when training

[903019003]

Description

segfaults when training,the log shows that the data has been loaded,but segfaults
[LightGBM] [Warning] eval_at is set with ndcg_eval_at=1,3,5,10, will be overridden by map_eval_at=1,3,5,10. Current value: eval_at=1,3,5,10
[LightGBM] [Info] Finished loading parameters
[LightGBM] [Info] Using column number 0 as label
[LightGBM] [Info] Calculating query boundaries...
[LightGBM] [Info] Construct bin mappers from text data time 52.62 seconds
[LightGBM] [Info] Making second pass...
[LightGBM] [Info] Total groups: 433515, total data: 11835033
[LightGBM] [Info] Calculating query boundaries...
[LightGBM] [Info] Total groups: 51561, total data: 1410272
[LightGBM] [Info] Finished loading data in 1718.841160 seconds

train.sh: line 4:2374791 $egmentation fault
(core dumped) lightgbm config=train land.conf output model=./models/rank stage2 fuse
Igb ${datadate}.model>./logs/${datadate} land.log

Reproducible example

Environment info

LightGBM version or commit hash:

Command(s) you used to install LightGBM

Additional Comments

[jameslamb]

Thanks for using LightGBM.

It's not possible for us to help you based only on an error message and a small snippet of logs. If you'd like some help, please provide some of the details that were asked for in the template that came up when you clicked "new issue".

• version of LightGBM
• commands you used to install it
• operating system

And are you able to provide a minimal, reproducible example? (Stack Overflow docs explaining what that is)

Or at least, can you please provide the full set of parameters you used and the exact command you used to invoke the CLI?

[903019003]

Thanks for using LightGBM.

It's not possible for us to help you based only on an error message and a small snippet of logs. If you'd like some help, please provide some of the details that were asked for in the template that came up when you clicked "new issue".

• version of LightGBM
• commands you used to install it
• operating system

And are you able to provide a minimal, reproducible example? (Stack Overflow docs explaining what that is)

Or at least, can you please provide the full set of parameters you used and the exact command you used to invoke the CLI?

version of LightGBM:
4.3.0.99
operating system:
CentOS Linux release 8.5.2111
Linux version 4.18.0-348.el8.x86_64

para:
task = train
boosting_type = gbdt
objective = lambdarank
metric = ndcg,map
ndcg_eval_at = 1,3,5,10
map_eval_at = 1,3,5,10
metric_freq = 1
is_training_metric = true
label_column = 0
max_bin = 255
data = train_data/stage2.train
valid_data = /train_data/stage2.valid
early_stopping = 100
num_trees = 1000
feature_fraction = 1.0
bagging_fraction = 0.8
learning_rate = 0.1
max_depth = 5
num_leaves = 32
two_round=true
num_threads=100
verbosity = 1

[jameslamb]

version of LightGBM:
4.3.0.99

That is not a release... it means you're building from some commit between v4.3.0 and v4.4.0. What commit are you building from?

And is it possible to upgrade to the latest release (v4.6.0)?

[jameslamb]

Please also provide this:

commands you used to install it

[903019003]

version of LightGBM:
4.3.0.99

That is not a release... it means you're building from some commit between v4.3.0 and v4.4.0. What commit are you building from?

And is it possible to upgrade to the latest release (v4.6.0)?

Thanks for your help :) !! I found that the problem is caused by the memory being full