[DRAFT] update evaluate to be concurrent #718
baskaryanAnnotations
1 warning and 2 notices
|
benchmark
ubuntu-latest pipelines will use ubuntu-24.04 soon. For more details, see https://github.com/actions/runner-images/issues/10636
|
|
Benchmark results:
python/langsmith/evaluation/_arunner.py#L1
...........
WARNING: the benchmark result may be unstable
* the standard deviation (93.3 ms) is 13% of the mean (696 ms)
Try to rerun the benchmark with more runs, values and/or loops.
Run 'python -m pyperf system tune' command to reduce the system jitter.
Use pyperf stats, pyperf dump and pyperf hist to analyze results.
Use --quiet option to hide these warnings.
create_5_000_run_trees: Mean +- std dev: 696 ms +- 93 ms
...........
WARNING: the benchmark result may be unstable
* the standard deviation (206 ms) is 15% of the mean (1.41 sec)
Try to rerun the benchmark with more runs, values and/or loops.
Run 'python -m pyperf system tune' command to reduce the system jitter.
Use pyperf stats, pyperf dump and pyperf hist to analyze results.
Use --quiet option to hide these warnings.
create_10_000_run_trees: Mean +- std dev: 1.41 sec +- 0.21 sec
...........
WARNING: the benchmark result may be unstable
* the standard deviation (257 ms) is 18% of the mean (1.44 sec)
Try to rerun the benchmark with more runs, values and/or loops.
Run 'python -m pyperf system tune' command to reduce the system jitter.
Use pyperf stats, pyperf dump and pyperf hist to analyze results.
Use --quiet option to hide these warnings.
create_20_000_run_trees: Mean +- std dev: 1.44 sec +- 0.26 sec
...........
dumps_class_nested_py_branch_and_leaf_200x400: Mean +- std dev: 695 us +- 7 us
...........
dumps_class_nested_py_leaf_50x100: Mean +- std dev: 25.7 ms +- 1.7 ms
...........
WARNING: the benchmark result may be unstable
* the standard deviation (11.4 ms) is 11% of the mean (109 ms)
Try to rerun the benchmark with more runs, values and/or loops.
Run 'python -m pyperf system tune' command to reduce the system jitter.
Use pyperf stats, pyperf dump and pyperf hist to analyze results.
Use --quiet option to hide these warnings.
dumps_class_nested_py_leaf_100x200: Mean +- std dev: 109 ms +- 11 ms
...........
dumps_dataclass_nested_50x100: Mean +- std dev: 25.9 ms +- 0.5 ms
...........
WARNING: the benchmark result may be unstable
* the standard deviation (16.0 ms) is 22% of the mean (72.5 ms)
Try to rerun the benchmark with more runs, values and/or loops.
Run 'python -m pyperf system tune' command to reduce the system jitter.
Use pyperf stats, pyperf dump and pyperf hist to analyze results.
Use --quiet option to hide these warnings.
dumps_pydantic_nested_50x100: Mean +- std dev: 72.5 ms +- 16.0 ms
...........
dumps_pydanticv1_nested_50x100: Mean +- std dev: 197 ms +- 5 ms
|
|
Comparison against main:
python/langsmith/evaluation/_arunner.py#L1
+-----------------------------------------------+----------+------------------------+
| Benchmark | main | changes |
+===============================================+==========+========================+
| dumps_pydanticv1_nested_50x100 | 217 ms | 197 ms: 1.10x faster |
+-----------------------------------------------+----------+------------------------+
| create_5_000_run_trees | 717 ms | 696 ms: 1.03x faster |
+-----------------------------------------------+----------+------------------------+
| dumps_class_nested_py_branch_and_leaf_200x400 | 691 us | 695 us: 1.00x slower |
+-----------------------------------------------+----------+------------------------+
| dumps_dataclass_nested_50x100 | 25.5 ms | 25.9 ms: 1.01x slower |
+-----------------------------------------------+----------+------------------------+
| dumps_class_nested_py_leaf_50x100 | 25.2 ms | 25.7 ms: 1.02x slower |
+-----------------------------------------------+----------+------------------------+
| create_10_000_run_trees | 1.38 sec | 1.41 sec: 1.02x slower |
+-----------------------------------------------+----------+------------------------+
| create_20_000_run_trees | 1.40 sec | 1.44 sec: 1.03x slower |
+-----------------------------------------------+----------+------------------------+
| dumps_class_nested_py_leaf_100x200 | 104 ms | 109 ms: 1.04x slower |
+-----------------------------------------------+----------+------------------------+
| dumps_pydantic_nested_50x100 | 66.1 ms | 72.5 ms: 1.10x slower |
+-----------------------------------------------+----------+------------------------+
| Geometric mean | (ref) | 1.01x slower |
+-----------------------------------------------+----------+------------------------+
|