Add inline evaluation results for summary evaluators #720
Annotations
1 warning and 2 notices
ubuntu-latest pipelines will use ubuntu-24.04 soon. For more details, see https://github.com/actions/runner-images/issues/10636
|
Annotation:
python/langsmith/evaluation/_arunner.py#L1
...........
WARNING: the benchmark result may be unstable
* the standard deviation (113 ms) is 16% of the mean (693 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: 693 ms +- 113 ms
...........
WARNING: the benchmark result may be unstable
* the standard deviation (186 ms) is 13% of the mean (1.42 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: 1.42 sec +- 0.19 sec
...........
WARNING: the benchmark result may be unstable
* the standard deviation (235 ms) is 15% of the mean (1.52 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: 1.52 sec +- 0.23 sec
...........
dumps_class_nested_py_branch_and_leaf_200x400: Mean +- std dev: 692 us +- 11 us
...........
dumps_class_nested_py_leaf_50x100: Mean +- std dev: 25.5 ms +- 0.3 ms
...........
dumps_class_nested_py_leaf_100x200: Mean +- std dev: 106 ms +- 2 ms
...........
dumps_dataclass_nested_50x100: Mean +- std dev: 26.1 ms +- 0.2 ms
...........
WARNING: the benchmark result may be unstable
* the standard deviation (17.7 ms) is 24% of the mean (75.3 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: 75.3 ms +- 17.7 ms
...........
dumps_pydanticv1_nested_50x100: Mean +- std dev: 202 ms +- 2 ms
|
Annotation:
python/langsmith/evaluation/_arunner.py#L1
+-----------------------------------------------+----------+------------------------+
| Benchmark | main | changes |
+===============================================+==========+========================+
| dumps_pydanticv1_nested_50x100 | 217 ms | 202 ms: 1.07x faster |
+-----------------------------------------------+----------+------------------------+
| create_5_000_run_trees | 717 ms | 693 ms: 1.03x faster |
+-----------------------------------------------+----------+------------------------+
| dumps_class_nested_py_branch_and_leaf_200x400 | 691 us | 692 us: 1.00x slower |
+-----------------------------------------------+----------+------------------------+
| dumps_class_nested_py_leaf_50x100 | 25.2 ms | 25.5 ms: 1.01x slower |
+-----------------------------------------------+----------+------------------------+
| dumps_class_nested_py_leaf_100x200 | 104 ms | 106 ms: 1.01x slower |
+-----------------------------------------------+----------+------------------------+
| dumps_dataclass_nested_50x100 | 25.5 ms | 26.1 ms: 1.02x slower |
+-----------------------------------------------+----------+------------------------+
| create_10_000_run_trees | 1.38 sec | 1.42 sec: 1.03x slower |
+-----------------------------------------------+----------+------------------------+
| create_20_000_run_trees | 1.40 sec | 1.52 sec: 1.08x slower |
+-----------------------------------------------+----------+------------------------+
| dumps_pydantic_nested_50x100 | 66.1 ms | 75.3 ms: 1.14x slower |
+-----------------------------------------------+----------+------------------------+
| Geometric mean | (ref) | 1.02x slower |
+-----------------------------------------------+----------+------------------------+
|
Loading