LILO hash computation and stamping for data freshness (#4992)#4992
Closed
ItsMrLin wants to merge 1 commit into
Closed
LILO hash computation and stamping for data freshness (#4992)#4992ItsMrLin wants to merge 1 commit into
ItsMrLin wants to merge 1 commit into
Conversation
meta-cla
Bot
added
the
CLA Signed
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 6, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 6, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #4992 +/- ##
==========================================
- Coverage 96.84% 96.80% -0.04%
==========================================
Files 604 605 +1
Lines 65022 65049 +27
==========================================
+ Hits 62971 62973 +2
- Misses 2051 2076 +25 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 9, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
force-pushed
the
export-D95284287
branch
from
3dab843 to
83ae087
Compare
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 9, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
force-pushed
the
export-D95284287
branch
from
83ae087 to
a3a52f3
Compare
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 9, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 9, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 9, 2026
Summary: Pull Request resolved: facebook#4992 Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
force-pushed
the
export-D95284287
branch
from
a3a52f3 to
942b0f9
Compare
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 9, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
force-pushed
the
export-D95284287
branch
from
942b0f9 to
03cb43d
Compare
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 11, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
meta-codesync
Bot
changed the title
ItsMrLin
force-pushed
the
export-D95284287
branch
from
03cb43d to
7c3c852
Compare
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Pull Request resolved: facebook#4992 Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
force-pushed
the
export-D95284287
branch
from
7c3c852 to
836fa17
Compare
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
force-pushed
the
export-D95284287
branch
from
836fa17 to
53dc52d
Compare
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
force-pushed
the
export-D95284287
branch
from
53dc52d to
b2487a0
Compare
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
added a commit
to ItsMrLin/Ax
that referenced
this pull request
Mar 13, 2026
Summary: Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
Summary: Pull Request resolved: facebook#4992 Add hash-based data freshness tracking for LILO (Language-in-the-Loop) pairwise preference labels. When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the experiment's LILO inputs (metric data for input_metric_names + LLM messages) onto the trial's _properties. If any of these inputs change (new data arrives, data is updated, or the user modifies LLM messages), the hash changes, indicating that existing LILO labels are stale. Changes: - Add `LILO_INPUT_HASH` key to `Keys` enum in `constants.py` - Create `ax/utils/common/hash_utils.py` with `compute_lilo_input_hash` (standalone hash function) and `get_current_lilo_hash` (convenience helper that looks up the pairwise `DerivedMetric` on an experiment, extracts `input_metric_names`, and computes the hash — returns `None` if no pairwise metric is registered) - Stamp hash in `LILOPairwiseMetric._compute_derived_values` after producing labels - Add tests for hash determinism, sensitivity to data/message changes, stamping, and `get_current_lilo_hash` helper Reviewed By: saitcakmak Differential Revision: D95284287
ItsMrLin
force-pushed
the
export-D95284287
branch
from
b2487a0 to
4bd8cb2
Compare
|
This pull request has been merged in 72d145c. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary:
Add hash-based data freshness tracking for LILO (Language-in-the-Loop)
pairwise preference labels.
When LILOPairwiseMetric produces labels, it now stamps a SHA-256 hash of the
experiment's LILO inputs (metric data for input_metric_names + LLM messages)
onto the trial's _properties. If any of these inputs change (new data arrives,
data is updated, or the user modifies LLM messages), the hash changes,
indicating that existing LILO labels are stale.
Changes:
LILO_INPUT_HASHkey toKeysenum inconstants.pyax/utils/common/hash_utils.pywithcompute_lilo_input_hash(standalone hash function) and
get_current_lilo_hash(convenience helperthat looks up the pairwise
DerivedMetricon an experiment, extractsinput_metric_names, and computes the hash — returnsNoneif no pairwisemetric is registered)
LILOPairwiseMetric._compute_derived_valuesafter producing labelsand
get_current_lilo_hashhelperReviewed By: saitcakmak
Differential Revision: D95284287