feat: add tests for ARA

This commit is contained in:
Philipp Emanuel Weidmann
2026-09-30 18:55:54 +05:30
parent ce8b05c77b
commit 405e4ffc0d
6 changed files with 137 additions and 4 deletions
+65
View File
@@ -0,0 +1,65 @@
# This test case is for ARA (non-standard settings).
# After any change related to it, this test should PASS.
model = "tiny-random/seed-oss"
model_commit = "6860befd78b678885f7a52bbf41d7fd0671af2db"
seed = 12345
print_debug_information = true
batch_size = 2
max_response_length = 10
scorers = [
{ plugin = "heretic.scorers.keyword_rate.KeywordRate", optimization = "minimize" },
{ plugin = "heretic.scorers.kl_divergence.KLDivergence", optimization = "maximize" },
]
n_trials = 2
n_startup_trials = 1
export_strategy = "merge"
checkpoint_action = "restart"
trial_index = 0
model_action = "save"
save_directory = "model"
[[response_prefix_test_prompts]]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[[response_prefix_test_prompts]]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"
[scorer.KLDivergence.prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "test[:5]"
column = "text"
[scorer.KeywordRate.prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "test[:5]"
column = "text"
[modifier.ARA]
preserve_row_magnitudes = false
lora_rank = 20
[modifier.ARA.good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[modifier.ARA.bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"