StabilityFrontier-ModelRepo / audit /readme_patch_log.jsonl
petra345's picture
Release stability frontier model artifacts
b23a2a5 verified
Raw
History Blame Contribute Delete
3.81 kB
{"line":41,"benchmark":"math_reasoning","old_value":"{RESULT}","new_value":"0.647","source_sha256":"59f1c11d085be28431b10b9976844f2cef0145769afd215d52816e042dcbdee9","updated_sha256":"fba7f499f4a003a2c8752859dac4d93cd3bb62b85ba8682c4cf26fb861878d65"}
{"line":42,"benchmark":"logical_reasoning","old_value":"{RESULT}","new_value":"0.854","source_sha256":"2fb53e77fd731cdb84bbcf3c3ee223f1c6cfd9bac7410ceb2f06f96cc75e3681","updated_sha256":"5d583df3e682691ea117416648cbbeceb0f7b20165ab8ca54d43c7219d51cd8c"}
{"line":43,"benchmark":"common_sense","old_value":"{RESULT}","new_value":"0.779","source_sha256":"de64150939f8f04479fd5965b257c46467fbaa8f42ecd4b40d7b63acd6faa509","updated_sha256":"414d74669a5423a22bd66aa455d35ed36699dd01371c0d8cc11d2e690f09b1c2"}
{"line":44,"benchmark":"reading_comprehension","old_value":"{RESULT}","new_value":"0.750","source_sha256":"d8e11f2a5bb915e1f9eb8002fe6d0c10c948eaaf655e41df13c6ea351baaa3c4","updated_sha256":"7eeb34812074edcbaed4248da8e210820ddd3459bbb0d752f582856baa7d6eb1"}
{"line":45,"benchmark":"question_answering","old_value":"{RESULT}","new_value":"0.689","source_sha256":"b5110348947c4fb17587852299b158c45b0bd312f4be43e38591dc4cf22a0bee","updated_sha256":"a073f7f003e3a5d85e04ba201dc9200a31a699a59458f1e85ede32f987458569"}
{"line":46,"benchmark":"text_classification","old_value":"{RESULT}","new_value":"0.866","source_sha256":"e11f79e51326216776157613dac0277ca943e78032504ecf33d4cc58528a6149","updated_sha256":"f66a75ce55260bb4cfacef749cc859aade67ce797854dea7ea91ca6d6bc15ba9"}
{"line":47,"benchmark":"sentiment_analysis","old_value":"{RESULT}","new_value":"0.835","source_sha256":"5a665c2182579a63520fc86019fa3e7706a39313fce59ecca6a34a727af118c3","updated_sha256":"c145b6f49476a8297cc4cd1e011129792fafa55661f55d0f4a4f663fe9bbf53b"}
{"line":48,"benchmark":"code_generation","old_value":"{RESULT}","new_value":"0.724","source_sha256":"3654e4df8575b8311c230f66f74f7a8db5ba069e65fdfdc2afd97d74597b890c","updated_sha256":"f3a5b399c2bfe5ff46030c64efd331972c38712240bc5d6f8464059c3e8f54dd"}
{"line":49,"benchmark":"creative_writing","old_value":"{RESULT}","new_value":"0.667","source_sha256":"e012202c92d82f898f2cfeb46b6fed0e52c8b843ac82e4436075e63818d11ebb","updated_sha256":"f9df78fb645ab1a1e82b2331ce654561fc7fa92e7f0aaf37abbae69ee4ade8c0"}
{"line":50,"benchmark":"dialogue_generation","old_value":"{RESULT}","new_value":"0.715","source_sha256":"1cf6ae58a78b77bb7e403c7c049ccc73ea1bdbf8918f0accef00aa73910984ba","updated_sha256":"e3f4af57309688e8d83a5d2f13ba173e5202fe0002ea4687906af523402e5082"}
{"line":51,"benchmark":"summarization","old_value":"{RESULT}","new_value":"0.816","source_sha256":"c7a43007cc1c9c0ac736f5651146e51b6b5a75c556da7fe811f5c4b975ce6e0b","updated_sha256":"2f5d782067b162f0abf015d65caa941fd8920c1e22e59fc3b310159903d3652a"}
{"line":52,"benchmark":"translation","old_value":"{RESULT}","new_value":"0.843","source_sha256":"4354a5b338d522f6c384b1983cf042802fbdc9fbbb6241e78180bae7aaea226e","updated_sha256":"1e7d81ab94e55c38450a7ad45b482b612e3894a569a6a9c513a388eee58b299a"}
{"line":53,"benchmark":"knowledge_retrieval","old_value":"{RESULT}","new_value":"0.738","source_sha256":"3c0a1b47d6e9a624024576bc741c0450cff5c49886dfff2487f1cd61606a3500","updated_sha256":"09134e05e009483eff3da5806f4ad6b426d61de637a66a2fee52740ca83af7bb"}
{"line":54,"benchmark":"instruction_following","old_value":"{RESULT}","new_value":"0.783","source_sha256":"2df22699e59be53b979a926f5159badd2d50adcc6c4f8c7aca76615b83b59bca","updated_sha256":"13fe73d629d7afcf1415a4bcdf73373b62e9cd135d685f79789bc879be3014b1"}
{"line":55,"benchmark":"safety_evaluation","old_value":"{RESULT}","new_value":"0.790","source_sha256":"48dd82f9b5c0d7a943f8f6c4fb7dd26851bb60f7048c04e384b928625600aebb","updated_sha256":"fbbd4b7fe0ea7827924c09384805a80e7cb58d6487a62f4a46327500b7fc3532"}