add eval heavy results for LLM360/CrystalChat and LLM360/CrystalCoder

exp_data/evals/evaluation_llm360_crystalchat_heavy.json

@@ -0,0 +1,82 @@
+{
+    "name": "dclm/eval/heavy",
+    "uuid": "0edca2de-5f6d-4ff4-b36d-58fedf9ed511",
+    "model": "LLM360/CrystalChat",
+    "creation_date": "2024_06_23-17_14_34",
+    "eval_metrics": {
+        "icl": {
+            "mmlu_zeroshot": 0.49118203421433765,
+            "hellaswag_zeroshot": 0.7257518172264099,
+            "jeopardy": 0.44828012883663176,
+            "triviaqa_sm_sub": 0.45899999141693115,
+            "gsm8k_cot": 0.27672478556632996,
+            "agi_eval_sat_math_cot": 0.05454545468091965,
+            "aqua_cot": 0.05306122452020645,
+            "svamp_cot": 0.550000011920929,
+            "bigbench_qa_wikidata": 0.7285074591636658,
+            "arc_easy": 0.7537878751754761,
+            "arc_challenge": 0.47184300422668457,
+            "mmlu_fewshot": 0.5318821093492341,
+            "bigbench_misconceptions": 0.611872136592865,
+            "copa": 0.8100000023841858,
+            "siqa": 0.8121801614761353,
+            "commonsense_qa": 0.8149058222770691,
+            "piqa": 0.7916213274002075,
+            "openbook_qa": 0.42399999499320984,
+            "bigbench_novel_concepts": 0.5625,
+            "bigbench_strange_stories": 0.6954023241996765,
+            "bigbench_strategy_qa": 0.6395806074142456,
+            "lambada_openai": 0.6988162398338318,
+            "hellaswag": 0.7455686330795288,
+            "winograd": 0.831501841545105,
+            "winogrande": 0.6819258332252502,
+            "bigbench_conlang_translation": 0.1768292635679245,
+            "bigbench_language_identification": 0.44780001044273376,
+            "bigbench_conceptual_combinations": 0.6990291476249695,
+            "bigbench_elementary_math_qa": 0.3252882659435272,
+            "bigbench_dyck_languages": 0.46799999475479126,
+            "agi_eval_lsat_ar": 0.269565224647522,
+            "bigbench_cs_algorithms": 0.6803030371665955,
+            "bigbench_logical_deduction": 0.414000004529953,
+            "bigbench_operators": 0.5190476179122925,
+            "bigbench_repeat_copy_logic": 0.46875,
+            "simple_arithmetic_nospaces": 0.25,
+            "simple_arithmetic_withspaces": 0.25600001215934753,
+            "math_qa": 0.27891385555267334,
+            "logi_qa": 0.3640553057193756,
+            "pubmed_qa_labeled": 0.7120000123977661,
+            "squad": 0.6070009469985962,
+            "agi_eval_lsat_rc": 0.5559701323509216,
+            "agi_eval_lsat_lr": 0.42941176891326904,
+            "coqa": 0.3893273174762726,
+            "bigbench_understanding_fables": 0.5661375522613525,
+            "boolq": 0.8284403681755066,
+            "agi_eval_sat_en": 0.6601941585540771,
+            "winogender_mc_female": 0.6166666746139526,
+            "winogender_mc_male": 0.5833333134651184,
+            "enterprise_pii_classification": 0.8055964708328247,
+            "bbq": 0.7637841918251731,
+            "gpqa_main": 0.2299107164144516,
+            "gpqa_diamond": 0.19191919267177582
+        }
+    },
+    "missing tasks": "[]",
+    "aggregated_task_categories_centered": {
+        "commonsense reasoning": 0.5056721038328877,
+        "language understanding": 0.5236024475329616,
+        "reading comprehension": 0.4991475528988399,
+        "safety": 0.3846903253685344,
+        "symbolic problem solving": 0.28766561410470637,
+        "world knowledge": 0.34202317620055717
+    },
+    "aggregated_centered_results": 0.40568592658807207,
+    "aggregated_results": 0.5324851958055062,
+    "rw_small": 0.7119581500689188,
+    "rw_small_centered": 0.5223704252326697,
+    "95%_CI_above": 0.6322675079397567,
+    "95%_CI_above_centered": 0.5159801635037385,
+    "99%_CI_above": 0.6380235204230185,
+    "99%_CI_above_centered": 0.5417409376048751,
+    "low_variance_datasets": 0.6183974771337076,
+    "low_variance_datasets_centered": 0.5240621761028209
+}

exp_data/evals/evaluation_llm360_crystalcoder_heavy.json

@@ -0,0 +1,82 @@
+{
+    "name": "dclm/eval/heavy",
+    "uuid": "a0dc2c19-3495-4a9d-8504-28d5b73cba4d",
+    "model": "LLM360/CrystalCoder",
+    "creation_date": "2024_06_25-03_34_14",
+    "eval_metrics": {
+        "icl": {
+            "mmlu_zeroshot": 0.374084400503259,
+            "hellaswag_zeroshot": 0.717486560344696,
+            "jeopardy": 0.47946962118148806,
+            "triviaqa_sm_sub": 0.46000000834465027,
+            "gsm8k_cot": 0.11372251808643341,
+            "agi_eval_sat_math_cot": 0.059090908616781235,
+            "aqua_cot": 0.04897959157824516,
+            "svamp_cot": 0.46000000834465027,
+            "bigbench_qa_wikidata": 0.7292948365211487,
+            "arc_easy": 0.7167508602142334,
+            "arc_challenge": 0.424914687871933,
+            "mmlu_fewshot": 0.4817048415803073,
+            "bigbench_misconceptions": 0.5205479264259338,
+            "copa": 0.7400000095367432,
+            "siqa": 0.7205731868743896,
+            "commonsense_qa": 0.7141687273979187,
+            "piqa": 0.780739963054657,
+            "openbook_qa": 0.38600000739097595,
+            "bigbench_novel_concepts": 0.59375,
+            "bigbench_strange_stories": 0.6436781883239746,
+            "bigbench_strategy_qa": 0.5923984050750732,
+            "lambada_openai": 0.5656898617744446,
+            "hellaswag": 0.7333200573921204,
+            "winograd": 0.8498168587684631,
+            "winogrande": 0.6795580387115479,
+            "bigbench_conlang_translation": 0.18292683362960815,
+            "bigbench_language_identification": 0.32589998841285706,
+            "bigbench_conceptual_combinations": 0.553398072719574,
+            "bigbench_elementary_math_qa": 0.30120545625686646,
+            "bigbench_dyck_languages": 0.41600000858306885,
+            "agi_eval_lsat_ar": 0.27391305565834045,
+            "bigbench_cs_algorithms": 0.6265151500701904,
+            "bigbench_logical_deduction": 0.2933333218097687,
+            "bigbench_operators": 0.5190476179122925,
+            "bigbench_repeat_copy_logic": 0.46875,
+            "simple_arithmetic_nospaces": 0.23899999260902405,
+            "simple_arithmetic_withspaces": 0.2370000034570694,
+            "math_qa": 0.27053302526474,
+            "logi_qa": 0.29032257199287415,
+            "pubmed_qa_labeled": 0.5339999794960022,
+            "squad": 0.6300851702690125,
+            "agi_eval_lsat_rc": 0.38805970549583435,
+            "agi_eval_lsat_lr": 0.31960785388946533,
+            "coqa": 0.44156330823898315,
+            "bigbench_understanding_fables": 0.45502644777297974,
+            "boolq": 0.7345565557479858,
+            "agi_eval_sat_en": 0.4563106894493103,
+            "winogender_mc_female": 0.6000000238418579,
+            "winogender_mc_male": 0.5833333134651184,
+            "enterprise_pii_classification": 0.7617083787918091,
+            "bbq": 0.5514446849172766,
+            "gpqa_main": 0.2299107164144516,
+            "gpqa_diamond": 0.1818181872367859
+        }
+    },
+    "missing tasks": "[]",
+    "aggregated_task_categories_centered": {
+        "commonsense reasoning": 0.4263667662631253,
+        "language understanding": 0.4672569049762027,
+        "reading comprehension": 0.3606951883258788,
+        "safety": 0.248243200508031,
+        "symbolic problem solving": 0.24264506751407772,
+        "world knowledge": 0.29221052439937817
+    },
+    "aggregated_centered_results": 0.33187367802374956,
+    "aggregated_results": 0.48020773938334366,
+    "rw_small": 0.6688777854045233,
+    "rw_small_centered": 0.4365750324656392,
+    "95%_CI_above": 0.5894522517726019,
+    "95%_CI_above_centered": 0.4495536445926848,
+    "99%_CI_above": 0.6053630136925241,
+    "99%_CI_above_centered": 0.494576455011657,
+    "low_variance_datasets": 0.5887973156842319,
+    "low_variance_datasets_centered": 0.48073897986479613
+}