Add

.gitattributes

@@ -3164,3 +3164,27 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 4b284b1b9c4/evaluation/generation/examples.4b284b1b9c4_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text
 4b284b1b9c4/evaluation/generation/examples.4b284b1b9c4_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text
 4b284b6bc4/evaluation/generation/examples.4b284b6bc4_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-web_nlg_en_PALM_prompt_4.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-wiki_lingua_en_tldr_en_3.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-wiki_lingua_en_tldr_en_4.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-wiki_lingua_en_tldr_en_5.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_gem_xsum_article_DOC_summary_1.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-web_nlg_en_PALM_prompt_2.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-wiki_lingua_en_tldr_en_1.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-wiki_lingua_en_tldr_en_2.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-web_nlg_en_PALM_prompt_1.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-web_nlg_en_PALM_prompt_3.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_gem_xsum_article_DOC_summary_0.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_gem_xsum_article_DOC_summary_2.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_gem_xsum_article_DOC_summary_5.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-wiki_lingua_en_tldr_en_0.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_gem_xsum_article_DOC_summary_3.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_gem_xsum_article_DOC_summary_4.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-web_nlg_en_PALM_prompt_0.jsonl filter=lfs diff=lfs merge=lfs -text
+4b284b12bc4opt4/evaluation/generation/examples.4b284b12bc4opt4_GEM-web_nlg_en_PALM_prompt_5.jsonl filter=lfs diff=lfs merge=lfs -text

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_0.json

@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.345,
+            "acc_stderr": 0.015039986742055237
+        },
+        "anli_r2": {
+            "acc": 0.338,
+            "acc_stderr": 0.01496596071022449
+        },
+        "anli_r3": {
+            "acc": 0.3441666666666667,
+            "acc_stderr": 0.013720551062295756
+        },
+        "cb": {
+            "acc": 0.375,
+            "acc_stderr": 0.06527912098338669,
+            "f1": 0.1986111111111111
+        },
+        "copa": {
+            "acc": 0.8,
+            "acc_stderr": 0.040201512610368445
+        },
+        "hellaswag": {
+            "acc": 0.4736108344951205,
+            "acc_stderr": 0.004982826916687145,
+            "acc_norm": 0.6177056363274248,
+            "acc_norm_stderr": 0.0048495478191344825
+        },
+        "rte": {
+            "acc": 0.5523465703971119,
+            "acc_stderr": 0.02993107036293953
+        },
+        "winogrande": {
+            "acc": 0.5872138910812944,
+            "acc_stderr": 0.013837060648682103
+        },
+        "storycloze_2016": {
+            "acc": 0.7049706039551042,
+            "acc_stderr": 0.010546232606962287
+        },
+        "boolq": {
+            "acc": 0.5091743119266054,
+            "acc_stderr": 0.00874358274491014
+        },
+        "arc_easy": {
+            "acc": 0.5753367003367004,
+            "acc_stderr": 0.01014265368748041,
+            "acc_norm": 0.515993265993266,
+            "acc_norm_stderr": 0.01025453358928818
+        },
+        "arc_challenge": {
+            "acc": 0.2713310580204778,
+            "acc_stderr": 0.012993807727545797,
+            "acc_norm": 0.2909556313993174,
+            "acc_norm_stderr": 0.013273077865907573
+        },
+        "sciq": {
+            "acc": 0.842,
+            "acc_stderr": 0.01153989467755957,
+            "acc_norm": 0.751,
+            "acc_norm_stderr": 0.013681600278702301
+        },
+        "piqa": {
+            "acc": 0.7388465723612623,
+            "acc_stderr": 0.01024873864993558,
+            "acc_norm": 0.7437431991294886,
+            "acc_norm_stderr": 0.010185787831565058
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_0_lm-eval_global_step109672_2023-05-15-10-12-47_0shots_backup.json

@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.345,
+            "acc_stderr": 0.015039986742055237
+        },
+        "anli_r2": {
+            "acc": 0.338,
+            "acc_stderr": 0.01496596071022449
+        },
+        "anli_r3": {
+            "acc": 0.3441666666666667,
+            "acc_stderr": 0.013720551062295756
+        },
+        "cb": {
+            "acc": 0.375,
+            "acc_stderr": 0.06527912098338669,
+            "f1": 0.1986111111111111
+        },
+        "copa": {
+            "acc": 0.8,
+            "acc_stderr": 0.040201512610368445
+        },
+        "hellaswag": {
+            "acc": 0.4736108344951205,
+            "acc_stderr": 0.004982826916687145,
+            "acc_norm": 0.6177056363274248,
+            "acc_norm_stderr": 0.0048495478191344825
+        },
+        "rte": {
+            "acc": 0.5523465703971119,
+            "acc_stderr": 0.02993107036293953
+        },
+        "winogrande": {
+            "acc": 0.5872138910812944,
+            "acc_stderr": 0.013837060648682103
+        },
+        "storycloze_2016": {
+            "acc": 0.7049706039551042,
+            "acc_stderr": 0.010546232606962287
+        },
+        "boolq": {
+            "acc": 0.5091743119266054,
+            "acc_stderr": 0.00874358274491014
+        },
+        "arc_easy": {
+            "acc": 0.5753367003367004,
+            "acc_stderr": 0.01014265368748041,
+            "acc_norm": 0.515993265993266,
+            "acc_norm_stderr": 0.01025453358928818
+        },
+        "arc_challenge": {
+            "acc": 0.2713310580204778,
+            "acc_stderr": 0.012993807727545797,
+            "acc_norm": 0.2909556313993174,
+            "acc_norm_stderr": 0.013273077865907573
+        },
+        "sciq": {
+            "acc": 0.842,
+            "acc_stderr": 0.01153989467755957,
+            "acc_norm": 0.751,
+            "acc_norm_stderr": 0.013681600278702301
+        },
+        "piqa": {
+            "acc": 0.7388465723612623,
+            "acc_stderr": 0.01024873864993558,
+            "acc_norm": 0.7437431991294886,
+            "acc_norm_stderr": 0.010185787831565058
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_1.json

@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.327,
+            "acc_stderr": 0.014842213153411239
+        },
+        "anli_r2": {
+            "acc": 0.318,
+            "acc_stderr": 0.014734079309311901
+        },
+        "anli_r3": {
+            "acc": 0.34,
+            "acc_stderr": 0.013680495725767784
+        },
+        "cb": {
+            "acc": 0.42857142857142855,
+            "acc_stderr": 0.06672848092813057,
+            "f1": 0.2385663082437276
+        },
+        "copa": {
+            "acc": 0.82,
+            "acc_stderr": 0.038612291966536955
+        },
+        "hellaswag": {
+            "acc": 0.4735112527384983,
+            "acc_stderr": 0.004982774293927781,
+            "acc_norm": 0.6200955984863573,
+            "acc_norm_stderr": 0.0048437085503865145
+        },
+        "rte": {
+            "acc": 0.5415162454873647,
+            "acc_stderr": 0.029992535385373314
+        },
+        "winogrande": {
+            "acc": 0.5872138910812944,
+            "acc_stderr": 0.013837060648682106
+        },
+        "storycloze_2016": {
+            "acc": 0.703901656867985,
+            "acc_stderr": 0.010557307688475123
+        },
+        "boolq": {
+            "acc": 0.536085626911315,
+            "acc_stderr": 0.008722250102078083
+        },
+        "arc_easy": {
+            "acc": 0.5934343434343434,
+            "acc_stderr": 0.01007905641922353,
+            "acc_norm": 0.5534511784511784,
+            "acc_norm_stderr": 0.010200990076245307
+        },
+        "arc_challenge": {
+            "acc": 0.28242320819112626,
+            "acc_stderr": 0.013155456884097224,
+            "acc_norm": 0.310580204778157,
+            "acc_norm_stderr": 0.013522292098053054
+        },
+        "sciq": {
+            "acc": 0.85,
+            "acc_stderr": 0.0112972398234093,
+            "acc_norm": 0.776,
+            "acc_norm_stderr": 0.013190830072364464
+        },
+        "piqa": {
+            "acc": 0.7404787812840044,
+            "acc_stderr": 0.010227939888173922,
+            "acc_norm": 0.7578890097932536,
+            "acc_norm_stderr": 0.009994371269104397
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_1_lm-eval_global_step109672_2023-05-15-10-12-47_1shots_backup.json

@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.327,
+            "acc_stderr": 0.014842213153411239
+        },
+        "anli_r2": {
+            "acc": 0.318,
+            "acc_stderr": 0.014734079309311901
+        },
+        "anli_r3": {
+            "acc": 0.34,
+            "acc_stderr": 0.013680495725767784
+        },
+        "cb": {
+            "acc": 0.42857142857142855,
+            "acc_stderr": 0.06672848092813057,
+            "f1": 0.2385663082437276
+        },
+        "copa": {
+            "acc": 0.82,
+            "acc_stderr": 0.038612291966536955
+        },
+        "hellaswag": {
+            "acc": 0.4735112527384983,
+            "acc_stderr": 0.004982774293927781,
+            "acc_norm": 0.6200955984863573,
+            "acc_norm_stderr": 0.0048437085503865145
+        },
+        "rte": {
+            "acc": 0.5415162454873647,
+            "acc_stderr": 0.029992535385373314
+        },
+        "winogrande": {
+            "acc": 0.5872138910812944,
+            "acc_stderr": 0.013837060648682106
+        },
+        "storycloze_2016": {
+            "acc": 0.703901656867985,
+            "acc_stderr": 0.010557307688475123
+        },
+        "boolq": {
+            "acc": 0.536085626911315,
+            "acc_stderr": 0.008722250102078083
+        },
+        "arc_easy": {
+            "acc": 0.5934343434343434,
+            "acc_stderr": 0.01007905641922353,
+            "acc_norm": 0.5534511784511784,
+            "acc_norm_stderr": 0.010200990076245307
+        },
+        "arc_challenge": {
+            "acc": 0.28242320819112626,
+            "acc_stderr": 0.013155456884097224,
+            "acc_norm": 0.310580204778157,
+            "acc_norm_stderr": 0.013522292098053054
+        },
+        "sciq": {
+            "acc": 0.85,
+            "acc_stderr": 0.0112972398234093,
+            "acc_norm": 0.776,
+            "acc_norm_stderr": 0.013190830072364464
+        },
+        "piqa": {
+            "acc": 0.7404787812840044,
+            "acc_stderr": 0.010227939888173922,
+            "acc_norm": 0.7578890097932536,
+            "acc_norm_stderr": 0.009994371269104397
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_2.json

@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.334,
+            "acc_stderr": 0.014922019523732963
+        },
+        "anli_r2": {
+            "acc": 0.325,
+            "acc_stderr": 0.014818724459095526
+        },
+        "anli_r3": {
+            "acc": 0.35083333333333333,
+            "acc_stderr": 0.013782212417178197
+        },
+        "cb": {
+            "acc": 0.4107142857142857,
+            "acc_stderr": 0.06633634150359541,
+            "f1": 0.23484848484848486
+        },
+        "copa": {
+            "acc": 0.82,
+            "acc_stderr": 0.03861229196653694
+        },
+        "hellaswag": {
+            "acc": 0.4720175263891655,
+            "acc_stderr": 0.004981961097590806,
+            "acc_norm": 0.6194981079466242,
+            "acc_norm_stderr": 0.0048451800342716195
+        },
+        "rte": {
+            "acc": 0.5018050541516246,
+            "acc_stderr": 0.030096267148976626
+        },
+        "winogrande": {
+            "acc": 0.584846093133386,
+            "acc_stderr": 0.013848684086658588
+        },
+        "storycloze_2016": {
+            "acc": 0.7135221806520577,
+            "acc_stderr": 0.01045510591863303
+        },
+        "boolq": {
+            "acc": 0.5461773700305811,
+            "acc_stderr": 0.008707680082127857
+        },
+        "arc_easy": {
+            "acc": 0.609006734006734,
+            "acc_stderr": 0.010012992232540636,
+            "acc_norm": 0.5614478114478114,
+            "acc_norm_stderr": 0.010182010275471116
+        },
+        "arc_challenge": {
+            "acc": 0.2841296928327645,
+            "acc_stderr": 0.013179442447653886,
+            "acc_norm": 0.30887372013651876,
+            "acc_norm_stderr": 0.013501770929344003
+        },
+        "sciq": {
+            "acc": 0.853,
+            "acc_stderr": 0.011203415395160336,
+            "acc_norm": 0.783,
+            "acc_norm_stderr": 0.01304151375727071
+        },
+        "piqa": {
+            "acc": 0.7464635473340587,
+            "acc_stderr": 0.010150090834551786,
+            "acc_norm": 0.7557127312295974,
+            "acc_norm_stderr": 0.010024765172284247
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_2_lm-eval_global_step109672_2023-05-15-10-12-47_2shots_backup.json

@@ -0,0 +1,87 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.334,
+            "acc_stderr": 0.014922019523732963
+        },
+        "anli_r2": {
+            "acc": 0.325,
+            "acc_stderr": 0.014818724459095526
+        },
+        "anli_r3": {
+            "acc": 0.35083333333333333,
+            "acc_stderr": 0.013782212417178197
+        },
+        "cb": {
+            "acc": 0.4107142857142857,
+            "acc_stderr": 0.06633634150359541,
+            "f1": 0.23484848484848486
+        },
+        "copa": {
+            "acc": 0.82,
+            "acc_stderr": 0.03861229196653694
+        },
+        "hellaswag": {
+            "acc": 0.4720175263891655,
+            "acc_stderr": 0.004981961097590806,
+            "acc_norm": 0.6194981079466242,
+            "acc_norm_stderr": 0.0048451800342716195
+        },
+        "rte": {
+            "acc": 0.5018050541516246,
+            "acc_stderr": 0.030096267148976626
+        },
+        "winogrande": {
+            "acc": 0.584846093133386,
+            "acc_stderr": 0.013848684086658588
+        },
+        "storycloze_2016": {
+            "acc": 0.7135221806520577,
+            "acc_stderr": 0.01045510591863303
+        },
+        "boolq": {
+            "acc": 0.5461773700305811,
+            "acc_stderr": 0.008707680082127857
+        },
+        "arc_easy": {
+            "acc": 0.609006734006734,
+            "acc_stderr": 0.010012992232540636,
+            "acc_norm": 0.5614478114478114,
+            "acc_norm_stderr": 0.010182010275471116
+        },
+        "arc_challenge": {
+            "acc": 0.2841296928327645,
+            "acc_stderr": 0.013179442447653886,
+            "acc_norm": 0.30887372013651876,
+            "acc_norm_stderr": 0.013501770929344003
+        },
+        "sciq": {
+            "acc": 0.853,
+            "acc_stderr": 0.011203415395160336,
+            "acc_norm": 0.783,
+            "acc_norm_stderr": 0.01304151375727071
+        },
+        "piqa": {
+            "acc": 0.7464635473340587,
+            "acc_stderr": 0.010150090834551786,
+            "acc_norm": 0.7557127312295974,
+            "acc_norm_stderr": 0.010024765172284247
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0,
+        "sciq": 0,
+        "piqa": 0
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_3.json

@@ -0,0 +1,73 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.329,
+            "acc_stderr": 0.014865395385928367
+        },
+        "anli_r2": {
+            "acc": 0.325,
+            "acc_stderr": 0.014818724459095526
+        },
+        "anli_r3": {
+            "acc": 0.3458333333333333,
+            "acc_stderr": 0.013736245342311012
+        },
+        "cb": {
+            "acc": 0.44642857142857145,
+            "acc_stderr": 0.06703189227942398,
+            "f1": 0.3862433862433863
+        },
+        "copa": {
+            "acc": 0.85,
+            "acc_stderr": 0.03588702812826371
+        },
+        "hellaswag": {
+            "acc": 0.4733120892252539,
+            "acc_stderr": 0.004982668452118941,
+            "acc_norm": 0.6216889065923122,
+            "acc_norm_stderr": 0.004839746491523517
+        },
+        "rte": {
+            "acc": 0.516245487364621,
+            "acc_stderr": 0.030080573208738064
+        },
+        "winogrande": {
+            "acc": 0.5785319652722968,
+            "acc_stderr": 0.0138780723774976
+        },
+        "storycloze_2016": {
+            "acc": 0.711918760021379,
+            "acc_stderr": 0.010472537019822582
+        },
+        "boolq": {
+            "acc": 0.5645259938837921,
+            "acc_stderr": 0.008671927333703594
+        },
+        "arc_easy": {
+            "acc": 0.5997474747474747,
+            "acc_stderr": 0.010053550119896129,
+            "acc_norm": 0.5749158249158249,
+            "acc_norm_stderr": 0.010143966195717845
+        },
+        "arc_challenge": {
+            "acc": 0.2781569965870307,
+            "acc_stderr": 0.013094469919538812,
+            "acc_norm": 0.3037542662116041,
+            "acc_norm_stderr": 0.01343890918477876
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_3_lm-eval_global_step109672_2023-05-15-10-12-47_3shots_backup.json

@@ -0,0 +1,73 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.329,
+            "acc_stderr": 0.014865395385928367
+        },
+        "anli_r2": {
+            "acc": 0.325,
+            "acc_stderr": 0.014818724459095526
+        },
+        "anli_r3": {
+            "acc": 0.3458333333333333,
+            "acc_stderr": 0.013736245342311012
+        },
+        "cb": {
+            "acc": 0.44642857142857145,
+            "acc_stderr": 0.06703189227942398,
+            "f1": 0.3862433862433863
+        },
+        "copa": {
+            "acc": 0.85,
+            "acc_stderr": 0.03588702812826371
+        },
+        "hellaswag": {
+            "acc": 0.4733120892252539,
+            "acc_stderr": 0.004982668452118941,
+            "acc_norm": 0.6216889065923122,
+            "acc_norm_stderr": 0.004839746491523517
+        },
+        "rte": {
+            "acc": 0.516245487364621,
+            "acc_stderr": 0.030080573208738064
+        },
+        "winogrande": {
+            "acc": 0.5785319652722968,
+            "acc_stderr": 0.0138780723774976
+        },
+        "storycloze_2016": {
+            "acc": 0.711918760021379,
+            "acc_stderr": 0.010472537019822582
+        },
+        "boolq": {
+            "acc": 0.5645259938837921,
+            "acc_stderr": 0.008671927333703594
+        },
+        "arc_easy": {
+            "acc": 0.5997474747474747,
+            "acc_stderr": 0.010053550119896129,
+            "acc_norm": 0.5749158249158249,
+            "acc_norm_stderr": 0.010143966195717845
+        },
+        "arc_challenge": {
+            "acc": 0.2781569965870307,
+            "acc_stderr": 0.013094469919538812,
+            "acc_norm": 0.3037542662116041,
+            "acc_norm_stderr": 0.01343890918477876
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1,
+        "arc_easy": 0,
+        "arc_challenge": 0
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_4.json

@@ -0,0 +1,59 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.342,
+            "acc_stderr": 0.015008706182121731
+        },
+        "anli_r2": {
+            "acc": 0.318,
+            "acc_stderr": 0.014734079309311901
+        },
+        "anli_r3": {
+            "acc": 0.3275,
+            "acc_stderr": 0.013553211167251944
+        },
+        "cb": {
+            "acc": 0.4642857142857143,
+            "acc_stderr": 0.0672477765493766,
+            "f1": 0.3282312925170068
+        },
+        "copa": {
+            "acc": 0.8,
+            "acc_stderr": 0.040201512610368445
+        },
+        "hellaswag": {
+            "acc": 0.47161919936267677,
+            "acc_stderr": 0.004981736689518751,
+            "acc_norm": 0.622087233618801,
+            "acc_norm_stderr": 0.004838747305783333
+        },
+        "rte": {
+            "acc": 0.5126353790613718,
+            "acc_stderr": 0.030086851767188564
+        },
+        "winogrande": {
+            "acc": 0.5864246250986582,
+            "acc_stderr": 0.013840971763195306
+        },
+        "storycloze_2016": {
+            "acc": 0.7076429716729022,
+            "acc_stderr": 0.01051823972978774
+        },
+        "boolq": {
+            "acc": 0.5581039755351682,
+            "acc_stderr": 0.008685806399014942
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_4_lm-eval_global_step109672_2023-05-15-10-12-47_4shots_backup.json

@@ -0,0 +1,59 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.342,
+            "acc_stderr": 0.015008706182121731
+        },
+        "anli_r2": {
+            "acc": 0.318,
+            "acc_stderr": 0.014734079309311901
+        },
+        "anli_r3": {
+            "acc": 0.3275,
+            "acc_stderr": 0.013553211167251944
+        },
+        "cb": {
+            "acc": 0.4642857142857143,
+            "acc_stderr": 0.0672477765493766,
+            "f1": 0.3282312925170068
+        },
+        "copa": {
+            "acc": 0.8,
+            "acc_stderr": 0.040201512610368445
+        },
+        "hellaswag": {
+            "acc": 0.47161919936267677,
+            "acc_stderr": 0.004981736689518751,
+            "acc_norm": 0.622087233618801,
+            "acc_norm_stderr": 0.004838747305783333
+        },
+        "rte": {
+            "acc": 0.5126353790613718,
+            "acc_stderr": 0.030086851767188564
+        },
+        "winogrande": {
+            "acc": 0.5864246250986582,
+            "acc_stderr": 0.013840971763195306
+        },
+        "storycloze_2016": {
+            "acc": 0.7076429716729022,
+            "acc_stderr": 0.01051823972978774
+        },
+        "boolq": {
+            "acc": 0.5581039755351682,
+            "acc_stderr": 0.008685806399014942
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0,
+        "boolq": 1
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_5.json

@@ -0,0 +1,54 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.318,
+            "acc_stderr": 0.014734079309311901
+        },
+        "anli_r2": {
+            "acc": 0.322,
+            "acc_stderr": 0.014782913600996662
+        },
+        "anli_r3": {
+            "acc": 0.3525,
+            "acc_stderr": 0.01379716491891836
+        },
+        "cb": {
+            "acc": 0.4642857142857143,
+            "acc_stderr": 0.06724777654937658,
+            "f1": 0.32575201760821715
+        },
+        "copa": {
+            "acc": 0.76,
+            "acc_stderr": 0.04292346959909283
+        },
+        "hellaswag": {
+            "acc": 0.4700258912567218,
+            "acc_stderr": 0.0049808072311367515,
+            "acc_norm": 0.6182035451105358,
+            "acc_norm_stderr": 0.0048483415604921335
+        },
+        "rte": {
+            "acc": 0.5090252707581228,
+            "acc_stderr": 0.030091559826331334
+        },
+        "winogrande": {
+            "acc": 0.5714285714285714,
+            "acc_stderr": 0.013908353814606696
+        },
+        "storycloze_2016": {
+            "acc": 0.7071084981293426,
+            "acc_stderr": 0.010523873293246305
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0
+    }
+}

4b284b12bc4opt4/evaluation/rankeval/4b284b12bc4opt4_5_lm-eval_global_step109672_2023-05-15-10-12-47_5shots_backup.json

@@ -0,0 +1,54 @@
+{
+    "results": {
+        "anli_r1": {
+            "acc": 0.318,
+            "acc_stderr": 0.014734079309311901
+        },
+        "anli_r2": {
+            "acc": 0.322,
+            "acc_stderr": 0.014782913600996662
+        },
+        "anli_r3": {
+            "acc": 0.3525,
+            "acc_stderr": 0.01379716491891836
+        },
+        "cb": {
+            "acc": 0.4642857142857143,
+            "acc_stderr": 0.06724777654937658,
+            "f1": 0.32575201760821715
+        },
+        "copa": {
+            "acc": 0.76,
+            "acc_stderr": 0.04292346959909283
+        },
+        "hellaswag": {
+            "acc": 0.4700258912567218,
+            "acc_stderr": 0.0049808072311367515,
+            "acc_norm": 0.6182035451105358,
+            "acc_norm_stderr": 0.0048483415604921335
+        },
+        "rte": {
+            "acc": 0.5090252707581228,
+            "acc_stderr": 0.030091559826331334
+        },
+        "winogrande": {
+            "acc": 0.5714285714285714,
+            "acc_stderr": 0.013908353814606696
+        },
+        "storycloze_2016": {
+            "acc": 0.7071084981293426,
+            "acc_stderr": 0.010523873293246305
+        }
+    },
+    "versions": {
+        "anli_r1": 0,
+        "anli_r2": 0,
+        "anli_r3": 0,
+        "cb": 1,
+        "copa": 0,
+        "hellaswag": 0,
+        "rte": 0,
+        "winogrande": 0,
+        "storycloze_2016": 0
+    }
+}

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e351a939564871527f6cded6dc4b0b5a90880bdbd18210e3b397f356738cac
+size 144841431

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d86aaa19b5745c2eee7b5eaf907296c3af660dc506229a253c4e7d50f5462b
+size 144841517

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c627d8aa7d8f95f387abcc9dc00ae33933a691e765f13e081ef49d7b979630b6
+size 144841453

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b28411b3f69b7c8746444f22718f486bfe034aaf2df7225ffc54b5a5c7db1b7
+size 144841517

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5866c859b6d1c9bfb0b837c71b6f67c0012caca102fea7880577b314e97c018
+size 144841453

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd10a89dafa7bf3018e8adfed0d93aff4563d140882456ddfd67332cb97b00b7
+size 144841453

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812fa3ed497b16432064603e4f24b77f05ea977419af6300e8f61183eb9fd012
+size 144841389

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a58a5b379206d43b19996d9c1168c23435a9c995e631a838469e8512cd02fba7
+size 144841517

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2242424ab63926bff3f0a1b9d82e520b4bc5820b8d2fadff720a6d21abc32985
+size 144841453

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8c5ba4914469dd60ea5b5cff83783bbe4eb93b702624339475f676437cc361
+size 144841581

4b284b12bc4opt4/global_step109672/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18cb99f24d9b65b8167524863145257df8f99b10b6c84a3f5fbfb1765a36ce7d
+size 144841453