Create results.json

results.json

@@ -0,0 +1,314 @@
+{
+  "results": {
+    "arc_challenge": {
+      "acc,none": 0.22525597269624573,
+      "acc_stderr,none": 0.0122078399954073,
+      "acc_norm,none": 0.22781569965870307,
+      "acc_norm_stderr,none": 0.012256708602326907
+    },
+    "arc_easy": {
+      "acc,none": 0.255050505050505,
+      "acc_stderr,none": 0.008944265906130731,
+      "acc_norm,none": 0.25673400673400676,
+      "acc_norm_stderr,none": 0.008963590834042407
+    },
+    "lambada_openai": {
+      "perplexity,none": NaN,
+      "perplexity_stderr,none": NaN,
+      "acc,none": 0.0015524936929943722,
+      "acc_stderr,none": 0.0005485163954600048
+    },
+    "logiqa": {
+      "acc,none": 0.20276497695852536,
+      "acc_stderr,none": 0.015770046635584564,
+      "acc_norm,none": 0.20276497695852536,
+      "acc_norm_stderr,none": 0.015770046635584564
+    },
+    "piqa": {
+      "acc,none": 0.49455930359085964,
+      "acc_stderr,none": 0.011665133500637066,
+      "acc_norm,none": 0.4923830250272035,
+      "acc_norm_stderr,none": 0.011664470424044978
+    },
+    "sciq": {
+      "acc,none": 0.014,
+      "acc_stderr,none": 0.0037172325482565773,
+      "acc_norm,none": 0.014,
+      "acc_norm_stderr,none": 0.003717232548256575
+    },
+    "winogrande": {
+      "acc,none": 0.5035516969218626,
+      "acc_stderr,none": 0.014052131146915857
+    },
+    "wsc": {
+      "acc,none": 0.6346153846153846,
+      "acc_stderr,none": 0.0474473339327792
+    }
+  },
+  "configs": {
+    "arc_challenge": {
+      "task": "arc_challenge",
+      "group": [
+        "ai2_arc"
+      ],
+      "dataset_path": "ai2_arc",
+      "dataset_name": "ARC-Challenge",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "Question: {{question}}\nAnswer:",
+      "doc_to_target": "{{choices.label.index(answerKey)}}",
+      "doc_to_choice": "{{choices.text}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "Question: {{question}}\nAnswer:"
+    },
+    "arc_easy": {
+      "task": "arc_easy",
+      "group": [
+        "ai2_arc"
+      ],
+      "dataset_path": "ai2_arc",
+      "dataset_name": "ARC-Easy",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "Question: {{question}}\nAnswer:",
+      "doc_to_target": "{{choices.label.index(answerKey)}}",
+      "doc_to_choice": "{{choices.text}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "Question: {{question}}\nAnswer:"
+    },
+    "lambada_openai": {
+      "task": "lambada_openai",
+      "group": [
+        "lambada"
+      ],
+      "dataset_path": "EleutherAI/lambada_openai",
+      "dataset_name": "default",
+      "test_split": "test",
+      "doc_to_text": "{{text.split(' ')[:-1]|join(' ')}}",
+      "doc_to_target": "{{' '+text.split(' ')[-1]}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "perplexity",
+          "aggregation": "perplexity",
+          "higher_is_better": false
+        },
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "loglikelihood",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "{{text}}"
+    },
+    "logiqa": {
+      "task": "logiqa",
+      "dataset_path": "EleutherAI/logiqa",
+      "dataset_name": "logiqa",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "<function doc_to_text at 0x7f015d114d30>",
+      "doc_to_target": "<function doc_to_target at 0x7f015d115090>",
+      "doc_to_choice": "{{options}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "{{context}}"
+    },
+    "piqa": {
+      "task": "piqa",
+      "dataset_path": "piqa",
+      "training_split": "train",
+      "validation_split": "validation",
+      "doc_to_text": "Question: {{goal}}\nAnswer:",
+      "doc_to_target": "label",
+      "doc_to_choice": "{{[sol1, sol2]}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "goal"
+    },
+    "sciq": {
+      "task": "sciq",
+      "dataset_path": "sciq",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "{{support.lstrip()}}\nQuestion: {{question}}\nAnswer:",
+      "doc_to_target": 3,
+      "doc_to_choice": "{{[distractor1, distractor2, distractor3, correct_answer]}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "{{support}} {{question}}"
+    },
+    "winogrande": {
+      "task": "winogrande",
+      "dataset_path": "winogrande",
+      "dataset_name": "winogrande_xl",
+      "training_split": "train",
+      "validation_split": "validation",
+      "doc_to_text": "<function doc_to_text at 0x7f015cf88f70>",
+      "doc_to_target": "<function doc_to_target at 0x7f015cf892d0>",
+      "doc_to_choice": "<function doc_to_choice at 0x7f015cf89630>",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "sentence"
+    },
+    "wsc": {
+      "task": "wsc",
+      "group": [
+        "super-glue-lm-eval-v1"
+      ],
+      "dataset_path": "super_glue",
+      "dataset_name": "wsc.fixed",
+      "training_split": "train",
+      "validation_split": "validation",
+      "doc_to_text": "<function default_doc_to_text at 0x7f015d0149d0>",
+      "doc_to_target": "label",
+      "doc_to_choice": [
+        "no",
+        "yes"
+      ],
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc"
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false
+    }
+  },
+  "versions": {
+    "arc_challenge": "Yaml",
+    "arc_easy": "Yaml",
+    "lambada_openai": "Yaml",
+    "logiqa": "Yaml",
+    "piqa": "Yaml",
+    "sciq": "Yaml",
+    "winogrande": "Yaml",
+    "wsc": "Yaml"
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=usvsnsp/pythia-70m-ppo",
+    "batch_size": 1,
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": ""
+  },
+  "git_hash": "b8d7d6c3"
+}