Create results.json

results.json

@@ -0,0 +1,314 @@
+{
+  "results": {
+    "arc_challenge": {
+      "acc,none": 0.22013651877133106,
+      "acc_stderr,none": 0.01210812488346098,
+      "acc_norm,none": 0.2568259385665529,
+      "acc_norm_stderr,none": 0.0127669237941168
+    },
+    "arc_easy": {
+      "acc,none": 0.5252525252525253,
+      "acc_stderr,none": 0.010246690042583849,
+      "acc_norm,none": 0.45580808080808083,
+      "acc_norm_stderr,none": 0.010219631763437851
+    },
+    "lambada_openai": {
+      "perplexity,none": 11.376566145729152,
+      "perplexity_stderr,none": 0.3623243347217423,
+      "acc,none": 0.48437803221424414,
+      "acc_stderr,none": 0.006962576790761946
+    },
+    "logiqa": {
+      "acc,none": 0.2119815668202765,
+      "acc_stderr,none": 0.01603099796061941,
+      "acc_norm,none": 0.2780337941628264,
+      "acc_norm_stderr,none": 0.01757318777028271
+    },
+    "piqa": {
+      "acc,none": 0.6817192600652884,
+      "acc_stderr,none": 0.010868093932082235,
+      "acc_norm,none": 0.6828073993471164,
+      "acc_norm_stderr,none": 0.01085815545438087
+    },
+    "sciq": {
+      "acc,none": 0.813,
+      "acc_stderr,none": 0.012336254828074133,
+      "acc_norm,none": 0.709,
+      "acc_norm_stderr,none": 0.014370995982377928
+    },
+    "winogrande": {
+      "acc,none": 0.5374901341752171,
+      "acc_stderr,none": 0.01401292818333658
+    },
+    "wsc": {
+      "acc,none": 0.36538461538461536,
+      "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 0x7ff737db4d30>",
+      "doc_to_target": "<function doc_to_target at 0x7ff737db5090>",
+      "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 0x7ff737c28f70>",
+      "doc_to_target": "<function doc_to_target at 0x7ff737c292d0>",
+      "doc_to_choice": "<function doc_to_choice at 0x7ff737c29630>",
+      "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 0x7ff737cb09d0>",
+      "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-410m-ppo,dtype=float16",
+    "batch_size": 1,
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": ""
+  },
+  "git_hash": "b8d7d6c3"
+}