Upload EEE results (en_ru_v3)

eval_results/eee/en_ru_v3_eclektic/eclektic/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/8bf58534-363a-4a5a-a03a-438d304b658c.json

@@ -0,0 +1,98 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "eclektic//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066883.400253",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066883.400253",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "eclektic",
+      "source_data": {
+        "dataset_name": "eclektic",
+        "source_type": "other"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "eclektic_transfer",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.16063188153690164,
+        "uncertainty": {
+          "num_samples": 4608
+        }
+      },
+      "generation_config": {
+        "generation_args": {
+          "temperature": 0.0,
+          "max_tokens": 64,
+          "max_attempts": 1
+        },
+        "additional_details": {
+          "until": "[\"\\n\"]",
+          "do_sample": "false",
+          "num_fewshot": "0"
+        }
+      }
+    },
+    {
+      "evaluation_name": "eclektic",
+      "source_data": {
+        "dataset_name": "eclektic",
+        "source_type": "other"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "eclektic_overall",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.008351972464866946,
+        "uncertainty": {
+          "num_samples": 4608
+        }
+      },
+      "generation_config": {
+        "generation_args": {
+          "temperature": 0.0,
+          "max_tokens": 64,
+          "max_attempts": 1
+        },
+        "additional_details": {
+          "until": "[\"\\n\"]",
+          "do_sample": "false",
+          "num_fewshot": "0"
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_en/global_mmlu_en/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/f96621d5-39ee-447e-a3e1-02eba9be3645.json

@@ -0,0 +1,57 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_en//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066883.748627",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066883.748627",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_en",
+      "source_data": {
+        "dataset_name": "global_mmlu_en",
+        "source_type": "other"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2625,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.021922856738675153,
+            "method": "bootstrap"
+          },
+          "num_samples": 400
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_en/global_mmlu_en_business/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/d5fde65a-960f-4e77-94fd-0a68bddfc758.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_en_business//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066883.748283",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066883.748283",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_en_business",
+      "source_data": {
+        "dataset_name": "global_mmlu_en_business",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereLabs/Global-MMLU-Lite",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2413793103448276,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.05667935960252491,
+            "method": "bootstrap"
+          },
+          "num_samples": 58
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_en/global_mmlu_en_humanities/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/a0a83b44-8159-4177-939d-caf9f0608399.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_en_humanities//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066883.748439",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066883.748439",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_en_humanities",
+      "source_data": {
+        "dataset_name": "global_mmlu_en_humanities",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereLabs/Global-MMLU-Lite",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.30392156862745096,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04576665403207762,
+            "method": "bootstrap"
+          },
+          "num_samples": 102
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_en/global_mmlu_en_medical/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/b52b2544-cd72-41ed-b0ee-1435d8c4da21.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_en_medical//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066883.748493",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066883.748493",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_en_medical",
+      "source_data": {
+        "dataset_name": "global_mmlu_en_medical",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereLabs/Global-MMLU-Lite",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.08333333333333333,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04671765921511567,
+            "method": "bootstrap"
+          },
+          "num_samples": 36
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_en/global_mmlu_en_other/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/5eb7c92f-5c29-4741-b1df-1aaf33f9d477.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_en_other//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066883.748531",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066883.748531",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_en_other",
+      "source_data": {
+        "dataset_name": "global_mmlu_en_other",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereLabs/Global-MMLU-Lite",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.32142857142857145,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.06297362289056344,
+            "method": "bootstrap"
+          },
+          "num_samples": 56
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_en/global_mmlu_en_social_sciences/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/aa212013-a70e-4383-8bec-38b712dac98c.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_en_social_sciences//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066883.748598",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066883.748598",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_en_social_sciences",
+      "source_data": {
+        "dataset_name": "global_mmlu_en_social_sciences",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereLabs/Global-MMLU-Lite",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.28431372549019607,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04488482852329018,
+            "method": "bootstrap"
+          },
+          "num_samples": 102
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_en/global_mmlu_en_stem/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/e8375c77-f578-4282-865b-1fe663e6a5ad.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_en_stem//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066883.748563",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066883.748563",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_en_stem",
+      "source_data": {
+        "dataset_name": "global_mmlu_en_stem",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereLabs/Global-MMLU-Lite",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.21739130434782608,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.06148754619013457,
+            "method": "bootstrap"
+          },
+          "num_samples": 46
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/519bf906-8916-4816-9392-736af017269e.json

@@ -0,0 +1,57 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126599",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126599",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru",
+        "source_type": "other"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.25580401652186296,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.0036789340871963253,
+            "method": "bootstrap"
+          },
+          "num_samples": 14042
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_abstract_algebra/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/eb91f724-83e8-4e59-882e-ad12b2bb4c8f.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_abstract_algebra//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125092",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125092",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_abstract_algebra",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_abstract_algebra",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.24,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04292346959909278,
+            "method": "bootstrap"
+          },
+          "num_samples": 100
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_anatomy/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/ba779820-a094-499b-bd2b-1462778b5016.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_anatomy//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125222",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125222",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_anatomy",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_anatomy",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.22962962962962963,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03633384414073468,
+            "method": "bootstrap"
+          },
+          "num_samples": 135
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_astronomy/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/bfe30c18-654a-4a95-bff8-0d4fc647d8a1.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_astronomy//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125263",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125263",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_astronomy",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_astronomy",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.21710526315789475,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03355045304882925,
+            "method": "bootstrap"
+          },
+          "num_samples": 152
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_business_ethics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/01014c35-5e90-4d00-84f1-b3b6144b80ef.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_business_ethics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125773",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125773",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_business_ethics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_business_ethics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.29,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.045604802157206865,
+            "method": "bootstrap"
+          },
+          "num_samples": 100
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_clinical_knowledge/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/a45aca21-3f1f-45f4-b557-c8a6fccf28f5.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_clinical_knowledge//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125801",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125801",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_clinical_knowledge",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_clinical_knowledge",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2528301886792453,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.026749899771241183,
+            "method": "bootstrap"
+          },
+          "num_samples": 265
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_college_biology/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/9caeef64-abbc-4edc-b469-9139e2f6b928.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_college_biology//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125292",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125292",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_college_biology",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_college_biology",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2916666666666667,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03800968060554863,
+            "method": "bootstrap"
+          },
+          "num_samples": 144
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_college_chemistry/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/4a0a69b1-6165-4e6d-91e1-266428d18059.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_college_chemistry//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125317",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125317",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_college_chemistry",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_college_chemistry",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.22,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.041633319989322654,
+            "method": "bootstrap"
+          },
+          "num_samples": 100
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_college_computer_science/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/a7b45667-d87e-4a34-bc29-31107f362825.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_college_computer_science//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125342",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125342",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_college_computer_science",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_college_computer_science",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.22,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.041633319989322654,
+            "method": "bootstrap"
+          },
+          "num_samples": 100
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_college_mathematics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/c0772644-85de-44d6-9336-47f34f490a9d.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_college_mathematics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125362",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125362",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_college_mathematics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_college_mathematics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.18,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03861229196653691,
+            "method": "bootstrap"
+          },
+          "num_samples": 100
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_college_medicine/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/be675aed-62e4-45e9-9652-48be40bb86b2.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_college_medicine//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.12582",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.12582",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_college_medicine",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_college_medicine",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2832369942196532,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03435568056047877,
+            "method": "bootstrap"
+          },
+          "num_samples": 173
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_college_physics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/eb6df5b1-15e7-46b5-87af-842fd28708ff.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_college_physics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125383",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125383",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_college_physics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_college_physics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.30392156862745096,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04576665403207762,
+            "method": "bootstrap"
+          },
+          "num_samples": 102
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_computer_security/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/e9f9e099-0922-4e3d-8908-0fe1100cba50.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_computer_security//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125403",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125403",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_computer_security",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_computer_security",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.33,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04725815626252609,
+            "method": "bootstrap"
+          },
+          "num_samples": 100
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_conceptual_physics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/455b30d6-75fc-46d0-a25e-f1015077ddcb.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_conceptual_physics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125422",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125422",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_conceptual_physics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_conceptual_physics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.3021276595744681,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03001755447188058,
+            "method": "bootstrap"
+          },
+          "num_samples": 235
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_econometrics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/093fc560-2f38-451a-a966-1eb7c91d1304.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_econometrics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126026",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126026",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_econometrics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_econometrics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.21929824561403508,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.038924311065187546,
+            "method": "bootstrap"
+          },
+          "num_samples": 114
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_electrical_engineering/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/a4972351-882a-4cb6-b367-d2009d18e11c.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_electrical_engineering//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125442",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125442",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_electrical_engineering",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_electrical_engineering",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.20689655172413793,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.033756724495605545,
+            "method": "bootstrap"
+          },
+          "num_samples": 145
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_elementary_mathematics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/8f30d01a-0e44-43f9-a492-b6225dc4cc3b.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_elementary_mathematics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125462",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125462",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_elementary_mathematics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_elementary_mathematics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.24338624338624337,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.022101128787415353,
+            "method": "bootstrap"
+          },
+          "num_samples": 378
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_formal_logic/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/c8748d05-858f-473c-9a20-7826f376fb34.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_formal_logic//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126246",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126246",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_formal_logic",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_formal_logic",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.1984126984126984,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03567016675276862,
+            "method": "bootstrap"
+          },
+          "num_samples": 126
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_global_facts/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/3f0e288b-0a1e-449d-ae2d-405ab6981680.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_global_facts//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.12584",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.12584",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_global_facts",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_global_facts",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.27,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04461960433384737,
+            "method": "bootstrap"
+          },
+          "num_samples": 100
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_biology/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/24a6d532-5ea0-4c9c-b988-18111d276f17.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_biology//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125485",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125485",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_biology",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_biology",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.24193548387096775,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.024362599693031024,
+            "method": "bootstrap"
+          },
+          "num_samples": 310
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_chemistry/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/ec85415c-eda6-44a3-b752-4de4e449211a.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_chemistry//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125503",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125503",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_chemistry",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_chemistry",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2512315270935961,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03051653073269444,
+            "method": "bootstrap"
+          },
+          "num_samples": 203
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_computer_science/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/c25b6784-983b-4c01-894c-0f0769c05e9a.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_computer_science//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125523",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125523",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_computer_science",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_computer_science",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.36,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.048241815132442176,
+            "method": "bootstrap"
+          },
+          "num_samples": 100
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_european_history/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/67e89853-28be-4b7e-acdc-857ad5046857.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_european_history//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126271",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126271",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_european_history",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_european_history",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.296969696969697,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03567969772268046,
+            "method": "bootstrap"
+          },
+          "num_samples": 165
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_geography/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/b6216c05-b321-4a5d-89db-08ead7664185.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_geography//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126044",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126044",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_geography",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_geography",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.20707070707070707,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.02886977846026699,
+            "method": "bootstrap"
+          },
+          "num_samples": 198
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_government_and_politics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/6ace5211-eeda-426f-a84c-b23a2cbbc5fa.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_government_and_politics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126063",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126063",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_government_and_politics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_government_and_politics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.21761658031088082,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.029778663037752975,
+            "method": "bootstrap"
+          },
+          "num_samples": 193
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_macroeconomics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/d2b6973d-38c4-46a3-84d9-c64de0be22f0.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_macroeconomics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126081",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126081",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_macroeconomics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_macroeconomics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2205128205128205,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.021020672680827836,
+            "method": "bootstrap"
+          },
+          "num_samples": 390
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_mathematics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/b85693fc-c128-4412-854b-412c31c10474.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_mathematics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125546",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125546",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_mathematics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_mathematics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.23703703703703705,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.02592887613276605,
+            "method": "bootstrap"
+          },
+          "num_samples": 270
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_microeconomics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/09b3936a-830d-43cb-b1ee-922bf802a2e8.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_microeconomics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126099",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126099",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_microeconomics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_microeconomics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2184873949579832,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.026841514322958934,
+            "method": "bootstrap"
+          },
+          "num_samples": 238
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_physics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/90c631fe-63ce-48fb-8eaf-9c856b1719fb.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_physics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125565",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125565",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_physics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_physics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2251655629139073,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03410435282008936,
+            "method": "bootstrap"
+          },
+          "num_samples": 151
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_psychology/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/47e3256b-67ee-4bfb-8a72-5548aa5660b5.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_psychology//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126116",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126116",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_psychology",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_psychology",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.24587155963302754,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.018461940968708502,
+            "method": "bootstrap"
+          },
+          "num_samples": 545
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_statistics/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/e97b8d91-55c7-45b4-903b-59bb87f5169b.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_statistics//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.12573",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.12573",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_statistics",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_statistics",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2175925925925926,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.028139689444859672,
+            "method": "bootstrap"
+          },
+          "num_samples": 216
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_us_history/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/86c59f4d-9061-4fed-afd8-c2d104299ae0.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_us_history//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126289",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126289",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_us_history",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_us_history",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.23529411764705882,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.029771775228145628,
+            "method": "bootstrap"
+          },
+          "num_samples": 204
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_high_school_world_history/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/78a0a2e3-30c3-419b-96ed-f7e3472568b5.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_high_school_world_history//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.12631",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.12631",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_high_school_world_history",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_high_school_world_history",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.25738396624472576,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.028458820991460302,
+            "method": "bootstrap"
+          },
+          "num_samples": 237
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_human_aging/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1cf51b61-8c75-4c77-89e0-fa0e8660f11a.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_human_aging//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125859",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125859",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_human_aging",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_human_aging",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2556053811659193,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.029275891003969906,
+            "method": "bootstrap"
+          },
+          "num_samples": 223
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_human_sexuality/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/7ad4bd4c-48dc-4dde-a3ad-31eb20144dee.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_human_sexuality//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126135",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126135",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_human_sexuality",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_human_sexuality",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2900763358778626,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03980066246467765,
+            "method": "bootstrap"
+          },
+          "num_samples": 131
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_humanities/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/d8ca1b18-af17-4632-bf5a-6e7d2fc5692e.json

@@ -0,0 +1,57 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_humanities//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126579",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126579",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_humanities",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_humanities",
+        "source_type": "other"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.2686503719447396,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.006452205544379729,
+            "method": "bootstrap"
+          },
+          "num_samples": 4705
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_international_law/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1f71c4c2-9b18-484c-bcd1-f0ed2650f2c8.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_international_law//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126328",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126328",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_international_law",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_international_law",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.4132231404958678,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04495087843548408,
+            "method": "bootstrap"
+          },
+          "num_samples": 121
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_jurisprudence/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/d8ce244e-4ead-4971-bccf-8b6ed668315a.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_jurisprudence//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.126345",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.126345",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_jurisprudence",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_jurisprudence",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.28703703703703703,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04373313040914761,
+            "method": "bootstrap"
+          },
+          "num_samples": 108
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_logical_fallacies/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/2478cfed-af70-4348-8f83-1090812039be.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_logical_fallacies//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.12636",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.12636",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_logical_fallacies",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_logical_fallacies",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.25153374233128833,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.03408997886857529,
+            "method": "bootstrap"
+          },
+          "num_samples": 163
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_machine_learning/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/4032d39a-75e6-4496-bc00-885007d06703.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_machine_learning//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125752",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125752",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_machine_learning",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_machine_learning",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.26785714285714285,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04203277291467762,
+            "method": "bootstrap"
+          },
+          "num_samples": 112
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_management/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/b10bd037-d345-42e4-a91b-ef1f101d774e.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_management//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125877",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125877",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_management",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_management",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.24271844660194175,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.04245022486384496,
+            "method": "bootstrap"
+          },
+          "num_samples": 103
+        }
+      }
+    }
+  ]
+}

eval_results/eee/en_ru_v3_mmlu_ru/global_mmlu_full_ru_marketing/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/421dd010-1a73-4f89-a5c3-f9cbd15e17b2.json

@@ -0,0 +1,59 @@
+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "global_mmlu_full_ru_marketing//gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3/1787066884.125895",
+  "evaluation_timestamp": "1787065862",
+  "retrieved_timestamp": "1787066884.125895",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "unknown",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "id": "/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3",
+    "developer": "",
+    "inference_engine": {
+      "name": "transformers"
+    },
+    "additional_details": {
+      "num_parameters": "6291689472",
+      "dtype": "torch.bfloat16",
+      "revision": "main",
+      "model_args": "{'pretrained': '/gpfs/ess6000-1/proj/dmfexp/trAr/torchtitan-mulitlingual/outputs/hf_export/llama3_7b_en_ru_v3', 'dtype': 'bfloat16'}"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "global_mmlu_full_ru_marketing",
+      "source_data": {
+        "dataset_name": "global_mmlu_full_ru_marketing",
+        "source_type": "hf_dataset",
+        "hf_repo": "CohereForAI/Global-MMLU",
+        "hf_split": "test"
+      },
+      "evaluation_timestamp": "1787065862",
+      "metric_config": {
+        "evaluation_description": "acc",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.24358974358974358,
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.02812096650391442,
+            "method": "bootstrap"
+          },
+          "num_samples": 234
+        }
+      }
+    }
+  ]
+}