Delete files evaluation/ c4_validation.json evaluation.log with huggingface_hub

evaluation/results__hf_ckpts__blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512__/results_2026-03-09T14-06-28.603901.json

@@ -1,609 +0,0 @@
-{
-  "results": {
-    "arc_challenge": {
-      "alias": "arc_challenge",
-      "acc,none": 0.29692832764505117,
-      "acc_stderr,none": 0.013352025976725228,
-      "acc_norm,none": 0.30802047781569963,
-      "acc_norm_stderr,none": 0.01349142951729204
-    },
-    "arc_easy": {
-      "alias": "arc_easy",
-      "acc,none": 0.6296296296296297,
-      "acc_stderr,none": 0.009908978578665757,
-      "acc_norm,none": 0.577020202020202,
-      "acc_norm_stderr,none": 0.010137328382209107
-    },
-    "boolq": {
-      "alias": "boolq",
-      "acc,none": 0.6256880733944954,
-      "acc_stderr,none": 0.008464246656443236
-    },
-    "hellaswag": {
-      "alias": "hellaswag",
-      "acc,none": 0.37422824138617805,
-      "acc_stderr,none": 0.004829339926388328,
-      "acc_norm,none": 0.4738099980083649,
-      "acc_norm_stderr,none": 0.004982931565945946
-    },
-    "lambada_openai": {
-      "alias": "lambada_openai",
-      "perplexity,none": 16.99295013502752,
-      "perplexity_stderr,none": 0.5693576969205276,
-      "acc,none": 0.443042887638269,
-      "acc_stderr,none": 0.0069206332420079265
-    },
-    "lambada_standard": {
-      "alias": "lambada_standard",
-      "perplexity,none": 27.533257711233524,
-      "perplexity_stderr,none": 0.9519324571988527,
-      "acc,none": 0.35532699398408696,
-      "acc_stderr,none": 0.006668004996315348
-    },
-    "piqa": {
-      "alias": "piqa",
-      "acc,none": 0.7023939064200218,
-      "acc_stderr,none": 0.01066735379238821,
-      "acc_norm,none": 0.6980413492927094,
-      "acc_norm_stderr,none": 0.010711732891588352
-    },
-    "social_iqa": {
-      "alias": "social_iqa",
-      "acc,none": 0.40890481064483114,
-      "acc_stderr,none": 0.011124710055682845
-    },
-    "wikitext": {
-      "alias": "wikitext",
-      "word_perplexity,none": 21.603753499994546,
-      "word_perplexity_stderr,none": "N/A",
-      "byte_perplexity,none": 1.7764935452161108,
-      "byte_perplexity_stderr,none": "N/A",
-      "bits_per_byte,none": 0.8290324467318287,
-      "bits_per_byte_stderr,none": "N/A"
-    },
-    "winogrande": {
-      "alias": "winogrande",
-      "acc,none": 0.5493291239147593,
-      "acc_stderr,none": 0.013983928869040235
-    }
-  },
-  "group_subtasks": {
-    "arc_challenge": [],
-    "arc_easy": [],
-    "boolq": [],
-    "hellaswag": [],
-    "lambada_openai": [],
-    "lambada_standard": [],
-    "piqa": [],
-    "social_iqa": [],
-    "wikitext": [],
-    "winogrande": []
-  },
-  "configs": {
-    "arc_challenge": {
-      "task": "arc_challenge",
-      "tag": [
-        "ai2_arc"
-      ],
-      "dataset_path": "allenai/ai2_arc",
-      "dataset_name": "ARC-Challenge",
-      "training_split": "train",
-      "validation_split": "validation",
-      "test_split": "test",
-      "doc_to_text": "Question: {{question}}\nAnswer:",
-      "doc_to_target": "{{choices.label.index(answerKey)}}",
-      "unsafe_code": false,
-      "doc_to_choice": "{{choices.text}}",
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "acc",
-          "aggregation": "mean",
-          "higher_is_better": true
-        },
-        {
-          "metric": "acc_norm",
-          "aggregation": "mean",
-          "higher_is_better": true
-        }
-      ],
-      "output_type": "multiple_choice",
-      "repeats": 1,
-      "should_decontaminate": true,
-      "doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
-      "metadata": {
-        "version": 1.0,
-        "pretrained": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-        "dtype": "bfloat16",
-        "trust_remote_code": true
-      }
-    },
-    "arc_easy": {
-      "task": "arc_easy",
-      "tag": [
-        "ai2_arc"
-      ],
-      "dataset_path": "allenai/ai2_arc",
-      "dataset_name": "ARC-Easy",
-      "training_split": "train",
-      "validation_split": "validation",
-      "test_split": "test",
-      "doc_to_text": "Question: {{question}}\nAnswer:",
-      "doc_to_target": "{{choices.label.index(answerKey)}}",
-      "unsafe_code": false,
-      "doc_to_choice": "{{choices.text}}",
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "acc",
-          "aggregation": "mean",
-          "higher_is_better": true
-        },
-        {
-          "metric": "acc_norm",
-          "aggregation": "mean",
-          "higher_is_better": true
-        }
-      ],
-      "output_type": "multiple_choice",
-      "repeats": 1,
-      "should_decontaminate": true,
-      "doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
-      "metadata": {
-        "version": 1.0,
-        "pretrained": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-        "dtype": "bfloat16",
-        "trust_remote_code": true
-      }
-    },
-    "boolq": {
-      "task": "boolq",
-      "tag": [
-        "super-glue-lm-eval-v1"
-      ],
-      "dataset_path": "super_glue",
-      "dataset_name": "boolq",
-      "training_split": "train",
-      "validation_split": "validation",
-      "doc_to_text": "{{passage}}\nQuestion: {{question}}?\nAnswer:",
-      "doc_to_target": "label",
-      "unsafe_code": false,
-      "doc_to_choice": [
-        "no",
-        "yes"
-      ],
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "acc"
-        }
-      ],
-      "output_type": "multiple_choice",
-      "repeats": 1,
-      "should_decontaminate": true,
-      "doc_to_decontamination_query": "passage",
-      "metadata": {
-        "version": 2.0,
-        "pretrained": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-        "dtype": "bfloat16",
-        "trust_remote_code": true
-      }
-    },
-    "hellaswag": {
-      "task": "hellaswag",
-      "tag": [
-        "multiple_choice"
-      ],
-      "dataset_path": "Rowan/hellaswag",
-      "training_split": "train",
-      "validation_split": "validation",
-      "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n    def _process_doc(doc):\n        ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n        out_doc = {\n            \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n            \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n            \"gold\": int(doc[\"label\"]),\n        }\n        return out_doc\n\n    return dataset.map(_process_doc)\n",
-      "doc_to_text": "{{query}}",
-      "doc_to_target": "{{label}}",
-      "unsafe_code": false,
-      "doc_to_choice": "choices",
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "acc",
-          "aggregation": "mean",
-          "higher_is_better": true
-        },
-        {
-          "metric": "acc_norm",
-          "aggregation": "mean",
-          "higher_is_better": true
-        }
-      ],
-      "output_type": "multiple_choice",
-      "repeats": 1,
-      "should_decontaminate": false,
-      "metadata": {
-        "version": 1.0,
-        "pretrained": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-        "dtype": "bfloat16",
-        "trust_remote_code": true
-      }
-    },
-    "lambada_openai": {
-      "task": "lambada_openai",
-      "tag": [
-        "lambada"
-      ],
-      "dataset_path": "EleutherAI/lambada_openai",
-      "dataset_name": "default",
-      "test_split": "test",
-      "doc_to_text": "{{text.split(' ')[:-1]|join(' ')}}",
-      "doc_to_target": "{{' '+text.split(' ')[-1]}}",
-      "unsafe_code": false,
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "perplexity",
-          "aggregation": "perplexity",
-          "higher_is_better": false
-        },
-        {
-          "metric": "acc",
-          "aggregation": "mean",
-          "higher_is_better": true
-        }
-      ],
-      "output_type": "loglikelihood",
-      "repeats": 1,
-      "should_decontaminate": true,
-      "doc_to_decontamination_query": "{{text}}",
-      "metadata": {
-        "version": 1.0,
-        "pretrained": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-        "dtype": "bfloat16",
-        "trust_remote_code": true
-      }
-    },
-    "lambada_standard": {
-      "task": "lambada_standard",
-      "tag": [
-        "lambada"
-      ],
-      "dataset_path": "lambada",
-      "validation_split": "validation",
-      "test_split": "test",
-      "doc_to_text": "{{text.split(' ')[:-1]|join(' ')}}",
-      "doc_to_target": "{{' '+text.split(' ')[-1]}}",
-      "unsafe_code": false,
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "perplexity",
-          "aggregation": "perplexity",
-          "higher_is_better": false
-        },
-        {
-          "metric": "acc",
-          "aggregation": "mean",
-          "higher_is_better": true
-        }
-      ],
-      "output_type": "loglikelihood",
-      "repeats": 1,
-      "should_decontaminate": true,
-      "doc_to_decontamination_query": "{{text}}",
-      "metadata": {
-        "version": 1.0,
-        "pretrained": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-        "dtype": "bfloat16",
-        "trust_remote_code": true
-      }
-    },
-    "piqa": {
-      "task": "piqa",
-      "dataset_path": "baber/piqa",
-      "training_split": "train",
-      "validation_split": "validation",
-      "doc_to_text": "Question: {{goal}}\nAnswer:",
-      "doc_to_target": "label",
-      "unsafe_code": false,
-      "doc_to_choice": "{{[sol1, sol2]}}",
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "acc",
-          "aggregation": "mean",
-          "higher_is_better": true
-        },
-        {
-          "metric": "acc_norm",
-          "aggregation": "mean",
-          "higher_is_better": true
-        }
-      ],
-      "output_type": "multiple_choice",
-      "repeats": 1,
-      "should_decontaminate": true,
-      "doc_to_decontamination_query": "goal",
-      "metadata": {
-        "version": 1.0,
-        "pretrained": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-        "dtype": "bfloat16",
-        "trust_remote_code": true
-      }
-    },
-    "social_iqa": {
-      "task": "social_iqa",
-      "dataset_path": "social_i_qa",
-      "training_split": "train",
-      "validation_split": "validation",
-      "doc_to_text": "Q: {{context}} {{question}}\nA:",
-      "doc_to_target": "{{ (label|int) - 1 }}",
-      "unsafe_code": false,
-      "doc_to_choice": "{{[answerA, answerB, answerC]}}",
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "acc",
-          "aggregation": "mean",
-          "higher_is_better": true
-        }
-      ],
-      "output_type": "multiple_choice",
-      "repeats": 1,
-      "should_decontaminate": false,
-      "metadata": {
-        "version": 0.0,
-        "pretrained": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-        "dtype": "bfloat16",
-        "trust_remote_code": true
-      }
-    },
-    "wikitext": {
-      "task": "wikitext",
-      "dataset_path": "EleutherAI/wikitext_document_level",
-      "dataset_name": "wikitext-2-raw-v1",
-      "training_split": "train",
-      "validation_split": "validation",
-      "test_split": "test",
-      "doc_to_text": "",
-      "doc_to_target": "def wikitext_detokenizer(doc):\n    string = doc[\"page\"]\n    # contractions\n    string = string.replace(\"s '\", \"s'\")\n    string = re.sub(r\"/' [0-9]/\", r\"/'[0-9]/\", string)\n    # number separators\n    string = string.replace(\" @-@ \", \"-\")\n    string = string.replace(\" @,@ \", \",\")\n    string = string.replace(\" @.@ \", \".\")\n    # punctuation\n    string = string.replace(\" : \", \": \")\n    string = string.replace(\" ; \", \"; \")\n    string = string.replace(\" . \", \". \")\n    string = string.replace(\" ! \", \"! \")\n    string = string.replace(\" ? \", \"? \")\n    string = string.replace(\" , \", \", \")\n    # double brackets\n    string = re.sub(r\"\\(\\s*([^\\)]*?)\\s*\\)\", r\"(\\1)\", string)\n    string = re.sub(r\"\\[\\s*([^\\]]*?)\\s*\\]\", r\"[\\1]\", string)\n    string = re.sub(r\"{\\s*([^}]*?)\\s*}\", r\"{\\1}\", string)\n    string = re.sub(r\"\\\"\\s*([^\\\"]*?)\\s*\\\"\", r'\"\\1\"', string)\n    string = re.sub(r\"'\\s*([^']*?)\\s*'\", r\"'\\1'\", string)\n    # miscellaneous\n    string = string.replace(\"= = = =\", \"====\")\n    string = string.replace(\"= = =\", \"===\")\n    string = string.replace(\"= =\", \"==\")\n    string = string.replace(\" \" + chr(176) + \" \", chr(176))\n    string = string.replace(\" \\n\", \"\\n\")\n    string = string.replace(\"\\n \", \"\\n\")\n    string = string.replace(\" N \", \" 1 \")\n    string = string.replace(\" 's\", \"'s\")\n\n    return string\n",
-      "unsafe_code": false,
-      "process_results": "def process_results(doc, results):\n    (loglikelihood,) = results\n    # IMPORTANT: wikitext counts number of words in *original doc before detokenization*\n    _words = len(re.split(r\"\\s+\", doc[\"page\"]))\n    _bytes = len(doc[\"page\"].encode(\"utf-8\"))\n    return {\n        \"word_perplexity\": (loglikelihood, _words),\n        \"byte_perplexity\": (loglikelihood, _bytes),\n        \"bits_per_byte\": (loglikelihood, _bytes),\n    }\n",
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "word_perplexity"
-        },
-        {
-          "metric": "byte_perplexity"
-        },
-        {
-          "metric": "bits_per_byte"
-        }
-      ],
-      "output_type": "loglikelihood_rolling",
-      "repeats": 1,
-      "should_decontaminate": true,
-      "doc_to_decontamination_query": "{{page}}",
-      "metadata": {
-        "version": 2.0,
-        "pretrained": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-        "dtype": "bfloat16",
-        "trust_remote_code": true
-      }
-    },
-    "winogrande": {
-      "task": "winogrande",
-      "dataset_path": "winogrande",
-      "dataset_name": "winogrande_xl",
-      "training_split": "train",
-      "validation_split": "validation",
-      "doc_to_text": "def doc_to_text(doc):\n    answer_to_num = {\"1\": 0, \"2\": 1}\n    return answer_to_num[doc[\"answer\"]]\n",
-      "doc_to_target": "def doc_to_target(doc):\n    idx = doc[\"sentence\"].index(\"_\") + 1\n    return doc[\"sentence\"][idx:].strip()\n",
-      "unsafe_code": false,
-      "doc_to_choice": "def doc_to_choice(doc):\n    idx = doc[\"sentence\"].index(\"_\")\n    options = [doc[\"option1\"], doc[\"option2\"]]\n    return [doc[\"sentence\"][:idx] + opt for opt in options]\n",
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "acc",
-          "aggregation": "mean",
-          "higher_is_better": true
-        }
-      ],
-      "output_type": "multiple_choice",
-      "repeats": 1,
-      "should_decontaminate": true,
-      "doc_to_decontamination_query": "sentence",
-      "metadata": {
-        "version": 1.0,
-        "pretrained": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-        "dtype": "bfloat16",
-        "trust_remote_code": true
-      }
-    }
-  },
-  "versions": {
-    "arc_challenge": 1.0,
-    "arc_easy": 1.0,
-    "boolq": 2.0,
-    "hellaswag": 1.0,
-    "lambada_openai": 1.0,
-    "lambada_standard": 1.0,
-    "piqa": 1.0,
-    "social_iqa": 0.0,
-    "wikitext": 2.0,
-    "winogrande": 1.0
-  },
-  "n-shot": {
-    "arc_challenge": 0,
-    "arc_easy": 0,
-    "boolq": 0,
-    "hellaswag": 0,
-    "lambada_openai": 0,
-    "lambada_standard": 0,
-    "piqa": 0,
-    "social_iqa": 0,
-    "wikitext": 0,
-    "winogrande": 0
-  },
-  "higher_is_better": {
-    "arc_challenge": {
-      "acc": true,
-      "acc_norm": true
-    },
-    "arc_easy": {
-      "acc": true,
-      "acc_norm": true
-    },
-    "boolq": {
-      "acc": true
-    },
-    "hellaswag": {
-      "acc": true,
-      "acc_norm": true
-    },
-    "lambada_openai": {
-      "perplexity": false,
-      "acc": true
-    },
-    "lambada_standard": {
-      "perplexity": false,
-      "acc": true
-    },
-    "piqa": {
-      "acc": true,
-      "acc_norm": true
-    },
-    "social_iqa": {
-      "acc": true
-    },
-    "wikitext": {
-      "word_perplexity": false,
-      "byte_perplexity": false,
-      "bits_per_byte": false
-    },
-    "winogrande": {
-      "acc": true
-    }
-  },
-  "n-samples": {
-    "winogrande": {
-      "original": 1267,
-      "effective": 1267
-    },
-    "wikitext": {
-      "original": 62,
-      "effective": 62
-    },
-    "social_iqa": {
-      "original": 1954,
-      "effective": 1954
-    },
-    "piqa": {
-      "original": 1838,
-      "effective": 1838
-    },
-    "lambada_standard": {
-      "original": 5153,
-      "effective": 5153
-    },
-    "lambada_openai": {
-      "original": 5153,
-      "effective": 5153
-    },
-    "hellaswag": {
-      "original": 10042,
-      "effective": 10042
-    },
-    "boolq": {
-      "original": 3270,
-      "effective": 3270
-    },
-    "arc_easy": {
-      "original": 2376,
-      "effective": 2376
-    },
-    "arc_challenge": {
-      "original": 1172,
-      "effective": 1172
-    }
-  },
-  "config": {
-    "model": "hf",
-    "model_args": "pretrained=results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/,dtype=bfloat16,trust_remote_code=True,trust_remote_code=True",
-    "model_num_parameters": 1450770714,
-    "model_dtype": "torch.bfloat16",
-    "model_revision": "main",
-    "model_sha": "",
-    "batch_size": "8",
-    "batch_sizes": [],
-    "device": "cuda:0",
-    "use_cache": null,
-    "limit": null,
-    "bootstrap_iters": 100000,
-    "gen_kwargs": null,
-    "random_seed": 0,
-    "numpy_seed": 1234,
-    "torch_seed": 1234,
-    "fewshot_seed": 1234
-  },
-  "git_hash": "core_v0.12.0-135-g7f33517",
-  "date": 1773035718.973999,
-  "pretty_env_info": "PyTorch version: 2.6.0+cu124\nIs debug build: False\nCUDA used to build PyTorch: 12.4\nROCM used to build PyTorch: N/A\n\nOS: CentOS Linux 7 (Core) (x86_64)\nGCC version: (conda-forge gcc 9.5.0-19) 9.5.0\nClang version: Could not collect\nCMake version: version 3.30.1\nLibc version: glibc-2.17\n\nPython version: 3.10.14 (main, May  6 2024, 19:42:50) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-3.10.0-1160.el7.x86_64-x86_64-with-glibc2.17\nIs CUDA available: True\nCUDA runtime version: 12.4.131\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A800-SXM4-80GB\nGPU 1: NVIDIA A800-SXM4-80GB\nGPU 2: NVIDIA A800-SXM4-80GB\nGPU 3: NVIDIA A800-SXM4-80GB\nGPU 4: NVIDIA A800-SXM4-80GB\nGPU 5: NVIDIA A800-SXM4-80GB\nGPU 6: NVIDIA A800-SXM4-80GB\nGPU 7: NVIDIA A800-SXM4-80GB\n\nNvidia driver version: 535.183.06\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:          x86_64\nCPU op-mode(s):        32-bit, 64-bit\nByte Order:            Little Endian\nCPU(s):                104\nOn-line CPU(s) list:   0-103\nThread(s) per core:    1\nCore(s) per socket:    52\nSocket(s):             2\nNUMA node(s):          2\nVendor ID:             GenuineIntel\nCPU family:            6\nModel:                 143\nModel name:            Intel(R) Xeon(R) Platinum 8470\nStepping:              8\nCPU MHz:               800.048\nCPU max MHz:           3800.0000\nCPU min MHz:           800.0000\nBogoMIPS:              4000.00\nVirtualization:        VT-x\nL1d cache:             48K\nL1i cache:             32K\nL2 cache:              2048K\nL3 cache:              107520K\nNUMA node0 CPU(s):     0-51\nNUMA node1 CPU(s):     52-103\nFlags:                 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_pt cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq cldemote movdiri movdir64b md_clear pconfig spec_ctrl intel_stibp flush_l1d arch_capabilities\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] nvidia-cublas-cu12==12.4.5.8\n[pip3] nvidia-cuda-cupti-cu12==12.4.127\n[pip3] nvidia-cuda-nvrtc-cu12==12.4.127\n[pip3] nvidia-cuda-runtime-cu12==12.4.127\n[pip3] nvidia-cudnn-cu12==9.1.0.70\n[pip3] nvidia-cufft-cu12==11.2.1.3\n[pip3] nvidia-curand-cu12==10.3.5.147\n[pip3] nvidia-cusolver-cu12==11.6.1.9\n[pip3] nvidia-cusparse-cu12==12.3.1.170\n[pip3] nvidia-cusparselt-cu12==0.6.2\n[pip3] nvidia-nccl-cu11==2.21.5\n[pip3] nvidia-nccl-cu12==2.21.5\n[pip3] nvidia-nvjitlink-cu12==12.4.127\n[pip3] nvidia-nvtx-cu12==12.4.127\n[pip3] torch==2.6.0\n[pip3] torchaudio==2.6.0\n[pip3] torchdata==0.11.0\n[pip3] torchvision==0.21.0\n[pip3] triton==3.2.0\n[conda] cuda-cudart               12.4.99              hd3aeb46_0    conda-forge\n[conda] cuda-cudart_linux-64      12.4.99              h59595ed_0    conda-forge\n[conda] cuda-cupti                12.4.127             he02047a_2    conda-forge\n[conda] cuda-libraries            12.4.0               ha770c72_0    conda-forge\n[conda] cuda-nvrtc                12.4.99              hd3aeb46_0    conda-forge\n[conda] cuda-nvtx                 12.4.127             he02047a_2    conda-forge\n[conda] cuda-opencl               12.4.99              h59595ed_0    conda-forge\n[conda] cuda-runtime              12.4.0               ha804496_0    conda-forge\n[conda] ffmpeg                    4.3                  hf484d3e_0    pytorch\n[conda] libcublas                 12.4.2.65            hd3aeb46_0    conda-forge\n[conda] libcufft                  11.2.0.44            hd3aeb46_0    conda-forge\n[conda] libcurand                 10.3.5.119           hd3aeb46_0    conda-forge\n[conda] libcusolver               11.6.0.99            hd3aeb46_0    conda-forge\n[conda] libcusparse               12.3.0.142           hd3aeb46_0    conda-forge\n[conda] libjpeg-turbo             2.0.0                h9bf148f_0    pytorch\n[conda] libnvjitlink              12.4.99              hd3aeb46_0    conda-forge\n[conda] mkl                       2023.1.0         h213fc3f_46344    defaults\n[conda] numpy                     1.26.4                   pypi_0    pypi\n[conda] nvidia-cublas-cu12        12.4.5.8                 pypi_0    pypi\n[conda] nvidia-cuda-cupti-cu12    12.4.127                 pypi_0    pypi\n[conda] nvidia-cuda-nvrtc-cu12    12.4.127                 pypi_0    pypi\n[conda] nvidia-cuda-runtime-cu12  12.4.127                 pypi_0    pypi\n[conda] nvidia-cudnn-cu12         9.1.0.70                 pypi_0    pypi\n[conda] nvidia-cufft-cu12         11.2.1.3                 pypi_0    pypi\n[conda] nvidia-curand-cu12        10.3.5.147               pypi_0    pypi\n[conda] nvidia-cusolver-cu12      11.6.1.9                 pypi_0    pypi\n[conda] nvidia-cusparse-cu12      12.3.1.170               pypi_0    pypi\n[conda] nvidia-cusparselt-cu12    0.6.2                    pypi_0    pypi\n[conda] nvidia-nccl-cu11          2.21.5                   pypi_0    pypi\n[conda] nvidia-nccl-cu12          2.21.5                   pypi_0    pypi\n[conda] nvidia-nvjitlink-cu12     12.4.127                 pypi_0    pypi\n[conda] nvidia-nvtx-cu12          12.4.127                 pypi_0    pypi\n[conda] pytorch-cuda              12.4                 hc786d27_6    pytorch\n[conda] pytorch-mutex             1.0                        cuda    pytorch\n[conda] torch                     2.6.0                    pypi_0    pypi\n[conda] torchaudio                2.6.0                    pypi_0    pypi\n[conda] torchdata                 0.11.0                   pypi_0    pypi\n[conda] torchvision               0.21.0                   pypi_0    pypi\n[conda] triton                    3.2.0                    pypi_0    pypi",
-  "transformers_version": "4.55.2",
-  "lm_eval_version": "0.4.9.1",
-  "upper_git_hash": null,
-  "tokenizer_pad_token": [
-    "<unk>",
-    "0"
-  ],
-  "tokenizer_eos_token": [
-    "<|im_end|>",
-    "73440"
-  ],
-  "tokenizer_bos_token": [
-    "<s>",
-    "1"
-  ],
-  "eot_token_id": 73440,
-  "max_length": 4096,
-  "task_hashes": {},
-  "model_source": "hf",
-  "model_name": "results/hf_ckpts/blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512/",
-  "model_name_sanitized": "results__hf_ckpts__blockffn_12b_mul1001_withmean_d64_s128_lr654e4_b512__",
-  "system_instruction": null,
-  "system_instruction_sha": null,
-  "fewshot_as_multiturn": false,
-  "chat_template": null,
-  "chat_template_sha": null,
-  "start_time": 11591492.163990611,
-  "end_time": 11592289.97671808,
-  "total_evaluation_time_seconds": "797.8127274680883"
-}