pankajmathur
/

orca_mini_v6_8b

@@ -1,135 +0,0 @@
-{
-  "results": {
-    "leaderboard_ifeval": {
-      "alias": "leaderboard_ifeval",
-      "prompt_level_strict_acc,none": 0.32532347504621073,
-      "prompt_level_strict_acc_stderr,none": 0.020160839912603118,
-      "inst_level_strict_acc,none": 0.4580335731414868,
-      "inst_level_strict_acc_stderr,none": "N/A",
-      "prompt_level_loose_acc,none": 0.3807763401109057,
-      "prompt_level_loose_acc_stderr,none": 0.020895937888190833,
-      "inst_level_loose_acc,none": 0.5059952038369304,
-      "inst_level_loose_acc_stderr,none": "N/A"
-    }
-  },
-  "group_subtasks": {
-    "leaderboard_ifeval": []
-  },
-  "configs": {
-    "leaderboard_ifeval": {
-      "task": "leaderboard_ifeval",
-      "dataset_path": "wis-k/instruction-following-eval",
-      "test_split": "train",
-      "doc_to_text": "prompt",
-      "doc_to_target": 0,
-      "process_results": "def process_results(doc, results):\n    inp = InputExample(\n        key=doc[\"key\"],\n        instruction_id_list=doc[\"instruction_id_list\"],\n        prompt=doc[\"prompt\"],\n        kwargs=doc[\"kwargs\"],\n    )\n    response = results[0]\n\n    out_strict = test_instruction_following_strict(inp, response)\n    out_loose = test_instruction_following_loose(inp, response)\n\n    return {\n        \"prompt_level_strict_acc\": out_strict.follow_all_instructions,\n        \"inst_level_strict_acc\": out_strict.follow_instruction_list,\n        \"prompt_level_loose_acc\": out_loose.follow_all_instructions,\n        \"inst_level_loose_acc\": out_loose.follow_instruction_list,\n    }\n",
-      "description": "",
-      "target_delimiter": " ",
-      "fewshot_delimiter": "\n\n",
-      "fewshot_config": {
-        "sampler": "first_n"
-      },
-      "num_fewshot": 0,
-      "metric_list": [
-        {
-          "metric": "prompt_level_strict_acc",
-          "aggregation": "mean",
-          "higher_is_better": true
-        },
-        {
-          "metric": "inst_level_strict_acc",
-          "aggregation": "def agg_inst_level_acc(items):\n    flat_items = [item for sublist in items for item in sublist]\n    inst_level_acc = sum(flat_items) / len(flat_items)\n    return inst_level_acc\n",
-          "higher_is_better": true
-        },
-        {
-          "metric": "prompt_level_loose_acc",
-          "aggregation": "mean",
-          "higher_is_better": true
-        },
-        {
-          "metric": "inst_level_loose_acc",
-          "aggregation": "def agg_inst_level_acc(items):\n    flat_items = [item for sublist in items for item in sublist]\n    inst_level_acc = sum(flat_items) / len(flat_items)\n    return inst_level_acc\n",
-          "higher_is_better": true
-        }
-      ],
-      "output_type": "generate_until",
-      "generation_kwargs": {
-        "until": [],
-        "do_sample": false,
-        "temperature": 0.0,
-        "max_gen_toks": 1280
-      },
-      "repeats": 1,
-      "should_decontaminate": false,
-      "metadata": {
-        "version": 2.0
-      }
-    }
-  },
-  "versions": {
-    "leaderboard_ifeval": 2.0
-  },
-  "n-shot": {
-    "leaderboard_ifeval": 0
-  },
-  "higher_is_better": {
-    "leaderboard_ifeval": {
-      "prompt_level_strict_acc": true,
-      "inst_level_strict_acc": true,
-      "prompt_level_loose_acc": true,
-      "inst_level_loose_acc": true
-    }
-  },
-  "n-samples": {
-    "leaderboard_ifeval": {
-      "original": 541,
-      "effective": 541
-    }
-  },
-  "config": {
-    "model": "hf",
-    "model_args": "pretrained=pankajmathur/orca_mini_v6_8b,dtype=bfloat16",
-    "batch_size": "auto",
-    "batch_sizes": [],
-    "device": "cuda:0",
-    "use_cache": "cache_pankajmathur/orca_mini_v6_8b/leaderboard_ifeval",
-    "limit": null,
-    "bootstrap_iters": 100000,
-    "gen_kwargs": null,
-    "random_seed": 0,
-    "numpy_seed": 1234,
-    "torch_seed": 1234,
-    "fewshot_seed": 1234
-  },
-  "git_hash": "773209c",
-  "date": 1720548070.8930266,
-  "pretty_env_info": "PyTorch version: 2.2.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.4 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: Could not collect\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-60-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: GPU 0: NVIDIA A100-SXM4-80GB\nNvidia driver version: 535.104.05\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\nAddress sizes:                   48 bits physical, 48 bits virtual\nByte Order:                      Little Endian\nCPU(s):                          256\nOn-line CPU(s) list:             0-255\nVendor ID:                       AuthenticAMD\nModel name:                      AMD EPYC 7763 64-Core Processor\nCPU family:                      25\nModel:                           1\nThread(s) per core:              2\nCore(s) per socket:              64\nSocket(s):                       2\nStepping:                        1\nFrequency boost:                 enabled\nCPU max MHz:                     3529.0520\nCPU min MHz:                     1500.0000\nBogoMIPS:                        4900.18\nFlags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca\nVirtualization:                  AMD-V\nL1d cache:                       4 MiB (128 instances)\nL1i cache:                       4 MiB (128 instances)\nL2 cache:                        64 MiB (128 instances)\nL3 cache:                        512 MiB (16 instances)\nNUMA node(s):                    8\nNUMA node0 CPU(s):               0-15,128-143\nNUMA node1 CPU(s):               16-31,144-159\nNUMA node2 CPU(s):               32-47,160-175\nNUMA node3 CPU(s):               48-63,176-191\nNUMA node4 CPU(s):               64-79,192-207\nNUMA node5 CPU(s):               80-95,208-223\nNUMA node6 CPU(s):               96-111,224-239\nNUMA node7 CPU(s):               112-127,240-255\nVulnerability Itlb multihit:     Not affected\nVulnerability L1tf:              Not affected\nVulnerability Mds:               Not affected\nVulnerability Meltdown:          Not affected\nVulnerability Mmio stale data:   Not affected\nVulnerability Retbleed:          Not affected\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:        Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:             Not affected\nVulnerability Tsx async abort:   Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.3\n[pip3] torch==2.2.0\n[pip3] torchaudio==2.2.0\n[pip3] torchvision==0.17.0\n[pip3] triton==2.2.0\n[conda] Could not collect",
-  "transformers_version": "4.42.3",
-  "upper_git_hash": "be01651cf6b611c09f088c336db74ea625227716",
-  "tokenizer_pad_token": [
-    "<|end_of_text|>",
-    "128001"
-  ],
-  "tokenizer_eos_token": [
-    "<|im_end|>",
-    "128256"
-  ],
-  "tokenizer_bos_token": [
-    "<|begin_of_text|>",
-    "128000"
-  ],
-  "eot_token_id": 128256,
-  "max_length": 8192,
-  "task_hashes": {},
-  "model_source": "hf",
-  "model_name": "pankajmathur/orca_mini_v6_8b",
-  "model_name_sanitized": "pankajmathur__orca_mini_v6_8b",
-  "system_instruction": null,
-  "system_instruction_sha": null,
-  "fewshot_as_multiturn": false,
-  "chat_template": null,
-  "chat_template_sha": null,
-  "start_time": 25395358.46866597,
-  "end_time": 25397357.615242016,
-  "total_evaluation_time_seconds": "1999.1465760469437"
-}