Upload results_2025-06-03T14-01-59.075185.json with huggingface_hub

results_2025-06-03T14-01-59.075185.json

@@ -0,0 +1,129 @@
+{
+  "results": {
+    "eq_bench": {
+      "alias": "eq_bench",
+      "eqbench,none": 81.31602651147857,
+      "eqbench_stderr,none": 4.502809805647872,
+      "percent_parseable,none": 100.0,
+      "percent_parseable_stderr,none": 0.0
+    }
+  },
+  "group_subtasks": {
+    "eq_bench": []
+  },
+  "configs": {
+    "eq_bench": {
+      "task": "eq_bench",
+      "dataset_path": "pbevan11/EQ-Bench",
+      "validation_split": "validation",
+      "doc_to_text": "prompt",
+      "doc_to_target": "reference_answer_fullscale",
+      "unsafe_code": false,
+      "process_results": "def calculate_score_fullscale(docs, results):\n    reference = eval(docs[\"reference_answer_fullscale\"])\n    user = dict(re.findall(r\"(\\w+):\\s+(\\d+)\", results[0]))\n    # First check that the emotions specified in the answer match those in the reference\n    if len(user.items()) != 4:\n        # print('! Error: 4 emotions were not returned')\n        # print(user)\n        return {\"eqbench\": 0, \"percent_parseable\": 0}\n    emotions_dict = {}\n    for emotion, user_emotion_score in user.items():\n        for i in range(1, 5):\n            if emotion == reference[f\"emotion{i}\"]:\n                emotions_dict[emotion] = True\n    if len(emotions_dict) != 4:\n        print(\"! Error: emotions did not match reference\")\n        print(user)\n        return {\"eqbench\": 0, \"percent_parseable\": 0}\n\n    difference_tally = (\n        0  # Tally of differerence from reference answers for this question\n    )\n\n    # Iterate over each emotion in the user's answers.\n    for emotion, user_emotion_score in user.items():\n        # If this emotion is in the reference, calculate the difference between the user's score and the reference score.\n        for i in range(1, 5):\n            if emotion == reference[f\"emotion{i}\"]:\n                d = abs(\n                    float(user_emotion_score) - float(reference[f\"emotion{i}_score\"])\n                )\n                # this will be a value between 0 and 10\n                if d == 0:\n                    scaled_difference = 0\n                elif d <= 5:\n                    # S-shaped scaling function\n                    # https://www.desmos.com/calculator\n                    # 6.5\\cdot\\ \\frac{1}{\\left(1\\ +\\ e^{\\left(-1.2\\cdot\\left(x-4\\right)\\right)}\\right)}\n                    scaled_difference = 6.5 * (1 / (1 + math.e ** (-1.2 * (d - 4))))\n\n                else:\n                    scaled_difference = d\n                difference_tally += scaled_difference\n\n    # Inverting the difference tally so that the closer the answer is to reference, the higher the score.\n    # The adjustment constant is chosen such that answering randomly produces a score of zero.\n    adjust_const = 0.7477\n    final_score = 10 - (difference_tally * adjust_const)\n    final_score_percent = final_score * 10\n\n    return {\"eqbench\": final_score_percent, \"percent_parseable\": 100}\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "eqbench",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "percent_parseable",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "do_sample": false,
+        "temperature": 0.0,
+        "max_gen_toks": 80,
+        "until": [
+          "\n\n"
+        ]
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 2.1,
+        "pretrained": "/home/quixi/Mango/models/quixi_dolphin-24B-3.2-sft",
+        "tokenizer": "/home/quixi/Mango/models/quixi_dolphin-24B-3.2-sft",
+        "max_gen_toks": 4096,
+        "max_model_len": 8192,
+        "enable_prefix_caching": true,
+        "enable_chunked_prefill": true,
+        "tensor_parallel_size": 8
+      }
+    }
+  },
+  "versions": {
+    "eq_bench": 2.1
+  },
+  "n-shot": {
+    "eq_bench": 0
+  },
+  "higher_is_better": {
+    "eq_bench": {
+      "eqbench": true,
+      "percent_parseable": true
+    }
+  },
+  "n-samples": {
+    "eq_bench": {
+      "original": 171,
+      "effective": 16
+    }
+  },
+  "config": {
+    "model": "vllm",
+    "model_args": "pretrained=/home/quixi/Mango/models/quixi_dolphin-24B-3.2-sft,tokenizer=/home/quixi/Mango/models/quixi_dolphin-24B-3.2-sft,max_gen_toks=4096,max_model_len=8192,enable_prefix_caching=True,enable_chunked_prefill=True,tensor_parallel_size=8",
+    "batch_size": "auto",
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": 16.0,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null,
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": "3f792954",
+  "date": 1748959193.3683586,
+  "pretty_env_info": "PyTorch version: 2.7.0+cu126\nIs debug build: False\nCUDA used to build PyTorch: 12.6\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 24.04.2 LTS (x86_64)\nGCC version: (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0\nClang version: Could not collect\nCMake version: Could not collect\nLibc version: glibc-2.39\n\nPython version: 3.12.3 (main, Feb  4 2025, 14:48:35) [GCC 13.3.0] (64-bit runtime)\nPython platform: Linux-6.8.0-60-generic-x86_64-with-glibc2.39\nIs CUDA available: True\nCUDA runtime version: Could not collect\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA GeForce RTX 3090\nGPU 1: NVIDIA GeForce RTX 3090\nGPU 2: NVIDIA GeForce RTX 3090\nGPU 3: NVIDIA GeForce RTX 3090\nGPU 4: NVIDIA GeForce RTX 3090\nGPU 5: NVIDIA GeForce RTX 3090\nGPU 6: NVIDIA GeForce RTX 3090\nGPU 7: NVIDIA GeForce RTX 3090\n\nNvidia driver version: 575.51.03\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:                        43 bits physical, 48 bits virtual\nByte Order:                           Little Endian\nCPU(s):                               64\nOn-line CPU(s) list:                  0-63\nVendor ID:                            AuthenticAMD\nModel name:                           AMD EPYC 7702 64-Core Processor\nCPU family:                           23\nModel:                                49\nThread(s) per core:                   1\nCore(s) per socket:                   64\nSocket(s):                            1\nStepping:                             0\nFrequency boost:                      enabled\nCPU(s) scaling MHz:                   80%\nCPU max MHz:                          2183.5930\nCPU min MHz:                          1500.0000\nBogoMIPS:                             3999.61\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 sse4_1 sse4_2 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 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 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 avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca sev sev_es\nVirtualization:                       AMD-V\nL1d cache:                            2 MiB (64 instances)\nL1i cache:                            2 MiB (64 instances)\nL2 cache:                             32 MiB (64 instances)\nL3 cache:                             256 MiB (16 instances)\nNUMA node(s):                         1\nNUMA node0 CPU(s):                    0-63\nVulnerability Gather data sampling:   Not affected\nVulnerability Itlb multihit:          Not affected\nVulnerability L1tf:                   Not affected\nVulnerability Mds:                    Not affected\nVulnerability Meltdown:               Not affected\nVulnerability Mmio stale data:        Not affected\nVulnerability Reg file data sampling: Not affected\nVulnerability Retbleed:               Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow:   Mitigation; SMT disabled\nVulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl\nVulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:             Mitigation; Retpolines; IBPB conditional; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds:                  Not affected\nVulnerability Tsx async abort:        Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==2.2.6\n[pip3] nvidia-cublas-cu12==12.6.4.1\n[pip3] nvidia-cuda-cupti-cu12==12.6.80\n[pip3] nvidia-cuda-nvrtc-cu12==12.6.77\n[pip3] nvidia-cuda-runtime-cu12==12.6.77\n[pip3] nvidia-cudnn-cu12==9.5.1.17\n[pip3] nvidia-cufft-cu12==11.3.0.4\n[pip3] nvidia-curand-cu12==10.3.7.77\n[pip3] nvidia-cusolver-cu12==11.7.1.2\n[pip3] nvidia-cusparse-cu12==12.5.4.2\n[pip3] nvidia-cusparselt-cu12==0.6.3\n[pip3] nvidia-nccl-cu12==2.26.2\n[pip3] nvidia-nvjitlink-cu12==12.6.85\n[pip3] nvidia-nvtx-cu12==12.6.77\n[pip3] torch==2.7.0\n[pip3] torchaudio==2.7.0\n[pip3] torchvision==0.22.0\n[pip3] triton==3.3.0\n[conda] Could not collect",
+  "transformers_version": "4.52.4",
+  "lm_eval_version": "0.4.8",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "</s>",
+    "2"
+  ],
+  "tokenizer_eos_token": [
+    "</s>",
+    "2"
+  ],
+  "tokenizer_bos_token": [
+    "<s>",
+    "1"
+  ],
+  "eot_token_id": 2,
+  "max_length": 8192,
+  "task_hashes": {
+    "eq_bench": "15da9ef6fb8cd693f90ddda4d08b4b68a3634f3bb4a646098d3883ec6fe9ba43"
+  },
+  "model_source": "vllm",
+  "model_name": "/home/quixi/Mango/models/quixi_dolphin-24B-3.2-sft",
+  "model_name_sanitized": "__home__quixi__Mango__models__quixi_dolphin-24B-3.2-sft",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": true,
+  "chat_template": "{%- set today = strftime_now(\"%Y-%m-%d\") %}\n{%- set default_system_message = \"You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\\nYour knowledge base was last updated on 2023-10-01. The current date is \" + today + \".\\n\\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \\\"What are some good restaurants around me?\\\" => \\\"Where are you?\\\" or \\\"When is the next flight to Tokyo\\\" => \\\"Where do you travel from?\\\")\" %}\n\n{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = default_system_message %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}\n\n{%- for message in loop_messages %}\n    {%- if message['role'] == 'user' %}\n        {{- '[INST]' + message['content'] + '[/INST]' }}\n    {%- elif message['role'] == 'system' %}\n        {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}\n    {%- elif message['role'] == 'assistant' %}\n        {{- message['content'] + eos_token }}\n    {%- else %}\n        {{- raise_exception('Only user, system and assistant roles are supported!') }}\n    {%- endif %}\n{%- endfor %}",
+  "chat_template_sha": "3934d199bfe5b6fab5cba1b5f8ee475e8d5738ac315f21cb09545b4e665cc005",
+  "start_time": 38949.771105402,
+  "end_time": 39078.444737744,
+  "total_evaluation_time_seconds": "128.67363234200457"
+}