hellaswag/__nm__drive0__shashata__quantized_models__SmolLM-135M-Instruct-quantized.w4a16/results_2024-08-21T23-18-58.065184.json

{
  "results": {
    "hellaswag": {
      "alias": "hellaswag",
      "acc,none": 0.34166500697072294,
      "acc_stderr,none": 0.004732986187325887,
      "acc_norm,none": 0.4080860386377216,
      "acc_norm_stderr,none": 0.004904747752286939
    }
  },
  "group_subtasks": {
    "hellaswag": []
  },
  "configs": {
    "hellaswag": {
      "task": "hellaswag",
      "tag": [
        "multiple_choice"
      ],
      "dataset_path": "hellaswag",
      "dataset_kwargs": {
        "trust_remote_code": true
      },
      "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}}",
      "doc_to_choice": "choices",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 10,
      "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
      }
    }
  },
  "versions": {
    "hellaswag": 1.0
  },
  "n-shot": {
    "hellaswag": 10
  },
  "higher_is_better": {
    "hellaswag": {
      "acc": true,
      "acc_norm": true
    }
  },
  "n-samples": {
    "hellaswag": {
      "original": 10042,
      "effective": 10042
    }
  },
  "config": {
    "model": "sparseml",
    "model_args": "pretrained=/nm/drive0/shashata/quantized_models/SmolLM-135M-Instruct-quantized.w4a16,dtype=bfloat16,max_legth=2048,add_bos_token=True,parallelize=True",
    "model_num_parameters": 137832768,
    "model_dtype": "torch.bfloat16",
    "model_revision": "main",
    "model_sha": "",
    "batch_size": "32",
    "batch_sizes": [],
    "device": null,
    "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": "4e55a1dd",
  "date": 1724295861.4291167,
  "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.35\n\nPython version: 3.11.9 | packaged by conda-forge | (main, Apr 19 2024, 18:36:13) [GCC 12.3.0] (64-bit runtime)\nPython platform: Linux-5.15.0-91-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.3.103\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 545.23.08\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:                           4900.20\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 erms 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 fsrm\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):                       2\nNUMA node0 CPU(s):                  0-63,128-191\nNUMA node1 CPU(s):                  64-127,192-255\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 Retbleed:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\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==1.26.4\n[pip3] onnx==1.14.1\n[pip3] onnxruntime==1.18.1\n[pip3] torch==2.4.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
  "transformers_version": "4.43.4",
  "upper_git_hash": null,
  "tokenizer_pad_token": [
    "<|im_end|>",
    "2"
  ],
  "tokenizer_eos_token": [
    "<|im_end|>",
    "2"
  ],
  "tokenizer_bos_token": [
    "<|im_start|>",
    "1"
  ],
  "eot_token_id": 2,
  "max_length": 2048,
  "task_hashes": {},
  "model_source": "sparseml",
  "model_name": "/nm/drive0/shashata/quantized_models/SmolLM-135M-Instruct-quantized.w4a16",
  "model_name_sanitized": "__nm__drive0__shashata__quantized_models__SmolLM-135M-Instruct-quantized.w4a16",
  "system_instruction": null,
  "system_instruction_sha": null,
  "fewshot_as_multiturn": false,
  "chat_template": null,
  "chat_template_sha": null,
  "start_time": 1866373.356318592,
  "end_time": 1867255.159892713,
  "total_evaluation_time_seconds": "881.8035741208587"
}