|
{ |
|
"results": { |
|
"gsm8k": { |
|
"exact_match,strict-match": 0.5526914329037149, |
|
"exact_match_stderr,strict-match": 0.013695795709089896, |
|
"exact_match,flexible-extract": 0.5534495830174374, |
|
"exact_match_stderr,flexible-extract": 0.013693566549743146, |
|
"alias": "gsm8k" |
|
} |
|
}, |
|
"group_subtasks": { |
|
"gsm8k": [] |
|
}, |
|
"configs": { |
|
"gsm8k": { |
|
"task": "gsm8k", |
|
"group": [ |
|
"math_word_problems" |
|
], |
|
"dataset_path": "gsm8k", |
|
"dataset_name": "main", |
|
"training_split": "train", |
|
"test_split": "test", |
|
"fewshot_split": "train", |
|
"doc_to_text": "Question: {{question}}\nAnswer:", |
|
"doc_to_target": "{{answer}}", |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 5, |
|
"metric_list": [ |
|
{ |
|
"metric": "exact_match", |
|
"aggregation": "mean", |
|
"higher_is_better": true, |
|
"ignore_case": true, |
|
"ignore_punctuation": false, |
|
"regexes_to_ignore": [ |
|
",", |
|
"\\$", |
|
"(?s).*#### ", |
|
"\\.$" |
|
] |
|
} |
|
], |
|
"output_type": "generate_until", |
|
"generation_kwargs": { |
|
"until": [ |
|
"Question:", |
|
"</s>", |
|
"<|im_end|>" |
|
], |
|
"do_sample": false, |
|
"temperature": 0.0 |
|
}, |
|
"repeats": 1, |
|
"filter_list": [ |
|
{ |
|
"name": "strict-match", |
|
"filter": [ |
|
{ |
|
"function": "regex", |
|
"regex_pattern": "#### (\\-?[0-9\\.\\,]+)" |
|
}, |
|
{ |
|
"function": "take_first" |
|
} |
|
] |
|
}, |
|
{ |
|
"name": "flexible-extract", |
|
"filter": [ |
|
{ |
|
"function": "regex", |
|
"group_select": -1, |
|
"regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)" |
|
}, |
|
{ |
|
"function": "take_first" |
|
} |
|
] |
|
} |
|
], |
|
"should_decontaminate": false, |
|
"metadata": { |
|
"version": 3.0 |
|
} |
|
} |
|
}, |
|
"versions": { |
|
"gsm8k": 3.0 |
|
}, |
|
"n-shot": { |
|
"gsm8k": 5 |
|
}, |
|
"higher_is_better": { |
|
"gsm8k": { |
|
"exact_match": true |
|
} |
|
}, |
|
"n-samples": { |
|
"gsm8k": { |
|
"original": 1319, |
|
"effective": 1319 |
|
} |
|
}, |
|
"config": { |
|
"model": "vllm", |
|
"model_args": "pretrained=/cache/abhinav/models/Phase1/gptq-Qwen/Qwen2-1.5B-Instruct-garage-bAInd/Open-Platypus-mse-damp0.1-ns512-seqlen4K,tensor_parallel_size=2,dtype=auto,add_bos_token=True,gpu_memory_utilization=0.4,data_parallel_size=1,max_model_len=4096", |
|
"batch_size": "auto", |
|
"batch_sizes": [], |
|
"device": "cuda", |
|
"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": null, |
|
"date": 1719628061.99107, |
|
"pretty_env_info": "PyTorch version: 2.3.0+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 3.29.6\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-5.15.0-101-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: \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: 4900.22\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] torch==2.3.0\n[pip3] triton==2.3.0\n[conda] Could not collect", |
|
"transformers_version": "4.41.2", |
|
"upper_git_hash": null, |
|
"task_hashes": {}, |
|
"model_source": "vllm", |
|
"model_name": "/cache/abhinav/models/Phase1/gptq-Qwen/Qwen2-1.5B-Instruct-garage-bAInd/Open-Platypus-mse-damp0.1-ns512-seqlen4K", |
|
"model_name_sanitized": "__cache__abhinav__models__Phase1__gptq-Qwen__Qwen2-1.5B-Instruct-garage-bAInd__Open-Platypus-mse-damp0.1-ns512-seqlen4K", |
|
"system_instruction": null, |
|
"system_instruction_sha": null, |
|
"fewshot_as_multiturn": false, |
|
"chat_template": null, |
|
"chat_template_sha": null, |
|
"start_time": 7641749.132861241, |
|
"end_time": 7641857.900817806, |
|
"total_evaluation_time_seconds": "108.76795656513423" |
|
} |