| { | |
| "results": { | |
| "moe_ien_tf": { | |
| "alias": "moe_ien_tf", | |
| "acc,none": 0.6340374377468658, | |
| "acc_stderr,none": 0.0063130565613714554, | |
| "acc_norm,none": 0.6340374377468658, | |
| "acc_norm_stderr,none": 0.0063130565613714554 | |
| } | |
| }, | |
| "group_subtasks": { | |
| "moe_ien_tf": [] | |
| }, | |
| "configs": { | |
| "moe_ien_tf": { | |
| "task": "moe_ien_tf", | |
| "tag": [ | |
| "multiple_choice" | |
| ], | |
| "dataset_path": "lm_eval/tasks/moe_ien_tf/moe_ien_tf.py", | |
| "dataset_name": "moe_ien_tf", | |
| "dataset_kwargs": { | |
| "trust_remote_code": true | |
| }, | |
| "validation_split": "validation", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_docs(doc):\n keys=[\"\u0635\u062d\u064a\u062d\u0629\",\n \"\u062e\u0627\u0637\u0626\u0629\"\n ]\n #keys =[\"\u0635\u0648\u0627\u0628\",\n # \"\u062e\u0637\u0623\"]\n target_key = int(doc[\"Answer\"])-1\n\n out_doc = {\n \"query\": \"\\n\\n\u0627\u0644\u0633\u0624\u0627\u0644:\" +doc[\"Question\"]+\"\\n\u0625\u062c\u0627\u0628\u0629:'\", \n \"choices\": keys,\n \"gold\": target_key,\n }\n return out_doc\n return dataset.map(_process_docs)\n", | |
| "doc_to_text": "query", | |
| "doc_to_target": "gold", | |
| "doc_to_choice": "choices", | |
| "description": "\u0641\u064a\u0645\u0627 \u064a\u0644\u064a \u0639\u0628\u0627\u0631\u0627\u062a \u0625\u0645\u0627 \u0635\u062d\u064a\u062d\u0629 \u0623\u0648 \u062e\u0627\u0637\u0626\u0629 \u062d\u0648\u0644 {{Subject}}\n \u0627\u0644\u0631\u062c\u0627\u0621 \u062a\u0635\u0646\u064a\u0641 \u0627\u0644\u0639\u0628\u0627\u0631\u0629 \u0625\u0644\u0649 '\u0635\u062d\u064a\u062d\u0629' \u0623\u0648 '\u062e\u0627\u0637\u0626\u0629' \u062f\u0648\u0646 \u0634\u0631\u062d ", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "balanced_cat" | |
| }, | |
| "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": 2.0 | |
| } | |
| } | |
| }, | |
| "versions": { | |
| "moe_ien_tf": 2.0 | |
| }, | |
| "n-shot": { | |
| "moe_ien_tf": 0 | |
| }, | |
| "higher_is_better": { | |
| "moe_ien_tf": { | |
| "acc": true, | |
| "acc_norm": true | |
| } | |
| }, | |
| "n-samples": { | |
| "moe_ien_tf": { | |
| "original": 5823, | |
| "effective": 5823 | |
| } | |
| }, | |
| "config": { | |
| "model": "hf", | |
| "model_args": "pretrained=mistralai/Mistral-7B-Instruct-v0.3,trust_remote_code=True,cache_dir=/tmp,parallelize=True", | |
| "model_num_parameters": 7248023552, | |
| "model_dtype": "torch.bfloat16", | |
| "model_revision": "main", | |
| "model_sha": "e0bc86c23ce5aae1db576c8cca6f06f1f73af2db", | |
| "batch_size": 1, | |
| "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": "b955b2950", | |
| "date": 1739618159.7425826, | |
| "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 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\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: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\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): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.88\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 tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\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: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\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; 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==1.26.4\n[pip3] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect", | |
| "transformers_version": "4.48.3", | |
| "upper_git_hash": null, | |
| "tokenizer_pad_token": [ | |
| "<unk>", | |
| "0" | |
| ], | |
| "tokenizer_eos_token": [ | |
| "</s>", | |
| "2" | |
| ], | |
| "tokenizer_bos_token": [ | |
| "<s>", | |
| "1" | |
| ], | |
| "eot_token_id": 2, | |
| "max_length": 32768, | |
| "task_hashes": { | |
| "moe_ien_tf": "87c1341e70cacc508279240f78ecd4d5d873569e238982ef3f15031c20f834da" | |
| }, | |
| "model_source": "hf", | |
| "model_name": "mistralai/Mistral-7B-Instruct-v0.3", | |
| "model_name_sanitized": "mistralai__Mistral-7B-Instruct-v0.3", | |
| "system_instruction": null, | |
| "system_instruction_sha": null, | |
| "fewshot_as_multiturn": false, | |
| "chat_template": "{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n{%- set user_messages = loop_messages | selectattr(\"role\", \"equalto\", \"user\") | list %}\n\n{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}\n{%- set ns = namespace() %}\n{%- set ns.index = 0 %}\n{%- for message in loop_messages %}\n {%- if not (message.role == \"tool\" or message.role == \"tool_results\" or (message.tool_calls is defined and message.tool_calls is not none)) %}\n {%- if (message[\"role\"] == \"user\") != (ns.index % 2 == 0) %}\n {{- raise_exception(\"After the optional system message, conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif %}\n {%- set ns.index = ns.index + 1 %}\n {%- endif %}\n{%- endfor %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if message[\"role\"] == \"user\" %}\n {%- if tools is not none and (message == user_messages[-1]) %}\n {{- \"[AVAILABLE_TOOLS] [\" }}\n {%- for tool in tools %}\n {%- set tool = tool.function %}\n {{- '{\"type\": \"function\", \"function\": {' }}\n {%- for key, val in tool.items() if key != \"return\" %}\n {%- if val is string %}\n {{- '\"' + key + '\": \"' + val + '\"' }}\n {%- else %}\n {{- '\"' + key + '\": ' + val|tojson }}\n {%- endif %}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \"}}\" }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- else %}\n {{- \"]\" }}\n {%- endif %}\n {%- endfor %}\n {{- \"[/AVAILABLE_TOOLS]\" }}\n {%- endif %}\n {%- if loop.last and system_message is defined %}\n {{- \"[INST] \" + system_message + \"\\n\\n\" + message[\"content\"] + \"[/INST]\" }}\n {%- else %}\n {{- \"[INST] \" + message[\"content\"] + \"[/INST]\" }}\n {%- endif %}\n {%- elif message.tool_calls is defined and message.tool_calls is not none %}\n {{- \"[TOOL_CALLS] [\" }}\n {%- for tool_call in message.tool_calls %}\n {%- set out = tool_call.function|tojson %}\n {{- out[:-1] }}\n {%- if not tool_call.id is defined or tool_call.id|length != 9 %}\n {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n {%- endif %}\n {{- ', \"id\": \"' + tool_call.id + '\"}' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- else %}\n {{- \"]\" + eos_token }}\n {%- endif %}\n {%- endfor %}\n {%- elif message[\"role\"] == \"assistant\" %}\n {{- \" \" + message[\"content\"]|trim + eos_token}}\n {%- elif message[\"role\"] == \"tool_results\" or message[\"role\"] == \"tool\" %}\n {%- if message.content is defined and message.content.content is defined %}\n {%- set content = message.content.content %}\n {%- else %}\n {%- set content = message.content %}\n {%- endif %}\n {{- '[TOOL_RESULTS] {\"content\": ' + content|string + \", \" }}\n {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}\n {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n {%- endif %}\n {{- '\"call_id\": \"' + message.tool_call_id + '\"}[/TOOL_RESULTS]' }}\n {%- else %}\n {{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial optional system message!\") }}\n {%- endif %}\n{%- endfor %}\n", | |
| "chat_template_sha": "e16746b40344d6c5b5265988e0328a0bf7277be86f1c335156eae07e29c82826", | |
| "start_time": 1583446.306152082, | |
| "end_time": 1583776.933878196, | |
| "total_evaluation_time_seconds": "330.62772611388937" | |
| } |