lanawwas/ALLaM-7B-Instruct-preview
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: lanawwas/ALLaM-7B-Instruct-preview
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-22 10:54:04 +08:00
commit 3e4c694337
466 changed files with 259661 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

123
evaluations/ar/Falcon3-7B-Instruct/acva_5_shot.json Normal file
View File

@@ -0,0 +1,123 @@
{
"results": {
"acva": {
"alias": "acva",
"acc,none": 0.6045924225028703,
"acc_stderr,none": 0.00523925695392083,
"acc_norm,none": 0.5897818599311137,
"acc_norm_stderr,none": 0.005270708411925859
}
},
"group_subtasks": {
"acva": []
},
"configs": {
"acva": {
"task": "acva",
"tag": [
"multiple_choice"
],
"dataset_path": "FreedomIntelligence/ACVA-Arabic-Cultural-Value-Alignment",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _format_subject(subject):\n \n arabic_words = subtasks_ar[subtasks.index(subject)]\n return arabic_words\n \n def _generate_subject(doc):\n subject = _format_subject(doc[\"id\"].split(\"-\")[0])\n\n return subject\n \n def _process_docs(doc):\n keys = [\"\u0635\u062d\",\n \"\u062e\u0637\u0623\"]\n subject = _generate_subject(doc)\n gold = keys.index(doc['answer'])\n out_doc = {\n \"id\": doc[\"id\"],\n \"query\": \"\\n\\n\\n\u0627\u0644\u0633\u0624\u0627\u0644:\" + doc[\"question\"]+\"\\n\u0625\u062c\u0627\u0628\u0629:'\",\n \"choices\": keys,\n \"gold\": gold,\n \"subject\": subject,\n }\n \n return out_doc\n\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' \u0623\u0648 '\u062e\u0637\u0623' \u062f\u0648\u0646 \u0634\u0631\u062d",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 5,
"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": 0.0
}
}
},
"versions": {
"acva": 0.0
},
"n-shot": {
"acva": 5
},
"higher_is_better": {
"acva": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"acva": {
"original": 8710,
"effective": 8710
}
},
"config": {
"model": "hf",
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7455550464,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
"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": "5e10e017",
"date": 1736889821.9957027,
"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": "4.48.0",
"upper_git_hash": "f64fe2f2a86055aaecced603b56097fd79201711",
"tokenizer_pad_token": [
"<|pad|>",
"2023"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"11"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 11,
"max_length": 32768,
"task_hashes": {
"acva": "f573ae5740e68711d257f2dc4a23db7c6b1c04895364f1af4b4eb64bfab793a4"
},
"model_source": "hf",
"model_name": "tiiuae/Falcon3-7B-Instruct",
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 600072.370318618,
"end_time": 600217.222010416,
"total_evaluation_time_seconds": "144.85169179795776"
}

142
evaluations/ar/Falcon3-7B-Instruct/ar_ifeval_0_shot.json Normal file
View File

@@ -0,0 +1,142 @@
{
"results": {
"ar_ifeval": {
"alias": "ar_ifeval",
"prompt_level_strict_acc,none": 0.08582089552238806,
"prompt_level_strict_acc_stderr,none": 0.012109752724743699,
"inst_level_strict_acc,none": 0.47918088737201364,
"inst_level_strict_acc_stderr,none": "N/A",
"prompt_level_loose_acc,none": 0.13805970149253732,
"prompt_level_loose_acc_stderr,none": 0.014914035308708435,
"inst_level_loose_acc,none": 0.5276450511945392,
"inst_level_loose_acc_stderr,none": "N/A"
}
},
"group_subtasks": {
"ar_ifeval": []
},
"configs": {
"ar_ifeval": {
"task": "ar_ifeval",
"dataset_path": "lm_eval/tasks/ar_ifeval/ar_ifeval.py",
"dataset_name": "ar_ifeval",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"doc_to_text": "prompt",
"doc_to_target": 0,
"process_results": "def process_results(doc, results):\n\n response = results[0]\n out_strict = process_sample(doc, response, 'strict')\n out_loose = process_sample(doc, response, 'loose')\n\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",
"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": 4.0
}
}
},
"versions": {
"ar_ifeval": 4.0
},
"n-shot": {
"ar_ifeval": 0
},
"higher_is_better": {
"ar_ifeval": {
"prompt_level_strict_acc": true,
"inst_level_strict_acc": true,
"prompt_level_loose_acc": true,
"inst_level_loose_acc": true
}
},
"n-samples": {
"ar_ifeval": {
"original": 536,
"effective": 536
}
},
"config": {
"model": "hf",
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7455550464,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
"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": 1739621196.897086,
"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": [
"<|pad|>",
"2023"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"11"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 11,
"max_length": 32768,
"task_hashes": {
"ar_ifeval": "ca837eed1e9f468712643d1fab81b7b48c88a8799239851476bdc889990e6b41"
},
"model_source": "hf",
"model_name": "tiiuae/Falcon3-7B-Instruct",
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n{{- '<|system|>\\n' }}\n{%- if messages[0]['role'] == 'system' %}\n{{- messages[0]['content'] }}\n{%- set remaining_messages = messages[1:] %}\n{%- else %}\n{%- set remaining_messages = messages %}\n{%- endif %}\n{{- 'You are a Falcon assistant skilled in function calling. You are helpful, respectful, and concise.\\n\\n# Tools\\n\\nYou have access to the following functions. You MUST use them to answer questions when needed. For each function call, you MUST return a JSON object inside <tool_call></tool_call> tags.\\n\\n<tools>' + tools|tojson(indent=2) + '</tools>\\n\\n# Output Format\\n\\nYour response MUST follow this format when making function calls:\\n<tool_call>\\n[\\n {\"name\": \"function_name\", \"arguments\": {\"arg1\": \"value1\", \"arg2\": \"value2\"}},\\n {\"name\": \"another_function\", \"arguments\": {\"arg\": \"value\"}}\\n]\\n</tool_call>\\nIf no function calls are needed, respond normally without the tool_call tags.\\n' }}\n{%- for message in remaining_messages %}\n{%- if message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if message.content %}\n{{- '<|assistant|>\\n' + message['content'] }}\n{%- endif %}\n{%- if message.tool_calls %}\n{{- '\\n<tool_call>\\n' }}\n{{- message.tool_calls|tojson(indent=2) }}\n{{- '\\n</tool_call>' }}\n{%- endif %}\n{{- eos_token + '\\n' }}\n{%- elif message['role'] == 'tool' %}\n{{- '<|assistant|>\\n<tool_response>\\n' + message['content'] + '\\n</tool_response>\\n' }}\n{%- endif %}\n{%- endfor %}\n{{- '<|assistant|>\\n' if add_generation_prompt }}\n{%- else %}\n{%- for message in messages %}\n{%- if message['role'] == 'system' %}\n{{- '<|system|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if not loop.last %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token + '\\n' }}\n{%- else %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token }}\n{%- endif %}\n{%- endif %}\n{%- if loop.last and add_generation_prompt %}\n{{- '<|assistant|>\\n' }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}",
"chat_template_sha": "914ccd80356f5822d1a50d97546e37f60c04ed831fe431aa40346574ec266901",
"start_time": 1395880.012817552,
"end_time": 1401371.318791154,
"total_evaluation_time_seconds": "5491.305973601993"
}

126
evaluations/ar/Falcon3-7B-Instruct/araMath_v3_5_shot.json Normal file
View File

@@ -0,0 +1,126 @@
{
"results": {
"araMath_v3": {
"alias": "araMath_v3",
"acc,none": 0.5652892561983471,
"acc_stderr,none": 0.020170519477736983,
"acc_norm,none": 0.5652892561983471,
"acc_norm_stderr,none": 0.020170519477736983
}
},
"group_subtasks": {
"araMath_v3": []
},
"configs": {
"araMath_v3": {
"task": "araMath_v3",
"tag": [
"multiple_choice"
],
"dataset_path": "lm_eval/tasks/araMath_v3/araMath_v3.py",
"dataset_name": "araMath_v3",
"dataset_kwargs": {
"trust_remote_code": true
},
"validation_split": "validation",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_docs(doc):\n def remove_prefix(choice):\n prefixes = [\"(A)\", \"(B)\", \"(C)\", \"(D)\"]\n for prefix in prefixes:\n if choice.startswith(prefix + \" \"):\n return choice[len(prefix) + 1:] \n return choice \n\n def format_example(doc, keys):\n question = doc[\"question\"].strip()\n choices = \"\".join(\n [f\"{key}. {remove_prefix(choice)}\\n\" for key, choice in zip(keys, doc[\"options\"])]\n )\n\n prompt = f\"\\n\\n\u0627\u0644\u0633\u0624\u0627\u0644: {question}\\n{choices}\\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:\"\n return prompt\n\n keys_en = [\"A\", \"B\", \"C\", \"D\"]\n out_doc = {\n \"query\": format_example(doc, keys_en),\n \"choices\": keys_en,\n \"gold\": keys_en.index(doc[\"label\"]),\n }\n return out_doc\n \n return dataset.map(_process_docs)\n",
"doc_to_text": "query",
"doc_to_target": "gold",
"doc_to_choice": "{{choices}}",
"description": "\u0645\u0646 \u0641\u0636\u0644\u0643 \u0627\u062e\u062a\u0631 \u0625\u062c\u0627\u0628\u0629 \u0648\u0627\u062d\u062f\u0629 \u0645\u0646 \u0628\u064a\u0646 'A\u060c B\u060c C\u060c D' \u062f\u0648\u0646 \u0634\u0631\u062d",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 5,
"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": true,
"doc_to_decontamination_query": "query",
"metadata": {
"version": 0.0
}
}
},
"versions": {
"araMath_v3": 0.0
},
"n-shot": {
"araMath_v3": 5
},
"higher_is_better": {
"araMath_v3": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"araMath_v3": {
"original": 605,
"effective": 605
}
},
"config": {
"model": "hf",
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7455550464,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
"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": 1739621084.921236,
"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": [
"<|pad|>",
"2023"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"11"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 11,
"max_length": 32768,
"task_hashes": {
"araMath_v3": "b7e29b20c532c7420cc659c6586d56642070560abff0925ed01ad8f200d8e72b"
},
"model_source": "hf",
"model_name": "tiiuae/Falcon3-7B-Instruct",
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n{{- '<|system|>\\n' }}\n{%- if messages[0]['role'] == 'system' %}\n{{- messages[0]['content'] }}\n{%- set remaining_messages = messages[1:] %}\n{%- else %}\n{%- set remaining_messages = messages %}\n{%- endif %}\n{{- 'You are a Falcon assistant skilled in function calling. You are helpful, respectful, and concise.\\n\\n# Tools\\n\\nYou have access to the following functions. You MUST use them to answer questions when needed. For each function call, you MUST return a JSON object inside <tool_call></tool_call> tags.\\n\\n<tools>' + tools|tojson(indent=2) + '</tools>\\n\\n# Output Format\\n\\nYour response MUST follow this format when making function calls:\\n<tool_call>\\n[\\n {\"name\": \"function_name\", \"arguments\": {\"arg1\": \"value1\", \"arg2\": \"value2\"}},\\n {\"name\": \"another_function\", \"arguments\": {\"arg\": \"value\"}}\\n]\\n</tool_call>\\nIf no function calls are needed, respond normally without the tool_call tags.\\n' }}\n{%- for message in remaining_messages %}\n{%- if message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if message.content %}\n{{- '<|assistant|>\\n' + message['content'] }}\n{%- endif %}\n{%- if message.tool_calls %}\n{{- '\\n<tool_call>\\n' }}\n{{- message.tool_calls|tojson(indent=2) }}\n{{- '\\n</tool_call>' }}\n{%- endif %}\n{{- eos_token + '\\n' }}\n{%- elif message['role'] == 'tool' %}\n{{- '<|assistant|>\\n<tool_response>\\n' + message['content'] + '\\n</tool_response>\\n' }}\n{%- endif %}\n{%- endfor %}\n{{- '<|assistant|>\\n' if add_generation_prompt }}\n{%- else %}\n{%- for message in messages %}\n{%- if message['role'] == 'system' %}\n{{- '<|system|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if not loop.last %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token + '\\n' }}\n{%- else %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token }}\n{%- endif %}\n{%- endif %}\n{%- if loop.last and add_generation_prompt %}\n{{- '<|assistant|>\\n' }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}",
"chat_template_sha": "914ccd80356f5822d1a50d97546e37f60c04ed831fe431aa40346574ec266901",
"start_time": 1395768.116667791,
"end_time": 1395816.745740765,
"total_evaluation_time_seconds": "48.629072973970324"
}

130
evaluations/ar/Falcon3-7B-Instruct/araPro_0_shot.json Normal file
View File

@@ -0,0 +1,130 @@
{
"results": {
"araPro": {
"alias": "araPro",
"acc,none": 0.41471705658868224,
"acc_stderr,none": 0.006967450316480296,
"acc_norm,none": 0.41471705658868224,
"acc_norm_stderr,none": 0.006967450316480296
}
},
"group_subtasks": {
"araPro": []
},
"configs": {
"araPro": {
"task": "araPro",
"tag": [
"multiple_choice"
],
"dataset_path": "lm_eval/tasks/araPro/araPro.py",
"dataset_name": "araPro",
"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 def remove_prefix(choice):\n return choice.replace('.', '') if '.' in choice[:2] else choice\n \n def format_example(doc, keys):\n question = doc[\"question\"].strip()\n \n choice_num = ['choice1', 'choice2', 'choice3', 'choice4']\n choices = \"\".join(\n [f\"{key}. {remove_prefix(doc[choice_num[index]])}\\n\" for index, key in enumerate(keys)]\n )\n\n prompt = f\"\\n\\n\\n\u0627\u0644\u0633\u0624\u0627\u0644: {question}\\n{choices} \\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:\"\n return prompt\n\n #keys = [\"1\", \"2\", \"3\", \"4\"]\n keys = [\"A\", \"B\", \"C\", \"D\"]\n out_doc = {\n \"query\": format_example(doc, keys), \n \"choices\": keys,\n \"gold\": doc[\"answer\"]-1,\n } \n\n return out_doc\n \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 \u0623\u0633\u0626\u0644\u0629 \u0627\u0644\u0627\u062e\u062a\u064a\u0627\u0631 \u0645\u0646 \u0645\u062a\u0639\u062f\u062f (\u0645\u0639 \u0627\u0644\u0625\u062c\u0627\u0628\u0627\u062a) \u0645\u0646 \u0641\u0636\u0644\u0643 \u0627\u062e\u062a\u0631 \u0625\u062c\u0627\u0628\u0629 \u0648\u0627\u062d\u062f\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": true,
"doc_to_decontamination_query": "Question",
"metadata": {
"version": 2.0
}
}
},
"versions": {
"araPro": 2.0
},
"n-shot": {
"araPro": 0
},
"higher_is_better": {
"araPro": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"araPro": {
"original": 5001,
"effective": 5001
}
},
"config": {
"model": "hf",
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7455550464,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
"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": 1739617143.3614087,
"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": [
"<|pad|>",
"2023"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"11"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 11,
"max_length": 32768,
"task_hashes": {
"araPro": "063166ad2e52146b6a051c978bf54b1397281e222da633e81fa50357d2409ee9"
},
"model_source": "hf",
"model_name": "tiiuae/Falcon3-7B-Instruct",
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n{{- '<|system|>\\n' }}\n{%- if messages[0]['role'] == 'system' %}\n{{- messages[0]['content'] }}\n{%- set remaining_messages = messages[1:] %}\n{%- else %}\n{%- set remaining_messages = messages %}\n{%- endif %}\n{{- 'You are a Falcon assistant skilled in function calling. You are helpful, respectful, and concise.\\n\\n# Tools\\n\\nYou have access to the following functions. You MUST use them to answer questions when needed. For each function call, you MUST return a JSON object inside <tool_call></tool_call> tags.\\n\\n<tools>' + tools|tojson(indent=2) + '</tools>\\n\\n# Output Format\\n\\nYour response MUST follow this format when making function calls:\\n<tool_call>\\n[\\n {\"name\": \"function_name\", \"arguments\": {\"arg1\": \"value1\", \"arg2\": \"value2\"}},\\n {\"name\": \"another_function\", \"arguments\": {\"arg\": \"value\"}}\\n]\\n</tool_call>\\nIf no function calls are needed, respond normally without the tool_call tags.\\n' }}\n{%- for message in remaining_messages %}\n{%- if message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if message.content %}\n{{- '<|assistant|>\\n' + message['content'] }}\n{%- endif %}\n{%- if message.tool_calls %}\n{{- '\\n<tool_call>\\n' }}\n{{- message.tool_calls|tojson(indent=2) }}\n{{- '\\n</tool_call>' }}\n{%- endif %}\n{{- eos_token + '\\n' }}\n{%- elif message['role'] == 'tool' %}\n{{- '<|assistant|>\\n<tool_response>\\n' + message['content'] + '\\n</tool_response>\\n' }}\n{%- endif %}\n{%- endfor %}\n{{- '<|assistant|>\\n' if add_generation_prompt }}\n{%- else %}\n{%- for message in messages %}\n{%- if message['role'] == 'system' %}\n{{- '<|system|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if not loop.last %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token + '\\n' }}\n{%- else %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token }}\n{%- endif %}\n{%- endif %}\n{%- if loop.last and add_generation_prompt %}\n{{- '<|assistant|>\\n' }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}",
"chat_template_sha": "914ccd80356f5822d1a50d97546e37f60c04ed831fe431aa40346574ec266901",
"start_time": 1391826.416201954,
"end_time": 1394850.089034202,
"total_evaluation_time_seconds": "3023.672832248034"
}

2090
evaluations/ar/Falcon3-7B-Instruct/arabicmmlu_0_shot.json Normal file
View File

File diff suppressed because it is too large Load Diff

126
evaluations/ar/Falcon3-7B-Instruct/etec_v2_0_shot.json Normal file
View File

@@ -0,0 +1,126 @@
{
"results": {
"etec_v2": {
"alias": "etec_v2",
"acc,none": 0.3751987281399046,
"acc_stderr,none": 0.01114886834610489,
"acc_norm,none": 0.3751987281399046,
"acc_norm_stderr,none": 0.01114886834610489
}
},
"group_subtasks": {
"etec_v2": []
},
"configs": {
"etec_v2": {
"task": "etec_v2",
"tag": [
"multiple_choice"
],
"dataset_path": "lm_eval/tasks/etec_v2/etec.py",
"dataset_name": "etec_v2",
"dataset_kwargs": {
"trust_remote_code": true
},
"validation_split": "validation",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_docs(doc):\n def format_example(doc, keys):\n question = doc[\"question\"].strip()\n \n choices = \"\".join(\n [f\"{key}. {choice}\\n\" for key, choice in zip(keys, doc[\"choices\"])]\n )\n prompt = f\"\u0627\u0644\u0633\u0624\u0627\u0644: {question}\\n{choices}\\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:\"\n return prompt\n print(doc[\"label\"])\n keys_ar = [\"\u0623\", \"\u0628\", \"\u062c\", \"\u062f\"]\n keys_en = [\"A\", \"B\", \"C\", \"D\"]\n out_doc = {\n \"query\": format_example(doc, keys_en),\n \"choices\": keys_en,\n \"gold\": int(doc[\"label\"])-1,\n }\n return out_doc\n \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 \u0623\u0633\u0626\u0644\u0629 \u0627\u0644\u0627\u062e\u062a\u064a\u0627\u0631 \u0645\u0646 \u0645\u062a\u0639\u062f\u062f (\u0645\u0639 \u0627\u0644\u0625\u062c\u0627\u0628\u0627\u062a) \u0645\u0646 \u0641\u0636\u0644\u0643 \u0627\u062e\u062a\u0631 \u0625\u062c\u0627\u0628\u0629 \u0648\u0627\u062d\u062f\u0629 \u062f\u0648\u0646 \u0634\u0631\u062d\n ",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"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": true,
"doc_to_decontamination_query": "query",
"metadata": {
"version": 0.0
}
}
},
"versions": {
"etec_v2": 0.0
},
"n-shot": {
"etec_v2": 0
},
"higher_is_better": {
"etec_v2": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"etec_v2": {
"original": 1887,
"effective": 1887
}
},
"config": {
"model": "hf",
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7455550464,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
"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": 1739620236.678696,
"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": [
"<|pad|>",
"2023"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"11"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 11,
"max_length": 32768,
"task_hashes": {
"etec_v2": "3a8dc6484af6c9538f122c1bbe5c6866dbe14df841fdf04ab7ff2b6437e8aeae"
},
"model_source": "hf",
"model_name": "tiiuae/Falcon3-7B-Instruct",
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n{{- '<|system|>\\n' }}\n{%- if messages[0]['role'] == 'system' %}\n{{- messages[0]['content'] }}\n{%- set remaining_messages = messages[1:] %}\n{%- else %}\n{%- set remaining_messages = messages %}\n{%- endif %}\n{{- 'You are a Falcon assistant skilled in function calling. You are helpful, respectful, and concise.\\n\\n# Tools\\n\\nYou have access to the following functions. You MUST use them to answer questions when needed. For each function call, you MUST return a JSON object inside <tool_call></tool_call> tags.\\n\\n<tools>' + tools|tojson(indent=2) + '</tools>\\n\\n# Output Format\\n\\nYour response MUST follow this format when making function calls:\\n<tool_call>\\n[\\n {\"name\": \"function_name\", \"arguments\": {\"arg1\": \"value1\", \"arg2\": \"value2\"}},\\n {\"name\": \"another_function\", \"arguments\": {\"arg\": \"value\"}}\\n]\\n</tool_call>\\nIf no function calls are needed, respond normally without the tool_call tags.\\n' }}\n{%- for message in remaining_messages %}\n{%- if message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if message.content %}\n{{- '<|assistant|>\\n' + message['content'] }}\n{%- endif %}\n{%- if message.tool_calls %}\n{{- '\\n<tool_call>\\n' }}\n{{- message.tool_calls|tojson(indent=2) }}\n{{- '\\n</tool_call>' }}\n{%- endif %}\n{{- eos_token + '\\n' }}\n{%- elif message['role'] == 'tool' %}\n{{- '<|assistant|>\\n<tool_response>\\n' + message['content'] + '\\n</tool_response>\\n' }}\n{%- endif %}\n{%- endfor %}\n{{- '<|assistant|>\\n' if add_generation_prompt }}\n{%- else %}\n{%- for message in messages %}\n{%- if message['role'] == 'system' %}\n{{- '<|system|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if not loop.last %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token + '\\n' }}\n{%- else %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token }}\n{%- endif %}\n{%- endif %}\n{%- if loop.last and add_generation_prompt %}\n{{- '<|assistant|>\\n' }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}",
"chat_template_sha": "914ccd80356f5822d1a50d97546e37f60c04ed831fe431aa40346574ec266901",
"start_time": 1394919.684315533,
"end_time": 1394995.42617788,
"total_evaluation_time_seconds": "75.7418623471167"
}

125
evaluations/ar/Falcon3-7B-Instruct/exams_ar_5_shot.json Normal file
View File

@@ -0,0 +1,125 @@
{
"results": {
"exams_ar": {
"alias": "exams_ar",
"acc,none": 0.31843575418994413,
"acc_stderr,none": 0.020122499132803468,
"acc_norm,none": 0.31843575418994413,
"acc_norm_stderr,none": 0.020122499132803468
}
},
"group_subtasks": {
"exams_ar": []
},
"configs": {
"exams_ar": {
"task": "exams_ar",
"tag": [
"multiple_choice"
],
"dataset_path": "lm_eval/tasks/exams_ar",
"dataset_name": "exams_ar",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n\n def _process_docs(doc):\n def format_example(doc, keys):\n \"\"\"\n <prompt>\n \u0633\u0624\u0627\u0644:\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\n \u0627\u062c\u0627\u0628\u0629:\n \"\"\"\n \n question = doc[\"question\"].strip()\n \n choices = \"\".join(\n [f\"{key}. {choice}\\n\" for key, choice in zip(keys, doc[\"choices\"])]\n )\n prompt = f\"\u0627\u0644\u0633\u0624\u0627\u0644: {question}\\n{choices} \\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:\"\n return prompt\n\n def _format_subject(subject):\n arabic_words = subtasks_ar[subtasks.index(subject)]\n return arabic_words\n\n keys = [\"A\", \"B\", \"C\", \"D\"]\n \n subject = doc['id'].split(\"-\")[0]\n description = f\"\ufed2\ufef4\ufee3\ufe8d \ufef2\ufee0\ufef3 \ufe84\ufeb4\ufe8c\ufedf\ufe93 \ufe8d\ufefc\ufea8\ufe98\ufef3\ufe8d\ufead \ufee2\ufee7 \ufee2\ufe98\ufecb\ufea9\ufea9 (\ufee2\ufecb \ufe8d\ufefa\ufe9f\ufe8e\ufe91\ufe8e\ufe97) \ufea1\ufeee\ufedf {_format_subject(subject)} \\n\" #\ufee2\ufee7 \ufed2\ufec0\ufee0\ufedb \ufe8e\ufea8\ufe97\ufead \ufe88\ufe9f\ufe8e\ufe91\ufe93 \ufeed\ufe8e\ufea3\ufea9\ufe93 \ufee2\ufee7 \ufe90\ufef4\ufee7 'A\u060c B\u060c C\u060c D' \ufea9\ufeee\ufee7 \ufeb5\ufeae\ufea3\\n\"\n\n out_doc = {\n \"idx\": doc[\"idx\"],\n \"id\": doc[\"id\"],\n 'dsecription': description,\n \"query\": format_example(doc, keys), # \"Question: \" + doc[\"question\"]['stem'] + \"\\nAnswer:\",\n \"choices\": keys,\n \"gold\": [\"A\", \"B\", \"C\", \"D\"].index(doc[\"label\"]),\n }\n return out_doc\n\n return dataset.map(_process_docs)\n",
"doc_to_text": "query",
"doc_to_target": "gold",
"doc_to_choice": "choices",
"description": "description",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 5,
"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": true,
"doc_to_decontamination_query": "query",
"metadata": {
"version": 0.0
}
}
},
"versions": {
"exams_ar": 0.0
},
"n-shot": {
"exams_ar": 5
},
"higher_is_better": {
"exams_ar": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"exams_ar": {
"original": 537,
"effective": 537
}
},
"config": {
"model": "hf",
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7455550464,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
"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": "5e10e017",
"date": 1736889028.6416683,
"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": "4.48.0",
"upper_git_hash": "f64fe2f2a86055aaecced603b56097fd79201711",
"tokenizer_pad_token": [
"<|pad|>",
"2023"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"11"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 11,
"max_length": 32768,
"task_hashes": {
"exams_ar": "f52ab3f14b240558420910fdb453ccb45c945cec187c0e60ea51cf6eff08973a"
},
"model_source": "hf",
"model_name": "tiiuae/Falcon3-7B-Instruct",
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 599279.04705073,
"end_time": 599692.233103212,
"total_evaluation_time_seconds": "413.1860524819931"
}

553
evaluations/ar/Falcon3-7B-Instruct/gat_0_shot.json Normal file
View File

@@ -0,0 +1,553 @@
{
"results": {
"gat": {
"acc,none": 0.27994481374639407,
"acc_stderr,none": 0.003542796359675536,
"alias": "gat"
},
"gat_algebra": {
"alias": " - gat_algebra",
"acc,none": 0.2571428571428571,
"acc_stderr,none": 0.008420562208967575
},
"gat_analogy": {
"alias": " - gat_analogy",
"acc,none": 0.24553734061930782,
"acc_stderr,none": 0.008216476082874105
},
"gat_arithmetic": {
"alias": " - gat_arithmetic",
"acc,none": 0.26573426573426573,
"acc_stderr,none": 0.008475894211016492
},
"gat_association": {
"alias": " - gat_association",
"acc,none": 0.24019138755980862,
"acc_stderr,none": 0.013221495215360054
},
"gat_comparisons": {
"alias": " - gat_comparisons",
"acc,none": 0.319672131147541,
"acc_stderr,none": 0.013357022766710734
},
"gat_completion": {
"alias": " - gat_completion",
"acc,none": 0.27520661157024795,
"acc_stderr,none": 0.012844683062506254
},
"gat_contextual": {
"alias": " - gat_contextual",
"acc,none": 0.26993865030674846,
"acc_stderr,none": 0.01229815625441917
},
"gat_geometry": {
"alias": " - gat_geometry",
"acc,none": 0.2876712328767123,
"acc_stderr,none": 0.023726723391354485
},
"gat_reading": {
"alias": " - gat_reading",
"acc,none": 0.3568998109640832,
"acc_stderr,none": 0.009317121354774414
}
},
"groups": {
"gat": {
"acc,none": 0.27994481374639407,
"acc_stderr,none": 0.003542796359675536,
"alias": "gat"
}
},
"group_subtasks": {
"gat": [
"gat_analogy",
"gat_association",
"gat_completion",
"gat_reading",
"gat_algebra",
"gat_arithmetic",
"gat_comparisons",
"gat_contextual",
"gat_geometry"
]
},
"configs": {
"gat_algebra": {
"task": "gat_algebra",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "algebra",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_analogy": {
"task": "gat_analogy",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "analogy",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_arithmetic": {
"task": "gat_arithmetic",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "arithmetic",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_association": {
"task": "gat_association",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "association",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_comparisons": {
"task": "gat_comparisons",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "comparisons",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_completion": {
"task": "gat_completion",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "completion",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_contextual": {
"task": "gat_contextual",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "contextual",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "\u0627\u0648\u062c\u062f \u0627\u0644\u062e\u0637\u0623 \u0627\u0644\u0633\u064a\u0627\u0642\u064a \u0641\u064a \u0627\u0644\u0639\u0628\u0627\u0631\u0629 \u0627\u0644\u062a\u0627\u0644\u064a\u0629 \u0645\u0646 \u0628\u064a\u0646 \u0627\u0644\u062e\u064a\u0627\u0631\u0627\u062a:",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_geometry": {
"task": "gat_geometry",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "geometry",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_reading": {
"task": "gat_reading",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "reading",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
}
},
"versions": {
"gat": 0,
"gat_algebra": 0.0,
"gat_analogy": 0.0,
"gat_arithmetic": 0.0,
"gat_association": 0.0,
"gat_comparisons": 0.0,
"gat_completion": 0.0,
"gat_contextual": 0.0,
"gat_geometry": 0.0,
"gat_reading": 0.0
},
"n-shot": {
"gat_algebra": 0,
"gat_analogy": 0,
"gat_arithmetic": 0,
"gat_association": 0,
"gat_comparisons": 0,
"gat_completion": 0,
"gat_contextual": 0,
"gat_geometry": 0,
"gat_reading": 0
},
"higher_is_better": {
"gat": {
"acc": true
},
"gat_algebra": {
"acc": true
},
"gat_analogy": {
"acc": true
},
"gat_arithmetic": {
"acc": true
},
"gat_association": {
"acc": true
},
"gat_comparisons": {
"acc": true
},
"gat_completion": {
"acc": true
},
"gat_contextual": {
"acc": true
},
"gat_geometry": {
"acc": true
},
"gat_reading": {
"acc": true
}
},
"n-samples": {
"gat_analogy": {
"original": 2745,
"effective": 2745
},
"gat_association": {
"original": 1045,
"effective": 1045
},
"gat_completion": {
"original": 1210,
"effective": 1210
},
"gat_reading": {
"original": 2645,
"effective": 2645
},
"gat_algebra": {
"original": 2695,
"effective": 2695
},
"gat_arithmetic": {
"original": 2717,
"effective": 2717
},
"gat_comparisons": {
"original": 1220,
"effective": 1220
},
"gat_contextual": {
"original": 1304,
"effective": 1304
},
"gat_geometry": {
"original": 365,
"effective": 365
}
},
"config": {
"model": "hf",
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7455550464,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
"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": "5e10e017",
"date": 1736891004.0192773,
"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": "4.48.0",
"upper_git_hash": "f64fe2f2a86055aaecced603b56097fd79201711",
"tokenizer_pad_token": [
"<|pad|>",
"2023"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"11"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 11,
"max_length": 32768,
"task_hashes": {
"gat_analogy": "04ac010c48ed039457058b512b7ac0586c7c76a628da7caaf9aeb8f3e99ae5e3",
"gat_association": "2cbd868d220125bfcc54ae738592ad902191e4b7f804ce1772ae29e2d3bb3bf6",
"gat_completion": "74cf159ef4a3455a6a0e984fed8e9e9a12f0dc21fde95c2058216c5a711a4d31",
"gat_reading": "6f21934e536e7dca65361d01e5cafc27f8070c4f0dccf5a88c1fe071194b78a4",
"gat_algebra": "20750c926608570eaf87d29981e5ab49b2b097bd52d7f749c44ab4e175d9fdd2",
"gat_arithmetic": "c4b0c73c269d9eb3e8482fbda42e69191c28b95e75e1517d5f9142c6ef410204",
"gat_comparisons": "88bc22db186a50cab28938ec1fc332366fa0bc886bc98edf810cc9ae938405db",
"gat_contextual": "b8e88ff29b62b54eb834dca696304ca0fe1ce55d5cf7d0a9f0204456e3955be6",
"gat_geometry": "229545188469d0512a3297737f4ec7afe88d8a30e7e04f87b4982548e83b1e56"
},
"model_source": "hf",
"model_name": "tiiuae/Falcon3-7B-Instruct",
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 601254.206185867,
"end_time": 601373.470204397,
"total_evaluation_time_seconds": "119.26401853002608"
}

127
evaluations/ar/Falcon3-7B-Instruct/moe_ien_mcq_0_shot.json Normal file
View File

@@ -0,0 +1,127 @@
{
"results": {
"moe_ien_mcq": {
"alias": "moe_ien_mcq",
"acc,none": 0.5265265265265265,
"acc_stderr,none": 0.004995706870392996,
"acc_norm,none": 0.5265265265265265,
"acc_norm_stderr,none": 0.004995706870392996
}
},
"group_subtasks": {
"moe_ien_mcq": []
},
"configs": {
"moe_ien_mcq": {
"task": "moe_ien_mcq",
"dataset_path": "lm_eval/tasks/moe_ien_mcq/ien_moe_mcq.py",
"dataset_name": "moe_ien_mcq",
"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 def remove_prefix(choice):\n return choice.split(\". \", 1)[1] if \". \" in choice else choice\n\n def format_example(doc, keys):\n question = doc[\"Question\"].strip()\n \n choices = \"\".join(\n [f\"{key}. {remove_prefix(choice)}\\n\" for key, choice in zip(keys, doc[\"Choices\"])]\n \n )\n prompt = f\"\\n\\n\u0633\u0624\u0627\u0644: {question}\\n{choices} \\n\u0627\u062c\u0627\u0628\u0629:\"\n return prompt\n\n keys = [\"A\", \"B\", \"C\", \"D\", \"E\", \"F\"][0:len(doc[\"Choices\"])]\n out_doc = {\n \"Query\": format_example(doc, keys), \n \"Choices\": keys,\n \"gold\": int(doc[\"Answer\"])-1, ## \n } \n return out_doc\n \n return dataset.map(_process_docs)\n",
"doc_to_text": "Query",
"doc_to_target": "gold",
"doc_to_choice": "{{Choices}}",
"description": "\u0641\u064a\u0645\u0627\u202f\u064a\u0644\u064a\u202f\u0623\u0633\u0626\u0644\u0629\u202f\u0627\u0644\u0627\u062e\u062a\u064a\u0627\u0631\u202f\u0645\u0646\u202f\u0645\u062a\u0639\u062f\u062f\u202f(\u0645\u0639\u202f\u0627\u0644\u0625\u062c\u0627\u0628\u0627\u062a)\u202f\u0641\u064a\u202f{{Subject}}",
"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": true,
"doc_to_decontamination_query": "Query",
"metadata": {
"version": 0.0
}
}
},
"versions": {
"moe_ien_mcq": 0.0
},
"n-shot": {
"moe_ien_mcq": 0
},
"higher_is_better": {
"moe_ien_mcq": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"moe_ien_mcq": {
"original": 9990,
"effective": 9990
}
},
"config": {
"model": "hf",
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7455550464,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
"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": 1739620378.768502,
"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": [
"<|pad|>",
"2023"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"11"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 11,
"max_length": 32768,
"task_hashes": {
"moe_ien_mcq": "1ae93edb904d572143b5f36dd5dfcc4b901240916d4735ea328083598c912446"
},
"model_source": "hf",
"model_name": "tiiuae/Falcon3-7B-Instruct",
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n{{- '<|system|>\\n' }}\n{%- if messages[0]['role'] == 'system' %}\n{{- messages[0]['content'] }}\n{%- set remaining_messages = messages[1:] %}\n{%- else %}\n{%- set remaining_messages = messages %}\n{%- endif %}\n{{- 'You are a Falcon assistant skilled in function calling. You are helpful, respectful, and concise.\\n\\n# Tools\\n\\nYou have access to the following functions. You MUST use them to answer questions when needed. For each function call, you MUST return a JSON object inside <tool_call></tool_call> tags.\\n\\n<tools>' + tools|tojson(indent=2) + '</tools>\\n\\n# Output Format\\n\\nYour response MUST follow this format when making function calls:\\n<tool_call>\\n[\\n {\"name\": \"function_name\", \"arguments\": {\"arg1\": \"value1\", \"arg2\": \"value2\"}},\\n {\"name\": \"another_function\", \"arguments\": {\"arg\": \"value\"}}\\n]\\n</tool_call>\\nIf no function calls are needed, respond normally without the tool_call tags.\\n' }}\n{%- for message in remaining_messages %}\n{%- if message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if message.content %}\n{{- '<|assistant|>\\n' + message['content'] }}\n{%- endif %}\n{%- if message.tool_calls %}\n{{- '\\n<tool_call>\\n' }}\n{{- message.tool_calls|tojson(indent=2) }}\n{{- '\\n</tool_call>' }}\n{%- endif %}\n{{- eos_token + '\\n' }}\n{%- elif message['role'] == 'tool' %}\n{{- '<|assistant|>\\n<tool_response>\\n' + message['content'] + '\\n</tool_response>\\n' }}\n{%- endif %}\n{%- endfor %}\n{{- '<|assistant|>\\n' if add_generation_prompt }}\n{%- else %}\n{%- for message in messages %}\n{%- if message['role'] == 'system' %}\n{{- '<|system|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if not loop.last %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token + '\\n' }}\n{%- else %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token }}\n{%- endif %}\n{%- endif %}\n{%- if loop.last and add_generation_prompt %}\n{{- '<|assistant|>\\n' }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}",
"chat_template_sha": "914ccd80356f5822d1a50d97546e37f60c04ed831fe431aa40346574ec266901",
"start_time": 1395061.894176973,
"end_time": 1395336.684131379,
"total_evaluation_time_seconds": "274.78995440597646"
}

129
evaluations/ar/Falcon3-7B-Instruct/moe_ien_tf_0_shot.json Normal file
View File

@@ -0,0 +1,129 @@
{
"results": {
"moe_ien_tf": {
"alias": "moe_ien_tf",
"acc,none": 0.576335222393955,
"acc_stderr,none": 0.006476086786980228,
"acc_norm,none": 0.576335222393955,
"acc_norm_stderr,none": 0.006476086786980228
}
},
"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=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7455550464,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
"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": 1739620722.9521024,
"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": [
"<|pad|>",
"2023"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"11"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 11,
"max_length": 32768,
"task_hashes": {
"moe_ien_tf": "ed81617ccb178d095c9a81fef15f5ba8b655782b26d36117f53c38b0a84e62e5"
},
"model_source": "hf",
"model_name": "tiiuae/Falcon3-7B-Instruct",
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n{{- '<|system|>\\n' }}\n{%- if messages[0]['role'] == 'system' %}\n{{- messages[0]['content'] }}\n{%- set remaining_messages = messages[1:] %}\n{%- else %}\n{%- set remaining_messages = messages %}\n{%- endif %}\n{{- 'You are a Falcon assistant skilled in function calling. You are helpful, respectful, and concise.\\n\\n# Tools\\n\\nYou have access to the following functions. You MUST use them to answer questions when needed. For each function call, you MUST return a JSON object inside <tool_call></tool_call> tags.\\n\\n<tools>' + tools|tojson(indent=2) + '</tools>\\n\\n# Output Format\\n\\nYour response MUST follow this format when making function calls:\\n<tool_call>\\n[\\n {\"name\": \"function_name\", \"arguments\": {\"arg1\": \"value1\", \"arg2\": \"value2\"}},\\n {\"name\": \"another_function\", \"arguments\": {\"arg\": \"value\"}}\\n]\\n</tool_call>\\nIf no function calls are needed, respond normally without the tool_call tags.\\n' }}\n{%- for message in remaining_messages %}\n{%- if message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if message.content %}\n{{- '<|assistant|>\\n' + message['content'] }}\n{%- endif %}\n{%- if message.tool_calls %}\n{{- '\\n<tool_call>\\n' }}\n{{- message.tool_calls|tojson(indent=2) }}\n{{- '\\n</tool_call>' }}\n{%- endif %}\n{{- eos_token + '\\n' }}\n{%- elif message['role'] == 'tool' %}\n{{- '<|assistant|>\\n<tool_response>\\n' + message['content'] + '\\n</tool_response>\\n' }}\n{%- endif %}\n{%- endfor %}\n{{- '<|assistant|>\\n' if add_generation_prompt }}\n{%- else %}\n{%- for message in messages %}\n{%- if message['role'] == 'system' %}\n{{- '<|system|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if not loop.last %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token + '\\n' }}\n{%- else %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token }}\n{%- endif %}\n{%- endif %}\n{%- if loop.last and add_generation_prompt %}\n{{- '<|assistant|>\\n' }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}",
"chat_template_sha": "914ccd80356f5822d1a50d97546e37f60c04ed831fe431aa40346574ec266901",
"start_time": 1395406.00589162,
"end_time": 1395704.54657667,
"total_evaluation_time_seconds": "298.54068504995666"
}

2711
evaluations/ar/Falcon3-7B-Instruct/openaimmlu_0_shot.json Normal file
View File

File diff suppressed because it is too large Load Diff