| { |
| "results": { |
| "hellaswag": { |
| "name": "hellaswag", |
| "alias": "hellaswag", |
| "sample_len": 10042, |
| "acc,none": 0.36875124477195775, |
| "acc_stderr,none": 0.004814803098436572, |
| "acc_norm,none": 0.4676359290977893, |
| "acc_norm_stderr,none": 0.004979317515432586 |
| }, |
| "arc_easy": { |
| "name": "arc_easy", |
| "alias": "arc_easy", |
| "sample_len": 2376, |
| "acc,none": 0.5534511784511784, |
| "acc_stderr,none": 0.010200990076245288, |
| "acc_norm,none": 0.5408249158249159, |
| "acc_norm_stderr,none": 0.010225526906982679 |
| }, |
| "arc_challenge": { |
| "name": "arc_challenge", |
| "alias": "arc_challenge", |
| "sample_len": 1172, |
| "acc,none": 0.2935153583617747, |
| "acc_stderr,none": 0.013307250444941061, |
| "acc_norm,none": 0.3199658703071672, |
| "acc_norm_stderr,none": 0.013631345807016129 |
| }, |
| "piqa": { |
| "name": "piqa", |
| "alias": "piqa", |
| "sample_len": 1838, |
| "acc,none": 0.6926006528835691, |
| "acc_stderr,none": 0.010765602506938959, |
| "acc_norm,none": 0.7094668117519043, |
| "acc_norm_stderr,none": 0.010592765034696548 |
| } |
| }, |
| "group_subtasks": {}, |
| "configs": { |
| "arc_challenge": { |
| "task": "arc_challenge", |
| "dataset_path": "allenai/ai2_arc", |
| "dataset_name": "ARC-Challenge", |
| "training_split": "train", |
| "validation_split": "validation", |
| "test_split": "test", |
| "doc_to_text": "Question: {{question}}\nAnswer:", |
| "doc_to_target": "{{choices.label.index(answerKey)}}", |
| "unsafe_code": false, |
| "doc_to_choice": "{{choices.text}}", |
| "description": "", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "default", |
| "split": null, |
| "process_docs": null, |
| "fewshot_indices": null, |
| "samples": null, |
| "doc_to_text": "Question: {{question}}\nAnswer:", |
| "doc_to_choice": "{{choices.text}}", |
| "doc_to_target": "{{choices.label.index(answerKey)}}", |
| "gen_prefix": null, |
| "fewshot_delimiter": "\n\n", |
| "target_delimiter": " " |
| }, |
| "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: {{question}}\nAnswer:", |
| "metadata": { |
| "version": 1.0, |
| "pretrained": "solintellegence/sol-pro", |
| "revision": "a22f3539b43e0450850748ce445849a06c9c64d6", |
| "dtype": "float32", |
| "trust_remote_code": true, |
| "config_source": "/tmp/uv-venv/lib/python3.13/site-packages/lm_eval/tasks/arc/arc_challenge.yaml" |
| } |
| }, |
| "arc_easy": { |
| "task": "arc_easy", |
| "dataset_path": "allenai/ai2_arc", |
| "dataset_name": "ARC-Easy", |
| "training_split": "train", |
| "validation_split": "validation", |
| "test_split": "test", |
| "doc_to_text": "Question: {{question}}\nAnswer:", |
| "doc_to_target": "{{choices.label.index(answerKey)}}", |
| "unsafe_code": false, |
| "doc_to_choice": "{{choices.text}}", |
| "description": "", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "default", |
| "split": null, |
| "process_docs": null, |
| "fewshot_indices": null, |
| "samples": null, |
| "doc_to_text": "Question: {{question}}\nAnswer:", |
| "doc_to_choice": "{{choices.text}}", |
| "doc_to_target": "{{choices.label.index(answerKey)}}", |
| "gen_prefix": null, |
| "fewshot_delimiter": "\n\n", |
| "target_delimiter": " " |
| }, |
| "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: {{question}}\nAnswer:", |
| "metadata": { |
| "version": 1.0, |
| "pretrained": "solintellegence/sol-pro", |
| "revision": "a22f3539b43e0450850748ce445849a06c9c64d6", |
| "dtype": "float32", |
| "trust_remote_code": true, |
| "config_source": "/tmp/uv-venv/lib/python3.13/site-packages/lm_eval/tasks/arc/arc_easy.yaml" |
| } |
| }, |
| "hellaswag": { |
| "task": "hellaswag", |
| "dataset_path": "Rowan/hellaswag", |
| "training_split": "train", |
| "validation_split": "validation", |
| "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n out_doc = {\n \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n \"gold\": int(doc[\"label\"]),\n }\n return out_doc\n\n return dataset.map(_process_doc)\n", |
| "doc_to_text": "{{query}}", |
| "doc_to_target": "{{label}}", |
| "unsafe_code": false, |
| "doc_to_choice": "choices", |
| "description": "", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "default", |
| "split": null, |
| "process_docs": "<function process_docs at 0x7fec604482c0>", |
| "fewshot_indices": null, |
| "samples": null, |
| "doc_to_text": "{{query}}", |
| "doc_to_choice": "choices", |
| "doc_to_target": "{{label}}", |
| "gen_prefix": null, |
| "fewshot_delimiter": "\n\n", |
| "target_delimiter": " " |
| }, |
| "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": 1.0, |
| "pretrained": "solintellegence/sol-pro", |
| "revision": "a22f3539b43e0450850748ce445849a06c9c64d6", |
| "dtype": "float32", |
| "trust_remote_code": true, |
| "config_source": "/tmp/uv-venv/lib/python3.13/site-packages/lm_eval/tasks/hellaswag/hellaswag.yaml" |
| } |
| }, |
| "piqa": { |
| "task": "piqa", |
| "dataset_path": "baber/piqa", |
| "training_split": "train", |
| "validation_split": "validation", |
| "doc_to_text": "Question: {{goal}}\nAnswer:", |
| "doc_to_target": "label", |
| "unsafe_code": false, |
| "doc_to_choice": "{{[sol1, sol2]}}", |
| "description": "", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "default", |
| "split": null, |
| "process_docs": null, |
| "fewshot_indices": null, |
| "samples": null, |
| "doc_to_text": "Question: {{goal}}\nAnswer:", |
| "doc_to_choice": "{{[sol1, sol2]}}", |
| "doc_to_target": "label", |
| "gen_prefix": null, |
| "fewshot_delimiter": "\n\n", |
| "target_delimiter": " " |
| }, |
| "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": "goal", |
| "metadata": { |
| "version": 1.0, |
| "pretrained": "solintellegence/sol-pro", |
| "revision": "a22f3539b43e0450850748ce445849a06c9c64d6", |
| "dtype": "float32", |
| "trust_remote_code": true, |
| "config_source": "/tmp/uv-venv/lib/python3.13/site-packages/lm_eval/tasks/piqa/piqa.yaml" |
| } |
| } |
| }, |
| "versions": { |
| "arc_challenge": 1.0, |
| "arc_easy": 1.0, |
| "hellaswag": 1.0, |
| "piqa": 1.0 |
| }, |
| "n-shot": { |
| "arc_challenge": 0, |
| "arc_easy": 0, |
| "hellaswag": 0, |
| "piqa": 0 |
| }, |
| "higher_is_better": { |
| "arc_challenge": { |
| "acc": true, |
| "acc_norm": true |
| }, |
| "arc_easy": { |
| "acc": true, |
| "acc_norm": true |
| }, |
| "hellaswag": { |
| "acc": true, |
| "acc_norm": true |
| }, |
| "piqa": { |
| "acc": true, |
| "acc_norm": true |
| } |
| }, |
| "n-samples": { |
| "hellaswag": { |
| "original": 10042, |
| "effective": 10042 |
| }, |
| "arc_easy": { |
| "original": 2376, |
| "effective": 2376 |
| }, |
| "arc_challenge": { |
| "original": 1172, |
| "effective": 1172 |
| }, |
| "piqa": { |
| "original": 1838, |
| "effective": 1838 |
| } |
| }, |
| "config": { |
| "model": "hf", |
| "model_args": { |
| "pretrained": "solintellegence/sol-pro", |
| "revision": "a22f3539b43e0450850748ce445849a06c9c64d6", |
| "dtype": "float32", |
| "trust_remote_code": true |
| }, |
| "model_num_parameters": 138037594, |
| "model_dtype": "torch.float32", |
| "model_revision": "a22f3539b43e0450850748ce445849a06c9c64d6", |
| "model_sha": "a22f3539b43e0450850748ce445849a06c9c64d6", |
| "batch_size": "64", |
| "batch_sizes": [], |
| "device": "cuda:0", |
| "use_cache": null, |
| "limit": null, |
| "bootstrap_iters": 100000, |
| "gen_kwargs": {}, |
| "random_seed": 0, |
| "numpy_seed": 1234, |
| "torch_seed": 1234, |
| "fewshot_seed": 1234 |
| }, |
| "git_hash": null, |
| "date": 1791420621.7781, |
| "pretty_env_info": "PyTorch version: 2.11.0+cu130\nIs debug build: False\nCUDA used to build PyTorch: 13.0\nROCM used to build PyTorch: N/A\n\nOS: Debian GNU/Linux 13 (trixie) (x86_64)\nGCC version: (Debian 14.2.0-19) 14.2.0\nClang version: Could not collect\nCMake version: Could not collect\nLibc version: glibc-2.41\n\nPython version: 3.13.11 (main, Feb 3 2026, 03:08:54) [GCC 14.2.0] (64-bit runtime)\nPython platform: Linux-4.19.0-gvisor-x86_64-with-glibc2.41\nIs CUDA available: True\nCUDA runtime version: 13.3.73\nCUDA_MODULE_LOADING set to: \nGPU models and configuration: GPU 0: NVIDIA RTX PRO 6000 Blackwell Server Edition\nNvidia driver version: 595.71.05\ncuDNN version: Could not collect\nIs XPU available: False\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\nCaching allocator config: N/A\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 46 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 20\nOn-line CPU(s) list: 0-19\nVendor ID: GenuineIntel\nModel name: unknown\nCPU family: 6\nModel: 207\nThread(s) per core: 1\nCore(s) per socket: 20\nSocket(s): 1\nStepping: unknown\nBogoMIPS: 3785.24\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities\nVirtualization: VT-x\n\nVersions of relevant libraries:\n[pip3] mypy_extensions==1.1.0\n[pip3] numpy==2.5.3\n[pip3] nvidia-cublas==13.1.0.3\n[pip3] nvidia-cuda-cupti==13.0.85\n[pip3] nvidia-cuda-nvrtc==13.0.88\n[pip3] nvidia-cuda-runtime==13.0.96\n[pip3] nvidia-cudnn-cu13==9.19.0.56\n[pip3] nvidia-cufft==12.0.0.61\n[pip3] nvidia-curand==10.4.0.35\n[pip3] nvidia-cusolver==12.0.4.66\n[pip3] nvidia-cusparse==12.6.3.3\n[pip3] nvidia-cusparselt-cu13==0.8.0\n[pip3] nvidia-nccl-cu12==2.30.7\n[pip3] nvidia-nccl-cu13==2.28.9\n[pip3] nvidia-nvjitlink==13.0.88\n[pip3] nvidia-nvtx==13.0.85\n[pip3] onnxruntime==1.27.0\n[pip3] optree==0.19.1\n[pip3] torch==2.11.0\n[pip3] torch_c_dlpack_ext==0.1.5\n[pip3] torchao==0.17.0\n[pip3] torchvision==0.26.0\n[pip3] triton==3.6.0\n[conda] Could not collect", |
| "transformers_version": "5.14.1", |
| "lm_eval_version": "0.4.12", |
| "upper_git_hash": null, |
| "tokenizer_pad_token": [ |
| "<pad>", |
| "3" |
| ], |
| "tokenizer_eos_token": [ |
| "<eos>", |
| "2" |
| ], |
| "tokenizer_bos_token": [ |
| null, |
| "None" |
| ], |
| "eot_token_id": 2, |
| "max_length": 2048, |
| "task_hashes": {}, |
| "model_source": "hf", |
| "model_name": "solintellegence/sol-pro", |
| "model_name_sanitized": "solintellegence__sol-pro", |
| "system_instruction": null, |
| "system_instruction_sha": null, |
| "fewshot_as_multiturn": null, |
| "chat_template": null, |
| "chat_template_sha": null, |
| "total_evaluation_time_seconds": "121.92508437099968" |
| } |
