{ "mode": "FULL", "limit": null, "max_len": 1024, "batch_size": 32, "tasks": [ "hellaswag", "arc_easy", "arc_challenge", "piqa", "winogrande", "openbookqa", "sciq", "boolq", "lambada_openai", "wikitext" ], "versions": { "lm_eval": "0.4.9.1", "transformers": "4.57.1", "torch": "2.11.0+cu130", "datasets": "3.6.0", "tokenizers": "0.22.2", "safetensors": "0.8.0", "huggingface_hub": "0.36.0" }, "cand": "muon-3e-4", "results": { "PicoLM-V4-85M-Instruct (muon 3e-4)": { "tasks": { "hellaswag": { "results": { "alias": "hellaswag", "acc,none": 0.3043218482374029, "acc_stderr,none": 0.004591792612775816, "acc_norm,none": 0.33588926508663614, "acc_norm_stderr,none": 0.004713351500885424 }, "version": 1.0, "n_samples": { "original": 10042, "effective": 10042 } }, "arc_easy": { "results": { "alias": "arc_easy", "acc,none": 0.5505050505050505, "acc_stderr,none": 0.010207308833916014, "acc_norm,none": 0.49663299663299665, "acc_norm_stderr,none": 0.010259550893799069 }, "version": 1.0, "n_samples": { "original": 2376, "effective": 2376 } }, "arc_challenge": { "results": { "alias": "arc_challenge", "acc,none": 0.23122866894197952, "acc_stderr,none": 0.01232085883477234, "acc_norm,none": 0.257679180887372, "acc_norm_stderr,none": 0.012780770562768334 }, "version": 1.0, "n_samples": { "original": 1172, "effective": 1172 } }, "piqa": { "results": { "alias": "piqa", "acc,none": 0.6343852013057671, "acc_stderr,none": 0.01123657167900628, "acc_norm,none": 0.6235038084874864, "acc_norm_stderr,none": 0.011304341550126641 }, "version": 1.0, "n_samples": { "original": 1838, "effective": 1838 } }, "winogrande": { "results": { "alias": "winogrande", "acc,none": 0.500394632991318, "acc_stderr,none": 0.01405248130604961 }, "version": 1.0, "n_samples": { "original": 1267, "effective": 1267 } }, "openbookqa": { "results": { "alias": "openbookqa", "acc,none": 0.226, "acc_stderr,none": 0.01872295644913999, "acc_norm,none": 0.318, "acc_norm_stderr,none": 0.020847571620814014 }, "version": 1.0, "n_samples": { "original": 500, "effective": 500 } }, "sciq": { "results": { "alias": "sciq", "acc,none": 0.8, "acc_stderr,none": 0.012655439943366653, "acc_norm,none": 0.728, "acc_norm_stderr,none": 0.014078856992462642 }, "version": 1.0, "n_samples": { "original": 1000, "effective": 1000 } }, "boolq": { "results": { "alias": "boolq", "acc,none": 0.5694189602446483, "acc_stderr,none": 0.0086603601459887 }, "version": 2.0, "n_samples": { "original": 3270, "effective": 3270 } }, "lambada_openai": { "results": { "alias": "lambada_openai", "perplexity,none": 56.43329490407561, "perplexity_stderr,none": 2.4147160893361925, "acc,none": 0.3021540849990297, "acc_stderr,none": 0.006397437889678647 }, "version": 1.0, "n_samples": { "original": 5153, "effective": 5153 } }, "wikitext": { "results": { "alias": "wikitext", "word_perplexity,none": 46.20592622522113, "word_perplexity_stderr,none": "N/A", "byte_perplexity,none": 2.0478907652821867, "byte_perplexity_stderr,none": "N/A", "bits_per_byte,none": 1.0341387638786332, "bits_per_byte_stderr,none": "N/A" }, "version": 2.0, "n_samples": { "original": 62, "effective": 62 } } }, "seconds": 563 }, "PicoLM-V4-85M Base (yeniden ko\u015fu)": { "tasks": { "hellaswag": { "results": { "alias": "hellaswag", "acc,none": 0.30023899621589323, "acc_stderr,none": 0.004574250396870965, "acc_norm,none": 0.32822146982672773, "acc_norm_stderr,none": 0.004686062421158042 }, "version": 1.0, "n_samples": { "original": 10042, "effective": 10042 } }, "arc_easy": { "results": { "alias": "arc_easy", "acc,none": 0.547979797979798, "acc_stderr,none": 0.010212436978834194, "acc_norm,none": 0.4877946127946128, "acc_norm_stderr,none": 0.010256726235129118 }, "version": 1.0, "n_samples": { "original": 2376, "effective": 2376 } }, "arc_challenge": { "results": { "alias": "arc_challenge", "acc,none": 0.22781569965870307, "acc_stderr,none": 0.012256708602326964, "acc_norm,none": 0.26791808873720135, "acc_norm_stderr,none": 0.012942030195136482 }, "version": 1.0, "n_samples": { "original": 1172, "effective": 1172 } }, "piqa": { "results": { "alias": "piqa", "acc,none": 0.6371055495103374, "acc_stderr,none": 0.011218667570840779, "acc_norm,none": 0.6387377584330794, "acc_norm_stderr,none": 0.011207738849429856 }, "version": 1.0, "n_samples": { "original": 1838, "effective": 1838 } }, "winogrande": { "results": { "alias": "winogrande", "acc,none": 0.5011838989739542, "acc_stderr,none": 0.014052446290528871 }, "version": 1.0, "n_samples": { "original": 1267, "effective": 1267 } }, "openbookqa": { "results": { "alias": "openbookqa", "acc,none": 0.204, "acc_stderr,none": 0.01803936910413861, "acc_norm,none": 0.314, "acc_norm_stderr,none": 0.020776701920308973 }, "version": 1.0, "n_samples": { "original": 500, "effective": 500 } }, "sciq": { "results": { "alias": "sciq", "acc,none": 0.785, "acc_stderr,none": 0.01299784381903183, "acc_norm,none": 0.684, "acc_norm_stderr,none": 0.014709193056057166 }, "version": 1.0, "n_samples": { "original": 1000, "effective": 1000 } }, "boolq": { "results": { "alias": "boolq", "acc,none": 0.591131498470948, "acc_stderr,none": 0.008598573693259202 }, "version": 2.0, "n_samples": { "original": 3270, "effective": 3270 } }, "lambada_openai": { "results": { "alias": "lambada_openai", "perplexity,none": 48.37149598891986, "perplexity_stderr,none": 1.9127391398353888, "acc,none": 0.3120512322918688, "acc_stderr,none": 0.006455101452843129 }, "version": 1.0, "n_samples": { "original": 5153, "effective": 5153 } }, "wikitext": { "results": { "alias": "wikitext", "word_perplexity,none": 38.82775268650654, "word_perplexity_stderr,none": "N/A", "byte_perplexity,none": 1.982337265879765, "byte_perplexity_stderr,none": "N/A", "bits_per_byte,none": 0.9872024370038607, "bits_per_byte_stderr,none": "N/A" }, "version": 2.0, "n_samples": { "original": 62, "effective": 62 } } }, "seconds": 547 } } }