Files
2026-07-13 12:45:13 +08:00

84 lines
2.5 KiB
JSON
Executable File

{
"results": {
"arc_challenge": {
"acc": 0.27986348122866894,
"acc_stderr": 0.013119040897725922,
"acc_norm": 0.3037542662116041,
"acc_norm_stderr": 0.013438909184778757
},
"arc_easy": {
"acc": 0.5942760942760943,
"acc_stderr": 0.010075755540128871,
"acc_norm": 0.5328282828282829,
"acc_norm_stderr": 0.010237645778853869
},
"boolq": {
"acc": 0.617125382262997,
"acc_stderr": 0.008501734385335953
},
"hellaswag": {
"acc": 0.4137621987651862,
"acc_stderr": 0.004915003499517833,
"acc_norm": 0.545309699263095,
"acc_norm_stderr": 0.004969251445596341
},
"lambada_openai": {
"ppl": 9.094700256232823,
"ppl_stderr": 0.2652067493709512,
"acc": 0.5173685231903745,
"acc_stderr": 0.006961773596960152
},
"openbookqa": {
"acc": 0.218,
"acc_stderr": 0.01848337822317886,
"acc_norm": 0.322,
"acc_norm_stderr": 0.020916668330019882
},
"piqa": {
"acc": 0.705658324265506,
"acc_stderr": 0.010633311470347498,
"acc_norm": 0.7067464635473341,
"acc_norm_stderr": 0.010621818421101931
},
"sciq": {
"acc": 0.891,
"acc_stderr": 0.009859828407037191,
"acc_norm": 0.816,
"acc_norm_stderr": 0.012259457340938588
},
"siqa": {
"acc": 0.4017400204708291,
"acc_stderr": 0.011093444192711183,
"acc_norm": 0.4314227226202661,
"acc_norm_stderr": 0.011207148736838392
},
"winogrande": {
"acc": 0.584846093133386,
"acc_stderr": 0.01384868408665859
}
},
"versions": {
"arc_challenge": 0,
"arc_easy": 0,
"boolq": 1,
"hellaswag": 0,
"lambada_openai": 0,
"openbookqa": 0,
"piqa": 0,
"sciq": 0,
"siqa": 0,
"winogrande": 0
},
"config": {
"model": "gpt2",
"model_args": "use_fast=True,pretrained=bigscience/bloom-3b,trust_remote_code=True,low_cpu_mem_usage=True,dtype=auto",
"num_fewshot": 0,
"batch_size": "8",
"batch_sizes": [],
"device": null,
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}