Files
stability-ai--stablelm/evals/stablelm-base-alpha-7b.json
2026-07-13 12:45:13 +08:00

91 lines
2.8 KiB
JSON

{
"results": {
"arc_challenge": {
"acc": 0.24829351535836178,
"acc_stderr": 0.012624912868089755,
"acc_norm": 0.27047781569965873,
"acc_norm_stderr": 0.012980954547659556
},
"arc_easy": {
"acc": 0.5054713804713805,
"acc_stderr": 0.01025916922861504,
"acc_norm": 0.44865319865319864,
"acc_norm_stderr": 0.010205540414612876
},
"boolq": {
"acc": 0.600611620795107,
"acc_stderr": 0.008566178448007831
},
"hellaswag": {
"acc": 0.3467436765584545,
"acc_stderr": 0.004749606196363328,
"acc_norm": 0.41216889065923124,
"acc_norm_stderr": 0.004912192800263316
},
"lambada_openai": {
"ppl": 9.459674222745228,
"ppl_stderr": 0.33183598007493614,
"acc": 0.5511352610130021,
"acc_stderr": 0.006929452414790843
},
"openbookqa": {
"acc": 0.214,
"acc_stderr": 0.018359797502387025,
"acc_norm": 0.32,
"acc_norm_stderr": 0.02088234048876181
},
"piqa": {
"acc": 0.6675734494015234,
"acc_stderr": 0.010991141557445587,
"acc_norm": 0.6735582154515778,
"acc_norm_stderr": 0.010940467046177304
},
"sciq": {
"acc": 0.801,
"acc_stderr": 0.012631649083099177,
"acc_norm": 0.697,
"acc_norm_stderr": 0.014539683710535257
},
"siqa": {
"acc": 0.394575230296827,
"acc_stderr": 0.011059713589720797,
"acc_norm": 0.4140225179119754,
"acc_norm_stderr": 0.011145545345176117
},
"truthfulqa_mc": {
"mc1": 0.23745410036719705,
"mc1_stderr": 0.014896277441041836,
"mc2": 0.3995908363542637,
"mc2_stderr": 0.014371652685680641
},
"winogrande": {
"acc": 0.5011838989739542,
"acc_stderr": 0.014052446290529012
}
},
"versions": {
"arc_challenge": 0,
"arc_easy": 0,
"boolq": 1,
"hellaswag": 0,
"lambada_openai": 0,
"openbookqa": 0,
"piqa": 0,
"sciq": 0,
"siqa": 0,
"truthfulqa_mc": 1,
"winogrande": 0
},
"config": {
"model": "gpt2",
"model_args": "use_fast=True,pretrained=stabilityai/stablelm-base-alpha-7b,trust_remote_code=True,low_cpu_mem_usage=True,dtype=auto",
"num_fewshot": 0,
"batch_size": "2",
"batch_sizes": [],
"device": "cuda:1",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}