Files
stability-ai--stablelm/evals/external/togethercomputer-RedPajama-INCITE-7B-Base2.json
2023-09-29 18:41:27 -04:00

91 lines
2.3 KiB
JSON
Executable File

{
"results": {
"arc_challenge": {
"acc": 0.3771331058020478,
"acc_stderr": 0.014163366896192593,
"acc_norm": 0.39419795221843,
"acc_norm_stderr": 0.014280522667467323
},
"arc_easy": {
"acc": 0.7234848484848485,
"acc_stderr": 0.00917788010146828,
"acc_norm": 0.6919191919191919,
"acc_norm_stderr": 0.009473887075826333
},
"boolq": {
"acc": 0.7076452599388379,
"acc_stderr": 0.00795527890990574
},
"hellaswag": {
"acc": 0.5256920932085242,
"acc_stderr": 0.004983189711208505,
"acc_norm": 0.7033459470225055,
"acc_norm_stderr": 0.004558491550673688
},
"lambada_openai": {
"ppl": 3.9176883876529036,
"ppl_stderr": 0.08360630042095321,
"acc": 0.713370851930914,
"acc_stderr": 0.006299845944000654
},
"openbookqa": {
"acc": 0.29,
"acc_stderr": 0.020313179231745186,
"acc_norm": 0.406,
"acc_norm_stderr": 0.021983962090086333
},
"piqa": {
"acc": 0.7714907508161044,
"acc_stderr": 0.009796313511829524,
"acc_norm": 0.7736670293797606,
"acc_norm_stderr": 0.009763294246879415
},
"sciq": {
"acc": 0.927,
"acc_stderr": 0.008230354715244055,
"acc_norm": 0.897,
"acc_norm_stderr": 0.009616833339695796
},
"siqa": {
"acc": 0.4257932446264074,
"acc_stderr": 0.011188771652377858,
"acc_norm": 0.44882292732855683,
"acc_norm_stderr": 0.011254649314820132
},
"truthfulqa_mc": {
"mc1": 0.23011015911872704,
"mc1_stderr": 0.014734557959807769,
"mc2": 0.3301333660822527,
"mc2_stderr": 0.012995959559501016
},
"winogrande": {
"acc": 0.6432517758484609,
"acc_stderr": 0.013463393958028733
}
},
"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=togethercomputer/RedPajama-INCITE-7B-Base,low_cpu_mem_usage=True,dtype=auto",
"num_fewshot": 0,
"batch_size": "8",
"batch_sizes": [],
"device": "cuda:2",
"no_cache": false,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}