Unverified Commit 4fbbd60f authored by Hailey Schoelkopf's avatar Hailey Schoelkopf Committed by GitHub
Browse files

Merge pull request #718 from EleutherAI/remove-results-folder

Remove Results folder temporarily
parents 5e59782e 1b9833dd
This diff is collapsed.
{
"results": {
"arc_challenge": {
"acc": 0.439419795221843,
"acc_stderr": 0.014503747823580122,
"acc_norm": 0.4462457337883959,
"acc_norm_stderr": 0.014526705548539982
},
"prost": {
"acc": 0.2688941076003416,
"acc_stderr": 0.0032393206239968247,
"acc_norm": 0.3052412467976089,
"acc_norm_stderr": 0.003364432149066356
},
"swag": {
"acc": 0.5673298010596821,
"acc_stderr": 0.003502894135944166,
"acc_norm": 0.6934919524142757,
"acc_norm_stderr": 0.0032596605453371346
},
"arc_easy": {
"acc": 0.7457912457912458,
"acc_stderr": 0.008934537681141528,
"acc_norm": 0.5989057239057239,
"acc_norm_stderr": 0.010057051106534378
},
"boolq": {
"acc": 0.6850152905198776,
"acc_stderr": 0.00812432724981665
},
"wsc273": {
"acc": 0.8608058608058609,
"acc_stderr": 0.020988366070851
},
"mc_taco": {
"em": 0.10960960960960961,
"f1": 0.4753174430074593
},
"piqa": {
"acc": 0.7883569096844396,
"acc_stderr": 0.009530351270479397,
"acc_norm": 0.7910772578890098,
"acc_norm_stderr": 0.009485227030105093
},
"hellaswag": {
"acc": 0.5910177255526787,
"acc_stderr": 0.004906411984476791,
"acc_norm": 0.7623979286994622,
"acc_norm_stderr": 0.004247442237702478
},
"winogrande": {
"acc": 0.7016574585635359,
"acc_stderr": 0.012858885010030434
},
"copa": {
"acc": 0.9,
"acc_stderr": 0.030151134457776348
},
"openbookqa": {
"acc": 0.306,
"acc_stderr": 0.020629569998345403,
"acc_norm": 0.422,
"acc_norm_stderr": 0.022109039310618552
}
},
"versions": {
"arc_challenge": 0,
"prost": 0,
"swag": 0,
"arc_easy": 0,
"boolq": 1,
"wsc273": 0,
"mc_taco": 0,
"piqa": 0,
"hellaswag": 0,
"winogrande": 0,
"copa": 0,
"openbookqa": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=/gaueko1/hizkuntza-ereduak/LLaMA/lm/huggingface/13B,use_accelerate=True",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda:0",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
{
"results": {
"mnli_mismatched": {
"acc": 0.45351912123677784,
"acc_stderr": 0.005020956265665617
},
"wnli": {
"acc": 0.4647887323943662,
"acc_stderr": 0.0596130578497224
},
"sst": {
"acc": 0.6536697247706422,
"acc_stderr": 0.01612186710508361
},
"cola": {
"mcc": 0.0,
"mcc_stderr": 0.0
},
"mnli": {
"acc": 0.43555781966377993,
"acc_stderr": 0.005005063722742048
},
"qnli": {
"acc": 0.4995423759838916,
"acc_stderr": 0.006765407718154766
},
"mrpc": {
"acc": 0.6862745098039216,
"acc_stderr": 0.022999936277943434,
"f1": 0.8134110787172011,
"f1_stderr": 0.01621238238910757
},
"rte": {
"acc": 0.6534296028880866,
"acc_stderr": 0.02864445699455754
},
"qqp": {
"acc": 0.3679198614889933,
"acc_stderr": 0.0023983700314094665,
"f1": 0.5365853658536586,
"f1_stderr": 0.0025607085094365924
}
},
"versions": {
"mnli_mismatched": 0,
"wnli": 1,
"sst": 0,
"cola": 0,
"mnli": 0,
"qnli": 0,
"mrpc": 0,
"rte": 0,
"qqp": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=/gaueko1/hizkuntza-ereduak/LLaMA/lm/huggingface/13B,use_accelerate=True",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda:0",
"no_cache": false,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
{
"results": {
"gsm8k": {
"acc": 0.13570887035633056,
"acc_stderr": 0.009433577908567345
}
},
"versions": {
"gsm8k": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=/gaueko1/hizkuntza-ereduak/LLaMA/lm/huggingface/13B,use_accelerate=True",
"num_fewshot": 8,
"batch_size": "auto",
"device": "cuda",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
{
"results": {
"lambada_openai": {
"ppl": 1279051.053451683,
"ppl_stderr": 60995.62964377304,
"acc": 0.0,
"acc_stderr": 0.0
},
"lambada_openai_mt_de": {
"ppl": 1310285.4433720284,
"ppl_stderr": 71395.90633942866,
"acc": 0.0,
"acc_stderr": 0.0
},
"lambada_openai_mt_it": {
"ppl": 4091504.352954044,
"ppl_stderr": 218020.965277226,
"acc": 0.0,
"acc_stderr": 0.0
},
"lambada_standard": {
"ppl": 1409047.9981006894,
"ppl_stderr": 47832.883755899915,
"acc": 0.0,
"acc_stderr": 0.0
},
"lambada_standard_cloze": {
"ppl": 4235345.031433833,
"ppl_stderr": 132892.5654001927,
"acc": 0.0,
"acc_stderr": 0.0
},
"lambada_openai_mt_fr": {
"ppl": 2461448.491005768,
"ppl_stderr": 128013.98724687536,
"acc": 0.0,
"acc_stderr": 0.0
},
"lambada_openai_cloze": {
"ppl": 204515.38946166556,
"ppl_stderr": 9705.341358126625,
"acc": 0.00019406171162429653,
"acc_stderr": 0.00019406171162430135
},
"lambada_openai_mt_en": {
"ppl": 1279051.053451683,
"ppl_stderr": 60995.62964377304,
"acc": 0.0,
"acc_stderr": 0.0
},
"lambada_openai_mt_es": {
"ppl": 1980241.7718905837,
"ppl_stderr": 101614.2034914904,
"acc": 0.0,
"acc_stderr": 0.0
}
},
"versions": {
"lambada_openai": 0,
"lambada_openai_mt_de": 0,
"lambada_openai_mt_it": 0,
"lambada_standard": 0,
"lambada_standard_cloze": 0,
"lambada_openai_mt_fr": 0,
"lambada_openai_cloze": 0,
"lambada_openai_mt_en": 0,
"lambada_openai_mt_es": 0
},
"config": {
"model": "hf-causal-experimental",
"model_args": "pretrained=/gaueko1/hizkuntza-ereduak/LLaMA/lm/huggingface/13B",
"num_fewshot": 0,
"batch_size": "auto",
"device": "cuda:0",
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment