lm1-misc-pile / 8b712b12b /evaluation /generation /slim.limited=3000.model=lm1-8b7-12b.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json
Muennighoff's picture
Add
66cf324
raw
history blame contribute delete
No virus
4.01 kB
{
"results": [
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"bleu": 0.36573098571999374,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"bleu_stderr": 0.04360246560901712
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rouge1_precision": 0.09072268249056871,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rouge1_precision_stderr": 0.003309127881928078
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rouge1_recall": 0.2567858530968384,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rouge1_recall_stderr": 0.004292381643415595
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rouge1_fmeasure": 0.11134690296906873,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rouge1_fmeasure_stderr": 0.002791584141599169
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rouge2_precision": 0.04188174110659927,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rouge2_precision_stderr": 0.00201017336799391
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rouge2_recall": 0.12225529287536878,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rouge2_recall_stderr": 0.0029565428717282195
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rouge2_fmeasure": 0.05139255155957873,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rouge2_fmeasure_stderr": 0.0017044945884763974
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rougeL_precision": 0.0820576144802433,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rougeL_precision_stderr": 0.002849358571939298
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rougeL_recall": 0.24398283648869387,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rougeL_recall_stderr": 0.004010077159680049
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rougeL_fmeasure": 0.1024427565171009,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rougeL_fmeasure_stderr": 0.002361887124438967
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rougeLsum_precision": 0.08363859011376361,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rougeLsum_precision_stderr": 0.0029610562342101215
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rougeLsum_recall": 0.24452543427182877,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rougeLsum_recall_stderr": 0.00401534422341755
},
{
"task_name": "GEM/web_nlg_en",
"prompt_name": "PALM_prompt",
"rougeLsum_fmeasure": 0.10363166429373906,
"dataset_path": "GEM/web_nlg",
"dataset_name": "en",
"subset": null,
"rougeLsum_fmeasure_stderr": 0.002442180833294991
}
],
"config": {
"model": "hf-causal",
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-12b/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
"task_args": "",
"num_fewshot": 4,
"batch_size": 16,
"device": "cuda",
"use_cache": false,
"limit": 3000,
"bootstrap_iters": 10,
"seed": 1234
}
}