bloomz / evaluation_bloomz /evaluation_val /mlsum_es /slim.limited=3000.model=xp3capmixnewcodelonglossseq_global_step498.task=mlsum_es.templates=summarise_this_in_es_few_sentences.fewshot=0.batchsize=4.seed=1234.timestamp=2022-09-11T02:20:44.json
Muennighoff's picture
Organize val files
baaf0c1
raw history blame
No virus
4.23 kB
{
"results": [
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"bleu": 2.7821053236675306,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"bleu_stderr": 0.11547426906777203
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rouge1_precision": 0.21888011387446746,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rouge1_precision_stderr": 0.002467769363765386
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rouge1_recall": 0.2599926409001897,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rouge1_recall_stderr": 0.003199531151457232
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rouge1_fmeasure": 0.20977060183296548,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rouge1_fmeasure_stderr": 0.002215423821196786
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rouge2_precision": 0.05195446332105216,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rouge2_precision_stderr": 0.0016363375624019096
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rouge2_recall": 0.0686141481900639,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rouge2_recall_stderr": 0.002095509341583397
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rouge2_fmeasure": 0.05234733312406368,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rouge2_fmeasure_stderr": 0.0015580839680454735
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rougeL_precision": 0.16853408734216013,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rougeL_precision_stderr": 0.0021008078358421135
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rougeL_recall": 0.19597150935158797,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rougeL_recall_stderr": 0.0025551844547328268
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rougeL_fmeasure": 0.15879516629311632,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rougeL_fmeasure_stderr": 0.0018075014060560566
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rougeLsum_precision": 0.17450463895712406,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rougeLsum_precision_stderr": 0.0021431721861983684
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rougeLsum_recall": 0.20509730700063683,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rougeLsum_recall_stderr": 0.002701824866588575
},
{
"task_name": "mlsum_es",
"prompt_name": "summarise_this_in_es_few_sentences",
"rougeLsum_fmeasure": 0.16512892741582888,
"dataset_path": "GEM/mlsum",
"dataset_name": "es",
"subset": "",
"rougeLsum_fmeasure_stderr": 0.00185597817383672
}
],
"config": {
"model": "hf-causal",
"model_args": "pretrained=/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/176bt0/xp3capmixnewcodelonglossseq_global_step498,use_accelerate=True,tokenizer=/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/176bt0/xp3capmixnewcodelonglossseq_global_step498,dtype=bfloat16",
"num_fewshot": 0,
"batch_size": 4,
"device": "cuda",
"use_cache": false,
"limit": 3000,
"bootstrap_iters": 10,
"seed": 1234
}
}