Cetvel / results /zero-shot /llama-3.2-1b.json
Ilker Kesen
update results
3050f94
{
"model": {
"model": "meta-llama/Llama-3.2-1B",
"api": "hf",
"dtype": "bfloat16",
"max_length": 131072,
"architecture": "LlamaForCausalLM",
"type": "pretrained",
"num_parameters": "1b"
},
"results": [
{
"name": "belebele_tr",
"task": "multiple_choice",
"acc": 0.29555555555555557,
"acc_norm": 0.29555555555555557
},
{
"name": "exams_tr",
"task": "multiple_choice",
"acc": 0.28498727735368956,
"acc_norm": 0.3053435114503817
},
{
"name": "check_worthiness",
"task": "multiple_choice",
"acc": 0.3880255941499086,
"acc_norm": 0.623400365630713
},
{
"name": "gecturk_generation",
"task": "grammatical_error_correction",
"exact_match": 0.00741489720256151
},
{
"name": "ironytr",
"task": "text_classification",
"acc": 0.5283333333333333,
"acc_norm": 0.5033333333333333
},
{
"name": "mkqa_tr",
"task": "extractive_question_answering",
"exact_match": 0.007694584196507843,
"f1": 0.03304091036050505
},
{
"name": "mlsum_tr",
"task": "summarization",
"rouge1": 0.23283491254211872,
"rouge2": 0.13426790568610214,
"rougeL": 0.18915548037371513
},
{
"name": "mnli_tr",
"task": "natural_language_inference",
"acc": 0.3232,
"acc_norm": 0.334
},
{
"name": "news_cat",
"task": "text_classification",
"acc": 0.58,
"acc_norm": 0.532
},
{
"name": "offenseval_tr",
"task": "text_classification",
"acc": 0.4671201814058957,
"acc_norm": 0.7820294784580499
},
{
"name": "relevance_judgment",
"task": "multiple_choice",
"acc": 0.56672760511883,
"acc_norm": 0.5781535648994516
},
{
"name": "snli_tr",
"task": "natural_language_inference",
"acc": 0.3239,
"acc_norm": 0.3105
},
{
"name": "sts_tr",
"task": "text_classification",
"acc": 0.17113850616388687,
"acc_norm": 0.22552574329224076
},
{
"name": "tquad",
"task": "extractive_question_answering",
"exact_match": 0.06278026905829596,
"f1": 0.21486130318406463
},
{
"name": "turkish_plu_goal_inference",
"task": "multiple_choice",
"acc": 0.35842293906810035,
"acc_norm": 0.4026284348864994
},
{
"name": "turkish_plu_next_event_prediction",
"task": "multiple_choice",
"acc": 0.3709923664122137,
"acc_norm": 0.467175572519084
},
{
"name": "turkish_plu_step_inference",
"task": "multiple_choice",
"acc": 0.27941176470588236,
"acc_norm": 0.41830065359477125
},
{
"name": "turkish_plu_step_ordering",
"task": "multiple_choice",
"acc": 0.5759059745347699,
"acc_norm": 0.5759059745347699
},
{
"name": "wiki_lingua_tr",
"task": "summarization",
"rouge1": 0.10861529436199803,
"rouge2": 0.034862923521078545,
"rougeL": 0.08692160533533941
},
{
"name": "wmt-tr-en-prompt",
"task": "machine_translation",
"wer": 3.910683208136067,
"bleu": 0.012043288243775466
},
{
"name": "xcopa_tr",
"task": "multiple_choice",
"acc": 0.556,
"acc_norm": 0.556
},
{
"name": "xlsum_tr",
"task": "summarization",
"rouge1": 0.16924699150407269,
"rouge2": 0.07190935921365724,
"rougeL": 0.13255123335488528
},
{
"name": "xnli_tr",
"task": "natural_language_inference",
"acc": 0.4389558232931727,
"acc_norm": 0.4389558232931727
},
{
"name": "xquad_tr",
"task": "extractive_question_answering",
"exact_match": 0.04873949579831932,
"f1": 0.11156636293859905
},
{
"name": "gecturk_generation",
"task": "grammatical_error_correction",
"exact_match": 0.0073185998362944775
},
{
"name": "mlsum_tr",
"task": "summarization",
"rouge1": 0.35440052022111407,
"rouge2": 0.2215476501673455,
"rougeL": 0.2911311598176804
},
{
"name": "wiki_lingua_tr",
"task": "summarization",
"rouge1": 0.18510384577665046,
"rouge2": 0.056181066004903614,
"rougeL": 0.1392211003290612
},
{
"name": "wmt-tr-en-prompt",
"task": "machine_translation",
"wer": 1.311990023748812,
"bleu": 0.02624044942774961
},
{
"name": "tr-wikihow-summ",
"task": "summarization",
"rouge1": 0.20233829108374618,
"rouge2": 0.05924574844289239,
"rougeL": 0.14920828977218778
},
{
"name": "xlsum_tr",
"task": "summarization",
"rouge1": 0.2429304790539497,
"rouge2": 0.09668008744707143,
"rougeL": 0.18327092913535944
}
]
}