huseinzol05's picture
Create README.md
2a51ca8
metadata
language:
  - ms
tags:
  - paraphrase
metrics:
  - sacrebleu

finetune-paraphrase-t5-base-standard-bahasa-cased

Finetuned T5 base on MS paraphrase tasks.

Dataset

  1. translated PAWS, https://huggingface.co/datasets/mesolitica/translated-PAWS
  2. translated MRPC, https://huggingface.co/datasets/mesolitica/translated-MRPC

Finetune details

  1. Finetune using single RTX 3090 Ti.

Scripts at https://github.com/huseinzol05/malaya/tree/master/session/paraphrase/hf-t5

Supported prefix

  1. parafrasa: {string}, for MS paraphrase.

Evaluation

Evaluated on MRPC validation set and PAWS test set.

{'name': 'BLEU',
 'score': 58.764876478744064,
 '_mean': -1.0,
 '_ci': -1.0,
 '_verbose': '84.5/65.8/53.0/43.1 (BP = 0.984 ratio = 0.985 hyp_len = 138828 ref_len = 141004)',
 'bp': 0.9844481274610702,
 'counts': [117307, 86700, 66087, 50665],
 'totals': [138828, 131754, 124680, 117606],
 'sys_len': 138828,
 'ref_len': 141004,
 'precisions': [84.49808396000807,
  65.80445375472472,
  53.00529355149182,
  43.080285019471795],
 'prec_str': '84.5/65.8/53.0/43.1',
 'ratio': 0.9845678136790446}