<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

base

This model is a fine-tuned version of google/flan-t5-base on the cnn_dailymail 3.0.0 dataset. It achieves the following results on the evaluation set:

• Loss: 1.4232
• Rouge1: 42.1388
• Rouge2: 19.7696
• Rougel: 30.1512
• Rougelsum: 39.3222
• Gen Len: 71.8562

Model description

• Model type: Language model
• Language(s) (NLP): English, Spanish, Japanese, Persian, Hindi, French, Chinese, Bengali, Gujarati, German, Telugu, Italian, Arabic, Polish, Tamil, Marathi, Malayalam, Oriya, Panjabi, Portuguese, Urdu, Galician, Hebrew, Korean, Catalan, Thai, Dutch, Indonesian, Vietnamese, Bulgarian, Filipino, Central Khmer, Lao, Turkish, Russian, Croatian, Swedish, Yoruba, Kurdish, Burmese, Malay, Czech, Finnish, Somali, Tagalog, Swahili, Sinhala, Kannada, Zhuang, Igbo, Xhosa, Romanian, Haitian, Estonian, Slovak, Lithuanian, Greek, Nepali, Assamese, Norwegian
• License: Apache 2.0
• Related Models: All FLAN-T5 Checkpoints
• Original Checkpoints: All Original FLAN-T5 Checkpoints
• Resources for more information:
  • Research paper
  • GitHub Repo
  • Hugging Face FLAN-T5 Docs (Similar to T5)

Intended uses & limitations

The information below in this section are copied from the model's official model card:

Language models, including Flan-T5, can potentially be used for language generation in a harmful way, according to Rae et al. (2021). Flan-T5 should not be used directly in any application,

Training and evaluation data

• Loss: 1.4232
• Rouge1: 42.1388
• Rouge2: 19.7696
• Rougel: 30.1512
• Rougelsum: 39.3222
• Gen Len: 71.8562

Training procedure

Training procedure example notebook for flan-T5 and pushing it to hub https://github.com/EveripediaNetwork/ai/blob/main/notebooks/Fine-Tuning-Flan-T5_1.ipynb

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 1
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: Constant
• num_epochs: 3.0

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1
• Tokenizers 0.12.1