long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP17
This model is a fine-tuned version of pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP16 on the kmfoda/booksum dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 64
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 3
Framework versions
- Transformers 4.23.0.dev0
- Pytorch 1.10.0+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
- Downloads last month
- 13
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model authors have turned it off explicitly.
Model tree for pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP17
Dataset used to train pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP17
Evaluation results
- ROUGE-1 on launch/gov_reporttest set verified36.843
- ROUGE-2 on launch/gov_reporttest set verified8.423
- ROUGE-L on launch/gov_reporttest set verified17.774
- ROUGE-LSUM on launch/gov_reporttest set verified33.290
- loss on launch/gov_reporttest set verified3.766
- gen_len on launch/gov_reporttest set verified213.885
- ROUGE-1 on kmfoda/booksumtest set verified35.432
- ROUGE-2 on kmfoda/booksumtest set verified5.959
- ROUGE-L on kmfoda/booksumtest set verified16.134
- ROUGE-LSUM on kmfoda/booksumtest set verified32.414