<!-- 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. -->
mt5-small-finetuned-arxiv-summarization
This model is a fine-tuned version of google/mt5-small on the pubmed-summarization dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 0.6353
- Rouge2: 0.0849
- Rougel: 0.5942
- Rougelsum: 0.6117
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: 5.6e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.0 | 1.0 | 1999 | nan | 0.6353 | 0.0849 | 0.5942 | 0.6117 |
| 0.0 | 2.0 | 3998 | nan | 0.6353 | 0.0849 | 0.5942 | 0.6117 |
| 0.0 | 3.0 | 5997 | nan | 0.6353 | 0.0849 | 0.5942 | 0.6117 |
| 0.0 | 4.0 | 7996 | nan | 0.6353 | 0.0849 | 0.5942 | 0.6117 |
| 0.0 | 5.0 | 9995 | nan | 0.6353 | 0.0849 | 0.5942 | 0.6117 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
