metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bart-paraphrasing-mlm
results: []
bart-paraphrasing-mlm
This model is a fine-tuned version of gayanin/bart-paraphrase-pubmed-1.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5510
- Rouge2 Precision: 0.7148
- Rouge2 Recall: 0.5223
- Rouge2 Fmeasure: 0.5866
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
---|---|---|---|---|---|---|
0.6799 | 1.0 | 13833 | 0.5982 | 0.7016 | 0.5122 | 0.5756 |
0.5894 | 2.0 | 27666 | 0.5663 | 0.7093 | 0.5193 | 0.583 |
0.5329 | 3.0 | 41499 | 0.5540 | 0.7129 | 0.5212 | 0.5853 |
0.4953 | 4.0 | 55332 | 0.5510 | 0.7148 | 0.5223 | 0.5866 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.4
- Tokenizers 0.11.6