<!-- 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. -->
bart-med-term-mlm
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2506
- Rouge2 Precision: 0.8338
- Rouge2 Recall: 0.6005
- Rouge2 Fmeasure: 0.6775
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 |
---|---|---|---|---|---|---|
0.3426 | 1.0 | 15827 | 0.3029 | 0.8184 | 0.5913 | 0.6664 |
0.2911 | 2.0 | 31654 | 0.2694 | 0.8278 | 0.5963 | 0.6727 |
0.2571 | 3.0 | 47481 | 0.2549 | 0.8318 | 0.5985 | 0.6753 |
0.2303 | 4.0 | 63308 | 0.2506 | 0.8338 | 0.6005 | 0.6775 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.4
- Tokenizers 0.11.6