<!-- 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-cnn-pubmed-arxiv-pubmed-arxiv-arxiv-v3-e4
This model is a fine-tuned version of theojolliffe/bart-cnn-pubmed-arxiv-pubmed-arxiv-arxiv on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8121
- Rouge1: 53.9237
- Rouge2: 34.5683
- Rougel: 36.5547
- Rougelsum: 51.0273
- Gen Len: 142.0
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: 2
- eval_batch_size: 2
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 398 | 0.8673 | 53.562 | 34.4013 | 36.5393 | 50.7868 | 142.0 |
0.826 | 2.0 | 796 | 0.8119 | 55.0909 | 36.5216 | 38.6034 | 52.718 | 142.0 |
0.5377 | 3.0 | 1194 | 0.8268 | 54.0198 | 35.9154 | 38.1218 | 51.2782 | 142.0 |
0.3817 | 4.0 | 1592 | 0.8121 | 53.9237 | 34.5683 | 36.5547 | 51.0273 | 142.0 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1