<!-- 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-large-cnn-1000-pad-early-lit
This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4800
- Rouge1: 28.4538
- Rouge2: 13.5656
- Rougel: 22.2066
- Rougelsum: 25.3361
- Gen Len: 66.53
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.1556 | 1.0 | 1000 | 0.4383 | 29.1275 | 14.1415 | 22.5802 | 26.37 | 65.93 |
| 0.0853 | 2.0 | 2000 | 0.4800 | 28.4538 | 13.5656 | 22.2066 | 25.3361 | 66.53 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2
- Datasets 1.18.3
- Tokenizers 0.11.0
