<!-- 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. -->
pegasus-cnn_dailymail-1000-lit-evalMA-ga1
This model is a fine-tuned version of google/pegasus-cnn_dailymail on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6852
- Rouge1: 25.8242
- Rouge2: 11.1309
- Rougel: 20.7946
- Rougelsum: 22.5591
- Gen Len: 46.32
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 250 | 1.7061 | 25.8547 | 10.8573 | 20.8419 | 22.5942 | 44.36 |
| 1.4533 | 2.0 | 500 | 1.6876 | 26.105 | 11.5635 | 21.132 | 23.044 | 45.65 |
| 1.4533 | 3.0 | 750 | 1.6852 | 25.8242 | 11.1309 | 20.7946 | 22.5591 | 46.32 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2
- Datasets 1.18.3
- Tokenizers 0.11.0
