<!-- 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-model3-0810
This model is a fine-tuned version of theojolliffe/pegasus-model-3-x25 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0128
- Rouge1: 74.5218
- Rouge2: 73.9903
- Rougel: 74.4946
- Rougelsum: 74.7509
- Gen Len: 122.9655
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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.3663 | 1.0 | 547 | 0.0960 | 70.3803 | 65.6296 | 64.7957 | 69.7556 | 122.7241 |
| 0.127 | 2.0 | 1094 | 0.0276 | 74.3121 | 73.3963 | 74.026 | 74.502 | 122.9655 |
| 0.0706 | 3.0 | 1641 | 0.0157 | 74.4541 | 73.5817 | 74.1314 | 74.5238 | 122.9655 |
| 0.046 | 4.0 | 2188 | 0.0128 | 74.5218 | 73.9903 | 74.4946 | 74.7509 | 122.9655 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1
