summarise
This model is a fine-tuned version of allenai/led-base-16384 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0497
- Rouge2 Precision: 0.3109
- Rouge2 Recall: 0.406
- Rouge2 Fmeasure: 0.3375
Model description
More information needed
Intended uses & limitations
max_input_length = 3072
max_output_length = 1000
led.config.max_length = 1000
led.config.min_length = 100
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| 1.7163 | 0.22 | 10 | 1.2307 | 0.1428 | 0.5118 | 0.2089 |
| 1.632 | 0.44 | 20 | 1.1337 | 0.36 | 0.3393 | 0.3181 |
| 1.0916 | 0.67 | 30 | 1.0738 | 0.2693 | 0.3487 | 0.2731 |
| 1.573 | 0.89 | 40 | 1.0497 | 0.3109 | 0.406 | 0.3375 |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 1.2.1
- Tokenizers 0.12.1