summarise_v7
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: 1.1204
- Rouge2 Precision: 0.2764
- Rouge2 Recall: 0.3441
- Rouge2 Fmeasure: 0.2853
Model description
More information needed
Intended uses & limitations
max_input_length = 1280
max_output_length = 512
led.config.max_length = 512
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 |
|---|---|---|---|---|---|---|
| 0.9594 | 0.22 | 10 | 1.3386 | 0.3393 | 0.3048 | 0.2973 |
| 1.2189 | 0.44 | 20 | 1.1956 | 0.1935 | 0.314 | 0.2164 |
| 1.0542 | 0.67 | 30 | 1.1580 | 0.2383 | 0.4133 | 0.2794 |
| 1.5145 | 0.89 | 40 | 1.1204 | 0.2764 | 0.3441 | 0.2853 |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 1.2.1
- Tokenizers 0.12.1