metadata
license: bsd-3-clause
base_model: pszemraj/led-base-book-summary
tags:
- generated_from_trainer
model-index:
- name: fine-tuned-led-base-book-summary
results: []
fine-tuned-led-base-book-summary
This model is a fine-tuned version of pszemraj/led-base-book-summary on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5918
- Rouge2 Precision: 0.0778
- Rouge2 Recall: 0.1291
- Rouge2 Fmeasure: 0.0958
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-06
- 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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| 3.1612 | 0.4 | 150 | 2.7501 | 0.0605 | 0.1088 | 0.0764 |
| 2.9645 | 0.8 | 300 | 2.6528 | 0.0732 | 0.1251 | 0.0909 |
| 2.6754 | 1.19 | 450 | 2.6192 | 0.0752 | 0.1216 | 0.0917 |
| 2.8581 | 1.59 | 600 | 2.5968 | 0.0763 | 0.1239 | 0.0933 |
| 2.7604 | 1.99 | 750 | 2.5918 | 0.0778 | 0.1291 | 0.0958 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.1
- Datasets 2.14.6
- Tokenizers 0.14.1