|
--- |
|
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: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# fine-tuned-led-base-book-summary |
|
|
|
This model is a fine-tuned version of [pszemraj/led-base-book-summary](https://huggingface.co./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 |
|
|