|
--- |
|
base_model: google/pegasus-x-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: pegasus-x-large_readme_summarization |
|
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. --> |
|
|
|
# pegasus-x-large_readme_summarization |
|
|
|
This model is a fine-tuned version of [google/pegasus-x-large](https://huggingface.co/google/pegasus-x-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9470 |
|
- Rouge1: 0.4688 |
|
- Rouge2: 0.3365 |
|
- Rougel: 0.4384 |
|
- Rougelsum: 0.4396 |
|
- Gen Len: 54.47 |
|
|
|
## 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 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 2.1846 | 1.0 | 5831 | 2.0536 | 0.4359 | 0.3076 | 0.4069 | 0.4073 | 59.759 | |
|
| 1.9702 | 2.0 | 11662 | 1.9768 | 0.4494 | 0.3191 | 0.4212 | 0.4215 | 61.4376 | |
|
| 1.8496 | 3.0 | 17493 | 1.9549 | 0.4614 | 0.3288 | 0.432 | 0.4325 | 59.9676 | |
|
| 1.6699 | 4.0 | 23324 | 1.9470 | 0.4688 | 0.3365 | 0.4384 | 0.4396 | 54.47 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
