metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: pegasus-base-qag-bg-finetuned-punctuation-bg
results: []
pegasus-base-qag-bg-finetuned-punctuation-bg
This model is a fine-tuned version of rmihaylov/pegasus-base-qag-bg on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0318
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: 5.6e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0563 | 1.0 | 4063 | 0.0279 |
| 0.0301 | 2.0 | 8126 | 0.0260 |
| 0.0227 | 3.0 | 12189 | 0.0259 |
| 0.0178 | 4.0 | 16252 | 0.0281 |
| 0.0145 | 5.0 | 20315 | 0.0290 |
| 0.0122 | 6.0 | 24378 | 0.0300 |
| 0.0105 | 7.0 | 28441 | 0.0305 |
| 0.0095 | 8.0 | 32504 | 0.0318 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2