metadata
base_model: Patcas/plbart-works
tags:
- generated_from_trainer
model-index:
- name: v5-my_awesome
results: []
v5-my_awesome
This model is a fine-tuned version of Patcas/plbart-works on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0208
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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 264 | 0.9325 |
| 1.0258 | 2.0 | 528 | 0.8500 |
| 1.0258 | 3.0 | 792 | 0.8358 |
| 0.3925 | 4.0 | 1056 | 0.8538 |
| 0.3925 | 5.0 | 1320 | 0.8462 |
| 0.2 | 6.0 | 1584 | 0.9122 |
| 0.2 | 7.0 | 1848 | 0.8987 |
| 0.1246 | 8.0 | 2112 | 0.8859 |
| 0.1246 | 9.0 | 2376 | 0.8990 |
| 0.0834 | 10.0 | 2640 | 0.9022 |
| 0.0834 | 11.0 | 2904 | 0.9212 |
| 0.058 | 12.0 | 3168 | 0.9542 |
| 0.058 | 13.0 | 3432 | 0.9466 |
| 0.0431 | 14.0 | 3696 | 0.9615 |
| 0.0431 | 15.0 | 3960 | 0.9675 |
| 0.0321 | 16.0 | 4224 | 0.9719 |
| 0.0321 | 17.0 | 4488 | 0.9786 |
| 0.0237 | 18.0 | 4752 | 0.9918 |
| 0.0189 | 19.0 | 5016 | 0.9911 |
| 0.0189 | 20.0 | 5280 | 0.9983 |
| 0.0143 | 21.0 | 5544 | 0.9973 |
| 0.0143 | 22.0 | 5808 | 1.0100 |
| 0.0129 | 23.0 | 6072 | 1.0160 |
| 0.0129 | 24.0 | 6336 | 1.0091 |
| 0.0097 | 25.0 | 6600 | 1.0191 |
| 0.0097 | 26.0 | 6864 | 1.0224 |
| 0.0084 | 27.0 | 7128 | 1.0238 |
| 0.0084 | 28.0 | 7392 | 1.0201 |
| 0.0079 | 29.0 | 7656 | 1.0200 |
| 0.0079 | 30.0 | 7920 | 1.0208 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0