metadata
base_model: Patcas/plbart-works
tags:
- generated_from_trainer
model-index:
- name: v4-my_awesome
results: []
v4-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: 1.0897
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 | 230 | 0.9567 |
| No log | 2.0 | 460 | 0.8849 |
| 0.9747 | 3.0 | 690 | 0.8750 |
| 0.9747 | 4.0 | 920 | 0.9034 |
| 0.3363 | 5.0 | 1150 | 0.9130 |
| 0.3363 | 6.0 | 1380 | 0.9173 |
| 0.1657 | 7.0 | 1610 | 0.9336 |
| 0.1657 | 8.0 | 1840 | 0.9556 |
| 0.0957 | 9.0 | 2070 | 0.9811 |
| 0.0957 | 10.0 | 2300 | 0.9835 |
| 0.0625 | 11.0 | 2530 | 0.9950 |
| 0.0625 | 12.0 | 2760 | 0.9918 |
| 0.0625 | 13.0 | 2990 | 1.0242 |
| 0.0429 | 14.0 | 3220 | 1.0211 |
| 0.0429 | 15.0 | 3450 | 1.0181 |
| 0.0317 | 16.0 | 3680 | 1.0250 |
| 0.0317 | 17.0 | 3910 | 1.0389 |
| 0.0244 | 18.0 | 4140 | 1.0467 |
| 0.0244 | 19.0 | 4370 | 1.0638 |
| 0.0192 | 20.0 | 4600 | 1.0697 |
| 0.0192 | 21.0 | 4830 | 1.0614 |
| 0.0124 | 22.0 | 5060 | 1.0723 |
| 0.0124 | 23.0 | 5290 | 1.0754 |
| 0.0122 | 24.0 | 5520 | 1.0809 |
| 0.0122 | 25.0 | 5750 | 1.0854 |
| 0.0122 | 26.0 | 5980 | 1.0937 |
| 0.0085 | 27.0 | 6210 | 1.0886 |
| 0.0085 | 28.0 | 6440 | 1.0892 |
| 0.0072 | 29.0 | 6670 | 1.0896 |
| 0.0072 | 30.0 | 6900 | 1.0897 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0