|
--- |
|
license: apache-2.0 |
|
base_model: SpamAcc/ingredient_prune |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ingredient_prune |
|
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. --> |
|
|
|
# ingredient_prune |
|
|
|
This model is a fine-tuned version of [SpamAcc/ingredient_prune](https://huggingface.co/SpamAcc/ingredient_prune) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0432 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 100 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.312 | 1.82 | 100 | 0.0295 | |
|
| 0.0533 | 3.64 | 200 | 0.0149 | |
|
| 0.0247 | 5.45 | 300 | 0.0136 | |
|
| 0.0149 | 7.27 | 400 | 0.0124 | |
|
| 0.0114 | 9.09 | 500 | 0.0127 | |
|
| 0.0086 | 10.91 | 600 | 0.0127 | |
|
| 0.0075 | 12.73 | 700 | 0.0145 | |
|
| 0.0061 | 14.55 | 800 | 0.0151 | |
|
| 0.0058 | 16.36 | 900 | 0.0161 | |
|
| 0.0044 | 18.18 | 1000 | 0.0169 | |
|
| 0.0039 | 20.0 | 1100 | 0.0199 | |
|
| 0.0044 | 21.82 | 1200 | 0.0181 | |
|
| 0.0035 | 23.64 | 1300 | 0.0230 | |
|
| 0.0039 | 25.45 | 1400 | 0.0226 | |
|
| 0.0028 | 27.27 | 1500 | 0.0234 | |
|
| 0.0026 | 29.09 | 1600 | 0.0272 | |
|
| 0.0023 | 30.91 | 1700 | 0.0261 | |
|
| 0.0028 | 32.73 | 1800 | 0.0254 | |
|
| 0.0018 | 34.55 | 1900 | 0.0268 | |
|
| 0.0022 | 36.36 | 2000 | 0.0303 | |
|
| 0.002 | 38.18 | 2100 | 0.0286 | |
|
| 0.0018 | 40.0 | 2200 | 0.0299 | |
|
| 0.0024 | 41.82 | 2300 | 0.0322 | |
|
| 0.0019 | 43.64 | 2400 | 0.0328 | |
|
| 0.0015 | 45.45 | 2500 | 0.0310 | |
|
| 0.002 | 47.27 | 2600 | 0.0352 | |
|
| 0.0015 | 49.09 | 2700 | 0.0361 | |
|
| 0.0013 | 50.91 | 2800 | 0.0358 | |
|
| 0.0011 | 52.73 | 2900 | 0.0368 | |
|
| 0.0017 | 54.55 | 3000 | 0.0387 | |
|
| 0.0012 | 56.36 | 3100 | 0.0384 | |
|
| 0.0011 | 58.18 | 3200 | 0.0402 | |
|
| 0.0016 | 60.0 | 3300 | 0.0394 | |
|
| 0.0012 | 61.82 | 3400 | 0.0403 | |
|
| 0.0013 | 63.64 | 3500 | 0.0392 | |
|
| 0.0011 | 65.45 | 3600 | 0.0413 | |
|
| 0.0015 | 67.27 | 3700 | 0.0400 | |
|
| 0.0021 | 69.09 | 3800 | 0.0412 | |
|
| 0.0009 | 70.91 | 3900 | 0.0410 | |
|
| 0.0013 | 72.73 | 4000 | 0.0419 | |
|
| 0.0009 | 74.55 | 4100 | 0.0415 | |
|
| 0.0011 | 76.36 | 4200 | 0.0418 | |
|
| 0.0008 | 78.18 | 4300 | 0.0422 | |
|
| 0.0013 | 80.0 | 4400 | 0.0434 | |
|
| 0.0011 | 81.82 | 4500 | 0.0436 | |
|
| 0.0011 | 83.64 | 4600 | 0.0434 | |
|
| 0.0008 | 85.45 | 4700 | 0.0434 | |
|
| 0.0009 | 87.27 | 4800 | 0.0436 | |
|
| 0.0006 | 89.09 | 4900 | 0.0442 | |
|
| 0.0009 | 90.91 | 5000 | 0.0436 | |
|
| 0.001 | 92.73 | 5100 | 0.0434 | |
|
| 0.0008 | 94.55 | 5200 | 0.0433 | |
|
| 0.0013 | 96.36 | 5300 | 0.0434 | |
|
| 0.001 | 98.18 | 5400 | 0.0433 | |
|
| 0.0008 | 100.0 | 5500 | 0.0432 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.2 |
|
|
