ludziej's picture
End of training
92f68a7 verified
|
raw
history blame
2.69 kB
---
tags:
- generated_from_trainer
model-index:
- name: calculator_model_test
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. -->
# calculator_model_test
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3578
## 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: 0.001
- train_batch_size: 512
- eval_batch_size: 512
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.9444 | 1.0 | 6 | 2.3826 |
| 2.1543 | 2.0 | 12 | 1.8663 |
| 1.7072 | 3.0 | 18 | 1.5640 |
| 1.4261 | 4.0 | 24 | 1.3127 |
| 1.2227 | 5.0 | 30 | 1.1949 |
| 1.061 | 6.0 | 36 | 1.0322 |
| 0.9789 | 7.0 | 42 | 0.9130 |
| 0.8812 | 8.0 | 48 | 0.8633 |
| 0.8289 | 9.0 | 54 | 0.7872 |
| 0.693 | 10.0 | 60 | 0.7300 |
| 0.7416 | 11.0 | 66 | 0.7454 |
| 0.6965 | 12.0 | 72 | 0.6641 |
| 0.6592 | 13.0 | 78 | 0.6362 |
| 0.6411 | 14.0 | 84 | 0.5824 |
| 0.5677 | 15.0 | 90 | 0.5541 |
| 0.5575 | 16.0 | 96 | 0.5299 |
| 0.5305 | 17.0 | 102 | 0.5435 |
| 0.5371 | 18.0 | 108 | 0.4937 |
| 0.4795 | 19.0 | 114 | 0.4800 |
| 0.4693 | 20.0 | 120 | 0.4486 |
| 0.4836 | 21.0 | 126 | 0.4478 |
| 0.4351 | 22.0 | 132 | 0.4323 |
| 0.47 | 23.0 | 138 | 0.4131 |
| 0.414 | 24.0 | 144 | 0.4023 |
| 0.4396 | 25.0 | 150 | 0.3961 |
| 0.4079 | 26.0 | 156 | 0.3870 |
| 0.4052 | 27.0 | 162 | 0.3846 |
| 0.3914 | 28.0 | 168 | 0.3676 |
| 0.4287 | 29.0 | 174 | 0.3593 |
| 0.3583 | 30.0 | 180 | 0.3578 |
### Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2