LordAbsurd2137's picture
End of training
c500ced verified
|
raw
history blame
3.2 kB
---
tags:
- generated_from_trainer
model-index:
- name: calculator_model_test2
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_test2
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: 0.1318
## 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: 40
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.9409 | 1.0 | 6 | 2.2604 |
| 2.0221 | 2.0 | 12 | 1.7164 |
| 1.5231 | 3.0 | 18 | 1.2971 |
| 1.1926 | 4.0 | 24 | 1.0828 |
| 1.0328 | 5.0 | 30 | 0.9510 |
| 0.9177 | 6.0 | 36 | 0.8256 |
| 0.8079 | 7.0 | 42 | 0.7383 |
| 0.7261 | 8.0 | 48 | 0.6878 |
| 0.6844 | 9.0 | 54 | 0.6245 |
| 0.6421 | 10.0 | 60 | 0.5833 |
| 0.6088 | 11.0 | 66 | 0.5801 |
| 0.5638 | 12.0 | 72 | 0.5270 |
| 0.5326 | 13.0 | 78 | 0.4975 |
| 0.5134 | 14.0 | 84 | 0.5070 |
| 0.5135 | 15.0 | 90 | 0.4415 |
| 0.468 | 16.0 | 96 | 0.4325 |
| 0.4442 | 17.0 | 102 | 0.4200 |
| 0.4214 | 18.0 | 108 | 0.4241 |
| 0.4115 | 19.0 | 114 | 0.3691 |
| 0.3885 | 20.0 | 120 | 0.3460 |
| 0.3641 | 21.0 | 126 | 0.3261 |
| 0.3445 | 22.0 | 132 | 0.2990 |
| 0.3198 | 23.0 | 138 | 0.2776 |
| 0.3043 | 24.0 | 144 | 0.2610 |
| 0.2885 | 25.0 | 150 | 0.2424 |
| 0.2709 | 26.0 | 156 | 0.2312 |
| 0.2537 | 27.0 | 162 | 0.2321 |
| 0.2475 | 28.0 | 168 | 0.2040 |
| 0.231 | 29.0 | 174 | 0.1949 |
| 0.2228 | 30.0 | 180 | 0.1797 |
| 0.2015 | 31.0 | 186 | 0.1713 |
| 0.202 | 32.0 | 192 | 0.1616 |
| 0.1793 | 33.0 | 198 | 0.1583 |
| 0.1849 | 34.0 | 204 | 0.1512 |
| 0.1726 | 35.0 | 210 | 0.1464 |
| 0.1703 | 36.0 | 216 | 0.1451 |
| 0.1611 | 37.0 | 222 | 0.1394 |
| 0.166 | 38.0 | 228 | 0.1353 |
| 0.1595 | 39.0 | 234 | 0.1326 |
| 0.1526 | 40.0 | 240 | 0.1318 |
### Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2