|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: codeparrot-small-custom-functions-dataset-python |
|
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. --> |
|
|
|
# codeparrot-small-custom-functions-dataset-python |
|
|
|
This model is a fine-tuned version of [codeparrot/codeparrot-small](https://huggingface.co./codeparrot/codeparrot-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4934 |
|
|
|
## 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.2357 | 0.12 | 1 | 0.9450 | |
|
| 1.0585 | 0.25 | 2 | 0.8835 | |
|
| 0.9853 | 0.38 | 3 | 0.8324 | |
|
| 0.9877 | 0.5 | 4 | 0.7932 | |
|
| 1.0075 | 0.62 | 5 | 0.7623 | |
|
| 0.8744 | 0.75 | 6 | 0.7335 | |
|
| 0.8627 | 0.88 | 7 | 0.7091 | |
|
| 0.8615 | 1.0 | 8 | 0.6893 | |
|
| 0.8016 | 1.12 | 9 | 0.6706 | |
|
| 0.7458 | 1.25 | 10 | 0.6540 | |
|
| 0.7335 | 1.38 | 11 | 0.6378 | |
|
| 0.7754 | 1.5 | 12 | 0.6243 | |
|
| 0.7684 | 1.62 | 13 | 0.6107 | |
|
| 0.7335 | 1.75 | 14 | 0.5985 | |
|
| 0.7418 | 1.88 | 15 | 0.5878 | |
|
| 0.5644 | 2.0 | 16 | 0.5792 | |
|
| 0.6464 | 2.12 | 17 | 0.5711 | |
|
| 0.7304 | 2.25 | 18 | 0.5622 | |
|
| 0.6848 | 2.38 | 19 | 0.5545 | |
|
| 0.7221 | 2.5 | 20 | 0.5480 | |
|
| 0.6053 | 2.62 | 21 | 0.5420 | |
|
| 0.6168 | 2.75 | 22 | 0.5370 | |
|
| 0.5823 | 2.88 | 23 | 0.5323 | |
|
| 0.7512 | 3.0 | 24 | 0.5279 | |
|
| 0.5745 | 3.12 | 25 | 0.5241 | |
|
| 0.674 | 3.25 | 26 | 0.5202 | |
|
| 0.5441 | 3.38 | 27 | 0.5167 | |
|
| 0.6236 | 3.5 | 28 | 0.5134 | |
|
| 0.6006 | 3.62 | 29 | 0.5102 | |
|
| 0.6279 | 3.75 | 30 | 0.5072 | |
|
| 0.6257 | 3.88 | 31 | 0.5046 | |
|
| 0.5408 | 4.0 | 32 | 0.5025 | |
|
| 0.5855 | 4.12 | 33 | 0.5004 | |
|
| 0.594 | 4.25 | 34 | 0.4984 | |
|
| 0.5985 | 4.38 | 35 | 0.4970 | |
|
| 0.6279 | 4.5 | 36 | 0.4958 | |
|
| 0.6151 | 4.62 | 37 | 0.4949 | |
|
| 0.5629 | 4.75 | 38 | 0.4942 | |
|
| 0.5148 | 4.88 | 39 | 0.4937 | |
|
| 0.4823 | 5.0 | 40 | 0.4934 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
