|
--- |
|
license: mit |
|
base_model: gpt2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: codeparrot-ds |
|
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-ds |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.9260 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 9.4997 | 0.18 | 10 | 8.0307 | |
|
| 7.1464 | 0.36 | 20 | 7.0639 | |
|
| 6.7447 | 0.54 | 30 | 6.8856 | |
|
| 6.4819 | 0.72 | 40 | 6.6801 | |
|
| 6.2576 | 0.9 | 50 | 6.4703 | |
|
| 6.0151 | 1.08 | 60 | 6.2236 | |
|
| 5.7178 | 1.26 | 70 | 6.0277 | |
|
| 5.5432 | 1.44 | 80 | 5.8780 | |
|
| 5.4003 | 1.62 | 90 | 5.7475 | |
|
| 5.2611 | 1.8 | 100 | 5.6555 | |
|
| 5.1703 | 1.98 | 110 | 5.5344 | |
|
| 5.0115 | 2.16 | 120 | 5.4731 | |
|
| 4.9182 | 2.34 | 130 | 5.3787 | |
|
| 4.8519 | 2.52 | 140 | 5.3300 | |
|
| 4.7389 | 2.7 | 150 | 5.2398 | |
|
| 4.6887 | 2.88 | 160 | 5.1947 | |
|
| 4.5515 | 3.06 | 170 | 5.1424 | |
|
| 4.4606 | 3.24 | 180 | 5.1048 | |
|
| 4.4699 | 3.42 | 190 | 5.0667 | |
|
| 4.3777 | 3.6 | 200 | 5.0200 | |
|
| 4.3894 | 3.78 | 210 | 4.9892 | |
|
| 4.3143 | 3.96 | 220 | 4.9688 | |
|
| 4.2688 | 4.14 | 230 | 4.9515 | |
|
| 4.2468 | 4.32 | 240 | 4.9410 | |
|
| 4.2191 | 4.5 | 250 | 4.9304 | |
|
| 4.2512 | 4.68 | 260 | 4.9270 | |
|
| 4.217 | 4.86 | 270 | 4.9260 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
