|
--- |
|
license: llama2 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: codellama/CodeLlama-7b-hf |
|
model-index: |
|
- name: sql-code-llama |
|
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. --> |
|
|
|
# sql-code-llama |
|
|
|
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4583 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 400 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.2023 | 0.04 | 20 | 2.0520 | |
|
| 1.212 | 0.07 | 40 | 0.8926 | |
|
| 0.8532 | 0.11 | 60 | 0.7526 | |
|
| 0.5953 | 0.14 | 80 | 0.5960 | |
|
| 0.3869 | 0.18 | 100 | 0.5596 | |
|
| 0.5738 | 0.22 | 120 | 0.5181 | |
|
| 0.4281 | 0.25 | 140 | 0.5080 | |
|
| 0.6451 | 0.29 | 160 | 0.5146 | |
|
| 0.4874 | 0.33 | 180 | 0.4893 | |
|
| 0.3588 | 0.36 | 200 | 0.5016 | |
|
| 0.5308 | 0.4 | 220 | 0.4816 | |
|
| 0.4006 | 0.43 | 240 | 0.4777 | |
|
| 0.5958 | 0.47 | 260 | 0.4780 | |
|
| 0.4682 | 0.51 | 280 | 0.4685 | |
|
| 0.3507 | 0.54 | 300 | 0.4753 | |
|
| 0.5079 | 0.58 | 320 | 0.4664 | |
|
| 0.3933 | 0.62 | 340 | 0.4626 | |
|
| 0.5839 | 0.65 | 360 | 0.4622 | |
|
| 0.4543 | 0.69 | 380 | 0.4594 | |
|
| 0.3475 | 0.72 | 400 | 0.4583 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.36.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
