|
|
--- |
|
|
library_name: peft |
|
|
license: apache-2.0 |
|
|
base_model: mistralai/Mistral-7B-v0.1 |
|
|
tags: |
|
|
- trl |
|
|
- sft |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- generator |
|
|
model-index: |
|
|
- name: code-bench-Mistral-7B-text-to-sql-v1 |
|
|
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. --> |
|
|
|
|
|
# code-bench-Mistral-7B-text-to-sql-v1 |
|
|
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.4298 |
|
|
|
|
|
## 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: 0.0002 |
|
|
- train_batch_size: 1 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 8 |
|
|
- total_train_batch_size: 8 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_ratio: 0.03 |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.8246 | 0.0619 | 10 | 0.7742 | |
|
|
| 0.6351 | 0.1238 | 20 | 0.7373 | |
|
|
| 0.573 | 0.1858 | 30 | 0.5941 | |
|
|
| 0.5628 | 0.2477 | 40 | 0.5330 | |
|
|
| 0.5169 | 0.3096 | 50 | 0.5149 | |
|
|
| 0.5002 | 0.3715 | 60 | 0.4909 | |
|
|
| 0.4825 | 0.4334 | 70 | 0.4721 | |
|
|
| 0.466 | 0.4954 | 80 | 0.4628 | |
|
|
| 0.4523 | 0.5573 | 90 | 0.4580 | |
|
|
| 0.4536 | 0.6192 | 100 | 0.4474 | |
|
|
| 0.4435 | 0.6811 | 110 | 0.4356 | |
|
|
| 0.4399 | 0.7430 | 120 | 0.4318 | |
|
|
| 0.4073 | 0.8050 | 130 | 0.4261 | |
|
|
| 0.4372 | 0.8669 | 140 | 0.4198 | |
|
|
| 0.4046 | 0.9288 | 150 | 0.4135 | |
|
|
| 0.3836 | 0.9907 | 160 | 0.4131 | |
|
|
| 0.2902 | 1.0526 | 170 | 0.4158 | |
|
|
| 0.3228 | 1.1146 | 180 | 0.4141 | |
|
|
| 0.3094 | 1.1765 | 190 | 0.4167 | |
|
|
| 0.294 | 1.2384 | 200 | 0.4127 | |
|
|
| 0.3081 | 1.3003 | 210 | 0.4047 | |
|
|
| 0.285 | 1.3622 | 220 | 0.4034 | |
|
|
| 0.2814 | 1.4241 | 230 | 0.4065 | |
|
|
| 0.2649 | 1.4861 | 240 | 0.4016 | |
|
|
| 0.2715 | 1.5480 | 250 | 0.3956 | |
|
|
| 0.2715 | 1.6099 | 260 | 0.3967 | |
|
|
| 0.2768 | 1.6718 | 270 | 0.3914 | |
|
|
| 0.2618 | 1.7337 | 280 | 0.3905 | |
|
|
| 0.2663 | 1.7957 | 290 | 0.3887 | |
|
|
| 0.2639 | 1.8576 | 300 | 0.3844 | |
|
|
| 0.2601 | 1.9195 | 310 | 0.3831 | |
|
|
| 0.2625 | 1.9814 | 320 | 0.3808 | |
|
|
| 0.1607 | 2.0433 | 330 | 0.4298 | |
|
|
| 0.1505 | 2.1053 | 340 | 0.4149 | |
|
|
| 0.1483 | 2.1672 | 350 | 0.4370 | |
|
|
| 0.1597 | 2.2291 | 360 | 0.4287 | |
|
|
| 0.1456 | 2.2910 | 370 | 0.4301 | |
|
|
| 0.1567 | 2.3529 | 380 | 0.4304 | |
|
|
| 0.1469 | 2.4149 | 390 | 0.4247 | |
|
|
| 0.1539 | 2.4768 | 400 | 0.4291 | |
|
|
| 0.1546 | 2.5387 | 410 | 0.4330 | |
|
|
| 0.1434 | 2.6006 | 420 | 0.4297 | |
|
|
| 0.1387 | 2.6625 | 430 | 0.4301 | |
|
|
| 0.1491 | 2.7245 | 440 | 0.4302 | |
|
|
| 0.1538 | 2.7864 | 450 | 0.4298 | |
|
|
| 0.1445 | 2.8483 | 460 | 0.4299 | |
|
|
| 0.1405 | 2.9102 | 470 | 0.4299 | |
|
|
| 0.1392 | 2.9721 | 480 | 0.4298 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.44.2 |
|
|
- Pytorch 2.5.1+cu121 |
|
|
- Datasets 2.21.0 |
|
|
- Tokenizers 0.19.1 |
