|
--- |
|
base_model: Deci/DeciLM-7B |
|
datasets: |
|
- generator |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: deci7bit-lora-sql |
|
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. --> |
|
|
|
# deci7bit-lora-sql |
|
|
|
This model is a fine-tuned version of [Deci/DeciLM-7B](https://huggingface.co/Deci/DeciLM-7B) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3613 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 1399 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 500 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.7762 | 0.0565 | 20 | 0.5080 | |
|
| 0.4829 | 0.1129 | 40 | 0.4278 | |
|
| 0.4283 | 0.1694 | 60 | 0.4019 | |
|
| 0.4102 | 0.2258 | 80 | 0.3903 | |
|
| 0.4 | 0.2823 | 100 | 0.3856 | |
|
| 0.3919 | 0.3387 | 120 | 0.3800 | |
|
| 0.3876 | 0.3952 | 140 | 0.3773 | |
|
| 0.3845 | 0.4517 | 160 | 0.3741 | |
|
| 0.3801 | 0.5081 | 180 | 0.3665 | |
|
| 0.3733 | 0.5646 | 200 | 0.3613 | |
|
| 0.3697 | 0.6210 | 220 | 0.3613 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.2.2+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
