|
|
--- |
|
|
library_name: peft |
|
|
license: other |
|
|
base_model: deepseek-ai/deepseek-coder-7b-instruct |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: NLP-smaller_batch |
|
|
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. --> |
|
|
|
|
|
# NLP-smaller_batch |
|
|
|
|
|
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.5870 |
|
|
|
|
|
## 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: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 4 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 3 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 1.9188 | 1.0 | 600 | 1.6714 | |
|
|
| 1.6554 | 2.0 | 1200 | 1.6053 | |
|
|
| 1.6031 | 3.0 | 1800 | 1.5870 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.15.2 |
|
|
- Transformers 4.51.3 |
|
|
- Pytorch 2.7.0+cu118 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
