|
--- |
|
library_name: peft |
|
license: bigcode-openrail-m |
|
base_model: bigcode/starcoderbase-1b |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: EMS_all_100_code-starcoder-lora-batch_10_steps_2000 |
|
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. --> |
|
|
|
# EMS_all_100_code-starcoder-lora-batch_10_steps_2000 |
|
|
|
This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0375 |
|
|
|
## 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: 10 |
|
- eval_batch_size: 10 |
|
- seed: 42 |
|
- 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: cosine |
|
- lr_scheduler_warmup_steps: 30 |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.416 | 0.05 | 100 | 0.4470 | |
|
| 0.3877 | 0.1 | 200 | 0.3435 | |
|
| 0.3784 | 0.15 | 300 | 0.2490 | |
|
| 0.1561 | 0.2 | 400 | 0.2118 | |
|
| 0.2157 | 0.25 | 500 | 0.1682 | |
|
| 0.1654 | 0.3 | 600 | 0.1379 | |
|
| 0.1178 | 0.35 | 700 | 0.1232 | |
|
| 0.1623 | 0.4 | 800 | 0.1032 | |
|
| 0.1204 | 0.45 | 900 | 0.0854 | |
|
| 0.1155 | 0.5 | 1000 | 0.0702 | |
|
| 0.0812 | 0.55 | 1100 | 0.0633 | |
|
| 0.0993 | 0.6 | 1200 | 0.0550 | |
|
| 0.0704 | 0.65 | 1300 | 0.0496 | |
|
| 0.0816 | 0.7 | 1400 | 0.0456 | |
|
| 0.0767 | 0.75 | 1500 | 0.0421 | |
|
| 0.0658 | 0.8 | 1600 | 0.0397 | |
|
| 0.0612 | 0.85 | 1700 | 0.0385 | |
|
| 0.0557 | 0.9 | 1800 | 0.0379 | |
|
| 0.07 | 0.95 | 1900 | 0.0376 | |
|
| 0.0695 | 1.0 | 2000 | 0.0375 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.14.0 |
|
- Transformers 4.46.3 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.20.3 |
