|
|
--- |
|
|
library_name: peft |
|
|
license: bigcode-openrail-m |
|
|
base_model: bigcode/starcoderbase-1b |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: peft-starcoder-lora-a100 |
|
|
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. --> |
|
|
|
|
|
# peft-starcoder-lora-a100 |
|
|
|
|
|
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: 1.1557 |
|
|
|
|
|
## 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: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 8 |
|
|
- total_train_batch_size: 64 |
|
|
- total_eval_batch_size: 64 |
|
|
- optimizer: Use 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.9702 | 0.05 | 100 | 0.9343 | |
|
|
| 0.8928 | 0.1 | 200 | 0.9666 | |
|
|
| 0.5992 | 0.15 | 300 | 0.9979 | |
|
|
| 0.8611 | 0.2 | 400 | 1.0115 | |
|
|
| 0.7631 | 0.25 | 500 | 1.0335 | |
|
|
| 0.7289 | 0.3 | 600 | 1.0624 | |
|
|
| 0.7408 | 0.35 | 700 | 1.0725 | |
|
|
| 0.5599 | 0.4 | 800 | 1.0900 | |
|
|
| 0.7736 | 0.45 | 900 | 1.0943 | |
|
|
| 0.7176 | 0.5 | 1000 | 1.1147 | |
|
|
| 0.4677 | 0.55 | 1100 | 1.1284 | |
|
|
| 0.6916 | 0.6 | 1200 | 1.1149 | |
|
|
| 0.5944 | 0.65 | 1300 | 1.1357 | |
|
|
| 0.66 | 0.7 | 1400 | 1.1425 | |
|
|
| 0.6722 | 0.75 | 1500 | 1.1408 | |
|
|
| 0.4843 | 0.8 | 1600 | 1.1575 | |
|
|
| 0.742 | 0.85 | 1700 | 1.1553 | |
|
|
| 0.6307 | 0.9 | 1800 | 1.1540 | |
|
|
| 0.5652 | 0.95 | 1900 | 1.1576 | |
|
|
| 0.6771 | 1.0 | 2000 | 1.1557 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.15.2 |
|
|
- Transformers 4.51.3 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.1 |
