|
--- |
|
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: 5.6557 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 30 |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 5.5246 | 0.05 | 100 | 7.4569 | |
|
| 5.6178 | 0.1 | 200 | 7.2622 | |
|
| 5.1291 | 0.15 | 300 | 6.4100 | |
|
| 5.0522 | 0.2 | 400 | 6.3068 | |
|
| 5.2029 | 0.25 | 500 | 6.1171 | |
|
| 4.6541 | 0.3 | 600 | 6.0183 | |
|
| 5.1002 | 0.35 | 700 | 6.0004 | |
|
| 5.0498 | 0.4 | 800 | 5.8895 | |
|
| 4.5412 | 0.45 | 900 | 5.8138 | |
|
| 5.0007 | 0.5 | 1000 | 5.8342 | |
|
| 5.0265 | 0.55 | 1100 | 5.7819 | |
|
| 4.4118 | 0.6 | 1200 | 5.7206 | |
|
| 4.7825 | 0.65 | 1300 | 5.7364 | |
|
| 4.9802 | 0.7 | 1400 | 5.7123 | |
|
| 4.3687 | 0.75 | 1500 | 5.6896 | |
|
| 4.8847 | 0.8 | 1600 | 5.6759 | |
|
| 4.9144 | 0.85 | 1700 | 5.6624 | |
|
| 4.2487 | 0.9 | 1800 | 5.6601 | |
|
| 4.7984 | 0.95 | 1900 | 5.6640 | |
|
| 4.7042 | 1.0 | 2000 | 5.6557 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
