Downloads · 30 days
3
23% of all-time downloads
starcode-fine-tune
amiraessawy/starcode-fine-tune
starcode-fine-tune is a machine learning model from amiraessawy. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as bigcode-openrail-m.
should probably proofread and complete it, then remove this comment. --
All-time downloads
13
Public
Repo size
423 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors22.2 MB · 100%
At a glance
- Library
- peft
- License
- bigcode-openrail-m
- Access
- Public
- Created
- Mar 11, 2025
- Updated
- Mar 11, 2025
- SHA
- 8941e2cd
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
starcode-fine-tune
This model is a fine-tuned version of bigcode/starcoderbase-1b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0591
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: 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 |
|---|---|---|---|
| 0.9656 | 0.05 | 100 | 0.9206 |
| 0.9897 | 0.1 | 200 | 0.9453 |
| 0.6515 | 0.15 | 300 | 0.9679 |
| 0.8963 | 0.2 | 400 | 0.9839 |
| 0.9494 | 0.25 | 500 | 0.9732 |
| 0.5738 | 0.3 | 600 | 1.0127 |
| 0.7979 | 0.35 | 700 | 1.0197 |
| 0.8265 | 0.4 | 800 | 1.0112 |
| 0.5204 | 0.45 | 900 | 1.0218 |
| 0.7504 | 0.5 | 1000 | 1.0333 |
| 0.7716 | 0.55 | 1100 | 1.0349 |
| 0.4745 | 0.6 | 1200 | 1.0494 |
| 0.6958 | 0.65 | 1300 | 1.0416 |
| 0.6842 | 0.7 | 1400 | 1.0456 |
| 0.5394 | 0.75 | 1500 | 1.0488 |
| 0.6572 | 0.8 | 1600 | 1.0547 |
| 0.6002 | 0.85 | 1700 | 1.0602 |
| 0.6013 | 0.9 | 1800 | 1.0629 |
| 0.5553 | 0.95 | 1900 | 1.0614 |
| 0.5881 | 1.0 | 2000 | 1.0591 |
Framework versions
- PEFT 0.14.0
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Library
- peft
- License
- bigcode-openrail-m
- Created
- Mar 11, 2025
- Updated
- Mar 11, 2025