|
|
--- |
|
|
library_name: peft |
|
|
license: bigcode-openrail-m |
|
|
base_model: bigcode/starcoderbase-1b |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: starcoder-1b-hf-stack-v1-lora |
|
|
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. --> |
|
|
|
|
|
# starcoder-1b-hf-stack-v1-lora |
|
|
|
|
|
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: 1.4037 |
|
|
|
|
|
## 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 |
|
|
- 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: 5 |
|
|
- training_steps: 100 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 1.0738 | 0.1 | 10 | 1.4130 | |
|
|
| 1.0391 | 0.2 | 20 | 1.4104 | |
|
|
| 0.9788 | 0.3 | 30 | 1.4124 | |
|
|
| 1.033 | 0.4 | 40 | 1.4151 | |
|
|
| 0.9991 | 0.5 | 50 | 1.4070 | |
|
|
| 1.0163 | 0.6 | 60 | 1.4138 | |
|
|
| 0.9945 | 0.7 | 70 | 1.4015 | |
|
|
| 0.9967 | 0.8 | 80 | 1.4051 | |
|
|
| 1.0755 | 0.9 | 90 | 1.4043 | |
|
|
| 0.9449 | 1.0 | 100 | 1.4037 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.3.2 |
|
|
- Tokenizers 0.21.0 |
