metadata
library_name: peft
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: peft-starcoder-lora-a100
results: []
peft-starcoder-lora-a100
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: 1.0590
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 |
|---|---|---|---|
| 0.9659 | 0.05 | 100 | 0.9193 |
| 0.9899 | 0.1 | 200 | 0.9442 |
| 0.6517 | 0.15 | 300 | 0.9689 |
| 0.8964 | 0.2 | 400 | 0.9810 |
| 0.9496 | 0.25 | 500 | 0.9721 |
| 0.5741 | 0.3 | 600 | 1.0061 |
| 0.7984 | 0.35 | 700 | 1.0172 |
| 0.8268 | 0.4 | 800 | 1.0140 |
| 0.5207 | 0.45 | 900 | 1.0180 |
| 0.7507 | 0.5 | 1000 | 1.0298 |
| 0.7717 | 0.55 | 1100 | 1.0366 |
| 0.4746 | 0.6 | 1200 | 1.0502 |
| 0.696 | 0.65 | 1300 | 1.0391 |
| 0.6846 | 0.7 | 1400 | 1.0470 |
| 0.5397 | 0.75 | 1500 | 1.0498 |
| 0.6567 | 0.8 | 1600 | 1.0540 |
| 0.6003 | 0.85 | 1700 | 1.0600 |
| 0.6013 | 0.9 | 1800 | 1.0620 |
| 0.555 | 0.95 | 1900 | 1.0616 |
| 0.5884 | 1.0 | 2000 | 1.0590 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.2
- Pytorch 2.5.1
- Datasets 3.2.0
- Tokenizers 0.21.0