metadata
library_name: peft
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: EMS_code-starcoder-lora-batch_5_2000
results: []
EMS_code-starcoder-lora-batch_5_2000
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: 1.0787
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: 5
- eval_batch_size: 5
- 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 |
|---|---|---|---|
| 0.4285 | 0.05 | 100 | 0.7660 |
| 0.3603 | 0.1 | 200 | 0.7604 |
| 0.3386 | 0.15 | 300 | 0.7899 |
| 0.3011 | 0.2 | 400 | 0.7911 |
| 0.2506 | 0.25 | 500 | 0.8331 |
| 0.2171 | 0.3 | 600 | 0.8452 |
| 0.1799 | 0.35 | 700 | 0.8751 |
| 0.1548 | 0.4 | 800 | 0.9256 |
| 0.1434 | 0.45 | 900 | 0.9176 |
| 0.1085 | 0.5 | 1000 | 0.9773 |
| 0.1032 | 0.55 | 1100 | 0.9757 |
| 0.093 | 0.6 | 1200 | 1.0143 |
| 0.0827 | 0.65 | 1300 | 1.0253 |
| 0.0765 | 0.7 | 1400 | 1.0489 |
| 0.0731 | 0.75 | 1500 | 1.0491 |
| 0.071 | 0.8 | 1600 | 1.0633 |
| 0.0667 | 0.85 | 1700 | 1.0734 |
| 0.0641 | 0.9 | 1800 | 1.0741 |
| 0.0641 | 0.95 | 1900 | 1.0791 |
| 0.0612 | 1.0 | 2000 | 1.0787 |
Framework versions
- PEFT 0.14.0
- Transformers 4.46.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.20.3