metadata
library_name: transformers
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: peft-starcoder-finetuned
results: []
peft-starcoder-finetuned
This model is a fine-tuned version of bigcode/starcoderbase-1b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5923
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- 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: 50
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5622 | 0.1992 | 100 | 1.2485 |
| 0.4589 | 0.3984 | 200 | 1.2126 |
| 0.4216 | 0.5976 | 300 | 1.2730 |
| 0.3743 | 0.7968 | 400 | 1.2278 |
| 0.3535 | 0.9960 | 500 | 1.2615 |
| 0.3011 | 1.1952 | 600 | 1.2960 |
| 0.2653 | 1.3944 | 700 | 1.3112 |
| 0.2734 | 1.5936 | 800 | 1.3759 |
| 0.2855 | 1.7928 | 900 | 1.3015 |
| 0.2528 | 1.9920 | 1000 | 1.3470 |
| 0.2083 | 2.1912 | 1100 | 1.4719 |
| 0.2318 | 2.3904 | 1200 | 1.4494 |
| 0.1935 | 2.5896 | 1300 | 1.4621 |
| 0.1809 | 2.7888 | 1400 | 1.4829 |
| 0.227 | 2.9880 | 1500 | 1.4911 |
| 0.1813 | 3.1873 | 1600 | 1.5903 |
| 0.1893 | 3.3865 | 1700 | 1.5906 |
| 0.1674 | 3.5857 | 1800 | 1.5916 |
| 0.1723 | 3.7849 | 1900 | 1.5921 |
| 0.1843 | 3.9841 | 2000 | 1.5923 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.3