metadata
base_model: bigcode/starcoderbase-1b
library_name: peft
license: bigcode-openrail-m
tags:
- generated_from_trainer
model-index:
- name: out
results: []
out
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: 0.7275
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.849 | 0.05 | 100 | 0.7259 |
| 0.777 | 0.1 | 200 | 0.7328 |
| 0.71 | 0.15 | 300 | 0.7398 |
| 0.7214 | 0.2 | 400 | 0.7538 |
| 0.6868 | 0.25 | 500 | 0.7621 |
| 0.8951 | 0.3 | 600 | 0.7636 |
| 0.9411 | 0.35 | 700 | 0.7690 |
| 0.9354 | 0.4 | 800 | 0.7763 |
| 0.8658 | 0.45 | 900 | 0.7617 |
| 0.7322 | 0.5 | 1000 | 0.7428 |
| 0.8219 | 0.55 | 1100 | 0.7444 |
| 0.8431 | 0.6 | 1200 | 0.7444 |
| 0.8644 | 0.65 | 1300 | 0.7459 |
| 0.8033 | 0.7 | 1400 | 0.7449 |
| 0.77 | 0.75 | 1500 | 0.7398 |
| 0.3502 | 0.8 | 1600 | 0.7405 |
| 0.5107 | 0.85 | 1700 | 0.7308 |
| 0.8587 | 0.9 | 1800 | 0.7265 |
| 0.714 | 0.95 | 1900 | 0.7277 |
| 0.7406 | 1.0 | 2000 | 0.7275 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1