metadata
base_model: bigcode/starcoderbase-1b
library_name: peft
license: bigcode-openrail-m
tags:
- generated_from_trainer
model-index:
- name: peft-starcoder-lora-h100
results: []
peft-starcoder-lora-h100
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: 1.0568
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 |
|---|---|---|---|
| 0.9675 | 0.05 | 100 | 0.9193 |
| 0.9915 | 0.1 | 200 | 0.9468 |
| 0.652 | 0.15 | 300 | 0.9646 |
| 0.8967 | 0.2 | 400 | 0.9767 |
| 0.9497 | 0.25 | 500 | 0.9700 |
| 0.5739 | 0.3 | 600 | 1.0008 |
| 0.799 | 0.35 | 700 | 1.0138 |
| 0.8269 | 0.4 | 800 | 1.0109 |
| 0.5207 | 0.45 | 900 | 1.0156 |
| 0.7507 | 0.5 | 1000 | 1.0319 |
| 0.7716 | 0.55 | 1100 | 1.0322 |
| 0.4743 | 0.6 | 1200 | 1.0489 |
| 0.6963 | 0.65 | 1300 | 1.0445 |
| 0.6841 | 0.7 | 1400 | 1.0475 |
| 0.5401 | 0.75 | 1500 | 1.0505 |
| 0.6562 | 0.8 | 1600 | 1.0566 |
| 0.601 | 0.85 | 1700 | 1.0603 |
| 0.6019 | 0.9 | 1800 | 1.0594 |
| 0.555 | 0.95 | 1900 | 1.0599 |
| 0.5885 | 1.0 | 2000 | 1.0568 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.1.0+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1