metadata
library_name: peft
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: starcoder-peft-airscript
results: []
starcoder-peft-airscript
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: 0.8171
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: 10
- eval_batch_size: 10
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 1400
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9892 | 0.0714 | 100 | 0.9351 |
| 0.7083 | 0.1429 | 200 | 0.7751 |
| 0.5442 | 0.2143 | 300 | 0.7227 |
| 0.4403 | 0.2857 | 400 | 0.7127 |
| 0.3724 | 0.3571 | 500 | 0.7285 |
| 0.3268 | 0.4286 | 600 | 0.7396 |
| 0.3057 | 0.5 | 700 | 0.7587 |
| 0.2798 | 0.5714 | 800 | 0.7704 |
| 0.2616 | 0.6429 | 900 | 0.7888 |
| 0.2418 | 0.7143 | 1000 | 0.8010 |
| 0.2314 | 0.7857 | 1100 | 0.8092 |
| 0.2268 | 0.8571 | 1200 | 0.8147 |
| 0.223 | 0.9286 | 1300 | 0.8185 |
| 0.2207 | 1.0 | 1400 | 0.8171 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.5.0
- Datasets 3.0.1
- Tokenizers 0.20.1