peft-starcoder-lora
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: 5.9439
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 |
|---|---|---|---|
| 5.8019 | 0.05 | 100 | 8.1006 |
| 5.9737 | 0.1 | 200 | 7.2985 |
| 5.1109 | 0.15 | 300 | 6.3542 |
| 5.0956 | 0.2 | 400 | 6.2918 |
| 5.2913 | 0.25 | 500 | 6.1454 |
| 4.6567 | 0.3 | 600 | 6.0157 |
| 5.1439 | 0.35 | 700 | 6.0052 |
| 5.2159 | 0.4 | 800 | 6.0141 |
| 4.7227 | 0.45 | 900 | 5.9708 |
| 5.2372 | 0.5 | 1000 | 5.9662 |
| 5.5667 | 0.55 | 1100 | 6.1102 |
| 4.6813 | 0.6 | 1200 | 5.9753 |
| 5.1002 | 0.65 | 1300 | 5.9829 |
| 5.327 | 0.7 | 1400 | 5.9327 |
| 4.6781 | 0.75 | 1500 | 5.9415 |
| 5.2732 | 0.8 | 1600 | 5.9264 |
| 5.2995 | 0.85 | 1700 | 5.9178 |
| 4.5842 | 0.9 | 1800 | 5.9290 |
| 5.2401 | 0.95 | 1900 | 5.9506 |
| 5.1396 | 1.0 | 2000 | 5.9439 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
Model tree for MariaK/peft-starcoder-lora
Base model
bigcode/starcoderbase-1b