peft-starcoder-lora-a100
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: 1.0550
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 |
|---|---|---|---|
| 1.0005 | 0.05 | 100 | 0.9347 |
| 0.9939 | 0.1 | 200 | 0.9456 |
| 0.6657 | 0.15 | 300 | 0.9741 |
| 0.876 | 0.2 | 400 | 0.9765 |
| 0.9736 | 0.25 | 500 | 0.9916 |
| 0.5713 | 0.3 | 600 | 0.9979 |
| 0.7916 | 0.35 | 700 | 1.0035 |
| 0.8799 | 0.4 | 800 | 1.0083 |
| 0.5209 | 0.45 | 900 | 1.0225 |
| 0.7409 | 0.5 | 1000 | 1.0318 |
| 0.7843 | 0.55 | 1100 | 1.0195 |
| 0.4715 | 0.6 | 1200 | 1.0547 |
| 0.7062 | 0.65 | 1300 | 1.0521 |
| 0.6678 | 0.7 | 1400 | 1.0479 |
| 0.5542 | 0.75 | 1500 | 1.0527 |
| 0.6735 | 0.8 | 1600 | 1.0521 |
| 0.591 | 0.85 | 1700 | 1.0556 |
| 0.619 | 0.9 | 1800 | 1.0586 |
| 0.5836 | 0.95 | 1900 | 1.0570 |
| 0.6231 | 1.0 | 2000 | 1.0550 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.13.3