metadata
base_model: bigcode/starcoderbase-1b
library_name: peft
license: bigcode-openrail-m
tags:
- generated_from_trainer
model-index:
- name: peft-starcoder-finetuned
results: []
peft-starcoder-finetuned
This model is a fine-tuned version of bigcode/starcoderbase-1b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0382
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: 5e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.276 | 0.0416 | 10 | 1.0832 |
| 1.2151 | 0.0833 | 20 | 1.0789 |
| 1.2213 | 0.1249 | 30 | 1.0736 |
| 1.1694 | 0.1666 | 40 | 1.0718 |
| 1.2627 | 0.2082 | 50 | 1.0696 |
| 1.1801 | 0.2499 | 60 | 1.0690 |
| 1.1013 | 0.2915 | 70 | 1.0637 |
| 1.082 | 0.3332 | 80 | 1.0643 |
| 1.0783 | 0.3748 | 90 | 1.0638 |
| 1.1166 | 0.4164 | 100 | 1.0615 |
| 1.1207 | 0.4581 | 110 | 1.0581 |
| 1.197 | 0.4997 | 120 | 1.0562 |
| 1.012 | 0.5414 | 130 | 1.0583 |
| 1.1291 | 0.5830 | 140 | 1.0515 |
| 1.0695 | 0.6247 | 150 | 1.0520 |
| 1.0924 | 0.6663 | 160 | 1.0514 |
| 1.1287 | 0.7080 | 170 | 1.0536 |
| 1.0514 | 0.7496 | 180 | 1.0508 |
| 1.1101 | 0.7913 | 190 | 1.0491 |
| 1.1474 | 0.8329 | 200 | 1.0489 |
| 1.1451 | 0.8745 | 210 | 1.0476 |
| 1.1688 | 0.9162 | 220 | 1.0434 |
| 1.053 | 0.9578 | 230 | 1.0447 |
| 1.0146 | 0.9995 | 240 | 1.0438 |
| 1.1127 | 1.0411 | 250 | 1.0442 |
| 0.9734 | 1.0828 | 260 | 1.0420 |
| 1.0315 | 1.1244 | 270 | 1.0445 |
| 1.0803 | 1.1661 | 280 | 1.0435 |
| 1.0892 | 1.2077 | 290 | 1.0440 |
| 1.0191 | 1.2493 | 300 | 1.0427 |
| 1.034 | 1.2910 | 310 | 1.0416 |
| 1.1136 | 1.3326 | 320 | 1.0413 |
| 0.9837 | 1.3743 | 330 | 1.0413 |
| 1.0659 | 1.4159 | 340 | 1.0405 |
| 0.9931 | 1.4576 | 350 | 1.0409 |
| 1.1141 | 1.4992 | 360 | 1.0403 |
| 1.0851 | 1.5409 | 370 | 1.0399 |
| 1.053 | 1.5825 | 380 | 1.0390 |
| 1.0652 | 1.6242 | 390 | 1.0395 |
| 1.0998 | 1.6658 | 400 | 1.0396 |
| 0.9909 | 1.7074 | 410 | 1.0390 |
| 1.0946 | 1.7491 | 420 | 1.0386 |
| 1.0471 | 1.7907 | 430 | 1.0382 |
| 0.9719 | 1.8324 | 440 | 1.0382 |
| 1.0641 | 1.8740 | 450 | 1.0382 |
| 1.0003 | 1.9157 | 460 | 1.0383 |
| 1.0128 | 1.9573 | 470 | 1.0383 |
| 1.0637 | 1.9990 | 480 | 1.0384 |
| 1.0583 | 2.0406 | 490 | 1.0383 |
| 0.991 | 2.0822 | 500 | 1.0382 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.3