metadata
library_name: peft
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: model
results: []
model
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: 0.9188
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: 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: 30
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7875 | 0.05 | 100 | 0.9020 |
| 0.8714 | 0.1 | 200 | 0.9049 |
| 0.9661 | 0.15 | 300 | 0.9036 |
| 0.9201 | 0.2 | 400 | 0.9043 |
| 0.9876 | 0.25 | 500 | 0.9063 |
| 0.7047 | 0.3 | 600 | 0.9101 |
| 0.9354 | 0.35 | 700 | 0.9089 |
| 0.9068 | 0.4 | 800 | 0.9108 |
| 0.9546 | 0.45 | 900 | 0.9116 |
| 0.7253 | 0.5 | 1000 | 0.9141 |
| 0.9153 | 0.55 | 1100 | 0.9136 |
| 0.9123 | 0.6 | 1200 | 0.9148 |
| 0.8961 | 0.65 | 1300 | 0.9148 |
| 0.8893 | 0.7 | 1400 | 0.9178 |
| 0.8112 | 0.75 | 1500 | 0.9178 |
| 0.8803 | 0.8 | 1600 | 0.9167 |
| 0.8693 | 0.85 | 1700 | 0.9167 |
| 0.8919 | 0.9 | 1800 | 0.9181 |
| 0.791 | 0.95 | 1900 | 0.9190 |
| 0.9191 | 1.0 | 2000 | 0.9188 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0