metadata
license: bigcode-openrail-m
library_name: peft
tags:
- generated_from_trainer
base_model: bigcode/starcoderbase-1b
model-index:
- name: peft-lora-starcoder1B-Instruction-ny8-MIX-2000
results: []
peft-lora-starcoder1B-Instruction-ny8-MIX-2000
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: 0.1039
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1705 | 0.05 | 100 | 0.1413 |
| 0.1338 | 0.1 | 200 | 0.1216 |
| 0.1191 | 0.15 | 300 | 0.1143 |
| 0.1147 | 0.2 | 400 | 0.1084 |
| 0.1109 | 0.25 | 500 | 0.1063 |
| 0.1061 | 0.3 | 600 | 0.1041 |
| 0.1059 | 0.35 | 700 | 0.1037 |
| 0.1018 | 0.4 | 800 | 0.1026 |
| 0.1011 | 0.45 | 900 | 0.1021 |
| 0.0996 | 0.5 | 1000 | 0.1017 |
| 0.0981 | 0.55 | 1100 | 0.1010 |
| 0.0961 | 0.6 | 1200 | 0.1012 |
| 0.0941 | 0.65 | 1300 | 0.1020 |
| 0.0926 | 0.7 | 1400 | 0.1018 |
| 0.0907 | 0.75 | 1500 | 0.1026 |
| 0.0901 | 0.8 | 1600 | 0.1028 |
| 0.0872 | 0.85 | 1700 | 0.1034 |
| 0.0889 | 0.9 | 1800 | 0.1037 |
| 0.087 | 0.95 | 1900 | 0.1038 |
| 0.0876 | 1.0 | 2000 | 0.1039 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0