metadata
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: peft-lora-starcoderbase1b-personal-copilot-A100-40GB-colab-cosine
results: []
library_name: peft
peft-lora-starcoderbase1b-personal-copilot-A100-40GB-colab-cosine
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: 0.4154
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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 |
|---|---|---|---|
| 0.8697 | 0.05 | 100 | 0.7531 |
| 0.7477 | 0.1 | 200 | 0.6309 |
| 0.7431 | 0.15 | 300 | 0.6068 |
| 0.8674 | 0.2 | 400 | 0.5779 |
| 0.7061 | 0.25 | 500 | 0.5563 |
| 0.6532 | 0.3 | 600 | 0.5014 |
| 0.7218 | 0.35 | 700 | 0.4968 |
| 0.9061 | 0.4 | 800 | 0.4863 |
| 0.5569 | 0.45 | 900 | 0.4807 |
| 0.5734 | 0.5 | 1000 | 0.4418 |
| 0.5504 | 0.55 | 1100 | 0.4403 |
| 0.6654 | 0.6 | 1200 | 0.4333 |
| 0.4556 | 0.65 | 1300 | 0.4311 |
| 0.5476 | 0.7 | 1400 | 0.4205 |
| 0.4514 | 0.75 | 1500 | 0.4161 |
| 0.3709 | 0.8 | 1600 | 0.4151 |
| 0.4068 | 0.85 | 1700 | 0.4149 |
| 0.3977 | 0.9 | 1800 | 0.4163 |
| 0.4122 | 0.95 | 1900 | 0.4155 |
| 0.3718 | 1.0 | 2000 | 0.4154 |
Framework versions
- PEFT 0.5.0.dev0
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3