metadata
license: bigcode-openrail-m
base_model: bigcode/starcoder
tags:
- generated_from_trainer
model-index:
- name: peft-lora-starcoder15B-personal-copilot-A100-40GB-colab
results: []
peft-lora-starcoder15B-personal-copilot-A100-40GB-colab
This model is a fine-tuned version of bigcode/starcoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4471
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6622 | 0.1 | 100 | 0.5890 |
| 0.6234 | 0.2 | 200 | 0.5315 |
| 0.6612 | 0.3 | 300 | 0.4849 |
| 0.5546 | 0.4 | 400 | 0.4655 |
| 0.489 | 0.5 | 500 | 0.4620 |
| 0.5305 | 0.6 | 600 | 0.4541 |
| 0.5022 | 0.7 | 700 | 0.4492 |
| 0.577 | 0.8 | 800 | 0.4479 |
| 0.4889 | 0.9 | 900 | 0.4470 |
| 0.5597 | 1.0 | 1000 | 0.4471 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3