metadata
license: bigcode-openrail-m
library_name: peft
tags:
- generated_from_trainer
base_model: bigcode/starcoder
model-index:
- name: peft-lora-zencoder15B-personal-copilot
results: []
peft-lora-zencoder15B-personal-copilot
This model is a fine-tuned version of bigcode/starcoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3124
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
|---|---|---|---|
| 0.7534 | 0.1 | 100 | 0.4016 |
| 0.6715 | 0.2 | 200 | 0.3700 |
| 0.5283 | 0.3 | 300 | 0.3647 |
| 0.574 | 0.4 | 400 | 0.3388 |
| 0.5841 | 0.5 | 500 | 0.3193 |
| 0.5268 | 0.6 | 600 | 0.3202 |
| 0.5043 | 0.7 | 700 | 0.3124 |
| 0.4981 | 0.8 | 800 | 0.3138 |
| 0.4995 | 0.9 | 900 | 0.3126 |
| 0.4779 | 1.0 | 1000 | 0.3124 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0