metadata
library_name: peft
tags:
- generated_from_trainer
base_model: codellama/CodeLlama-13b-Instruct-hf
model-index:
- name: peft-lora-CodeLlama-13b-web-copilot
results: []
peft-lora-CodeLlama-13b-web-copilot
This model is a fine-tuned version of codellama/CodeLlama-13b-Instruct-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5057
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: 0.0003
- 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_ratio: 0.1
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6412 | 0.05 | 100 | 0.7106 |
| 0.6793 | 0.1 | 200 | 0.6769 |
| 0.5832 | 0.15 | 300 | 0.6106 |
| 0.4985 | 0.2 | 400 | 0.5781 |
| 0.4751 | 0.25 | 500 | 0.5553 |
| 0.3364 | 0.3 | 600 | 0.5514 |
| 0.5155 | 0.35 | 700 | 0.5374 |
| 0.302 | 0.4 | 800 | 0.5297 |
| 0.8282 | 0.45 | 900 | 0.5221 |
| 0.4002 | 0.5 | 1000 | 0.5145 |
| 0.3956 | 0.55 | 1100 | 0.5091 |
| 0.2477 | 0.6 | 1200 | 0.5085 |
| 0.3478 | 0.65 | 1300 | 0.5042 |
| 0.2842 | 0.7 | 1400 | 0.5040 |
| 0.7054 | 0.75 | 1500 | 0.5044 |
| 0.2784 | 0.8 | 1600 | 0.5046 |
| 0.3101 | 0.85 | 1700 | 0.5047 |
| 0.2627 | 0.9 | 1800 | 0.5048 |
| 0.3749 | 0.95 | 1900 | 0.5057 |
| 0.1992 | 1.0 | 2000 | 0.5057 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2