metadata
license: llama2
library_name: peft
tags:
- generated_from_trainer
base_model: codellama/CodeLlama-7b-Instruct-hf
model-index:
- name: codellama-hugcoder-v2
results: []
codellama-hugcoder-v2
This model is a fine-tuned version of codellama/CodeLlama-7b-Instruct-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4602
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: 16
- eval_batch_size: 16
- seed: 11
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|
| 0.5827 | 0.05 | 100 | 0.6188 |
| 0.5648 | 0.1 | 200 | 0.5643 |
| 0.5316 | 0.15 | 300 | 0.5359 |
| 0.5008 | 0.2 | 400 | 0.5202 |
| 0.4919 | 0.25 | 500 | 0.5042 |
| 0.4665 | 0.3 | 600 | 0.4962 |
| 0.4324 | 0.35 | 700 | 0.4856 |
| 0.4179 | 0.4 | 800 | 0.4804 |
| 0.3614 | 0.45 | 900 | 0.4738 |
| 0.4344 | 0.5 | 1000 | 0.4703 |
| 0.3473 | 0.55 | 1100 | 0.4672 |
| 0.3777 | 0.6 | 1200 | 0.4648 |
| 0.3378 | 0.65 | 1300 | 0.4620 |
| 0.3744 | 0.7 | 1400 | 0.4614 |
| 0.3834 | 0.75 | 1500 | 0.4610 |
| 0.2859 | 0.8 | 1600 | 0.4603 |
| 0.3787 | 0.85 | 1700 | 0.4598 |
| 0.3132 | 0.9 | 1800 | 0.4597 |
| 0.3607 | 0.95 | 1900 | 0.4595 |
| 0.3684 | 1.0 | 2000 | 0.4602 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1