metadata
license: llama2
base_model: codellama/CodeLlama-13b-hf
tags:
- generated_from_trainer
model-index:
- name: code-llama-13b-text-to-sparql
results: []
code-llama-13b-text-to-sparql
This model is a fine-tuned version of codellama/CodeLlama-13b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1870
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: 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: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1121 | 0.0710 | 20 | 1.0865 |
| 0.6067 | 0.1421 | 40 | 0.3437 |
| 0.2982 | 0.2131 | 60 | 0.2775 |
| 0.2433 | 0.2842 | 80 | 0.2465 |
| 0.2162 | 0.3552 | 100 | 0.2657 |
| 0.2308 | 0.4263 | 120 | 0.2303 |
| 0.2356 | 0.4973 | 140 | 0.2217 |
| 0.239 | 0.5684 | 160 | 0.2167 |
| 0.2159 | 0.6394 | 180 | 0.2112 |
| 0.2005 | 0.7105 | 200 | 0.2217 |
| 0.2177 | 0.7815 | 220 | 0.2070 |
| 0.2048 | 0.8526 | 240 | 0.2018 |
| 0.2092 | 0.9236 | 260 | 0.1976 |
| 0.2057 | 0.9947 | 280 | 0.1959 |
| 0.198 | 1.0657 | 300 | 0.1929 |
| 0.1988 | 1.1368 | 320 | 0.1908 |
| 0.1886 | 1.2078 | 340 | 0.1906 |
| 0.1927 | 1.2789 | 360 | 0.1883 |
| 0.1841 | 1.3499 | 380 | 0.1872 |
| 0.1863 | 1.4210 | 400 | 0.1870 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.10.1
- Tokenizers 0.19.1