metadata
license: llama2
library_name: peft
tags:
- generated_from_trainer
base_model: codellama/CodeLlama-7b-hf
model-index:
- name: sql-code-llama
results: []
sql-code-llama
This model is a fine-tuned version of codellama/CodeLlama-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4621
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: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 400
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1563 | 0.04 | 20 | 1.9767 |
| 1.1222 | 0.07 | 40 | 0.8267 |
| 0.814 | 0.11 | 60 | 0.6637 |
| 0.5956 | 0.14 | 80 | 0.5908 |
| 0.405 | 0.18 | 100 | 0.5643 |
| 0.5643 | 0.22 | 120 | 0.5204 |
| 0.4326 | 0.25 | 140 | 0.5107 |
| 0.6401 | 0.29 | 160 | 0.5211 |
| 0.4789 | 0.33 | 180 | 0.4908 |
| 0.3577 | 0.36 | 200 | 0.5069 |
| 0.5289 | 0.4 | 220 | 0.4851 |
| 0.3971 | 0.43 | 240 | 0.4811 |
| 0.5972 | 0.47 | 260 | 0.4807 |
| 0.4683 | 0.51 | 280 | 0.4712 |
| 0.3442 | 0.54 | 300 | 0.4790 |
| 0.5148 | 0.58 | 320 | 0.4692 |
| 0.3917 | 0.62 | 340 | 0.4661 |
| 0.5769 | 0.65 | 360 | 0.4661 |
| 0.4603 | 0.69 | 380 | 0.4629 |
| 0.3461 | 0.72 | 400 | 0.4621 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.36.0
- Pytorch 2.0.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2