metadata
license: llama2
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: meta-llama/CodeLlama-7b-Instruct-hf
model-index:
- name: codellama-instruct-mojo
results: []
codellama-instruct-mojo
This model is a fine-tuned version of meta-llama/CodeLlama-7b-Instruct-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4163
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7629 | 1.0 | 50 | 1.2447 |
| 1.1745 | 2.0 | 100 | 1.0526 |
| 0.8293 | 3.0 | 150 | 1.0006 |
| 0.6443 | 4.0 | 200 | 1.0057 |
| 0.5093 | 5.0 | 250 | 1.0275 |
| 0.4048 | 6.0 | 300 | 1.0305 |
| 0.3276 | 7.0 | 350 | 1.1752 |
| 0.2657 | 8.0 | 400 | 1.2200 |
| 0.2288 | 9.0 | 450 | 1.3527 |
| 0.1876 | 10.0 | 500 | 1.4163 |
Framework versions
- PEFT 0.11.2.dev0
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1