metadata
library_name: peft
base_model: NousResearch/CodeLlama-7b-hf-flash
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 8a92b98d-5b26-493c-9f01-be0f56fe4232
results: []
8a92b98d-5b26-493c-9f01-be0f56fe4232
This model is a fine-tuned version of NousResearch/CodeLlama-7b-hf-flash on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6937
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: 0.000203
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0001 | 1 | 1.1523 |
| 2.1042 | 0.0036 | 50 | 0.9426 |
| 1.8717 | 0.0071 | 100 | 0.8532 |
| 1.6186 | 0.0107 | 150 | 0.8275 |
| 1.7291 | 0.0143 | 200 | 0.7944 |
| 1.6774 | 0.0179 | 250 | 0.7708 |
| 1.6611 | 0.0214 | 300 | 0.7363 |
| 1.5363 | 0.0250 | 350 | 0.7127 |
| 1.5478 | 0.0286 | 400 | 0.7001 |
| 1.555 | 0.0322 | 450 | 0.6947 |
| 1.6401 | 0.0357 | 500 | 0.6937 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1