metadata
library_name: peft
base_model: NousResearch/CodeLlama-13b-hf
tags:
- axolotl
- generated_from_trainer
model-index:
- name: fdaf4540-db8f-4836-b1d2-f4d818a04a6b
results: []
fdaf4540-db8f-4836-b1d2-f4d818a04a6b
This model is a fine-tuned version of NousResearch/CodeLlama-13b-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4017
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: 0.000206
- 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 | 0.0002 | 1 | 2.3596 |
| 2.5797 | 0.0120 | 50 | 0.8047 |
| 2.4339 | 0.0240 | 100 | 0.6783 |
| 1.8452 | 0.0360 | 150 | 0.6230 |
| 1.6012 | 0.0480 | 200 | 0.5664 |
| 1.489 | 0.0600 | 250 | 0.5061 |
| 1.3479 | 0.0720 | 300 | 0.4863 |
| 1.4152 | 0.0839 | 350 | 0.4434 |
| 1.8286 | 0.0959 | 400 | 0.4185 |
| 1.2354 | 0.1079 | 450 | 0.4053 |
| 0.9806 | 0.1199 | 500 | 0.4017 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1