---
license: llama2
library_name: peft
tags:
- axolotl
- generated_from_trainer
base_model: codellama/CodeLlama-7b-hf
model-index:
- name: EvolCodeLlama-7b
results: []
---
[
](https://github.com/OpenAccess-AI-Collective/axolotl)
See axolotl config
axolotl version: `0.4.0`
```yaml
base_model: codellama/CodeLlama-7b-hf
base_model_config: codellama/CodeLlama-7b-hf
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true
hub_model_id: EvolCodeLlama-7b
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: mlabonne/Evol-Instruct-Python-1k
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.02
output_dir: ./qlora-out
adapter: qlora
lora_model_dir:
sequence_len: 2048
sample_packing: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project: axolotl
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 100
eval_steps: 0.01
save_strategy: epoch
save_steps:
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: ""
eos_token: ""
unk_token: ""
```
# EvolCodeLlama-7b
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3796
## 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: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.3178 | 0.01 | 1 | 0.5311 |
| 0.3147 | 0.03 | 4 | 0.5312 |
| 0.3626 | 0.07 | 8 | 0.5310 |
| 0.6265 | 0.1 | 12 | 0.5296 |
| 0.429 | 0.14 | 16 | 0.5270 |
| 0.5086 | 0.17 | 20 | 0.5205 |
| 0.4335 | 0.21 | 24 | 0.5067 |
| 0.3383 | 0.24 | 28 | 0.4842 |
| 0.3688 | 0.28 | 32 | 0.4603 |
| 0.2528 | 0.31 | 36 | 0.4403 |
| 0.3105 | 0.35 | 40 | 0.4251 |
| 0.4936 | 0.38 | 44 | 0.4162 |
| 0.4146 | 0.42 | 48 | 0.4086 |
| 0.3327 | 0.45 | 52 | 0.4024 |
| 0.3429 | 0.48 | 56 | 0.3971 |
| 0.3328 | 0.52 | 60 | 0.3937 |
| 0.1844 | 0.55 | 64 | 0.3901 |
| 0.3001 | 0.59 | 68 | 0.3887 |
| 0.3632 | 0.62 | 72 | 0.3872 |
| 0.1997 | 0.66 | 76 | 0.3847 |
| 0.2461 | 0.69 | 80 | 0.3823 |
| 0.2865 | 0.73 | 84 | 0.3812 |
| 0.26 | 0.76 | 88 | 0.3805 |
| 0.3191 | 0.8 | 92 | 0.3792 |
| 0.4642 | 0.83 | 96 | 0.3763 |
| 0.2649 | 0.87 | 100 | 0.3750 |
| 0.2095 | 0.9 | 104 | 0.3727 |
| 0.2738 | 0.94 | 108 | 0.3737 |
| 0.4274 | 0.97 | 112 | 0.3730 |
| 0.2722 | 1.0 | 116 | 0.3724 |
| 0.2164 | 1.02 | 120 | 0.3705 |
| 0.1549 | 1.05 | 124 | 0.3726 |
| 0.3051 | 1.08 | 128 | 0.3725 |
| 0.1873 | 1.12 | 132 | 0.3730 |
| 0.3388 | 1.15 | 136 | 0.3738 |
| 0.2504 | 1.19 | 140 | 0.3741 |
| 0.2851 | 1.22 | 144 | 0.3714 |
| 0.2365 | 1.26 | 148 | 0.3690 |
| 0.3986 | 1.29 | 152 | 0.3699 |
| 0.1913 | 1.33 | 156 | 0.3720 |
| 0.1963 | 1.36 | 160 | 0.3698 |
| 0.1824 | 1.4 | 164 | 0.3679 |
| 0.1453 | 1.43 | 168 | 0.3685 |
| 0.3073 | 1.47 | 172 | 0.3702 |
| 0.1501 | 1.5 | 176 | 0.3692 |
| 0.2167 | 1.53 | 180 | 0.3662 |
| 0.3007 | 1.57 | 184 | 0.3660 |
| 0.2203 | 1.6 | 188 | 0.3666 |
| 0.3978 | 1.64 | 192 | 0.3669 |
| 0.2397 | 1.67 | 196 | 0.3663 |
| 0.2161 | 1.71 | 200 | 0.3656 |
| 0.2593 | 1.74 | 204 | 0.3651 |
| 0.2113 | 1.78 | 208 | 0.3658 |
| 0.2435 | 1.81 | 212 | 0.3657 |
| 0.2625 | 1.85 | 216 | 0.3639 |
| 0.302 | 1.88 | 220 | 0.3624 |
| 0.2556 | 1.92 | 224 | 0.3611 |
| 0.2063 | 1.95 | 228 | 0.3609 |
| 0.1994 | 1.98 | 232 | 0.3612 |
| 0.2229 | 2.02 | 236 | 0.3613 |
| 0.1983 | 2.03 | 240 | 0.3634 |
| 0.1925 | 2.06 | 244 | 0.3725 |
| 0.1778 | 2.1 | 248 | 0.3832 |
| 0.1293 | 2.13 | 252 | 0.3834 |
| 0.2166 | 2.16 | 256 | 0.3789 |
| 0.2082 | 2.2 | 260 | 0.3760 |
| 0.1858 | 2.23 | 264 | 0.3761 |
| 0.1862 | 2.27 | 268 | 0.3763 |
| 0.1619 | 2.3 | 272 | 0.3783 |
| 0.174 | 2.34 | 276 | 0.3786 |
| 0.2414 | 2.37 | 280 | 0.3790 |
| 0.1977 | 2.41 | 284 | 0.3783 |
| 0.1678 | 2.44 | 288 | 0.3784 |
| 0.2263 | 2.48 | 292 | 0.3786 |
| 0.082 | 2.51 | 296 | 0.3783 |
| 0.2621 | 2.55 | 300 | 0.3784 |
| 0.1754 | 2.58 | 304 | 0.3795 |
| 0.1957 | 2.61 | 308 | 0.3802 |
| 0.1203 | 2.65 | 312 | 0.3803 |
| 0.1388 | 2.68 | 316 | 0.3796 |
| 0.1699 | 2.72 | 320 | 0.3796 |
| 0.161 | 2.75 | 324 | 0.3796 |
| 0.2394 | 2.79 | 328 | 0.3792 |
| 0.1465 | 2.82 | 332 | 0.3795 |
| 0.1746 | 2.86 | 336 | 0.3794 |
| 0.1839 | 2.89 | 340 | 0.3795 |
| 0.1581 | 2.93 | 344 | 0.3796 |
### Framework versions
- PEFT 0.8.2
- Transformers 4.39.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.17.1
- Tokenizers 0.15.0