|
|
--- |
|
|
license: llama2 |
|
|
library_name: peft |
|
|
tags: |
|
|
- axolotl |
|
|
- generated_from_trainer |
|
|
base_model: codellama/CodeLlama-7b-hf |
|
|
model-index: |
|
|
- name: firsttestmodel |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
|
<details><summary>See axolotl config</summary> |
|
|
|
|
|
axolotl version: `0.3.0` |
|
|
```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: Delosint/firsttestmodel |
|
|
|
|
|
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: "<s>" |
|
|
eos_token: "</s>" |
|
|
unk_token: "<unk>" |
|
|
|
|
|
``` |
|
|
|
|
|
</details><br> |
|
|
|
|
|
# firsttestmodel |
|
|
|
|
|
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: 0.3784 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.3474 | 0.01 | 1 | 0.4985 | |
|
|
| 0.3136 | 0.03 | 4 | 0.4987 | |
|
|
| 0.2984 | 0.07 | 8 | 0.4984 | |
|
|
| 0.4396 | 0.1 | 12 | 0.4979 | |
|
|
| 0.3686 | 0.14 | 16 | 0.4963 | |
|
|
| 0.3355 | 0.17 | 20 | 0.4918 | |
|
|
| 0.429 | 0.21 | 24 | 0.4814 | |
|
|
| 0.4015 | 0.24 | 28 | 0.4635 | |
|
|
| 0.3275 | 0.28 | 32 | 0.4446 | |
|
|
| 0.2563 | 0.31 | 36 | 0.4285 | |
|
|
| 0.3785 | 0.35 | 40 | 0.4177 | |
|
|
| 0.2965 | 0.38 | 44 | 0.4109 | |
|
|
| 0.2679 | 0.42 | 48 | 0.4027 | |
|
|
| 0.2457 | 0.45 | 52 | 0.3961 | |
|
|
| 0.3267 | 0.48 | 56 | 0.3915 | |
|
|
| 0.2899 | 0.52 | 60 | 0.3879 | |
|
|
| 0.1844 | 0.55 | 64 | 0.3881 | |
|
|
| 0.2586 | 0.59 | 68 | 0.3869 | |
|
|
| 0.3105 | 0.62 | 72 | 0.3837 | |
|
|
| 0.3795 | 0.66 | 76 | 0.3819 | |
|
|
| 0.2062 | 0.69 | 80 | 0.3792 | |
|
|
| 0.3173 | 0.73 | 84 | 0.3792 | |
|
|
| 0.2307 | 0.76 | 88 | 0.3766 | |
|
|
| 0.2821 | 0.8 | 92 | 0.3747 | |
|
|
| 0.2716 | 0.83 | 96 | 0.3736 | |
|
|
| 0.2945 | 0.87 | 100 | 0.3724 | |
|
|
| 0.2312 | 0.9 | 104 | 0.3712 | |
|
|
| 0.2475 | 0.94 | 108 | 0.3715 | |
|
|
| 0.2301 | 0.97 | 112 | 0.3716 | |
|
|
| 0.2029 | 1.0 | 116 | 0.3713 | |
|
|
| 0.264 | 1.02 | 120 | 0.3707 | |
|
|
| 0.2477 | 1.05 | 124 | 0.3726 | |
|
|
| 0.1987 | 1.09 | 128 | 0.3683 | |
|
|
| 0.2305 | 1.12 | 132 | 0.3675 | |
|
|
| 0.1542 | 1.16 | 136 | 0.3683 | |
|
|
| 0.1954 | 1.19 | 140 | 0.3696 | |
|
|
| 0.2245 | 1.23 | 144 | 0.3676 | |
|
|
| 0.1973 | 1.26 | 148 | 0.3690 | |
|
|
| 0.1482 | 1.29 | 152 | 0.3704 | |
|
|
| 0.2861 | 1.33 | 156 | 0.3704 | |
|
|
| 0.2825 | 1.36 | 160 | 0.3699 | |
|
|
| 0.2489 | 1.4 | 164 | 0.3683 | |
|
|
| 0.2053 | 1.43 | 168 | 0.3687 | |
|
|
| 0.1664 | 1.47 | 172 | 0.3697 | |
|
|
| 0.2351 | 1.5 | 176 | 0.3692 | |
|
|
| 0.2673 | 1.54 | 180 | 0.3674 | |
|
|
| 0.2567 | 1.57 | 184 | 0.3662 | |
|
|
| 0.1764 | 1.61 | 188 | 0.3669 | |
|
|
| 0.2437 | 1.64 | 192 | 0.3661 | |
|
|
| 0.2143 | 1.68 | 196 | 0.3669 | |
|
|
| 0.2085 | 1.71 | 200 | 0.3646 | |
|
|
| 0.2415 | 1.74 | 204 | 0.3634 | |
|
|
| 0.1899 | 1.78 | 208 | 0.3633 | |
|
|
| 0.2752 | 1.81 | 212 | 0.3629 | |
|
|
| 0.2529 | 1.85 | 216 | 0.3604 | |
|
|
| 0.2462 | 1.88 | 220 | 0.3603 | |
|
|
| 0.2511 | 1.92 | 224 | 0.3604 | |
|
|
| 0.2749 | 1.95 | 228 | 0.3598 | |
|
|
| 0.2161 | 1.99 | 232 | 0.3593 | |
|
|
| 0.3901 | 2.02 | 236 | 0.3591 | |
|
|
| 0.2167 | 2.03 | 240 | 0.3621 | |
|
|
| 0.1812 | 2.07 | 244 | 0.3709 | |
|
|
| 0.297 | 2.1 | 248 | 0.3782 | |
|
|
| 0.2031 | 2.14 | 252 | 0.3752 | |
|
|
| 0.139 | 2.17 | 256 | 0.3707 | |
|
|
| 0.2033 | 2.21 | 260 | 0.3704 | |
|
|
| 0.2495 | 2.24 | 264 | 0.3720 | |
|
|
| 0.1739 | 2.28 | 268 | 0.3746 | |
|
|
| 0.1681 | 2.31 | 272 | 0.3761 | |
|
|
| 0.1923 | 2.35 | 276 | 0.3763 | |
|
|
| 0.2174 | 2.38 | 280 | 0.3780 | |
|
|
| 0.1989 | 2.42 | 284 | 0.3786 | |
|
|
| 0.1443 | 2.45 | 288 | 0.3777 | |
|
|
| 0.1682 | 2.48 | 292 | 0.3773 | |
|
|
| 0.1814 | 2.52 | 296 | 0.3771 | |
|
|
| 0.1655 | 2.55 | 300 | 0.3774 | |
|
|
| 0.1533 | 2.59 | 304 | 0.3772 | |
|
|
| 0.2995 | 2.62 | 308 | 0.3770 | |
|
|
| 0.1535 | 2.66 | 312 | 0.3777 | |
|
|
| 0.1876 | 2.69 | 316 | 0.3782 | |
|
|
| 0.1866 | 2.73 | 320 | 0.3781 | |
|
|
| 0.1719 | 2.76 | 324 | 0.3783 | |
|
|
| 0.2005 | 2.8 | 328 | 0.3785 | |
|
|
| 0.2659 | 2.83 | 332 | 0.3785 | |
|
|
| 0.2045 | 2.87 | 336 | 0.3784 | |
|
|
| 0.2695 | 2.9 | 340 | 0.3783 | |
|
|
| 0.1407 | 2.94 | 344 | 0.3784 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.7.2.dev0 |
|
|
- Transformers 4.37.0.dev0 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 2.16.1 |
|
|
- Tokenizers 0.15.0 |
