|
--- |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: meta-llama/Llama-2-7b-hf |
|
model-index: |
|
- name: models/auto-improving-run |
|
results: [] |
|
--- |
|
|
|
[<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: `0.4.0` |
|
```yaml |
|
# This file is used by the training script in train.ipynb. You can read more about |
|
# the format and see more examples at https://github.com/OpenAccess-AI-Collective/axolotl. |
|
# One of the parameters you might want to play around with is `num_epochs`: if you have a |
|
# smaller dataset size, making that large can have good results. |
|
|
|
base_model: meta-llama/Llama-2-7b-hf |
|
base_model_config: meta-llama/Llama-2-7b-hf |
|
model_type: LlamaForCausalLM |
|
tokenizer_type: LlamaTokenizer |
|
is_llama_derived_model: true |
|
|
|
load_in_8bit: true |
|
load_in_4bit: false |
|
strict: false |
|
|
|
datasets: |
|
- path: ./resources/train_aug.jsonl |
|
type: alpaca |
|
dataset_prepared_path: ./resources/last_run_prepared |
|
val_set_size: 0.05 |
|
output_dir: ./models/auto-improving-run |
|
|
|
sequence_len: 4096 |
|
sample_packing: true |
|
|
|
adapter: lora |
|
lora_model_dir: |
|
lora_r: 32 |
|
lora_alpha: 16 |
|
lora_dropout: 0.05 |
|
lora_target_linear: true |
|
lora_fan_in_fan_out: |
|
|
|
# This will report stats from your training run to https://wandb.ai/. If you don't want to create a wandb account you can comment this section out. |
|
wandb_project: google-boolq |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_run_id: auto-improving-run |
|
wandb_log_model: |
|
|
|
|
|
gradient_accumulation_steps: 4 |
|
micro_batch_size: 2 |
|
num_epochs: 5 |
|
optimizer: adamw_bnb_8bit |
|
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: false |
|
|
|
warmup_steps: 10 |
|
eval_steps: 20 |
|
save_steps: 60 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
bos_token: "<s>" |
|
eos_token: "</s>" |
|
unk_token: "<unk>" |
|
``` |
|
|
|
</details><br> |
|
|
|
# models/auto-improving-run |
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the google/boolq dataset with a research platform that iterates on the model inaccuracies, gets refined by expert, and re-performs training. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3435 |
|
|
|
## 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: 10 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 7.9638 | 0.01 | 1 | 8.3163 | |
|
| 0.3508 | 0.28 | 20 | 0.3923 | |
|
| 0.3166 | 0.55 | 40 | 0.3505 | |
|
| 0.3363 | 0.83 | 60 | 0.3775 | |
|
| 0.3295 | 1.09 | 80 | 0.3478 | |
|
| 0.3232 | 1.36 | 100 | 0.3514 | |
|
| 0.3569 | 1.64 | 120 | 0.3504 | |
|
| 0.3379 | 1.92 | 140 | 0.3475 | |
|
| 0.3234 | 2.17 | 160 | 0.3623 | |
|
| 0.3442 | 2.45 | 180 | 0.3580 | |
|
| 0.3103 | 2.73 | 200 | 0.3426 | |
|
| 0.3253 | 3.0 | 220 | 0.3415 | |
|
| 0.3291 | 3.26 | 240 | 0.3457 | |
|
| 0.3248 | 3.54 | 260 | 0.3427 | |
|
| 0.3463 | 3.81 | 280 | 0.3486 | |
|
| 0.3273 | 4.07 | 300 | 0.3431 | |
|
| 0.3071 | 4.35 | 320 | 0.3416 | |
|
| 0.3227 | 4.62 | 340 | 0.3433 | |
|
| 0.3333 | 4.9 | 360 | 0.3435 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.40.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.0 |
|
|
|
### Evaluation |
|
|
|
These are the metrics reported on the test data (10% of boolq) |
|
|
|
model='auto-improving-llama' accuracy=0.8629969418960245 avg_time=0.044935779816513415 avg_cost=1.6101987767584347e-05 |
