|
|
|
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig |
|
from unsloth import FastLanguageModel |
|
import torch |
|
max_seq_length = 512 |
|
dtype = None |
|
load_in_4bit = True |
|
|
|
model_id = "llm-jp/llm-jp-3-13b" |
|
new_model_id = "llm-jp-3-13b-finetune-2" |
|
|
|
model, tokenizer = FastLanguageModel.from_pretrained( |
|
model_name=model_id, |
|
dtype=dtype, |
|
load_in_4bit=load_in_4bit, |
|
trust_remote_code=True, |
|
) |
|
|
|
|
|
model = FastLanguageModel.get_peft_model( |
|
model, |
|
r = 32, |
|
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj", |
|
"gate_proj", "up_proj", "down_proj",], |
|
lora_alpha = 32, |
|
lora_dropout = 0.05, |
|
bias = "none", |
|
use_gradient_checkpointing = "unsloth", |
|
random_state = 3407, |
|
use_rslora = False, |
|
loftq_config = None, |
|
max_seq_length = max_seq_length, |
|
) |
|
|
|
|
|
|
|
|
|
HF_TOKEN = "" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
"""==============""" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
from datasets import load_dataset |
|
|
|
dataset = load_dataset("json", data_files="Distribution20241221_all/Distribution20241221_all/ichikara-instruction-003-001-1.json") |
|
|
|
|
|
|
|
prompt = """### 指示 |
|
{} |
|
### 回答 |
|
{}""" |
|
|
|
|
|
|
|
""" |
|
formatting_prompts_func: 各データをプロンプトに合わせた形式に合わせる |
|
""" |
|
EOS_TOKEN = tokenizer.eos_token |
|
def formatting_prompts_func(examples): |
|
input = examples["text"] |
|
output = examples["output"] |
|
text = prompt.format(input, output) + EOS_TOKEN |
|
return { "formatted_text" : text, } |
|
pass |
|
|
|
|
|
dataset = dataset.map( |
|
formatting_prompts_func, |
|
num_proc= 4, |
|
) |
|
|
|
print(dataset) |
|
|
|
|
|
print(dataset["train"]["formatted_text"][3]) |
|
|
|
|
|
|
|
|
|
""" |
|
training_arguments: 学習の設定 |
|
|
|
- output_dir: |
|
-トレーニング後のモデルを保存するディレクトリ |
|
|
|
- per_device_train_batch_size: |
|
- デバイスごとのトレーニングバッチサイズ |
|
|
|
- per_device_eval_batch_size: |
|
- デバイスごとの評価バッチサイズ |
|
|
|
- gradient_accumulation_steps: |
|
- 勾配を更新する前にステップを積み重ねる回数 |
|
|
|
- optim: |
|
- オプティマイザの設定 |
|
|
|
- num_train_epochs: |
|
- エポック数 |
|
|
|
- eval_strategy: |
|
- 評価の戦略 ("no"/"steps"/"epoch") |
|
|
|
- eval_steps: |
|
- eval_strategyが"steps"のとき、評価を行うstep間隔 |
|
|
|
- logging_strategy: |
|
- ログ記録の戦略 |
|
|
|
- logging_steps: |
|
- ログを出力するステップ間隔 |
|
|
|
- warmup_steps: |
|
- 学習率のウォームアップステップ数 |
|
|
|
- save_steps: |
|
- モデルを保存するステップ間隔 |
|
|
|
- save_total_limit: |
|
- 保存しておくcheckpointの数 |
|
|
|
- max_steps: |
|
- トレーニングの最大ステップ数 |
|
|
|
- learning_rate: |
|
- 学習率 |
|
|
|
- fp16: |
|
- 16bit浮動小数点の使用設定(第8回演習を参考にすると良いです) |
|
|
|
- bf16: |
|
- BFloat16の使用設定 |
|
|
|
- group_by_length: |
|
- 入力シーケンスの長さによりバッチをグループ化 (トレーニングの効率化) |
|
|
|
- report_to: |
|
- ログの送信先 ("wandb"/"tensorboard"など) |
|
""" |
|
from trl import SFTTrainer |
|
from transformers import TrainingArguments |
|
from unsloth import is_bfloat16_supported |
|
|
|
trainer = SFTTrainer( |
|
model = model, |
|
tokenizer = tokenizer, |
|
train_dataset=dataset["train"], |
|
max_seq_length = max_seq_length, |
|
dataset_text_field="formatted_text", |
|
packing = False, |
|
args = TrainingArguments( |
|
per_device_train_batch_size = 2, |
|
gradient_accumulation_steps = 4, |
|
num_train_epochs = 1, |
|
logging_steps = 10, |
|
warmup_steps = 10, |
|
save_steps=100, |
|
save_total_limit=2, |
|
max_steps=-1, |
|
learning_rate = 2e-4, |
|
fp16 = not is_bfloat16_supported(), |
|
bf16 = is_bfloat16_supported(), |
|
group_by_length=True, |
|
seed = 3407, |
|
output_dir = "outputs", |
|
report_to = "none", |
|
), |
|
) |
|
|
|
|
|
|
|
|
|
gpu_stats = torch.cuda.get_device_properties(0) |
|
start_gpu_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3) |
|
max_memory = round(gpu_stats.total_memory / 1024 / 1024 / 1024, 3) |
|
print(f"GPU = {gpu_stats.name}. Max memory = {max_memory} GB.") |
|
print(f"{start_gpu_memory} GB of memory reserved.") |
|
|
|
|
|
|
|
trainer_stats = trainer.train() |
|
|
|
|
|
|
|
|
|
import json |
|
datasets = [] |
|
with open("./elyza-tasks-100-TV_0.jsonl", "r") as f: |
|
item = "" |
|
for line in f: |
|
line = line.strip() |
|
item += line |
|
if item.endswith("}"): |
|
datasets.append(json.loads(item)) |
|
item = "" |
|
|
|
|
|
|
|
from tqdm import tqdm |
|
|
|
|
|
FastLanguageModel.for_inference(model) |
|
|
|
results = [] |
|
for dt in tqdm(datasets): |
|
input = dt["input"] |
|
|
|
prompt = f"""### 指示\n{input}\n### 回答\n""" |
|
|
|
|
|
inputs = tokenizer([prompt], return_tensors = "pt").to(model.device) |
|
|
|
outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2) |
|
prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1] |
|
|
|
results.append({"task_id": dt["task_id"], "input": input, "output": prediction}) |
|
|
|
|
|
with open(f"{new_model_id}_output.jsonl", 'w', encoding='utf-8') as f: |
|
for result in results: |
|
json.dump(result, f, ensure_ascii=False) |
|
f.write('\n') |
|
|
|
|
|
|
|
|
|
|
|
HF_WRITE_TOKEN = "" |
|
model.push_to_hub_merged( |
|
new_model_id, |
|
tokenizer=tokenizer, |
|
save_method="lora", |
|
token=HF_WRITE_TOKEN, |
|
private=True |
|
) |
|
|
|
|
|
|
|
|
|
|