VOOZH about

URL: https://huggingface.co/yandex/YandexGPT-5-Lite-8B-pretrain/discussions/1

⇱ yandex/YandexGPT-5-Lite-8B-pretrain · Дообучение модели через torchtune


Дообучение модели через torchtune

#1
by vorobyov01 - opened

Вот пример базового рецепта по дообучению с lora:

Скачиваем репозиторий:

mkdir torchtune
cd torchtune
tune download yandex/YandexGPT-5-Lite-8B-pretrain \
 --output-dir YandexGPT-5-Lite-8B-pretrain

Смотрим список конфигов и копируем подходящий под задачу:

tune ls
tune cp llama3_1/8B_lora training_config.yaml

Изменяем конфиг – адаптируем его под нашу модель и делаем подходящим под задачу. Например, такой вариант подойдет для lora-обучения на инстракт датасете alpaca-cleaned:

output_dir: <HOME_PATH>/torchtune/result_dir # /home/vorobyov01/torchtune/result_dir

# Tokenizer
tokenizer:
 _component_: torchtune.models.llama2.llama2_tokenizer
 path: <HOME_PATH>/torchtune/YandexGPT-5-Lite-8B-pretrain/tokenizer.model
 max_seq_len: null

# Model Arguments
model:
 _component_: torchtune.models.llama3.lora_llama3
 lora_attn_modules: ['q_proj', 'v_proj', 'output_proj']
 apply_lora_to_mlp: True
 apply_lora_to_output: False
 lora_rank: 8
 lora_alpha: 16
 lora_dropout: 0.0

 vocab_size: 129024
 num_layers: 32
 num_heads: 32
 num_kv_heads: 8
 embed_dim: 4096
 max_seq_len: 32768
 intermediate_dim: 14336
 attn_dropout: 0.0
 norm_eps: 0.000001

checkpointer:
 _component_: torchtune.training.FullModelHFCheckpointer
 checkpoint_dir: <HOME_PATH>/torchtune/YandexGPT-5-Lite-8B-pretrain
 checkpoint_files: [
 model-00001-of-00004.safetensors,
 model-00002-of-00004.safetensors,
 model-00003-of-00004.safetensors,
 model-00004-of-00004.safetensors
 ]
 recipe_checkpoint: null
 output_dir: ${output_dir}
 model_type: LLAMA3
resume_from_checkpoint: False
save_adapter_weights_only: False

# Dataset and Sampler
dataset:
 _component_: torchtune.datasets.alpaca_cleaned_dataset
 packed: False # True increases speed
seed: null
shuffle: True
batch_size: 2

# Optimizer and Scheduler
optimizer:
 _component_: torch.optim.AdamW
 fused: True
 weight_decay: 0.01
 lr: 3e-4
lr_scheduler:
 _component_: torchtune.training.lr_schedulers.get_cosine_schedule_with_warmup
 num_warmup_steps: 100

loss:
 _component_: torchtune.modules.loss.CEWithChunkedOutputLoss

# Training
epochs: 1
max_steps_per_epoch: null
gradient_accumulation_steps: 8 # Use to increase effective batch size
compile: False # torch.compile the model + loss, True increases speed + decreases memory

# Logging
metric_logger:
 _component_: torchtune.training.metric_logging.DiskLogger
 log_dir: ${output_dir}/logs
log_every_n_steps: 1
log_peak_memory_stats: True

# Environment
device: cuda
dtype: bf16
enable_activation_checkpointing: False # True reduces memory
enable_activation_offloading: False # True reduces memory


# Profiler (disabled)
profiler:
 _component_: torchtune.training.setup_torch_profiler
 enabled: False
 #Output directory of trace artifacts
 output_dir: ${output_dir}/profiling_outputs

 #`torch.profiler.ProfilerActivity` types to trace
 cpu: True
 cuda: True

 #trace options passed to `torch.profiler.profile`
 profile_memory: False
 with_stack: False
 record_shapes: True
 with_flops: False

 # `torch.profiler.schedule` options:
 # wait_steps -> wait, warmup_steps -> warmup, active_steps -> active, num_cycles -> repeat
 wait_steps: 5
 warmup_steps: 3
 active_steps: 2
 num_cycles: 1

Запускаем обучение:

tune run lora_finetune_single_device --config training_config.yaml

Можно на нескольких GPU:

CUDA_VISIBLE_DEVICES="0,1,2,3" tune run --nproc-per-node 4 lora_finetune_distributed --config training_config.yaml

Аналогично можно и через https://github.com/EvilFreelancer/impruver реализовать тюн, правда конфиг надо будет чуть подправить, займусь этим сегодня

Там число 12 затерялось в конфиге профайлера:

profiler:
component: torchtune.training.setup_torch_profiler
enabled: False
12
#Output directory of trace artifacts
output_dir: ${output_dir}/profiling_outputs

👁 image.png

· Sign up or log in to comment