recipes/smollm2/sft/config.yaml

# Model arguments
model_name_or_path: HuggingFaceTB/SmolLM2-1.7B
model_revision: main
tokenizer_name_or_path: HuggingFaceTB/SmolLM2-1.7B-Instruct # Custom tokenizer with <|im_start|> and <|im_end|> tokens
torch_dtype: bfloat16
use_flash_attention_2: true

# Data training arguments
dataset_mixer:
  HuggingFaceTB/smoltalk: 1.0

dataset_configs:
- all

dataset_splits:
- train
- test
preprocessing_num_workers: 36

# SFT trainer config
bf16: true
do_eval: true
evaluation_strategy: epoch
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
hub_model_id: smollm2-1.7B-sft
hub_strategy: every_save
learning_rate: 3.0e-04 
log_level: info
logging_steps: 5
logging_strategy: steps
lr_scheduler_type: cosine
max_seq_length: 8192
max_steps: -1
num_train_epochs: 2
output_dir: data/smollm2-1.7B-sft
overwrite_output_dir: true
per_device_eval_batch_size: 4
per_device_train_batch_size: 4
push_to_hub: true
remove_unused_columns: true
report_to:
- tensorboard
- wandb
save_strategy: "no"
seed: 42
warmup_ratio: 0.1