assistant_tag: gpt
bf16: true
content_tag: value
cutoff_len: 16384
dataloader_num_workers: 4
dataloader_persistent_workers: true
dataloader_pin_memory: true
dataset: mlfoundations-dev/no_pipeline_math_1k
dataset_dir: ONLINE
ddp_timeout: 180000000
deepspeed: dcft/train/zero3.json
do_train: true
enable_liger_kernel: true
finetuning_type: full
global_batch_size: 96
gradient_accumulation_steps: 6
hub_model_id: mlfoundations-dev/no_pipeline_math_1k
learning_rate: 2.0e-05
logging_steps: 1
lr_scheduler_type: cosine
messages: conversations
model_name_or_path: Qwen/Qwen2.5-7B-Instruct
num_train_epochs: 7.0
output_dir: /scratch/08002/gsmyrnis/checkpoints/no_pipeline_math_1k
overwrite_cache: true
per_device_train_batch_size: 1
plot_loss: true
preprocessing_num_workers: 16
push_to_db: true
push_to_hub: true
report_to: wandb
role_tag: from
save_strategy: epoch
stage: sft
template: qwen25
user_tag: human
warmup_ratio: 0.1