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/a1_code_codeforces_python_submissions
dataset_dir: ONLINE
ddp_timeout: 180000000
deepspeed: dcft/train/zero3.json
do_train: true
enable_liger_kernel: false
eval_strategy: 'no'
finetuning_type: full
formatting: sharegpt
global_batch_size: 128
gradient_accumulation_steps: 4
hub_model_id: mlfoundations-dev/medium_a1_code_codeforces_python_submissions
include_hp: dcft/train/hp_settings/paper/reasoning_medium.yaml
learning_rate: 4.0e-05
logging_steps: 1
lr_scheduler_type: cosine
messages: conversations
model_name_or_path: Qwen/Qwen2.5-7B-Instruct
num_train_epochs: 5.0
output_dir: /tmp/dcft_checkpoints/train/checkpoints/medium_a1_code_codeforces_python_submissions
overwrite_cache: true
per_device_train_batch_size: 1
plot_loss: true
preprocessing_num_workers: 4
push_to_db: true
push_to_hub: true
report_to: wandb
role_tag: from
run_name: medium_a1_code_codeforces_python_submissions
save_strategy: epoch
stage: sft
template: qwen25
user_tag: human
warmup_ratio: 0.1