40 lines
988 B
YAML
40 lines
988 B
YAML
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/openthoughts3
|
|
dataset_dir: ONLINE
|
|
ddp_timeout: '180000000'
|
|
deepspeed: /opt/ml/code/zero3.json
|
|
do_train: 'True'
|
|
enable_liger_kernel: 'True'
|
|
finetuning_type: full
|
|
formatting: sharegpt
|
|
global_batch_size: '256'
|
|
gradient_accumulation_steps: '1'
|
|
hub_model_id: mlfoundations-dev/openthoughts3_full_qwen25_1b
|
|
learning_rate: '0.00016'
|
|
logging_steps: '1'
|
|
lr_scheduler_type: cosine
|
|
messages: conversations
|
|
model_name_or_path: Qwen/Qwen2.5-1.5B-Instruct
|
|
num_train_epochs: '7.0'
|
|
output_dir: /opt/ml/model
|
|
overwrite_cache: 'True'
|
|
per_device_train_batch_size: '4'
|
|
plot_loss: 'True'
|
|
preprocessing_num_workers: '16'
|
|
push_to_db: 'True'
|
|
push_to_hub: 'True'
|
|
report_to: wandb
|
|
role_tag: from
|
|
run_name: openthoughts3_full_qwen25_1b
|
|
save_strategy: epoch
|
|
stage: sft
|
|
template: qwen25
|
|
user_tag: human
|
|
warmup_ratio: '0.1'
|