初始化项目,由ModelHub XC社区提供模型
Model: ayh015/myLightningOPD Source: Original Platform
This commit is contained in:
41
configs/sft/qwen3-8b-base-open-thoughts3-qwen3-32b.yaml
Normal file
41
configs/sft/qwen3-8b-base-open-thoughts3-qwen3-32b.yaml
Normal file
@@ -0,0 +1,41 @@
|
||||
### model
|
||||
model_name_or_path: Qwen/Qwen3-8B-Base
|
||||
|
||||
### method
|
||||
stage: sft
|
||||
do_train: true
|
||||
finetuning_type: full
|
||||
deepspeed: examples/deepspeed/ds_z1_config.json
|
||||
enable_liger_kernel: true
|
||||
packing: true
|
||||
|
||||
|
||||
### dataset
|
||||
dataset: openthoughts3_300k_qwen3-32b
|
||||
template: qwen3
|
||||
cutoff_len: 16384
|
||||
overwrite_cache: true
|
||||
preprocessing_num_workers: 16
|
||||
dataloader_persistent_workers: true
|
||||
dataloader_pin_memory: true
|
||||
dataloader_num_workers: 4
|
||||
|
||||
### output
|
||||
logging_steps: 1
|
||||
save_steps: 100
|
||||
save_total_limit: 10
|
||||
plot_loss: true
|
||||
overwrite_output_dir: false
|
||||
save_only_model: false
|
||||
report_to: wandb
|
||||
run_name: qwen3-8b-base-open-thoughts3-qwen3-32b
|
||||
|
||||
### train
|
||||
per_device_train_batch_size: 2
|
||||
gradient_accumulation_steps: 2
|
||||
learning_rate: 8e-5
|
||||
max_steps: 3000
|
||||
lr_scheduler_type: cosine
|
||||
warmup_ratio: 0.1
|
||||
bf16: true
|
||||
ddp_timeout: 180000000
|
||||
Reference in New Issue
Block a user