如何关闭验证集？

[GasolSun36]

Reminder

• I have read the README and searched the existing issues.

System Info

4块A800-80g

Reproduction

CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/train_full/qwen2vl_full_sft.yaml

Expected behavior

model

model_name_or_path: ../qwen/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/51c47430f97dd7c74aa1fa6825e68a813478097f

method

stage: sft
do_train: true
do_eval: false
do_predict: false
finetuning_type: full
deepspeed: examples/deepspeed/ds_z3_config.json

dataset

dataset: mllm_demo
template: qwen2_vl
cutoff_len: 1024
max_samples: 1000
overwrite_cache: true
preprocessing_num_workers: 16

output

output_dir: saves/qwen2_vl-7b/full/sft
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true

train

per_device_train_batch_size: 1
gradient_accumulation_steps: 2
learning_rate: 1.0e-5
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true
ddp_timeout: 180000000

eval

val_size: 0
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 1000000

设置了do_eval和do_predict=False不管用，把val-size调成0了也不管用。我期望训练过程不需要任何的验证。

Others

No response