We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
4块A800-80g
CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/train_full/qwen2vl_full_sft.yaml
model_name_or_path: ../qwen/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/51c47430f97dd7c74aa1fa6825e68a813478097f
stage: sft do_train: true do_eval: false do_predict: false finetuning_type: full deepspeed: examples/deepspeed/ds_z3_config.json
dataset: mllm_demo template: qwen2_vl cutoff_len: 1024 max_samples: 1000 overwrite_cache: true preprocessing_num_workers: 16
output_dir: saves/qwen2_vl-7b/full/sft logging_steps: 10 save_steps: 500 plot_loss: true overwrite_output_dir: true
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
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。
No response
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Reminder
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
The text was updated successfully, but these errors were encountered: