Views
No views yet
bf16: true
cutoff_len: 2000
dataset: sydney
dataset_dir: data
ddp_timeout: 180000000
do_train: true
finetuning_type: lora
flash_attn: auto
gradient_accumulation_steps: 16
include_num_input_tokens_seen: true
learning_rate: 5.0e-05
logging_steps: 1
lora_alpha: 32
lora_dropout: 0
lora_rank: 32
lora_target: all
loraplus_lr_ratio: 4
lr_scheduler_type: cosine
max_grad_norm: 1.0
max_samples: 160000
model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
num_train_epochs: 1.0
optim: adamw_8bit
output_dir: saves/Qwen2-VL-7B-Instruct/lora/train_2024-10-05-18-44-10-2
packing: true
per_device_train_batch_size: 1
plot_loss: true
preprocessing_num_workers: 16
report_to: none
save_steps: 200
stage: sft
template: qwen2_vl
train_on_prompt: true
use_unsloth: true
warmup_steps: 25