alpha: 0.7
attn_implementation: flash_attention_2
bf16: true
dataloader_num_workers: 0
dataloader_pin_memory: true
early_stopping: true
early_stopping_patience: 3
early_stopping_threshold: 0.0
eval_data: /data/vibe_exp/dia-guard/dataset/dia_splits/val.jsonl
eval_steps: 200
eval_strategy: steps
gradient_accumulation_steps: 1
gradient_checkpointing: true
learning_rate: 5.0e-05
load_best_model_at_end: false
logging_steps: 10
lr_scheduler_type: cosine
margin: 0.3
max_grad_norm: 1.0
max_seq_length: 2048
metric_for_best_model: eval_loss
model_name: google/gemma-3-270m-it
num_epochs: 3
output_dir: /data/vibe_exp/dia-guard/models/group3_student_ft_baseline/full_ft/gemma_3_270m_it
per_device_eval_batch_size: 256
per_device_train_batch_size: 256
report_to: wandb
run_name: gemma-3-270m-ce-ft
save_steps: 500
save_strategy: steps
save_total_limit: 3
temperature: 0.05
tf32: true
train_data: /data/vibe_exp/dia-guard/dataset/dia_splits/train.jsonl
trust_remote_code: false
use_liger_kernel: true
warmup_steps: 4218
weight_decay: 0.01