project_name: DUSUNEN-Atlas-278M-v1
base_model: intfloat/multilingual-e5-base
base_model_revision: d128750597153bb5987e10b1c3493a34e5a4502a
dataset_id: GoktugD/DUSUNEN-HardNegatives-50K-v1
seed: 3407
max_seq_length: 256
train_rows: 50000
validation_rows: 2000
epochs: 1
learning_rate: 1.0e-5
warmup_ratio: 0.05
per_device_batch_size: 8
gradient_accumulation_steps: 8
loss_mini_batch_size: 4
matryoshka_dims: [768, 512, 384, 256, 128, 64]
matryoshka_dims_per_step: 4
gradient_checkpointing: true
bf16: true
cuda_memory_fraction: 0.50
step_pause_seconds: 0.75
eval_steps: 250
save_steps: 250
logging_steps: 5