dataset_prepared_path: train_on_inputs: false # Only train on assistant responses
# ==================== # QLORA CONFIGURATION # ==================== adapter: qlora load_in_4bit: true lora_r: 128 lora_alpha: 128 lora_dropout: 0.1 lora_target_linear: true # lora_modules_to_save: # Uncomment only if you added NEW tokens
# ==================== # TRAINING PARAMETERS # ==================== num_epochs: 2 micro_batch_size: 4 gradient_accumulation_steps: 2 learning_rate: 1.5e-5 optimizer: paged_adamw_8bit lr_scheduler: rex warmup_ratio: 0.05 weight_decay: 0.01 max_grad_norm: 1.0
# ==================== # SEQUENCE & PACKING # ==================== sequence_len: 8192 sample_packing: true eval_sample_packing: false pad_to_sequence_len: true
# ==================== # HARDWARE OPTIMIZATIONS # ==================== bf16: auto flash_attention: true gradient_checkpointing: true
# ==================== # EVALUATION & CHECKPOINTING # ==================== save_strategy: steps save_steps: 5 save_total_limit: 5 # Keep best + last few checkpoints load_best_model_at_end: true greater_is_better: false
# ==================== # LOGGING & OUTPUT # ==================== output_dir: ./Upscale_Mistral-PT-SFT-2 logging_steps: 2 save_safetensors: true
# ==================== # WANDB TRACKING # ==================== wandb_project: MS3-2-SFT wandb_entity: your_entity wandb_name: run_name