| {"model": "HuggingFaceH4/zephyr-7b-alpha", "data_path": "data/", "project_name": "zephyr-math", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 2e-05, "epochs": 3, "batch_size": 4, "warmup_ratio": 0.03, "gradient_accumulation": 4, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": 10, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "rishiraj/zephyr-math", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": true, "username": null, "use_flash_attention_2": false, "log": "wandb", "disable_gradient_checkpointing": false} |