| {"model": "ahxt/llama2_xs_460M_experimental", "data_path": "Felladrin/autotrain-data-llama2_xs_460M_experimental_instruct", "project_name": "/tmp/model", "train_split": "train", "valid_split": null, "text_column": "autotrain_text", "rejected_text_column": null, "lr": 0.0002, "epochs": 1, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": true, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.1, "logging_steps": -1, "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": 2048, "repo_id": "Felladrin/llama2_xs_460M_experimental_instruct-0", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": "Felladrin", "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false, "model_ref": null, "dpo_beta": 0.1, "prompt_text_column": null} |