| { | |
| "model_name": "llama_3_med_chat_lr_0.0001_warmup_20_epochs_5_fp", | |
| "torch_dtype": "torch.float16", | |
| "device_map": "auto", | |
| "trust_remote_code": false, | |
| "base_model_name": "NousResearch/Meta-Llama-3-8B-Instruct", | |
| "adapter_config": { | |
| "peft_type": "LORA", | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct", | |
| "revision": null, | |
| "task_type": "CAUSAL_LM", | |
| "inference_mode": false, | |
| "r": 16, | |
| "target_modules": [ | |
| "k_proj", | |
| "o_proj", | |
| "v_proj", | |
| "q_proj" | |
| ], | |
| "lora_alpha": 16, | |
| "lora_dropout": 0.1, | |
| "fan_in_fan_out": false, | |
| "bias": "none", | |
| "modules_to_save": null, | |
| "init_lora_weights": true, | |
| "layers_to_transform": null, | |
| "layers_pattern": null, | |
| "rank_pattern": {}, | |
| "alpha_pattern": {}, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "loftq_config": {} | |
| }, | |
| "config_class": "PeftConfig" | |
| } | |