| { | |
| "model": "meta-llama/Llama-4-Scout-17B-16E-Instruct", | |
| "exported_base_reference": "togethercomputer/Llama-4-Scout-17B-16E-Instruct_bnb_4bit", | |
| "winning_autoscientist_model_id": "adaption_llama_4_scout_17b_16_agri_evidence_qa_158a7fd8", | |
| "hyperparams": { | |
| "base_model_size": "109B", | |
| "n_epochs": 3, | |
| "batch_size": "max", | |
| "learning_rate": 0.0001, | |
| "lora": true, | |
| "lora_r": 64, | |
| "lora_alpha": 128, | |
| "lora_dropout": 0, | |
| "lora_trainable_modules": "q_proj,k_proj,v_proj,o_proj,shared_expert.gate_proj,shared_expert.up_proj,shared_expert.down_proj,feed_forward.gate_proj,feed_forward.up_proj,feed_forward.down_proj", | |
| "lr_scheduler_type": "cosine", | |
| "min_lr_ratio": 0.1, | |
| "scheduler_num_cycles": 0.5, | |
| "warmup_ratio": 0.1, | |
| "max_grad_norm": 1, | |
| "weight_decay": 0.01, | |
| "n_evals": 5, | |
| "training_method": "sft", | |
| "train_on_inputs": false | |
| } | |
| } | |