{ "base": "vllm-sr/d3-mini@df99bf4ca4418bc6908ee68e9b7479af1f3b8800", "seed": 1, "optimizer_steps": 1038, "selected_checkpoint": "final", "args": { "dtype": "bfloat16", "max_length": "8192", "max_tokens": "8192", "grad_accum": "16", "epochs": "2.0", "max_steps": "0", "lr": "0.0001", "readout_lr": "2e-05", "weight_decay": "0.0", "warmup": "0.05", "clip": "1.0", "lora_r": "16", "lora_alpha": "32", "lora_dropout": "0.05", "lora_targets": "['q_proj', 'k_proj', 'v_proj', 'o_proj', 'in_proj_qkv', 'in_proj_z', 'out_proj', 'gate_proj', 'up_proj', 'down_proj']", "rslora": "False", "freeze_readout": "False", "label_smoothing": "0.05", "shuffle_choices": "True", "no_grad_ckpt": "False", "eval_every": "400", "save_every": "400", "eval_batch": "8", "seed": "1", "log_every": "10", "vram_margin_gib": "3.0", "no_vram_check": "False", "abort_on_low_vram": "True" } }