{ "run_id": "split0_init101", "kind": "trained", "group": "split0", "title": "split0: init seed 101, split seed 0, weight decay 1.0, task add", "fn_name": "add", "label_seed": null, "split_seed": 0, "init_seed": 101, "frac_train": 0.3, "lr": 0.001, "weight_decay": 1.0, "betas": [ 0.9, 0.98 ], "warmup_steps": 10, "num_steps": 40000, "ckpt_steps": [ 0, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1100, 1200, 1300, 1400, 1500, 1600, 1700, 1800, 1900, 2000, 2100, 2200, 2300, 2400, 2500, 2600, 2700, 2800, 2900, 3000, 3100, 3200, 3300, 3400, 3500, 3600, 3700, 3800, 3900, 4000, 4100, 4200, 4300, 4400, 4500, 4600, 4700, 4800, 4900, 5000, 5100, 5200, 5300, 5400, 5500, 5600, 5700, 5800, 5900, 6000, 6100, 6200, 6300, 6400, 6500, 6600, 6700, 6800, 6900, 7000, 7100, 7200, 7300, 7400, 7500, 7600, 7700, 7800, 7900, 8000, 8100, 8200, 8300, 8400, 8500, 8600, 8700, 8800, 8900, 9000, 9100, 9200, 9300, 9400, 9500, 9600, 9700, 9800, 9900, 10000, 10100, 10200, 10300, 10400, 10500, 10600, 10700, 10800, 10900, 11000, 11100, 11200, 11300, 11400, 11500, 11600, 11700, 11800, 11900, 12000, 12100, 12200, 12300, 12400, 12500, 12600, 12700, 12800, 12900, 13000, 13100, 13200, 13300, 13400, 13500, 13600, 13700, 13800, 13900, 14000, 14100, 14200, 14300, 14400, 14500, 14600, 14700, 14800, 14900, 15000, 15100, 15200, 15300, 15400, 15500, 15600, 15700, 15800, 15900, 16000, 16100, 16200, 16300, 16400, 16500, 16600, 16700, 16800, 16900, 17000, 17100, 17200, 17300, 17400, 17500, 17600, 17700, 17800, 17900, 18000, 18100, 18200, 18300, 18400, 18500, 18600, 18700, 18800, 18900, 19000, 19100, 19200, 19300, 19400, 19500, 19600, 19700, 19800, 19900, 20000, 20100, 20200, 20300, 20400, 20500, 20600, 20700, 20800, 20900, 21000, 21100, 21200, 21300, 21400, 21500, 21600, 21700, 21800, 21900, 22000, 22100, 22200, 22300, 22400, 22500, 22600, 22700, 22800, 22900, 23000, 23100, 23200, 23300, 23400, 23500, 23600, 23700, 23800, 23900, 24000, 24100, 24200, 24300, 24400, 24500, 24600, 24700, 24800, 24900, 25000, 25100, 25200, 25300, 25400, 25500, 25600, 25700, 25800, 25900, 26000, 26100, 26200, 26300, 26400, 26500, 26600, 26700, 26800, 26900, 27000, 27100, 27200, 27300, 27400, 27500, 27600, 27700, 27800, 27900, 28000, 28100, 28200, 28300, 28400, 28500, 28600, 28700, 28800, 28900, 29000, 29100, 29200, 29300, 29400, 29500, 29600, 29700, 29800, 29900, 30000, 30100, 30200, 30300, 30400, 30500, 30600, 30700, 30800, 30900, 31000, 31100, 31200, 31300, 31400, 31500, 31600, 31700, 31800, 31900, 32000, 32100, 32200, 32300, 32400, 32500, 32600, 32700, 32800, 32900, 33000, 33100, 33200, 33300, 33400, 33500, 33600, 33700, 33800, 33900, 34000, 34100, 34200, 34300, 34400, 34500, 34600, 34700, 34800, 34900, 35000, 35100, 35200, 35300, 35400, 35500, 35600, 35700, 35800, 35900, 36000, 36100, 36200, 36300, 36400, 36500, 36600, 36700, 36800, 36900, 37000, 37100, 37200, 37300, 37400, 37500, 37600, 37700, 37800, 37900, 38000, 38100, 38200, 38300, 38400, 38500, 38600, 38700, 38800, 38900, 39000, 39100, 39200, 39300, 39400, 39500, 39600, 39700, 39800, 39900, 40000 ], "optim_steps": [ 1000, 2000, 3000, 4000, 5000, 6000, 7000, 8000, 9000, 10000, 11000, 12000, 13000, 14000, 15000, 16000, 17000, 18000, 19000, 20000, 21000, 22000, 23000, 24000, 25000, 26000, 27000, 28000, 29000, 30000, 31000, 32000, 33000, 34000, 35000, 36000, 37000, 38000, 39000, 40000 ], "param_names": [ "embed.W_E", "pos_embed.W_pos", "blocks.0.attn.W_K", "blocks.0.attn.W_Q", "blocks.0.attn.W_V", "blocks.0.attn.W_O", "blocks.0.mlp.W_in", "blocks.0.mlp.b_in", "blocks.0.mlp.W_out", "blocks.0.mlp.b_out", "unembed.W_U" ], "model_shape": { "d_vocab": 114, "d_model": 128, "n_ctx": 3, "d_mlp": 512, "n_heads": 4, "d_head": 32, "n_layers": 1 }, "deterministic": true, "trained_with": [ "wd1_s0", "wd1_s1", "wd1_s2", "wd1_s3", "wd1_s4", "wd1_s5", "wd1_s6", "wd1_s7", "wd1_s8", "wd1_s9", "wd1_s10", "wd0_s0", "wd0_s1", "wd0_s2", "wd0_s3", "wd0_s4", "rand_s0", "rand_s1", "rand_s2", "split0_init100", "split0_init101", "split0_init102" ], "train_seconds_all_runs": 4247.704825599998, "environment": { "python": "3.12.13", "platform": "Windows-11-10.0.26200-SP0", "torch": "2.14.1+cu130", "cuda_build": "13.0", "device": "cuda", "cublas_workspace_config": ":4096:8", "repo_commit": "1f23b658e5c73c82cfa4a404504ead271e19645d", "submodule_commit": "38776db1804a27369b504f43db0611521bf9e860", "gpu_name": "NVIDIA GeForce RTX 5070 Laptop GPU", "gpu_capability": [ 12, 0 ] } }