Cormac Shannon
84b04d12e9
Pipeline works on MPS (~105 s per 300-step run), results are reproducible, and the divergence stop works. Not experimental evidence. Claude-Session: https://claude.ai/code/session_01S8KN7NuUCm8nXLmy6eDuVv
36 lines
2.5 KiB
JSON
36 lines
2.5 KiB
JSON
{"type": "eval", "iter": 0, "train_loss": 10.9141, "val_loss": 10.9167, "t": 5.28}
|
|
{"type": "train", "iter": 0, "loss": 10.9193, "ms": 4306.09, "t": 5.61}
|
|
{"type": "train", "iter": 10, "loss": 9.717, "ms": 277.79, "t": 8.4}
|
|
{"type": "train", "iter": 20, "loss": 7.856, "ms": 278.89, "t": 11.19}
|
|
{"type": "train", "iter": 30, "loss": 5.8282, "ms": 280.65, "t": 13.98}
|
|
{"type": "train", "iter": 40, "loss": 5.188, "ms": 280.42, "t": 16.81}
|
|
{"type": "train", "iter": 50, "loss": 4.7399, "ms": 279.76, "t": 19.6}
|
|
{"type": "train", "iter": 60, "loss": 4.4652, "ms": 279.16, "t": 22.4}
|
|
{"type": "train", "iter": 70, "loss": 4.3047, "ms": 279.57, "t": 25.2}
|
|
{"type": "train", "iter": 80, "loss": 4.1141, "ms": 280.67, "t": 28.0}
|
|
{"type": "train", "iter": 90, "loss": 4.0799, "ms": 279.89, "t": 30.8}
|
|
{"type": "eval", "iter": 100, "train_loss": 4.0112, "val_loss": 4.0447, "t": 37.28}
|
|
{"type": "train", "iter": 100, "loss": 3.9923, "ms": 4480.26, "t": 37.81}
|
|
{"type": "train", "iter": 110, "loss": 3.9961, "ms": 280.65, "t": 40.61}
|
|
{"type": "train", "iter": 120, "loss": 3.802, "ms": 280.13, "t": 43.4}
|
|
{"type": "train", "iter": 130, "loss": 3.8455, "ms": 279.15, "t": 46.2}
|
|
{"type": "train", "iter": 140, "loss": 3.8329, "ms": 278.97, "t": 48.99}
|
|
{"type": "train", "iter": 150, "loss": 3.8187, "ms": 279.6, "t": 51.79}
|
|
{"type": "train", "iter": 160, "loss": 3.683, "ms": 280.52, "t": 54.59}
|
|
{"type": "train", "iter": 170, "loss": 3.7639, "ms": 280.91, "t": 57.39}
|
|
{"type": "train", "iter": 180, "loss": 3.6422, "ms": 280.01, "t": 60.19}
|
|
{"type": "train", "iter": 190, "loss": 3.4959, "ms": 294.68, "t": 63.04}
|
|
{"type": "eval", "iter": 200, "train_loss": 3.5542, "val_loss": 3.5984, "t": 69.66}
|
|
{"type": "train", "iter": 200, "loss": 3.4831, "ms": 4487.24, "t": 70.09}
|
|
{"type": "train", "iter": 210, "loss": 3.5612, "ms": 280.52, "t": 72.91}
|
|
{"type": "train", "iter": 220, "loss": 3.5742, "ms": 291.78, "t": 75.76}
|
|
{"type": "train", "iter": 230, "loss": 3.458, "ms": 282.25, "t": 78.58}
|
|
{"type": "train", "iter": 240, "loss": 3.5315, "ms": 281.29, "t": 81.4}
|
|
{"type": "train", "iter": 250, "loss": 3.4362, "ms": 281.5, "t": 84.21}
|
|
{"type": "train", "iter": 260, "loss": 3.4534, "ms": 281.67, "t": 87.03}
|
|
{"type": "train", "iter": 270, "loss": 3.4163, "ms": 281.69, "t": 89.85}
|
|
{"type": "train", "iter": 280, "loss": 3.3884, "ms": 282.78, "t": 92.67}
|
|
{"type": "train", "iter": 290, "loss": 3.3656, "ms": 292.04, "t": 95.52}
|
|
{"type": "eval", "iter": 300, "train_loss": 3.3974, "val_loss": 3.459, "t": 102.13}
|
|
{"type": "train", "iter": 300, "loss": 3.3888, "ms": 4461.83, "t": 102.56}
|