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": 10.9101, "val_loss": 10.9119, "t": 5.35}
|
|
{"type": "train", "iter": 0, "loss": 10.9141, "ms": 4381.39, "t": 5.68}
|
|
{"type": "train", "iter": 10, "loss": 7.244, "ms": 282.91, "t": 8.5}
|
|
{"type": "train", "iter": 20, "loss": 6.685, "ms": 282.55, "t": 11.33}
|
|
{"type": "train", "iter": 30, "loss": 5.8816, "ms": 282.81, "t": 14.15}
|
|
{"type": "train", "iter": 40, "loss": 6.0125, "ms": 282.89, "t": 16.98}
|
|
{"type": "train", "iter": 50, "loss": 5.9419, "ms": 281.66, "t": 19.81}
|
|
{"type": "train", "iter": 60, "loss": 5.8631, "ms": 283.47, "t": 22.71}
|
|
{"type": "train", "iter": 70, "loss": 5.6184, "ms": 287.64, "t": 25.59}
|
|
{"type": "train", "iter": 80, "loss": 5.3906, "ms": 294.14, "t": 28.56}
|
|
{"type": "train", "iter": 90, "loss": 5.2812, "ms": 284.17, "t": 31.53}
|
|
{"type": "eval", "iter": 100, "train_loss": 5.1683, "val_loss": 5.2052, "t": 38.32}
|
|
{"type": "train", "iter": 100, "loss": 5.1892, "ms": 4687.97, "t": 38.88}
|
|
{"type": "train", "iter": 110, "loss": 5.1302, "ms": 284.39, "t": 41.78}
|
|
{"type": "train", "iter": 120, "loss": 4.8073, "ms": 284.14, "t": 44.63}
|
|
{"type": "train", "iter": 130, "loss": 4.7233, "ms": 284.49, "t": 47.47}
|
|
{"type": "train", "iter": 140, "loss": 4.604, "ms": 284.17, "t": 50.32}
|
|
{"type": "train", "iter": 150, "loss": 4.5495, "ms": 284.19, "t": 53.21}
|
|
{"type": "train", "iter": 160, "loss": 4.376, "ms": 286.09, "t": 56.2}
|
|
{"type": "train", "iter": 170, "loss": 4.469, "ms": 309.41, "t": 59.19}
|
|
{"type": "train", "iter": 180, "loss": 4.3172, "ms": 284.88, "t": 62.19}
|
|
{"type": "train", "iter": 190, "loss": 4.1296, "ms": 294.5, "t": 65.17}
|
|
{"type": "eval", "iter": 200, "train_loss": 4.2006, "val_loss": 4.2389, "t": 71.94}
|
|
{"type": "train", "iter": 200, "loss": 4.1261, "ms": 4612.6, "t": 72.39}
|
|
{"type": "train", "iter": 210, "loss": 4.2153, "ms": 292.29, "t": 75.27}
|
|
{"type": "train", "iter": 220, "loss": 4.1696, "ms": 283.53, "t": 78.13}
|
|
{"type": "train", "iter": 230, "loss": 4.0597, "ms": 290.17, "t": 81.02}
|
|
{"type": "train", "iter": 240, "loss": 4.0813, "ms": 286.98, "t": 83.9}
|
|
{"type": "train", "iter": 250, "loss": 3.9827, "ms": 284.4, "t": 86.76}
|
|
{"type": "train", "iter": 260, "loss": 3.9723, "ms": 284.78, "t": 89.61}
|
|
{"type": "train", "iter": 270, "loss": 3.928, "ms": 287.37, "t": 92.47}
|
|
{"type": "train", "iter": 280, "loss": 3.8621, "ms": 284.67, "t": 95.32}
|
|
{"type": "train", "iter": 290, "loss": 3.8471, "ms": 283.42, "t": 98.17}
|
|
{"type": "eval", "iter": 300, "train_loss": 3.8471, "val_loss": 3.9026, "t": 104.93}
|
|
{"type": "train", "iter": 300, "loss": 3.8235, "ms": 4652.7, "t": 105.39}
|