Wisp-15M / training_log.jsonl
DedeProGames's picture
Wisp-15M: 3.00B tokens
942ba60 verified
Raw History Blame Contribute Delete
37.8 kB
{"step": 50, "tokens": 13107200, "loss": 5.9735, "lr": 0.001842, "gnorm": 1.941, "tok_s": 116678, "elapsed_min": 1.87, "eta_min": 142.8, "cost_usd": 0.043}
{"step": 100, "tokens": 26214400, "loss": 5.2579, "lr": 0.003684, "gnorm": 0.518, "tok_s": 145018, "elapsed_min": 3.38, "eta_min": 141.3, "cost_usd": 0.063}
{"step": 150, "tokens": 39321600, "loss": 4.9108, "lr": 0.005526, "gnorm": 0.431, "tok_s": 136285, "elapsed_min": 4.98, "eta_min": 143.5, "cost_usd": 0.084}
{"step": 200, "tokens": 52428800, "loss": 4.6576, "lr": 0.007, "gnorm": 0.575, "tok_s": 134695, "elapsed_min": 6.6, "eta_min": 144.3, "cost_usd": 0.106}
{"step": 250, "tokens": 65536000, "loss": 4.4183, "lr": 0.007, "gnorm": 0.351, "tok_s": 134057, "elapsed_min": 8.23, "eta_min": 139.5, "cost_usd": 0.128}
{"step": 300, "tokens": 78643200, "loss": 4.1418, "lr": 0.007, "gnorm": 0.291, "tok_s": 134238, "elapsed_min": 9.86, "eta_min": 135.5, "cost_usd": 0.149}
{"step": 350, "tokens": 91750400, "loss": 3.9358, "lr": 0.007, "gnorm": 0.268, "tok_s": 134132, "elapsed_min": 11.49, "eta_min": 133.3, "cost_usd": 0.171}
{"step": 400, "tokens": 104857600, "loss": 3.7695, "lr": 0.007, "gnorm": 0.295, "tok_s": 133957, "elapsed_min": 13.12, "eta_min": 131.6, "cost_usd": 0.193}
{"step": 450, "tokens": 117964800, "loss": 3.5545, "lr": 0.007, "gnorm": 0.268, "tok_s": 133879, "elapsed_min": 14.75, "eta_min": 130.1, "cost_usd": 0.214}
{"step": 500, "tokens": 131072000, "loss": 3.5182, "lr": 0.007, "gnorm": 0.301, "tok_s": 133930, "elapsed_min": 16.38, "eta_min": 128.3, "cost_usd": 0.236}
{"step": 550, "tokens": 144179200, "loss": 3.5958, "lr": 0.007, "gnorm": 0.303, "tok_s": 133837, "elapsed_min": 18.01, "eta_min": 126.6, "cost_usd": 0.258}
{"step": 600, "tokens": 157286400, "loss": 3.4827, "lr": 0.007, "gnorm": 0.251, "tok_s": 133930, "elapsed_min": 19.65, "eta_min": 125.0, "cost_usd": 0.28}
{"step": 650, "tokens": 170393600, "loss": 3.5263, "lr": 0.007, "gnorm": 0.249, "tok_s": 133915, "elapsed_min": 21.28, "eta_min": 123.4, "cost_usd": 0.301}
{"step": 700, "tokens": 183500800, "loss": 3.4466, "lr": 0.007, "gnorm": 0.211, "tok_s": 133935, "elapsed_min": 22.91, "eta_min": 121.7, "cost_usd": 0.323}
{"step": 750, "tokens": 196608000, "loss": 3.4587, "lr": 0.007, "gnorm": 0.225, "tok_s": 133870, "elapsed_min": 24.54, "eta_min": 120.1, "cost_usd": 0.345}
{"step": 800, "tokens": 209715200, "loss": 3.4529, "lr": 0.007, "gnorm": 0.224, "tok_s": 133757, "elapsed_min": 26.17, "eta_min": 118.5, "cost_usd": 0.367}
{"step": 850, "tokens": 222822400, "loss": 3.3337, "lr": 0.007, "gnorm": 0.227, "tok_s": 133968, "elapsed_min": 27.8, "eta_min": 116.9, "cost_usd": 0.388}
{"step": 900, "tokens": 235929600, "loss": 3.1141, "lr": 0.007, "gnorm": 0.219, "tok_s": 133976, "elapsed_min": 29.43, "eta_min": 115.2, "cost_usd": 0.41}
{"step": 950, "tokens": 249036800, "loss": 3.3102, "lr": 0.007, "gnorm": 0.213, "tok_s": 133821, "elapsed_min": 31.07, "eta_min": 113.4, "cost_usd": 0.432}
{"step": 1000, "tokens": 262144000, "loss": 3.3499, "lr": 0.007, "gnorm": 0.224, "tok_s": 134069, "elapsed_min": 32.7, "eta_min": 111.8, "cost_usd": 0.454}
{"step": 1000, "tokens": 262144000, "val": {"dclm": 3.641, "finemath": 2.829, "fineweb": 3.4368, "stack": 2.0977, "avg": 3.0011}}
{"step": 1050, "tokens": 275251200, "loss": 3.2948, "lr": 0.007, "gnorm": 0.197, "tok_s": 131211, "elapsed_min": 34.36, "eta_min": 110.3, "cost_usd": 0.476}
{"step": 1100, "tokens": 288358400, "loss": 3.318, "lr": 0.007, "gnorm": 0.201, "tok_s": 134286, "elapsed_min": 35.99, "eta_min": 108.7, "cost_usd": 0.498}
{"step": 1150, "tokens": 301465600, "loss": 3.3211, "lr": 0.007, "gnorm": 0.183, "tok_s": 134291, "elapsed_min": 37.61, "eta_min": 107.0, "cost_usd": 0.519}
{"step": 1200, "tokens": 314572800, "loss": 3.2319, "lr": 0.007, "gnorm": 0.182, "tok_s": 134240, "elapsed_min": 39.24, "eta_min": 331.8, "cost_usd": 0.541}
{"step": 1250, "tokens": 327680000, "loss": 3.3195, "lr": 0.007, "gnorm": 0.336, "tok_s": 134292, "elapsed_min": 40.87, "eta_min": 330.2, "cost_usd": 0.563}
{"step": 1300, "tokens": 340787200, "loss": 3.2135, "lr": 0.007, "gnorm": 0.192, "tok_s": 134236, "elapsed_min": 42.5, "eta_min": 328.6, "cost_usd": 0.584}
{"step": 1350, "tokens": 353894400, "loss": 3.2725, "lr": 0.007, "gnorm": 0.2, "tok_s": 134216, "elapsed_min": 44.12, "eta_min": 327.0, "cost_usd": 0.606}
{"step": 1400, "tokens": 367001600, "loss": 3.1549, "lr": 0.007, "gnorm": 0.198, "tok_s": 134317, "elapsed_min": 45.75, "eta_min": 325.3, "cost_usd": 0.628}
{"step": 1450, "tokens": 380108800, "loss": 3.2754, "lr": 0.007, "gnorm": 0.209, "tok_s": 134268, "elapsed_min": 47.38, "eta_min": 323.6, "cost_usd": 0.649}
{"step": 1500, "tokens": 393216000, "loss": 3.1192, "lr": 0.007, "gnorm": 0.215, "tok_s": 134290, "elapsed_min": 49.0, "eta_min": 322.0, "cost_usd": 0.671}
{"step": 1550, "tokens": 406323200, "loss": 3.2617, "lr": 0.007, "gnorm": 0.175, "tok_s": 134271, "elapsed_min": 50.63, "eta_min": 320.4, "cost_usd": 0.693}
{"step": 1600, "tokens": 419430400, "loss": 3.1331, "lr": 0.007, "gnorm": 0.2, "tok_s": 134306, "elapsed_min": 52.26, "eta_min": 318.8, "cost_usd": 0.715}
{"step": 1650, "tokens": 432537600, "loss": 3.2758, "lr": 0.007, "gnorm": 0.21, "tok_s": 134340, "elapsed_min": 53.88, "eta_min": 317.1, "cost_usd": 0.736}
{"step": 1700, "tokens": 445644800, "loss": 3.1678, "lr": 0.007, "gnorm": 0.19, "tok_s": 134396, "elapsed_min": 55.51, "eta_min": 315.4, "cost_usd": 0.758}
{"step": 1750, "tokens": 458752000, "loss": 3.2038, "lr": 0.007, "gnorm": 0.209, "tok_s": 134262, "elapsed_min": 57.14, "eta_min": 313.8, "cost_usd": 0.78}
{"step": 1800, "tokens": 471859200, "loss": 3.1852, "lr": 0.007, "gnorm": 0.174, "tok_s": 134162, "elapsed_min": 58.76, "eta_min": 312.5, "cost_usd": 0.801}
{"step": 1850, "tokens": 484966400, "loss": 3.1427, "lr": 0.007, "gnorm": 0.212, "tok_s": 134215, "elapsed_min": 60.39, "eta_min": 309.9, "cost_usd": 0.823}
{"step": 1900, "tokens": 498073600, "loss": 3.1062, "lr": 0.007, "gnorm": 0.188, "tok_s": 134335, "elapsed_min": 62.02, "eta_min": 308.1, "cost_usd": 0.845}
{"step": 1950, "tokens": 511180800, "loss": 3.2238, "lr": 0.007, "gnorm": 0.179, "tok_s": 134269, "elapsed_min": 63.65, "eta_min": 307.4, "cost_usd": 0.866}
{"step": 2000, "tokens": 524288000, "loss": 3.0813, "lr": 0.007, "gnorm": 0.172, "tok_s": 134173, "elapsed_min": 65.27, "eta_min": 306.0, "cost_usd": 0.888}
{"step": 2000, "tokens": 524288000, "val": {"dclm": 3.5066, "finemath": 2.6546, "fineweb": 3.287, "stack": 1.8957, "avg": 2.836}}
{"step": 2050, "tokens": 537395200, "loss": 3.1242, "lr": 0.007, "gnorm": 0.17, "tok_s": 131415, "elapsed_min": 66.94, "eta_min": 304.2, "cost_usd": 0.91}
{"step": 2100, "tokens": 550502400, "loss": 3.1031, "lr": 0.007, "gnorm": 0.172, "tok_s": 134391, "elapsed_min": 68.56, "eta_min": 302.4, "cost_usd": 0.932}
{"step": 2150, "tokens": 563609600, "loss": 3.1187, "lr": 0.007, "gnorm": 0.183, "tok_s": 134149, "elapsed_min": 70.19, "eta_min": 301.0, "cost_usd": 0.954}
{"step": 2200, "tokens": 576716800, "loss": 3.1908, "lr": 0.007, "gnorm": 0.184, "tok_s": 134342, "elapsed_min": 71.82, "eta_min": 299.5, "cost_usd": 0.975}
{"step": 2250, "tokens": 589824000, "loss": 3.2001, "lr": 0.007, "gnorm": 0.179, "tok_s": 134226, "elapsed_min": 73.44, "eta_min": 297.7, "cost_usd": 0.997}
{"step": 2300, "tokens": 602931200, "loss": 3.1719, "lr": 0.007, "gnorm": 0.181, "tok_s": 134294, "elapsed_min": 75.07, "eta_min": 296.2, "cost_usd": 1.019}
{"step": 2350, "tokens": 616038400, "loss": 3.1626, "lr": 0.007, "gnorm": 0.174, "tok_s": 134429, "elapsed_min": 76.69, "eta_min": 294.3, "cost_usd": 1.04}
{"step": 2400, "tokens": 629145600, "loss": 3.2086, "lr": 0.007, "gnorm": 0.176, "tok_s": 134317, "elapsed_min": 78.32, "eta_min": 292.7, "cost_usd": 1.062}
{"step": 2450, "tokens": 642252800, "loss": 3.1619, "lr": 0.007, "gnorm": 0.169, "tok_s": 134442, "elapsed_min": 79.95, "eta_min": 291.1, "cost_usd": 1.084}
{"step": 2500, "tokens": 655360000, "loss": 3.1548, "lr": 0.007, "gnorm": 0.16, "tok_s": 134326, "elapsed_min": 81.57, "eta_min": 289.4, "cost_usd": 1.105}
{"step": 2550, "tokens": 668467200, "loss": 3.2046, "lr": 0.007, "gnorm": 0.162, "tok_s": 134440, "elapsed_min": 83.2, "eta_min": 287.8, "cost_usd": 1.127}
{"step": 2600, "tokens": 681574400, "loss": 3.0819, "lr": 0.007, "gnorm": 0.197, "tok_s": 134394, "elapsed_min": 84.82, "eta_min": 286.1, "cost_usd": 1.149}
{"step": 2650, "tokens": 694681600, "loss": 3.1084, "lr": 0.007, "gnorm": 0.176, "tok_s": 134304, "elapsed_min": 86.45, "eta_min": 284.6, "cost_usd": 1.17}
{"step": 2700, "tokens": 707788800, "loss": 3.077, "lr": 0.007, "gnorm": 0.183, "tok_s": 134517, "elapsed_min": 88.07, "eta_min": 282.9, "cost_usd": 1.192}
{"step": 2750, "tokens": 720896000, "loss": 3.1611, "lr": 0.007, "gnorm": 0.181, "tok_s": 134248, "elapsed_min": 89.7, "eta_min": 281.3, "cost_usd": 1.214}
{"step": 2800, "tokens": 734003200, "loss": 3.0317, "lr": 0.007, "gnorm": 0.166, "tok_s": 133997, "elapsed_min": 91.33, "eta_min": 279.3, "cost_usd": 1.235}
{"step": 2850, "tokens": 747110400, "loss": 3.1505, "lr": 0.007, "gnorm": 0.157, "tok_s": 134302, "elapsed_min": 92.96, "eta_min": 277.6, "cost_usd": 1.257}
{"step": 2900, "tokens": 760217600, "loss": 3.0724, "lr": 0.007, "gnorm": 0.16, "tok_s": 134161, "elapsed_min": 94.59, "eta_min": 276.8, "cost_usd": 1.279}
{"step": 2950, "tokens": 773324800, "loss": 3.069, "lr": 0.007, "gnorm": 0.169, "tok_s": 134174, "elapsed_min": 96.21, "eta_min": 275.3, "cost_usd": 1.301}
{"step": 3000, "tokens": 786432000, "loss": 3.078, "lr": 0.007, "gnorm": 0.177, "tok_s": 134083, "elapsed_min": 97.84, "eta_min": 273.8, "cost_usd": 1.322}
{"step": 3000, "tokens": 786432000, "val": {"dclm": 3.4534, "finemath": 2.5945, "fineweb": 3.2282, "stack": 1.844, "avg": 2.78}}
{"step": 3050, "tokens": 799539200, "loss": 3.0146, "lr": 0.007, "gnorm": 0.145, "tok_s": 131277, "elapsed_min": 99.51, "eta_min": 272.1, "cost_usd": 1.345}
{"step": 3100, "tokens": 812646400, "loss": 3.1616, "lr": 0.007, "gnorm": 0.176, "tok_s": 134229, "elapsed_min": 101.13, "eta_min": 270.3, "cost_usd": 1.366}
{"step": 3150, "tokens": 825753600, "loss": 3.0285, "lr": 0.007, "gnorm": 0.151, "tok_s": 134270, "elapsed_min": 102.76, "eta_min": 268.7, "cost_usd": 1.388}
{"step": 3200, "tokens": 838860800, "loss": 3.0001, "lr": 0.007, "gnorm": 0.169, "tok_s": 134249, "elapsed_min": 104.39, "eta_min": 267.0, "cost_usd": 1.41}
{"step": 3250, "tokens": 851968000, "loss": 3.0728, "lr": 0.007, "gnorm": 0.173, "tok_s": 133776, "elapsed_min": 106.02, "eta_min": 265.9, "cost_usd": 1.431}
{"step": 3300, "tokens": 865075200, "loss": 3.2736, "lr": 0.007, "gnorm": 0.183, "tok_s": 133880, "elapsed_min": 107.65, "eta_min": 264.6, "cost_usd": 1.453}
{"step": 3350, "tokens": 878182400, "loss": 3.1032, "lr": 0.007, "gnorm": 0.166, "tok_s": 133975, "elapsed_min": 109.28, "eta_min": 262.8, "cost_usd": 1.475}
{"step": 3400, "tokens": 891289600, "loss": 3.1025, "lr": 0.007, "gnorm": 0.152, "tok_s": 133906, "elapsed_min": 110.92, "eta_min": 261.2, "cost_usd": 1.497}
{"step": 3450, "tokens": 904396800, "loss": 2.919, "lr": 0.007, "gnorm": 0.15, "tok_s": 133778, "elapsed_min": 112.55, "eta_min": 259.7, "cost_usd": 1.518}
{"step": 3500, "tokens": 917504000, "loss": 3.0903, "lr": 0.007, "gnorm": 0.153, "tok_s": 134001, "elapsed_min": 114.18, "eta_min": 258.0, "cost_usd": 1.54}
{"step": 3550, "tokens": 930611200, "loss": 3.0713, "lr": 0.007, "gnorm": 0.166, "tok_s": 133866, "elapsed_min": 115.81, "eta_min": 256.3, "cost_usd": 1.562}
{"step": 3600, "tokens": 943718400, "loss": 3.1553, "lr": 0.007, "gnorm": 0.141, "tok_s": 133818, "elapsed_min": 117.44, "eta_min": 254.9, "cost_usd": 1.584}
{"step": 3650, "tokens": 956825600, "loss": 3.0782, "lr": 0.007, "gnorm": 0.145, "tok_s": 134228, "elapsed_min": 119.07, "eta_min": 252.9, "cost_usd": 1.605}
{"step": 3700, "tokens": 969932800, "loss": 3.0402, "lr": 0.007, "gnorm": 0.169, "tok_s": 134048, "elapsed_min": 120.7, "eta_min": 250.3, "cost_usd": 1.627}
{"step": 3750, "tokens": 983040000, "loss": 3.1617, "lr": 0.007, "gnorm": 0.152, "tok_s": 134190, "elapsed_min": 122.33, "eta_min": 248.7, "cost_usd": 1.649}
{"step": 3800, "tokens": 996147200, "loss": 3.0294, "lr": 0.007, "gnorm": 0.148, "tok_s": 134330, "elapsed_min": 123.95, "eta_min": 247.6, "cost_usd": 1.67}
{"step": 3850, "tokens": 1009254400, "loss": 3.0123, "lr": 0.007, "gnorm": 0.157, "tok_s": 134318, "elapsed_min": 125.58, "eta_min": 245.9, "cost_usd": 1.692}
{"step": 3900, "tokens": 1022361600, "loss": 3.146, "lr": 0.007, "gnorm": 0.145, "tok_s": 134223, "elapsed_min": 127.21, "eta_min": 244.3, "cost_usd": 1.714}
{"step": 3950, "tokens": 1035468800, "loss": 3.1388, "lr": 0.007, "gnorm": 0.176, "tok_s": 134233, "elapsed_min": 128.84, "eta_min": 242.8, "cost_usd": 1.736}
{"step": 4000, "tokens": 1048576000, "loss": 3.0941, "lr": 0.007, "gnorm": 0.136, "tok_s": 134235, "elapsed_min": 130.46, "eta_min": 241.2, "cost_usd": 1.757}
{"step": 4000, "tokens": 1048576000, "val": {"dclm": 3.4304, "finemath": 2.5558, "fineweb": 3.1921, "stack": 1.8104, "avg": 2.7472}}
{"step": 4050, "tokens": 1061683200, "loss": 3.0149, "lr": 0.007, "gnorm": 0.141, "tok_s": 131304, "elapsed_min": 132.13, "eta_min": 239.5, "cost_usd": 1.779}
{"step": 4100, "tokens": 1074790400, "loss": 3.0667, "lr": 0.007, "gnorm": 0.144, "tok_s": 134299, "elapsed_min": 133.75, "eta_min": 237.8, "cost_usd": 1.801}
{"step": 4150, "tokens": 1087897600, "loss": 3.1135, "lr": 0.007, "gnorm": 0.139, "tok_s": 134267, "elapsed_min": 135.38, "eta_min": 236.2, "cost_usd": 1.823}
{"step": 4200, "tokens": 1101004800, "loss": 2.9492, "lr": 0.007, "gnorm": 0.14, "tok_s": 134312, "elapsed_min": 137.01, "eta_min": 234.6, "cost_usd": 1.845}
{"step": 4250, "tokens": 1114112000, "loss": 3.0256, "lr": 0.007, "gnorm": 0.137, "tok_s": 134135, "elapsed_min": 138.64, "eta_min": 233.1, "cost_usd": 1.866}
{"step": 4300, "tokens": 1127219200, "loss": 3.0895, "lr": 0.007, "gnorm": 0.134, "tok_s": 134181, "elapsed_min": 140.26, "eta_min": 231.6, "cost_usd": 1.888}
{"step": 4350, "tokens": 1140326400, "loss": 3.0936, "lr": 0.007, "gnorm": 0.148, "tok_s": 134286, "elapsed_min": 141.89, "eta_min": 229.8, "cost_usd": 1.91}
{"step": 4400, "tokens": 1153433600, "loss": 3.0021, "lr": 0.007, "gnorm": 0.126, "tok_s": 134307, "elapsed_min": 143.52, "eta_min": 228.1, "cost_usd": 1.931}
{"step": 4450, "tokens": 1166540800, "loss": 3.08, "lr": 0.007, "gnorm": 0.156, "tok_s": 134309, "elapsed_min": 145.14, "eta_min": 226.5, "cost_usd": 1.953}
{"step": 4500, "tokens": 1179648000, "loss": 3.1347, "lr": 0.007, "gnorm": 0.154, "tok_s": 134350, "elapsed_min": 146.77, "eta_min": 224.8, "cost_usd": 1.975}
{"step": 4550, "tokens": 1192755200, "loss": 3.0766, "lr": 0.007, "gnorm": 0.136, "tok_s": 134358, "elapsed_min": 148.4, "eta_min": 223.1, "cost_usd": 1.996}
{"step": 4600, "tokens": 1205862400, "loss": 3.0984, "lr": 0.007, "gnorm": 0.136, "tok_s": 134163, "elapsed_min": 150.02, "eta_min": 221.7, "cost_usd": 2.018}
{"step": 4650, "tokens": 1218969600, "loss": 3.2507, "lr": 0.007, "gnorm": 0.146, "tok_s": 134048, "elapsed_min": 151.65, "eta_min": 219.6, "cost_usd": 2.04}
{"step": 4700, "tokens": 1232076800, "loss": 3.076, "lr": 0.007, "gnorm": 0.131, "tok_s": 134243, "elapsed_min": 153.28, "eta_min": 217.9, "cost_usd": 2.061}
{"step": 4750, "tokens": 1245184000, "loss": 3.0631, "lr": 0.007, "gnorm": 0.166, "tok_s": 134229, "elapsed_min": 154.91, "eta_min": 216.9, "cost_usd": 2.083}
{"step": 4800, "tokens": 1258291200, "loss": 3.2039, "lr": 0.007, "gnorm": 0.159, "tok_s": 134207, "elapsed_min": 156.54, "eta_min": 215.3, "cost_usd": 2.105}
{"step": 4850, "tokens": 1271398400, "loss": 3.1253, "lr": 0.007, "gnorm": 0.139, "tok_s": 134180, "elapsed_min": 158.16, "eta_min": 213.7, "cost_usd": 2.127}
{"step": 4900, "tokens": 1284505600, "loss": 3.074, "lr": 0.007, "gnorm": 0.141, "tok_s": 134316, "elapsed_min": 159.79, "eta_min": 212.0, "cost_usd": 2.148}
{"step": 4950, "tokens": 1297612800, "loss": 3.1734, "lr": 0.007, "gnorm": 0.132, "tok_s": 134220, "elapsed_min": 161.42, "eta_min": 210.3, "cost_usd": 2.17}
{"step": 5000, "tokens": 1310720000, "loss": 3.0067, "lr": 0.007, "gnorm": 0.151, "tok_s": 134231, "elapsed_min": 163.05, "eta_min": 208.8, "cost_usd": 2.192}
{"step": 5000, "tokens": 1310720000, "val": {"dclm": 3.4042, "finemath": 2.5482, "fineweb": 3.1724, "stack": 1.7754, "avg": 2.725}}
{"step": 5050, "tokens": 1323827200, "loss": 3.0406, "lr": 0.007, "gnorm": 0.152, "tok_s": 131328, "elapsed_min": 164.71, "eta_min": 207.1, "cost_usd": 2.214}
{"step": 5100, "tokens": 1336934400, "loss": 2.9662, "lr": 0.007, "gnorm": 0.144, "tok_s": 134222, "elapsed_min": 166.34, "eta_min": 205.5, "cost_usd": 2.236}
{"step": 5150, "tokens": 1350041600, "loss": 2.985, "lr": 0.007, "gnorm": 0.144, "tok_s": 134256, "elapsed_min": 167.96, "eta_min": 203.9, "cost_usd": 2.257}
{"step": 5200, "tokens": 1363148800, "loss": 3.1311, "lr": 0.007, "gnorm": 0.125, "tok_s": 134203, "elapsed_min": 169.59, "eta_min": 202.3, "cost_usd": 2.279}
{"step": 5250, "tokens": 1376256000, "loss": 3.0711, "lr": 0.007, "gnorm": 0.142, "tok_s": 134216, "elapsed_min": 171.22, "eta_min": 200.7, "cost_usd": 2.301}
{"step": 5300, "tokens": 1389363200, "loss": 3.1053, "lr": 0.007, "gnorm": 0.143, "tok_s": 134335, "elapsed_min": 172.84, "eta_min": 199.0, "cost_usd": 2.322}
{"step": 5350, "tokens": 1402470400, "loss": 3.0046, "lr": 0.007, "gnorm": 0.14, "tok_s": 134246, "elapsed_min": 174.47, "eta_min": 197.3, "cost_usd": 2.344}
{"step": 5400, "tokens": 1415577600, "loss": 3.058, "lr": 0.007, "gnorm": 0.138, "tok_s": 134121, "elapsed_min": 176.1, "eta_min": 195.9, "cost_usd": 2.366}
{"step": 5450, "tokens": 1428684800, "loss": 3.1332, "lr": 0.007, "gnorm": 0.123, "tok_s": 134240, "elapsed_min": 177.73, "eta_min": 194.3, "cost_usd": 2.387}
{"step": 5500, "tokens": 1441792000, "loss": 3.0222, "lr": 0.007, "gnorm": 0.132, "tok_s": 134382, "elapsed_min": 179.35, "eta_min": 192.5, "cost_usd": 2.409}
{"step": 5550, "tokens": 1454899200, "loss": 3.0215, "lr": 0.007, "gnorm": 0.135, "tok_s": 134123, "elapsed_min": 180.98, "eta_min": 190.3, "cost_usd": 2.431}
{"step": 5600, "tokens": 1468006400, "loss": 3.1019, "lr": 0.007, "gnorm": 0.142, "tok_s": 134301, "elapsed_min": 182.61, "eta_min": 188.8, "cost_usd": 2.453}
{"step": 5650, "tokens": 1481113600, "loss": 3.0448, "lr": 0.007, "gnorm": 0.139, "tok_s": 134333, "elapsed_min": 184.24, "eta_min": 187.6, "cost_usd": 2.474}
{"step": 5700, "tokens": 1494220800, "loss": 3.0353, "lr": 0.007, "gnorm": 0.141, "tok_s": 134203, "elapsed_min": 185.86, "eta_min": 186.0, "cost_usd": 2.496}
{"step": 5750, "tokens": 1507328000, "loss": 3.0206, "lr": 0.007, "gnorm": 0.129, "tok_s": 134290, "elapsed_min": 187.49, "eta_min": 184.5, "cost_usd": 2.518}
{"step": 5800, "tokens": 1520435200, "loss": 2.9837, "lr": 0.007, "gnorm": 0.132, "tok_s": 134416, "elapsed_min": 189.12, "eta_min": 182.7, "cost_usd": 2.539}
{"step": 5850, "tokens": 1533542400, "loss": 3.1048, "lr": 0.007, "gnorm": 0.138, "tok_s": 134338, "elapsed_min": 190.74, "eta_min": 181.0, "cost_usd": 2.561}
{"step": 5900, "tokens": 1546649600, "loss": 2.9863, "lr": 0.007, "gnorm": 0.141, "tok_s": 134286, "elapsed_min": 192.37, "eta_min": 179.5, "cost_usd": 2.583}
{"step": 5950, "tokens": 1559756800, "loss": 3.0351, "lr": 0.007, "gnorm": 0.131, "tok_s": 134265, "elapsed_min": 194.0, "eta_min": 177.9, "cost_usd": 2.604}
{"step": 6000, "tokens": 1572864000, "loss": 2.9753, "lr": 0.007, "gnorm": 0.15, "tok_s": 134245, "elapsed_min": 195.62, "eta_min": 176.3, "cost_usd": 2.626}
{"step": 6000, "tokens": 1572864000, "val": {"dclm": 3.3959, "finemath": 2.5241, "fineweb": 3.1566, "stack": 1.7624, "avg": 2.7097}}
{"step": 6050, "tokens": 1585971200, "loss": 3.0949, "lr": 0.007, "gnorm": 0.143, "tok_s": 131327, "elapsed_min": 197.29, "eta_min": 174.7, "cost_usd": 2.648}
{"step": 6100, "tokens": 1599078400, "loss": 3.0712, "lr": 0.007, "gnorm": 0.146, "tok_s": 134315, "elapsed_min": 198.91, "eta_min": 173.0, "cost_usd": 2.67}
{"step": 6150, "tokens": 1612185600, "loss": 3.1058, "lr": 0.007, "gnorm": 0.136, "tok_s": 134292, "elapsed_min": 200.54, "eta_min": 171.4, "cost_usd": 2.692}
{"step": 6200, "tokens": 1625292800, "loss": 3.1066, "lr": 0.007, "gnorm": 0.135, "tok_s": 134272, "elapsed_min": 202.17, "eta_min": 169.8, "cost_usd": 2.713}
{"step": 6250, "tokens": 1638400000, "loss": 3.0733, "lr": 0.007, "gnorm": 0.138, "tok_s": 134303, "elapsed_min": 203.79, "eta_min": 168.2, "cost_usd": 2.735}
{"step": 6300, "tokens": 1651507200, "loss": 2.9701, "lr": 0.007, "gnorm": 0.154, "tok_s": 134275, "elapsed_min": 205.42, "eta_min": 166.6, "cost_usd": 2.757}
{"step": 6350, "tokens": 1664614400, "loss": 3.1082, "lr": 0.007, "gnorm": 0.137, "tok_s": 134339, "elapsed_min": 207.05, "eta_min": 164.9, "cost_usd": 2.778}
{"step": 6400, "tokens": 1677721600, "loss": 3.0164, "lr": 0.007, "gnorm": 0.148, "tok_s": 134225, "elapsed_min": 208.67, "eta_min": 163.4, "cost_usd": 2.8}
{"step": 6450, "tokens": 1690828800, "loss": 3.084, "lr": 0.007, "gnorm": 0.126, "tok_s": 134193, "elapsed_min": 210.3, "eta_min": 161.3, "cost_usd": 2.822}
{"step": 6500, "tokens": 1703936000, "loss": 3.0154, "lr": 0.007, "gnorm": 0.127, "tok_s": 134215, "elapsed_min": 211.93, "eta_min": 159.7, "cost_usd": 2.843}
{"step": 6550, "tokens": 1717043200, "loss": 2.9617, "lr": 0.007, "gnorm": 0.127, "tok_s": 134326, "elapsed_min": 213.55, "eta_min": 158.5, "cost_usd": 2.865}
{"step": 6600, "tokens": 1730150400, "loss": 3.0587, "lr": 0.007, "gnorm": 0.139, "tok_s": 134388, "elapsed_min": 215.18, "eta_min": 156.8, "cost_usd": 2.887}
{"step": 6650, "tokens": 1743257600, "loss": 3.1371, "lr": 0.007, "gnorm": 0.137, "tok_s": 134326, "elapsed_min": 216.81, "eta_min": 155.2, "cost_usd": 2.909}
{"step": 6700, "tokens": 1756364800, "loss": 3.1152, "lr": 0.007, "gnorm": 0.147, "tok_s": 134315, "elapsed_min": 218.43, "eta_min": 153.6, "cost_usd": 2.93}
{"step": 6750, "tokens": 1769472000, "loss": 3.0299, "lr": 0.007, "gnorm": 0.14, "tok_s": 134386, "elapsed_min": 220.06, "eta_min": 151.9, "cost_usd": 2.952}
{"step": 6800, "tokens": 1782579200, "loss": 3.0516, "lr": 0.007, "gnorm": 0.154, "tok_s": 134332, "elapsed_min": 221.68, "eta_min": 150.3, "cost_usd": 2.974}
{"step": 6850, "tokens": 1795686400, "loss": 3.0337, "lr": 0.007, "gnorm": 0.15, "tok_s": 134219, "elapsed_min": 223.31, "eta_min": 148.8, "cost_usd": 2.995}
{"step": 6900, "tokens": 1808793600, "loss": 3.0589, "lr": 0.007, "gnorm": 0.155, "tok_s": 134321, "elapsed_min": 224.94, "eta_min": 147.2, "cost_usd": 3.017}
{"step": 6950, "tokens": 1821900800, "loss": 3.0346, "lr": 0.007, "gnorm": 0.14, "tok_s": 134303, "elapsed_min": 226.57, "eta_min": 145.5, "cost_usd": 3.039}
{"step": 7000, "tokens": 1835008000, "loss": 3.1405, "lr": 0.007, "gnorm": 0.143, "tok_s": 134270, "elapsed_min": 228.19, "eta_min": 143.9, "cost_usd": 3.06}
{"step": 7000, "tokens": 1835008000, "val": {"dclm": 3.3826, "finemath": 2.5171, "fineweb": 3.1498, "stack": 1.7742, "avg": 2.7059}}
{"step": 7050, "tokens": 1848115200, "loss": 3.029, "lr": 0.007, "gnorm": 0.136, "tok_s": 131291, "elapsed_min": 229.86, "eta_min": 142.3, "cost_usd": 3.082}
{"step": 7100, "tokens": 1861222400, "loss": 3.0513, "lr": 0.007, "gnorm": 0.156, "tok_s": 134175, "elapsed_min": 231.48, "eta_min": 140.8, "cost_usd": 3.104}
{"step": 7150, "tokens": 1874329600, "loss": 3.0308, "lr": 0.007, "gnorm": 0.149, "tok_s": 134291, "elapsed_min": 233.11, "eta_min": 139.1, "cost_usd": 3.126}
{"step": 7200, "tokens": 1887436800, "loss": 3.0755, "lr": 0.007, "gnorm": 0.141, "tok_s": 134339, "elapsed_min": 234.74, "eta_min": 137.4, "cost_usd": 3.148}
{"step": 7250, "tokens": 1900544000, "loss": 2.9869, "lr": 0.007, "gnorm": 0.152, "tok_s": 134347, "elapsed_min": 236.36, "eta_min": 135.8, "cost_usd": 3.169}
{"step": 7300, "tokens": 1913651200, "loss": 3.04, "lr": 0.007, "gnorm": 0.118, "tok_s": 134302, "elapsed_min": 237.99, "eta_min": 134.2, "cost_usd": 3.191}
{"step": 7350, "tokens": 1926758400, "loss": 3.0053, "lr": 0.007, "gnorm": 0.132, "tok_s": 134230, "elapsed_min": 239.62, "eta_min": 132.6, "cost_usd": 3.213}
{"step": 7400, "tokens": 1939865600, "loss": 3.1038, "lr": 0.007, "gnorm": 0.142, "tok_s": 134064, "elapsed_min": 241.25, "eta_min": 130.7, "cost_usd": 3.234}
{"step": 7450, "tokens": 1952972800, "loss": 3.0249, "lr": 0.007, "gnorm": 0.149, "tok_s": 134326, "elapsed_min": 242.87, "eta_min": 129.0, "cost_usd": 3.256}
{"step": 7500, "tokens": 1966080000, "loss": 3.1051, "lr": 0.007, "gnorm": 0.136, "tok_s": 134233, "elapsed_min": 244.5, "eta_min": 127.7, "cost_usd": 3.278}
{"step": 7550, "tokens": 1979187200, "loss": 3.015, "lr": 0.007, "gnorm": 0.14, "tok_s": 134189, "elapsed_min": 246.13, "eta_min": 126.2, "cost_usd": 3.299}
{"step": 7600, "tokens": 1992294400, "loss": 3.0734, "lr": 0.007, "gnorm": 0.142, "tok_s": 134237, "elapsed_min": 247.76, "eta_min": 124.6, "cost_usd": 3.321}
{"step": 7650, "tokens": 2005401600, "loss": 3.0382, "lr": 0.007, "gnorm": 0.127, "tok_s": 134175, "elapsed_min": 249.38, "eta_min": 122.9, "cost_usd": 3.343}
{"step": 7700, "tokens": 2018508800, "loss": 2.9785, "lr": 0.007, "gnorm": 0.146, "tok_s": 134241, "elapsed_min": 251.01, "eta_min": 121.3, "cost_usd": 3.365}
{"step": 7750, "tokens": 2031616000, "loss": 2.9694, "lr": 0.007, "gnorm": 0.137, "tok_s": 134271, "elapsed_min": 252.64, "eta_min": 119.7, "cost_usd": 3.386}
{"step": 7800, "tokens": 2044723200, "loss": 3.0247, "lr": 0.007, "gnorm": 0.127, "tok_s": 134330, "elapsed_min": 254.26, "eta_min": 118.0, "cost_usd": 3.408}
{"step": 7850, "tokens": 2057830400, "loss": 3.0222, "lr": 0.007, "gnorm": 0.146, "tok_s": 134303, "elapsed_min": 255.89, "eta_min": 116.4, "cost_usd": 3.43}
{"step": 7900, "tokens": 2070937600, "loss": 3.0145, "lr": 0.007, "gnorm": 0.164, "tok_s": 134283, "elapsed_min": 257.52, "eta_min": 114.8, "cost_usd": 3.451}
{"step": 7950, "tokens": 2084044800, "loss": 3.016, "lr": 0.007, "gnorm": 0.143, "tok_s": 134383, "elapsed_min": 259.14, "eta_min": 113.1, "cost_usd": 3.473}
{"step": 8000, "tokens": 2097152000, "loss": 2.9818, "lr": 0.007, "gnorm": 0.161, "tok_s": 134380, "elapsed_min": 260.77, "eta_min": 111.5, "cost_usd": 3.495}
{"step": 8000, "tokens": 2097152000, "val": {"dclm": 3.3775, "finemath": 2.5073, "fineweb": 3.1451, "stack": 1.7382, "avg": 2.692}}
{"step": 8050, "tokens": 2110259200, "loss": 2.9759, "lr": 0.007, "gnorm": 0.147, "tok_s": 131279, "elapsed_min": 262.43, "eta_min": 109.9, "cost_usd": 3.517}
{"step": 8100, "tokens": 2123366400, "loss": 3.0755, "lr": 0.007, "gnorm": 0.158, "tok_s": 134369, "elapsed_min": 264.06, "eta_min": 108.3, "cost_usd": 3.539}
{"step": 8150, "tokens": 2136473600, "loss": 2.9764, "lr": 0.007, "gnorm": 0.14, "tok_s": 134345, "elapsed_min": 265.68, "eta_min": 106.6, "cost_usd": 3.56}
{"step": 8200, "tokens": 2149580800, "loss": 3.0862, "lr": 0.007, "gnorm": 0.143, "tok_s": 134229, "elapsed_min": 267.31, "eta_min": 105.1, "cost_usd": 3.582}
{"step": 8250, "tokens": 2162688000, "loss": 3.1409, "lr": 0.007, "gnorm": 0.14, "tok_s": 134367, "elapsed_min": 268.94, "eta_min": 103.4, "cost_usd": 3.604}
{"step": 8300, "tokens": 2175795200, "loss": 2.9188, "lr": 0.007, "gnorm": 0.152, "tok_s": 134349, "elapsed_min": 270.56, "eta_min": 101.4, "cost_usd": 3.625}
{"step": 8350, "tokens": 2188902400, "loss": 2.9445, "lr": 0.007, "gnorm": 0.136, "tok_s": 134398, "elapsed_min": 272.19, "eta_min": 99.8, "cost_usd": 3.647}
{"step": 8400, "tokens": 2202009600, "loss": 2.9227, "lr": 0.007, "gnorm": 0.151, "tok_s": 134396, "elapsed_min": 273.82, "eta_min": 98.5, "cost_usd": 3.669}
{"step": 8450, "tokens": 2215116800, "loss": 2.9466, "lr": 0.007, "gnorm": 0.168, "tok_s": 134345, "elapsed_min": 275.44, "eta_min": 96.9, "cost_usd": 3.69}
{"step": 8500, "tokens": 2228224000, "loss": 2.9971, "lr": 0.007, "gnorm": 0.144, "tok_s": 134291, "elapsed_min": 277.07, "eta_min": 95.3, "cost_usd": 3.712}
{"step": 8550, "tokens": 2241331200, "loss": 2.9765, "lr": 0.007, "gnorm": 0.132, "tok_s": 134370, "elapsed_min": 278.69, "eta_min": 93.7, "cost_usd": 3.734}
{"step": 8600, "tokens": 2254438400, "loss": 3.1546, "lr": 0.007, "gnorm": 0.147, "tok_s": 134359, "elapsed_min": 280.32, "eta_min": 92.0, "cost_usd": 3.755}
{"step": 8650, "tokens": 2267545600, "loss": 3.0504, "lr": 0.007, "gnorm": 0.146, "tok_s": 134384, "elapsed_min": 281.95, "eta_min": 90.4, "cost_usd": 3.777}
{"step": 8700, "tokens": 2280652800, "loss": 3.0737, "lr": 0.007, "gnorm": 0.146, "tok_s": 134441, "elapsed_min": 283.57, "eta_min": 88.8, "cost_usd": 3.799}
{"step": 8750, "tokens": 2293760000, "loss": 3.0798, "lr": 0.007, "gnorm": 0.127, "tok_s": 134463, "elapsed_min": 285.19, "eta_min": 87.1, "cost_usd": 3.82}
{"step": 8800, "tokens": 2306867200, "loss": 3.1563, "lr": 0.007, "gnorm": 0.137, "tok_s": 134317, "elapsed_min": 286.82, "eta_min": 85.6, "cost_usd": 3.842}
{"step": 8850, "tokens": 2319974400, "loss": 3.0055, "lr": 0.007, "gnorm": 0.127, "tok_s": 134431, "elapsed_min": 288.45, "eta_min": 83.9, "cost_usd": 3.864}
{"step": 8900, "tokens": 2333081600, "loss": 3.0422, "lr": 0.007, "gnorm": 0.149, "tok_s": 134336, "elapsed_min": 290.07, "eta_min": 82.3, "cost_usd": 3.885}
{"step": 8950, "tokens": 2346188800, "loss": 2.9729, "lr": 0.007, "gnorm": 0.155, "tok_s": 134364, "elapsed_min": 291.7, "eta_min": 80.7, "cost_usd": 3.907}
{"step": 9000, "tokens": 2359296000, "loss": 3.0358, "lr": 0.007, "gnorm": 0.153, "tok_s": 134440, "elapsed_min": 293.32, "eta_min": 79.1, "cost_usd": 3.929}
{"step": 9000, "tokens": 2359296000, "val": {"dclm": 3.3717, "finemath": 2.4859, "fineweb": 3.1316, "stack": 1.7351, "avg": 2.6811}}
{"step": 9050, "tokens": 2372403200, "loss": 3.1662, "lr": 0.007, "gnorm": 0.151, "tok_s": 131464, "elapsed_min": 294.98, "eta_min": 77.4, "cost_usd": 3.951}
{"step": 9100, "tokens": 2385510400, "loss": 3.0389, "lr": 0.007, "gnorm": 0.145, "tok_s": 134412, "elapsed_min": 296.61, "eta_min": 75.8, "cost_usd": 3.973}
{"step": 9150, "tokens": 2398617600, "loss": 2.9812, "lr": 0.007, "gnorm": 0.144, "tok_s": 134342, "elapsed_min": 298.24, "eta_min": 74.2, "cost_usd": 3.994}
{"step": 9200, "tokens": 2411724800, "loss": 3.0568, "lr": 0.006865, "gnorm": 0.134, "tok_s": 134326, "elapsed_min": 299.86, "eta_min": 72.4, "cost_usd": 4.016}
{"step": 9250, "tokens": 2424832000, "loss": 3.0444, "lr": 0.006713, "gnorm": 0.126, "tok_s": 134194, "elapsed_min": 301.49, "eta_min": 70.6, "cost_usd": 4.038}
{"step": 9300, "tokens": 2437939200, "loss": 3.0868, "lr": 0.00656, "gnorm": 0.148, "tok_s": 134309, "elapsed_min": 303.12, "eta_min": 69.2, "cost_usd": 4.059}
{"step": 9350, "tokens": 2451046400, "loss": 3.05, "lr": 0.006407, "gnorm": 0.125, "tok_s": 134311, "elapsed_min": 304.74, "eta_min": 67.8, "cost_usd": 4.081}
{"step": 9400, "tokens": 2464153600, "loss": 3.0006, "lr": 0.006254, "gnorm": 0.14, "tok_s": 134362, "elapsed_min": 306.37, "eta_min": 66.2, "cost_usd": 4.103}
{"step": 9450, "tokens": 2477260800, "loss": 3.0166, "lr": 0.006101, "gnorm": 0.124, "tok_s": 134353, "elapsed_min": 307.99, "eta_min": 64.5, "cost_usd": 4.124}
{"step": 9500, "tokens": 2490368000, "loss": 2.9326, "lr": 0.005948, "gnorm": 0.132, "tok_s": 134267, "elapsed_min": 309.62, "eta_min": 62.9, "cost_usd": 4.146}
{"step": 9550, "tokens": 2503475200, "loss": 3.0102, "lr": 0.005795, "gnorm": 0.118, "tok_s": 134399, "elapsed_min": 311.25, "eta_min": 61.3, "cost_usd": 4.168}
{"step": 9600, "tokens": 2516582400, "loss": 3.0544, "lr": 0.005642, "gnorm": 0.126, "tok_s": 134395, "elapsed_min": 312.87, "eta_min": 59.7, "cost_usd": 4.189}
{"step": 9650, "tokens": 2529689600, "loss": 2.9517, "lr": 0.005489, "gnorm": 0.125, "tok_s": 134332, "elapsed_min": 314.5, "eta_min": 58.1, "cost_usd": 4.211}
{"step": 9700, "tokens": 2542796800, "loss": 2.9026, "lr": 0.005336, "gnorm": 0.122, "tok_s": 134197, "elapsed_min": 316.13, "eta_min": 56.5, "cost_usd": 4.233}
{"step": 9750, "tokens": 2555904000, "loss": 2.955, "lr": 0.005183, "gnorm": 0.127, "tok_s": 134281, "elapsed_min": 317.75, "eta_min": 54.9, "cost_usd": 4.254}
{"step": 9800, "tokens": 2569011200, "loss": 2.8608, "lr": 0.005031, "gnorm": 0.132, "tok_s": 134298, "elapsed_min": 319.38, "eta_min": 53.2, "cost_usd": 4.276}
{"step": 9850, "tokens": 2582118400, "loss": 2.8522, "lr": 0.004878, "gnorm": 0.128, "tok_s": 134401, "elapsed_min": 321.01, "eta_min": 51.6, "cost_usd": 4.298}
{"step": 9900, "tokens": 2595225600, "loss": 2.9496, "lr": 0.004725, "gnorm": 0.121, "tok_s": 134417, "elapsed_min": 322.63, "eta_min": 50.0, "cost_usd": 4.319}
{"step": 9950, "tokens": 2608332800, "loss": 2.9955, "lr": 0.004572, "gnorm": 0.12, "tok_s": 134266, "elapsed_min": 324.26, "eta_min": 48.4, "cost_usd": 4.341}
{"step": 10000, "tokens": 2621440000, "loss": 2.9203, "lr": 0.004419, "gnorm": 0.12, "tok_s": 134403, "elapsed_min": 325.88, "eta_min": 46.7, "cost_usd": 4.363}
{"step": 10000, "tokens": 2621440000, "val": {"dclm": 3.2988, "finemath": 2.415, "fineweb": 3.0587, "stack": 1.6468, "avg": 2.6048}}
{"step": 10050, "tokens": 2634547200, "loss": 2.9394, "lr": 0.004266, "gnorm": 0.115, "tok_s": 131684, "elapsed_min": 327.54, "eta_min": 45.1, "cost_usd": 4.385}
{"step": 10100, "tokens": 2647654400, "loss": 3.0485, "lr": 0.004113, "gnorm": 0.116, "tok_s": 134724, "elapsed_min": 329.16, "eta_min": 43.4, "cost_usd": 4.407}
{"step": 10150, "tokens": 2660761600, "loss": 3.0523, "lr": 0.00396, "gnorm": 0.133, "tok_s": 134348, "elapsed_min": 330.79, "eta_min": 41.7, "cost_usd": 4.428}
{"step": 10200, "tokens": 2673868800, "loss": 3.0208, "lr": 0.003807, "gnorm": 0.139, "tok_s": 134478, "elapsed_min": 332.41, "eta_min": 40.1, "cost_usd": 4.45}
{"step": 10250, "tokens": 2686976000, "loss": 2.9216, "lr": 0.003654, "gnorm": 0.105, "tok_s": 134414, "elapsed_min": 334.04, "eta_min": 38.6, "cost_usd": 4.472}
{"step": 10300, "tokens": 2700083200, "loss": 2.9301, "lr": 0.003502, "gnorm": 0.12, "tok_s": 134231, "elapsed_min": 335.67, "eta_min": 37.0, "cost_usd": 4.493}
{"step": 10350, "tokens": 2713190400, "loss": 2.9689, "lr": 0.003349, "gnorm": 0.103, "tok_s": 134219, "elapsed_min": 337.29, "eta_min": 35.4, "cost_usd": 4.515}
{"step": 10400, "tokens": 2726297600, "loss": 2.8918, "lr": 0.003196, "gnorm": 0.105, "tok_s": 134126, "elapsed_min": 338.92, "eta_min": 33.8, "cost_usd": 4.537}
{"step": 10450, "tokens": 2739404800, "loss": 2.8998, "lr": 0.003043, "gnorm": 0.131, "tok_s": 134174, "elapsed_min": 340.55, "eta_min": 32.2, "cost_usd": 4.558}
{"step": 10500, "tokens": 2752512000, "loss": 2.9605, "lr": 0.00289, "gnorm": 0.113, "tok_s": 134184, "elapsed_min": 342.18, "eta_min": 30.6, "cost_usd": 4.58}
{"step": 10550, "tokens": 2765619200, "loss": 2.828, "lr": 0.002737, "gnorm": 0.105, "tok_s": 134798, "elapsed_min": 343.8, "eta_min": 28.9, "cost_usd": 4.602}
{"step": 10600, "tokens": 2778726400, "loss": 2.9943, "lr": 0.002584, "gnorm": 0.101, "tok_s": 135621, "elapsed_min": 345.41, "eta_min": 27.1, "cost_usd": 4.623}
{"step": 10650, "tokens": 2791833600, "loss": 2.8484, "lr": 0.002431, "gnorm": 0.096, "tok_s": 135248, "elapsed_min": 347.03, "eta_min": 25.5, "cost_usd": 4.645}
{"step": 10700, "tokens": 2804940800, "loss": 2.9248, "lr": 0.002278, "gnorm": 0.105, "tok_s": 135368, "elapsed_min": 348.64, "eta_min": 23.9, "cost_usd": 4.666}
{"step": 10750, "tokens": 2818048000, "loss": 2.8582, "lr": 0.002125, "gnorm": 0.105, "tok_s": 136404, "elapsed_min": 350.24, "eta_min": 22.2, "cost_usd": 4.688}
{"step": 10800, "tokens": 2831155200, "loss": 2.837, "lr": 0.001972, "gnorm": 0.097, "tok_s": 136422, "elapsed_min": 351.84, "eta_min": 20.5, "cost_usd": 4.709}
{"step": 10850, "tokens": 2844262400, "loss": 2.7994, "lr": 0.00182, "gnorm": 0.111, "tok_s": 136946, "elapsed_min": 353.44, "eta_min": 18.9, "cost_usd": 4.73}
{"step": 10900, "tokens": 2857369600, "loss": 2.7795, "lr": 0.001667, "gnorm": 0.106, "tok_s": 137057, "elapsed_min": 355.03, "eta_min": 17.3, "cost_usd": 4.752}
{"step": 10950, "tokens": 2870476800, "loss": 2.7902, "lr": 0.001514, "gnorm": 0.097, "tok_s": 137052, "elapsed_min": 356.63, "eta_min": 15.7, "cost_usd": 4.773}
{"step": 11000, "tokens": 2883584000, "loss": 2.8408, "lr": 0.001361, "gnorm": 0.094, "tok_s": 136912, "elapsed_min": 358.22, "eta_min": 14.1, "cost_usd": 4.794}
{"step": 11000, "tokens": 2883584000, "val": {"dclm": 3.203, "finemath": 2.316, "fineweb": 2.9576, "stack": 1.5133, "avg": 2.4975}}
{"step": 11050, "tokens": 2896691200, "loss": 2.9175, "lr": 0.001208, "gnorm": 0.09, "tok_s": 133927, "elapsed_min": 359.85, "eta_min": 12.5, "cost_usd": 4.816}
{"step": 11100, "tokens": 2909798400, "loss": 2.739, "lr": 0.001055, "gnorm": 0.089, "tok_s": 137355, "elapsed_min": 361.44, "eta_min": 10.9, "cost_usd": 4.837}
{"step": 11150, "tokens": 2922905600, "loss": 2.7874, "lr": 0.000902, "gnorm": 0.093, "tok_s": 135833, "elapsed_min": 363.05, "eta_min": 9.3, "cost_usd": 4.858}
{"step": 11200, "tokens": 2936012800, "loss": 2.9161, "lr": 0.000749, "gnorm": 0.097, "tok_s": 135571, "elapsed_min": 364.66, "eta_min": 7.8, "cost_usd": 4.88}
{"step": 11250, "tokens": 2949120000, "loss": 2.8143, "lr": 0.000596, "gnorm": 0.09, "tok_s": 135510, "elapsed_min": 366.27, "eta_min": 6.2, "cost_usd": 4.901}
{"step": 11300, "tokens": 2962227200, "loss": 2.8791, "lr": 0.000443, "gnorm": 0.093, "tok_s": 135450, "elapsed_min": 367.89, "eta_min": 4.6, "cost_usd": 4.923}
{"step": 11350, "tokens": 2975334400, "loss": 2.7999, "lr": 0.000291, "gnorm": 0.086, "tok_s": 135421, "elapsed_min": 369.5, "eta_min": 3.0, "cost_usd": 4.944}
{"step": 11400, "tokens": 2988441600, "loss": 2.6924, "lr": 0.000138, "gnorm": 0.088, "tok_s": 135283, "elapsed_min": 371.12, "eta_min": 1.4, "cost_usd": 4.966}
{"step": 11444, "tokens": 2999975936, "loss": 2.8077, "lr": 3e-06, "gnorm": 0.081, "tok_s": 135584, "elapsed_min": 372.53, "eta_min": 0.0, "cost_usd": 4.985}
{"step": 11444, "tokens": 2999975936, "val": {"dclm": 3.1669, "finemath": 2.2753, "fineweb": 2.9144, "stack": 1.4606, "avg": 2.4543}}