Log snapshot @ step 4400
Browse files- logs/log_4400.jsonl +222 -0
logs/log_4400.jsonl
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"step": 0, "val_loss": 10.48933, "val_ppl": 35929.921, "event": "baseline"}
|
| 2 |
+
{"event": "run_start", "step": 0, "max_steps": 145000, "arch": "Rose X2", "tst_enabled": true, "ddp_enabled": false, "started_at": "2026-10-30T07:45:43.925369"}
|
| 3 |
+
{"step": 20, "epoch": 0.0, "loss": 10.09868, "ppl": 24310.788, "lr": 5.7e-05, "grad": 3.8799, "tokens_seen": 10480640, "compute_tokens": 10480640, "tok_s": 362337.9, "tst_active": true}
|
| 4 |
+
{"step": 40, "epoch": 0.0, "loss": 8.38317, "ppl": 4372.853, "lr": 0.000117, "grad": 2.2844, "tokens_seen": 20961280, "compute_tokens": 20961280, "tok_s": 366061.3, "tst_active": true}
|
| 5 |
+
{"step": 60, "epoch": 0.0, "loss": 7.23461, "ppl": 1386.603, "lr": 0.000177, "grad": 1.1701, "tokens_seen": 31441920, "compute_tokens": 31441920, "tok_s": 364917.4, "tst_active": true}
|
| 6 |
+
{"step": 80, "epoch": 0.001, "loss": 6.91204, "ppl": 1004.29, "lr": 0.000237, "grad": 1.3689, "tokens_seen": 41922560, "compute_tokens": 41922560, "tok_s": 362674.8, "tst_active": true}
|
| 7 |
+
{"step": 100, "epoch": 0.001, "loss": 6.83238, "ppl": 927.395, "lr": 0.000297, "grad": 1.3208, "tokens_seen": 52403200, "compute_tokens": 52403200, "tok_s": 354304.8, "tst_active": true}
|
| 8 |
+
{"step": 120, "epoch": 0.001, "loss": 6.61977, "ppl": 749.77, "lr": 0.000357, "grad": 1.2122, "tokens_seen": 62883840, "compute_tokens": 62883840, "tok_s": 361522.4, "tst_active": true}
|
| 9 |
+
{"step": 140, "epoch": 0.001, "loss": 6.586, "ppl": 724.875, "lr": 0.000417, "grad": 1.0447, "tokens_seen": 73364480, "compute_tokens": 73364480, "tok_s": 362710.6, "tst_active": true}
|
| 10 |
+
{"step": 160, "epoch": 0.001, "loss": 6.58957, "ppl": 727.466, "lr": 0.000477, "grad": 0.8991, "tokens_seen": 83845120, "compute_tokens": 83845120, "tok_s": 364219.3, "tst_active": true}
|
| 11 |
+
{"step": 180, "epoch": 0.001, "loss": 6.29914, "ppl": 544.106, "lr": 0.000537, "grad": 0.7136, "tokens_seen": 94325760, "compute_tokens": 94325760, "tok_s": 364198.8, "tst_active": true}
|
| 12 |
+
{"step": 200, "epoch": 0.001, "loss": 6.26725, "ppl": 527.024, "lr": 0.000597, "grad": 0.4278, "tokens_seen": 104806400, "compute_tokens": 104806400, "tok_s": 365110.0, "tst_active": true}
|
| 13 |
+
{"step": 220, "epoch": 0.002, "loss": 6.36752, "ppl": 582.609, "lr": 0.000657, "grad": 0.791, "tokens_seen": 115287040, "compute_tokens": 115287040, "tok_s": 357462.1, "tst_active": true}
|
| 14 |
+
{"step": 240, "epoch": 0.002, "loss": 6.34429, "ppl": 569.233, "lr": 0.000717, "grad": 0.8303, "tokens_seen": 125767680, "compute_tokens": 125767680, "tok_s": 364132.7, "tst_active": true}
|
| 15 |
+
{"step": 260, "epoch": 0.002, "loss": 6.22629, "ppl": 505.875, "lr": 0.000777, "grad": 0.9313, "tokens_seen": 136248320, "compute_tokens": 136248320, "tok_s": 364295.9, "tst_active": true}
|
| 16 |
+
{"step": 280, "epoch": 0.002, "loss": 6.02813, "ppl": 414.938, "lr": 0.000837, "grad": 0.5927, "tokens_seen": 146728960, "compute_tokens": 146728960, "tok_s": 364409.0, "tst_active": true}
|
| 17 |
+
{"step": 300, "epoch": 0.002, "loss": 6.08764, "ppl": 440.381, "lr": 0.000897, "grad": 0.708, "tokens_seen": 157209600, "compute_tokens": 157209600, "tok_s": 360361.7, "tst_active": true}
|
| 18 |
+
{"step": 320, "epoch": 0.002, "loss": 6.08326, "ppl": 438.458, "lr": 0.000957, "grad": 0.4566, "tokens_seen": 167690240, "compute_tokens": 167690240, "tok_s": 364755.6, "tst_active": true}
|
| 19 |
+
{"step": 340, "epoch": 0.002, "loss": 5.85996, "ppl": 350.71, "lr": 0.001017, "grad": 0.4591, "tokens_seen": 178170880, "compute_tokens": 178170880, "tok_s": 362206.3, "tst_active": true}
|
| 20 |
+
{"step": 360, "epoch": 0.002, "loss": 6.00622, "ppl": 405.948, "lr": 0.001077, "grad": 0.3487, "tokens_seen": 188651520, "compute_tokens": 188651520, "tok_s": 364100.0, "tst_active": true}
|
| 21 |
+
{"step": 380, "epoch": 0.003, "loss": 6.01815, "ppl": 410.816, "lr": 0.001137, "grad": 0.3629, "tokens_seen": 199132160, "compute_tokens": 199132160, "tok_s": 364015.8, "tst_active": true}
|
| 22 |
+
{"step": 400, "epoch": 0.003, "loss": 5.83865, "ppl": 343.316, "lr": 0.001197, "grad": 0.4983, "tokens_seen": 209612800, "compute_tokens": 209612800, "tok_s": 363892.7, "tst_active": true}
|
| 23 |
+
{"step": 420, "epoch": 0.003, "loss": 5.87381, "ppl": 355.601, "lr": 0.001257, "grad": 0.2681, "tokens_seen": 220093440, "compute_tokens": 220093440, "tok_s": 366179.3, "tst_active": true}
|
| 24 |
+
{"step": 440, "epoch": 0.003, "loss": 5.86433, "ppl": 352.245, "lr": 0.001317, "grad": 0.1994, "tokens_seen": 230574080, "compute_tokens": 230574080, "tok_s": 364353.6, "tst_active": true}
|
| 25 |
+
{"step": 460, "epoch": 0.003, "loss": 3.46167, "ppl": 31.87, "lr": 0.001377, "grad": 11.0781, "tokens_seen": 241054720, "compute_tokens": 241054720, "tok_s": 365814.6, "tst_active": true}
|
| 26 |
+
{"step": 480, "epoch": 0.003, "loss": 6.07926, "ppl": 436.705, "lr": 0.001437, "grad": 0.1677, "tokens_seen": 251535360, "compute_tokens": 251535360, "tok_s": 365846.2, "tst_active": true}
|
| 27 |
+
{"step": 500, "epoch": 0.003, "loss": 5.74687, "ppl": 313.209, "lr": 0.001497, "grad": 0.2629, "tokens_seen": 262016000, "compute_tokens": 262016000, "tok_s": 365066.0, "tst_active": true}
|
| 28 |
+
{"step": 520, "epoch": 0.004, "loss": 5.57154, "ppl": 262.837, "lr": 0.0015, "grad": 0.8984, "tokens_seen": 272496640, "compute_tokens": 272496640, "tok_s": 356687.3, "tst_active": true}
|
| 29 |
+
{"step": 540, "epoch": 0.004, "loss": 5.87642, "ppl": 356.531, "lr": 0.0015, "grad": 0.2123, "tokens_seen": 282977280, "compute_tokens": 282977280, "tok_s": 365542.7, "tst_active": true}
|
| 30 |
+
{"step": 560, "epoch": 0.004, "loss": 5.82428, "ppl": 338.419, "lr": 0.0015, "grad": 0.1955, "tokens_seen": 293457920, "compute_tokens": 293457920, "tok_s": 364363.6, "tst_active": true}
|
| 31 |
+
{"step": 580, "epoch": 0.004, "loss": 5.78075, "ppl": 324.002, "lr": 0.0015, "grad": 0.3405, "tokens_seen": 303938560, "compute_tokens": 303938560, "tok_s": 364344.1, "tst_active": true}
|
| 32 |
+
{"step": 600, "epoch": 0.004, "loss": 5.87834, "ppl": 357.215, "lr": 0.0015, "grad": 0.1845, "tokens_seen": 314419200, "compute_tokens": 314419200, "tok_s": 365519.9, "tst_active": true}
|
| 33 |
+
{"step": 620, "epoch": 0.004, "loss": 5.77764, "ppl": 322.995, "lr": 0.0015, "grad": 0.1653, "tokens_seen": 324899840, "compute_tokens": 324899840, "tok_s": 364869.9, "tst_active": true}
|
| 34 |
+
{"step": 640, "epoch": 0.004, "loss": 5.86465, "ppl": 352.359, "lr": 0.0015, "grad": 0.1682, "tokens_seen": 335380480, "compute_tokens": 335380480, "tok_s": 364352.6, "tst_active": true}
|
| 35 |
+
{"step": 660, "epoch": 0.005, "loss": 5.65819, "ppl": 286.63, "lr": 0.0015, "grad": 0.2957, "tokens_seen": 345861120, "compute_tokens": 345861120, "tok_s": 361575.4, "tst_active": true}
|
| 36 |
+
{"step": 680, "epoch": 0.005, "loss": 5.77656, "ppl": 322.648, "lr": 0.0015, "grad": 0.139, "tokens_seen": 356341760, "compute_tokens": 356341760, "tok_s": 363520.5, "tst_active": true}
|
| 37 |
+
{"step": 700, "epoch": 0.005, "loss": 5.65626, "ppl": 286.078, "lr": 0.0015, "grad": 0.164, "tokens_seen": 366822400, "compute_tokens": 366822400, "tok_s": 362880.2, "tst_active": true}
|
| 38 |
+
{"step": 720, "epoch": 0.005, "loss": 5.91228, "ppl": 369.547, "lr": 0.0015, "grad": 0.1639, "tokens_seen": 377303040, "compute_tokens": 377303040, "tok_s": 361694.5, "tst_active": true}
|
| 39 |
+
{"step": 740, "epoch": 0.005, "loss": 5.81677, "ppl": 335.885, "lr": 0.0015, "grad": 0.1602, "tokens_seen": 387783680, "compute_tokens": 387783680, "tok_s": 360834.6, "tst_active": true}
|
| 40 |
+
{"step": 760, "epoch": 0.005, "loss": 5.65391, "ppl": 285.407, "lr": 0.0015, "grad": 0.1285, "tokens_seen": 398264320, "compute_tokens": 398264320, "tok_s": 362116.6, "tst_active": true}
|
| 41 |
+
{"step": 780, "epoch": 0.005, "loss": 5.58933, "ppl": 267.556, "lr": 0.0015, "grad": 0.1443, "tokens_seen": 408744960, "compute_tokens": 408744960, "tok_s": 363022.9, "tst_active": true}
|
| 42 |
+
{"step": 800, "epoch": 0.005, "loss": 5.47042, "ppl": 237.559, "lr": 0.0015, "grad": 0.6223, "tokens_seen": 419225600, "compute_tokens": 419225600, "tok_s": 364562.9, "tst_active": true}
|
| 43 |
+
{"step": 820, "epoch": 0.006, "loss": 5.59502, "ppl": 269.082, "lr": 0.0015, "grad": 0.1639, "tokens_seen": 429706240, "compute_tokens": 429706240, "tok_s": 363958.4, "tst_active": true}
|
| 44 |
+
{"step": 840, "epoch": 0.006, "loss": 5.60258, "ppl": 271.125, "lr": 0.0015, "grad": 0.1792, "tokens_seen": 440186880, "compute_tokens": 440186880, "tok_s": 362299.6, "tst_active": true}
|
| 45 |
+
{"step": 860, "epoch": 0.006, "loss": 5.59342, "ppl": 268.653, "lr": 0.0015, "grad": 0.1605, "tokens_seen": 450667520, "compute_tokens": 450667520, "tok_s": 365380.5, "tst_active": true}
|
| 46 |
+
{"step": 880, "epoch": 0.006, "loss": 5.75658, "ppl": 316.264, "lr": 0.0015, "grad": 0.1601, "tokens_seen": 461148160, "compute_tokens": 461148160, "tok_s": 364924.5, "tst_active": true}
|
| 47 |
+
{"step": 900, "epoch": 0.006, "loss": 5.58583, "ppl": 266.623, "lr": 0.0015, "grad": 0.1538, "tokens_seen": 471628800, "compute_tokens": 471628800, "tok_s": 362910.2, "tst_active": true}
|
| 48 |
+
{"step": 920, "epoch": 0.006, "loss": 5.61839, "ppl": 275.446, "lr": 0.0015, "grad": 0.1477, "tokens_seen": 482109440, "compute_tokens": 482109440, "tok_s": 360995.2, "tst_active": true}
|
| 49 |
+
{"step": 940, "epoch": 0.006, "loss": 5.71299, "ppl": 302.775, "lr": 0.0015, "grad": 0.1371, "tokens_seen": 492590080, "compute_tokens": 492590080, "tok_s": 363740.7, "tst_active": true}
|
| 50 |
+
{"step": 960, "epoch": 0.007, "loss": 5.60086, "ppl": 270.659, "lr": 0.0015, "grad": 0.1468, "tokens_seen": 503070720, "compute_tokens": 503070720, "tok_s": 365114.8, "tst_active": true}
|
| 51 |
+
{"step": 980, "epoch": 0.007, "loss": 4.8328, "ppl": 125.562, "lr": 0.0015, "grad": 2.9677, "tokens_seen": 513551360, "compute_tokens": 513551360, "tok_s": 364368.1, "tst_active": true}
|
| 52 |
+
{"step": 1000, "epoch": 0.007, "loss": 5.54527, "ppl": 256.024, "lr": 0.0015, "grad": 0.1227, "tokens_seen": 524032000, "compute_tokens": 524032000, "tok_s": 363605.3, "tst_active": true}
|
| 53 |
+
{"step": 1020, "epoch": 0.007, "loss": 5.63311, "ppl": 279.531, "lr": 0.0015, "grad": 0.152, "tokens_seen": 534512640, "compute_tokens": 534512640, "tok_s": 364049.1, "tst_active": true}
|
| 54 |
+
{"step": 1040, "epoch": 0.007, "loss": 5.59419, "ppl": 268.861, "lr": 0.0015, "grad": 0.157, "tokens_seen": 544993280, "compute_tokens": 544993280, "tok_s": 362813.5, "tst_active": true}
|
| 55 |
+
{"step": 1060, "epoch": 0.007, "loss": 5.80776, "ppl": 332.871, "lr": 0.0015, "grad": 0.153, "tokens_seen": 555473920, "compute_tokens": 555473920, "tok_s": 357467.5, "tst_active": true}
|
| 56 |
+
{"step": 1080, "epoch": 0.007, "loss": 5.46241, "ppl": 235.664, "lr": 0.0015, "grad": 0.1337, "tokens_seen": 565954560, "compute_tokens": 565954560, "tok_s": 362658.7, "tst_active": true}
|
| 57 |
+
{"step": 1100, "epoch": 0.008, "loss": 5.70629, "ppl": 300.754, "lr": 0.0015, "grad": 0.1316, "tokens_seen": 576435200, "compute_tokens": 576435200, "tok_s": 363972.3, "tst_active": true}
|
| 58 |
+
{"step": 1120, "epoch": 0.008, "loss": 5.54738, "ppl": 256.565, "lr": 0.0015, "grad": 0.1158, "tokens_seen": 586915840, "compute_tokens": 586915840, "tok_s": 363125.4, "tst_active": true}
|
| 59 |
+
{"step": 1140, "epoch": 0.008, "loss": 5.51486, "ppl": 248.354, "lr": 0.0015, "grad": 0.1543, "tokens_seen": 597396480, "compute_tokens": 597396480, "tok_s": 361662.5, "tst_active": true}
|
| 60 |
+
{"step": 1160, "epoch": 0.008, "loss": 5.51484, "ppl": 248.351, "lr": 0.0015, "grad": 0.1781, "tokens_seen": 607877120, "compute_tokens": 607877120, "tok_s": 364085.2, "tst_active": true}
|
| 61 |
+
{"step": 1180, "epoch": 0.008, "loss": 5.53811, "ppl": 254.196, "lr": 0.0015, "grad": 0.1308, "tokens_seen": 618357760, "compute_tokens": 618357760, "tok_s": 361430.5, "tst_active": true}
|
| 62 |
+
{"step": 1200, "epoch": 0.008, "loss": 5.47188, "ppl": 237.907, "lr": 0.0015, "grad": 0.219, "tokens_seen": 628838400, "compute_tokens": 628838400, "tok_s": 363419.1, "tst_active": true}
|
| 63 |
+
{"step": 1220, "epoch": 0.008, "loss": 5.51024, "ppl": 247.211, "lr": 0.0015, "grad": 0.1636, "tokens_seen": 639319040, "compute_tokens": 639319040, "tok_s": 365456.3, "tst_active": true}
|
| 64 |
+
{"step": 1240, "epoch": 0.009, "loss": 5.59291, "ppl": 268.516, "lr": 0.0015, "grad": 0.1416, "tokens_seen": 649799680, "compute_tokens": 649799680, "tok_s": 363580.8, "tst_active": true}
|
| 65 |
+
{"step": 1260, "epoch": 0.009, "loss": 5.77187, "ppl": 321.136, "lr": 0.0015, "grad": 0.2631, "tokens_seen": 660280320, "compute_tokens": 660280320, "tok_s": 363063.0, "tst_active": true}
|
| 66 |
+
{"step": 1280, "epoch": 0.009, "loss": 5.46728, "ppl": 236.816, "lr": 0.0015, "grad": 3.1426, "tokens_seen": 670760960, "compute_tokens": 670760960, "tok_s": 362663.9, "tst_active": true}
|
| 67 |
+
{"step": 1300, "epoch": 0.009, "loss": 5.4096, "ppl": 223.542, "lr": 0.0015, "grad": 0.4534, "tokens_seen": 681241600, "compute_tokens": 681241600, "tok_s": 363761.1, "tst_active": true}
|
| 68 |
+
{"step": 1320, "epoch": 0.009, "loss": 5.59035, "ppl": 267.83, "lr": 0.0015, "grad": 0.9101, "tokens_seen": 691722240, "compute_tokens": 691722240, "tok_s": 362364.8, "tst_active": true}
|
| 69 |
+
{"step": 1340, "epoch": 0.009, "loss": 5.55075, "ppl": 257.431, "lr": 0.0015, "grad": 0.2858, "tokens_seen": 702202880, "compute_tokens": 702202880, "tok_s": 362063.0, "tst_active": true}
|
| 70 |
+
{"step": 1360, "epoch": 0.009, "loss": 5.47996, "ppl": 239.837, "lr": 0.0015, "grad": 0.5854, "tokens_seen": 712683520, "compute_tokens": 712683520, "tok_s": 364405.9, "tst_active": true}
|
| 71 |
+
{"step": 1380, "epoch": 0.009, "loss": 5.51339, "ppl": 247.99, "lr": 0.0015, "grad": 0.2776, "tokens_seen": 723164160, "compute_tokens": 723164160, "tok_s": 362449.6, "tst_active": true}
|
| 72 |
+
{"step": 1400, "epoch": 0.01, "loss": 5.48137, "ppl": 240.177, "lr": 0.0015, "grad": 0.3711, "tokens_seen": 733644800, "compute_tokens": 733644800, "tok_s": 357981.3, "tst_active": true}
|
| 73 |
+
{"step": 1420, "epoch": 0.01, "loss": 5.44651, "ppl": 231.948, "lr": 0.0015, "grad": 0.5624, "tokens_seen": 744125440, "compute_tokens": 744125440, "tok_s": 362019.1, "tst_active": true}
|
| 74 |
+
{"step": 1440, "epoch": 0.01, "loss": 5.45481, "ppl": 233.88, "lr": 0.0015, "grad": 0.4203, "tokens_seen": 754606080, "compute_tokens": 754606080, "tok_s": 361546.4, "tst_active": true}
|
| 75 |
+
{"step": 1460, "epoch": 0.01, "loss": 5.54626, "ppl": 256.278, "lr": 0.0015, "grad": 0.34, "tokens_seen": 765086720, "compute_tokens": 765086720, "tok_s": 362246.8, "tst_active": true}
|
| 76 |
+
{"step": 1480, "epoch": 0.01, "loss": 5.41832, "ppl": 225.499, "lr": 0.0015, "grad": 0.1822, "tokens_seen": 775567360, "compute_tokens": 775567360, "tok_s": 362181.4, "tst_active": true}
|
| 77 |
+
{"step": 1500, "epoch": 0.01, "loss": 5.52656, "ppl": 251.278, "lr": 0.0015, "grad": 0.2038, "tokens_seen": 786048000, "compute_tokens": 786048000, "tok_s": 361017.4, "tst_active": true}
|
| 78 |
+
{"step": 1520, "epoch": 0.01, "loss": 5.58122, "ppl": 265.395, "lr": 0.0015, "grad": 0.283, "tokens_seen": 796528640, "compute_tokens": 796528640, "tok_s": 362885.9, "tst_active": true}
|
| 79 |
+
{"step": 1540, "epoch": 0.011, "loss": 5.60232, "ppl": 271.054, "lr": 0.0015, "grad": 0.2532, "tokens_seen": 807009280, "compute_tokens": 807009280, "tok_s": 361899.0, "tst_active": true}
|
| 80 |
+
{"step": 1560, "epoch": 0.011, "loss": 5.5824, "ppl": 265.709, "lr": 0.0015, "grad": 0.1281, "tokens_seen": 817489920, "compute_tokens": 817489920, "tok_s": 362951.0, "tst_active": true}
|
| 81 |
+
{"step": 1580, "epoch": 0.011, "loss": 5.67848, "ppl": 292.504, "lr": 0.0015, "grad": 0.7378, "tokens_seen": 827970560, "compute_tokens": 827970560, "tok_s": 360498.0, "tst_active": true}
|
| 82 |
+
{"step": 1600, "epoch": 0.011, "loss": 5.16443, "ppl": 174.938, "lr": 0.0015, "grad": 0.3275, "tokens_seen": 838451200, "compute_tokens": 838451200, "tok_s": 362252.4, "tst_active": true}
|
| 83 |
+
{"step": 1620, "epoch": 0.011, "loss": 5.26487, "ppl": 193.422, "lr": 0.0015, "grad": 0.1782, "tokens_seen": 848931840, "compute_tokens": 848931840, "tok_s": 365443.8, "tst_active": true}
|
| 84 |
+
{"step": 1640, "epoch": 0.011, "loss": 5.52914, "ppl": 251.927, "lr": 0.0015, "grad": 0.2138, "tokens_seen": 859412480, "compute_tokens": 859412480, "tok_s": 362118.7, "tst_active": true}
|
| 85 |
+
{"step": 1660, "epoch": 0.011, "loss": 5.37378, "ppl": 215.676, "lr": 0.0015, "grad": 0.2489, "tokens_seen": 869893120, "compute_tokens": 869893120, "tok_s": 360132.7, "tst_active": true}
|
| 86 |
+
{"step": 1680, "epoch": 0.012, "loss": 5.46433, "ppl": 236.117, "lr": 0.0015, "grad": 0.3715, "tokens_seen": 880373760, "compute_tokens": 880373760, "tok_s": 361831.8, "tst_active": true}
|
| 87 |
+
{"step": 1700, "epoch": 0.012, "loss": 5.3338, "ppl": 207.223, "lr": 0.0015, "grad": 0.2386, "tokens_seen": 890854400, "compute_tokens": 890854400, "tok_s": 362939.1, "tst_active": true}
|
| 88 |
+
{"step": 1720, "epoch": 0.012, "loss": 5.3892, "ppl": 219.029, "lr": 0.0015, "grad": 0.4088, "tokens_seen": 901335040, "compute_tokens": 901335040, "tok_s": 362924.7, "tst_active": true}
|
| 89 |
+
{"step": 1740, "epoch": 0.012, "loss": 5.47944, "ppl": 239.712, "lr": 0.0015, "grad": 0.5766, "tokens_seen": 911815680, "compute_tokens": 911815680, "tok_s": 360177.6, "tst_active": true}
|
| 90 |
+
{"step": 1760, "epoch": 0.012, "loss": 5.42217, "ppl": 226.37, "lr": 0.0015, "grad": 0.1079, "tokens_seen": 922296320, "compute_tokens": 922296320, "tok_s": 359252.8, "tst_active": true}
|
| 91 |
+
{"step": 1780, "epoch": 0.012, "loss": 5.49218, "ppl": 242.787, "lr": 0.0015, "grad": 0.3214, "tokens_seen": 932776960, "compute_tokens": 932776960, "tok_s": 362624.9, "tst_active": true}
|
| 92 |
+
{"step": 1800, "epoch": 0.012, "loss": 5.47403, "ppl": 238.418, "lr": 0.0015, "grad": 0.4808, "tokens_seen": 943257600, "compute_tokens": 943257600, "tok_s": 361009.3, "tst_active": true}
|
| 93 |
+
{"step": 1820, "epoch": 0.013, "loss": 5.49937, "ppl": 244.537, "lr": 0.0015, "grad": 0.6007, "tokens_seen": 953738240, "compute_tokens": 953738240, "tok_s": 363022.1, "tst_active": true}
|
| 94 |
+
{"step": 1840, "epoch": 0.013, "loss": 4.97601, "ppl": 144.896, "lr": 0.0015, "grad": 0.5799, "tokens_seen": 964218880, "compute_tokens": 964218880, "tok_s": 362208.6, "tst_active": true}
|
| 95 |
+
{"step": 1860, "epoch": 0.013, "loss": 5.38394, "ppl": 217.879, "lr": 0.0015, "grad": 0.5928, "tokens_seen": 974699520, "compute_tokens": 974699520, "tok_s": 351141.7, "tst_active": true}
|
| 96 |
+
{"step": 1880, "epoch": 0.013, "loss": 5.40321, "ppl": 222.118, "lr": 0.0015, "grad": 0.1478, "tokens_seen": 985180160, "compute_tokens": 985180160, "tok_s": 360419.7, "tst_active": true}
|
| 97 |
+
{"step": 1900, "epoch": 0.013, "loss": 5.43286, "ppl": 228.802, "lr": 0.0015, "grad": 0.443, "tokens_seen": 995660800, "compute_tokens": 995660800, "tok_s": 360448.9, "tst_active": true}
|
| 98 |
+
{"step": 1920, "epoch": 0.013, "loss": 5.45171, "ppl": 233.157, "lr": 0.0015, "grad": 1.3152, "tokens_seen": 1006141440, "compute_tokens": 1006141440, "tok_s": 360607.8, "tst_active": true}
|
| 99 |
+
{"step": 1940, "epoch": 0.013, "loss": 5.45017, "ppl": 232.798, "lr": 0.0015, "grad": 0.5616, "tokens_seen": 1016622080, "compute_tokens": 1016622080, "tok_s": 360446.2, "tst_active": true}
|
| 100 |
+
{"step": 1960, "epoch": 0.013, "loss": 5.45519, "ppl": 233.969, "lr": 0.0015, "grad": 0.1549, "tokens_seen": 1027102720, "compute_tokens": 1027102720, "tok_s": 361387.9, "tst_active": true}
|
| 101 |
+
{"step": 1980, "epoch": 0.014, "loss": 5.50408, "ppl": 245.692, "lr": 0.0015, "grad": 0.6849, "tokens_seen": 1037583360, "compute_tokens": 1037583360, "tok_s": 363184.3, "tst_active": true}
|
| 102 |
+
{"step": 2000, "epoch": 0.014, "loss": 5.45922, "ppl": 234.914, "lr": 0.0015, "grad": 1.2663, "tokens_seen": 1048064000, "compute_tokens": 1048064000, "tok_s": 363833.6, "tst_active": true}
|
| 103 |
+
{"step": 2020, "epoch": 0.014, "loss": 5.50787, "ppl": 246.625, "lr": 0.0015, "grad": 0.1088, "tokens_seen": 1058544640, "compute_tokens": 1058544640, "tok_s": 363038.0, "tst_active": true}
|
| 104 |
+
{"step": 2040, "epoch": 0.014, "loss": 5.62053, "ppl": 276.035, "lr": 0.0015, "grad": 0.2907, "tokens_seen": 1069025280, "compute_tokens": 1069025280, "tok_s": 360287.0, "tst_active": true}
|
| 105 |
+
{"step": 2060, "epoch": 0.014, "loss": 5.33567, "ppl": 207.612, "lr": 0.0015, "grad": 0.2077, "tokens_seen": 1079505920, "compute_tokens": 1079505920, "tok_s": 363914.6, "tst_active": true}
|
| 106 |
+
{"step": 2080, "epoch": 0.014, "loss": 5.37397, "ppl": 215.717, "lr": 0.0015, "grad": 0.3789, "tokens_seen": 1089986560, "compute_tokens": 1089986560, "tok_s": 363620.8, "tst_active": true}
|
| 107 |
+
{"step": 2100, "epoch": 0.014, "loss": 5.48096, "ppl": 240.076, "lr": 0.0015, "grad": 0.7131, "tokens_seen": 1100467200, "compute_tokens": 1100467200, "tok_s": 348316.1, "tst_active": true}
|
| 108 |
+
{"step": 2120, "epoch": 0.015, "loss": 5.48437, "ppl": 240.898, "lr": 0.0015, "grad": 0.3892, "tokens_seen": 1110947840, "compute_tokens": 1110947840, "tok_s": 362214.3, "tst_active": true}
|
| 109 |
+
{"step": 2140, "epoch": 0.015, "loss": 5.42775, "ppl": 227.636, "lr": 0.0015, "grad": 0.3994, "tokens_seen": 1121428480, "compute_tokens": 1121428480, "tok_s": 356656.9, "tst_active": true}
|
| 110 |
+
{"step": 2160, "epoch": 0.015, "loss": 5.2793, "ppl": 196.233, "lr": 0.0015, "grad": 0.2052, "tokens_seen": 1131909120, "compute_tokens": 1131909120, "tok_s": 362890.7, "tst_active": true}
|
| 111 |
+
{"step": 2180, "epoch": 0.015, "loss": 5.51461, "ppl": 248.293, "lr": 0.0015, "grad": 0.3878, "tokens_seen": 1142389760, "compute_tokens": 1142389760, "tok_s": 360027.4, "tst_active": true}
|
| 112 |
+
{"step": 2200, "epoch": 0.015, "loss": 5.32245, "ppl": 204.886, "lr": 0.0015, "grad": 0.4049, "tokens_seen": 1152870400, "compute_tokens": 1152870400, "tok_s": 363769.6, "tst_active": true}
|
| 113 |
+
{"step": 2220, "epoch": 0.015, "loss": 5.29594, "ppl": 199.526, "lr": 0.0015, "grad": 0.2716, "tokens_seen": 1163351040, "compute_tokens": 1163351040, "tok_s": 363721.1, "tst_active": true}
|
| 114 |
+
{"step": 2240, "epoch": 0.015, "loss": 5.47412, "ppl": 238.442, "lr": 0.0015, "grad": 0.7071, "tokens_seen": 1173831680, "compute_tokens": 1173831680, "tok_s": 356797.3, "tst_active": true}
|
| 115 |
+
{"step": 2260, "epoch": 0.016, "loss": 5.33082, "ppl": 206.606, "lr": 0.0015, "grad": 0.2618, "tokens_seen": 1184312320, "compute_tokens": 1184312320, "tok_s": 362744.9, "tst_active": true}
|
| 116 |
+
{"step": 2280, "epoch": 0.016, "loss": 5.42538, "ppl": 227.098, "lr": 0.0015, "grad": 0.1796, "tokens_seen": 1194792960, "compute_tokens": 1194792960, "tok_s": 362581.0, "tst_active": true}
|
| 117 |
+
{"step": 2300, "epoch": 0.016, "loss": 5.32904, "ppl": 206.241, "lr": 0.0015, "grad": 0.4772, "tokens_seen": 1205273600, "compute_tokens": 1205273600, "tok_s": 364377.7, "tst_active": true}
|
| 118 |
+
{"step": 2320, "epoch": 0.016, "loss": 5.52391, "ppl": 250.612, "lr": 0.0015, "grad": 0.3231, "tokens_seen": 1215754240, "compute_tokens": 1215754240, "tok_s": 362168.7, "tst_active": true}
|
| 119 |
+
{"step": 2340, "epoch": 0.016, "loss": 5.47748, "ppl": 239.243, "lr": 0.0015, "grad": 0.2051, "tokens_seen": 1226234880, "compute_tokens": 1226234880, "tok_s": 361610.2, "tst_active": true}
|
| 120 |
+
{"step": 2360, "epoch": 0.016, "loss": 5.41183, "ppl": 224.042, "lr": 0.0015, "grad": 0.207, "tokens_seen": 1236715520, "compute_tokens": 1236715520, "tok_s": 362178.9, "tst_active": true}
|
| 121 |
+
{"step": 2380, "epoch": 0.016, "loss": 5.35518, "ppl": 211.702, "lr": 0.0015, "grad": 0.5015, "tokens_seen": 1247196160, "compute_tokens": 1247196160, "tok_s": 362815.0, "tst_active": true}
|
| 122 |
+
{"step": 2400, "epoch": 0.016, "loss": 5.3815, "ppl": 217.348, "lr": 0.0015, "grad": 0.5423, "tokens_seen": 1257676800, "compute_tokens": 1257676800, "tok_s": 355770.8, "tst_active": true}
|
| 123 |
+
{"step": 2420, "epoch": 0.017, "loss": 5.42714, "ppl": 227.498, "lr": 0.0015, "grad": 0.6616, "tokens_seen": 1268157440, "compute_tokens": 1268157440, "tok_s": 365433.0, "tst_active": true}
|
| 124 |
+
{"step": 2440, "epoch": 0.017, "loss": 5.24015, "ppl": 188.699, "lr": 0.0015, "grad": 0.2739, "tokens_seen": 1278638080, "compute_tokens": 1278638080, "tok_s": 351995.3, "tst_active": true}
|
| 125 |
+
{"step": 2460, "epoch": 0.017, "loss": 5.31539, "ppl": 203.445, "lr": 0.0015, "grad": 0.4613, "tokens_seen": 1289118720, "compute_tokens": 1289118720, "tok_s": 363050.1, "tst_active": true}
|
| 126 |
+
{"step": 2480, "epoch": 0.017, "loss": 5.38802, "ppl": 218.769, "lr": 0.0015, "grad": 0.1184, "tokens_seen": 1299599360, "compute_tokens": 1299599360, "tok_s": 362657.2, "tst_active": true}
|
| 127 |
+
{"step": 2500, "epoch": 0.017, "loss": 5.39479, "ppl": 220.257, "lr": 0.0015, "grad": 0.2852, "tokens_seen": 1310080000, "compute_tokens": 1310080000, "tok_s": 363754.1, "tst_active": true}
|
| 128 |
+
{"step": 2520, "epoch": 0.017, "loss": 5.29093, "ppl": 198.527, "lr": 0.0015, "grad": 0.1254, "tokens_seen": 1320560640, "compute_tokens": 1320560640, "tok_s": 361391.0, "tst_active": true}
|
| 129 |
+
{"step": 2540, "epoch": 0.017, "loss": 5.31738, "ppl": 203.85, "lr": 0.0015, "grad": 0.8208, "tokens_seen": 1331041280, "compute_tokens": 1331041280, "tok_s": 363774.6, "tst_active": true}
|
| 130 |
+
{"step": 2560, "epoch": 0.018, "loss": 5.40668, "ppl": 222.89, "lr": 0.0015, "grad": 0.5788, "tokens_seen": 1341521920, "compute_tokens": 1341521920, "tok_s": 361554.9, "tst_active": true}
|
| 131 |
+
{"step": 2580, "epoch": 0.018, "loss": 5.31782, "ppl": 203.938, "lr": 0.0015, "grad": 0.1823, "tokens_seen": 1352002560, "compute_tokens": 1352002560, "tok_s": 363164.8, "tst_active": true}
|
| 132 |
+
{"step": 2600, "epoch": 0.018, "loss": 5.43878, "ppl": 230.161, "lr": 0.0015, "grad": 0.1113, "tokens_seen": 1362483200, "compute_tokens": 1362483200, "tok_s": 363524.1, "tst_active": true}
|
| 133 |
+
{"step": 2620, "epoch": 0.018, "loss": 5.46141, "ppl": 235.428, "lr": 0.0015, "grad": 0.1867, "tokens_seen": 1372963840, "compute_tokens": 1372963840, "tok_s": 362521.5, "tst_active": true}
|
| 134 |
+
{"step": 2640, "epoch": 0.018, "loss": 5.34481, "ppl": 209.518, "lr": 0.0015, "grad": 0.1229, "tokens_seen": 1383444480, "compute_tokens": 1383444480, "tok_s": 362115.8, "tst_active": true}
|
| 135 |
+
{"step": 2660, "epoch": 0.018, "loss": 5.27019, "ppl": 194.454, "lr": 0.0015, "grad": 0.155, "tokens_seen": 1393925120, "compute_tokens": 1393925120, "tok_s": 363824.1, "tst_active": true}
|
| 136 |
+
{"step": 2680, "epoch": 0.018, "loss": 5.60831, "ppl": 272.684, "lr": 0.0015, "grad": 0.4101, "tokens_seen": 1404405760, "compute_tokens": 1404405760, "tok_s": 362815.0, "tst_active": true}
|
| 137 |
+
{"step": 2700, "epoch": 0.019, "loss": 5.54719, "ppl": 256.516, "lr": 0.0015, "grad": 0.1979, "tokens_seen": 1414886400, "compute_tokens": 1414886400, "tok_s": 362652.6, "tst_active": true}
|
| 138 |
+
{"step": 2720, "epoch": 0.019, "loss": 5.47467, "ppl": 238.572, "lr": 0.0015, "grad": 0.3248, "tokens_seen": 1425367040, "compute_tokens": 1425367040, "tok_s": 363535.7, "tst_active": true}
|
| 139 |
+
{"step": 2740, "epoch": 0.019, "loss": 5.62949, "ppl": 278.519, "lr": 0.0015, "grad": 0.2004, "tokens_seen": 1435847680, "compute_tokens": 1435847680, "tok_s": 363101.3, "tst_active": true}
|
| 140 |
+
{"step": 2760, "epoch": 0.019, "loss": 5.14415, "ppl": 171.426, "lr": 0.0015, "grad": 0.6611, "tokens_seen": 1446328320, "compute_tokens": 1446328320, "tok_s": 364797.9, "tst_active": true}
|
| 141 |
+
{"step": 2780, "epoch": 0.019, "loss": 5.33702, "ppl": 207.893, "lr": 0.0015, "grad": 1.1503, "tokens_seen": 1456808960, "compute_tokens": 1456808960, "tok_s": 356605.4, "tst_active": true}
|
| 142 |
+
{"step": 2800, "epoch": 0.019, "loss": 5.3664, "ppl": 214.091, "lr": 0.0015, "grad": 0.4025, "tokens_seen": 1467289600, "compute_tokens": 1467289600, "tok_s": 363931.2, "tst_active": true}
|
| 143 |
+
{"step": 2820, "epoch": 0.019, "loss": 5.11983, "ppl": 167.306, "lr": 0.0015, "grad": 0.1395, "tokens_seen": 1477770240, "compute_tokens": 1477770240, "tok_s": 365785.8, "tst_active": true}
|
| 144 |
+
{"step": 2840, "epoch": 0.02, "loss": 5.32781, "ppl": 205.987, "lr": 0.0015, "grad": 0.1875, "tokens_seen": 1488250880, "compute_tokens": 1488250880, "tok_s": 364543.5, "tst_active": true}
|
| 145 |
+
{"step": 2860, "epoch": 0.02, "loss": 5.27938, "ppl": 196.249, "lr": 0.0015, "grad": 0.329, "tokens_seen": 1498731520, "compute_tokens": 1498731520, "tok_s": 364480.9, "tst_active": true}
|
| 146 |
+
{"step": 2880, "epoch": 0.02, "loss": 5.53234, "ppl": 252.735, "lr": 0.0015, "grad": 0.5546, "tokens_seen": 1509212160, "compute_tokens": 1509212160, "tok_s": 355958.5, "tst_active": true}
|
| 147 |
+
{"step": 2900, "epoch": 0.02, "loss": 5.35683, "ppl": 212.052, "lr": 0.0015, "grad": 0.5495, "tokens_seen": 1519692800, "compute_tokens": 1519692800, "tok_s": 363268.7, "tst_active": true}
|
| 148 |
+
{"step": 2920, "epoch": 0.02, "loss": 5.43629, "ppl": 229.589, "lr": 0.0015, "grad": 0.1549, "tokens_seen": 1530173440, "compute_tokens": 1530173440, "tok_s": 364799.8, "tst_active": true}
|
| 149 |
+
{"step": 2940, "epoch": 0.02, "loss": 5.2327, "ppl": 187.298, "lr": 0.0015, "grad": 0.1609, "tokens_seen": 1540654080, "compute_tokens": 1540654080, "tok_s": 362330.4, "tst_active": true}
|
| 150 |
+
{"step": 2960, "epoch": 0.02, "loss": 5.65719, "ppl": 286.342, "lr": 0.0015, "grad": 0.7793, "tokens_seen": 1551134720, "compute_tokens": 1551134720, "tok_s": 365004.3, "tst_active": true}
|
| 151 |
+
{"step": 2980, "epoch": 0.02, "loss": 5.49158, "ppl": 242.641, "lr": 0.0015, "grad": 0.2061, "tokens_seen": 1561615360, "compute_tokens": 1561615360, "tok_s": 364545.2, "tst_active": true}
|
| 152 |
+
{"step": 3000, "epoch": 0.021, "loss": 5.25539, "ppl": 191.596, "lr": 0.0015, "grad": 0.1956, "tokens_seen": 1572096000, "compute_tokens": 1572096000, "tok_s": 364088.6, "tst_active": true}
|
| 153 |
+
{"step": 3020, "epoch": 0.021, "loss": 5.33134, "ppl": 206.714, "lr": 0.0015, "grad": 0.3279, "tokens_seen": 1582576640, "compute_tokens": 1582576640, "tok_s": 362992.6, "tst_active": true}
|
| 154 |
+
{"step": 3040, "epoch": 0.021, "loss": 5.22913, "ppl": 186.63, "lr": 0.0015, "grad": 0.209, "tokens_seen": 1593057280, "compute_tokens": 1593057280, "tok_s": 363050.4, "tst_active": true}
|
| 155 |
+
{"step": 3060, "epoch": 0.021, "loss": 5.49468, "ppl": 243.393, "lr": 0.0015, "grad": 0.1228, "tokens_seen": 1603537920, "compute_tokens": 1603537920, "tok_s": 363645.6, "tst_active": true}
|
| 156 |
+
{"step": 3080, "epoch": 0.021, "loss": 5.46297, "ppl": 235.797, "lr": 0.0015, "grad": 0.8074, "tokens_seen": 1614018560, "compute_tokens": 1614018560, "tok_s": 363095.8, "tst_active": true}
|
| 157 |
+
{"step": 3100, "epoch": 0.021, "loss": 5.42074, "ppl": 226.046, "lr": 0.0015, "grad": 0.336, "tokens_seen": 1624499200, "compute_tokens": 1624499200, "tok_s": 362088.1, "tst_active": true}
|
| 158 |
+
{"step": 3120, "epoch": 0.021, "loss": 5.31863, "ppl": 204.104, "lr": 0.0015, "grad": 0.2692, "tokens_seen": 1634979840, "compute_tokens": 1634979840, "tok_s": 362514.8, "tst_active": true}
|
| 159 |
+
{"step": 3140, "epoch": 0.022, "loss": 5.52612, "ppl": 251.167, "lr": 0.0015, "grad": 0.1465, "tokens_seen": 1645460480, "compute_tokens": 1645460480, "tok_s": 362328.7, "tst_active": true}
|
| 160 |
+
{"step": 3160, "epoch": 0.022, "loss": 5.3025, "ppl": 200.838, "lr": 0.0015, "grad": 0.1309, "tokens_seen": 1655941120, "compute_tokens": 1655941120, "tok_s": 363098.2, "tst_active": true}
|
| 161 |
+
{"step": 3180, "epoch": 0.022, "loss": 5.41334, "ppl": 224.381, "lr": 0.0015, "grad": 0.3508, "tokens_seen": 1666421760, "compute_tokens": 1666421760, "tok_s": 363904.9, "tst_active": true}
|
| 162 |
+
{"step": 3200, "epoch": 0.022, "loss": 5.30068, "ppl": 200.472, "lr": 0.0015, "grad": 0.1053, "tokens_seen": 1676902400, "compute_tokens": 1676902400, "tok_s": 360739.5, "tst_active": true}
|
| 163 |
+
{"step": 3220, "epoch": 0.022, "loss": 5.35696, "ppl": 212.08, "lr": 0.0015, "grad": 0.6524, "tokens_seen": 1687383040, "compute_tokens": 1687383040, "tok_s": 357174.4, "tst_active": true}
|
| 164 |
+
{"step": 3240, "epoch": 0.022, "loss": 5.35605, "ppl": 211.887, "lr": 0.0015, "grad": 0.1061, "tokens_seen": 1697863680, "compute_tokens": 1697863680, "tok_s": 362416.3, "tst_active": true}
|
| 165 |
+
{"step": 3260, "epoch": 0.022, "loss": 5.08629, "ppl": 161.788, "lr": 0.0015, "grad": 0.1888, "tokens_seen": 1708344320, "compute_tokens": 1708344320, "tok_s": 362771.5, "tst_active": true}
|
| 166 |
+
{"step": 3280, "epoch": 0.023, "loss": 5.1554, "ppl": 173.366, "lr": 0.0015, "grad": 0.9456, "tokens_seen": 1718824960, "compute_tokens": 1718824960, "tok_s": 364356.5, "tst_active": true}
|
| 167 |
+
{"step": 3300, "epoch": 0.023, "loss": 5.30645, "ppl": 201.633, "lr": 0.0015, "grad": 0.2248, "tokens_seen": 1729305600, "compute_tokens": 1729305600, "tok_s": 364246.8, "tst_active": true}
|
| 168 |
+
{"step": 3320, "epoch": 0.023, "loss": 5.38753, "ppl": 218.662, "lr": 0.0015, "grad": 0.4787, "tokens_seen": 1739786240, "compute_tokens": 1739786240, "tok_s": 364593.8, "tst_active": true}
|
| 169 |
+
{"step": 3340, "epoch": 0.023, "loss": 5.38224, "ppl": 217.508, "lr": 0.0015, "grad": 0.2144, "tokens_seen": 1750266880, "compute_tokens": 1750266880, "tok_s": 357965.4, "tst_active": true}
|
| 170 |
+
{"step": 3360, "epoch": 0.023, "loss": 5.42481, "ppl": 226.967, "lr": 0.0015, "grad": 0.1612, "tokens_seen": 1760747520, "compute_tokens": 1760747520, "tok_s": 355401.1, "tst_active": true}
|
| 171 |
+
{"step": 3380, "epoch": 0.023, "loss": 5.32931, "ppl": 206.295, "lr": 0.0015, "grad": 0.2442, "tokens_seen": 1771228160, "compute_tokens": 1771228160, "tok_s": 364282.0, "tst_active": true}
|
| 172 |
+
{"step": 3400, "epoch": 0.023, "loss": 5.30398, "ppl": 201.136, "lr": 0.0015, "grad": 0.1876, "tokens_seen": 1781708800, "compute_tokens": 1781708800, "tok_s": 364835.7, "tst_active": true}
|
| 173 |
+
{"step": 3420, "epoch": 0.024, "loss": 5.1871, "ppl": 178.949, "lr": 0.0015, "grad": 0.2084, "tokens_seen": 1792189440, "compute_tokens": 1792189440, "tok_s": 364986.6, "tst_active": true}
|
| 174 |
+
{"step": 3440, "epoch": 0.024, "loss": 5.28748, "ppl": 197.845, "lr": 0.0015, "grad": 0.2739, "tokens_seen": 1802670080, "compute_tokens": 1802670080, "tok_s": 364167.5, "tst_active": true}
|
| 175 |
+
{"step": 3460, "epoch": 0.024, "loss": 5.18852, "ppl": 179.202, "lr": 0.0015, "grad": 0.3206, "tokens_seen": 1813150720, "compute_tokens": 1813150720, "tok_s": 363796.2, "tst_active": true}
|
| 176 |
+
{"step": 3480, "epoch": 0.024, "loss": 5.26134, "ppl": 192.739, "lr": 0.0015, "grad": 0.1391, "tokens_seen": 1823631360, "compute_tokens": 1823631360, "tok_s": 364366.0, "tst_active": true}
|
| 177 |
+
{"step": 3500, "epoch": 0.024, "loss": 5.25643, "ppl": 191.796, "lr": 0.0015, "grad": 0.1921, "tokens_seen": 1834112000, "compute_tokens": 1834112000, "tok_s": 362809.9, "tst_active": true}
|
| 178 |
+
{"step": 3520, "epoch": 0.024, "loss": 5.40236, "ppl": 221.93, "lr": 0.0015, "grad": 0.9235, "tokens_seen": 1844592640, "compute_tokens": 1844592640, "tok_s": 360176.3, "tst_active": true}
|
| 179 |
+
{"step": 3540, "epoch": 0.024, "loss": 5.18295, "ppl": 178.207, "lr": 0.0015, "grad": 0.5877, "tokens_seen": 1855073280, "compute_tokens": 1855073280, "tok_s": 363385.3, "tst_active": true}
|
| 180 |
+
{"step": 3560, "epoch": 0.024, "loss": 5.42327, "ppl": 226.62, "lr": 0.0015, "grad": 0.4581, "tokens_seen": 1865553920, "compute_tokens": 1865553920, "tok_s": 362647.2, "tst_active": true}
|
| 181 |
+
{"step": 3580, "epoch": 0.025, "loss": 5.44008, "ppl": 230.46, "lr": 0.0015, "grad": 0.6363, "tokens_seen": 1876034560, "compute_tokens": 1876034560, "tok_s": 362608.6, "tst_active": true}
|
| 182 |
+
{"step": 3600, "epoch": 0.025, "loss": 5.22402, "ppl": 185.678, "lr": 0.0015, "grad": 0.1084, "tokens_seen": 1886515200, "compute_tokens": 1886515200, "tok_s": 363957.6, "tst_active": true}
|
| 183 |
+
{"step": 3620, "epoch": 0.025, "loss": 5.15803, "ppl": 173.822, "lr": 0.0015, "grad": 0.1256, "tokens_seen": 1896995840, "compute_tokens": 1896995840, "tok_s": 365168.1, "tst_active": true}
|
| 184 |
+
{"step": 3640, "epoch": 0.025, "loss": 5.42522, "ppl": 227.062, "lr": 0.0015, "grad": 0.246, "tokens_seen": 1907476480, "compute_tokens": 1907476480, "tok_s": 363874.3, "tst_active": true}
|
| 185 |
+
{"step": 3660, "epoch": 0.025, "loss": 5.38789, "ppl": 218.742, "lr": 0.0015, "grad": 0.1694, "tokens_seen": 1917957120, "compute_tokens": 1917957120, "tok_s": 363655.9, "tst_active": true}
|
| 186 |
+
{"step": 3680, "epoch": 0.025, "loss": 5.21578, "ppl": 184.156, "lr": 0.0015, "grad": 0.2505, "tokens_seen": 1928437760, "compute_tokens": 1928437760, "tok_s": 364469.5, "tst_active": true}
|
| 187 |
+
{"step": 3700, "epoch": 0.025, "loss": 5.28406, "ppl": 197.169, "lr": 0.0015, "grad": 0.1262, "tokens_seen": 1938918400, "compute_tokens": 1938918400, "tok_s": 350412.5, "tst_active": true}
|
| 188 |
+
{"step": 3720, "epoch": 0.026, "loss": 5.27492, "ppl": 195.375, "lr": 0.0015, "grad": 0.1023, "tokens_seen": 1949399040, "compute_tokens": 1949399040, "tok_s": 363810.9, "tst_active": true}
|
| 189 |
+
{"step": 3740, "epoch": 0.026, "loss": 5.24039, "ppl": 188.743, "lr": 0.0015, "grad": 0.235, "tokens_seen": 1959879680, "compute_tokens": 1959879680, "tok_s": 364457.9, "tst_active": true}
|
| 190 |
+
{"step": 3760, "epoch": 0.026, "loss": 5.29005, "ppl": 198.352, "lr": 0.0015, "grad": 0.224, "tokens_seen": 1970360320, "compute_tokens": 1970360320, "tok_s": 363859.3, "tst_active": true}
|
| 191 |
+
{"step": 3780, "epoch": 0.026, "loss": 5.50854, "ppl": 246.789, "lr": 0.0015, "grad": 0.5269, "tokens_seen": 1980840960, "compute_tokens": 1980840960, "tok_s": 362399.6, "tst_active": true}
|
| 192 |
+
{"step": 3800, "epoch": 0.026, "loss": 5.37668, "ppl": 216.302, "lr": 0.0015, "grad": 0.0988, "tokens_seen": 1991321600, "compute_tokens": 1991321600, "tok_s": 364231.3, "tst_active": true}
|
| 193 |
+
{"step": 3820, "epoch": 0.026, "loss": 5.10275, "ppl": 164.473, "lr": 0.0015, "grad": 0.1358, "tokens_seen": 2001802240, "compute_tokens": 2001802240, "tok_s": 364480.3, "tst_active": true}
|
| 194 |
+
{"step": 3840, "epoch": 0.026, "loss": 5.28336, "ppl": 197.031, "lr": 0.0015, "grad": 0.1566, "tokens_seen": 2012282880, "compute_tokens": 2012282880, "tok_s": 361313.0, "tst_active": true}
|
| 195 |
+
{"step": 3860, "epoch": 0.027, "loss": 5.34159, "ppl": 208.845, "lr": 0.0015, "grad": 0.2796, "tokens_seen": 2022763520, "compute_tokens": 2022763520, "tok_s": 357276.1, "tst_active": true}
|
| 196 |
+
{"step": 3880, "epoch": 0.027, "loss": 5.02598, "ppl": 152.32, "lr": 0.0015, "grad": 1.2289, "tokens_seen": 2033244160, "compute_tokens": 2033244160, "tok_s": 364395.9, "tst_active": true}
|
| 197 |
+
{"step": 3900, "epoch": 0.027, "loss": 5.27053, "ppl": 194.52, "lr": 0.0015, "grad": 0.1653, "tokens_seen": 2043724800, "compute_tokens": 2043724800, "tok_s": 363484.0, "tst_active": true}
|
| 198 |
+
{"step": 3920, "epoch": 0.027, "loss": 5.23703, "ppl": 188.111, "lr": 0.0015, "grad": 0.1235, "tokens_seen": 2054205440, "compute_tokens": 2054205440, "tok_s": 363468.7, "tst_active": true}
|
| 199 |
+
{"step": 3940, "epoch": 0.027, "loss": 5.2345, "ppl": 187.635, "lr": 0.0015, "grad": 0.2059, "tokens_seen": 2064686080, "compute_tokens": 2064686080, "tok_s": 363271.9, "tst_active": true}
|
| 200 |
+
{"step": 3960, "epoch": 0.027, "loss": 5.56395, "ppl": 260.851, "lr": 0.0015, "grad": 0.3107, "tokens_seen": 2075166720, "compute_tokens": 2075166720, "tok_s": 361661.3, "tst_active": true}
|
| 201 |
+
{"step": 3980, "epoch": 0.027, "loss": 5.3726, "ppl": 215.422, "lr": 0.0015, "grad": 0.6971, "tokens_seen": 2085647360, "compute_tokens": 2085647360, "tok_s": 359669.1, "tst_active": true}
|
| 202 |
+
{"step": 4000, "epoch": 0.027, "loss": 5.30134, "ppl": 200.605, "lr": 0.0015, "grad": 0.1171, "tokens_seen": 2096128000, "compute_tokens": 2096128000, "tok_s": 358449.0, "tst_active": true}
|
| 203 |
+
{"step": 4020, "epoch": 0.028, "loss": 5.26127, "ppl": 192.726, "lr": 0.0015, "grad": 0.5156, "tokens_seen": 2106608640, "compute_tokens": 2106608640, "tok_s": 353517.9, "tst_active": true}
|
| 204 |
+
{"step": 4040, "epoch": 0.028, "loss": 5.08324, "ppl": 161.296, "lr": 0.0015, "grad": 0.2116, "tokens_seen": 2117089280, "compute_tokens": 2117089280, "tok_s": 350195.1, "tst_active": true}
|
| 205 |
+
{"step": 4060, "epoch": 0.028, "loss": 4.96377, "ppl": 143.133, "lr": 0.0015, "grad": 0.4604, "tokens_seen": 2127569920, "compute_tokens": 2127569920, "tok_s": 358450.5, "tst_active": true}
|
| 206 |
+
{"step": 4080, "epoch": 0.028, "loss": 5.27547, "ppl": 195.483, "lr": 0.0015, "grad": 0.1229, "tokens_seen": 2138050560, "compute_tokens": 2138050560, "tok_s": 361296.8, "tst_active": true}
|
| 207 |
+
{"step": 4100, "epoch": 0.028, "loss": 5.25727, "ppl": 191.956, "lr": 0.0015, "grad": 0.564, "tokens_seen": 2148531200, "compute_tokens": 2148531200, "tok_s": 359291.5, "tst_active": true}
|
| 208 |
+
{"step": 4120, "epoch": 0.028, "loss": 5.29202, "ppl": 198.744, "lr": 0.0015, "grad": 0.1231, "tokens_seen": 2159011840, "compute_tokens": 2159011840, "tok_s": 361537.8, "tst_active": true}
|
| 209 |
+
{"step": 4140, "epoch": 0.028, "loss": 5.29388, "ppl": 199.115, "lr": 0.0015, "grad": 0.0966, "tokens_seen": 2169492480, "compute_tokens": 2169492480, "tok_s": 360473.0, "tst_active": true}
|
| 210 |
+
{"step": 4160, "epoch": 0.029, "loss": 5.39173, "ppl": 219.583, "lr": 0.0015, "grad": 0.2496, "tokens_seen": 2179973120, "compute_tokens": 2179973120, "tok_s": 359705.0, "tst_active": true}
|
| 211 |
+
{"step": 4180, "epoch": 0.029, "loss": 5.27798, "ppl": 195.973, "lr": 0.0015, "grad": 0.838, "tokens_seen": 2190453760, "compute_tokens": 2190453760, "tok_s": 364499.4, "tst_active": true}
|
| 212 |
+
{"step": 4200, "epoch": 0.029, "loss": 5.30161, "ppl": 200.659, "lr": 0.0015, "grad": 0.136, "tokens_seen": 2200934400, "compute_tokens": 2200934400, "tok_s": 362413.7, "tst_active": true}
|
| 213 |
+
{"step": 4220, "epoch": 0.029, "loss": 5.25833, "ppl": 192.161, "lr": 0.0015, "grad": 0.1262, "tokens_seen": 2211415040, "compute_tokens": 2211415040, "tok_s": 363797.3, "tst_active": true}
|
| 214 |
+
{"step": 4240, "epoch": 0.029, "loss": 5.31359, "ppl": 203.078, "lr": 0.0015, "grad": 0.5668, "tokens_seen": 2221895680, "compute_tokens": 2221895680, "tok_s": 362378.4, "tst_active": true}
|
| 215 |
+
{"step": 4260, "epoch": 0.029, "loss": 5.27258, "ppl": 194.919, "lr": 0.0015, "grad": 0.1056, "tokens_seen": 2232376320, "compute_tokens": 2232376320, "tok_s": 362211.6, "tst_active": true}
|
| 216 |
+
{"step": 4280, "epoch": 0.029, "loss": 5.22692, "ppl": 186.219, "lr": 0.0015, "grad": 0.1092, "tokens_seen": 2242856960, "compute_tokens": 2242856960, "tok_s": 363084.8, "tst_active": true}
|
| 217 |
+
{"step": 4300, "epoch": 0.03, "loss": 5.57612, "ppl": 264.046, "lr": 0.0015, "grad": 0.134, "tokens_seen": 2253337600, "compute_tokens": 2253337600, "tok_s": 364143.0, "tst_active": true}
|
| 218 |
+
{"step": 4320, "epoch": 0.03, "loss": 5.24376, "ppl": 189.381, "lr": 0.0015, "grad": 0.21, "tokens_seen": 2263818240, "compute_tokens": 2263818240, "tok_s": 362470.8, "tst_active": true}
|
| 219 |
+
{"step": 4340, "epoch": 0.03, "loss": 5.24677, "ppl": 189.952, "lr": 0.0015, "grad": 0.3023, "tokens_seen": 2274298880, "compute_tokens": 2274298880, "tok_s": 363758.4, "tst_active": true}
|
| 220 |
+
{"step": 4360, "epoch": 0.03, "loss": 5.39981, "ppl": 221.363, "lr": 0.0015, "grad": 0.4637, "tokens_seen": 2284779520, "compute_tokens": 2284779520, "tok_s": 364707.3, "tst_active": true}
|
| 221 |
+
{"step": 4380, "epoch": 0.03, "loss": 5.3747, "ppl": 215.876, "lr": 0.0015, "grad": 0.1138, "tokens_seen": 2295260160, "compute_tokens": 2295260160, "tok_s": 364875.8, "tst_active": true}
|
| 222 |
+
{"step": 4400, "epoch": 0.03, "loss": 5.2988, "ppl": 200.096, "lr": 0.0015, "grad": 0.2773, "tokens_seen": 2305740800, "compute_tokens": 2305740800, "tok_s": 363472.2, "tst_active": true}
|