Log snapshot @ step 2000
Browse files- logs/log_2000.jsonl +102 -0
logs/log_2000.jsonl
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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}
|