ckpt probe_log.jsonl
Browse files- probe_log.jsonl +100 -0
probe_log.jsonl
CHANGED
|
@@ -2599,3 +2599,103 @@
|
|
| 2599 |
{"type": "train", "step": 2598, "loss": 1.01499, "gnorm": 0.2236, "lr": 0.00017887179178800467, "tokens": 9477, "L": 817, "bl2": 10679824, "ckpt_on": false, "samples_seen": 41568, "step_ms": 1740.1, "ts": 1790077693.6, "ema_loss": 1.19498}
|
| 2600 |
{"type": "train", "step": 2599, "loss": 0.9982, "gnorm": 0.1187, "lr": 0.00017870795149472636, "tokens": 10032, "L": 770, "bl2": 9486400, "ckpt_on": false, "samples_seen": 41584, "step_ms": 2209.7, "ts": 1790077696.5, "ema_loss": 1.19104}
|
| 2601 |
{"type": "train", "step": 2600, "loss": 1.05941, "gnorm": 0.2695, "lr": 0.0001785441736843128, "tokens": 10458, "L": 803, "bl2": 10316944, "ckpt_on": false, "samples_seen": 41600, "step_ms": 2446.1, "ts": 1790077699.1, "mem_alloc_gb": 3.71, "mem_reserved_gb": 44.49, "ema_loss": 1.18841}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2599 |
{"type": "train", "step": 2598, "loss": 1.01499, "gnorm": 0.2236, "lr": 0.00017887179178800467, "tokens": 9477, "L": 817, "bl2": 10679824, "ckpt_on": false, "samples_seen": 41568, "step_ms": 1740.1, "ts": 1790077693.6, "ema_loss": 1.19498}
|
| 2600 |
{"type": "train", "step": 2599, "loss": 0.9982, "gnorm": 0.1187, "lr": 0.00017870795149472636, "tokens": 10032, "L": 770, "bl2": 9486400, "ckpt_on": false, "samples_seen": 41584, "step_ms": 2209.7, "ts": 1790077696.5, "ema_loss": 1.19104}
|
| 2601 |
{"type": "train", "step": 2600, "loss": 1.05941, "gnorm": 0.2695, "lr": 0.0001785441736843128, "tokens": 10458, "L": 803, "bl2": 10316944, "ckpt_on": false, "samples_seen": 41600, "step_ms": 2446.1, "ts": 1790077699.1, "mem_alloc_gb": 3.71, "mem_reserved_gb": 44.49, "ema_loss": 1.18841}
|
| 2602 |
+
{"type": "train", "step": 2601, "loss": 1.19265, "gnorm": 0.2314, "lr": 0.00017838045846303786, "tokens": 10101, "L": 854, "bl2": 11669056, "ckpt_on": false, "samples_seen": 41616, "step_ms": 2444.6, "ts": 1790077709.1, "ema_loss": 1.18849}
|
| 2603 |
+
{"type": "train", "step": 2602, "loss": 1.0664, "gnorm": 0.1865, "lr": 0.00017821680593713436, "tokens": 9946, "L": 690, "bl2": 7617600, "ckpt_on": false, "samples_seen": 41632, "step_ms": 1927.0, "ts": 1790077711.1, "ema_loss": 1.18605}
|
| 2604 |
+
{"type": "train", "step": 2603, "loss": 1.06873, "gnorm": 0.1465, "lr": 0.0001780532162127947, "tokens": 10467, "L": 800, "bl2": 10240000, "ckpt_on": false, "samples_seen": 41648, "step_ms": 2332.0, "ts": 1790077714.1, "ema_loss": 1.18371}
|
| 2605 |
+
{"type": "train", "step": 2604, "loss": 1.01723, "gnorm": 0.25, "lr": 0.0001778896893961706, "tokens": 11090, "L": 807, "bl2": 10419984, "ckpt_on": false, "samples_seen": 41664, "step_ms": 2061.4, "ts": 1790077716.3, "ema_loss": 1.18038}
|
| 2606 |
+
{"type": "train", "step": 2605, "loss": 1.06171, "gnorm": 0.3926, "lr": 0.00017772622559337258, "tokens": 8609, "L": 780, "bl2": 9734400, "ckpt_on": false, "samples_seen": 41680, "step_ms": 2233.2, "ts": 1790077718.5, "ema_loss": 1.178}
|
| 2607 |
+
{"type": "train", "step": 2606, "loss": 1.05874, "gnorm": 0.1426, "lr": 0.00017756282491047083, "tokens": 9894, "L": 786, "bl2": 9884736, "ckpt_on": false, "samples_seen": 41696, "step_ms": 2227.5, "ts": 1790077721.4, "ema_loss": 1.17562}
|
| 2608 |
+
{"type": "train", "step": 2607, "loss": 1.13035, "gnorm": 0.2256, "lr": 0.00017739948745349417, "tokens": 9929, "L": 805, "bl2": 10368400, "ckpt_on": false, "samples_seen": 41712, "step_ms": 2308.6, "ts": 1790077723.8, "ema_loss": 1.17471}
|
| 2609 |
+
{"type": "train", "step": 2608, "loss": 1.43204, "gnorm": 0.2041, "lr": 0.00017723621332843033, "tokens": 9831, "L": 854, "bl2": 11669056, "ckpt_on": false, "samples_seen": 41728, "step_ms": 2119.1000000000004, "ts": 1790077726.6, "ema_loss": 1.17986}
|
| 2610 |
+
{"type": "train", "step": 2609, "loss": 1.03256, "gnorm": 0.2539, "lr": 0.00017707300264122633, "tokens": 10746, "L": 857, "bl2": 11751184, "ckpt_on": false, "samples_seen": 41744, "step_ms": 2543.4, "ts": 1790077729.2, "ema_loss": 1.17691}
|
| 2611 |
+
{"type": "train", "step": 2610, "loss": 1.07098, "gnorm": 0.2207, "lr": 0.0001769098554977877, "tokens": 10824, "L": 810, "bl2": 10497600, "ckpt_on": false, "samples_seen": 41760, "step_ms": 2516.5, "ts": 1790077731.8, "ema_loss": 1.17479}
|
| 2612 |
+
{"type": "train", "step": 2611, "loss": 1.46655, "gnorm": 0.3086, "lr": 0.00017674677200397892, "tokens": 8961, "L": 787, "bl2": 9909904, "ckpt_on": false, "samples_seen": 41776, "step_ms": 2435.9, "ts": 1790077740.1, "ema_loss": 1.18063}
|
| 2613 |
+
{"type": "train", "step": 2612, "loss": 1.02802, "gnorm": 0.2734, "lr": 0.00017658375226562313, "tokens": 10131, "L": 770, "bl2": 9486400, "ckpt_on": false, "samples_seen": 41792, "step_ms": 2160.1, "ts": 1790077742.3, "ema_loss": 1.17758}
|
| 2614 |
+
{"type": "train", "step": 2613, "loss": 1.06296, "gnorm": 0.166, "lr": 0.00017642079638850188, "tokens": 9814, "L": 807, "bl2": 10419984, "ckpt_on": false, "samples_seen": 41808, "step_ms": 1667.3, "ts": 1790077744.0, "ema_loss": 1.17529}
|
| 2615 |
+
{"type": "train", "step": 2614, "loss": 1.04524, "gnorm": 0.334, "lr": 0.00017625790447835566, "tokens": 9221, "L": 838, "bl2": 11235904, "ckpt_on": false, "samples_seen": 41824, "step_ms": 1808.9, "ts": 1790077746.4, "ema_loss": 1.17268}
|
| 2616 |
+
{"type": "train", "step": 2615, "loss": 1.0611, "gnorm": 0.1973, "lr": 0.00017609507664088315, "tokens": 10172, "L": 811, "bl2": 10523536, "ckpt_on": false, "samples_seen": 41840, "step_ms": 2559.6, "ts": 1790077749.1, "ema_loss": 1.17045}
|
| 2617 |
+
{"type": "train", "step": 2616, "loss": 1.15872, "gnorm": 0.3047, "lr": 0.00017593231298174172, "tokens": 9509, "L": 788, "bl2": 9935104, "ckpt_on": false, "samples_seen": 41856, "step_ms": 2258.3, "ts": 1790077751.5, "ema_loss": 1.17022}
|
| 2618 |
+
{"type": "train", "step": 2617, "loss": 1.30607, "gnorm": 0.248, "lr": 0.00017576961360654675, "tokens": 10476, "L": 841, "bl2": 11316496, "ckpt_on": false, "samples_seen": 41872, "step_ms": 2547.5, "ts": 1790077754.6, "ema_loss": 1.17294}
|
| 2619 |
+
{"type": "train", "step": 2618, "loss": 1.12319, "gnorm": 0.3105, "lr": 0.0001756069786208721, "tokens": 10710, "L": 832, "bl2": 11075584, "ckpt_on": false, "samples_seen": 41888, "step_ms": 2043.2, "ts": 1790077756.7, "ema_loss": 1.17194}
|
| 2620 |
+
{"type": "train", "step": 2619, "loss": 0.89959, "gnorm": 0.2412, "lr": 0.00017544440813025013, "tokens": 9300, "L": 774, "bl2": 9585216, "ckpt_on": false, "samples_seen": 41904, "step_ms": 2137.3, "ts": 1790077759.4, "ema_loss": 1.16649}
|
| 2621 |
+
{"type": "train", "step": 2620, "loss": 1.10801, "gnorm": 0.2266, "lr": 0.0001752819022401707, "tokens": 9349, "L": 783, "bl2": 9809424, "ckpt_on": false, "samples_seen": 41920, "step_ms": 2143.3, "ts": 1790077761.6, "mem_alloc_gb": 3.71, "mem_reserved_gb": 85.63, "ema_loss": 1.16532}
|
| 2622 |
+
{"type": "train", "step": 2621, "loss": 1.06386, "gnorm": 0.2617, "lr": 0.00017511946105608234, "tokens": 10466, "L": 846, "bl2": 11451456, "ckpt_on": false, "samples_seen": 41936, "step_ms": 2622.6000000000004, "ts": 1790077765.7, "ema_loss": 1.16329}
|
| 2623 |
+
{"type": "train", "step": 2622, "loss": 1.04028, "gnorm": 0.1816, "lr": 0.00017495708468339137, "tokens": 10509, "L": 828, "bl2": 10969344, "ckpt_on": false, "samples_seen": 41952, "step_ms": 2706.1000000000004, "ts": 1790077769.0, "ema_loss": 1.16083}
|
| 2624 |
+
{"type": "train", "step": 2623, "loss": 1.12612, "gnorm": 0.2109, "lr": 0.00017479477322746194, "tokens": 10707, "L": 762, "bl2": 9290304, "ckpt_on": false, "samples_seen": 41968, "step_ms": 2403.0, "ts": 1790077771.4, "ema_loss": 1.16014}
|
| 2625 |
+
{"type": "train", "step": 2624, "loss": 1.01928, "gnorm": 0.1885, "lr": 0.00017463252679361625, "tokens": 10410, "L": 819, "bl2": 10732176, "ckpt_on": false, "samples_seen": 41984, "step_ms": 1695.8, "ts": 1790077773.7, "ema_loss": 1.15732}
|
| 2626 |
+
{"type": "train", "step": 2625, "loss": 1.37596, "gnorm": 0.2109, "lr": 0.0001744703454871342, "tokens": 8584, "L": 801, "bl2": 10265616, "ckpt_on": false, "samples_seen": 42000, "step_ms": 2556.6, "ts": 1790077776.4, "ema_loss": 1.1617}
|
| 2627 |
+
{"type": "train", "step": 2626, "loss": 0.97557, "gnorm": 0.2061, "lr": 0.00017430822941325364, "tokens": 9391, "L": 800, "bl2": 10240000, "ckpt_on": false, "samples_seen": 42016, "step_ms": 2021.6999999999998, "ts": 1790077778.5, "ema_loss": 1.15797}
|
| 2628 |
+
{"type": "train", "step": 2627, "loss": 1.05519, "gnorm": 0.1807, "lr": 0.00017414617867716965, "tokens": 10870, "L": 815, "bl2": 10627600, "ckpt_on": false, "samples_seen": 42032, "step_ms": 2496.8, "ts": 1790077781.6, "ema_loss": 1.15592}
|
| 2629 |
+
{"type": "train", "step": 2628, "loss": 1.19188, "gnorm": 0.1807, "lr": 0.00017398419338403553, "tokens": 10150, "L": 857, "bl2": 11751184, "ckpt_on": false, "samples_seen": 42048, "step_ms": 3021.2, "ts": 1790077784.7, "ema_loss": 1.15664}
|
| 2630 |
+
{"type": "train", "step": 2629, "loss": 1.18625, "gnorm": 0.1777, "lr": 0.00017382227363896163, "tokens": 10296, "L": 825, "bl2": 10890000, "ckpt_on": false, "samples_seen": 42064, "step_ms": 2861.8999999999996, "ts": 1790077788.2, "ema_loss": 1.15723}
|
| 2631 |
+
{"type": "train", "step": 2630, "loss": 0.98018, "gnorm": 0.2041, "lr": 0.00017366041954701571, "tokens": 9756, "L": 806, "bl2": 10394176, "ckpt_on": false, "samples_seen": 42080, "step_ms": 2617.6000000000004, "ts": 1790077790.9, "ema_loss": 1.15369}
|
| 2632 |
+
{"type": "train", "step": 2631, "loss": 0.98853, "gnorm": 0.2578, "lr": 0.0001734986312132235, "tokens": 9360, "L": 772, "bl2": 9535744, "ckpt_on": false, "samples_seen": 42096, "step_ms": 1942.4, "ts": 1790077792.9, "ema_loss": 1.15038}
|
| 2633 |
+
{"type": "train", "step": 2632, "loss": 1.08209, "gnorm": 0.1826, "lr": 0.00017333690874256742, "tokens": 10635, "L": 775, "bl2": 9610000, "ckpt_on": false, "samples_seen": 42112, "step_ms": 2154.6, "ts": 1790077795.9, "ema_loss": 1.14902}
|
| 2634 |
+
{"type": "train", "step": 2633, "loss": 1.11425, "gnorm": 0.2158, "lr": 0.0001731752522399875, "tokens": 10656, "L": 801, "bl2": 10265616, "ckpt_on": false, "samples_seen": 42128, "step_ms": 1715.1, "ts": 1790077797.7, "ema_loss": 1.14832}
|
| 2635 |
+
{"type": "train", "step": 2634, "loss": 1.32838, "gnorm": 0.2891, "lr": 0.00017301366181038098, "tokens": 9647, "L": 839, "bl2": 11262736, "ckpt_on": false, "samples_seen": 42144, "step_ms": 1780.8, "ts": 1790077800.5, "ema_loss": 1.15192}
|
| 2636 |
+
{"type": "train", "step": 2635, "loss": 1.08312, "gnorm": 0.2168, "lr": 0.000172852137558602, "tokens": 10300, "L": 806, "bl2": 10394176, "ckpt_on": false, "samples_seen": 42160, "step_ms": 2457.5, "ts": 1790077803.0, "ema_loss": 1.15055}
|
| 2637 |
+
{"type": "train", "step": 2636, "loss": 1.07277, "gnorm": 0.1787, "lr": 0.00017269067958946194, "tokens": 10148, "L": 847, "bl2": 11478544, "ckpt_on": false, "samples_seen": 42176, "step_ms": 2643.5, "ts": 1790077805.7, "ema_loss": 1.14899}
|
| 2638 |
+
{"type": "train", "step": 2637, "loss": 1.06298, "gnorm": 0.1924, "lr": 0.00017252928800772914, "tokens": 10490, "L": 780, "bl2": 9734400, "ckpt_on": false, "samples_seen": 42192, "step_ms": 2472.8, "ts": 1790077808.8, "ema_loss": 1.14727}
|
| 2639 |
+
{"type": "train", "step": 2638, "loss": 1.08178, "gnorm": 0.1406, "lr": 0.00017236796291812895, "tokens": 10985, "L": 826, "bl2": 10916416, "ckpt_on": false, "samples_seen": 42208, "step_ms": 2612.5, "ts": 1790077811.5, "ema_loss": 1.14596}
|
| 2640 |
+
{"type": "train", "step": 2639, "loss": 1.1695, "gnorm": 0.291, "lr": 0.00017220670442534325, "tokens": 9877, "L": 799, "bl2": 10214416, "ckpt_on": false, "samples_seen": 42224, "step_ms": 2721.6, "ts": 1790077814.8, "ema_loss": 1.14643}
|
| 2641 |
+
{"type": "train", "step": 2640, "loss": 1.26364, "gnorm": 0.2373, "lr": 0.00017204551263401107, "tokens": 9855, "L": 841, "bl2": 11316496, "ckpt_on": false, "samples_seen": 42240, "step_ms": 2164.0, "ts": 1790077817.1, "mem_alloc_gb": 3.71, "mem_reserved_gb": 94.11, "ema_loss": 1.14878}
|
| 2642 |
+
{"type": "train", "step": 2641, "loss": 0.97445, "gnorm": 0.3926, "lr": 0.00017188438764872806, "tokens": 10900, "L": 800, "bl2": 10240000, "ckpt_on": false, "samples_seen": 42256, "step_ms": 2326.0, "ts": 1790077819.5, "ema_loss": 1.14529}
|
| 2643 |
+
{"type": "train", "step": 2642, "loss": 0.98878, "gnorm": 0.207, "lr": 0.00017172332957404629, "tokens": 9809, "L": 777, "bl2": 9659664, "ckpt_on": false, "samples_seen": 42272, "step_ms": 2648.2, "ts": 1790077822.8, "ema_loss": 1.14216}
|
| 2644 |
+
{"type": "train", "step": 2643, "loss": 1.25698, "gnorm": 0.2197, "lr": 0.00017156233851447472, "tokens": 9976, "L": 766, "bl2": 9388096, "ckpt_on": false, "samples_seen": 42288, "step_ms": 2030.2, "ts": 1790077824.9, "ema_loss": 1.14446}
|
| 2645 |
+
{"type": "train", "step": 2644, "loss": 0.99153, "gnorm": 0.167, "lr": 0.00017140141457447879, "tokens": 10549, "L": 796, "bl2": 10137856, "ckpt_on": false, "samples_seen": 42304, "step_ms": 2410.6000000000004, "ts": 1790077828.0, "ema_loss": 1.1414}
|
| 2646 |
+
{"type": "train", "step": 2645, "loss": 1.095, "gnorm": 0.1777, "lr": 0.00017124055785848003, "tokens": 10116, "L": 803, "bl2": 10316944, "ckpt_on": false, "samples_seen": 42320, "step_ms": 2120.0, "ts": 1790077830.2, "ema_loss": 1.14047}
|
| 2647 |
+
{"type": "train", "step": 2646, "loss": 1.06764, "gnorm": 0.3496, "lr": 0.00017107976847085683, "tokens": 10028, "L": 833, "bl2": 11102224, "ckpt_on": false, "samples_seen": 42336, "step_ms": 2565.5, "ts": 1790077832.9, "ema_loss": 1.13901}
|
| 2648 |
+
{"type": "train", "step": 2647, "loss": 0.98947, "gnorm": 0.4355, "lr": 0.00017091904651594358, "tokens": 9968, "L": 800, "bl2": 10240000, "ckpt_on": false, "samples_seen": 42352, "step_ms": 2778.6, "ts": 1790077836.3, "ema_loss": 1.13602}
|
| 2649 |
+
{"type": "train", "step": 2648, "loss": 1.04244, "gnorm": 0.1709, "lr": 0.00017075839209803117, "tokens": 9880, "L": 843, "bl2": 11370384, "ckpt_on": false, "samples_seen": 42368, "step_ms": 2122.2, "ts": 1790077838.5, "ema_loss": 1.13415}
|
| 2650 |
+
{"type": "train", "step": 2649, "loss": 0.95145, "gnorm": 0.332, "lr": 0.00017059780532136624, "tokens": 9250, "L": 780, "bl2": 9734400, "ckpt_on": false, "samples_seen": 42384, "step_ms": 2205.7, "ts": 1790077841.3, "ema_loss": 1.1305}
|
| 2651 |
+
{"type": "train", "step": 2650, "loss": 1.02553, "gnorm": 0.2158, "lr": 0.0001704372862901521, "tokens": 10579, "L": 784, "bl2": 9834496, "ckpt_on": false, "samples_seen": 42400, "step_ms": 2131.1, "ts": 1790077843.5, "ema_loss": 1.1284}
|
| 2652 |
+
{"type": "train", "step": 2651, "loss": 1.27718, "gnorm": 0.2119, "lr": 0.00017027683510854766, "tokens": 9911, "L": 789, "bl2": 9960336, "ckpt_on": false, "samples_seen": 42416, "step_ms": 2085.1, "ts": 1790077846.5, "ema_loss": 1.13137}
|
| 2653 |
+
{"type": "train", "step": 2652, "loss": 1.22022, "gnorm": 0.2676, "lr": 0.0001701164518806678, "tokens": 9308, "L": 804, "bl2": 10342656, "ckpt_on": false, "samples_seen": 42432, "step_ms": 2421.9, "ts": 1790077849.0, "ema_loss": 1.13315}
|
| 2654 |
+
{"type": "train", "step": 2653, "loss": 1.0287, "gnorm": 0.2852, "lr": 0.0001699561367105838, "tokens": 10136, "L": 792, "bl2": 10036224, "ckpt_on": false, "samples_seen": 42448, "step_ms": 2102.0, "ts": 1790077851.8, "ema_loss": 1.13106}
|
| 2655 |
+
{"type": "train", "step": 2654, "loss": 1.01373, "gnorm": 0.4551, "lr": 0.00016979588970232213, "tokens": 10054, "L": 792, "bl2": 10036224, "ckpt_on": false, "samples_seen": 42464, "step_ms": 2352.2, "ts": 1790077854.3, "ema_loss": 1.12871}
|
| 2656 |
+
{"type": "train", "step": 2655, "loss": 1.00354, "gnorm": 0.3555, "lr": 0.00016963571095986545, "tokens": 9959, "L": 793, "bl2": 10061584, "ckpt_on": false, "samples_seen": 42480, "step_ms": 2129.0, "ts": 1790077857.0, "ema_loss": 1.12621}
|
| 2657 |
+
{"type": "train", "step": 2656, "loss": 0.96583, "gnorm": 0.2354, "lr": 0.0001694756005871521, "tokens": 10364, "L": 815, "bl2": 10627600, "ckpt_on": false, "samples_seen": 42496, "step_ms": 1672.8000000000002, "ts": 1790077858.8, "ema_loss": 1.123}
|
| 2658 |
+
{"type": "train", "step": 2657, "loss": 1.22914, "gnorm": 0.2969, "lr": 0.0001693155586880758, "tokens": 10517, "L": 778, "bl2": 9684544, "ckpt_on": false, "samples_seen": 42512, "step_ms": 2515.9, "ts": 1790077861.4, "ema_loss": 1.12513}
|
| 2659 |
+
{"type": "train", "step": 2658, "loss": 1.15428, "gnorm": 0.2432, "lr": 0.000169155585366486, "tokens": 9380, "L": 773, "bl2": 9560464, "ckpt_on": false, "samples_seen": 42528, "step_ms": 2182.0, "ts": 1790077864.3, "ema_loss": 1.12571}
|
| 2660 |
+
{"type": "train", "step": 2659, "loss": 1.04307, "gnorm": 0.5156, "lr": 0.00016899568072618778, "tokens": 10889, "L": 828, "bl2": 10969344, "ckpt_on": false, "samples_seen": 42544, "step_ms": 2268.6, "ts": 1790077866.6, "ema_loss": 1.12406}
|
| 2661 |
+
{"type": "train", "step": 2660, "loss": 0.97309, "gnorm": 0.2256, "lr": 0.00016883584487094156, "tokens": 10495, "L": 805, "bl2": 10368400, "ckpt_on": false, "samples_seen": 42560, "step_ms": 2488.5, "ts": 1790077875.8, "mem_alloc_gb": 3.71, "mem_reserved_gb": 44.08, "ema_loss": 1.12104}
|
| 2662 |
+
{"type": "train", "step": 2661, "loss": 0.99866, "gnorm": 0.2314, "lr": 0.00016867607790446287, "tokens": 9178, "L": 773, "bl2": 9560464, "ckpt_on": false, "samples_seen": 42576, "step_ms": 1915.3, "ts": 1790077877.8, "ema_loss": 1.11859}
|
| 2663 |
+
{"type": "train", "step": 2662, "loss": 1.1145, "gnorm": 0.2227, "lr": 0.0001685163799304229, "tokens": 9890, "L": 804, "bl2": 10342656, "ckpt_on": false, "samples_seen": 42592, "step_ms": 2376.1, "ts": 1790077886.8, "ema_loss": 1.11851}
|
| 2664 |
+
{"type": "train", "step": 2663, "loss": 1.13185, "gnorm": 0.3184, "lr": 0.000168356751052448, "tokens": 10048, "L": 792, "bl2": 10036224, "ckpt_on": false, "samples_seen": 42608, "step_ms": 1975.0, "ts": 1790077888.9, "ema_loss": 1.11877}
|
| 2665 |
+
{"type": "train", "step": 2664, "loss": 0.94098, "gnorm": 0.2891, "lr": 0.00016819719137411946, "tokens": 9975, "L": 799, "bl2": 10214416, "ckpt_on": false, "samples_seen": 42624, "step_ms": 2295.6, "ts": 1790077891.2, "ema_loss": 1.11522}
|
| 2666 |
+
{"type": "train", "step": 2665, "loss": 0.92267, "gnorm": 0.4609, "lr": 0.00016803770099897385, "tokens": 10205, "L": 782, "bl2": 9784384, "ckpt_on": false, "samples_seen": 42640, "step_ms": 2219.4, "ts": 1790077894.0, "ema_loss": 1.11137}
|
| 2667 |
+
{"type": "train", "step": 2666, "loss": 1.21344, "gnorm": 0.4004, "lr": 0.00016787828003050296, "tokens": 9736, "L": 818, "bl2": 10705984, "ckpt_on": false, "samples_seen": 42656, "step_ms": 2220.5, "ts": 1790077896.4, "ema_loss": 1.11341}
|
| 2668 |
+
{"type": "train", "step": 2667, "loss": 1.00425, "gnorm": 0.2969, "lr": 0.00016771892857215298, "tokens": 10593, "L": 803, "bl2": 10316944, "ckpt_on": false, "samples_seen": 42672, "step_ms": 2002.5, "ts": 1790077898.5, "ema_loss": 1.11123}
|
| 2669 |
+
{"type": "train", "step": 2668, "loss": 1.26421, "gnorm": 0.2676, "lr": 0.00016755964672732557, "tokens": 10471, "L": 807, "bl2": 10419984, "ckpt_on": false, "samples_seen": 42688, "step_ms": 1692.6999999999998, "ts": 1790077900.9, "ema_loss": 1.11429}
|
| 2670 |
+
{"type": "train", "step": 2669, "loss": 0.88211, "gnorm": 0.7539, "lr": 0.00016740043459937692, "tokens": 10203, "L": 814, "bl2": 10601536, "ckpt_on": false, "samples_seen": 42704, "step_ms": 1690.1, "ts": 1790077902.7, "ema_loss": 1.10964}
|
| 2671 |
+
{"type": "train", "step": 2670, "loss": 1.10792, "gnorm": 0.4102, "lr": 0.00016724129229161818, "tokens": 10444, "L": 840, "bl2": 11289600, "ckpt_on": false, "samples_seen": 42720, "step_ms": 2806.2, "ts": 1790077906.2, "ema_loss": 1.10961}
|
| 2672 |
+
{"type": "train", "step": 2671, "loss": 1.06794, "gnorm": 0.2236, "lr": 0.0001670822199073148, "tokens": 10024, "L": 682, "bl2": 7441984, "ckpt_on": false, "samples_seen": 42736, "step_ms": 1645.9, "ts": 1790077907.9, "ema_loss": 1.10877}
|
| 2673 |
+
{"type": "train", "step": 2672, "loss": 1.21333, "gnorm": 0.3262, "lr": 0.0001669232175496873, "tokens": 10493, "L": 798, "bl2": 10188864, "ckpt_on": false, "samples_seen": 42752, "step_ms": 2336.0, "ts": 1790077910.4, "ema_loss": 1.11087}
|
| 2674 |
+
{"type": "train", "step": 2673, "loss": 1.01832, "gnorm": 0.1836, "lr": 0.00016676428532191067, "tokens": 10052, "L": 763, "bl2": 9314704, "ckpt_on": false, "samples_seen": 42768, "step_ms": 2049.3, "ts": 1790077913.0, "ema_loss": 1.10901}
|
| 2675 |
+
{"type": "train", "step": 2674, "loss": 1.122, "gnorm": 0.3145, "lr": 0.00016660542332711404, "tokens": 10208, "L": 853, "bl2": 11641744, "ckpt_on": false, "samples_seen": 42784, "step_ms": 2007.2, "ts": 1790077915.1, "ema_loss": 1.10927}
|
| 2676 |
+
{"type": "train", "step": 2675, "loss": 1.00268, "gnorm": 0.2773, "lr": 0.00016644663166838153, "tokens": 9735, "L": 776, "bl2": 9634816, "ckpt_on": false, "samples_seen": 42800, "step_ms": 2128.2, "ts": 1790077917.7, "ema_loss": 1.10714}
|
| 2677 |
+
{"type": "train", "step": 2676, "loss": 1.00375, "gnorm": 0.3027, "lr": 0.0001662879104487511, "tokens": 10368, "L": 791, "bl2": 10010896, "ckpt_on": false, "samples_seen": 42816, "step_ms": 2398.1, "ts": 1790077920.3, "ema_loss": 1.10507}
|
| 2678 |
+
{"type": "train", "step": 2677, "loss": 1.01999, "gnorm": 0.2578, "lr": 0.00016612925977121533, "tokens": 9856, "L": 805, "bl2": 10368400, "ckpt_on": false, "samples_seen": 42832, "step_ms": 2038.5, "ts": 1790077922.4, "ema_loss": 1.10337}
|
| 2679 |
+
{"type": "train", "step": 2678, "loss": 0.96993, "gnorm": 0.2188, "lr": 0.000165970679738721, "tokens": 10660, "L": 799, "bl2": 10214416, "ckpt_on": false, "samples_seen": 42848, "step_ms": 2558.1, "ts": 1790077925.6, "ema_loss": 1.1007}
|
| 2680 |
+
{"type": "train", "step": 2679, "loss": 1.33226, "gnorm": 0.2002, "lr": 0.00016581217045416867, "tokens": 9115, "L": 756, "bl2": 9144576, "ckpt_on": false, "samples_seen": 42864, "step_ms": 1993.2, "ts": 1790077927.8, "ema_loss": 1.10534}
|
| 2681 |
+
{"type": "train", "step": 2680, "loss": 1.20583, "gnorm": 0.167, "lr": 0.00016565373202041364, "tokens": 9955, "L": 794, "bl2": 10086976, "ckpt_on": false, "samples_seen": 42880, "step_ms": 2386.2, "ts": 1790077931.2, "mem_alloc_gb": 3.71, "mem_reserved_gb": 44.36, "ema_loss": 1.10735}
|
| 2682 |
+
{"type": "train", "step": 2681, "loss": 1.1635, "gnorm": 0.2422, "lr": 0.0001654953645402647, "tokens": 9045, "L": 813, "bl2": 10575504, "ckpt_on": false, "samples_seen": 42896, "step_ms": 2030.5, "ts": 1790077933.3, "ema_loss": 1.10847}
|
| 2683 |
+
{"type": "train", "step": 2682, "loss": 1.05212, "gnorm": 0.1699, "lr": 0.0001653370681164849, "tokens": 11154, "L": 828, "bl2": 10969344, "ckpt_on": false, "samples_seen": 42912, "step_ms": 2385.5, "ts": 1790077935.8, "ema_loss": 1.10734}
|
| 2684 |
+
{"type": "train", "step": 2683, "loss": 1.07272, "gnorm": 0.1973, "lr": 0.00016517884285179092, "tokens": 11039, "L": 832, "bl2": 11075584, "ckpt_on": false, "samples_seen": 42928, "step_ms": 2314.1000000000004, "ts": 1790077938.8, "ema_loss": 1.10665}
|
| 2685 |
+
{"type": "train", "step": 2684, "loss": 1.13933, "gnorm": 0.2266, "lr": 0.00016502068884885354, "tokens": 9441, "L": 753, "bl2": 9072144, "ckpt_on": false, "samples_seen": 42944, "step_ms": 2167.8, "ts": 1790077941.0, "ema_loss": 1.1073}
|
| 2686 |
+
{"type": "train", "step": 2685, "loss": 1.04937, "gnorm": 0.2637, "lr": 0.0001648626062102972, "tokens": 10299, "L": 832, "bl2": 11075584, "ckpt_on": false, "samples_seen": 42960, "step_ms": 1680.9, "ts": 1790077943.3, "ema_loss": 1.10614}
|
| 2687 |
+
{"type": "train", "step": 2686, "loss": 0.96795, "gnorm": 0.1514, "lr": 0.00016470459503869985, "tokens": 9560, "L": 773, "bl2": 9560464, "ckpt_on": false, "samples_seen": 42976, "step_ms": 2206.3, "ts": 1790077945.6, "ema_loss": 1.10338}
|
| 2688 |
+
{"type": "train", "step": 2687, "loss": 1.09208, "gnorm": 0.3359, "lr": 0.0001645466554365933, "tokens": 10654, "L": 720, "bl2": 8294400, "ckpt_on": false, "samples_seen": 42992, "step_ms": 1797.7, "ts": 1790077948.0, "ema_loss": 1.10315}
|
| 2689 |
+
{"type": "train", "step": 2688, "loss": 1.11161, "gnorm": 0.2812, "lr": 0.00016438878750646302, "tokens": 9144, "L": 796, "bl2": 10137856, "ckpt_on": false, "samples_seen": 43008, "step_ms": 1810.1, "ts": 1790077949.8, "ema_loss": 1.10332}
|
| 2690 |
+
{"type": "train", "step": 2689, "loss": 1.09537, "gnorm": 0.1816, "lr": 0.0001642309913507475, "tokens": 10125, "L": 806, "bl2": 10394176, "ckpt_on": false, "samples_seen": 43024, "step_ms": 2423.6, "ts": 1790077953.0, "ema_loss": 1.10316}
|
| 2691 |
+
{"type": "train", "step": 2690, "loss": 1.1033, "gnorm": 0.2598, "lr": 0.00016407326707183908, "tokens": 9116, "L": 715, "bl2": 8179600, "ckpt_on": false, "samples_seen": 43040, "step_ms": 2050.5, "ts": 1790077955.7, "ema_loss": 1.10317}
|
| 2692 |
+
{"type": "train", "step": 2691, "loss": 1.03595, "gnorm": 0.2754, "lr": 0.00016391561477208338, "tokens": 10818, "L": 796, "bl2": 10137856, "ckpt_on": false, "samples_seen": 43056, "step_ms": 1818.4, "ts": 1790077957.7, "ema_loss": 1.10182}
|
| 2693 |
+
{"type": "train", "step": 2692, "loss": 1.12815, "gnorm": 0.166, "lr": 0.0001637580345537793, "tokens": 9543, "L": 724, "bl2": 8386816, "ckpt_on": false, "samples_seen": 43072, "step_ms": 2116.6, "ts": 1790077959.8, "ema_loss": 1.10235}
|
| 2694 |
+
{"type": "train", "step": 2693, "loss": 1.09766, "gnorm": 0.416, "lr": 0.00016360052651917878, "tokens": 9925, "L": 795, "bl2": 10112400, "ckpt_on": false, "samples_seen": 43088, "step_ms": 2596.4, "ts": 1790077963.0, "ema_loss": 1.10226}
|
| 2695 |
+
{"type": "train", "step": 2694, "loss": 0.93622, "gnorm": 0.1855, "lr": 0.00016344309077048714, "tokens": 9598, "L": 737, "bl2": 8690704, "ckpt_on": false, "samples_seen": 43104, "step_ms": 1971.9, "ts": 1790077965.0, "ema_loss": 1.09893}
|
| 2696 |
+
{"type": "train", "step": 2695, "loss": 1.04978, "gnorm": 0.1611, "lr": 0.0001632857274098628, "tokens": 9703, "L": 769, "bl2": 9461776, "ckpt_on": false, "samples_seen": 43120, "step_ms": 2033.7, "ts": 1790077967.6, "ema_loss": 1.09795}
|
| 2697 |
+
{"type": "train", "step": 2696, "loss": 1.01418, "gnorm": 0.2139, "lr": 0.00016312843653941693, "tokens": 10477, "L": 886, "bl2": 12559936, "ckpt_on": false, "samples_seen": 43136, "step_ms": 2696.0, "ts": 1790077970.5, "ema_loss": 1.09628}
|
| 2698 |
+
{"type": "train", "step": 2697, "loss": 1.13133, "gnorm": 0.291, "lr": 0.00016297121826121426, "tokens": 11009, "L": 846, "bl2": 11451456, "ckpt_on": false, "samples_seen": 43152, "step_ms": 2078.8, "ts": 1790077972.6, "ema_loss": 1.09698}
|
| 2699 |
+
{"type": "train", "step": 2698, "loss": 0.9368, "gnorm": 0.2236, "lr": 0.00016281407267727162, "tokens": 9868, "L": 747, "bl2": 8928144, "ckpt_on": false, "samples_seen": 43168, "step_ms": 1936.2, "ts": 1790077975.1, "ema_loss": 1.09377}
|
| 2700 |
+
{"type": "train", "step": 2699, "loss": 1.09097, "gnorm": 0.209, "lr": 0.00016265699988955926, "tokens": 9381, "L": 780, "bl2": 9734400, "ckpt_on": false, "samples_seen": 43184, "step_ms": 2142.0, "ts": 1790077977.3, "ema_loss": 1.09372}
|
| 2701 |
+
{"type": "train", "step": 2700, "loss": 0.86682, "gnorm": 0.2891, "lr": 0.00016250000000000007, "tokens": 10054, "L": 804, "bl2": 10342656, "ckpt_on": false, "samples_seen": 43200, "step_ms": 2269.7, "ts": 1790077980.1, "mem_alloc_gb": 3.71, "mem_reserved_gb": 44.1, "ema_loss": 1.08918}
|