| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 2181, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "grad_norm": 15.334183542211342, |
| "learning_rate": 1.5151515151515153e-05, |
| "loss": 6.3953, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 14.31536467947777, |
| "learning_rate": 3.0303030303030306e-05, |
| "loss": 6.4092, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 10.73679735786722, |
| "learning_rate": 4.545454545454546e-05, |
| "loss": 6.2051, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 8.935093821485406, |
| "learning_rate": 6.060606060606061e-05, |
| "loss": 5.8817, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 8.935093821485406, |
| "learning_rate": 6.060606060606061e-05, |
| "loss": 5.6877, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 6.44033956555991, |
| "learning_rate": 7.575757575757576e-05, |
| "loss": 5.624, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 7.59289488978937, |
| "learning_rate": 9.090909090909092e-05, |
| "loss": 5.6317, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 4.869407827655017, |
| "learning_rate": 0.00010606060606060606, |
| "loss": 5.4535, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 3.8117335919670823, |
| "learning_rate": 0.00012121212121212122, |
| "loss": 5.2621, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 3.4927415152472805, |
| "learning_rate": 0.00013636363636363637, |
| "loss": 5.176, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 3.4927415152472805, |
| "learning_rate": 0.00013636363636363637, |
| "loss": 5.0248, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 3.1126716562676577, |
| "learning_rate": 0.00015151515151515152, |
| "loss": 5.1131, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 2.4345766010663925, |
| "learning_rate": 0.00016666666666666666, |
| "loss": 5.0588, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 2.329733026509153, |
| "learning_rate": 0.00018181818181818183, |
| "loss": 4.929, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 5.364713180731029, |
| "learning_rate": 0.00019696969696969695, |
| "loss": 4.8973, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 2.464208337532836, |
| "learning_rate": 0.00021212121212121213, |
| "loss": 4.7068, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 2.027422473550685, |
| "learning_rate": 0.00022727272727272727, |
| "loss": 4.6938, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 1.9976258099547546, |
| "learning_rate": 0.00024242424242424245, |
| "loss": 4.5624, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 1.823188090176418, |
| "learning_rate": 0.00025757575757575756, |
| "loss": 4.581, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 1.459545627765441, |
| "learning_rate": 0.00027272727272727274, |
| "loss": 4.7432, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 1.3558166216164915, |
| "learning_rate": 0.0002878787878787879, |
| "loss": 4.5708, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 1.1197103800746975, |
| "learning_rate": 0.00030303030303030303, |
| "loss": 4.4382, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 1.2994352592912017, |
| "learning_rate": 0.0003181818181818182, |
| "loss": 4.4326, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 1.0686511351448147, |
| "learning_rate": 0.0003333333333333333, |
| "loss": 4.4413, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 1.0012323519121575, |
| "learning_rate": 0.0003484848484848485, |
| "loss": 4.4045, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 0.7758514042010983, |
| "learning_rate": 0.00036363636363636367, |
| "loss": 4.3725, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 0.8164809885246237, |
| "learning_rate": 0.0003787878787878788, |
| "loss": 4.4365, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 0.7688793256485448, |
| "learning_rate": 0.0003939393939393939, |
| "loss": 4.398, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 0.6259466508692746, |
| "learning_rate": 0.00040909090909090913, |
| "loss": 4.3952, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 0.7309984988874876, |
| "learning_rate": 0.00042424242424242425, |
| "loss": 4.3468, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 0.6907660868331702, |
| "learning_rate": 0.0004393939393939394, |
| "loss": 4.3493, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 0.8260039395023467, |
| "learning_rate": 0.00045454545454545455, |
| "loss": 4.3453, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.5976764894044625, |
| "learning_rate": 0.0004696969696969697, |
| "loss": 4.354, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.537667211938002, |
| "learning_rate": 0.0004848484848484849, |
| "loss": 4.3147, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.7412158668324115, |
| "learning_rate": 0.0005, |
| "loss": 4.3077, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.5585053100253914, |
| "learning_rate": 0.0005151515151515151, |
| "loss": 4.2118, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.7618978347592349, |
| "learning_rate": 0.0005303030303030302, |
| "loss": 4.2607, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.5071283705192057, |
| "learning_rate": 0.0005454545454545455, |
| "loss": 4.1861, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.9266836507881187, |
| "learning_rate": 0.0005606060606060606, |
| "loss": 4.2818, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.4947819375787067, |
| "learning_rate": 0.0005757575757575758, |
| "loss": 4.3188, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.7034491866529747, |
| "learning_rate": 0.0005909090909090909, |
| "loss": 4.0721, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.44054063945280847, |
| "learning_rate": 0.0006060606060606061, |
| "loss": 4.1524, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.5237189251271526, |
| "learning_rate": 0.0006212121212121212, |
| "loss": 4.2286, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.8007456273367883, |
| "learning_rate": 0.0006363636363636364, |
| "loss": 4.1539, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.8199538545137269, |
| "learning_rate": 0.0006515151515151515, |
| "loss": 4.1381, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.608328613360647, |
| "learning_rate": 0.0006666666666666666, |
| "loss": 4.1422, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.9515450180240922, |
| "learning_rate": 0.0006818181818181818, |
| "loss": 4.1147, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.5570776611155092, |
| "learning_rate": 0.000696969696969697, |
| "loss": 4.1083, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 1.0714118049565002, |
| "learning_rate": 0.0007121212121212122, |
| "loss": 4.2335, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.6269252546943217, |
| "learning_rate": 0.0007272727272727273, |
| "loss": 4.1088, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.6443354520995405, |
| "learning_rate": 0.0007424242424242425, |
| "loss": 4.1396, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.53831150976723, |
| "learning_rate": 0.0007575757575757576, |
| "loss": 4.2359, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.7596109063363826, |
| "learning_rate": 0.0007727272727272727, |
| "loss": 4.2306, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.545574935870758, |
| "learning_rate": 0.0007878787878787878, |
| "loss": 4.1167, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.794245336655487, |
| "learning_rate": 0.000803030303030303, |
| "loss": 4.084, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.9256573011892618, |
| "learning_rate": 0.0008181818181818183, |
| "loss": 4.1522, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.9782222163815075, |
| "learning_rate": 0.0008333333333333334, |
| "loss": 4.0859, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.9182989283422611, |
| "learning_rate": 0.0008484848484848485, |
| "loss": 4.184, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 1.0929956032834736, |
| "learning_rate": 0.0008636363636363636, |
| "loss": 4.0662, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.8785356028994228, |
| "learning_rate": 0.0008787878787878789, |
| "loss": 4.0462, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.8146560927654142, |
| "learning_rate": 0.000893939393939394, |
| "loss": 3.9316, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.5682637413201722, |
| "learning_rate": 0.0009090909090909091, |
| "loss": 3.9911, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.6490006987339698, |
| "learning_rate": 0.0009242424242424242, |
| "loss": 4.0214, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.662798665234368, |
| "learning_rate": 0.0009393939393939394, |
| "loss": 4.2227, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.8270171825487339, |
| "learning_rate": 0.0009545454545454546, |
| "loss": 3.9213, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.8066863086820539, |
| "learning_rate": 0.0009696969696969698, |
| "loss": 4.0164, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 1.0435186091560793, |
| "learning_rate": 0.000984848484848485, |
| "loss": 4.0336, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.8861497789062082, |
| "learning_rate": 0.001, |
| "loss": 3.9092, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.8777743573885423, |
| "learning_rate": 0.0009999994484067654, |
| "loss": 3.9999, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.8721459286919013, |
| "learning_rate": 0.0009999977936282788, |
| "loss": 3.9012, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 1.0970360057076605, |
| "learning_rate": 0.0009999950356681913, |
| "loss": 3.9757, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.7024753195909463, |
| "learning_rate": 0.0009999911745325876, |
| "loss": 3.8857, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.6157990364902758, |
| "learning_rate": 0.0009999862102299873, |
| "loss": 3.7689, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.8109890893012737, |
| "learning_rate": 0.0009999801427713433, |
| "loss": 3.794, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.8087095935136683, |
| "learning_rate": 0.0009999729721700424, |
| "loss": 3.8955, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.9068180388073529, |
| "learning_rate": 0.000999964698441906, |
| "loss": 3.7971, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.7986733858573573, |
| "learning_rate": 0.0009999553216051892, |
| "loss": 3.8309, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.8558487050084156, |
| "learning_rate": 0.00099994484168058, |
| "loss": 3.7554, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.6535165810097047, |
| "learning_rate": 0.0009999332586912019, |
| "loss": 3.7326, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.6014388816160134, |
| "learning_rate": 0.0009999205726626108, |
| "loss": 3.7996, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.9771455740666994, |
| "learning_rate": 0.000999906783622797, |
| "loss": 3.7263, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.8678749834289413, |
| "learning_rate": 0.0009998918916021842, |
| "loss": 3.7084, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.6241484355459758, |
| "learning_rate": 0.0009998758966336297, |
| "loss": 3.7792, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.8361325477286393, |
| "learning_rate": 0.0009998587987524242, |
| "loss": 3.7602, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 2.4413849986100598, |
| "learning_rate": 0.0009998405979962926, |
| "loss": 3.872, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.7338156634476518, |
| "learning_rate": 0.000999821294405392, |
| "loss": 3.8277, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.5993696263742313, |
| "learning_rate": 0.0009998008880223134, |
| "loss": 3.5891, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.7675612960345141, |
| "learning_rate": 0.000999779378892081, |
| "loss": 3.7728, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.6530382503056259, |
| "learning_rate": 0.0009997567670621522, |
| "loss": 3.6719, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.894559011900143, |
| "learning_rate": 0.0009997330525824165, |
| "loss": 3.7646, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.6789104976438548, |
| "learning_rate": 0.0009997082355051976, |
| "loss": 3.6285, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.7979525041676214, |
| "learning_rate": 0.000999682315885251, |
| "loss": 3.6415, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.6278442062579862, |
| "learning_rate": 0.0009996552937797645, |
| "loss": 3.6463, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.6292037380802387, |
| "learning_rate": 0.0009996271692483596, |
| "loss": 3.6561, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.6894325733315846, |
| "learning_rate": 0.0009995979423530893, |
| "loss": 3.6773, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.6380513826941416, |
| "learning_rate": 0.000999567613158439, |
| "loss": 3.6817, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.6543608398065544, |
| "learning_rate": 0.0009995361817313263, |
| "loss": 3.7264, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.5746662706450479, |
| "learning_rate": 0.0009995036481411004, |
| "loss": 3.685, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.748499621328208, |
| "learning_rate": 0.0009994700124595429, |
| "loss": 3.6078, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.5509670997306202, |
| "learning_rate": 0.0009994352747608663, |
| "loss": 3.6032, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.8489749123700031, |
| "learning_rate": 0.0009993994351217151, |
| "loss": 3.6827, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.7238950554497341, |
| "learning_rate": 0.000999362493621165, |
| "loss": 3.4744, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.8122144072730191, |
| "learning_rate": 0.0009993244503407226, |
| "loss": 3.6001, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.8838107058285632, |
| "learning_rate": 0.0009992853053643258, |
| "loss": 3.6702, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.7704350591480358, |
| "learning_rate": 0.0009992450587783426, |
| "loss": 3.5606, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.679292370355895, |
| "learning_rate": 0.000999203710671572, |
| "loss": 3.5626, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.7040420564583791, |
| "learning_rate": 0.0009991612611352438, |
| "loss": 3.492, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.6814758363563421, |
| "learning_rate": 0.0009991177102630173, |
| "loss": 3.5041, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.6571307656152292, |
| "learning_rate": 0.0009990730581509817, |
| "loss": 3.5634, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.8622160957375191, |
| "learning_rate": 0.0009990273048976566, |
| "loss": 3.6068, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.7658243845750742, |
| "learning_rate": 0.0009989804506039905, |
| "loss": 3.5963, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.7581465861271133, |
| "learning_rate": 0.0009989324953733614, |
| "loss": 3.5124, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.633786462819318, |
| "learning_rate": 0.0009988834393115766, |
| "loss": 3.4073, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 1.587758674834298, |
| "learning_rate": 0.000998833282526872, |
| "loss": 3.5337, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.7887660135230425, |
| "learning_rate": 0.0009987820251299122, |
| "loss": 3.5422, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.5973874168234299, |
| "learning_rate": 0.00099872966723379, |
| "loss": 3.571, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.7916766982956738, |
| "learning_rate": 0.0009986762089540266, |
| "loss": 3.5928, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.8585483171965513, |
| "learning_rate": 0.0009986216504085709, |
| "loss": 3.5248, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.7186900820446693, |
| "learning_rate": 0.0009985659917177991, |
| "loss": 3.5388, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 1.6218747102931899, |
| "learning_rate": 0.0009985092330045155, |
| "loss": 3.5662, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.8588977604039649, |
| "learning_rate": 0.0009984513743939508, |
| "loss": 3.418, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 1.1808048291966062, |
| "learning_rate": 0.0009983924160137626, |
| "loss": 3.4905, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 1.078358928754179, |
| "learning_rate": 0.000998332357994035, |
| "loss": 3.5081, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.7101468774646937, |
| "learning_rate": 0.0009982712004672786, |
| "loss": 3.5121, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.7490959721725653, |
| "learning_rate": 0.0009982089435684295, |
| "loss": 3.474, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.6937126116470814, |
| "learning_rate": 0.0009981455874348499, |
| "loss": 3.4265, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.6373108971387584, |
| "learning_rate": 0.0009980811322063269, |
| "loss": 3.3637, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.7558767197302974, |
| "learning_rate": 0.0009980155780250728, |
| "loss": 3.4071, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.5843040071786609, |
| "learning_rate": 0.0009979489250357243, |
| "loss": 3.4394, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.5674023457149213, |
| "learning_rate": 0.0009978811733853431, |
| "loss": 3.3745, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.650655555100603, |
| "learning_rate": 0.0009978123232234147, |
| "loss": 3.3438, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.6172935509401164, |
| "learning_rate": 0.000997742374701848, |
| "loss": 3.3881, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.6420321383609022, |
| "learning_rate": 0.0009976713279749754, |
| "loss": 3.4387, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.9525428078141334, |
| "learning_rate": 0.0009975991831995528, |
| "loss": 3.4011, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.7158229405524252, |
| "learning_rate": 0.0009975259405347581, |
| "loss": 3.4362, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.6158658745774443, |
| "learning_rate": 0.0009974516001421926, |
| "loss": 3.3401, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.6435221535813938, |
| "learning_rate": 0.000997376162185878, |
| "loss": 3.386, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.6790666011137657, |
| "learning_rate": 0.0009972996268322594, |
| "loss": 3.445, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.6262954606136751, |
| "learning_rate": 0.0009972219942502017, |
| "loss": 3.3569, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.5707875593708921, |
| "learning_rate": 0.0009971432646109918, |
| "loss": 3.3925, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.5920945241247064, |
| "learning_rate": 0.0009970634380883365, |
| "loss": 3.3138, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6431365647220689, |
| "learning_rate": 0.0009969825148583627, |
| "loss": 3.3789, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.7071034962129757, |
| "learning_rate": 0.0009969004950996173, |
| "loss": 3.3169, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6194824830769352, |
| "learning_rate": 0.0009968173789930668, |
| "loss": 3.332, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6768122581044627, |
| "learning_rate": 0.0009967331667220958, |
| "loss": 3.3548, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6952602017914864, |
| "learning_rate": 0.0009966478584725086, |
| "loss": 3.4044, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6185759293493853, |
| "learning_rate": 0.0009965614544325263, |
| "loss": 3.3228, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6851209179612645, |
| "learning_rate": 0.000996473954792789, |
| "loss": 3.4032, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6253416093926321, |
| "learning_rate": 0.0009963853597463532, |
| "loss": 3.42, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6444570979113228, |
| "learning_rate": 0.000996295669488693, |
| "loss": 3.3186, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.608962296259015, |
| "learning_rate": 0.0009962048842176979, |
| "loss": 3.3538, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.7085204679023983, |
| "learning_rate": 0.0009961130041336748, |
| "loss": 3.3251, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6532665740582476, |
| "learning_rate": 0.0009960200294393449, |
| "loss": 3.1889, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.5879079578522121, |
| "learning_rate": 0.0009959259603398453, |
| "loss": 3.3303, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6145408842708578, |
| "learning_rate": 0.0009958307970427275, |
| "loss": 3.3817, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6001591055676142, |
| "learning_rate": 0.0009957345397579572, |
| "loss": 3.3216, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6032506724503474, |
| "learning_rate": 0.0009956371886979138, |
| "loss": 3.2529, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.901684698803946, |
| "learning_rate": 0.00099553874407739, |
| "loss": 3.2188, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.683311987086415, |
| "learning_rate": 0.0009954392061135916, |
| "loss": 3.3088, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6503417436722514, |
| "learning_rate": 0.0009953385750261364, |
| "loss": 3.3113, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 1.0295499275838136, |
| "learning_rate": 0.0009952368510370538, |
| "loss": 3.2399, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.7739312943137796, |
| "learning_rate": 0.0009951340343707852, |
| "loss": 3.2649, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.6926746358337985, |
| "learning_rate": 0.0009950301252541823, |
| "loss": 3.3578, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.821973930424514, |
| "learning_rate": 0.0009949251239165075, |
| "loss": 3.2506, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6586332112991091, |
| "learning_rate": 0.000994819030589433, |
| "loss": 3.2575, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6286074623593879, |
| "learning_rate": 0.00099471184550704, |
| "loss": 3.3631, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6089631495754848, |
| "learning_rate": 0.0009946035689058189, |
| "loss": 3.3434, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6212237580466767, |
| "learning_rate": 0.0009944942010246681, |
| "loss": 3.242, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.5498055194198729, |
| "learning_rate": 0.0009943837421048942, |
| "loss": 3.1635, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6869329306346331, |
| "learning_rate": 0.0009942721923902106, |
| "loss": 3.2343, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6962182475726276, |
| "learning_rate": 0.0009941595521267377, |
| "loss": 3.3655, |
| "step": 171 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6216639081621088, |
| "learning_rate": 0.0009940458215630017, |
| "loss": 3.3103, |
| "step": 172 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6929987170066136, |
| "learning_rate": 0.0009939310009499348, |
| "loss": 3.3897, |
| "step": 173 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.7110465634225929, |
| "learning_rate": 0.000993815090540874, |
| "loss": 3.2578, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.622019677525455, |
| "learning_rate": 0.000993698090591561, |
| "loss": 3.1882, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.5816722130159141, |
| "learning_rate": 0.0009935800013601416, |
| "loss": 3.1681, |
| "step": 176 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6633471749867508, |
| "learning_rate": 0.000993460823107164, |
| "loss": 3.212, |
| "step": 177 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.650727452266244, |
| "learning_rate": 0.0009933405560955803, |
| "loss": 3.2569, |
| "step": 178 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.7664263430579104, |
| "learning_rate": 0.0009932192005907446, |
| "loss": 3.223, |
| "step": 179 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.7705550286324775, |
| "learning_rate": 0.0009930967568604118, |
| "loss": 3.1576, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6860061789031866, |
| "learning_rate": 0.000992973225174739, |
| "loss": 3.3222, |
| "step": 181 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6679888989785246, |
| "learning_rate": 0.0009928486058062827, |
| "loss": 3.2575, |
| "step": 182 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6377201788940962, |
| "learning_rate": 0.0009927228990299999, |
| "loss": 3.194, |
| "step": 183 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.6291411300050938, |
| "learning_rate": 0.0009925961051232468, |
| "loss": 3.1926, |
| "step": 184 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.7606666924920321, |
| "learning_rate": 0.000992468224365778, |
| "loss": 3.0882, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6692843018687604, |
| "learning_rate": 0.000992339257039746, |
| "loss": 3.1292, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6953704166608796, |
| "learning_rate": 0.0009922092034297006, |
| "loss": 3.1047, |
| "step": 187 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6431215579242893, |
| "learning_rate": 0.0009920780638225891, |
| "loss": 3.1409, |
| "step": 188 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6391287096000579, |
| "learning_rate": 0.0009919458385077538, |
| "loss": 3.1852, |
| "step": 189 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6593809882343142, |
| "learning_rate": 0.0009918125277769336, |
| "loss": 3.2141, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6778759635636019, |
| "learning_rate": 0.0009916781319242614, |
| "loss": 3.1545, |
| "step": 191 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6778759635636019, |
| "learning_rate": 0.0009916781319242614, |
| "loss": 3.165, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.7031304029576592, |
| "learning_rate": 0.0009915426512462646, |
| "loss": 3.2513, |
| "step": 193 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.7694765650079874, |
| "learning_rate": 0.0009914060860418644, |
| "loss": 3.1375, |
| "step": 194 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6339380636026481, |
| "learning_rate": 0.000991268436612374, |
| "loss": 3.1465, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.709252890827903, |
| "learning_rate": 0.0009911297032614997, |
| "loss": 3.0834, |
| "step": 196 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.7561505183826184, |
| "learning_rate": 0.000990989886295339, |
| "loss": 3.1231, |
| "step": 197 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.7055645722845291, |
| "learning_rate": 0.0009908489860223804, |
| "loss": 3.1163, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6900483256146748, |
| "learning_rate": 0.000990707002753502, |
| "loss": 3.1392, |
| "step": 199 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.8006164611955585, |
| "learning_rate": 0.0009905639368019724, |
| "loss": 3.1327, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6926855197491865, |
| "learning_rate": 0.0009904197884834482, |
| "loss": 3.0998, |
| "step": 201 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.7444768853308613, |
| "learning_rate": 0.0009902745581159742, |
| "loss": 3.0752, |
| "step": 202 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.797218390576468, |
| "learning_rate": 0.0009901282460199829, |
| "loss": 3.1195, |
| "step": 203 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.7211102951341859, |
| "learning_rate": 0.0009899808525182935, |
| "loss": 3.0272, |
| "step": 204 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.6445655085501315, |
| "learning_rate": 0.0009898323779361107, |
| "loss": 3.0389, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.7736070304356024, |
| "learning_rate": 0.000989682822601025, |
| "loss": 3.0735, |
| "step": 206 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.8042817790772433, |
| "learning_rate": 0.0009895321868430113, |
| "loss": 3.0739, |
| "step": 207 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7461344403883747, |
| "learning_rate": 0.0009893804709944281, |
| "loss": 3.0899, |
| "step": 208 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.833134773928923, |
| "learning_rate": 0.0009892276753900174, |
| "loss": 3.1053, |
| "step": 209 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7098684342372011, |
| "learning_rate": 0.0009890738003669028, |
| "loss": 3.1318, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7745211964796063, |
| "learning_rate": 0.0009889188462645904, |
| "loss": 3.0791, |
| "step": 211 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 1.062429485571328, |
| "learning_rate": 0.0009887628134249667, |
| "loss": 2.976, |
| "step": 212 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7249253932217932, |
| "learning_rate": 0.0009886057021922983, |
| "loss": 2.8416, |
| "step": 213 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7483356388482424, |
| "learning_rate": 0.0009884475129132311, |
| "loss": 3.0788, |
| "step": 214 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7119047686507263, |
| "learning_rate": 0.0009882882459367897, |
| "loss": 3.1152, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7624960299877818, |
| "learning_rate": 0.0009881279016143766, |
| "loss": 3.0291, |
| "step": 216 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7284852085113764, |
| "learning_rate": 0.0009879664802997707, |
| "loss": 3.0801, |
| "step": 217 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.8845250399253491, |
| "learning_rate": 0.000987803982349128, |
| "loss": 3.0061, |
| "step": 218 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7421809918882757, |
| "learning_rate": 0.0009876404081209796, |
| "loss": 2.9947, |
| "step": 219 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.8238004614778821, |
| "learning_rate": 0.000987475757976231, |
| "loss": 3.0152, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7747288426324181, |
| "learning_rate": 0.000987310032278162, |
| "loss": 2.9793, |
| "step": 221 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7849542778701295, |
| "learning_rate": 0.0009871432313924254, |
| "loss": 3.0175, |
| "step": 222 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.6902885999342769, |
| "learning_rate": 0.000986975355687046, |
| "loss": 3.0009, |
| "step": 223 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.993209360223465, |
| "learning_rate": 0.0009868064055324204, |
| "loss": 2.978, |
| "step": 224 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.8214531729727206, |
| "learning_rate": 0.0009866363813013153, |
| "loss": 3.0543, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7317341011288563, |
| "learning_rate": 0.0009864652833688676, |
| "loss": 2.9523, |
| "step": 226 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.6956798998451439, |
| "learning_rate": 0.0009862931121125836, |
| "loss": 2.9438, |
| "step": 227 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.6919980872800705, |
| "learning_rate": 0.000986119867912337, |
| "loss": 3.0331, |
| "step": 228 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7091707660273089, |
| "learning_rate": 0.000985945551150369, |
| "loss": 2.9797, |
| "step": 229 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.7065015816978751, |
| "learning_rate": 0.0009857701622112876, |
| "loss": 3.0031, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.8232317104727906, |
| "learning_rate": 0.000985593701482066, |
| "loss": 2.9164, |
| "step": 231 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.7996160627390247, |
| "learning_rate": 0.0009854161693520424, |
| "loss": 3.0261, |
| "step": 232 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.7993126363169994, |
| "learning_rate": 0.0009852375662129194, |
| "loss": 3.0287, |
| "step": 233 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.7249445145482315, |
| "learning_rate": 0.0009850578924587613, |
| "loss": 2.9649, |
| "step": 234 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.6816923350166996, |
| "learning_rate": 0.000984877148485996, |
| "loss": 2.9753, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.7012150222962508, |
| "learning_rate": 0.000984695334693412, |
| "loss": 3.0873, |
| "step": 236 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.772853973568081, |
| "learning_rate": 0.000984512451482158, |
| "loss": 2.9, |
| "step": 237 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.7131395059162757, |
| "learning_rate": 0.0009843284992557431, |
| "loss": 3.0357, |
| "step": 238 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.762102329525046, |
| "learning_rate": 0.000984143478420034, |
| "loss": 2.9197, |
| "step": 239 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.8252462205733532, |
| "learning_rate": 0.0009839573893832563, |
| "loss": 3.0668, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.7303452534815433, |
| "learning_rate": 0.000983770232555991, |
| "loss": 2.9979, |
| "step": 241 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.6942886930060724, |
| "learning_rate": 0.0009835820083511765, |
| "loss": 2.9804, |
| "step": 242 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.647045852342847, |
| "learning_rate": 0.0009833927171841055, |
| "loss": 2.9787, |
| "step": 243 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.699290228090126, |
| "learning_rate": 0.0009832023594724246, |
| "loss": 2.9967, |
| "step": 244 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.6270824876108666, |
| "learning_rate": 0.0009830109356361344, |
| "loss": 2.9551, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.681996767253554, |
| "learning_rate": 0.0009828184460975867, |
| "loss": 2.9289, |
| "step": 246 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.7073874994574992, |
| "learning_rate": 0.0009826248912814855, |
| "loss": 2.9432, |
| "step": 247 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.7312271991807926, |
| "learning_rate": 0.0009824302716148847, |
| "loss": 2.81, |
| "step": 248 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.6829641901427884, |
| "learning_rate": 0.0009822345875271884, |
| "loss": 2.8718, |
| "step": 249 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.6983961119061649, |
| "learning_rate": 0.0009820378394501481, |
| "loss": 2.9806, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.6999462650671663, |
| "learning_rate": 0.0009818400278178636, |
| "loss": 3.0112, |
| "step": 251 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.7559034111246584, |
| "learning_rate": 0.0009816411530667814, |
| "loss": 3.0101, |
| "step": 252 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.7262700158140356, |
| "learning_rate": 0.000981441215635693, |
| "loss": 2.9548, |
| "step": 253 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.6711266847726256, |
| "learning_rate": 0.0009812402159657353, |
| "loss": 3.0252, |
| "step": 254 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.7180487511803231, |
| "learning_rate": 0.000981038154500388, |
| "loss": 2.9127, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.6774185622643832, |
| "learning_rate": 0.0009808350316854746, |
| "loss": 2.9318, |
| "step": 256 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.6944061747160357, |
| "learning_rate": 0.0009806308479691594, |
| "loss": 2.96, |
| "step": 257 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.680063180222825, |
| "learning_rate": 0.0009804256038019482, |
| "loss": 2.9403, |
| "step": 258 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.640125125682984, |
| "learning_rate": 0.0009802192996366857, |
| "loss": 2.8379, |
| "step": 259 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.7262210337167265, |
| "learning_rate": 0.0009800119359285563, |
| "loss": 2.9944, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.7913651482749727, |
| "learning_rate": 0.0009798035131350813, |
| "loss": 2.9766, |
| "step": 261 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.6566430338772425, |
| "learning_rate": 0.0009795940317161194, |
| "loss": 2.8788, |
| "step": 262 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.676157144553763, |
| "learning_rate": 0.0009793834921338646, |
| "loss": 2.9066, |
| "step": 263 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.7159002391331705, |
| "learning_rate": 0.0009791718948528457, |
| "loss": 2.9857, |
| "step": 264 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.6648538671058444, |
| "learning_rate": 0.0009789592403399252, |
| "loss": 2.9183, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.7191165029645384, |
| "learning_rate": 0.0009787455290642985, |
| "loss": 2.8994, |
| "step": 266 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.6638951560078662, |
| "learning_rate": 0.000978530761497492, |
| "loss": 2.8373, |
| "step": 267 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.7190470301981947, |
| "learning_rate": 0.0009783149381133633, |
| "loss": 2.8709, |
| "step": 268 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 1.2008229752434898, |
| "learning_rate": 0.0009780980593880992, |
| "loss": 2.8989, |
| "step": 269 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.6452579355675543, |
| "learning_rate": 0.0009778801258002153, |
| "loss": 2.8376, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.6408919240792208, |
| "learning_rate": 0.000977661137830554, |
| "loss": 2.7667, |
| "step": 271 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.636755957491758, |
| "learning_rate": 0.0009774410959622845, |
| "loss": 2.8751, |
| "step": 272 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6361776113664193, |
| "learning_rate": 0.000977220000680901, |
| "loss": 2.8672, |
| "step": 273 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6361776113664193, |
| "learning_rate": 0.000977220000680901, |
| "loss": 2.8625, |
| "step": 274 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6848229956698715, |
| "learning_rate": 0.000976997852474223, |
| "loss": 2.8775, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 1.1235010547924027, |
| "learning_rate": 0.0009767746518323914, |
| "loss": 2.9035, |
| "step": 276 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6609295564768467, |
| "learning_rate": 0.0009765503992478704, |
| "loss": 2.9161, |
| "step": 277 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.7163304278893385, |
| "learning_rate": 0.0009763250952154449, |
| "loss": 2.8547, |
| "step": 278 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6554407460418303, |
| "learning_rate": 0.0009760987402322195, |
| "loss": 2.8575, |
| "step": 279 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.7002718038656189, |
| "learning_rate": 0.0009758713347976178, |
| "loss": 2.8785, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.653155064396982, |
| "learning_rate": 0.000975642879413381, |
| "loss": 2.8912, |
| "step": 281 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.656740925196336, |
| "learning_rate": 0.0009754133745835665, |
| "loss": 2.8661, |
| "step": 282 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6593340569116168, |
| "learning_rate": 0.0009751828208145482, |
| "loss": 2.8234, |
| "step": 283 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.745857422199865, |
| "learning_rate": 0.0009749512186150131, |
| "loss": 2.8908, |
| "step": 284 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.7452959701859863, |
| "learning_rate": 0.0009747185684959625, |
| "loss": 2.8084, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 1.614065702649731, |
| "learning_rate": 0.000974484870970709, |
| "loss": 2.8733, |
| "step": 286 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 1.7147860025344097, |
| "learning_rate": 0.0009742501265548767, |
| "loss": 2.9304, |
| "step": 287 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6213586587032996, |
| "learning_rate": 0.0009740143357663993, |
| "loss": 2.8991, |
| "step": 288 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6621498060186065, |
| "learning_rate": 0.000973777499125519, |
| "loss": 2.9464, |
| "step": 289 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.686591797342712, |
| "learning_rate": 0.0009735396171547859, |
| "loss": 2.8961, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6678682803238307, |
| "learning_rate": 0.0009733006903790564, |
| "loss": 2.7951, |
| "step": 291 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6493061735708802, |
| "learning_rate": 0.0009730607193254922, |
| "loss": 2.8296, |
| "step": 292 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.5893251831560374, |
| "learning_rate": 0.0009728197045235585, |
| "loss": 2.8551, |
| "step": 293 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.6167707754626185, |
| "learning_rate": 0.0009725776465050242, |
| "loss": 2.7936, |
| "step": 294 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.7792967534161264, |
| "learning_rate": 0.0009723345458039594, |
| "loss": 2.8642, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6149544613562459, |
| "learning_rate": 0.000972090402956735, |
| "loss": 2.8906, |
| "step": 296 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.7049316524119515, |
| "learning_rate": 0.0009718452185020212, |
| "loss": 2.8912, |
| "step": 297 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6410395122511617, |
| "learning_rate": 0.0009715989929807862, |
| "loss": 2.9408, |
| "step": 298 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6426362240373914, |
| "learning_rate": 0.0009713517269362955, |
| "loss": 2.727, |
| "step": 299 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6051291101212836, |
| "learning_rate": 0.0009711034209141101, |
| "loss": 2.8916, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6384276789391041, |
| "learning_rate": 0.0009708540754620856, |
| "loss": 2.874, |
| "step": 301 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6430396794508206, |
| "learning_rate": 0.0009706036911303713, |
| "loss": 2.8705, |
| "step": 302 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.5960039462158002, |
| "learning_rate": 0.0009703522684714083, |
| "loss": 2.8801, |
| "step": 303 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.7089156623188639, |
| "learning_rate": 0.0009700998080399286, |
| "loss": 2.8116, |
| "step": 304 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6296831337596133, |
| "learning_rate": 0.0009698463103929542, |
| "loss": 2.8264, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.746036604925989, |
| "learning_rate": 0.0009695917760897954, |
| "loss": 2.7711, |
| "step": 306 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6868581586529265, |
| "learning_rate": 0.0009693362056920501, |
| "loss": 2.7068, |
| "step": 307 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6154264303934269, |
| "learning_rate": 0.0009690795997636015, |
| "loss": 2.8539, |
| "step": 308 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6973437361593837, |
| "learning_rate": 0.0009688219588706179, |
| "loss": 2.8401, |
| "step": 309 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6630002583094217, |
| "learning_rate": 0.0009685632835815518, |
| "loss": 2.9085, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6013661431775347, |
| "learning_rate": 0.0009683035744671367, |
| "loss": 2.796, |
| "step": 311 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6690687149116704, |
| "learning_rate": 0.0009680428321003883, |
| "loss": 2.8152, |
| "step": 312 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6799068946752611, |
| "learning_rate": 0.000967781057056601, |
| "loss": 2.8923, |
| "step": 313 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.7524604478957374, |
| "learning_rate": 0.0009675182499133485, |
| "loss": 2.9197, |
| "step": 314 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6539641865600384, |
| "learning_rate": 0.0009672544112504813, |
| "loss": 2.7931, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.6141866384507794, |
| "learning_rate": 0.0009669895416501257, |
| "loss": 2.8343, |
| "step": 316 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.700552784539624, |
| "learning_rate": 0.0009667236416966833, |
| "loss": 2.875, |
| "step": 317 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.7039024799562249, |
| "learning_rate": 0.0009664567119768281, |
| "loss": 2.8372, |
| "step": 318 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6663868798389415, |
| "learning_rate": 0.0009661887530795067, |
| "loss": 2.8878, |
| "step": 319 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.627338131055199, |
| "learning_rate": 0.0009659197655959365, |
| "loss": 2.8041, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.5840112073104475, |
| "learning_rate": 0.000965649750119604, |
| "loss": 2.8261, |
| "step": 321 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6262100121594774, |
| "learning_rate": 0.0009653787072462643, |
| "loss": 2.7942, |
| "step": 322 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6226878766730823, |
| "learning_rate": 0.0009651066375739388, |
| "loss": 2.8571, |
| "step": 323 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6602959230650758, |
| "learning_rate": 0.000964833541702915, |
| "loss": 2.8523, |
| "step": 324 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.640845619919307, |
| "learning_rate": 0.0009645594202357438, |
| "loss": 2.814, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6330846369227421, |
| "learning_rate": 0.0009642842737772397, |
| "loss": 2.8969, |
| "step": 326 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6273623151604033, |
| "learning_rate": 0.0009640081029344782, |
| "loss": 2.7834, |
| "step": 327 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6465044265124769, |
| "learning_rate": 0.0009637309083167956, |
| "loss": 2.8358, |
| "step": 328 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6217611585443336, |
| "learning_rate": 0.0009634526905357859, |
| "loss": 2.7883, |
| "step": 329 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6543699660513408, |
| "learning_rate": 0.000963173450205302, |
| "loss": 2.7956, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6234383055487751, |
| "learning_rate": 0.0009628931879414517, |
| "loss": 2.9168, |
| "step": 331 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6220623731726608, |
| "learning_rate": 0.0009626119043625983, |
| "loss": 2.8599, |
| "step": 332 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6748401507576823, |
| "learning_rate": 0.0009623296000893582, |
| "loss": 2.8581, |
| "step": 333 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6538965389462665, |
| "learning_rate": 0.0009620462757446, |
| "loss": 2.7055, |
| "step": 334 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6521167677050568, |
| "learning_rate": 0.0009617619319534428, |
| "loss": 2.8118, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.639410864161994, |
| "learning_rate": 0.000961476569343255, |
| "loss": 2.8828, |
| "step": 336 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6496352884939414, |
| "learning_rate": 0.0009611901885436529, |
| "loss": 2.8429, |
| "step": 337 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.6057147851907673, |
| "learning_rate": 0.0009609027901864996, |
| "loss": 2.7846, |
| "step": 338 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.5793771473148083, |
| "learning_rate": 0.0009606143749059029, |
| "loss": 2.8003, |
| "step": 339 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.5969300267865852, |
| "learning_rate": 0.0009603249433382144, |
| "loss": 2.9063, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6106089397600502, |
| "learning_rate": 0.0009600344961220282, |
| "loss": 2.7864, |
| "step": 341 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6064707204076621, |
| "learning_rate": 0.0009597430338981791, |
| "loss": 2.677, |
| "step": 342 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6487459178866255, |
| "learning_rate": 0.0009594505573097414, |
| "loss": 2.7711, |
| "step": 343 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6152197778563439, |
| "learning_rate": 0.0009591570670020277, |
| "loss": 2.8346, |
| "step": 344 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6731210017887308, |
| "learning_rate": 0.0009588625636225871, |
| "loss": 2.9529, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6328351487205508, |
| "learning_rate": 0.0009585670478212036, |
| "loss": 2.7889, |
| "step": 346 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6611086059999134, |
| "learning_rate": 0.0009582705202498956, |
| "loss": 2.8333, |
| "step": 347 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6493357611885273, |
| "learning_rate": 0.0009579729815629133, |
| "loss": 2.8206, |
| "step": 348 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6427865161555848, |
| "learning_rate": 0.0009576744324167379, |
| "loss": 2.8568, |
| "step": 349 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.5944224464925874, |
| "learning_rate": 0.0009573748734700804, |
| "loss": 2.8123, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.5787066085224676, |
| "learning_rate": 0.0009570743053838796, |
| "loss": 2.9277, |
| "step": 351 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.555935418322191, |
| "learning_rate": 0.0009567727288213005, |
| "loss": 2.8067, |
| "step": 352 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.5944815483233737, |
| "learning_rate": 0.0009564701444477337, |
| "loss": 2.7504, |
| "step": 353 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.5895995945211255, |
| "learning_rate": 0.000956166552930793, |
| "loss": 2.8147, |
| "step": 354 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.5811282304989394, |
| "learning_rate": 0.0009558619549403147, |
| "loss": 2.8326, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6128103669274317, |
| "learning_rate": 0.0009555563511483555, |
| "loss": 2.8219, |
| "step": 356 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.6694675795329117, |
| "learning_rate": 0.0009552497422291912, |
| "loss": 2.8253, |
| "step": 357 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.5901370605109635, |
| "learning_rate": 0.0009549421288593157, |
| "loss": 2.7227, |
| "step": 358 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.7132018502477857, |
| "learning_rate": 0.0009546335117174385, |
| "loss": 2.8846, |
| "step": 359 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.5768373266080664, |
| "learning_rate": 0.0009543238914844843, |
| "loss": 2.7979, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.6685543163838495, |
| "learning_rate": 0.0009540132688435907, |
| "loss": 2.8061, |
| "step": 361 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.557546006700034, |
| "learning_rate": 0.0009537016444801074, |
| "loss": 2.8037, |
| "step": 362 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.5903848193835529, |
| "learning_rate": 0.0009533890190815935, |
| "loss": 2.7572, |
| "step": 363 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.6146836708830032, |
| "learning_rate": 0.0009530753933378173, |
| "loss": 2.7039, |
| "step": 364 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.6445440686364086, |
| "learning_rate": 0.0009527607679407545, |
| "loss": 2.8018, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.5833885089423918, |
| "learning_rate": 0.0009524451435845857, |
| "loss": 2.8137, |
| "step": 366 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.5530393441130761, |
| "learning_rate": 0.0009521285209656963, |
| "loss": 2.7997, |
| "step": 367 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.6146008020169156, |
| "learning_rate": 0.0009518109007826734, |
| "loss": 2.7539, |
| "step": 368 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.5711985422464281, |
| "learning_rate": 0.0009514922837363059, |
| "loss": 2.8672, |
| "step": 369 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.5559494956250339, |
| "learning_rate": 0.0009511726705295817, |
| "loss": 2.884, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.6310861999859323, |
| "learning_rate": 0.000950852061867687, |
| "loss": 2.8707, |
| "step": 371 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.576951148459554, |
| "learning_rate": 0.0009505304584580038, |
| "loss": 2.8549, |
| "step": 372 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.6125388422111081, |
| "learning_rate": 0.0009502078610101092, |
| "loss": 2.7688, |
| "step": 373 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.6004755447509498, |
| "learning_rate": 0.0009498842702357736, |
| "loss": 2.7189, |
| "step": 374 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.6595203663611379, |
| "learning_rate": 0.0009495596868489587, |
| "loss": 2.8169, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.564290459249208, |
| "learning_rate": 0.0009492341115658167, |
| "loss": 2.7599, |
| "step": 376 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.599133095738916, |
| "learning_rate": 0.0009489075451046879, |
| "loss": 2.9008, |
| "step": 377 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.5828856685146881, |
| "learning_rate": 0.0009485799881861, |
| "loss": 2.8826, |
| "step": 378 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.6069338797974693, |
| "learning_rate": 0.0009482514415327654, |
| "loss": 2.7426, |
| "step": 379 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.5751488154609321, |
| "learning_rate": 0.000947921905869581, |
| "loss": 2.7411, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.622646444871956, |
| "learning_rate": 0.0009475913819236248, |
| "loss": 2.9724, |
| "step": 381 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.6125310739787075, |
| "learning_rate": 0.0009472598704241561, |
| "loss": 2.8001, |
| "step": 382 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.570176574205134, |
| "learning_rate": 0.0009469273721026131, |
| "loss": 2.75, |
| "step": 383 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5528072296740599, |
| "learning_rate": 0.0009465938876926111, |
| "loss": 2.9417, |
| "step": 384 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5673429676794667, |
| "learning_rate": 0.0009462594179299406, |
| "loss": 2.737, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5446184155535325, |
| "learning_rate": 0.0009459239635525672, |
| "loss": 2.8637, |
| "step": 386 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5600092823266422, |
| "learning_rate": 0.0009455875253006281, |
| "loss": 2.7102, |
| "step": 387 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5899711821075407, |
| "learning_rate": 0.0009452501039164315, |
| "loss": 2.8966, |
| "step": 388 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.6154766098518095, |
| "learning_rate": 0.0009449117001444549, |
| "loss": 2.9194, |
| "step": 389 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.6416503969323492, |
| "learning_rate": 0.0009445723147313433, |
| "loss": 2.9095, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5823792814890851, |
| "learning_rate": 0.0009442319484259074, |
| "loss": 2.7616, |
| "step": 391 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.8813887004343529, |
| "learning_rate": 0.0009438906019791222, |
| "loss": 2.8224, |
| "step": 392 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.6002719871963206, |
| "learning_rate": 0.0009435482761441251, |
| "loss": 2.7723, |
| "step": 393 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.6889879120123602, |
| "learning_rate": 0.000943204971676215, |
| "loss": 2.9485, |
| "step": 394 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5583260057508286, |
| "learning_rate": 0.0009428606893328493, |
| "loss": 2.6752, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5962856783871717, |
| "learning_rate": 0.0009425154298736432, |
| "loss": 2.786, |
| "step": 396 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.7313626208204935, |
| "learning_rate": 0.0009421691940603678, |
| "loss": 2.7454, |
| "step": 397 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.6161618396211846, |
| "learning_rate": 0.0009418219826569488, |
| "loss": 2.6239, |
| "step": 398 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5841405925577571, |
| "learning_rate": 0.0009414737964294635, |
| "loss": 2.8175, |
| "step": 399 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.6169179108177675, |
| "learning_rate": 0.000941124636146141, |
| "loss": 2.7625, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.7110378526321456, |
| "learning_rate": 0.0009407745025773589, |
| "loss": 2.7327, |
| "step": 401 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5807949637386735, |
| "learning_rate": 0.0009404233964956423, |
| "loss": 2.7821, |
| "step": 402 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.5708094269315408, |
| "learning_rate": 0.0009400713186756625, |
| "loss": 2.6991, |
| "step": 403 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5586998890380273, |
| "learning_rate": 0.0009397182698942342, |
| "loss": 2.7562, |
| "step": 404 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5642397230604842, |
| "learning_rate": 0.0009393642509303149, |
| "loss": 2.8027, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.6891387968876841, |
| "learning_rate": 0.0009390092625650023, |
| "loss": 2.8194, |
| "step": 406 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5350125208276858, |
| "learning_rate": 0.0009386533055815332, |
| "loss": 2.8028, |
| "step": 407 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.6175308400179292, |
| "learning_rate": 0.0009382963807652813, |
| "loss": 2.7263, |
| "step": 408 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5439771285797257, |
| "learning_rate": 0.000937938488903756, |
| "loss": 2.7272, |
| "step": 409 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.6700331891626545, |
| "learning_rate": 0.0009375796307866003, |
| "loss": 2.7747, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5939856740272327, |
| "learning_rate": 0.0009372198072055888, |
| "loss": 2.8302, |
| "step": 411 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.6108782073760339, |
| "learning_rate": 0.0009368590189546268, |
| "loss": 2.7245, |
| "step": 412 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5581764910479498, |
| "learning_rate": 0.0009364972668297474, |
| "loss": 2.6952, |
| "step": 413 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5518461981906551, |
| "learning_rate": 0.0009361345516291111, |
| "loss": 2.6951, |
| "step": 414 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.6327053173561057, |
| "learning_rate": 0.0009357708741530024, |
| "loss": 2.8152, |
| "step": 415 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.751910258816782, |
| "learning_rate": 0.00093540623520383, |
| "loss": 2.7491, |
| "step": 416 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 1.2081171933560433, |
| "learning_rate": 0.000935040635586123, |
| "loss": 2.775, |
| "step": 417 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.739998429397638, |
| "learning_rate": 0.0009346740761065305, |
| "loss": 2.8999, |
| "step": 418 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.534619729304632, |
| "learning_rate": 0.0009343065575738197, |
| "loss": 2.6595, |
| "step": 419 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5623193070095451, |
| "learning_rate": 0.0009339380807988733, |
| "loss": 2.8423, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5604826092350274, |
| "learning_rate": 0.0009335686465946887, |
| "loss": 2.7518, |
| "step": 421 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5390016478087265, |
| "learning_rate": 0.0009331982557763754, |
| "loss": 2.6923, |
| "step": 422 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.6131814405442452, |
| "learning_rate": 0.0009328269091611537, |
| "loss": 2.7471, |
| "step": 423 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5675982407992965, |
| "learning_rate": 0.0009324546075683524, |
| "loss": 2.8276, |
| "step": 424 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.5458800058757823, |
| "learning_rate": 0.0009320813518194083, |
| "loss": 2.6895, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.6299391692477817, |
| "learning_rate": 0.0009317071427378624, |
| "loss": 2.7456, |
| "step": 426 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.6214288087877275, |
| "learning_rate": 0.0009313319811493594, |
| "loss": 2.7394, |
| "step": 427 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5962828842003414, |
| "learning_rate": 0.000930955867881646, |
| "loss": 2.7733, |
| "step": 428 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5396795297594269, |
| "learning_rate": 0.0009305788037645681, |
| "loss": 2.7292, |
| "step": 429 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.6111796381558718, |
| "learning_rate": 0.0009302007896300697, |
| "loss": 2.7991, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.53856607581584, |
| "learning_rate": 0.0009298218263121911, |
| "loss": 2.704, |
| "step": 431 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5460113018783559, |
| "learning_rate": 0.0009294419146470668, |
| "loss": 2.7212, |
| "step": 432 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5119518390120248, |
| "learning_rate": 0.0009290610554729234, |
| "loss": 2.7711, |
| "step": 433 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5519449522885417, |
| "learning_rate": 0.0009286792496300784, |
| "loss": 2.8108, |
| "step": 434 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5464485307690538, |
| "learning_rate": 0.0009282964979609379, |
| "loss": 2.6572, |
| "step": 435 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5474289462268974, |
| "learning_rate": 0.0009279128013099947, |
| "loss": 2.717, |
| "step": 436 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5484787600782545, |
| "learning_rate": 0.0009275281605238268, |
| "loss": 2.71, |
| "step": 437 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.6057885718406562, |
| "learning_rate": 0.0009271425764510953, |
| "loss": 2.7159, |
| "step": 438 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5891560654237684, |
| "learning_rate": 0.0009267560499425423, |
| "loss": 2.8402, |
| "step": 439 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.6202219192870312, |
| "learning_rate": 0.0009263685818509895, |
| "loss": 2.7436, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5711673423821138, |
| "learning_rate": 0.000925980173031336, |
| "loss": 2.7829, |
| "step": 441 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5567806982521943, |
| "learning_rate": 0.0009255908243405567, |
| "loss": 2.6559, |
| "step": 442 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5904447491181827, |
| "learning_rate": 0.0009252005366376996, |
| "loss": 2.8856, |
| "step": 443 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5545321608494346, |
| "learning_rate": 0.0009248093107838852, |
| "loss": 2.7997, |
| "step": 444 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.8769480163623165, |
| "learning_rate": 0.0009244171476423036, |
| "loss": 2.7926, |
| "step": 445 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5240402400298211, |
| "learning_rate": 0.0009240240480782129, |
| "loss": 2.8524, |
| "step": 446 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.5423373216796497, |
| "learning_rate": 0.0009236300129589376, |
| "loss": 2.8038, |
| "step": 447 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5564436599980042, |
| "learning_rate": 0.0009232350431538657, |
| "loss": 2.7816, |
| "step": 448 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5689707607012272, |
| "learning_rate": 0.0009228391395344482, |
| "loss": 2.8483, |
| "step": 449 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5775000312511759, |
| "learning_rate": 0.000922442302974196, |
| "loss": 2.7534, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5338590951931702, |
| "learning_rate": 0.0009220445343486785, |
| "loss": 2.7963, |
| "step": 451 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5703645701758161, |
| "learning_rate": 0.0009216458345355217, |
| "loss": 2.739, |
| "step": 452 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5994615515658506, |
| "learning_rate": 0.0009212462044144061, |
| "loss": 2.8256, |
| "step": 453 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5685248270535956, |
| "learning_rate": 0.0009208456448670648, |
| "loss": 2.6835, |
| "step": 454 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5922921246621345, |
| "learning_rate": 0.0009204441567772816, |
| "loss": 2.7572, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.6028614974424339, |
| "learning_rate": 0.0009200417410308888, |
| "loss": 2.6175, |
| "step": 456 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.546837043916075, |
| "learning_rate": 0.0009196383985157656, |
| "loss": 2.8258, |
| "step": 457 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.530793690369746, |
| "learning_rate": 0.000919234130121836, |
| "loss": 2.6793, |
| "step": 458 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5372131342020495, |
| "learning_rate": 0.0009188289367410672, |
| "loss": 2.7943, |
| "step": 459 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5508044877690208, |
| "learning_rate": 0.0009184228192674666, |
| "loss": 2.7506, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5798695394231989, |
| "learning_rate": 0.0009180157785970808, |
| "loss": 2.7287, |
| "step": 461 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5326059305321164, |
| "learning_rate": 0.0009176078156279932, |
| "loss": 2.892, |
| "step": 462 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5424984086265584, |
| "learning_rate": 0.0009171989312603226, |
| "loss": 2.6636, |
| "step": 463 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5601416004072663, |
| "learning_rate": 0.0009167891263962202, |
| "loss": 2.6852, |
| "step": 464 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5497932205316466, |
| "learning_rate": 0.0009163784019398685, |
| "loss": 2.6234, |
| "step": 465 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5917256034831518, |
| "learning_rate": 0.0009159667587974785, |
| "loss": 2.7916, |
| "step": 466 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.5701707696939897, |
| "learning_rate": 0.0009155541978772887, |
| "loss": 2.8344, |
| "step": 467 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.595486879270033, |
| "learning_rate": 0.0009151407200895625, |
| "loss": 2.7275, |
| "step": 468 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5607425434296898, |
| "learning_rate": 0.000914726326346586, |
| "loss": 2.8386, |
| "step": 469 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5586673238737594, |
| "learning_rate": 0.0009143110175626661, |
| "loss": 2.777, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5722397073014405, |
| "learning_rate": 0.0009138947946541291, |
| "loss": 2.6459, |
| "step": 471 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5464186429223988, |
| "learning_rate": 0.0009134776585393181, |
| "loss": 2.8462, |
| "step": 472 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5434157905367923, |
| "learning_rate": 0.0009130596101385906, |
| "loss": 2.6763, |
| "step": 473 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5316356607107424, |
| "learning_rate": 0.0009126406503743174, |
| "loss": 2.8224, |
| "step": 474 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5208560679994397, |
| "learning_rate": 0.0009122207801708802, |
| "loss": 2.7313, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5382543927061512, |
| "learning_rate": 0.0009118000004546689, |
| "loss": 2.7067, |
| "step": 476 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5483597029232145, |
| "learning_rate": 0.0009113783121540807, |
| "loss": 2.7181, |
| "step": 477 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.6827406948818237, |
| "learning_rate": 0.0009109557161995172, |
| "loss": 2.8014, |
| "step": 478 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5539274148425849, |
| "learning_rate": 0.0009105322135233828, |
| "loss": 2.7481, |
| "step": 479 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5679940381856933, |
| "learning_rate": 0.0009101078050600821, |
| "loss": 2.7877, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5609409886210408, |
| "learning_rate": 0.0009096824917460186, |
| "loss": 2.6772, |
| "step": 481 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5664985418513951, |
| "learning_rate": 0.0009092562745195921, |
| "loss": 2.7792, |
| "step": 482 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5312064300179586, |
| "learning_rate": 0.0009088291543211967, |
| "loss": 2.7761, |
| "step": 483 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.612938005294704, |
| "learning_rate": 0.0009084011320932188, |
| "loss": 2.8076, |
| "step": 484 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5941062131399235, |
| "learning_rate": 0.0009079722087800352, |
| "loss": 2.7129, |
| "step": 485 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5573570280673128, |
| "learning_rate": 0.0009075423853280106, |
| "loss": 2.7137, |
| "step": 486 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5532586619645483, |
| "learning_rate": 0.0009071116626854958, |
| "loss": 2.7246, |
| "step": 487 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5373853918781696, |
| "learning_rate": 0.0009066800418028256, |
| "loss": 2.7947, |
| "step": 488 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5246510989245057, |
| "learning_rate": 0.0009062475236323168, |
| "loss": 2.6843, |
| "step": 489 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.5843202022911487, |
| "learning_rate": 0.0009058141091282656, |
| "loss": 2.6843, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5815277401260301, |
| "learning_rate": 0.0009053797992469461, |
| "loss": 2.7808, |
| "step": 491 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.605160074412178, |
| "learning_rate": 0.0009049445949466078, |
| "loss": 2.6709, |
| "step": 492 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.6105340642381326, |
| "learning_rate": 0.0009045084971874737, |
| "loss": 2.7345, |
| "step": 493 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.6071148801953588, |
| "learning_rate": 0.0009040715069317382, |
| "loss": 2.7153, |
| "step": 494 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5761699225565616, |
| "learning_rate": 0.0009036336251435648, |
| "loss": 2.6775, |
| "step": 495 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5621982375319667, |
| "learning_rate": 0.0009031948527890839, |
| "loss": 2.7482, |
| "step": 496 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.556531452650355, |
| "learning_rate": 0.000902755190836391, |
| "loss": 2.8073, |
| "step": 497 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.6156876779444932, |
| "learning_rate": 0.0009023146402555442, |
| "loss": 2.7955, |
| "step": 498 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5990609659110069, |
| "learning_rate": 0.0009018732020185624, |
| "loss": 2.7626, |
| "step": 499 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5605536543544598, |
| "learning_rate": 0.0009014308770994235, |
| "loss": 2.6551, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5597304670473284, |
| "learning_rate": 0.0009009876664740605, |
| "loss": 2.6506, |
| "step": 501 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5713669937950526, |
| "learning_rate": 0.0009005435711203618, |
| "loss": 2.6344, |
| "step": 502 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5881838488404152, |
| "learning_rate": 0.000900098592018167, |
| "loss": 2.693, |
| "step": 503 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5417564306230721, |
| "learning_rate": 0.0008996527301492663, |
| "loss": 2.6741, |
| "step": 504 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5804715533896078, |
| "learning_rate": 0.0008992059864973972, |
| "loss": 2.8408, |
| "step": 505 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5410947295625333, |
| "learning_rate": 0.0008987583620482427, |
| "loss": 2.7127, |
| "step": 506 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.542102817332693, |
| "learning_rate": 0.0008983098577894292, |
| "loss": 2.6676, |
| "step": 507 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5543470487429215, |
| "learning_rate": 0.0008978604747105246, |
| "loss": 2.7148, |
| "step": 508 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5296711088136848, |
| "learning_rate": 0.0008974102138030354, |
| "loss": 2.65, |
| "step": 509 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.6301581341720567, |
| "learning_rate": 0.000896959076060405, |
| "loss": 2.8443, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.6028334452965141, |
| "learning_rate": 0.0008965070624780116, |
| "loss": 2.6607, |
| "step": 511 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.5734693127325966, |
| "learning_rate": 0.0008960541740531658, |
| "loss": 2.7483, |
| "step": 512 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5552923805397628, |
| "learning_rate": 0.0008956004117851083, |
| "loss": 2.6549, |
| "step": 513 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5263597594985705, |
| "learning_rate": 0.0008951457766750079, |
| "loss": 2.7293, |
| "step": 514 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.536874189465578, |
| "learning_rate": 0.0008946902697259593, |
| "loss": 2.7151, |
| "step": 515 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5452104700218603, |
| "learning_rate": 0.0008942338919429805, |
| "loss": 2.767, |
| "step": 516 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5195345177574965, |
| "learning_rate": 0.0008937766443330113, |
| "loss": 2.6043, |
| "step": 517 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.523265670546355, |
| "learning_rate": 0.0008933185279049103, |
| "loss": 2.7128, |
| "step": 518 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5474723937180358, |
| "learning_rate": 0.0008928595436694532, |
| "loss": 2.7396, |
| "step": 519 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5664270354913638, |
| "learning_rate": 0.0008923996926393305, |
| "loss": 2.7105, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.585691229686609, |
| "learning_rate": 0.0008919389758291449, |
| "loss": 2.802, |
| "step": 521 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5413532123361643, |
| "learning_rate": 0.0008914773942554098, |
| "loss": 2.6161, |
| "step": 522 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5508023674308857, |
| "learning_rate": 0.000891014948936546, |
| "loss": 2.7455, |
| "step": 523 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5345208487117149, |
| "learning_rate": 0.0008905516408928804, |
| "loss": 2.6215, |
| "step": 524 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5938027494494098, |
| "learning_rate": 0.0008900874711466434, |
| "loss": 2.7805, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.529919236037923, |
| "learning_rate": 0.0008896224407219666, |
| "loss": 2.7145, |
| "step": 526 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5654128024505742, |
| "learning_rate": 0.0008891565506448804, |
| "loss": 2.5867, |
| "step": 527 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5374826353609415, |
| "learning_rate": 0.0008886898019433122, |
| "loss": 2.6175, |
| "step": 528 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5908845101303762, |
| "learning_rate": 0.0008882221956470836, |
| "loss": 2.7456, |
| "step": 529 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.531554072883436, |
| "learning_rate": 0.0008877537327879086, |
| "loss": 2.6531, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5436252820359765, |
| "learning_rate": 0.0008872844143993908, |
| "loss": 2.7158, |
| "step": 531 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.500996568464473, |
| "learning_rate": 0.0008868142415170218, |
| "loss": 2.7104, |
| "step": 532 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5210802752850416, |
| "learning_rate": 0.0008863432151781781, |
| "loss": 2.604, |
| "step": 533 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.5772417824055223, |
| "learning_rate": 0.0008858713364221195, |
| "loss": 2.7662, |
| "step": 534 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5217001342168802, |
| "learning_rate": 0.0008853986062899868, |
| "loss": 2.7906, |
| "step": 535 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.514848741584364, |
| "learning_rate": 0.0008849250258247986, |
| "loss": 2.7023, |
| "step": 536 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5199449136274414, |
| "learning_rate": 0.0008844505960714503, |
| "loss": 2.7632, |
| "step": 537 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5238920163675016, |
| "learning_rate": 0.0008839753180767108, |
| "loss": 2.7804, |
| "step": 538 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5439366160698038, |
| "learning_rate": 0.0008834991928892204, |
| "loss": 2.617, |
| "step": 539 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5457258129936736, |
| "learning_rate": 0.000883022221559489, |
| "loss": 2.7154, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5595402009516594, |
| "learning_rate": 0.0008825444051398934, |
| "loss": 2.5754, |
| "step": 541 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.546045127743336, |
| "learning_rate": 0.0008820657446846745, |
| "loss": 2.8472, |
| "step": 542 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5321727353154101, |
| "learning_rate": 0.000881586241249936, |
| "loss": 2.5905, |
| "step": 543 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5488893297410015, |
| "learning_rate": 0.0008811058958936411, |
| "loss": 2.6368, |
| "step": 544 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5957771205718407, |
| "learning_rate": 0.000880624709675611, |
| "loss": 2.7619, |
| "step": 545 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.552552028914066, |
| "learning_rate": 0.000880142683657522, |
| "loss": 2.8426, |
| "step": 546 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5714132989589364, |
| "learning_rate": 0.0008796598189029029, |
| "loss": 2.6563, |
| "step": 547 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5555963228160256, |
| "learning_rate": 0.0008791761164771338, |
| "loss": 2.6428, |
| "step": 548 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5808904142821768, |
| "learning_rate": 0.0008786915774474424, |
| "loss": 2.7795, |
| "step": 549 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5107669976350262, |
| "learning_rate": 0.0008782062028829027, |
| "loss": 2.6106, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.6361648807640892, |
| "learning_rate": 0.0008777199938544318, |
| "loss": 2.7433, |
| "step": 551 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5180859618501872, |
| "learning_rate": 0.0008772329514347883, |
| "loss": 2.7522, |
| "step": 552 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5061530297528282, |
| "learning_rate": 0.0008767450766985694, |
| "loss": 2.8041, |
| "step": 553 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5375169603162063, |
| "learning_rate": 0.0008762563707222086, |
| "loss": 2.7399, |
| "step": 554 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5910523142407333, |
| "learning_rate": 0.0008757668345839738, |
| "loss": 2.7372, |
| "step": 555 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.5557913588569249, |
| "learning_rate": 0.0008752764693639638, |
| "loss": 2.729, |
| "step": 556 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5125657443715916, |
| "learning_rate": 0.0008747852761441078, |
| "loss": 2.6984, |
| "step": 557 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5080317123514281, |
| "learning_rate": 0.0008742932560081607, |
| "loss": 2.845, |
| "step": 558 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5322551076379304, |
| "learning_rate": 0.0008738004100417025, |
| "loss": 2.7735, |
| "step": 559 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.549568118512464, |
| "learning_rate": 0.0008733067393321355, |
| "loss": 2.6656, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.6393122178971771, |
| "learning_rate": 0.000872812244968681, |
| "loss": 2.6503, |
| "step": 561 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.48128520651941664, |
| "learning_rate": 0.0008723169280423783, |
| "loss": 2.6212, |
| "step": 562 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.4997250422270272, |
| "learning_rate": 0.0008718207896460811, |
| "loss": 2.7339, |
| "step": 563 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5221946438248469, |
| "learning_rate": 0.0008713238308744557, |
| "loss": 2.7432, |
| "step": 564 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5316415257608551, |
| "learning_rate": 0.0008708260528239789, |
| "loss": 2.7337, |
| "step": 565 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5402808789498333, |
| "learning_rate": 0.000870327456592934, |
| "loss": 2.7003, |
| "step": 566 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5732853969408304, |
| "learning_rate": 0.0008698280432814107, |
| "loss": 2.6845, |
| "step": 567 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5174691477296729, |
| "learning_rate": 0.000869327813991301, |
| "loss": 2.8997, |
| "step": 568 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5674923716835623, |
| "learning_rate": 0.0008688267698262971, |
| "loss": 2.6864, |
| "step": 569 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5310616504203381, |
| "learning_rate": 0.0008683249118918894, |
| "loss": 2.7109, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5478562489084389, |
| "learning_rate": 0.0008678222412953637, |
| "loss": 2.5486, |
| "step": 571 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.48210888285061676, |
| "learning_rate": 0.0008673187591457987, |
| "loss": 2.6885, |
| "step": 572 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5095396962755419, |
| "learning_rate": 0.0008668144665540639, |
| "loss": 2.6624, |
| "step": 573 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5201197409138298, |
| "learning_rate": 0.0008663093646328167, |
| "loss": 2.6073, |
| "step": 574 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.49926846788596185, |
| "learning_rate": 0.0008658034544965003, |
| "loss": 2.7108, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.5928071420026597, |
| "learning_rate": 0.0008652967372613412, |
| "loss": 2.7071, |
| "step": 576 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.580790369980711, |
| "learning_rate": 0.0008647892140453466, |
| "loss": 2.7502, |
| "step": 577 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5447931032229416, |
| "learning_rate": 0.0008642808859683021, |
| "loss": 2.8153, |
| "step": 578 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5329831849195207, |
| "learning_rate": 0.0008637717541517689, |
| "loss": 2.6622, |
| "step": 579 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5473686204540716, |
| "learning_rate": 0.0008632618197190816, |
| "loss": 2.7854, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5180624059527283, |
| "learning_rate": 0.0008627510837953458, |
| "loss": 2.6366, |
| "step": 581 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.539718887652329, |
| "learning_rate": 0.0008622395475074355, |
| "loss": 2.7344, |
| "step": 582 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5501575535824617, |
| "learning_rate": 0.0008617272119839903, |
| "loss": 2.6977, |
| "step": 583 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.4839087846082587, |
| "learning_rate": 0.0008612140783554136, |
| "loss": 2.667, |
| "step": 584 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5036540659629368, |
| "learning_rate": 0.0008607001477538696, |
| "loss": 2.7218, |
| "step": 585 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.4841581011778591, |
| "learning_rate": 0.0008601854213132807, |
| "loss": 2.7512, |
| "step": 586 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5422631854143893, |
| "learning_rate": 0.0008596699001693256, |
| "loss": 2.8027, |
| "step": 587 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5200231463293805, |
| "learning_rate": 0.000859153585459436, |
| "loss": 2.734, |
| "step": 588 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5462007498820824, |
| "learning_rate": 0.0008586364783227949, |
| "loss": 2.6283, |
| "step": 589 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5044518782244392, |
| "learning_rate": 0.0008581185799003332, |
| "loss": 2.6256, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.529048268347528, |
| "learning_rate": 0.0008575998913347283, |
| "loss": 2.6763, |
| "step": 591 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5872794645515884, |
| "learning_rate": 0.0008570804137704004, |
| "loss": 2.6494, |
| "step": 592 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5238922296840669, |
| "learning_rate": 0.0008565601483535108, |
| "loss": 2.651, |
| "step": 593 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5292318451138486, |
| "learning_rate": 0.0008560390962319591, |
| "loss": 2.6953, |
| "step": 594 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5308430144060405, |
| "learning_rate": 0.0008555172585553804, |
| "loss": 2.7061, |
| "step": 595 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5426444363122956, |
| "learning_rate": 0.0008549946364751435, |
| "loss": 2.735, |
| "step": 596 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.4960687925229807, |
| "learning_rate": 0.0008544712311443475, |
| "loss": 2.6207, |
| "step": 597 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5646751327288234, |
| "learning_rate": 0.0008539470437178196, |
| "loss": 2.6295, |
| "step": 598 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.5773171931605461, |
| "learning_rate": 0.000853422075352113, |
| "loss": 2.6393, |
| "step": 599 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.7070519670854635, |
| "learning_rate": 0.0008528963272055035, |
| "loss": 2.7749, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5479601580342474, |
| "learning_rate": 0.0008523698004379877, |
| "loss": 2.6885, |
| "step": 601 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5382041060442451, |
| "learning_rate": 0.00085184249621128, |
| "loss": 2.7755, |
| "step": 602 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5428838112241099, |
| "learning_rate": 0.0008513144156888101, |
| "loss": 2.615, |
| "step": 603 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5350995959672302, |
| "learning_rate": 0.0008507855600357207, |
| "loss": 2.6739, |
| "step": 604 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5447358313338942, |
| "learning_rate": 0.0008502559304188644, |
| "loss": 2.7058, |
| "step": 605 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5108354432894767, |
| "learning_rate": 0.0008497255280068019, |
| "loss": 2.7229, |
| "step": 606 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5663865880505383, |
| "learning_rate": 0.0008491943539697986, |
| "loss": 2.6739, |
| "step": 607 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5619492498627989, |
| "learning_rate": 0.0008486624094798226, |
| "loss": 2.6299, |
| "step": 608 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5329783887884124, |
| "learning_rate": 0.0008481296957105417, |
| "loss": 2.6891, |
| "step": 609 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5392492577605642, |
| "learning_rate": 0.0008475962138373213, |
| "loss": 2.6478, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5217758592597876, |
| "learning_rate": 0.0008470619650372211, |
| "loss": 2.6749, |
| "step": 611 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5252187717151474, |
| "learning_rate": 0.0008465269504889934, |
| "loss": 2.7351, |
| "step": 612 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5926238296786239, |
| "learning_rate": 0.0008459911713730799, |
| "loss": 2.6466, |
| "step": 613 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.507951296485482, |
| "learning_rate": 0.0008454546288716089, |
| "loss": 2.6473, |
| "step": 614 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.530564931532586, |
| "learning_rate": 0.0008449173241683935, |
| "loss": 2.6424, |
| "step": 615 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5168085897635017, |
| "learning_rate": 0.0008443792584489281, |
| "loss": 2.745, |
| "step": 616 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5187504144524554, |
| "learning_rate": 0.0008438404329003863, |
| "loss": 2.6937, |
| "step": 617 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5320508804717348, |
| "learning_rate": 0.0008433008487116183, |
| "loss": 2.6259, |
| "step": 618 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5402330692624593, |
| "learning_rate": 0.0008427605070731481, |
| "loss": 2.759, |
| "step": 619 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5063445025368052, |
| "learning_rate": 0.0008422194091771708, |
| "loss": 2.7394, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.5604688547017086, |
| "learning_rate": 0.0008416775562175503, |
| "loss": 2.6156, |
| "step": 621 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.567709690511373, |
| "learning_rate": 0.000841134949389816, |
| "loss": 2.7382, |
| "step": 622 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5298825939606623, |
| "learning_rate": 0.0008405915898911611, |
| "loss": 2.7089, |
| "step": 623 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5071592192115674, |
| "learning_rate": 0.0008400474789204396, |
| "loss": 2.6199, |
| "step": 624 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5555014442869661, |
| "learning_rate": 0.0008395026176781626, |
| "loss": 2.655, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.4910133930854562, |
| "learning_rate": 0.0008389570073664976, |
| "loss": 2.7445, |
| "step": 626 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.534646929315611, |
| "learning_rate": 0.0008384106491892642, |
| "loss": 2.6595, |
| "step": 627 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.4941309427310147, |
| "learning_rate": 0.0008378635443519327, |
| "loss": 2.6757, |
| "step": 628 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5095800171769095, |
| "learning_rate": 0.0008373156940616199, |
| "loss": 2.7959, |
| "step": 629 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5164506103016576, |
| "learning_rate": 0.0008367670995270882, |
| "loss": 2.7063, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5357810000912309, |
| "learning_rate": 0.0008362177619587416, |
| "loss": 2.6123, |
| "step": 631 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5305888114907911, |
| "learning_rate": 0.0008356676825686238, |
| "loss": 2.6097, |
| "step": 632 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5412613303574713, |
| "learning_rate": 0.0008351168625704147, |
| "loss": 2.6069, |
| "step": 633 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5260623006232825, |
| "learning_rate": 0.0008345653031794292, |
| "loss": 2.6432, |
| "step": 634 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5166126950091822, |
| "learning_rate": 0.0008340130056126125, |
| "loss": 2.6922, |
| "step": 635 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.6749683281835602, |
| "learning_rate": 0.0008334599710885394, |
| "loss": 2.6642, |
| "step": 636 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5420621464643194, |
| "learning_rate": 0.0008329062008274098, |
| "loss": 2.7189, |
| "step": 637 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5189309051046375, |
| "learning_rate": 0.000832351696051048, |
| "loss": 2.7337, |
| "step": 638 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5147734629804254, |
| "learning_rate": 0.000831796457982898, |
| "loss": 2.7303, |
| "step": 639 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.537626426785238, |
| "learning_rate": 0.0008312404878480222, |
| "loss": 2.6757, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5419937212407758, |
| "learning_rate": 0.0008306837868730979, |
| "loss": 2.66, |
| "step": 641 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.509250905749369, |
| "learning_rate": 0.0008301263562864152, |
| "loss": 2.728, |
| "step": 642 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5153603333418589, |
| "learning_rate": 0.0008295681973178737, |
| "loss": 2.586, |
| "step": 643 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5403337331318514, |
| "learning_rate": 0.0008290093111989804, |
| "loss": 2.6481, |
| "step": 644 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.504131733020366, |
| "learning_rate": 0.0008284496991628465, |
| "loss": 2.6575, |
| "step": 645 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5307815604049854, |
| "learning_rate": 0.0008278893624441847, |
| "loss": 2.6352, |
| "step": 646 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.4994574312275876, |
| "learning_rate": 0.000827328302279307, |
| "loss": 2.6175, |
| "step": 647 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.49041288894408014, |
| "learning_rate": 0.0008267665199061211, |
| "loss": 2.7015, |
| "step": 648 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5274843669342639, |
| "learning_rate": 0.0008262040165641288, |
| "loss": 2.776, |
| "step": 649 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5533014873504699, |
| "learning_rate": 0.0008256407934944219, |
| "loss": 2.7189, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5238782403461647, |
| "learning_rate": 0.0008250768519396807, |
| "loss": 2.7653, |
| "step": 651 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5071208031966006, |
| "learning_rate": 0.0008245121931441706, |
| "loss": 2.7106, |
| "step": 652 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.524353727359798, |
| "learning_rate": 0.0008239468183537393, |
| "loss": 2.6294, |
| "step": 653 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5098040397918049, |
| "learning_rate": 0.0008233807288158146, |
| "loss": 2.6535, |
| "step": 654 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5450814380754564, |
| "learning_rate": 0.0008228139257794012, |
| "loss": 2.6591, |
| "step": 655 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.49414341199157413, |
| "learning_rate": 0.0008222464104950778, |
| "loss": 2.8167, |
| "step": 656 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5420816986311767, |
| "learning_rate": 0.000821678184214995, |
| "loss": 2.6291, |
| "step": 657 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5438366305520779, |
| "learning_rate": 0.0008211092481928716, |
| "loss": 2.588, |
| "step": 658 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5228174667596475, |
| "learning_rate": 0.0008205396036839927, |
| "loss": 2.625, |
| "step": 659 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5812976017257665, |
| "learning_rate": 0.0008199692519452069, |
| "loss": 2.691, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5256847609095364, |
| "learning_rate": 0.0008193981942349224, |
| "loss": 2.6297, |
| "step": 661 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5778126736611795, |
| "learning_rate": 0.0008188264318131056, |
| "loss": 2.8018, |
| "step": 662 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5763192287042777, |
| "learning_rate": 0.0008182539659412776, |
| "loss": 2.6391, |
| "step": 663 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.49127514027154756, |
| "learning_rate": 0.0008176807978825118, |
| "loss": 2.7499, |
| "step": 664 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.5167135928849841, |
| "learning_rate": 0.0008171069289014306, |
| "loss": 2.7108, |
| "step": 665 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.5080697002273578, |
| "learning_rate": 0.0008165323602642028, |
| "loss": 2.6992, |
| "step": 666 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.5230471270407268, |
| "learning_rate": 0.0008159570932385414, |
| "loss": 2.7112, |
| "step": 667 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.49127459662262, |
| "learning_rate": 0.0008153811290936999, |
| "loss": 2.6228, |
| "step": 668 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.6583462745862124, |
| "learning_rate": 0.0008148044691004698, |
| "loss": 2.6592, |
| "step": 669 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.528612376543792, |
| "learning_rate": 0.0008142271145311783, |
| "loss": 2.5896, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.5123767266917941, |
| "learning_rate": 0.000813649066659685, |
| "loss": 2.7415, |
| "step": 671 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.823789344121993, |
| "learning_rate": 0.0008130703267613787, |
| "loss": 2.6258, |
| "step": 672 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.4979629563876908, |
| "learning_rate": 0.0008124908961131759, |
| "loss": 2.7535, |
| "step": 673 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.5078646450187342, |
| "learning_rate": 0.0008119107759935163, |
| "loss": 2.6529, |
| "step": 674 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.4480128693546292, |
| "learning_rate": 0.0008113299676823615, |
| "loss": 2.7672, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.4970384427957344, |
| "learning_rate": 0.0008107484724611911, |
| "loss": 2.7448, |
| "step": 676 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.494481452355186, |
| "learning_rate": 0.0008101662916130006, |
| "loss": 2.6728, |
| "step": 677 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.4999857912417589, |
| "learning_rate": 0.0008095834264222979, |
| "loss": 2.7141, |
| "step": 678 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.48835208043571626, |
| "learning_rate": 0.0008089998781751009, |
| "loss": 2.6271, |
| "step": 679 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.5253767705396146, |
| "learning_rate": 0.0008084156481589349, |
| "loss": 2.7308, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.5047823738744652, |
| "learning_rate": 0.0008078307376628291, |
| "loss": 2.6089, |
| "step": 681 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.5339764618286758, |
| "learning_rate": 0.0008072451479773143, |
| "loss": 2.6913, |
| "step": 682 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.5389516550842799, |
| "learning_rate": 0.0008066588803944195, |
| "loss": 2.6219, |
| "step": 683 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.48563204641202906, |
| "learning_rate": 0.0008060719362076697, |
| "loss": 2.6992, |
| "step": 684 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.5616245000266832, |
| "learning_rate": 0.0008054843167120826, |
| "loss": 2.6669, |
| "step": 685 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.5201334964593227, |
| "learning_rate": 0.0008048960232041663, |
| "loss": 2.7408, |
| "step": 686 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.466413327942957, |
| "learning_rate": 0.0008043070569819153, |
| "loss": 2.6633, |
| "step": 687 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5337631982809081, |
| "learning_rate": 0.0008037174193448089, |
| "loss": 2.5494, |
| "step": 688 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.564875738403792, |
| "learning_rate": 0.0008031271115938077, |
| "loss": 2.7689, |
| "step": 689 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5196588322515633, |
| "learning_rate": 0.0008025361350313505, |
| "loss": 2.7973, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.48441149954246093, |
| "learning_rate": 0.0008019444909613523, |
| "loss": 2.6558, |
| "step": 691 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.517684811118877, |
| "learning_rate": 0.0008013521806892003, |
| "loss": 2.8665, |
| "step": 692 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.48313839325760527, |
| "learning_rate": 0.000800759205521752, |
| "loss": 2.6097, |
| "step": 693 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.510175528106201, |
| "learning_rate": 0.0008001655667673318, |
| "loss": 2.637, |
| "step": 694 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.4870489010820059, |
| "learning_rate": 0.0007995712657357279, |
| "loss": 2.7049, |
| "step": 695 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.47072656461450313, |
| "learning_rate": 0.0007989763037381904, |
| "loss": 2.7008, |
| "step": 696 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5098282431514173, |
| "learning_rate": 0.0007983806820874271, |
| "loss": 2.6005, |
| "step": 697 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.7034007780738194, |
| "learning_rate": 0.0007977844020976016, |
| "loss": 2.6155, |
| "step": 698 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5411725993237723, |
| "learning_rate": 0.00079718746508433, |
| "loss": 2.7321, |
| "step": 699 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5198298636129081, |
| "learning_rate": 0.0007965898723646776, |
| "loss": 2.8037, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5229309340137156, |
| "learning_rate": 0.0007959916252571573, |
| "loss": 2.7201, |
| "step": 701 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.529160201923999, |
| "learning_rate": 0.000795392725081725, |
| "loss": 2.6895, |
| "step": 702 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5109421857525615, |
| "learning_rate": 0.000794793173159778, |
| "loss": 2.7482, |
| "step": 703 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5102185229783007, |
| "learning_rate": 0.0007941929708141513, |
| "loss": 2.6236, |
| "step": 704 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.49168295616232144, |
| "learning_rate": 0.0007935921193691153, |
| "loss": 2.7348, |
| "step": 705 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5243224074168978, |
| "learning_rate": 0.0007929906201503722, |
| "loss": 2.69, |
| "step": 706 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.547027773610455, |
| "learning_rate": 0.0007923884744850536, |
| "loss": 2.6048, |
| "step": 707 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5068208282459593, |
| "learning_rate": 0.0007917856837017176, |
| "loss": 2.6607, |
| "step": 708 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5204952272017995, |
| "learning_rate": 0.0007911822491303452, |
| "loss": 2.6043, |
| "step": 709 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5178630366637932, |
| "learning_rate": 0.0007905781721023382, |
| "loss": 2.5806, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5525411687979763, |
| "learning_rate": 0.000789973453950516, |
| "loss": 2.6812, |
| "step": 711 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.6658233879714814, |
| "learning_rate": 0.000789368096009112, |
| "loss": 2.7683, |
| "step": 712 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5660981815475495, |
| "learning_rate": 0.0007887620996137721, |
| "loss": 2.5193, |
| "step": 713 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5340095637836035, |
| "learning_rate": 0.0007881554661015497, |
| "loss": 2.6497, |
| "step": 714 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 1.1601095914587924, |
| "learning_rate": 0.0007875481968109051, |
| "loss": 2.5519, |
| "step": 715 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5230739622563734, |
| "learning_rate": 0.0007869402930817007, |
| "loss": 2.6414, |
| "step": 716 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5109069117889349, |
| "learning_rate": 0.0007863317562551987, |
| "loss": 2.6568, |
| "step": 717 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.49208779186029783, |
| "learning_rate": 0.0007857225876740584, |
| "loss": 2.7564, |
| "step": 718 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5489609556115185, |
| "learning_rate": 0.0007851127886823327, |
| "loss": 2.7053, |
| "step": 719 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.4841690884426475, |
| "learning_rate": 0.0007845023606254658, |
| "loss": 2.5602, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5095592526096626, |
| "learning_rate": 0.0007838913048502894, |
| "loss": 2.6861, |
| "step": 721 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5846737474186913, |
| "learning_rate": 0.0007832796227050208, |
| "loss": 2.7117, |
| "step": 722 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 2.3385368263353055, |
| "learning_rate": 0.0007826673155392587, |
| "loss": 2.6194, |
| "step": 723 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5057591036466761, |
| "learning_rate": 0.000782054384703981, |
| "loss": 2.7834, |
| "step": 724 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5181657600947097, |
| "learning_rate": 0.0007814408315515418, |
| "loss": 2.6413, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5008376137544304, |
| "learning_rate": 0.0007808266574356683, |
| "loss": 2.6438, |
| "step": 726 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.48820716669379344, |
| "learning_rate": 0.0007802118637114573, |
| "loss": 2.7063, |
| "step": 727 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.5009883736102675, |
| "learning_rate": 0.0007795964517353734, |
| "loss": 2.7783, |
| "step": 728 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.4659231723961216, |
| "learning_rate": 0.0007789804228652449, |
| "loss": 2.6872, |
| "step": 729 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.469741214676294, |
| "learning_rate": 0.0007783637784602609, |
| "loss": 2.5769, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5152514574156891, |
| "learning_rate": 0.0007777465198809692, |
| "loss": 2.636, |
| "step": 731 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.4980086399213333, |
| "learning_rate": 0.0007771286484892722, |
| "loss": 2.6577, |
| "step": 732 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.516818603051374, |
| "learning_rate": 0.000776510165648425, |
| "loss": 2.648, |
| "step": 733 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5075683643196635, |
| "learning_rate": 0.0007758910727230311, |
| "loss": 2.5922, |
| "step": 734 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.503983068805173, |
| "learning_rate": 0.0007752713710790404, |
| "loss": 2.5159, |
| "step": 735 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.4853808579083275, |
| "learning_rate": 0.0007746510620837459, |
| "loss": 2.684, |
| "step": 736 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5404508472264766, |
| "learning_rate": 0.0007740301471057807, |
| "loss": 2.6636, |
| "step": 737 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5391721483898614, |
| "learning_rate": 0.0007734086275151146, |
| "loss": 2.7155, |
| "step": 738 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5187089285840832, |
| "learning_rate": 0.0007727865046830517, |
| "loss": 2.6627, |
| "step": 739 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.4980868269802583, |
| "learning_rate": 0.0007721637799822269, |
| "loss": 2.6458, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5088986134874054, |
| "learning_rate": 0.0007715404547866032, |
| "loss": 2.6178, |
| "step": 741 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.6400960886309558, |
| "learning_rate": 0.0007709165304714685, |
| "loss": 2.5625, |
| "step": 742 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5340438252307524, |
| "learning_rate": 0.0007702920084134324, |
| "loss": 2.5971, |
| "step": 743 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.4910596650277195, |
| "learning_rate": 0.0007696668899904236, |
| "loss": 2.7426, |
| "step": 744 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5236995659806015, |
| "learning_rate": 0.0007690411765816864, |
| "loss": 2.5774, |
| "step": 745 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5033695540995622, |
| "learning_rate": 0.0007684148695677778, |
| "loss": 2.6691, |
| "step": 746 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5057856012189824, |
| "learning_rate": 0.000767787970330565, |
| "loss": 2.5154, |
| "step": 747 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5197205533305491, |
| "learning_rate": 0.000767160480253221, |
| "loss": 2.633, |
| "step": 748 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5405328286996239, |
| "learning_rate": 0.0007665324007202235, |
| "loss": 2.6621, |
| "step": 749 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5542375024274725, |
| "learning_rate": 0.0007659037331173498, |
| "loss": 2.6425, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.5199896610828446, |
| "learning_rate": 0.0007652744788316752, |
| "loss": 2.63, |
| "step": 751 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.4943417962403092, |
| "learning_rate": 0.0007646446392515692, |
| "loss": 2.7921, |
| "step": 752 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.5024239856826195, |
| "learning_rate": 0.000764014215766693, |
| "loss": 2.6609, |
| "step": 753 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.49782903590418215, |
| "learning_rate": 0.0007633832097679958, |
| "loss": 2.714, |
| "step": 754 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.4978967316281506, |
| "learning_rate": 0.0007627516226477122, |
| "loss": 2.6286, |
| "step": 755 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.499805628838432, |
| "learning_rate": 0.0007621194557993589, |
| "loss": 2.7185, |
| "step": 756 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.48950700222138466, |
| "learning_rate": 0.0007614867106177319, |
| "loss": 2.8366, |
| "step": 757 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.49672962330187775, |
| "learning_rate": 0.0007608533884989029, |
| "loss": 2.5802, |
| "step": 758 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.4809964108459586, |
| "learning_rate": 0.0007602194908402166, |
| "loss": 2.6885, |
| "step": 759 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.4928863383849547, |
| "learning_rate": 0.0007595850190402877, |
| "loss": 2.6761, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.5655941083167252, |
| "learning_rate": 0.0007589499744989976, |
| "loss": 2.648, |
| "step": 761 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.5033094826870588, |
| "learning_rate": 0.0007583143586174916, |
| "loss": 2.4775, |
| "step": 762 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.5421693215065777, |
| "learning_rate": 0.000757678172798175, |
| "loss": 2.7451, |
| "step": 763 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.4813537010984121, |
| "learning_rate": 0.0007570414184447112, |
| "loss": 2.5545, |
| "step": 764 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.5079025356679536, |
| "learning_rate": 0.0007564040969620179, |
| "loss": 2.5151, |
| "step": 765 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.5299383812243097, |
| "learning_rate": 0.0007557662097562636, |
| "loss": 2.7488, |
| "step": 766 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.5034875374235614, |
| "learning_rate": 0.0007551277582348658, |
| "loss": 2.6783, |
| "step": 767 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.5062730345377302, |
| "learning_rate": 0.0007544887438064862, |
| "loss": 2.6487, |
| "step": 768 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.47911723630381275, |
| "learning_rate": 0.0007538491678810294, |
| "loss": 2.622, |
| "step": 769 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.5368734867185738, |
| "learning_rate": 0.0007532090318696381, |
| "loss": 2.6507, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.4898209086510718, |
| "learning_rate": 0.0007525683371846913, |
| "loss": 2.5326, |
| "step": 771 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.47981612403894097, |
| "learning_rate": 0.0007519270852398001, |
| "loss": 2.6239, |
| "step": 772 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.5169260495925971, |
| "learning_rate": 0.000751285277449806, |
| "loss": 2.6164, |
| "step": 773 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.4918740454662726, |
| "learning_rate": 0.0007506429152307756, |
| "loss": 2.6829, |
| "step": 774 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.49843762700935923, |
| "learning_rate": 0.00075, |
| "loss": 2.655, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5225417750767407, |
| "learning_rate": 0.00074935653317599, |
| "loss": 2.6094, |
| "step": 776 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.45796901971030546, |
| "learning_rate": 0.000748712516178473, |
| "loss": 2.6143, |
| "step": 777 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.48948593570582205, |
| "learning_rate": 0.0007480679504283911, |
| "loss": 2.5953, |
| "step": 778 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.6534069263394732, |
| "learning_rate": 0.0007474228373478964, |
| "loss": 2.4699, |
| "step": 779 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.4932885934271518, |
| "learning_rate": 0.0007467771783603492, |
| "loss": 2.6767, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5261243421499394, |
| "learning_rate": 0.0007461309748903138, |
| "loss": 2.6068, |
| "step": 781 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5665671727764583, |
| "learning_rate": 0.0007454842283635562, |
| "loss": 2.6213, |
| "step": 782 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5037432414855236, |
| "learning_rate": 0.0007448369402070404, |
| "loss": 2.5171, |
| "step": 783 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.47416311673523087, |
| "learning_rate": 0.0007441891118489254, |
| "loss": 2.6265, |
| "step": 784 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5191819328187548, |
| "learning_rate": 0.0007435407447185622, |
| "loss": 2.6423, |
| "step": 785 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5249671236285853, |
| "learning_rate": 0.0007428918402464908, |
| "loss": 2.531, |
| "step": 786 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5202653264057286, |
| "learning_rate": 0.0007422423998644359, |
| "loss": 2.5294, |
| "step": 787 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5374037207991947, |
| "learning_rate": 0.0007415924250053055, |
| "loss": 2.5898, |
| "step": 788 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5096980188187046, |
| "learning_rate": 0.0007409419171031865, |
| "loss": 2.6428, |
| "step": 789 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5106185638358339, |
| "learning_rate": 0.0007402908775933419, |
| "loss": 2.787, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5412188303503519, |
| "learning_rate": 0.0007396393079122077, |
| "loss": 2.6233, |
| "step": 791 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5192001935221651, |
| "learning_rate": 0.0007389872094973896, |
| "loss": 2.7349, |
| "step": 792 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5270359354388962, |
| "learning_rate": 0.00073833458378766, |
| "loss": 2.7331, |
| "step": 793 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5090634055340401, |
| "learning_rate": 0.0007376814322229544, |
| "loss": 2.5773, |
| "step": 794 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.5500788369490899, |
| "learning_rate": 0.0007370277562443688, |
| "loss": 2.5945, |
| "step": 795 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.48862990885057206, |
| "learning_rate": 0.0007363735572941564, |
| "loss": 2.6061, |
| "step": 796 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5387298373204925, |
| "learning_rate": 0.0007357188368157236, |
| "loss": 2.5521, |
| "step": 797 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.4928593316405636, |
| "learning_rate": 0.0007350635962536284, |
| "loss": 2.6715, |
| "step": 798 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.6001375653191091, |
| "learning_rate": 0.0007344078370535756, |
| "loss": 2.5747, |
| "step": 799 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5005471338194297, |
| "learning_rate": 0.0007337515606624148, |
| "loss": 2.6258, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5538529216015211, |
| "learning_rate": 0.0007330947685281362, |
| "loss": 2.6679, |
| "step": 801 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5195096634956257, |
| "learning_rate": 0.0007324374620998682, |
| "loss": 2.6261, |
| "step": 802 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5076871416373812, |
| "learning_rate": 0.000731779642827874, |
| "loss": 2.622, |
| "step": 803 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5114291041296672, |
| "learning_rate": 0.0007311213121635483, |
| "loss": 2.6507, |
| "step": 804 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5160927776441065, |
| "learning_rate": 0.0007304624715594139, |
| "loss": 2.6523, |
| "step": 805 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.4716647082131927, |
| "learning_rate": 0.0007298031224691193, |
| "loss": 2.6256, |
| "step": 806 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5120089490438244, |
| "learning_rate": 0.0007291432663474339, |
| "loss": 2.5474, |
| "step": 807 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5187771884818635, |
| "learning_rate": 0.0007284829046502467, |
| "loss": 2.5333, |
| "step": 808 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.4993189341469725, |
| "learning_rate": 0.0007278220388345619, |
| "loss": 2.6069, |
| "step": 809 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5117522806051772, |
| "learning_rate": 0.0007271606703584958, |
| "loss": 2.5997, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5756106991936478, |
| "learning_rate": 0.000726498800681274, |
| "loss": 2.6332, |
| "step": 811 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5062546911557835, |
| "learning_rate": 0.0007258364312632279, |
| "loss": 2.7383, |
| "step": 812 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5318941152229897, |
| "learning_rate": 0.0007251735635657915, |
| "loss": 2.5477, |
| "step": 813 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5060814105918627, |
| "learning_rate": 0.000724510199051498, |
| "loss": 2.6313, |
| "step": 814 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.4751114674301648, |
| "learning_rate": 0.0007238463391839769, |
| "loss": 2.5949, |
| "step": 815 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.5452027198582088, |
| "learning_rate": 0.0007231819854279508, |
| "loss": 2.5861, |
| "step": 816 |
| }, |
| { |
| "epoch": 0.37, |
| "grad_norm": 0.48912749297577657, |
| "learning_rate": 0.0007225171392492316, |
| "loss": 2.7191, |
| "step": 817 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.6654645130908652, |
| "learning_rate": 0.0007218518021147182, |
| "loss": 2.54, |
| "step": 818 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.5177749379295773, |
| "learning_rate": 0.0007211859754923923, |
| "loss": 2.5988, |
| "step": 819 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.4608562798175019, |
| "learning_rate": 0.0007205196608513158, |
| "loss": 2.6842, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.4732611493468024, |
| "learning_rate": 0.0007198528596616272, |
| "loss": 2.5647, |
| "step": 821 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.500130899073409, |
| "learning_rate": 0.0007191855733945387, |
| "loss": 2.5399, |
| "step": 822 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.5467942645479031, |
| "learning_rate": 0.0007185178035223327, |
| "loss": 2.5407, |
| "step": 823 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.5306766000368929, |
| "learning_rate": 0.0007178495515183583, |
| "loss": 2.6368, |
| "step": 824 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.48221421584884006, |
| "learning_rate": 0.000717180818857029, |
| "loss": 2.682, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.5084267770960798, |
| "learning_rate": 0.0007165116070138182, |
| "loss": 2.7035, |
| "step": 826 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.5413480373408373, |
| "learning_rate": 0.0007158419174652569, |
| "loss": 2.5351, |
| "step": 827 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.4845871419905945, |
| "learning_rate": 0.00071517175168893, |
| "loss": 2.615, |
| "step": 828 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.5011043010033078, |
| "learning_rate": 0.0007145011111634732, |
| "loss": 2.7433, |
| "step": 829 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.4993843950403768, |
| "learning_rate": 0.0007138299973685694, |
| "loss": 2.5872, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.5014362953383041, |
| "learning_rate": 0.0007131584117849459, |
| "loss": 2.6472, |
| "step": 831 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.5198096005430778, |
| "learning_rate": 0.0007124863558943713, |
| "loss": 2.6275, |
| "step": 832 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.5065469601156936, |
| "learning_rate": 0.0007118138311796514, |
| "loss": 2.6688, |
| "step": 833 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.4848672893484705, |
| "learning_rate": 0.0007111408391246262, |
| "loss": 2.6492, |
| "step": 834 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.469939629569195, |
| "learning_rate": 0.0007104673812141675, |
| "loss": 2.6553, |
| "step": 835 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.4924971099279137, |
| "learning_rate": 0.0007097934589341745, |
| "loss": 2.6635, |
| "step": 836 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.4874698080279927, |
| "learning_rate": 0.0007091190737715711, |
| "loss": 2.5977, |
| "step": 837 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.47340158873949323, |
| "learning_rate": 0.0007084442272143026, |
| "loss": 2.4962, |
| "step": 838 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.4687048606346052, |
| "learning_rate": 0.000707768920751332, |
| "loss": 2.5425, |
| "step": 839 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5180636285666904, |
| "learning_rate": 0.0007070931558726373, |
| "loss": 2.5758, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.48324892831501354, |
| "learning_rate": 0.0007064169340692076, |
| "loss": 2.6005, |
| "step": 841 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5104427558503446, |
| "learning_rate": 0.0007057402568330407, |
| "loss": 2.7379, |
| "step": 842 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.4808464846757174, |
| "learning_rate": 0.0007050631256571389, |
| "loss": 2.6912, |
| "step": 843 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.4865993503084966, |
| "learning_rate": 0.000704385542035506, |
| "loss": 2.5581, |
| "step": 844 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5239838239288972, |
| "learning_rate": 0.000703707507463144, |
| "loss": 2.5916, |
| "step": 845 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5269947202599253, |
| "learning_rate": 0.0007030290234360505, |
| "loss": 2.7584, |
| "step": 846 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5691815197109601, |
| "learning_rate": 0.0007023500914512139, |
| "loss": 2.6368, |
| "step": 847 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5540971717762148, |
| "learning_rate": 0.0007016707130066116, |
| "loss": 2.6408, |
| "step": 848 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5416872991702514, |
| "learning_rate": 0.0007009908896012055, |
| "loss": 2.6063, |
| "step": 849 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.4756539066320772, |
| "learning_rate": 0.0007003106227349399, |
| "loss": 2.5105, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.4882687323656551, |
| "learning_rate": 0.000699629913908737, |
| "loss": 2.6872, |
| "step": 851 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5257784933794785, |
| "learning_rate": 0.0006989487646244943, |
| "loss": 2.5112, |
| "step": 852 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.464511055470616, |
| "learning_rate": 0.0006982671763850814, |
| "loss": 2.6785, |
| "step": 853 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.47228348156343614, |
| "learning_rate": 0.0006975851506943359, |
| "loss": 2.594, |
| "step": 854 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5124754997413656, |
| "learning_rate": 0.0006969026890570611, |
| "loss": 2.7041, |
| "step": 855 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.8281933196896523, |
| "learning_rate": 0.0006962197929790216, |
| "loss": 2.6274, |
| "step": 856 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5083217255638749, |
| "learning_rate": 0.0006955364639669409, |
| "loss": 2.5726, |
| "step": 857 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.48364133228919204, |
| "learning_rate": 0.0006948527035284978, |
| "loss": 2.6041, |
| "step": 858 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.506091985968748, |
| "learning_rate": 0.0006941685131723225, |
| "loss": 2.5186, |
| "step": 859 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.5021531169449972, |
| "learning_rate": 0.0006934838944079943, |
| "loss": 2.5852, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.39, |
| "grad_norm": 0.513351889232173, |
| "learning_rate": 0.0006927988487460378, |
| "loss": 2.6758, |
| "step": 861 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5121245179791045, |
| "learning_rate": 0.0006921133776979186, |
| "loss": 2.7138, |
| "step": 862 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.4992860625337511, |
| "learning_rate": 0.0006914274827760418, |
| "loss": 2.6527, |
| "step": 863 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5173680482025728, |
| "learning_rate": 0.0006907411654937475, |
| "loss": 2.6188, |
| "step": 864 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5016936739834356, |
| "learning_rate": 0.0006900544273653075, |
| "loss": 2.5223, |
| "step": 865 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5240322274244642, |
| "learning_rate": 0.000689367269905922, |
| "loss": 2.6587, |
| "step": 866 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.4840512836184572, |
| "learning_rate": 0.0006886796946317168, |
| "loss": 2.7042, |
| "step": 867 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5621089082465842, |
| "learning_rate": 0.0006879917030597397, |
| "loss": 2.562, |
| "step": 868 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.6357638905002186, |
| "learning_rate": 0.0006873032967079561, |
| "loss": 2.6532, |
| "step": 869 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.4890030287915046, |
| "learning_rate": 0.0006866144770952474, |
| "loss": 2.6008, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5056033168697459, |
| "learning_rate": 0.0006859252457414067, |
| "loss": 2.6498, |
| "step": 871 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5104938015296011, |
| "learning_rate": 0.0006852356041671351, |
| "loss": 2.6382, |
| "step": 872 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5307841173469469, |
| "learning_rate": 0.0006845455538940394, |
| "loss": 2.6491, |
| "step": 873 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5218099531927868, |
| "learning_rate": 0.0006838550964446276, |
| "loss": 2.6116, |
| "step": 874 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.48625066331584355, |
| "learning_rate": 0.0006831642333423067, |
| "loss": 2.555, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5680458697610679, |
| "learning_rate": 0.000682472966111378, |
| "loss": 2.6123, |
| "step": 876 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.4901863103216082, |
| "learning_rate": 0.0006817812962770348, |
| "loss": 2.6802, |
| "step": 877 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.47601238515957844, |
| "learning_rate": 0.0006810892253653589, |
| "loss": 2.6415, |
| "step": 878 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5335078397474983, |
| "learning_rate": 0.0006803967549033167, |
| "loss": 2.5863, |
| "step": 879 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.4539952433255645, |
| "learning_rate": 0.0006797038864187564, |
| "loss": 2.5759, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.4902638830372613, |
| "learning_rate": 0.0006790106214404043, |
| "loss": 2.6765, |
| "step": 881 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.4572143962178758, |
| "learning_rate": 0.0006783169614978614, |
| "loss": 2.6068, |
| "step": 882 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.5001614706984928, |
| "learning_rate": 0.0006776229081216001, |
| "loss": 2.5803, |
| "step": 883 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.4978614607556119, |
| "learning_rate": 0.0006769284628429611, |
| "loss": 2.6198, |
| "step": 884 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.4942746333237267, |
| "learning_rate": 0.0006762336271941498, |
| "loss": 2.5579, |
| "step": 885 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.4949714256331289, |
| "learning_rate": 0.0006755384027082326, |
| "loss": 2.5969, |
| "step": 886 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.49259816275669915, |
| "learning_rate": 0.0006748427909191342, |
| "loss": 2.5524, |
| "step": 887 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.4900060996477784, |
| "learning_rate": 0.0006741467933616335, |
| "loss": 2.524, |
| "step": 888 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.5698969026558444, |
| "learning_rate": 0.0006734504115713604, |
| "loss": 2.6651, |
| "step": 889 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.5076961480360436, |
| "learning_rate": 0.0006727536470847932, |
| "loss": 2.7112, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.49481661607185856, |
| "learning_rate": 0.000672056501439254, |
| "loss": 2.6263, |
| "step": 891 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.5208206490139011, |
| "learning_rate": 0.0006713589761729063, |
| "loss": 2.6166, |
| "step": 892 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.556796802041649, |
| "learning_rate": 0.0006706610728247508, |
| "loss": 2.3937, |
| "step": 893 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.5079132802397542, |
| "learning_rate": 0.0006699627929346227, |
| "loss": 2.7514, |
| "step": 894 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.47972328258947605, |
| "learning_rate": 0.0006692641380431879, |
| "loss": 2.6507, |
| "step": 895 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.46346084677829796, |
| "learning_rate": 0.0006685651096919393, |
| "loss": 2.5666, |
| "step": 896 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.506481445860542, |
| "learning_rate": 0.0006678657094231944, |
| "loss": 2.684, |
| "step": 897 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.47979502430937093, |
| "learning_rate": 0.0006671659387800909, |
| "loss": 2.5755, |
| "step": 898 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.4953577644349483, |
| "learning_rate": 0.000666465799306584, |
| "loss": 2.5121, |
| "step": 899 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.46962389310257296, |
| "learning_rate": 0.0006657652925474423, |
| "loss": 2.6936, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.499771183345115, |
| "learning_rate": 0.000665064420048245, |
| "loss": 2.5901, |
| "step": 901 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.5001110637782155, |
| "learning_rate": 0.0006643631833553785, |
| "loss": 2.6185, |
| "step": 902 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.5482579359825841, |
| "learning_rate": 0.000663661584016032, |
| "loss": 2.7865, |
| "step": 903 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.47414403594195514, |
| "learning_rate": 0.0006629596235781957, |
| "loss": 2.6704, |
| "step": 904 |
| }, |
| { |
| "epoch": 0.41, |
| "grad_norm": 0.4675706307124171, |
| "learning_rate": 0.0006622573035906556, |
| "loss": 2.6554, |
| "step": 905 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.48302002264934185, |
| "learning_rate": 0.0006615546256029921, |
| "loss": 2.6727, |
| "step": 906 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.49263113981341683, |
| "learning_rate": 0.0006608515911655743, |
| "loss": 2.5784, |
| "step": 907 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.5034710210130895, |
| "learning_rate": 0.0006601482018295591, |
| "loss": 2.5312, |
| "step": 908 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.5460240391734935, |
| "learning_rate": 0.0006594444591468851, |
| "loss": 2.6502, |
| "step": 909 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.5333076944291396, |
| "learning_rate": 0.0006587403646702713, |
| "loss": 2.6624, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.5193829905440761, |
| "learning_rate": 0.0006580359199532126, |
| "loss": 2.6477, |
| "step": 911 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.4810943773722182, |
| "learning_rate": 0.000657331126549977, |
| "loss": 2.6201, |
| "step": 912 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.5849002682876532, |
| "learning_rate": 0.0006566259860156014, |
| "loss": 2.6133, |
| "step": 913 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.520201558269608, |
| "learning_rate": 0.0006559204999058888, |
| "loss": 2.6175, |
| "step": 914 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.48715615710257376, |
| "learning_rate": 0.0006552146697774049, |
| "loss": 2.6167, |
| "step": 915 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.4933916865571285, |
| "learning_rate": 0.0006545084971874737, |
| "loss": 2.5732, |
| "step": 916 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.47208272694867753, |
| "learning_rate": 0.0006538019836941758, |
| "loss": 2.5341, |
| "step": 917 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.5274866125704785, |
| "learning_rate": 0.0006530951308563431, |
| "loss": 2.5958, |
| "step": 918 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.4930654945250193, |
| "learning_rate": 0.0006523879402335567, |
| "loss": 2.5599, |
| "step": 919 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.45768778447037867, |
| "learning_rate": 0.0006516804133861429, |
| "loss": 2.5575, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.47312762411497267, |
| "learning_rate": 0.0006509725518751698, |
| "loss": 2.6976, |
| "step": 921 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.7815791471938398, |
| "learning_rate": 0.0006502643572624438, |
| "loss": 2.5052, |
| "step": 922 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.45781078559413346, |
| "learning_rate": 0.0006495558311105064, |
| "loss": 2.5508, |
| "step": 923 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.4786949076813085, |
| "learning_rate": 0.0006488469749826305, |
| "loss": 2.5752, |
| "step": 924 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.46018002827630095, |
| "learning_rate": 0.000648137790442817, |
| "loss": 2.5097, |
| "step": 925 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.4798543873471958, |
| "learning_rate": 0.0006474282790557916, |
| "loss": 2.5578, |
| "step": 926 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.46107048661421923, |
| "learning_rate": 0.000646718442387001, |
| "loss": 2.6017, |
| "step": 927 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.4656781292518367, |
| "learning_rate": 0.0006460082820026094, |
| "loss": 2.5737, |
| "step": 928 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.5091166961122364, |
| "learning_rate": 0.0006452977994694959, |
| "loss": 2.4595, |
| "step": 929 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.46921798795838876, |
| "learning_rate": 0.0006445869963552496, |
| "loss": 2.6933, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.5215508925810978, |
| "learning_rate": 0.0006438758742281672, |
| "loss": 2.5432, |
| "step": 931 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.5711713789738587, |
| "learning_rate": 0.0006431644346572495, |
| "loss": 2.6963, |
| "step": 932 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.4918468771002222, |
| "learning_rate": 0.0006424526792121974, |
| "loss": 2.6904, |
| "step": 933 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.4846683371573201, |
| "learning_rate": 0.0006417406094634089, |
| "loss": 2.5194, |
| "step": 934 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.462505202200313, |
| "learning_rate": 0.0006410282269819756, |
| "loss": 2.5543, |
| "step": 935 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.45142203675522, |
| "learning_rate": 0.0006403155333396787, |
| "loss": 2.6707, |
| "step": 936 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.46741352176192896, |
| "learning_rate": 0.0006396025301089863, |
| "loss": 2.5685, |
| "step": 937 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.4872999922314525, |
| "learning_rate": 0.0006388892188630493, |
| "loss": 2.6183, |
| "step": 938 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.4886167731766419, |
| "learning_rate": 0.0006381756011756982, |
| "loss": 2.618, |
| "step": 939 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.5536900036780444, |
| "learning_rate": 0.0006374616786214403, |
| "loss": 2.5775, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.492476400793871, |
| "learning_rate": 0.0006367474527754544, |
| "loss": 2.6323, |
| "step": 941 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.48893358058507796, |
| "learning_rate": 0.0006360329252135894, |
| "loss": 2.499, |
| "step": 942 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.5324438375785346, |
| "learning_rate": 0.0006353180975123595, |
| "loss": 2.5781, |
| "step": 943 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.5156506730690181, |
| "learning_rate": 0.0006346029712489413, |
| "loss": 2.6874, |
| "step": 944 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.5003705569703046, |
| "learning_rate": 0.0006338875480011698, |
| "loss": 2.6368, |
| "step": 945 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.5081120857421467, |
| "learning_rate": 0.0006331718293475357, |
| "loss": 2.4931, |
| "step": 946 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.5198629666750033, |
| "learning_rate": 0.0006324558168671811, |
| "loss": 2.7714, |
| "step": 947 |
| }, |
| { |
| "epoch": 0.43, |
| "grad_norm": 0.5058373739828541, |
| "learning_rate": 0.0006317395121398968, |
| "loss": 2.5653, |
| "step": 948 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.569126772486162, |
| "learning_rate": 0.0006310229167461179, |
| "loss": 2.7054, |
| "step": 949 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.46850314112376235, |
| "learning_rate": 0.0006303060322669214, |
| "loss": 2.592, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.4613972304711361, |
| "learning_rate": 0.0006295888602840214, |
| "loss": 2.5595, |
| "step": 951 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.48506161976123746, |
| "learning_rate": 0.0006288714023797671, |
| "loss": 2.6063, |
| "step": 952 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.48049835657720347, |
| "learning_rate": 0.000628153660137138, |
| "loss": 2.5625, |
| "step": 953 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.5035052228346791, |
| "learning_rate": 0.0006274356351397413, |
| "loss": 2.6186, |
| "step": 954 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.5062119180466912, |
| "learning_rate": 0.0006267173289718079, |
| "loss": 2.5269, |
| "step": 955 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.5007432898517803, |
| "learning_rate": 0.000625998743218189, |
| "loss": 2.596, |
| "step": 956 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.518672943891324, |
| "learning_rate": 0.000625279879464353, |
| "loss": 2.5877, |
| "step": 957 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.5428092584678056, |
| "learning_rate": 0.000624560739296381, |
| "loss": 2.6649, |
| "step": 958 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.49793503976455716, |
| "learning_rate": 0.0006238413243009648, |
| "loss": 2.6289, |
| "step": 959 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.5108946921359309, |
| "learning_rate": 0.000623121636065402, |
| "loss": 2.6196, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.5075054021053248, |
| "learning_rate": 0.0006224016761775933, |
| "loss": 2.6071, |
| "step": 961 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.5018308306198189, |
| "learning_rate": 0.0006216814462260386, |
| "loss": 2.6505, |
| "step": 962 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.5489559014707082, |
| "learning_rate": 0.0006209609477998338, |
| "loss": 2.6472, |
| "step": 963 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.5033502432261472, |
| "learning_rate": 0.0006202401824886674, |
| "loss": 2.5487, |
| "step": 964 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.47371337698280985, |
| "learning_rate": 0.0006195191518828162, |
| "loss": 2.5569, |
| "step": 965 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.490235122611094, |
| "learning_rate": 0.0006187978575731427, |
| "loss": 2.6342, |
| "step": 966 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.45991486109341867, |
| "learning_rate": 0.0006180763011510911, |
| "loss": 2.6306, |
| "step": 967 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.4691686183113801, |
| "learning_rate": 0.000617354484208684, |
| "loss": 2.5883, |
| "step": 968 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.4826111860921563, |
| "learning_rate": 0.0006166324083385189, |
| "loss": 2.5151, |
| "step": 969 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.46998949870523504, |
| "learning_rate": 0.0006159100751337642, |
| "loss": 2.567, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.6505948544143287, |
| "learning_rate": 0.0006151874861881565, |
| "loss": 2.5785, |
| "step": 971 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.4875416066960976, |
| "learning_rate": 0.0006144646430959964, |
| "loss": 2.5721, |
| "step": 972 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.48908393943068057, |
| "learning_rate": 0.0006137415474521454, |
| "loss": 2.7258, |
| "step": 973 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.4653396515836369, |
| "learning_rate": 0.0006130182008520222, |
| "loss": 2.6658, |
| "step": 974 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.44820354066808465, |
| "learning_rate": 0.000612294604891599, |
| "loss": 2.6617, |
| "step": 975 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.48302769816114616, |
| "learning_rate": 0.0006115707611673986, |
| "loss": 2.6433, |
| "step": 976 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.4792194401504088, |
| "learning_rate": 0.0006108466712764902, |
| "loss": 2.5897, |
| "step": 977 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.4986121221928656, |
| "learning_rate": 0.0006101223368164858, |
| "loss": 2.637, |
| "step": 978 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.49112249819668663, |
| "learning_rate": 0.0006093977593855375, |
| "loss": 2.609, |
| "step": 979 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.487492736076904, |
| "learning_rate": 0.0006086729405823335, |
| "loss": 2.6014, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.5118450279977643, |
| "learning_rate": 0.0006079478820060943, |
| "loss": 2.5801, |
| "step": 981 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.5406173621078206, |
| "learning_rate": 0.0006072225852565695, |
| "loss": 2.6059, |
| "step": 982 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.5416460304817735, |
| "learning_rate": 0.0006064970519340341, |
| "loss": 2.5781, |
| "step": 983 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.47817677197539177, |
| "learning_rate": 0.0006057712836392856, |
| "loss": 2.5957, |
| "step": 984 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.5197895910356457, |
| "learning_rate": 0.0006050452819736389, |
| "loss": 2.593, |
| "step": 985 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.5355710810015067, |
| "learning_rate": 0.000604319048538925, |
| "loss": 2.5158, |
| "step": 986 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.48819765134633875, |
| "learning_rate": 0.0006035925849374855, |
| "loss": 2.631, |
| "step": 987 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.48961309996203733, |
| "learning_rate": 0.0006028658927721697, |
| "loss": 2.6103, |
| "step": 988 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.45553899281513754, |
| "learning_rate": 0.0006021389736463321, |
| "loss": 2.5334, |
| "step": 989 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.48384154402255175, |
| "learning_rate": 0.0006014118291638271, |
| "loss": 2.5288, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.49066493568584363, |
| "learning_rate": 0.0006006844609290065, |
| "loss": 2.6104, |
| "step": 991 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 0.48904124072585536, |
| "learning_rate": 0.0005999568705467161, |
| "loss": 2.6363, |
| "step": 992 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.4744443827182406, |
| "learning_rate": 0.0005992290596222915, |
| "loss": 2.6371, |
| "step": 993 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.5155250265479482, |
| "learning_rate": 0.0005985010297615551, |
| "loss": 2.5371, |
| "step": 994 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.5489196400821047, |
| "learning_rate": 0.0005977727825708123, |
| "loss": 2.6149, |
| "step": 995 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.4610203794648474, |
| "learning_rate": 0.0005970443196568478, |
| "loss": 2.4639, |
| "step": 996 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.486280431459794, |
| "learning_rate": 0.0005963156426269227, |
| "loss": 2.6164, |
| "step": 997 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.5304650247567722, |
| "learning_rate": 0.0005955867530887702, |
| "loss": 2.6158, |
| "step": 998 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.48832926954739747, |
| "learning_rate": 0.0005948576526505923, |
| "loss": 2.5533, |
| "step": 999 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.49084287359527395, |
| "learning_rate": 0.0005941283429210568, |
| "loss": 2.6339, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.4751825107693994, |
| "learning_rate": 0.0005933988255092926, |
| "loss": 2.5624, |
| "step": 1001 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.5412149949295578, |
| "learning_rate": 0.0005926691020248874, |
| "loss": 2.5846, |
| "step": 1002 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.49332400780709607, |
| "learning_rate": 0.0005919391740778833, |
| "loss": 2.5239, |
| "step": 1003 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.4883063259039968, |
| "learning_rate": 0.0005912090432787736, |
| "loss": 2.5575, |
| "step": 1004 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.4827236879858857, |
| "learning_rate": 0.000590478711238499, |
| "loss": 2.6041, |
| "step": 1005 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.4672710500987914, |
| "learning_rate": 0.0005897481795684446, |
| "loss": 2.5629, |
| "step": 1006 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.4828107461865755, |
| "learning_rate": 0.0005890174498804355, |
| "loss": 2.6065, |
| "step": 1007 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.6147410421667513, |
| "learning_rate": 0.0005882865237867339, |
| "loss": 2.5857, |
| "step": 1008 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.4697196393824099, |
| "learning_rate": 0.0005875554029000353, |
| "loss": 2.5832, |
| "step": 1009 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.5522453153686488, |
| "learning_rate": 0.0005868240888334653, |
| "loss": 2.5483, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.5048999246632299, |
| "learning_rate": 0.0005860925832005753, |
| "loss": 2.5707, |
| "step": 1011 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.5087495418310176, |
| "learning_rate": 0.0005853608876153395, |
| "loss": 2.6485, |
| "step": 1012 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.5044919237584781, |
| "learning_rate": 0.0005846290036921512, |
| "loss": 2.585, |
| "step": 1013 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 0.4825861643512527, |
| "learning_rate": 0.0005838969330458195, |
| "loss": 2.5881, |
| "step": 1014 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.49433453504631586, |
| "learning_rate": 0.0005831646772915651, |
| "loss": 2.5263, |
| "step": 1015 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.48176105458829344, |
| "learning_rate": 0.0005824322380450173, |
| "loss": 2.6433, |
| "step": 1016 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.4811824763117871, |
| "learning_rate": 0.0005816996169222102, |
| "loss": 2.5914, |
| "step": 1017 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.44664846263894153, |
| "learning_rate": 0.0005809668155395793, |
| "loss": 2.6338, |
| "step": 1018 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.48015706917802126, |
| "learning_rate": 0.0005802338355139578, |
| "loss": 2.5372, |
| "step": 1019 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.48507991526984334, |
| "learning_rate": 0.0005795006784625728, |
| "loss": 2.6549, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.4531354072624084, |
| "learning_rate": 0.0005787673460030423, |
| "loss": 2.5455, |
| "step": 1021 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.46961966288855694, |
| "learning_rate": 0.000578033839753371, |
| "loss": 2.604, |
| "step": 1022 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.5171394072034508, |
| "learning_rate": 0.0005773001613319476, |
| "loss": 2.4944, |
| "step": 1023 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.46695112398751404, |
| "learning_rate": 0.00057656631235754, |
| "loss": 2.5454, |
| "step": 1024 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.4741929756135385, |
| "learning_rate": 0.0005758322944492929, |
| "loss": 2.6943, |
| "step": 1025 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.4749606044265288, |
| "learning_rate": 0.0005750981092267237, |
| "loss": 2.5839, |
| "step": 1026 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.5373625595062073, |
| "learning_rate": 0.0005743637583097183, |
| "loss": 2.5793, |
| "step": 1027 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.46754624945624196, |
| "learning_rate": 0.0005736292433185291, |
| "loss": 2.6454, |
| "step": 1028 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.49119848992209647, |
| "learning_rate": 0.0005728945658737699, |
| "loss": 2.5763, |
| "step": 1029 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.5043113747345601, |
| "learning_rate": 0.0005721597275964133, |
| "loss": 2.6832, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.4748417781715398, |
| "learning_rate": 0.0005714247301077865, |
| "loss": 2.8747, |
| "step": 1031 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.48907437696127326, |
| "learning_rate": 0.0005706895750295682, |
| "loss": 2.5702, |
| "step": 1032 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.5074165640140402, |
| "learning_rate": 0.0005699542639837844, |
| "loss": 2.6779, |
| "step": 1033 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.48616813252574587, |
| "learning_rate": 0.0005692187985928055, |
| "loss": 2.5749, |
| "step": 1034 |
| }, |
| { |
| "epoch": 0.47, |
| "grad_norm": 0.4876684363537643, |
| "learning_rate": 0.0005684831804793427, |
| "loss": 2.5724, |
| "step": 1035 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.4980270499303405, |
| "learning_rate": 0.0005677474112664438, |
| "loss": 2.6105, |
| "step": 1036 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.6146714434793061, |
| "learning_rate": 0.0005670114925774899, |
| "loss": 2.703, |
| "step": 1037 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.4987558443967257, |
| "learning_rate": 0.0005662754260361924, |
| "loss": 2.6365, |
| "step": 1038 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.49126801109874413, |
| "learning_rate": 0.0005655392132665884, |
| "loss": 2.8046, |
| "step": 1039 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.48814283352791077, |
| "learning_rate": 0.000564802855893038, |
| "loss": 2.6187, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.5383754061624473, |
| "learning_rate": 0.0005640663555402198, |
| "loss": 2.6115, |
| "step": 1041 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.491737539813333, |
| "learning_rate": 0.0005633297138331285, |
| "loss": 2.5706, |
| "step": 1042 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.5086927101847561, |
| "learning_rate": 0.0005625929323970705, |
| "loss": 2.5448, |
| "step": 1043 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.6831674146693324, |
| "learning_rate": 0.0005618560128576603, |
| "loss": 2.5549, |
| "step": 1044 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.5024033962043765, |
| "learning_rate": 0.0005611189568408173, |
| "loss": 2.5801, |
| "step": 1045 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.5226498327797711, |
| "learning_rate": 0.0005603817659727619, |
| "loss": 2.497, |
| "step": 1046 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.5131567745916148, |
| "learning_rate": 0.0005596444418800121, |
| "loss": 2.6763, |
| "step": 1047 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.5141126423699963, |
| "learning_rate": 0.0005589069861893798, |
| "loss": 2.5548, |
| "step": 1048 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.5264933059500744, |
| "learning_rate": 0.0005581694005279673, |
| "loss": 2.4227, |
| "step": 1049 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.4738752468530269, |
| "learning_rate": 0.0005574316865231637, |
| "loss": 2.4673, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.5034035791677333, |
| "learning_rate": 0.0005566938458026411, |
| "loss": 2.5719, |
| "step": 1051 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.5439846366046128, |
| "learning_rate": 0.0005559558799943514, |
| "loss": 2.5983, |
| "step": 1052 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.554677797453197, |
| "learning_rate": 0.0005552177907265223, |
| "loss": 2.5193, |
| "step": 1053 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.5139297686286605, |
| "learning_rate": 0.000554479579627654, |
| "loss": 2.5956, |
| "step": 1054 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.6688641723470222, |
| "learning_rate": 0.0005537412483265157, |
| "loss": 2.5694, |
| "step": 1055 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.7901300223007175, |
| "learning_rate": 0.0005530027984521413, |
| "loss": 2.5077, |
| "step": 1056 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.4924850457538904, |
| "learning_rate": 0.0005522642316338268, |
| "loss": 2.5207, |
| "step": 1057 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.49114079443129455, |
| "learning_rate": 0.0005515255495011259, |
| "loss": 2.6157, |
| "step": 1058 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4692662885440379, |
| "learning_rate": 0.0005507867536838472, |
| "loss": 2.6147, |
| "step": 1059 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4751978722445961, |
| "learning_rate": 0.0005500478458120492, |
| "loss": 2.4996, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4749827485817902, |
| "learning_rate": 0.0005493088275160387, |
| "loss": 2.6609, |
| "step": 1061 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.49428317593988186, |
| "learning_rate": 0.0005485697004263657, |
| "loss": 2.5614, |
| "step": 1062 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4935789178135557, |
| "learning_rate": 0.0005478304661738199, |
| "loss": 2.7314, |
| "step": 1063 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.49607318505757797, |
| "learning_rate": 0.0005470911263894279, |
| "loss": 2.6142, |
| "step": 1064 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.5144462012328416, |
| "learning_rate": 0.0005463516827044491, |
| "loss": 2.5873, |
| "step": 1065 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4639940808792902, |
| "learning_rate": 0.000545612136750372, |
| "loss": 2.5284, |
| "step": 1066 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4729172525532307, |
| "learning_rate": 0.0005448724901589107, |
| "loss": 2.5932, |
| "step": 1067 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.47467970331297166, |
| "learning_rate": 0.0005441327445620014, |
| "loss": 2.7455, |
| "step": 1068 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.45806739525112655, |
| "learning_rate": 0.0005433929015917988, |
| "loss": 2.4958, |
| "step": 1069 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.49095221712195775, |
| "learning_rate": 0.0005426529628806724, |
| "loss": 2.6721, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4663386360554239, |
| "learning_rate": 0.0005419129300612029, |
| "loss": 2.5783, |
| "step": 1071 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4621762547361632, |
| "learning_rate": 0.000541172804766179, |
| "loss": 2.5061, |
| "step": 1072 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.5003155348713653, |
| "learning_rate": 0.0005404325886285927, |
| "loss": 2.5712, |
| "step": 1073 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.6729727876949734, |
| "learning_rate": 0.000539692283281637, |
| "loss": 2.5728, |
| "step": 1074 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.5656057416122677, |
| "learning_rate": 0.0005389518903587017, |
| "loss": 2.5309, |
| "step": 1075 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.5354917692851118, |
| "learning_rate": 0.0005382114114933695, |
| "loss": 2.5837, |
| "step": 1076 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4956493222852819, |
| "learning_rate": 0.0005374708483194132, |
| "loss": 2.6065, |
| "step": 1077 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4968247173298669, |
| "learning_rate": 0.000536730202470791, |
| "loss": 2.5065, |
| "step": 1078 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.4810138008360289, |
| "learning_rate": 0.0005359894755816443, |
| "loss": 2.5543, |
| "step": 1079 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.49513012883762525, |
| "learning_rate": 0.0005352486692862926, |
| "loss": 2.5036, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5182698803176612, |
| "learning_rate": 0.0005345077852192307, |
| "loss": 2.6555, |
| "step": 1081 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5101267801645413, |
| "learning_rate": 0.0005337668250151254, |
| "loss": 2.5682, |
| "step": 1082 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.467740622685136, |
| "learning_rate": 0.0005330257903088111, |
| "loss": 2.5016, |
| "step": 1083 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.4809646540167895, |
| "learning_rate": 0.000532284682735287, |
| "loss": 2.4971, |
| "step": 1084 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5156666407318927, |
| "learning_rate": 0.0005315435039297124, |
| "loss": 2.4928, |
| "step": 1085 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5060357915571028, |
| "learning_rate": 0.0005308022555274046, |
| "loss": 2.5168, |
| "step": 1086 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5133828297137754, |
| "learning_rate": 0.0005300609391638336, |
| "loss": 2.4902, |
| "step": 1087 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5173907124542971, |
| "learning_rate": 0.0005293195564746201, |
| "loss": 2.6082, |
| "step": 1088 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.4830331639741894, |
| "learning_rate": 0.0005285781090955304, |
| "loss": 2.612, |
| "step": 1089 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.4529877983557972, |
| "learning_rate": 0.0005278365986624743, |
| "loss": 2.6088, |
| "step": 1090 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.4851056718035542, |
| "learning_rate": 0.0005270950268115001, |
| "loss": 2.5571, |
| "step": 1091 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.4976717567350475, |
| "learning_rate": 0.0005263533951787919, |
| "loss": 2.7147, |
| "step": 1092 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.4779899753464984, |
| "learning_rate": 0.000525611705400666, |
| "loss": 2.691, |
| "step": 1093 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5523597494655119, |
| "learning_rate": 0.0005248699591135664, |
| "loss": 2.6002, |
| "step": 1094 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.46594210796481766, |
| "learning_rate": 0.0005241281579540618, |
| "loss": 2.6322, |
| "step": 1095 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.4929144243629796, |
| "learning_rate": 0.0005233863035588427, |
| "loss": 2.515, |
| "step": 1096 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5443502881940565, |
| "learning_rate": 0.0005226443975647161, |
| "loss": 2.5802, |
| "step": 1097 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5025124870348087, |
| "learning_rate": 0.0005219024416086036, |
| "loss": 2.5631, |
| "step": 1098 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.6004752467724771, |
| "learning_rate": 0.0005211604373275366, |
| "loss": 2.5877, |
| "step": 1099 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.4924040193167507, |
| "learning_rate": 0.0005204183863586533, |
| "loss": 2.6153, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5072856030893523, |
| "learning_rate": 0.0005196762903391951, |
| "loss": 2.4809, |
| "step": 1101 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.440099246754052, |
| "learning_rate": 0.0005189341509065023, |
| "loss": 2.5165, |
| "step": 1102 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.5210944201539706, |
| "learning_rate": 0.0005181919696980112, |
| "loss": 2.643, |
| "step": 1103 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.5079715522952144, |
| "learning_rate": 0.0005174497483512506, |
| "loss": 2.5404, |
| "step": 1104 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.4716346672816434, |
| "learning_rate": 0.0005167074885038374, |
| "loss": 2.5778, |
| "step": 1105 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.5265027308685682, |
| "learning_rate": 0.0005159651917934735, |
| "loss": 2.5361, |
| "step": 1106 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.4992701021604148, |
| "learning_rate": 0.0005152228598579428, |
| "loss": 2.6493, |
| "step": 1107 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.5059452642163268, |
| "learning_rate": 0.000514480494335106, |
| "loss": 2.5574, |
| "step": 1108 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.4887996719158124, |
| "learning_rate": 0.0005137380968628983, |
| "loss": 2.5906, |
| "step": 1109 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.46953922819541316, |
| "learning_rate": 0.0005129956690793255, |
| "loss": 2.5079, |
| "step": 1110 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.5100585084626605, |
| "learning_rate": 0.0005122532126224601, |
| "loss": 2.6128, |
| "step": 1111 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.4754515229059993, |
| "learning_rate": 0.0005115107291304378, |
| "loss": 2.5515, |
| "step": 1112 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.49677501819553604, |
| "learning_rate": 0.0005107682202414544, |
| "loss": 2.5133, |
| "step": 1113 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.5109530469944327, |
| "learning_rate": 0.0005100256875937613, |
| "loss": 2.546, |
| "step": 1114 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.4902881263341436, |
| "learning_rate": 0.0005092831328256625, |
| "loss": 2.6095, |
| "step": 1115 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.4784691093909391, |
| "learning_rate": 0.0005085405575755105, |
| "loss": 2.5617, |
| "step": 1116 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.8066808152095734, |
| "learning_rate": 0.0005077979634817034, |
| "loss": 2.6607, |
| "step": 1117 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.501806651108021, |
| "learning_rate": 0.0005070553521826808, |
| "loss": 2.6595, |
| "step": 1118 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.58896709318231, |
| "learning_rate": 0.00050631272531692, |
| "loss": 2.5293, |
| "step": 1119 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.4959960829284305, |
| "learning_rate": 0.0005055700845229327, |
| "loss": 2.6362, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.5119601135869184, |
| "learning_rate": 0.000504827431439262, |
| "loss": 2.4794, |
| "step": 1121 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.5307688680918823, |
| "learning_rate": 0.000504084767704477, |
| "loss": 2.7174, |
| "step": 1122 |
| }, |
| { |
| "epoch": 0.51, |
| "grad_norm": 0.5084070907453492, |
| "learning_rate": 0.0005033420949571712, |
| "loss": 2.511, |
| "step": 1123 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.48031119824548285, |
| "learning_rate": 0.0005025994148359574, |
| "loss": 2.6054, |
| "step": 1124 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.475555447795644, |
| "learning_rate": 0.0005018567289794651, |
| "loss": 2.5638, |
| "step": 1125 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.4890864245490359, |
| "learning_rate": 0.0005011140390263362, |
| "loss": 2.5094, |
| "step": 1126 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.47214161500079566, |
| "learning_rate": 0.0005003713466152218, |
| "loss": 2.5932, |
| "step": 1127 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.49299554192875095, |
| "learning_rate": 0.0004996286533847783, |
| "loss": 2.6078, |
| "step": 1128 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.46766640462326403, |
| "learning_rate": 0.000498885960973664, |
| "loss": 2.5225, |
| "step": 1129 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.4677002907912059, |
| "learning_rate": 0.000498143271020535, |
| "loss": 2.646, |
| "step": 1130 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.471490363973374, |
| "learning_rate": 0.0004974005851640428, |
| "loss": 2.4734, |
| "step": 1131 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.5074414256665462, |
| "learning_rate": 0.000496657905042829, |
| "loss": 2.5437, |
| "step": 1132 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.46617628689130736, |
| "learning_rate": 0.0004959152322955232, |
| "loss": 2.6067, |
| "step": 1133 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.6021325399791526, |
| "learning_rate": 0.0004951725685607382, |
| "loss": 2.5564, |
| "step": 1134 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.4916982097564103, |
| "learning_rate": 0.0004944299154770673, |
| "loss": 2.5587, |
| "step": 1135 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.4863671675224928, |
| "learning_rate": 0.0004936872746830802, |
| "loss": 2.546, |
| "step": 1136 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.471495147020904, |
| "learning_rate": 0.0004929446478173195, |
| "loss": 2.5092, |
| "step": 1137 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.5910734512742601, |
| "learning_rate": 0.0004922020365182968, |
| "loss": 2.5281, |
| "step": 1138 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.47079993192903213, |
| "learning_rate": 0.0004914594424244897, |
| "loss": 2.443, |
| "step": 1139 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.567672411796144, |
| "learning_rate": 0.0004907168671743376, |
| "loss": 2.5567, |
| "step": 1140 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.5036195750337888, |
| "learning_rate": 0.0004899743124062387, |
| "loss": 2.5901, |
| "step": 1141 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.47588335280875477, |
| "learning_rate": 0.0004892317797585456, |
| "loss": 2.5868, |
| "step": 1142 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.48300398166645137, |
| "learning_rate": 0.0004884892708695623, |
| "loss": 2.512, |
| "step": 1143 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.4827611671666561, |
| "learning_rate": 0.0004877467873775402, |
| "loss": 2.5594, |
| "step": 1144 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.47008748094829705, |
| "learning_rate": 0.00048700433092067473, |
| "loss": 2.6153, |
| "step": 1145 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.4764111138569683, |
| "learning_rate": 0.0004862619031371019, |
| "loss": 2.58, |
| "step": 1146 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.4991102421030436, |
| "learning_rate": 0.0004855195056648942, |
| "loss": 2.5521, |
| "step": 1147 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.4672443974346137, |
| "learning_rate": 0.00048477714014205734, |
| "loss": 2.6519, |
| "step": 1148 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.49732193150229714, |
| "learning_rate": 0.00048403480820652644, |
| "loss": 2.5519, |
| "step": 1149 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.5003177147433701, |
| "learning_rate": 0.0004832925114961629, |
| "loss": 2.7171, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.47157589459670907, |
| "learning_rate": 0.0004825502516487497, |
| "loss": 2.5116, |
| "step": 1151 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.47395607540409296, |
| "learning_rate": 0.00048180803030198896, |
| "loss": 2.6144, |
| "step": 1152 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.516504072258377, |
| "learning_rate": 0.0004810658490934979, |
| "loss": 2.58, |
| "step": 1153 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.464283020526906, |
| "learning_rate": 0.000480323709660805, |
| "loss": 2.5911, |
| "step": 1154 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.47926203234386505, |
| "learning_rate": 0.0004795816136413467, |
| "loss": 2.4417, |
| "step": 1155 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.46451940229063404, |
| "learning_rate": 0.00047883956267246353, |
| "loss": 2.5138, |
| "step": 1156 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.5383970282931108, |
| "learning_rate": 0.00047809755839139657, |
| "loss": 2.5126, |
| "step": 1157 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.4596243114987058, |
| "learning_rate": 0.0004773556024352841, |
| "loss": 2.5495, |
| "step": 1158 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.5032269632935293, |
| "learning_rate": 0.00047661369644115754, |
| "loss": 2.6198, |
| "step": 1159 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.5053826078691768, |
| "learning_rate": 0.0004758718420459383, |
| "loss": 2.5607, |
| "step": 1160 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.4782103976413002, |
| "learning_rate": 0.0004751300408864339, |
| "loss": 2.5102, |
| "step": 1161 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.5110613870908824, |
| "learning_rate": 0.00047438829459933414, |
| "loss": 2.5141, |
| "step": 1162 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.49007991562410763, |
| "learning_rate": 0.0004736466048212082, |
| "loss": 2.6601, |
| "step": 1163 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.4872797656909252, |
| "learning_rate": 0.0004729049731885002, |
| "loss": 2.7242, |
| "step": 1164 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.4790674005596643, |
| "learning_rate": 0.000472163401337526, |
| "loss": 2.5512, |
| "step": 1165 |
| }, |
| { |
| "epoch": 0.53, |
| "grad_norm": 0.46386523005716945, |
| "learning_rate": 0.00047142189090446985, |
| "loss": 2.5223, |
| "step": 1166 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.5717488223024524, |
| "learning_rate": 0.0004706804435253802, |
| "loss": 2.5852, |
| "step": 1167 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.49400519968724277, |
| "learning_rate": 0.0004699390608361665, |
| "loss": 2.6773, |
| "step": 1168 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.4938392017929943, |
| "learning_rate": 0.0004691977444725955, |
| "loss": 2.5567, |
| "step": 1169 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.4793193234106016, |
| "learning_rate": 0.0004684564960702877, |
| "loss": 2.6884, |
| "step": 1170 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.4608313006288057, |
| "learning_rate": 0.0004677153172647131, |
| "loss": 2.5058, |
| "step": 1171 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.47909891978115254, |
| "learning_rate": 0.00046697420969118894, |
| "loss": 2.5208, |
| "step": 1172 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.4863878199377069, |
| "learning_rate": 0.00046623317498487466, |
| "loss": 2.4783, |
| "step": 1173 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.5121135043312043, |
| "learning_rate": 0.0004654922147807694, |
| "loss": 2.5928, |
| "step": 1174 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.48288887254818563, |
| "learning_rate": 0.00046475133071370757, |
| "loss": 2.4906, |
| "step": 1175 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.48892430693402233, |
| "learning_rate": 0.00046401052441835574, |
| "loss": 2.5101, |
| "step": 1176 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.47744926962413686, |
| "learning_rate": 0.000463269797529209, |
| "loss": 2.5464, |
| "step": 1177 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.48552128481082213, |
| "learning_rate": 0.00046252915168058697, |
| "loss": 2.5757, |
| "step": 1178 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.47973864065544647, |
| "learning_rate": 0.0004617885885066305, |
| "loss": 2.6013, |
| "step": 1179 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.48671497050413853, |
| "learning_rate": 0.0004610481096412984, |
| "loss": 2.5949, |
| "step": 1180 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.5003711073443966, |
| "learning_rate": 0.000460307716718363, |
| "loss": 2.5334, |
| "step": 1181 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.48380837959050954, |
| "learning_rate": 0.0004595674113714074, |
| "loss": 2.4381, |
| "step": 1182 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.4957977499924627, |
| "learning_rate": 0.0004588271952338212, |
| "loss": 2.4453, |
| "step": 1183 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.4774663575338855, |
| "learning_rate": 0.00045808706993879714, |
| "loss": 2.6253, |
| "step": 1184 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.4763223148768074, |
| "learning_rate": 0.00045734703711932767, |
| "loss": 2.6534, |
| "step": 1185 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.4726740384823678, |
| "learning_rate": 0.0004566070984082013, |
| "loss": 2.5257, |
| "step": 1186 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.4707026761727539, |
| "learning_rate": 0.00045586725543799865, |
| "loss": 2.6213, |
| "step": 1187 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 0.4681335726550162, |
| "learning_rate": 0.00045512750984108937, |
| "loss": 2.6074, |
| "step": 1188 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.474441065865084, |
| "learning_rate": 0.000454387863249628, |
| "loss": 2.6528, |
| "step": 1189 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.46685347107696074, |
| "learning_rate": 0.00045364831729555096, |
| "loss": 2.5279, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.49782420064452415, |
| "learning_rate": 0.0004529088736105721, |
| "loss": 2.5053, |
| "step": 1191 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.5112754282807319, |
| "learning_rate": 0.0004521695338261802, |
| "loss": 2.5213, |
| "step": 1192 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.5890455516600644, |
| "learning_rate": 0.0004514302995736344, |
| "loss": 2.4831, |
| "step": 1193 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.4731258501378143, |
| "learning_rate": 0.0004506911724839613, |
| "loss": 2.4778, |
| "step": 1194 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.47619487019279905, |
| "learning_rate": 0.0004499521541879508, |
| "loss": 2.5313, |
| "step": 1195 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.47411817987316657, |
| "learning_rate": 0.00044921324631615303, |
| "loss": 2.55, |
| "step": 1196 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.8048183047718689, |
| "learning_rate": 0.0004484744504988742, |
| "loss": 2.6522, |
| "step": 1197 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.47917387748539775, |
| "learning_rate": 0.00044773576836617336, |
| "loss": 2.5698, |
| "step": 1198 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.4513227521963297, |
| "learning_rate": 0.0004469972015478588, |
| "loss": 2.5016, |
| "step": 1199 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.4656142253847835, |
| "learning_rate": 0.0004462587516734844, |
| "loss": 2.5465, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.5040098443503638, |
| "learning_rate": 0.00044552042037234596, |
| "loss": 2.4489, |
| "step": 1201 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.5022112373432399, |
| "learning_rate": 0.00044478220927347774, |
| "loss": 2.5412, |
| "step": 1202 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.474338235282293, |
| "learning_rate": 0.00044404412000564875, |
| "loss": 2.5214, |
| "step": 1203 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.4631707809951272, |
| "learning_rate": 0.000443306154197359, |
| "loss": 2.6601, |
| "step": 1204 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.4757474889384979, |
| "learning_rate": 0.00044256831347683646, |
| "loss": 2.5578, |
| "step": 1205 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.4483177067623047, |
| "learning_rate": 0.0004418305994720328, |
| "loss": 2.6109, |
| "step": 1206 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.5122837991964855, |
| "learning_rate": 0.0004410930138106203, |
| "loss": 2.4819, |
| "step": 1207 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.5005999591359361, |
| "learning_rate": 0.000440355558119988, |
| "loss": 2.4924, |
| "step": 1208 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.674829023658193, |
| "learning_rate": 0.00043961823402723814, |
| "loss": 2.6076, |
| "step": 1209 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 0.4995670462462274, |
| "learning_rate": 0.0004388810431591829, |
| "loss": 2.6372, |
| "step": 1210 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.5532631826917694, |
| "learning_rate": 0.0004381439871423398, |
| "loss": 2.4781, |
| "step": 1211 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.45992533391989143, |
| "learning_rate": 0.00043740706760292966, |
| "loss": 2.4768, |
| "step": 1212 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.4977462119143139, |
| "learning_rate": 0.0004366702861668716, |
| "loss": 2.477, |
| "step": 1213 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.516324255448675, |
| "learning_rate": 0.00043593364445978036, |
| "loss": 2.6451, |
| "step": 1214 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.48951240815290115, |
| "learning_rate": 0.0004351971441069622, |
| "loss": 2.5032, |
| "step": 1215 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.5191208156723685, |
| "learning_rate": 0.0004344607867334116, |
| "loss": 2.6059, |
| "step": 1216 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.5060688854122894, |
| "learning_rate": 0.00043372457396380766, |
| "loss": 2.6461, |
| "step": 1217 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.5095692866826174, |
| "learning_rate": 0.00043298850742251013, |
| "loss": 2.5769, |
| "step": 1218 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.4867972424145987, |
| "learning_rate": 0.0004322525887335563, |
| "loss": 2.5355, |
| "step": 1219 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.5718041162844648, |
| "learning_rate": 0.00043151681952065734, |
| "loss": 2.6465, |
| "step": 1220 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.49906602412168066, |
| "learning_rate": 0.00043078120140719456, |
| "loss": 2.608, |
| "step": 1221 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.49451427182077407, |
| "learning_rate": 0.0004300457360162158, |
| "loss": 2.5436, |
| "step": 1222 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.4548544604049159, |
| "learning_rate": 0.0004293104249704319, |
| "loss": 2.5215, |
| "step": 1223 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.5341901563451606, |
| "learning_rate": 0.00042857526989221355, |
| "loss": 2.542, |
| "step": 1224 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.4660251893910219, |
| "learning_rate": 0.00042784027240358674, |
| "loss": 2.5696, |
| "step": 1225 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.5413107433827202, |
| "learning_rate": 0.0004271054341262301, |
| "loss": 2.5816, |
| "step": 1226 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.47398519971681097, |
| "learning_rate": 0.000426370756681471, |
| "loss": 2.4954, |
| "step": 1227 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.4507222441655678, |
| "learning_rate": 0.0004256362416902817, |
| "loss": 2.6003, |
| "step": 1228 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.4655071375735518, |
| "learning_rate": 0.00042490189077327637, |
| "loss": 2.7148, |
| "step": 1229 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.4758400280901852, |
| "learning_rate": 0.00042416770555070703, |
| "loss": 2.5751, |
| "step": 1230 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.504670026191004, |
| "learning_rate": 0.00042343368764246, |
| "loss": 2.6562, |
| "step": 1231 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.47965905681206716, |
| "learning_rate": 0.0004226998386680524, |
| "loss": 2.6161, |
| "step": 1232 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.5265772670055533, |
| "learning_rate": 0.000421966160246629, |
| "loss": 2.5646, |
| "step": 1233 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.485844369493024, |
| "learning_rate": 0.00042123265399695783, |
| "loss": 2.6232, |
| "step": 1234 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.5086362152135065, |
| "learning_rate": 0.0004204993215374273, |
| "loss": 2.693, |
| "step": 1235 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.48729310222703054, |
| "learning_rate": 0.00041976616448604226, |
| "loss": 2.4543, |
| "step": 1236 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.536506233773375, |
| "learning_rate": 0.00041903318446042076, |
| "loss": 2.4969, |
| "step": 1237 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.518866226128123, |
| "learning_rate": 0.00041830038307778984, |
| "loss": 2.6204, |
| "step": 1238 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.5633435508674336, |
| "learning_rate": 0.0004175677619549828, |
| "loss": 2.5323, |
| "step": 1239 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.46048162942714727, |
| "learning_rate": 0.000416835322708435, |
| "loss": 2.5368, |
| "step": 1240 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.49026142739765327, |
| "learning_rate": 0.00041610306695418056, |
| "loss": 2.5829, |
| "step": 1241 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.46032109802020477, |
| "learning_rate": 0.0004153709963078488, |
| "loss": 2.5698, |
| "step": 1242 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.507590985167933, |
| "learning_rate": 0.0004146391123846606, |
| "loss": 2.575, |
| "step": 1243 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.4651179120939466, |
| "learning_rate": 0.0004139074167994249, |
| "loss": 2.593, |
| "step": 1244 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.4977087092264955, |
| "learning_rate": 0.00041317591116653486, |
| "loss": 2.6088, |
| "step": 1245 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.5084236193733496, |
| "learning_rate": 0.0004124445970999648, |
| "loss": 2.6445, |
| "step": 1246 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.48710342337954526, |
| "learning_rate": 0.00041171347621326627, |
| "loss": 2.5802, |
| "step": 1247 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.4970109609211338, |
| "learning_rate": 0.00041098255011956465, |
| "loss": 2.5797, |
| "step": 1248 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.46949921124751054, |
| "learning_rate": 0.00041025182043155547, |
| "loss": 2.5439, |
| "step": 1249 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.4656417632788495, |
| "learning_rate": 0.000409521288761501, |
| "loss": 2.4398, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.48622814211379906, |
| "learning_rate": 0.00040879095672122646, |
| "loss": 2.5341, |
| "step": 1251 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.5110382887656361, |
| "learning_rate": 0.0004080608259221167, |
| "loss": 2.5079, |
| "step": 1252 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.4739238736138375, |
| "learning_rate": 0.0004073308979751126, |
| "loss": 2.472, |
| "step": 1253 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 0.5070649491411399, |
| "learning_rate": 0.0004066011744907074, |
| "loss": 2.6259, |
| "step": 1254 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.5897177202714806, |
| "learning_rate": 0.00040587165707894326, |
| "loss": 2.4781, |
| "step": 1255 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.4723365581759212, |
| "learning_rate": 0.0004051423473494076, |
| "loss": 2.6842, |
| "step": 1256 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.4944708956908848, |
| "learning_rate": 0.0004044132469112299, |
| "loss": 2.4541, |
| "step": 1257 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.4742978779085549, |
| "learning_rate": 0.00040368435737307733, |
| "loss": 2.5274, |
| "step": 1258 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.4876876997687887, |
| "learning_rate": 0.00040295568034315224, |
| "loss": 2.5516, |
| "step": 1259 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.488842512532198, |
| "learning_rate": 0.0004022272174291878, |
| "loss": 2.5845, |
| "step": 1260 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.5179688679352668, |
| "learning_rate": 0.0004014989702384449, |
| "loss": 2.6278, |
| "step": 1261 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.5357252897285723, |
| "learning_rate": 0.00040077094037770843, |
| "loss": 2.4759, |
| "step": 1262 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.49996532484898765, |
| "learning_rate": 0.0004000431294532838, |
| "loss": 2.5458, |
| "step": 1263 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.48758959994077467, |
| "learning_rate": 0.0003993155390709935, |
| "loss": 2.6305, |
| "step": 1264 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.5136034688975738, |
| "learning_rate": 0.0003985881708361729, |
| "loss": 2.5093, |
| "step": 1265 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.47577820164960166, |
| "learning_rate": 0.00039786102635366784, |
| "loss": 2.6651, |
| "step": 1266 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.6134603725624118, |
| "learning_rate": 0.0003971341072278302, |
| "loss": 2.4891, |
| "step": 1267 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.47233431702380874, |
| "learning_rate": 0.00039640741506251457, |
| "loss": 2.629, |
| "step": 1268 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.49080872115936136, |
| "learning_rate": 0.00039568095146107495, |
| "loss": 2.6906, |
| "step": 1269 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.4908704673889577, |
| "learning_rate": 0.00039495471802636096, |
| "loss": 2.5047, |
| "step": 1270 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.543920933936737, |
| "learning_rate": 0.0003942287163607145, |
| "loss": 2.6101, |
| "step": 1271 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.5067969055623021, |
| "learning_rate": 0.0003935029480659658, |
| "loss": 2.4835, |
| "step": 1272 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.4851135374809145, |
| "learning_rate": 0.00039277741474343054, |
| "loss": 2.5903, |
| "step": 1273 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.2340205543910958, |
| "learning_rate": 0.0003920521179939057, |
| "loss": 2.4809, |
| "step": 1274 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 0.4584219963054918, |
| "learning_rate": 0.00039132705941766644, |
| "loss": 2.4593, |
| "step": 1275 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.465828027087544, |
| "learning_rate": 0.0003906022406144624, |
| "loss": 2.6069, |
| "step": 1276 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.4639606466620596, |
| "learning_rate": 0.0003898776631835143, |
| "loss": 2.5763, |
| "step": 1277 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.5324820101554165, |
| "learning_rate": 0.00038915332872350994, |
| "loss": 2.571, |
| "step": 1278 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.47732466374962806, |
| "learning_rate": 0.00038842923883260135, |
| "loss": 2.6248, |
| "step": 1279 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.4757803395992666, |
| "learning_rate": 0.00038770539510840093, |
| "loss": 2.6055, |
| "step": 1280 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.47693907264732166, |
| "learning_rate": 0.00038698179914797783, |
| "loss": 2.5444, |
| "step": 1281 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.47299868193114025, |
| "learning_rate": 0.0003862584525478545, |
| "loss": 2.633, |
| "step": 1282 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.5028622354370005, |
| "learning_rate": 0.00038553535690400353, |
| "loss": 2.456, |
| "step": 1283 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.4637950458771561, |
| "learning_rate": 0.00038481251381184355, |
| "loss": 2.5668, |
| "step": 1284 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.5179253360630954, |
| "learning_rate": 0.00038408992486623584, |
| "loss": 2.5142, |
| "step": 1285 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.5321139530190038, |
| "learning_rate": 0.00038336759166148117, |
| "loss": 2.5317, |
| "step": 1286 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.5108457726253977, |
| "learning_rate": 0.0003826455157913159, |
| "loss": 2.5121, |
| "step": 1287 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.4822414838670178, |
| "learning_rate": 0.00038192369884890886, |
| "loss": 2.497, |
| "step": 1288 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.5024316217701124, |
| "learning_rate": 0.00038120214242685723, |
| "loss": 2.584, |
| "step": 1289 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.49882633832269535, |
| "learning_rate": 0.00038048084811718373, |
| "loss": 2.5859, |
| "step": 1290 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.48947262380303735, |
| "learning_rate": 0.0003797598175113327, |
| "loss": 2.5518, |
| "step": 1291 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.4957334215287397, |
| "learning_rate": 0.0003790390522001662, |
| "loss": 2.5355, |
| "step": 1292 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.4745942287519778, |
| "learning_rate": 0.0003783185537739615, |
| "loss": 2.5633, |
| "step": 1293 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.4808428297509044, |
| "learning_rate": 0.00037759832382240697, |
| "loss": 2.5985, |
| "step": 1294 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.465748433070569, |
| "learning_rate": 0.00037687836393459826, |
| "loss": 2.6995, |
| "step": 1295 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.46600806081776097, |
| "learning_rate": 0.0003761586756990354, |
| "loss": 2.4876, |
| "step": 1296 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.47560536304540724, |
| "learning_rate": 0.0003754392607036191, |
| "loss": 2.5264, |
| "step": 1297 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.49001822112717475, |
| "learning_rate": 0.0003747201205356472, |
| "loss": 2.6098, |
| "step": 1298 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.6722785086039373, |
| "learning_rate": 0.0003740012567818111, |
| "loss": 2.6067, |
| "step": 1299 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.467866677442058, |
| "learning_rate": 0.0003732826710281922, |
| "loss": 2.4873, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.5643838526601067, |
| "learning_rate": 0.0003725643648602588, |
| "loss": 2.595, |
| "step": 1301 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.4484938925843124, |
| "learning_rate": 0.0003718463398628621, |
| "loss": 2.468, |
| "step": 1302 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.4834718406654649, |
| "learning_rate": 0.0003711285976202331, |
| "loss": 2.5377, |
| "step": 1303 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.4604330643014678, |
| "learning_rate": 0.0003704111397159787, |
| "loss": 2.4352, |
| "step": 1304 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.49304243731703834, |
| "learning_rate": 0.0003696939677330788, |
| "loss": 2.4306, |
| "step": 1305 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.5155013377375821, |
| "learning_rate": 0.00036897708325388213, |
| "loss": 2.5469, |
| "step": 1306 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.45329189091974414, |
| "learning_rate": 0.0003682604878601034, |
| "loss": 2.4666, |
| "step": 1307 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.5272562823256126, |
| "learning_rate": 0.000367544183132819, |
| "loss": 2.5467, |
| "step": 1308 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.5158484831143616, |
| "learning_rate": 0.0003668281706524645, |
| "loss": 2.6156, |
| "step": 1309 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.4879800748382205, |
| "learning_rate": 0.0003661124519988304, |
| "loss": 2.5737, |
| "step": 1310 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.5047982975539099, |
| "learning_rate": 0.00036539702875105893, |
| "loss": 2.5844, |
| "step": 1311 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.45489760145455577, |
| "learning_rate": 0.0003646819024876406, |
| "loss": 2.5123, |
| "step": 1312 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.47015077140387734, |
| "learning_rate": 0.0003639670747864107, |
| "loss": 2.4232, |
| "step": 1313 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.4723674037855837, |
| "learning_rate": 0.00036325254722454584, |
| "loss": 2.4481, |
| "step": 1314 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.4848802040615322, |
| "learning_rate": 0.00036253832137855997, |
| "loss": 2.4732, |
| "step": 1315 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.48900269724537787, |
| "learning_rate": 0.00036182439882430183, |
| "loss": 2.6082, |
| "step": 1316 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.5332068585419067, |
| "learning_rate": 0.00036111078113695096, |
| "loss": 2.6445, |
| "step": 1317 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.48187203337562035, |
| "learning_rate": 0.0003603974698910139, |
| "loss": 2.4195, |
| "step": 1318 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.5001440514617363, |
| "learning_rate": 0.0003596844666603214, |
| "loss": 2.6752, |
| "step": 1319 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.5446755422789141, |
| "learning_rate": 0.0003589717730180245, |
| "loss": 2.5654, |
| "step": 1320 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.4812762368212247, |
| "learning_rate": 0.00035825939053659117, |
| "loss": 2.4375, |
| "step": 1321 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.5400044706153792, |
| "learning_rate": 0.00035754732078780273, |
| "loss": 2.5397, |
| "step": 1322 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.5391475561046014, |
| "learning_rate": 0.00035683556534275076, |
| "loss": 2.635, |
| "step": 1323 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.4586787398574348, |
| "learning_rate": 0.00035612412577183303, |
| "loss": 2.585, |
| "step": 1324 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.47860197591845605, |
| "learning_rate": 0.00035541300364475063, |
| "loss": 2.4857, |
| "step": 1325 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.5087649611302382, |
| "learning_rate": 0.0003547022005305043, |
| "loss": 2.3812, |
| "step": 1326 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.5143590279851625, |
| "learning_rate": 0.0003539917179973907, |
| "loss": 2.5768, |
| "step": 1327 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.5006797937926649, |
| "learning_rate": 0.00035328155761299917, |
| "loss": 2.4567, |
| "step": 1328 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.4952262683920909, |
| "learning_rate": 0.0003525717209442085, |
| "loss": 2.559, |
| "step": 1329 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.4878537034921233, |
| "learning_rate": 0.00035186220955718306, |
| "loss": 2.6182, |
| "step": 1330 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.4881876746413367, |
| "learning_rate": 0.0003511530250173696, |
| "loss": 2.5592, |
| "step": 1331 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.4755644543378069, |
| "learning_rate": 0.00035044416888949364, |
| "loss": 2.559, |
| "step": 1332 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.46776578970820676, |
| "learning_rate": 0.0003497356427375562, |
| "loss": 2.5993, |
| "step": 1333 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.5233541289873381, |
| "learning_rate": 0.00034902744812483034, |
| "loss": 2.6065, |
| "step": 1334 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.4660846097255129, |
| "learning_rate": 0.00034831958661385714, |
| "loss": 2.4916, |
| "step": 1335 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.4624217249232578, |
| "learning_rate": 0.0003476120597664434, |
| "loss": 2.5064, |
| "step": 1336 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.45996317918311547, |
| "learning_rate": 0.00034690486914365704, |
| "loss": 2.3557, |
| "step": 1337 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.4886388610435767, |
| "learning_rate": 0.00034619801630582435, |
| "loss": 2.4811, |
| "step": 1338 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.4707582067507129, |
| "learning_rate": 0.00034549150281252633, |
| "loss": 2.505, |
| "step": 1339 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.46736754361997485, |
| "learning_rate": 0.0003447853302225952, |
| "loss": 2.5418, |
| "step": 1340 |
| }, |
| { |
| "epoch": 0.61, |
| "grad_norm": 0.47814310698625617, |
| "learning_rate": 0.00034407950009411126, |
| "loss": 2.6108, |
| "step": 1341 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.4745204258023517, |
| "learning_rate": 0.00034337401398439873, |
| "loss": 2.5034, |
| "step": 1342 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.45418657265867757, |
| "learning_rate": 0.00034266887345002305, |
| "loss": 2.5924, |
| "step": 1343 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.46716852087020755, |
| "learning_rate": 0.0003419640800467874, |
| "loss": 2.536, |
| "step": 1344 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.45934567217819156, |
| "learning_rate": 0.0003412596353297288, |
| "loss": 2.6409, |
| "step": 1345 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.4937772692802365, |
| "learning_rate": 0.00034055554085311493, |
| "loss": 2.5637, |
| "step": 1346 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.47426373574473035, |
| "learning_rate": 0.00033985179817044105, |
| "loss": 2.5364, |
| "step": 1347 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.49849390148381556, |
| "learning_rate": 0.0003391484088344257, |
| "loss": 2.491, |
| "step": 1348 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.4894140740203577, |
| "learning_rate": 0.00033844537439700807, |
| "loss": 2.4938, |
| "step": 1349 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.47562466034177703, |
| "learning_rate": 0.00033774269640934445, |
| "loss": 2.719, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.4830626008735886, |
| "learning_rate": 0.0003370403764218045, |
| "loss": 2.5091, |
| "step": 1351 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.4868710079208404, |
| "learning_rate": 0.000336338415983968, |
| "loss": 2.5703, |
| "step": 1352 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.47144077254446803, |
| "learning_rate": 0.00033563681664462155, |
| "loss": 2.5453, |
| "step": 1353 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.5132024051449068, |
| "learning_rate": 0.000334935579951755, |
| "loss": 2.4592, |
| "step": 1354 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.49580661240811447, |
| "learning_rate": 0.0003342347074525578, |
| "loss": 2.5374, |
| "step": 1355 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.5437321846957165, |
| "learning_rate": 0.0003335342006934161, |
| "loss": 2.5572, |
| "step": 1356 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.4925593067211401, |
| "learning_rate": 0.00033283406121990914, |
| "loss": 2.3857, |
| "step": 1357 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.4664840914862339, |
| "learning_rate": 0.0003321342905768057, |
| "loss": 2.5059, |
| "step": 1358 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.46678573739111345, |
| "learning_rate": 0.00033143489030806086, |
| "loss": 2.621, |
| "step": 1359 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.5041420742504115, |
| "learning_rate": 0.00033073586195681227, |
| "loss": 2.5844, |
| "step": 1360 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.49159625651948147, |
| "learning_rate": 0.00033003720706537736, |
| "loss": 2.5878, |
| "step": 1361 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.49503868833164927, |
| "learning_rate": 0.0003293389271752492, |
| "loss": 2.4992, |
| "step": 1362 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.4633280442719238, |
| "learning_rate": 0.00032864102382709374, |
| "loss": 2.476, |
| "step": 1363 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.48592868994901806, |
| "learning_rate": 0.000327943498560746, |
| "loss": 2.4815, |
| "step": 1364 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.480279676367649, |
| "learning_rate": 0.00032724635291520694, |
| "loss": 2.5418, |
| "step": 1365 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.5093736524263478, |
| "learning_rate": 0.00032654958842863967, |
| "loss": 2.4441, |
| "step": 1366 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.4943176821521901, |
| "learning_rate": 0.0003258532066383667, |
| "loss": 2.5626, |
| "step": 1367 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.5169663274559559, |
| "learning_rate": 0.000325157209080866, |
| "loss": 2.4873, |
| "step": 1368 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.49582267647368533, |
| "learning_rate": 0.00032446159729176743, |
| "loss": 2.4958, |
| "step": 1369 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.5036468007810699, |
| "learning_rate": 0.0003237663728058502, |
| "loss": 2.6683, |
| "step": 1370 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.4966347138579822, |
| "learning_rate": 0.0003230715371570389, |
| "loss": 2.4622, |
| "step": 1371 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.5206321255682719, |
| "learning_rate": 0.00032237709187839996, |
| "loss": 2.4495, |
| "step": 1372 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.48723848578914847, |
| "learning_rate": 0.0003216830385021388, |
| "loss": 2.5588, |
| "step": 1373 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.46498897866748684, |
| "learning_rate": 0.0003209893785595959, |
| "loss": 2.5271, |
| "step": 1374 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.45874735687505813, |
| "learning_rate": 0.00032029611358124366, |
| "loss": 2.645, |
| "step": 1375 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.49623267093345264, |
| "learning_rate": 0.00031960324509668336, |
| "loss": 2.6186, |
| "step": 1376 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.5503386142978517, |
| "learning_rate": 0.0003189107746346412, |
| "loss": 2.4244, |
| "step": 1377 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.47443311149126927, |
| "learning_rate": 0.0003182187037229653, |
| "loss": 2.5574, |
| "step": 1378 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.5042211089436232, |
| "learning_rate": 0.0003175270338886221, |
| "loss": 2.5498, |
| "step": 1379 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.47220823232172154, |
| "learning_rate": 0.00031683576665769345, |
| "loss": 2.4084, |
| "step": 1380 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.49880953091279945, |
| "learning_rate": 0.0003161449035553724, |
| "loss": 2.573, |
| "step": 1381 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.48413487565873964, |
| "learning_rate": 0.00031545444610596077, |
| "loss": 2.5081, |
| "step": 1382 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.5255110097436843, |
| "learning_rate": 0.000314764395832865, |
| "loss": 2.6389, |
| "step": 1383 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.4800537101215283, |
| "learning_rate": 0.0003140747542585934, |
| "loss": 2.6409, |
| "step": 1384 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.5081410257296504, |
| "learning_rate": 0.00031338552290475266, |
| "loss": 2.5725, |
| "step": 1385 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.4828542480969836, |
| "learning_rate": 0.00031269670329204396, |
| "loss": 2.497, |
| "step": 1386 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.47910168831843175, |
| "learning_rate": 0.0003120082969402604, |
| "loss": 2.5309, |
| "step": 1387 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.4912043766343376, |
| "learning_rate": 0.00031132030536828314, |
| "loss": 2.5998, |
| "step": 1388 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.46169246821788557, |
| "learning_rate": 0.00031063273009407805, |
| "loss": 2.4682, |
| "step": 1389 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.5126335536008015, |
| "learning_rate": 0.00030994557263469265, |
| "loss": 2.5181, |
| "step": 1390 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.49268447858180975, |
| "learning_rate": 0.0003092588345062526, |
| "loss": 2.5638, |
| "step": 1391 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.4966112860635878, |
| "learning_rate": 0.0003085725172239582, |
| "loss": 2.4802, |
| "step": 1392 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.49160145496277713, |
| "learning_rate": 0.0003078866223020815, |
| "loss": 2.6038, |
| "step": 1393 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.4987954795960643, |
| "learning_rate": 0.0003072011512539624, |
| "loss": 2.467, |
| "step": 1394 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.4751616269603192, |
| "learning_rate": 0.00030651610559200574, |
| "loss": 2.5333, |
| "step": 1395 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.5009679305435549, |
| "learning_rate": 0.00030583148682767757, |
| "loss": 2.5997, |
| "step": 1396 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.46624702215518726, |
| "learning_rate": 0.00030514729647150243, |
| "loss": 2.4828, |
| "step": 1397 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.5492797836500279, |
| "learning_rate": 0.0003044635360330592, |
| "loss": 2.4672, |
| "step": 1398 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.48542172429871383, |
| "learning_rate": 0.00030378020702097845, |
| "loss": 2.5184, |
| "step": 1399 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.6294222555633776, |
| "learning_rate": 0.000303097310942939, |
| "loss": 2.5015, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.4988995832639893, |
| "learning_rate": 0.0003024148493056641, |
| "loss": 2.5101, |
| "step": 1401 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.4874141136748491, |
| "learning_rate": 0.00030173282361491865, |
| "loss": 2.6608, |
| "step": 1402 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.46805484705165984, |
| "learning_rate": 0.0003010512353755057, |
| "loss": 2.5411, |
| "step": 1403 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.46975473513424865, |
| "learning_rate": 0.00030037008609126313, |
| "loss": 2.5277, |
| "step": 1404 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.4516873656792182, |
| "learning_rate": 0.0002996893772650602, |
| "loss": 2.5416, |
| "step": 1405 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.544884080376768, |
| "learning_rate": 0.0002990091103987945, |
| "loss": 2.4457, |
| "step": 1406 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.48161834816885024, |
| "learning_rate": 0.0002983292869933886, |
| "loss": 2.6056, |
| "step": 1407 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.4677856409281954, |
| "learning_rate": 0.0002976499085487862, |
| "loss": 2.4537, |
| "step": 1408 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.4821309563551348, |
| "learning_rate": 0.00029697097656394963, |
| "loss": 2.513, |
| "step": 1409 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.5132644521682134, |
| "learning_rate": 0.00029629249253685595, |
| "loss": 2.5721, |
| "step": 1410 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.46774669093618304, |
| "learning_rate": 0.00029561445796449416, |
| "loss": 2.4906, |
| "step": 1411 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.5046537410624408, |
| "learning_rate": 0.0002949368743428612, |
| "loss": 2.5419, |
| "step": 1412 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.4642538629365702, |
| "learning_rate": 0.0002942597431669593, |
| "loss": 2.4932, |
| "step": 1413 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.4768657736918968, |
| "learning_rate": 0.0002935830659307924, |
| "loss": 2.5275, |
| "step": 1414 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.5649219454281154, |
| "learning_rate": 0.0002929068441273629, |
| "loss": 2.565, |
| "step": 1415 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.48552542436472956, |
| "learning_rate": 0.0002922310792486681, |
| "loss": 2.4915, |
| "step": 1416 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.47971791142286546, |
| "learning_rate": 0.00029155577278569745, |
| "loss": 2.5185, |
| "step": 1417 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.47665850240954155, |
| "learning_rate": 0.00029088092622842895, |
| "loss": 2.5721, |
| "step": 1418 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.5373047178865096, |
| "learning_rate": 0.00029020654106582544, |
| "loss": 2.4108, |
| "step": 1419 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.47149128153497094, |
| "learning_rate": 0.0002895326187858326, |
| "loss": 2.5262, |
| "step": 1420 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.514917922238104, |
| "learning_rate": 0.00028885916087537377, |
| "loss": 2.5523, |
| "step": 1421 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.5904146838967499, |
| "learning_rate": 0.00028818616882034877, |
| "loss": 2.5138, |
| "step": 1422 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.4901182137580135, |
| "learning_rate": 0.0002875136441056286, |
| "loss": 2.6495, |
| "step": 1423 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.49338704297207286, |
| "learning_rate": 0.000286841588215054, |
| "loss": 2.4916, |
| "step": 1424 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.5008776282053377, |
| "learning_rate": 0.0002861700026314308, |
| "loss": 2.5351, |
| "step": 1425 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.47958859087746714, |
| "learning_rate": 0.00028549888883652686, |
| "loss": 2.4856, |
| "step": 1426 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.5201678517829401, |
| "learning_rate": 0.00028482824831107, |
| "loss": 2.5675, |
| "step": 1427 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 0.47424978496782116, |
| "learning_rate": 0.000284158082534743, |
| "loss": 2.652, |
| "step": 1428 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.49199569098761553, |
| "learning_rate": 0.00028348839298618177, |
| "loss": 2.5071, |
| "step": 1429 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4914365103531419, |
| "learning_rate": 0.0002828191811429709, |
| "loss": 2.4617, |
| "step": 1430 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4571506678293313, |
| "learning_rate": 0.00028215044848164164, |
| "loss": 2.5033, |
| "step": 1431 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.47262546503373015, |
| "learning_rate": 0.00028148219647766747, |
| "loss": 2.5614, |
| "step": 1432 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4710455750897678, |
| "learning_rate": 0.00028081442660546124, |
| "loss": 2.6222, |
| "step": 1433 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.505956871495638, |
| "learning_rate": 0.0002801471403383728, |
| "loss": 2.5086, |
| "step": 1434 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4805725704676084, |
| "learning_rate": 0.00027948033914868415, |
| "loss": 2.5041, |
| "step": 1435 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.5344114340182097, |
| "learning_rate": 0.00027881402450760775, |
| "loss": 2.5981, |
| "step": 1436 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.481343478733675, |
| "learning_rate": 0.00027814819788528165, |
| "loss": 2.4257, |
| "step": 1437 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4875397328306738, |
| "learning_rate": 0.00027748286075076836, |
| "loss": 2.4801, |
| "step": 1438 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4781940230964243, |
| "learning_rate": 0.00027681801457204937, |
| "loss": 2.4075, |
| "step": 1439 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.5196921641021108, |
| "learning_rate": 0.00027615366081602306, |
| "loss": 2.5214, |
| "step": 1440 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4462359415368417, |
| "learning_rate": 0.0002754898009485021, |
| "loss": 2.5955, |
| "step": 1441 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4712567710725366, |
| "learning_rate": 0.0002748264364342085, |
| "loss": 2.5067, |
| "step": 1442 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.494298281728956, |
| "learning_rate": 0.00027416356873677204, |
| "loss": 2.4297, |
| "step": 1443 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4880999179956286, |
| "learning_rate": 0.0002735011993187258, |
| "loss": 2.4518, |
| "step": 1444 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4622433494617717, |
| "learning_rate": 0.0002728393296415042, |
| "loss": 2.5715, |
| "step": 1445 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4751972782337856, |
| "learning_rate": 0.00027217796116543817, |
| "loss": 2.5737, |
| "step": 1446 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.49254117511531753, |
| "learning_rate": 0.0002715170953497532, |
| "loss": 2.5733, |
| "step": 1447 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.49508342985487047, |
| "learning_rate": 0.00027085673365256614, |
| "loss": 2.5712, |
| "step": 1448 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4725154910446781, |
| "learning_rate": 0.00027019687753088075, |
| "loss": 2.4773, |
| "step": 1449 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.4853206061850111, |
| "learning_rate": 0.00026953752844058597, |
| "loss": 2.5142, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.5064261321837593, |
| "learning_rate": 0.0002688786878364516, |
| "loss": 2.4413, |
| "step": 1451 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.5088531940199746, |
| "learning_rate": 0.00026822035717212597, |
| "loss": 2.5568, |
| "step": 1452 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.5010648981389428, |
| "learning_rate": 0.00026756253790013193, |
| "loss": 2.5802, |
| "step": 1453 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.495042483534161, |
| "learning_rate": 0.0002669052314718641, |
| "loss": 2.5409, |
| "step": 1454 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.4803203299077956, |
| "learning_rate": 0.0002662484393375855, |
| "loss": 2.515, |
| "step": 1455 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.5391223036508788, |
| "learning_rate": 0.00026559216294642446, |
| "loss": 2.4938, |
| "step": 1456 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.4563596018093572, |
| "learning_rate": 0.0002649364037463718, |
| "loss": 2.4955, |
| "step": 1457 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.46732161830883145, |
| "learning_rate": 0.0002642811631842764, |
| "loss": 2.4425, |
| "step": 1458 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.4827548136014153, |
| "learning_rate": 0.0002636264427058439, |
| "loss": 2.397, |
| "step": 1459 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.48474008094498866, |
| "learning_rate": 0.00026297224375563123, |
| "loss": 2.5423, |
| "step": 1460 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.47570527654955125, |
| "learning_rate": 0.00026231856777704575, |
| "loss": 2.5116, |
| "step": 1461 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.48327551148628944, |
| "learning_rate": 0.00026166541621234026, |
| "loss": 2.5043, |
| "step": 1462 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.470748650250389, |
| "learning_rate": 0.00026101279050261045, |
| "loss": 2.5991, |
| "step": 1463 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.5186237323827524, |
| "learning_rate": 0.00026036069208779247, |
| "loss": 2.4756, |
| "step": 1464 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.5070927310619432, |
| "learning_rate": 0.0002597091224066581, |
| "loss": 2.6277, |
| "step": 1465 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.47766013284236913, |
| "learning_rate": 0.00025905808289681365, |
| "loss": 2.5716, |
| "step": 1466 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.5132429293707753, |
| "learning_rate": 0.0002584075749946946, |
| "loss": 2.5985, |
| "step": 1467 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.540381610781196, |
| "learning_rate": 0.00025775760013556424, |
| "loss": 2.4278, |
| "step": 1468 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.5040458420074884, |
| "learning_rate": 0.0002571081597535095, |
| "loss": 2.5866, |
| "step": 1469 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.5118147012097991, |
| "learning_rate": 0.00025645925528143776, |
| "loss": 2.4568, |
| "step": 1470 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.49247271196601816, |
| "learning_rate": 0.0002558108881510747, |
| "loss": 2.621, |
| "step": 1471 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.46399357899521015, |
| "learning_rate": 0.00025516305979295963, |
| "loss": 2.5179, |
| "step": 1472 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.6127159033579637, |
| "learning_rate": 0.0002545157716364439, |
| "loss": 2.4771, |
| "step": 1473 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4751975348492116, |
| "learning_rate": 0.00025386902510968624, |
| "loss": 2.6065, |
| "step": 1474 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4430163461347138, |
| "learning_rate": 0.00025322282163965095, |
| "loss": 2.5084, |
| "step": 1475 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.5018374134771989, |
| "learning_rate": 0.00025257716265210384, |
| "loss": 2.5331, |
| "step": 1476 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.46103334564784776, |
| "learning_rate": 0.0002519320495716091, |
| "loss": 2.5079, |
| "step": 1477 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4717534121747625, |
| "learning_rate": 0.00025128748382152716, |
| "loss": 2.4881, |
| "step": 1478 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4577503620841734, |
| "learning_rate": 0.00025064346682401016, |
| "loss": 2.5098, |
| "step": 1479 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4911364029231089, |
| "learning_rate": 0.0002500000000000001, |
| "loss": 2.5039, |
| "step": 1480 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4733645912544866, |
| "learning_rate": 0.0002493570847692246, |
| "loss": 2.5678, |
| "step": 1481 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.5013069318401949, |
| "learning_rate": 0.00024871472255019424, |
| "loss": 2.4884, |
| "step": 1482 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4672198999527607, |
| "learning_rate": 0.00024807291476019994, |
| "loss": 2.4859, |
| "step": 1483 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.5119011785274646, |
| "learning_rate": 0.00024743166281530877, |
| "loss": 2.52, |
| "step": 1484 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.5322873522495466, |
| "learning_rate": 0.000246790968130362, |
| "loss": 2.6008, |
| "step": 1485 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.46582398737621755, |
| "learning_rate": 0.0002461508321189706, |
| "loss": 2.4573, |
| "step": 1486 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.5082643669269433, |
| "learning_rate": 0.00024551125619351385, |
| "loss": 2.4951, |
| "step": 1487 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4652624124087935, |
| "learning_rate": 0.00024487224176513453, |
| "loss": 2.4961, |
| "step": 1488 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.47622224767440474, |
| "learning_rate": 0.0002442337902437365, |
| "loss": 2.5545, |
| "step": 1489 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4984117470041608, |
| "learning_rate": 0.0002435959030379824, |
| "loss": 2.5833, |
| "step": 1490 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4730090651776588, |
| "learning_rate": 0.00024295858155528888, |
| "loss": 2.5422, |
| "step": 1491 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.49861307146860945, |
| "learning_rate": 0.00024232182720182523, |
| "loss": 2.5897, |
| "step": 1492 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.4794923731398395, |
| "learning_rate": 0.00024168564138250855, |
| "loss": 2.5377, |
| "step": 1493 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.4825323366351967, |
| "learning_rate": 0.00024105002550100246, |
| "loss": 2.5014, |
| "step": 1494 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.4832074778746107, |
| "learning_rate": 0.00024041498095971254, |
| "loss": 2.4831, |
| "step": 1495 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.6118239650682353, |
| "learning_rate": 0.0002397805091597835, |
| "loss": 2.4872, |
| "step": 1496 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.47854727063587554, |
| "learning_rate": 0.0002391466115010973, |
| "loss": 2.5464, |
| "step": 1497 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.548196757107001, |
| "learning_rate": 0.00023851328938226808, |
| "loss": 2.4805, |
| "step": 1498 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.46352364659659423, |
| "learning_rate": 0.00023788054420064109, |
| "loss": 2.4641, |
| "step": 1499 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.49325873708203904, |
| "learning_rate": 0.00023724837735228773, |
| "loss": 2.5961, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.5095608172164786, |
| "learning_rate": 0.00023661679023200422, |
| "loss": 2.5123, |
| "step": 1501 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.48002724383872725, |
| "learning_rate": 0.00023598578423330714, |
| "loss": 2.5669, |
| "step": 1502 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.46226535861443896, |
| "learning_rate": 0.00023535536074843083, |
| "loss": 2.5015, |
| "step": 1503 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.47080900563427647, |
| "learning_rate": 0.00023472552116832502, |
| "loss": 2.618, |
| "step": 1504 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.5251217959971037, |
| "learning_rate": 0.0002340962668826503, |
| "loss": 2.5541, |
| "step": 1505 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.5200375000051676, |
| "learning_rate": 0.00023346759927977663, |
| "loss": 2.5799, |
| "step": 1506 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.4833558120330395, |
| "learning_rate": 0.0002328395197467789, |
| "loss": 2.4802, |
| "step": 1507 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.4830166418674597, |
| "learning_rate": 0.00023221202966943515, |
| "loss": 2.5332, |
| "step": 1508 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.5415033350063272, |
| "learning_rate": 0.0002315851304322223, |
| "loss": 2.5345, |
| "step": 1509 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.47331789247697625, |
| "learning_rate": 0.0002309588234183137, |
| "loss": 2.6293, |
| "step": 1510 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.48278951179038826, |
| "learning_rate": 0.00023033311000957653, |
| "loss": 2.5428, |
| "step": 1511 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.45892920519337205, |
| "learning_rate": 0.00022970799158656758, |
| "loss": 2.4423, |
| "step": 1512 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.4794362266722693, |
| "learning_rate": 0.0002290834695285316, |
| "loss": 2.5394, |
| "step": 1513 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.48337433490961357, |
| "learning_rate": 0.00022845954521339678, |
| "loss": 2.5342, |
| "step": 1514 |
| }, |
| { |
| "epoch": 0.69, |
| "grad_norm": 0.5230914869828908, |
| "learning_rate": 0.0002278362200177732, |
| "loss": 2.5081, |
| "step": 1515 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.48425351417598533, |
| "learning_rate": 0.00022721349531694852, |
| "loss": 2.5183, |
| "step": 1516 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.47211055965660004, |
| "learning_rate": 0.0002265913724848855, |
| "loss": 2.5699, |
| "step": 1517 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.5232190680085489, |
| "learning_rate": 0.00022596985289421946, |
| "loss": 2.5264, |
| "step": 1518 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.4858103442389283, |
| "learning_rate": 0.00022534893791625405, |
| "loss": 2.4808, |
| "step": 1519 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.46443924939296055, |
| "learning_rate": 0.00022472862892095968, |
| "loss": 2.4538, |
| "step": 1520 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.4818658381152557, |
| "learning_rate": 0.00022410892727696896, |
| "loss": 2.4197, |
| "step": 1521 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.5014207045345472, |
| "learning_rate": 0.0002234898343515751, |
| "loss": 2.4573, |
| "step": 1522 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.48138858393177497, |
| "learning_rate": 0.00022287135151072792, |
| "loss": 2.4983, |
| "step": 1523 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.5327316709479498, |
| "learning_rate": 0.00022225348011903096, |
| "loss": 2.5039, |
| "step": 1524 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.5251729017117021, |
| "learning_rate": 0.0002216362215397393, |
| "loss": 2.3611, |
| "step": 1525 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.47734541912906703, |
| "learning_rate": 0.00022101957713475522, |
| "loss": 2.4942, |
| "step": 1526 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.46046695887483313, |
| "learning_rate": 0.00022040354826462666, |
| "loss": 2.4706, |
| "step": 1527 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.468294464458692, |
| "learning_rate": 0.0002197881362885426, |
| "loss": 2.4444, |
| "step": 1528 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.5066718567109901, |
| "learning_rate": 0.0002191733425643318, |
| "loss": 2.4453, |
| "step": 1529 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.5214025347149304, |
| "learning_rate": 0.00021855916844845826, |
| "loss": 2.6116, |
| "step": 1530 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.5098033475906325, |
| "learning_rate": 0.00021794561529601898, |
| "loss": 2.5839, |
| "step": 1531 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.4914531184589839, |
| "learning_rate": 0.00021733268446074138, |
| "loss": 2.541, |
| "step": 1532 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.4917800941586923, |
| "learning_rate": 0.00021672037729497917, |
| "loss": 2.4557, |
| "step": 1533 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.5001173647273122, |
| "learning_rate": 0.0002161086951497106, |
| "loss": 2.518, |
| "step": 1534 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.45594098334098093, |
| "learning_rate": 0.00021549763937453442, |
| "loss": 2.4216, |
| "step": 1535 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.4765583766673243, |
| "learning_rate": 0.00021488721131766736, |
| "loss": 2.4689, |
| "step": 1536 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.4832482792424047, |
| "learning_rate": 0.00021427741232594183, |
| "loss": 2.5447, |
| "step": 1537 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.511687129830672, |
| "learning_rate": 0.0002136682437448013, |
| "loss": 2.5113, |
| "step": 1538 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.48241922984121777, |
| "learning_rate": 0.0002130597069182994, |
| "loss": 2.621, |
| "step": 1539 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.6436339421209261, |
| "learning_rate": 0.0002124518031890948, |
| "loss": 2.5618, |
| "step": 1540 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.48068501566147, |
| "learning_rate": 0.0002118445338984502, |
| "loss": 2.4966, |
| "step": 1541 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.5101703982506236, |
| "learning_rate": 0.00021123790038622808, |
| "loss": 2.479, |
| "step": 1542 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.4891036511660931, |
| "learning_rate": 0.0002106319039908879, |
| "loss": 2.4503, |
| "step": 1543 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.4921003844449901, |
| "learning_rate": 0.00021002654604948412, |
| "loss": 2.4845, |
| "step": 1544 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.45621095341711565, |
| "learning_rate": 0.00020942182789766172, |
| "loss": 2.4921, |
| "step": 1545 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.48434000645762654, |
| "learning_rate": 0.00020881775086965492, |
| "loss": 2.6627, |
| "step": 1546 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.5106282347825893, |
| "learning_rate": 0.00020821431629828246, |
| "loss": 2.6176, |
| "step": 1547 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.5021064573950054, |
| "learning_rate": 0.00020761152551494643, |
| "loss": 2.4083, |
| "step": 1548 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.4812233993880702, |
| "learning_rate": 0.00020700937984962798, |
| "loss": 2.5964, |
| "step": 1549 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.4795695268319673, |
| "learning_rate": 0.0002064078806308848, |
| "loss": 2.513, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.5107367687211399, |
| "learning_rate": 0.00020580702918584882, |
| "loss": 2.535, |
| "step": 1551 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.4752185943795663, |
| "learning_rate": 0.000205206826840222, |
| "loss": 2.597, |
| "step": 1552 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.4607529106399874, |
| "learning_rate": 0.0002046072749182751, |
| "loss": 2.5172, |
| "step": 1553 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.4615952287352696, |
| "learning_rate": 0.00020400837474284273, |
| "loss": 2.5357, |
| "step": 1554 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.4604952096080498, |
| "learning_rate": 0.0002034101276353224, |
| "loss": 2.5073, |
| "step": 1555 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.5272462397432423, |
| "learning_rate": 0.00020281253491567027, |
| "loss": 2.5265, |
| "step": 1556 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.49938438391868123, |
| "learning_rate": 0.0002022155979023984, |
| "loss": 2.5946, |
| "step": 1557 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.47355845560500254, |
| "learning_rate": 0.000201619317912573, |
| "loss": 2.5534, |
| "step": 1558 |
| }, |
| { |
| "epoch": 0.71, |
| "grad_norm": 0.4932289001583615, |
| "learning_rate": 0.00020102369626180962, |
| "loss": 2.481, |
| "step": 1559 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.474506767383386, |
| "learning_rate": 0.0002004287342642721, |
| "loss": 2.5807, |
| "step": 1560 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.5639457440160446, |
| "learning_rate": 0.00019983443323266824, |
| "loss": 2.4772, |
| "step": 1561 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.46811817936440936, |
| "learning_rate": 0.00019924079447824805, |
| "loss": 2.4557, |
| "step": 1562 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.48406297519290353, |
| "learning_rate": 0.00019864781931079977, |
| "loss": 2.4555, |
| "step": 1563 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.46311120737178213, |
| "learning_rate": 0.00019805550903864773, |
| "loss": 2.4533, |
| "step": 1564 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.4898011950462646, |
| "learning_rate": 0.00019746386496864948, |
| "loss": 2.536, |
| "step": 1565 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.4946896248382084, |
| "learning_rate": 0.00019687288840619226, |
| "loss": 2.5051, |
| "step": 1566 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.5035234304081819, |
| "learning_rate": 0.0001962825806551911, |
| "loss": 2.5636, |
| "step": 1567 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.49445524511223055, |
| "learning_rate": 0.0001956929430180846, |
| "loss": 2.3886, |
| "step": 1568 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.523352151551309, |
| "learning_rate": 0.00019510397679583374, |
| "loss": 2.5909, |
| "step": 1569 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.4965206369992815, |
| "learning_rate": 0.0001945156832879174, |
| "loss": 2.4218, |
| "step": 1570 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.5177267527356685, |
| "learning_rate": 0.00019392806379233036, |
| "loss": 2.5656, |
| "step": 1571 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.507376364475753, |
| "learning_rate": 0.00019334111960558065, |
| "loss": 2.5149, |
| "step": 1572 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.46706578782902725, |
| "learning_rate": 0.00019275485202268573, |
| "loss": 2.4809, |
| "step": 1573 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.4648861412331565, |
| "learning_rate": 0.00019216926233717085, |
| "loss": 2.5226, |
| "step": 1574 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.49798902112979165, |
| "learning_rate": 0.00019158435184106498, |
| "loss": 2.4042, |
| "step": 1575 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.493790120333228, |
| "learning_rate": 0.00019100012182489905, |
| "loss": 2.5849, |
| "step": 1576 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.5355709069506043, |
| "learning_rate": 0.00019041657357770226, |
| "loss": 2.4819, |
| "step": 1577 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.4864511282233987, |
| "learning_rate": 0.00018983370838699943, |
| "loss": 2.4797, |
| "step": 1578 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.4942692058241062, |
| "learning_rate": 0.00018925152753880892, |
| "loss": 2.4481, |
| "step": 1579 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.4840096888247512, |
| "learning_rate": 0.00018867003231763847, |
| "loss": 2.4639, |
| "step": 1580 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.496265141250742, |
| "learning_rate": 0.00018808922400648375, |
| "loss": 2.423, |
| "step": 1581 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.4974384195059018, |
| "learning_rate": 0.00018750910388682428, |
| "loss": 2.4973, |
| "step": 1582 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.47512751485591537, |
| "learning_rate": 0.00018692967323862125, |
| "loss": 2.5591, |
| "step": 1583 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.525108975300194, |
| "learning_rate": 0.00018635093334031517, |
| "loss": 2.5464, |
| "step": 1584 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.546641582134751, |
| "learning_rate": 0.00018577288546882165, |
| "loss": 2.478, |
| "step": 1585 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.5273777845217823, |
| "learning_rate": 0.00018519553089953023, |
| "loss": 2.4148, |
| "step": 1586 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.476244748681866, |
| "learning_rate": 0.0001846188709063001, |
| "loss": 2.4662, |
| "step": 1587 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.4875177933216557, |
| "learning_rate": 0.00018404290676145857, |
| "loss": 2.5639, |
| "step": 1588 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.4939188755307638, |
| "learning_rate": 0.00018346763973579722, |
| "loss": 2.4521, |
| "step": 1589 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.48577061311415487, |
| "learning_rate": 0.00018289307109856939, |
| "loss": 2.5163, |
| "step": 1590 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.48168641811734986, |
| "learning_rate": 0.0001823192021174882, |
| "loss": 2.6481, |
| "step": 1591 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.5034920961930996, |
| "learning_rate": 0.0001817460340587223, |
| "loss": 2.4905, |
| "step": 1592 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.48083138344743676, |
| "learning_rate": 0.00018117356818689445, |
| "loss": 2.5144, |
| "step": 1593 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.5349798176404107, |
| "learning_rate": 0.00018060180576507756, |
| "loss": 2.5361, |
| "step": 1594 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.48090104161230124, |
| "learning_rate": 0.00018003074805479313, |
| "loss": 2.4044, |
| "step": 1595 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.48585762864074516, |
| "learning_rate": 0.00017946039631600724, |
| "loss": 2.5826, |
| "step": 1596 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.4824414533006241, |
| "learning_rate": 0.00017889075180712837, |
| "loss": 2.4508, |
| "step": 1597 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.47826087806216905, |
| "learning_rate": 0.00017832181578500512, |
| "loss": 2.4877, |
| "step": 1598 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.4784862217568717, |
| "learning_rate": 0.0001777535895049221, |
| "loss": 2.5941, |
| "step": 1599 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.5196238928683884, |
| "learning_rate": 0.0001771860742205988, |
| "loss": 2.631, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.49554744375547105, |
| "learning_rate": 0.00017661927118418525, |
| "loss": 2.4004, |
| "step": 1601 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.4941037592486409, |
| "learning_rate": 0.00017605318164626066, |
| "loss": 2.5673, |
| "step": 1602 |
| }, |
| { |
| "epoch": 0.73, |
| "grad_norm": 0.5035067315617257, |
| "learning_rate": 0.00017548780685582949, |
| "loss": 2.5243, |
| "step": 1603 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.4529856276518901, |
| "learning_rate": 0.00017492314806031922, |
| "loss": 2.4957, |
| "step": 1604 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.45859103688874886, |
| "learning_rate": 0.00017435920650557806, |
| "loss": 2.4506, |
| "step": 1605 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.47759535382786206, |
| "learning_rate": 0.00017379598343587112, |
| "loss": 2.5057, |
| "step": 1606 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.4637423956897907, |
| "learning_rate": 0.00017323348009387878, |
| "loss": 2.5433, |
| "step": 1607 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.47521564529292065, |
| "learning_rate": 0.0001726716977206929, |
| "loss": 2.4712, |
| "step": 1608 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.4605404174857888, |
| "learning_rate": 0.00017211063755581525, |
| "loss": 2.4718, |
| "step": 1609 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.5014871257122527, |
| "learning_rate": 0.0001715503008371536, |
| "loss": 2.5391, |
| "step": 1610 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.48290274281105183, |
| "learning_rate": 0.0001709906888010196, |
| "loss": 2.5362, |
| "step": 1611 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.5847408548645123, |
| "learning_rate": 0.00017043180268212638, |
| "loss": 2.4297, |
| "step": 1612 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.4944949717823857, |
| "learning_rate": 0.00016987364371358481, |
| "loss": 2.5927, |
| "step": 1613 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.5005281524201621, |
| "learning_rate": 0.00016931621312690214, |
| "loss": 2.492, |
| "step": 1614 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.44817567752842474, |
| "learning_rate": 0.00016875951215197777, |
| "loss": 2.4909, |
| "step": 1615 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.4892436751502635, |
| "learning_rate": 0.00016820354201710214, |
| "loss": 2.4724, |
| "step": 1616 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.4935872844656989, |
| "learning_rate": 0.00016764830394895203, |
| "loss": 2.5213, |
| "step": 1617 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.4761066026386569, |
| "learning_rate": 0.00016709379917259027, |
| "loss": 2.5463, |
| "step": 1618 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.49604543791428235, |
| "learning_rate": 0.00016654002891146091, |
| "loss": 2.5822, |
| "step": 1619 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.48162316688145657, |
| "learning_rate": 0.00016598699438738764, |
| "loss": 2.4697, |
| "step": 1620 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.4792254361666622, |
| "learning_rate": 0.00016543469682057105, |
| "loss": 2.44, |
| "step": 1621 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.4855658989709376, |
| "learning_rate": 0.00016488313742958526, |
| "loss": 2.6176, |
| "step": 1622 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.4843143784669569, |
| "learning_rate": 0.00016433231743137646, |
| "loss": 2.5971, |
| "step": 1623 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.5016927015144359, |
| "learning_rate": 0.0001637822380412584, |
| "loss": 2.3871, |
| "step": 1624 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.45181938467929933, |
| "learning_rate": 0.00016323290047291195, |
| "loss": 2.4962, |
| "step": 1625 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.504190692683163, |
| "learning_rate": 0.0001626843059383803, |
| "loss": 2.4758, |
| "step": 1626 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.5111624141693232, |
| "learning_rate": 0.00016213645564806752, |
| "loss": 2.3735, |
| "step": 1627 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.4914731996924969, |
| "learning_rate": 0.0001615893508107359, |
| "loss": 2.5085, |
| "step": 1628 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.4809907302855462, |
| "learning_rate": 0.00016104299263350252, |
| "loss": 2.4434, |
| "step": 1629 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.507401396841625, |
| "learning_rate": 0.00016049738232183758, |
| "loss": 2.488, |
| "step": 1630 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.4732055563178188, |
| "learning_rate": 0.0001599525210795606, |
| "loss": 2.6078, |
| "step": 1631 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.4891277658257485, |
| "learning_rate": 0.00015940841010883889, |
| "loss": 2.4637, |
| "step": 1632 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.5103153224929414, |
| "learning_rate": 0.00015886505061018413, |
| "loss": 2.428, |
| "step": 1633 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.479213323621243, |
| "learning_rate": 0.0001583224437824498, |
| "loss": 2.5798, |
| "step": 1634 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.5156678070491773, |
| "learning_rate": 0.0001577805908228293, |
| "loss": 2.4249, |
| "step": 1635 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.4867312368125412, |
| "learning_rate": 0.00015723949292685191, |
| "loss": 2.563, |
| "step": 1636 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.4817007994197343, |
| "learning_rate": 0.0001566991512883818, |
| "loss": 2.5492, |
| "step": 1637 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.4853975273245689, |
| "learning_rate": 0.00015615956709961378, |
| "loss": 2.5562, |
| "step": 1638 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.4937560660022486, |
| "learning_rate": 0.00015562074155107215, |
| "loss": 2.5272, |
| "step": 1639 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.5091009929686225, |
| "learning_rate": 0.0001550826758316068, |
| "loss": 2.5943, |
| "step": 1640 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.5116399697372868, |
| "learning_rate": 0.00015454537112839122, |
| "loss": 2.5594, |
| "step": 1641 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.5336052117112724, |
| "learning_rate": 0.00015400882862692033, |
| "loss": 2.361, |
| "step": 1642 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.4817994199538644, |
| "learning_rate": 0.00015347304951100665, |
| "loss": 2.5476, |
| "step": 1643 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.5327944497417435, |
| "learning_rate": 0.00015293803496277907, |
| "loss": 2.4896, |
| "step": 1644 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.49252872444787554, |
| "learning_rate": 0.00015240378616267886, |
| "loss": 2.397, |
| "step": 1645 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 0.4911301718625873, |
| "learning_rate": 0.00015187030428945843, |
| "loss": 2.558, |
| "step": 1646 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.533979786705545, |
| "learning_rate": 0.0001513375905201776, |
| "loss": 2.4986, |
| "step": 1647 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.542633491769744, |
| "learning_rate": 0.00015080564603020142, |
| "loss": 2.6112, |
| "step": 1648 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.48332187510046054, |
| "learning_rate": 0.0001502744719931982, |
| "loss": 2.6157, |
| "step": 1649 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.49602479515450015, |
| "learning_rate": 0.00014974406958113558, |
| "loss": 2.5562, |
| "step": 1650 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.4986682306798925, |
| "learning_rate": 0.00014921443996427947, |
| "loss": 2.4802, |
| "step": 1651 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.4763393206209734, |
| "learning_rate": 0.0001486855843111901, |
| "loss": 2.41, |
| "step": 1652 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.5157884271130471, |
| "learning_rate": 0.0001481575037887201, |
| "loss": 2.4418, |
| "step": 1653 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.5347292277827711, |
| "learning_rate": 0.00014763019956201253, |
| "loss": 2.5275, |
| "step": 1654 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.5186546622123759, |
| "learning_rate": 0.0001471036727944966, |
| "loss": 2.4704, |
| "step": 1655 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.4759363857147006, |
| "learning_rate": 0.0001465779246478872, |
| "loss": 2.4618, |
| "step": 1656 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.5121476593273676, |
| "learning_rate": 0.00014605295628218045, |
| "loss": 2.5409, |
| "step": 1657 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.47747012770687514, |
| "learning_rate": 0.0001455287688556527, |
| "loss": 2.3948, |
| "step": 1658 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.49182001061442304, |
| "learning_rate": 0.00014500536352485673, |
| "loss": 2.6656, |
| "step": 1659 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.5069101311313788, |
| "learning_rate": 0.00014448274144461965, |
| "loss": 2.5333, |
| "step": 1660 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.47722357145773503, |
| "learning_rate": 0.00014396090376804112, |
| "loss": 2.5886, |
| "step": 1661 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.45236270366705084, |
| "learning_rate": 0.00014343985164648926, |
| "loss": 2.4291, |
| "step": 1662 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.5136379799945935, |
| "learning_rate": 0.00014291958622959973, |
| "loss": 2.618, |
| "step": 1663 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.4759127319803049, |
| "learning_rate": 0.00014240010866527176, |
| "loss": 2.4588, |
| "step": 1664 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.4535562464881232, |
| "learning_rate": 0.00014188142009966686, |
| "loss": 2.4396, |
| "step": 1665 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.5206111989837898, |
| "learning_rate": 0.0001413635216772053, |
| "loss": 2.5328, |
| "step": 1666 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.5083822686894234, |
| "learning_rate": 0.000140846414540564, |
| "loss": 2.5421, |
| "step": 1667 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.46069193818270154, |
| "learning_rate": 0.00014033009983067452, |
| "loss": 2.4654, |
| "step": 1668 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.47941043462781313, |
| "learning_rate": 0.00013981457868671927, |
| "loss": 2.5035, |
| "step": 1669 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.493956466904586, |
| "learning_rate": 0.0001392998522461305, |
| "loss": 2.457, |
| "step": 1670 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.5523205855598111, |
| "learning_rate": 0.00013878592164458635, |
| "loss": 2.5295, |
| "step": 1671 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.5166288192191227, |
| "learning_rate": 0.00013827278801600978, |
| "loss": 2.4781, |
| "step": 1672 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.47358172327439146, |
| "learning_rate": 0.0001377604524925647, |
| "loss": 2.4814, |
| "step": 1673 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.4770301352213666, |
| "learning_rate": 0.00013724891620465424, |
| "loss": 2.5479, |
| "step": 1674 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.4880976901676004, |
| "learning_rate": 0.0001367381802809185, |
| "loss": 2.4838, |
| "step": 1675 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.5711241412311223, |
| "learning_rate": 0.00013622824584823113, |
| "loss": 2.4185, |
| "step": 1676 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.49428911380322793, |
| "learning_rate": 0.00013571911403169795, |
| "loss": 2.4018, |
| "step": 1677 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.5939362491722024, |
| "learning_rate": 0.0001352107859546533, |
| "loss": 2.479, |
| "step": 1678 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.4887741420753013, |
| "learning_rate": 0.00013470326273865886, |
| "loss": 2.4499, |
| "step": 1679 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.4775187133132671, |
| "learning_rate": 0.00013419654550349985, |
| "loss": 2.4855, |
| "step": 1680 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.5213150259392106, |
| "learning_rate": 0.00013369063536718346, |
| "loss": 2.5284, |
| "step": 1681 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.48517389680326095, |
| "learning_rate": 0.00013318553344593632, |
| "loss": 2.5156, |
| "step": 1682 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.45933898295250414, |
| "learning_rate": 0.00013268124085420136, |
| "loss": 2.5019, |
| "step": 1683 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.49288778513831705, |
| "learning_rate": 0.0001321777587046364, |
| "loss": 2.4447, |
| "step": 1684 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.49814618804823596, |
| "learning_rate": 0.00013167508810811059, |
| "loss": 2.463, |
| "step": 1685 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.4787583974368575, |
| "learning_rate": 0.0001311732301737029, |
| "loss": 2.4905, |
| "step": 1686 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.4773848541282779, |
| "learning_rate": 0.0001306721860086991, |
| "loss": 2.5249, |
| "step": 1687 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.506856499297519, |
| "learning_rate": 0.00013017195671858928, |
| "loss": 2.4788, |
| "step": 1688 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.4944017197136427, |
| "learning_rate": 0.0001296725434070661, |
| "loss": 2.5228, |
| "step": 1689 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.5219955083690255, |
| "learning_rate": 0.00012917394717602121, |
| "loss": 2.4959, |
| "step": 1690 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.5340253590174425, |
| "learning_rate": 0.00012867616912554426, |
| "loss": 2.4934, |
| "step": 1691 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.5316267520351655, |
| "learning_rate": 0.00012817921035391882, |
| "loss": 2.4332, |
| "step": 1692 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.4840527660459306, |
| "learning_rate": 0.00012768307195762168, |
| "loss": 2.4553, |
| "step": 1693 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.4989323434240688, |
| "learning_rate": 0.00012718775503131908, |
| "loss": 2.5446, |
| "step": 1694 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.5154240566204931, |
| "learning_rate": 0.0001266932606678646, |
| "loss": 2.4555, |
| "step": 1695 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.4834608174923797, |
| "learning_rate": 0.00012619958995829756, |
| "loss": 2.4454, |
| "step": 1696 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.4798070045845761, |
| "learning_rate": 0.0001257067439918394, |
| "loss": 2.5407, |
| "step": 1697 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.47380589667045514, |
| "learning_rate": 0.00012521472385589234, |
| "loss": 2.471, |
| "step": 1698 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.49925322110277814, |
| "learning_rate": 0.00012472353063603626, |
| "loss": 2.6223, |
| "step": 1699 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.510693353358162, |
| "learning_rate": 0.0001242331654160263, |
| "loss": 2.447, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.49337152499586484, |
| "learning_rate": 0.0001237436292777914, |
| "loss": 2.3888, |
| "step": 1701 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.5014663755819757, |
| "learning_rate": 0.00012325492330143061, |
| "loss": 2.5923, |
| "step": 1702 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.5534822560704987, |
| "learning_rate": 0.00012276704856521175, |
| "loss": 2.4527, |
| "step": 1703 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.4539182451745059, |
| "learning_rate": 0.00012228000614556816, |
| "loss": 2.5278, |
| "step": 1704 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.4748313317188319, |
| "learning_rate": 0.00012179379711709738, |
| "loss": 2.5057, |
| "step": 1705 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.5084200021162434, |
| "learning_rate": 0.0001213084225525577, |
| "loss": 2.4865, |
| "step": 1706 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.4710324151826903, |
| "learning_rate": 0.00012082388352286627, |
| "loss": 2.5069, |
| "step": 1707 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.4765828994810984, |
| "learning_rate": 0.00012034018109709716, |
| "loss": 2.5095, |
| "step": 1708 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.4933785732079107, |
| "learning_rate": 0.00011985731634247809, |
| "loss": 2.4232, |
| "step": 1709 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.48013457649120683, |
| "learning_rate": 0.00011937529032438904, |
| "loss": 2.6492, |
| "step": 1710 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.5277859315980274, |
| "learning_rate": 0.00011889410410635887, |
| "loss": 2.3981, |
| "step": 1711 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.47396965540581415, |
| "learning_rate": 0.0001184137587500641, |
| "loss": 2.4431, |
| "step": 1712 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.4900516036924553, |
| "learning_rate": 0.00011793425531532564, |
| "loss": 2.5181, |
| "step": 1713 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.514664452602415, |
| "learning_rate": 0.00011745559486010671, |
| "loss": 2.5229, |
| "step": 1714 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.4977949605464075, |
| "learning_rate": 0.00011697777844051105, |
| "loss": 2.5569, |
| "step": 1715 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.4766505302523954, |
| "learning_rate": 0.00011650080711077964, |
| "loss": 2.5016, |
| "step": 1716 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.4783613767475764, |
| "learning_rate": 0.00011602468192328936, |
| "loss": 2.5262, |
| "step": 1717 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.5500730863746356, |
| "learning_rate": 0.00011554940392854973, |
| "loss": 2.5306, |
| "step": 1718 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.49403130978791154, |
| "learning_rate": 0.00011507497417520146, |
| "loss": 2.5006, |
| "step": 1719 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.49100523001026963, |
| "learning_rate": 0.00011460139371001339, |
| "loss": 2.4076, |
| "step": 1720 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.4684378206856686, |
| "learning_rate": 0.00011412866357788049, |
| "loss": 2.5132, |
| "step": 1721 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.48382970199174696, |
| "learning_rate": 0.00011365678482182207, |
| "loss": 2.5031, |
| "step": 1722 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.5073055774512982, |
| "learning_rate": 0.0001131857584829783, |
| "loss": 2.4654, |
| "step": 1723 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.48419954553261507, |
| "learning_rate": 0.0001127155856006093, |
| "loss": 2.4107, |
| "step": 1724 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.45819131915920314, |
| "learning_rate": 0.00011224626721209141, |
| "loss": 2.5007, |
| "step": 1725 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.48985203806950944, |
| "learning_rate": 0.0001117778043529164, |
| "loss": 2.4952, |
| "step": 1726 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.4771497637444371, |
| "learning_rate": 0.0001113101980566879, |
| "loss": 2.4493, |
| "step": 1727 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.48700291111572364, |
| "learning_rate": 0.00011084344935511958, |
| "loss": 2.5351, |
| "step": 1728 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.49499866982566637, |
| "learning_rate": 0.00011037755927803345, |
| "loss": 2.4717, |
| "step": 1729 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.48340526480304186, |
| "learning_rate": 0.00010991252885335651, |
| "loss": 2.501, |
| "step": 1730 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.47954406731772076, |
| "learning_rate": 0.00010944835910711958, |
| "loss": 2.5217, |
| "step": 1731 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.511854445840703, |
| "learning_rate": 0.00010898505106345396, |
| "loss": 2.4747, |
| "step": 1732 |
| }, |
| { |
| "epoch": 0.79, |
| "grad_norm": 0.5063829232739724, |
| "learning_rate": 0.00010852260574459022, |
| "loss": 2.4484, |
| "step": 1733 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.49597496485661313, |
| "learning_rate": 0.00010806102417085512, |
| "loss": 2.6122, |
| "step": 1734 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.4507929494770593, |
| "learning_rate": 0.00010760030736066951, |
| "loss": 2.5208, |
| "step": 1735 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.5065136701854726, |
| "learning_rate": 0.00010714045633054687, |
| "loss": 2.5252, |
| "step": 1736 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.6033620144440229, |
| "learning_rate": 0.00010668147209508971, |
| "loss": 2.5541, |
| "step": 1737 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.493535983774145, |
| "learning_rate": 0.00010622335566698877, |
| "loss": 2.4999, |
| "step": 1738 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.48564024994086313, |
| "learning_rate": 0.00010576610805701942, |
| "loss": 2.6395, |
| "step": 1739 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.7955208443640502, |
| "learning_rate": 0.00010530973027404073, |
| "loss": 2.4878, |
| "step": 1740 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.503930891979233, |
| "learning_rate": 0.00010485422332499212, |
| "loss": 2.4314, |
| "step": 1741 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.5628557508733957, |
| "learning_rate": 0.00010439958821489165, |
| "loss": 2.4612, |
| "step": 1742 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.4966902856980962, |
| "learning_rate": 0.00010394582594683428, |
| "loss": 2.4953, |
| "step": 1743 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.511269305249655, |
| "learning_rate": 0.0001034929375219884, |
| "loss": 2.4392, |
| "step": 1744 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.5153797695401156, |
| "learning_rate": 0.00010304092393959514, |
| "loss": 2.4748, |
| "step": 1745 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.47898597196056075, |
| "learning_rate": 0.00010258978619696468, |
| "loss": 2.5389, |
| "step": 1746 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.49265700010979446, |
| "learning_rate": 0.00010213952528947551, |
| "loss": 2.5826, |
| "step": 1747 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.4852075396244413, |
| "learning_rate": 0.00010169014221057089, |
| "loss": 2.5547, |
| "step": 1748 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.4841250148186547, |
| "learning_rate": 0.00010124163795175734, |
| "loss": 2.4577, |
| "step": 1749 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.47138964495383906, |
| "learning_rate": 0.00010079401350260287, |
| "loss": 2.5312, |
| "step": 1750 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.4837905974005405, |
| "learning_rate": 0.00010034726985073362, |
| "loss": 2.4862, |
| "step": 1751 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.4989005400341248, |
| "learning_rate": 9.9901407981833e-05, |
| "loss": 2.5092, |
| "step": 1752 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.49713508101862813, |
| "learning_rate": 9.94564288796384e-05, |
| "loss": 2.5192, |
| "step": 1753 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.50943757525149, |
| "learning_rate": 9.901233352593953e-05, |
| "loss": 2.4949, |
| "step": 1754 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.49912301670356146, |
| "learning_rate": 9.856912290057668e-05, |
| "loss": 2.5736, |
| "step": 1755 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.5625804318324512, |
| "learning_rate": 9.812679798143748e-05, |
| "loss": 2.4296, |
| "step": 1756 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.4982124139572677, |
| "learning_rate": 9.768535974445586e-05, |
| "loss": 2.444, |
| "step": 1757 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.8223101819355314, |
| "learning_rate": 9.724480916360906e-05, |
| "loss": 2.5988, |
| "step": 1758 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.5124444392805361, |
| "learning_rate": 9.68051472109162e-05, |
| "loss": 2.4044, |
| "step": 1759 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.5146328333009864, |
| "learning_rate": 9.636637485643529e-05, |
| "loss": 2.5374, |
| "step": 1760 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.6680579659934772, |
| "learning_rate": 9.592849306826174e-05, |
| "loss": 2.4889, |
| "step": 1761 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.49364845389021234, |
| "learning_rate": 9.549150281252633e-05, |
| "loss": 2.4319, |
| "step": 1762 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.5104584088031892, |
| "learning_rate": 9.505540505339223e-05, |
| "loss": 2.5033, |
| "step": 1763 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.4814119754755146, |
| "learning_rate": 9.4620200753054e-05, |
| "loss": 2.4788, |
| "step": 1764 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.5005591747400733, |
| "learning_rate": 9.418589087173441e-05, |
| "loss": 2.5262, |
| "step": 1765 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.529873407008499, |
| "learning_rate": 9.375247636768325e-05, |
| "loss": 2.3737, |
| "step": 1766 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.4836862452869986, |
| "learning_rate": 9.331995819717443e-05, |
| "loss": 2.4929, |
| "step": 1767 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.46450793289742176, |
| "learning_rate": 9.288833731450419e-05, |
| "loss": 2.4862, |
| "step": 1768 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.47222459703150393, |
| "learning_rate": 9.245761467198948e-05, |
| "loss": 2.4091, |
| "step": 1769 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.5014324055095087, |
| "learning_rate": 9.20277912199648e-05, |
| "loss": 2.4998, |
| "step": 1770 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.50025820350285, |
| "learning_rate": 9.159886790678123e-05, |
| "loss": 2.4854, |
| "step": 1771 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.47154902887902367, |
| "learning_rate": 9.11708456788033e-05, |
| "loss": 2.4234, |
| "step": 1772 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.5474633494982973, |
| "learning_rate": 9.074372548040793e-05, |
| "loss": 2.5218, |
| "step": 1773 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.49686082002805537, |
| "learning_rate": 9.031750825398145e-05, |
| "loss": 2.5018, |
| "step": 1774 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.4873292601965894, |
| "learning_rate": 8.98921949399179e-05, |
| "loss": 2.3941, |
| "step": 1775 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.47548810331996233, |
| "learning_rate": 8.94677864766173e-05, |
| "loss": 2.4201, |
| "step": 1776 |
| }, |
| { |
| "epoch": 0.81, |
| "grad_norm": 0.5418194297293858, |
| "learning_rate": 8.904428380048269e-05, |
| "loss": 2.5013, |
| "step": 1777 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.4928800199857713, |
| "learning_rate": 8.862168784591929e-05, |
| "loss": 2.5545, |
| "step": 1778 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.4947379856755676, |
| "learning_rate": 8.819999954533115e-05, |
| "loss": 2.4557, |
| "step": 1779 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.471991602953924, |
| "learning_rate": 8.777921982911996e-05, |
| "loss": 2.4329, |
| "step": 1780 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.4948737635468671, |
| "learning_rate": 8.735934962568253e-05, |
| "loss": 2.4656, |
| "step": 1781 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.5080957225585496, |
| "learning_rate": 8.694038986140945e-05, |
| "loss": 2.5197, |
| "step": 1782 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.5050049855018721, |
| "learning_rate": 8.652234146068206e-05, |
| "loss": 2.528, |
| "step": 1783 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.49562522996915914, |
| "learning_rate": 8.610520534587086e-05, |
| "loss": 2.5923, |
| "step": 1784 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.4815958893621696, |
| "learning_rate": 8.568898243733397e-05, |
| "loss": 2.5384, |
| "step": 1785 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.48266413036771605, |
| "learning_rate": 8.527367365341409e-05, |
| "loss": 2.4513, |
| "step": 1786 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.5443793463319634, |
| "learning_rate": 8.485927991043757e-05, |
| "loss": 2.4751, |
| "step": 1787 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.4856938403270964, |
| "learning_rate": 8.444580212271125e-05, |
| "loss": 2.5508, |
| "step": 1788 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.4816153059357494, |
| "learning_rate": 8.403324120252159e-05, |
| "loss": 2.4635, |
| "step": 1789 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.4885065424963726, |
| "learning_rate": 8.362159806013175e-05, |
| "loss": 2.4324, |
| "step": 1790 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.47557615634661826, |
| "learning_rate": 8.321087360377988e-05, |
| "loss": 2.54, |
| "step": 1791 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.8616762548429036, |
| "learning_rate": 8.280106873967752e-05, |
| "loss": 2.5042, |
| "step": 1792 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 1.4167907801381532, |
| "learning_rate": 8.239218437200679e-05, |
| "loss": 2.5076, |
| "step": 1793 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.5274666101077635, |
| "learning_rate": 8.198422140291939e-05, |
| "loss": 2.5264, |
| "step": 1794 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.481591538498639, |
| "learning_rate": 8.157718073253351e-05, |
| "loss": 2.5296, |
| "step": 1795 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.4836225474953764, |
| "learning_rate": 8.117106325893287e-05, |
| "loss": 2.5597, |
| "step": 1796 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.4708858650048459, |
| "learning_rate": 8.076586987816404e-05, |
| "loss": 2.4979, |
| "step": 1797 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.5047344065059012, |
| "learning_rate": 8.036160148423449e-05, |
| "loss": 2.3733, |
| "step": 1798 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.5042772691541274, |
| "learning_rate": 7.995825896911141e-05, |
| "loss": 2.5229, |
| "step": 1799 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.5041097814385216, |
| "learning_rate": 7.955584322271853e-05, |
| "loss": 2.4416, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.6772215223163667, |
| "learning_rate": 7.915435513293523e-05, |
| "loss": 2.4646, |
| "step": 1801 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.5029120093730223, |
| "learning_rate": 7.875379558559387e-05, |
| "loss": 2.4936, |
| "step": 1802 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.4654108666741528, |
| "learning_rate": 7.835416546447838e-05, |
| "loss": 2.5086, |
| "step": 1803 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.4851997142629299, |
| "learning_rate": 7.795546565132167e-05, |
| "loss": 2.4338, |
| "step": 1804 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.4563319398488783, |
| "learning_rate": 7.755769702580412e-05, |
| "loss": 2.4164, |
| "step": 1805 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.48525836796972727, |
| "learning_rate": 7.716086046555193e-05, |
| "loss": 2.4929, |
| "step": 1806 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.4933679596164138, |
| "learning_rate": 7.676495684613432e-05, |
| "loss": 2.6171, |
| "step": 1807 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.4938516618914545, |
| "learning_rate": 7.636998704106252e-05, |
| "loss": 2.4494, |
| "step": 1808 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.46706827546379526, |
| "learning_rate": 7.597595192178702e-05, |
| "loss": 2.5476, |
| "step": 1809 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.5103330490727399, |
| "learning_rate": 7.558285235769646e-05, |
| "loss": 2.4865, |
| "step": 1810 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.5282290131744511, |
| "learning_rate": 7.519068921611494e-05, |
| "loss": 2.5073, |
| "step": 1811 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.459631186149333, |
| "learning_rate": 7.479946336230047e-05, |
| "loss": 2.4776, |
| "step": 1812 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.4751450121165003, |
| "learning_rate": 7.440917565944349e-05, |
| "loss": 2.4864, |
| "step": 1813 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.5060765169709829, |
| "learning_rate": 7.4019826968664e-05, |
| "loss": 2.4836, |
| "step": 1814 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.46014060686689534, |
| "learning_rate": 7.363141814901053e-05, |
| "loss": 2.4447, |
| "step": 1815 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.466719426825169, |
| "learning_rate": 7.32439500574577e-05, |
| "loss": 2.4263, |
| "step": 1816 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.4538765011842207, |
| "learning_rate": 7.285742354890473e-05, |
| "loss": 2.4786, |
| "step": 1817 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.601929132614099, |
| "learning_rate": 7.247183947617325e-05, |
| "loss": 2.3913, |
| "step": 1818 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.5169227078725083, |
| "learning_rate": 7.20871986900053e-05, |
| "loss": 2.3806, |
| "step": 1819 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.46057406424872444, |
| "learning_rate": 7.170350203906218e-05, |
| "loss": 2.4692, |
| "step": 1820 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.45837009198496315, |
| "learning_rate": 7.132075036992158e-05, |
| "loss": 2.454, |
| "step": 1821 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.46808778954642893, |
| "learning_rate": 7.093894452707666e-05, |
| "loss": 2.5897, |
| "step": 1822 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.514265848948864, |
| "learning_rate": 7.055808535293334e-05, |
| "loss": 2.4993, |
| "step": 1823 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.497951858549981, |
| "learning_rate": 7.017817368780888e-05, |
| "loss": 2.4791, |
| "step": 1824 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.5299718681970162, |
| "learning_rate": 6.979921036993042e-05, |
| "loss": 2.4607, |
| "step": 1825 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.4918698191060388, |
| "learning_rate": 6.942119623543202e-05, |
| "loss": 2.5562, |
| "step": 1826 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.5140213043923514, |
| "learning_rate": 6.904413211835414e-05, |
| "loss": 2.4798, |
| "step": 1827 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.4753103253088113, |
| "learning_rate": 6.866801885064056e-05, |
| "loss": 2.5199, |
| "step": 1828 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.4774725333675286, |
| "learning_rate": 6.829285726213769e-05, |
| "loss": 2.3753, |
| "step": 1829 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.4922906848244813, |
| "learning_rate": 6.79186481805918e-05, |
| "loss": 2.5291, |
| "step": 1830 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.5037774359183158, |
| "learning_rate": 6.754539243164754e-05, |
| "loss": 2.6262, |
| "step": 1831 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.5624207455104502, |
| "learning_rate": 6.717309083884654e-05, |
| "loss": 2.4032, |
| "step": 1832 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.4901647397490662, |
| "learning_rate": 6.680174422362468e-05, |
| "loss": 2.551, |
| "step": 1833 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.5981633174839787, |
| "learning_rate": 6.643135340531136e-05, |
| "loss": 2.4371, |
| "step": 1834 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.4703156366756965, |
| "learning_rate": 6.606191920112664e-05, |
| "loss": 2.4547, |
| "step": 1835 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.4750314055756865, |
| "learning_rate": 6.569344242618036e-05, |
| "loss": 2.5008, |
| "step": 1836 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.4750850455377836, |
| "learning_rate": 6.532592389346958e-05, |
| "loss": 2.4193, |
| "step": 1837 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.4903293387618661, |
| "learning_rate": 6.495936441387713e-05, |
| "loss": 2.3482, |
| "step": 1838 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.5762463374447352, |
| "learning_rate": 6.459376479617013e-05, |
| "loss": 2.5263, |
| "step": 1839 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.5321391048258907, |
| "learning_rate": 6.422912584699752e-05, |
| "loss": 2.4921, |
| "step": 1840 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.4817674618793209, |
| "learning_rate": 6.386544837088904e-05, |
| "loss": 2.4861, |
| "step": 1841 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.5007780511540679, |
| "learning_rate": 6.350273317025251e-05, |
| "loss": 2.4532, |
| "step": 1842 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.46545193488150516, |
| "learning_rate": 6.314098104537324e-05, |
| "loss": 2.4325, |
| "step": 1843 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.46275730470567783, |
| "learning_rate": 6.278019279441122e-05, |
| "loss": 2.49, |
| "step": 1844 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.4872804831206214, |
| "learning_rate": 6.242036921339972e-05, |
| "loss": 2.504, |
| "step": 1845 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.5022271566408651, |
| "learning_rate": 6.206151109624402e-05, |
| "loss": 2.4448, |
| "step": 1846 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.4883273442039465, |
| "learning_rate": 6.170361923471868e-05, |
| "loss": 2.4733, |
| "step": 1847 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.5366690188458575, |
| "learning_rate": 6.134669441846691e-05, |
| "loss": 2.4988, |
| "step": 1848 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.48109178164459643, |
| "learning_rate": 6.099073743499772e-05, |
| "loss": 2.4073, |
| "step": 1849 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.46104925802551533, |
| "learning_rate": 6.063574906968511e-05, |
| "loss": 2.4887, |
| "step": 1850 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.4523454432709686, |
| "learning_rate": 6.028173010576582e-05, |
| "loss": 2.4282, |
| "step": 1851 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.49217240165589776, |
| "learning_rate": 5.9928681324337544e-05, |
| "loss": 2.5639, |
| "step": 1852 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.48893482476264827, |
| "learning_rate": 5.957660350435773e-05, |
| "loss": 2.4191, |
| "step": 1853 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.46864859368149986, |
| "learning_rate": 5.922549742264122e-05, |
| "loss": 2.4846, |
| "step": 1854 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.4748291780861821, |
| "learning_rate": 5.8875363853859166e-05, |
| "loss": 2.5217, |
| "step": 1855 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.48604447665038564, |
| "learning_rate": 5.852620357053651e-05, |
| "loss": 2.3752, |
| "step": 1856 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.5241776253953592, |
| "learning_rate": 5.8178017343051336e-05, |
| "loss": 2.5564, |
| "step": 1857 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.4998661117080439, |
| "learning_rate": 5.783080593963219e-05, |
| "loss": 2.4466, |
| "step": 1858 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.46278033577691946, |
| "learning_rate": 5.748457012635683e-05, |
| "loss": 2.3751, |
| "step": 1859 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.4830880016324968, |
| "learning_rate": 5.713931066715078e-05, |
| "loss": 2.4588, |
| "step": 1860 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.48607590924483707, |
| "learning_rate": 5.679502832378497e-05, |
| "loss": 2.4272, |
| "step": 1861 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.5109731811139948, |
| "learning_rate": 5.645172385587482e-05, |
| "loss": 2.5773, |
| "step": 1862 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.48675120768507907, |
| "learning_rate": 5.6109398020877834e-05, |
| "loss": 2.5622, |
| "step": 1863 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 0.46030329773837253, |
| "learning_rate": 5.576805157409265e-05, |
| "loss": 2.4461, |
| "step": 1864 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.4813309294245707, |
| "learning_rate": 5.542768526865677e-05, |
| "loss": 2.4583, |
| "step": 1865 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.4708836384976647, |
| "learning_rate": 5.508829985554509e-05, |
| "loss": 2.3381, |
| "step": 1866 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.5261588855277416, |
| "learning_rate": 5.474989608356856e-05, |
| "loss": 2.4841, |
| "step": 1867 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.5000825794389359, |
| "learning_rate": 5.441247469937194e-05, |
| "loss": 2.5021, |
| "step": 1868 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.5656641204699344, |
| "learning_rate": 5.407603644743286e-05, |
| "loss": 2.4857, |
| "step": 1869 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.498358394158879, |
| "learning_rate": 5.374058207005944e-05, |
| "loss": 2.6085, |
| "step": 1870 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.7368926795812009, |
| "learning_rate": 5.3406112307389066e-05, |
| "loss": 2.5744, |
| "step": 1871 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.4795977693410511, |
| "learning_rate": 5.3072627897386926e-05, |
| "loss": 2.4284, |
| "step": 1872 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.48887482962541645, |
| "learning_rate": 5.27401295758439e-05, |
| "loss": 2.5113, |
| "step": 1873 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.5008906195103082, |
| "learning_rate": 5.2408618076375315e-05, |
| "loss": 2.4958, |
| "step": 1874 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.5319428958109043, |
| "learning_rate": 5.207809413041914e-05, |
| "loss": 2.368, |
| "step": 1875 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.4835563168853959, |
| "learning_rate": 5.174855846723459e-05, |
| "loss": 2.5121, |
| "step": 1876 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.4948933838226983, |
| "learning_rate": 5.1420011813900104e-05, |
| "loss": 2.4179, |
| "step": 1877 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.4697347661111251, |
| "learning_rate": 5.109245489531211e-05, |
| "loss": 2.4139, |
| "step": 1878 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.5106428517031374, |
| "learning_rate": 5.0765888434183446e-05, |
| "loss": 2.4866, |
| "step": 1879 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.4692167121679813, |
| "learning_rate": 5.0440313151041364e-05, |
| "loss": 2.5335, |
| "step": 1880 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.4901350561540393, |
| "learning_rate": 5.011572976422657e-05, |
| "loss": 2.5113, |
| "step": 1881 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.5081179718805583, |
| "learning_rate": 4.9792138989890825e-05, |
| "loss": 2.5291, |
| "step": 1882 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.5216489942728352, |
| "learning_rate": 4.9469541541996234e-05, |
| "loss": 2.4894, |
| "step": 1883 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.49252597194726827, |
| "learning_rate": 4.914793813231305e-05, |
| "loss": 2.4614, |
| "step": 1884 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.6077253947767929, |
| "learning_rate": 4.882732947041818e-05, |
| "loss": 2.4602, |
| "step": 1885 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.4903814664496128, |
| "learning_rate": 4.850771626369416e-05, |
| "loss": 2.4503, |
| "step": 1886 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.482163118854688, |
| "learning_rate": 4.818909921732662e-05, |
| "loss": 2.5783, |
| "step": 1887 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.6936218449782011, |
| "learning_rate": 4.787147903430383e-05, |
| "loss": 2.4654, |
| "step": 1888 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.45670242998591226, |
| "learning_rate": 4.755485641541424e-05, |
| "loss": 2.5051, |
| "step": 1889 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.46405375755871187, |
| "learning_rate": 4.723923205924557e-05, |
| "loss": 2.464, |
| "step": 1890 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.47956668781743667, |
| "learning_rate": 4.6924606662182736e-05, |
| "loss": 2.6138, |
| "step": 1891 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.4737388213988824, |
| "learning_rate": 4.6610980918406596e-05, |
| "loss": 2.4638, |
| "step": 1892 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.4786841871309686, |
| "learning_rate": 4.629835551989276e-05, |
| "loss": 2.4283, |
| "step": 1893 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.5108205496990064, |
| "learning_rate": 4.5986731156409224e-05, |
| "loss": 2.5586, |
| "step": 1894 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.5434047482309888, |
| "learning_rate": 4.567610851551568e-05, |
| "loss": 2.42, |
| "step": 1895 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.5014960048530787, |
| "learning_rate": 4.536648828256146e-05, |
| "loss": 2.5231, |
| "step": 1896 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.5031417635019236, |
| "learning_rate": 4.505787114068433e-05, |
| "loss": 2.566, |
| "step": 1897 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.5162901063903608, |
| "learning_rate": 4.4750257770808764e-05, |
| "loss": 2.5724, |
| "step": 1898 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.46703377282722, |
| "learning_rate": 4.444364885164448e-05, |
| "loss": 2.4333, |
| "step": 1899 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.4916373508413243, |
| "learning_rate": 4.413804505968533e-05, |
| "loss": 2.4356, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.4865391948858508, |
| "learning_rate": 4.3833447069206944e-05, |
| "loss": 2.4295, |
| "step": 1901 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.4834698173562601, |
| "learning_rate": 4.352985555226635e-05, |
| "loss": 2.437, |
| "step": 1902 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.4947423756627944, |
| "learning_rate": 4.322727117869951e-05, |
| "loss": 2.4773, |
| "step": 1903 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.48642882126878173, |
| "learning_rate": 4.29256946161205e-05, |
| "loss": 2.381, |
| "step": 1904 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.48654210041953627, |
| "learning_rate": 4.262512652991968e-05, |
| "loss": 2.6013, |
| "step": 1905 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.48760732489191366, |
| "learning_rate": 4.2325567583262113e-05, |
| "loss": 2.4916, |
| "step": 1906 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.5061578445414661, |
| "learning_rate": 4.2027018437086895e-05, |
| "loss": 2.5317, |
| "step": 1907 |
| }, |
| { |
| "epoch": 0.87, |
| "grad_norm": 0.49864772561663084, |
| "learning_rate": 4.172947975010449e-05, |
| "loss": 2.4018, |
| "step": 1908 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.4718942118267857, |
| "learning_rate": 4.143295217879645e-05, |
| "loss": 2.4173, |
| "step": 1909 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.5439177215546779, |
| "learning_rate": 4.113743637741296e-05, |
| "loss": 2.425, |
| "step": 1910 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.5657490002007386, |
| "learning_rate": 4.084293299797226e-05, |
| "loss": 2.4059, |
| "step": 1911 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.4882167906904221, |
| "learning_rate": 4.054944269025862e-05, |
| "loss": 2.5516, |
| "step": 1912 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.49121266487086207, |
| "learning_rate": 4.025696610182095e-05, |
| "loss": 2.4082, |
| "step": 1913 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.4864668948140098, |
| "learning_rate": 3.996550387797187e-05, |
| "loss": 2.5932, |
| "step": 1914 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.5009717280466736, |
| "learning_rate": 3.9675056661785556e-05, |
| "loss": 2.5624, |
| "step": 1915 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.4780980121947334, |
| "learning_rate": 3.9385625094097154e-05, |
| "loss": 2.4247, |
| "step": 1916 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.5050455394262786, |
| "learning_rate": 3.909720981350034e-05, |
| "loss": 2.4489, |
| "step": 1917 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.48303948975384065, |
| "learning_rate": 3.880981145634704e-05, |
| "loss": 2.4087, |
| "step": 1918 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.48303477871781375, |
| "learning_rate": 3.852343065674507e-05, |
| "loss": 2.4086, |
| "step": 1919 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.4603602936798697, |
| "learning_rate": 3.8238068046557276e-05, |
| "loss": 2.4351, |
| "step": 1920 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.5312239089721331, |
| "learning_rate": 3.795372425540006e-05, |
| "loss": 2.4597, |
| "step": 1921 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.47949901054773925, |
| "learning_rate": 3.76703999106418e-05, |
| "loss": 2.5543, |
| "step": 1922 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.526415826603923, |
| "learning_rate": 3.7388095637401754e-05, |
| "loss": 2.4712, |
| "step": 1923 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.48977800882487166, |
| "learning_rate": 3.7106812058548376e-05, |
| "loss": 2.5438, |
| "step": 1924 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.4904417163750087, |
| "learning_rate": 3.682654979469807e-05, |
| "loss": 2.5555, |
| "step": 1925 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.5328538940353083, |
| "learning_rate": 3.654730946421403e-05, |
| "loss": 2.524, |
| "step": 1926 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.47947208647196915, |
| "learning_rate": 3.6269091683204466e-05, |
| "loss": 2.5465, |
| "step": 1927 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.47668564587936885, |
| "learning_rate": 3.5991897065521693e-05, |
| "loss": 2.4988, |
| "step": 1928 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.46932070635022216, |
| "learning_rate": 3.571572622276026e-05, |
| "loss": 2.4493, |
| "step": 1929 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.48305946295140123, |
| "learning_rate": 3.544057976425619e-05, |
| "loss": 2.5577, |
| "step": 1930 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.5407896032545131, |
| "learning_rate": 3.5166458297085146e-05, |
| "loss": 2.5098, |
| "step": 1931 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.4731746412914242, |
| "learning_rate": 3.489336242606111e-05, |
| "loss": 2.5131, |
| "step": 1932 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.4829946660821869, |
| "learning_rate": 3.462129275373577e-05, |
| "loss": 2.4328, |
| "step": 1933 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.5102092459689559, |
| "learning_rate": 3.4350249880395924e-05, |
| "loss": 2.4461, |
| "step": 1934 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.4800180998749246, |
| "learning_rate": 3.408023440406355e-05, |
| "loss": 2.444, |
| "step": 1935 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.5523121052442633, |
| "learning_rate": 3.381124692049331e-05, |
| "loss": 2.5434, |
| "step": 1936 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.4745325573071214, |
| "learning_rate": 3.354328802317197e-05, |
| "loss": 2.4155, |
| "step": 1937 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.4821317676563876, |
| "learning_rate": 3.327635830331677e-05, |
| "loss": 2.4111, |
| "step": 1938 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.45925757495143193, |
| "learning_rate": 3.3010458349874206e-05, |
| "loss": 2.4418, |
| "step": 1939 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.4736223344866007, |
| "learning_rate": 3.2745588749518775e-05, |
| "loss": 2.5035, |
| "step": 1940 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.4801701461411315, |
| "learning_rate": 3.248175008665161e-05, |
| "loss": 2.5028, |
| "step": 1941 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.5039213243783119, |
| "learning_rate": 3.221894294339911e-05, |
| "loss": 2.4216, |
| "step": 1942 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.48221406974786735, |
| "learning_rate": 3.1957167899611836e-05, |
| "loss": 2.4934, |
| "step": 1943 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.5057883336355808, |
| "learning_rate": 3.169642553286334e-05, |
| "loss": 2.4381, |
| "step": 1944 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.47173219991284926, |
| "learning_rate": 3.143671641844831e-05, |
| "loss": 2.5562, |
| "step": 1945 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.48352077379144026, |
| "learning_rate": 3.117804112938205e-05, |
| "loss": 2.4171, |
| "step": 1946 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.5522797538192431, |
| "learning_rate": 3.092040023639869e-05, |
| "loss": 2.4185, |
| "step": 1947 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.5019269932976773, |
| "learning_rate": 3.066379430795002e-05, |
| "loss": 2.4648, |
| "step": 1948 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.46347258436862193, |
| "learning_rate": 3.040822391020459e-05, |
| "loss": 2.4269, |
| "step": 1949 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.4891437801207331, |
| "learning_rate": 3.0153689607045842e-05, |
| "loss": 2.4576, |
| "step": 1950 |
| }, |
| { |
| "epoch": 0.89, |
| "grad_norm": 0.4853641089034576, |
| "learning_rate": 2.9900191960071545e-05, |
| "loss": 2.4877, |
| "step": 1951 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.5435269151837682, |
| "learning_rate": 2.9647731528591848e-05, |
| "loss": 2.4506, |
| "step": 1952 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.49877825150658556, |
| "learning_rate": 2.9396308869628795e-05, |
| "loss": 2.5198, |
| "step": 1953 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.48986698376256627, |
| "learning_rate": 2.914592453791448e-05, |
| "loss": 2.5206, |
| "step": 1954 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.560819387589192, |
| "learning_rate": 2.8896579085889994e-05, |
| "loss": 2.4551, |
| "step": 1955 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.5252954607521844, |
| "learning_rate": 2.86482730637046e-05, |
| "loss": 2.4499, |
| "step": 1956 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.49384808945048086, |
| "learning_rate": 2.840100701921383e-05, |
| "loss": 2.4737, |
| "step": 1957 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.5059505510346757, |
| "learning_rate": 2.8154781497978898e-05, |
| "loss": 2.4973, |
| "step": 1958 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.48951206497683153, |
| "learning_rate": 2.7909597043265013e-05, |
| "loss": 2.4502, |
| "step": 1959 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.46567043035881156, |
| "learning_rate": 2.7665454196040662e-05, |
| "loss": 2.4743, |
| "step": 1960 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.46554817766833295, |
| "learning_rate": 2.7422353494975905e-05, |
| "loss": 2.544, |
| "step": 1961 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.45679726602575377, |
| "learning_rate": 2.7180295476441573e-05, |
| "loss": 2.5594, |
| "step": 1962 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.501511873500935, |
| "learning_rate": 2.6939280674508016e-05, |
| "loss": 2.428, |
| "step": 1963 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.5009907662659845, |
| "learning_rate": 2.669930962094358e-05, |
| "loss": 2.4699, |
| "step": 1964 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.512467420665581, |
| "learning_rate": 2.6460382845214126e-05, |
| "loss": 2.4946, |
| "step": 1965 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.49094519896944616, |
| "learning_rate": 2.6222500874481025e-05, |
| "loss": 2.4896, |
| "step": 1966 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.48041931545896044, |
| "learning_rate": 2.5985664233600827e-05, |
| "loss": 2.4688, |
| "step": 1967 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.5100220687824957, |
| "learning_rate": 2.574987344512336e-05, |
| "loss": 2.5375, |
| "step": 1968 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.4716229763846753, |
| "learning_rate": 2.5515129029290984e-05, |
| "loss": 2.5024, |
| "step": 1969 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 1.0929421676100497, |
| "learning_rate": 2.5281431504037556e-05, |
| "loss": 2.5356, |
| "step": 1970 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.49918124338700626, |
| "learning_rate": 2.504878138498684e-05, |
| "loss": 2.4546, |
| "step": 1971 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.47399268023274604, |
| "learning_rate": 2.48171791854519e-05, |
| "loss": 2.4131, |
| "step": 1972 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.4845999467154265, |
| "learning_rate": 2.4586625416433473e-05, |
| "loss": 2.5363, |
| "step": 1973 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.49500461115610306, |
| "learning_rate": 2.435712058661921e-05, |
| "loss": 2.4741, |
| "step": 1974 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.5233151818523865, |
| "learning_rate": 2.4128665202382327e-05, |
| "loss": 2.4008, |
| "step": 1975 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.5452661030265512, |
| "learning_rate": 2.3901259767780515e-05, |
| "loss": 2.5341, |
| "step": 1976 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.4770015990662068, |
| "learning_rate": 2.367490478455514e-05, |
| "loss": 2.4577, |
| "step": 1977 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.48485906537023915, |
| "learning_rate": 2.3449600752129597e-05, |
| "loss": 2.5299, |
| "step": 1978 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.46183679793499416, |
| "learning_rate": 2.3225348167608685e-05, |
| "loss": 2.3936, |
| "step": 1979 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.4821146665559986, |
| "learning_rate": 2.3002147525777118e-05, |
| "loss": 2.55, |
| "step": 1980 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.6164382219986398, |
| "learning_rate": 2.2779999319098856e-05, |
| "loss": 2.56, |
| "step": 1981 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.5026970771701417, |
| "learning_rate": 2.255890403771571e-05, |
| "loss": 2.5092, |
| "step": 1982 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.49910797459413053, |
| "learning_rate": 2.233886216944614e-05, |
| "loss": 2.492, |
| "step": 1983 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.46146701079860186, |
| "learning_rate": 2.211987419978484e-05, |
| "loss": 2.4613, |
| "step": 1984 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.5050686073231441, |
| "learning_rate": 2.1901940611900705e-05, |
| "loss": 2.5237, |
| "step": 1985 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.4914686953950003, |
| "learning_rate": 2.168506188663666e-05, |
| "loss": 2.5052, |
| "step": 1986 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.5303359569493579, |
| "learning_rate": 2.1469238502507925e-05, |
| "loss": 2.4869, |
| "step": 1987 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.4943791525474323, |
| "learning_rate": 2.125447093570154e-05, |
| "loss": 2.4554, |
| "step": 1988 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.5147752218756598, |
| "learning_rate": 2.1040759660074793e-05, |
| "loss": 2.4473, |
| "step": 1989 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.5072610010721472, |
| "learning_rate": 2.0828105147154273e-05, |
| "loss": 2.4531, |
| "step": 1990 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.5199398745289093, |
| "learning_rate": 2.061650786613545e-05, |
| "loss": 2.5437, |
| "step": 1991 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.4930133335930063, |
| "learning_rate": 2.040596828388058e-05, |
| "loss": 2.4675, |
| "step": 1992 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.532490746334357, |
| "learning_rate": 2.019648686491865e-05, |
| "loss": 2.4218, |
| "step": 1993 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.7370255592023508, |
| "learning_rate": 1.9988064071443767e-05, |
| "loss": 2.5113, |
| "step": 1994 |
| }, |
| { |
| "epoch": 0.91, |
| "grad_norm": 0.5436379564350523, |
| "learning_rate": 1.9780700363314253e-05, |
| "loss": 2.3584, |
| "step": 1995 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.48132282221703765, |
| "learning_rate": 1.957439619805196e-05, |
| "loss": 2.4921, |
| "step": 1996 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.4708231175800447, |
| "learning_rate": 1.9369152030840554e-05, |
| "loss": 2.5432, |
| "step": 1997 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.5563782794384785, |
| "learning_rate": 1.916496831452552e-05, |
| "loss": 2.4359, |
| "step": 1998 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.5114882131568582, |
| "learning_rate": 1.8961845499611998e-05, |
| "loss": 2.5905, |
| "step": 1999 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.4880752304981728, |
| "learning_rate": 1.8759784034264925e-05, |
| "loss": 2.4887, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.5323161523470346, |
| "learning_rate": 1.855878436430708e-05, |
| "loss": 2.5326, |
| "step": 2001 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.47157170127883696, |
| "learning_rate": 1.835884693321871e-05, |
| "loss": 2.4134, |
| "step": 2002 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.49114966690345, |
| "learning_rate": 1.8159972182136386e-05, |
| "loss": 2.4905, |
| "step": 2003 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.491082134886774, |
| "learning_rate": 1.7962160549851945e-05, |
| "loss": 2.4529, |
| "step": 2004 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.4801357114114866, |
| "learning_rate": 1.776541247281177e-05, |
| "loss": 2.4727, |
| "step": 2005 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.509095342145642, |
| "learning_rate": 1.7569728385115224e-05, |
| "loss": 2.5574, |
| "step": 2006 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.5097171842549065, |
| "learning_rate": 1.7375108718514665e-05, |
| "loss": 2.4573, |
| "step": 2007 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.4823075465357155, |
| "learning_rate": 1.7181553902413438e-05, |
| "loss": 2.4303, |
| "step": 2008 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.6546860948679964, |
| "learning_rate": 1.698906436386577e-05, |
| "loss": 2.4546, |
| "step": 2009 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.4917037950901913, |
| "learning_rate": 1.679764052757532e-05, |
| "loss": 2.5625, |
| "step": 2010 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.49994100973774624, |
| "learning_rate": 1.6607282815894464e-05, |
| "loss": 2.3691, |
| "step": 2011 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.4990241322206325, |
| "learning_rate": 1.6417991648823405e-05, |
| "loss": 2.5469, |
| "step": 2012 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.4932168738774991, |
| "learning_rate": 1.6229767444008835e-05, |
| "loss": 2.4302, |
| "step": 2013 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.4875518396329534, |
| "learning_rate": 1.604261061674378e-05, |
| "loss": 2.5478, |
| "step": 2014 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.6454126710120985, |
| "learning_rate": 1.5856521579965865e-05, |
| "loss": 2.6175, |
| "step": 2015 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.5055937238181455, |
| "learning_rate": 1.5671500744256938e-05, |
| "loss": 2.5034, |
| "step": 2016 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.47635889166794393, |
| "learning_rate": 1.5487548517841953e-05, |
| "loss": 2.476, |
| "step": 2017 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.5336045625755271, |
| "learning_rate": 1.530466530658814e-05, |
| "loss": 2.5308, |
| "step": 2018 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.5172939929617569, |
| "learning_rate": 1.5122851514004054e-05, |
| "loss": 2.3614, |
| "step": 2019 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4757758823010626, |
| "learning_rate": 1.4942107541238703e-05, |
| "loss": 2.3322, |
| "step": 2020 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4804067393706192, |
| "learning_rate": 1.4762433787080809e-05, |
| "loss": 2.5821, |
| "step": 2021 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4754063035149768, |
| "learning_rate": 1.4583830647957541e-05, |
| "loss": 2.4715, |
| "step": 2022 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.5000014537188122, |
| "learning_rate": 1.4406298517934068e-05, |
| "loss": 2.463, |
| "step": 2023 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.5075333980084101, |
| "learning_rate": 1.4229837788712562e-05, |
| "loss": 2.3814, |
| "step": 2024 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4904552147185035, |
| "learning_rate": 1.4054448849631085e-05, |
| "loss": 2.4512, |
| "step": 2025 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4792345242704972, |
| "learning_rate": 1.3880132087663145e-05, |
| "loss": 2.4654, |
| "step": 2026 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.5134879241802485, |
| "learning_rate": 1.3706887887416419e-05, |
| "loss": 2.484, |
| "step": 2027 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4954283810262002, |
| "learning_rate": 1.3534716631132316e-05, |
| "loss": 2.461, |
| "step": 2028 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.5014956633593537, |
| "learning_rate": 1.3363618698684853e-05, |
| "loss": 2.5204, |
| "step": 2029 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4969925563821702, |
| "learning_rate": 1.3193594467579728e-05, |
| "loss": 2.5149, |
| "step": 2030 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4911311492079942, |
| "learning_rate": 1.3024644312954026e-05, |
| "loss": 2.4795, |
| "step": 2031 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.5084963675840046, |
| "learning_rate": 1.2856768607574564e-05, |
| "loss": 2.4777, |
| "step": 2032 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.5096912965984526, |
| "learning_rate": 1.2689967721837947e-05, |
| "loss": 2.3458, |
| "step": 2033 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.5049546047447335, |
| "learning_rate": 1.2524242023769006e-05, |
| "loss": 2.588, |
| "step": 2034 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.45721813721371607, |
| "learning_rate": 1.2359591879020526e-05, |
| "loss": 2.4826, |
| "step": 2035 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4728103270635401, |
| "learning_rate": 1.2196017650872081e-05, |
| "loss": 2.3964, |
| "step": 2036 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4907367104114579, |
| "learning_rate": 1.2033519700229367e-05, |
| "loss": 2.438, |
| "step": 2037 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4879408004082002, |
| "learning_rate": 1.1872098385623586e-05, |
| "loss": 2.5577, |
| "step": 2038 |
| }, |
| { |
| "epoch": 0.93, |
| "grad_norm": 0.4910732040281035, |
| "learning_rate": 1.1711754063210289e-05, |
| "loss": 2.4018, |
| "step": 2039 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.47648301419418737, |
| "learning_rate": 1.155248708676887e-05, |
| "loss": 2.5155, |
| "step": 2040 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4928258043640432, |
| "learning_rate": 1.1394297807701737e-05, |
| "loss": 2.4796, |
| "step": 2041 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 1.005372186007324, |
| "learning_rate": 1.1237186575033254e-05, |
| "loss": 2.4706, |
| "step": 2042 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4949588915559148, |
| "learning_rate": 1.1081153735409522e-05, |
| "loss": 2.5309, |
| "step": 2043 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4753699725302466, |
| "learning_rate": 1.0926199633097156e-05, |
| "loss": 2.4801, |
| "step": 2044 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.5048022388447162, |
| "learning_rate": 1.0772324609982787e-05, |
| "loss": 2.411, |
| "step": 2045 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4927953732607588, |
| "learning_rate": 1.0619529005571893e-05, |
| "loss": 2.4746, |
| "step": 2046 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.5077009782481647, |
| "learning_rate": 1.0467813156988748e-05, |
| "loss": 2.4294, |
| "step": 2047 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4847765932078565, |
| "learning_rate": 1.0317177398975031e-05, |
| "loss": 2.4751, |
| "step": 2048 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.527379999993964, |
| "learning_rate": 1.0167622063889326e-05, |
| "loss": 2.4698, |
| "step": 2049 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4729862220438588, |
| "learning_rate": 1.0019147481706625e-05, |
| "loss": 2.4782, |
| "step": 2050 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.48009827926623366, |
| "learning_rate": 9.871753980017051e-06, |
| "loss": 2.5649, |
| "step": 2051 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.47838933785777, |
| "learning_rate": 9.725441884025855e-06, |
| "loss": 2.3869, |
| "step": 2052 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4746947976568592, |
| "learning_rate": 9.580211516551862e-06, |
| "loss": 2.4709, |
| "step": 2053 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4712898014812378, |
| "learning_rate": 9.436063198027589e-06, |
| "loss": 2.4506, |
| "step": 2054 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4623473852765303, |
| "learning_rate": 9.292997246497959e-06, |
| "loss": 2.5209, |
| "step": 2055 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4776475573453676, |
| "learning_rate": 9.151013977619693e-06, |
| "loss": 2.4915, |
| "step": 2056 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.5074122405791872, |
| "learning_rate": 9.010113704661038e-06, |
| "loss": 2.4626, |
| "step": 2057 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4670897745966293, |
| "learning_rate": 8.870296738500316e-06, |
| "loss": 2.4971, |
| "step": 2058 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.5143094590541853, |
| "learning_rate": 8.731563387626095e-06, |
| "loss": 2.4525, |
| "step": 2059 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.5011476310034546, |
| "learning_rate": 8.59391395813569e-06, |
| "loss": 2.4572, |
| "step": 2060 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.4741412436593503, |
| "learning_rate": 8.457348753735328e-06, |
| "loss": 2.5132, |
| "step": 2061 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.5704137368161645, |
| "learning_rate": 8.321868075738593e-06, |
| "loss": 2.4595, |
| "step": 2062 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.49766703644202903, |
| "learning_rate": 8.187472223066371e-06, |
| "loss": 2.4716, |
| "step": 2063 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.5133284223945, |
| "learning_rate": 8.054161492246136e-06, |
| "loss": 2.3944, |
| "step": 2064 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.49823063226729314, |
| "learning_rate": 7.921936177411049e-06, |
| "loss": 2.4098, |
| "step": 2065 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.49444181077158084, |
| "learning_rate": 7.790796570299463e-06, |
| "loss": 2.4163, |
| "step": 2066 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.5091361745533021, |
| "learning_rate": 7.660742960254207e-06, |
| "loss": 2.4534, |
| "step": 2067 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.4900621391583813, |
| "learning_rate": 7.531775634222138e-06, |
| "loss": 2.4829, |
| "step": 2068 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.47268213651558, |
| "learning_rate": 7.403894876753192e-06, |
| "loss": 2.4371, |
| "step": 2069 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.4885451211929637, |
| "learning_rate": 7.277100970000061e-06, |
| "loss": 2.5524, |
| "step": 2070 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.500851390095697, |
| "learning_rate": 7.151394193717408e-06, |
| "loss": 2.5406, |
| "step": 2071 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.4915888483775141, |
| "learning_rate": 7.026774825261151e-06, |
| "loss": 2.4252, |
| "step": 2072 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.5259123027157919, |
| "learning_rate": 6.903243139588233e-06, |
| "loss": 2.5472, |
| "step": 2073 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.5442062453428818, |
| "learning_rate": 6.780799409255522e-06, |
| "loss": 2.518, |
| "step": 2074 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.47628913720135474, |
| "learning_rate": 6.659443904419637e-06, |
| "loss": 2.406, |
| "step": 2075 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.4916574721105695, |
| "learning_rate": 6.539176892836008e-06, |
| "loss": 2.4239, |
| "step": 2076 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.575247528272575, |
| "learning_rate": 6.4199986398585375e-06, |
| "loss": 2.3819, |
| "step": 2077 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.48732906262419134, |
| "learning_rate": 6.3019094084388884e-06, |
| "loss": 2.4649, |
| "step": 2078 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.4788177932463562, |
| "learning_rate": 6.18490945912592e-06, |
| "loss": 2.5012, |
| "step": 2079 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.48597524261246655, |
| "learning_rate": 6.068999050065249e-06, |
| "loss": 2.4729, |
| "step": 2080 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.500767041864634, |
| "learning_rate": 5.9541784369983586e-06, |
| "loss": 2.5646, |
| "step": 2081 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.5025836087103193, |
| "learning_rate": 5.840447873262433e-06, |
| "loss": 2.5491, |
| "step": 2082 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.46771767381121415, |
| "learning_rate": 5.727807609789471e-06, |
| "loss": 2.4522, |
| "step": 2083 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4983920031723868, |
| "learning_rate": 5.616257895105892e-06, |
| "loss": 2.3517, |
| "step": 2084 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4705762303657622, |
| "learning_rate": 5.505798975331933e-06, |
| "loss": 2.4275, |
| "step": 2085 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4669622390562371, |
| "learning_rate": 5.396431094181198e-06, |
| "loss": 2.5087, |
| "step": 2086 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4789481605851321, |
| "learning_rate": 5.288154492960107e-06, |
| "loss": 2.4055, |
| "step": 2087 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4785364862160196, |
| "learning_rate": 5.1809694105671155e-06, |
| "loss": 2.49, |
| "step": 2088 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.49818257370203706, |
| "learning_rate": 5.074876083492441e-06, |
| "loss": 2.5684, |
| "step": 2089 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4797587929027699, |
| "learning_rate": 4.96987474581767e-06, |
| "loss": 2.4203, |
| "step": 2090 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4971341554142611, |
| "learning_rate": 4.865965629214819e-06, |
| "loss": 2.5878, |
| "step": 2091 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.571295429097993, |
| "learning_rate": 4.763148962946218e-06, |
| "loss": 2.4079, |
| "step": 2092 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4919726241613823, |
| "learning_rate": 4.661424973863681e-06, |
| "loss": 2.4963, |
| "step": 2093 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.49525327946542247, |
| "learning_rate": 4.560793886408398e-06, |
| "loss": 2.4571, |
| "step": 2094 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4724948388596101, |
| "learning_rate": 4.461255922609986e-06, |
| "loss": 2.4277, |
| "step": 2095 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.5364031955977825, |
| "learning_rate": 4.362811302086267e-06, |
| "loss": 2.5375, |
| "step": 2096 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.5109930657736065, |
| "learning_rate": 4.265460242042885e-06, |
| "loss": 2.4633, |
| "step": 2097 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.5131264700282294, |
| "learning_rate": 4.169202957272522e-06, |
| "loss": 2.501, |
| "step": 2098 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4893304034262606, |
| "learning_rate": 4.074039660154738e-06, |
| "loss": 2.4512, |
| "step": 2099 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.45774046632092485, |
| "learning_rate": 3.9799705606551325e-06, |
| "loss": 2.456, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4921167226050657, |
| "learning_rate": 3.886995866325294e-06, |
| "loss": 2.472, |
| "step": 2101 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.4821257148422846, |
| "learning_rate": 3.795115782302072e-06, |
| "loss": 2.4768, |
| "step": 2102 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.5022196465234987, |
| "learning_rate": 3.704330511307197e-06, |
| "loss": 2.436, |
| "step": 2103 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.49862236577786934, |
| "learning_rate": 3.614640253646828e-06, |
| "loss": 2.5122, |
| "step": 2104 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.5149755362211641, |
| "learning_rate": 3.5260452072110594e-06, |
| "loss": 2.5265, |
| "step": 2105 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.4586148528723697, |
| "learning_rate": 3.4385455674737498e-06, |
| "loss": 2.5292, |
| "step": 2106 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.46829708585739643, |
| "learning_rate": 3.3521415274915256e-06, |
| "loss": 2.3848, |
| "step": 2107 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.47488522403445166, |
| "learning_rate": 3.2668332779041133e-06, |
| "loss": 2.3766, |
| "step": 2108 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.46291186903784415, |
| "learning_rate": 3.1826210069332838e-06, |
| "loss": 2.4884, |
| "step": 2109 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.502417291174347, |
| "learning_rate": 3.0995049003826324e-06, |
| "loss": 2.3689, |
| "step": 2110 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.5018633266435826, |
| "learning_rate": 3.017485141637355e-06, |
| "loss": 2.5394, |
| "step": 2111 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.5147278218606549, |
| "learning_rate": 2.9365619116636376e-06, |
| "loss": 2.4793, |
| "step": 2112 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.4873776740288169, |
| "learning_rate": 2.856735389008269e-06, |
| "loss": 2.4465, |
| "step": 2113 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.49952269152827605, |
| "learning_rate": 2.778005749798307e-06, |
| "loss": 2.4819, |
| "step": 2114 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.4827570120671754, |
| "learning_rate": 2.700373167740744e-06, |
| "loss": 2.4937, |
| "step": 2115 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.4767822759970456, |
| "learning_rate": 2.62383781412201e-06, |
| "loss": 2.4221, |
| "step": 2116 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.49631338354892857, |
| "learning_rate": 2.5483998578076373e-06, |
| "loss": 2.4656, |
| "step": 2117 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.46581095430041736, |
| "learning_rate": 2.4740594652418736e-06, |
| "loss": 2.4223, |
| "step": 2118 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.4954907199652474, |
| "learning_rate": 2.4008168004472917e-06, |
| "loss": 2.4094, |
| "step": 2119 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.5717720855708256, |
| "learning_rate": 2.3286720250246253e-06, |
| "loss": 2.4427, |
| "step": 2120 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.5525858576103646, |
| "learning_rate": 2.2576252981520994e-06, |
| "loss": 2.4902, |
| "step": 2121 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.47730642030564785, |
| "learning_rate": 2.1876767765853233e-06, |
| "loss": 2.5534, |
| "step": 2122 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.4910930506033946, |
| "learning_rate": 2.118826614656788e-06, |
| "loss": 2.4954, |
| "step": 2123 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.5330845879927308, |
| "learning_rate": 2.051074964275701e-06, |
| "loss": 2.4726, |
| "step": 2124 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.4770446077255869, |
| "learning_rate": 1.984421974927375e-06, |
| "loss": 2.455, |
| "step": 2125 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.5120780366766747, |
| "learning_rate": 1.9188677936731734e-06, |
| "loss": 2.5046, |
| "step": 2126 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.46544144962602096, |
| "learning_rate": 1.8544125651501208e-06, |
| "loss": 2.3986, |
| "step": 2127 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.5100749216571794, |
| "learning_rate": 1.7910564315704035e-06, |
| "loss": 2.4108, |
| "step": 2128 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.4748849002992767, |
| "learning_rate": 1.7287995327214257e-06, |
| "loss": 2.3489, |
| "step": 2129 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.49090628804909153, |
| "learning_rate": 1.6676420059649754e-06, |
| "loss": 2.4982, |
| "step": 2130 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.5062990620972769, |
| "learning_rate": 1.6075839862374485e-06, |
| "loss": 2.4923, |
| "step": 2131 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.493134111905619, |
| "learning_rate": 1.5486256060492366e-06, |
| "loss": 2.5911, |
| "step": 2132 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.47959544593017767, |
| "learning_rate": 1.4907669954844495e-06, |
| "loss": 2.5305, |
| "step": 2133 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.7126617688388097, |
| "learning_rate": 1.434008282200805e-06, |
| "loss": 2.545, |
| "step": 2134 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.49912613887323126, |
| "learning_rate": 1.3783495914291844e-06, |
| "loss": 2.5278, |
| "step": 2135 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.5722512021341065, |
| "learning_rate": 1.3237910459734104e-06, |
| "loss": 2.4369, |
| "step": 2136 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.5537452905093762, |
| "learning_rate": 1.270332766210025e-06, |
| "loss": 2.4576, |
| "step": 2137 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.5425966378832828, |
| "learning_rate": 1.2179748700879012e-06, |
| "loss": 2.5897, |
| "step": 2138 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.5419819623731383, |
| "learning_rate": 1.1667174731280205e-06, |
| "loss": 2.4396, |
| "step": 2139 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.4762825247403025, |
| "learning_rate": 1.1165606884234182e-06, |
| "loss": 2.538, |
| "step": 2140 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.527931190161454, |
| "learning_rate": 1.0675046266386268e-06, |
| "loss": 2.4361, |
| "step": 2141 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.4867336619331765, |
| "learning_rate": 1.019549396009567e-06, |
| "loss": 2.3803, |
| "step": 2142 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.4998646959527815, |
| "learning_rate": 9.726951023434348e-07, |
| "loss": 2.3418, |
| "step": 2143 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.5061290908429377, |
| "learning_rate": 9.269418490182591e-07, |
| "loss": 2.5682, |
| "step": 2144 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.4852530326253009, |
| "learning_rate": 8.822897369827332e-07, |
| "loss": 2.4229, |
| "step": 2145 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.5057087484607322, |
| "learning_rate": 8.387388647561611e-07, |
| "loss": 2.443, |
| "step": 2146 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.49348505526957187, |
| "learning_rate": 7.962893284279016e-07, |
| "loss": 2.5218, |
| "step": 2147 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.4770240817922311, |
| "learning_rate": 7.549412216574791e-07, |
| "loss": 2.3741, |
| "step": 2148 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.5132304677833384, |
| "learning_rate": 7.146946356743067e-07, |
| "loss": 2.5666, |
| "step": 2149 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.4790007181959527, |
| "learning_rate": 6.755496592773524e-07, |
| "loss": 2.4661, |
| "step": 2150 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.49836513177022873, |
| "learning_rate": 6.375063788349733e-07, |
| "loss": 2.4423, |
| "step": 2151 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.492811904082209, |
| "learning_rate": 6.005648782848594e-07, |
| "loss": 2.4255, |
| "step": 2152 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.5156433787540523, |
| "learning_rate": 5.647252391337565e-07, |
| "loss": 2.4083, |
| "step": 2153 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.4860523045121307, |
| "learning_rate": 5.299875404572441e-07, |
| "loss": 2.41, |
| "step": 2154 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.5223852012720372, |
| "learning_rate": 4.963518588996796e-07, |
| "loss": 2.5174, |
| "step": 2155 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.5075082446650242, |
| "learning_rate": 4.638182686738657e-07, |
| "loss": 2.4065, |
| "step": 2156 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.4828785565186172, |
| "learning_rate": 4.3238684156110543e-07, |
| "loss": 2.4401, |
| "step": 2157 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.47910176572472657, |
| "learning_rate": 4.020576469108139e-07, |
| "loss": 2.3745, |
| "step": 2158 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.8782221779529013, |
| "learning_rate": 3.7283075164046274e-07, |
| "loss": 2.4932, |
| "step": 2159 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.5023723283229619, |
| "learning_rate": 3.4470622023557995e-07, |
| "loss": 2.5, |
| "step": 2160 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.5310681660621072, |
| "learning_rate": 3.176841147492504e-07, |
| "loss": 2.4444, |
| "step": 2161 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.5058732658534343, |
| "learning_rate": 2.9176449480244895e-07, |
| "loss": 2.5176, |
| "step": 2162 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.48750895657358884, |
| "learning_rate": 2.6694741758342967e-07, |
| "loss": 2.5568, |
| "step": 2163 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.4789460081525747, |
| "learning_rate": 2.432329378478926e-07, |
| "loss": 2.4972, |
| "step": 2164 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.49579177702325705, |
| "learning_rate": 2.2062110791892798e-07, |
| "loss": 2.5511, |
| "step": 2165 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.6183086093820623, |
| "learning_rate": 1.9911197768662792e-07, |
| "loss": 2.3835, |
| "step": 2166 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.5669083042554872, |
| "learning_rate": 1.7870559460814173e-07, |
| "loss": 2.5518, |
| "step": 2167 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.46943474797646356, |
| "learning_rate": 1.5940200370750947e-07, |
| "loss": 2.3666, |
| "step": 2168 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.5029190298044919, |
| "learning_rate": 1.4120124757577291e-07, |
| "loss": 2.5405, |
| "step": 2169 |
| }, |
| { |
| "epoch": 0.99, |
| "grad_norm": 0.48010716603752884, |
| "learning_rate": 1.2410336637047603e-07, |
| "loss": 2.4405, |
| "step": 2170 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5506638813629005, |
| "learning_rate": 1.081083978159425e-07, |
| "loss": 2.5395, |
| "step": 2171 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.543759757146145, |
| "learning_rate": 9.321637720310915e-08, |
| "loss": 2.4721, |
| "step": 2172 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5184851101390616, |
| "learning_rate": 7.942733738924845e-08, |
| "loss": 2.5206, |
| "step": 2173 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.571162890984348, |
| "learning_rate": 6.6741308798135e-08, |
| "loss": 2.4937, |
| "step": 2174 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5149293193161172, |
| "learning_rate": 5.5158319419934546e-08, |
| "loss": 2.5035, |
| "step": 2175 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.47024036796736274, |
| "learning_rate": 4.4678394810981906e-08, |
| "loss": 2.4219, |
| "step": 2176 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5226112930768279, |
| "learning_rate": 3.5301558093947527e-08, |
| "loss": 2.5069, |
| "step": 2177 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.4857705839918862, |
| "learning_rate": 2.7027829957559925e-08, |
| "loss": 2.4189, |
| "step": 2178 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5055955514572312, |
| "learning_rate": 1.985722865682771e-08, |
| "loss": 2.4737, |
| "step": 2179 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5069603934824679, |
| "learning_rate": 1.3789770012762048e-08, |
| "loss": 2.3872, |
| "step": 2180 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.47342048873214454, |
| "learning_rate": 8.825467412376665e-09, |
| "loss": 2.5051, |
| "step": 2181 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 2181, |
| "total_flos": 119999253848064.0, |
| "train_loss": 2.71029020897132, |
| "train_runtime": 2905.1846, |
| "train_samples_per_second": 192.114, |
| "train_steps_per_second": 0.751 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 2181, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 3000, |
| "total_flos": 119999253848064.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
