BB4B-ep2 / trainer_state.json
Fizzarolli's picture
Upload folder using huggingface_hub
d98e84b verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 868,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002304147465437788,
"grad_norm": 0.0,
"learning_rate": 9.998846730480915e-06,
"loss": 3.6297,
"step": 1
},
{
"epoch": 0.004608294930875576,
"grad_norm": 0.0,
"learning_rate": 9.997691064419303e-06,
"loss": 3.7821,
"step": 2
},
{
"epoch": 0.0069124423963133645,
"grad_norm": 0.0,
"learning_rate": 9.996532994337224e-06,
"loss": 3.0545,
"step": 3
},
{
"epoch": 0.009216589861751152,
"grad_norm": 0.0,
"learning_rate": 9.99537251272559e-06,
"loss": 3.3776,
"step": 4
},
{
"epoch": 0.01152073732718894,
"grad_norm": 0.0,
"learning_rate": 9.994209612044008e-06,
"loss": 2.6629,
"step": 5
},
{
"epoch": 0.013824884792626729,
"grad_norm": 0.0,
"learning_rate": 9.993044284720612e-06,
"loss": 2.9764,
"step": 6
},
{
"epoch": 0.016129032258064516,
"grad_norm": 0.0,
"learning_rate": 9.99187652315191e-06,
"loss": 3.0443,
"step": 7
},
{
"epoch": 0.018433179723502304,
"grad_norm": 0.0,
"learning_rate": 9.990706319702603e-06,
"loss": 2.9777,
"step": 8
},
{
"epoch": 0.020737327188940093,
"grad_norm": 0.0,
"learning_rate": 9.989533666705432e-06,
"loss": 2.6634,
"step": 9
},
{
"epoch": 0.02304147465437788,
"grad_norm": 0.0,
"learning_rate": 9.988358556461003e-06,
"loss": 2.5688,
"step": 10
},
{
"epoch": 0.02534562211981567,
"grad_norm": 0.0,
"learning_rate": 9.98718098123762e-06,
"loss": 2.7999,
"step": 11
},
{
"epoch": 0.027649769585253458,
"grad_norm": 0.0,
"learning_rate": 9.986000933271115e-06,
"loss": 2.8395,
"step": 12
},
{
"epoch": 0.029953917050691243,
"grad_norm": 0.0,
"learning_rate": 9.984818404764686e-06,
"loss": 2.9181,
"step": 13
},
{
"epoch": 0.03225806451612903,
"grad_norm": 0.0,
"learning_rate": 9.983633387888708e-06,
"loss": 2.3633,
"step": 14
},
{
"epoch": 0.03456221198156682,
"grad_norm": 0.0,
"learning_rate": 9.982445874780575e-06,
"loss": 2.6805,
"step": 15
},
{
"epoch": 0.03686635944700461,
"grad_norm": 0.0,
"learning_rate": 9.981255857544517e-06,
"loss": 3.2891,
"step": 16
},
{
"epoch": 0.03917050691244239,
"grad_norm": 0.0,
"learning_rate": 9.980063328251437e-06,
"loss": 2.3438,
"step": 17
},
{
"epoch": 0.041474654377880185,
"grad_norm": 0.0,
"learning_rate": 9.97886827893872e-06,
"loss": 3.0867,
"step": 18
},
{
"epoch": 0.04377880184331797,
"grad_norm": 0.0,
"learning_rate": 9.97767070161006e-06,
"loss": 3.0397,
"step": 19
},
{
"epoch": 0.04608294930875576,
"grad_norm": 0.0,
"learning_rate": 9.976470588235294e-06,
"loss": 2.675,
"step": 20
},
{
"epoch": 0.04838709677419355,
"grad_norm": 0.0,
"learning_rate": 9.975267930750206e-06,
"loss": 2.588,
"step": 21
},
{
"epoch": 0.05069124423963134,
"grad_norm": 0.0,
"learning_rate": 9.974062721056355e-06,
"loss": 2.5917,
"step": 22
},
{
"epoch": 0.052995391705069124,
"grad_norm": 0.0,
"learning_rate": 9.97285495102089e-06,
"loss": 2.6421,
"step": 23
},
{
"epoch": 0.055299539170506916,
"grad_norm": 0.0,
"learning_rate": 9.971644612476371e-06,
"loss": 2.8325,
"step": 24
},
{
"epoch": 0.0576036866359447,
"grad_norm": 0.0,
"learning_rate": 9.970431697220581e-06,
"loss": 2.7928,
"step": 25
},
{
"epoch": 0.059907834101382486,
"grad_norm": 0.0,
"learning_rate": 9.96921619701634e-06,
"loss": 2.7043,
"step": 26
},
{
"epoch": 0.06221198156682028,
"grad_norm": 0.0,
"learning_rate": 9.967998103591326e-06,
"loss": 2.5606,
"step": 27
},
{
"epoch": 0.06451612903225806,
"grad_norm": 0.0,
"learning_rate": 9.966777408637875e-06,
"loss": 2.5944,
"step": 28
},
{
"epoch": 0.06682027649769585,
"grad_norm": 0.0,
"learning_rate": 9.965554103812804e-06,
"loss": 2.0101,
"step": 29
},
{
"epoch": 0.06912442396313365,
"grad_norm": 0.0,
"learning_rate": 9.964328180737219e-06,
"loss": 2.669,
"step": 30
},
{
"epoch": 0.07142857142857142,
"grad_norm": 0.0,
"learning_rate": 9.963099630996312e-06,
"loss": 2.5637,
"step": 31
},
{
"epoch": 0.07373271889400922,
"grad_norm": 0.0,
"learning_rate": 9.961868446139181e-06,
"loss": 2.8749,
"step": 32
},
{
"epoch": 0.07603686635944701,
"grad_norm": 0.0,
"learning_rate": 9.960634617678637e-06,
"loss": 2.8018,
"step": 33
},
{
"epoch": 0.07834101382488479,
"grad_norm": 0.0,
"learning_rate": 9.959398137090996e-06,
"loss": 2.5725,
"step": 34
},
{
"epoch": 0.08064516129032258,
"grad_norm": 0.0,
"learning_rate": 9.958158995815901e-06,
"loss": 2.8989,
"step": 35
},
{
"epoch": 0.08294930875576037,
"grad_norm": 0.0,
"learning_rate": 9.956917185256105e-06,
"loss": 2.4909,
"step": 36
},
{
"epoch": 0.08525345622119816,
"grad_norm": 0.0,
"learning_rate": 9.955672696777287e-06,
"loss": 2.5061,
"step": 37
},
{
"epoch": 0.08755760368663594,
"grad_norm": 0.0,
"learning_rate": 9.954425521707844e-06,
"loss": 2.3851,
"step": 38
},
{
"epoch": 0.08986175115207373,
"grad_norm": 0.0,
"learning_rate": 9.953175651338697e-06,
"loss": 3.0129,
"step": 39
},
{
"epoch": 0.09216589861751152,
"grad_norm": 0.0,
"learning_rate": 9.951923076923079e-06,
"loss": 2.8212,
"step": 40
},
{
"epoch": 0.0944700460829493,
"grad_norm": 0.0,
"learning_rate": 9.950667789676334e-06,
"loss": 2.952,
"step": 41
},
{
"epoch": 0.0967741935483871,
"grad_norm": 0.0,
"learning_rate": 9.949409780775717e-06,
"loss": 2.2857,
"step": 42
},
{
"epoch": 0.09907834101382489,
"grad_norm": 0.0,
"learning_rate": 9.948149041360185e-06,
"loss": 2.2268,
"step": 43
},
{
"epoch": 0.10138248847926268,
"grad_norm": 0.0,
"learning_rate": 9.94688556253018e-06,
"loss": 2.7615,
"step": 44
},
{
"epoch": 0.10368663594470046,
"grad_norm": 0.0,
"learning_rate": 9.945619335347432e-06,
"loss": 3.1013,
"step": 45
},
{
"epoch": 0.10599078341013825,
"grad_norm": 0.0,
"learning_rate": 9.944350350834746e-06,
"loss": 3.0616,
"step": 46
},
{
"epoch": 0.10829493087557604,
"grad_norm": 0.0,
"learning_rate": 9.943078599975779e-06,
"loss": 2.2084,
"step": 47
},
{
"epoch": 0.11059907834101383,
"grad_norm": 0.0,
"learning_rate": 9.941804073714841e-06,
"loss": 2.1988,
"step": 48
},
{
"epoch": 0.11290322580645161,
"grad_norm": 0.0,
"learning_rate": 9.94052676295667e-06,
"loss": 2.5741,
"step": 49
},
{
"epoch": 0.1152073732718894,
"grad_norm": 0.0,
"learning_rate": 9.939246658566223e-06,
"loss": 2.4302,
"step": 50
},
{
"epoch": 0.1175115207373272,
"grad_norm": 0.0,
"learning_rate": 9.937963751368447e-06,
"loss": 2.5109,
"step": 51
},
{
"epoch": 0.11981566820276497,
"grad_norm": 0.0,
"learning_rate": 9.936678032148077e-06,
"loss": 2.2233,
"step": 52
},
{
"epoch": 0.12211981566820276,
"grad_norm": 0.0,
"learning_rate": 9.935389491649398e-06,
"loss": 3.1745,
"step": 53
},
{
"epoch": 0.12442396313364056,
"grad_norm": 0.0,
"learning_rate": 9.934098120576033e-06,
"loss": 2.6837,
"step": 54
},
{
"epoch": 0.12672811059907835,
"grad_norm": 0.0,
"learning_rate": 9.932803909590715e-06,
"loss": 2.5496,
"step": 55
},
{
"epoch": 0.12903225806451613,
"grad_norm": 0.0,
"learning_rate": 9.931506849315069e-06,
"loss": 2.6769,
"step": 56
},
{
"epoch": 0.1313364055299539,
"grad_norm": 0.0,
"learning_rate": 9.930206930329376e-06,
"loss": 2.4358,
"step": 57
},
{
"epoch": 0.1336405529953917,
"grad_norm": 0.0,
"learning_rate": 9.928904143172348e-06,
"loss": 2.6133,
"step": 58
},
{
"epoch": 0.1359447004608295,
"grad_norm": 0.0,
"learning_rate": 9.927598478340902e-06,
"loss": 2.6126,
"step": 59
},
{
"epoch": 0.1382488479262673,
"grad_norm": 0.0,
"learning_rate": 9.926289926289927e-06,
"loss": 2.3671,
"step": 60
},
{
"epoch": 0.14055299539170507,
"grad_norm": 0.0,
"learning_rate": 9.92497847743205e-06,
"loss": 2.3528,
"step": 61
},
{
"epoch": 0.14285714285714285,
"grad_norm": 0.0,
"learning_rate": 9.923664122137405e-06,
"loss": 2.894,
"step": 62
},
{
"epoch": 0.14516129032258066,
"grad_norm": 0.0,
"learning_rate": 9.922346850733393e-06,
"loss": 2.944,
"step": 63
},
{
"epoch": 0.14746543778801843,
"grad_norm": 0.0,
"learning_rate": 9.921026653504443e-06,
"loss": 2.495,
"step": 64
},
{
"epoch": 0.1497695852534562,
"grad_norm": 0.0,
"learning_rate": 9.919703520691786e-06,
"loss": 2.2919,
"step": 65
},
{
"epoch": 0.15207373271889402,
"grad_norm": 0.0,
"learning_rate": 9.918377442493198e-06,
"loss": 2.6164,
"step": 66
},
{
"epoch": 0.1543778801843318,
"grad_norm": 0.0,
"learning_rate": 9.917048409062771e-06,
"loss": 2.5487,
"step": 67
},
{
"epoch": 0.15668202764976957,
"grad_norm": 0.0,
"learning_rate": 9.91571641051066e-06,
"loss": 2.6602,
"step": 68
},
{
"epoch": 0.15898617511520738,
"grad_norm": 0.0,
"learning_rate": 9.914381436902843e-06,
"loss": 2.5056,
"step": 69
},
{
"epoch": 0.16129032258064516,
"grad_norm": 0.0,
"learning_rate": 9.913043478260871e-06,
"loss": 2.8503,
"step": 70
},
{
"epoch": 0.16359447004608296,
"grad_norm": 0.0,
"learning_rate": 9.911702524561623e-06,
"loss": 2.6178,
"step": 71
},
{
"epoch": 0.16589861751152074,
"grad_norm": 0.0,
"learning_rate": 9.910358565737052e-06,
"loss": 2.7173,
"step": 72
},
{
"epoch": 0.16820276497695852,
"grad_norm": 0.0,
"learning_rate": 9.909011591673938e-06,
"loss": 2.4166,
"step": 73
},
{
"epoch": 0.17050691244239632,
"grad_norm": 0.0,
"learning_rate": 9.907661592213627e-06,
"loss": 2.5658,
"step": 74
},
{
"epoch": 0.1728110599078341,
"grad_norm": 0.0,
"learning_rate": 9.906308557151781e-06,
"loss": 2.3656,
"step": 75
},
{
"epoch": 0.17511520737327188,
"grad_norm": 0.0,
"learning_rate": 9.90495247623812e-06,
"loss": 2.4611,
"step": 76
},
{
"epoch": 0.1774193548387097,
"grad_norm": 0.0,
"learning_rate": 9.903593339176162e-06,
"loss": 2.2937,
"step": 77
},
{
"epoch": 0.17972350230414746,
"grad_norm": 0.0,
"learning_rate": 9.902231135622965e-06,
"loss": 2.172,
"step": 78
},
{
"epoch": 0.18202764976958524,
"grad_norm": 0.0,
"learning_rate": 9.900865855188858e-06,
"loss": 2.4489,
"step": 79
},
{
"epoch": 0.18433179723502305,
"grad_norm": 0.0,
"learning_rate": 9.899497487437187e-06,
"loss": 2.7153,
"step": 80
},
{
"epoch": 0.18663594470046083,
"grad_norm": 0.0,
"learning_rate": 9.89812602188404e-06,
"loss": 2.7078,
"step": 81
},
{
"epoch": 0.1889400921658986,
"grad_norm": 0.0,
"learning_rate": 9.896751447997987e-06,
"loss": 2.1448,
"step": 82
},
{
"epoch": 0.1912442396313364,
"grad_norm": 0.0,
"learning_rate": 9.8953737551998e-06,
"loss": 2.4494,
"step": 83
},
{
"epoch": 0.1935483870967742,
"grad_norm": 0.0,
"learning_rate": 9.893992932862191e-06,
"loss": 2.5461,
"step": 84
},
{
"epoch": 0.195852534562212,
"grad_norm": 0.0,
"learning_rate": 9.89260897030954e-06,
"loss": 2.219,
"step": 85
},
{
"epoch": 0.19815668202764977,
"grad_norm": 0.0,
"learning_rate": 9.891221856817608e-06,
"loss": 2.6866,
"step": 86
},
{
"epoch": 0.20046082949308755,
"grad_norm": 0.0,
"learning_rate": 9.889831581613272e-06,
"loss": 2.2086,
"step": 87
},
{
"epoch": 0.20276497695852536,
"grad_norm": 0.0,
"learning_rate": 9.88843813387424e-06,
"loss": 2.658,
"step": 88
},
{
"epoch": 0.20506912442396313,
"grad_norm": 0.0,
"learning_rate": 9.887041502728773e-06,
"loss": 2.2961,
"step": 89
},
{
"epoch": 0.2073732718894009,
"grad_norm": 0.0,
"learning_rate": 9.885641677255401e-06,
"loss": 2.5561,
"step": 90
},
{
"epoch": 0.20967741935483872,
"grad_norm": 0.0,
"learning_rate": 9.884238646482637e-06,
"loss": 2.5409,
"step": 91
},
{
"epoch": 0.2119815668202765,
"grad_norm": 0.0,
"learning_rate": 9.882832399388692e-06,
"loss": 2.2584,
"step": 92
},
{
"epoch": 0.21428571428571427,
"grad_norm": 0.0,
"learning_rate": 9.881422924901188e-06,
"loss": 2.5798,
"step": 93
},
{
"epoch": 0.21658986175115208,
"grad_norm": 0.0,
"learning_rate": 9.88001021189686e-06,
"loss": 2.6547,
"step": 94
},
{
"epoch": 0.21889400921658986,
"grad_norm": 0.0,
"learning_rate": 9.878594249201278e-06,
"loss": 1.9719,
"step": 95
},
{
"epoch": 0.22119815668202766,
"grad_norm": 0.0,
"learning_rate": 9.877175025588538e-06,
"loss": 2.6163,
"step": 96
},
{
"epoch": 0.22350230414746544,
"grad_norm": 0.0,
"learning_rate": 9.875752529780967e-06,
"loss": 2.5005,
"step": 97
},
{
"epoch": 0.22580645161290322,
"grad_norm": 0.0,
"learning_rate": 9.874326750448835e-06,
"loss": 2.4969,
"step": 98
},
{
"epoch": 0.22811059907834103,
"grad_norm": 0.0,
"learning_rate": 9.872897676210041e-06,
"loss": 2.4532,
"step": 99
},
{
"epoch": 0.2304147465437788,
"grad_norm": 0.0,
"learning_rate": 9.871465295629821e-06,
"loss": 2.7851,
"step": 100
},
{
"epoch": 0.23271889400921658,
"grad_norm": 0.0,
"learning_rate": 9.870029597220437e-06,
"loss": 2.4056,
"step": 101
},
{
"epoch": 0.2350230414746544,
"grad_norm": 0.0,
"learning_rate": 9.868590569440867e-06,
"loss": 2.4184,
"step": 102
},
{
"epoch": 0.23732718894009217,
"grad_norm": 0.0,
"learning_rate": 9.867148200696505e-06,
"loss": 2.4005,
"step": 103
},
{
"epoch": 0.23963133640552994,
"grad_norm": 0.0,
"learning_rate": 9.865702479338843e-06,
"loss": 2.3063,
"step": 104
},
{
"epoch": 0.24193548387096775,
"grad_norm": 0.0,
"learning_rate": 9.86425339366516e-06,
"loss": 2.309,
"step": 105
},
{
"epoch": 0.24423963133640553,
"grad_norm": 0.0,
"learning_rate": 9.8628009319182e-06,
"loss": 2.2872,
"step": 106
},
{
"epoch": 0.2465437788018433,
"grad_norm": 0.0,
"learning_rate": 9.861345082285862e-06,
"loss": 2.5453,
"step": 107
},
{
"epoch": 0.2488479262672811,
"grad_norm": 0.0,
"learning_rate": 9.859885832900883e-06,
"loss": 2.4237,
"step": 108
},
{
"epoch": 0.2511520737327189,
"grad_norm": 0.0,
"learning_rate": 9.8584231718405e-06,
"loss": 2.7325,
"step": 109
},
{
"epoch": 0.2534562211981567,
"grad_norm": 0.0,
"learning_rate": 9.856957087126139e-06,
"loss": 2.8046,
"step": 110
},
{
"epoch": 0.2557603686635945,
"grad_norm": 0.0,
"learning_rate": 9.855487566723084e-06,
"loss": 2.3187,
"step": 111
},
{
"epoch": 0.25806451612903225,
"grad_norm": 0.0,
"learning_rate": 9.854014598540148e-06,
"loss": 2.1758,
"step": 112
},
{
"epoch": 0.26036866359447003,
"grad_norm": 0.0,
"learning_rate": 9.852538170429336e-06,
"loss": 2.3946,
"step": 113
},
{
"epoch": 0.2626728110599078,
"grad_norm": 0.0,
"learning_rate": 9.851058270185526e-06,
"loss": 2.5586,
"step": 114
},
{
"epoch": 0.26497695852534564,
"grad_norm": 0.0,
"learning_rate": 9.849574885546111e-06,
"loss": 2.4507,
"step": 115
},
{
"epoch": 0.2672811059907834,
"grad_norm": 0.0,
"learning_rate": 9.848088004190675e-06,
"loss": 2.2848,
"step": 116
},
{
"epoch": 0.2695852534562212,
"grad_norm": 0.0,
"learning_rate": 9.846597613740658e-06,
"loss": 2.7136,
"step": 117
},
{
"epoch": 0.271889400921659,
"grad_norm": 0.0,
"learning_rate": 9.845103701758992e-06,
"loss": 2.2407,
"step": 118
},
{
"epoch": 0.27419354838709675,
"grad_norm": 0.0,
"learning_rate": 9.843606255749772e-06,
"loss": 1.8917,
"step": 119
},
{
"epoch": 0.2764976958525346,
"grad_norm": 0.0,
"learning_rate": 9.842105263157896e-06,
"loss": 2.49,
"step": 120
},
{
"epoch": 0.27880184331797236,
"grad_norm": 0.0,
"learning_rate": 9.840600711368727e-06,
"loss": 2.2081,
"step": 121
},
{
"epoch": 0.28110599078341014,
"grad_norm": 0.0,
"learning_rate": 9.839092587707729e-06,
"loss": 2.5349,
"step": 122
},
{
"epoch": 0.2834101382488479,
"grad_norm": 0.0,
"learning_rate": 9.837580879440117e-06,
"loss": 2.2057,
"step": 123
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.0,
"learning_rate": 9.836065573770494e-06,
"loss": 2.6525,
"step": 124
},
{
"epoch": 0.2880184331797235,
"grad_norm": 0.0,
"learning_rate": 9.834546657842488e-06,
"loss": 2.466,
"step": 125
},
{
"epoch": 0.2903225806451613,
"grad_norm": 0.0,
"learning_rate": 9.833024118738406e-06,
"loss": 2.3602,
"step": 126
},
{
"epoch": 0.2926267281105991,
"grad_norm": 0.0,
"learning_rate": 9.831497943478838e-06,
"loss": 1.9779,
"step": 127
},
{
"epoch": 0.29493087557603687,
"grad_norm": 0.0,
"learning_rate": 9.829968119022318e-06,
"loss": 2.0746,
"step": 128
},
{
"epoch": 0.29723502304147464,
"grad_norm": 0.0,
"learning_rate": 9.82843463226493e-06,
"loss": 2.5047,
"step": 129
},
{
"epoch": 0.2995391705069124,
"grad_norm": 0.0,
"learning_rate": 9.826897470039947e-06,
"loss": 2.3455,
"step": 130
},
{
"epoch": 0.30184331797235026,
"grad_norm": 0.0,
"learning_rate": 9.825356619117452e-06,
"loss": 2.7969,
"step": 131
},
{
"epoch": 0.30414746543778803,
"grad_norm": 0.0,
"learning_rate": 9.823812066203951e-06,
"loss": 2.1092,
"step": 132
},
{
"epoch": 0.3064516129032258,
"grad_norm": 0.0,
"learning_rate": 9.822263797942004e-06,
"loss": 2.454,
"step": 133
},
{
"epoch": 0.3087557603686636,
"grad_norm": 0.0,
"learning_rate": 9.82071180090982e-06,
"loss": 2.2478,
"step": 134
},
{
"epoch": 0.31105990783410137,
"grad_norm": 0.0,
"learning_rate": 9.819156061620899e-06,
"loss": 2.1831,
"step": 135
},
{
"epoch": 0.31336405529953915,
"grad_norm": 0.0,
"learning_rate": 9.817596566523606e-06,
"loss": 2.199,
"step": 136
},
{
"epoch": 0.315668202764977,
"grad_norm": 0.0,
"learning_rate": 9.816033302000808e-06,
"loss": 2.3337,
"step": 137
},
{
"epoch": 0.31797235023041476,
"grad_norm": 0.0,
"learning_rate": 9.814466254369455e-06,
"loss": 2.3119,
"step": 138
},
{
"epoch": 0.32027649769585254,
"grad_norm": 0.0,
"learning_rate": 9.8128954098802e-06,
"loss": 2.319,
"step": 139
},
{
"epoch": 0.3225806451612903,
"grad_norm": 0.0,
"learning_rate": 9.811320754716981e-06,
"loss": 2.37,
"step": 140
},
{
"epoch": 0.3248847926267281,
"grad_norm": 0.0,
"learning_rate": 9.809742274996628e-06,
"loss": 2.3041,
"step": 141
},
{
"epoch": 0.3271889400921659,
"grad_norm": 0.0,
"learning_rate": 9.808159956768442e-06,
"loss": 2.7213,
"step": 142
},
{
"epoch": 0.3294930875576037,
"grad_norm": 0.0,
"learning_rate": 9.806573786013798e-06,
"loss": 2.6252,
"step": 143
},
{
"epoch": 0.3317972350230415,
"grad_norm": 0.0,
"learning_rate": 9.80498374864572e-06,
"loss": 1.8312,
"step": 144
},
{
"epoch": 0.33410138248847926,
"grad_norm": 0.0,
"learning_rate": 9.803389830508476e-06,
"loss": 2.4053,
"step": 145
},
{
"epoch": 0.33640552995391704,
"grad_norm": 0.0,
"learning_rate": 9.80179201737714e-06,
"loss": 2.3841,
"step": 146
},
{
"epoch": 0.3387096774193548,
"grad_norm": 0.0,
"learning_rate": 9.800190294957183e-06,
"loss": 2.4041,
"step": 147
},
{
"epoch": 0.34101382488479265,
"grad_norm": 0.0,
"learning_rate": 9.79858464888405e-06,
"loss": 2.0689,
"step": 148
},
{
"epoch": 0.3433179723502304,
"grad_norm": 0.0,
"learning_rate": 9.796975064722715e-06,
"loss": 2.0356,
"step": 149
},
{
"epoch": 0.3456221198156682,
"grad_norm": 0.0,
"learning_rate": 9.795361527967258e-06,
"loss": 2.0666,
"step": 150
},
{
"epoch": 0.347926267281106,
"grad_norm": 0.0,
"learning_rate": 9.793744024040433e-06,
"loss": 2.5768,
"step": 151
},
{
"epoch": 0.35023041474654376,
"grad_norm": 0.0,
"learning_rate": 9.792122538293217e-06,
"loss": 2.1563,
"step": 152
},
{
"epoch": 0.35253456221198154,
"grad_norm": 0.0,
"learning_rate": 9.790497056004383e-06,
"loss": 2.3727,
"step": 153
},
{
"epoch": 0.3548387096774194,
"grad_norm": 0.0,
"learning_rate": 9.78886756238004e-06,
"loss": 1.9836,
"step": 154
},
{
"epoch": 0.35714285714285715,
"grad_norm": 0.0,
"learning_rate": 9.787234042553192e-06,
"loss": 2.0014,
"step": 155
},
{
"epoch": 0.35944700460829493,
"grad_norm": 0.0,
"learning_rate": 9.785596481583288e-06,
"loss": 2.128,
"step": 156
},
{
"epoch": 0.3617511520737327,
"grad_norm": 0.0,
"learning_rate": 9.78395486445576e-06,
"loss": 1.9376,
"step": 157
},
{
"epoch": 0.3640552995391705,
"grad_norm": 0.0,
"learning_rate": 9.782309176081566e-06,
"loss": 2.6088,
"step": 158
},
{
"epoch": 0.3663594470046083,
"grad_norm": 0.0,
"learning_rate": 9.780659401296732e-06,
"loss": 2.476,
"step": 159
},
{
"epoch": 0.3686635944700461,
"grad_norm": 0.0,
"learning_rate": 9.779005524861878e-06,
"loss": 2.2163,
"step": 160
},
{
"epoch": 0.3709677419354839,
"grad_norm": 0.0,
"learning_rate": 9.777347531461764e-06,
"loss": 2.6048,
"step": 161
},
{
"epoch": 0.37327188940092165,
"grad_norm": 0.0,
"learning_rate": 9.775685405704793e-06,
"loss": 2.2061,
"step": 162
},
{
"epoch": 0.37557603686635943,
"grad_norm": 0.0,
"learning_rate": 9.774019132122557e-06,
"loss": 2.4101,
"step": 163
},
{
"epoch": 0.3778801843317972,
"grad_norm": 0.0,
"learning_rate": 9.77234869516935e-06,
"loss": 2.5347,
"step": 164
},
{
"epoch": 0.38018433179723504,
"grad_norm": 0.0,
"learning_rate": 9.770674079221682e-06,
"loss": 2.1867,
"step": 165
},
{
"epoch": 0.3824884792626728,
"grad_norm": 0.0,
"learning_rate": 9.768995268577792e-06,
"loss": 2.3605,
"step": 166
},
{
"epoch": 0.3847926267281106,
"grad_norm": 0.0,
"learning_rate": 9.767312247457155e-06,
"loss": 2.1918,
"step": 167
},
{
"epoch": 0.3870967741935484,
"grad_norm": 0.0,
"learning_rate": 9.765625e-06,
"loss": 2.4631,
"step": 168
},
{
"epoch": 0.38940092165898615,
"grad_norm": 0.0,
"learning_rate": 9.763933510266798e-06,
"loss": 2.077,
"step": 169
},
{
"epoch": 0.391705069124424,
"grad_norm": 0.0,
"learning_rate": 9.762237762237764e-06,
"loss": 2.274,
"step": 170
},
{
"epoch": 0.39400921658986177,
"grad_norm": 0.0,
"learning_rate": 9.760537739812353e-06,
"loss": 2.5203,
"step": 171
},
{
"epoch": 0.39631336405529954,
"grad_norm": 0.0,
"learning_rate": 9.75883342680875e-06,
"loss": 2.2468,
"step": 172
},
{
"epoch": 0.3986175115207373,
"grad_norm": 0.0,
"learning_rate": 9.757124806963358e-06,
"loss": 2.2579,
"step": 173
},
{
"epoch": 0.4009216589861751,
"grad_norm": 0.0,
"learning_rate": 9.755411863930279e-06,
"loss": 2.3655,
"step": 174
},
{
"epoch": 0.4032258064516129,
"grad_norm": 0.0,
"learning_rate": 9.75369458128079e-06,
"loss": 2.353,
"step": 175
},
{
"epoch": 0.4055299539170507,
"grad_norm": 0.0,
"learning_rate": 9.75197294250282e-06,
"loss": 2.2856,
"step": 176
},
{
"epoch": 0.4078341013824885,
"grad_norm": 0.0,
"learning_rate": 9.750246931000424e-06,
"loss": 2.2884,
"step": 177
},
{
"epoch": 0.41013824884792627,
"grad_norm": 0.0,
"learning_rate": 9.748516530093248e-06,
"loss": 2.1927,
"step": 178
},
{
"epoch": 0.41244239631336405,
"grad_norm": 0.0,
"learning_rate": 9.746781723015986e-06,
"loss": 2.4978,
"step": 179
},
{
"epoch": 0.4147465437788018,
"grad_norm": 0.0,
"learning_rate": 9.745042492917848e-06,
"loss": 2.1364,
"step": 180
},
{
"epoch": 0.41705069124423966,
"grad_norm": 0.0,
"learning_rate": 9.743298822862007e-06,
"loss": 2.4476,
"step": 181
},
{
"epoch": 0.41935483870967744,
"grad_norm": 0.0,
"learning_rate": 9.74155069582505e-06,
"loss": 1.8542,
"step": 182
},
{
"epoch": 0.4216589861751152,
"grad_norm": 0.0,
"learning_rate": 9.739798094696433e-06,
"loss": 2.2825,
"step": 183
},
{
"epoch": 0.423963133640553,
"grad_norm": 0.0,
"learning_rate": 9.738041002277906e-06,
"loss": 2.504,
"step": 184
},
{
"epoch": 0.42626728110599077,
"grad_norm": 0.0,
"learning_rate": 9.736279401282966e-06,
"loss": 2.1668,
"step": 185
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.0,
"learning_rate": 9.734513274336284e-06,
"loss": 2.2124,
"step": 186
},
{
"epoch": 0.4308755760368664,
"grad_norm": 0.0,
"learning_rate": 9.732742603973132e-06,
"loss": 2.0533,
"step": 187
},
{
"epoch": 0.43317972350230416,
"grad_norm": 0.0,
"learning_rate": 9.73096737263881e-06,
"loss": 2.2371,
"step": 188
},
{
"epoch": 0.43548387096774194,
"grad_norm": 0.0,
"learning_rate": 9.729187562688066e-06,
"loss": 2.577,
"step": 189
},
{
"epoch": 0.4377880184331797,
"grad_norm": 0.0,
"learning_rate": 9.727403156384506e-06,
"loss": 2.0062,
"step": 190
},
{
"epoch": 0.4400921658986175,
"grad_norm": 0.0,
"learning_rate": 9.725614135900015e-06,
"loss": 2.5623,
"step": 191
},
{
"epoch": 0.4423963133640553,
"grad_norm": 0.0,
"learning_rate": 9.723820483314155e-06,
"loss": 2.3879,
"step": 192
},
{
"epoch": 0.4447004608294931,
"grad_norm": 0.0,
"learning_rate": 9.722022180613568e-06,
"loss": 2.3884,
"step": 193
},
{
"epoch": 0.4470046082949309,
"grad_norm": 0.0,
"learning_rate": 9.720219209691377e-06,
"loss": 2.1677,
"step": 194
},
{
"epoch": 0.44930875576036866,
"grad_norm": 0.0,
"learning_rate": 9.71841155234657e-06,
"loss": 2.1849,
"step": 195
},
{
"epoch": 0.45161290322580644,
"grad_norm": 0.0,
"learning_rate": 9.7165991902834e-06,
"loss": 2.4744,
"step": 196
},
{
"epoch": 0.4539170506912442,
"grad_norm": 0.0,
"learning_rate": 9.714782105110758e-06,
"loss": 2.1845,
"step": 197
},
{
"epoch": 0.45622119815668205,
"grad_norm": 0.0,
"learning_rate": 9.71296027834155e-06,
"loss": 2.1075,
"step": 198
},
{
"epoch": 0.45852534562211983,
"grad_norm": 0.0,
"learning_rate": 9.711133691392076e-06,
"loss": 2.2594,
"step": 199
},
{
"epoch": 0.4608294930875576,
"grad_norm": 0.0,
"learning_rate": 9.709302325581395e-06,
"loss": 2.0445,
"step": 200
},
{
"epoch": 0.4631336405529954,
"grad_norm": 0.0,
"learning_rate": 9.707466162130695e-06,
"loss": 1.8306,
"step": 201
},
{
"epoch": 0.46543778801843316,
"grad_norm": 0.0,
"learning_rate": 9.705625182162635e-06,
"loss": 2.0827,
"step": 202
},
{
"epoch": 0.46774193548387094,
"grad_norm": 0.0,
"learning_rate": 9.703779366700715e-06,
"loss": 2.4998,
"step": 203
},
{
"epoch": 0.4700460829493088,
"grad_norm": 0.0,
"learning_rate": 9.701928696668615e-06,
"loss": 1.9692,
"step": 204
},
{
"epoch": 0.47235023041474655,
"grad_norm": 0.0,
"learning_rate": 9.70007315288954e-06,
"loss": 2.2138,
"step": 205
},
{
"epoch": 0.47465437788018433,
"grad_norm": 0.0,
"learning_rate": 9.698212716085556e-06,
"loss": 2.3699,
"step": 206
},
{
"epoch": 0.4769585253456221,
"grad_norm": 0.0,
"learning_rate": 9.696347366876926e-06,
"loss": 2.2658,
"step": 207
},
{
"epoch": 0.4792626728110599,
"grad_norm": 0.0,
"learning_rate": 9.694477085781434e-06,
"loss": 2.3592,
"step": 208
},
{
"epoch": 0.4815668202764977,
"grad_norm": 0.0,
"learning_rate": 9.692601853213708e-06,
"loss": 2.1424,
"step": 209
},
{
"epoch": 0.4838709677419355,
"grad_norm": 0.0,
"learning_rate": 9.690721649484536e-06,
"loss": 2.1127,
"step": 210
},
{
"epoch": 0.4861751152073733,
"grad_norm": 0.0,
"learning_rate": 9.688836454800178e-06,
"loss": 2.39,
"step": 211
},
{
"epoch": 0.48847926267281105,
"grad_norm": 0.0,
"learning_rate": 9.686946249261665e-06,
"loss": 2.2204,
"step": 212
},
{
"epoch": 0.49078341013824883,
"grad_norm": 0.0,
"learning_rate": 9.685051012864114e-06,
"loss": 2.2297,
"step": 213
},
{
"epoch": 0.4930875576036866,
"grad_norm": 0.0,
"learning_rate": 9.683150725496004e-06,
"loss": 2.2213,
"step": 214
},
{
"epoch": 0.49539170506912444,
"grad_norm": 0.0,
"learning_rate": 9.681245366938474e-06,
"loss": 2.3086,
"step": 215
},
{
"epoch": 0.4976958525345622,
"grad_norm": 0.0,
"learning_rate": 9.679334916864607e-06,
"loss": 2.1777,
"step": 216
},
{
"epoch": 0.5,
"grad_norm": 0.0,
"learning_rate": 9.67741935483871e-06,
"loss": 2.2379,
"step": 217
},
{
"epoch": 0.5023041474654378,
"grad_norm": 0.0,
"learning_rate": 9.675498660315571e-06,
"loss": 2.3132,
"step": 218
},
{
"epoch": 0.5046082949308756,
"grad_norm": 0.0,
"learning_rate": 9.673572812639739e-06,
"loss": 2.0896,
"step": 219
},
{
"epoch": 0.5069124423963134,
"grad_norm": 0.0,
"learning_rate": 9.671641791044779e-06,
"loss": 2.1555,
"step": 220
},
{
"epoch": 0.5092165898617511,
"grad_norm": 0.0,
"learning_rate": 9.669705574652519e-06,
"loss": 2.2675,
"step": 221
},
{
"epoch": 0.511520737327189,
"grad_norm": 0.0,
"learning_rate": 9.667764142472315e-06,
"loss": 2.0952,
"step": 222
},
{
"epoch": 0.5138248847926268,
"grad_norm": 0.0,
"learning_rate": 9.665817473400271e-06,
"loss": 2.1719,
"step": 223
},
{
"epoch": 0.5161290322580645,
"grad_norm": 0.0,
"learning_rate": 9.663865546218488e-06,
"loss": 2.269,
"step": 224
},
{
"epoch": 0.5184331797235023,
"grad_norm": 0.0,
"learning_rate": 9.66190833959429e-06,
"loss": 2.3643,
"step": 225
},
{
"epoch": 0.5207373271889401,
"grad_norm": 0.0,
"learning_rate": 9.659945832079446e-06,
"loss": 2.2851,
"step": 226
},
{
"epoch": 0.5230414746543779,
"grad_norm": 0.0,
"learning_rate": 9.657978002109388e-06,
"loss": 2.2314,
"step": 227
},
{
"epoch": 0.5253456221198156,
"grad_norm": 0.0,
"learning_rate": 9.656004828002415e-06,
"loss": 2.306,
"step": 228
},
{
"epoch": 0.5276497695852534,
"grad_norm": 0.0,
"learning_rate": 9.654026287958907e-06,
"loss": 2.72,
"step": 229
},
{
"epoch": 0.5299539170506913,
"grad_norm": 0.0,
"learning_rate": 9.652042360060516e-06,
"loss": 2.2472,
"step": 230
},
{
"epoch": 0.532258064516129,
"grad_norm": 0.0,
"learning_rate": 9.650053022269354e-06,
"loss": 2.14,
"step": 231
},
{
"epoch": 0.5345622119815668,
"grad_norm": 0.0,
"learning_rate": 9.648058252427186e-06,
"loss": 2.1352,
"step": 232
},
{
"epoch": 0.5368663594470046,
"grad_norm": 0.0,
"learning_rate": 9.646058028254597e-06,
"loss": 2.1396,
"step": 233
},
{
"epoch": 0.5391705069124424,
"grad_norm": 0.0,
"learning_rate": 9.644052327350167e-06,
"loss": 2.0091,
"step": 234
},
{
"epoch": 0.5414746543778802,
"grad_norm": 0.0,
"learning_rate": 9.642041127189643e-06,
"loss": 2.3559,
"step": 235
},
{
"epoch": 0.543778801843318,
"grad_norm": 0.0,
"learning_rate": 9.640024405125077e-06,
"loss": 2.2764,
"step": 236
},
{
"epoch": 0.5460829493087558,
"grad_norm": 0.0,
"learning_rate": 9.638002138383995e-06,
"loss": 2.4431,
"step": 237
},
{
"epoch": 0.5483870967741935,
"grad_norm": 0.0,
"learning_rate": 9.635974304068522e-06,
"loss": 2.2692,
"step": 238
},
{
"epoch": 0.5506912442396313,
"grad_norm": 0.0,
"learning_rate": 9.633940879154541e-06,
"loss": 2.2558,
"step": 239
},
{
"epoch": 0.5529953917050692,
"grad_norm": 0.0,
"learning_rate": 9.631901840490798e-06,
"loss": 1.8841,
"step": 240
},
{
"epoch": 0.5552995391705069,
"grad_norm": 0.0,
"learning_rate": 9.629857164798035e-06,
"loss": 2.243,
"step": 241
},
{
"epoch": 0.5576036866359447,
"grad_norm": 0.0,
"learning_rate": 9.627806828668103e-06,
"loss": 2.7055,
"step": 242
},
{
"epoch": 0.5599078341013825,
"grad_norm": 0.0,
"learning_rate": 9.625750808563067e-06,
"loss": 2.0709,
"step": 243
},
{
"epoch": 0.5622119815668203,
"grad_norm": 0.0,
"learning_rate": 9.623689080814313e-06,
"loss": 2.2729,
"step": 244
},
{
"epoch": 0.5645161290322581,
"grad_norm": 0.0,
"learning_rate": 9.621621621621622e-06,
"loss": 2.1815,
"step": 245
},
{
"epoch": 0.5668202764976958,
"grad_norm": 0.0,
"learning_rate": 9.619548407052275e-06,
"loss": 2.3074,
"step": 246
},
{
"epoch": 0.5691244239631337,
"grad_norm": 0.0,
"learning_rate": 9.617469413040112e-06,
"loss": 2.2204,
"step": 247
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.0,
"learning_rate": 9.615384615384616e-06,
"loss": 2.2254,
"step": 248
},
{
"epoch": 0.5737327188940092,
"grad_norm": 0.0,
"learning_rate": 9.613293989749963e-06,
"loss": 2.2028,
"step": 249
},
{
"epoch": 0.576036866359447,
"grad_norm": 0.0,
"learning_rate": 9.611197511664076e-06,
"loss": 1.9041,
"step": 250
},
{
"epoch": 0.5783410138248848,
"grad_norm": 0.0,
"learning_rate": 9.609095156517678e-06,
"loss": 2.1567,
"step": 251
},
{
"epoch": 0.5806451612903226,
"grad_norm": 0.0,
"learning_rate": 9.60698689956332e-06,
"loss": 2.2442,
"step": 252
},
{
"epoch": 0.5829493087557603,
"grad_norm": 0.0,
"learning_rate": 9.604872715914416e-06,
"loss": 2.244,
"step": 253
},
{
"epoch": 0.5852534562211982,
"grad_norm": 0.0,
"learning_rate": 9.602752580544262e-06,
"loss": 2.3902,
"step": 254
},
{
"epoch": 0.5875576036866359,
"grad_norm": 0.0,
"learning_rate": 9.600626468285045e-06,
"loss": 2.3403,
"step": 255
},
{
"epoch": 0.5898617511520737,
"grad_norm": 0.0,
"learning_rate": 9.598494353826851e-06,
"loss": 2.3575,
"step": 256
},
{
"epoch": 0.5921658986175116,
"grad_norm": 0.0,
"learning_rate": 9.596356211716666e-06,
"loss": 2.3505,
"step": 257
},
{
"epoch": 0.5944700460829493,
"grad_norm": 0.0,
"learning_rate": 9.594212016357346e-06,
"loss": 2.1773,
"step": 258
},
{
"epoch": 0.5967741935483871,
"grad_norm": 0.0,
"learning_rate": 9.592061742006616e-06,
"loss": 2.296,
"step": 259
},
{
"epoch": 0.5990783410138248,
"grad_norm": 0.0,
"learning_rate": 9.589905362776025e-06,
"loss": 1.9344,
"step": 260
},
{
"epoch": 0.6013824884792627,
"grad_norm": 0.0,
"learning_rate": 9.587742852629917e-06,
"loss": 2.5543,
"step": 261
},
{
"epoch": 0.6036866359447005,
"grad_norm": 0.0,
"learning_rate": 9.585574185384373e-06,
"loss": 2.7177,
"step": 262
},
{
"epoch": 0.6059907834101382,
"grad_norm": 0.0,
"learning_rate": 9.583399334706163e-06,
"loss": 2.3868,
"step": 263
},
{
"epoch": 0.6082949308755761,
"grad_norm": 0.0,
"learning_rate": 9.581218274111676e-06,
"loss": 2.3185,
"step": 264
},
{
"epoch": 0.6105990783410138,
"grad_norm": 0.0,
"learning_rate": 9.579030976965846e-06,
"loss": 1.9385,
"step": 265
},
{
"epoch": 0.6129032258064516,
"grad_norm": 0.0,
"learning_rate": 9.57683741648107e-06,
"loss": 2.3687,
"step": 266
},
{
"epoch": 0.6152073732718893,
"grad_norm": 0.0,
"learning_rate": 9.574637565716107e-06,
"loss": 2.2045,
"step": 267
},
{
"epoch": 0.6175115207373272,
"grad_norm": 0.0,
"learning_rate": 9.572431397574987e-06,
"loss": 2.4644,
"step": 268
},
{
"epoch": 0.619815668202765,
"grad_norm": 0.0,
"learning_rate": 9.57021888480588e-06,
"loss": 2.3897,
"step": 269
},
{
"epoch": 0.6221198156682027,
"grad_norm": 0.0,
"learning_rate": 9.568e-06,
"loss": 2.4176,
"step": 270
},
{
"epoch": 0.6244239631336406,
"grad_norm": 0.0,
"learning_rate": 9.56577471559045e-06,
"loss": 2.3342,
"step": 271
},
{
"epoch": 0.6267281105990783,
"grad_norm": 0.0,
"learning_rate": 9.563543003851093e-06,
"loss": 2.3815,
"step": 272
},
{
"epoch": 0.6290322580645161,
"grad_norm": 0.0,
"learning_rate": 9.561304836895388e-06,
"loss": 2.435,
"step": 273
},
{
"epoch": 0.631336405529954,
"grad_norm": 0.0,
"learning_rate": 9.55906018667525e-06,
"loss": 2.4491,
"step": 274
},
{
"epoch": 0.6336405529953917,
"grad_norm": 0.0,
"learning_rate": 9.556809024979856e-06,
"loss": 2.3206,
"step": 275
},
{
"epoch": 0.6359447004608295,
"grad_norm": 0.0,
"learning_rate": 9.554551323434475e-06,
"loss": 2.1149,
"step": 276
},
{
"epoch": 0.6382488479262672,
"grad_norm": 0.0,
"learning_rate": 9.552287053499273e-06,
"loss": 2.2707,
"step": 277
},
{
"epoch": 0.6405529953917051,
"grad_norm": 0.0,
"learning_rate": 9.550016186468114e-06,
"loss": 2.3246,
"step": 278
},
{
"epoch": 0.6428571428571429,
"grad_norm": 0.0,
"learning_rate": 9.547738693467338e-06,
"loss": 2.2557,
"step": 279
},
{
"epoch": 0.6451612903225806,
"grad_norm": 0.0,
"learning_rate": 9.545454545454547e-06,
"loss": 2.3648,
"step": 280
},
{
"epoch": 0.6474654377880185,
"grad_norm": 0.0,
"learning_rate": 9.543163713217365e-06,
"loss": 2.3793,
"step": 281
},
{
"epoch": 0.6497695852534562,
"grad_norm": 0.0,
"learning_rate": 9.540866167372192e-06,
"loss": 2.2765,
"step": 282
},
{
"epoch": 0.652073732718894,
"grad_norm": 0.0,
"learning_rate": 9.538561878362955e-06,
"loss": 2.3297,
"step": 283
},
{
"epoch": 0.6543778801843319,
"grad_norm": 0.0,
"learning_rate": 9.53625081645983e-06,
"loss": 2.2636,
"step": 284
},
{
"epoch": 0.6566820276497696,
"grad_norm": 0.0,
"learning_rate": 9.533932951757974e-06,
"loss": 2.271,
"step": 285
},
{
"epoch": 0.6589861751152074,
"grad_norm": 0.0,
"learning_rate": 9.53160825417622e-06,
"loss": 2.497,
"step": 286
},
{
"epoch": 0.6612903225806451,
"grad_norm": 0.0,
"learning_rate": 9.529276693455799e-06,
"loss": 1.994,
"step": 287
},
{
"epoch": 0.663594470046083,
"grad_norm": 0.0,
"learning_rate": 9.526938239159003e-06,
"loss": 1.9041,
"step": 288
},
{
"epoch": 0.6658986175115207,
"grad_norm": 0.0,
"learning_rate": 9.524592860667874e-06,
"loss": 2.3384,
"step": 289
},
{
"epoch": 0.6682027649769585,
"grad_norm": 0.0,
"learning_rate": 9.522240527182867e-06,
"loss": 2.0346,
"step": 290
},
{
"epoch": 0.6705069124423964,
"grad_norm": 0.0,
"learning_rate": 9.519881207721498e-06,
"loss": 2.1251,
"step": 291
},
{
"epoch": 0.6728110599078341,
"grad_norm": 0.0,
"learning_rate": 9.517514871116987e-06,
"loss": 2.3156,
"step": 292
},
{
"epoch": 0.6751152073732719,
"grad_norm": 0.0,
"learning_rate": 9.51514148601688e-06,
"loss": 2.3411,
"step": 293
},
{
"epoch": 0.6774193548387096,
"grad_norm": 0.0,
"learning_rate": 9.512761020881673e-06,
"loss": 2.5454,
"step": 294
},
{
"epoch": 0.6797235023041475,
"grad_norm": 0.0,
"learning_rate": 9.510373443983403e-06,
"loss": 1.864,
"step": 295
},
{
"epoch": 0.6820276497695853,
"grad_norm": 0.0,
"learning_rate": 9.507978723404256e-06,
"loss": 2.2479,
"step": 296
},
{
"epoch": 0.684331797235023,
"grad_norm": 0.0,
"learning_rate": 9.505576827035126e-06,
"loss": 2.2826,
"step": 297
},
{
"epoch": 0.6866359447004609,
"grad_norm": 0.0,
"learning_rate": 9.503167722574192e-06,
"loss": 1.8908,
"step": 298
},
{
"epoch": 0.6889400921658986,
"grad_norm": 0.0,
"learning_rate": 9.500751377525463e-06,
"loss": 2.0887,
"step": 299
},
{
"epoch": 0.6912442396313364,
"grad_norm": 0.0,
"learning_rate": 9.498327759197325e-06,
"loss": 1.9868,
"step": 300
},
{
"epoch": 0.6935483870967742,
"grad_norm": 0.0,
"learning_rate": 9.495896834701056e-06,
"loss": 2.03,
"step": 301
},
{
"epoch": 0.695852534562212,
"grad_norm": 0.0,
"learning_rate": 9.493458570949348e-06,
"loss": 2.413,
"step": 302
},
{
"epoch": 0.6981566820276498,
"grad_norm": 0.0,
"learning_rate": 9.491012934654798e-06,
"loss": 2.2828,
"step": 303
},
{
"epoch": 0.7004608294930875,
"grad_norm": 0.0,
"learning_rate": 9.488559892328399e-06,
"loss": 2.4673,
"step": 304
},
{
"epoch": 0.7027649769585254,
"grad_norm": 0.0,
"learning_rate": 9.486099410278012e-06,
"loss": 2.1999,
"step": 305
},
{
"epoch": 0.7050691244239631,
"grad_norm": 0.0,
"learning_rate": 9.483631454606818e-06,
"loss": 2.1067,
"step": 306
},
{
"epoch": 0.7073732718894009,
"grad_norm": 0.0,
"learning_rate": 9.481155991211765e-06,
"loss": 2.0962,
"step": 307
},
{
"epoch": 0.7096774193548387,
"grad_norm": 0.0,
"learning_rate": 9.47867298578199e-06,
"loss": 2.4821,
"step": 308
},
{
"epoch": 0.7119815668202765,
"grad_norm": 0.0,
"learning_rate": 9.476182403797255e-06,
"loss": 2.4688,
"step": 309
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.0,
"learning_rate": 9.473684210526317e-06,
"loss": 2.1085,
"step": 310
},
{
"epoch": 0.716589861751152,
"grad_norm": 0.0,
"learning_rate": 9.471178371025337e-06,
"loss": 2.435,
"step": 311
},
{
"epoch": 0.7188940092165899,
"grad_norm": 0.0,
"learning_rate": 9.46866485013624e-06,
"loss": 2.3131,
"step": 312
},
{
"epoch": 0.7211981566820277,
"grad_norm": 0.0,
"learning_rate": 9.466143612485077e-06,
"loss": 2.5537,
"step": 313
},
{
"epoch": 0.7235023041474654,
"grad_norm": 0.0,
"learning_rate": 9.463614622480356e-06,
"loss": 2.1758,
"step": 314
},
{
"epoch": 0.7258064516129032,
"grad_norm": 0.0,
"learning_rate": 9.461077844311378e-06,
"loss": 2.2752,
"step": 315
},
{
"epoch": 0.728110599078341,
"grad_norm": 0.0,
"learning_rate": 9.45853324194654e-06,
"loss": 2.0488,
"step": 316
},
{
"epoch": 0.7304147465437788,
"grad_norm": 0.0,
"learning_rate": 9.45598077913163e-06,
"loss": 2.3105,
"step": 317
},
{
"epoch": 0.7327188940092166,
"grad_norm": 0.0,
"learning_rate": 9.453420419388106e-06,
"loss": 1.936,
"step": 318
},
{
"epoch": 0.7350230414746544,
"grad_norm": 0.0,
"learning_rate": 9.450852126011364e-06,
"loss": 2.1634,
"step": 319
},
{
"epoch": 0.7373271889400922,
"grad_norm": 0.0,
"learning_rate": 9.448275862068967e-06,
"loss": 1.9953,
"step": 320
},
{
"epoch": 0.7396313364055299,
"grad_norm": 0.0,
"learning_rate": 9.445691590398895e-06,
"loss": 2.3994,
"step": 321
},
{
"epoch": 0.7419354838709677,
"grad_norm": 0.0,
"learning_rate": 9.44309927360775e-06,
"loss": 1.837,
"step": 322
},
{
"epoch": 0.7442396313364056,
"grad_norm": 0.0,
"learning_rate": 9.440498874068943e-06,
"loss": 2.0258,
"step": 323
},
{
"epoch": 0.7465437788018433,
"grad_norm": 0.0,
"learning_rate": 9.43789035392089e-06,
"loss": 2.5129,
"step": 324
},
{
"epoch": 0.7488479262672811,
"grad_norm": 0.0,
"learning_rate": 9.435273675065161e-06,
"loss": 2.0436,
"step": 325
},
{
"epoch": 0.7511520737327189,
"grad_norm": 0.0,
"learning_rate": 9.432648799164637e-06,
"loss": 2.4449,
"step": 326
},
{
"epoch": 0.7534562211981567,
"grad_norm": 0.0,
"learning_rate": 9.430015687641625e-06,
"loss": 2.0828,
"step": 327
},
{
"epoch": 0.7557603686635944,
"grad_norm": 0.0,
"learning_rate": 9.42737430167598e-06,
"loss": 2.3661,
"step": 328
},
{
"epoch": 0.7580645161290323,
"grad_norm": 0.0,
"learning_rate": 9.424724602203184e-06,
"loss": 1.9816,
"step": 329
},
{
"epoch": 0.7603686635944701,
"grad_norm": 0.0,
"learning_rate": 9.422066549912434e-06,
"loss": 2.3207,
"step": 330
},
{
"epoch": 0.7626728110599078,
"grad_norm": 0.0,
"learning_rate": 9.419400105244694e-06,
"loss": 2.1479,
"step": 331
},
{
"epoch": 0.7649769585253456,
"grad_norm": 0.0,
"learning_rate": 9.416725228390726e-06,
"loss": 2.211,
"step": 332
},
{
"epoch": 0.7672811059907834,
"grad_norm": 0.0,
"learning_rate": 9.41404187928911e-06,
"loss": 1.8804,
"step": 333
},
{
"epoch": 0.7695852534562212,
"grad_norm": 0.0,
"learning_rate": 9.411350017624251e-06,
"loss": 2.1775,
"step": 334
},
{
"epoch": 0.771889400921659,
"grad_norm": 0.0,
"learning_rate": 9.40864960282436e-06,
"loss": 2.2466,
"step": 335
},
{
"epoch": 0.7741935483870968,
"grad_norm": 0.0,
"learning_rate": 9.405940594059407e-06,
"loss": 2.0984,
"step": 336
},
{
"epoch": 0.7764976958525346,
"grad_norm": 0.0,
"learning_rate": 9.403222950239065e-06,
"loss": 2.5951,
"step": 337
},
{
"epoch": 0.7788018433179723,
"grad_norm": 0.0,
"learning_rate": 9.400496630010643e-06,
"loss": 2.1321,
"step": 338
},
{
"epoch": 0.7811059907834101,
"grad_norm": 0.0,
"learning_rate": 9.397761591756973e-06,
"loss": 1.8965,
"step": 339
},
{
"epoch": 0.783410138248848,
"grad_norm": 0.0,
"learning_rate": 9.395017793594307e-06,
"loss": 2.4059,
"step": 340
},
{
"epoch": 0.7857142857142857,
"grad_norm": 0.0,
"learning_rate": 9.392265193370167e-06,
"loss": 2.4522,
"step": 341
},
{
"epoch": 0.7880184331797235,
"grad_norm": 0.0,
"learning_rate": 9.389503748661194e-06,
"loss": 2.4031,
"step": 342
},
{
"epoch": 0.7903225806451613,
"grad_norm": 0.0,
"learning_rate": 9.386733416770964e-06,
"loss": 2.3547,
"step": 343
},
{
"epoch": 0.7926267281105991,
"grad_norm": 0.0,
"learning_rate": 9.383954154727794e-06,
"loss": 2.0233,
"step": 344
},
{
"epoch": 0.7949308755760369,
"grad_norm": 0.0,
"learning_rate": 9.381165919282512e-06,
"loss": 2.3673,
"step": 345
},
{
"epoch": 0.7972350230414746,
"grad_norm": 0.0,
"learning_rate": 9.378368666906218e-06,
"loss": 2.4832,
"step": 346
},
{
"epoch": 0.7995391705069125,
"grad_norm": 0.0,
"learning_rate": 9.375562353788017e-06,
"loss": 2.0684,
"step": 347
},
{
"epoch": 0.8018433179723502,
"grad_norm": 0.0,
"learning_rate": 9.372746935832732e-06,
"loss": 2.1924,
"step": 348
},
{
"epoch": 0.804147465437788,
"grad_norm": 0.0,
"learning_rate": 9.369922368658603e-06,
"loss": 2.3609,
"step": 349
},
{
"epoch": 0.8064516129032258,
"grad_norm": 0.0,
"learning_rate": 9.367088607594939e-06,
"loss": 2.2614,
"step": 350
},
{
"epoch": 0.8087557603686636,
"grad_norm": 0.0,
"learning_rate": 9.364245607679769e-06,
"loss": 2.5841,
"step": 351
},
{
"epoch": 0.8110599078341014,
"grad_norm": 0.0,
"learning_rate": 9.361393323657475e-06,
"loss": 2.038,
"step": 352
},
{
"epoch": 0.8133640552995391,
"grad_norm": 0.0,
"learning_rate": 9.358531709976377e-06,
"loss": 2.2917,
"step": 353
},
{
"epoch": 0.815668202764977,
"grad_norm": 0.0,
"learning_rate": 9.355660720786313e-06,
"loss": 2.0844,
"step": 354
},
{
"epoch": 0.8179723502304147,
"grad_norm": 0.0,
"learning_rate": 9.352780309936191e-06,
"loss": 1.7098,
"step": 355
},
{
"epoch": 0.8202764976958525,
"grad_norm": 0.0,
"learning_rate": 9.349890430971511e-06,
"loss": 2.4264,
"step": 356
},
{
"epoch": 0.8225806451612904,
"grad_norm": 0.0,
"learning_rate": 9.346991037131882e-06,
"loss": 2.4563,
"step": 357
},
{
"epoch": 0.8248847926267281,
"grad_norm": 0.0,
"learning_rate": 9.34408208134848e-06,
"loss": 1.9052,
"step": 358
},
{
"epoch": 0.8271889400921659,
"grad_norm": 0.0,
"learning_rate": 9.341163516241514e-06,
"loss": 2.1467,
"step": 359
},
{
"epoch": 0.8294930875576036,
"grad_norm": 0.0,
"learning_rate": 9.338235294117646e-06,
"loss": 2.2446,
"step": 360
},
{
"epoch": 0.8317972350230415,
"grad_norm": 0.0,
"learning_rate": 9.33529736696741e-06,
"loss": 2.1227,
"step": 361
},
{
"epoch": 0.8341013824884793,
"grad_norm": 0.0,
"learning_rate": 9.332349686462561e-06,
"loss": 2.2938,
"step": 362
},
{
"epoch": 0.836405529953917,
"grad_norm": 0.0,
"learning_rate": 9.329392203953447e-06,
"loss": 2.2272,
"step": 363
},
{
"epoch": 0.8387096774193549,
"grad_norm": 0.0,
"learning_rate": 9.326424870466322e-06,
"loss": 1.9074,
"step": 364
},
{
"epoch": 0.8410138248847926,
"grad_norm": 0.0,
"learning_rate": 9.32344763670065e-06,
"loss": 1.7826,
"step": 365
},
{
"epoch": 0.8433179723502304,
"grad_norm": 0.0,
"learning_rate": 9.320460453026365e-06,
"loss": 2.4799,
"step": 366
},
{
"epoch": 0.8456221198156681,
"grad_norm": 0.0,
"learning_rate": 9.317463269481124e-06,
"loss": 1.8732,
"step": 367
},
{
"epoch": 0.847926267281106,
"grad_norm": 0.0,
"learning_rate": 9.314456035767513e-06,
"loss": 2.4681,
"step": 368
},
{
"epoch": 0.8502304147465438,
"grad_norm": 0.0,
"learning_rate": 9.311438701250233e-06,
"loss": 1.7413,
"step": 369
},
{
"epoch": 0.8525345622119815,
"grad_norm": 0.0,
"learning_rate": 9.308411214953271e-06,
"loss": 2.2242,
"step": 370
},
{
"epoch": 0.8548387096774194,
"grad_norm": 0.0,
"learning_rate": 9.305373525557013e-06,
"loss": 2.6895,
"step": 371
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.0,
"learning_rate": 9.30232558139535e-06,
"loss": 1.8005,
"step": 372
},
{
"epoch": 0.8594470046082949,
"grad_norm": 0.0,
"learning_rate": 9.299267330452753e-06,
"loss": 1.9613,
"step": 373
},
{
"epoch": 0.8617511520737328,
"grad_norm": 0.0,
"learning_rate": 9.29619872036131e-06,
"loss": 2.441,
"step": 374
},
{
"epoch": 0.8640552995391705,
"grad_norm": 0.0,
"learning_rate": 9.29311969839774e-06,
"loss": 2.0829,
"step": 375
},
{
"epoch": 0.8663594470046083,
"grad_norm": 0.0,
"learning_rate": 9.290030211480364e-06,
"loss": 2.0612,
"step": 376
},
{
"epoch": 0.868663594470046,
"grad_norm": 0.0,
"learning_rate": 9.286930206166069e-06,
"loss": 2.1892,
"step": 377
},
{
"epoch": 0.8709677419354839,
"grad_norm": 0.0,
"learning_rate": 9.283819628647214e-06,
"loss": 2.562,
"step": 378
},
{
"epoch": 0.8732718894009217,
"grad_norm": 0.0,
"learning_rate": 9.280698424748529e-06,
"loss": 2.2855,
"step": 379
},
{
"epoch": 0.8755760368663594,
"grad_norm": 0.0,
"learning_rate": 9.277566539923955e-06,
"loss": 2.4445,
"step": 380
},
{
"epoch": 0.8778801843317973,
"grad_norm": 0.0,
"learning_rate": 9.274423919253477e-06,
"loss": 2.1253,
"step": 381
},
{
"epoch": 0.880184331797235,
"grad_norm": 0.0,
"learning_rate": 9.271270507439909e-06,
"loss": 2.4146,
"step": 382
},
{
"epoch": 0.8824884792626728,
"grad_norm": 0.0,
"learning_rate": 9.268106248805657e-06,
"loss": 2.4259,
"step": 383
},
{
"epoch": 0.8847926267281107,
"grad_norm": 0.0,
"learning_rate": 9.264931087289435e-06,
"loss": 2.227,
"step": 384
},
{
"epoch": 0.8870967741935484,
"grad_norm": 0.0,
"learning_rate": 9.261744966442955e-06,
"loss": 2.437,
"step": 385
},
{
"epoch": 0.8894009216589862,
"grad_norm": 0.0,
"learning_rate": 9.258547829427584e-06,
"loss": 2.3971,
"step": 386
},
{
"epoch": 0.8917050691244239,
"grad_norm": 0.0,
"learning_rate": 9.255339619010967e-06,
"loss": 2.164,
"step": 387
},
{
"epoch": 0.8940092165898618,
"grad_norm": 0.0,
"learning_rate": 9.252120277563609e-06,
"loss": 2.22,
"step": 388
},
{
"epoch": 0.8963133640552995,
"grad_norm": 0.0,
"learning_rate": 9.248889747055418e-06,
"loss": 2.1684,
"step": 389
},
{
"epoch": 0.8986175115207373,
"grad_norm": 0.0,
"learning_rate": 9.245647969052225e-06,
"loss": 2.0864,
"step": 390
},
{
"epoch": 0.9009216589861752,
"grad_norm": 0.0,
"learning_rate": 9.242394884712266e-06,
"loss": 2.3236,
"step": 391
},
{
"epoch": 0.9032258064516129,
"grad_norm": 0.0,
"learning_rate": 9.23913043478261e-06,
"loss": 2.205,
"step": 392
},
{
"epoch": 0.9055299539170507,
"grad_norm": 0.0,
"learning_rate": 9.235854559595567e-06,
"loss": 1.9739,
"step": 393
},
{
"epoch": 0.9078341013824884,
"grad_norm": 0.0,
"learning_rate": 9.232567199065057e-06,
"loss": 2.1698,
"step": 394
},
{
"epoch": 0.9101382488479263,
"grad_norm": 0.0,
"learning_rate": 9.229268292682927e-06,
"loss": 2.1516,
"step": 395
},
{
"epoch": 0.9124423963133641,
"grad_norm": 0.0,
"learning_rate": 9.225957779515246e-06,
"loss": 1.8965,
"step": 396
},
{
"epoch": 0.9147465437788018,
"grad_norm": 0.0,
"learning_rate": 9.222635598198551e-06,
"loss": 2.0203,
"step": 397
},
{
"epoch": 0.9170506912442397,
"grad_norm": 0.0,
"learning_rate": 9.219301686936056e-06,
"loss": 2.5318,
"step": 398
},
{
"epoch": 0.9193548387096774,
"grad_norm": 0.0,
"learning_rate": 9.21595598349381e-06,
"loss": 2.1496,
"step": 399
},
{
"epoch": 0.9216589861751152,
"grad_norm": 0.0,
"learning_rate": 9.21259842519685e-06,
"loss": 1.8457,
"step": 400
},
{
"epoch": 0.923963133640553,
"grad_norm": 0.0,
"learning_rate": 9.209228948925261e-06,
"loss": 2.0916,
"step": 401
},
{
"epoch": 0.9262672811059908,
"grad_norm": 0.0,
"learning_rate": 9.205847491110234e-06,
"loss": 2.4179,
"step": 402
},
{
"epoch": 0.9285714285714286,
"grad_norm": 0.0,
"learning_rate": 9.202453987730062e-06,
"loss": 1.8332,
"step": 403
},
{
"epoch": 0.9308755760368663,
"grad_norm": 0.0,
"learning_rate": 9.199048374306107e-06,
"loss": 2.5119,
"step": 404
},
{
"epoch": 0.9331797235023042,
"grad_norm": 0.0,
"learning_rate": 9.19563058589871e-06,
"loss": 1.9103,
"step": 405
},
{
"epoch": 0.9354838709677419,
"grad_norm": 0.0,
"learning_rate": 9.192200557103064e-06,
"loss": 2.5436,
"step": 406
},
{
"epoch": 0.9377880184331797,
"grad_norm": 0.0,
"learning_rate": 9.188758222045046e-06,
"loss": 2.1996,
"step": 407
},
{
"epoch": 0.9400921658986175,
"grad_norm": 0.0,
"learning_rate": 9.185303514376996e-06,
"loss": 2.1928,
"step": 408
},
{
"epoch": 0.9423963133640553,
"grad_norm": 0.0,
"learning_rate": 9.181836367273456e-06,
"loss": 2.39,
"step": 409
},
{
"epoch": 0.9447004608294931,
"grad_norm": 0.0,
"learning_rate": 9.178356713426856e-06,
"loss": 1.9289,
"step": 410
},
{
"epoch": 0.9470046082949308,
"grad_norm": 0.0,
"learning_rate": 9.174864485043165e-06,
"loss": 1.6711,
"step": 411
},
{
"epoch": 0.9493087557603687,
"grad_norm": 0.0,
"learning_rate": 9.17135961383749e-06,
"loss": 1.9521,
"step": 412
},
{
"epoch": 0.9516129032258065,
"grad_norm": 0.0,
"learning_rate": 9.16784203102962e-06,
"loss": 2.1426,
"step": 413
},
{
"epoch": 0.9539170506912442,
"grad_norm": 0.0,
"learning_rate": 9.164311667339525e-06,
"loss": 2.3366,
"step": 414
},
{
"epoch": 0.956221198156682,
"grad_norm": 0.0,
"learning_rate": 9.160768452982811e-06,
"loss": 2.5255,
"step": 415
},
{
"epoch": 0.9585253456221198,
"grad_norm": 0.0,
"learning_rate": 9.157212317666126e-06,
"loss": 2.3075,
"step": 416
},
{
"epoch": 0.9608294930875576,
"grad_norm": 0.0,
"learning_rate": 9.153643190582505e-06,
"loss": 2.2583,
"step": 417
},
{
"epoch": 0.9631336405529954,
"grad_norm": 0.0,
"learning_rate": 9.15006100040667e-06,
"loss": 2.0314,
"step": 418
},
{
"epoch": 0.9654377880184332,
"grad_norm": 0.0,
"learning_rate": 9.146465675290284e-06,
"loss": 2.3014,
"step": 419
},
{
"epoch": 0.967741935483871,
"grad_norm": 0.0,
"learning_rate": 9.142857142857142e-06,
"loss": 2.5585,
"step": 420
},
{
"epoch": 0.9700460829493087,
"grad_norm": 0.0,
"learning_rate": 9.139235330198323e-06,
"loss": 2.2314,
"step": 421
},
{
"epoch": 0.9723502304147466,
"grad_norm": 0.0,
"learning_rate": 9.135600163867268e-06,
"loss": 2.3196,
"step": 422
},
{
"epoch": 0.9746543778801844,
"grad_norm": 0.0,
"learning_rate": 9.131951569874822e-06,
"loss": 2.2138,
"step": 423
},
{
"epoch": 0.9769585253456221,
"grad_norm": 0.0,
"learning_rate": 9.128289473684213e-06,
"loss": 2.3115,
"step": 424
},
{
"epoch": 0.9792626728110599,
"grad_norm": 0.0,
"learning_rate": 9.124613800205974e-06,
"loss": 2.3028,
"step": 425
},
{
"epoch": 0.9815668202764977,
"grad_norm": 0.0,
"learning_rate": 9.120924473792819e-06,
"loss": 2.3505,
"step": 426
},
{
"epoch": 0.9838709677419355,
"grad_norm": 0.0,
"learning_rate": 9.117221418234443e-06,
"loss": 2.2614,
"step": 427
},
{
"epoch": 0.9861751152073732,
"grad_norm": 0.0,
"learning_rate": 9.113504556752279e-06,
"loss": 2.0659,
"step": 428
},
{
"epoch": 0.988479262672811,
"grad_norm": 0.0,
"learning_rate": 9.10977381199419e-06,
"loss": 2.0262,
"step": 429
},
{
"epoch": 0.9907834101382489,
"grad_norm": 0.0,
"learning_rate": 9.106029106029106e-06,
"loss": 2.4228,
"step": 430
},
{
"epoch": 0.9930875576036866,
"grad_norm": 0.0,
"learning_rate": 9.102270360341596e-06,
"loss": 1.9768,
"step": 431
},
{
"epoch": 0.9953917050691244,
"grad_norm": 0.0,
"learning_rate": 9.098497495826378e-06,
"loss": 1.817,
"step": 432
},
{
"epoch": 0.9976958525345622,
"grad_norm": 0.0,
"learning_rate": 9.094710432782772e-06,
"loss": 2.1856,
"step": 433
},
{
"epoch": 1.0,
"grad_norm": 0.0,
"learning_rate": 9.090909090909091e-06,
"loss": 2.3401,
"step": 434
},
{
"epoch": 1.0023041474654377,
"grad_norm": 0.0,
"learning_rate": 9.087093389296958e-06,
"loss": 2.5513,
"step": 435
},
{
"epoch": 1.0046082949308757,
"grad_norm": 0.0,
"learning_rate": 9.083263246425568e-06,
"loss": 2.1191,
"step": 436
},
{
"epoch": 1.0069124423963134,
"grad_norm": 0.0,
"learning_rate": 9.079418580155889e-06,
"loss": 2.1874,
"step": 437
},
{
"epoch": 1.0092165898617511,
"grad_norm": 0.0,
"learning_rate": 9.075559307724779e-06,
"loss": 2.2957,
"step": 438
},
{
"epoch": 1.0115207373271888,
"grad_norm": 0.0,
"learning_rate": 9.071685345739058e-06,
"loss": 2.178,
"step": 439
},
{
"epoch": 1.0138248847926268,
"grad_norm": 0.0,
"learning_rate": 9.067796610169493e-06,
"loss": 2.1927,
"step": 440
},
{
"epoch": 1.0161290322580645,
"grad_norm": 0.0,
"learning_rate": 9.063893016344726e-06,
"loss": 2.1682,
"step": 441
},
{
"epoch": 1.0184331797235022,
"grad_norm": 0.0,
"learning_rate": 9.05997447894513e-06,
"loss": 2.2347,
"step": 442
},
{
"epoch": 1.0207373271889402,
"grad_norm": 0.0,
"learning_rate": 9.056040911996592e-06,
"loss": 2.3404,
"step": 443
},
{
"epoch": 1.023041474654378,
"grad_norm": 0.0,
"learning_rate": 9.052092228864219e-06,
"loss": 2.2901,
"step": 444
},
{
"epoch": 1.0253456221198156,
"grad_norm": 0.0,
"learning_rate": 9.04812834224599e-06,
"loss": 1.9081,
"step": 445
},
{
"epoch": 1.0276497695852536,
"grad_norm": 0.0,
"learning_rate": 9.044149164166311e-06,
"loss": 2.0529,
"step": 446
},
{
"epoch": 1.0299539170506913,
"grad_norm": 0.0,
"learning_rate": 9.040154605969508e-06,
"loss": 2.3772,
"step": 447
},
{
"epoch": 1.032258064516129,
"grad_norm": 0.0,
"learning_rate": 9.036144578313254e-06,
"loss": 2.3574,
"step": 448
},
{
"epoch": 1.0345622119815667,
"grad_norm": 0.0,
"learning_rate": 9.032118991161889e-06,
"loss": 2.0081,
"step": 449
},
{
"epoch": 1.0368663594470047,
"grad_norm": 0.0,
"learning_rate": 9.028077753779698e-06,
"loss": 2.0889,
"step": 450
},
{
"epoch": 1.0391705069124424,
"grad_norm": 0.0,
"learning_rate": 9.024020774724086e-06,
"loss": 2.5457,
"step": 451
},
{
"epoch": 1.0414746543778801,
"grad_norm": 0.0,
"learning_rate": 9.019947961838683e-06,
"loss": 1.9219,
"step": 452
},
{
"epoch": 1.043778801843318,
"grad_norm": 0.0,
"learning_rate": 9.01585922224636e-06,
"loss": 2.3704,
"step": 453
},
{
"epoch": 1.0460829493087558,
"grad_norm": 0.0,
"learning_rate": 9.011754462342185e-06,
"loss": 2.1011,
"step": 454
},
{
"epoch": 1.0483870967741935,
"grad_norm": 0.0,
"learning_rate": 9.007633587786259e-06,
"loss": 2.1355,
"step": 455
},
{
"epoch": 1.0506912442396312,
"grad_norm": 0.0,
"learning_rate": 9.003496503496504e-06,
"loss": 2.5515,
"step": 456
},
{
"epoch": 1.0529953917050692,
"grad_norm": 0.0,
"learning_rate": 8.99934311364134e-06,
"loss": 2.3604,
"step": 457
},
{
"epoch": 1.055299539170507,
"grad_norm": 0.0,
"learning_rate": 8.995173321632296e-06,
"loss": 2.2622,
"step": 458
},
{
"epoch": 1.0576036866359446,
"grad_norm": 0.0,
"learning_rate": 8.990987030116509e-06,
"loss": 2.4929,
"step": 459
},
{
"epoch": 1.0599078341013826,
"grad_norm": 0.0,
"learning_rate": 8.986784140969164e-06,
"loss": 2.1313,
"step": 460
},
{
"epoch": 1.0622119815668203,
"grad_norm": 0.0,
"learning_rate": 8.982564555285809e-06,
"loss": 2.2448,
"step": 461
},
{
"epoch": 1.064516129032258,
"grad_norm": 0.0,
"learning_rate": 8.978328173374614e-06,
"loss": 2.1678,
"step": 462
},
{
"epoch": 1.066820276497696,
"grad_norm": 0.0,
"learning_rate": 8.974074894748505e-06,
"loss": 2.3513,
"step": 463
},
{
"epoch": 1.0691244239631337,
"grad_norm": 0.0,
"learning_rate": 8.969804618117229e-06,
"loss": 2.2733,
"step": 464
},
{
"epoch": 1.0714285714285714,
"grad_norm": 0.0,
"learning_rate": 8.96551724137931e-06,
"loss": 2.2442,
"step": 465
},
{
"epoch": 1.0737327188940091,
"grad_norm": 0.0,
"learning_rate": 8.961212661613909e-06,
"loss": 1.8666,
"step": 466
},
{
"epoch": 1.076036866359447,
"grad_norm": 0.0,
"learning_rate": 8.956890775072592e-06,
"loss": 2.0399,
"step": 467
},
{
"epoch": 1.0783410138248848,
"grad_norm": 0.0,
"learning_rate": 8.952551477170994e-06,
"loss": 2.0874,
"step": 468
},
{
"epoch": 1.0806451612903225,
"grad_norm": 0.0,
"learning_rate": 8.948194662480377e-06,
"loss": 2.0166,
"step": 469
},
{
"epoch": 1.0829493087557605,
"grad_norm": 0.0,
"learning_rate": 8.943820224719103e-06,
"loss": 2.1944,
"step": 470
},
{
"epoch": 1.0852534562211982,
"grad_norm": 0.0,
"learning_rate": 8.939428056743977e-06,
"loss": 2.1455,
"step": 471
},
{
"epoch": 1.087557603686636,
"grad_norm": 0.0,
"learning_rate": 8.935018050541517e-06,
"loss": 2.539,
"step": 472
},
{
"epoch": 1.0898617511520738,
"grad_norm": 0.0,
"learning_rate": 8.930590097219082e-06,
"loss": 2.2455,
"step": 473
},
{
"epoch": 1.0921658986175116,
"grad_norm": 0.0,
"learning_rate": 8.926144086995923e-06,
"loss": 2.1535,
"step": 474
},
{
"epoch": 1.0944700460829493,
"grad_norm": 0.0,
"learning_rate": 8.921679909194099e-06,
"loss": 2.2458,
"step": 475
},
{
"epoch": 1.096774193548387,
"grad_norm": 0.0,
"learning_rate": 8.9171974522293e-06,
"loss": 2.1534,
"step": 476
},
{
"epoch": 1.099078341013825,
"grad_norm": 0.0,
"learning_rate": 8.91269660360155e-06,
"loss": 2.2254,
"step": 477
},
{
"epoch": 1.1013824884792627,
"grad_norm": 0.0,
"learning_rate": 8.908177249885793e-06,
"loss": 2.0497,
"step": 478
},
{
"epoch": 1.1036866359447004,
"grad_norm": 0.0,
"learning_rate": 8.903639276722361e-06,
"loss": 2.1932,
"step": 479
},
{
"epoch": 1.1059907834101383,
"grad_norm": 0.0,
"learning_rate": 8.899082568807339e-06,
"loss": 2.2727,
"step": 480
},
{
"epoch": 1.108294930875576,
"grad_norm": 0.0,
"learning_rate": 8.894507009882784e-06,
"loss": 2.0313,
"step": 481
},
{
"epoch": 1.1105990783410138,
"grad_norm": 0.0,
"learning_rate": 8.889912482726854e-06,
"loss": 2.0227,
"step": 482
},
{
"epoch": 1.1129032258064515,
"grad_norm": 0.0,
"learning_rate": 8.88529886914378e-06,
"loss": 2.1115,
"step": 483
},
{
"epoch": 1.1152073732718895,
"grad_norm": 0.0,
"learning_rate": 8.880666049953746e-06,
"loss": 2.3122,
"step": 484
},
{
"epoch": 1.1175115207373272,
"grad_norm": 0.0,
"learning_rate": 8.87601390498262e-06,
"loss": 2.1055,
"step": 485
},
{
"epoch": 1.119815668202765,
"grad_norm": 0.0,
"learning_rate": 8.871342313051557e-06,
"loss": 2.2331,
"step": 486
},
{
"epoch": 1.1221198156682028,
"grad_norm": 0.0,
"learning_rate": 8.86665115196649e-06,
"loss": 2.1796,
"step": 487
},
{
"epoch": 1.1244239631336406,
"grad_norm": 0.0,
"learning_rate": 8.861940298507463e-06,
"loss": 2.304,
"step": 488
},
{
"epoch": 1.1267281105990783,
"grad_norm": 0.0,
"learning_rate": 8.857209628417855e-06,
"loss": 2.354,
"step": 489
},
{
"epoch": 1.129032258064516,
"grad_norm": 0.0,
"learning_rate": 8.852459016393443e-06,
"loss": 2.3015,
"step": 490
},
{
"epoch": 1.131336405529954,
"grad_norm": 0.0,
"learning_rate": 8.847688336071346e-06,
"loss": 2.2448,
"step": 491
},
{
"epoch": 1.1336405529953917,
"grad_norm": 0.0,
"learning_rate": 8.842897460018816e-06,
"loss": 2.3596,
"step": 492
},
{
"epoch": 1.1359447004608294,
"grad_norm": 0.0,
"learning_rate": 8.838086259721895e-06,
"loss": 1.9896,
"step": 493
},
{
"epoch": 1.1382488479262673,
"grad_norm": 0.0,
"learning_rate": 8.833254605573925e-06,
"loss": 2.1158,
"step": 494
},
{
"epoch": 1.140552995391705,
"grad_norm": 0.0,
"learning_rate": 8.828402366863905e-06,
"loss": 2.4531,
"step": 495
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.0,
"learning_rate": 8.823529411764707e-06,
"loss": 2.0021,
"step": 496
},
{
"epoch": 1.1451612903225807,
"grad_norm": 0.0,
"learning_rate": 8.81863560732113e-06,
"loss": 2.1852,
"step": 497
},
{
"epoch": 1.1474654377880185,
"grad_norm": 0.0,
"learning_rate": 8.813720819437828e-06,
"loss": 1.98,
"step": 498
},
{
"epoch": 1.1497695852534562,
"grad_norm": 0.0,
"learning_rate": 8.808784912867032e-06,
"loss": 1.9642,
"step": 499
},
{
"epoch": 1.1520737327188941,
"grad_norm": 0.0,
"learning_rate": 8.803827751196173e-06,
"loss": 2.2951,
"step": 500
},
{
"epoch": 1.1543778801843319,
"grad_norm": 0.0,
"learning_rate": 8.798849196835292e-06,
"loss": 2.087,
"step": 501
},
{
"epoch": 1.1566820276497696,
"grad_norm": 0.0,
"learning_rate": 8.793849111004326e-06,
"loss": 2.2937,
"step": 502
},
{
"epoch": 1.1589861751152073,
"grad_norm": 0.0,
"learning_rate": 8.788827353720203e-06,
"loss": 2.4084,
"step": 503
},
{
"epoch": 1.1612903225806452,
"grad_norm": 0.0,
"learning_rate": 8.783783783783785e-06,
"loss": 2.0154,
"step": 504
},
{
"epoch": 1.163594470046083,
"grad_norm": 0.0,
"learning_rate": 8.778718258766626e-06,
"loss": 2.0608,
"step": 505
},
{
"epoch": 1.1658986175115207,
"grad_norm": 0.0,
"learning_rate": 8.773630634997577e-06,
"loss": 2.0001,
"step": 506
},
{
"epoch": 1.1682027649769586,
"grad_norm": 0.0,
"learning_rate": 8.768520767549187e-06,
"loss": 1.861,
"step": 507
},
{
"epoch": 1.1705069124423964,
"grad_norm": 0.0,
"learning_rate": 8.763388510223954e-06,
"loss": 2.2712,
"step": 508
},
{
"epoch": 1.172811059907834,
"grad_norm": 0.0,
"learning_rate": 8.758233715540376e-06,
"loss": 2.2442,
"step": 509
},
{
"epoch": 1.1751152073732718,
"grad_norm": 0.0,
"learning_rate": 8.753056234718826e-06,
"loss": 1.9768,
"step": 510
},
{
"epoch": 1.1774193548387097,
"grad_norm": 0.0,
"learning_rate": 8.747855917667238e-06,
"loss": 2.2363,
"step": 511
},
{
"epoch": 1.1797235023041475,
"grad_norm": 0.0,
"learning_rate": 8.742632612966601e-06,
"loss": 1.926,
"step": 512
},
{
"epoch": 1.1820276497695852,
"grad_norm": 0.0,
"learning_rate": 8.737386167856265e-06,
"loss": 1.9019,
"step": 513
},
{
"epoch": 1.1843317972350231,
"grad_norm": 0.0,
"learning_rate": 8.732116428219042e-06,
"loss": 1.8069,
"step": 514
},
{
"epoch": 1.1866359447004609,
"grad_norm": 0.0,
"learning_rate": 8.726823238566132e-06,
"loss": 2.3622,
"step": 515
},
{
"epoch": 1.1889400921658986,
"grad_norm": 0.0,
"learning_rate": 8.721506442021803e-06,
"loss": 2.2355,
"step": 516
},
{
"epoch": 1.1912442396313363,
"grad_norm": 0.0,
"learning_rate": 8.716165880307922e-06,
"loss": 1.9082,
"step": 517
},
{
"epoch": 1.1935483870967742,
"grad_norm": 0.0,
"learning_rate": 8.710801393728223e-06,
"loss": 2.0509,
"step": 518
},
{
"epoch": 1.195852534562212,
"grad_norm": 0.0,
"learning_rate": 8.705412821152409e-06,
"loss": 2.2892,
"step": 519
},
{
"epoch": 1.1981566820276497,
"grad_norm": 0.0,
"learning_rate": 8.700000000000001e-06,
"loss": 2.4489,
"step": 520
},
{
"epoch": 1.2004608294930876,
"grad_norm": 0.0,
"learning_rate": 8.694562766224006e-06,
"loss": 2.1379,
"step": 521
},
{
"epoch": 1.2027649769585254,
"grad_norm": 0.0,
"learning_rate": 8.689100954294325e-06,
"loss": 2.3232,
"step": 522
},
{
"epoch": 1.205069124423963,
"grad_norm": 0.0,
"learning_rate": 8.683614397180973e-06,
"loss": 2.2577,
"step": 523
},
{
"epoch": 1.2073732718894008,
"grad_norm": 0.0,
"learning_rate": 8.678102926337033e-06,
"loss": 1.9628,
"step": 524
},
{
"epoch": 1.2096774193548387,
"grad_norm": 0.0,
"learning_rate": 8.672566371681416e-06,
"loss": 2.2783,
"step": 525
},
{
"epoch": 1.2119815668202765,
"grad_norm": 0.0,
"learning_rate": 8.667004561581348e-06,
"loss": 2.0486,
"step": 526
},
{
"epoch": 1.2142857142857142,
"grad_norm": 0.0,
"learning_rate": 8.661417322834646e-06,
"loss": 2.3865,
"step": 527
},
{
"epoch": 1.2165898617511521,
"grad_norm": 0.0,
"learning_rate": 8.655804480651731e-06,
"loss": 2.0669,
"step": 528
},
{
"epoch": 1.2188940092165899,
"grad_norm": 0.0,
"learning_rate": 8.650165858637407e-06,
"loss": 2.321,
"step": 529
},
{
"epoch": 1.2211981566820276,
"grad_norm": 0.0,
"learning_rate": 8.64450127877238e-06,
"loss": 2.2825,
"step": 530
},
{
"epoch": 1.2235023041474655,
"grad_norm": 0.0,
"learning_rate": 8.638810561394516e-06,
"loss": 2.1408,
"step": 531
},
{
"epoch": 1.2258064516129032,
"grad_norm": 0.0,
"learning_rate": 8.633093525179856e-06,
"loss": 2.0595,
"step": 532
},
{
"epoch": 1.228110599078341,
"grad_norm": 0.0,
"learning_rate": 8.62734998712336e-06,
"loss": 2.4359,
"step": 533
},
{
"epoch": 1.230414746543779,
"grad_norm": 0.0,
"learning_rate": 8.62157976251936e-06,
"loss": 2.0414,
"step": 534
},
{
"epoch": 1.2327188940092166,
"grad_norm": 0.0,
"learning_rate": 8.615782664941786e-06,
"loss": 2.1725,
"step": 535
},
{
"epoch": 1.2350230414746544,
"grad_norm": 0.0,
"learning_rate": 8.609958506224068e-06,
"loss": 2.0361,
"step": 536
},
{
"epoch": 1.237327188940092,
"grad_norm": 0.0,
"learning_rate": 8.604107096438784e-06,
"loss": 2.1823,
"step": 537
},
{
"epoch": 1.23963133640553,
"grad_norm": 0.0,
"learning_rate": 8.59822824387702e-06,
"loss": 2.1377,
"step": 538
},
{
"epoch": 1.2419354838709677,
"grad_norm": 0.0,
"learning_rate": 8.592321755027422e-06,
"loss": 2.2211,
"step": 539
},
{
"epoch": 1.2442396313364055,
"grad_norm": 0.0,
"learning_rate": 8.586387434554974e-06,
"loss": 2.2804,
"step": 540
},
{
"epoch": 1.2465437788018434,
"grad_norm": 0.0,
"learning_rate": 8.580425085279455e-06,
"loss": 2.0535,
"step": 541
},
{
"epoch": 1.2488479262672811,
"grad_norm": 0.0,
"learning_rate": 8.574434508153603e-06,
"loss": 2.2902,
"step": 542
},
{
"epoch": 1.2511520737327189,
"grad_norm": 0.0,
"learning_rate": 8.56841550224097e-06,
"loss": 2.2136,
"step": 543
},
{
"epoch": 1.2534562211981566,
"grad_norm": 0.0,
"learning_rate": 8.562367864693448e-06,
"loss": 2.1156,
"step": 544
},
{
"epoch": 1.2557603686635945,
"grad_norm": 0.0,
"learning_rate": 8.556291390728475e-06,
"loss": 1.8844,
"step": 545
},
{
"epoch": 1.2580645161290323,
"grad_norm": 0.0,
"learning_rate": 8.55018587360595e-06,
"loss": 2.2077,
"step": 546
},
{
"epoch": 1.26036866359447,
"grad_norm": 0.0,
"learning_rate": 8.544051104604738e-06,
"loss": 2.0569,
"step": 547
},
{
"epoch": 1.262672811059908,
"grad_norm": 0.0,
"learning_rate": 8.537886872998934e-06,
"loss": 2.3563,
"step": 548
},
{
"epoch": 1.2649769585253456,
"grad_norm": 0.0,
"learning_rate": 8.5316929660337e-06,
"loss": 1.7421,
"step": 549
},
{
"epoch": 1.2672811059907834,
"grad_norm": 0.0,
"learning_rate": 8.525469168900806e-06,
"loss": 2.539,
"step": 550
},
{
"epoch": 1.269585253456221,
"grad_norm": 0.0,
"learning_rate": 8.519215264713787e-06,
"loss": 2.1152,
"step": 551
},
{
"epoch": 1.271889400921659,
"grad_norm": 0.0,
"learning_rate": 8.512931034482758e-06,
"loss": 2.1897,
"step": 552
},
{
"epoch": 1.2741935483870968,
"grad_norm": 0.0,
"learning_rate": 8.506616257088848e-06,
"loss": 2.3483,
"step": 553
},
{
"epoch": 1.2764976958525347,
"grad_norm": 0.0,
"learning_rate": 8.500270709258256e-06,
"loss": 2.1675,
"step": 554
},
{
"epoch": 1.2788018433179724,
"grad_norm": 0.0,
"learning_rate": 8.493894165535958e-06,
"loss": 2.3407,
"step": 555
},
{
"epoch": 1.2811059907834101,
"grad_norm": 0.0,
"learning_rate": 8.487486398258977e-06,
"loss": 2.3402,
"step": 556
},
{
"epoch": 1.2834101382488479,
"grad_norm": 0.0,
"learning_rate": 8.481047177529316e-06,
"loss": 2.1818,
"step": 557
},
{
"epoch": 1.2857142857142856,
"grad_norm": 0.0,
"learning_rate": 8.47457627118644e-06,
"loss": 2.0397,
"step": 558
},
{
"epoch": 1.2880184331797235,
"grad_norm": 0.0,
"learning_rate": 8.468073444779393e-06,
"loss": 2.3515,
"step": 559
},
{
"epoch": 1.2903225806451613,
"grad_norm": 0.0,
"learning_rate": 8.46153846153846e-06,
"loss": 2.1762,
"step": 560
},
{
"epoch": 1.2926267281105992,
"grad_norm": 0.0,
"learning_rate": 8.454971082346463e-06,
"loss": 2.0294,
"step": 561
},
{
"epoch": 1.294930875576037,
"grad_norm": 0.0,
"learning_rate": 8.448371065709553e-06,
"loss": 2.1765,
"step": 562
},
{
"epoch": 1.2972350230414746,
"grad_norm": 0.0,
"learning_rate": 8.441738167727651e-06,
"loss": 2.2303,
"step": 563
},
{
"epoch": 1.2995391705069124,
"grad_norm": 0.0,
"learning_rate": 8.435072142064373e-06,
"loss": 2.1646,
"step": 564
},
{
"epoch": 1.3018433179723503,
"grad_norm": 0.0,
"learning_rate": 8.428372739916551e-06,
"loss": 2.3313,
"step": 565
},
{
"epoch": 1.304147465437788,
"grad_norm": 0.0,
"learning_rate": 8.42163970998327e-06,
"loss": 2.1818,
"step": 566
},
{
"epoch": 1.3064516129032258,
"grad_norm": 0.0,
"learning_rate": 8.414872798434444e-06,
"loss": 1.9629,
"step": 567
},
{
"epoch": 1.3087557603686637,
"grad_norm": 0.0,
"learning_rate": 8.408071748878924e-06,
"loss": 2.284,
"step": 568
},
{
"epoch": 1.3110599078341014,
"grad_norm": 0.0,
"learning_rate": 8.401236302332116e-06,
"loss": 2.4839,
"step": 569
},
{
"epoch": 1.3133640552995391,
"grad_norm": 0.0,
"learning_rate": 8.3943661971831e-06,
"loss": 2.4827,
"step": 570
},
{
"epoch": 1.3156682027649769,
"grad_norm": 0.0,
"learning_rate": 8.387461169161254e-06,
"loss": 1.8538,
"step": 571
},
{
"epoch": 1.3179723502304148,
"grad_norm": 0.0,
"learning_rate": 8.38052095130238e-06,
"loss": 2.1597,
"step": 572
},
{
"epoch": 1.3202764976958525,
"grad_norm": 0.0,
"learning_rate": 8.373545273914277e-06,
"loss": 2.2918,
"step": 573
},
{
"epoch": 1.3225806451612903,
"grad_norm": 0.0,
"learning_rate": 8.366533864541834e-06,
"loss": 2.257,
"step": 574
},
{
"epoch": 1.3248847926267282,
"grad_norm": 0.0,
"learning_rate": 8.359486447931526e-06,
"loss": 2.2058,
"step": 575
},
{
"epoch": 1.327188940092166,
"grad_norm": 0.0,
"learning_rate": 8.352402745995425e-06,
"loss": 2.3933,
"step": 576
},
{
"epoch": 1.3294930875576036,
"grad_norm": 0.0,
"learning_rate": 8.34528247777459e-06,
"loss": 1.9175,
"step": 577
},
{
"epoch": 1.3317972350230414,
"grad_norm": 0.0,
"learning_rate": 8.338125359401957e-06,
"loss": 2.0542,
"step": 578
},
{
"epoch": 1.3341013824884793,
"grad_norm": 0.0,
"learning_rate": 8.330931104064572e-06,
"loss": 2.3477,
"step": 579
},
{
"epoch": 1.336405529953917,
"grad_norm": 0.0,
"learning_rate": 8.32369942196532e-06,
"loss": 1.8106,
"step": 580
},
{
"epoch": 1.3387096774193548,
"grad_norm": 0.0,
"learning_rate": 8.316430020283975e-06,
"loss": 2.2048,
"step": 581
},
{
"epoch": 1.3410138248847927,
"grad_norm": 0.0,
"learning_rate": 8.309122603137711e-06,
"loss": 2.2727,
"step": 582
},
{
"epoch": 1.3433179723502304,
"grad_norm": 0.0,
"learning_rate": 8.301776871540926e-06,
"loss": 2.3041,
"step": 583
},
{
"epoch": 1.3456221198156681,
"grad_norm": 0.0,
"learning_rate": 8.294392523364487e-06,
"loss": 2.2184,
"step": 584
},
{
"epoch": 1.3479262672811059,
"grad_norm": 0.0,
"learning_rate": 8.28696925329429e-06,
"loss": 2.1741,
"step": 585
},
{
"epoch": 1.3502304147465438,
"grad_norm": 0.0,
"learning_rate": 8.279506752789194e-06,
"loss": 2.3027,
"step": 586
},
{
"epoch": 1.3525345622119815,
"grad_norm": 0.0,
"learning_rate": 8.272004710038269e-06,
"loss": 1.8337,
"step": 587
},
{
"epoch": 1.3548387096774195,
"grad_norm": 0.0,
"learning_rate": 8.264462809917356e-06,
"loss": 2.2419,
"step": 588
},
{
"epoch": 1.3571428571428572,
"grad_norm": 0.0,
"learning_rate": 8.256880733944954e-06,
"loss": 2.0455,
"step": 589
},
{
"epoch": 1.359447004608295,
"grad_norm": 0.0,
"learning_rate": 8.249258160237388e-06,
"loss": 2.2288,
"step": 590
},
{
"epoch": 1.3617511520737327,
"grad_norm": 0.0,
"learning_rate": 8.241594763463255e-06,
"loss": 2.3845,
"step": 591
},
{
"epoch": 1.3640552995391704,
"grad_norm": 0.0,
"learning_rate": 8.233890214797137e-06,
"loss": 1.8509,
"step": 592
},
{
"epoch": 1.3663594470046083,
"grad_norm": 0.0,
"learning_rate": 8.226144181872571e-06,
"loss": 2.3071,
"step": 593
},
{
"epoch": 1.368663594470046,
"grad_norm": 0.0,
"learning_rate": 8.218356328734255e-06,
"loss": 2.3412,
"step": 594
},
{
"epoch": 1.370967741935484,
"grad_norm": 0.0,
"learning_rate": 8.210526315789475e-06,
"loss": 2.3244,
"step": 595
},
{
"epoch": 1.3732718894009217,
"grad_norm": 0.0,
"learning_rate": 8.202653799758746e-06,
"loss": 2.2093,
"step": 596
},
{
"epoch": 1.3755760368663594,
"grad_norm": 0.0,
"learning_rate": 8.194738433625643e-06,
"loss": 2.245,
"step": 597
},
{
"epoch": 1.3778801843317972,
"grad_norm": 0.0,
"learning_rate": 8.18677986658581e-06,
"loss": 1.8521,
"step": 598
},
{
"epoch": 1.380184331797235,
"grad_norm": 0.0,
"learning_rate": 8.178777743995136e-06,
"loss": 2.327,
"step": 599
},
{
"epoch": 1.3824884792626728,
"grad_norm": 0.0,
"learning_rate": 8.170731707317073e-06,
"loss": 1.9856,
"step": 600
},
{
"epoch": 1.3847926267281105,
"grad_norm": 0.0,
"learning_rate": 8.162641394069091e-06,
"loss": 1.8187,
"step": 601
},
{
"epoch": 1.3870967741935485,
"grad_norm": 0.0,
"learning_rate": 8.154506437768241e-06,
"loss": 1.9824,
"step": 602
},
{
"epoch": 1.3894009216589862,
"grad_norm": 0.0,
"learning_rate": 8.146326467875806e-06,
"loss": 1.7706,
"step": 603
},
{
"epoch": 1.391705069124424,
"grad_norm": 0.0,
"learning_rate": 8.13810110974106e-06,
"loss": 2.423,
"step": 604
},
{
"epoch": 1.3940092165898617,
"grad_norm": 0.0,
"learning_rate": 8.129829984544051e-06,
"loss": 2.2774,
"step": 605
},
{
"epoch": 1.3963133640552996,
"grad_norm": 0.0,
"learning_rate": 8.121512709237446e-06,
"loss": 2.2349,
"step": 606
},
{
"epoch": 1.3986175115207373,
"grad_norm": 0.0,
"learning_rate": 8.113148896487411e-06,
"loss": 2.1761,
"step": 607
},
{
"epoch": 1.400921658986175,
"grad_norm": 0.0,
"learning_rate": 8.104738154613467e-06,
"loss": 1.6387,
"step": 608
},
{
"epoch": 1.403225806451613,
"grad_norm": 0.0,
"learning_rate": 8.096280087527354e-06,
"loss": 2.0971,
"step": 609
},
{
"epoch": 1.4055299539170507,
"grad_norm": 0.0,
"learning_rate": 8.087774294670848e-06,
"loss": 2.3251,
"step": 610
},
{
"epoch": 1.4078341013824884,
"grad_norm": 0.0,
"learning_rate": 8.079220370952531e-06,
"loss": 1.9343,
"step": 611
},
{
"epoch": 1.4101382488479262,
"grad_norm": 0.0,
"learning_rate": 8.070617906683481e-06,
"loss": 2.2662,
"step": 612
},
{
"epoch": 1.412442396313364,
"grad_norm": 0.0,
"learning_rate": 8.061966487511855e-06,
"loss": 2.2092,
"step": 613
},
{
"epoch": 1.4147465437788018,
"grad_norm": 0.0,
"learning_rate": 8.053265694356374e-06,
"loss": 2.0375,
"step": 614
},
{
"epoch": 1.4170506912442398,
"grad_norm": 0.0,
"learning_rate": 8.044515103338633e-06,
"loss": 2.3473,
"step": 615
},
{
"epoch": 1.4193548387096775,
"grad_norm": 0.0,
"learning_rate": 8.035714285714286e-06,
"loss": 2.5178,
"step": 616
},
{
"epoch": 1.4216589861751152,
"grad_norm": 0.0,
"learning_rate": 8.026862807803005e-06,
"loss": 2.1105,
"step": 617
},
{
"epoch": 1.423963133640553,
"grad_norm": 0.0,
"learning_rate": 8.017960230917255e-06,
"loss": 1.9589,
"step": 618
},
{
"epoch": 1.4262672811059907,
"grad_norm": 0.0,
"learning_rate": 8.009006111289803e-06,
"loss": 2.2071,
"step": 619
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.0,
"learning_rate": 8.000000000000001e-06,
"loss": 2.3059,
"step": 620
},
{
"epoch": 1.4308755760368663,
"grad_norm": 0.0,
"learning_rate": 7.990941442898738e-06,
"loss": 2.3726,
"step": 621
},
{
"epoch": 1.4331797235023043,
"grad_norm": 0.0,
"learning_rate": 7.981829980532122e-06,
"loss": 2.0598,
"step": 622
},
{
"epoch": 1.435483870967742,
"grad_norm": 0.0,
"learning_rate": 7.97266514806378e-06,
"loss": 2.1011,
"step": 623
},
{
"epoch": 1.4377880184331797,
"grad_norm": 0.0,
"learning_rate": 7.963446475195824e-06,
"loss": 2.0975,
"step": 624
},
{
"epoch": 1.4400921658986174,
"grad_norm": 0.0,
"learning_rate": 7.95417348608838e-06,
"loss": 2.1737,
"step": 625
},
{
"epoch": 1.4423963133640554,
"grad_norm": 0.0,
"learning_rate": 7.944845699277742e-06,
"loss": 2.1402,
"step": 626
},
{
"epoch": 1.444700460829493,
"grad_norm": 0.0,
"learning_rate": 7.935462627593021e-06,
"loss": 2.194,
"step": 627
},
{
"epoch": 1.4470046082949308,
"grad_norm": 0.0,
"learning_rate": 7.926023778071336e-06,
"loss": 2.0133,
"step": 628
},
{
"epoch": 1.4493087557603688,
"grad_norm": 0.0,
"learning_rate": 7.916528651871482e-06,
"loss": 2.3248,
"step": 629
},
{
"epoch": 1.4516129032258065,
"grad_norm": 0.0,
"learning_rate": 7.906976744186046e-06,
"loss": 2.114,
"step": 630
},
{
"epoch": 1.4539170506912442,
"grad_norm": 0.0,
"learning_rate": 7.89736754415195e-06,
"loss": 2.2423,
"step": 631
},
{
"epoch": 1.456221198156682,
"grad_norm": 0.0,
"learning_rate": 7.887700534759358e-06,
"loss": 2.4931,
"step": 632
},
{
"epoch": 1.4585253456221199,
"grad_norm": 0.0,
"learning_rate": 7.877975192758967e-06,
"loss": 2.1069,
"step": 633
},
{
"epoch": 1.4608294930875576,
"grad_norm": 0.0,
"learning_rate": 7.868190988567587e-06,
"loss": 2.4308,
"step": 634
},
{
"epoch": 1.4631336405529953,
"grad_norm": 0.0,
"learning_rate": 7.858347386172008e-06,
"loss": 2.1255,
"step": 635
},
{
"epoch": 1.4654377880184333,
"grad_norm": 0.0,
"learning_rate": 7.848443843031123e-06,
"loss": 2.1629,
"step": 636
},
{
"epoch": 1.467741935483871,
"grad_norm": 0.0,
"learning_rate": 7.838479809976249e-06,
"loss": 2.1334,
"step": 637
},
{
"epoch": 1.4700460829493087,
"grad_norm": 0.0,
"learning_rate": 7.8284547311096e-06,
"loss": 2.2989,
"step": 638
},
{
"epoch": 1.4723502304147464,
"grad_norm": 0.0,
"learning_rate": 7.818368043700922e-06,
"loss": 2.0108,
"step": 639
},
{
"epoch": 1.4746543778801844,
"grad_norm": 0.0,
"learning_rate": 7.808219178082192e-06,
"loss": 1.9985,
"step": 640
},
{
"epoch": 1.476958525345622,
"grad_norm": 0.0,
"learning_rate": 7.798007557540365e-06,
"loss": 2.3147,
"step": 641
},
{
"epoch": 1.4792626728110598,
"grad_norm": 0.0,
"learning_rate": 7.787732598208133e-06,
"loss": 2.327,
"step": 642
},
{
"epoch": 1.4815668202764978,
"grad_norm": 0.0,
"learning_rate": 7.777393708952645e-06,
"loss": 2.0685,
"step": 643
},
{
"epoch": 1.4838709677419355,
"grad_norm": 0.0,
"learning_rate": 7.766990291262136e-06,
"loss": 1.9718,
"step": 644
},
{
"epoch": 1.4861751152073732,
"grad_norm": 0.0,
"learning_rate": 7.756521739130437e-06,
"loss": 2.3679,
"step": 645
},
{
"epoch": 1.488479262672811,
"grad_norm": 0.0,
"learning_rate": 7.745987438939288e-06,
"loss": 1.9236,
"step": 646
},
{
"epoch": 1.4907834101382489,
"grad_norm": 0.0,
"learning_rate": 7.735386769338468e-06,
"loss": 2.2692,
"step": 647
},
{
"epoch": 1.4930875576036866,
"grad_norm": 0.0,
"learning_rate": 7.724719101123595e-06,
"loss": 2.076,
"step": 648
},
{
"epoch": 1.4953917050691246,
"grad_norm": 0.0,
"learning_rate": 7.713983797111659e-06,
"loss": 2.1628,
"step": 649
},
{
"epoch": 1.4976958525345623,
"grad_norm": 0.0,
"learning_rate": 7.703180212014134e-06,
"loss": 2.4163,
"step": 650
},
{
"epoch": 1.5,
"grad_norm": 0.0,
"learning_rate": 7.692307692307692e-06,
"loss": 2.0675,
"step": 651
},
{
"epoch": 1.5023041474654377,
"grad_norm": 0.0,
"learning_rate": 7.681365576102418e-06,
"loss": 2.2859,
"step": 652
},
{
"epoch": 1.5046082949308754,
"grad_norm": 0.0,
"learning_rate": 7.670353193007492e-06,
"loss": 2.2192,
"step": 653
},
{
"epoch": 1.5069124423963134,
"grad_norm": 0.0,
"learning_rate": 7.659269863994274e-06,
"loss": 2.104,
"step": 654
},
{
"epoch": 1.5092165898617511,
"grad_norm": 0.0,
"learning_rate": 7.648114901256734e-06,
"loss": 2.3686,
"step": 655
},
{
"epoch": 1.511520737327189,
"grad_norm": 0.0,
"learning_rate": 7.636887608069165e-06,
"loss": 2.2697,
"step": 656
},
{
"epoch": 1.5138248847926268,
"grad_norm": 0.0,
"learning_rate": 7.625587278641128e-06,
"loss": 2.4146,
"step": 657
},
{
"epoch": 1.5161290322580645,
"grad_norm": 0.0,
"learning_rate": 7.614213197969545e-06,
"loss": 2.4442,
"step": 658
},
{
"epoch": 1.5184331797235022,
"grad_norm": 0.0,
"learning_rate": 7.6027646416878876e-06,
"loss": 2.3551,
"step": 659
},
{
"epoch": 1.52073732718894,
"grad_norm": 0.0,
"learning_rate": 7.591240875912409e-06,
"loss": 2.5825,
"step": 660
},
{
"epoch": 1.523041474654378,
"grad_norm": 0.0,
"learning_rate": 7.579641157085317e-06,
"loss": 2.2146,
"step": 661
},
{
"epoch": 1.5253456221198156,
"grad_norm": 0.0,
"learning_rate": 7.567964731814842e-06,
"loss": 2.3835,
"step": 662
},
{
"epoch": 1.5276497695852536,
"grad_norm": 0.0,
"learning_rate": 7.5562108367121265e-06,
"loss": 1.9557,
"step": 663
},
{
"epoch": 1.5299539170506913,
"grad_norm": 0.0,
"learning_rate": 7.544378698224851e-06,
"loss": 2.2251,
"step": 664
},
{
"epoch": 1.532258064516129,
"grad_norm": 0.0,
"learning_rate": 7.532467532467532e-06,
"loss": 2.2089,
"step": 665
},
{
"epoch": 1.5345622119815667,
"grad_norm": 0.0,
"learning_rate": 7.5204765450484e-06,
"loss": 2.3537,
"step": 666
},
{
"epoch": 1.5368663594470044,
"grad_norm": 0.0,
"learning_rate": 7.508404930892791e-06,
"loss": 2.2675,
"step": 667
},
{
"epoch": 1.5391705069124424,
"grad_norm": 0.0,
"learning_rate": 7.496251874062969e-06,
"loss": 2.2828,
"step": 668
},
{
"epoch": 1.5414746543778803,
"grad_norm": 0.0,
"learning_rate": 7.484016547574278e-06,
"loss": 2.5155,
"step": 669
},
{
"epoch": 1.543778801843318,
"grad_norm": 0.0,
"learning_rate": 7.471698113207549e-06,
"loss": 2.3364,
"step": 670
},
{
"epoch": 1.5460829493087558,
"grad_norm": 0.0,
"learning_rate": 7.459295721317683e-06,
"loss": 1.7703,
"step": 671
},
{
"epoch": 1.5483870967741935,
"grad_norm": 0.0,
"learning_rate": 7.446808510638298e-06,
"loss": 2.331,
"step": 672
},
{
"epoch": 1.5506912442396312,
"grad_norm": 0.0,
"learning_rate": 7.434235608082349e-06,
"loss": 2.2976,
"step": 673
},
{
"epoch": 1.5529953917050692,
"grad_norm": 0.0,
"learning_rate": 7.421576128538639e-06,
"loss": 2.2165,
"step": 674
},
{
"epoch": 1.555299539170507,
"grad_norm": 0.0,
"learning_rate": 7.408829174664108e-06,
"loss": 2.3928,
"step": 675
},
{
"epoch": 1.5576036866359448,
"grad_norm": 0.0,
"learning_rate": 7.395993836671803e-06,
"loss": 2.3778,
"step": 676
},
{
"epoch": 1.5599078341013826,
"grad_norm": 0.0,
"learning_rate": 7.383069192114418e-06,
"loss": 2.5435,
"step": 677
},
{
"epoch": 1.5622119815668203,
"grad_norm": 0.0,
"learning_rate": 7.370054305663304e-06,
"loss": 2.3359,
"step": 678
},
{
"epoch": 1.564516129032258,
"grad_norm": 0.0,
"learning_rate": 7.3569482288828335e-06,
"loss": 2.1116,
"step": 679
},
{
"epoch": 1.5668202764976957,
"grad_norm": 0.0,
"learning_rate": 7.34375e-06,
"loss": 2.2972,
"step": 680
},
{
"epoch": 1.5691244239631337,
"grad_norm": 0.0,
"learning_rate": 7.3304586436691505e-06,
"loss": 2.0481,
"step": 681
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.0,
"learning_rate": 7.317073170731709e-06,
"loss": 2.0658,
"step": 682
},
{
"epoch": 1.5737327188940093,
"grad_norm": 0.0,
"learning_rate": 7.303592577970787e-06,
"loss": 1.8831,
"step": 683
},
{
"epoch": 1.576036866359447,
"grad_norm": 0.0,
"learning_rate": 7.29001584786054e-06,
"loss": 2.4854,
"step": 684
},
{
"epoch": 1.5783410138248848,
"grad_norm": 0.0,
"learning_rate": 7.2763419483101405e-06,
"loss": 2.5698,
"step": 685
},
{
"epoch": 1.5806451612903225,
"grad_norm": 0.0,
"learning_rate": 7.262569832402235e-06,
"loss": 1.8958,
"step": 686
},
{
"epoch": 1.5829493087557602,
"grad_norm": 0.0,
"learning_rate": 7.2486984381257516e-06,
"loss": 2.0024,
"step": 687
},
{
"epoch": 1.5852534562211982,
"grad_norm": 0.0,
"learning_rate": 7.234726688102894e-06,
"loss": 2.306,
"step": 688
},
{
"epoch": 1.587557603686636,
"grad_norm": 0.0,
"learning_rate": 7.220653489310205e-06,
"loss": 2.3266,
"step": 689
},
{
"epoch": 1.5898617511520738,
"grad_norm": 0.0,
"learning_rate": 7.206477732793522e-06,
"loss": 2.123,
"step": 690
},
{
"epoch": 1.5921658986175116,
"grad_norm": 0.0,
"learning_rate": 7.192198293376676e-06,
"loss": 2.0752,
"step": 691
},
{
"epoch": 1.5944700460829493,
"grad_norm": 0.0,
"learning_rate": 7.177814029363785e-06,
"loss": 2.1435,
"step": 692
},
{
"epoch": 1.596774193548387,
"grad_norm": 0.0,
"learning_rate": 7.1633237822349565e-06,
"loss": 2.1723,
"step": 693
},
{
"epoch": 1.5990783410138247,
"grad_norm": 0.0,
"learning_rate": 7.148726376335251e-06,
"loss": 2.1988,
"step": 694
},
{
"epoch": 1.6013824884792627,
"grad_norm": 0.0,
"learning_rate": 7.134020618556702e-06,
"loss": 1.8426,
"step": 695
},
{
"epoch": 1.6036866359447006,
"grad_norm": 0.0,
"learning_rate": 7.119205298013245e-06,
"loss": 2.2582,
"step": 696
},
{
"epoch": 1.6059907834101383,
"grad_norm": 0.0,
"learning_rate": 7.104279185708352e-06,
"loss": 2.3248,
"step": 697
},
{
"epoch": 1.608294930875576,
"grad_norm": 0.0,
"learning_rate": 7.089241034195163e-06,
"loss": 2.0316,
"step": 698
},
{
"epoch": 1.6105990783410138,
"grad_norm": 0.0,
"learning_rate": 7.074089577228968e-06,
"loss": 2.4332,
"step": 699
},
{
"epoch": 1.6129032258064515,
"grad_norm": 0.0,
"learning_rate": 7.058823529411766e-06,
"loss": 2.1161,
"step": 700
},
{
"epoch": 1.6152073732718892,
"grad_norm": 0.0,
"learning_rate": 7.0434415858287656e-06,
"loss": 2.2994,
"step": 701
},
{
"epoch": 1.6175115207373272,
"grad_norm": 0.0,
"learning_rate": 7.027942421676546e-06,
"loss": 2.5017,
"step": 702
},
{
"epoch": 1.6198156682027651,
"grad_norm": 0.0,
"learning_rate": 7.012324691882704e-06,
"loss": 2.23,
"step": 703
},
{
"epoch": 1.6221198156682028,
"grad_norm": 0.0,
"learning_rate": 6.9965870307167235e-06,
"loss": 1.8913,
"step": 704
},
{
"epoch": 1.6244239631336406,
"grad_norm": 0.0,
"learning_rate": 6.980728051391863e-06,
"loss": 1.853,
"step": 705
},
{
"epoch": 1.6267281105990783,
"grad_norm": 0.0,
"learning_rate": 6.9647463456577815e-06,
"loss": 2.2723,
"step": 706
},
{
"epoch": 1.629032258064516,
"grad_norm": 0.0,
"learning_rate": 6.948640483383685e-06,
"loss": 2.071,
"step": 707
},
{
"epoch": 1.631336405529954,
"grad_norm": 0.0,
"learning_rate": 6.932409012131715e-06,
"loss": 2.2638,
"step": 708
},
{
"epoch": 1.6336405529953917,
"grad_norm": 0.0,
"learning_rate": 6.916050456720314e-06,
"loss": 2.1189,
"step": 709
},
{
"epoch": 1.6359447004608296,
"grad_norm": 0.0,
"learning_rate": 6.899563318777293e-06,
"loss": 2.348,
"step": 710
},
{
"epoch": 1.6382488479262673,
"grad_norm": 0.0,
"learning_rate": 6.882946076282333e-06,
"loss": 2.4884,
"step": 711
},
{
"epoch": 1.640552995391705,
"grad_norm": 0.0,
"learning_rate": 6.866197183098592e-06,
"loss": 2.2421,
"step": 712
},
{
"epoch": 1.6428571428571428,
"grad_norm": 0.0,
"learning_rate": 6.849315068493151e-06,
"loss": 2.0634,
"step": 713
},
{
"epoch": 1.6451612903225805,
"grad_norm": 0.0,
"learning_rate": 6.832298136645963e-06,
"loss": 2.3555,
"step": 714
},
{
"epoch": 1.6474654377880185,
"grad_norm": 0.0,
"learning_rate": 6.815144766146993e-06,
"loss": 2.0054,
"step": 715
},
{
"epoch": 1.6497695852534562,
"grad_norm": 0.0,
"learning_rate": 6.797853309481217e-06,
"loss": 2.0496,
"step": 716
},
{
"epoch": 1.6520737327188941,
"grad_norm": 0.0,
"learning_rate": 6.780422092501123e-06,
"loss": 2.3211,
"step": 717
},
{
"epoch": 1.6543778801843319,
"grad_norm": 0.0,
"learning_rate": 6.762849413886385e-06,
"loss": 1.9154,
"step": 718
},
{
"epoch": 1.6566820276497696,
"grad_norm": 0.0,
"learning_rate": 6.745133544590313e-06,
"loss": 2.1494,
"step": 719
},
{
"epoch": 1.6589861751152073,
"grad_norm": 0.0,
"learning_rate": 6.7272727272727275e-06,
"loss": 2.1532,
"step": 720
},
{
"epoch": 1.661290322580645,
"grad_norm": 0.0,
"learning_rate": 6.70926517571885e-06,
"loss": 1.9703,
"step": 721
},
{
"epoch": 1.663594470046083,
"grad_norm": 0.0,
"learning_rate": 6.691109074243812e-06,
"loss": 2.4101,
"step": 722
},
{
"epoch": 1.6658986175115207,
"grad_norm": 0.0,
"learning_rate": 6.672802577082374e-06,
"loss": 2.3254,
"step": 723
},
{
"epoch": 1.6682027649769586,
"grad_norm": 0.0,
"learning_rate": 6.654343807763401e-06,
"loss": 2.2264,
"step": 724
},
{
"epoch": 1.6705069124423964,
"grad_norm": 0.0,
"learning_rate": 6.6357308584686775e-06,
"loss": 2.2232,
"step": 725
},
{
"epoch": 1.672811059907834,
"grad_norm": 0.0,
"learning_rate": 6.616961789375583e-06,
"loss": 2.228,
"step": 726
},
{
"epoch": 1.6751152073732718,
"grad_norm": 0.0,
"learning_rate": 6.598034627983154e-06,
"loss": 2.5189,
"step": 727
},
{
"epoch": 1.6774193548387095,
"grad_norm": 0.0,
"learning_rate": 6.578947368421052e-06,
"loss": 2.0719,
"step": 728
},
{
"epoch": 1.6797235023041475,
"grad_norm": 0.0,
"learning_rate": 6.559697970740916e-06,
"loss": 1.9752,
"step": 729
},
{
"epoch": 1.6820276497695854,
"grad_norm": 0.0,
"learning_rate": 6.5402843601895735e-06,
"loss": 2.1016,
"step": 730
},
{
"epoch": 1.6843317972350231,
"grad_norm": 0.0,
"learning_rate": 6.52070442646359e-06,
"loss": 2.1034,
"step": 731
},
{
"epoch": 1.6866359447004609,
"grad_norm": 0.0,
"learning_rate": 6.500956022944551e-06,
"loss": 2.2459,
"step": 732
},
{
"epoch": 1.6889400921658986,
"grad_norm": 0.0,
"learning_rate": 6.481036965914547e-06,
"loss": 2.0818,
"step": 733
},
{
"epoch": 1.6912442396313363,
"grad_norm": 0.0,
"learning_rate": 6.460945033751206e-06,
"loss": 2.4337,
"step": 734
},
{
"epoch": 1.6935483870967742,
"grad_norm": 0.0,
"learning_rate": 6.440677966101695e-06,
"loss": 2.3903,
"step": 735
},
{
"epoch": 1.695852534562212,
"grad_norm": 0.0,
"learning_rate": 6.42023346303502e-06,
"loss": 2.1265,
"step": 736
},
{
"epoch": 1.69815668202765,
"grad_norm": 0.0,
"learning_rate": 6.3996091841719595e-06,
"loss": 2.1477,
"step": 737
},
{
"epoch": 1.7004608294930876,
"grad_norm": 0.0,
"learning_rate": 6.3788027477919535e-06,
"loss": 2.4987,
"step": 738
},
{
"epoch": 1.7027649769585254,
"grad_norm": 0.0,
"learning_rate": 6.357811729916214e-06,
"loss": 2.423,
"step": 739
},
{
"epoch": 1.705069124423963,
"grad_norm": 0.0,
"learning_rate": 6.336633663366336e-06,
"loss": 2.3027,
"step": 740
},
{
"epoch": 1.7073732718894008,
"grad_norm": 0.0,
"learning_rate": 6.315266036797612e-06,
"loss": 2.4029,
"step": 741
},
{
"epoch": 1.7096774193548387,
"grad_norm": 0.0,
"learning_rate": 6.2937062937062944e-06,
"loss": 2.0332,
"step": 742
},
{
"epoch": 1.7119815668202765,
"grad_norm": 0.0,
"learning_rate": 6.271951831409935e-06,
"loss": 2.2298,
"step": 743
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.0,
"learning_rate": 6.25e-06,
"loss": 2.1978,
"step": 744
},
{
"epoch": 1.7165898617511521,
"grad_norm": 0.0,
"learning_rate": 6.227848101265823e-06,
"loss": 2.148,
"step": 745
},
{
"epoch": 1.7188940092165899,
"grad_norm": 0.0,
"learning_rate": 6.205493387589013e-06,
"loss": 1.7415,
"step": 746
},
{
"epoch": 1.7211981566820276,
"grad_norm": 0.0,
"learning_rate": 6.182933060807359e-06,
"loss": 2.1957,
"step": 747
},
{
"epoch": 1.7235023041474653,
"grad_norm": 0.0,
"learning_rate": 6.1601642710472284e-06,
"loss": 2.2568,
"step": 748
},
{
"epoch": 1.7258064516129032,
"grad_norm": 0.0,
"learning_rate": 6.137184115523466e-06,
"loss": 2.2825,
"step": 749
},
{
"epoch": 1.728110599078341,
"grad_norm": 0.0,
"learning_rate": 6.113989637305699e-06,
"loss": 2.5317,
"step": 750
},
{
"epoch": 1.730414746543779,
"grad_norm": 0.0,
"learning_rate": 6.090577824049974e-06,
"loss": 2.4529,
"step": 751
},
{
"epoch": 1.7327188940092166,
"grad_norm": 0.0,
"learning_rate": 6.066945606694561e-06,
"loss": 2.4748,
"step": 752
},
{
"epoch": 1.7350230414746544,
"grad_norm": 0.0,
"learning_rate": 6.04308985811876e-06,
"loss": 2.3451,
"step": 753
},
{
"epoch": 1.737327188940092,
"grad_norm": 0.0,
"learning_rate": 6.0190073917634635e-06,
"loss": 2.0164,
"step": 754
},
{
"epoch": 1.7396313364055298,
"grad_norm": 0.0,
"learning_rate": 5.994694960212202e-06,
"loss": 1.9073,
"step": 755
},
{
"epoch": 1.7419354838709677,
"grad_norm": 0.0,
"learning_rate": 5.970149253731343e-06,
"loss": 2.2839,
"step": 756
},
{
"epoch": 1.7442396313364057,
"grad_norm": 0.0,
"learning_rate": 5.945366898768078e-06,
"loss": 2.1681,
"step": 757
},
{
"epoch": 1.7465437788018434,
"grad_norm": 0.0,
"learning_rate": 5.920344456404736e-06,
"loss": 2.3917,
"step": 758
},
{
"epoch": 1.7488479262672811,
"grad_norm": 0.0,
"learning_rate": 5.895078420767983e-06,
"loss": 1.9239,
"step": 759
},
{
"epoch": 1.7511520737327189,
"grad_norm": 0.0,
"learning_rate": 5.869565217391304e-06,
"loss": 2.3452,
"step": 760
},
{
"epoch": 1.7534562211981566,
"grad_norm": 0.0,
"learning_rate": 5.843801201529219e-06,
"loss": 2.2105,
"step": 761
},
{
"epoch": 1.7557603686635943,
"grad_norm": 0.0,
"learning_rate": 5.817782656421514e-06,
"loss": 2.2953,
"step": 762
},
{
"epoch": 1.7580645161290323,
"grad_norm": 0.0,
"learning_rate": 5.791505791505793e-06,
"loss": 2.3598,
"step": 763
},
{
"epoch": 1.7603686635944702,
"grad_norm": 0.0,
"learning_rate": 5.7649667405764965e-06,
"loss": 2.2871,
"step": 764
},
{
"epoch": 1.762672811059908,
"grad_norm": 0.0,
"learning_rate": 5.7381615598885795e-06,
"loss": 2.3103,
"step": 765
},
{
"epoch": 1.7649769585253456,
"grad_norm": 0.0,
"learning_rate": 5.711086226203808e-06,
"loss": 2.3354,
"step": 766
},
{
"epoch": 1.7672811059907834,
"grad_norm": 0.0,
"learning_rate": 5.683736634777714e-06,
"loss": 2.0412,
"step": 767
},
{
"epoch": 1.769585253456221,
"grad_norm": 0.0,
"learning_rate": 5.656108597285067e-06,
"loss": 2.3042,
"step": 768
},
{
"epoch": 1.771889400921659,
"grad_norm": 0.0,
"learning_rate": 5.628197839681638e-06,
"loss": 2.301,
"step": 769
},
{
"epoch": 1.7741935483870968,
"grad_norm": 0.0,
"learning_rate": 5.600000000000001e-06,
"loss": 2.3394,
"step": 770
},
{
"epoch": 1.7764976958525347,
"grad_norm": 0.0,
"learning_rate": 5.571510626076968e-06,
"loss": 1.991,
"step": 771
},
{
"epoch": 1.7788018433179724,
"grad_norm": 0.0,
"learning_rate": 5.5427251732101625e-06,
"loss": 2.0793,
"step": 772
},
{
"epoch": 1.7811059907834101,
"grad_norm": 0.0,
"learning_rate": 5.513639001741149e-06,
"loss": 1.9698,
"step": 773
},
{
"epoch": 1.7834101382488479,
"grad_norm": 0.0,
"learning_rate": 5.4842473745624265e-06,
"loss": 2.305,
"step": 774
},
{
"epoch": 1.7857142857142856,
"grad_norm": 0.0,
"learning_rate": 5.4545454545454545e-06,
"loss": 2.5145,
"step": 775
},
{
"epoch": 1.7880184331797235,
"grad_norm": 0.0,
"learning_rate": 5.424528301886792e-06,
"loss": 2.2537,
"step": 776
},
{
"epoch": 1.7903225806451613,
"grad_norm": 0.0,
"learning_rate": 5.394190871369295e-06,
"loss": 2.1169,
"step": 777
},
{
"epoch": 1.7926267281105992,
"grad_norm": 0.0,
"learning_rate": 5.363528009535162e-06,
"loss": 2.1254,
"step": 778
},
{
"epoch": 1.794930875576037,
"grad_norm": 0.0,
"learning_rate": 5.332534451767526e-06,
"loss": 1.9744,
"step": 779
},
{
"epoch": 1.7972350230414746,
"grad_norm": 0.0,
"learning_rate": 5.301204819277109e-06,
"loss": 1.861,
"step": 780
},
{
"epoch": 1.7995391705069124,
"grad_norm": 0.0,
"learning_rate": 5.269533615990309e-06,
"loss": 2.1956,
"step": 781
},
{
"epoch": 1.80184331797235,
"grad_norm": 0.0,
"learning_rate": 5.237515225334957e-06,
"loss": 2.0532,
"step": 782
},
{
"epoch": 1.804147465437788,
"grad_norm": 0.0,
"learning_rate": 5.20514390691978e-06,
"loss": 2.402,
"step": 783
},
{
"epoch": 1.8064516129032258,
"grad_norm": 0.0,
"learning_rate": 5.172413793103448e-06,
"loss": 2.6081,
"step": 784
},
{
"epoch": 1.8087557603686637,
"grad_norm": 0.0,
"learning_rate": 5.139318885448916e-06,
"loss": 2.4214,
"step": 785
},
{
"epoch": 1.8110599078341014,
"grad_norm": 0.0,
"learning_rate": 5.1058530510585306e-06,
"loss": 1.9568,
"step": 786
},
{
"epoch": 1.8133640552995391,
"grad_norm": 0.0,
"learning_rate": 5.072010018785223e-06,
"loss": 2.3105,
"step": 787
},
{
"epoch": 1.8156682027649769,
"grad_norm": 0.0,
"learning_rate": 5.037783375314862e-06,
"loss": 2.113,
"step": 788
},
{
"epoch": 1.8179723502304146,
"grad_norm": 0.0,
"learning_rate": 5.00316656111463e-06,
"loss": 2.2062,
"step": 789
},
{
"epoch": 1.8202764976958525,
"grad_norm": 0.0,
"learning_rate": 4.968152866242038e-06,
"loss": 2.2599,
"step": 790
},
{
"epoch": 1.8225806451612905,
"grad_norm": 0.0,
"learning_rate": 4.932735426008968e-06,
"loss": 2.1384,
"step": 791
},
{
"epoch": 1.8248847926267282,
"grad_norm": 0.0,
"learning_rate": 4.896907216494845e-06,
"loss": 1.8991,
"step": 792
},
{
"epoch": 1.827188940092166,
"grad_norm": 0.0,
"learning_rate": 4.8606610499027876e-06,
"loss": 2.3475,
"step": 793
},
{
"epoch": 1.8294930875576036,
"grad_norm": 0.0,
"learning_rate": 4.823989569752283e-06,
"loss": 1.9257,
"step": 794
},
{
"epoch": 1.8317972350230414,
"grad_norm": 0.0,
"learning_rate": 4.78688524590164e-06,
"loss": 1.7366,
"step": 795
},
{
"epoch": 1.8341013824884793,
"grad_norm": 0.0,
"learning_rate": 4.74934036939314e-06,
"loss": 2.0084,
"step": 796
},
{
"epoch": 1.836405529953917,
"grad_norm": 0.0,
"learning_rate": 4.711347047113471e-06,
"loss": 2.2387,
"step": 797
},
{
"epoch": 1.838709677419355,
"grad_norm": 0.0,
"learning_rate": 4.672897196261682e-06,
"loss": 2.065,
"step": 798
},
{
"epoch": 1.8410138248847927,
"grad_norm": 0.0,
"learning_rate": 4.633982538616521e-06,
"loss": 2.0072,
"step": 799
},
{
"epoch": 1.8433179723502304,
"grad_norm": 0.0,
"learning_rate": 4.594594594594596e-06,
"loss": 2.233,
"step": 800
},
{
"epoch": 1.8456221198156681,
"grad_norm": 0.0,
"learning_rate": 4.554724677090415e-06,
"loss": 2.2987,
"step": 801
},
{
"epoch": 1.8479262672811059,
"grad_norm": 0.0,
"learning_rate": 4.5143638850889195e-06,
"loss": 2.0798,
"step": 802
},
{
"epoch": 1.8502304147465438,
"grad_norm": 0.0,
"learning_rate": 4.473503097040606e-06,
"loss": 2.1042,
"step": 803
},
{
"epoch": 1.8525345622119815,
"grad_norm": 0.0,
"learning_rate": 4.43213296398892e-06,
"loss": 1.9728,
"step": 804
},
{
"epoch": 1.8548387096774195,
"grad_norm": 0.0,
"learning_rate": 4.390243902439025e-06,
"loss": 2.1751,
"step": 805
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.0,
"learning_rate": 4.347826086956522e-06,
"loss": 2.2449,
"step": 806
},
{
"epoch": 1.859447004608295,
"grad_norm": 0.0,
"learning_rate": 4.304869442484122e-06,
"loss": 2.041,
"step": 807
},
{
"epoch": 1.8617511520737327,
"grad_norm": 0.0,
"learning_rate": 4.2613636363636365e-06,
"loss": 1.8616,
"step": 808
},
{
"epoch": 1.8640552995391704,
"grad_norm": 0.0,
"learning_rate": 4.217298070050036e-06,
"loss": 2.4581,
"step": 809
},
{
"epoch": 1.8663594470046083,
"grad_norm": 0.0,
"learning_rate": 4.172661870503597e-06,
"loss": 2.0801,
"step": 810
},
{
"epoch": 1.868663594470046,
"grad_norm": 0.0,
"learning_rate": 4.127443881245474e-06,
"loss": 1.9342,
"step": 811
},
{
"epoch": 1.870967741935484,
"grad_norm": 0.0,
"learning_rate": 4.081632653061224e-06,
"loss": 1.948,
"step": 812
},
{
"epoch": 1.8732718894009217,
"grad_norm": 0.0,
"learning_rate": 4.035216434336023e-06,
"loss": 2.3085,
"step": 813
},
{
"epoch": 1.8755760368663594,
"grad_norm": 0.0,
"learning_rate": 3.988183161004432e-06,
"loss": 1.9853,
"step": 814
},
{
"epoch": 1.8778801843317972,
"grad_norm": 0.0,
"learning_rate": 3.9405204460966546e-06,
"loss": 1.929,
"step": 815
},
{
"epoch": 1.8801843317972349,
"grad_norm": 0.0,
"learning_rate": 3.892215568862276e-06,
"loss": 2.3427,
"step": 816
},
{
"epoch": 1.8824884792626728,
"grad_norm": 0.0,
"learning_rate": 3.843255463451395e-06,
"loss": 2.5295,
"step": 817
},
{
"epoch": 1.8847926267281108,
"grad_norm": 0.0,
"learning_rate": 3.793626707132018e-06,
"loss": 2.1848,
"step": 818
},
{
"epoch": 1.8870967741935485,
"grad_norm": 0.0,
"learning_rate": 3.7433155080213903e-06,
"loss": 1.9892,
"step": 819
},
{
"epoch": 1.8894009216589862,
"grad_norm": 0.0,
"learning_rate": 3.692307692307692e-06,
"loss": 1.9724,
"step": 820
},
{
"epoch": 1.891705069124424,
"grad_norm": 0.0,
"learning_rate": 3.640588690937258e-06,
"loss": 2.2537,
"step": 821
},
{
"epoch": 1.8940092165898617,
"grad_norm": 0.0,
"learning_rate": 3.5881435257410295e-06,
"loss": 2.278,
"step": 822
},
{
"epoch": 1.8963133640552994,
"grad_norm": 0.0,
"learning_rate": 3.5349567949725054e-06,
"loss": 2.2778,
"step": 823
},
{
"epoch": 1.8986175115207373,
"grad_norm": 0.0,
"learning_rate": 3.4810126582278482e-06,
"loss": 2.572,
"step": 824
},
{
"epoch": 1.9009216589861753,
"grad_norm": 0.0,
"learning_rate": 3.426294820717132e-06,
"loss": 2.3863,
"step": 825
},
{
"epoch": 1.903225806451613,
"grad_norm": 0.0,
"learning_rate": 3.3707865168539327e-06,
"loss": 2.0672,
"step": 826
},
{
"epoch": 1.9055299539170507,
"grad_norm": 0.0,
"learning_rate": 3.3144704931285366e-06,
"loss": 2.2825,
"step": 827
},
{
"epoch": 1.9078341013824884,
"grad_norm": 0.0,
"learning_rate": 3.2573289902280133e-06,
"loss": 1.962,
"step": 828
},
{
"epoch": 1.9101382488479262,
"grad_norm": 0.0,
"learning_rate": 3.1993437243642333e-06,
"loss": 2.27,
"step": 829
},
{
"epoch": 1.912442396313364,
"grad_norm": 0.0,
"learning_rate": 3.140495867768595e-06,
"loss": 1.9069,
"step": 830
},
{
"epoch": 1.9147465437788018,
"grad_norm": 0.0,
"learning_rate": 3.080766028309742e-06,
"loss": 1.9966,
"step": 831
},
{
"epoch": 1.9170506912442398,
"grad_norm": 0.0,
"learning_rate": 3.02013422818792e-06,
"loss": 2.3821,
"step": 832
},
{
"epoch": 1.9193548387096775,
"grad_norm": 0.0,
"learning_rate": 2.958579881656805e-06,
"loss": 2.5374,
"step": 833
},
{
"epoch": 1.9216589861751152,
"grad_norm": 0.0,
"learning_rate": 2.896081771720613e-06,
"loss": 2.5009,
"step": 834
},
{
"epoch": 1.923963133640553,
"grad_norm": 0.0,
"learning_rate": 2.8326180257510733e-06,
"loss": 2.4116,
"step": 835
},
{
"epoch": 1.9262672811059907,
"grad_norm": 0.0,
"learning_rate": 2.768166089965398e-06,
"loss": 2.0421,
"step": 836
},
{
"epoch": 1.9285714285714286,
"grad_norm": 0.0,
"learning_rate": 2.7027027027027026e-06,
"loss": 2.5362,
"step": 837
},
{
"epoch": 1.9308755760368663,
"grad_norm": 0.0,
"learning_rate": 2.6362038664323376e-06,
"loss": 2.173,
"step": 838
},
{
"epoch": 1.9331797235023043,
"grad_norm": 0.0,
"learning_rate": 2.5686448184233835e-06,
"loss": 2.3125,
"step": 839
},
{
"epoch": 1.935483870967742,
"grad_norm": 0.0,
"learning_rate": 2.5e-06,
"loss": 2.2148,
"step": 840
},
{
"epoch": 1.9377880184331797,
"grad_norm": 0.0,
"learning_rate": 2.4302430243024304e-06,
"loss": 2.2172,
"step": 841
},
{
"epoch": 1.9400921658986174,
"grad_norm": 0.0,
"learning_rate": 2.3593466424682394e-06,
"loss": 2.1904,
"step": 842
},
{
"epoch": 1.9423963133640552,
"grad_norm": 0.0,
"learning_rate": 2.2872827081427264e-06,
"loss": 2.1084,
"step": 843
},
{
"epoch": 1.944700460829493,
"grad_norm": 0.0,
"learning_rate": 2.2140221402214023e-06,
"loss": 2.2455,
"step": 844
},
{
"epoch": 1.9470046082949308,
"grad_norm": 0.0,
"learning_rate": 2.1395348837209305e-06,
"loss": 2.2483,
"step": 845
},
{
"epoch": 1.9493087557603688,
"grad_norm": 0.0,
"learning_rate": 2.0637898686679174e-06,
"loss": 2.305,
"step": 846
},
{
"epoch": 1.9516129032258065,
"grad_norm": 0.0,
"learning_rate": 1.9867549668874175e-06,
"loss": 2.3151,
"step": 847
},
{
"epoch": 1.9539170506912442,
"grad_norm": 0.0,
"learning_rate": 1.908396946564886e-06,
"loss": 2.1444,
"step": 848
},
{
"epoch": 1.956221198156682,
"grad_norm": 0.0,
"learning_rate": 1.828681424446583e-06,
"loss": 2.3103,
"step": 849
},
{
"epoch": 1.9585253456221197,
"grad_norm": 0.0,
"learning_rate": 1.7475728155339805e-06,
"loss": 2.2019,
"step": 850
},
{
"epoch": 1.9608294930875576,
"grad_norm": 0.0,
"learning_rate": 1.6650342801175317e-06,
"loss": 2.297,
"step": 851
},
{
"epoch": 1.9631336405529956,
"grad_norm": 0.0,
"learning_rate": 1.5810276679841899e-06,
"loss": 2.261,
"step": 852
},
{
"epoch": 1.9654377880184333,
"grad_norm": 0.0,
"learning_rate": 1.4955134596211368e-06,
"loss": 2.0714,
"step": 853
},
{
"epoch": 1.967741935483871,
"grad_norm": 0.0,
"learning_rate": 1.4084507042253523e-06,
"loss": 2.0849,
"step": 854
},
{
"epoch": 1.9700460829493087,
"grad_norm": 0.0,
"learning_rate": 1.3197969543147206e-06,
"loss": 1.8001,
"step": 855
},
{
"epoch": 1.9723502304147464,
"grad_norm": 0.0,
"learning_rate": 1.2295081967213118e-06,
"loss": 1.8648,
"step": 856
},
{
"epoch": 1.9746543778801844,
"grad_norm": 0.0,
"learning_rate": 1.1375387797311274e-06,
"loss": 2.1359,
"step": 857
},
{
"epoch": 1.976958525345622,
"grad_norm": 0.0,
"learning_rate": 1.0438413361169103e-06,
"loss": 2.278,
"step": 858
},
{
"epoch": 1.97926267281106,
"grad_norm": 0.0,
"learning_rate": 9.483667017913594e-07,
"loss": 2.2074,
"step": 859
},
{
"epoch": 1.9815668202764978,
"grad_norm": 0.0,
"learning_rate": 8.510638297872341e-07,
"loss": 2.1091,
"step": 860
},
{
"epoch": 1.9838709677419355,
"grad_norm": 0.0,
"learning_rate": 7.518796992481203e-07,
"loss": 2.358,
"step": 861
},
{
"epoch": 1.9861751152073732,
"grad_norm": 0.0,
"learning_rate": 6.507592190889371e-07,
"loss": 1.9049,
"step": 862
},
{
"epoch": 1.988479262672811,
"grad_norm": 0.0,
"learning_rate": 5.47645125958379e-07,
"loss": 2.2344,
"step": 863
},
{
"epoch": 1.9907834101382489,
"grad_norm": 0.0,
"learning_rate": 4.4247787610619474e-07,
"loss": 2.163,
"step": 864
},
{
"epoch": 1.9930875576036866,
"grad_norm": 0.0,
"learning_rate": 3.3519553072625703e-07,
"loss": 2.1836,
"step": 865
},
{
"epoch": 1.9953917050691246,
"grad_norm": 0.0,
"learning_rate": 2.257336343115124e-07,
"loss": 2.2758,
"step": 866
},
{
"epoch": 1.9976958525345623,
"grad_norm": 0.0,
"learning_rate": 1.1402508551881413e-07,
"loss": 2.1508,
"step": 867
},
{
"epoch": 2.0,
"grad_norm": 0.0,
"learning_rate": 0,
"loss": 2.1981,
"step": 868
}
],
"logging_steps": 1,
"max_steps": 868,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 217,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.1905444258583675e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}