| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.032734074612906575, | |
| "eval_steps": 500, | |
| "global_step": 630, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.967684234392304, | |
| "learning_rate": 8.722043470761813e-09, | |
| "loss": 1.4217, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0271119924702425, | |
| "learning_rate": 1.7444086941523626e-08, | |
| "loss": 1.3854, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0212962641045844, | |
| "learning_rate": 2.6166130412285438e-08, | |
| "loss": 1.421, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.969098210999342, | |
| "learning_rate": 3.488817388304725e-08, | |
| "loss": 1.3894, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9600462061407877, | |
| "learning_rate": 4.361021735380907e-08, | |
| "loss": 1.3803, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.074991458239833, | |
| "learning_rate": 5.2332260824570876e-08, | |
| "loss": 1.3815, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.026445479098331, | |
| "learning_rate": 6.105430429533269e-08, | |
| "loss": 1.3684, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9268992001978744, | |
| "learning_rate": 6.97763477660945e-08, | |
| "loss": 1.4307, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.020642302186043, | |
| "learning_rate": 7.849839123685631e-08, | |
| "loss": 1.3318, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0765469986494853, | |
| "learning_rate": 8.722043470761814e-08, | |
| "loss": 1.3942, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.081729945762728, | |
| "learning_rate": 9.594247817837994e-08, | |
| "loss": 1.3555, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0021774146670808, | |
| "learning_rate": 1.0466452164914175e-07, | |
| "loss": 1.4366, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.059550099782956, | |
| "learning_rate": 1.1338656511990357e-07, | |
| "loss": 1.3999, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9198920843423073, | |
| "learning_rate": 1.2210860859066538e-07, | |
| "loss": 1.3949, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.013793892067568, | |
| "learning_rate": 1.308306520614272e-07, | |
| "loss": 1.4062, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9189606946894022, | |
| "learning_rate": 1.39552695532189e-07, | |
| "loss": 1.401, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9989048069702475, | |
| "learning_rate": 1.4827473900295083e-07, | |
| "loss": 1.39, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8873329349365613, | |
| "learning_rate": 1.5699678247371262e-07, | |
| "loss": 1.4061, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8867416403445345, | |
| "learning_rate": 1.6571882594447446e-07, | |
| "loss": 1.4032, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9725069440958127, | |
| "learning_rate": 1.7444086941523627e-07, | |
| "loss": 1.3772, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0049844241627675, | |
| "learning_rate": 1.8316291288599806e-07, | |
| "loss": 1.3907, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.878905929699835, | |
| "learning_rate": 1.9188495635675987e-07, | |
| "loss": 1.4029, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8262523355216014, | |
| "learning_rate": 2.006069998275217e-07, | |
| "loss": 1.3488, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.913459302454502, | |
| "learning_rate": 2.093290432982835e-07, | |
| "loss": 1.3888, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.924777837323026, | |
| "learning_rate": 2.1805108676904532e-07, | |
| "loss": 1.3423, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0238436977422207, | |
| "learning_rate": 2.2677313023980713e-07, | |
| "loss": 1.4083, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9404632380821036, | |
| "learning_rate": 2.3549517371056895e-07, | |
| "loss": 1.3325, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9624670572200222, | |
| "learning_rate": 2.4421721718133076e-07, | |
| "loss": 1.4221, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9307501329723236, | |
| "learning_rate": 2.5293926065209255e-07, | |
| "loss": 1.3827, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8568182093611365, | |
| "learning_rate": 2.616613041228544e-07, | |
| "loss": 1.394, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0056868600386544, | |
| "learning_rate": 2.703833475936162e-07, | |
| "loss": 1.3585, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.928843591728527, | |
| "learning_rate": 2.79105391064378e-07, | |
| "loss": 1.3927, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.979059280785437, | |
| "learning_rate": 2.878274345351398e-07, | |
| "loss": 1.4622, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.948156874136048, | |
| "learning_rate": 2.9654947800590165e-07, | |
| "loss": 1.3583, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.883247676830032, | |
| "learning_rate": 3.0527152147666344e-07, | |
| "loss": 1.3533, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.058107134456641, | |
| "learning_rate": 3.1399356494742523e-07, | |
| "loss": 1.3904, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0535192707251237, | |
| "learning_rate": 3.2271560841818707e-07, | |
| "loss": 1.3978, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.897725634603183, | |
| "learning_rate": 3.314376518889489e-07, | |
| "loss": 1.3422, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.869420148217502, | |
| "learning_rate": 3.401596953597107e-07, | |
| "loss": 1.4465, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9815636403050676, | |
| "learning_rate": 3.4888173883047254e-07, | |
| "loss": 1.407, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9486391625075123, | |
| "learning_rate": 3.576037823012343e-07, | |
| "loss": 1.391, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9396534742524283, | |
| "learning_rate": 3.663258257719961e-07, | |
| "loss": 1.4191, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.954105365539368, | |
| "learning_rate": 3.7504786924275796e-07, | |
| "loss": 1.4039, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9899210526299482, | |
| "learning_rate": 3.8376991271351975e-07, | |
| "loss": 1.3606, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9715202250605515, | |
| "learning_rate": 3.924919561842816e-07, | |
| "loss": 1.3561, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8726950910953133, | |
| "learning_rate": 4.012139996550434e-07, | |
| "loss": 1.4004, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9356806631744568, | |
| "learning_rate": 4.0993604312580517e-07, | |
| "loss": 1.3626, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.828385414972167, | |
| "learning_rate": 4.18658086596567e-07, | |
| "loss": 1.416, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.860775941749999, | |
| "learning_rate": 4.273801300673288e-07, | |
| "loss": 1.4232, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.908555437519401, | |
| "learning_rate": 4.3610217353809064e-07, | |
| "loss": 1.371, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0110809579629283, | |
| "learning_rate": 4.448242170088525e-07, | |
| "loss": 1.3886, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8879956038976062, | |
| "learning_rate": 4.5354626047961427e-07, | |
| "loss": 1.3677, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9475494022582405, | |
| "learning_rate": 4.622683039503761e-07, | |
| "loss": 1.3596, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9208201499436677, | |
| "learning_rate": 4.709903474211379e-07, | |
| "loss": 1.3795, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9250691956165293, | |
| "learning_rate": 4.797123908918997e-07, | |
| "loss": 1.3521, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0059604294844795, | |
| "learning_rate": 4.884344343626615e-07, | |
| "loss": 1.3872, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9408348770709347, | |
| "learning_rate": 4.971564778334233e-07, | |
| "loss": 1.41, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9941841393676247, | |
| "learning_rate": 5.058785213041851e-07, | |
| "loss": 1.4293, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9287843738148744, | |
| "learning_rate": 5.146005647749469e-07, | |
| "loss": 1.411, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9468093301597533, | |
| "learning_rate": 5.233226082457088e-07, | |
| "loss": 1.3508, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.854893968299532, | |
| "learning_rate": 5.320446517164706e-07, | |
| "loss": 1.4042, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9224674242946387, | |
| "learning_rate": 5.407666951872324e-07, | |
| "loss": 1.4182, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.025591867750147, | |
| "learning_rate": 5.494887386579943e-07, | |
| "loss": 1.4162, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9351339151935045, | |
| "learning_rate": 5.58210782128756e-07, | |
| "loss": 1.2956, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9740598113404677, | |
| "learning_rate": 5.669328255995178e-07, | |
| "loss": 1.4181, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8698658052840464, | |
| "learning_rate": 5.756548690702796e-07, | |
| "loss": 1.3885, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.847745090454755, | |
| "learning_rate": 5.843769125410415e-07, | |
| "loss": 1.4268, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.53006793293518, | |
| "learning_rate": 5.930989560118033e-07, | |
| "loss": 1.4369, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.02012038605618, | |
| "learning_rate": 6.01820999482565e-07, | |
| "loss": 1.406, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8502665195139074, | |
| "learning_rate": 6.105430429533269e-07, | |
| "loss": 1.4273, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.966110454182966, | |
| "learning_rate": 6.192650864240887e-07, | |
| "loss": 1.3822, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9117409152319604, | |
| "learning_rate": 6.279871298948505e-07, | |
| "loss": 1.3758, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9583103749551247, | |
| "learning_rate": 6.367091733656124e-07, | |
| "loss": 1.3821, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9976941225678524, | |
| "learning_rate": 6.454312168363741e-07, | |
| "loss": 1.3818, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9208562033277237, | |
| "learning_rate": 6.541532603071359e-07, | |
| "loss": 1.4249, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9753607287344868, | |
| "learning_rate": 6.628753037778978e-07, | |
| "loss": 1.394, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.852059681146882, | |
| "learning_rate": 6.715973472486596e-07, | |
| "loss": 1.3735, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9721541467116075, | |
| "learning_rate": 6.803193907194214e-07, | |
| "loss": 1.3284, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.959460844473033, | |
| "learning_rate": 6.890414341901832e-07, | |
| "loss": 1.3998, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8741209861248747, | |
| "learning_rate": 6.977634776609451e-07, | |
| "loss": 1.3696, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.916879772765294, | |
| "learning_rate": 7.064855211317069e-07, | |
| "loss": 1.4736, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.069300514821944, | |
| "learning_rate": 7.152075646024686e-07, | |
| "loss": 1.3341, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.966078167553101, | |
| "learning_rate": 7.239296080732305e-07, | |
| "loss": 1.3705, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.891366947828864, | |
| "learning_rate": 7.326516515439922e-07, | |
| "loss": 1.4036, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0015624379292687, | |
| "learning_rate": 7.41373695014754e-07, | |
| "loss": 1.3548, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9762714989519297, | |
| "learning_rate": 7.500957384855159e-07, | |
| "loss": 1.4038, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0417489896152325, | |
| "learning_rate": 7.588177819562777e-07, | |
| "loss": 1.3972, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.957367413809754, | |
| "learning_rate": 7.675398254270395e-07, | |
| "loss": 1.376, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9811178726545466, | |
| "learning_rate": 7.762618688978014e-07, | |
| "loss": 1.366, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9882512869731994, | |
| "learning_rate": 7.849839123685632e-07, | |
| "loss": 1.3835, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.878782548871192, | |
| "learning_rate": 7.93705955839325e-07, | |
| "loss": 1.3372, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.9971417051306344, | |
| "learning_rate": 8.024279993100868e-07, | |
| "loss": 1.4037, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.0231933357399066, | |
| "learning_rate": 8.111500427808487e-07, | |
| "loss": 1.3692, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8777305685815024, | |
| "learning_rate": 8.198720862516103e-07, | |
| "loss": 1.3493, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.990027107011572, | |
| "learning_rate": 8.285941297223721e-07, | |
| "loss": 1.3586, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.818072292309908, | |
| "learning_rate": 8.37316173193134e-07, | |
| "loss": 1.3612, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.1271514088993144, | |
| "learning_rate": 8.460382166638958e-07, | |
| "loss": 1.336, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0169265133833396, | |
| "learning_rate": 8.547602601346576e-07, | |
| "loss": 1.3665, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9482660829507994, | |
| "learning_rate": 8.634823036054195e-07, | |
| "loss": 1.3551, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.087617940804514, | |
| "learning_rate": 8.722043470761813e-07, | |
| "loss": 1.3659, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.894747860556493, | |
| "learning_rate": 8.72204341205319e-07, | |
| "loss": 1.4032, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9567796592966546, | |
| "learning_rate": 8.722043235927325e-07, | |
| "loss": 1.3568, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.130564519854559, | |
| "learning_rate": 8.72204294238422e-07, | |
| "loss": 1.3567, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.98891915499642, | |
| "learning_rate": 8.722042531423884e-07, | |
| "loss": 1.3865, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.036577692929289, | |
| "learning_rate": 8.722042003046327e-07, | |
| "loss": 1.3901, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.001761214468399, | |
| "learning_rate": 8.722041357251567e-07, | |
| "loss": 1.4117, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.006505553779288, | |
| "learning_rate": 8.722040594039618e-07, | |
| "loss": 1.4083, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.970081989296889, | |
| "learning_rate": 8.722039713410501e-07, | |
| "loss": 1.3163, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9452680507051863, | |
| "learning_rate": 8.72203871536424e-07, | |
| "loss": 1.3367, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0057027079906216, | |
| "learning_rate": 8.722037599900863e-07, | |
| "loss": 1.3893, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9731127424958697, | |
| "learning_rate": 8.722036367020397e-07, | |
| "loss": 1.3604, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.884218184477182, | |
| "learning_rate": 8.722035016722879e-07, | |
| "loss": 1.4651, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.8763866239897644, | |
| "learning_rate": 8.722033549008343e-07, | |
| "loss": 1.3947, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.927176134008426, | |
| "learning_rate": 8.722031963876829e-07, | |
| "loss": 1.3667, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9924621440798664, | |
| "learning_rate": 8.72203026132838e-07, | |
| "loss": 1.3632, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0499504528400943, | |
| "learning_rate": 8.72202844136304e-07, | |
| "loss": 1.4176, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9684475725772392, | |
| "learning_rate": 8.722026503980863e-07, | |
| "loss": 1.4146, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9148264494394662, | |
| "learning_rate": 8.722024449181895e-07, | |
| "loss": 1.4205, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.947431519938494, | |
| "learning_rate": 8.722022276966194e-07, | |
| "loss": 1.3281, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.955626479582277, | |
| "learning_rate": 8.72201998733382e-07, | |
| "loss": 1.3465, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.028540598737732, | |
| "learning_rate": 8.722017580284832e-07, | |
| "loss": 1.3472, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9197378030040753, | |
| "learning_rate": 8.722015055819296e-07, | |
| "loss": 1.381, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0574320249257227, | |
| "learning_rate": 8.722012413937282e-07, | |
| "loss": 1.4225, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.913538682906452, | |
| "learning_rate": 8.722009654638856e-07, | |
| "loss": 1.3536, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.886066575609779, | |
| "learning_rate": 8.722006777924096e-07, | |
| "loss": 1.3736, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.957758024407401, | |
| "learning_rate": 8.722003783793081e-07, | |
| "loss": 1.3973, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.958995782934072, | |
| "learning_rate": 8.722000672245888e-07, | |
| "loss": 1.3954, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.987991679162308, | |
| "learning_rate": 8.721997443282602e-07, | |
| "loss": 1.3757, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0909686056252434, | |
| "learning_rate": 8.721994096903311e-07, | |
| "loss": 1.3462, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9477825764652494, | |
| "learning_rate": 8.721990633108104e-07, | |
| "loss": 1.4295, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.947921751933276, | |
| "learning_rate": 8.721987051897074e-07, | |
| "loss": 1.3854, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.8440480288328427, | |
| "learning_rate": 8.721983353270319e-07, | |
| "loss": 1.4106, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9792049006251906, | |
| "learning_rate": 8.721979537227935e-07, | |
| "loss": 1.3913, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9238731192373746, | |
| "learning_rate": 8.721975603770031e-07, | |
| "loss": 1.3695, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0773774260583155, | |
| "learning_rate": 8.721971552896706e-07, | |
| "loss": 1.3629, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9679219250269044, | |
| "learning_rate": 8.721967384608074e-07, | |
| "loss": 1.4205, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.030565370577699, | |
| "learning_rate": 8.721963098904246e-07, | |
| "loss": 1.4311, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0375097512582503, | |
| "learning_rate": 8.721958695785336e-07, | |
| "loss": 1.4069, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.92214551378445, | |
| "learning_rate": 8.721954175251462e-07, | |
| "loss": 1.422, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.1283303266405578, | |
| "learning_rate": 8.721949537302749e-07, | |
| "loss": 1.432, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.1049340924381705, | |
| "learning_rate": 8.72194478193932e-07, | |
| "loss": 1.3815, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.869253522521714, | |
| "learning_rate": 8.721939909161303e-07, | |
| "loss": 1.391, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.8752461370622306, | |
| "learning_rate": 8.721934918968828e-07, | |
| "loss": 1.3769, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.909751532098998, | |
| "learning_rate": 8.721929811362032e-07, | |
| "loss": 1.3995, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0462324191538572, | |
| "learning_rate": 8.72192458634105e-07, | |
| "loss": 1.3689, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9750194133891363, | |
| "learning_rate": 8.721919243906024e-07, | |
| "loss": 1.3707, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.932835851287147, | |
| "learning_rate": 8.721913784057099e-07, | |
| "loss": 1.3676, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9429516387295926, | |
| "learning_rate": 8.721908206794419e-07, | |
| "loss": 1.3731, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.994182650351975, | |
| "learning_rate": 8.721902512118136e-07, | |
| "loss": 1.3542, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.876833046636617, | |
| "learning_rate": 8.721896700028404e-07, | |
| "loss": 1.4124, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.945327518176284, | |
| "learning_rate": 8.721890770525377e-07, | |
| "loss": 1.4137, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 21.047240653653276, | |
| "learning_rate": 8.721884723609218e-07, | |
| "loss": 1.4264, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.029952956834553, | |
| "learning_rate": 8.721878559280086e-07, | |
| "loss": 1.4372, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.137230528895406, | |
| "learning_rate": 8.721872277538151e-07, | |
| "loss": 1.4019, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9696146910825694, | |
| "learning_rate": 8.72186587838358e-07, | |
| "loss": 1.4515, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.980760336638325, | |
| "learning_rate": 8.721859361816546e-07, | |
| "loss": 1.4203, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.086006727040003, | |
| "learning_rate": 8.721852727837222e-07, | |
| "loss": 1.3712, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.003419403761712, | |
| "learning_rate": 8.72184597644579e-07, | |
| "loss": 1.4107, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0463864266769773, | |
| "learning_rate": 8.72183910764243e-07, | |
| "loss": 1.4082, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.950362004991645, | |
| "learning_rate": 8.721832121427326e-07, | |
| "loss": 1.352, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.8779668562920815, | |
| "learning_rate": 8.721825017800669e-07, | |
| "loss": 1.4236, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0172810234945455, | |
| "learning_rate": 8.721817796762648e-07, | |
| "loss": 1.3871, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9726094865888224, | |
| "learning_rate": 8.721810458313457e-07, | |
| "loss": 1.349, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0322153773349334, | |
| "learning_rate": 8.721803002453297e-07, | |
| "loss": 1.3935, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0249194383352283, | |
| "learning_rate": 8.721795429182364e-07, | |
| "loss": 1.3849, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9938901642866718, | |
| "learning_rate": 8.721787738500866e-07, | |
| "loss": 1.4267, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.923274256584191, | |
| "learning_rate": 8.721779930409007e-07, | |
| "loss": 1.4283, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.8466301519873785, | |
| "learning_rate": 8.721772004906999e-07, | |
| "loss": 1.3842, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0052783960700165, | |
| "learning_rate": 8.721763961995056e-07, | |
| "loss": 1.4335, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0935980229307614, | |
| "learning_rate": 8.721755801673391e-07, | |
| "loss": 1.3751, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0201926532008505, | |
| "learning_rate": 8.721747523942229e-07, | |
| "loss": 1.383, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.964731945306275, | |
| "learning_rate": 8.721739128801788e-07, | |
| "loss": 1.3359, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.928301273992501, | |
| "learning_rate": 8.721730616252297e-07, | |
| "loss": 1.3461, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9759904501938617, | |
| "learning_rate": 8.721721986293985e-07, | |
| "loss": 1.3644, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.040389211247673, | |
| "learning_rate": 8.721713238927082e-07, | |
| "loss": 1.4341, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.005645814777094, | |
| "learning_rate": 8.721704374151826e-07, | |
| "loss": 1.3967, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.1272949994089823, | |
| "learning_rate": 8.721695391968456e-07, | |
| "loss": 1.3796, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0684527006439533, | |
| "learning_rate": 8.721686292377211e-07, | |
| "loss": 1.3905, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9348716760076603, | |
| "learning_rate": 8.721677075378338e-07, | |
| "loss": 1.3905, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9873597802095304, | |
| "learning_rate": 8.721667740972085e-07, | |
| "loss": 1.4103, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.979793648840201, | |
| "learning_rate": 8.721658289158703e-07, | |
| "loss": 1.3622, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.937468774579186, | |
| "learning_rate": 8.721648719938447e-07, | |
| "loss": 1.414, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.879104091071243, | |
| "learning_rate": 8.721639033311573e-07, | |
| "loss": 1.3108, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0663878291218203, | |
| "learning_rate": 8.721629229278344e-07, | |
| "loss": 1.3543, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9407287447315826, | |
| "learning_rate": 8.721619307839025e-07, | |
| "loss": 1.3753, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.967538550932994, | |
| "learning_rate": 8.721609268993879e-07, | |
| "loss": 1.3973, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.057519293009879, | |
| "learning_rate": 8.721599112743179e-07, | |
| "loss": 1.4036, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.936392616519391, | |
| "learning_rate": 8.721588839087197e-07, | |
| "loss": 1.4852, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9670464594249197, | |
| "learning_rate": 8.721578448026212e-07, | |
| "loss": 1.3643, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0273720809079663, | |
| "learning_rate": 8.721567939560502e-07, | |
| "loss": 1.4109, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0651462806238854, | |
| "learning_rate": 8.721557313690349e-07, | |
| "loss": 1.3599, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9487059919929326, | |
| "learning_rate": 8.721546570416042e-07, | |
| "loss": 1.3377, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0998938976371146, | |
| "learning_rate": 8.721535709737867e-07, | |
| "loss": 1.3685, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.940826121224176, | |
| "learning_rate": 8.721524731656118e-07, | |
| "loss": 1.4174, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.014412763659776, | |
| "learning_rate": 8.721513636171093e-07, | |
| "loss": 1.3758, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0608004542672678, | |
| "learning_rate": 8.721502423283086e-07, | |
| "loss": 1.3716, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.94244083669587, | |
| "learning_rate": 8.721491092992403e-07, | |
| "loss": 1.3937, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9911802591493144, | |
| "learning_rate": 8.721479645299345e-07, | |
| "loss": 1.4164, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0344694715702065, | |
| "learning_rate": 8.721468080204223e-07, | |
| "loss": 1.4167, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.865667879330454, | |
| "learning_rate": 8.72145639770735e-07, | |
| "loss": 1.4041, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.072739743995507, | |
| "learning_rate": 8.721444597809037e-07, | |
| "loss": 1.4133, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0276333439793843, | |
| "learning_rate": 8.721432680509603e-07, | |
| "loss": 1.3605, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0465572110487686, | |
| "learning_rate": 8.721420645809369e-07, | |
| "loss": 1.3134, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9542599421921376, | |
| "learning_rate": 8.721408493708659e-07, | |
| "loss": 1.4148, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.90720227559915, | |
| "learning_rate": 8.721396224207801e-07, | |
| "loss": 1.3997, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0246259249156617, | |
| "learning_rate": 8.721383837307123e-07, | |
| "loss": 1.4238, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9975853807488453, | |
| "learning_rate": 8.721371333006962e-07, | |
| "loss": 1.3879, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0021383888830258, | |
| "learning_rate": 8.721358711307651e-07, | |
| "loss": 1.3349, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0201205392426296, | |
| "learning_rate": 8.721345972209533e-07, | |
| "loss": 1.3692, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.972139743981842, | |
| "learning_rate": 8.721333115712948e-07, | |
| "loss": 1.3856, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9209251468195276, | |
| "learning_rate": 8.721320141818245e-07, | |
| "loss": 1.3726, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9320196507721277, | |
| "learning_rate": 8.721307050525772e-07, | |
| "loss": 1.4143, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0002549106343337, | |
| "learning_rate": 8.72129384183588e-07, | |
| "loss": 1.3897, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9582570275362206, | |
| "learning_rate": 8.721280515748928e-07, | |
| "loss": 1.3756, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0145408653891526, | |
| "learning_rate": 8.721267072265271e-07, | |
| "loss": 1.3929, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0495215598431553, | |
| "learning_rate": 8.721253511385274e-07, | |
| "loss": 1.4061, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9254365712957613, | |
| "learning_rate": 8.721239833109302e-07, | |
| "loss": 1.3903, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.997455071778174, | |
| "learning_rate": 8.72122603743772e-07, | |
| "loss": 1.4246, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9195114563849627, | |
| "learning_rate": 8.721212124370902e-07, | |
| "loss": 1.3968, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0160422542520706, | |
| "learning_rate": 8.721198093909225e-07, | |
| "loss": 1.4347, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.01404121750226, | |
| "learning_rate": 8.721183946053062e-07, | |
| "loss": 1.3945, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0611502119276692, | |
| "learning_rate": 8.721169680802796e-07, | |
| "loss": 1.3975, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0684020412598727, | |
| "learning_rate": 8.721155298158811e-07, | |
| "loss": 1.373, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9440206694677027, | |
| "learning_rate": 8.721140798121494e-07, | |
| "loss": 1.3432, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.974581850771121, | |
| "learning_rate": 8.721126180691237e-07, | |
| "loss": 1.3095, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9933489105960844, | |
| "learning_rate": 8.721111445868431e-07, | |
| "loss": 1.3885, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9831661987665528, | |
| "learning_rate": 8.721096593653475e-07, | |
| "loss": 1.3126, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.100080295310524, | |
| "learning_rate": 8.721081624046766e-07, | |
| "loss": 1.3567, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.989885190608965, | |
| "learning_rate": 8.72106653704871e-07, | |
| "loss": 1.3899, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0712176271885023, | |
| "learning_rate": 8.721051332659713e-07, | |
| "loss": 1.4208, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.062312373029536, | |
| "learning_rate": 8.721036010880183e-07, | |
| "loss": 1.4147, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9701616634317083, | |
| "learning_rate": 8.721020571710533e-07, | |
| "loss": 1.434, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9572643731393646, | |
| "learning_rate": 8.721005015151179e-07, | |
| "loss": 1.3795, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.997406682050713, | |
| "learning_rate": 8.720989341202539e-07, | |
| "loss": 1.4501, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9106126480356522, | |
| "learning_rate": 8.720973549865035e-07, | |
| "loss": 1.3684, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9444070042644817, | |
| "learning_rate": 8.720957641139094e-07, | |
| "loss": 1.4213, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.8728037311842822, | |
| "learning_rate": 8.720941615025142e-07, | |
| "loss": 1.3519, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.015889105815668, | |
| "learning_rate": 8.720925471523613e-07, | |
| "loss": 1.4162, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9419377055914744, | |
| "learning_rate": 8.72090921063494e-07, | |
| "loss": 1.3357, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.89008663153287, | |
| "learning_rate": 8.720892832359559e-07, | |
| "loss": 1.3647, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9219232048658736, | |
| "learning_rate": 8.720876336697914e-07, | |
| "loss": 1.4069, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.96537590149616, | |
| "learning_rate": 8.72085972365045e-07, | |
| "loss": 1.4118, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.883655732971505, | |
| "learning_rate": 8.720842993217609e-07, | |
| "loss": 1.4136, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9788747864733764, | |
| "learning_rate": 8.720826145399848e-07, | |
| "loss": 1.3976, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.875570982035785, | |
| "learning_rate": 8.720809180197616e-07, | |
| "loss": 1.426, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9926412719867304, | |
| "learning_rate": 8.720792097611372e-07, | |
| "loss": 1.3629, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.958723584893194, | |
| "learning_rate": 8.720774897641574e-07, | |
| "loss": 1.3918, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.968992238648431, | |
| "learning_rate": 8.720757580288688e-07, | |
| "loss": 1.4241, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.889688463405204, | |
| "learning_rate": 8.720740145553177e-07, | |
| "loss": 1.4101, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9993006762652312, | |
| "learning_rate": 8.720722593435512e-07, | |
| "loss": 1.3857, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.980847240255761, | |
| "learning_rate": 8.720704923936167e-07, | |
| "loss": 1.4077, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.884007977441845, | |
| "learning_rate": 8.720687137055615e-07, | |
| "loss": 1.3822, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9646728227580645, | |
| "learning_rate": 8.720669232794336e-07, | |
| "loss": 1.3737, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.893382783809774, | |
| "learning_rate": 8.720651211152813e-07, | |
| "loss": 1.3762, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.024418707419624, | |
| "learning_rate": 8.72063307213153e-07, | |
| "loss": 1.3546, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0252657870696495, | |
| "learning_rate": 8.720614815730977e-07, | |
| "loss": 1.3661, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0208601885030606, | |
| "learning_rate": 8.720596441951642e-07, | |
| "loss": 1.4182, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0552975630549954, | |
| "learning_rate": 8.720577950794024e-07, | |
| "loss": 1.38, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.916749346833794, | |
| "learning_rate": 8.720559342258619e-07, | |
| "loss": 1.4049, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.035247531851327, | |
| "learning_rate": 8.720540616345928e-07, | |
| "loss": 1.4256, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9902303644665205, | |
| "learning_rate": 8.720521773056454e-07, | |
| "loss": 1.3356, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.119044393884763, | |
| "learning_rate": 8.720502812390706e-07, | |
| "loss": 1.4103, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9552269954583803, | |
| "learning_rate": 8.720483734349194e-07, | |
| "loss": 1.3855, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.017213443982555, | |
| "learning_rate": 8.720464538932433e-07, | |
| "loss": 1.3902, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.925567645830183, | |
| "learning_rate": 8.720445226140937e-07, | |
| "loss": 1.4519, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.983266195022755, | |
| "learning_rate": 8.720425795975228e-07, | |
| "loss": 1.3971, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.992218221530755, | |
| "learning_rate": 8.720406248435828e-07, | |
| "loss": 1.4231, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9250759809857882, | |
| "learning_rate": 8.720386583523264e-07, | |
| "loss": 1.3877, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.022334104434051, | |
| "learning_rate": 8.720366801238065e-07, | |
| "loss": 1.4133, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.90248743689466, | |
| "learning_rate": 8.720346901580765e-07, | |
| "loss": 1.3889, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.006981215139682, | |
| "learning_rate": 8.720326884551899e-07, | |
| "loss": 1.3657, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.996511837199606, | |
| "learning_rate": 8.720306750152005e-07, | |
| "loss": 1.3918, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9853146230235317, | |
| "learning_rate": 8.720286498381625e-07, | |
| "loss": 1.3983, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.936322205558776, | |
| "learning_rate": 8.720266129241307e-07, | |
| "loss": 1.3549, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0336499138604984, | |
| "learning_rate": 8.720245642731596e-07, | |
| "loss": 1.3614, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9761367095195514, | |
| "learning_rate": 8.720225038853046e-07, | |
| "loss": 1.4223, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.8383029378391256, | |
| "learning_rate": 8.72020431760621e-07, | |
| "loss": 1.3027, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0012216332284964, | |
| "learning_rate": 8.720183478991647e-07, | |
| "loss": 1.307, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.202220665410359, | |
| "learning_rate": 8.720162523009919e-07, | |
| "loss": 1.3495, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.926537743004413, | |
| "learning_rate": 8.720141449661587e-07, | |
| "loss": 1.346, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.025411005245412, | |
| "learning_rate": 8.720120258947223e-07, | |
| "loss": 1.3581, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.010956090798263, | |
| "learning_rate": 8.720098950867392e-07, | |
| "loss": 1.3634, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0383205174055727, | |
| "learning_rate": 8.720077525422671e-07, | |
| "loss": 1.3642, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.967895550740301, | |
| "learning_rate": 8.720055982613638e-07, | |
| "loss": 1.3841, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.9365373503076246, | |
| "learning_rate": 8.720034322440872e-07, | |
| "loss": 1.3527, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.1104370711279214, | |
| "learning_rate": 8.720012544904955e-07, | |
| "loss": 1.3483, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.952339289555111, | |
| "learning_rate": 8.719990650006473e-07, | |
| "loss": 1.3956, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.942959986729864, | |
| "learning_rate": 8.719968637746018e-07, | |
| "loss": 1.4256, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.1019407497257507, | |
| "learning_rate": 8.71994650812418e-07, | |
| "loss": 1.3786, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0501476908245984, | |
| "learning_rate": 8.719924261141557e-07, | |
| "loss": 1.4158, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9781394711393507, | |
| "learning_rate": 8.719901896798748e-07, | |
| "loss": 1.427, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0411329565229646, | |
| "learning_rate": 8.719879415096352e-07, | |
| "loss": 1.4281, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.022154009359811, | |
| "learning_rate": 8.719856816034978e-07, | |
| "loss": 1.435, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.965921869395771, | |
| "learning_rate": 8.719834099615232e-07, | |
| "loss": 1.3766, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.026938014636579, | |
| "learning_rate": 8.719811265837728e-07, | |
| "loss": 1.3612, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9969914810093115, | |
| "learning_rate": 8.719788314703078e-07, | |
| "loss": 1.3371, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.8906070169866545, | |
| "learning_rate": 8.719765246211902e-07, | |
| "loss": 1.3826, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0301378229830593, | |
| "learning_rate": 8.71974206036482e-07, | |
| "loss": 1.3937, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9673359121672145, | |
| "learning_rate": 8.719718757162457e-07, | |
| "loss": 1.3838, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.972360304451488, | |
| "learning_rate": 8.719695336605439e-07, | |
| "loss": 1.4382, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9493767886841242, | |
| "learning_rate": 8.7196717986944e-07, | |
| "loss": 1.3651, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.031661286320472, | |
| "learning_rate": 8.719648143429969e-07, | |
| "loss": 1.3482, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.920995409830151, | |
| "learning_rate": 8.719624370812787e-07, | |
| "loss": 1.4115, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.920727312220773, | |
| "learning_rate": 8.719600480843491e-07, | |
| "loss": 1.396, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.945684201201641, | |
| "learning_rate": 8.719576473522726e-07, | |
| "loss": 1.3557, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0651768014119956, | |
| "learning_rate": 8.719552348851139e-07, | |
| "loss": 1.389, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.1250149616393577, | |
| "learning_rate": 8.719528106829378e-07, | |
| "loss": 1.469, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.977539941978143, | |
| "learning_rate": 8.719503747458096e-07, | |
| "loss": 1.3536, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0745479693463924, | |
| "learning_rate": 8.71947927073795e-07, | |
| "loss": 1.3877, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.2160266553797667, | |
| "learning_rate": 8.719454676669596e-07, | |
| "loss": 1.3988, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.134783336833123, | |
| "learning_rate": 8.719429965253698e-07, | |
| "loss": 1.4104, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.908012731710042, | |
| "learning_rate": 8.719405136490924e-07, | |
| "loss": 1.4186, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9868078254055934, | |
| "learning_rate": 8.71938019038194e-07, | |
| "loss": 1.2836, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 9.747982306246115, | |
| "learning_rate": 8.719355126927416e-07, | |
| "loss": 1.3331, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9503527741257476, | |
| "learning_rate": 8.719329946128029e-07, | |
| "loss": 1.3993, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.000724848973538, | |
| "learning_rate": 8.719304647984458e-07, | |
| "loss": 1.3621, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0259025600243032, | |
| "learning_rate": 8.719279232497381e-07, | |
| "loss": 1.4128, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.95272448132235, | |
| "learning_rate": 8.719253699667485e-07, | |
| "loss": 1.4239, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.7978451838553986, | |
| "learning_rate": 8.719228049495456e-07, | |
| "loss": 1.3694, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.976459149812301, | |
| "learning_rate": 8.719202281981985e-07, | |
| "loss": 1.3413, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9711797841726377, | |
| "learning_rate": 8.719176397127765e-07, | |
| "loss": 1.3616, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0204333297285815, | |
| "learning_rate": 8.719150394933495e-07, | |
| "loss": 1.4126, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0181766925849556, | |
| "learning_rate": 8.719124275399874e-07, | |
| "loss": 1.4323, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9167139561107893, | |
| "learning_rate": 8.719098038527604e-07, | |
| "loss": 1.4484, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9378575085429013, | |
| "learning_rate": 8.719071684317393e-07, | |
| "loss": 1.3775, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.94943978740792, | |
| "learning_rate": 8.719045212769951e-07, | |
| "loss": 1.3897, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.958505276332381, | |
| "learning_rate": 8.719018623885988e-07, | |
| "loss": 1.394, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.145867503995205, | |
| "learning_rate": 8.718991917666222e-07, | |
| "loss": 1.379, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9734480635815728, | |
| "learning_rate": 8.718965094111372e-07, | |
| "loss": 1.3953, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9049260797132335, | |
| "learning_rate": 8.71893815322216e-07, | |
| "loss": 1.3827, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.98953226106279, | |
| "learning_rate": 8.718911094999311e-07, | |
| "loss": 1.3862, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.898375435464832, | |
| "learning_rate": 8.718883919443554e-07, | |
| "loss": 1.4134, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9986915176885027, | |
| "learning_rate": 8.718856626555621e-07, | |
| "loss": 1.391, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.054114308668177, | |
| "learning_rate": 8.718829216336246e-07, | |
| "loss": 1.414, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.966556344517333, | |
| "learning_rate": 8.718801688786166e-07, | |
| "loss": 1.4188, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.1040321426982134, | |
| "learning_rate": 8.718774043906126e-07, | |
| "loss": 1.3538, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0055709258768832, | |
| "learning_rate": 8.718746281696866e-07, | |
| "loss": 1.4413, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9449143169829277, | |
| "learning_rate": 8.718718402159136e-07, | |
| "loss": 1.3449, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9706428099571305, | |
| "learning_rate": 8.718690405293686e-07, | |
| "loss": 1.4158, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0814964982203112, | |
| "learning_rate": 8.718662291101268e-07, | |
| "loss": 1.3981, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.036501892302947, | |
| "learning_rate": 8.718634059582641e-07, | |
| "loss": 1.4047, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0667912243139535, | |
| "learning_rate": 8.718605710738567e-07, | |
| "loss": 1.4436, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.096788465549673, | |
| "learning_rate": 8.718577244569806e-07, | |
| "loss": 1.4332, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.031370455846918, | |
| "learning_rate": 8.718548661077125e-07, | |
| "loss": 1.3962, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9672083000240344, | |
| "learning_rate": 8.718519960261294e-07, | |
| "loss": 1.4205, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.007883947100492, | |
| "learning_rate": 8.718491142123086e-07, | |
| "loss": 1.3446, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9748300479515253, | |
| "learning_rate": 8.718462206663277e-07, | |
| "loss": 1.3854, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0397247689440396, | |
| "learning_rate": 8.718433153882645e-07, | |
| "loss": 1.4125, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.001960481680682, | |
| "learning_rate": 8.718403983781974e-07, | |
| "loss": 1.3947, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0664806351413088, | |
| "learning_rate": 8.718374696362047e-07, | |
| "loss": 1.3624, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0210504760194175, | |
| "learning_rate": 8.718345291623656e-07, | |
| "loss": 1.4671, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.971388652881855, | |
| "learning_rate": 8.718315769567588e-07, | |
| "loss": 1.3472, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.952431051174851, | |
| "learning_rate": 8.718286130194643e-07, | |
| "loss": 1.3779, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.12691241920494, | |
| "learning_rate": 8.718256373505615e-07, | |
| "loss": 1.4117, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0148285597590796, | |
| "learning_rate": 8.718226499501307e-07, | |
| "loss": 1.3676, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.98672263886442, | |
| "learning_rate": 8.718196508182523e-07, | |
| "loss": 1.4435, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.968930206941385, | |
| "learning_rate": 8.718166399550071e-07, | |
| "loss": 1.4378, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0425445228617187, | |
| "learning_rate": 8.718136173604761e-07, | |
| "loss": 1.3597, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9276879829658107, | |
| "learning_rate": 8.718105830347405e-07, | |
| "loss": 1.3689, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9317936344250413, | |
| "learning_rate": 8.718075369778825e-07, | |
| "loss": 1.3721, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9645490048095637, | |
| "learning_rate": 8.718044791899837e-07, | |
| "loss": 1.3987, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0365564821005977, | |
| "learning_rate": 8.718014096711265e-07, | |
| "loss": 1.3868, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9682770215203553, | |
| "learning_rate": 8.717983284213936e-07, | |
| "loss": 1.3415, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.134935849661195, | |
| "learning_rate": 8.717952354408679e-07, | |
| "loss": 1.3293, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.8124045479008384, | |
| "learning_rate": 8.717921307296327e-07, | |
| "loss": 1.4101, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.870855459457384, | |
| "learning_rate": 8.717890142877717e-07, | |
| "loss": 1.4129, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.996734500928963, | |
| "learning_rate": 8.717858861153686e-07, | |
| "loss": 1.4188, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.905301300393811, | |
| "learning_rate": 8.717827462125079e-07, | |
| "loss": 1.3503, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.963215198908182, | |
| "learning_rate": 8.717795945792739e-07, | |
| "loss": 1.3539, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.058342559604312, | |
| "learning_rate": 8.717764312157515e-07, | |
| "loss": 1.3911, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9650165681938128, | |
| "learning_rate": 8.717732561220258e-07, | |
| "loss": 1.4207, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9793800118049454, | |
| "learning_rate": 8.717700692981826e-07, | |
| "loss": 1.3691, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9162869272769556, | |
| "learning_rate": 8.717668707443075e-07, | |
| "loss": 1.395, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9636673086391485, | |
| "learning_rate": 8.717636604604865e-07, | |
| "loss": 1.4023, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.959298293762338, | |
| "learning_rate": 8.717604384468061e-07, | |
| "loss": 1.4328, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.965235704696395, | |
| "learning_rate": 8.717572047033532e-07, | |
| "loss": 1.4354, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.127226354296215, | |
| "learning_rate": 8.717539592302147e-07, | |
| "loss": 1.3904, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9772007199986428, | |
| "learning_rate": 8.717507020274781e-07, | |
| "loss": 1.3997, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.1654089044177103, | |
| "learning_rate": 8.717474330952311e-07, | |
| "loss": 1.3664, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.897024330171534, | |
| "learning_rate": 8.717441524335616e-07, | |
| "loss": 1.3815, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9908064118392947, | |
| "learning_rate": 8.717408600425579e-07, | |
| "loss": 1.4008, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.1674379998791475, | |
| "learning_rate": 8.717375559223089e-07, | |
| "loss": 1.4134, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.810265806813017, | |
| "learning_rate": 8.717342400729033e-07, | |
| "loss": 1.4046, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9789538191272626, | |
| "learning_rate": 8.717309124944306e-07, | |
| "loss": 1.3957, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.995888914357539, | |
| "learning_rate": 8.717275731869801e-07, | |
| "loss": 1.3823, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.94123727534938, | |
| "learning_rate": 8.71724222150642e-07, | |
| "loss": 1.3577, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.907211393678648, | |
| "learning_rate": 8.717208593855062e-07, | |
| "loss": 1.4016, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9549644446432546, | |
| "learning_rate": 8.717174848916635e-07, | |
| "loss": 1.3554, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.047404295254929, | |
| "learning_rate": 8.717140986692047e-07, | |
| "loss": 1.3977, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0015613969735218, | |
| "learning_rate": 8.717107007182211e-07, | |
| "loss": 1.4159, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.99276033713888, | |
| "learning_rate": 8.71707291038804e-07, | |
| "loss": 1.4194, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9613959661694427, | |
| "learning_rate": 8.717038696310452e-07, | |
| "loss": 1.4072, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.984569722219675, | |
| "learning_rate": 8.717004364950369e-07, | |
| "loss": 1.4018, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.927152138759416, | |
| "learning_rate": 8.716969916308715e-07, | |
| "loss": 1.4038, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0771539333400764, | |
| "learning_rate": 8.716935350386416e-07, | |
| "loss": 1.3754, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.970985940726889, | |
| "learning_rate": 8.716900667184406e-07, | |
| "loss": 1.4458, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0928065462412633, | |
| "learning_rate": 8.716865866703617e-07, | |
| "loss": 1.371, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9309896563133697, | |
| "learning_rate": 8.716830948944986e-07, | |
| "loss": 1.3509, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0455988834094736, | |
| "learning_rate": 8.716795913909452e-07, | |
| "loss": 1.3827, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.061462286190086, | |
| "learning_rate": 8.716760761597961e-07, | |
| "loss": 1.3926, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9080714574645516, | |
| "learning_rate": 8.716725492011458e-07, | |
| "loss": 1.4101, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9046604352395207, | |
| "learning_rate": 8.716690105150891e-07, | |
| "loss": 1.335, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.946411297505849, | |
| "learning_rate": 8.716654601017216e-07, | |
| "loss": 1.4109, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9811491538335915, | |
| "learning_rate": 8.716618979611386e-07, | |
| "loss": 1.4007, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.828391151750033, | |
| "learning_rate": 8.716583240934361e-07, | |
| "loss": 1.4194, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.861846008744537, | |
| "learning_rate": 8.716547384987104e-07, | |
| "loss": 1.3164, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.8751261295501274, | |
| "learning_rate": 8.716511411770581e-07, | |
| "loss": 1.4447, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.085208227054159, | |
| "learning_rate": 8.716475321285758e-07, | |
| "loss": 1.3732, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.926763955103524, | |
| "learning_rate": 8.716439113533609e-07, | |
| "loss": 1.427, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.021150407067775, | |
| "learning_rate": 8.716402788515107e-07, | |
| "loss": 1.4123, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0835953078832476, | |
| "learning_rate": 8.716366346231232e-07, | |
| "loss": 1.3225, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.084681723058033, | |
| "learning_rate": 8.716329786682964e-07, | |
| "loss": 1.4007, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9354891039496507, | |
| "learning_rate": 8.716293109871288e-07, | |
| "loss": 1.374, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.072363269165642, | |
| "learning_rate": 8.71625631579719e-07, | |
| "loss": 1.355, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9000514864569373, | |
| "learning_rate": 8.716219404461663e-07, | |
| "loss": 1.3718, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0562397719571766, | |
| "learning_rate": 8.716182375865698e-07, | |
| "loss": 1.3814, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0526646692685717, | |
| "learning_rate": 8.716145230010296e-07, | |
| "loss": 1.3772, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0966573543083538, | |
| "learning_rate": 8.716107966896452e-07, | |
| "loss": 1.4287, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0880361698977263, | |
| "learning_rate": 8.716070586525174e-07, | |
| "loss": 1.3751, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.832576232775376, | |
| "learning_rate": 8.716033088897465e-07, | |
| "loss": 1.416, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.965237748755546, | |
| "learning_rate": 8.715995474014337e-07, | |
| "loss": 1.3621, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0463957419921783, | |
| "learning_rate": 8.7159577418768e-07, | |
| "loss": 1.357, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9739015917876723, | |
| "learning_rate": 8.715919892485873e-07, | |
| "loss": 1.3873, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.8676852163892037, | |
| "learning_rate": 8.715881925842573e-07, | |
| "loss": 1.4051, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.088087320089484, | |
| "learning_rate": 8.715843841947923e-07, | |
| "loss": 1.3151, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0270665713855367, | |
| "learning_rate": 8.715805640802949e-07, | |
| "loss": 1.3679, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9869536543983366, | |
| "learning_rate": 8.715767322408678e-07, | |
| "loss": 1.3528, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9112845523257675, | |
| "learning_rate": 8.715728886766143e-07, | |
| "loss": 1.442, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0049960527344544, | |
| "learning_rate": 8.715690333876378e-07, | |
| "loss": 1.3681, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9921307040597664, | |
| "learning_rate": 8.715651663740421e-07, | |
| "loss": 1.4314, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0109768676656605, | |
| "learning_rate": 8.715612876359315e-07, | |
| "loss": 1.3847, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.039247694352697, | |
| "learning_rate": 8.715573971734103e-07, | |
| "loss": 1.4317, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.019898918932762, | |
| "learning_rate": 8.71553494986583e-07, | |
| "loss": 1.3623, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.00522079476457, | |
| "learning_rate": 8.71549581075555e-07, | |
| "loss": 1.3884, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9610972813683794, | |
| "learning_rate": 8.715456554404316e-07, | |
| "loss": 1.3315, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.967170476790787, | |
| "learning_rate": 8.715417180813185e-07, | |
| "loss": 1.4207, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9522241028635285, | |
| "learning_rate": 8.715377689983216e-07, | |
| "loss": 1.4012, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.928961724018662, | |
| "learning_rate": 8.715338081915475e-07, | |
| "loss": 1.3869, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.952221930130988, | |
| "learning_rate": 8.715298356611025e-07, | |
| "loss": 1.3703, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0536781428675335, | |
| "learning_rate": 8.715258514070937e-07, | |
| "loss": 1.3682, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.128913913582799, | |
| "learning_rate": 8.715218554296284e-07, | |
| "loss": 1.3435, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0301910736766318, | |
| "learning_rate": 8.715178477288141e-07, | |
| "loss": 1.3975, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.962217823506329, | |
| "learning_rate": 8.715138283047589e-07, | |
| "loss": 1.3488, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0039607070469647, | |
| "learning_rate": 8.715097971575708e-07, | |
| "loss": 1.378, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0602288102993938, | |
| "learning_rate": 8.715057542873585e-07, | |
| "loss": 1.3572, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.969434960629606, | |
| "learning_rate": 8.715016996942307e-07, | |
| "loss": 1.3713, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9917667276430477, | |
| "learning_rate": 8.714976333782967e-07, | |
| "loss": 1.4607, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.2046134996002436, | |
| "learning_rate": 8.714935553396659e-07, | |
| "loss": 1.3853, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.1097764355868733, | |
| "learning_rate": 8.714894655784481e-07, | |
| "loss": 1.371, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9715612348659124, | |
| "learning_rate": 8.714853640947534e-07, | |
| "loss": 1.392, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9321597700386333, | |
| "learning_rate": 8.714812508886925e-07, | |
| "loss": 1.4051, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.949095796893927, | |
| "learning_rate": 8.714771259603758e-07, | |
| "loss": 1.3469, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9290487074046756, | |
| "learning_rate": 8.714729893099144e-07, | |
| "loss": 1.3629, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0295532590400196, | |
| "learning_rate": 8.714688409374198e-07, | |
| "loss": 1.3689, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.965897130998238, | |
| "learning_rate": 8.714646808430036e-07, | |
| "loss": 1.3619, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0935335333535336, | |
| "learning_rate": 8.714605090267779e-07, | |
| "loss": 1.3781, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.986770714363214, | |
| "learning_rate": 8.71456325488855e-07, | |
| "loss": 1.364, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.950553960144967, | |
| "learning_rate": 8.714521302293475e-07, | |
| "loss": 1.4063, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.014174300238565, | |
| "learning_rate": 8.714479232483683e-07, | |
| "loss": 1.3676, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.24671603526281, | |
| "learning_rate": 8.714437045460308e-07, | |
| "loss": 1.3578, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.1623556544347724, | |
| "learning_rate": 8.714394741224484e-07, | |
| "loss": 1.3645, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0025864567325122, | |
| "learning_rate": 8.714352319777354e-07, | |
| "loss": 1.3607, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.94717894620833, | |
| "learning_rate": 8.714309781120056e-07, | |
| "loss": 1.3498, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.8964926477515935, | |
| "learning_rate": 8.714267125253735e-07, | |
| "loss": 1.3728, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.1656664213505823, | |
| "learning_rate": 8.714224352179544e-07, | |
| "loss": 1.4176, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.020188270295796, | |
| "learning_rate": 8.71418146189863e-07, | |
| "loss": 1.4194, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.978569270321128, | |
| "learning_rate": 8.71413845441215e-07, | |
| "loss": 1.3749, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9396855197827283, | |
| "learning_rate": 8.714095329721261e-07, | |
| "loss": 1.3795, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9422669465457387, | |
| "learning_rate": 8.714052087827125e-07, | |
| "loss": 1.3834, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.010282715520298, | |
| "learning_rate": 8.714008728730907e-07, | |
| "loss": 1.3531, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9717500175741116, | |
| "learning_rate": 8.713965252433773e-07, | |
| "loss": 1.3667, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.052704318228861, | |
| "learning_rate": 8.713921658936892e-07, | |
| "loss": 1.3456, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.528710625831412, | |
| "learning_rate": 8.713877948241442e-07, | |
| "loss": 1.3936, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.9466834730933833, | |
| "learning_rate": 8.713834120348596e-07, | |
| "loss": 1.3217, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0996541898765226, | |
| "learning_rate": 8.713790175259536e-07, | |
| "loss": 1.3855, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.982252067970699, | |
| "learning_rate": 8.713746112975446e-07, | |
| "loss": 1.384, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.1109077626663844, | |
| "learning_rate": 8.713701933497509e-07, | |
| "loss": 1.3561, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0394061264038115, | |
| "learning_rate": 8.713657636826918e-07, | |
| "loss": 1.468, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0969706383479, | |
| "learning_rate": 8.713613222964863e-07, | |
| "loss": 1.3993, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0348133446475662, | |
| "learning_rate": 8.713568691912542e-07, | |
| "loss": 1.387, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.0273826285615195, | |
| "learning_rate": 8.713524043671153e-07, | |
| "loss": 1.3959, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.141130816615921, | |
| "learning_rate": 8.713479278241898e-07, | |
| "loss": 1.4479, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0490824173681945, | |
| "learning_rate": 8.713434395625983e-07, | |
| "loss": 1.3583, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9474474845957404, | |
| "learning_rate": 8.713389395824614e-07, | |
| "loss": 1.3344, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9486918699061118, | |
| "learning_rate": 8.713344278839005e-07, | |
| "loss": 1.4022, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9302492343255344, | |
| "learning_rate": 8.71329904467037e-07, | |
| "loss": 1.3344, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9531126631866753, | |
| "learning_rate": 8.713253693319929e-07, | |
| "loss": 1.3451, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.8555050387157213, | |
| "learning_rate": 8.713208224788899e-07, | |
| "loss": 1.3287, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0850474903019305, | |
| "learning_rate": 8.713162639078507e-07, | |
| "loss": 1.4153, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9916349483264004, | |
| "learning_rate": 8.71311693618998e-07, | |
| "loss": 1.4025, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0448173115664545, | |
| "learning_rate": 8.713071116124549e-07, | |
| "loss": 1.4129, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9652773442800022, | |
| "learning_rate": 8.713025178883445e-07, | |
| "loss": 1.3688, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.8707509231071127, | |
| "learning_rate": 8.712979124467906e-07, | |
| "loss": 1.3714, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.968740384281211, | |
| "learning_rate": 8.712932952879176e-07, | |
| "loss": 1.4012, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.938361663169202, | |
| "learning_rate": 8.712886664118492e-07, | |
| "loss": 1.406, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.1217977871072775, | |
| "learning_rate": 8.712840258187104e-07, | |
| "loss": 1.3822, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9353035115177915, | |
| "learning_rate": 8.71279373508626e-07, | |
| "loss": 1.3578, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.014072001165337, | |
| "learning_rate": 8.712747094817213e-07, | |
| "loss": 1.4454, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.969346395207918, | |
| "learning_rate": 8.71270033738122e-07, | |
| "loss": 1.3705, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.050484611788353, | |
| "learning_rate": 8.712653462779539e-07, | |
| "loss": 1.3551, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.940761479764165, | |
| "learning_rate": 8.71260647101343e-07, | |
| "loss": 1.4147, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9928956127151944, | |
| "learning_rate": 8.712559362084161e-07, | |
| "loss": 1.3604, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0125472864930805, | |
| "learning_rate": 8.712512135993e-07, | |
| "loss": 1.4183, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.940381713821346, | |
| "learning_rate": 8.712464792741218e-07, | |
| "loss": 1.4414, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0279511535103336, | |
| "learning_rate": 8.712417332330089e-07, | |
| "loss": 1.3505, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9922191158837954, | |
| "learning_rate": 8.712369754760892e-07, | |
| "loss": 1.4028, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0184990677208834, | |
| "learning_rate": 8.712322060034907e-07, | |
| "loss": 1.3465, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.05423073796875, | |
| "learning_rate": 8.712274248153418e-07, | |
| "loss": 1.3416, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.1326601737410025, | |
| "learning_rate": 8.712226319117715e-07, | |
| "loss": 1.3924, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.995785462842688, | |
| "learning_rate": 8.712178272929084e-07, | |
| "loss": 1.3895, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9760799944825806, | |
| "learning_rate": 8.712130109588823e-07, | |
| "loss": 1.4104, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9654696172148896, | |
| "learning_rate": 8.712081829098225e-07, | |
| "loss": 1.378, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9968608921090265, | |
| "learning_rate": 8.712033431458593e-07, | |
| "loss": 1.4264, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.969211803711655, | |
| "learning_rate": 8.711984916671229e-07, | |
| "loss": 1.3607, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.942118444739339, | |
| "learning_rate": 8.711936284737438e-07, | |
| "loss": 1.3899, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.98791974032871, | |
| "learning_rate": 8.711887535658529e-07, | |
| "loss": 1.3459, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9216444622419537, | |
| "learning_rate": 8.711838669435818e-07, | |
| "loss": 1.4116, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9987312946412206, | |
| "learning_rate": 8.711789686070618e-07, | |
| "loss": 1.4126, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9997602427201926, | |
| "learning_rate": 8.711740585564249e-07, | |
| "loss": 1.3392, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9736815652309683, | |
| "learning_rate": 8.711691367918032e-07, | |
| "loss": 1.3483, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0854886077878487, | |
| "learning_rate": 8.711642033133292e-07, | |
| "loss": 1.3842, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.061838785099914, | |
| "learning_rate": 8.711592581211358e-07, | |
| "loss": 1.3658, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.023168820723632, | |
| "learning_rate": 8.711543012153561e-07, | |
| "loss": 1.3929, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.970076769155023, | |
| "learning_rate": 8.711493325961236e-07, | |
| "loss": 1.3587, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.002070690376611, | |
| "learning_rate": 8.71144352263572e-07, | |
| "loss": 1.367, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.995354883459173, | |
| "learning_rate": 8.711393602178357e-07, | |
| "loss": 1.4185, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 24.26995863156332, | |
| "learning_rate": 8.711343564590487e-07, | |
| "loss": 1.3982, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.065387181865347, | |
| "learning_rate": 8.711293409873459e-07, | |
| "loss": 1.3668, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.965733738900826, | |
| "learning_rate": 8.711243138028624e-07, | |
| "loss": 1.3989, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.909922562005101, | |
| "learning_rate": 8.711192749057334e-07, | |
| "loss": 1.3548, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9485719715840824, | |
| "learning_rate": 8.711142242960946e-07, | |
| "loss": 1.3982, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0587521051463598, | |
| "learning_rate": 8.711091619740822e-07, | |
| "loss": 1.4208, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.016741791642564, | |
| "learning_rate": 8.711040879398322e-07, | |
| "loss": 1.3776, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.087201787399773, | |
| "learning_rate": 8.710990021934814e-07, | |
| "loss": 1.3509, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.1398002317055873, | |
| "learning_rate": 8.710939047351665e-07, | |
| "loss": 1.4054, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.003141522348306, | |
| "learning_rate": 8.710887955650252e-07, | |
| "loss": 1.3895, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0461324715788862, | |
| "learning_rate": 8.710836746831946e-07, | |
| "loss": 1.4143, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.956952816424475, | |
| "learning_rate": 8.710785420898127e-07, | |
| "loss": 1.4008, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.8987555743390168, | |
| "learning_rate": 8.710733977850179e-07, | |
| "loss": 1.3823, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0536968376300284, | |
| "learning_rate": 8.710682417689485e-07, | |
| "loss": 1.4578, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.969066979149947, | |
| "learning_rate": 8.710630740417435e-07, | |
| "loss": 1.428, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.1272335317584905, | |
| "learning_rate": 8.710578946035417e-07, | |
| "loss": 1.3562, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9753498641377742, | |
| "learning_rate": 8.710527034544828e-07, | |
| "loss": 1.3953, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.943913278878306, | |
| "learning_rate": 8.710475005947067e-07, | |
| "loss": 1.3626, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9513572324834727, | |
| "learning_rate": 8.710422860243531e-07, | |
| "loss": 1.3461, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0849634901753284, | |
| "learning_rate": 8.710370597435629e-07, | |
| "loss": 1.3663, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.138354533416878, | |
| "learning_rate": 8.710318217524763e-07, | |
| "loss": 1.3141, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.972312260895404, | |
| "learning_rate": 8.710265720512346e-07, | |
| "loss": 1.3633, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0591517440498097, | |
| "learning_rate": 8.710213106399791e-07, | |
| "loss": 1.3557, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.8524186182545987, | |
| "learning_rate": 8.710160375188516e-07, | |
| "loss": 1.3676, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9822890833732956, | |
| "learning_rate": 8.710107526879938e-07, | |
| "loss": 1.4331, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9176351551822868, | |
| "learning_rate": 8.710054561475481e-07, | |
| "loss": 1.371, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.94388048856757, | |
| "learning_rate": 8.71000147897657e-07, | |
| "loss": 1.393, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.085541520730895, | |
| "learning_rate": 8.709948279384639e-07, | |
| "loss": 1.3937, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9491352117439757, | |
| "learning_rate": 8.709894962701115e-07, | |
| "loss": 1.3526, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9933004115427444, | |
| "learning_rate": 8.709841528927436e-07, | |
| "loss": 1.3916, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.959458221957766, | |
| "learning_rate": 8.70978797806504e-07, | |
| "loss": 1.3462, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.963203467802987, | |
| "learning_rate": 8.709734310115368e-07, | |
| "loss": 1.3783, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9902951999179312, | |
| "learning_rate": 8.709680525079866e-07, | |
| "loss": 1.362, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.948654339418917, | |
| "learning_rate": 8.709626622959983e-07, | |
| "loss": 1.3841, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.001564005849718, | |
| "learning_rate": 8.709572603757169e-07, | |
| "loss": 1.3572, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0380595324448416, | |
| "learning_rate": 8.709518467472878e-07, | |
| "loss": 1.4171, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.896631790474921, | |
| "learning_rate": 8.709464214108568e-07, | |
| "loss": 1.3448, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9319635944784475, | |
| "learning_rate": 8.709409843665701e-07, | |
| "loss": 1.3917, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.963100470234962, | |
| "learning_rate": 8.709355356145739e-07, | |
| "loss": 1.3655, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.030553118915969, | |
| "learning_rate": 8.709300751550151e-07, | |
| "loss": 1.3365, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.4928530382016887, | |
| "learning_rate": 8.709246029880405e-07, | |
| "loss": 1.3662, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.030669221337684, | |
| "learning_rate": 8.709191191137976e-07, | |
| "loss": 1.4529, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.155457882933603, | |
| "learning_rate": 8.70913623532434e-07, | |
| "loss": 1.4022, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9856956704586115, | |
| "learning_rate": 8.709081162440975e-07, | |
| "loss": 1.3989, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9343339295028015, | |
| "learning_rate": 8.709025972489367e-07, | |
| "loss": 1.4212, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.1952129991940543, | |
| "learning_rate": 8.708970665471e-07, | |
| "loss": 1.4436, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.015106319776789, | |
| "learning_rate": 8.708915241387364e-07, | |
| "loss": 1.4422, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.022781702862628, | |
| "learning_rate": 8.708859700239951e-07, | |
| "loss": 1.3789, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.932454535389442, | |
| "learning_rate": 8.708804042030254e-07, | |
| "loss": 1.3783, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.1075106961875165, | |
| "learning_rate": 8.708748266759774e-07, | |
| "loss": 1.3904, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.8613959925148356, | |
| "learning_rate": 8.708692374430014e-07, | |
| "loss": 1.3701, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9916282178733447, | |
| "learning_rate": 8.708636365042476e-07, | |
| "loss": 1.3517, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.8578706799379554, | |
| "learning_rate": 8.70858023859867e-07, | |
| "loss": 1.4124, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0055644119433533, | |
| "learning_rate": 8.708523995100105e-07, | |
| "loss": 1.3869, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.027942807639001, | |
| "learning_rate": 8.708467634548298e-07, | |
| "loss": 1.3703, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.1584010302430836, | |
| "learning_rate": 8.708411156944765e-07, | |
| "loss": 1.3852, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.08434624814754, | |
| "learning_rate": 8.708354562291027e-07, | |
| "loss": 1.4008, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.937949504985518, | |
| "learning_rate": 8.708297850588607e-07, | |
| "loss": 1.4026, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0080974250898116, | |
| "learning_rate": 8.708241021839032e-07, | |
| "loss": 1.3992, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.986930909094618, | |
| "learning_rate": 8.708184076043833e-07, | |
| "loss": 1.3504, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.1912323292885363, | |
| "learning_rate": 8.708127013204543e-07, | |
| "loss": 1.3919, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.203030731079236, | |
| "learning_rate": 8.708069833322698e-07, | |
| "loss": 1.3601, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.097916109715531, | |
| "learning_rate": 8.708012536399837e-07, | |
| "loss": 1.3619, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0656903032705327, | |
| "learning_rate": 8.707955122437504e-07, | |
| "loss": 1.3162, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.002875260439292, | |
| "learning_rate": 8.707897591437243e-07, | |
| "loss": 1.389, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0143271490705077, | |
| "learning_rate": 8.707839943400606e-07, | |
| "loss": 1.3323, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.096313689982386, | |
| "learning_rate": 8.707782178329142e-07, | |
| "loss": 1.3813, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.960471861335116, | |
| "learning_rate": 8.707724296224408e-07, | |
| "loss": 1.3472, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0072247729027115, | |
| "learning_rate": 8.707666297087963e-07, | |
| "loss": 1.3522, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.949063388714746, | |
| "learning_rate": 8.707608180921366e-07, | |
| "loss": 1.3928, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.1121870350751064, | |
| "learning_rate": 8.707549947726183e-07, | |
| "loss": 1.4399, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9609559500955003, | |
| "learning_rate": 8.707491597503982e-07, | |
| "loss": 1.3898, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9585328248619587, | |
| "learning_rate": 8.707433130256336e-07, | |
| "loss": 1.379, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.918687510312111, | |
| "learning_rate": 8.707374545984816e-07, | |
| "loss": 1.4176, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.15488138702356, | |
| "learning_rate": 8.707315844691002e-07, | |
| "loss": 1.3706, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9610415881399677, | |
| "learning_rate": 8.707257026376471e-07, | |
| "loss": 1.3641, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0862098441133234, | |
| "learning_rate": 8.707198091042811e-07, | |
| "loss": 1.3893, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9328888264242106, | |
| "learning_rate": 8.707139038691606e-07, | |
| "loss": 1.333, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.97580891347495, | |
| "learning_rate": 8.707079869324446e-07, | |
| "loss": 1.3607, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.000962296933563, | |
| "learning_rate": 8.707020582942925e-07, | |
| "loss": 1.424, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.984700606909975, | |
| "learning_rate": 8.706961179548639e-07, | |
| "loss": 1.3912, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.998907818017932, | |
| "learning_rate": 8.706901659143189e-07, | |
| "loss": 1.4241, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.95254670370234, | |
| "learning_rate": 8.706842021728173e-07, | |
| "loss": 1.3759, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.134652976665768, | |
| "learning_rate": 8.706782267305202e-07, | |
| "loss": 1.3767, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.972318633221704, | |
| "learning_rate": 8.706722395875881e-07, | |
| "loss": 1.3648, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.8607560362869124, | |
| "learning_rate": 8.706662407441824e-07, | |
| "loss": 1.3946, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.8921206621422653, | |
| "learning_rate": 8.706602302004645e-07, | |
| "loss": 1.4396, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.949264928829496, | |
| "learning_rate": 8.706542079565962e-07, | |
| "loss": 1.3475, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.996499503605724, | |
| "learning_rate": 8.706481740127399e-07, | |
| "loss": 1.37, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9235932803770868, | |
| "learning_rate": 8.706421283690578e-07, | |
| "loss": 1.2987, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0655234851680824, | |
| "learning_rate": 8.706360710257128e-07, | |
| "loss": 1.3903, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.968020759665533, | |
| "learning_rate": 8.706300019828679e-07, | |
| "loss": 1.4227, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.116571254583397, | |
| "learning_rate": 8.706239212406866e-07, | |
| "loss": 1.4153, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0578559650775383, | |
| "learning_rate": 8.706178287993326e-07, | |
| "loss": 1.4168, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9399476742786907, | |
| "learning_rate": 8.706117246589699e-07, | |
| "loss": 1.3448, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.045715774895227, | |
| "learning_rate": 8.706056088197628e-07, | |
| "loss": 1.4323, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.8892619986413655, | |
| "learning_rate": 8.705994812818759e-07, | |
| "loss": 1.3688, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0537421060657257, | |
| "learning_rate": 8.705933420454745e-07, | |
| "loss": 1.2805, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.02315805498333, | |
| "learning_rate": 8.705871911107236e-07, | |
| "loss": 1.3664, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0968669538104705, | |
| "learning_rate": 8.70581028477789e-07, | |
| "loss": 1.4156, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.958411205891844, | |
| "learning_rate": 8.705748541468365e-07, | |
| "loss": 1.3879, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0644896141269213, | |
| "learning_rate": 8.705686681180324e-07, | |
| "loss": 1.406, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.9355330340666947, | |
| "learning_rate": 8.705624703915431e-07, | |
| "loss": 1.4157, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.0295134625264732, | |
| "learning_rate": 8.705562609675357e-07, | |
| "loss": 1.3595, | |
| "step": 630 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 19246, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 105, | |
| "total_flos": 164886478848000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |