| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.989308624376337, | |
| "eval_steps": 500, | |
| "global_step": 875, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005702066999287242, | |
| "grad_norm": 884.3019409179688, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 12.0862, | |
| "num_input_tokens_seen": 6368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011404133998574484, | |
| "grad_norm": 843.7129516601562, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 12.1914, | |
| "num_input_tokens_seen": 12384, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017106200997861726, | |
| "grad_norm": 838.2268676757812, | |
| "learning_rate": 1.5e-06, | |
| "loss": 11.9748, | |
| "num_input_tokens_seen": 18624, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022808267997148968, | |
| "grad_norm": 757.4126586914062, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 11.5009, | |
| "num_input_tokens_seen": 25488, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02851033499643621, | |
| "grad_norm": 627.78759765625, | |
| "learning_rate": 2.5e-06, | |
| "loss": 8.7827, | |
| "num_input_tokens_seen": 32368, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03421240199572345, | |
| "grad_norm": 409.04754638671875, | |
| "learning_rate": 3e-06, | |
| "loss": 6.5054, | |
| "num_input_tokens_seen": 39008, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03991446899501069, | |
| "grad_norm": 373.82159423828125, | |
| "learning_rate": 3.5e-06, | |
| "loss": 5.2127, | |
| "num_input_tokens_seen": 45984, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.045616535994297935, | |
| "grad_norm": 351.687744140625, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.749, | |
| "num_input_tokens_seen": 52656, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05131860299358518, | |
| "grad_norm": 278.171875, | |
| "learning_rate": 4.5e-06, | |
| "loss": 1.0344, | |
| "num_input_tokens_seen": 59408, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05702066999287242, | |
| "grad_norm": 309.93524169921875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6484, | |
| "num_input_tokens_seen": 66096, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06272273699215966, | |
| "grad_norm": 360.1611633300781, | |
| "learning_rate": 4.999983511654997e-06, | |
| "loss": 1.8744, | |
| "num_input_tokens_seen": 72592, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0684248039914469, | |
| "grad_norm": 90.9323501586914, | |
| "learning_rate": 4.999934046837479e-06, | |
| "loss": 0.4507, | |
| "num_input_tokens_seen": 79456, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07412687099073414, | |
| "grad_norm": 303.21185302734375, | |
| "learning_rate": 4.99985160619992e-06, | |
| "loss": 1.6065, | |
| "num_input_tokens_seen": 86016, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07982893799002139, | |
| "grad_norm": 264.76409912109375, | |
| "learning_rate": 4.99973619082977e-06, | |
| "loss": 1.647, | |
| "num_input_tokens_seen": 92336, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08553100498930863, | |
| "grad_norm": 102.49153137207031, | |
| "learning_rate": 4.999587802249433e-06, | |
| "loss": 0.4799, | |
| "num_input_tokens_seen": 99120, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09123307198859587, | |
| "grad_norm": 128.62033081054688, | |
| "learning_rate": 4.999406442416258e-06, | |
| "loss": 0.5683, | |
| "num_input_tokens_seen": 105712, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09693513898788311, | |
| "grad_norm": 137.42129516601562, | |
| "learning_rate": 4.9991921137225e-06, | |
| "loss": 1.1372, | |
| "num_input_tokens_seen": 112480, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10263720598717035, | |
| "grad_norm": 11.351543426513672, | |
| "learning_rate": 4.998944818995301e-06, | |
| "loss": 0.3574, | |
| "num_input_tokens_seen": 119136, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1083392729864576, | |
| "grad_norm": 27.159238815307617, | |
| "learning_rate": 4.9986645614966465e-06, | |
| "loss": 0.3492, | |
| "num_input_tokens_seen": 125632, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11404133998574484, | |
| "grad_norm": 111.3335952758789, | |
| "learning_rate": 4.998351344923323e-06, | |
| "loss": 1.0766, | |
| "num_input_tokens_seen": 132208, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11974340698503208, | |
| "grad_norm": 41.73637771606445, | |
| "learning_rate": 4.998005173406865e-06, | |
| "loss": 0.3635, | |
| "num_input_tokens_seen": 138624, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12544547398431932, | |
| "grad_norm": 131.07913208007812, | |
| "learning_rate": 4.997626051513512e-06, | |
| "loss": 1.5452, | |
| "num_input_tokens_seen": 145056, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13114754098360656, | |
| "grad_norm": 85.91304779052734, | |
| "learning_rate": 4.997213984244138e-06, | |
| "loss": 0.9203, | |
| "num_input_tokens_seen": 151696, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1368496079828938, | |
| "grad_norm": 31.326322555541992, | |
| "learning_rate": 4.9967689770341885e-06, | |
| "loss": 0.3603, | |
| "num_input_tokens_seen": 158080, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14255167498218105, | |
| "grad_norm": 81.54974365234375, | |
| "learning_rate": 4.996291035753608e-06, | |
| "loss": 0.7598, | |
| "num_input_tokens_seen": 164560, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1482537419814683, | |
| "grad_norm": 65.69086456298828, | |
| "learning_rate": 4.995780166706768e-06, | |
| "loss": 0.5039, | |
| "num_input_tokens_seen": 171296, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.15395580898075553, | |
| "grad_norm": 63.37894821166992, | |
| "learning_rate": 4.995236376632373e-06, | |
| "loss": 0.4744, | |
| "num_input_tokens_seen": 177696, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.15965787598004277, | |
| "grad_norm": 32.942325592041016, | |
| "learning_rate": 4.994659672703384e-06, | |
| "loss": 0.3387, | |
| "num_input_tokens_seen": 184384, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.16535994297933002, | |
| "grad_norm": 27.978893280029297, | |
| "learning_rate": 4.994050062526915e-06, | |
| "loss": 0.3363, | |
| "num_input_tokens_seen": 190736, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.17106200997861726, | |
| "grad_norm": 25.147125244140625, | |
| "learning_rate": 4.993407554144137e-06, | |
| "loss": 0.2842, | |
| "num_input_tokens_seen": 197328, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1767640769779045, | |
| "grad_norm": 17.1385498046875, | |
| "learning_rate": 4.992732156030169e-06, | |
| "loss": 0.2779, | |
| "num_input_tokens_seen": 204096, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.18246614397719174, | |
| "grad_norm": 20.462833404541016, | |
| "learning_rate": 4.992023877093969e-06, | |
| "loss": 0.242, | |
| "num_input_tokens_seen": 210432, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.18816821097647898, | |
| "grad_norm": 18.327606201171875, | |
| "learning_rate": 4.991282726678215e-06, | |
| "loss": 0.2279, | |
| "num_input_tokens_seen": 217072, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19387027797576623, | |
| "grad_norm": 8.27484130859375, | |
| "learning_rate": 4.990508714559182e-06, | |
| "loss": 0.1862, | |
| "num_input_tokens_seen": 223680, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.19957234497505347, | |
| "grad_norm": 26.527591705322266, | |
| "learning_rate": 4.989701850946613e-06, | |
| "loss": 0.2974, | |
| "num_input_tokens_seen": 230272, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2052744119743407, | |
| "grad_norm": 6.094027519226074, | |
| "learning_rate": 4.988862146483585e-06, | |
| "loss": 0.182, | |
| "num_input_tokens_seen": 236912, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.21097647897362795, | |
| "grad_norm": 13.250824928283691, | |
| "learning_rate": 4.9879896122463675e-06, | |
| "loss": 0.1516, | |
| "num_input_tokens_seen": 243424, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2166785459729152, | |
| "grad_norm": 7.909171104431152, | |
| "learning_rate": 4.987084259744276e-06, | |
| "loss": 0.2325, | |
| "num_input_tokens_seen": 250288, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.22238061297220243, | |
| "grad_norm": 5.98098611831665, | |
| "learning_rate": 4.986146100919522e-06, | |
| "loss": 0.1389, | |
| "num_input_tokens_seen": 256640, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.22808267997148968, | |
| "grad_norm": 10.780566215515137, | |
| "learning_rate": 4.985175148147057e-06, | |
| "loss": 0.2076, | |
| "num_input_tokens_seen": 263360, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23378474697077692, | |
| "grad_norm": 11.498775482177734, | |
| "learning_rate": 4.9841714142344015e-06, | |
| "loss": 0.1476, | |
| "num_input_tokens_seen": 270304, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.23948681397006416, | |
| "grad_norm": 9.130556106567383, | |
| "learning_rate": 4.9831349124214855e-06, | |
| "loss": 0.159, | |
| "num_input_tokens_seen": 276752, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2451888809693514, | |
| "grad_norm": 17.099760055541992, | |
| "learning_rate": 4.982065656380468e-06, | |
| "loss": 0.1761, | |
| "num_input_tokens_seen": 283296, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.25089094796863864, | |
| "grad_norm": 7.222073554992676, | |
| "learning_rate": 4.980963660215561e-06, | |
| "loss": 0.1581, | |
| "num_input_tokens_seen": 289888, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.25659301496792586, | |
| "grad_norm": 8.980274200439453, | |
| "learning_rate": 4.979828938462836e-06, | |
| "loss": 0.1454, | |
| "num_input_tokens_seen": 296528, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 23.71878433227539, | |
| "learning_rate": 4.9786615060900415e-06, | |
| "loss": 0.1823, | |
| "num_input_tokens_seen": 303216, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.26799714896650034, | |
| "grad_norm": 26.473339080810547, | |
| "learning_rate": 4.9774613784964e-06, | |
| "loss": 0.2675, | |
| "num_input_tokens_seen": 309968, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2736992159657876, | |
| "grad_norm": 11.917190551757812, | |
| "learning_rate": 4.976228571512405e-06, | |
| "loss": 0.1482, | |
| "num_input_tokens_seen": 316512, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2794012829650748, | |
| "grad_norm": 9.98794937133789, | |
| "learning_rate": 4.9749631013996146e-06, | |
| "loss": 0.1258, | |
| "num_input_tokens_seen": 323008, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2851033499643621, | |
| "grad_norm": 17.47338104248047, | |
| "learning_rate": 4.973664984850435e-06, | |
| "loss": 0.1921, | |
| "num_input_tokens_seen": 329888, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2908054169636493, | |
| "grad_norm": 18.32182502746582, | |
| "learning_rate": 4.9723342389879e-06, | |
| "loss": 0.1491, | |
| "num_input_tokens_seen": 336480, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2965074839629366, | |
| "grad_norm": 10.995071411132812, | |
| "learning_rate": 4.970970881365449e-06, | |
| "loss": 0.1186, | |
| "num_input_tokens_seen": 342992, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3022095509622238, | |
| "grad_norm": 15.977797508239746, | |
| "learning_rate": 4.96957492996669e-06, | |
| "loss": 0.2011, | |
| "num_input_tokens_seen": 349776, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.30791161796151106, | |
| "grad_norm": 5.898417949676514, | |
| "learning_rate": 4.968146403205164e-06, | |
| "loss": 0.1301, | |
| "num_input_tokens_seen": 356432, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3136136849607983, | |
| "grad_norm": 10.29259967803955, | |
| "learning_rate": 4.966685319924105e-06, | |
| "loss": 0.1563, | |
| "num_input_tokens_seen": 362592, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.31931575196008555, | |
| "grad_norm": 12.916869163513184, | |
| "learning_rate": 4.965191699396192e-06, | |
| "loss": 0.1667, | |
| "num_input_tokens_seen": 369040, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.32501781895937276, | |
| "grad_norm": 6.394758701324463, | |
| "learning_rate": 4.9636655613232866e-06, | |
| "loss": 0.134, | |
| "num_input_tokens_seen": 375552, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.33071988595866003, | |
| "grad_norm": 4.55596399307251, | |
| "learning_rate": 4.962106925836182e-06, | |
| "loss": 0.1753, | |
| "num_input_tokens_seen": 382304, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.33642195295794725, | |
| "grad_norm": 5.786614418029785, | |
| "learning_rate": 4.960515813494335e-06, | |
| "loss": 0.1381, | |
| "num_input_tokens_seen": 388960, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.3421240199572345, | |
| "grad_norm": 3.520648956298828, | |
| "learning_rate": 4.958892245285594e-06, | |
| "loss": 0.0927, | |
| "num_input_tokens_seen": 395888, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 6.477549076080322, | |
| "learning_rate": 4.957236242625918e-06, | |
| "loss": 0.1608, | |
| "num_input_tokens_seen": 402432, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.353528153955809, | |
| "grad_norm": 8.49998664855957, | |
| "learning_rate": 4.955547827359103e-06, | |
| "loss": 0.1219, | |
| "num_input_tokens_seen": 408832, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.3592302209550962, | |
| "grad_norm": 7.314529895782471, | |
| "learning_rate": 4.953827021756489e-06, | |
| "loss": 0.1674, | |
| "num_input_tokens_seen": 415232, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3649322879543835, | |
| "grad_norm": 8.064135551452637, | |
| "learning_rate": 4.952073848516663e-06, | |
| "loss": 0.1413, | |
| "num_input_tokens_seen": 421536, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.3706343549536707, | |
| "grad_norm": 6.086092472076416, | |
| "learning_rate": 4.950288330765167e-06, | |
| "loss": 0.1515, | |
| "num_input_tokens_seen": 428176, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.37633642195295797, | |
| "grad_norm": 5.5795063972473145, | |
| "learning_rate": 4.948470492054186e-06, | |
| "loss": 0.1904, | |
| "num_input_tokens_seen": 434592, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3820384889522452, | |
| "grad_norm": 4.6880879402160645, | |
| "learning_rate": 4.946620356362243e-06, | |
| "loss": 0.1283, | |
| "num_input_tokens_seen": 440912, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.38774055595153245, | |
| "grad_norm": 13.155076026916504, | |
| "learning_rate": 4.944737948093876e-06, | |
| "loss": 0.1686, | |
| "num_input_tokens_seen": 447232, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.39344262295081966, | |
| "grad_norm": 3.164670467376709, | |
| "learning_rate": 4.942823292079325e-06, | |
| "loss": 0.1451, | |
| "num_input_tokens_seen": 453920, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.39914468995010693, | |
| "grad_norm": 15.198010444641113, | |
| "learning_rate": 4.9408764135741955e-06, | |
| "loss": 0.1635, | |
| "num_input_tokens_seen": 460320, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.40484675694939415, | |
| "grad_norm": 7.284903049468994, | |
| "learning_rate": 4.9388973382591325e-06, | |
| "loss": 0.1182, | |
| "num_input_tokens_seen": 466816, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4105488239486814, | |
| "grad_norm": 7.4862799644470215, | |
| "learning_rate": 4.936886092239475e-06, | |
| "loss": 0.1328, | |
| "num_input_tokens_seen": 473488, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.41625089094796863, | |
| "grad_norm": 4.4039435386657715, | |
| "learning_rate": 4.9348427020449206e-06, | |
| "loss": 0.1312, | |
| "num_input_tokens_seen": 480592, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4219529579472559, | |
| "grad_norm": 7.053802967071533, | |
| "learning_rate": 4.932767194629164e-06, | |
| "loss": 0.1439, | |
| "num_input_tokens_seen": 487584, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.4276550249465431, | |
| "grad_norm": 6.4606709480285645, | |
| "learning_rate": 4.9306595973695545e-06, | |
| "loss": 0.1534, | |
| "num_input_tokens_seen": 494400, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4333570919458304, | |
| "grad_norm": 8.80456256866455, | |
| "learning_rate": 4.928519938066723e-06, | |
| "loss": 0.1159, | |
| "num_input_tokens_seen": 500624, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.4390591589451176, | |
| "grad_norm": 5.863775253295898, | |
| "learning_rate": 4.926348244944221e-06, | |
| "loss": 0.1291, | |
| "num_input_tokens_seen": 507168, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.44476122594440487, | |
| "grad_norm": 6.417506217956543, | |
| "learning_rate": 4.924144546648151e-06, | |
| "loss": 0.145, | |
| "num_input_tokens_seen": 513968, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.4504632929436921, | |
| "grad_norm": 4.409994602203369, | |
| "learning_rate": 4.9219088722467825e-06, | |
| "loss": 0.1155, | |
| "num_input_tokens_seen": 520432, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.45616535994297935, | |
| "grad_norm": 4.534794330596924, | |
| "learning_rate": 4.91964125123017e-06, | |
| "loss": 0.1153, | |
| "num_input_tokens_seen": 527392, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.46186742694226657, | |
| "grad_norm": 20.643110275268555, | |
| "learning_rate": 4.917341713509772e-06, | |
| "loss": 0.1673, | |
| "num_input_tokens_seen": 533712, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.46756949394155384, | |
| "grad_norm": 27.360891342163086, | |
| "learning_rate": 4.915010289418042e-06, | |
| "loss": 0.2122, | |
| "num_input_tokens_seen": 540544, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.47327156094084105, | |
| "grad_norm": 13.000382423400879, | |
| "learning_rate": 4.912647009708041e-06, | |
| "loss": 0.1092, | |
| "num_input_tokens_seen": 546832, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.4789736279401283, | |
| "grad_norm": 5.801584720611572, | |
| "learning_rate": 4.910251905553025e-06, | |
| "loss": 0.148, | |
| "num_input_tokens_seen": 553776, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.48467569493941554, | |
| "grad_norm": 9.308876037597656, | |
| "learning_rate": 4.907825008546039e-06, | |
| "loss": 0.1237, | |
| "num_input_tokens_seen": 560208, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4903777619387028, | |
| "grad_norm": 3.73714542388916, | |
| "learning_rate": 4.905366350699493e-06, | |
| "loss": 0.106, | |
| "num_input_tokens_seen": 566688, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.49607982893799, | |
| "grad_norm": 4.344607830047607, | |
| "learning_rate": 4.902875964444746e-06, | |
| "loss": 0.1131, | |
| "num_input_tokens_seen": 573184, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5017818959372773, | |
| "grad_norm": 4.39575719833374, | |
| "learning_rate": 4.900353882631679e-06, | |
| "loss": 0.1343, | |
| "num_input_tokens_seen": 579920, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5074839629365645, | |
| "grad_norm": 2.9490160942077637, | |
| "learning_rate": 4.897800138528254e-06, | |
| "loss": 0.0873, | |
| "num_input_tokens_seen": 586864, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.5131860299358517, | |
| "grad_norm": 7.676606178283691, | |
| "learning_rate": 4.8952147658200815e-06, | |
| "loss": 0.1412, | |
| "num_input_tokens_seen": 593392, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.518888096935139, | |
| "grad_norm": 5.407953262329102, | |
| "learning_rate": 4.892597798609976e-06, | |
| "loss": 0.0983, | |
| "num_input_tokens_seen": 599824, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 4.343061923980713, | |
| "learning_rate": 4.889949271417504e-06, | |
| "loss": 0.1322, | |
| "num_input_tokens_seen": 606384, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.5302922309337135, | |
| "grad_norm": 4.196661949157715, | |
| "learning_rate": 4.88726921917853e-06, | |
| "loss": 0.1345, | |
| "num_input_tokens_seen": 613408, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.5359942979330007, | |
| "grad_norm": 6.040660381317139, | |
| "learning_rate": 4.884557677244755e-06, | |
| "loss": 0.1367, | |
| "num_input_tokens_seen": 620096, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.5416963649322879, | |
| "grad_norm": 4.8859100341796875, | |
| "learning_rate": 4.8818146813832475e-06, | |
| "loss": 0.1228, | |
| "num_input_tokens_seen": 626400, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5473984319315752, | |
| "grad_norm": 13.37174129486084, | |
| "learning_rate": 4.879040267775981e-06, | |
| "loss": 0.2031, | |
| "num_input_tokens_seen": 633088, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.5531004989308624, | |
| "grad_norm": 4.321401596069336, | |
| "learning_rate": 4.8762344730193445e-06, | |
| "loss": 0.1235, | |
| "num_input_tokens_seen": 639584, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.5588025659301497, | |
| "grad_norm": 10.194490432739258, | |
| "learning_rate": 4.873397334123667e-06, | |
| "loss": 0.1136, | |
| "num_input_tokens_seen": 646160, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.5645046329294369, | |
| "grad_norm": 4.425650119781494, | |
| "learning_rate": 4.87052888851273e-06, | |
| "loss": 0.1065, | |
| "num_input_tokens_seen": 652992, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5702066999287242, | |
| "grad_norm": 13.328121185302734, | |
| "learning_rate": 4.867629174023269e-06, | |
| "loss": 0.1489, | |
| "num_input_tokens_seen": 659952, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5759087669280114, | |
| "grad_norm": 3.278292417526245, | |
| "learning_rate": 4.864698228904479e-06, | |
| "loss": 0.1057, | |
| "num_input_tokens_seen": 666400, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.5816108339272986, | |
| "grad_norm": 13.085524559020996, | |
| "learning_rate": 4.861736091817506e-06, | |
| "loss": 0.1382, | |
| "num_input_tokens_seen": 673008, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.5873129009265858, | |
| "grad_norm": 10.3684663772583, | |
| "learning_rate": 4.858742801834943e-06, | |
| "loss": 0.119, | |
| "num_input_tokens_seen": 679680, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.5930149679258732, | |
| "grad_norm": 3.594886064529419, | |
| "learning_rate": 4.855718398440306e-06, | |
| "loss": 0.1058, | |
| "num_input_tokens_seen": 685968, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.5987170349251604, | |
| "grad_norm": 3.6079792976379395, | |
| "learning_rate": 4.852662921527523e-06, | |
| "loss": 0.0622, | |
| "num_input_tokens_seen": 692496, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6044191019244476, | |
| "grad_norm": 4.3337602615356445, | |
| "learning_rate": 4.849576411400397e-06, | |
| "loss": 0.08, | |
| "num_input_tokens_seen": 699040, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.6101211689237348, | |
| "grad_norm": 7.190303325653076, | |
| "learning_rate": 4.846458908772085e-06, | |
| "loss": 0.1147, | |
| "num_input_tokens_seen": 705792, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.6158232359230221, | |
| "grad_norm": 11.85684871673584, | |
| "learning_rate": 4.843310454764553e-06, | |
| "loss": 0.1084, | |
| "num_input_tokens_seen": 712912, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6215253029223093, | |
| "grad_norm": 5.83061408996582, | |
| "learning_rate": 4.840131090908038e-06, | |
| "loss": 0.1195, | |
| "num_input_tokens_seen": 719488, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.6272273699215966, | |
| "grad_norm": 5.0566511154174805, | |
| "learning_rate": 4.8369208591405e-06, | |
| "loss": 0.0877, | |
| "num_input_tokens_seen": 725872, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6329294369208838, | |
| "grad_norm": 7.780054092407227, | |
| "learning_rate": 4.833679801807064e-06, | |
| "loss": 0.1405, | |
| "num_input_tokens_seen": 732336, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.6386315039201711, | |
| "grad_norm": 7.04516077041626, | |
| "learning_rate": 4.8304079616594684e-06, | |
| "loss": 0.1014, | |
| "num_input_tokens_seen": 739200, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.6443335709194583, | |
| "grad_norm": 7.1423516273498535, | |
| "learning_rate": 4.827105381855496e-06, | |
| "loss": 0.1094, | |
| "num_input_tokens_seen": 745568, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.6500356379187455, | |
| "grad_norm": 3.5626931190490723, | |
| "learning_rate": 4.823772105958408e-06, | |
| "loss": 0.1301, | |
| "num_input_tokens_seen": 751872, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 4.6096296310424805, | |
| "learning_rate": 4.820408177936365e-06, | |
| "loss": 0.0939, | |
| "num_input_tokens_seen": 758784, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.6614397719173201, | |
| "grad_norm": 7.992829322814941, | |
| "learning_rate": 4.817013642161853e-06, | |
| "loss": 0.122, | |
| "num_input_tokens_seen": 765552, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.6671418389166073, | |
| "grad_norm": 4.512622356414795, | |
| "learning_rate": 4.8135885434110935e-06, | |
| "loss": 0.1296, | |
| "num_input_tokens_seen": 772096, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.6728439059158945, | |
| "grad_norm": 4.544010639190674, | |
| "learning_rate": 4.810132926863454e-06, | |
| "loss": 0.108, | |
| "num_input_tokens_seen": 778512, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.6785459729151817, | |
| "grad_norm": 2.2902719974517822, | |
| "learning_rate": 4.8066468381008525e-06, | |
| "loss": 0.0779, | |
| "num_input_tokens_seen": 784992, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.684248039914469, | |
| "grad_norm": 5.215991497039795, | |
| "learning_rate": 4.803130323107157e-06, | |
| "loss": 0.1358, | |
| "num_input_tokens_seen": 791392, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6899501069137562, | |
| "grad_norm": 3.8735485076904297, | |
| "learning_rate": 4.799583428267577e-06, | |
| "loss": 0.1485, | |
| "num_input_tokens_seen": 798320, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 3.4041693210601807, | |
| "learning_rate": 4.796006200368054e-06, | |
| "loss": 0.09, | |
| "num_input_tokens_seen": 804896, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.7013542409123307, | |
| "grad_norm": 5.4052839279174805, | |
| "learning_rate": 4.792398686594641e-06, | |
| "loss": 0.108, | |
| "num_input_tokens_seen": 811504, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.707056307911618, | |
| "grad_norm": 9.151551246643066, | |
| "learning_rate": 4.788760934532883e-06, | |
| "loss": 0.1557, | |
| "num_input_tokens_seen": 818176, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.7127583749109052, | |
| "grad_norm": 8.451269149780273, | |
| "learning_rate": 4.785092992167192e-06, | |
| "loss": 0.1206, | |
| "num_input_tokens_seen": 824272, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7184604419101924, | |
| "grad_norm": 5.943455219268799, | |
| "learning_rate": 4.7813949078802035e-06, | |
| "loss": 0.0977, | |
| "num_input_tokens_seen": 830656, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.7241625089094796, | |
| "grad_norm": 5.474506855010986, | |
| "learning_rate": 4.777666730452151e-06, | |
| "loss": 0.1223, | |
| "num_input_tokens_seen": 837680, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.729864575908767, | |
| "grad_norm": 8.626420974731445, | |
| "learning_rate": 4.773908509060214e-06, | |
| "loss": 0.1751, | |
| "num_input_tokens_seen": 844624, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.7355666429080542, | |
| "grad_norm": 3.8866775035858154, | |
| "learning_rate": 4.770120293277876e-06, | |
| "loss": 0.1016, | |
| "num_input_tokens_seen": 851312, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.7412687099073414, | |
| "grad_norm": 4.498022556304932, | |
| "learning_rate": 4.766302133074261e-06, | |
| "loss": 0.1351, | |
| "num_input_tokens_seen": 858256, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7469707769066286, | |
| "grad_norm": 3.3039486408233643, | |
| "learning_rate": 4.762454078813483e-06, | |
| "loss": 0.0891, | |
| "num_input_tokens_seen": 864912, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.7526728439059159, | |
| "grad_norm": 2.1555142402648926, | |
| "learning_rate": 4.758576181253981e-06, | |
| "loss": 0.07, | |
| "num_input_tokens_seen": 871552, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.7583749109052031, | |
| "grad_norm": 4.617002964019775, | |
| "learning_rate": 4.7546684915478445e-06, | |
| "loss": 0.1325, | |
| "num_input_tokens_seen": 878256, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.7640769779044904, | |
| "grad_norm": 4.712822914123535, | |
| "learning_rate": 4.750731061240143e-06, | |
| "loss": 0.1074, | |
| "num_input_tokens_seen": 885216, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.7697790449037776, | |
| "grad_norm": 3.698430061340332, | |
| "learning_rate": 4.746763942268243e-06, | |
| "loss": 0.0949, | |
| "num_input_tokens_seen": 891552, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7754811119030649, | |
| "grad_norm": 6.280089855194092, | |
| "learning_rate": 4.742767186961126e-06, | |
| "loss": 0.0813, | |
| "num_input_tokens_seen": 898432, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.7811831789023521, | |
| "grad_norm": 3.984236240386963, | |
| "learning_rate": 4.738740848038695e-06, | |
| "loss": 0.092, | |
| "num_input_tokens_seen": 905184, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 4.700631141662598, | |
| "learning_rate": 4.7346849786110835e-06, | |
| "loss": 0.0679, | |
| "num_input_tokens_seen": 911856, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.7925873129009265, | |
| "grad_norm": 4.287609100341797, | |
| "learning_rate": 4.730599632177952e-06, | |
| "loss": 0.1234, | |
| "num_input_tokens_seen": 918320, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.7982893799002139, | |
| "grad_norm": 10.069003105163574, | |
| "learning_rate": 4.726484862627779e-06, | |
| "loss": 0.1281, | |
| "num_input_tokens_seen": 925536, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8039914468995011, | |
| "grad_norm": 3.5951642990112305, | |
| "learning_rate": 4.7223407242371595e-06, | |
| "loss": 0.0834, | |
| "num_input_tokens_seen": 932064, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.8096935138987883, | |
| "grad_norm": 3.834705352783203, | |
| "learning_rate": 4.718167271670078e-06, | |
| "loss": 0.0863, | |
| "num_input_tokens_seen": 938688, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.8153955808980755, | |
| "grad_norm": 5.181819438934326, | |
| "learning_rate": 4.713964559977196e-06, | |
| "loss": 0.0503, | |
| "num_input_tokens_seen": 945456, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.8210976478973628, | |
| "grad_norm": 6.386320114135742, | |
| "learning_rate": 4.709732644595122e-06, | |
| "loss": 0.1619, | |
| "num_input_tokens_seen": 951872, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.82679971489665, | |
| "grad_norm": 3.679490566253662, | |
| "learning_rate": 4.7054715813456795e-06, | |
| "loss": 0.1112, | |
| "num_input_tokens_seen": 958320, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8325017818959373, | |
| "grad_norm": 5.969015121459961, | |
| "learning_rate": 4.701181426435174e-06, | |
| "loss": 0.0939, | |
| "num_input_tokens_seen": 965008, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.8382038488952245, | |
| "grad_norm": 2.577047824859619, | |
| "learning_rate": 4.69686223645365e-06, | |
| "loss": 0.0549, | |
| "num_input_tokens_seen": 971520, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.8439059158945118, | |
| "grad_norm": 5.369522571563721, | |
| "learning_rate": 4.692514068374142e-06, | |
| "loss": 0.1128, | |
| "num_input_tokens_seen": 978512, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.849607982893799, | |
| "grad_norm": 5.3961615562438965, | |
| "learning_rate": 4.688136979551926e-06, | |
| "loss": 0.0862, | |
| "num_input_tokens_seen": 985264, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.8553100498930862, | |
| "grad_norm": 3.643087148666382, | |
| "learning_rate": 4.683731027723764e-06, | |
| "loss": 0.0769, | |
| "num_input_tokens_seen": 991552, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8610121168923734, | |
| "grad_norm": 4.090428352355957, | |
| "learning_rate": 4.679296271007138e-06, | |
| "loss": 0.1199, | |
| "num_input_tokens_seen": 998064, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.8667141838916608, | |
| "grad_norm": 6.78312349319458, | |
| "learning_rate": 4.674832767899486e-06, | |
| "loss": 0.093, | |
| "num_input_tokens_seen": 1004864, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.872416250890948, | |
| "grad_norm": 5.438461780548096, | |
| "learning_rate": 4.670340577277433e-06, | |
| "loss": 0.0903, | |
| "num_input_tokens_seen": 1011568, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.8781183178902352, | |
| "grad_norm": 5.802255153656006, | |
| "learning_rate": 4.665819758396009e-06, | |
| "loss": 0.0877, | |
| "num_input_tokens_seen": 1018320, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.8838203848895224, | |
| "grad_norm": 4.546239852905273, | |
| "learning_rate": 4.661270370887872e-06, | |
| "loss": 0.1049, | |
| "num_input_tokens_seen": 1024640, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.8895224518888097, | |
| "grad_norm": 5.347127914428711, | |
| "learning_rate": 4.656692474762518e-06, | |
| "loss": 0.1052, | |
| "num_input_tokens_seen": 1031312, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.895224518888097, | |
| "grad_norm": 6.227194786071777, | |
| "learning_rate": 4.652086130405492e-06, | |
| "loss": 0.1196, | |
| "num_input_tokens_seen": 1037936, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.9009265858873842, | |
| "grad_norm": 3.103381872177124, | |
| "learning_rate": 4.647451398577589e-06, | |
| "loss": 0.0427, | |
| "num_input_tokens_seen": 1044496, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.9066286528866714, | |
| "grad_norm": 2.1822800636291504, | |
| "learning_rate": 4.642788340414056e-06, | |
| "loss": 0.0764, | |
| "num_input_tokens_seen": 1051456, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.9123307198859587, | |
| "grad_norm": 4.704215049743652, | |
| "learning_rate": 4.638097017423783e-06, | |
| "loss": 0.0812, | |
| "num_input_tokens_seen": 1057952, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9180327868852459, | |
| "grad_norm": 3.070636510848999, | |
| "learning_rate": 4.63337749148849e-06, | |
| "loss": 0.0807, | |
| "num_input_tokens_seen": 1065024, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.9237348538845331, | |
| "grad_norm": 8.418425559997559, | |
| "learning_rate": 4.628629824861915e-06, | |
| "loss": 0.1475, | |
| "num_input_tokens_seen": 1071968, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.9294369208838203, | |
| "grad_norm": 4.310948371887207, | |
| "learning_rate": 4.62385408016899e-06, | |
| "loss": 0.0507, | |
| "num_input_tokens_seen": 1078256, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.9351389878831077, | |
| "grad_norm": 8.601131439208984, | |
| "learning_rate": 4.619050320405017e-06, | |
| "loss": 0.1015, | |
| "num_input_tokens_seen": 1084752, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.9408410548823949, | |
| "grad_norm": 4.491447925567627, | |
| "learning_rate": 4.614218608934834e-06, | |
| "loss": 0.0957, | |
| "num_input_tokens_seen": 1091376, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9465431218816821, | |
| "grad_norm": 8.606071472167969, | |
| "learning_rate": 4.609359009491981e-06, | |
| "loss": 0.1327, | |
| "num_input_tokens_seen": 1098176, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.9522451888809693, | |
| "grad_norm": 5.092894077301025, | |
| "learning_rate": 4.60447158617786e-06, | |
| "loss": 0.0782, | |
| "num_input_tokens_seen": 1104848, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.9579472558802566, | |
| "grad_norm": 4.862101078033447, | |
| "learning_rate": 4.599556403460889e-06, | |
| "loss": 0.0768, | |
| "num_input_tokens_seen": 1111120, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.9636493228795439, | |
| "grad_norm": 4.805572032928467, | |
| "learning_rate": 4.59461352617565e-06, | |
| "loss": 0.033, | |
| "num_input_tokens_seen": 1117440, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.9693513898788311, | |
| "grad_norm": 4.407527446746826, | |
| "learning_rate": 4.589643019522036e-06, | |
| "loss": 0.1295, | |
| "num_input_tokens_seen": 1123968, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9750534568781183, | |
| "grad_norm": 12.811196327209473, | |
| "learning_rate": 4.584644949064391e-06, | |
| "loss": 0.1216, | |
| "num_input_tokens_seen": 1130656, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.9807555238774056, | |
| "grad_norm": 5.432493686676025, | |
| "learning_rate": 4.579619380730642e-06, | |
| "loss": 0.0896, | |
| "num_input_tokens_seen": 1137088, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.9864575908766928, | |
| "grad_norm": 4.3895745277404785, | |
| "learning_rate": 4.574566380811432e-06, | |
| "loss": 0.101, | |
| "num_input_tokens_seen": 1144064, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.99215965787598, | |
| "grad_norm": 6.614623069763184, | |
| "learning_rate": 4.569486015959247e-06, | |
| "loss": 0.0787, | |
| "num_input_tokens_seen": 1150560, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.9978617248752673, | |
| "grad_norm": 10.594895362854004, | |
| "learning_rate": 4.564378353187533e-06, | |
| "loss": 0.1118, | |
| "num_input_tokens_seen": 1157184, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.0035637918745546, | |
| "grad_norm": 6.2672576904296875, | |
| "learning_rate": 4.5592434598698144e-06, | |
| "loss": 0.0671, | |
| "num_input_tokens_seen": 1163712, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.0092658588738417, | |
| "grad_norm": 5.011196136474609, | |
| "learning_rate": 4.5540814037388056e-06, | |
| "loss": 0.0862, | |
| "num_input_tokens_seen": 1170480, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.014967925873129, | |
| "grad_norm": 2.275132179260254, | |
| "learning_rate": 4.548892252885518e-06, | |
| "loss": 0.0385, | |
| "num_input_tokens_seen": 1176768, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.0206699928724163, | |
| "grad_norm": 5.401920795440674, | |
| "learning_rate": 4.543676075758356e-06, | |
| "loss": 0.0557, | |
| "num_input_tokens_seen": 1183520, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.0263720598717034, | |
| "grad_norm": 6.662536144256592, | |
| "learning_rate": 4.538432941162227e-06, | |
| "loss": 0.0692, | |
| "num_input_tokens_seen": 1189968, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0320741268709908, | |
| "grad_norm": 6.5178093910217285, | |
| "learning_rate": 4.533162918257615e-06, | |
| "loss": 0.1001, | |
| "num_input_tokens_seen": 1196432, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.037776193870278, | |
| "grad_norm": 4.606156349182129, | |
| "learning_rate": 4.5278660765596885e-06, | |
| "loss": 0.0782, | |
| "num_input_tokens_seen": 1203024, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.0434782608695652, | |
| "grad_norm": 3.283186674118042, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.0324, | |
| "num_input_tokens_seen": 1209744, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.0491803278688525, | |
| "grad_norm": 6.526776313781738, | |
| "learning_rate": 4.517192216612415e-06, | |
| "loss": 0.0671, | |
| "num_input_tokens_seen": 1216080, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.0548823948681396, | |
| "grad_norm": 3.7458949089050293, | |
| "learning_rate": 4.511815339158497e-06, | |
| "loss": 0.051, | |
| "num_input_tokens_seen": 1223328, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.060584461867427, | |
| "grad_norm": 5.047933101654053, | |
| "learning_rate": 4.506411924500263e-06, | |
| "loss": 0.0565, | |
| "num_input_tokens_seen": 1230192, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.0662865288667143, | |
| "grad_norm": 3.9890875816345215, | |
| "learning_rate": 4.500982043912404e-06, | |
| "loss": 0.0393, | |
| "num_input_tokens_seen": 1236992, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.0719885958660014, | |
| "grad_norm": 5.807724475860596, | |
| "learning_rate": 4.495525769018717e-06, | |
| "loss": 0.0922, | |
| "num_input_tokens_seen": 1243776, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.0776906628652887, | |
| "grad_norm": 6.556837558746338, | |
| "learning_rate": 4.490043171791155e-06, | |
| "loss": 0.0518, | |
| "num_input_tokens_seen": 1250752, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.0833927298645758, | |
| "grad_norm": 4.41609525680542, | |
| "learning_rate": 4.484534324548883e-06, | |
| "loss": 0.0894, | |
| "num_input_tokens_seen": 1257344, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0890947968638631, | |
| "grad_norm": 5.981895446777344, | |
| "learning_rate": 4.47899929995732e-06, | |
| "loss": 0.0631, | |
| "num_input_tokens_seen": 1264064, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.0947968638631504, | |
| "grad_norm": 4.5273966789245605, | |
| "learning_rate": 4.47343817102718e-06, | |
| "loss": 0.0464, | |
| "num_input_tokens_seen": 1270608, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.1004989308624376, | |
| "grad_norm": 4.48996639251709, | |
| "learning_rate": 4.4678510111135154e-06, | |
| "loss": 0.0652, | |
| "num_input_tokens_seen": 1277056, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.1062009978617249, | |
| "grad_norm": 3.518558979034424, | |
| "learning_rate": 4.462237893914742e-06, | |
| "loss": 0.0317, | |
| "num_input_tokens_seen": 1283776, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.1119030648610122, | |
| "grad_norm": 8.252947807312012, | |
| "learning_rate": 4.456598893471668e-06, | |
| "loss": 0.0485, | |
| "num_input_tokens_seen": 1290368, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.1176051318602993, | |
| "grad_norm": 2.3548762798309326, | |
| "learning_rate": 4.450934084166524e-06, | |
| "loss": 0.0325, | |
| "num_input_tokens_seen": 1297040, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.1233071988595866, | |
| "grad_norm": 3.5539638996124268, | |
| "learning_rate": 4.445243540721972e-06, | |
| "loss": 0.0753, | |
| "num_input_tokens_seen": 1303856, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.129009265858874, | |
| "grad_norm": 1.5808628797531128, | |
| "learning_rate": 4.439527338200129e-06, | |
| "loss": 0.0159, | |
| "num_input_tokens_seen": 1310384, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.134711332858161, | |
| "grad_norm": 6.414031982421875, | |
| "learning_rate": 4.433785552001569e-06, | |
| "loss": 0.0718, | |
| "num_input_tokens_seen": 1316976, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.1404133998574484, | |
| "grad_norm": 6.116299629211426, | |
| "learning_rate": 4.428018257864333e-06, | |
| "loss": 0.0491, | |
| "num_input_tokens_seen": 1323520, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1461154668567355, | |
| "grad_norm": 3.120823860168457, | |
| "learning_rate": 4.422225531862929e-06, | |
| "loss": 0.0608, | |
| "num_input_tokens_seen": 1329984, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.1518175338560228, | |
| "grad_norm": 3.8637633323669434, | |
| "learning_rate": 4.416407450407332e-06, | |
| "loss": 0.0631, | |
| "num_input_tokens_seen": 1336704, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.1575196008553101, | |
| "grad_norm": 2.4866721630096436, | |
| "learning_rate": 4.4105640902419665e-06, | |
| "loss": 0.024, | |
| "num_input_tokens_seen": 1343344, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.1632216678545972, | |
| "grad_norm": 3.9751436710357666, | |
| "learning_rate": 4.404695528444704e-06, | |
| "loss": 0.0453, | |
| "num_input_tokens_seen": 1350144, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.1689237348538846, | |
| "grad_norm": 5.458123683929443, | |
| "learning_rate": 4.398801842425842e-06, | |
| "loss": 0.0345, | |
| "num_input_tokens_seen": 1356672, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.1746258018531717, | |
| "grad_norm": 2.4415106773376465, | |
| "learning_rate": 4.392883109927083e-06, | |
| "loss": 0.015, | |
| "num_input_tokens_seen": 1363200, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.180327868852459, | |
| "grad_norm": 5.5863423347473145, | |
| "learning_rate": 4.3869394090205105e-06, | |
| "loss": 0.0731, | |
| "num_input_tokens_seen": 1369408, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.1860299358517463, | |
| "grad_norm": 5.382776737213135, | |
| "learning_rate": 4.380970818107556e-06, | |
| "loss": 0.056, | |
| "num_input_tokens_seen": 1376480, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.1917320028510334, | |
| "grad_norm": 8.42451286315918, | |
| "learning_rate": 4.374977415917969e-06, | |
| "loss": 0.1013, | |
| "num_input_tokens_seen": 1382944, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.1974340698503207, | |
| "grad_norm": 4.907031536102295, | |
| "learning_rate": 4.368959281508776e-06, | |
| "loss": 0.0254, | |
| "num_input_tokens_seen": 1389824, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.203136136849608, | |
| "grad_norm": 4.632014274597168, | |
| "learning_rate": 4.3629164942632385e-06, | |
| "loss": 0.0526, | |
| "num_input_tokens_seen": 1396448, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.2088382038488952, | |
| "grad_norm": 5.454948902130127, | |
| "learning_rate": 4.356849133889805e-06, | |
| "loss": 0.037, | |
| "num_input_tokens_seen": 1402976, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.2145402708481825, | |
| "grad_norm": 2.4538490772247314, | |
| "learning_rate": 4.350757280421061e-06, | |
| "loss": 0.0438, | |
| "num_input_tokens_seen": 1409648, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.2202423378474698, | |
| "grad_norm": 5.704830169677734, | |
| "learning_rate": 4.34464101421267e-06, | |
| "loss": 0.0496, | |
| "num_input_tokens_seen": 1416320, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.225944404846757, | |
| "grad_norm": 2.5545387268066406, | |
| "learning_rate": 4.3385004159423195e-06, | |
| "loss": 0.0453, | |
| "num_input_tokens_seen": 1422768, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.2316464718460443, | |
| "grad_norm": 2.7966182231903076, | |
| "learning_rate": 4.332335566608651e-06, | |
| "loss": 0.0428, | |
| "num_input_tokens_seen": 1429392, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.2373485388453314, | |
| "grad_norm": 6.403561592102051, | |
| "learning_rate": 4.3261465475301956e-06, | |
| "loss": 0.113, | |
| "num_input_tokens_seen": 1435872, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.2430506058446187, | |
| "grad_norm": 3.515782594680786, | |
| "learning_rate": 4.319933440344298e-06, | |
| "loss": 0.0934, | |
| "num_input_tokens_seen": 1443024, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.248752672843906, | |
| "grad_norm": 2.879307985305786, | |
| "learning_rate": 4.313696327006042e-06, | |
| "loss": 0.0495, | |
| "num_input_tokens_seen": 1449488, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.2544547398431931, | |
| "grad_norm": 5.576188564300537, | |
| "learning_rate": 4.307435289787169e-06, | |
| "loss": 0.0962, | |
| "num_input_tokens_seen": 1455808, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2601568068424804, | |
| "grad_norm": 3.0014944076538086, | |
| "learning_rate": 4.301150411274993e-06, | |
| "loss": 0.0546, | |
| "num_input_tokens_seen": 1462480, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 1.2658588738417675, | |
| "grad_norm": 2.2942137718200684, | |
| "learning_rate": 4.294841774371308e-06, | |
| "loss": 0.0321, | |
| "num_input_tokens_seen": 1468832, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.2715609408410549, | |
| "grad_norm": 4.320146560668945, | |
| "learning_rate": 4.288509462291302e-06, | |
| "loss": 0.042, | |
| "num_input_tokens_seen": 1475440, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.2772630078403422, | |
| "grad_norm": 2.6255133152008057, | |
| "learning_rate": 4.282153558562451e-06, | |
| "loss": 0.0554, | |
| "num_input_tokens_seen": 1482336, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.2829650748396293, | |
| "grad_norm": 2.2276813983917236, | |
| "learning_rate": 4.2757741470234214e-06, | |
| "loss": 0.0263, | |
| "num_input_tokens_seen": 1489472, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.2886671418389166, | |
| "grad_norm": 2.610847234725952, | |
| "learning_rate": 4.269371311822965e-06, | |
| "loss": 0.0433, | |
| "num_input_tokens_seen": 1496304, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 1.2943692088382037, | |
| "grad_norm": 4.202786445617676, | |
| "learning_rate": 4.262945137418806e-06, | |
| "loss": 0.0569, | |
| "num_input_tokens_seen": 1502896, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.300071275837491, | |
| "grad_norm": 4.87699031829834, | |
| "learning_rate": 4.256495708576527e-06, | |
| "loss": 0.0532, | |
| "num_input_tokens_seen": 1510224, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.3057733428367784, | |
| "grad_norm": 2.4840846061706543, | |
| "learning_rate": 4.250023110368458e-06, | |
| "loss": 0.0155, | |
| "num_input_tokens_seen": 1516624, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 3.5216634273529053, | |
| "learning_rate": 4.243527428172541e-06, | |
| "loss": 0.0277, | |
| "num_input_tokens_seen": 1523088, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.3171774768353528, | |
| "grad_norm": 5.229778289794922, | |
| "learning_rate": 4.237008747671218e-06, | |
| "loss": 0.074, | |
| "num_input_tokens_seen": 1529936, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.3228795438346401, | |
| "grad_norm": 7.132479190826416, | |
| "learning_rate": 4.230467154850289e-06, | |
| "loss": 0.0861, | |
| "num_input_tokens_seen": 1536320, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.3285816108339272, | |
| "grad_norm": 4.4164228439331055, | |
| "learning_rate": 4.2239027359977885e-06, | |
| "loss": 0.0669, | |
| "num_input_tokens_seen": 1543056, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 1.3342836778332146, | |
| "grad_norm": 5.823759078979492, | |
| "learning_rate": 4.217315577702836e-06, | |
| "loss": 0.0703, | |
| "num_input_tokens_seen": 1549664, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.3399857448325019, | |
| "grad_norm": 1.5898804664611816, | |
| "learning_rate": 4.210705766854505e-06, | |
| "loss": 0.0172, | |
| "num_input_tokens_seen": 1556384, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.345687811831789, | |
| "grad_norm": 7.746312618255615, | |
| "learning_rate": 4.2040733906406664e-06, | |
| "loss": 0.1336, | |
| "num_input_tokens_seen": 1563216, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 1.3513898788310763, | |
| "grad_norm": 2.8517649173736572, | |
| "learning_rate": 4.197418536546846e-06, | |
| "loss": 0.0207, | |
| "num_input_tokens_seen": 1569664, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 1.3570919458303634, | |
| "grad_norm": 8.109379768371582, | |
| "learning_rate": 4.190741292355071e-06, | |
| "loss": 0.0815, | |
| "num_input_tokens_seen": 1576464, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.3627940128296507, | |
| "grad_norm": 9.140835762023926, | |
| "learning_rate": 4.184041746142702e-06, | |
| "loss": 0.0453, | |
| "num_input_tokens_seen": 1582816, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 1.368496079828938, | |
| "grad_norm": 4.517364025115967, | |
| "learning_rate": 4.177319986281285e-06, | |
| "loss": 0.0791, | |
| "num_input_tokens_seen": 1589344, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3741981468282252, | |
| "grad_norm": 3.070476770401001, | |
| "learning_rate": 4.170576101435377e-06, | |
| "loss": 0.0344, | |
| "num_input_tokens_seen": 1595888, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 1.3799002138275125, | |
| "grad_norm": 4.99822998046875, | |
| "learning_rate": 4.163810180561376e-06, | |
| "loss": 0.0532, | |
| "num_input_tokens_seen": 1602736, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.3856022808267996, | |
| "grad_norm": 4.312646389007568, | |
| "learning_rate": 4.157022312906352e-06, | |
| "loss": 0.0574, | |
| "num_input_tokens_seen": 1609456, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.391304347826087, | |
| "grad_norm": 6.092965126037598, | |
| "learning_rate": 4.150212588006871e-06, | |
| "loss": 0.1002, | |
| "num_input_tokens_seen": 1616032, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.3970064148253742, | |
| "grad_norm": 3.6262662410736084, | |
| "learning_rate": 4.143381095687805e-06, | |
| "loss": 0.0314, | |
| "num_input_tokens_seen": 1622800, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.4027084818246616, | |
| "grad_norm": 7.102707386016846, | |
| "learning_rate": 4.1365279260611575e-06, | |
| "loss": 0.0689, | |
| "num_input_tokens_seen": 1629248, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.4084105488239487, | |
| "grad_norm": 6.31537389755249, | |
| "learning_rate": 4.129653169524867e-06, | |
| "loss": 0.0587, | |
| "num_input_tokens_seen": 1635568, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.414112615823236, | |
| "grad_norm": 3.1155130863189697, | |
| "learning_rate": 4.12275691676162e-06, | |
| "loss": 0.0433, | |
| "num_input_tokens_seen": 1642208, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 1.419814682822523, | |
| "grad_norm": 3.728424310684204, | |
| "learning_rate": 4.115839258737654e-06, | |
| "loss": 0.0306, | |
| "num_input_tokens_seen": 1648720, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 1.4255167498218104, | |
| "grad_norm": 3.9587793350219727, | |
| "learning_rate": 4.108900286701553e-06, | |
| "loss": 0.0454, | |
| "num_input_tokens_seen": 1655296, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.4312188168210978, | |
| "grad_norm": 5.638779163360596, | |
| "learning_rate": 4.101940092183048e-06, | |
| "loss": 0.0464, | |
| "num_input_tokens_seen": 1662272, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.4369208838203849, | |
| "grad_norm": 8.67476749420166, | |
| "learning_rate": 4.094958766991812e-06, | |
| "loss": 0.0578, | |
| "num_input_tokens_seen": 1669168, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.4426229508196722, | |
| "grad_norm": 4.2457404136657715, | |
| "learning_rate": 4.087956403216243e-06, | |
| "loss": 0.0369, | |
| "num_input_tokens_seen": 1675440, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 1.4483250178189593, | |
| "grad_norm": 6.338396072387695, | |
| "learning_rate": 4.080933093222253e-06, | |
| "loss": 0.0686, | |
| "num_input_tokens_seen": 1682080, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.4540270848182466, | |
| "grad_norm": 3.969381809234619, | |
| "learning_rate": 4.073888929652048e-06, | |
| "loss": 0.0873, | |
| "num_input_tokens_seen": 1688896, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.459729151817534, | |
| "grad_norm": 5.51995325088501, | |
| "learning_rate": 4.066824005422907e-06, | |
| "loss": 0.0466, | |
| "num_input_tokens_seen": 1695760, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.465431218816821, | |
| "grad_norm": 7.369187355041504, | |
| "learning_rate": 4.059738413725958e-06, | |
| "loss": 0.0349, | |
| "num_input_tokens_seen": 1702352, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 1.4711332858161084, | |
| "grad_norm": 8.143928527832031, | |
| "learning_rate": 4.0526322480249435e-06, | |
| "loss": 0.061, | |
| "num_input_tokens_seen": 1709120, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 1.4768353528153955, | |
| "grad_norm": 4.497892379760742, | |
| "learning_rate": 4.045505602054995e-06, | |
| "loss": 0.0801, | |
| "num_input_tokens_seen": 1716000, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.4825374198146828, | |
| "grad_norm": 4.872470378875732, | |
| "learning_rate": 4.0383585698213874e-06, | |
| "loss": 0.0406, | |
| "num_input_tokens_seen": 1722080, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4882394868139701, | |
| "grad_norm": 3.8097238540649414, | |
| "learning_rate": 4.03119124559831e-06, | |
| "loss": 0.0417, | |
| "num_input_tokens_seen": 1728960, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.4939415538132574, | |
| "grad_norm": 3.029526948928833, | |
| "learning_rate": 4.0240037239276146e-06, | |
| "loss": 0.0178, | |
| "num_input_tokens_seen": 1735408, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 1.4996436208125445, | |
| "grad_norm": 2.9828808307647705, | |
| "learning_rate": 4.016796099617569e-06, | |
| "loss": 0.0238, | |
| "num_input_tokens_seen": 1742032, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 1.5053456878118316, | |
| "grad_norm": 10.337291717529297, | |
| "learning_rate": 4.009568467741611e-06, | |
| "loss": 0.0842, | |
| "num_input_tokens_seen": 1748848, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.511047754811119, | |
| "grad_norm": 5.436164855957031, | |
| "learning_rate": 4.002320923637091e-06, | |
| "loss": 0.0354, | |
| "num_input_tokens_seen": 1755584, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.5167498218104063, | |
| "grad_norm": 7.981906414031982, | |
| "learning_rate": 3.995053562904015e-06, | |
| "loss": 0.072, | |
| "num_input_tokens_seen": 1762464, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 1.5224518888096936, | |
| "grad_norm": 2.6612589359283447, | |
| "learning_rate": 3.987766481403785e-06, | |
| "loss": 0.0297, | |
| "num_input_tokens_seen": 1769008, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 1.5281539558089807, | |
| "grad_norm": 5.873383522033691, | |
| "learning_rate": 3.98045977525793e-06, | |
| "loss": 0.0355, | |
| "num_input_tokens_seen": 1775808, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.533856022808268, | |
| "grad_norm": 4.245385646820068, | |
| "learning_rate": 3.973133540846844e-06, | |
| "loss": 0.0669, | |
| "num_input_tokens_seen": 1782416, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 1.5395580898075552, | |
| "grad_norm": 5.252135276794434, | |
| "learning_rate": 3.965787874808513e-06, | |
| "loss": 0.0622, | |
| "num_input_tokens_seen": 1788960, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.5452601568068425, | |
| "grad_norm": 7.067147731781006, | |
| "learning_rate": 3.958422874037236e-06, | |
| "loss": 0.0436, | |
| "num_input_tokens_seen": 1795600, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 1.5509622238061298, | |
| "grad_norm": 3.885929822921753, | |
| "learning_rate": 3.951038635682352e-06, | |
| "loss": 0.0265, | |
| "num_input_tokens_seen": 1802144, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 1.5566642908054171, | |
| "grad_norm": 3.3886828422546387, | |
| "learning_rate": 3.943635257146959e-06, | |
| "loss": 0.0165, | |
| "num_input_tokens_seen": 1808656, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.5623663578047042, | |
| "grad_norm": 1.3812897205352783, | |
| "learning_rate": 3.936212836086621e-06, | |
| "loss": 0.0246, | |
| "num_input_tokens_seen": 1815360, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 1.5680684248039913, | |
| "grad_norm": 5.722872257232666, | |
| "learning_rate": 3.928771470408092e-06, | |
| "loss": 0.0929, | |
| "num_input_tokens_seen": 1822048, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.5737704918032787, | |
| "grad_norm": 5.5266313552856445, | |
| "learning_rate": 3.921311258268013e-06, | |
| "loss": 0.0591, | |
| "num_input_tokens_seen": 1828416, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 1.579472558802566, | |
| "grad_norm": 4.463235855102539, | |
| "learning_rate": 3.913832298071629e-06, | |
| "loss": 0.0479, | |
| "num_input_tokens_seen": 1835008, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 1.5851746258018533, | |
| "grad_norm": 5.2619757652282715, | |
| "learning_rate": 3.906334688471479e-06, | |
| "loss": 0.0414, | |
| "num_input_tokens_seen": 1841536, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 1.5908766928011404, | |
| "grad_norm": 3.2384073734283447, | |
| "learning_rate": 3.8988185283661005e-06, | |
| "loss": 0.0591, | |
| "num_input_tokens_seen": 1848064, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 1.5965787598004275, | |
| "grad_norm": 9.16089153289795, | |
| "learning_rate": 3.891283916898729e-06, | |
| "loss": 0.0797, | |
| "num_input_tokens_seen": 1854640, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.6022808267997148, | |
| "grad_norm": 2.8571524620056152, | |
| "learning_rate": 3.88373095345598e-06, | |
| "loss": 0.0338, | |
| "num_input_tokens_seen": 1861184, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 1.6079828937990022, | |
| "grad_norm": 5.12972354888916, | |
| "learning_rate": 3.876159737666552e-06, | |
| "loss": 0.0764, | |
| "num_input_tokens_seen": 1867856, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 1.6136849607982895, | |
| "grad_norm": 4.020384311676025, | |
| "learning_rate": 3.868570369399894e-06, | |
| "loss": 0.0835, | |
| "num_input_tokens_seen": 1874768, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 1.6193870277975766, | |
| "grad_norm": 3.4921162128448486, | |
| "learning_rate": 3.860962948764906e-06, | |
| "loss": 0.0644, | |
| "num_input_tokens_seen": 1881488, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 1.6250890947968637, | |
| "grad_norm": 3.6133933067321777, | |
| "learning_rate": 3.85333757610861e-06, | |
| "loss": 0.0265, | |
| "num_input_tokens_seen": 1888032, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.630791161796151, | |
| "grad_norm": 2.9440054893493652, | |
| "learning_rate": 3.845694352014825e-06, | |
| "loss": 0.0934, | |
| "num_input_tokens_seen": 1895008, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 1.6364932287954383, | |
| "grad_norm": 4.363600730895996, | |
| "learning_rate": 3.838033377302844e-06, | |
| "loss": 0.0436, | |
| "num_input_tokens_seen": 1901392, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.6421952957947257, | |
| "grad_norm": 2.8621530532836914, | |
| "learning_rate": 3.8303547530261025e-06, | |
| "loss": 0.0461, | |
| "num_input_tokens_seen": 1907936, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.6478973627940128, | |
| "grad_norm": 4.192432403564453, | |
| "learning_rate": 3.8226585804708435e-06, | |
| "loss": 0.0521, | |
| "num_input_tokens_seen": 1914608, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 1.6535994297933, | |
| "grad_norm": 2.4695684909820557, | |
| "learning_rate": 3.814944961154788e-06, | |
| "loss": 0.0282, | |
| "num_input_tokens_seen": 1920848, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.6593014967925872, | |
| "grad_norm": 4.6032562255859375, | |
| "learning_rate": 3.807213996825788e-06, | |
| "loss": 0.0408, | |
| "num_input_tokens_seen": 1927600, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 1.6650035637918745, | |
| "grad_norm": 3.675687789916992, | |
| "learning_rate": 3.799465789460491e-06, | |
| "loss": 0.0435, | |
| "num_input_tokens_seen": 1934096, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 1.6707056307911619, | |
| "grad_norm": 2.347770929336548, | |
| "learning_rate": 3.791700441262987e-06, | |
| "loss": 0.0459, | |
| "num_input_tokens_seen": 1940816, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 1.6764076977904492, | |
| "grad_norm": 4.666854381561279, | |
| "learning_rate": 3.7839180546634703e-06, | |
| "loss": 0.046, | |
| "num_input_tokens_seen": 1947392, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.6821097647897363, | |
| "grad_norm": 5.212928295135498, | |
| "learning_rate": 3.77611873231688e-06, | |
| "loss": 0.0338, | |
| "num_input_tokens_seen": 1954272, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.6878118317890234, | |
| "grad_norm": 0.8700922727584839, | |
| "learning_rate": 3.7683025771015515e-06, | |
| "loss": 0.0304, | |
| "num_input_tokens_seen": 1960640, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 1.6935138987883107, | |
| "grad_norm": 6.290396690368652, | |
| "learning_rate": 3.760469692117854e-06, | |
| "loss": 0.0652, | |
| "num_input_tokens_seen": 1967440, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 1.699215965787598, | |
| "grad_norm": 3.9211745262145996, | |
| "learning_rate": 3.7526201806868372e-06, | |
| "loss": 0.0233, | |
| "num_input_tokens_seen": 1973968, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 1.7049180327868854, | |
| "grad_norm": 3.1297361850738525, | |
| "learning_rate": 3.744754146348862e-06, | |
| "loss": 0.0447, | |
| "num_input_tokens_seen": 1980496, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 1.7106200997861725, | |
| "grad_norm": 6.064594745635986, | |
| "learning_rate": 3.736871692862239e-06, | |
| "loss": 0.0599, | |
| "num_input_tokens_seen": 1987184, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.7163221667854596, | |
| "grad_norm": 6.277172565460205, | |
| "learning_rate": 3.7289729242018584e-06, | |
| "loss": 0.0607, | |
| "num_input_tokens_seen": 1993968, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 1.722024233784747, | |
| "grad_norm": 4.980268955230713, | |
| "learning_rate": 3.721057944557819e-06, | |
| "loss": 0.0449, | |
| "num_input_tokens_seen": 2000640, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 1.7277263007840342, | |
| "grad_norm": 4.455365180969238, | |
| "learning_rate": 3.713126858334052e-06, | |
| "loss": 0.0294, | |
| "num_input_tokens_seen": 2006784, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 1.7334283677833215, | |
| "grad_norm": 8.115938186645508, | |
| "learning_rate": 3.705179770146946e-06, | |
| "loss": 0.058, | |
| "num_input_tokens_seen": 2013280, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 1.7391304347826086, | |
| "grad_norm": 5.212691307067871, | |
| "learning_rate": 3.6972167848239677e-06, | |
| "loss": 0.0774, | |
| "num_input_tokens_seen": 2019984, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.744832501781896, | |
| "grad_norm": 3.045757532119751, | |
| "learning_rate": 3.689238007402275e-06, | |
| "loss": 0.0718, | |
| "num_input_tokens_seen": 2026624, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 1.750534568781183, | |
| "grad_norm": 4.732903003692627, | |
| "learning_rate": 3.6812435431273375e-06, | |
| "loss": 0.0642, | |
| "num_input_tokens_seen": 2033136, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 1.7562366357804704, | |
| "grad_norm": 4.424813270568848, | |
| "learning_rate": 3.673233497451541e-06, | |
| "loss": 0.0992, | |
| "num_input_tokens_seen": 2039680, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 1.7619387027797577, | |
| "grad_norm": 2.3566956520080566, | |
| "learning_rate": 3.6652079760328045e-06, | |
| "loss": 0.0325, | |
| "num_input_tokens_seen": 2046096, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 1.767640769779045, | |
| "grad_norm": 3.0203731060028076, | |
| "learning_rate": 3.6571670847331802e-06, | |
| "loss": 0.0403, | |
| "num_input_tokens_seen": 2052432, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.7733428367783322, | |
| "grad_norm": 4.3480753898620605, | |
| "learning_rate": 3.6491109296174604e-06, | |
| "loss": 0.0619, | |
| "num_input_tokens_seen": 2058848, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 1.7790449037776193, | |
| "grad_norm": 4.105159282684326, | |
| "learning_rate": 3.6410396169517763e-06, | |
| "loss": 0.0609, | |
| "num_input_tokens_seen": 2065344, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.7847469707769066, | |
| "grad_norm": 2.991960048675537, | |
| "learning_rate": 3.632953253202199e-06, | |
| "loss": 0.0523, | |
| "num_input_tokens_seen": 2071696, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 1.790449037776194, | |
| "grad_norm": 3.855825662612915, | |
| "learning_rate": 3.624851945033332e-06, | |
| "loss": 0.0481, | |
| "num_input_tokens_seen": 2078736, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 1.7961511047754812, | |
| "grad_norm": 3.1060192584991455, | |
| "learning_rate": 3.6167357993069075e-06, | |
| "loss": 0.0353, | |
| "num_input_tokens_seen": 2085088, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.8018531717747683, | |
| "grad_norm": 2.189758777618408, | |
| "learning_rate": 3.608604923080373e-06, | |
| "loss": 0.0408, | |
| "num_input_tokens_seen": 2091504, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 1.8075552387740554, | |
| "grad_norm": 2.719782590866089, | |
| "learning_rate": 3.6004594236054837e-06, | |
| "loss": 0.0368, | |
| "num_input_tokens_seen": 2097984, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.8132573057733428, | |
| "grad_norm": 4.720352649688721, | |
| "learning_rate": 3.592299408326883e-06, | |
| "loss": 0.0614, | |
| "num_input_tokens_seen": 2104560, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.81895937277263, | |
| "grad_norm": 4.813574314117432, | |
| "learning_rate": 3.584124984880689e-06, | |
| "loss": 0.0328, | |
| "num_input_tokens_seen": 2110832, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 1.8246614397719174, | |
| "grad_norm": 6.9829816818237305, | |
| "learning_rate": 3.5759362610930733e-06, | |
| "loss": 0.0658, | |
| "num_input_tokens_seen": 2117008, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.8303635067712045, | |
| "grad_norm": 3.228569269180298, | |
| "learning_rate": 3.5677333449788376e-06, | |
| "loss": 0.0491, | |
| "num_input_tokens_seen": 2123312, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 1.8360655737704918, | |
| "grad_norm": 3.437143087387085, | |
| "learning_rate": 3.5595163447399912e-06, | |
| "loss": 0.0411, | |
| "num_input_tokens_seen": 2129872, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 1.841767640769779, | |
| "grad_norm": 3.455941677093506, | |
| "learning_rate": 3.551285368764321e-06, | |
| "loss": 0.0281, | |
| "num_input_tokens_seen": 2136688, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 1.8474697077690663, | |
| "grad_norm": 5.369020938873291, | |
| "learning_rate": 3.5430405256239653e-06, | |
| "loss": 0.0319, | |
| "num_input_tokens_seen": 2143184, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.8531717747683536, | |
| "grad_norm": 4.390781402587891, | |
| "learning_rate": 3.5347819240739783e-06, | |
| "loss": 0.0919, | |
| "num_input_tokens_seen": 2149712, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.858873841767641, | |
| "grad_norm": 5.870974540710449, | |
| "learning_rate": 3.5265096730508972e-06, | |
| "loss": 0.069, | |
| "num_input_tokens_seen": 2156432, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 1.864575908766928, | |
| "grad_norm": 3.885589122772217, | |
| "learning_rate": 3.5182238816713055e-06, | |
| "loss": 0.0615, | |
| "num_input_tokens_seen": 2163088, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 1.8702779757662151, | |
| "grad_norm": 4.062203407287598, | |
| "learning_rate": 3.509924659230392e-06, | |
| "loss": 0.046, | |
| "num_input_tokens_seen": 2169664, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 1.8759800427655025, | |
| "grad_norm": 4.7195000648498535, | |
| "learning_rate": 3.5016121152005123e-06, | |
| "loss": 0.0317, | |
| "num_input_tokens_seen": 2176272, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 1.8816821097647898, | |
| "grad_norm": 3.965040922164917, | |
| "learning_rate": 3.4932863592297393e-06, | |
| "loss": 0.0614, | |
| "num_input_tokens_seen": 2182736, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.887384176764077, | |
| "grad_norm": 6.761993885040283, | |
| "learning_rate": 3.4849475011404242e-06, | |
| "loss": 0.0651, | |
| "num_input_tokens_seen": 2189824, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 1.8930862437633642, | |
| "grad_norm": 3.391899585723877, | |
| "learning_rate": 3.4765956509277416e-06, | |
| "loss": 0.0283, | |
| "num_input_tokens_seen": 2196400, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 1.8987883107626513, | |
| "grad_norm": 3.1956787109375, | |
| "learning_rate": 3.4682309187582425e-06, | |
| "loss": 0.0406, | |
| "num_input_tokens_seen": 2202896, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.9044903777619386, | |
| "grad_norm": 3.3207476139068604, | |
| "learning_rate": 3.459853414968398e-06, | |
| "loss": 0.029, | |
| "num_input_tokens_seen": 2209552, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 1.910192444761226, | |
| "grad_norm": 4.4404616355896, | |
| "learning_rate": 3.451463250063146e-06, | |
| "loss": 0.0202, | |
| "num_input_tokens_seen": 2215920, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.9158945117605133, | |
| "grad_norm": 2.3631815910339355, | |
| "learning_rate": 3.443060534714434e-06, | |
| "loss": 0.0246, | |
| "num_input_tokens_seen": 2222384, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.9215965787598004, | |
| "grad_norm": 5.453686714172363, | |
| "learning_rate": 3.4346453797597577e-06, | |
| "loss": 0.0755, | |
| "num_input_tokens_seen": 2228864, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.9272986457590877, | |
| "grad_norm": 1.8340721130371094, | |
| "learning_rate": 3.4262178962006994e-06, | |
| "loss": 0.0162, | |
| "num_input_tokens_seen": 2235328, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 1.9330007127583748, | |
| "grad_norm": 1.1222234964370728, | |
| "learning_rate": 3.4177781952014646e-06, | |
| "loss": 0.0127, | |
| "num_input_tokens_seen": 2241760, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 1.9387027797576621, | |
| "grad_norm": 2.823270082473755, | |
| "learning_rate": 3.409326388087414e-06, | |
| "loss": 0.0225, | |
| "num_input_tokens_seen": 2247968, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.9444048467569495, | |
| "grad_norm": 5.46552038192749, | |
| "learning_rate": 3.400862586343597e-06, | |
| "loss": 0.0556, | |
| "num_input_tokens_seen": 2254528, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 1.9501069137562368, | |
| "grad_norm": 3.3685600757598877, | |
| "learning_rate": 3.3923869016132816e-06, | |
| "loss": 0.0282, | |
| "num_input_tokens_seen": 2260928, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.955808980755524, | |
| "grad_norm": 1.8859189748764038, | |
| "learning_rate": 3.3838994456964774e-06, | |
| "loss": 0.0222, | |
| "num_input_tokens_seen": 2268016, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 1.961511047754811, | |
| "grad_norm": 6.896831035614014, | |
| "learning_rate": 3.375400330548466e-06, | |
| "loss": 0.0387, | |
| "num_input_tokens_seen": 2274592, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 1.9672131147540983, | |
| "grad_norm": 5.995792388916016, | |
| "learning_rate": 3.3668896682783216e-06, | |
| "loss": 0.0589, | |
| "num_input_tokens_seen": 2281216, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.9729151817533856, | |
| "grad_norm": 7.283161640167236, | |
| "learning_rate": 3.358367571147433e-06, | |
| "loss": 0.1223, | |
| "num_input_tokens_seen": 2287680, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 1.978617248752673, | |
| "grad_norm": 7.267601013183594, | |
| "learning_rate": 3.3498341515680216e-06, | |
| "loss": 0.0546, | |
| "num_input_tokens_seen": 2294592, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 1.98431931575196, | |
| "grad_norm": 5.150763511657715, | |
| "learning_rate": 3.3412895221016605e-06, | |
| "loss": 0.0686, | |
| "num_input_tokens_seen": 2301120, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.9900213827512472, | |
| "grad_norm": 4.490513801574707, | |
| "learning_rate": 3.3327337954577893e-06, | |
| "loss": 0.0316, | |
| "num_input_tokens_seen": 2307552, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 1.9957234497505345, | |
| "grad_norm": 4.953909873962402, | |
| "learning_rate": 3.324167084492226e-06, | |
| "loss": 0.036, | |
| "num_input_tokens_seen": 2314048, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.001425516749822, | |
| "grad_norm": 3.9158685207366943, | |
| "learning_rate": 3.315589502205678e-06, | |
| "loss": 0.0681, | |
| "num_input_tokens_seen": 2320912, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 2.007127583749109, | |
| "grad_norm": 1.852107286453247, | |
| "learning_rate": 3.3070011617422564e-06, | |
| "loss": 0.0133, | |
| "num_input_tokens_seen": 2327488, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 2.0128296507483965, | |
| "grad_norm": 2.2540292739868164, | |
| "learning_rate": 3.2984021763879757e-06, | |
| "loss": 0.0086, | |
| "num_input_tokens_seen": 2334432, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 2.0185317177476834, | |
| "grad_norm": 1.3720698356628418, | |
| "learning_rate": 3.2897926595692663e-06, | |
| "loss": 0.0066, | |
| "num_input_tokens_seen": 2341136, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 2.0242337847469707, | |
| "grad_norm": 1.604500651359558, | |
| "learning_rate": 3.281172724851476e-06, | |
| "loss": 0.0137, | |
| "num_input_tokens_seen": 2347680, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.029935851746258, | |
| "grad_norm": 1.1898442506790161, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.0104, | |
| "num_input_tokens_seen": 2354352, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 2.0356379187455453, | |
| "grad_norm": 2.400050640106201, | |
| "learning_rate": 3.2639020566656316e-06, | |
| "loss": 0.029, | |
| "num_input_tokens_seen": 2360912, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 2.0413399857448327, | |
| "grad_norm": 6.066676139831543, | |
| "learning_rate": 3.2552515510093674e-06, | |
| "loss": 0.0628, | |
| "num_input_tokens_seen": 2367552, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 2.0470420527441195, | |
| "grad_norm": 3.0650413036346436, | |
| "learning_rate": 3.2465910830745926e-06, | |
| "loss": 0.0492, | |
| "num_input_tokens_seen": 2373888, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 2.052744119743407, | |
| "grad_norm": 3.076413154602051, | |
| "learning_rate": 3.2379207670987352e-06, | |
| "loss": 0.0217, | |
| "num_input_tokens_seen": 2380528, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.058446186742694, | |
| "grad_norm": 5.445115089416504, | |
| "learning_rate": 3.2292407174491224e-06, | |
| "loss": 0.01, | |
| "num_input_tokens_seen": 2387584, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 2.0641482537419815, | |
| "grad_norm": 2.9979920387268066, | |
| "learning_rate": 3.2205510486214783e-06, | |
| "loss": 0.0193, | |
| "num_input_tokens_seen": 2394560, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 2.069850320741269, | |
| "grad_norm": 2.777930736541748, | |
| "learning_rate": 3.211851875238408e-06, | |
| "loss": 0.016, | |
| "num_input_tokens_seen": 2401232, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 2.075552387740556, | |
| "grad_norm": 0.7351799607276917, | |
| "learning_rate": 3.2031433120478894e-06, | |
| "loss": 0.0025, | |
| "num_input_tokens_seen": 2407888, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 2.081254454739843, | |
| "grad_norm": 0.19965003430843353, | |
| "learning_rate": 3.1944254739217584e-06, | |
| "loss": 0.002, | |
| "num_input_tokens_seen": 2414288, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.0869565217391304, | |
| "grad_norm": 1.0815672874450684, | |
| "learning_rate": 3.1856984758541924e-06, | |
| "loss": 0.0113, | |
| "num_input_tokens_seen": 2420768, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 2.0926585887384177, | |
| "grad_norm": 1.7040127515792847, | |
| "learning_rate": 3.176962432960197e-06, | |
| "loss": 0.0047, | |
| "num_input_tokens_seen": 2427280, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 2.098360655737705, | |
| "grad_norm": 2.0529940128326416, | |
| "learning_rate": 3.1682174604740808e-06, | |
| "loss": 0.0186, | |
| "num_input_tokens_seen": 2433824, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 2.1040627227369924, | |
| "grad_norm": 0.9493989944458008, | |
| "learning_rate": 3.159463673747945e-06, | |
| "loss": 0.0033, | |
| "num_input_tokens_seen": 2440416, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 2.1097647897362792, | |
| "grad_norm": 3.0499930381774902, | |
| "learning_rate": 3.150701188250153e-06, | |
| "loss": 0.0344, | |
| "num_input_tokens_seen": 2446928, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.1154668567355666, | |
| "grad_norm": 5.7982177734375, | |
| "learning_rate": 3.141930119563812e-06, | |
| "loss": 0.0362, | |
| "num_input_tokens_seen": 2453664, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 2.121168923734854, | |
| "grad_norm": 0.2506842017173767, | |
| "learning_rate": 3.133150583385247e-06, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 2460256, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 2.126870990734141, | |
| "grad_norm": 1.3631197214126587, | |
| "learning_rate": 3.1243626955224766e-06, | |
| "loss": 0.0317, | |
| "num_input_tokens_seen": 2466912, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 2.1325730577334285, | |
| "grad_norm": 2.615264892578125, | |
| "learning_rate": 3.1155665718936806e-06, | |
| "loss": 0.0158, | |
| "num_input_tokens_seen": 2473936, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 2.1382751247327154, | |
| "grad_norm": 3.0895676612854004, | |
| "learning_rate": 3.106762328525677e-06, | |
| "loss": 0.0154, | |
| "num_input_tokens_seen": 2480640, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.1439771917320027, | |
| "grad_norm": 2.583371639251709, | |
| "learning_rate": 3.0979500815523865e-06, | |
| "loss": 0.0178, | |
| "num_input_tokens_seen": 2487152, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 2.14967925873129, | |
| "grad_norm": 8.645212173461914, | |
| "learning_rate": 3.089129947213305e-06, | |
| "loss": 0.0686, | |
| "num_input_tokens_seen": 2493664, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 2.1553813257305774, | |
| "grad_norm": 5.1428046226501465, | |
| "learning_rate": 3.0803020418519666e-06, | |
| "loss": 0.0289, | |
| "num_input_tokens_seen": 2500336, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.1610833927298647, | |
| "grad_norm": 6.207760810852051, | |
| "learning_rate": 3.071466481914409e-06, | |
| "loss": 0.0122, | |
| "num_input_tokens_seen": 2507360, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 2.1667854597291516, | |
| "grad_norm": 2.8542068004608154, | |
| "learning_rate": 3.0626233839476434e-06, | |
| "loss": 0.0258, | |
| "num_input_tokens_seen": 2513872, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.172487526728439, | |
| "grad_norm": 0.9682677388191223, | |
| "learning_rate": 3.053772864598108e-06, | |
| "loss": 0.0033, | |
| "num_input_tokens_seen": 2520208, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 2.1781895937277262, | |
| "grad_norm": 1.7404452562332153, | |
| "learning_rate": 3.0449150406101367e-06, | |
| "loss": 0.01, | |
| "num_input_tokens_seen": 2526752, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 2.1838916607270136, | |
| "grad_norm": 5.735099792480469, | |
| "learning_rate": 3.0360500288244155e-06, | |
| "loss": 0.0185, | |
| "num_input_tokens_seen": 2532784, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 2.189593727726301, | |
| "grad_norm": 5.3574748039245605, | |
| "learning_rate": 3.0271779461764427e-06, | |
| "loss": 0.0171, | |
| "num_input_tokens_seen": 2539456, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 2.1952957947255882, | |
| "grad_norm": 3.465667486190796, | |
| "learning_rate": 3.018298909694986e-06, | |
| "loss": 0.0049, | |
| "num_input_tokens_seen": 2546144, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.200997861724875, | |
| "grad_norm": 1.0288059711456299, | |
| "learning_rate": 3.00941303650054e-06, | |
| "loss": 0.0044, | |
| "num_input_tokens_seen": 2552768, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 2.2066999287241624, | |
| "grad_norm": 1.7451399564743042, | |
| "learning_rate": 3.0005204438037767e-06, | |
| "loss": 0.0218, | |
| "num_input_tokens_seen": 2559248, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 2.2124019957234498, | |
| "grad_norm": 4.361851215362549, | |
| "learning_rate": 2.991621248904007e-06, | |
| "loss": 0.026, | |
| "num_input_tokens_seen": 2566096, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 2.218104062722737, | |
| "grad_norm": 1.2106692790985107, | |
| "learning_rate": 2.9827155691876266e-06, | |
| "loss": 0.0037, | |
| "num_input_tokens_seen": 2572944, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 2.2238061297220244, | |
| "grad_norm": 1.0988516807556152, | |
| "learning_rate": 2.973803522126571e-06, | |
| "loss": 0.0031, | |
| "num_input_tokens_seen": 2579600, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.2295081967213113, | |
| "grad_norm": 1.429746150970459, | |
| "learning_rate": 2.964885225276767e-06, | |
| "loss": 0.0188, | |
| "num_input_tokens_seen": 2586624, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 2.2352102637205986, | |
| "grad_norm": 2.6677236557006836, | |
| "learning_rate": 2.9559607962765773e-06, | |
| "loss": 0.0302, | |
| "num_input_tokens_seen": 2593600, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 2.240912330719886, | |
| "grad_norm": 2.7065508365631104, | |
| "learning_rate": 2.947030352845255e-06, | |
| "loss": 0.0205, | |
| "num_input_tokens_seen": 2600224, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 2.2466143977191733, | |
| "grad_norm": 5.244087219238281, | |
| "learning_rate": 2.9380940127813834e-06, | |
| "loss": 0.0347, | |
| "num_input_tokens_seen": 2606704, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 2.2523164647184606, | |
| "grad_norm": 5.431631088256836, | |
| "learning_rate": 2.9291518939613317e-06, | |
| "loss": 0.065, | |
| "num_input_tokens_seen": 2612816, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 2.258018531717748, | |
| "grad_norm": 7.171090126037598, | |
| "learning_rate": 2.9202041143376895e-06, | |
| "loss": 0.0662, | |
| "num_input_tokens_seen": 2619840, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 2.263720598717035, | |
| "grad_norm": 2.2391579151153564, | |
| "learning_rate": 2.9112507919377213e-06, | |
| "loss": 0.0348, | |
| "num_input_tokens_seen": 2626400, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 2.269422665716322, | |
| "grad_norm": 5.090347766876221, | |
| "learning_rate": 2.9022920448618e-06, | |
| "loss": 0.0105, | |
| "num_input_tokens_seen": 2632928, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 2.2751247327156094, | |
| "grad_norm": 5.373437881469727, | |
| "learning_rate": 2.893327991281857e-06, | |
| "loss": 0.0478, | |
| "num_input_tokens_seen": 2639488, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 2.2808267997148968, | |
| "grad_norm": 2.078587770462036, | |
| "learning_rate": 2.8843587494398177e-06, | |
| "loss": 0.0048, | |
| "num_input_tokens_seen": 2645696, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.2865288667141836, | |
| "grad_norm": 4.209392070770264, | |
| "learning_rate": 2.8753844376460462e-06, | |
| "loss": 0.0416, | |
| "num_input_tokens_seen": 2652768, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 2.292230933713471, | |
| "grad_norm": 1.7363594770431519, | |
| "learning_rate": 2.8664051742777803e-06, | |
| "loss": 0.009, | |
| "num_input_tokens_seen": 2659600, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 2.2979330007127583, | |
| "grad_norm": 2.1213040351867676, | |
| "learning_rate": 2.857421077777576e-06, | |
| "loss": 0.0145, | |
| "num_input_tokens_seen": 2666608, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 2.3036350677120456, | |
| "grad_norm": 1.049506664276123, | |
| "learning_rate": 2.8484322666517373e-06, | |
| "loss": 0.0239, | |
| "num_input_tokens_seen": 2673408, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 2.309337134711333, | |
| "grad_norm": 1.5871895551681519, | |
| "learning_rate": 2.83943885946876e-06, | |
| "loss": 0.0151, | |
| "num_input_tokens_seen": 2679824, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 2.3150392017106203, | |
| "grad_norm": 2.483149766921997, | |
| "learning_rate": 2.8304409748577655e-06, | |
| "loss": 0.0597, | |
| "num_input_tokens_seen": 2686608, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 2.320741268709907, | |
| "grad_norm": 1.4659909009933472, | |
| "learning_rate": 2.821438731506933e-06, | |
| "loss": 0.0213, | |
| "num_input_tokens_seen": 2693728, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 2.3264433357091945, | |
| "grad_norm": 2.8195438385009766, | |
| "learning_rate": 2.8124322481619388e-06, | |
| "loss": 0.0197, | |
| "num_input_tokens_seen": 2700240, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 2.332145402708482, | |
| "grad_norm": 6.738165855407715, | |
| "learning_rate": 2.803421643624386e-06, | |
| "loss": 0.0435, | |
| "num_input_tokens_seen": 2706592, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 2.337847469707769, | |
| "grad_norm": 1.9087073802947998, | |
| "learning_rate": 2.7944070367502404e-06, | |
| "loss": 0.0127, | |
| "num_input_tokens_seen": 2712960, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.3435495367070565, | |
| "grad_norm": 0.8072167038917542, | |
| "learning_rate": 2.7853885464482594e-06, | |
| "loss": 0.0123, | |
| "num_input_tokens_seen": 2719648, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 2.3492516037063433, | |
| "grad_norm": 3.834771156311035, | |
| "learning_rate": 2.7763662916784285e-06, | |
| "loss": 0.0331, | |
| "num_input_tokens_seen": 2726672, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 2.3549536707056307, | |
| "grad_norm": 2.7633399963378906, | |
| "learning_rate": 2.767340391450384e-06, | |
| "loss": 0.0507, | |
| "num_input_tokens_seen": 2733520, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 2.360655737704918, | |
| "grad_norm": 1.5225905179977417, | |
| "learning_rate": 2.758310964821855e-06, | |
| "loss": 0.0447, | |
| "num_input_tokens_seen": 2740208, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 2.3663578047042053, | |
| "grad_norm": 1.4298495054244995, | |
| "learning_rate": 2.7492781308970805e-06, | |
| "loss": 0.0252, | |
| "num_input_tokens_seen": 2746560, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 2.3720598717034926, | |
| "grad_norm": 1.6047407388687134, | |
| "learning_rate": 2.7402420088252472e-06, | |
| "loss": 0.0117, | |
| "num_input_tokens_seen": 2752672, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 2.37776193870278, | |
| "grad_norm": 1.5428413152694702, | |
| "learning_rate": 2.7312027177989132e-06, | |
| "loss": 0.0149, | |
| "num_input_tokens_seen": 2759168, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 2.383464005702067, | |
| "grad_norm": 0.30333733558654785, | |
| "learning_rate": 2.7221603770524374e-06, | |
| "loss": 0.0038, | |
| "num_input_tokens_seen": 2765680, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 2.389166072701354, | |
| "grad_norm": 6.950188636779785, | |
| "learning_rate": 2.713115105860407e-06, | |
| "loss": 0.0374, | |
| "num_input_tokens_seen": 2772480, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 2.3948681397006415, | |
| "grad_norm": 1.8761096000671387, | |
| "learning_rate": 2.7040670235360643e-06, | |
| "loss": 0.0246, | |
| "num_input_tokens_seen": 2779072, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.400570206699929, | |
| "grad_norm": 3.416837453842163, | |
| "learning_rate": 2.6950162494297316e-06, | |
| "loss": 0.0363, | |
| "num_input_tokens_seen": 2785536, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 2.406272273699216, | |
| "grad_norm": 0.9194361567497253, | |
| "learning_rate": 2.6859629029272365e-06, | |
| "loss": 0.0197, | |
| "num_input_tokens_seen": 2792192, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 2.411974340698503, | |
| "grad_norm": 1.3932160139083862, | |
| "learning_rate": 2.676907103448341e-06, | |
| "loss": 0.0113, | |
| "num_input_tokens_seen": 2798992, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 2.4176764076977904, | |
| "grad_norm": 5.138923168182373, | |
| "learning_rate": 2.667848970445161e-06, | |
| "loss": 0.0255, | |
| "num_input_tokens_seen": 2805360, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 2.4233784746970777, | |
| "grad_norm": 2.4364206790924072, | |
| "learning_rate": 2.658788623400595e-06, | |
| "loss": 0.0184, | |
| "num_input_tokens_seen": 2812000, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.429080541696365, | |
| "grad_norm": 3.580717086791992, | |
| "learning_rate": 2.6497261818267438e-06, | |
| "loss": 0.0397, | |
| "num_input_tokens_seen": 2818752, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 2.4347826086956523, | |
| "grad_norm": 2.4379868507385254, | |
| "learning_rate": 2.6406617652633405e-06, | |
| "loss": 0.0242, | |
| "num_input_tokens_seen": 2825616, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 2.4404846756949397, | |
| "grad_norm": 2.464996337890625, | |
| "learning_rate": 2.6315954932761645e-06, | |
| "loss": 0.0168, | |
| "num_input_tokens_seen": 2832384, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 2.4461867426942265, | |
| "grad_norm": 1.3222076892852783, | |
| "learning_rate": 2.6225274854554733e-06, | |
| "loss": 0.0034, | |
| "num_input_tokens_seen": 2839152, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 2.451888809693514, | |
| "grad_norm": 1.6748195886611938, | |
| "learning_rate": 2.61345786141442e-06, | |
| "loss": 0.0063, | |
| "num_input_tokens_seen": 2845856, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.457590876692801, | |
| "grad_norm": 2.3060872554779053, | |
| "learning_rate": 2.6043867407874774e-06, | |
| "loss": 0.0229, | |
| "num_input_tokens_seen": 2852736, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 2.4632929436920885, | |
| "grad_norm": 0.5100630521774292, | |
| "learning_rate": 2.5953142432288573e-06, | |
| "loss": 0.0047, | |
| "num_input_tokens_seen": 2859456, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.4689950106913754, | |
| "grad_norm": 1.8006185293197632, | |
| "learning_rate": 2.5862404884109366e-06, | |
| "loss": 0.0271, | |
| "num_input_tokens_seen": 2866016, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 2.4746970776906627, | |
| "grad_norm": 1.213702917098999, | |
| "learning_rate": 2.5771655960226753e-06, | |
| "loss": 0.0041, | |
| "num_input_tokens_seen": 2872448, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 2.48039914468995, | |
| "grad_norm": 1.6707085371017456, | |
| "learning_rate": 2.568089685768038e-06, | |
| "loss": 0.015, | |
| "num_input_tokens_seen": 2879088, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 2.4861012116892374, | |
| "grad_norm": 5.4278059005737305, | |
| "learning_rate": 2.559012877364417e-06, | |
| "loss": 0.042, | |
| "num_input_tokens_seen": 2885408, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 2.4918032786885247, | |
| "grad_norm": 1.1846269369125366, | |
| "learning_rate": 2.54993529054105e-06, | |
| "loss": 0.0099, | |
| "num_input_tokens_seen": 2891936, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 2.497505345687812, | |
| "grad_norm": 3.3710663318634033, | |
| "learning_rate": 2.5408570450374452e-06, | |
| "loss": 0.0215, | |
| "num_input_tokens_seen": 2898304, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 2.5032074126870993, | |
| "grad_norm": 0.21116487681865692, | |
| "learning_rate": 2.531778260601796e-06, | |
| "loss": 0.0013, | |
| "num_input_tokens_seen": 2905200, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 2.5089094796863862, | |
| "grad_norm": 0.9096330404281616, | |
| "learning_rate": 2.522699056989408e-06, | |
| "loss": 0.0248, | |
| "num_input_tokens_seen": 2911648, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.5146115466856735, | |
| "grad_norm": 4.185869216918945, | |
| "learning_rate": 2.5136195539611135e-06, | |
| "loss": 0.034, | |
| "num_input_tokens_seen": 2918864, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 2.520313613684961, | |
| "grad_norm": 5.981312274932861, | |
| "learning_rate": 2.5045398712816954e-06, | |
| "loss": 0.0484, | |
| "num_input_tokens_seen": 2925648, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 2.526015680684248, | |
| "grad_norm": 4.155544757843018, | |
| "learning_rate": 2.4954601287183054e-06, | |
| "loss": 0.0519, | |
| "num_input_tokens_seen": 2932368, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 2.531717747683535, | |
| "grad_norm": 1.5854977369308472, | |
| "learning_rate": 2.4863804460388877e-06, | |
| "loss": 0.0088, | |
| "num_input_tokens_seen": 2938752, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 2.5374198146828224, | |
| "grad_norm": 1.6894891262054443, | |
| "learning_rate": 2.4773009430105923e-06, | |
| "loss": 0.0249, | |
| "num_input_tokens_seen": 2945280, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 2.5431218816821097, | |
| "grad_norm": 0.4828067719936371, | |
| "learning_rate": 2.468221739398205e-06, | |
| "loss": 0.0041, | |
| "num_input_tokens_seen": 2952048, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 2.548823948681397, | |
| "grad_norm": 1.1254082918167114, | |
| "learning_rate": 2.459142954962555e-06, | |
| "loss": 0.0058, | |
| "num_input_tokens_seen": 2958848, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 2.5545260156806844, | |
| "grad_norm": 1.2685133218765259, | |
| "learning_rate": 2.4500647094589507e-06, | |
| "loss": 0.0053, | |
| "num_input_tokens_seen": 2965264, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 2.5602280826799717, | |
| "grad_norm": 2.40993595123291, | |
| "learning_rate": 2.4409871226355835e-06, | |
| "loss": 0.0212, | |
| "num_input_tokens_seen": 2971920, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 2.5659301496792586, | |
| "grad_norm": 1.316887617111206, | |
| "learning_rate": 2.4319103142319624e-06, | |
| "loss": 0.0074, | |
| "num_input_tokens_seen": 2978368, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.571632216678546, | |
| "grad_norm": 0.8872145414352417, | |
| "learning_rate": 2.422834403977325e-06, | |
| "loss": 0.0075, | |
| "num_input_tokens_seen": 2985168, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 2.5773342836778332, | |
| "grad_norm": 1.6685765981674194, | |
| "learning_rate": 2.413759511589064e-06, | |
| "loss": 0.0119, | |
| "num_input_tokens_seen": 2991744, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 2.5830363506771206, | |
| "grad_norm": 2.919286012649536, | |
| "learning_rate": 2.404685756771143e-06, | |
| "loss": 0.0231, | |
| "num_input_tokens_seen": 2998320, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 2.5887384176764074, | |
| "grad_norm": 1.551300287246704, | |
| "learning_rate": 2.3956132592125234e-06, | |
| "loss": 0.0046, | |
| "num_input_tokens_seen": 3005056, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 2.5944404846756948, | |
| "grad_norm": 5.427515983581543, | |
| "learning_rate": 2.3865421385855807e-06, | |
| "loss": 0.0071, | |
| "num_input_tokens_seen": 3011696, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 2.600142551674982, | |
| "grad_norm": 2.1635303497314453, | |
| "learning_rate": 2.3774725145445276e-06, | |
| "loss": 0.0148, | |
| "num_input_tokens_seen": 3018416, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 2.6058446186742694, | |
| "grad_norm": 0.261139839887619, | |
| "learning_rate": 2.3684045067238363e-06, | |
| "loss": 0.0011, | |
| "num_input_tokens_seen": 3025040, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 2.6115466856735567, | |
| "grad_norm": 0.7715526819229126, | |
| "learning_rate": 2.359338234736661e-06, | |
| "loss": 0.005, | |
| "num_input_tokens_seen": 3031472, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 2.617248752672844, | |
| "grad_norm": 1.2660444974899292, | |
| "learning_rate": 2.3502738181732566e-06, | |
| "loss": 0.0348, | |
| "num_input_tokens_seen": 3038176, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "grad_norm": 0.49736925959587097, | |
| "learning_rate": 2.341211376599406e-06, | |
| "loss": 0.0024, | |
| "num_input_tokens_seen": 3044592, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.6286528866714183, | |
| "grad_norm": 0.3166240155696869, | |
| "learning_rate": 2.3321510295548396e-06, | |
| "loss": 0.0013, | |
| "num_input_tokens_seen": 3050976, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 2.6343549536707056, | |
| "grad_norm": 2.3578577041625977, | |
| "learning_rate": 2.32309289655166e-06, | |
| "loss": 0.0408, | |
| "num_input_tokens_seen": 3057568, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 2.640057020669993, | |
| "grad_norm": 2.359955310821533, | |
| "learning_rate": 2.3140370970727644e-06, | |
| "loss": 0.0069, | |
| "num_input_tokens_seen": 3064288, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 2.6457590876692803, | |
| "grad_norm": 1.4914777278900146, | |
| "learning_rate": 2.30498375057027e-06, | |
| "loss": 0.0382, | |
| "num_input_tokens_seen": 3070832, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 2.651461154668567, | |
| "grad_norm": 2.532496213912964, | |
| "learning_rate": 2.2959329764639366e-06, | |
| "loss": 0.0179, | |
| "num_input_tokens_seen": 3076992, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 2.6571632216678545, | |
| "grad_norm": 3.0252954959869385, | |
| "learning_rate": 2.286884894139594e-06, | |
| "loss": 0.0073, | |
| "num_input_tokens_seen": 3083632, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 2.662865288667142, | |
| "grad_norm": 2.534813165664673, | |
| "learning_rate": 2.2778396229475634e-06, | |
| "loss": 0.06, | |
| "num_input_tokens_seen": 3090128, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 2.668567355666429, | |
| "grad_norm": 1.6760576963424683, | |
| "learning_rate": 2.2687972822010885e-06, | |
| "loss": 0.0443, | |
| "num_input_tokens_seen": 3096768, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 2.6742694226657164, | |
| "grad_norm": 2.89322829246521, | |
| "learning_rate": 2.259757991174753e-06, | |
| "loss": 0.0082, | |
| "num_input_tokens_seen": 3103104, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 2.6799714896650038, | |
| "grad_norm": 2.089461088180542, | |
| "learning_rate": 2.2507218691029204e-06, | |
| "loss": 0.0036, | |
| "num_input_tokens_seen": 3109616, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.6856735566642906, | |
| "grad_norm": 2.481194019317627, | |
| "learning_rate": 2.2416890351781452e-06, | |
| "loss": 0.0129, | |
| "num_input_tokens_seen": 3116432, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 2.691375623663578, | |
| "grad_norm": 2.657470703125, | |
| "learning_rate": 2.2326596085496166e-06, | |
| "loss": 0.0122, | |
| "num_input_tokens_seen": 3123232, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 2.6970776906628653, | |
| "grad_norm": 2.6968326568603516, | |
| "learning_rate": 2.2236337083215727e-06, | |
| "loss": 0.0285, | |
| "num_input_tokens_seen": 3129664, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 2.7027797576621526, | |
| "grad_norm": 2.0984086990356445, | |
| "learning_rate": 2.2146114535517415e-06, | |
| "loss": 0.0132, | |
| "num_input_tokens_seen": 3136128, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 2.7084818246614395, | |
| "grad_norm": 3.109532117843628, | |
| "learning_rate": 2.20559296324976e-06, | |
| "loss": 0.0359, | |
| "num_input_tokens_seen": 3142960, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.714183891660727, | |
| "grad_norm": 0.43073195219039917, | |
| "learning_rate": 2.1965783563756148e-06, | |
| "loss": 0.0039, | |
| "num_input_tokens_seen": 3149216, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 2.719885958660014, | |
| "grad_norm": 1.3117117881774902, | |
| "learning_rate": 2.1875677518380616e-06, | |
| "loss": 0.0151, | |
| "num_input_tokens_seen": 3155840, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 2.7255880256593015, | |
| "grad_norm": 3.4339799880981445, | |
| "learning_rate": 2.178561268493068e-06, | |
| "loss": 0.0406, | |
| "num_input_tokens_seen": 3162176, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 2.731290092658589, | |
| "grad_norm": 0.5435781478881836, | |
| "learning_rate": 2.1695590251422353e-06, | |
| "loss": 0.0055, | |
| "num_input_tokens_seen": 3168528, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 2.736992159657876, | |
| "grad_norm": 3.829059600830078, | |
| "learning_rate": 2.1605611405312406e-06, | |
| "loss": 0.0414, | |
| "num_input_tokens_seen": 3175296, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.7426942266571634, | |
| "grad_norm": 2.039680242538452, | |
| "learning_rate": 2.1515677333482635e-06, | |
| "loss": 0.0199, | |
| "num_input_tokens_seen": 3182112, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 2.7483962936564503, | |
| "grad_norm": 0.9767200946807861, | |
| "learning_rate": 2.1425789222224254e-06, | |
| "loss": 0.0141, | |
| "num_input_tokens_seen": 3189008, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 2.7540983606557377, | |
| "grad_norm": 2.2033214569091797, | |
| "learning_rate": 2.13359482572222e-06, | |
| "loss": 0.0281, | |
| "num_input_tokens_seen": 3195280, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 2.759800427655025, | |
| "grad_norm": 2.3245043754577637, | |
| "learning_rate": 2.124615562353955e-06, | |
| "loss": 0.0273, | |
| "num_input_tokens_seen": 3201840, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 2.7655024946543123, | |
| "grad_norm": 0.9290107488632202, | |
| "learning_rate": 2.115641250560183e-06, | |
| "loss": 0.0048, | |
| "num_input_tokens_seen": 3208048, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 2.771204561653599, | |
| "grad_norm": 3.848163604736328, | |
| "learning_rate": 2.106672008718144e-06, | |
| "loss": 0.0312, | |
| "num_input_tokens_seen": 3214368, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.7769066286528865, | |
| "grad_norm": 2.497357130050659, | |
| "learning_rate": 2.0977079551382006e-06, | |
| "loss": 0.011, | |
| "num_input_tokens_seen": 3221008, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 2.782608695652174, | |
| "grad_norm": 2.660881519317627, | |
| "learning_rate": 2.08874920806228e-06, | |
| "loss": 0.0109, | |
| "num_input_tokens_seen": 3227584, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 2.788310762651461, | |
| "grad_norm": 1.4301801919937134, | |
| "learning_rate": 2.079795885662311e-06, | |
| "loss": 0.0051, | |
| "num_input_tokens_seen": 3234224, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 2.7940128296507485, | |
| "grad_norm": 1.022800087928772, | |
| "learning_rate": 2.07084810603867e-06, | |
| "loss": 0.0033, | |
| "num_input_tokens_seen": 3240544, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.799714896650036, | |
| "grad_norm": 2.826751708984375, | |
| "learning_rate": 2.0619059872186174e-06, | |
| "loss": 0.0228, | |
| "num_input_tokens_seen": 3247120, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 2.805416963649323, | |
| "grad_norm": 6.670321941375732, | |
| "learning_rate": 2.0529696471547455e-06, | |
| "loss": 0.0192, | |
| "num_input_tokens_seen": 3253744, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 2.81111903064861, | |
| "grad_norm": 3.9984092712402344, | |
| "learning_rate": 2.044039203723423e-06, | |
| "loss": 0.0067, | |
| "num_input_tokens_seen": 3260512, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 2.8168210976478973, | |
| "grad_norm": 4.25165319442749, | |
| "learning_rate": 2.035114774723233e-06, | |
| "loss": 0.0558, | |
| "num_input_tokens_seen": 3267008, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 2.8225231646471847, | |
| "grad_norm": 1.6763029098510742, | |
| "learning_rate": 2.02619647787343e-06, | |
| "loss": 0.0247, | |
| "num_input_tokens_seen": 3273696, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.828225231646472, | |
| "grad_norm": 4.306890964508057, | |
| "learning_rate": 2.017284430812374e-06, | |
| "loss": 0.0501, | |
| "num_input_tokens_seen": 3280368, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 2.833927298645759, | |
| "grad_norm": 4.766158103942871, | |
| "learning_rate": 2.008378751095994e-06, | |
| "loss": 0.0268, | |
| "num_input_tokens_seen": 3287200, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 2.839629365645046, | |
| "grad_norm": 2.9017302989959717, | |
| "learning_rate": 1.9994795561962237e-06, | |
| "loss": 0.0323, | |
| "num_input_tokens_seen": 3293648, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 2.8453314326443335, | |
| "grad_norm": 1.3675230741500854, | |
| "learning_rate": 1.990586963499461e-06, | |
| "loss": 0.0469, | |
| "num_input_tokens_seen": 3300496, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 2.851033499643621, | |
| "grad_norm": 6.752871513366699, | |
| "learning_rate": 1.981701090305014e-06, | |
| "loss": 0.06, | |
| "num_input_tokens_seen": 3306624, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.856735566642908, | |
| "grad_norm": 3.9464950561523438, | |
| "learning_rate": 1.9728220538235577e-06, | |
| "loss": 0.0153, | |
| "num_input_tokens_seen": 3313312, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 2.8624376336421955, | |
| "grad_norm": 0.293773353099823, | |
| "learning_rate": 1.963949971175585e-06, | |
| "loss": 0.0019, | |
| "num_input_tokens_seen": 3319872, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 2.8681397006414824, | |
| "grad_norm": 0.5789422392845154, | |
| "learning_rate": 1.955084959389864e-06, | |
| "loss": 0.0037, | |
| "num_input_tokens_seen": 3326288, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 2.8738417676407697, | |
| "grad_norm": 1.1285568475723267, | |
| "learning_rate": 1.9462271354018925e-06, | |
| "loss": 0.0091, | |
| "num_input_tokens_seen": 3332816, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 2.879543834640057, | |
| "grad_norm": 0.7351142764091492, | |
| "learning_rate": 1.937376616052357e-06, | |
| "loss": 0.0038, | |
| "num_input_tokens_seen": 3339248, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 2.8852459016393444, | |
| "grad_norm": 0.5724226236343384, | |
| "learning_rate": 1.9285335180855906e-06, | |
| "loss": 0.0026, | |
| "num_input_tokens_seen": 3345440, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 2.8909479686386312, | |
| "grad_norm": 4.474715709686279, | |
| "learning_rate": 1.9196979581480347e-06, | |
| "loss": 0.0198, | |
| "num_input_tokens_seen": 3352176, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 2.8966500356379186, | |
| "grad_norm": 4.141156196594238, | |
| "learning_rate": 1.9108700527866954e-06, | |
| "loss": 0.0372, | |
| "num_input_tokens_seen": 3358720, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 2.902352102637206, | |
| "grad_norm": 0.5210357904434204, | |
| "learning_rate": 1.9020499184476137e-06, | |
| "loss": 0.0063, | |
| "num_input_tokens_seen": 3365472, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 2.908054169636493, | |
| "grad_norm": 0.7672094106674194, | |
| "learning_rate": 1.8932376714743237e-06, | |
| "loss": 0.0034, | |
| "num_input_tokens_seen": 3371728, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.9137562366357805, | |
| "grad_norm": 1.55528724193573, | |
| "learning_rate": 1.88443342810632e-06, | |
| "loss": 0.0049, | |
| "num_input_tokens_seen": 3378608, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 2.919458303635068, | |
| "grad_norm": 2.993779420852661, | |
| "learning_rate": 1.8756373044775238e-06, | |
| "loss": 0.0236, | |
| "num_input_tokens_seen": 3385280, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 2.925160370634355, | |
| "grad_norm": 1.1400753259658813, | |
| "learning_rate": 1.8668494166147532e-06, | |
| "loss": 0.0326, | |
| "num_input_tokens_seen": 3391872, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 2.930862437633642, | |
| "grad_norm": 1.8988653421401978, | |
| "learning_rate": 1.8580698804361886e-06, | |
| "loss": 0.0349, | |
| "num_input_tokens_seen": 3398512, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 2.9365645046329294, | |
| "grad_norm": 0.7114527225494385, | |
| "learning_rate": 1.8492988117498478e-06, | |
| "loss": 0.0034, | |
| "num_input_tokens_seen": 3405376, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 2.9422665716322167, | |
| "grad_norm": 3.2026875019073486, | |
| "learning_rate": 1.840536326252055e-06, | |
| "loss": 0.0309, | |
| "num_input_tokens_seen": 3412192, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 2.947968638631504, | |
| "grad_norm": 3.8607699871063232, | |
| "learning_rate": 1.8317825395259199e-06, | |
| "loss": 0.0185, | |
| "num_input_tokens_seen": 3418896, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 2.953670705630791, | |
| "grad_norm": 0.7184828519821167, | |
| "learning_rate": 1.8230375670398037e-06, | |
| "loss": 0.0054, | |
| "num_input_tokens_seen": 3425456, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 2.9593727726300783, | |
| "grad_norm": 8.588293075561523, | |
| "learning_rate": 1.8143015241458082e-06, | |
| "loss": 0.0076, | |
| "num_input_tokens_seen": 3432384, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 2.9650748396293656, | |
| "grad_norm": 1.3687328100204468, | |
| "learning_rate": 1.8055745260782415e-06, | |
| "loss": 0.0191, | |
| "num_input_tokens_seen": 3438928, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.970776906628653, | |
| "grad_norm": 4.8277812004089355, | |
| "learning_rate": 1.7968566879521112e-06, | |
| "loss": 0.0348, | |
| "num_input_tokens_seen": 3445424, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 2.9764789736279402, | |
| "grad_norm": 1.5100287199020386, | |
| "learning_rate": 1.7881481247615923e-06, | |
| "loss": 0.0166, | |
| "num_input_tokens_seen": 3452176, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 2.9821810406272276, | |
| "grad_norm": 4.24040412902832, | |
| "learning_rate": 1.779448951378523e-06, | |
| "loss": 0.0322, | |
| "num_input_tokens_seen": 3458912, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 2.987883107626515, | |
| "grad_norm": 1.88912832736969, | |
| "learning_rate": 1.7707592825508776e-06, | |
| "loss": 0.0063, | |
| "num_input_tokens_seen": 3465136, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 2.9935851746258018, | |
| "grad_norm": 0.41476720571517944, | |
| "learning_rate": 1.7620792329012656e-06, | |
| "loss": 0.0021, | |
| "num_input_tokens_seen": 3471920, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.999287241625089, | |
| "grad_norm": 1.5852344036102295, | |
| "learning_rate": 1.7534089169254076e-06, | |
| "loss": 0.0116, | |
| "num_input_tokens_seen": 3478608, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 3.0049893086243764, | |
| "grad_norm": 0.4748835861682892, | |
| "learning_rate": 1.7447484489906332e-06, | |
| "loss": 0.0027, | |
| "num_input_tokens_seen": 3485232, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 3.0106913756236637, | |
| "grad_norm": 1.6355117559432983, | |
| "learning_rate": 1.7360979433343686e-06, | |
| "loss": 0.0076, | |
| "num_input_tokens_seen": 3491840, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 3.0163934426229506, | |
| "grad_norm": 1.1035512685775757, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.006, | |
| "num_input_tokens_seen": 3498896, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 3.022095509622238, | |
| "grad_norm": 0.10061535239219666, | |
| "learning_rate": 1.7188272751485246e-06, | |
| "loss": 0.0008, | |
| "num_input_tokens_seen": 3505488, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.0277975766215253, | |
| "grad_norm": 1.6864421367645264, | |
| "learning_rate": 1.710207340430734e-06, | |
| "loss": 0.0139, | |
| "num_input_tokens_seen": 3512144, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 3.0334996436208126, | |
| "grad_norm": 1.3023935556411743, | |
| "learning_rate": 1.7015978236120245e-06, | |
| "loss": 0.0123, | |
| "num_input_tokens_seen": 3519008, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 3.0392017106201, | |
| "grad_norm": 0.0782478079199791, | |
| "learning_rate": 1.6929988382577442e-06, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 3525408, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 3.0449037776193872, | |
| "grad_norm": 0.06191781163215637, | |
| "learning_rate": 1.6844104977943219e-06, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 3531744, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 3.050605844618674, | |
| "grad_norm": 0.7478132247924805, | |
| "learning_rate": 1.6758329155077746e-06, | |
| "loss": 0.0025, | |
| "num_input_tokens_seen": 3538240, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 3.0563079116179614, | |
| "grad_norm": 0.1811976581811905, | |
| "learning_rate": 1.667266204542211e-06, | |
| "loss": 0.0008, | |
| "num_input_tokens_seen": 3544944, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 3.0620099786172488, | |
| "grad_norm": 0.06903179734945297, | |
| "learning_rate": 1.6587104778983397e-06, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 3551664, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 3.067712045616536, | |
| "grad_norm": 0.029220720753073692, | |
| "learning_rate": 1.650165848431979e-06, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 3558368, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 3.0734141126158234, | |
| "grad_norm": 3.4635422229766846, | |
| "learning_rate": 1.641632428852568e-06, | |
| "loss": 0.0092, | |
| "num_input_tokens_seen": 3564912, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 3.0791161796151103, | |
| "grad_norm": 2.6266937255859375, | |
| "learning_rate": 1.633110331721679e-06, | |
| "loss": 0.009, | |
| "num_input_tokens_seen": 3571760, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.0848182466143976, | |
| "grad_norm": 4.367438316345215, | |
| "learning_rate": 1.624599669451535e-06, | |
| "loss": 0.0356, | |
| "num_input_tokens_seen": 3578608, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 3.090520313613685, | |
| "grad_norm": 0.09718136489391327, | |
| "learning_rate": 1.6161005543035234e-06, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 3585568, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 3.0962223806129723, | |
| "grad_norm": 0.16700978577136993, | |
| "learning_rate": 1.6076130983867194e-06, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 3592448, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 3.1019244476122596, | |
| "grad_norm": 0.21411505341529846, | |
| "learning_rate": 1.5991374136564033e-06, | |
| "loss": 0.0007, | |
| "num_input_tokens_seen": 3598896, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 3.1076265146115465, | |
| "grad_norm": 0.13308338820934296, | |
| "learning_rate": 1.5906736119125871e-06, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 3605664, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 3.113328581610834, | |
| "grad_norm": 0.09795942157506943, | |
| "learning_rate": 1.582221804798536e-06, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 3612272, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 3.119030648610121, | |
| "grad_norm": 0.03890947997570038, | |
| "learning_rate": 1.5737821037993016e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 3618992, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 3.1247327156094085, | |
| "grad_norm": 0.07518395781517029, | |
| "learning_rate": 1.565354620240243e-06, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 3625584, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 3.130434782608696, | |
| "grad_norm": 0.03526531159877777, | |
| "learning_rate": 1.5569394652855674e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 3631936, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 3.1361368496079827, | |
| "grad_norm": 1.2385015487670898, | |
| "learning_rate": 1.5485367499368547e-06, | |
| "loss": 0.0085, | |
| "num_input_tokens_seen": 3638640, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.14183891660727, | |
| "grad_norm": 0.7123975157737732, | |
| "learning_rate": 1.5401465850316038e-06, | |
| "loss": 0.0007, | |
| "num_input_tokens_seen": 3645248, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 3.1475409836065573, | |
| "grad_norm": 1.5488688945770264, | |
| "learning_rate": 1.5317690812417583e-06, | |
| "loss": 0.002, | |
| "num_input_tokens_seen": 3651696, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 3.1532430506058446, | |
| "grad_norm": 0.1425732523202896, | |
| "learning_rate": 1.5234043490722588e-06, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 3658368, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 3.158945117605132, | |
| "grad_norm": 0.09034785628318787, | |
| "learning_rate": 1.5150524988595764e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 3664944, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 3.1646471846044193, | |
| "grad_norm": 1.720540165901184, | |
| "learning_rate": 1.5067136407702615e-06, | |
| "loss": 0.002, | |
| "num_input_tokens_seen": 3671632, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 3.170349251603706, | |
| "grad_norm": 0.052824657410383224, | |
| "learning_rate": 1.4983878847994888e-06, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 3678288, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 3.1760513186029935, | |
| "grad_norm": 0.19170065224170685, | |
| "learning_rate": 1.4900753407696087e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 3684976, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 3.181753385602281, | |
| "grad_norm": 0.0425780825316906, | |
| "learning_rate": 1.4817761183286949e-06, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 3692000, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 3.187455452601568, | |
| "grad_norm": 2.74068284034729, | |
| "learning_rate": 1.4734903269491036e-06, | |
| "loss": 0.0312, | |
| "num_input_tokens_seen": 3698608, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 3.1931575196008555, | |
| "grad_norm": 0.05014929175376892, | |
| "learning_rate": 1.4652180759260224e-06, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 3705328, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.1988595866001424, | |
| "grad_norm": 0.03240165859460831, | |
| "learning_rate": 1.4569594743760362e-06, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 3711952, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 3.2045616535994297, | |
| "grad_norm": 2.2007806301116943, | |
| "learning_rate": 1.4487146312356797e-06, | |
| "loss": 0.0475, | |
| "num_input_tokens_seen": 3718432, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 3.210263720598717, | |
| "grad_norm": 1.0569113492965698, | |
| "learning_rate": 1.4404836552600102e-06, | |
| "loss": 0.0016, | |
| "num_input_tokens_seen": 3724880, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 3.2159657875980043, | |
| "grad_norm": 0.05176587775349617, | |
| "learning_rate": 1.4322666550211628e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 3731504, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 3.2216678545972917, | |
| "grad_norm": 0.06603796780109406, | |
| "learning_rate": 1.4240637389069284e-06, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 3737728, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 3.227369921596579, | |
| "grad_norm": 1.1058824062347412, | |
| "learning_rate": 1.4158750151193118e-06, | |
| "loss": 0.014, | |
| "num_input_tokens_seen": 3744256, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 3.233071988595866, | |
| "grad_norm": 1.7707825899124146, | |
| "learning_rate": 1.4077005916731178e-06, | |
| "loss": 0.043, | |
| "num_input_tokens_seen": 3751008, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 3.238774055595153, | |
| "grad_norm": 1.7744121551513672, | |
| "learning_rate": 1.399540576394517e-06, | |
| "loss": 0.0283, | |
| "num_input_tokens_seen": 3757888, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 3.2444761225944405, | |
| "grad_norm": 1.144587755203247, | |
| "learning_rate": 1.3913950769196275e-06, | |
| "loss": 0.0137, | |
| "num_input_tokens_seen": 3764400, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 3.250178189593728, | |
| "grad_norm": 1.3597573041915894, | |
| "learning_rate": 1.3832642006930935e-06, | |
| "loss": 0.0249, | |
| "num_input_tokens_seen": 3770816, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.2558802565930147, | |
| "grad_norm": 0.1739058941602707, | |
| "learning_rate": 1.375148054966669e-06, | |
| "loss": 0.0014, | |
| "num_input_tokens_seen": 3777360, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 3.261582323592302, | |
| "grad_norm": 0.8273450136184692, | |
| "learning_rate": 1.3670467467978016e-06, | |
| "loss": 0.0034, | |
| "num_input_tokens_seen": 3783968, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 3.2672843905915894, | |
| "grad_norm": 1.998255968093872, | |
| "learning_rate": 1.3589603830482246e-06, | |
| "loss": 0.0073, | |
| "num_input_tokens_seen": 3790448, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 3.2729864575908767, | |
| "grad_norm": 2.1162617206573486, | |
| "learning_rate": 1.3508890703825406e-06, | |
| "loss": 0.0147, | |
| "num_input_tokens_seen": 3796992, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 3.278688524590164, | |
| "grad_norm": 0.47663643956184387, | |
| "learning_rate": 1.342832915266821e-06, | |
| "loss": 0.0019, | |
| "num_input_tokens_seen": 3803488, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.2843905915894513, | |
| "grad_norm": 1.3029382228851318, | |
| "learning_rate": 1.334792023967196e-06, | |
| "loss": 0.0025, | |
| "num_input_tokens_seen": 3810304, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 3.2900926585887382, | |
| "grad_norm": 0.48294466733932495, | |
| "learning_rate": 1.3267665025484597e-06, | |
| "loss": 0.0018, | |
| "num_input_tokens_seen": 3817072, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 3.2957947255880256, | |
| "grad_norm": 0.5423978567123413, | |
| "learning_rate": 1.3187564568726642e-06, | |
| "loss": 0.0023, | |
| "num_input_tokens_seen": 3824064, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 3.301496792587313, | |
| "grad_norm": 1.4614927768707275, | |
| "learning_rate": 1.3107619925977262e-06, | |
| "loss": 0.0077, | |
| "num_input_tokens_seen": 3830848, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 3.3071988595866, | |
| "grad_norm": 0.24164794385433197, | |
| "learning_rate": 1.3027832151760328e-06, | |
| "loss": 0.0014, | |
| "num_input_tokens_seen": 3837696, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.3129009265858875, | |
| "grad_norm": 0.607139527797699, | |
| "learning_rate": 1.2948202298530544e-06, | |
| "loss": 0.0037, | |
| "num_input_tokens_seen": 3844096, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 3.3186029935851744, | |
| "grad_norm": 1.8388640880584717, | |
| "learning_rate": 1.2868731416659492e-06, | |
| "loss": 0.016, | |
| "num_input_tokens_seen": 3850432, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 3.3243050605844617, | |
| "grad_norm": 0.24856287240982056, | |
| "learning_rate": 1.2789420554421823e-06, | |
| "loss": 0.0014, | |
| "num_input_tokens_seen": 3856992, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 3.330007127583749, | |
| "grad_norm": 3.3995144367218018, | |
| "learning_rate": 1.2710270757981418e-06, | |
| "loss": 0.0307, | |
| "num_input_tokens_seen": 3863664, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 3.3357091945830364, | |
| "grad_norm": 0.22360347211360931, | |
| "learning_rate": 1.263128307137762e-06, | |
| "loss": 0.0011, | |
| "num_input_tokens_seen": 3870512, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 3.3414112615823237, | |
| "grad_norm": 4.8242950439453125, | |
| "learning_rate": 1.255245853651139e-06, | |
| "loss": 0.0187, | |
| "num_input_tokens_seen": 3877264, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 3.347113328581611, | |
| "grad_norm": 1.2942771911621094, | |
| "learning_rate": 1.2473798193131634e-06, | |
| "loss": 0.0092, | |
| "num_input_tokens_seen": 3883936, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 3.352815395580898, | |
| "grad_norm": 0.22458510100841522, | |
| "learning_rate": 1.2395303078821466e-06, | |
| "loss": 0.0016, | |
| "num_input_tokens_seen": 3890464, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 3.3585174625801852, | |
| "grad_norm": 2.22206711769104, | |
| "learning_rate": 1.2316974228984489e-06, | |
| "loss": 0.0118, | |
| "num_input_tokens_seen": 3896720, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 3.3642195295794726, | |
| "grad_norm": 1.945656180381775, | |
| "learning_rate": 1.22388126768312e-06, | |
| "loss": 0.0227, | |
| "num_input_tokens_seen": 3903440, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.36992159657876, | |
| "grad_norm": 1.0150567293167114, | |
| "learning_rate": 1.2160819453365301e-06, | |
| "loss": 0.0084, | |
| "num_input_tokens_seen": 3910112, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 3.375623663578047, | |
| "grad_norm": 1.5612642765045166, | |
| "learning_rate": 1.2082995587370136e-06, | |
| "loss": 0.019, | |
| "num_input_tokens_seen": 3916704, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 3.381325730577334, | |
| "grad_norm": 1.6889121532440186, | |
| "learning_rate": 1.2005342105395094e-06, | |
| "loss": 0.0073, | |
| "num_input_tokens_seen": 3923136, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 3.3870277975766214, | |
| "grad_norm": 0.3054364025592804, | |
| "learning_rate": 1.1927860031742116e-06, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 3929696, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 3.3927298645759087, | |
| "grad_norm": 1.479589581489563, | |
| "learning_rate": 1.1850550388452125e-06, | |
| "loss": 0.0117, | |
| "num_input_tokens_seen": 3936016, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 3.398431931575196, | |
| "grad_norm": 2.0437428951263428, | |
| "learning_rate": 1.177341419529157e-06, | |
| "loss": 0.017, | |
| "num_input_tokens_seen": 3942480, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 3.4041339985744834, | |
| "grad_norm": 1.273624062538147, | |
| "learning_rate": 1.1696452469738984e-06, | |
| "loss": 0.0054, | |
| "num_input_tokens_seen": 3948928, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 3.4098360655737707, | |
| "grad_norm": 0.9993485808372498, | |
| "learning_rate": 1.1619666226971565e-06, | |
| "loss": 0.0041, | |
| "num_input_tokens_seen": 3955248, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 3.4155381325730576, | |
| "grad_norm": 0.3728763163089752, | |
| "learning_rate": 1.1543056479851755e-06, | |
| "loss": 0.002, | |
| "num_input_tokens_seen": 3961760, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 3.421240199572345, | |
| "grad_norm": 0.3200441002845764, | |
| "learning_rate": 1.1466624238913907e-06, | |
| "loss": 0.0022, | |
| "num_input_tokens_seen": 3968112, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.4269422665716323, | |
| "grad_norm": 0.08588572591543198, | |
| "learning_rate": 1.1390370512350936e-06, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 3974864, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 3.4326443335709196, | |
| "grad_norm": 6.460862636566162, | |
| "learning_rate": 1.1314296306001065e-06, | |
| "loss": 0.0148, | |
| "num_input_tokens_seen": 3981296, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 3.4383464005702065, | |
| "grad_norm": 1.9962701797485352, | |
| "learning_rate": 1.1238402623334494e-06, | |
| "loss": 0.049, | |
| "num_input_tokens_seen": 3987648, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 3.444048467569494, | |
| "grad_norm": 0.4922191798686981, | |
| "learning_rate": 1.1162690465440198e-06, | |
| "loss": 0.0027, | |
| "num_input_tokens_seen": 3994208, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 3.449750534568781, | |
| "grad_norm": 0.15748071670532227, | |
| "learning_rate": 1.1087160831012713e-06, | |
| "loss": 0.0007, | |
| "num_input_tokens_seen": 4001280, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 3.4554526015680684, | |
| "grad_norm": 0.9574026465415955, | |
| "learning_rate": 1.1011814716338995e-06, | |
| "loss": 0.006, | |
| "num_input_tokens_seen": 4008128, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 3.4611546685673558, | |
| "grad_norm": 0.867205798625946, | |
| "learning_rate": 1.093665311528521e-06, | |
| "loss": 0.0066, | |
| "num_input_tokens_seen": 4014848, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 3.466856735566643, | |
| "grad_norm": 2.434412717819214, | |
| "learning_rate": 1.0861677019283717e-06, | |
| "loss": 0.0255, | |
| "num_input_tokens_seen": 4021296, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 3.47255880256593, | |
| "grad_norm": 1.8824217319488525, | |
| "learning_rate": 1.0786887417319867e-06, | |
| "loss": 0.0075, | |
| "num_input_tokens_seen": 4027872, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 3.4782608695652173, | |
| "grad_norm": 3.1213793754577637, | |
| "learning_rate": 1.0712285295919092e-06, | |
| "loss": 0.0068, | |
| "num_input_tokens_seen": 4034768, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.4839629365645046, | |
| "grad_norm": 0.11539681255817413, | |
| "learning_rate": 1.0637871639133793e-06, | |
| "loss": 0.0008, | |
| "num_input_tokens_seen": 4041408, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 3.489665003563792, | |
| "grad_norm": 1.6134257316589355, | |
| "learning_rate": 1.056364742853043e-06, | |
| "loss": 0.0132, | |
| "num_input_tokens_seen": 4048256, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 3.4953670705630793, | |
| "grad_norm": 0.3129463493824005, | |
| "learning_rate": 1.048961364317648e-06, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 4055184, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 3.501069137562366, | |
| "grad_norm": 0.39868372678756714, | |
| "learning_rate": 1.0415771259627646e-06, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 4061904, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 3.5067712045616535, | |
| "grad_norm": 0.08058975636959076, | |
| "learning_rate": 1.034212125191487e-06, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 4068560, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 3.512473271560941, | |
| "grad_norm": 0.15611045062541962, | |
| "learning_rate": 1.0268664591531557e-06, | |
| "loss": 0.001, | |
| "num_input_tokens_seen": 4075072, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 3.518175338560228, | |
| "grad_norm": 1.9207406044006348, | |
| "learning_rate": 1.0195402247420705e-06, | |
| "loss": 0.0219, | |
| "num_input_tokens_seen": 4081840, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 3.5238774055595155, | |
| "grad_norm": 0.09913857281208038, | |
| "learning_rate": 1.012233518596216e-06, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 4088512, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 3.5295794725588028, | |
| "grad_norm": 10.642138481140137, | |
| "learning_rate": 1.0049464370959846e-06, | |
| "loss": 0.036, | |
| "num_input_tokens_seen": 4095168, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 3.5352815395580897, | |
| "grad_norm": 5.640021324157715, | |
| "learning_rate": 9.97679076362909e-07, | |
| "loss": 0.0034, | |
| "num_input_tokens_seen": 4102112, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.540983606557377, | |
| "grad_norm": 0.6071515679359436, | |
| "learning_rate": 9.904315322583894e-07, | |
| "loss": 0.0039, | |
| "num_input_tokens_seen": 4108432, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 3.5466856735566643, | |
| "grad_norm": 0.25435176491737366, | |
| "learning_rate": 9.832039003824317e-07, | |
| "loss": 0.0011, | |
| "num_input_tokens_seen": 4115152, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 3.5523877405559516, | |
| "grad_norm": 0.1996757537126541, | |
| "learning_rate": 9.759962760723856e-07, | |
| "loss": 0.0017, | |
| "num_input_tokens_seen": 4121696, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 3.5580898075552385, | |
| "grad_norm": 1.3054097890853882, | |
| "learning_rate": 9.6880875440169e-07, | |
| "loss": 0.0057, | |
| "num_input_tokens_seen": 4128160, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.563791874554526, | |
| "grad_norm": 1.3929048776626587, | |
| "learning_rate": 9.616414301786128e-07, | |
| "loss": 0.0199, | |
| "num_input_tokens_seen": 4134912, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 3.569493941553813, | |
| "grad_norm": 0.8480359315872192, | |
| "learning_rate": 9.544943979450067e-07, | |
| "loss": 0.0294, | |
| "num_input_tokens_seen": 4141504, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 3.5751960085531005, | |
| "grad_norm": 1.4291871786117554, | |
| "learning_rate": 9.473677519750568e-07, | |
| "loss": 0.0124, | |
| "num_input_tokens_seen": 4148144, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 3.580898075552388, | |
| "grad_norm": 0.862804651260376, | |
| "learning_rate": 9.40261586274043e-07, | |
| "loss": 0.0058, | |
| "num_input_tokens_seen": 4154880, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 3.586600142551675, | |
| "grad_norm": 0.9178187847137451, | |
| "learning_rate": 9.331759945770935e-07, | |
| "loss": 0.0113, | |
| "num_input_tokens_seen": 4162240, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 3.5923022095509625, | |
| "grad_norm": 2.0041568279266357, | |
| "learning_rate": 9.261110703479531e-07, | |
| "loss": 0.0058, | |
| "num_input_tokens_seen": 4169008, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.5980042765502493, | |
| "grad_norm": 0.3672866225242615, | |
| "learning_rate": 9.190669067777475e-07, | |
| "loss": 0.0019, | |
| "num_input_tokens_seen": 4175488, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 3.6037063435495367, | |
| "grad_norm": 1.909638524055481, | |
| "learning_rate": 9.120435967837571e-07, | |
| "loss": 0.0443, | |
| "num_input_tokens_seen": 4182208, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 3.609408410548824, | |
| "grad_norm": 3.312385320663452, | |
| "learning_rate": 9.050412330081885e-07, | |
| "loss": 0.0246, | |
| "num_input_tokens_seen": 4188512, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 3.6151104775481113, | |
| "grad_norm": 0.535926342010498, | |
| "learning_rate": 8.980599078169528e-07, | |
| "loss": 0.0039, | |
| "num_input_tokens_seen": 4194992, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 3.620812544547398, | |
| "grad_norm": 2.76286244392395, | |
| "learning_rate": 8.910997132984481e-07, | |
| "loss": 0.0302, | |
| "num_input_tokens_seen": 4201632, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 3.6265146115466855, | |
| "grad_norm": 0.6582239866256714, | |
| "learning_rate": 8.841607412623471e-07, | |
| "loss": 0.0039, | |
| "num_input_tokens_seen": 4208096, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.632216678545973, | |
| "grad_norm": 1.006136417388916, | |
| "learning_rate": 8.772430832383797e-07, | |
| "loss": 0.0096, | |
| "num_input_tokens_seen": 4214720, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 3.63791874554526, | |
| "grad_norm": 4.465051651000977, | |
| "learning_rate": 8.703468304751342e-07, | |
| "loss": 0.0314, | |
| "num_input_tokens_seen": 4221280, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 3.6436208125445475, | |
| "grad_norm": 2.6803739070892334, | |
| "learning_rate": 8.634720739388433e-07, | |
| "loss": 0.0301, | |
| "num_input_tokens_seen": 4227744, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 3.649322879543835, | |
| "grad_norm": 0.1741700917482376, | |
| "learning_rate": 8.566189043121953e-07, | |
| "loss": 0.0012, | |
| "num_input_tokens_seen": 4234240, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.655024946543122, | |
| "grad_norm": 0.14672909677028656, | |
| "learning_rate": 8.49787411993129e-07, | |
| "loss": 0.001, | |
| "num_input_tokens_seen": 4240640, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 3.660727013542409, | |
| "grad_norm": 0.39767521619796753, | |
| "learning_rate": 8.429776870936485e-07, | |
| "loss": 0.0053, | |
| "num_input_tokens_seen": 4247232, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 3.6664290805416964, | |
| "grad_norm": 1.980200171470642, | |
| "learning_rate": 8.361898194386251e-07, | |
| "loss": 0.0107, | |
| "num_input_tokens_seen": 4254368, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 3.6721311475409837, | |
| "grad_norm": 0.1616886407136917, | |
| "learning_rate": 8.294238985646244e-07, | |
| "loss": 0.0016, | |
| "num_input_tokens_seen": 4260992, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 3.677833214540271, | |
| "grad_norm": 0.871669352054596, | |
| "learning_rate": 8.22680013718715e-07, | |
| "loss": 0.0109, | |
| "num_input_tokens_seen": 4267632, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 3.683535281539558, | |
| "grad_norm": 1.4398808479309082, | |
| "learning_rate": 8.159582538572985e-07, | |
| "loss": 0.0107, | |
| "num_input_tokens_seen": 4274032, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 3.689237348538845, | |
| "grad_norm": 0.1330898255109787, | |
| "learning_rate": 8.092587076449304e-07, | |
| "loss": 0.0013, | |
| "num_input_tokens_seen": 4280608, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 3.6949394155381325, | |
| "grad_norm": 0.6880252957344055, | |
| "learning_rate": 8.025814634531545e-07, | |
| "loss": 0.0097, | |
| "num_input_tokens_seen": 4287632, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 3.70064148253742, | |
| "grad_norm": 0.8941037058830261, | |
| "learning_rate": 7.959266093593343e-07, | |
| "loss": 0.0082, | |
| "num_input_tokens_seen": 4294560, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 3.706343549536707, | |
| "grad_norm": 2.7201638221740723, | |
| "learning_rate": 7.892942331454959e-07, | |
| "loss": 0.0209, | |
| "num_input_tokens_seen": 4300880, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.7120456165359945, | |
| "grad_norm": 0.16370153427124023, | |
| "learning_rate": 7.826844222971644e-07, | |
| "loss": 0.0014, | |
| "num_input_tokens_seen": 4307776, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 3.7177476835352814, | |
| "grad_norm": 1.3239191770553589, | |
| "learning_rate": 7.760972640022127e-07, | |
| "loss": 0.019, | |
| "num_input_tokens_seen": 4314304, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 3.7234497505345687, | |
| "grad_norm": 2.6364285945892334, | |
| "learning_rate": 7.695328451497111e-07, | |
| "loss": 0.0187, | |
| "num_input_tokens_seen": 4320656, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 3.729151817533856, | |
| "grad_norm": 1.4038536548614502, | |
| "learning_rate": 7.629912523287833e-07, | |
| "loss": 0.0118, | |
| "num_input_tokens_seen": 4327056, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 3.7348538845331434, | |
| "grad_norm": 0.34292855858802795, | |
| "learning_rate": 7.564725718274601e-07, | |
| "loss": 0.0027, | |
| "num_input_tokens_seen": 4333712, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 3.7405559515324303, | |
| "grad_norm": 1.6340289115905762, | |
| "learning_rate": 7.49976889631544e-07, | |
| "loss": 0.0088, | |
| "num_input_tokens_seen": 4340336, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 3.7462580185317176, | |
| "grad_norm": 1.5728880167007446, | |
| "learning_rate": 7.435042914234733e-07, | |
| "loss": 0.0252, | |
| "num_input_tokens_seen": 4346688, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 3.751960085531005, | |
| "grad_norm": 0.4033033549785614, | |
| "learning_rate": 7.370548625811954e-07, | |
| "loss": 0.003, | |
| "num_input_tokens_seen": 4353440, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 3.7576621525302922, | |
| "grad_norm": 3.087113618850708, | |
| "learning_rate": 7.306286881770361e-07, | |
| "loss": 0.0149, | |
| "num_input_tokens_seen": 4359952, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 3.7633642195295796, | |
| "grad_norm": 0.11130305379629135, | |
| "learning_rate": 7.242258529765794e-07, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 4366672, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.769066286528867, | |
| "grad_norm": 0.28085440397262573, | |
| "learning_rate": 7.178464414375496e-07, | |
| "loss": 0.0023, | |
| "num_input_tokens_seen": 4373136, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 3.774768353528154, | |
| "grad_norm": 0.9258376359939575, | |
| "learning_rate": 7.114905377086989e-07, | |
| "loss": 0.0062, | |
| "num_input_tokens_seen": 4379392, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 3.780470420527441, | |
| "grad_norm": 0.7785882949829102, | |
| "learning_rate": 7.051582256286929e-07, | |
| "loss": 0.0077, | |
| "num_input_tokens_seen": 4386320, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 3.7861724875267284, | |
| "grad_norm": 0.8045741319656372, | |
| "learning_rate": 6.98849588725009e-07, | |
| "loss": 0.0091, | |
| "num_input_tokens_seen": 4393008, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 3.7918745545260157, | |
| "grad_norm": 0.30582883954048157, | |
| "learning_rate": 6.925647102128319e-07, | |
| "loss": 0.0027, | |
| "num_input_tokens_seen": 4399680, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 3.797576621525303, | |
| "grad_norm": 1.122971773147583, | |
| "learning_rate": 6.863036729939593e-07, | |
| "loss": 0.0048, | |
| "num_input_tokens_seen": 4406624, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.80327868852459, | |
| "grad_norm": 1.0433896780014038, | |
| "learning_rate": 6.800665596557027e-07, | |
| "loss": 0.0084, | |
| "num_input_tokens_seen": 4413200, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 3.8089807555238773, | |
| "grad_norm": 0.5954147577285767, | |
| "learning_rate": 6.738534524698057e-07, | |
| "loss": 0.0037, | |
| "num_input_tokens_seen": 4419728, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 3.8146828225231646, | |
| "grad_norm": 0.2919423282146454, | |
| "learning_rate": 6.676644333913496e-07, | |
| "loss": 0.0013, | |
| "num_input_tokens_seen": 4426320, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 3.820384889522452, | |
| "grad_norm": 1.0446901321411133, | |
| "learning_rate": 6.614995840576816e-07, | |
| "loss": 0.0099, | |
| "num_input_tokens_seen": 4432480, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.8260869565217392, | |
| "grad_norm": 0.051127150654792786, | |
| "learning_rate": 6.553589857873304e-07, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 4438784, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 3.8317890235210266, | |
| "grad_norm": 1.680815577507019, | |
| "learning_rate": 6.4924271957894e-07, | |
| "loss": 0.0196, | |
| "num_input_tokens_seen": 4445200, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 3.8374910905203135, | |
| "grad_norm": 0.45610514283180237, | |
| "learning_rate": 6.431508661101954e-07, | |
| "loss": 0.0013, | |
| "num_input_tokens_seen": 4451616, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 3.8431931575196008, | |
| "grad_norm": 0.179911807179451, | |
| "learning_rate": 6.370835057367622e-07, | |
| "loss": 0.0008, | |
| "num_input_tokens_seen": 4457808, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 3.848895224518888, | |
| "grad_norm": 1.4267868995666504, | |
| "learning_rate": 6.31040718491224e-07, | |
| "loss": 0.0177, | |
| "num_input_tokens_seen": 4464448, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 3.8545972915181754, | |
| "grad_norm": 1.7962915897369385, | |
| "learning_rate": 6.250225840820315e-07, | |
| "loss": 0.0148, | |
| "num_input_tokens_seen": 4471168, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 3.8602993585174623, | |
| "grad_norm": 0.5019521713256836, | |
| "learning_rate": 6.190291818924449e-07, | |
| "loss": 0.0012, | |
| "num_input_tokens_seen": 4477424, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 3.8660014255167496, | |
| "grad_norm": 0.6949150562286377, | |
| "learning_rate": 6.130605909794907e-07, | |
| "loss": 0.0031, | |
| "num_input_tokens_seen": 4484080, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 3.871703492516037, | |
| "grad_norm": 1.9541274309158325, | |
| "learning_rate": 6.071168900729171e-07, | |
| "loss": 0.0024, | |
| "num_input_tokens_seen": 4490832, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 3.8774055595153243, | |
| "grad_norm": 0.13762035965919495, | |
| "learning_rate": 6.011981575741583e-07, | |
| "loss": 0.0008, | |
| "num_input_tokens_seen": 4497472, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.8831076265146116, | |
| "grad_norm": 0.760161280632019, | |
| "learning_rate": 5.953044715552967e-07, | |
| "loss": 0.0042, | |
| "num_input_tokens_seen": 4504064, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 3.888809693513899, | |
| "grad_norm": 2.114305257797241, | |
| "learning_rate": 5.894359097580343e-07, | |
| "loss": 0.0235, | |
| "num_input_tokens_seen": 4511136, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 3.8945117605131863, | |
| "grad_norm": 0.7031646370887756, | |
| "learning_rate": 5.835925495926684e-07, | |
| "loss": 0.0029, | |
| "num_input_tokens_seen": 4518176, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 3.900213827512473, | |
| "grad_norm": 1.012243628501892, | |
| "learning_rate": 5.777744681370709e-07, | |
| "loss": 0.0037, | |
| "num_input_tokens_seen": 4524592, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 3.9059158945117605, | |
| "grad_norm": 1.2794705629348755, | |
| "learning_rate": 5.719817421356686e-07, | |
| "loss": 0.0145, | |
| "num_input_tokens_seen": 4531216, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 3.911617961511048, | |
| "grad_norm": 0.8958796262741089, | |
| "learning_rate": 5.662144479984322e-07, | |
| "loss": 0.0093, | |
| "num_input_tokens_seen": 4537776, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 3.917320028510335, | |
| "grad_norm": 0.7218899130821228, | |
| "learning_rate": 5.604726617998721e-07, | |
| "loss": 0.0066, | |
| "num_input_tokens_seen": 4544272, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 3.923022095509622, | |
| "grad_norm": 0.16522099077701569, | |
| "learning_rate": 5.54756459278028e-07, | |
| "loss": 0.001, | |
| "num_input_tokens_seen": 4550736, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 3.9287241625089093, | |
| "grad_norm": 0.7687943577766418, | |
| "learning_rate": 5.490659158334774e-07, | |
| "loss": 0.0029, | |
| "num_input_tokens_seen": 4557024, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 3.9344262295081966, | |
| "grad_norm": 2.5592455863952637, | |
| "learning_rate": 5.434011065283326e-07, | |
| "loss": 0.0232, | |
| "num_input_tokens_seen": 4563712, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.940128296507484, | |
| "grad_norm": 0.07579555362462997, | |
| "learning_rate": 5.377621060852595e-07, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 4570336, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 3.9458303635067713, | |
| "grad_norm": 0.05152352526783943, | |
| "learning_rate": 5.321489888864848e-07, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 4577008, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 3.9515324305060586, | |
| "grad_norm": 0.2156032770872116, | |
| "learning_rate": 5.2656182897282e-07, | |
| "loss": 0.0011, | |
| "num_input_tokens_seen": 4583744, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 3.957234497505346, | |
| "grad_norm": 0.3031976819038391, | |
| "learning_rate": 5.210007000426812e-07, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 4590432, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 3.962936564504633, | |
| "grad_norm": 0.21700264513492584, | |
| "learning_rate": 5.154656754511175e-07, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 4596816, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 3.96863863150392, | |
| "grad_norm": 0.5650395154953003, | |
| "learning_rate": 5.099568282088446e-07, | |
| "loss": 0.0039, | |
| "num_input_tokens_seen": 4603536, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 3.9743406985032075, | |
| "grad_norm": 1.3010212182998657, | |
| "learning_rate": 5.044742309812833e-07, | |
| "loss": 0.0109, | |
| "num_input_tokens_seen": 4610128, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 3.980042765502495, | |
| "grad_norm": 2.5407936573028564, | |
| "learning_rate": 4.990179560875963e-07, | |
| "loss": 0.0455, | |
| "num_input_tokens_seen": 4616400, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 3.9857448325017817, | |
| "grad_norm": 0.05278922989964485, | |
| "learning_rate": 4.935880754997377e-07, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 4622544, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 3.991446899501069, | |
| "grad_norm": 0.14981479942798615, | |
| "learning_rate": 4.881846608415028e-07, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 4628928, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.9971489665003563, | |
| "grad_norm": 0.054193057119846344, | |
| "learning_rate": 4.828077833875849e-07, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 4635312, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 4.002851033499644, | |
| "grad_norm": 0.1286012977361679, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 4641696, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 4.008553100498931, | |
| "grad_norm": 0.817335307598114, | |
| "learning_rate": 4.7213392344031215e-07, | |
| "loss": 0.0041, | |
| "num_input_tokens_seen": 4648800, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 4.014255167498218, | |
| "grad_norm": 0.2602868676185608, | |
| "learning_rate": 4.6683708174238506e-07, | |
| "loss": 0.0017, | |
| "num_input_tokens_seen": 4655392, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 4.019957234497506, | |
| "grad_norm": 0.05918978899717331, | |
| "learning_rate": 4.6156705883777434e-07, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 4661808, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 4.025659301496793, | |
| "grad_norm": 3.1517393589019775, | |
| "learning_rate": 4.5632392424164367e-07, | |
| "loss": 0.0101, | |
| "num_input_tokens_seen": 4668576, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 4.031361368496079, | |
| "grad_norm": 1.1861796379089355, | |
| "learning_rate": 4.511077471144831e-07, | |
| "loss": 0.0206, | |
| "num_input_tokens_seen": 4674944, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 4.037063435495367, | |
| "grad_norm": 0.8727283477783203, | |
| "learning_rate": 4.4591859626119447e-07, | |
| "loss": 0.0058, | |
| "num_input_tokens_seen": 4681840, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 4.042765502494654, | |
| "grad_norm": 0.18443292379379272, | |
| "learning_rate": 4.4075654013018635e-07, | |
| "loss": 0.0007, | |
| "num_input_tokens_seen": 4688528, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 4.048467569493941, | |
| "grad_norm": 0.6552385687828064, | |
| "learning_rate": 4.3562164681246825e-07, | |
| "loss": 0.0035, | |
| "num_input_tokens_seen": 4694992, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.054169636493229, | |
| "grad_norm": 0.8831287026405334, | |
| "learning_rate": 4.3051398404075436e-07, | |
| "loss": 0.0074, | |
| "num_input_tokens_seen": 4701328, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 4.059871703492516, | |
| "grad_norm": 0.026319758966565132, | |
| "learning_rate": 4.254336191885683e-07, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 4707808, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 4.065573770491803, | |
| "grad_norm": 0.17212285101413727, | |
| "learning_rate": 4.203806192693588e-07, | |
| "loss": 0.001, | |
| "num_input_tokens_seen": 4714592, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 4.071275837491091, | |
| "grad_norm": 0.0908040776848793, | |
| "learning_rate": 4.1535505093560885e-07, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 4721408, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 4.076977904490378, | |
| "grad_norm": 0.4635961055755615, | |
| "learning_rate": 4.103569804779642e-07, | |
| "loss": 0.0044, | |
| "num_input_tokens_seen": 4728224, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 4.082679971489665, | |
| "grad_norm": 0.8470099568367004, | |
| "learning_rate": 4.0538647382435017e-07, | |
| "loss": 0.0065, | |
| "num_input_tokens_seen": 4735040, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 4.088382038488953, | |
| "grad_norm": 0.09076406061649323, | |
| "learning_rate": 4.0044359653911183e-07, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 4741584, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 4.094084105488239, | |
| "grad_norm": 0.707586407661438, | |
| "learning_rate": 3.955284138221402e-07, | |
| "loss": 0.0044, | |
| "num_input_tokens_seen": 4748160, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 4.099786172487526, | |
| "grad_norm": 2.276195526123047, | |
| "learning_rate": 3.9064099050802024e-07, | |
| "loss": 0.0111, | |
| "num_input_tokens_seen": 4754752, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 4.105488239486814, | |
| "grad_norm": 1.1030926704406738, | |
| "learning_rate": 3.85781391065167e-07, | |
| "loss": 0.0123, | |
| "num_input_tokens_seen": 4761168, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.111190306486101, | |
| "grad_norm": 0.12873871624469757, | |
| "learning_rate": 3.809496795949838e-07, | |
| "loss": 0.0011, | |
| "num_input_tokens_seen": 4767376, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 4.116892373485388, | |
| "grad_norm": 0.030298732221126556, | |
| "learning_rate": 3.7614591983100995e-07, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 4774224, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 4.122594440484676, | |
| "grad_norm": 0.4066639840602875, | |
| "learning_rate": 3.713701751380855e-07, | |
| "loss": 0.002, | |
| "num_input_tokens_seen": 4780656, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 4.128296507483963, | |
| "grad_norm": 0.6175351738929749, | |
| "learning_rate": 3.666225085115108e-07, | |
| "loss": 0.004, | |
| "num_input_tokens_seen": 4786944, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 4.13399857448325, | |
| "grad_norm": 0.16811884939670563, | |
| "learning_rate": 3.619029825762177e-07, | |
| "loss": 0.001, | |
| "num_input_tokens_seen": 4793488, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 4.139700641482538, | |
| "grad_norm": 0.3199079930782318, | |
| "learning_rate": 3.5721165958594345e-07, | |
| "loss": 0.0013, | |
| "num_input_tokens_seen": 4799872, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 4.145402708481825, | |
| "grad_norm": 0.02896907553076744, | |
| "learning_rate": 3.525486014224108e-07, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 4806656, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 4.151104775481112, | |
| "grad_norm": 0.12801134586334229, | |
| "learning_rate": 3.479138695945086e-07, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 4813408, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 4.156806842480399, | |
| "grad_norm": 0.22655466198921204, | |
| "learning_rate": 3.433075252374826e-07, | |
| "loss": 0.0011, | |
| "num_input_tokens_seen": 4819904, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 4.162508909479686, | |
| "grad_norm": 0.7603595852851868, | |
| "learning_rate": 3.3872962911212836e-07, | |
| "loss": 0.0046, | |
| "num_input_tokens_seen": 4826848, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.168210976478973, | |
| "grad_norm": 0.557383120059967, | |
| "learning_rate": 3.341802416039913e-07, | |
| "loss": 0.0026, | |
| "num_input_tokens_seen": 4833648, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 4.173913043478261, | |
| "grad_norm": 0.26344913244247437, | |
| "learning_rate": 3.296594227225677e-07, | |
| "loss": 0.0045, | |
| "num_input_tokens_seen": 4840000, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 4.179615110477548, | |
| "grad_norm": 3.3977065086364746, | |
| "learning_rate": 3.2516723210051476e-07, | |
| "loss": 0.0154, | |
| "num_input_tokens_seen": 4846544, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 4.185317177476835, | |
| "grad_norm": 0.20362620055675507, | |
| "learning_rate": 3.20703728992863e-07, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 4853344, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 4.191019244476123, | |
| "grad_norm": 0.03981434926390648, | |
| "learning_rate": 3.162689722762366e-07, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 4860016, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 4.19672131147541, | |
| "grad_norm": 0.08564602583646774, | |
| "learning_rate": 3.118630204480741e-07, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 4866816, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 4.202423378474697, | |
| "grad_norm": 0.583420991897583, | |
| "learning_rate": 3.0748593162585853e-07, | |
| "loss": 0.0021, | |
| "num_input_tokens_seen": 4873168, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 4.208125445473985, | |
| "grad_norm": 0.10381372272968292, | |
| "learning_rate": 3.0313776354635005e-07, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 4879776, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 4.213827512473271, | |
| "grad_norm": 1.8905394077301025, | |
| "learning_rate": 2.988185735648258e-07, | |
| "loss": 0.0359, | |
| "num_input_tokens_seen": 4886720, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 4.2195295794725585, | |
| "grad_norm": 0.05700286850333214, | |
| "learning_rate": 2.9452841865432126e-07, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 4893376, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.225231646471846, | |
| "grad_norm": 1.4328497648239136, | |
| "learning_rate": 2.902673554048793e-07, | |
| "loss": 0.0093, | |
| "num_input_tokens_seen": 4899984, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 4.230933713471133, | |
| "grad_norm": 0.29192915558815, | |
| "learning_rate": 2.8603544002280463e-07, | |
| "loss": 0.0011, | |
| "num_input_tokens_seen": 4906800, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 4.23663578047042, | |
| "grad_norm": 0.314852237701416, | |
| "learning_rate": 2.818327283299227e-07, | |
| "loss": 0.0014, | |
| "num_input_tokens_seen": 4913296, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 4.242337847469708, | |
| "grad_norm": 0.5625317692756653, | |
| "learning_rate": 2.7765927576284076e-07, | |
| "loss": 0.0041, | |
| "num_input_tokens_seen": 4919808, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 4.248039914468995, | |
| "grad_norm": 0.6194710731506348, | |
| "learning_rate": 2.735151373722214e-07, | |
| "loss": 0.0077, | |
| "num_input_tokens_seen": 4926176, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 4.253741981468282, | |
| "grad_norm": 0.1176173985004425, | |
| "learning_rate": 2.694003678220489e-07, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 4932480, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 4.25944404846757, | |
| "grad_norm": 0.28074905276298523, | |
| "learning_rate": 2.6531502138891665e-07, | |
| "loss": 0.0015, | |
| "num_input_tokens_seen": 4939104, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 4.265146115466857, | |
| "grad_norm": 1.147383451461792, | |
| "learning_rate": 2.612591519613053e-07, | |
| "loss": 0.0072, | |
| "num_input_tokens_seen": 4945728, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 4.270848182466144, | |
| "grad_norm": 0.22705648839473724, | |
| "learning_rate": 2.5723281303887545e-07, | |
| "loss": 0.001, | |
| "num_input_tokens_seen": 4952240, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 4.276550249465431, | |
| "grad_norm": 0.6860646605491638, | |
| "learning_rate": 2.5323605773175775e-07, | |
| "loss": 0.0043, | |
| "num_input_tokens_seen": 4958752, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.282252316464718, | |
| "grad_norm": 0.6111099123954773, | |
| "learning_rate": 2.4926893875985766e-07, | |
| "loss": 0.003, | |
| "num_input_tokens_seen": 4965376, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 4.2879543834640055, | |
| "grad_norm": 1.1241867542266846, | |
| "learning_rate": 2.4533150845215514e-07, | |
| "loss": 0.0047, | |
| "num_input_tokens_seen": 4971680, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 4.293656450463293, | |
| "grad_norm": 0.09292508661746979, | |
| "learning_rate": 2.414238187460191e-07, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 4978368, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 4.29935851746258, | |
| "grad_norm": 0.08100103586912155, | |
| "learning_rate": 2.3754592118651748e-07, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 4984816, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 4.3050605844618675, | |
| "grad_norm": 0.8663838505744934, | |
| "learning_rate": 2.336978669257406e-07, | |
| "loss": 0.0036, | |
| "num_input_tokens_seen": 4991648, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 4.310762651461155, | |
| "grad_norm": 0.07981377094984055, | |
| "learning_rate": 2.2987970672212506e-07, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 4997904, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 4.316464718460442, | |
| "grad_norm": 0.05137365683913231, | |
| "learning_rate": 2.26091490939786e-07, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5004592, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 4.322166785459729, | |
| "grad_norm": 1.287177562713623, | |
| "learning_rate": 2.2233326954785e-07, | |
| "loss": 0.0089, | |
| "num_input_tokens_seen": 5011152, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 4.327868852459017, | |
| "grad_norm": 0.024704981595277786, | |
| "learning_rate": 2.186050921197974e-07, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5017888, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 4.333570919458303, | |
| "grad_norm": 0.03882192447781563, | |
| "learning_rate": 2.149070078328089e-07, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5024656, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.3392729864575905, | |
| "grad_norm": 0.6126242876052856, | |
| "learning_rate": 2.1123906546711675e-07, | |
| "loss": 0.0033, | |
| "num_input_tokens_seen": 5030944, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 4.344975053456878, | |
| "grad_norm": 0.9626344442367554, | |
| "learning_rate": 2.0760131340536006e-07, | |
| "loss": 0.0109, | |
| "num_input_tokens_seen": 5037584, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 4.350677120456165, | |
| "grad_norm": 0.6008232235908508, | |
| "learning_rate": 2.0399379963194715e-07, | |
| "loss": 0.0031, | |
| "num_input_tokens_seen": 5043904, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 4.3563791874554525, | |
| "grad_norm": 0.28160446882247925, | |
| "learning_rate": 2.004165717324233e-07, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 5050256, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 4.36208125445474, | |
| "grad_norm": 0.22114770114421844, | |
| "learning_rate": 1.9686967689284354e-07, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 5057056, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 4.367783321454027, | |
| "grad_norm": 0.5921658277511597, | |
| "learning_rate": 1.9335316189914826e-07, | |
| "loss": 0.0035, | |
| "num_input_tokens_seen": 5063472, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 4.3734853884533145, | |
| "grad_norm": 1.4691166877746582, | |
| "learning_rate": 1.8986707313654707e-07, | |
| "loss": 0.0143, | |
| "num_input_tokens_seen": 5070160, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 4.379187455452602, | |
| "grad_norm": 0.6398491859436035, | |
| "learning_rate": 1.864114565889069e-07, | |
| "loss": 0.0037, | |
| "num_input_tokens_seen": 5076784, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 4.384889522451889, | |
| "grad_norm": 1.2515215873718262, | |
| "learning_rate": 1.8298635783814743e-07, | |
| "loss": 0.0082, | |
| "num_input_tokens_seen": 5083280, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 4.3905915894511764, | |
| "grad_norm": 0.048939384520053864, | |
| "learning_rate": 1.7959182206363502e-07, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5089824, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.396293656450463, | |
| "grad_norm": 1.496209740638733, | |
| "learning_rate": 1.7622789404159318e-07, | |
| "loss": 0.0156, | |
| "num_input_tokens_seen": 5096176, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 4.40199572344975, | |
| "grad_norm": 0.07701216638088226, | |
| "learning_rate": 1.728946181445043e-07, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5102784, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 4.4076977904490375, | |
| "grad_norm": 0.8384713530540466, | |
| "learning_rate": 1.6959203834053224e-07, | |
| "loss": 0.0028, | |
| "num_input_tokens_seen": 5109504, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 4.413399857448325, | |
| "grad_norm": 0.03958812728524208, | |
| "learning_rate": 1.6632019819293632e-07, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5116240, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 4.419101924447612, | |
| "grad_norm": 1.7000349760055542, | |
| "learning_rate": 1.6307914085950117e-07, | |
| "loss": 0.0109, | |
| "num_input_tokens_seen": 5122576, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 4.4248039914468995, | |
| "grad_norm": 1.9781132936477661, | |
| "learning_rate": 1.5986890909196224e-07, | |
| "loss": 0.0214, | |
| "num_input_tokens_seen": 5128976, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 4.430506058446187, | |
| "grad_norm": 0.0699346512556076, | |
| "learning_rate": 1.5668954523544776e-07, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 5135456, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 4.436208125445474, | |
| "grad_norm": 0.7114868760108948, | |
| "learning_rate": 1.535410912279159e-07, | |
| "loss": 0.0034, | |
| "num_input_tokens_seen": 5142000, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 4.4419101924447615, | |
| "grad_norm": 0.28993305563926697, | |
| "learning_rate": 1.504235885996036e-07, | |
| "loss": 0.0014, | |
| "num_input_tokens_seen": 5148704, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 4.447612259444049, | |
| "grad_norm": 0.2542056143283844, | |
| "learning_rate": 1.4733707847247814e-07, | |
| "loss": 0.0012, | |
| "num_input_tokens_seen": 5155472, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.453314326443335, | |
| "grad_norm": 0.2563529312610626, | |
| "learning_rate": 1.4428160155969402e-07, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 5162096, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 4.459016393442623, | |
| "grad_norm": 0.6606563925743103, | |
| "learning_rate": 1.4125719816505761e-07, | |
| "loss": 0.0038, | |
| "num_input_tokens_seen": 5168944, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 4.46471846044191, | |
| "grad_norm": 0.05460350960493088, | |
| "learning_rate": 1.3826390818249434e-07, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5175328, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 4.470420527441197, | |
| "grad_norm": 0.2057548314332962, | |
| "learning_rate": 1.3530177109552233e-07, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 5182032, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 4.4761225944404845, | |
| "grad_norm": 1.137696385383606, | |
| "learning_rate": 1.3237082597673173e-07, | |
| "loss": 0.012, | |
| "num_input_tokens_seen": 5189200, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 4.481824661439772, | |
| "grad_norm": 0.0833611786365509, | |
| "learning_rate": 1.294711114872707e-07, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5195968, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 4.487526728439059, | |
| "grad_norm": 0.025540605187416077, | |
| "learning_rate": 1.2660266587633334e-07, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5202528, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 4.4932287954383465, | |
| "grad_norm": 0.7630849480628967, | |
| "learning_rate": 1.2376552698065647e-07, | |
| "loss": 0.0066, | |
| "num_input_tokens_seen": 5208944, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 4.498930862437634, | |
| "grad_norm": 0.015869060531258583, | |
| "learning_rate": 1.2095973222401914e-07, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5215888, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 4.504632929436921, | |
| "grad_norm": 0.1820346564054489, | |
| "learning_rate": 1.1818531861675226e-07, | |
| "loss": 0.0008, | |
| "num_input_tokens_seen": 5222608, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.5103349964362085, | |
| "grad_norm": 0.028767000883817673, | |
| "learning_rate": 1.1544232275524592e-07, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5229600, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 4.516037063435496, | |
| "grad_norm": 0.009326450526714325, | |
| "learning_rate": 1.1273078082147059e-07, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5236368, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 4.521739130434782, | |
| "grad_norm": 0.16667701303958893, | |
| "learning_rate": 1.1005072858249616e-07, | |
| "loss": 0.0007, | |
| "num_input_tokens_seen": 5243296, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 4.52744119743407, | |
| "grad_norm": 0.06731978803873062, | |
| "learning_rate": 1.0740220139002445e-07, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5249952, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 4.533143264433357, | |
| "grad_norm": 0.6377565264701843, | |
| "learning_rate": 1.0478523417991882e-07, | |
| "loss": 0.0034, | |
| "num_input_tokens_seen": 5257328, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 4.538845331432644, | |
| "grad_norm": 0.09127297252416611, | |
| "learning_rate": 1.0219986147174705e-07, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 5264608, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 4.544547398431932, | |
| "grad_norm": 0.08946079760789871, | |
| "learning_rate": 9.964611736832109e-08, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5270928, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 4.550249465431219, | |
| "grad_norm": 0.043789055198431015, | |
| "learning_rate": 9.712403555525357e-08, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5277408, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 4.555951532430506, | |
| "grad_norm": 1.0420541763305664, | |
| "learning_rate": 9.463364930050762e-08, | |
| "loss": 0.0097, | |
| "num_input_tokens_seen": 5284304, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 4.5616535994297935, | |
| "grad_norm": 0.037041183561086655, | |
| "learning_rate": 9.217499145396187e-08, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5290816, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.567355666429081, | |
| "grad_norm": 0.5905625820159912, | |
| "learning_rate": 8.97480944469753e-08, | |
| "loss": 0.0029, | |
| "num_input_tokens_seen": 5297680, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 4.573057733428367, | |
| "grad_norm": 1.1155067682266235, | |
| "learning_rate": 8.73529902919601e-08, | |
| "loss": 0.0059, | |
| "num_input_tokens_seen": 5304464, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 4.578759800427655, | |
| "grad_norm": 0.018409363925457, | |
| "learning_rate": 8.498971058195887e-08, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5311072, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 4.584461867426942, | |
| "grad_norm": 0.09573342651128769, | |
| "learning_rate": 8.265828649022867e-08, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 5317776, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 4.590163934426229, | |
| "grad_norm": 0.029178114607930183, | |
| "learning_rate": 8.035874876982957e-08, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5324160, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 4.595866001425517, | |
| "grad_norm": 0.789979875087738, | |
| "learning_rate": 7.809112775321869e-08, | |
| "loss": 0.004, | |
| "num_input_tokens_seen": 5330768, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 4.601568068424804, | |
| "grad_norm": 0.28636226058006287, | |
| "learning_rate": 7.585545335184935e-08, | |
| "loss": 0.0013, | |
| "num_input_tokens_seen": 5337376, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 4.607270135424091, | |
| "grad_norm": 0.11878740787506104, | |
| "learning_rate": 7.365175505577915e-08, | |
| "loss": 0.0011, | |
| "num_input_tokens_seen": 5344080, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 4.612972202423379, | |
| "grad_norm": 0.3786606788635254, | |
| "learning_rate": 7.148006193327783e-08, | |
| "loss": 0.0017, | |
| "num_input_tokens_seen": 5350448, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 4.618674269422666, | |
| "grad_norm": 1.0686554908752441, | |
| "learning_rate": 6.93404026304459e-08, | |
| "loss": 0.0049, | |
| "num_input_tokens_seen": 5356800, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.624376336421953, | |
| "grad_norm": 0.708344578742981, | |
| "learning_rate": 6.723280537083571e-08, | |
| "loss": 0.0047, | |
| "num_input_tokens_seen": 5363056, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 4.6300784034212406, | |
| "grad_norm": 0.029089799150824547, | |
| "learning_rate": 6.515729795508019e-08, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5369280, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 4.635780470420528, | |
| "grad_norm": 0.06976296752691269, | |
| "learning_rate": 6.311390776052529e-08, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5376016, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 4.641482537419814, | |
| "grad_norm": 0.05825020745396614, | |
| "learning_rate": 6.110266174086859e-08, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5382768, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 4.647184604419102, | |
| "grad_norm": 1.069995641708374, | |
| "learning_rate": 5.912358642580496e-08, | |
| "loss": 0.0098, | |
| "num_input_tokens_seen": 5389200, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 4.652886671418389, | |
| "grad_norm": 0.28126129508018494, | |
| "learning_rate": 5.717670792067587e-08, | |
| "loss": 0.0014, | |
| "num_input_tokens_seen": 5395776, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 4.658588738417676, | |
| "grad_norm": 0.14872530102729797, | |
| "learning_rate": 5.526205190612449e-08, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 5402688, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 4.664290805416964, | |
| "grad_norm": 1.2570905685424805, | |
| "learning_rate": 5.337964363775816e-08, | |
| "loss": 0.0099, | |
| "num_input_tokens_seen": 5409152, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 4.669992872416251, | |
| "grad_norm": 0.3209165036678314, | |
| "learning_rate": 5.1529507945814185e-08, | |
| "loss": 0.0019, | |
| "num_input_tokens_seen": 5415744, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 4.675694939415538, | |
| "grad_norm": 0.1433120220899582, | |
| "learning_rate": 4.971166923483372e-08, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 5422048, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.681397006414826, | |
| "grad_norm": 1.7018483877182007, | |
| "learning_rate": 4.792615148333735e-08, | |
| "loss": 0.0189, | |
| "num_input_tokens_seen": 5428368, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 4.687099073414113, | |
| "grad_norm": 0.011967192403972149, | |
| "learning_rate": 4.617297824351219e-08, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5434960, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 4.6928011404134, | |
| "grad_norm": 1.1888624429702759, | |
| "learning_rate": 4.4452172640897515e-08, | |
| "loss": 0.0075, | |
| "num_input_tokens_seen": 5441776, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 4.698503207412687, | |
| "grad_norm": 0.0656069964170456, | |
| "learning_rate": 4.2763757374083006e-08, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 5448768, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 4.704205274411974, | |
| "grad_norm": 0.02361738122999668, | |
| "learning_rate": 4.110775471440703e-08, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5455472, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 4.709907341411261, | |
| "grad_norm": 0.10109017789363861, | |
| "learning_rate": 3.948418650566499e-08, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 5461856, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 4.715609408410549, | |
| "grad_norm": 0.31169602274894714, | |
| "learning_rate": 3.7893074163817824e-08, | |
| "loss": 0.0015, | |
| "num_input_tokens_seen": 5468608, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 4.721311475409836, | |
| "grad_norm": 0.04045119881629944, | |
| "learning_rate": 3.633443867671393e-08, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5475216, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 4.727013542409123, | |
| "grad_norm": 0.6061815023422241, | |
| "learning_rate": 3.4808300603808574e-08, | |
| "loss": 0.0137, | |
| "num_input_tokens_seen": 5481952, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 4.732715609408411, | |
| "grad_norm": 0.09090006351470947, | |
| "learning_rate": 3.331468007589489e-08, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 5488720, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.738417676407698, | |
| "grad_norm": 0.1739615947008133, | |
| "learning_rate": 3.18535967948369e-08, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 5495440, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 4.744119743406985, | |
| "grad_norm": 0.04561722278594971, | |
| "learning_rate": 3.042507003331141e-08, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5501840, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 4.749821810406273, | |
| "grad_norm": 0.09544459730386734, | |
| "learning_rate": 2.902911863455121e-08, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 5508192, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 4.75552387740556, | |
| "grad_norm": 0.9669187664985657, | |
| "learning_rate": 2.7665761012099777e-08, | |
| "loss": 0.0064, | |
| "num_input_tokens_seen": 5514832, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 4.761225944404847, | |
| "grad_norm": 7.617751121520996, | |
| "learning_rate": 2.6335015149565324e-08, | |
| "loss": 0.01, | |
| "num_input_tokens_seen": 5520832, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 4.766928011404134, | |
| "grad_norm": 0.7793776988983154, | |
| "learning_rate": 2.5036898600385716e-08, | |
| "loss": 0.0047, | |
| "num_input_tokens_seen": 5527200, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 4.772630078403421, | |
| "grad_norm": 0.07317044585943222, | |
| "learning_rate": 2.377142848759506e-08, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 5533664, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 4.778332145402708, | |
| "grad_norm": 0.10957920551300049, | |
| "learning_rate": 2.2538621503600255e-08, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 5540400, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 4.784034212401996, | |
| "grad_norm": 0.3689444363117218, | |
| "learning_rate": 2.1338493909958956e-08, | |
| "loss": 0.0018, | |
| "num_input_tokens_seen": 5547152, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 4.789736279401283, | |
| "grad_norm": 0.09837047755718231, | |
| "learning_rate": 2.017106153716475e-08, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5553792, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.79543834640057, | |
| "grad_norm": 1.0303527116775513, | |
| "learning_rate": 1.9036339784440082e-08, | |
| "loss": 0.0093, | |
| "num_input_tokens_seen": 5560144, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 4.801140413399858, | |
| "grad_norm": 0.24677984416484833, | |
| "learning_rate": 1.793434361953228e-08, | |
| "loss": 0.0007, | |
| "num_input_tokens_seen": 5566640, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 4.806842480399145, | |
| "grad_norm": 0.6943243741989136, | |
| "learning_rate": 1.6865087578515073e-08, | |
| "loss": 0.0043, | |
| "num_input_tokens_seen": 5573424, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 4.812544547398432, | |
| "grad_norm": 0.018405841663479805, | |
| "learning_rate": 1.5828585765599315e-08, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5580208, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 4.818246614397719, | |
| "grad_norm": 0.025661015883088112, | |
| "learning_rate": 1.482485185294369e-08, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5586720, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 4.823948681397006, | |
| "grad_norm": 0.021062418818473816, | |
| "learning_rate": 1.3853899080477628e-08, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5593120, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 4.829650748396293, | |
| "grad_norm": 0.7667257785797119, | |
| "learning_rate": 1.291574025572423e-08, | |
| "loss": 0.0046, | |
| "num_input_tokens_seen": 5600016, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 4.835352815395581, | |
| "grad_norm": 0.018968243151903152, | |
| "learning_rate": 1.2010387753632891e-08, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5606800, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 4.841054882394868, | |
| "grad_norm": 0.4931604266166687, | |
| "learning_rate": 1.1137853516414999e-08, | |
| "loss": 0.0025, | |
| "num_input_tokens_seen": 5613200, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 4.846756949394155, | |
| "grad_norm": 0.0513661690056324, | |
| "learning_rate": 1.0298149053387107e-08, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5619792, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.852459016393443, | |
| "grad_norm": 0.04170714318752289, | |
| "learning_rate": 9.491285440818288e-09, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5626720, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 4.85816108339273, | |
| "grad_norm": 0.031740520149469376, | |
| "learning_rate": 8.717273321785513e-09, | |
| "loss": 0.0002, | |
| "num_input_tokens_seen": 5633328, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 4.863863150392017, | |
| "grad_norm": 0.15657615661621094, | |
| "learning_rate": 7.976122906031559e-09, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 5640240, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 4.869565217391305, | |
| "grad_norm": 0.2195972204208374, | |
| "learning_rate": 7.267843969831767e-09, | |
| "loss": 0.002, | |
| "num_input_tokens_seen": 5646608, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 4.875267284390592, | |
| "grad_norm": 0.8132025003433228, | |
| "learning_rate": 6.592445855863883e-09, | |
| "loss": 0.0052, | |
| "num_input_tokens_seen": 5653632, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 4.880969351389879, | |
| "grad_norm": 0.01100305374711752, | |
| "learning_rate": 5.949937473085643e-09, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5660576, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 4.886671418389166, | |
| "grad_norm": 0.6500959396362305, | |
| "learning_rate": 5.340327296616821e-09, | |
| "loss": 0.0032, | |
| "num_input_tokens_seen": 5667312, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 4.892373485388453, | |
| "grad_norm": 0.05256979167461395, | |
| "learning_rate": 4.763623367627645e-09, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5673984, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 4.89807555238774, | |
| "grad_norm": 0.0746457576751709, | |
| "learning_rate": 4.219833293233333e-09, | |
| "loss": 0.0003, | |
| "num_input_tokens_seen": 5680448, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 4.903777619387028, | |
| "grad_norm": 0.021520154550671577, | |
| "learning_rate": 3.7089642463922217e-09, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5687248, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.909479686386315, | |
| "grad_norm": 0.13376076519489288, | |
| "learning_rate": 3.231022965812236e-09, | |
| "loss": 0.0006, | |
| "num_input_tokens_seen": 5693792, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 4.915181753385602, | |
| "grad_norm": 0.6564909815788269, | |
| "learning_rate": 2.7860157558620703e-09, | |
| "loss": 0.0044, | |
| "num_input_tokens_seen": 5700368, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 4.92088382038489, | |
| "grad_norm": 0.331143319606781, | |
| "learning_rate": 2.3739484864879203e-09, | |
| "loss": 0.0007, | |
| "num_input_tokens_seen": 5706672, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 4.926585887384177, | |
| "grad_norm": 0.0895066112279892, | |
| "learning_rate": 1.9948265931352128e-09, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 5713840, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 4.932287954383464, | |
| "grad_norm": 1.506907343864441, | |
| "learning_rate": 1.6486550766783849e-09, | |
| "loss": 0.0067, | |
| "num_input_tokens_seen": 5720272, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 4.937990021382751, | |
| "grad_norm": 0.10082338750362396, | |
| "learning_rate": 1.3354385033534368e-09, | |
| "loss": 0.0005, | |
| "num_input_tokens_seen": 5727040, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 4.943692088382038, | |
| "grad_norm": 0.3792347311973572, | |
| "learning_rate": 1.055181004698813e-09, | |
| "loss": 0.0017, | |
| "num_input_tokens_seen": 5733696, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 4.949394155381325, | |
| "grad_norm": 0.820798397064209, | |
| "learning_rate": 8.07886277500447e-10, | |
| "loss": 0.0065, | |
| "num_input_tokens_seen": 5740064, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 4.955096222380613, | |
| "grad_norm": 0.11408527195453644, | |
| "learning_rate": 5.935575837429097e-10, | |
| "loss": 0.0009, | |
| "num_input_tokens_seen": 5746624, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 4.9607982893799, | |
| "grad_norm": 0.014658835716545582, | |
| "learning_rate": 4.1219775056666746e-10, | |
| "loss": 0.0001, | |
| "num_input_tokens_seen": 5753456, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.966500356379187, | |
| "grad_norm": 1.0549769401550293, | |
| "learning_rate": 2.638091702303336e-10, | |
| "loss": 0.0096, | |
| "num_input_tokens_seen": 5759808, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 4.972202423378475, | |
| "grad_norm": 2.1060280799865723, | |
| "learning_rate": 1.4839380007986014e-10, | |
| "loss": 0.0099, | |
| "num_input_tokens_seen": 5766288, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 4.977904490377762, | |
| "grad_norm": 0.06906285136938095, | |
| "learning_rate": 6.595316252161476e-11, | |
| "loss": 0.0004, | |
| "num_input_tokens_seen": 5772848, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 4.983606557377049, | |
| "grad_norm": 0.5131366848945618, | |
| "learning_rate": 1.6488345003506933e-11, | |
| "loss": 0.0026, | |
| "num_input_tokens_seen": 5779552, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 4.989308624376337, | |
| "grad_norm": 0.508285641670227, | |
| "learning_rate": 0.0, | |
| "loss": 0.0029, | |
| "num_input_tokens_seen": 5786192, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 4.989308624376337, | |
| "num_input_tokens_seen": 5786192, | |
| "step": 875, | |
| "total_flos": 2.6054961380143923e+17, | |
| "train_loss": 0.1388659444341361, | |
| "train_runtime": 11572.721, | |
| "train_samples_per_second": 9.693, | |
| "train_steps_per_second": 0.076 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 875, | |
| "num_input_tokens_seen": 5786192, | |
| "num_train_epochs": 5, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.6054961380143923e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |