| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.19745502413339183, | |
| "eval_steps": 50, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013163668275559457, | |
| "grad_norm": 1.8360265202958839, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2376, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026327336551118913, | |
| "grad_norm": 2.009163406670022, | |
| "learning_rate": 1.999777729859618e-05, | |
| "loss": 2.2265, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003949100482667837, | |
| "grad_norm": 7.803051666492677, | |
| "learning_rate": 1.9991110182465032e-05, | |
| "loss": 2.3019, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005265467310223783, | |
| "grad_norm": 4.779885950620012, | |
| "learning_rate": 1.9980001615408228e-05, | |
| "loss": 2.3013, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006581834137779728, | |
| "grad_norm": 2.9742143761357225, | |
| "learning_rate": 1.9964456535631287e-05, | |
| "loss": 2.2388, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007898200965335674, | |
| "grad_norm": 1.8726314051597182, | |
| "learning_rate": 1.9944481853548335e-05, | |
| "loss": 2.2208, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009214567792891619, | |
| "grad_norm": 1.3112081484759899, | |
| "learning_rate": 1.9920086448710162e-05, | |
| "loss": 2.2066, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010530934620447565, | |
| "grad_norm": 0.909275674438629, | |
| "learning_rate": 1.9891281165856876e-05, | |
| "loss": 2.1706, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01184730144800351, | |
| "grad_norm": 0.7030168404800303, | |
| "learning_rate": 1.9858078810097004e-05, | |
| "loss": 2.1915, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013163668275559455, | |
| "grad_norm": 0.7229786040704992, | |
| "learning_rate": 1.98204941412151e-05, | |
| "loss": 2.183, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014480035103115402, | |
| "grad_norm": 0.6543993900873311, | |
| "learning_rate": 1.9778543867110428e-05, | |
| "loss": 2.1794, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015796401930671347, | |
| "grad_norm": 0.588685837316444, | |
| "learning_rate": 1.9732246636369605e-05, | |
| "loss": 2.1752, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017112768758227294, | |
| "grad_norm": 0.5429351720927647, | |
| "learning_rate": 1.968162302997659e-05, | |
| "loss": 2.1723, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018429135585783237, | |
| "grad_norm": 0.5689701777712141, | |
| "learning_rate": 1.962669555216358e-05, | |
| "loss": 2.1523, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019745502413339184, | |
| "grad_norm": 0.4947995423433805, | |
| "learning_rate": 1.9567488620406984e-05, | |
| "loss": 2.1636, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02106186924089513, | |
| "grad_norm": 0.5490041038773252, | |
| "learning_rate": 1.9504028554572865e-05, | |
| "loss": 2.1433, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022378236068451074, | |
| "grad_norm": 0.45063899354358605, | |
| "learning_rate": 1.943634356521671e-05, | |
| "loss": 2.1497, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02369460289600702, | |
| "grad_norm": 0.4644886833950337, | |
| "learning_rate": 1.9364463741042694e-05, | |
| "loss": 2.1091, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025010969723562967, | |
| "grad_norm": 0.42859605401949585, | |
| "learning_rate": 1.928842103552803e-05, | |
| "loss": 2.1189, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02632733655111891, | |
| "grad_norm": 0.4251126925791648, | |
| "learning_rate": 1.920824925271838e-05, | |
| "loss": 2.1263, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027643703378674857, | |
| "grad_norm": 0.42872735466039197, | |
| "learning_rate": 1.9123984032200586e-05, | |
| "loss": 2.1058, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028960070206230804, | |
| "grad_norm": 0.3994789042165044, | |
| "learning_rate": 1.9035662833259433e-05, | |
| "loss": 2.1166, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.030276437033786747, | |
| "grad_norm": 0.43451224425457347, | |
| "learning_rate": 1.8943324918225495e-05, | |
| "loss": 2.115, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.031592803861342694, | |
| "grad_norm": 0.47477550866034224, | |
| "learning_rate": 1.8847011335021447e-05, | |
| "loss": 2.0992, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03290917068889864, | |
| "grad_norm": 0.45702008497595437, | |
| "learning_rate": 1.874676489891461e-05, | |
| "loss": 2.0945, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03422553751645459, | |
| "grad_norm": 0.4552076980222439, | |
| "learning_rate": 1.8642630173483832e-05, | |
| "loss": 2.0913, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03554190434401053, | |
| "grad_norm": 0.491260417241798, | |
| "learning_rate": 1.85346534508092e-05, | |
| "loss": 2.0905, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.036858271171566474, | |
| "grad_norm": 0.5318585287005395, | |
| "learning_rate": 1.8422882730893323e-05, | |
| "loss": 2.1053, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03817463799912242, | |
| "grad_norm": 0.5542803704045, | |
| "learning_rate": 1.8307367700323412e-05, | |
| "loss": 2.1018, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03949100482667837, | |
| "grad_norm": 0.6717212863111561, | |
| "learning_rate": 1.8188159710183595e-05, | |
| "loss": 2.0679, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.040807371654234315, | |
| "grad_norm": 0.8673497250675066, | |
| "learning_rate": 1.8065311753227272e-05, | |
| "loss": 2.1119, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04212373848179026, | |
| "grad_norm": 1.436849681655791, | |
| "learning_rate": 1.7938878440319722e-05, | |
| "loss": 2.0968, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0434401053093462, | |
| "grad_norm": 1.190835978972668, | |
| "learning_rate": 1.7808915976161364e-05, | |
| "loss": 2.0994, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04475647213690215, | |
| "grad_norm": 1.2789704145502667, | |
| "learning_rate": 1.7675482134302503e-05, | |
| "loss": 2.0776, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.046072838964458095, | |
| "grad_norm": 1.1908199031673121, | |
| "learning_rate": 1.753863623146066e-05, | |
| "loss": 2.0773, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04738920579201404, | |
| "grad_norm": 1.0738268261460098, | |
| "learning_rate": 1.7398439101151908e-05, | |
| "loss": 2.0658, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04870557261956999, | |
| "grad_norm": 1.499778847610675, | |
| "learning_rate": 1.7254953066647915e-05, | |
| "loss": 2.0634, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.050021939447125935, | |
| "grad_norm": 0.8619559460048767, | |
| "learning_rate": 1.710824191327075e-05, | |
| "loss": 2.0997, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.051338306274681875, | |
| "grad_norm": 0.998834944268982, | |
| "learning_rate": 1.695837086003772e-05, | |
| "loss": 2.0717, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05265467310223782, | |
| "grad_norm": 0.9284767405070206, | |
| "learning_rate": 1.680540653066891e-05, | |
| "loss": 2.0662, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05397103992979377, | |
| "grad_norm": 0.8269926285276109, | |
| "learning_rate": 1.6649416923970248e-05, | |
| "loss": 2.0684, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.055287406757349715, | |
| "grad_norm": 0.8418661467632398, | |
| "learning_rate": 1.649047138360529e-05, | |
| "loss": 2.0572, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05660377358490566, | |
| "grad_norm": 0.8075424945075163, | |
| "learning_rate": 1.632864056726917e-05, | |
| "loss": 2.0551, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05792014041246161, | |
| "grad_norm": 0.8592395950636671, | |
| "learning_rate": 1.6163996415278423e-05, | |
| "loss": 2.0813, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05923650724001755, | |
| "grad_norm": 0.8707928517784076, | |
| "learning_rate": 1.5996612118590604e-05, | |
| "loss": 2.058, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.060552874067573495, | |
| "grad_norm": 1.0946448809183573, | |
| "learning_rate": 1.5826562086267956e-05, | |
| "loss": 2.0766, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06186924089512944, | |
| "grad_norm": 1.1506056250842094, | |
| "learning_rate": 1.565392191239959e-05, | |
| "loss": 2.0614, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06318560772268539, | |
| "grad_norm": 0.9795793219442529, | |
| "learning_rate": 1.5478768342496872e-05, | |
| "loss": 2.052, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06450197455024133, | |
| "grad_norm": 0.8754633709742095, | |
| "learning_rate": 1.5301179239376936e-05, | |
| "loss": 2.0629, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06581834137779728, | |
| "grad_norm": 0.7414365414012022, | |
| "learning_rate": 1.512123354854955e-05, | |
| "loss": 2.0415, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06713470820535322, | |
| "grad_norm": 0.7509358446177548, | |
| "learning_rate": 1.4939011263122635e-05, | |
| "loss": 2.0429, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.06845107503290918, | |
| "grad_norm": 0.5818796852647607, | |
| "learning_rate": 1.4754593388242117e-05, | |
| "loss": 2.0483, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.06976744186046512, | |
| "grad_norm": 0.7495835555591435, | |
| "learning_rate": 1.4568061905081874e-05, | |
| "loss": 2.0385, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.07108380868802106, | |
| "grad_norm": 0.8459840499756317, | |
| "learning_rate": 1.4379499734399797e-05, | |
| "loss": 2.049, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.07240017551557701, | |
| "grad_norm": 0.8720087506162435, | |
| "learning_rate": 1.4188990699676186e-05, | |
| "loss": 2.0453, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.07371654234313295, | |
| "grad_norm": 0.9273128675534362, | |
| "learning_rate": 1.3996619489850822e-05, | |
| "loss": 2.0565, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0750329091706889, | |
| "grad_norm": 0.921546466784409, | |
| "learning_rate": 1.3802471621675337e-05, | |
| "loss": 2.0373, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.07634927599824484, | |
| "grad_norm": 0.960376659848532, | |
| "learning_rate": 1.3606633401697557e-05, | |
| "loss": 2.0602, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0776656428258008, | |
| "grad_norm": 0.8413415416983288, | |
| "learning_rate": 1.340919188789477e-05, | |
| "loss": 2.0376, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.07898200965335674, | |
| "grad_norm": 0.6864608041510765, | |
| "learning_rate": 1.3210234850972966e-05, | |
| "loss": 2.0557, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08029837648091268, | |
| "grad_norm": 0.6505238720949514, | |
| "learning_rate": 1.300985073534919e-05, | |
| "loss": 2.054, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.08161474330846863, | |
| "grad_norm": 0.6736911062568327, | |
| "learning_rate": 1.280812861983446e-05, | |
| "loss": 2.033, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.08293111013602457, | |
| "grad_norm": 0.6570824389898786, | |
| "learning_rate": 1.2605158178034656e-05, | |
| "loss": 2.0379, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.08424747696358052, | |
| "grad_norm": 0.5671962154230362, | |
| "learning_rate": 1.2401029638486952e-05, | |
| "loss": 2.0129, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.08556384379113646, | |
| "grad_norm": 0.5692124705561362, | |
| "learning_rate": 1.219583374454963e-05, | |
| "loss": 2.0476, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0868802106186924, | |
| "grad_norm": 0.5725981777607406, | |
| "learning_rate": 1.1989661714063e-05, | |
| "loss": 2.0655, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.08819657744624836, | |
| "grad_norm": 0.4556259469574247, | |
| "learning_rate": 1.1782605198799371e-05, | |
| "loss": 2.0504, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0895129442738043, | |
| "grad_norm": 0.524007537125908, | |
| "learning_rate": 1.157475624372018e-05, | |
| "loss": 2.0239, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.09082931110136025, | |
| "grad_norm": 0.6552766297935877, | |
| "learning_rate": 1.1366207246058269e-05, | |
| "loss": 2.0344, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.09214567792891619, | |
| "grad_norm": 0.6000476533713694, | |
| "learning_rate": 1.1157050914243614e-05, | |
| "loss": 2.0425, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09346204475647214, | |
| "grad_norm": 0.427069095339742, | |
| "learning_rate": 1.0947380226690686e-05, | |
| "loss": 2.0366, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.09477841158402808, | |
| "grad_norm": 0.5458014746249031, | |
| "learning_rate": 1.0737288390465792e-05, | |
| "loss": 2.0269, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.09609477841158402, | |
| "grad_norm": 0.5713926359911967, | |
| "learning_rate": 1.0526868799852797e-05, | |
| "loss": 2.0494, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.09741114523913998, | |
| "grad_norm": 0.4450305194171364, | |
| "learning_rate": 1.031621499483559e-05, | |
| "loss": 2.0424, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.09872751206669592, | |
| "grad_norm": 0.5075528646964534, | |
| "learning_rate": 1.0105420619515798e-05, | |
| "loss": 2.03, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.10004387889425187, | |
| "grad_norm": 0.5365058261419554, | |
| "learning_rate": 9.894579380484206e-06, | |
| "loss": 2.0464, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.10136024572180781, | |
| "grad_norm": 0.41835317382658394, | |
| "learning_rate": 9.683785005164412e-06, | |
| "loss": 2.0501, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.10267661254936375, | |
| "grad_norm": 0.5041401192953681, | |
| "learning_rate": 9.473131200147205e-06, | |
| "loss": 2.0566, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.1039929793769197, | |
| "grad_norm": 0.44036179707697953, | |
| "learning_rate": 9.262711609534211e-06, | |
| "loss": 2.0415, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.10530934620447564, | |
| "grad_norm": 0.4296904409039965, | |
| "learning_rate": 9.052619773309318e-06, | |
| "loss": 2.0311, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1066257130320316, | |
| "grad_norm": 0.47878235738714614, | |
| "learning_rate": 8.842949085756389e-06, | |
| "loss": 2.0265, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.10794207985958754, | |
| "grad_norm": 0.4459594258814587, | |
| "learning_rate": 8.633792753941733e-06, | |
| "loss": 2.0353, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.10925844668714349, | |
| "grad_norm": 0.4266677596542947, | |
| "learning_rate": 8.425243756279824e-06, | |
| "loss": 2.0135, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.11057481351469943, | |
| "grad_norm": 0.4265568331885457, | |
| "learning_rate": 8.217394801200632e-06, | |
| "loss": 2.0346, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.11189118034225537, | |
| "grad_norm": 0.44368664638146177, | |
| "learning_rate": 8.010338285937006e-06, | |
| "loss": 2.0221, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.11320754716981132, | |
| "grad_norm": 0.43460183890888726, | |
| "learning_rate": 7.804166255450372e-06, | |
| "loss": 2.0283, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.11452391399736726, | |
| "grad_norm": 0.41620052704046173, | |
| "learning_rate": 7.598970361513052e-06, | |
| "loss": 2.0304, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.11584028082492322, | |
| "grad_norm": 0.3847308156120455, | |
| "learning_rate": 7.394841821965345e-06, | |
| "loss": 2.0065, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.11715664765247916, | |
| "grad_norm": 0.4283805976950811, | |
| "learning_rate": 7.191871380165538e-06, | |
| "loss": 2.0299, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.1184730144800351, | |
| "grad_norm": 0.38899376829654797, | |
| "learning_rate": 6.990149264650814e-06, | |
| "loss": 2.0211, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11978938130759105, | |
| "grad_norm": 0.4248507957889963, | |
| "learning_rate": 6.789765149027039e-06, | |
| "loss": 2.0283, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.12110574813514699, | |
| "grad_norm": 0.37316050005965007, | |
| "learning_rate": 6.590808112105232e-06, | |
| "loss": 2.042, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.12242211496270294, | |
| "grad_norm": 0.3822106653644349, | |
| "learning_rate": 6.3933665983024465e-06, | |
| "loss": 2.0279, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.12373848179025888, | |
| "grad_norm": 0.3644082107183213, | |
| "learning_rate": 6.197528378324664e-06, | |
| "loss": 2.0052, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.12505484861781482, | |
| "grad_norm": 0.3494588716878707, | |
| "learning_rate": 6.003380510149179e-06, | |
| "loss": 2.0307, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.12637121544537078, | |
| "grad_norm": 0.3622691814510023, | |
| "learning_rate": 5.8110093003238175e-06, | |
| "loss": 2.0539, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.12768758227292673, | |
| "grad_norm": 0.3543061636513716, | |
| "learning_rate": 5.620500265600206e-06, | |
| "loss": 2.0272, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.12900394910048266, | |
| "grad_norm": 0.32877859379020974, | |
| "learning_rate": 5.431938094918132e-06, | |
| "loss": 2.0354, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1303203159280386, | |
| "grad_norm": 0.35523489454351176, | |
| "learning_rate": 5.245406611757882e-06, | |
| "loss": 2.0344, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.13163668275559456, | |
| "grad_norm": 0.31685538402742514, | |
| "learning_rate": 5.060988736877366e-06, | |
| "loss": 2.0143, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13295304958315052, | |
| "grad_norm": 0.3297522128972124, | |
| "learning_rate": 4.878766451450451e-06, | |
| "loss": 2.0225, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.13426941641070644, | |
| "grad_norm": 0.33497503575163823, | |
| "learning_rate": 4.698820760623064e-06, | |
| "loss": 2.0145, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.1355857832382624, | |
| "grad_norm": 0.28908150200035015, | |
| "learning_rate": 4.5212316575031325e-06, | |
| "loss": 2.0263, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.13690215006581835, | |
| "grad_norm": 0.32192201799340825, | |
| "learning_rate": 4.346078087600411e-06, | |
| "loss": 2.0308, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.13821851689337428, | |
| "grad_norm": 0.3023784272686272, | |
| "learning_rate": 4.173437913732048e-06, | |
| "loss": 2.0266, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.13953488372093023, | |
| "grad_norm": 0.3126656763207986, | |
| "learning_rate": 4.003387881409397e-06, | |
| "loss": 2.0304, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.14085125054848618, | |
| "grad_norm": 0.2847069746988514, | |
| "learning_rate": 3.836003584721577e-06, | |
| "loss": 2.0285, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.1421676173760421, | |
| "grad_norm": 0.27905205818415024, | |
| "learning_rate": 3.6713594327308343e-06, | |
| "loss": 2.0148, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.14348398420359806, | |
| "grad_norm": 0.2850201850545098, | |
| "learning_rate": 3.509528616394716e-06, | |
| "loss": 2.0309, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.14480035103115402, | |
| "grad_norm": 0.2770161441690118, | |
| "learning_rate": 3.3505830760297543e-06, | |
| "loss": 2.0265, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.14611671785870997, | |
| "grad_norm": 0.25930968811114846, | |
| "learning_rate": 3.1945934693310897e-06, | |
| "loss": 2.032, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.1474330846862659, | |
| "grad_norm": 0.2907837763007102, | |
| "learning_rate": 3.0416291399622834e-06, | |
| "loss": 2.0579, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.14874945151382185, | |
| "grad_norm": 0.27456058940318046, | |
| "learning_rate": 2.891758086729253e-06, | |
| "loss": 2.0089, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.1500658183413778, | |
| "grad_norm": 0.26495906570608607, | |
| "learning_rate": 2.7450469333520856e-06, | |
| "loss": 2.0163, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.15138218516893373, | |
| "grad_norm": 0.24999690416201278, | |
| "learning_rate": 2.6015608988480956e-06, | |
| "loss": 2.0182, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.15269855199648968, | |
| "grad_norm": 0.2750137021153546, | |
| "learning_rate": 2.4613637685393433e-06, | |
| "loss": 2.0288, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.15401491882404564, | |
| "grad_norm": 0.25095947862604434, | |
| "learning_rate": 2.324517865697501e-06, | |
| "loss": 2.0018, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.1553312856516016, | |
| "grad_norm": 0.25035612273116925, | |
| "learning_rate": 2.19108402383864e-06, | |
| "loss": 2.014, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.15664765247915752, | |
| "grad_norm": 0.24837509630018656, | |
| "learning_rate": 2.06112155968028e-06, | |
| "loss": 2.0339, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.15796401930671347, | |
| "grad_norm": 0.2368931937103148, | |
| "learning_rate": 1.9346882467727323e-06, | |
| "loss": 2.0376, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.15928038613426942, | |
| "grad_norm": 0.2545967675793146, | |
| "learning_rate": 1.811840289816409e-06, | |
| "loss": 2.0307, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.16059675296182535, | |
| "grad_norm": 0.25131860633611014, | |
| "learning_rate": 1.6926322996765899e-06, | |
| "loss": 2.0301, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.1619131197893813, | |
| "grad_norm": 0.22809678013944915, | |
| "learning_rate": 1.5771172691066793e-06, | |
| "loss": 2.0351, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.16322948661693726, | |
| "grad_norm": 0.22689368961517264, | |
| "learning_rate": 1.4653465491908003e-06, | |
| "loss": 2.057, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.1645458534444932, | |
| "grad_norm": 0.24712441799177087, | |
| "learning_rate": 1.3573698265161683e-06, | |
| "loss": 2.014, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.16586222027204914, | |
| "grad_norm": 0.2314976942269643, | |
| "learning_rate": 1.2532351010853916e-06, | |
| "loss": 2.0179, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.1671785870996051, | |
| "grad_norm": 0.21885346239753412, | |
| "learning_rate": 1.152988664978556e-06, | |
| "loss": 2.0257, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.16849495392716105, | |
| "grad_norm": 0.23535944331000042, | |
| "learning_rate": 1.0566750817745076e-06, | |
| "loss": 2.0324, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.16981132075471697, | |
| "grad_norm": 0.236607442464291, | |
| "learning_rate": 9.6433716674057e-07, | |
| "loss": 2.0242, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.17112768758227292, | |
| "grad_norm": 0.22524921141369292, | |
| "learning_rate": 8.760159677994174e-07, | |
| "loss": 2.0297, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.17244405440982888, | |
| "grad_norm": 0.20920459504636824, | |
| "learning_rate": 7.91750747281621e-07, | |
| "loss": 2.0197, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.1737604212373848, | |
| "grad_norm": 0.21684013420732584, | |
| "learning_rate": 7.115789644719728e-07, | |
| "loss": 2.0392, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.17507678806494076, | |
| "grad_norm": 0.21477934466201076, | |
| "learning_rate": 6.355362589573078e-07, | |
| "loss": 2.0214, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.1763931548924967, | |
| "grad_norm": 0.21985406702266574, | |
| "learning_rate": 5.636564347832907e-07, | |
| "loss": 2.0269, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.17770952172005267, | |
| "grad_norm": 0.2052096519443174, | |
| "learning_rate": 4.95971445427137e-07, | |
| "loss": 2.0275, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.1790258885476086, | |
| "grad_norm": 0.219939251818976, | |
| "learning_rate": 4.3251137959302023e-07, | |
| "loss": 2.0143, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.18034225537516455, | |
| "grad_norm": 0.20490790805603135, | |
| "learning_rate": 3.733044478364234e-07, | |
| "loss": 2.0121, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.1816586222027205, | |
| "grad_norm": 0.19305915219239544, | |
| "learning_rate": 3.1837697002341293e-07, | |
| "loss": 2.0228, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.18297498903027642, | |
| "grad_norm": 0.2006700892759159, | |
| "learning_rate": 2.677533636303964e-07, | |
| "loss": 2.0126, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.18429135585783238, | |
| "grad_norm": 0.1958550260568627, | |
| "learning_rate": 2.214561328895748e-07, | |
| "loss": 2.0181, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.18560772268538833, | |
| "grad_norm": 0.21059995141009716, | |
| "learning_rate": 1.7950585878489856e-07, | |
| "loss": 2.0232, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.18692408951294429, | |
| "grad_norm": 0.19442411154311956, | |
| "learning_rate": 1.419211899029971e-07, | |
| "loss": 2.0135, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.1882404563405002, | |
| "grad_norm": 0.19241503320219153, | |
| "learning_rate": 1.0871883414312778e-07, | |
| "loss": 2.0241, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.18955682316805617, | |
| "grad_norm": 0.19325540063259095, | |
| "learning_rate": 7.99135512898408e-08, | |
| "loss": 2.0161, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.19087318999561212, | |
| "grad_norm": 0.20007002634183835, | |
| "learning_rate": 5.55181464516652e-08, | |
| "loss": 2.0195, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.19218955682316805, | |
| "grad_norm": 0.20565401855736842, | |
| "learning_rate": 3.554346436871581e-08, | |
| "loss": 2.0142, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.193505923650724, | |
| "grad_norm": 0.1962770877782674, | |
| "learning_rate": 1.9998384591773945e-08, | |
| "loss": 2.0221, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.19482229047827995, | |
| "grad_norm": 0.19269410833986975, | |
| "learning_rate": 8.889817534969425e-09, | |
| "loss": 2.0294, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.1961386573058359, | |
| "grad_norm": 0.19364725540708555, | |
| "learning_rate": 2.222701403818972e-09, | |
| "loss": 2.0189, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.19745502413339183, | |
| "grad_norm": 0.20479143193778032, | |
| "learning_rate": 0.0, | |
| "loss": 2.0316, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.19745502413339183, | |
| "step": 150, | |
| "total_flos": 349677715193856.0, | |
| "train_loss": 2.06172225634257, | |
| "train_runtime": 5203.5464, | |
| "train_samples_per_second": 58.114, | |
| "train_steps_per_second": 0.029 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 349677715193856.0, | |
| "train_batch_size": 42, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |