| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.059862316671655195, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000598623166716552, | |
| "grad_norm": 0.05297638103365898, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3658, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000598623166716552, | |
| "eval_loss": 10.36592960357666, | |
| "eval_runtime": 19.1787, | |
| "eval_samples_per_second": 73.363, | |
| "eval_steps_per_second": 9.177, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001197246333433104, | |
| "grad_norm": 0.046588554978370667, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3673, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017958695001496557, | |
| "grad_norm": 0.04986940696835518, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3668, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002394492666866208, | |
| "grad_norm": 0.05246109887957573, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3656, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00299311583358276, | |
| "grad_norm": 0.053375598043203354, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3666, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0035917390002993114, | |
| "grad_norm": 0.048240792006254196, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3663, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004190362167015863, | |
| "grad_norm": 0.04708974435925484, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3672, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004788985333732416, | |
| "grad_norm": 0.05008562281727791, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3661, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005387608500448967, | |
| "grad_norm": 0.05149425193667412, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3666, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005387608500448967, | |
| "eval_loss": 10.365216255187988, | |
| "eval_runtime": 19.1516, | |
| "eval_samples_per_second": 73.466, | |
| "eval_steps_per_second": 9.19, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00598623166716552, | |
| "grad_norm": 0.05135948210954666, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3646, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006584854833882071, | |
| "grad_norm": 0.049057915806770325, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3648, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007183478000598623, | |
| "grad_norm": 0.047746140509843826, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3646, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007782101167315175, | |
| "grad_norm": 0.05682039260864258, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3637, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008380724334031727, | |
| "grad_norm": 0.051367051899433136, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3624, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008979347500748278, | |
| "grad_norm": 0.050826847553253174, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3621, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009577970667464832, | |
| "grad_norm": 0.05443935841321945, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3651, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010176593834181383, | |
| "grad_norm": 0.052258800715208054, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3657, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010775217000897935, | |
| "grad_norm": 0.05204823985695839, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3663, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010775217000897935, | |
| "eval_loss": 10.363334655761719, | |
| "eval_runtime": 19.2079, | |
| "eval_samples_per_second": 73.251, | |
| "eval_steps_per_second": 9.163, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011373840167614486, | |
| "grad_norm": 0.05081361532211304, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3624, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01197246333433104, | |
| "grad_norm": 0.05326412618160248, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.366, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012571086501047591, | |
| "grad_norm": 0.05424303561449051, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3656, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013169709667764143, | |
| "grad_norm": 0.05486943945288658, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3608, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.013768332834480694, | |
| "grad_norm": 0.05334225296974182, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.3629, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014366956001197246, | |
| "grad_norm": 0.06037595868110657, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3641, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014965579167913799, | |
| "grad_norm": 0.06032309681177139, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3644, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01556420233463035, | |
| "grad_norm": 0.05547843128442764, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 10.3617, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.016162825501346904, | |
| "grad_norm": 0.05889257416129112, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 10.3626, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.016162825501346904, | |
| "eval_loss": 10.3612699508667, | |
| "eval_runtime": 19.1495, | |
| "eval_samples_per_second": 73.474, | |
| "eval_steps_per_second": 9.191, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.016761448668063453, | |
| "grad_norm": 0.06325730681419373, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3622, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.017360071834780007, | |
| "grad_norm": 0.061731647700071335, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 10.3599, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.017958695001496557, | |
| "grad_norm": 0.06298218667507172, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3596, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01855731816821311, | |
| "grad_norm": 0.06180060654878616, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 10.3596, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.019155941334929663, | |
| "grad_norm": 0.07021529972553253, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 10.359, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.019754564501646213, | |
| "grad_norm": 0.0688524842262268, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 10.3599, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.020353187668362766, | |
| "grad_norm": 0.06575062870979309, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 10.3625, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.020951810835079316, | |
| "grad_norm": 0.06917359679937363, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3589, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02155043400179587, | |
| "grad_norm": 0.07031112164258957, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 10.3596, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02155043400179587, | |
| "eval_loss": 10.3589506149292, | |
| "eval_runtime": 19.1447, | |
| "eval_samples_per_second": 73.493, | |
| "eval_steps_per_second": 9.193, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.022149057168512423, | |
| "grad_norm": 0.07395584136247635, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 10.3595, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.022747680335228972, | |
| "grad_norm": 0.06716927886009216, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 10.3576, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.023346303501945526, | |
| "grad_norm": 0.07539640367031097, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 10.3576, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02394492666866208, | |
| "grad_norm": 0.06986698508262634, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3604, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02454354983537863, | |
| "grad_norm": 0.07508890330791473, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 10.3587, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.025142173002095182, | |
| "grad_norm": 0.07691463083028793, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 10.3573, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.025740796168811732, | |
| "grad_norm": 0.07898183912038803, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 10.3602, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.026339419335528285, | |
| "grad_norm": 0.07909112423658371, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 10.3552, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02693804250224484, | |
| "grad_norm": 0.07970287650823593, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3566, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02693804250224484, | |
| "eval_loss": 10.356497764587402, | |
| "eval_runtime": 19.0898, | |
| "eval_samples_per_second": 73.704, | |
| "eval_steps_per_second": 9.22, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.027536665668961388, | |
| "grad_norm": 0.08517519384622574, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3541, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02813528883567794, | |
| "grad_norm": 0.07858609408140182, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 10.3542, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02873391200239449, | |
| "grad_norm": 0.08469705283641815, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 10.3538, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.029332535169111044, | |
| "grad_norm": 0.08389224112033844, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 10.3565, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.029931158335827598, | |
| "grad_norm": 0.08589687198400497, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3555, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.030529781502544148, | |
| "grad_norm": 0.08752743154764175, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 10.3551, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0311284046692607, | |
| "grad_norm": 0.08634073287248611, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 10.355, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.03172702783597725, | |
| "grad_norm": 0.08753424137830734, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 10.3568, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.03232565100269381, | |
| "grad_norm": 0.09251561015844345, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 10.3562, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03232565100269381, | |
| "eval_loss": 10.354073524475098, | |
| "eval_runtime": 19.2067, | |
| "eval_samples_per_second": 73.256, | |
| "eval_steps_per_second": 9.163, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03292427416941036, | |
| "grad_norm": 0.09084399044513702, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3536, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03352289733612691, | |
| "grad_norm": 0.08787762373685837, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 10.3558, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.03412152050284346, | |
| "grad_norm": 0.08676216006278992, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 10.3541, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.034720143669560014, | |
| "grad_norm": 0.09232042729854584, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 10.3544, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03531876683627656, | |
| "grad_norm": 0.09193498641252518, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 10.3535, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.03591739000299311, | |
| "grad_norm": 0.09521281719207764, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 10.3544, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03651601316970967, | |
| "grad_norm": 0.0845554769039154, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 10.359, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03711463633642622, | |
| "grad_norm": 0.09302161633968353, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 10.3516, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.03771325950314277, | |
| "grad_norm": 0.09675883501768112, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 10.349, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03771325950314277, | |
| "eval_loss": 10.352017402648926, | |
| "eval_runtime": 19.1958, | |
| "eval_samples_per_second": 73.297, | |
| "eval_steps_per_second": 9.169, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.038311882669859326, | |
| "grad_norm": 0.10135606676340103, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 10.3525, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.038910505836575876, | |
| "grad_norm": 0.09586833417415619, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 10.352, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.039509129003292426, | |
| "grad_norm": 0.1056274026632309, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 10.3543, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.04010775217000898, | |
| "grad_norm": 0.10619088262319565, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 10.3514, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.04070637533672553, | |
| "grad_norm": 0.09910062700510025, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 10.3532, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.04130499850344208, | |
| "grad_norm": 0.10119229555130005, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 10.3507, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.04190362167015863, | |
| "grad_norm": 0.1075066477060318, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.35, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04250224483687519, | |
| "grad_norm": 0.10859640687704086, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 10.3509, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.04310086800359174, | |
| "grad_norm": 0.0968688502907753, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 10.352, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.04310086800359174, | |
| "eval_loss": 10.35054874420166, | |
| "eval_runtime": 19.2033, | |
| "eval_samples_per_second": 73.269, | |
| "eval_steps_per_second": 9.165, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.04369949117030829, | |
| "grad_norm": 0.10456672310829163, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 10.3497, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.044298114337024845, | |
| "grad_norm": 0.10538659244775772, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 10.3505, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.044896737503741395, | |
| "grad_norm": 0.10384473204612732, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 10.3491, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.045495360670457945, | |
| "grad_norm": 0.10774772614240646, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 10.3513, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0460939838371745, | |
| "grad_norm": 0.10038568079471588, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 10.353, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.04669260700389105, | |
| "grad_norm": 0.10181721299886703, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 10.3517, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0472912301706076, | |
| "grad_norm": 0.10325980931520462, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 10.3504, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.04788985333732416, | |
| "grad_norm": 0.1077234223484993, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 10.3515, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04848847650404071, | |
| "grad_norm": 0.11477098613977432, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 10.3494, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.04848847650404071, | |
| "eval_loss": 10.349677085876465, | |
| "eval_runtime": 19.2103, | |
| "eval_samples_per_second": 73.242, | |
| "eval_steps_per_second": 9.162, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.04908709967075726, | |
| "grad_norm": 0.10639707744121552, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.3508, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.04968572283747381, | |
| "grad_norm": 0.10731644928455353, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 10.3518, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.050284346004190364, | |
| "grad_norm": 0.11128324270248413, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 10.3501, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.050882969170906914, | |
| "grad_norm": 0.1119207963347435, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.349, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.051481592337623464, | |
| "grad_norm": 0.12384051084518433, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 10.3503, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.05208021550434002, | |
| "grad_norm": 0.11188597977161407, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 10.3501, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.05267883867105657, | |
| "grad_norm": 0.10519222915172577, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 10.3496, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.05327746183777312, | |
| "grad_norm": 0.10873488336801529, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 10.3502, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.05387608500448968, | |
| "grad_norm": 0.11624474823474884, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 10.349, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05387608500448968, | |
| "eval_loss": 10.34931755065918, | |
| "eval_runtime": 19.207, | |
| "eval_samples_per_second": 73.255, | |
| "eval_steps_per_second": 9.163, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.054474708171206226, | |
| "grad_norm": 0.10113722831010818, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 10.3514, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.055073331337922776, | |
| "grad_norm": 0.10293326526880264, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 10.3512, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.05567195450463933, | |
| "grad_norm": 0.1147138923406601, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 10.3492, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.05627057767135588, | |
| "grad_norm": 0.11943775415420532, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 10.3465, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.05686920083807243, | |
| "grad_norm": 0.09904798120260239, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 10.3508, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.05746782400478898, | |
| "grad_norm": 0.10152188688516617, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 10.3515, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.05806644717150554, | |
| "grad_norm": 0.10223829746246338, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 10.3493, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.05866507033822209, | |
| "grad_norm": 0.112350694835186, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 10.3513, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.05926369350493864, | |
| "grad_norm": 0.10627704858779907, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 10.348, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.05926369350493864, | |
| "eval_loss": 10.34925365447998, | |
| "eval_runtime": 19.147, | |
| "eval_samples_per_second": 73.484, | |
| "eval_steps_per_second": 9.192, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.059862316671655195, | |
| "grad_norm": 0.10532322525978088, | |
| "learning_rate": 0.0, | |
| "loss": 10.3493, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 10460489318400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |