| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.24539877300613497, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00245398773006135, | |
| "grad_norm": 1.2490895986557007, | |
| "learning_rate": 1e-05, | |
| "loss": 0.377, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00245398773006135, | |
| "eval_loss": 0.3467381000518799, | |
| "eval_runtime": 73.3044, | |
| "eval_samples_per_second": 4.679, | |
| "eval_steps_per_second": 0.587, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0049079754601227, | |
| "grad_norm": 0.9828861951828003, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2967, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007361963190184049, | |
| "grad_norm": 1.7154072523117065, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4348, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0098159509202454, | |
| "grad_norm": 1.0366357564926147, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4483, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012269938650306749, | |
| "grad_norm": 0.5755931735038757, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3339, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014723926380368098, | |
| "grad_norm": 0.538214921951294, | |
| "learning_rate": 6e-05, | |
| "loss": 0.2947, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01717791411042945, | |
| "grad_norm": 0.6407910585403442, | |
| "learning_rate": 7e-05, | |
| "loss": 0.3255, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0196319018404908, | |
| "grad_norm": 0.5397402048110962, | |
| "learning_rate": 8e-05, | |
| "loss": 0.2128, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022085889570552148, | |
| "grad_norm": 0.4955255091190338, | |
| "learning_rate": 9e-05, | |
| "loss": 0.2757, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022085889570552148, | |
| "eval_loss": 0.19442740082740784, | |
| "eval_runtime": 72.614, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 0.592, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024539877300613498, | |
| "grad_norm": 0.6418875455856323, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2009, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026993865030674847, | |
| "grad_norm": 0.49799808859825134, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.1871, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029447852760736196, | |
| "grad_norm": 0.38547053933143616, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.1577, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03190184049079755, | |
| "grad_norm": 0.4232013523578644, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.1357, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0343558282208589, | |
| "grad_norm": 0.26138433814048767, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.102, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03680981595092025, | |
| "grad_norm": 0.2390362024307251, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.1143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0392638036809816, | |
| "grad_norm": 0.3332692086696625, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.1448, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04171779141104295, | |
| "grad_norm": 0.24300773441791534, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.1121, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.044171779141104296, | |
| "grad_norm": 0.36635148525238037, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.1723, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.044171779141104296, | |
| "eval_loss": 0.11410464346408844, | |
| "eval_runtime": 72.6128, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 0.592, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.046625766871165646, | |
| "grad_norm": 0.2136872410774231, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0939, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.049079754601226995, | |
| "grad_norm": 0.2869775593280792, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.1161, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.051533742331288344, | |
| "grad_norm": 0.21182110905647278, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0954, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.053987730061349694, | |
| "grad_norm": 0.4248709976673126, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0941, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05644171779141104, | |
| "grad_norm": 0.16834016144275665, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.0836, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05889570552147239, | |
| "grad_norm": 0.25709477066993713, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0771, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06134969325153374, | |
| "grad_norm": 0.3403218686580658, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1511, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0638036809815951, | |
| "grad_norm": 0.15573786199092865, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.0681, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06625766871165645, | |
| "grad_norm": 0.26487231254577637, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.1362, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06625766871165645, | |
| "eval_loss": 0.09782156348228455, | |
| "eval_runtime": 72.5753, | |
| "eval_samples_per_second": 4.726, | |
| "eval_steps_per_second": 0.592, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0687116564417178, | |
| "grad_norm": 0.30442625284194946, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.078, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07116564417177915, | |
| "grad_norm": 0.17983438074588776, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 0.1232, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0736196319018405, | |
| "grad_norm": 0.18753987550735474, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.1154, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07607361963190185, | |
| "grad_norm": 0.14537593722343445, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 0.0899, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0785276073619632, | |
| "grad_norm": 0.180735781788826, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.0981, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08098159509202454, | |
| "grad_norm": 0.15630754828453064, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.1026, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0834355828220859, | |
| "grad_norm": 0.2722282111644745, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.1142, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08588957055214724, | |
| "grad_norm": 0.1411922425031662, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0742, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08834355828220859, | |
| "grad_norm": 0.17076779901981354, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.1097, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08834355828220859, | |
| "eval_loss": 0.09277616441249847, | |
| "eval_runtime": 72.5864, | |
| "eval_samples_per_second": 4.725, | |
| "eval_steps_per_second": 0.592, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09079754601226994, | |
| "grad_norm": 0.17781254649162292, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.1031, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09325153374233129, | |
| "grad_norm": 0.11563621461391449, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.0678, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09570552147239264, | |
| "grad_norm": 0.18766151368618011, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.1294, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09815950920245399, | |
| "grad_norm": 0.20950351655483246, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1023, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10061349693251534, | |
| "grad_norm": 0.13120564818382263, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 0.083, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10306748466257669, | |
| "grad_norm": 0.16755475103855133, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0912, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10552147239263804, | |
| "grad_norm": 0.12863048911094666, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.092, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10797546012269939, | |
| "grad_norm": 0.14830118417739868, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.0955, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11042944785276074, | |
| "grad_norm": 0.2248990535736084, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.093, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11042944785276074, | |
| "eval_loss": 0.08893309533596039, | |
| "eval_runtime": 72.552, | |
| "eval_samples_per_second": 4.728, | |
| "eval_steps_per_second": 0.593, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11288343558282209, | |
| "grad_norm": 0.1789003610610962, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0969, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11533742331288344, | |
| "grad_norm": 0.29910632967948914, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 0.1165, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11779141104294479, | |
| "grad_norm": 0.16039490699768066, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0858, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12024539877300613, | |
| "grad_norm": 0.1589939296245575, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.0924, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12269938650306748, | |
| "grad_norm": 0.17117133736610413, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0931, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12515337423312883, | |
| "grad_norm": 0.12616045773029327, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.0895, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.1276073619631902, | |
| "grad_norm": 0.133722722530365, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.0935, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13006134969325153, | |
| "grad_norm": 0.2328999936580658, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 0.0983, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1325153374233129, | |
| "grad_norm": 0.1427900344133377, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0799, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1325153374233129, | |
| "eval_loss": 0.08606944978237152, | |
| "eval_runtime": 72.534, | |
| "eval_samples_per_second": 4.729, | |
| "eval_steps_per_second": 0.593, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13496932515337423, | |
| "grad_norm": 0.16906791925430298, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0607, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1374233128834356, | |
| "grad_norm": 0.13459601998329163, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.0849, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.13987730061349693, | |
| "grad_norm": 0.17573149502277374, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.0727, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1423312883435583, | |
| "grad_norm": 0.14718861877918243, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.0842, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.14478527607361963, | |
| "grad_norm": 0.13461712002754211, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 0.0713, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.147239263803681, | |
| "grad_norm": 0.14543554186820984, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0835, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14969325153374233, | |
| "grad_norm": 0.1449080854654312, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.076, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1521472392638037, | |
| "grad_norm": 0.15544362366199493, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.0936, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.15460122699386503, | |
| "grad_norm": 0.1345524936914444, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.0855, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.15460122699386503, | |
| "eval_loss": 0.08375449478626251, | |
| "eval_runtime": 72.5986, | |
| "eval_samples_per_second": 4.725, | |
| "eval_steps_per_second": 0.592, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1570552147239264, | |
| "grad_norm": 0.1138109564781189, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.076, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.15950920245398773, | |
| "grad_norm": 0.14898569881916046, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0799, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1619631901840491, | |
| "grad_norm": 0.13991095125675201, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0779, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.16441717791411042, | |
| "grad_norm": 0.2358105480670929, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 0.1083, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.1668711656441718, | |
| "grad_norm": 0.1775648146867752, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.0879, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.16932515337423312, | |
| "grad_norm": 0.1891743540763855, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.102, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.17177914110429449, | |
| "grad_norm": 0.16097727417945862, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0914, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17423312883435582, | |
| "grad_norm": 0.09334325790405273, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 0.0564, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.17668711656441718, | |
| "grad_norm": 0.12249859422445297, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.06, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.17668711656441718, | |
| "eval_loss": 0.08157961070537567, | |
| "eval_runtime": 72.6132, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 0.592, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.17914110429447852, | |
| "grad_norm": 0.12387010455131531, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0835, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.18159509202453988, | |
| "grad_norm": 0.1005992442369461, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.0569, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.18404907975460122, | |
| "grad_norm": 0.1461544632911682, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0591, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.18650306748466258, | |
| "grad_norm": 0.15801814198493958, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.107, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.18895705521472392, | |
| "grad_norm": 0.14311841130256653, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 0.0723, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.19141104294478528, | |
| "grad_norm": 0.26355618238449097, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.1375, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.19386503067484662, | |
| "grad_norm": 0.18676921725273132, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 0.0876, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.19631901840490798, | |
| "grad_norm": 0.15667636692523956, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0802, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19877300613496932, | |
| "grad_norm": 0.1485484093427658, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 0.093, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.19877300613496932, | |
| "eval_loss": 0.08068693429231644, | |
| "eval_runtime": 72.5605, | |
| "eval_samples_per_second": 4.727, | |
| "eval_steps_per_second": 0.593, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.20122699386503068, | |
| "grad_norm": 0.17449061572551727, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.081, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.20368098159509201, | |
| "grad_norm": 0.18600428104400635, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 0.0983, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.20613496932515338, | |
| "grad_norm": 0.25841566920280457, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.1364, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2085889570552147, | |
| "grad_norm": 0.15932850539684296, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0906, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.21104294478527608, | |
| "grad_norm": 0.1419418305158615, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.0762, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.2134969325153374, | |
| "grad_norm": 0.1434643417596817, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 0.0746, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.21595092024539878, | |
| "grad_norm": 0.1833578497171402, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.0677, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2184049079754601, | |
| "grad_norm": 0.12698689103126526, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 0.0722, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.22085889570552147, | |
| "grad_norm": 0.13668203353881836, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0869, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22085889570552147, | |
| "eval_loss": 0.07971709966659546, | |
| "eval_runtime": 72.5838, | |
| "eval_samples_per_second": 4.726, | |
| "eval_steps_per_second": 0.592, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2233128834355828, | |
| "grad_norm": 0.17934265732765198, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0912, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.22576687116564417, | |
| "grad_norm": 0.2167123705148697, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.1007, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2282208588957055, | |
| "grad_norm": 0.1933976113796234, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 0.0885, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.23067484662576687, | |
| "grad_norm": 0.15569214522838593, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.1064, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.2331288343558282, | |
| "grad_norm": 0.10046561807394028, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0589, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.23558282208588957, | |
| "grad_norm": 0.18496468663215637, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.0663, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.23803680981595093, | |
| "grad_norm": 0.15307293832302094, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 0.087, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.24049079754601227, | |
| "grad_norm": 0.703031599521637, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.0849, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.24294478527607363, | |
| "grad_norm": 0.12190704792737961, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 0.0673, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.24294478527607363, | |
| "eval_loss": 0.07961469888687134, | |
| "eval_runtime": 72.5905, | |
| "eval_samples_per_second": 4.725, | |
| "eval_steps_per_second": 0.592, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.24539877300613497, | |
| "grad_norm": 0.1318531483411789, | |
| "learning_rate": 0.0, | |
| "loss": 0.0657, | |
| "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": 1.283465000559575e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |