| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4319654427645788, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004319654427645789, | |
| "grad_norm": 0.9524998068809509, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2163, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004319654427645789, | |
| "eval_loss": 0.2543673515319824, | |
| "eval_runtime": 44.0589, | |
| "eval_samples_per_second": 4.426, | |
| "eval_steps_per_second": 0.567, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008639308855291577, | |
| "grad_norm": 1.4569298028945923, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2263, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012958963282937365, | |
| "grad_norm": 1.389264702796936, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2592, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017278617710583154, | |
| "grad_norm": 0.33641600608825684, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1356, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02159827213822894, | |
| "grad_norm": 0.5771126747131348, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1613, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02591792656587473, | |
| "grad_norm": 1.5870953798294067, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3035, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03023758099352052, | |
| "grad_norm": 0.6865023374557495, | |
| "learning_rate": 7e-05, | |
| "loss": 0.122, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03455723542116631, | |
| "grad_norm": 0.5479922890663147, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0986, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.038876889848812095, | |
| "grad_norm": 0.6865485906600952, | |
| "learning_rate": 9e-05, | |
| "loss": 0.1016, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.038876889848812095, | |
| "eval_loss": 0.07106531411409378, | |
| "eval_runtime": 42.6177, | |
| "eval_samples_per_second": 4.576, | |
| "eval_steps_per_second": 0.587, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04319654427645788, | |
| "grad_norm": 0.37363576889038086, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0888, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.047516198704103674, | |
| "grad_norm": 0.28562089800834656, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.0604, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05183585313174946, | |
| "grad_norm": 0.23990653455257416, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0482, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.056155507559395246, | |
| "grad_norm": 0.39102837443351746, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.0524, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06047516198704104, | |
| "grad_norm": 1.527226209640503, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.0633, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06479481641468683, | |
| "grad_norm": 0.4168100953102112, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0409, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06911447084233262, | |
| "grad_norm": 0.263187050819397, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.0261, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0734341252699784, | |
| "grad_norm": 0.28248730301856995, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.0258, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07775377969762419, | |
| "grad_norm": 0.20124828815460205, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0309, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07775377969762419, | |
| "eval_loss": 0.02298855595290661, | |
| "eval_runtime": 42.6058, | |
| "eval_samples_per_second": 4.577, | |
| "eval_steps_per_second": 0.587, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08207343412526998, | |
| "grad_norm": 0.17783138155937195, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0225, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08639308855291576, | |
| "grad_norm": 0.20173536241054535, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.022, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09071274298056156, | |
| "grad_norm": 0.1374434232711792, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0227, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09503239740820735, | |
| "grad_norm": 0.1510484218597412, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0207, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09935205183585313, | |
| "grad_norm": 0.2596878409385681, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.0244, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10367170626349892, | |
| "grad_norm": 0.26210731267929077, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0163, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1079913606911447, | |
| "grad_norm": 0.20492668449878693, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0285, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11231101511879049, | |
| "grad_norm": 0.14693544805049896, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.015, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11663066954643629, | |
| "grad_norm": 0.07715924829244614, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.0086, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11663066954643629, | |
| "eval_loss": 0.011002009734511375, | |
| "eval_runtime": 42.615, | |
| "eval_samples_per_second": 4.576, | |
| "eval_steps_per_second": 0.587, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12095032397408208, | |
| "grad_norm": 0.14009982347488403, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0083, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12526997840172785, | |
| "grad_norm": 0.09885896742343903, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 0.0094, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12958963282937366, | |
| "grad_norm": 0.5052633881568909, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0134, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13390928725701945, | |
| "grad_norm": 0.11304973810911179, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 0.0151, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13822894168466524, | |
| "grad_norm": 0.09011288732290268, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.0083, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14254859611231102, | |
| "grad_norm": 0.11702302098274231, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.0093, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1468682505399568, | |
| "grad_norm": 0.09262354671955109, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.0117, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1511879049676026, | |
| "grad_norm": 0.11039795726537704, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0173, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15550755939524838, | |
| "grad_norm": 0.18931828439235687, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.0053, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15550755939524838, | |
| "eval_loss": 0.00827693473547697, | |
| "eval_runtime": 42.6233, | |
| "eval_samples_per_second": 4.575, | |
| "eval_steps_per_second": 0.587, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15982721382289417, | |
| "grad_norm": 0.1090330183506012, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0073, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16414686825053995, | |
| "grad_norm": 0.08737006038427353, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.0071, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16846652267818574, | |
| "grad_norm": 0.13259300589561462, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.0076, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.17278617710583152, | |
| "grad_norm": 0.22442105412483215, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0122, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1771058315334773, | |
| "grad_norm": 0.08325769752264023, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 0.0048, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18142548596112312, | |
| "grad_norm": 0.12202583253383636, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0055, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1857451403887689, | |
| "grad_norm": 0.0481962226331234, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.0046, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1900647948164147, | |
| "grad_norm": 0.06810636073350906, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.0056, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.19438444924406048, | |
| "grad_norm": 0.07894303649663925, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0055, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19438444924406048, | |
| "eval_loss": 0.005382665432989597, | |
| "eval_runtime": 42.6181, | |
| "eval_samples_per_second": 4.576, | |
| "eval_steps_per_second": 0.587, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19870410367170627, | |
| "grad_norm": 0.0615725964307785, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0054, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.20302375809935205, | |
| "grad_norm": 0.24329596757888794, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 0.0132, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.20734341252699784, | |
| "grad_norm": 0.0349898636341095, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0034, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.21166306695464362, | |
| "grad_norm": 0.05601835995912552, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.0062, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2159827213822894, | |
| "grad_norm": 0.06486399471759796, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0043, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2203023758099352, | |
| "grad_norm": 0.1450735628604889, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.0079, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.22462203023758098, | |
| "grad_norm": 0.09253419190645218, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.0064, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.22894168466522677, | |
| "grad_norm": 0.1478482335805893, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 0.0056, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.23326133909287258, | |
| "grad_norm": 0.0666055679321289, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0034, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.23326133909287258, | |
| "eval_loss": 0.0044831158593297005, | |
| "eval_runtime": 42.6508, | |
| "eval_samples_per_second": 4.572, | |
| "eval_steps_per_second": 0.586, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.23758099352051837, | |
| "grad_norm": 0.05718037858605385, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0036, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24190064794816415, | |
| "grad_norm": 0.047772157937288284, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.0033, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.24622030237580994, | |
| "grad_norm": 0.1433199644088745, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.0066, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2505399568034557, | |
| "grad_norm": 0.14454364776611328, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.003, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2548596112311015, | |
| "grad_norm": 0.0677032396197319, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 0.0022, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2591792656587473, | |
| "grad_norm": 0.056752149015665054, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0053, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2634989200863931, | |
| "grad_norm": 0.05664772540330887, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.0027, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2678185745140389, | |
| "grad_norm": 0.0625712126493454, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.0045, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.27213822894168466, | |
| "grad_norm": 0.08698461949825287, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.0039, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.27213822894168466, | |
| "eval_loss": 0.0033045976888388395, | |
| "eval_runtime": 42.6105, | |
| "eval_samples_per_second": 4.576, | |
| "eval_steps_per_second": 0.587, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.27645788336933047, | |
| "grad_norm": 0.31703194975852966, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0054, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.28077753779697623, | |
| "grad_norm": 0.057455211877822876, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0045, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.28509719222462204, | |
| "grad_norm": 0.043769922107458115, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0022, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2894168466522678, | |
| "grad_norm": 0.06640162318944931, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 0.0022, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2937365010799136, | |
| "grad_norm": 0.18320414423942566, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.002, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2980561555075594, | |
| "grad_norm": 0.05843820422887802, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.0038, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3023758099352052, | |
| "grad_norm": 0.041529346257448196, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0043, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.30669546436285094, | |
| "grad_norm": 0.0774838998913765, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 0.0042, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.31101511879049676, | |
| "grad_norm": 0.02668030932545662, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.0016, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.31101511879049676, | |
| "eval_loss": 0.0033292018342763186, | |
| "eval_runtime": 42.6419, | |
| "eval_samples_per_second": 4.573, | |
| "eval_steps_per_second": 0.586, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.31533477321814257, | |
| "grad_norm": 0.062281470745801926, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0051, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.31965442764578833, | |
| "grad_norm": 0.03590645641088486, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.0024, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.32397408207343414, | |
| "grad_norm": 0.08888695389032364, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0049, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3282937365010799, | |
| "grad_norm": 0.0329754464328289, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.0014, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3326133909287257, | |
| "grad_norm": 0.06644655019044876, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 0.005, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3369330453563715, | |
| "grad_norm": 0.071534663438797, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.0032, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3412526997840173, | |
| "grad_norm": 0.048516895622015, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 0.0039, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.34557235421166305, | |
| "grad_norm": 0.05907434597611427, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0029, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.34989200863930886, | |
| "grad_norm": 0.04661243036389351, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 0.0039, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.34989200863930886, | |
| "eval_loss": 0.0029163085855543613, | |
| "eval_runtime": 42.6384, | |
| "eval_samples_per_second": 4.573, | |
| "eval_steps_per_second": 0.586, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3542116630669546, | |
| "grad_norm": 0.04970655217766762, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0035, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.35853131749460043, | |
| "grad_norm": 0.05986812338232994, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 0.0069, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.36285097192224625, | |
| "grad_norm": 0.04365411773324013, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.0029, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.367170626349892, | |
| "grad_norm": 0.13277940452098846, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0056, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3714902807775378, | |
| "grad_norm": 0.05331737548112869, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.0032, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.3758099352051836, | |
| "grad_norm": 0.034497883170843124, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 0.0034, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.3801295896328294, | |
| "grad_norm": 0.024258598685264587, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.0021, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.38444924406047515, | |
| "grad_norm": 0.06567387282848358, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 0.0071, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.38876889848812096, | |
| "grad_norm": 0.05820886418223381, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.004, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.38876889848812096, | |
| "eval_loss": 0.002866251626983285, | |
| "eval_runtime": 42.5996, | |
| "eval_samples_per_second": 4.578, | |
| "eval_steps_per_second": 0.587, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3930885529157667, | |
| "grad_norm": 0.07091183215379715, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0051, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.39740820734341253, | |
| "grad_norm": 0.07214067131280899, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.0031, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.4017278617710583, | |
| "grad_norm": 0.047936685383319855, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 0.0033, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4060475161987041, | |
| "grad_norm": 0.04225027561187744, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.0041, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.4103671706263499, | |
| "grad_norm": 0.13431866466999054, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0038, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4146868250539957, | |
| "grad_norm": 0.07035449892282486, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.0038, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.4190064794816415, | |
| "grad_norm": 0.05573286861181259, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 0.0036, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.42332613390928725, | |
| "grad_norm": 0.09693485498428345, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.0048, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.42764578833693306, | |
| "grad_norm": 0.02684597484767437, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 0.0014, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.42764578833693306, | |
| "eval_loss": 0.002881319960579276, | |
| "eval_runtime": 42.5998, | |
| "eval_samples_per_second": 4.577, | |
| "eval_steps_per_second": 0.587, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.4319654427645788, | |
| "grad_norm": 0.02570461854338646, | |
| "learning_rate": 0.0, | |
| "loss": 0.0019, | |
| "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": 1.4652273850318848e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |