| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.016874789065136685, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016874789065136686, | |
| "grad_norm": 0.028356848284602165, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3763, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016874789065136686, | |
| "eval_loss": 10.379347801208496, | |
| "eval_runtime": 31.4288, | |
| "eval_samples_per_second": 158.772, | |
| "eval_steps_per_second": 19.854, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003374957813027337, | |
| "grad_norm": 0.030948113650083542, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3797, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005062436719541006, | |
| "grad_norm": 0.03464093431830406, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3791, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006749915626054674, | |
| "grad_norm": 0.02786366082727909, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3794, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008437394532568343, | |
| "grad_norm": 0.03303991258144379, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3766, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010124873439082012, | |
| "grad_norm": 0.03207448497414589, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3775, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001181235234559568, | |
| "grad_norm": 0.032260727137327194, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3742, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013499831252109348, | |
| "grad_norm": 0.029525339603424072, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3764, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015187310158623017, | |
| "grad_norm": 0.02664221078157425, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3771, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015187310158623017, | |
| "eval_loss": 10.379043579101562, | |
| "eval_runtime": 32.3213, | |
| "eval_samples_per_second": 154.388, | |
| "eval_steps_per_second": 19.306, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016874789065136687, | |
| "grad_norm": 0.03607453778386116, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3778, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018562267971650355, | |
| "grad_norm": 0.03146832808852196, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.38, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0020249746878164025, | |
| "grad_norm": 0.03396669775247574, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3798, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021937225784677693, | |
| "grad_norm": 0.031829774379730225, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3776, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002362470469119136, | |
| "grad_norm": 0.035005245357751846, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3792, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002531218359770503, | |
| "grad_norm": 0.028895363211631775, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3802, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026999662504218697, | |
| "grad_norm": 0.03257288783788681, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3779, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0028687141410732365, | |
| "grad_norm": 0.03187789395451546, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.378, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0030374620317246033, | |
| "grad_norm": 0.027622371912002563, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3802, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0030374620317246033, | |
| "eval_loss": 10.378274917602539, | |
| "eval_runtime": 32.1709, | |
| "eval_samples_per_second": 155.109, | |
| "eval_steps_per_second": 19.396, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00320620992237597, | |
| "grad_norm": 0.030003849416971207, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3806, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0033749578130273373, | |
| "grad_norm": 0.029102297499775887, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3803, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003543705703678704, | |
| "grad_norm": 0.03206076845526695, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3796, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003712453594330071, | |
| "grad_norm": 0.03624172881245613, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3777, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0038812014849814377, | |
| "grad_norm": 0.03577917814254761, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.3781, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004049949375632805, | |
| "grad_norm": 0.04020218178629875, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3796, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004218697266284171, | |
| "grad_norm": 0.03285733237862587, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3808, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004387445156935539, | |
| "grad_norm": 0.0344129353761673, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 10.3801, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004556193047586905, | |
| "grad_norm": 0.031542327255010605, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 10.3739, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004556193047586905, | |
| "eval_loss": 10.377501487731934, | |
| "eval_runtime": 31.7582, | |
| "eval_samples_per_second": 157.125, | |
| "eval_steps_per_second": 19.648, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004724940938238272, | |
| "grad_norm": 0.04038287326693535, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.38, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0048936888288896386, | |
| "grad_norm": 0.035440899431705475, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 10.3777, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005062436719541006, | |
| "grad_norm": 0.03684794902801514, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3777, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005231184610192373, | |
| "grad_norm": 0.037094008177518845, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 10.3753, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005399932500843739, | |
| "grad_norm": 0.03849518671631813, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 10.3778, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005568680391495107, | |
| "grad_norm": 0.0341559536755085, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 10.3773, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005737428282146473, | |
| "grad_norm": 0.03298812732100487, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 10.3769, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00590617617279784, | |
| "grad_norm": 0.03586151450872421, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3772, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006074924063449207, | |
| "grad_norm": 0.03737131133675575, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 10.3802, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006074924063449207, | |
| "eval_loss": 10.376688957214355, | |
| "eval_runtime": 32.1576, | |
| "eval_samples_per_second": 155.173, | |
| "eval_steps_per_second": 19.404, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006243671954100574, | |
| "grad_norm": 0.04200604930520058, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 10.3742, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00641241984475194, | |
| "grad_norm": 0.035852398723363876, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 10.3775, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0065811677354033074, | |
| "grad_norm": 0.03388199955224991, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 10.372, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006749915626054675, | |
| "grad_norm": 0.04054049402475357, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3777, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006918663516706041, | |
| "grad_norm": 0.046149663627147675, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 10.3765, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007087411407357408, | |
| "grad_norm": 0.034650132060050964, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 10.3765, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007256159298008775, | |
| "grad_norm": 0.040765125304460526, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 10.3776, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007424907188660142, | |
| "grad_norm": 0.03693521395325661, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 10.3762, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007593655079311508, | |
| "grad_norm": 0.03654073178768158, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3725, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007593655079311508, | |
| "eval_loss": 10.375885009765625, | |
| "eval_runtime": 32.2421, | |
| "eval_samples_per_second": 154.767, | |
| "eval_steps_per_second": 19.354, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0077624029699628755, | |
| "grad_norm": 0.041708655655384064, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.377, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007931150860614243, | |
| "grad_norm": 0.035714827477931976, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 10.3767, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.00809989875126561, | |
| "grad_norm": 0.040123410522937775, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 10.3781, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008268646641916975, | |
| "grad_norm": 0.03628898411989212, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 10.3737, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008437394532568343, | |
| "grad_norm": 0.03732474520802498, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3756, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00860614242321971, | |
| "grad_norm": 0.041091788560152054, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 10.3762, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.008774890313871077, | |
| "grad_norm": 0.03889773413538933, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 10.3749, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.008943638204522443, | |
| "grad_norm": 0.04212617129087448, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 10.3748, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.00911238609517381, | |
| "grad_norm": 0.049688007682561874, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 10.3742, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.00911238609517381, | |
| "eval_loss": 10.37514591217041, | |
| "eval_runtime": 31.7725, | |
| "eval_samples_per_second": 157.054, | |
| "eval_steps_per_second": 19.64, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.009281133985825177, | |
| "grad_norm": 0.0415961779654026, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3771, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.009449881876476544, | |
| "grad_norm": 0.03901247680187225, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 10.3763, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.009618629767127912, | |
| "grad_norm": 0.04563918337225914, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 10.3735, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.009787377657779277, | |
| "grad_norm": 0.04503565654158592, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 10.3787, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.009956125548430644, | |
| "grad_norm": 0.03429818153381348, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 10.3757, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.010124873439082012, | |
| "grad_norm": 0.047185059636831284, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 10.3727, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010293621329733379, | |
| "grad_norm": 0.036875538527965546, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 10.3743, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.010462369220384746, | |
| "grad_norm": 0.04312184825539589, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 10.3725, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.010631117111036112, | |
| "grad_norm": 0.044379640370607376, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 10.3707, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.010631117111036112, | |
| "eval_loss": 10.374529838562012, | |
| "eval_runtime": 32.241, | |
| "eval_samples_per_second": 154.772, | |
| "eval_steps_per_second": 19.354, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.010799865001687479, | |
| "grad_norm": 0.04435788467526436, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 10.3744, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.010968612892338846, | |
| "grad_norm": 0.057436853647232056, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 10.3749, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.011137360782990213, | |
| "grad_norm": 0.05647885799407959, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 10.3746, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.011306108673641579, | |
| "grad_norm": 0.04587814584374428, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 10.371, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.011474856564292946, | |
| "grad_norm": 0.05366501957178116, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 10.3735, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.011643604454944313, | |
| "grad_norm": 0.047794099897146225, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 10.373, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.01181235234559568, | |
| "grad_norm": 0.038880761712789536, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3792, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.011981100236247048, | |
| "grad_norm": 0.057157162576913834, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 10.374, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.012149848126898413, | |
| "grad_norm": 0.05762377753853798, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 10.3734, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.012149848126898413, | |
| "eval_loss": 10.374056816101074, | |
| "eval_runtime": 32.3321, | |
| "eval_samples_per_second": 154.336, | |
| "eval_steps_per_second": 19.3, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.01231859601754978, | |
| "grad_norm": 0.04748730733990669, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 10.376, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.012487343908201148, | |
| "grad_norm": 0.06332851946353912, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 10.3701, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.012656091798852515, | |
| "grad_norm": 0.04641574248671532, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 10.3772, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01282483968950388, | |
| "grad_norm": 0.054799892008304596, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 10.3725, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.012993587580155248, | |
| "grad_norm": 0.05315915495157242, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 10.3739, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.013162335470806615, | |
| "grad_norm": 0.046220242977142334, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 10.3714, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.013331083361457982, | |
| "grad_norm": 0.04859282448887825, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 10.3754, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.01349983125210935, | |
| "grad_norm": 0.060404203832149506, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 10.3756, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013668579142760715, | |
| "grad_norm": 0.06335998326539993, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 10.3758, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.013668579142760715, | |
| "eval_loss": 10.373773574829102, | |
| "eval_runtime": 31.5985, | |
| "eval_samples_per_second": 157.919, | |
| "eval_steps_per_second": 19.748, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.013837327033412082, | |
| "grad_norm": 0.049019236117601395, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.3761, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.01400607492406345, | |
| "grad_norm": 0.04913691058754921, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 10.3713, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.014174822814714817, | |
| "grad_norm": 0.06034684181213379, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 10.371, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.014343570705366182, | |
| "grad_norm": 0.056725285947322845, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3693, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.01451231859601755, | |
| "grad_norm": 0.05660969018936157, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 10.373, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.014681066486668917, | |
| "grad_norm": 0.047730952501297, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 10.3779, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.014849814377320284, | |
| "grad_norm": 0.0632791817188263, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 10.3775, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.015018562267971651, | |
| "grad_norm": 0.047488924115896225, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 10.3759, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.015187310158623017, | |
| "grad_norm": 0.051669273525476456, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 10.3746, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.015187310158623017, | |
| "eval_loss": 10.373652458190918, | |
| "eval_runtime": 32.1617, | |
| "eval_samples_per_second": 155.153, | |
| "eval_steps_per_second": 19.402, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.015356058049274384, | |
| "grad_norm": 0.05271625518798828, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 10.3734, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.015524805939925751, | |
| "grad_norm": 0.04908578842878342, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 10.3732, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.015693553830577116, | |
| "grad_norm": 0.044553857296705246, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 10.3752, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.015862301721228485, | |
| "grad_norm": 0.05484282970428467, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 10.3737, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.01603104961187985, | |
| "grad_norm": 0.05750522017478943, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 10.373, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.01619979750253122, | |
| "grad_norm": 0.05236552655696869, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 10.3743, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.016368545393182585, | |
| "grad_norm": 0.05108887702226639, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 10.3744, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.01653729328383395, | |
| "grad_norm": 0.05697884410619736, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 10.3761, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.01670604117448532, | |
| "grad_norm": 0.04061485826969147, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 10.3719, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.01670604117448532, | |
| "eval_loss": 10.373628616333008, | |
| "eval_runtime": 32.35, | |
| "eval_samples_per_second": 154.25, | |
| "eval_steps_per_second": 19.289, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.016874789065136685, | |
| "grad_norm": 0.058139506727457047, | |
| "learning_rate": 0.0, | |
| "loss": 10.3726, | |
| "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": 5230244659200.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |