| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2306805074971165, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002306805074971165, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002306805074971165, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.6349, | |
| "eval_samples_per_second": 6.935, | |
| "eval_steps_per_second": 0.874, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00461361014994233, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006920415224913495, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00922722029988466, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011534025374855825, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01384083044982699, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016147635524798153, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01845444059976932, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020761245674740483, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020761245674740483, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.1464, | |
| "eval_samples_per_second": 7.0, | |
| "eval_steps_per_second": 0.882, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02306805074971165, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025374855824682813, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.999390827019096e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02768166089965398, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9975640502598243e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029988465974625143, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9945218953682736e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03229527104959631, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9902680687415704e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03460207612456748, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03690888119953864, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9702957262759964e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04152249134948097, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.961261695938319e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04152249134948097, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.1327, | |
| "eval_samples_per_second": 7.001, | |
| "eval_steps_per_second": 0.882, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04382929642445214, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0461361014994233, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04844290657439446, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9271838545667876e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05074971164936563, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0530565167243368, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8987940462991673e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05536332179930796, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8829475928589272e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05767012687427912, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05997693194925029, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.848048096156426e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06228373702422145, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8290375725550417e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06228373702422145, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.3014, | |
| "eval_samples_per_second": 6.979, | |
| "eval_steps_per_second": 0.88, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06459054209919261, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06689734717416378, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.788010753606722e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06920415224913495, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07151095732410612, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7431448254773943e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07381776239907728, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7193398003386514e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07612456747404844, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6946583704589973e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08073817762399077, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08304498269896193, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6156614753256583e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08304498269896193, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.1788, | |
| "eval_samples_per_second": 6.995, | |
| "eval_steps_per_second": 0.882, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0853517877739331, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08765859284890427, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5591929034707468e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08996539792387544, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.529919264233205e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0922722029988466, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09457900807381776, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.469471562785891e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09688581314878893, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4383711467890776e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09919261822376009, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4067366430758004e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10149942329873125, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3746065934159123e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10380622837370242, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.342020143325669e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10380622837370242, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.1153, | |
| "eval_samples_per_second": 7.004, | |
| "eval_steps_per_second": 0.883, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1061130334486736, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10841983852364476, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2756373558169992e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11072664359861592, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2419218955996677e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11303344867358708, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2079116908177592e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11534025374855825, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1391731009600655e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.11995386389850057, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.12226066897347174, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0697564737441254e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1245674740484429, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0348994967025012e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1245674740484429, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.1304, | |
| "eval_samples_per_second": 7.002, | |
| "eval_steps_per_second": 0.882, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.12687427912341406, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.12918108419838523, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.651005032974994e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1314878892733564, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.302435262558748e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.13379469434832755, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.13610149942329874, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.60826899039935e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1384083044982699, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14071510957324107, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.92088309182241e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.14302191464821223, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.580781044003324e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1453287197231834, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.243626441830009e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1453287197231834, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.1358, | |
| "eval_samples_per_second": 7.001, | |
| "eval_steps_per_second": 0.882, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.14763552479815456, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.14994232987312572, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.579798566743314e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1522491349480969, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.25393406584088e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.15455594002306805, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.932633569242e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.616288532109225e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.15916955017301038, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.305284372141095e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.16147635524798154, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1637831603229527, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.700807357667953e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.16608996539792387, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.408070965292534e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.16608996539792387, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.1358, | |
| "eval_samples_per_second": 7.001, | |
| "eval_steps_per_second": 0.882, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.16839677047289503, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1707035755478662, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8433852467434175e-06, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.17301038062283736, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5721239031346067e-06, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.17531718569780855, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.1776239907727797, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0534162954100264e-06, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.17993079584775087, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8066019966134907e-06, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.18223760092272204, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5685517452260566e-06, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.1845444059976932, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18685121107266436, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.119892463932781e-06, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.18685121107266436, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.1612, | |
| "eval_samples_per_second": 6.998, | |
| "eval_steps_per_second": 0.882, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.18915801614763553, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.1914648212226067, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.709624274449584e-06, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.19377162629757785, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5195190384357405e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.19607843137254902, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.19838523644752018, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1705240714107301e-06, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.20069204152249134, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.012059537008332e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.2029988465974625, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.20530565167243367, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.281614543321269e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.20761245674740483, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20761245674740483, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.1792, | |
| "eval_samples_per_second": 6.995, | |
| "eval_steps_per_second": 0.882, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.209919261822376, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.894348370484648e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.2122260668973472, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8738304061681107e-07, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.21453287197231835, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.970427372400353e-07, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.21683967704728951, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.21914648212226068, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.519224698779198e-07, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.22145328719723184, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.731931258429638e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.223760092272203, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4781046317267103e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.22606689734717417, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4359497401758026e-08, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.22837370242214533, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.091729809042379e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.22837370242214533, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.1291, | |
| "eval_samples_per_second": 7.002, | |
| "eval_steps_per_second": 0.882, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2306805074971165, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "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": 1.0126761420600115e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |