| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6600660066006601, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006600660066006601, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006600660066006601, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.8697, | |
| "eval_samples_per_second": 12.969, | |
| "eval_steps_per_second": 1.621, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013201320132013201, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019801980198019802, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.026402640264026403, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.033003300330033, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.039603960396039604, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0462046204620462, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.052805280528052806, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0594059405940594, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0594059405940594, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.4029, | |
| "eval_samples_per_second": 13.613, | |
| "eval_steps_per_second": 1.702, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.066006600660066, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07260726072607261, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.999390827019096e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07920792079207921, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9975640502598243e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0858085808580858, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9945218953682736e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0924092409240924, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9902680687415704e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09900990099009901, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10561056105610561, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11221122112211221, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9702957262759964e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1188118811881188, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.961261695938319e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1188118811881188, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.4035, | |
| "eval_samples_per_second": 13.612, | |
| "eval_steps_per_second": 1.701, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1254125412541254, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.132013201320132, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13861386138613863, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9271838545667876e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14521452145214522, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15181518151815182, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8987940462991673e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8829475928589272e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16501650165016502, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1716171617161716, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.848048096156426e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1782178217821782, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8290375725550417e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1782178217821782, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.409, | |
| "eval_samples_per_second": 13.604, | |
| "eval_steps_per_second": 1.7, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1848184818481848, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19141914191419143, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.788010753606722e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.19801980198019803, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20462046204620463, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7431448254773943e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.21122112211221122, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7193398003386514e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.21782178217821782, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6946583704589973e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.22442244224422442, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23102310231023102, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6156614753256583e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.4108, | |
| "eval_samples_per_second": 13.601, | |
| "eval_steps_per_second": 1.7, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24422442244224424, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2508250825082508, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5591929034707468e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.25742574257425743, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.529919264233205e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.264026402640264, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2706270627062706, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.469471562785891e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.27722772277227725, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4383711467890776e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2838283828382838, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4067366430758004e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.29042904290429045, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3746065934159123e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.297029702970297, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.342020143325669e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.297029702970297, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.3931, | |
| "eval_samples_per_second": 13.627, | |
| "eval_steps_per_second": 1.703, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.30363036303630364, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3102310231023102, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2756373558169992e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2419218955996677e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3234323432343234, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2079116908177592e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.33003300330033003, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33663366336633666, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1391731009600655e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3432343234323432, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.34983498349834985, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0697564737441254e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3564356435643564, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0348994967025012e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3564356435643564, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.4104, | |
| "eval_samples_per_second": 13.602, | |
| "eval_steps_per_second": 1.7, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.36303630363036304, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3696369636963696, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.651005032974994e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.37623762376237624, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.302435262558748e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.38283828382838286, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.38943894389438943, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.60826899039935e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.40264026402640263, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.92088309182241e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.40924092409240925, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.580781044003324e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4158415841584158, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.243626441830009e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4158415841584158, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.4017, | |
| "eval_samples_per_second": 13.615, | |
| "eval_steps_per_second": 1.702, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.42244224422442245, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.429042904290429, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.579798566743314e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.43564356435643564, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.25393406584088e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.44224422442244227, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.932633569242e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.44884488448844884, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.616288532109225e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.45544554455445546, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.305284372141095e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.46204620462046203, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46864686468646866, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.700807357667953e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.408070965292534e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.4077, | |
| "eval_samples_per_second": 13.606, | |
| "eval_steps_per_second": 1.701, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.48184818481848185, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4884488448844885, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8433852467434175e-06, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.49504950495049505, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5721239031346067e-06, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5016501650165016, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5082508250825083, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0534162954100264e-06, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5148514851485149, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8066019966134907e-06, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5214521452145214, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5685517452260566e-06, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.528052805280528, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5346534653465347, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.119892463932781e-06, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5346534653465347, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.4082, | |
| "eval_samples_per_second": 13.605, | |
| "eval_steps_per_second": 1.701, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5412541254125413, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5478547854785478, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.709624274449584e-06, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5544554455445545, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5195190384357405e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5610561056105611, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5676567656765676, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1705240714107301e-06, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5742574257425742, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.012059537008332e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5808580858085809, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5874587458745875, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.281614543321269e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.594059405940594, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.594059405940594, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.3988, | |
| "eval_samples_per_second": 13.619, | |
| "eval_steps_per_second": 1.702, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6006600660066007, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.894348370484648e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6072607260726073, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8738304061681107e-07, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6138613861386139, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.970427372400353e-07, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6204620462046204, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6270627062706271, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.519224698779198e-07, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.731931258429638e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6402640264026402, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4781046317267103e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6468646864686468, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4359497401758026e-08, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6534653465346535, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.091729809042379e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6534653465346535, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.4006, | |
| "eval_samples_per_second": 13.616, | |
| "eval_steps_per_second": 1.702, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6600660066006601, | |
| "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": 3.762598013042688e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |