| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6688963210702341, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006688963210702341, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006688963210702341, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.3651, | |
| "eval_samples_per_second": 23.485, | |
| "eval_steps_per_second": 2.982, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013377926421404682, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020066889632107024, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.026755852842809364, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.033444816053511704, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04013377926421405, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.046822742474916385, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05351170568561873, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06020066889632107, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06020066889632107, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1716, | |
| "eval_samples_per_second": 30.204, | |
| "eval_steps_per_second": 3.835, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06688963210702341, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07357859531772576, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.999390827019096e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0802675585284281, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9975640502598243e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9945218953682736e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09364548494983277, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9902680687415704e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10033444816053512, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10702341137123746, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11371237458193979, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9702957262759964e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12040133779264214, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.961261695938319e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12040133779264214, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1641, | |
| "eval_samples_per_second": 30.259, | |
| "eval_steps_per_second": 3.842, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12709030100334448, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13377926421404682, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14046822742474915, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9271838545667876e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14715719063545152, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8987940462991673e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1605351170568562, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8829475928589272e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16722408026755853, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.848048096156426e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1806020066889632, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8290375725550417e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1806020066889632, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1978, | |
| "eval_samples_per_second": 30.016, | |
| "eval_steps_per_second": 3.812, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.18729096989966554, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1939799331103679, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.788010753606722e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20066889632107024, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20735785953177258, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7431448254773943e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2140468227424749, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7193398003386514e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22073578595317725, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6946583704589973e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.22742474916387959, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23411371237458195, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2408026755852843, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6156614753256583e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2408026755852843, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1749, | |
| "eval_samples_per_second": 30.181, | |
| "eval_steps_per_second": 3.832, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24749163879598662, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.25418060200668896, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5591929034707468e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.529919264233205e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.26755852842809363, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27424749163879597, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.469471562785891e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2809364548494983, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4383711467890776e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.28762541806020064, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4067366430758004e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.29431438127090304, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3746065934159123e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3010033444816054, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.342020143325669e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3010033444816054, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1691, | |
| "eval_samples_per_second": 30.222, | |
| "eval_steps_per_second": 3.838, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.31438127090301005, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2756373558169992e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3210702341137124, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2419218955996677e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3277591973244147, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2079116908177592e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.33444816053511706, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3411371237458194, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1391731009600655e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.35451505016722407, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0697564737441254e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3612040133779264, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0348994967025012e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3612040133779264, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.194, | |
| "eval_samples_per_second": 30.043, | |
| "eval_steps_per_second": 3.815, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.36789297658862874, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3745819397993311, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.651005032974994e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.38127090301003347, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.302435262558748e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3879598662207358, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.39464882943143814, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.60826899039935e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.4013377926421405, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4080267558528428, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.92088309182241e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.41471571906354515, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.580781044003324e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4214046822742475, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.243626441830009e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4214046822742475, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1734, | |
| "eval_samples_per_second": 30.192, | |
| "eval_steps_per_second": 3.834, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4280936454849498, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.579798566743314e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4414715719063545, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.25393406584088e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.44816053511705684, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.932633569242e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.45484949832775917, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.616288532109225e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.305284372141095e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.4682274247491639, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.47491638795986624, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.700807357667953e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4816053511705686, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.408070965292534e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4816053511705686, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1686, | |
| "eval_samples_per_second": 30.226, | |
| "eval_steps_per_second": 3.838, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4882943143812709, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.49498327759197325, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8433852467434175e-06, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5016722408026756, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5721239031346067e-06, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5083612040133779, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5150501672240803, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0534162954100264e-06, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8066019966134907e-06, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5284280936454849, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5685517452260566e-06, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.5351170568561873, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5418060200668896, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.119892463932781e-06, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5418060200668896, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1778, | |
| "eval_samples_per_second": 30.16, | |
| "eval_steps_per_second": 3.83, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5484949832775919, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5551839464882943, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.709624274449584e-06, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5618729096989966, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5195190384357405e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.568561872909699, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5752508361204013, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1705240714107301e-06, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5819397993311036, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.012059537008332e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5886287625418061, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5953177257525084, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.281614543321269e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.6020066889632107, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6020066889632107, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1709, | |
| "eval_samples_per_second": 30.209, | |
| "eval_steps_per_second": 3.836, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6086956521739131, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.894348370484648e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8738304061681107e-07, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6220735785953178, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.970427372400353e-07, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6287625418060201, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6354515050167224, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.519224698779198e-07, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6421404682274248, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.731931258429638e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6488294314381271, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4781046317267103e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6555183946488294, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4359497401758026e-08, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6622073578595318, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.091729809042379e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6622073578595318, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1935, | |
| "eval_samples_per_second": 30.047, | |
| "eval_steps_per_second": 3.815, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6688963210702341, | |
| "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": 1.0911308983566336e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |