|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 114, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 5e-05, |
|
"loss": 0.1289, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1311, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 0.1223, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1101, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00019995921928281894, |
|
"loss": 0.1267, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00019983691039261357, |
|
"loss": 0.1282, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00019963317308626914, |
|
"loss": 0.1038, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00019934817353485501, |
|
"loss": 0.127, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0001989821441880933, |
|
"loss": 0.094, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00019853538358476932, |
|
"loss": 0.0962, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00019800825610923934, |
|
"loss": 0.0842, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00019740119169423337, |
|
"loss": 0.1035, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00019671468547019573, |
|
"loss": 0.0779, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.00019594929736144976, |
|
"loss": 0.0685, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.00019510565162951537, |
|
"loss": 0.0872, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.00019418443636395248, |
|
"loss": 0.0964, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.00019318640292114524, |
|
"loss": 0.1025, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.000192112365311485, |
|
"loss": 0.1233, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00019096319953545185, |
|
"loss": 0.0674, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.00018973984286913584, |
|
"loss": 0.1079, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.00018844329309978145, |
|
"loss": 0.0891, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.00018707460771197774, |
|
"loss": 0.1057, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.0001856349030251589, |
|
"loss": 0.1094, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.00018412535328311814, |
|
"loss": 0.0945, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.0001825471896962774, |
|
"loss": 0.093, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.00018090169943749476, |
|
"loss": 0.1067, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.00017919022459222752, |
|
"loss": 0.0718, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.00017741416106390826, |
|
"loss": 0.0786, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.00017557495743542585, |
|
"loss": 0.0852, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.0001736741137876405, |
|
"loss": 0.0796, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.00017171318047589637, |
|
"loss": 0.1008, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.00016969375686552937, |
|
"loss": 0.0952, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.00016761749002740193, |
|
"loss": 0.0881, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.00016548607339452853, |
|
"loss": 0.0955, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.00016330124538088705, |
|
"loss": 0.0823, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.00016106478796354382, |
|
"loss": 0.1021, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 0.00015877852522924732, |
|
"loss": 0.1055, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.00015644432188667695, |
|
"loss": 0.0823, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.00015406408174555976, |
|
"loss": 0.082, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 0.0001516397461638962, |
|
"loss": 0.0913, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.0001491732924645604, |
|
"loss": 0.0723, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.00014666673232256738, |
|
"loss": 0.0957, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.00014412211012432212, |
|
"loss": 0.0708, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.00014154150130018866, |
|
"loss": 0.0619, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.00013892701063173918, |
|
"loss": 0.0955, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.0001362807705350641, |
|
"loss": 0.0798, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.00013360493932154302, |
|
"loss": 0.0767, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.00013090169943749476, |
|
"loss": 0.0754, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.00012817325568414297, |
|
"loss": 0.0798, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.00012542183341934872, |
|
"loss": 0.0859, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 0.00012264967674257646, |
|
"loss": 0.0859, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 0.00011985904666457455, |
|
"loss": 0.0795, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 0.0001170522192632624, |
|
"loss": 0.0671, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.00011423148382732853, |
|
"loss": 0.0791, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 0.00011139914098905406, |
|
"loss": 0.085, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.00010855750084788398, |
|
"loss": 0.0637, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 0.00010570888108627681, |
|
"loss": 0.0713, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 0.00010285560507936961, |
|
"loss": 0.0646, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0585, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 9.71443949206304e-05, |
|
"loss": 0.0757, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 9.42911189137232e-05, |
|
"loss": 0.0551, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 9.144249915211605e-05, |
|
"loss": 0.0801, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 8.860085901094595e-05, |
|
"loss": 0.062, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 8.57685161726715e-05, |
|
"loss": 0.0614, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 8.294778073673762e-05, |
|
"loss": 0.0674, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 8.014095333542548e-05, |
|
"loss": 0.0803, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 7.735032325742355e-05, |
|
"loss": 0.0724, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 7.457816658065134e-05, |
|
"loss": 0.0701, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 7.182674431585704e-05, |
|
"loss": 0.082, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 6.909830056250527e-05, |
|
"loss": 0.0754, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 6.639506067845697e-05, |
|
"loss": 0.0789, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 6.371922946493591e-05, |
|
"loss": 0.0654, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 6.107298936826086e-05, |
|
"loss": 0.0616, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 5.845849869981137e-05, |
|
"loss": 0.0631, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 5.5877889875677845e-05, |
|
"loss": 0.0645, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 5.333326767743263e-05, |
|
"loss": 0.0596, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 5.082670753543961e-05, |
|
"loss": 0.0803, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 4.836025383610382e-05, |
|
"loss": 0.0559, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 4.593591825444028e-05, |
|
"loss": 0.0592, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 4.355567811332311e-05, |
|
"loss": 0.0509, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 4.12214747707527e-05, |
|
"loss": 0.0535, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 3.893521203645618e-05, |
|
"loss": 0.0558, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 3.669875461911297e-05, |
|
"loss": 0.0752, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 3.45139266054715e-05, |
|
"loss": 0.0551, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 3.238250997259808e-05, |
|
"loss": 0.0764, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 3.030624313447067e-05, |
|
"loss": 0.0531, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 2.828681952410366e-05, |
|
"loss": 0.0389, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 2.6325886212359498e-05, |
|
"loss": 0.0446, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 2.4425042564574184e-05, |
|
"loss": 0.0441, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 2.2585838936091754e-05, |
|
"loss": 0.0521, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 2.0809775407772503e-05, |
|
"loss": 0.064, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 1.9098300562505266e-05, |
|
"loss": 0.0491, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 1.74528103037226e-05, |
|
"loss": 0.0623, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 2.47, |
|
"learning_rate": 1.587464671688187e-05, |
|
"loss": 0.0574, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 1.4365096974841108e-05, |
|
"loss": 0.0432, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 1.2925392288022298e-05, |
|
"loss": 0.0562, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 1.1556706900218572e-05, |
|
"loss": 0.0527, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 1.026015713086418e-05, |
|
"loss": 0.0469, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 9.036800464548157e-06, |
|
"loss": 0.0497, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 7.887634688515e-06, |
|
"loss": 0.0592, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 6.813597078854772e-06, |
|
"loss": 0.0491, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 5.8155636360475385e-06, |
|
"loss": 0.0469, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 4.8943483704846475e-06, |
|
"loss": 0.056, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 2.74, |
|
"learning_rate": 4.050702638550275e-06, |
|
"loss": 0.0433, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 3.2853145298042953e-06, |
|
"loss": 0.0514, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 2.5988083057666533e-06, |
|
"loss": 0.0431, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 1.9917438907606556e-06, |
|
"loss": 0.0609, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 1.4646164152307018e-06, |
|
"loss": 0.0466, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 1.0178558119067315e-06, |
|
"loss": 0.0697, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 6.518264651449779e-07, |
|
"loss": 0.0427, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 3.6682691373086665e-07, |
|
"loss": 0.0594, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 1.630896073864352e-07, |
|
"loss": 0.0544, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 4.078071718107701e-08, |
|
"loss": 0.0663, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.0521, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 114, |
|
"total_flos": 2704210919424.0, |
|
"train_loss": 0.07567342122395833, |
|
"train_runtime": 1438.7994, |
|
"train_samples_per_second": 4.967, |
|
"train_steps_per_second": 0.079 |
|
} |
|
], |
|
"logging_steps": 1.0, |
|
"max_steps": 114, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 800, |
|
"total_flos": 2704210919424.0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|