|
{ |
|
"best_metric": 0.6790379881858826, |
|
"best_model_checkpoint": "petsona-cat/checkpoint-1835", |
|
"epoch": 5.0, |
|
"eval_steps": 500, |
|
"global_step": 1835, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04904632152588556, |
|
"grad_norm": 13.090154647827148, |
|
"learning_rate": 4.891304347826087e-06, |
|
"loss": 2.2711, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.09809264305177112, |
|
"grad_norm": 10.665365219116211, |
|
"learning_rate": 9.782608695652175e-06, |
|
"loss": 2.2911, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.14713896457765668, |
|
"grad_norm": 9.563919067382812, |
|
"learning_rate": 1.4673913043478263e-05, |
|
"loss": 2.059, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.19618528610354224, |
|
"grad_norm": 11.644034385681152, |
|
"learning_rate": 1.956521739130435e-05, |
|
"loss": 1.9083, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.2452316076294278, |
|
"grad_norm": 9.686708450317383, |
|
"learning_rate": 2.4456521739130436e-05, |
|
"loss": 1.7345, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.29427792915531337, |
|
"grad_norm": 8.462738037109375, |
|
"learning_rate": 2.9347826086956526e-05, |
|
"loss": 1.5031, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 0.34332425068119893, |
|
"grad_norm": 10.496886253356934, |
|
"learning_rate": 3.423913043478261e-05, |
|
"loss": 1.3148, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 0.3923705722070845, |
|
"grad_norm": 10.159104347229004, |
|
"learning_rate": 3.91304347826087e-05, |
|
"loss": 1.2048, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 0.44141689373297005, |
|
"grad_norm": 7.318648338317871, |
|
"learning_rate": 4.4021739130434786e-05, |
|
"loss": 1.2868, |
|
"step": 162 |
|
}, |
|
{ |
|
"epoch": 0.4904632152588556, |
|
"grad_norm": 11.507461547851562, |
|
"learning_rate": 4.891304347826087e-05, |
|
"loss": 1.2105, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.5395095367847411, |
|
"grad_norm": 5.680470943450928, |
|
"learning_rate": 4.957601453664446e-05, |
|
"loss": 1.0724, |
|
"step": 198 |
|
}, |
|
{ |
|
"epoch": 0.5885558583106267, |
|
"grad_norm": 8.683788299560547, |
|
"learning_rate": 4.9030890369473045e-05, |
|
"loss": 1.1899, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 0.6376021798365122, |
|
"grad_norm": 7.334160804748535, |
|
"learning_rate": 4.848576620230164e-05, |
|
"loss": 1.0224, |
|
"step": 234 |
|
}, |
|
{ |
|
"epoch": 0.6866485013623979, |
|
"grad_norm": 8.717308044433594, |
|
"learning_rate": 4.794064203513023e-05, |
|
"loss": 0.9976, |
|
"step": 252 |
|
}, |
|
{ |
|
"epoch": 0.7356948228882834, |
|
"grad_norm": 12.613802909851074, |
|
"learning_rate": 4.739551786795882e-05, |
|
"loss": 0.9753, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.784741144414169, |
|
"grad_norm": 7.462376594543457, |
|
"learning_rate": 4.6850393700787405e-05, |
|
"loss": 1.1063, |
|
"step": 288 |
|
}, |
|
{ |
|
"epoch": 0.8337874659400545, |
|
"grad_norm": 8.719904899597168, |
|
"learning_rate": 4.630526953361599e-05, |
|
"loss": 1.0311, |
|
"step": 306 |
|
}, |
|
{ |
|
"epoch": 0.8828337874659401, |
|
"grad_norm": 9.132880210876465, |
|
"learning_rate": 4.576014536644458e-05, |
|
"loss": 0.9735, |
|
"step": 324 |
|
}, |
|
{ |
|
"epoch": 0.9318801089918256, |
|
"grad_norm": 8.101548194885254, |
|
"learning_rate": 4.521502119927317e-05, |
|
"loss": 1.0608, |
|
"step": 342 |
|
}, |
|
{ |
|
"epoch": 0.9809264305177112, |
|
"grad_norm": 9.457178115844727, |
|
"learning_rate": 4.466989703210176e-05, |
|
"loss": 1.0543, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.7394270122783083, |
|
"eval_f1_macro": 0.6775647712813081, |
|
"eval_f1_micro": 0.7394270122783083, |
|
"eval_f1_weighted": 0.7229253713683983, |
|
"eval_loss": 0.7820252180099487, |
|
"eval_precision_macro": 0.6673572429051899, |
|
"eval_precision_micro": 0.7394270122783083, |
|
"eval_precision_weighted": 0.7129395935578096, |
|
"eval_recall_macro": 0.6932339656729901, |
|
"eval_recall_micro": 0.7394270122783083, |
|
"eval_recall_weighted": 0.7394270122783083, |
|
"eval_runtime": 501.3115, |
|
"eval_samples_per_second": 1.462, |
|
"eval_steps_per_second": 0.092, |
|
"step": 367 |
|
}, |
|
{ |
|
"epoch": 1.0299727520435966, |
|
"grad_norm": 6.45409631729126, |
|
"learning_rate": 4.4124772864930345e-05, |
|
"loss": 0.8511, |
|
"step": 378 |
|
}, |
|
{ |
|
"epoch": 1.0790190735694822, |
|
"grad_norm": 4.8151164054870605, |
|
"learning_rate": 4.357964869775893e-05, |
|
"loss": 0.7645, |
|
"step": 396 |
|
}, |
|
{ |
|
"epoch": 1.1280653950953679, |
|
"grad_norm": 6.06305456161499, |
|
"learning_rate": 4.3034524530587525e-05, |
|
"loss": 0.7095, |
|
"step": 414 |
|
}, |
|
{ |
|
"epoch": 1.1771117166212535, |
|
"grad_norm": 8.338302612304688, |
|
"learning_rate": 4.248940036341612e-05, |
|
"loss": 0.7537, |
|
"step": 432 |
|
}, |
|
{ |
|
"epoch": 1.226158038147139, |
|
"grad_norm": 8.91988754272461, |
|
"learning_rate": 4.1944276196244705e-05, |
|
"loss": 1.0268, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.2752043596730245, |
|
"grad_norm": 8.219625473022461, |
|
"learning_rate": 4.139915202907329e-05, |
|
"loss": 0.7882, |
|
"step": 468 |
|
}, |
|
{ |
|
"epoch": 1.32425068119891, |
|
"grad_norm": 6.649393081665039, |
|
"learning_rate": 4.085402786190188e-05, |
|
"loss": 0.9177, |
|
"step": 486 |
|
}, |
|
{ |
|
"epoch": 1.3732970027247957, |
|
"grad_norm": 10.92117977142334, |
|
"learning_rate": 4.030890369473047e-05, |
|
"loss": 0.8006, |
|
"step": 504 |
|
}, |
|
{ |
|
"epoch": 1.422343324250681, |
|
"grad_norm": 7.338125705718994, |
|
"learning_rate": 3.976377952755906e-05, |
|
"loss": 0.7833, |
|
"step": 522 |
|
}, |
|
{ |
|
"epoch": 1.4713896457765667, |
|
"grad_norm": 7.391980171203613, |
|
"learning_rate": 3.9218655360387645e-05, |
|
"loss": 0.794, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 1.5204359673024523, |
|
"grad_norm": 7.255425930023193, |
|
"learning_rate": 3.867353119321623e-05, |
|
"loss": 0.6818, |
|
"step": 558 |
|
}, |
|
{ |
|
"epoch": 1.569482288828338, |
|
"grad_norm": 9.407766342163086, |
|
"learning_rate": 3.812840702604482e-05, |
|
"loss": 0.7966, |
|
"step": 576 |
|
}, |
|
{ |
|
"epoch": 1.6185286103542236, |
|
"grad_norm": 8.508045196533203, |
|
"learning_rate": 3.758328285887341e-05, |
|
"loss": 0.7673, |
|
"step": 594 |
|
}, |
|
{ |
|
"epoch": 1.667574931880109, |
|
"grad_norm": 10.17292308807373, |
|
"learning_rate": 3.7038158691702005e-05, |
|
"loss": 0.8005, |
|
"step": 612 |
|
}, |
|
{ |
|
"epoch": 1.7166212534059946, |
|
"grad_norm": 7.042759895324707, |
|
"learning_rate": 3.649303452453059e-05, |
|
"loss": 0.7716, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 1.76566757493188, |
|
"grad_norm": 10.45976448059082, |
|
"learning_rate": 3.594791035735918e-05, |
|
"loss": 0.722, |
|
"step": 648 |
|
}, |
|
{ |
|
"epoch": 1.8147138964577656, |
|
"grad_norm": 10.023469924926758, |
|
"learning_rate": 3.5402786190187765e-05, |
|
"loss": 0.6968, |
|
"step": 666 |
|
}, |
|
{ |
|
"epoch": 1.8637602179836512, |
|
"grad_norm": 8.609762191772461, |
|
"learning_rate": 3.485766202301636e-05, |
|
"loss": 0.8295, |
|
"step": 684 |
|
}, |
|
{ |
|
"epoch": 1.9128065395095368, |
|
"grad_norm": 5.7018842697143555, |
|
"learning_rate": 3.4312537855844944e-05, |
|
"loss": 0.7729, |
|
"step": 702 |
|
}, |
|
{ |
|
"epoch": 1.9618528610354224, |
|
"grad_norm": 9.336709022521973, |
|
"learning_rate": 3.376741368867353e-05, |
|
"loss": 0.8679, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.7708049113233287, |
|
"eval_f1_macro": 0.744396838344231, |
|
"eval_f1_micro": 0.7708049113233287, |
|
"eval_f1_weighted": 0.769490062085142, |
|
"eval_loss": 0.7198029160499573, |
|
"eval_precision_macro": 0.7471497356802382, |
|
"eval_precision_micro": 0.7708049113233287, |
|
"eval_precision_weighted": 0.7700316353146535, |
|
"eval_recall_macro": 0.7438821138211381, |
|
"eval_recall_micro": 0.7708049113233287, |
|
"eval_recall_weighted": 0.7708049113233287, |
|
"eval_runtime": 526.4938, |
|
"eval_samples_per_second": 1.392, |
|
"eval_steps_per_second": 0.087, |
|
"step": 734 |
|
}, |
|
{ |
|
"epoch": 2.010899182561308, |
|
"grad_norm": 3.749079942703247, |
|
"learning_rate": 3.322228952150212e-05, |
|
"loss": 0.7638, |
|
"step": 738 |
|
}, |
|
{ |
|
"epoch": 2.0599455040871932, |
|
"grad_norm": 5.066211223602295, |
|
"learning_rate": 3.2677165354330704e-05, |
|
"loss": 0.7479, |
|
"step": 756 |
|
}, |
|
{ |
|
"epoch": 2.108991825613079, |
|
"grad_norm": 5.5539116859436035, |
|
"learning_rate": 3.21320411871593e-05, |
|
"loss": 0.6329, |
|
"step": 774 |
|
}, |
|
{ |
|
"epoch": 2.1580381471389645, |
|
"grad_norm": 7.377701282501221, |
|
"learning_rate": 3.158691701998789e-05, |
|
"loss": 0.5928, |
|
"step": 792 |
|
}, |
|
{ |
|
"epoch": 2.20708446866485, |
|
"grad_norm": 1.7499698400497437, |
|
"learning_rate": 3.104179285281648e-05, |
|
"loss": 0.5315, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 2.2561307901907357, |
|
"grad_norm": 12.155342102050781, |
|
"learning_rate": 3.0496668685645064e-05, |
|
"loss": 0.6642, |
|
"step": 828 |
|
}, |
|
{ |
|
"epoch": 2.3051771117166213, |
|
"grad_norm": 7.592235088348389, |
|
"learning_rate": 2.9951544518473658e-05, |
|
"loss": 0.5364, |
|
"step": 846 |
|
}, |
|
{ |
|
"epoch": 2.354223433242507, |
|
"grad_norm": 8.232931137084961, |
|
"learning_rate": 2.9406420351302244e-05, |
|
"loss": 0.5136, |
|
"step": 864 |
|
}, |
|
{ |
|
"epoch": 2.4032697547683926, |
|
"grad_norm": 7.107213497161865, |
|
"learning_rate": 2.886129618413083e-05, |
|
"loss": 0.5777, |
|
"step": 882 |
|
}, |
|
{ |
|
"epoch": 2.452316076294278, |
|
"grad_norm": 4.498622894287109, |
|
"learning_rate": 2.8316172016959417e-05, |
|
"loss": 0.6736, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 2.5013623978201633, |
|
"grad_norm": 13.404940605163574, |
|
"learning_rate": 2.7771047849788007e-05, |
|
"loss": 0.6628, |
|
"step": 918 |
|
}, |
|
{ |
|
"epoch": 2.550408719346049, |
|
"grad_norm": 10.440755844116211, |
|
"learning_rate": 2.72259236826166e-05, |
|
"loss": 0.5867, |
|
"step": 936 |
|
}, |
|
{ |
|
"epoch": 2.5994550408719346, |
|
"grad_norm": 5.166727066040039, |
|
"learning_rate": 2.6680799515445187e-05, |
|
"loss": 0.6759, |
|
"step": 954 |
|
}, |
|
{ |
|
"epoch": 2.64850136239782, |
|
"grad_norm": 6.91835355758667, |
|
"learning_rate": 2.6135675348273774e-05, |
|
"loss": 0.8065, |
|
"step": 972 |
|
}, |
|
{ |
|
"epoch": 2.697547683923706, |
|
"grad_norm": 5.450559139251709, |
|
"learning_rate": 2.5590551181102364e-05, |
|
"loss": 0.5886, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 2.7465940054495914, |
|
"grad_norm": 11.601627349853516, |
|
"learning_rate": 2.504542701393095e-05, |
|
"loss": 0.8291, |
|
"step": 1008 |
|
}, |
|
{ |
|
"epoch": 2.7956403269754766, |
|
"grad_norm": 6.433958530426025, |
|
"learning_rate": 2.450030284675954e-05, |
|
"loss": 0.6658, |
|
"step": 1026 |
|
}, |
|
{ |
|
"epoch": 2.844686648501362, |
|
"grad_norm": 8.672781944274902, |
|
"learning_rate": 2.395517867958813e-05, |
|
"loss": 0.577, |
|
"step": 1044 |
|
}, |
|
{ |
|
"epoch": 2.893732970027248, |
|
"grad_norm": 5.865307807922363, |
|
"learning_rate": 2.3410054512416717e-05, |
|
"loss": 0.6015, |
|
"step": 1062 |
|
}, |
|
{ |
|
"epoch": 2.9427792915531334, |
|
"grad_norm": 7.018499374389648, |
|
"learning_rate": 2.2864930345245307e-05, |
|
"loss": 0.5292, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 2.991825613079019, |
|
"grad_norm": 8.684929847717285, |
|
"learning_rate": 2.2319806178073897e-05, |
|
"loss": 0.6743, |
|
"step": 1098 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.7762619372442019, |
|
"eval_f1_macro": 0.7352337273015235, |
|
"eval_f1_micro": 0.7762619372442019, |
|
"eval_f1_weighted": 0.7700415467128165, |
|
"eval_loss": 0.7334316372871399, |
|
"eval_precision_macro": 0.7602211726711597, |
|
"eval_precision_micro": 0.7762619372442019, |
|
"eval_precision_weighted": 0.7759104610468709, |
|
"eval_recall_macro": 0.7309406052393856, |
|
"eval_recall_micro": 0.7762619372442019, |
|
"eval_recall_weighted": 0.7762619372442019, |
|
"eval_runtime": 468.0039, |
|
"eval_samples_per_second": 1.566, |
|
"eval_steps_per_second": 0.098, |
|
"step": 1101 |
|
}, |
|
{ |
|
"epoch": 3.0408719346049047, |
|
"grad_norm": 5.529566287994385, |
|
"learning_rate": 2.1774682010902484e-05, |
|
"loss": 0.5119, |
|
"step": 1116 |
|
}, |
|
{ |
|
"epoch": 3.0899182561307903, |
|
"grad_norm": 8.672910690307617, |
|
"learning_rate": 2.1229557843731074e-05, |
|
"loss": 0.3846, |
|
"step": 1134 |
|
}, |
|
{ |
|
"epoch": 3.138964577656676, |
|
"grad_norm": 6.369070529937744, |
|
"learning_rate": 2.068443367655966e-05, |
|
"loss": 0.4705, |
|
"step": 1152 |
|
}, |
|
{ |
|
"epoch": 3.1880108991825615, |
|
"grad_norm": 6.632961273193359, |
|
"learning_rate": 2.013930950938825e-05, |
|
"loss": 0.5078, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 3.2370572207084467, |
|
"grad_norm": 13.185933113098145, |
|
"learning_rate": 1.959418534221684e-05, |
|
"loss": 0.4132, |
|
"step": 1188 |
|
}, |
|
{ |
|
"epoch": 3.2861035422343323, |
|
"grad_norm": 2.94797682762146, |
|
"learning_rate": 1.9049061175045427e-05, |
|
"loss": 0.5002, |
|
"step": 1206 |
|
}, |
|
{ |
|
"epoch": 3.335149863760218, |
|
"grad_norm": 8.657658576965332, |
|
"learning_rate": 1.8503937007874017e-05, |
|
"loss": 0.7647, |
|
"step": 1224 |
|
}, |
|
{ |
|
"epoch": 3.3841961852861036, |
|
"grad_norm": 7.174124717712402, |
|
"learning_rate": 1.7958812840702604e-05, |
|
"loss": 0.5301, |
|
"step": 1242 |
|
}, |
|
{ |
|
"epoch": 3.433242506811989, |
|
"grad_norm": 8.120543479919434, |
|
"learning_rate": 1.7413688673531194e-05, |
|
"loss": 0.4428, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 3.482288828337875, |
|
"grad_norm": 10.651689529418945, |
|
"learning_rate": 1.6868564506359784e-05, |
|
"loss": 0.6033, |
|
"step": 1278 |
|
}, |
|
{ |
|
"epoch": 3.53133514986376, |
|
"grad_norm": 14.153423309326172, |
|
"learning_rate": 1.6323440339188374e-05, |
|
"loss": 0.5152, |
|
"step": 1296 |
|
}, |
|
{ |
|
"epoch": 3.5803814713896456, |
|
"grad_norm": 8.533557891845703, |
|
"learning_rate": 1.577831617201696e-05, |
|
"loss": 0.6689, |
|
"step": 1314 |
|
}, |
|
{ |
|
"epoch": 3.629427792915531, |
|
"grad_norm": 12.795997619628906, |
|
"learning_rate": 1.5233192004845548e-05, |
|
"loss": 0.4701, |
|
"step": 1332 |
|
}, |
|
{ |
|
"epoch": 3.678474114441417, |
|
"grad_norm": 8.181031227111816, |
|
"learning_rate": 1.4688067837674138e-05, |
|
"loss": 0.4875, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 3.7275204359673024, |
|
"grad_norm": 8.397069931030273, |
|
"learning_rate": 1.4142943670502725e-05, |
|
"loss": 0.4234, |
|
"step": 1368 |
|
}, |
|
{ |
|
"epoch": 3.776566757493188, |
|
"grad_norm": 6.6668548583984375, |
|
"learning_rate": 1.3597819503331317e-05, |
|
"loss": 0.4799, |
|
"step": 1386 |
|
}, |
|
{ |
|
"epoch": 3.8256130790190737, |
|
"grad_norm": 3.7310755252838135, |
|
"learning_rate": 1.3052695336159903e-05, |
|
"loss": 0.4241, |
|
"step": 1404 |
|
}, |
|
{ |
|
"epoch": 3.8746594005449593, |
|
"grad_norm": 7.294261455535889, |
|
"learning_rate": 1.2507571168988492e-05, |
|
"loss": 0.4828, |
|
"step": 1422 |
|
}, |
|
{ |
|
"epoch": 3.923705722070845, |
|
"grad_norm": 11.431266784667969, |
|
"learning_rate": 1.1962447001817082e-05, |
|
"loss": 0.4837, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 3.9727520435967305, |
|
"grad_norm": 10.630217552185059, |
|
"learning_rate": 1.141732283464567e-05, |
|
"loss": 0.4148, |
|
"step": 1458 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.7926330150068213, |
|
"eval_f1_macro": 0.7482822112088491, |
|
"eval_f1_micro": 0.7926330150068213, |
|
"eval_f1_weighted": 0.7859610744604464, |
|
"eval_loss": 0.680126428604126, |
|
"eval_precision_macro": 0.7591045700614258, |
|
"eval_precision_micro": 0.7926330150068213, |
|
"eval_precision_weighted": 0.7865124628151742, |
|
"eval_recall_macro": 0.7507125112917796, |
|
"eval_recall_micro": 0.7926330150068213, |
|
"eval_recall_weighted": 0.7926330150068213, |
|
"eval_runtime": 446.0494, |
|
"eval_samples_per_second": 1.643, |
|
"eval_steps_per_second": 0.103, |
|
"step": 1468 |
|
}, |
|
{ |
|
"epoch": 4.021798365122616, |
|
"grad_norm": 8.096855163574219, |
|
"learning_rate": 1.0872198667474258e-05, |
|
"loss": 0.4162, |
|
"step": 1476 |
|
}, |
|
{ |
|
"epoch": 4.070844686648502, |
|
"grad_norm": 4.436280250549316, |
|
"learning_rate": 1.0327074500302846e-05, |
|
"loss": 0.3999, |
|
"step": 1494 |
|
}, |
|
{ |
|
"epoch": 4.1198910081743865, |
|
"grad_norm": 3.2468502521514893, |
|
"learning_rate": 9.781950333131436e-06, |
|
"loss": 0.269, |
|
"step": 1512 |
|
}, |
|
{ |
|
"epoch": 4.168937329700272, |
|
"grad_norm": 5.88806676864624, |
|
"learning_rate": 9.236826165960025e-06, |
|
"loss": 0.3749, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 4.217983651226158, |
|
"grad_norm": 1.9926618337631226, |
|
"learning_rate": 8.691701998788613e-06, |
|
"loss": 0.3893, |
|
"step": 1548 |
|
}, |
|
{ |
|
"epoch": 4.267029972752043, |
|
"grad_norm": 7.686309814453125, |
|
"learning_rate": 8.146577831617203e-06, |
|
"loss": 0.3134, |
|
"step": 1566 |
|
}, |
|
{ |
|
"epoch": 4.316076294277929, |
|
"grad_norm": 3.9294235706329346, |
|
"learning_rate": 7.6014536644457905e-06, |
|
"loss": 0.3415, |
|
"step": 1584 |
|
}, |
|
{ |
|
"epoch": 4.3651226158038146, |
|
"grad_norm": 4.247501850128174, |
|
"learning_rate": 7.056329497274379e-06, |
|
"loss": 0.4167, |
|
"step": 1602 |
|
}, |
|
{ |
|
"epoch": 4.4141689373297, |
|
"grad_norm": 8.502470970153809, |
|
"learning_rate": 6.511205330102968e-06, |
|
"loss": 0.5261, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 4.463215258855586, |
|
"grad_norm": 5.880737781524658, |
|
"learning_rate": 5.966081162931557e-06, |
|
"loss": 0.5806, |
|
"step": 1638 |
|
}, |
|
{ |
|
"epoch": 4.512261580381471, |
|
"grad_norm": 10.550583839416504, |
|
"learning_rate": 5.420956995760146e-06, |
|
"loss": 0.3798, |
|
"step": 1656 |
|
}, |
|
{ |
|
"epoch": 4.561307901907357, |
|
"grad_norm": 6.919607639312744, |
|
"learning_rate": 4.875832828588734e-06, |
|
"loss": 0.4235, |
|
"step": 1674 |
|
}, |
|
{ |
|
"epoch": 4.610354223433243, |
|
"grad_norm": 11.466157913208008, |
|
"learning_rate": 4.330708661417323e-06, |
|
"loss": 0.4009, |
|
"step": 1692 |
|
}, |
|
{ |
|
"epoch": 4.659400544959128, |
|
"grad_norm": 7.428606033325195, |
|
"learning_rate": 3.785584494245912e-06, |
|
"loss": 0.3749, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 4.708446866485014, |
|
"grad_norm": 14.596545219421387, |
|
"learning_rate": 3.2404603270745003e-06, |
|
"loss": 0.3822, |
|
"step": 1728 |
|
}, |
|
{ |
|
"epoch": 4.7574931880108995, |
|
"grad_norm": 1.3340034484863281, |
|
"learning_rate": 2.695336159903089e-06, |
|
"loss": 0.402, |
|
"step": 1746 |
|
}, |
|
{ |
|
"epoch": 4.806539509536785, |
|
"grad_norm": 12.544507026672363, |
|
"learning_rate": 2.150211992731678e-06, |
|
"loss": 0.3577, |
|
"step": 1764 |
|
}, |
|
{ |
|
"epoch": 4.855585831062671, |
|
"grad_norm": 7.779797077178955, |
|
"learning_rate": 1.6050878255602666e-06, |
|
"loss": 0.5092, |
|
"step": 1782 |
|
}, |
|
{ |
|
"epoch": 4.904632152588556, |
|
"grad_norm": 4.97097110748291, |
|
"learning_rate": 1.0599636583888554e-06, |
|
"loss": 0.3382, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 4.953678474114441, |
|
"grad_norm": 2.9842166900634766, |
|
"learning_rate": 5.14839491217444e-07, |
|
"loss": 0.2765, |
|
"step": 1818 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.7953615279672579, |
|
"eval_f1_macro": 0.7441167259748385, |
|
"eval_f1_micro": 0.7953615279672579, |
|
"eval_f1_weighted": 0.7877909517913628, |
|
"eval_loss": 0.6790379881858826, |
|
"eval_precision_macro": 0.7576756562000598, |
|
"eval_precision_micro": 0.7953615279672579, |
|
"eval_precision_weighted": 0.7895482398510546, |
|
"eval_recall_macro": 0.7464961607949413, |
|
"eval_recall_micro": 0.7953615279672579, |
|
"eval_recall_weighted": 0.7953615279672579, |
|
"eval_runtime": 505.8176, |
|
"eval_samples_per_second": 1.449, |
|
"eval_steps_per_second": 0.091, |
|
"step": 1835 |
|
} |
|
], |
|
"logging_steps": 18, |
|
"max_steps": 1835, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 5, |
|
"early_stopping_threshold": 0.01 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.1887708574999347e+19, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|