| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9994447529150472, | |
| "eval_steps": 100, | |
| "global_step": 450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01110494169905608, | |
| "grad_norm": 5.397180080413818, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 1.3609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02220988339811216, | |
| "grad_norm": 3.014500141143799, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 1.366, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03331482509716824, | |
| "grad_norm": 2.8811240196228027, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.2626, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04441976679622432, | |
| "grad_norm": 2.0619661808013916, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 1.1859, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0555247084952804, | |
| "grad_norm": 1.5281075239181519, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 1.1469, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06662965019433648, | |
| "grad_norm": 1.2808576822280884, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.1063, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07773459189339256, | |
| "grad_norm": 1.2353777885437012, | |
| "learning_rate": 1.555555555555556e-05, | |
| "loss": 1.0649, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08883953359244864, | |
| "grad_norm": 1.280089020729065, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 1.0574, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09994447529150471, | |
| "grad_norm": 1.1332577466964722, | |
| "learning_rate": 2e-05, | |
| "loss": 1.059, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1110494169905608, | |
| "grad_norm": 1.115410566329956, | |
| "learning_rate": 1.9992479525042305e-05, | |
| "loss": 1.0259, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12215435868961688, | |
| "grad_norm": 1.1548365354537964, | |
| "learning_rate": 1.996992941167792e-05, | |
| "loss": 1.0407, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.13325930038867295, | |
| "grad_norm": 1.1644798517227173, | |
| "learning_rate": 1.9932383577419432e-05, | |
| "loss": 1.0219, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14436424208772905, | |
| "grad_norm": 1.0820422172546387, | |
| "learning_rate": 1.9879898494768093e-05, | |
| "loss": 1.0128, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.15546918378678512, | |
| "grad_norm": 1.086032748222351, | |
| "learning_rate": 1.9812553106273848e-05, | |
| "loss": 1.0004, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1665741254858412, | |
| "grad_norm": 1.0374068021774292, | |
| "learning_rate": 1.973044870579824e-05, | |
| "loss": 1.0018, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1776790671848973, | |
| "grad_norm": 1.0140597820281982, | |
| "learning_rate": 1.9633708786158803e-05, | |
| "loss": 0.9955, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18878400888395336, | |
| "grad_norm": 1.124200701713562, | |
| "learning_rate": 1.9522478853384154e-05, | |
| "loss": 0.9913, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.19988895058300943, | |
| "grad_norm": 1.048175573348999, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.9913, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.21099389228206553, | |
| "grad_norm": 1.1582220792770386, | |
| "learning_rate": 1.9257239692688907e-05, | |
| "loss": 1.0055, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2220988339811216, | |
| "grad_norm": 0.9994953870773315, | |
| "learning_rate": 1.9103629409661468e-05, | |
| "loss": 0.9986, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2220988339811216, | |
| "eval_loss": 1.0169899463653564, | |
| "eval_runtime": 32.3732, | |
| "eval_samples_per_second": 7.908, | |
| "eval_steps_per_second": 0.988, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23320377568017767, | |
| "grad_norm": 1.1112126111984253, | |
| "learning_rate": 1.8936326403234125e-05, | |
| "loss": 0.9954, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.24430871737923376, | |
| "grad_norm": 1.0678929090499878, | |
| "learning_rate": 1.8755582313020912e-05, | |
| "loss": 0.9847, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.25541365907828983, | |
| "grad_norm": 1.041691780090332, | |
| "learning_rate": 1.8561668995302668e-05, | |
| "loss": 0.9853, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2665186007773459, | |
| "grad_norm": 1.0803673267364502, | |
| "learning_rate": 1.8354878114129368e-05, | |
| "loss": 0.9597, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.277623542476402, | |
| "grad_norm": 1.0018560886383057, | |
| "learning_rate": 1.8135520702629677e-05, | |
| "loss": 0.9833, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2887284841754581, | |
| "grad_norm": 1.1001731157302856, | |
| "learning_rate": 1.7903926695187595e-05, | |
| "loss": 0.9699, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.29983342587451417, | |
| "grad_norm": 1.0463827848434448, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.9712, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.31093836757357024, | |
| "grad_norm": 1.3691056966781616, | |
| "learning_rate": 1.740544013109005e-05, | |
| "loss": 0.987, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3220433092726263, | |
| "grad_norm": 1.0720419883728027, | |
| "learning_rate": 1.7139297345578992e-05, | |
| "loss": 0.9626, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3331482509716824, | |
| "grad_norm": 1.0211371183395386, | |
| "learning_rate": 1.686241637868734e-05, | |
| "loss": 0.9522, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3442531926707385, | |
| "grad_norm": 1.0119701623916626, | |
| "learning_rate": 1.657521368569064e-05, | |
| "loss": 0.977, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.3553581343697946, | |
| "grad_norm": 1.0520477294921875, | |
| "learning_rate": 1.627812124672099e-05, | |
| "loss": 0.9769, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.36646307606885065, | |
| "grad_norm": 1.1625330448150635, | |
| "learning_rate": 1.5971585917027864e-05, | |
| "loss": 0.9802, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.3775680177679067, | |
| "grad_norm": 1.0677601099014282, | |
| "learning_rate": 1.5656068754865388e-05, | |
| "loss": 0.96, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3886729594669628, | |
| "grad_norm": 1.1049383878707886, | |
| "learning_rate": 1.5332044328016916e-05, | |
| "loss": 0.9643, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.39977790116601886, | |
| "grad_norm": 1.062893271446228, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.9386, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.410882842865075, | |
| "grad_norm": 1.0128767490386963, | |
| "learning_rate": 1.4660435197025391e-05, | |
| "loss": 0.9559, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.42198778456413105, | |
| "grad_norm": 1.0378108024597168, | |
| "learning_rate": 1.4313860656812537e-05, | |
| "loss": 0.9347, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4330927262631871, | |
| "grad_norm": 1.0094784498214722, | |
| "learning_rate": 1.396079766039157e-05, | |
| "loss": 0.9623, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.4441976679622432, | |
| "grad_norm": 0.9790409803390503, | |
| "learning_rate": 1.3601777248047105e-05, | |
| "loss": 0.9678, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4441976679622432, | |
| "eval_loss": 0.9827648997306824, | |
| "eval_runtime": 32.188, | |
| "eval_samples_per_second": 7.953, | |
| "eval_steps_per_second": 0.994, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45530260966129926, | |
| "grad_norm": 0.9436436891555786, | |
| "learning_rate": 1.3237339420583213e-05, | |
| "loss": 0.96, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.46640755136035533, | |
| "grad_norm": 0.9316679239273071, | |
| "learning_rate": 1.2868032327110904e-05, | |
| "loss": 0.9326, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.47751249305941146, | |
| "grad_norm": 0.9514685273170471, | |
| "learning_rate": 1.2494411440579814e-05, | |
| "loss": 0.9661, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.48861743475846753, | |
| "grad_norm": 1.0059814453125, | |
| "learning_rate": 1.211703872229411e-05, | |
| "loss": 0.915, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4997223764575236, | |
| "grad_norm": 0.9615886211395264, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.9478, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5108273181565797, | |
| "grad_norm": 0.9393269419670105, | |
| "learning_rate": 1.1353312997501313e-05, | |
| "loss": 0.93, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5219322598556357, | |
| "grad_norm": 0.9677947759628296, | |
| "learning_rate": 1.0968108707031792e-05, | |
| "loss": 0.9507, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.5330372015546918, | |
| "grad_norm": 0.9616990685462952, | |
| "learning_rate": 1.0581448289104759e-05, | |
| "loss": 0.9205, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5441421432537479, | |
| "grad_norm": 0.9439184665679932, | |
| "learning_rate": 1.0193913317718245e-05, | |
| "loss": 0.9673, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.555247084952804, | |
| "grad_norm": 1.0039938688278198, | |
| "learning_rate": 9.806086682281759e-06, | |
| "loss": 0.9373, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5663520266518601, | |
| "grad_norm": 0.966042697429657, | |
| "learning_rate": 9.418551710895243e-06, | |
| "loss": 0.9518, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.5774569683509162, | |
| "grad_norm": 0.9549779891967773, | |
| "learning_rate": 9.03189129296821e-06, | |
| "loss": 0.9537, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5885619100499723, | |
| "grad_norm": 0.9227808713912964, | |
| "learning_rate": 8.646687002498692e-06, | |
| "loss": 0.9477, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.5996668517490283, | |
| "grad_norm": 0.9466913938522339, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.9306, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6107717934480844, | |
| "grad_norm": 0.8789124488830566, | |
| "learning_rate": 7.882961277705897e-06, | |
| "loss": 0.9392, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6218767351471405, | |
| "grad_norm": 0.9538043737411499, | |
| "learning_rate": 7.505588559420188e-06, | |
| "loss": 0.9541, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6329816768461966, | |
| "grad_norm": 0.9842989444732666, | |
| "learning_rate": 7.131967672889101e-06, | |
| "loss": 0.9555, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.6440866185452526, | |
| "grad_norm": 0.951591432094574, | |
| "learning_rate": 6.762660579416791e-06, | |
| "loss": 0.947, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6551915602443087, | |
| "grad_norm": 0.9323354363441467, | |
| "learning_rate": 6.3982227519528986e-06, | |
| "loss": 0.9434, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.6662965019433648, | |
| "grad_norm": 0.8553444147109985, | |
| "learning_rate": 6.039202339608432e-06, | |
| "loss": 0.9332, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6662965019433648, | |
| "eval_loss": 0.964606523513794, | |
| "eval_runtime": 32.3264, | |
| "eval_samples_per_second": 7.919, | |
| "eval_steps_per_second": 0.99, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6774014436424208, | |
| "grad_norm": 0.9099004864692688, | |
| "learning_rate": 5.686139343187468e-06, | |
| "loss": 0.9368, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.688506385341477, | |
| "grad_norm": 0.8473957777023315, | |
| "learning_rate": 5.339564802974615e-06, | |
| "loss": 0.9326, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6996113270405331, | |
| "grad_norm": 0.8807346224784851, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.9316, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.7107162687395892, | |
| "grad_norm": 0.9112072587013245, | |
| "learning_rate": 4.66795567198309e-06, | |
| "loss": 0.9502, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7218212104386452, | |
| "grad_norm": 0.892538845539093, | |
| "learning_rate": 4.343931245134616e-06, | |
| "loss": 0.9412, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7329261521377013, | |
| "grad_norm": 0.8999789357185364, | |
| "learning_rate": 4.028414082972141e-06, | |
| "loss": 0.9345, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7440310938367574, | |
| "grad_norm": 0.878555178642273, | |
| "learning_rate": 3.7218787532790167e-06, | |
| "loss": 0.9271, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.7551360355358134, | |
| "grad_norm": 0.8958238363265991, | |
| "learning_rate": 3.424786314309365e-06, | |
| "loss": 0.9289, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7662409772348695, | |
| "grad_norm": 0.8239888548851013, | |
| "learning_rate": 3.1375836213126653e-06, | |
| "loss": 0.9422, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.7773459189339256, | |
| "grad_norm": 0.9257540702819824, | |
| "learning_rate": 2.8607026544210115e-06, | |
| "loss": 0.9281, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7884508606329816, | |
| "grad_norm": 0.883544921875, | |
| "learning_rate": 2.594559868909956e-06, | |
| "loss": 0.9136, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.7995558023320377, | |
| "grad_norm": 6.725770950317383, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.938, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8106607440310938, | |
| "grad_norm": 0.8539109230041504, | |
| "learning_rate": 2.0960733048124082e-06, | |
| "loss": 0.9311, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.82176568573015, | |
| "grad_norm": 0.9241852760314941, | |
| "learning_rate": 1.8644792973703252e-06, | |
| "loss": 0.9349, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.832870627429206, | |
| "grad_norm": 0.8888701796531677, | |
| "learning_rate": 1.6451218858706374e-06, | |
| "loss": 0.9426, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8439755691282621, | |
| "grad_norm": 0.8378512263298035, | |
| "learning_rate": 1.4383310046973365e-06, | |
| "loss": 0.9213, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8550805108273182, | |
| "grad_norm": 0.8606922626495361, | |
| "learning_rate": 1.2444176869790925e-06, | |
| "loss": 0.927, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.8661854525263742, | |
| "grad_norm": 0.7981701493263245, | |
| "learning_rate": 1.0636735967658785e-06, | |
| "loss": 0.9145, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8772903942254303, | |
| "grad_norm": 0.8214133977890015, | |
| "learning_rate": 8.963705903385344e-07, | |
| "loss": 0.9398, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.8883953359244864, | |
| "grad_norm": 0.8718788623809814, | |
| "learning_rate": 7.427603073110967e-07, | |
| "loss": 0.9027, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8883953359244864, | |
| "eval_loss": 0.9576538801193237, | |
| "eval_runtime": 31.9874, | |
| "eval_samples_per_second": 8.003, | |
| "eval_steps_per_second": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8995002776235425, | |
| "grad_norm": 0.8060287237167358, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.9305, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.9106052193225985, | |
| "grad_norm": 0.8300138711929321, | |
| "learning_rate": 4.775211466158469e-07, | |
| "loss": 0.9381, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9217101610216546, | |
| "grad_norm": 0.8601639270782471, | |
| "learning_rate": 3.662912138411967e-07, | |
| "loss": 0.9231, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.9328151027207107, | |
| "grad_norm": 0.8134458065032959, | |
| "learning_rate": 2.6955129420176193e-07, | |
| "loss": 0.9115, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9439200444197668, | |
| "grad_norm": 0.7816701531410217, | |
| "learning_rate": 1.874468937261531e-07, | |
| "loss": 0.9183, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9550249861188229, | |
| "grad_norm": 0.8716827034950256, | |
| "learning_rate": 1.201015052319099e-07, | |
| "loss": 0.9503, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.966129927817879, | |
| "grad_norm": 0.8040913939476013, | |
| "learning_rate": 6.761642258056977e-08, | |
| "loss": 0.9306, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.9772348695169351, | |
| "grad_norm": 0.7763182520866394, | |
| "learning_rate": 3.0070588322079765e-08, | |
| "loss": 0.9244, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9883398112159911, | |
| "grad_norm": 0.825076162815094, | |
| "learning_rate": 7.520474957699586e-09, | |
| "loss": 0.9321, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.9994447529150472, | |
| "grad_norm": 0.8443522453308105, | |
| "learning_rate": 0.0, | |
| "loss": 0.9389, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9994447529150472, | |
| "step": 450, | |
| "total_flos": 1.8998720188121088e+17, | |
| "train_loss": 0.9762679852379693, | |
| "train_runtime": 18617.8565, | |
| "train_samples_per_second": 2.321, | |
| "train_steps_per_second": 0.024 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8998720188121088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |