| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 20.0, |
| "eval_steps": 500, |
| "global_step": 1420, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07042253521126761, |
| "grad_norm": 298.37652587890625, |
| "learning_rate": 0.00019943661971830986, |
| "loss": 32.3915, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.14084507042253522, |
| "grad_norm": 93.51129150390625, |
| "learning_rate": 0.0001987323943661972, |
| "loss": 28.743, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2112676056338028, |
| "grad_norm": 47.780601501464844, |
| "learning_rate": 0.00019802816901408452, |
| "loss": 25.2619, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.28169014084507044, |
| "grad_norm": 50.333736419677734, |
| "learning_rate": 0.00019732394366197184, |
| "loss": 22.2152, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.352112676056338, |
| "grad_norm": 16.70964241027832, |
| "learning_rate": 0.00019661971830985917, |
| "loss": 18.6695, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.4225352112676056, |
| "grad_norm": 15.14587688446045, |
| "learning_rate": 0.0001959154929577465, |
| "loss": 14.7068, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.49295774647887325, |
| "grad_norm": 9.351914405822754, |
| "learning_rate": 0.00019521126760563382, |
| "loss": 8.1565, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.5633802816901409, |
| "grad_norm": 8.563234329223633, |
| "learning_rate": 0.00019450704225352114, |
| "loss": 5.4416, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6338028169014085, |
| "grad_norm": 6.7714691162109375, |
| "learning_rate": 0.00019380281690140847, |
| "loss": 5.0701, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.704225352112676, |
| "grad_norm": 4.738491535186768, |
| "learning_rate": 0.0001930985915492958, |
| "loss": 4.6657, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7746478873239436, |
| "grad_norm": 5.511097431182861, |
| "learning_rate": 0.00019239436619718312, |
| "loss": 4.2706, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.8450704225352113, |
| "grad_norm": 5.683650970458984, |
| "learning_rate": 0.00019169014084507045, |
| "loss": 3.8374, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9154929577464789, |
| "grad_norm": 4.763166427612305, |
| "learning_rate": 0.00019098591549295774, |
| "loss": 3.3471, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.9859154929577465, |
| "grad_norm": 2.353513240814209, |
| "learning_rate": 0.00019028169014084507, |
| "loss": 2.9019, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.327265977859497, |
| "eval_runtime": 1.3559, |
| "eval_samples_per_second": 279.528, |
| "eval_steps_per_second": 2.213, |
| "step": 71 |
| }, |
| { |
| "epoch": 1.056338028169014, |
| "grad_norm": 2.5209953784942627, |
| "learning_rate": 0.0001895774647887324, |
| "loss": 2.5521, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.1267605633802817, |
| "grad_norm": 0.8227373957633972, |
| "learning_rate": 0.00018887323943661972, |
| "loss": 2.3236, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.1971830985915493, |
| "grad_norm": 0.8206098675727844, |
| "learning_rate": 0.00018816901408450705, |
| "loss": 2.1289, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.267605633802817, |
| "grad_norm": 0.748960018157959, |
| "learning_rate": 0.00018746478873239437, |
| "loss": 1.6767, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.3380281690140845, |
| "grad_norm": 0.4808853566646576, |
| "learning_rate": 0.0001867605633802817, |
| "loss": 1.419, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.408450704225352, |
| "grad_norm": 1.964240312576294, |
| "learning_rate": 0.00018605633802816902, |
| "loss": 1.3036, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.4788732394366197, |
| "grad_norm": 0.2643977403640747, |
| "learning_rate": 0.00018535211267605635, |
| "loss": 1.2568, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.5492957746478875, |
| "grad_norm": 0.38880959153175354, |
| "learning_rate": 0.00018464788732394367, |
| "loss": 1.2002, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.619718309859155, |
| "grad_norm": 0.22605347633361816, |
| "learning_rate": 0.000183943661971831, |
| "loss": 1.1694, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.6901408450704225, |
| "grad_norm": 0.23560728132724762, |
| "learning_rate": 0.00018323943661971832, |
| "loss": 1.1492, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.76056338028169, |
| "grad_norm": 0.15073446929454803, |
| "learning_rate": 0.00018253521126760565, |
| "loss": 1.1263, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.8309859154929577, |
| "grad_norm": 0.12264095991849899, |
| "learning_rate": 0.00018183098591549298, |
| "loss": 1.1051, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.9014084507042255, |
| "grad_norm": 0.1781918853521347, |
| "learning_rate": 0.0001811267605633803, |
| "loss": 1.0964, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.971830985915493, |
| "grad_norm": 0.15171071887016296, |
| "learning_rate": 0.00018042253521126763, |
| "loss": 1.0779, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.0098963975906372, |
| "eval_runtime": 1.3563, |
| "eval_samples_per_second": 279.438, |
| "eval_steps_per_second": 2.212, |
| "step": 142 |
| }, |
| { |
| "epoch": 2.0422535211267605, |
| "grad_norm": 0.11982790380716324, |
| "learning_rate": 0.00017971830985915495, |
| "loss": 1.0746, |
| "step": 145 |
| }, |
| { |
| "epoch": 2.112676056338028, |
| "grad_norm": 0.11876315623521805, |
| "learning_rate": 0.00017901408450704228, |
| "loss": 1.0658, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.183098591549296, |
| "grad_norm": 0.09626977145671844, |
| "learning_rate": 0.0001783098591549296, |
| "loss": 1.0535, |
| "step": 155 |
| }, |
| { |
| "epoch": 2.2535211267605635, |
| "grad_norm": 0.11824846267700195, |
| "learning_rate": 0.00017760563380281693, |
| "loss": 1.0492, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.323943661971831, |
| "grad_norm": 0.1524844616651535, |
| "learning_rate": 0.00017690140845070425, |
| "loss": 1.04, |
| "step": 165 |
| }, |
| { |
| "epoch": 2.3943661971830985, |
| "grad_norm": 0.10610729455947876, |
| "learning_rate": 0.00017619718309859158, |
| "loss": 1.0355, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.464788732394366, |
| "grad_norm": 0.09342360496520996, |
| "learning_rate": 0.0001754929577464789, |
| "loss": 1.0333, |
| "step": 175 |
| }, |
| { |
| "epoch": 2.535211267605634, |
| "grad_norm": 0.10479816794395447, |
| "learning_rate": 0.0001747887323943662, |
| "loss": 1.0318, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.6056338028169015, |
| "grad_norm": 0.0711260586977005, |
| "learning_rate": 0.00017408450704225353, |
| "loss": 1.0241, |
| "step": 185 |
| }, |
| { |
| "epoch": 2.676056338028169, |
| "grad_norm": 0.11890017986297607, |
| "learning_rate": 0.00017338028169014086, |
| "loss": 1.0241, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.7464788732394365, |
| "grad_norm": 0.10851440578699112, |
| "learning_rate": 0.00017267605633802818, |
| "loss": 1.018, |
| "step": 195 |
| }, |
| { |
| "epoch": 2.816901408450704, |
| "grad_norm": 0.1457432061433792, |
| "learning_rate": 0.0001719718309859155, |
| "loss": 1.0149, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.887323943661972, |
| "grad_norm": 0.0658695176243782, |
| "learning_rate": 0.00017126760563380283, |
| "loss": 1.0093, |
| "step": 205 |
| }, |
| { |
| "epoch": 2.9577464788732395, |
| "grad_norm": 0.09453574568033218, |
| "learning_rate": 0.00017056338028169016, |
| "loss": 1.0081, |
| "step": 210 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.9575695395469666, |
| "eval_runtime": 1.3565, |
| "eval_samples_per_second": 279.401, |
| "eval_steps_per_second": 2.212, |
| "step": 213 |
| }, |
| { |
| "epoch": 3.028169014084507, |
| "grad_norm": 0.13185155391693115, |
| "learning_rate": 0.00016985915492957746, |
| "loss": 1.0059, |
| "step": 215 |
| }, |
| { |
| "epoch": 3.0985915492957745, |
| "grad_norm": 0.10181483626365662, |
| "learning_rate": 0.00016915492957746478, |
| "loss": 0.9993, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.169014084507042, |
| "grad_norm": 0.07031014561653137, |
| "learning_rate": 0.0001684507042253521, |
| "loss": 1.0002, |
| "step": 225 |
| }, |
| { |
| "epoch": 3.23943661971831, |
| "grad_norm": 0.08129975944757462, |
| "learning_rate": 0.00016774647887323943, |
| "loss": 0.9966, |
| "step": 230 |
| }, |
| { |
| "epoch": 3.3098591549295775, |
| "grad_norm": 0.061685919761657715, |
| "learning_rate": 0.00016704225352112676, |
| "loss": 0.9986, |
| "step": 235 |
| }, |
| { |
| "epoch": 3.380281690140845, |
| "grad_norm": 0.10376816242933273, |
| "learning_rate": 0.00016633802816901408, |
| "loss": 0.9914, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.4507042253521125, |
| "grad_norm": 0.16595374047756195, |
| "learning_rate": 0.0001656338028169014, |
| "loss": 0.9944, |
| "step": 245 |
| }, |
| { |
| "epoch": 3.52112676056338, |
| "grad_norm": 0.0959262102842331, |
| "learning_rate": 0.00016492957746478873, |
| "loss": 0.99, |
| "step": 250 |
| }, |
| { |
| "epoch": 3.591549295774648, |
| "grad_norm": 0.04954326152801514, |
| "learning_rate": 0.00016422535211267606, |
| "loss": 0.9887, |
| "step": 255 |
| }, |
| { |
| "epoch": 3.6619718309859155, |
| "grad_norm": 0.09042917937040329, |
| "learning_rate": 0.00016352112676056339, |
| "loss": 0.989, |
| "step": 260 |
| }, |
| { |
| "epoch": 3.732394366197183, |
| "grad_norm": 0.1556464284658432, |
| "learning_rate": 0.0001628169014084507, |
| "loss": 0.9914, |
| "step": 265 |
| }, |
| { |
| "epoch": 3.802816901408451, |
| "grad_norm": 0.0660383403301239, |
| "learning_rate": 0.00016211267605633804, |
| "loss": 0.9874, |
| "step": 270 |
| }, |
| { |
| "epoch": 3.873239436619718, |
| "grad_norm": 0.08755503594875336, |
| "learning_rate": 0.00016140845070422536, |
| "loss": 0.9823, |
| "step": 275 |
| }, |
| { |
| "epoch": 3.943661971830986, |
| "grad_norm": 0.07488470524549484, |
| "learning_rate": 0.0001607042253521127, |
| "loss": 0.9846, |
| "step": 280 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.9477686285972595, |
| "eval_runtime": 1.356, |
| "eval_samples_per_second": 279.49, |
| "eval_steps_per_second": 2.212, |
| "step": 284 |
| }, |
| { |
| "epoch": 4.014084507042254, |
| "grad_norm": 0.0663798451423645, |
| "learning_rate": 0.00016, |
| "loss": 0.9813, |
| "step": 285 |
| }, |
| { |
| "epoch": 4.084507042253521, |
| "grad_norm": 0.07960853725671768, |
| "learning_rate": 0.00015929577464788734, |
| "loss": 0.9834, |
| "step": 290 |
| }, |
| { |
| "epoch": 4.154929577464789, |
| "grad_norm": 0.0459803082048893, |
| "learning_rate": 0.00015859154929577466, |
| "loss": 0.9813, |
| "step": 295 |
| }, |
| { |
| "epoch": 4.225352112676056, |
| "grad_norm": 1.369140386581421, |
| "learning_rate": 0.00015788732394366196, |
| "loss": 0.9847, |
| "step": 300 |
| }, |
| { |
| "epoch": 4.295774647887324, |
| "grad_norm": 5.1048102378845215, |
| "learning_rate": 0.0001571830985915493, |
| "loss": 0.9825, |
| "step": 305 |
| }, |
| { |
| "epoch": 4.366197183098592, |
| "grad_norm": 0.722586452960968, |
| "learning_rate": 0.00015647887323943661, |
| "loss": 0.9782, |
| "step": 310 |
| }, |
| { |
| "epoch": 4.436619718309859, |
| "grad_norm": 0.11551281064748764, |
| "learning_rate": 0.00015577464788732394, |
| "loss": 0.9775, |
| "step": 315 |
| }, |
| { |
| "epoch": 4.507042253521127, |
| "grad_norm": 0.07706153392791748, |
| "learning_rate": 0.00015507042253521126, |
| "loss": 0.9765, |
| "step": 320 |
| }, |
| { |
| "epoch": 4.577464788732394, |
| "grad_norm": 0.13360825181007385, |
| "learning_rate": 0.0001543661971830986, |
| "loss": 0.9825, |
| "step": 325 |
| }, |
| { |
| "epoch": 4.647887323943662, |
| "grad_norm": 0.0996808111667633, |
| "learning_rate": 0.00015366197183098592, |
| "loss": 0.9755, |
| "step": 330 |
| }, |
| { |
| "epoch": 4.71830985915493, |
| "grad_norm": 0.064101941883564, |
| "learning_rate": 0.00015295774647887324, |
| "loss": 0.9747, |
| "step": 335 |
| }, |
| { |
| "epoch": 4.788732394366197, |
| "grad_norm": 0.0587599016726017, |
| "learning_rate": 0.00015225352112676057, |
| "loss": 0.9762, |
| "step": 340 |
| }, |
| { |
| "epoch": 4.859154929577465, |
| "grad_norm": 0.08781857788562775, |
| "learning_rate": 0.0001515492957746479, |
| "loss": 0.9725, |
| "step": 345 |
| }, |
| { |
| "epoch": 4.929577464788732, |
| "grad_norm": 0.09201648831367493, |
| "learning_rate": 0.00015084507042253522, |
| "loss": 0.9751, |
| "step": 350 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.07896555215120316, |
| "learning_rate": 0.00015014084507042254, |
| "loss": 0.974, |
| "step": 355 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.9434144496917725, |
| "eval_runtime": 1.3282, |
| "eval_samples_per_second": 285.356, |
| "eval_steps_per_second": 2.259, |
| "step": 355 |
| }, |
| { |
| "epoch": 5.070422535211268, |
| "grad_norm": 0.06868085265159607, |
| "learning_rate": 0.00014943661971830987, |
| "loss": 0.9773, |
| "step": 360 |
| }, |
| { |
| "epoch": 5.140845070422535, |
| "grad_norm": 0.06904036551713943, |
| "learning_rate": 0.0001487323943661972, |
| "loss": 0.9724, |
| "step": 365 |
| }, |
| { |
| "epoch": 5.211267605633803, |
| "grad_norm": 0.05451333895325661, |
| "learning_rate": 0.00014802816901408452, |
| "loss": 0.9716, |
| "step": 370 |
| }, |
| { |
| "epoch": 5.28169014084507, |
| "grad_norm": 0.08863852173089981, |
| "learning_rate": 0.00014732394366197185, |
| "loss": 0.9692, |
| "step": 375 |
| }, |
| { |
| "epoch": 5.352112676056338, |
| "grad_norm": 0.06055117025971413, |
| "learning_rate": 0.00014661971830985917, |
| "loss": 0.9713, |
| "step": 380 |
| }, |
| { |
| "epoch": 5.422535211267606, |
| "grad_norm": 0.10994315892457962, |
| "learning_rate": 0.0001459154929577465, |
| "loss": 0.9707, |
| "step": 385 |
| }, |
| { |
| "epoch": 5.492957746478873, |
| "grad_norm": 0.09731490910053253, |
| "learning_rate": 0.00014521126760563382, |
| "loss": 0.9694, |
| "step": 390 |
| }, |
| { |
| "epoch": 5.563380281690141, |
| "grad_norm": 0.05324326828122139, |
| "learning_rate": 0.00014450704225352115, |
| "loss": 0.9666, |
| "step": 395 |
| }, |
| { |
| "epoch": 5.633802816901408, |
| "grad_norm": 0.05008189380168915, |
| "learning_rate": 0.00014380281690140847, |
| "loss": 0.9672, |
| "step": 400 |
| }, |
| { |
| "epoch": 5.704225352112676, |
| "grad_norm": 0.0279605221003294, |
| "learning_rate": 0.0001430985915492958, |
| "loss": 0.9676, |
| "step": 405 |
| }, |
| { |
| "epoch": 5.774647887323944, |
| "grad_norm": 0.0670681744813919, |
| "learning_rate": 0.00014239436619718312, |
| "loss": 0.9654, |
| "step": 410 |
| }, |
| { |
| "epoch": 5.845070422535211, |
| "grad_norm": 0.04129045829176903, |
| "learning_rate": 0.00014169014084507045, |
| "loss": 0.9659, |
| "step": 415 |
| }, |
| { |
| "epoch": 5.915492957746479, |
| "grad_norm": 0.04552697390317917, |
| "learning_rate": 0.00014098591549295775, |
| "loss": 0.9675, |
| "step": 420 |
| }, |
| { |
| "epoch": 5.985915492957746, |
| "grad_norm": 0.05515826866030693, |
| "learning_rate": 0.00014028169014084507, |
| "loss": 0.967, |
| "step": 425 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.9389934539794922, |
| "eval_runtime": 1.3536, |
| "eval_samples_per_second": 279.994, |
| "eval_steps_per_second": 2.216, |
| "step": 426 |
| }, |
| { |
| "epoch": 6.056338028169014, |
| "grad_norm": 0.060634512454271317, |
| "learning_rate": 0.0001395774647887324, |
| "loss": 0.9661, |
| "step": 430 |
| }, |
| { |
| "epoch": 6.126760563380282, |
| "grad_norm": 0.035951510071754456, |
| "learning_rate": 0.00013887323943661972, |
| "loss": 0.9673, |
| "step": 435 |
| }, |
| { |
| "epoch": 6.197183098591549, |
| "grad_norm": 0.07630197703838348, |
| "learning_rate": 0.00013816901408450705, |
| "loss": 0.969, |
| "step": 440 |
| }, |
| { |
| "epoch": 6.267605633802817, |
| "grad_norm": 0.048709649592638016, |
| "learning_rate": 0.00013746478873239438, |
| "loss": 0.9605, |
| "step": 445 |
| }, |
| { |
| "epoch": 6.338028169014084, |
| "grad_norm": 0.08284774422645569, |
| "learning_rate": 0.0001367605633802817, |
| "loss": 0.9647, |
| "step": 450 |
| }, |
| { |
| "epoch": 6.408450704225352, |
| "grad_norm": 0.10234501212835312, |
| "learning_rate": 0.00013605633802816903, |
| "loss": 0.9649, |
| "step": 455 |
| }, |
| { |
| "epoch": 6.47887323943662, |
| "grad_norm": 0.07582994550466537, |
| "learning_rate": 0.00013535211267605635, |
| "loss": 0.9637, |
| "step": 460 |
| }, |
| { |
| "epoch": 6.549295774647887, |
| "grad_norm": 0.032033782452344894, |
| "learning_rate": 0.00013464788732394368, |
| "loss": 0.9616, |
| "step": 465 |
| }, |
| { |
| "epoch": 6.619718309859155, |
| "grad_norm": 0.029730021953582764, |
| "learning_rate": 0.000133943661971831, |
| "loss": 0.961, |
| "step": 470 |
| }, |
| { |
| "epoch": 6.690140845070422, |
| "grad_norm": 0.036565788090229034, |
| "learning_rate": 0.00013323943661971833, |
| "loss": 0.9613, |
| "step": 475 |
| }, |
| { |
| "epoch": 6.76056338028169, |
| "grad_norm": 0.046678755432367325, |
| "learning_rate": 0.00013253521126760565, |
| "loss": 0.9631, |
| "step": 480 |
| }, |
| { |
| "epoch": 6.830985915492958, |
| "grad_norm": 0.11235543340444565, |
| "learning_rate": 0.00013183098591549295, |
| "loss": 0.9617, |
| "step": 485 |
| }, |
| { |
| "epoch": 6.901408450704225, |
| "grad_norm": 0.04812972992658615, |
| "learning_rate": 0.00013112676056338028, |
| "loss": 0.9599, |
| "step": 490 |
| }, |
| { |
| "epoch": 6.971830985915493, |
| "grad_norm": 0.05159539356827736, |
| "learning_rate": 0.0001304225352112676, |
| "loss": 0.9622, |
| "step": 495 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.938995361328125, |
| "eval_runtime": 1.3575, |
| "eval_samples_per_second": 279.181, |
| "eval_steps_per_second": 2.21, |
| "step": 497 |
| }, |
| { |
| "epoch": 7.042253521126761, |
| "grad_norm": 0.046111464500427246, |
| "learning_rate": 0.00012971830985915493, |
| "loss": 0.9592, |
| "step": 500 |
| }, |
| { |
| "epoch": 7.112676056338028, |
| "grad_norm": 0.09057960659265518, |
| "learning_rate": 0.00012901408450704226, |
| "loss": 0.9605, |
| "step": 505 |
| }, |
| { |
| "epoch": 7.183098591549296, |
| "grad_norm": 0.06652987748384476, |
| "learning_rate": 0.00012830985915492958, |
| "loss": 0.9595, |
| "step": 510 |
| }, |
| { |
| "epoch": 7.253521126760563, |
| "grad_norm": 0.05949646607041359, |
| "learning_rate": 0.0001276056338028169, |
| "loss": 0.9586, |
| "step": 515 |
| }, |
| { |
| "epoch": 7.323943661971831, |
| "grad_norm": 0.04339510202407837, |
| "learning_rate": 0.00012690140845070423, |
| "loss": 0.9594, |
| "step": 520 |
| }, |
| { |
| "epoch": 7.394366197183099, |
| "grad_norm": 0.06728670001029968, |
| "learning_rate": 0.00012619718309859156, |
| "loss": 0.9613, |
| "step": 525 |
| }, |
| { |
| "epoch": 7.464788732394366, |
| "grad_norm": 0.03795556724071503, |
| "learning_rate": 0.00012549295774647888, |
| "loss": 0.9563, |
| "step": 530 |
| }, |
| { |
| "epoch": 7.535211267605634, |
| "grad_norm": 0.0375334694981575, |
| "learning_rate": 0.00012478873239436618, |
| "loss": 0.9601, |
| "step": 535 |
| }, |
| { |
| "epoch": 7.605633802816901, |
| "grad_norm": 0.057856108993291855, |
| "learning_rate": 0.0001240845070422535, |
| "loss": 0.9616, |
| "step": 540 |
| }, |
| { |
| "epoch": 7.676056338028169, |
| "grad_norm": 0.03536657989025116, |
| "learning_rate": 0.00012338028169014083, |
| "loss": 0.9557, |
| "step": 545 |
| }, |
| { |
| "epoch": 7.746478873239437, |
| "grad_norm": 0.05437963828444481, |
| "learning_rate": 0.00012267605633802816, |
| "loss": 0.9596, |
| "step": 550 |
| }, |
| { |
| "epoch": 7.816901408450704, |
| "grad_norm": 0.0574585422873497, |
| "learning_rate": 0.0001219718309859155, |
| "loss": 0.9583, |
| "step": 555 |
| }, |
| { |
| "epoch": 7.887323943661972, |
| "grad_norm": 0.0447322279214859, |
| "learning_rate": 0.00012126760563380282, |
| "loss": 0.9599, |
| "step": 560 |
| }, |
| { |
| "epoch": 7.957746478873239, |
| "grad_norm": 0.06250979751348495, |
| "learning_rate": 0.00012056338028169015, |
| "loss": 0.9581, |
| "step": 565 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.9374349117279053, |
| "eval_runtime": 1.356, |
| "eval_samples_per_second": 279.498, |
| "eval_steps_per_second": 2.212, |
| "step": 568 |
| }, |
| { |
| "epoch": 8.028169014084508, |
| "grad_norm": 0.02564265951514244, |
| "learning_rate": 0.00011985915492957746, |
| "loss": 0.9574, |
| "step": 570 |
| }, |
| { |
| "epoch": 8.098591549295774, |
| "grad_norm": 0.047478966414928436, |
| "learning_rate": 0.00011915492957746479, |
| "loss": 0.9538, |
| "step": 575 |
| }, |
| { |
| "epoch": 8.169014084507042, |
| "grad_norm": 0.04486701637506485, |
| "learning_rate": 0.00011845070422535211, |
| "loss": 0.957, |
| "step": 580 |
| }, |
| { |
| "epoch": 8.23943661971831, |
| "grad_norm": 0.03243768587708473, |
| "learning_rate": 0.00011774647887323944, |
| "loss": 0.9549, |
| "step": 585 |
| }, |
| { |
| "epoch": 8.309859154929578, |
| "grad_norm": 0.023309363052248955, |
| "learning_rate": 0.00011704225352112676, |
| "loss": 0.9552, |
| "step": 590 |
| }, |
| { |
| "epoch": 8.380281690140846, |
| "grad_norm": 0.06186755374073982, |
| "learning_rate": 0.00011633802816901409, |
| "loss": 0.956, |
| "step": 595 |
| }, |
| { |
| "epoch": 8.450704225352112, |
| "grad_norm": 0.033569905906915665, |
| "learning_rate": 0.00011563380281690141, |
| "loss": 0.9558, |
| "step": 600 |
| }, |
| { |
| "epoch": 8.52112676056338, |
| "grad_norm": 0.02437894605100155, |
| "learning_rate": 0.00011492957746478874, |
| "loss": 0.9539, |
| "step": 605 |
| }, |
| { |
| "epoch": 8.591549295774648, |
| "grad_norm": 0.0500415675342083, |
| "learning_rate": 0.00011422535211267606, |
| "loss": 0.9567, |
| "step": 610 |
| }, |
| { |
| "epoch": 8.661971830985916, |
| "grad_norm": 0.03755724057555199, |
| "learning_rate": 0.00011352112676056339, |
| "loss": 0.9561, |
| "step": 615 |
| }, |
| { |
| "epoch": 8.732394366197184, |
| "grad_norm": 0.06001519784331322, |
| "learning_rate": 0.00011281690140845072, |
| "loss": 0.9587, |
| "step": 620 |
| }, |
| { |
| "epoch": 8.80281690140845, |
| "grad_norm": 0.03620074316859245, |
| "learning_rate": 0.00011211267605633804, |
| "loss": 0.9541, |
| "step": 625 |
| }, |
| { |
| "epoch": 8.873239436619718, |
| "grad_norm": 0.052633192390203476, |
| "learning_rate": 0.00011140845070422537, |
| "loss": 0.9552, |
| "step": 630 |
| }, |
| { |
| "epoch": 8.943661971830986, |
| "grad_norm": 0.06923436373472214, |
| "learning_rate": 0.00011070422535211269, |
| "loss": 0.9562, |
| "step": 635 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.9356324672698975, |
| "eval_runtime": 1.356, |
| "eval_samples_per_second": 279.507, |
| "eval_steps_per_second": 2.212, |
| "step": 639 |
| }, |
| { |
| "epoch": 9.014084507042254, |
| "grad_norm": 0.030308526009321213, |
| "learning_rate": 0.00011000000000000002, |
| "loss": 0.9567, |
| "step": 640 |
| }, |
| { |
| "epoch": 9.084507042253522, |
| "grad_norm": 0.04463675990700722, |
| "learning_rate": 0.00010929577464788734, |
| "loss": 0.9534, |
| "step": 645 |
| }, |
| { |
| "epoch": 9.154929577464788, |
| "grad_norm": 0.07801490277051926, |
| "learning_rate": 0.00010859154929577467, |
| "loss": 0.9532, |
| "step": 650 |
| }, |
| { |
| "epoch": 9.225352112676056, |
| "grad_norm": 0.07350599020719528, |
| "learning_rate": 0.00010788732394366197, |
| "loss": 0.9573, |
| "step": 655 |
| }, |
| { |
| "epoch": 9.295774647887324, |
| "grad_norm": 0.04489121586084366, |
| "learning_rate": 0.00010718309859154929, |
| "loss": 0.9529, |
| "step": 660 |
| }, |
| { |
| "epoch": 9.366197183098592, |
| "grad_norm": 0.03186199814081192, |
| "learning_rate": 0.00010647887323943662, |
| "loss": 0.9547, |
| "step": 665 |
| }, |
| { |
| "epoch": 9.43661971830986, |
| "grad_norm": 0.050086986273527145, |
| "learning_rate": 0.00010577464788732394, |
| "loss": 0.9537, |
| "step": 670 |
| }, |
| { |
| "epoch": 9.507042253521126, |
| "grad_norm": 0.037186432629823685, |
| "learning_rate": 0.00010507042253521127, |
| "loss": 0.9526, |
| "step": 675 |
| }, |
| { |
| "epoch": 9.577464788732394, |
| "grad_norm": 0.07604589313268661, |
| "learning_rate": 0.0001043661971830986, |
| "loss": 0.9548, |
| "step": 680 |
| }, |
| { |
| "epoch": 9.647887323943662, |
| "grad_norm": 0.0647517517209053, |
| "learning_rate": 0.00010366197183098592, |
| "loss": 0.9565, |
| "step": 685 |
| }, |
| { |
| "epoch": 9.71830985915493, |
| "grad_norm": 0.0681651309132576, |
| "learning_rate": 0.00010295774647887325, |
| "loss": 0.9533, |
| "step": 690 |
| }, |
| { |
| "epoch": 9.788732394366198, |
| "grad_norm": 0.04616454616189003, |
| "learning_rate": 0.00010225352112676057, |
| "loss": 0.9529, |
| "step": 695 |
| }, |
| { |
| "epoch": 9.859154929577464, |
| "grad_norm": 0.029675917699933052, |
| "learning_rate": 0.0001015492957746479, |
| "loss": 0.9521, |
| "step": 700 |
| }, |
| { |
| "epoch": 9.929577464788732, |
| "grad_norm": 0.025709936395287514, |
| "learning_rate": 0.00010084507042253521, |
| "loss": 0.9494, |
| "step": 705 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.02850981615483761, |
| "learning_rate": 0.00010014084507042253, |
| "loss": 0.9522, |
| "step": 710 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.9344412684440613, |
| "eval_runtime": 1.3287, |
| "eval_samples_per_second": 285.24, |
| "eval_steps_per_second": 2.258, |
| "step": 710 |
| }, |
| { |
| "epoch": 10.070422535211268, |
| "grad_norm": 0.05556517466902733, |
| "learning_rate": 9.943661971830986e-05, |
| "loss": 0.9529, |
| "step": 715 |
| }, |
| { |
| "epoch": 10.140845070422536, |
| "grad_norm": 0.06735611706972122, |
| "learning_rate": 9.873239436619719e-05, |
| "loss": 0.9531, |
| "step": 720 |
| }, |
| { |
| "epoch": 10.211267605633802, |
| "grad_norm": 0.05679089203476906, |
| "learning_rate": 9.802816901408451e-05, |
| "loss": 0.9511, |
| "step": 725 |
| }, |
| { |
| "epoch": 10.28169014084507, |
| "grad_norm": 0.09331786632537842, |
| "learning_rate": 9.732394366197184e-05, |
| "loss": 0.9509, |
| "step": 730 |
| }, |
| { |
| "epoch": 10.352112676056338, |
| "grad_norm": 0.06282954663038254, |
| "learning_rate": 9.661971830985916e-05, |
| "loss": 0.952, |
| "step": 735 |
| }, |
| { |
| "epoch": 10.422535211267606, |
| "grad_norm": 0.06508725136518478, |
| "learning_rate": 9.591549295774649e-05, |
| "loss": 0.9534, |
| "step": 740 |
| }, |
| { |
| "epoch": 10.492957746478874, |
| "grad_norm": 0.041396528482437134, |
| "learning_rate": 9.52112676056338e-05, |
| "loss": 0.9537, |
| "step": 745 |
| }, |
| { |
| "epoch": 10.56338028169014, |
| "grad_norm": 0.04602223262190819, |
| "learning_rate": 9.450704225352112e-05, |
| "loss": 0.951, |
| "step": 750 |
| }, |
| { |
| "epoch": 10.633802816901408, |
| "grad_norm": 0.03372340276837349, |
| "learning_rate": 9.380281690140845e-05, |
| "loss": 0.9498, |
| "step": 755 |
| }, |
| { |
| "epoch": 10.704225352112676, |
| "grad_norm": 0.03808495029807091, |
| "learning_rate": 9.309859154929578e-05, |
| "loss": 0.9504, |
| "step": 760 |
| }, |
| { |
| "epoch": 10.774647887323944, |
| "grad_norm": 0.027203522622585297, |
| "learning_rate": 9.23943661971831e-05, |
| "loss": 0.9514, |
| "step": 765 |
| }, |
| { |
| "epoch": 10.845070422535212, |
| "grad_norm": 0.03273136168718338, |
| "learning_rate": 9.169014084507043e-05, |
| "loss": 0.9496, |
| "step": 770 |
| }, |
| { |
| "epoch": 10.915492957746478, |
| "grad_norm": 0.03632248193025589, |
| "learning_rate": 9.098591549295775e-05, |
| "loss": 0.9518, |
| "step": 775 |
| }, |
| { |
| "epoch": 10.985915492957746, |
| "grad_norm": 0.04196527600288391, |
| "learning_rate": 9.028169014084508e-05, |
| "loss": 0.9493, |
| "step": 780 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.9340574145317078, |
| "eval_runtime": 1.3554, |
| "eval_samples_per_second": 279.624, |
| "eval_steps_per_second": 2.213, |
| "step": 781 |
| }, |
| { |
| "epoch": 11.056338028169014, |
| "grad_norm": 0.02801569737493992, |
| "learning_rate": 8.95774647887324e-05, |
| "loss": 0.9506, |
| "step": 785 |
| }, |
| { |
| "epoch": 11.126760563380282, |
| "grad_norm": 0.07875282317399979, |
| "learning_rate": 8.887323943661973e-05, |
| "loss": 0.9527, |
| "step": 790 |
| }, |
| { |
| "epoch": 11.19718309859155, |
| "grad_norm": 0.06978793442249298, |
| "learning_rate": 8.816901408450705e-05, |
| "loss": 0.9513, |
| "step": 795 |
| }, |
| { |
| "epoch": 11.267605633802816, |
| "grad_norm": 0.05102715268731117, |
| "learning_rate": 8.746478873239437e-05, |
| "loss": 0.9493, |
| "step": 800 |
| }, |
| { |
| "epoch": 11.338028169014084, |
| "grad_norm": 0.037087179720401764, |
| "learning_rate": 8.676056338028169e-05, |
| "loss": 0.9482, |
| "step": 805 |
| }, |
| { |
| "epoch": 11.408450704225352, |
| "grad_norm": 0.026025516912341118, |
| "learning_rate": 8.605633802816902e-05, |
| "loss": 0.9499, |
| "step": 810 |
| }, |
| { |
| "epoch": 11.47887323943662, |
| "grad_norm": 0.046463027596473694, |
| "learning_rate": 8.535211267605634e-05, |
| "loss": 0.9526, |
| "step": 815 |
| }, |
| { |
| "epoch": 11.549295774647888, |
| "grad_norm": 0.03885842487215996, |
| "learning_rate": 8.464788732394367e-05, |
| "loss": 0.9508, |
| "step": 820 |
| }, |
| { |
| "epoch": 11.619718309859154, |
| "grad_norm": 0.042792994529008865, |
| "learning_rate": 8.3943661971831e-05, |
| "loss": 0.9491, |
| "step": 825 |
| }, |
| { |
| "epoch": 11.690140845070422, |
| "grad_norm": 0.040800243616104126, |
| "learning_rate": 8.323943661971832e-05, |
| "loss": 0.9502, |
| "step": 830 |
| }, |
| { |
| "epoch": 11.76056338028169, |
| "grad_norm": 0.04244118928909302, |
| "learning_rate": 8.253521126760565e-05, |
| "loss": 0.9463, |
| "step": 835 |
| }, |
| { |
| "epoch": 11.830985915492958, |
| "grad_norm": 0.027077561244368553, |
| "learning_rate": 8.183098591549296e-05, |
| "loss": 0.9486, |
| "step": 840 |
| }, |
| { |
| "epoch": 11.901408450704226, |
| "grad_norm": 0.0710897371172905, |
| "learning_rate": 8.112676056338028e-05, |
| "loss": 0.9498, |
| "step": 845 |
| }, |
| { |
| "epoch": 11.971830985915492, |
| "grad_norm": 0.027009285986423492, |
| "learning_rate": 8.042253521126761e-05, |
| "loss": 0.9492, |
| "step": 850 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.934472382068634, |
| "eval_runtime": 1.3559, |
| "eval_samples_per_second": 279.512, |
| "eval_steps_per_second": 2.212, |
| "step": 852 |
| }, |
| { |
| "epoch": 12.04225352112676, |
| "grad_norm": 0.027241826057434082, |
| "learning_rate": 7.971830985915493e-05, |
| "loss": 0.9485, |
| "step": 855 |
| }, |
| { |
| "epoch": 12.112676056338028, |
| "grad_norm": 17.60222816467285, |
| "learning_rate": 7.901408450704225e-05, |
| "loss": 0.9505, |
| "step": 860 |
| }, |
| { |
| "epoch": 12.183098591549296, |
| "grad_norm": 0.04522601515054703, |
| "learning_rate": 7.830985915492957e-05, |
| "loss": 0.9511, |
| "step": 865 |
| }, |
| { |
| "epoch": 12.253521126760564, |
| "grad_norm": 0.0453733466565609, |
| "learning_rate": 7.76056338028169e-05, |
| "loss": 0.9488, |
| "step": 870 |
| }, |
| { |
| "epoch": 12.323943661971832, |
| "grad_norm": 0.04800290986895561, |
| "learning_rate": 7.690140845070422e-05, |
| "loss": 0.9484, |
| "step": 875 |
| }, |
| { |
| "epoch": 12.394366197183098, |
| "grad_norm": 0.056329064071178436, |
| "learning_rate": 7.619718309859155e-05, |
| "loss": 0.9488, |
| "step": 880 |
| }, |
| { |
| "epoch": 12.464788732394366, |
| "grad_norm": 0.04998723790049553, |
| "learning_rate": 7.549295774647887e-05, |
| "loss": 0.9491, |
| "step": 885 |
| }, |
| { |
| "epoch": 12.535211267605634, |
| "grad_norm": 0.024647079408168793, |
| "learning_rate": 7.47887323943662e-05, |
| "loss": 0.9474, |
| "step": 890 |
| }, |
| { |
| "epoch": 12.605633802816902, |
| "grad_norm": 0.06089835241436958, |
| "learning_rate": 7.408450704225352e-05, |
| "loss": 0.9487, |
| "step": 895 |
| }, |
| { |
| "epoch": 12.676056338028168, |
| "grad_norm": 0.07820327579975128, |
| "learning_rate": 7.338028169014085e-05, |
| "loss": 0.9486, |
| "step": 900 |
| }, |
| { |
| "epoch": 12.746478873239436, |
| "grad_norm": 0.03777018189430237, |
| "learning_rate": 7.267605633802818e-05, |
| "loss": 0.9483, |
| "step": 905 |
| }, |
| { |
| "epoch": 12.816901408450704, |
| "grad_norm": 0.038660142570734024, |
| "learning_rate": 7.19718309859155e-05, |
| "loss": 0.9478, |
| "step": 910 |
| }, |
| { |
| "epoch": 12.887323943661972, |
| "grad_norm": 0.028829969465732574, |
| "learning_rate": 7.126760563380283e-05, |
| "loss": 0.9471, |
| "step": 915 |
| }, |
| { |
| "epoch": 12.95774647887324, |
| "grad_norm": 0.02644144371151924, |
| "learning_rate": 7.056338028169014e-05, |
| "loss": 0.9493, |
| "step": 920 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 0.9329857230186462, |
| "eval_runtime": 1.3566, |
| "eval_samples_per_second": 279.384, |
| "eval_steps_per_second": 2.211, |
| "step": 923 |
| }, |
| { |
| "epoch": 13.028169014084508, |
| "grad_norm": 0.027125298976898193, |
| "learning_rate": 6.985915492957746e-05, |
| "loss": 0.948, |
| "step": 925 |
| }, |
| { |
| "epoch": 13.098591549295774, |
| "grad_norm": 0.025396650657057762, |
| "learning_rate": 6.915492957746479e-05, |
| "loss": 0.9485, |
| "step": 930 |
| }, |
| { |
| "epoch": 13.169014084507042, |
| "grad_norm": 0.039986852556467056, |
| "learning_rate": 6.845070422535212e-05, |
| "loss": 0.948, |
| "step": 935 |
| }, |
| { |
| "epoch": 13.23943661971831, |
| "grad_norm": 0.04669572040438652, |
| "learning_rate": 6.774647887323944e-05, |
| "loss": 0.9484, |
| "step": 940 |
| }, |
| { |
| "epoch": 13.309859154929578, |
| "grad_norm": 0.05597477778792381, |
| "learning_rate": 6.704225352112677e-05, |
| "loss": 0.9492, |
| "step": 945 |
| }, |
| { |
| "epoch": 13.380281690140846, |
| "grad_norm": 0.03363762050867081, |
| "learning_rate": 6.633802816901409e-05, |
| "loss": 0.9479, |
| "step": 950 |
| }, |
| { |
| "epoch": 13.450704225352112, |
| "grad_norm": 0.0501028336584568, |
| "learning_rate": 6.563380281690142e-05, |
| "loss": 0.9472, |
| "step": 955 |
| }, |
| { |
| "epoch": 13.52112676056338, |
| "grad_norm": 0.02368428371846676, |
| "learning_rate": 6.492957746478874e-05, |
| "loss": 0.9473, |
| "step": 960 |
| }, |
| { |
| "epoch": 13.591549295774648, |
| "grad_norm": 0.024430401623249054, |
| "learning_rate": 6.422535211267607e-05, |
| "loss": 0.9461, |
| "step": 965 |
| }, |
| { |
| "epoch": 13.661971830985916, |
| "grad_norm": 0.036314696073532104, |
| "learning_rate": 6.35211267605634e-05, |
| "loss": 0.9469, |
| "step": 970 |
| }, |
| { |
| "epoch": 13.732394366197184, |
| "grad_norm": 0.03353135287761688, |
| "learning_rate": 6.28169014084507e-05, |
| "loss": 0.9468, |
| "step": 975 |
| }, |
| { |
| "epoch": 13.80281690140845, |
| "grad_norm": 0.0263178963214159, |
| "learning_rate": 6.211267605633803e-05, |
| "loss": 0.9484, |
| "step": 980 |
| }, |
| { |
| "epoch": 13.873239436619718, |
| "grad_norm": 0.06421630084514618, |
| "learning_rate": 6.140845070422536e-05, |
| "loss": 0.9481, |
| "step": 985 |
| }, |
| { |
| "epoch": 13.943661971830986, |
| "grad_norm": 0.03617294877767563, |
| "learning_rate": 6.0704225352112676e-05, |
| "loss": 0.9467, |
| "step": 990 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.9325685501098633, |
| "eval_runtime": 1.3557, |
| "eval_samples_per_second": 279.559, |
| "eval_steps_per_second": 2.213, |
| "step": 994 |
| }, |
| { |
| "epoch": 14.014084507042254, |
| "grad_norm": 0.05025329068303108, |
| "learning_rate": 6e-05, |
| "loss": 0.9447, |
| "step": 995 |
| }, |
| { |
| "epoch": 14.084507042253522, |
| "grad_norm": 0.03912140801548958, |
| "learning_rate": 5.929577464788733e-05, |
| "loss": 0.9468, |
| "step": 1000 |
| }, |
| { |
| "epoch": 14.154929577464788, |
| "grad_norm": 0.030682148411870003, |
| "learning_rate": 5.859154929577465e-05, |
| "loss": 0.9454, |
| "step": 1005 |
| }, |
| { |
| "epoch": 14.225352112676056, |
| "grad_norm": 0.06476651132106781, |
| "learning_rate": 5.788732394366198e-05, |
| "loss": 0.946, |
| "step": 1010 |
| }, |
| { |
| "epoch": 14.295774647887324, |
| "grad_norm": 0.01931784488260746, |
| "learning_rate": 5.71830985915493e-05, |
| "loss": 0.9458, |
| "step": 1015 |
| }, |
| { |
| "epoch": 14.366197183098592, |
| "grad_norm": 0.030390406027436256, |
| "learning_rate": 5.647887323943662e-05, |
| "loss": 0.9464, |
| "step": 1020 |
| }, |
| { |
| "epoch": 14.43661971830986, |
| "grad_norm": 0.060740068554878235, |
| "learning_rate": 5.577464788732395e-05, |
| "loss": 0.9459, |
| "step": 1025 |
| }, |
| { |
| "epoch": 14.507042253521126, |
| "grad_norm": 0.034336596727371216, |
| "learning_rate": 5.5070422535211273e-05, |
| "loss": 0.9454, |
| "step": 1030 |
| }, |
| { |
| "epoch": 14.577464788732394, |
| "grad_norm": 0.04022248461842537, |
| "learning_rate": 5.43661971830986e-05, |
| "loss": 0.9459, |
| "step": 1035 |
| }, |
| { |
| "epoch": 14.647887323943662, |
| "grad_norm": 0.03897751495242119, |
| "learning_rate": 5.366197183098591e-05, |
| "loss": 0.948, |
| "step": 1040 |
| }, |
| { |
| "epoch": 14.71830985915493, |
| "grad_norm": 0.017990631982684135, |
| "learning_rate": 5.2957746478873237e-05, |
| "loss": 0.9461, |
| "step": 1045 |
| }, |
| { |
| "epoch": 14.788732394366198, |
| "grad_norm": 0.04828361049294472, |
| "learning_rate": 5.225352112676056e-05, |
| "loss": 0.9473, |
| "step": 1050 |
| }, |
| { |
| "epoch": 14.859154929577464, |
| "grad_norm": 0.040516018867492676, |
| "learning_rate": 5.154929577464789e-05, |
| "loss": 0.9466, |
| "step": 1055 |
| }, |
| { |
| "epoch": 14.929577464788732, |
| "grad_norm": 0.023633386939764023, |
| "learning_rate": 5.084507042253521e-05, |
| "loss": 0.9483, |
| "step": 1060 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 0.03356311842799187, |
| "learning_rate": 5.014084507042254e-05, |
| "loss": 0.9433, |
| "step": 1065 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 0.9321981072425842, |
| "eval_runtime": 1.3288, |
| "eval_samples_per_second": 285.221, |
| "eval_steps_per_second": 2.258, |
| "step": 1065 |
| }, |
| { |
| "epoch": 15.070422535211268, |
| "grad_norm": 0.031062249094247818, |
| "learning_rate": 4.9436619718309864e-05, |
| "loss": 0.9449, |
| "step": 1070 |
| }, |
| { |
| "epoch": 15.140845070422536, |
| "grad_norm": 0.03606761246919632, |
| "learning_rate": 4.873239436619719e-05, |
| "loss": 0.9452, |
| "step": 1075 |
| }, |
| { |
| "epoch": 15.211267605633802, |
| "grad_norm": 0.03723893314599991, |
| "learning_rate": 4.8028169014084515e-05, |
| "loss": 0.9495, |
| "step": 1080 |
| }, |
| { |
| "epoch": 15.28169014084507, |
| "grad_norm": 0.022561002522706985, |
| "learning_rate": 4.7323943661971834e-05, |
| "loss": 0.9451, |
| "step": 1085 |
| }, |
| { |
| "epoch": 15.352112676056338, |
| "grad_norm": 0.03934817761182785, |
| "learning_rate": 4.661971830985915e-05, |
| "loss": 0.9465, |
| "step": 1090 |
| }, |
| { |
| "epoch": 15.422535211267606, |
| "grad_norm": 0.021020477637648582, |
| "learning_rate": 4.591549295774648e-05, |
| "loss": 0.9458, |
| "step": 1095 |
| }, |
| { |
| "epoch": 15.492957746478874, |
| "grad_norm": 0.029691854491829872, |
| "learning_rate": 4.5211267605633804e-05, |
| "loss": 0.9464, |
| "step": 1100 |
| }, |
| { |
| "epoch": 15.56338028169014, |
| "grad_norm": 0.030643166974186897, |
| "learning_rate": 4.450704225352113e-05, |
| "loss": 0.9438, |
| "step": 1105 |
| }, |
| { |
| "epoch": 15.633802816901408, |
| "grad_norm": 0.0261048823595047, |
| "learning_rate": 4.3802816901408455e-05, |
| "loss": 0.9442, |
| "step": 1110 |
| }, |
| { |
| "epoch": 15.704225352112676, |
| "grad_norm": 0.04185587912797928, |
| "learning_rate": 4.3098591549295774e-05, |
| "loss": 0.9455, |
| "step": 1115 |
| }, |
| { |
| "epoch": 15.774647887323944, |
| "grad_norm": 0.03181832283735275, |
| "learning_rate": 4.23943661971831e-05, |
| "loss": 0.9452, |
| "step": 1120 |
| }, |
| { |
| "epoch": 15.845070422535212, |
| "grad_norm": 0.017347080633044243, |
| "learning_rate": 4.1690140845070425e-05, |
| "loss": 0.9445, |
| "step": 1125 |
| }, |
| { |
| "epoch": 15.915492957746478, |
| "grad_norm": 0.0175313837826252, |
| "learning_rate": 4.098591549295775e-05, |
| "loss": 0.9462, |
| "step": 1130 |
| }, |
| { |
| "epoch": 15.985915492957746, |
| "grad_norm": 0.016237597912549973, |
| "learning_rate": 4.0281690140845076e-05, |
| "loss": 0.9441, |
| "step": 1135 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.932042121887207, |
| "eval_runtime": 1.3559, |
| "eval_samples_per_second": 279.512, |
| "eval_steps_per_second": 2.212, |
| "step": 1136 |
| }, |
| { |
| "epoch": 16.056338028169016, |
| "grad_norm": 0.02838326431810856, |
| "learning_rate": 3.9577464788732395e-05, |
| "loss": 0.9443, |
| "step": 1140 |
| }, |
| { |
| "epoch": 16.12676056338028, |
| "grad_norm": 0.03755342960357666, |
| "learning_rate": 3.887323943661972e-05, |
| "loss": 0.9448, |
| "step": 1145 |
| }, |
| { |
| "epoch": 16.197183098591548, |
| "grad_norm": 0.019139522686600685, |
| "learning_rate": 3.8169014084507046e-05, |
| "loss": 0.945, |
| "step": 1150 |
| }, |
| { |
| "epoch": 16.267605633802816, |
| "grad_norm": 0.029503419995307922, |
| "learning_rate": 3.746478873239437e-05, |
| "loss": 0.9437, |
| "step": 1155 |
| }, |
| { |
| "epoch": 16.338028169014084, |
| "grad_norm": 0.02175034210085869, |
| "learning_rate": 3.676056338028169e-05, |
| "loss": 0.9458, |
| "step": 1160 |
| }, |
| { |
| "epoch": 16.408450704225352, |
| "grad_norm": 0.041107743978500366, |
| "learning_rate": 3.6056338028169015e-05, |
| "loss": 0.9462, |
| "step": 1165 |
| }, |
| { |
| "epoch": 16.47887323943662, |
| "grad_norm": 0.03304363787174225, |
| "learning_rate": 3.5352112676056334e-05, |
| "loss": 0.9456, |
| "step": 1170 |
| }, |
| { |
| "epoch": 16.549295774647888, |
| "grad_norm": 0.02730601467192173, |
| "learning_rate": 3.464788732394366e-05, |
| "loss": 0.9447, |
| "step": 1175 |
| }, |
| { |
| "epoch": 16.619718309859156, |
| "grad_norm": 0.03291373327374458, |
| "learning_rate": 3.3943661971830985e-05, |
| "loss": 0.9452, |
| "step": 1180 |
| }, |
| { |
| "epoch": 16.690140845070424, |
| "grad_norm": 0.023141978308558464, |
| "learning_rate": 3.323943661971831e-05, |
| "loss": 0.9437, |
| "step": 1185 |
| }, |
| { |
| "epoch": 16.760563380281692, |
| "grad_norm": 0.02332274429500103, |
| "learning_rate": 3.2535211267605636e-05, |
| "loss": 0.9438, |
| "step": 1190 |
| }, |
| { |
| "epoch": 16.830985915492956, |
| "grad_norm": 0.050522513687610626, |
| "learning_rate": 3.183098591549296e-05, |
| "loss": 0.9437, |
| "step": 1195 |
| }, |
| { |
| "epoch": 16.901408450704224, |
| "grad_norm": 0.02046947181224823, |
| "learning_rate": 3.112676056338028e-05, |
| "loss": 0.9453, |
| "step": 1200 |
| }, |
| { |
| "epoch": 16.971830985915492, |
| "grad_norm": 0.06999664008617401, |
| "learning_rate": 3.0422535211267606e-05, |
| "loss": 0.9453, |
| "step": 1205 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 0.9319289326667786, |
| "eval_runtime": 1.3556, |
| "eval_samples_per_second": 279.59, |
| "eval_steps_per_second": 2.213, |
| "step": 1207 |
| }, |
| { |
| "epoch": 17.04225352112676, |
| "grad_norm": 0.027964303269982338, |
| "learning_rate": 2.971830985915493e-05, |
| "loss": 0.9437, |
| "step": 1210 |
| }, |
| { |
| "epoch": 17.112676056338028, |
| "grad_norm": 0.021849192678928375, |
| "learning_rate": 2.9014084507042254e-05, |
| "loss": 0.9451, |
| "step": 1215 |
| }, |
| { |
| "epoch": 17.183098591549296, |
| "grad_norm": 0.06382541358470917, |
| "learning_rate": 2.830985915492958e-05, |
| "loss": 0.9446, |
| "step": 1220 |
| }, |
| { |
| "epoch": 17.253521126760564, |
| "grad_norm": 0.018395431339740753, |
| "learning_rate": 2.7605633802816905e-05, |
| "loss": 0.9449, |
| "step": 1225 |
| }, |
| { |
| "epoch": 17.323943661971832, |
| "grad_norm": 0.02647424302995205, |
| "learning_rate": 2.6901408450704224e-05, |
| "loss": 0.943, |
| "step": 1230 |
| }, |
| { |
| "epoch": 17.3943661971831, |
| "grad_norm": 0.053954143077135086, |
| "learning_rate": 2.619718309859155e-05, |
| "loss": 0.9451, |
| "step": 1235 |
| }, |
| { |
| "epoch": 17.464788732394368, |
| "grad_norm": 0.03957201540470123, |
| "learning_rate": 2.5492957746478875e-05, |
| "loss": 0.9448, |
| "step": 1240 |
| }, |
| { |
| "epoch": 17.535211267605632, |
| "grad_norm": 0.0455038957297802, |
| "learning_rate": 2.47887323943662e-05, |
| "loss": 0.9441, |
| "step": 1245 |
| }, |
| { |
| "epoch": 17.6056338028169, |
| "grad_norm": 0.03737751021981239, |
| "learning_rate": 2.4084507042253522e-05, |
| "loss": 0.9469, |
| "step": 1250 |
| }, |
| { |
| "epoch": 17.676056338028168, |
| "grad_norm": 0.038107406347990036, |
| "learning_rate": 2.3380281690140845e-05, |
| "loss": 0.9445, |
| "step": 1255 |
| }, |
| { |
| "epoch": 17.746478873239436, |
| "grad_norm": 0.04548390954732895, |
| "learning_rate": 2.267605633802817e-05, |
| "loss": 0.9451, |
| "step": 1260 |
| }, |
| { |
| "epoch": 17.816901408450704, |
| "grad_norm": 0.03373611345887184, |
| "learning_rate": 2.1971830985915496e-05, |
| "loss": 0.9438, |
| "step": 1265 |
| }, |
| { |
| "epoch": 17.887323943661972, |
| "grad_norm": 0.029089247807860374, |
| "learning_rate": 2.1267605633802818e-05, |
| "loss": 0.9435, |
| "step": 1270 |
| }, |
| { |
| "epoch": 17.95774647887324, |
| "grad_norm": 0.027908792719244957, |
| "learning_rate": 2.0563380281690143e-05, |
| "loss": 0.9433, |
| "step": 1275 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.9321526885032654, |
| "eval_runtime": 1.3562, |
| "eval_samples_per_second": 279.464, |
| "eval_steps_per_second": 2.212, |
| "step": 1278 |
| }, |
| { |
| "epoch": 18.028169014084508, |
| "grad_norm": 0.038007136434316635, |
| "learning_rate": 1.9859154929577465e-05, |
| "loss": 0.9433, |
| "step": 1280 |
| }, |
| { |
| "epoch": 18.098591549295776, |
| "grad_norm": 0.055055730044841766, |
| "learning_rate": 1.9154929577464788e-05, |
| "loss": 0.9444, |
| "step": 1285 |
| }, |
| { |
| "epoch": 18.169014084507044, |
| "grad_norm": 0.024233724921941757, |
| "learning_rate": 1.8450704225352113e-05, |
| "loss": 0.9448, |
| "step": 1290 |
| }, |
| { |
| "epoch": 18.239436619718308, |
| "grad_norm": 0.02525465376675129, |
| "learning_rate": 1.774647887323944e-05, |
| "loss": 0.9452, |
| "step": 1295 |
| }, |
| { |
| "epoch": 18.309859154929576, |
| "grad_norm": 0.03696692734956741, |
| "learning_rate": 1.704225352112676e-05, |
| "loss": 0.9451, |
| "step": 1300 |
| }, |
| { |
| "epoch": 18.380281690140844, |
| "grad_norm": 0.012775393202900887, |
| "learning_rate": 1.6338028169014086e-05, |
| "loss": 0.9424, |
| "step": 1305 |
| }, |
| { |
| "epoch": 18.450704225352112, |
| "grad_norm": 0.04282708466053009, |
| "learning_rate": 1.5633802816901412e-05, |
| "loss": 0.9439, |
| "step": 1310 |
| }, |
| { |
| "epoch": 18.52112676056338, |
| "grad_norm": 0.026728734374046326, |
| "learning_rate": 1.4929577464788732e-05, |
| "loss": 0.9432, |
| "step": 1315 |
| }, |
| { |
| "epoch": 18.591549295774648, |
| "grad_norm": 0.038278259336948395, |
| "learning_rate": 1.4225352112676058e-05, |
| "loss": 0.9437, |
| "step": 1320 |
| }, |
| { |
| "epoch": 18.661971830985916, |
| "grad_norm": 0.0476648211479187, |
| "learning_rate": 1.352112676056338e-05, |
| "loss": 0.9442, |
| "step": 1325 |
| }, |
| { |
| "epoch": 18.732394366197184, |
| "grad_norm": 0.017152875661849976, |
| "learning_rate": 1.2816901408450704e-05, |
| "loss": 0.9439, |
| "step": 1330 |
| }, |
| { |
| "epoch": 18.802816901408452, |
| "grad_norm": 0.02195524424314499, |
| "learning_rate": 1.211267605633803e-05, |
| "loss": 0.9441, |
| "step": 1335 |
| }, |
| { |
| "epoch": 18.87323943661972, |
| "grad_norm": 0.03179704770445824, |
| "learning_rate": 1.1408450704225353e-05, |
| "loss": 0.944, |
| "step": 1340 |
| }, |
| { |
| "epoch": 18.943661971830984, |
| "grad_norm": 0.01666986383497715, |
| "learning_rate": 1.0704225352112677e-05, |
| "loss": 0.9436, |
| "step": 1345 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 0.9319114685058594, |
| "eval_runtime": 1.3555, |
| "eval_samples_per_second": 279.596, |
| "eval_steps_per_second": 2.213, |
| "step": 1349 |
| }, |
| { |
| "epoch": 19.014084507042252, |
| "grad_norm": 0.027670254930853844, |
| "learning_rate": 1e-05, |
| "loss": 0.9441, |
| "step": 1350 |
| }, |
| { |
| "epoch": 19.08450704225352, |
| "grad_norm": 0.05388191342353821, |
| "learning_rate": 9.295774647887325e-06, |
| "loss": 0.9445, |
| "step": 1355 |
| }, |
| { |
| "epoch": 19.154929577464788, |
| "grad_norm": 0.02966221235692501, |
| "learning_rate": 8.591549295774648e-06, |
| "loss": 0.9432, |
| "step": 1360 |
| }, |
| { |
| "epoch": 19.225352112676056, |
| "grad_norm": 0.02553911693394184, |
| "learning_rate": 7.887323943661972e-06, |
| "loss": 0.9434, |
| "step": 1365 |
| }, |
| { |
| "epoch": 19.295774647887324, |
| "grad_norm": 0.03100278414785862, |
| "learning_rate": 7.183098591549296e-06, |
| "loss": 0.9438, |
| "step": 1370 |
| }, |
| { |
| "epoch": 19.366197183098592, |
| "grad_norm": 0.03018755465745926, |
| "learning_rate": 6.47887323943662e-06, |
| "loss": 0.9442, |
| "step": 1375 |
| }, |
| { |
| "epoch": 19.43661971830986, |
| "grad_norm": 0.019777249544858932, |
| "learning_rate": 5.774647887323944e-06, |
| "loss": 0.9438, |
| "step": 1380 |
| }, |
| { |
| "epoch": 19.507042253521128, |
| "grad_norm": 0.036921270191669464, |
| "learning_rate": 5.070422535211268e-06, |
| "loss": 0.9435, |
| "step": 1385 |
| }, |
| { |
| "epoch": 19.577464788732396, |
| "grad_norm": 0.038511138409376144, |
| "learning_rate": 4.3661971830985915e-06, |
| "loss": 0.9442, |
| "step": 1390 |
| }, |
| { |
| "epoch": 19.647887323943664, |
| "grad_norm": 0.03045705333352089, |
| "learning_rate": 3.6619718309859158e-06, |
| "loss": 0.9443, |
| "step": 1395 |
| }, |
| { |
| "epoch": 19.718309859154928, |
| "grad_norm": 0.037487465888261795, |
| "learning_rate": 2.9577464788732396e-06, |
| "loss": 0.9435, |
| "step": 1400 |
| }, |
| { |
| "epoch": 19.788732394366196, |
| "grad_norm": 0.022748373448848724, |
| "learning_rate": 2.2535211267605635e-06, |
| "loss": 0.9439, |
| "step": 1405 |
| }, |
| { |
| "epoch": 19.859154929577464, |
| "grad_norm": 0.037895116955041885, |
| "learning_rate": 1.5492957746478875e-06, |
| "loss": 0.9438, |
| "step": 1410 |
| }, |
| { |
| "epoch": 19.929577464788732, |
| "grad_norm": 0.02999270148575306, |
| "learning_rate": 8.450704225352112e-07, |
| "loss": 0.9429, |
| "step": 1415 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 0.03205498680472374, |
| "learning_rate": 1.4084507042253522e-07, |
| "loss": 0.9441, |
| "step": 1420 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.931971549987793, |
| "eval_runtime": 1.3285, |
| "eval_samples_per_second": 285.277, |
| "eval_steps_per_second": 2.258, |
| "step": 1420 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1420, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.424179214123008e+16, |
| "train_batch_size": 48, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
