| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.996845425867508, | |
| "eval_steps": 500, | |
| "global_step": 1108, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5020396709442139, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 132.3528, | |
| "eval_samples_per_second": 35.307, | |
| "eval_steps_per_second": 4.42, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 0.018026137899954935, | |
| "grad_norm": 11.620719909667969, | |
| "learning_rate": 4.9548736462093865e-05, | |
| "loss": 0.2661, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03605227579990987, | |
| "grad_norm": 1.2112946510314941, | |
| "learning_rate": 4.909747292418773e-05, | |
| "loss": 0.0513, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054078413699864804, | |
| "grad_norm": 0.3561903238296509, | |
| "learning_rate": 4.864620938628159e-05, | |
| "loss": 0.0542, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07210455159981974, | |
| "grad_norm": 15.130791664123535, | |
| "learning_rate": 4.819494584837546e-05, | |
| "loss": 0.1113, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09013068949977468, | |
| "grad_norm": 10.50532054901123, | |
| "learning_rate": 4.7743682310469314e-05, | |
| "loss": 0.0417, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10815682739972961, | |
| "grad_norm": 7.872809410095215, | |
| "learning_rate": 4.7292418772563177e-05, | |
| "loss": 0.0652, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12618296529968454, | |
| "grad_norm": 0.3549640476703644, | |
| "learning_rate": 4.684115523465704e-05, | |
| "loss": 0.0476, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14420910319963948, | |
| "grad_norm": 3.7721316814422607, | |
| "learning_rate": 4.63898916967509e-05, | |
| "loss": 0.0489, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16223524109959442, | |
| "grad_norm": 1.7026127576828003, | |
| "learning_rate": 4.5938628158844764e-05, | |
| "loss": 0.0795, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18026137899954936, | |
| "grad_norm": 0.6303790807723999, | |
| "learning_rate": 4.548736462093863e-05, | |
| "loss": 0.0187, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19828751689950427, | |
| "grad_norm": 0.14402388036251068, | |
| "learning_rate": 4.5036101083032495e-05, | |
| "loss": 0.056, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.21631365479945922, | |
| "grad_norm": 0.2994736135005951, | |
| "learning_rate": 4.458483754512636e-05, | |
| "loss": 0.0697, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23433979269941416, | |
| "grad_norm": 0.5501758456230164, | |
| "learning_rate": 4.413357400722022e-05, | |
| "loss": 0.0518, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.25236593059936907, | |
| "grad_norm": 6.304769992828369, | |
| "learning_rate": 4.368231046931408e-05, | |
| "loss": 0.0583, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.270392068499324, | |
| "grad_norm": 0.6018352508544922, | |
| "learning_rate": 4.3231046931407945e-05, | |
| "loss": 0.0455, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.28841820639927895, | |
| "grad_norm": 5.612204551696777, | |
| "learning_rate": 4.277978339350181e-05, | |
| "loss": 0.0415, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3064443442992339, | |
| "grad_norm": 8.740653991699219, | |
| "learning_rate": 4.232851985559567e-05, | |
| "loss": 0.0435, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.32447048219918884, | |
| "grad_norm": 0.3686186373233795, | |
| "learning_rate": 4.187725631768953e-05, | |
| "loss": 0.0629, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3424966200991438, | |
| "grad_norm": 0.5254208445549011, | |
| "learning_rate": 4.1425992779783394e-05, | |
| "loss": 0.0544, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3605227579990987, | |
| "grad_norm": 6.638070583343506, | |
| "learning_rate": 4.0974729241877256e-05, | |
| "loss": 0.0833, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3785488958990536, | |
| "grad_norm": 7.016050815582275, | |
| "learning_rate": 4.052346570397112e-05, | |
| "loss": 0.0641, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.39657503379900855, | |
| "grad_norm": 0.49279534816741943, | |
| "learning_rate": 4.007220216606498e-05, | |
| "loss": 0.031, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4146011716989635, | |
| "grad_norm": 2.8472509384155273, | |
| "learning_rate": 3.962093862815885e-05, | |
| "loss": 0.081, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.43262730959891843, | |
| "grad_norm": 3.4148313999176025, | |
| "learning_rate": 3.916967509025271e-05, | |
| "loss": 0.0579, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.45065344749887337, | |
| "grad_norm": 0.18055088818073273, | |
| "learning_rate": 3.8718411552346575e-05, | |
| "loss": 0.0238, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4686795853988283, | |
| "grad_norm": 0.2409915030002594, | |
| "learning_rate": 3.826714801444044e-05, | |
| "loss": 0.0179, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.48670572329878325, | |
| "grad_norm": 10.743939399719238, | |
| "learning_rate": 3.78158844765343e-05, | |
| "loss": 0.0578, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5047318611987381, | |
| "grad_norm": 20.40981674194336, | |
| "learning_rate": 3.7364620938628155e-05, | |
| "loss": 0.0667, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5227579990986931, | |
| "grad_norm": 0.8752731680870056, | |
| "learning_rate": 3.6913357400722025e-05, | |
| "loss": 0.0312, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.540784136998648, | |
| "grad_norm": 4.817637920379639, | |
| "learning_rate": 3.646209386281589e-05, | |
| "loss": 0.0517, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.558810274898603, | |
| "grad_norm": 6.971864700317383, | |
| "learning_rate": 3.601083032490975e-05, | |
| "loss": 0.0344, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5768364127985579, | |
| "grad_norm": 0.742476224899292, | |
| "learning_rate": 3.555956678700361e-05, | |
| "loss": 0.0561, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5948625506985128, | |
| "grad_norm": 0.7727406024932861, | |
| "learning_rate": 3.5108303249097474e-05, | |
| "loss": 0.0617, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6128886885984678, | |
| "grad_norm": 0.6510533094406128, | |
| "learning_rate": 3.4657039711191336e-05, | |
| "loss": 0.0551, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "grad_norm": 4.241283893585205, | |
| "learning_rate": 3.42057761732852e-05, | |
| "loss": 0.026, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6489409643983777, | |
| "grad_norm": 0.18860740959644318, | |
| "learning_rate": 3.375451263537907e-05, | |
| "loss": 0.0367, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6669671022983326, | |
| "grad_norm": 0.13881151378154755, | |
| "learning_rate": 3.330324909747293e-05, | |
| "loss": 0.0434, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6849932401982876, | |
| "grad_norm": 0.45671743154525757, | |
| "learning_rate": 3.2851985559566786e-05, | |
| "loss": 0.049, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7030193780982424, | |
| "grad_norm": 0.5025729537010193, | |
| "learning_rate": 3.240072202166065e-05, | |
| "loss": 0.0266, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7210455159981974, | |
| "grad_norm": 0.3955366611480713, | |
| "learning_rate": 3.194945848375451e-05, | |
| "loss": 0.0264, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7390716538981523, | |
| "grad_norm": 11.814117431640625, | |
| "learning_rate": 3.149819494584837e-05, | |
| "loss": 0.0495, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7570977917981072, | |
| "grad_norm": 10.024807929992676, | |
| "learning_rate": 3.104693140794224e-05, | |
| "loss": 0.0262, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7751239296980622, | |
| "grad_norm": 0.23220416903495789, | |
| "learning_rate": 3.0595667870036104e-05, | |
| "loss": 0.0826, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7931500675980171, | |
| "grad_norm": 1.059012532234192, | |
| "learning_rate": 3.0144404332129967e-05, | |
| "loss": 0.0323, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8111762054979721, | |
| "grad_norm": 5.872659683227539, | |
| "learning_rate": 2.969314079422383e-05, | |
| "loss": 0.0616, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.829202343397927, | |
| "grad_norm": 0.3091956377029419, | |
| "learning_rate": 2.924187725631769e-05, | |
| "loss": 0.0439, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.847228481297882, | |
| "grad_norm": 0.7430059909820557, | |
| "learning_rate": 2.879061371841155e-05, | |
| "loss": 0.0758, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.8652546191978369, | |
| "grad_norm": 0.5902143120765686, | |
| "learning_rate": 2.8339350180505413e-05, | |
| "loss": 0.0448, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8832807570977917, | |
| "grad_norm": 5.876249313354492, | |
| "learning_rate": 2.7888086642599282e-05, | |
| "loss": 0.0356, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9013068949977467, | |
| "grad_norm": 3.5948667526245117, | |
| "learning_rate": 2.7436823104693144e-05, | |
| "loss": 0.053, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9193330328977016, | |
| "grad_norm": 9.958101272583008, | |
| "learning_rate": 2.6985559566787007e-05, | |
| "loss": 0.0234, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.9373591707976566, | |
| "grad_norm": 0.7074028253555298, | |
| "learning_rate": 2.6534296028880866e-05, | |
| "loss": 0.052, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9553853086976115, | |
| "grad_norm": 0.37822696566581726, | |
| "learning_rate": 2.6083032490974728e-05, | |
| "loss": 0.0517, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9734114465975665, | |
| "grad_norm": 0.5355275869369507, | |
| "learning_rate": 2.563176895306859e-05, | |
| "loss": 0.0327, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9914375844975214, | |
| "grad_norm": 0.4926086366176605, | |
| "learning_rate": 2.518050541516246e-05, | |
| "loss": 0.042, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.04069153591990471, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 142.0447, | |
| "eval_samples_per_second": 32.898, | |
| "eval_steps_per_second": 4.118, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.0090130689499774, | |
| "grad_norm": 0.7699225544929504, | |
| "learning_rate": 2.472924187725632e-05, | |
| "loss": 0.0093, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.0270392068499323, | |
| "grad_norm": 2.445814609527588, | |
| "learning_rate": 2.427797833935018e-05, | |
| "loss": 0.0348, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.0450653447498874, | |
| "grad_norm": 0.38662949204444885, | |
| "learning_rate": 2.3826714801444043e-05, | |
| "loss": 0.0165, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.0630914826498423, | |
| "grad_norm": 0.1346297264099121, | |
| "learning_rate": 2.3375451263537906e-05, | |
| "loss": 0.0759, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.0811176205497972, | |
| "grad_norm": 12.862547874450684, | |
| "learning_rate": 2.292418772563177e-05, | |
| "loss": 0.0296, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.099143758449752, | |
| "grad_norm": 3.661592960357666, | |
| "learning_rate": 2.2472924187725634e-05, | |
| "loss": 0.0182, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.117169896349707, | |
| "grad_norm": 4.039327144622803, | |
| "learning_rate": 2.2021660649819496e-05, | |
| "loss": 0.0484, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.135196034249662, | |
| "grad_norm": 7.463378429412842, | |
| "learning_rate": 2.157039711191336e-05, | |
| "loss": 0.051, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.153222172149617, | |
| "grad_norm": 4.8609724044799805, | |
| "learning_rate": 2.111913357400722e-05, | |
| "loss": 0.0641, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.1712483100495719, | |
| "grad_norm": 10.486072540283203, | |
| "learning_rate": 2.0667870036101083e-05, | |
| "loss": 0.0626, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.1892744479495267, | |
| "grad_norm": 0.24464073777198792, | |
| "learning_rate": 2.0216606498194946e-05, | |
| "loss": 0.0193, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.2073005858494819, | |
| "grad_norm": 3.8871383666992188, | |
| "learning_rate": 1.976534296028881e-05, | |
| "loss": 0.0303, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.2253267237494367, | |
| "grad_norm": 0.4887860119342804, | |
| "learning_rate": 1.9314079422382674e-05, | |
| "loss": 0.0447, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.2433528616493916, | |
| "grad_norm": 0.1695612519979477, | |
| "learning_rate": 1.8862815884476533e-05, | |
| "loss": 0.0327, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.2613789995493465, | |
| "grad_norm": 9.335827827453613, | |
| "learning_rate": 1.84115523465704e-05, | |
| "loss": 0.0186, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.2794051374493014, | |
| "grad_norm": 0.8768898248672485, | |
| "learning_rate": 1.796028880866426e-05, | |
| "loss": 0.0582, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.2974312753492563, | |
| "grad_norm": 0.18744328618049622, | |
| "learning_rate": 1.7509025270758123e-05, | |
| "loss": 0.0019, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.3154574132492114, | |
| "grad_norm": 6.990164756774902, | |
| "learning_rate": 1.7057761732851986e-05, | |
| "loss": 0.0601, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.3334835511491663, | |
| "grad_norm": 7.397508144378662, | |
| "learning_rate": 1.6606498194945848e-05, | |
| "loss": 0.0841, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.3515096890491212, | |
| "grad_norm": 0.5567547082901001, | |
| "learning_rate": 1.615523465703971e-05, | |
| "loss": 0.0356, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.3695358269490763, | |
| "grad_norm": 0.42192819714546204, | |
| "learning_rate": 1.5703971119133576e-05, | |
| "loss": 0.0094, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.3875619648490312, | |
| "grad_norm": 5.491224765777588, | |
| "learning_rate": 1.5252707581227438e-05, | |
| "loss": 0.0319, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.405588102748986, | |
| "grad_norm": 0.10327385365962982, | |
| "learning_rate": 1.4801444043321299e-05, | |
| "loss": 0.0282, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.423614240648941, | |
| "grad_norm": 0.2903471887111664, | |
| "learning_rate": 1.4350180505415165e-05, | |
| "loss": 0.0444, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.4416403785488958, | |
| "grad_norm": 5.516872882843018, | |
| "learning_rate": 1.3898916967509026e-05, | |
| "loss": 0.068, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.4596665164488507, | |
| "grad_norm": 0.15897555649280548, | |
| "learning_rate": 1.3447653429602888e-05, | |
| "loss": 0.0011, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.4776926543488058, | |
| "grad_norm": 9.496695518493652, | |
| "learning_rate": 1.299638989169675e-05, | |
| "loss": 0.0535, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.4957187922487607, | |
| "grad_norm": 0.23458808660507202, | |
| "learning_rate": 1.2545126353790614e-05, | |
| "loss": 0.0353, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.5137449301487156, | |
| "grad_norm": 6.693735599517822, | |
| "learning_rate": 1.2093862815884477e-05, | |
| "loss": 0.0235, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.5317710680486707, | |
| "grad_norm": 7.055171966552734, | |
| "learning_rate": 1.164259927797834e-05, | |
| "loss": 0.0315, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.5497972059486256, | |
| "grad_norm": 0.1647280752658844, | |
| "learning_rate": 1.1191335740072201e-05, | |
| "loss": 0.041, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.5678233438485805, | |
| "grad_norm": 31.603675842285156, | |
| "learning_rate": 1.0740072202166066e-05, | |
| "loss": 0.0637, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.5858494817485354, | |
| "grad_norm": 5.558256149291992, | |
| "learning_rate": 1.028880866425993e-05, | |
| "loss": 0.0534, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.6038756196484902, | |
| "grad_norm": 4.783972263336182, | |
| "learning_rate": 9.83754512635379e-06, | |
| "loss": 0.0382, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.6219017575484451, | |
| "grad_norm": 5.161861419677734, | |
| "learning_rate": 9.386281588447654e-06, | |
| "loss": 0.0454, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.6399278954484002, | |
| "grad_norm": 5.796766757965088, | |
| "learning_rate": 8.935018050541517e-06, | |
| "loss": 0.0221, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.6579540333483551, | |
| "grad_norm": 0.6868887543678284, | |
| "learning_rate": 8.483754512635379e-06, | |
| "loss": 0.028, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.67598017124831, | |
| "grad_norm": 0.27316200733184814, | |
| "learning_rate": 8.032490974729243e-06, | |
| "loss": 0.0234, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.694006309148265, | |
| "grad_norm": 0.4934704303741455, | |
| "learning_rate": 7.581227436823105e-06, | |
| "loss": 0.0171, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.71203244704822, | |
| "grad_norm": 0.4003954231739044, | |
| "learning_rate": 7.129963898916968e-06, | |
| "loss": 0.0159, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.7300585849481749, | |
| "grad_norm": 0.2824706733226776, | |
| "learning_rate": 6.678700361010831e-06, | |
| "loss": 0.0853, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.7480847228481298, | |
| "grad_norm": 0.14133542776107788, | |
| "learning_rate": 6.227436823104693e-06, | |
| "loss": 0.032, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.7661108607480847, | |
| "grad_norm": 0.30818939208984375, | |
| "learning_rate": 5.776173285198557e-06, | |
| "loss": 0.0258, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.7841369986480395, | |
| "grad_norm": 0.1608804315328598, | |
| "learning_rate": 5.324909747292419e-06, | |
| "loss": 0.0598, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.8021631365479944, | |
| "grad_norm": 33.14769744873047, | |
| "learning_rate": 4.873646209386281e-06, | |
| "loss": 0.0409, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.8201892744479495, | |
| "grad_norm": 0.9574671983718872, | |
| "learning_rate": 4.422382671480145e-06, | |
| "loss": 0.0245, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.8382154123479044, | |
| "grad_norm": 0.41375967860221863, | |
| "learning_rate": 3.971119133574008e-06, | |
| "loss": 0.0377, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.8562415502478595, | |
| "grad_norm": 3.852210760116577, | |
| "learning_rate": 3.51985559566787e-06, | |
| "loss": 0.0358, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.8742676881478144, | |
| "grad_norm": 7.285823822021484, | |
| "learning_rate": 3.068592057761733e-06, | |
| "loss": 0.0617, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.8922938260477693, | |
| "grad_norm": 0.22026002407073975, | |
| "learning_rate": 2.6173285198555957e-06, | |
| "loss": 0.0423, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.9103199639477242, | |
| "grad_norm": 0.30483102798461914, | |
| "learning_rate": 2.1660649819494585e-06, | |
| "loss": 0.0083, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.928346101847679, | |
| "grad_norm": 2.322383165359497, | |
| "learning_rate": 1.7148014440433215e-06, | |
| "loss": 0.0112, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.946372239747634, | |
| "grad_norm": 0.2074129730463028, | |
| "learning_rate": 1.263537906137184e-06, | |
| "loss": 0.0314, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.9643983776475888, | |
| "grad_norm": 0.543554425239563, | |
| "learning_rate": 8.122743682310469e-07, | |
| "loss": 0.0244, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.982424515547544, | |
| "grad_norm": 0.8434537053108215, | |
| "learning_rate": 3.610108303249098e-07, | |
| "loss": 0.0453, | |
| "step": 1100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1108, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 7.68611172962304e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |