| { | |
| "best_metric": 0.39477089047431946, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 2.002844950213371, | |
| "eval_steps": 25, | |
| "global_step": 132, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015173067804646752, | |
| "grad_norm": 17.388423919677734, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 30.457, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015173067804646752, | |
| "eval_loss": 0.8401981592178345, | |
| "eval_runtime": 4.1216, | |
| "eval_samples_per_second": 12.131, | |
| "eval_steps_per_second": 12.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030346135609293504, | |
| "grad_norm": 10.178067207336426, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 30.335, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04551920341394026, | |
| "grad_norm": 10.258736610412598, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 28.3123, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06069227121858701, | |
| "grad_norm": 10.296838760375977, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 27.9287, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07586533902323377, | |
| "grad_norm": 12.867237091064453, | |
| "learning_rate": 0.00015, | |
| "loss": 25.3598, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09103840682788052, | |
| "grad_norm": 12.431685447692871, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 22.2146, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10621147463252727, | |
| "grad_norm": 13.944931983947754, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 19.7453, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12138454243717402, | |
| "grad_norm": 23.274085998535156, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 19.6562, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13655761024182078, | |
| "grad_norm": 23.921234130859375, | |
| "learning_rate": 0.00027, | |
| "loss": 15.7789, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15173067804646753, | |
| "grad_norm": 31.0799560546875, | |
| "learning_rate": 0.0003, | |
| "loss": 18.6639, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16690374585111428, | |
| "grad_norm": 27.46465301513672, | |
| "learning_rate": 0.00029995027012714694, | |
| "loss": 15.0467, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18207681365576103, | |
| "grad_norm": 21.228845596313477, | |
| "learning_rate": 0.00029980111348272456, | |
| "loss": 16.0005, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19724988146040778, | |
| "grad_norm": 17.686410903930664, | |
| "learning_rate": 0.00029955262896727894, | |
| "loss": 15.2921, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.21242294926505453, | |
| "grad_norm": 16.29988670349121, | |
| "learning_rate": 0.00029920498134218835, | |
| "loss": 14.4487, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.22759601706970128, | |
| "grad_norm": 18.719757080078125, | |
| "learning_rate": 0.0002987584011204152, | |
| "loss": 12.782, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.24276908487434803, | |
| "grad_norm": 19.07723617553711, | |
| "learning_rate": 0.0002982131844136615, | |
| "loss": 12.9955, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2579421526789948, | |
| "grad_norm": 45.31391143798828, | |
| "learning_rate": 0.0002975696927360274, | |
| "loss": 23.8883, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.27311522048364156, | |
| "grad_norm": 27.076311111450195, | |
| "learning_rate": 0.0002968283527643036, | |
| "loss": 21.5994, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 15.616254806518555, | |
| "learning_rate": 0.00029598965605505737, | |
| "loss": 18.592, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.30346135609293506, | |
| "grad_norm": 18.812135696411133, | |
| "learning_rate": 0.000295054158718698, | |
| "loss": 16.3996, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3186344238975818, | |
| "grad_norm": 14.7747163772583, | |
| "learning_rate": 0.0002940224810507402, | |
| "loss": 16.5481, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.33380749170222856, | |
| "grad_norm": 13.129542350769043, | |
| "learning_rate": 0.00029289530712050735, | |
| "loss": 14.6397, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3489805595068753, | |
| "grad_norm": 13.189936637878418, | |
| "learning_rate": 0.0002916733843175492, | |
| "loss": 14.889, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.36415362731152207, | |
| "grad_norm": 11.230732917785645, | |
| "learning_rate": 0.000290357522856074, | |
| "loss": 13.3495, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3793266951161688, | |
| "grad_norm": 10.45602798461914, | |
| "learning_rate": 0.0002889485952377242, | |
| "loss": 13.97, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3793266951161688, | |
| "eval_loss": 0.4615178406238556, | |
| "eval_runtime": 4.1945, | |
| "eval_samples_per_second": 11.92, | |
| "eval_steps_per_second": 11.92, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39449976292081557, | |
| "grad_norm": 9.400847434997559, | |
| "learning_rate": 0.0002874475356730507, | |
| "loss": 13.0953, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4096728307254623, | |
| "grad_norm": 10.215126037597656, | |
| "learning_rate": 0.0002858553394620707, | |
| "loss": 14.0127, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.42484589853010907, | |
| "grad_norm": 8.064435958862305, | |
| "learning_rate": 0.0002841730623343193, | |
| "loss": 12.4928, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4400189663347558, | |
| "grad_norm": 10.052416801452637, | |
| "learning_rate": 0.00028240181974883207, | |
| "loss": 14.195, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.45519203413940257, | |
| "grad_norm": 9.893036842346191, | |
| "learning_rate": 0.00028054278615452326, | |
| "loss": 12.9534, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4703651019440493, | |
| "grad_norm": 9.579009056091309, | |
| "learning_rate": 0.0002785971942114498, | |
| "loss": 11.9894, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.48553816974869607, | |
| "grad_norm": 10.615213394165039, | |
| "learning_rate": 0.0002765663339734778, | |
| "loss": 11.5054, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5007112375533428, | |
| "grad_norm": 18.542469024658203, | |
| "learning_rate": 0.0002744515520328928, | |
| "loss": 17.3979, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5158843053579896, | |
| "grad_norm": 15.90185260772705, | |
| "learning_rate": 0.00027225425062752165, | |
| "loss": 16.0495, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5310573731626363, | |
| "grad_norm": 12.792567253112793, | |
| "learning_rate": 0.0002699758867109579, | |
| "loss": 15.2643, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5462304409672831, | |
| "grad_norm": 9.845219612121582, | |
| "learning_rate": 0.0002676179709865066, | |
| "loss": 13.5142, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 12.22781753540039, | |
| "learning_rate": 0.00026518206690549, | |
| "loss": 14.2178, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5765765765765766, | |
| "grad_norm": 10.745471954345703, | |
| "learning_rate": 0.0002626697896305779, | |
| "loss": 12.9431, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5917496443812233, | |
| "grad_norm": 10.67679500579834, | |
| "learning_rate": 0.00026008280496482984, | |
| "loss": 15.1994, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6069227121858701, | |
| "grad_norm": 8.882881164550781, | |
| "learning_rate": 0.000257422828247159, | |
| "loss": 14.0005, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6220957799905168, | |
| "grad_norm": 9.826411247253418, | |
| "learning_rate": 0.00025469162321495147, | |
| "loss": 12.5264, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6372688477951636, | |
| "grad_norm": 8.515768051147461, | |
| "learning_rate": 0.00025189100083459397, | |
| "loss": 11.0442, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6524419155998104, | |
| "grad_norm": 9.0559720993042, | |
| "learning_rate": 0.00024902281810068475, | |
| "loss": 11.7402, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6676149834044571, | |
| "grad_norm": 9.556861877441406, | |
| "learning_rate": 0.0002460889768047263, | |
| "loss": 12.4502, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6827880512091038, | |
| "grad_norm": 8.837124824523926, | |
| "learning_rate": 0.0002430914222741134, | |
| "loss": 12.4087, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6979611190137506, | |
| "grad_norm": 15.878302574157715, | |
| "learning_rate": 0.00024003214208225522, | |
| "loss": 11.0582, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7131341868183974, | |
| "grad_norm": 9.87769603729248, | |
| "learning_rate": 0.00023691316473068452, | |
| "loss": 11.3891, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7283072546230441, | |
| "grad_norm": 8.35490608215332, | |
| "learning_rate": 0.00023373655830402968, | |
| "loss": 9.9121, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7434803224276908, | |
| "grad_norm": 17.935434341430664, | |
| "learning_rate": 0.00023050442909874007, | |
| "loss": 16.9965, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7586533902323376, | |
| "grad_norm": 15.285179138183594, | |
| "learning_rate": 0.00022721892022647462, | |
| "loss": 16.4137, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7586533902323376, | |
| "eval_loss": 0.4162628650665283, | |
| "eval_runtime": 4.1979, | |
| "eval_samples_per_second": 11.911, | |
| "eval_steps_per_second": 11.911, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7738264580369844, | |
| "grad_norm": 11.381631851196289, | |
| "learning_rate": 0.00022388221019307967, | |
| "loss": 14.1246, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7889995258416311, | |
| "grad_norm": 10.287455558776855, | |
| "learning_rate": 0.000220496511454098, | |
| "loss": 13.1531, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8041725936462779, | |
| "grad_norm": 10.540827751159668, | |
| "learning_rate": 0.00021706406894776709, | |
| "loss": 12.6342, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.8193456614509246, | |
| "grad_norm": 10.495640754699707, | |
| "learning_rate": 0.0002135871586064791, | |
| "loss": 13.6827, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8345187292555714, | |
| "grad_norm": 12.297253608703613, | |
| "learning_rate": 0.00021006808584768998, | |
| "loss": 13.6184, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8496917970602181, | |
| "grad_norm": 10.440007209777832, | |
| "learning_rate": 0.00020650918404527775, | |
| "loss": 12.9478, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 10.427011489868164, | |
| "learning_rate": 0.00020291281298236423, | |
| "loss": 12.4868, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8800379326695116, | |
| "grad_norm": 9.420439720153809, | |
| "learning_rate": 0.00019928135728662522, | |
| "loss": 13.8967, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.8952110004741584, | |
| "grad_norm": 10.802536964416504, | |
| "learning_rate": 0.0001956172248491277, | |
| "loss": 14.1609, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.9103840682788051, | |
| "grad_norm": 8.980121612548828, | |
| "learning_rate": 0.00019192284522774142, | |
| "loss": 13.0885, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9255571360834519, | |
| "grad_norm": 8.586287498474121, | |
| "learning_rate": 0.00018820066803618428, | |
| "loss": 10.7247, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.9407302038880986, | |
| "grad_norm": 10.254575729370117, | |
| "learning_rate": 0.00018445316131976934, | |
| "loss": 12.6883, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.9559032716927454, | |
| "grad_norm": 10.308297157287598, | |
| "learning_rate": 0.00018068280991893014, | |
| "loss": 10.7828, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.9710763394973921, | |
| "grad_norm": 10.438807487487793, | |
| "learning_rate": 0.00017689211382161034, | |
| "loss": 9.4578, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.9862494073020389, | |
| "grad_norm": 16.487628936767578, | |
| "learning_rate": 0.00017308358650560928, | |
| "loss": 13.0305, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.0014224751066856, | |
| "grad_norm": 8.836454391479492, | |
| "learning_rate": 0.00016925975327198266, | |
| "loss": 12.8189, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0165955429113325, | |
| "grad_norm": 10.768722534179688, | |
| "learning_rate": 0.00016542314957060405, | |
| "loss": 14.4475, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.0317686107159791, | |
| "grad_norm": 8.652929306030273, | |
| "learning_rate": 0.00016157631931899697, | |
| "loss": 15.0635, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.0469416785206258, | |
| "grad_norm": 7.712925910949707, | |
| "learning_rate": 0.00015772181321555196, | |
| "loss": 12.3852, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.0621147463252727, | |
| "grad_norm": 9.161529541015625, | |
| "learning_rate": 0.0001538621870482483, | |
| "loss": 12.3397, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0772878141299194, | |
| "grad_norm": 8.765726089477539, | |
| "learning_rate": 0.00015, | |
| "loss": 11.8658, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.0924608819345663, | |
| "grad_norm": 8.678772926330566, | |
| "learning_rate": 0.00014613781295175172, | |
| "loss": 11.8749, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.107633949739213, | |
| "grad_norm": 8.968255996704102, | |
| "learning_rate": 0.000142278186784448, | |
| "loss": 11.2309, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.1228070175438596, | |
| "grad_norm": 8.212029457092285, | |
| "learning_rate": 0.00013842368068100303, | |
| "loss": 9.0183, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.1379800853485065, | |
| "grad_norm": 7.790862560272217, | |
| "learning_rate": 0.00013457685042939592, | |
| "loss": 10.4468, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.1379800853485065, | |
| "eval_loss": 0.39976993203163147, | |
| "eval_runtime": 4.1988, | |
| "eval_samples_per_second": 11.908, | |
| "eval_steps_per_second": 11.908, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.1531531531531531, | |
| "grad_norm": 7.495136260986328, | |
| "learning_rate": 0.00013074024672801731, | |
| "loss": 9.8966, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.1683262209577998, | |
| "grad_norm": 8.63007640838623, | |
| "learning_rate": 0.0001269164134943907, | |
| "loss": 9.9346, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.1834992887624467, | |
| "grad_norm": 9.116193771362305, | |
| "learning_rate": 0.00012310788617838966, | |
| "loss": 11.3677, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.1986723565670934, | |
| "grad_norm": 9.81653881072998, | |
| "learning_rate": 0.0001193171900810699, | |
| "loss": 10.2669, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.2138454243717403, | |
| "grad_norm": 10.604126930236816, | |
| "learning_rate": 0.00011554683868023067, | |
| "loss": 10.7322, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.229018492176387, | |
| "grad_norm": 10.463966369628906, | |
| "learning_rate": 0.0001117993319638157, | |
| "loss": 9.2057, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.2441915599810336, | |
| "grad_norm": 9.727025985717773, | |
| "learning_rate": 0.00010807715477225858, | |
| "loss": 8.6479, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.2593646277856805, | |
| "grad_norm": 13.668055534362793, | |
| "learning_rate": 0.00010438277515087233, | |
| "loss": 14.4636, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.2745376955903271, | |
| "grad_norm": 11.730889320373535, | |
| "learning_rate": 0.00010071864271337478, | |
| "loss": 14.0765, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.2897107633949738, | |
| "grad_norm": 11.76871109008789, | |
| "learning_rate": 9.708718701763577e-05, | |
| "loss": 12.6621, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.3048838311996207, | |
| "grad_norm": 12.476866722106934, | |
| "learning_rate": 9.34908159547222e-05, | |
| "loss": 12.6543, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.3200568990042674, | |
| "grad_norm": 9.014403343200684, | |
| "learning_rate": 8.993191415231e-05, | |
| "loss": 10.5078, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.3352299668089143, | |
| "grad_norm": 8.82985782623291, | |
| "learning_rate": 8.641284139352091e-05, | |
| "loss": 10.1313, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.350403034613561, | |
| "grad_norm": 9.604599952697754, | |
| "learning_rate": 8.293593105223287e-05, | |
| "loss": 10.9247, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.3655761024182076, | |
| "grad_norm": 8.465795516967773, | |
| "learning_rate": 7.950348854590204e-05, | |
| "loss": 9.671, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3807491702228545, | |
| "grad_norm": 8.575054168701172, | |
| "learning_rate": 7.611778980692035e-05, | |
| "loss": 10.2636, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.3959222380275011, | |
| "grad_norm": 7.928877830505371, | |
| "learning_rate": 7.278107977352543e-05, | |
| "loss": 8.982, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.411095305832148, | |
| "grad_norm": 9.111271858215332, | |
| "learning_rate": 6.949557090125994e-05, | |
| "loss": 9.8091, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.4262683736367947, | |
| "grad_norm": 8.69306468963623, | |
| "learning_rate": 6.626344169597031e-05, | |
| "loss": 9.7754, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.4414414414414414, | |
| "grad_norm": 8.90804386138916, | |
| "learning_rate": 6.308683526931545e-05, | |
| "loss": 9.7669, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.4566145092460883, | |
| "grad_norm": 9.999079704284668, | |
| "learning_rate": 5.996785791774478e-05, | |
| "loss": 9.0066, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.471787577050735, | |
| "grad_norm": 9.848721504211426, | |
| "learning_rate": 5.690857772588657e-05, | |
| "loss": 8.0642, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.4869606448553818, | |
| "grad_norm": 10.121479988098145, | |
| "learning_rate": 5.391102319527373e-05, | |
| "loss": 8.1109, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.5021337126600285, | |
| "grad_norm": 11.15321159362793, | |
| "learning_rate": 5.0977181899315214e-05, | |
| "loss": 15.3952, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.5173067804646752, | |
| "grad_norm": 10.735111236572266, | |
| "learning_rate": 4.8108999165406026e-05, | |
| "loss": 14.3337, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5173067804646752, | |
| "eval_loss": 0.39477089047431946, | |
| "eval_runtime": 4.2024, | |
| "eval_samples_per_second": 11.898, | |
| "eval_steps_per_second": 11.898, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5324798482693218, | |
| "grad_norm": 8.945897102355957, | |
| "learning_rate": 4.5308376785048434e-05, | |
| "loss": 11.1062, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.5476529160739687, | |
| "grad_norm": 9.844161987304688, | |
| "learning_rate": 4.257717175284103e-05, | |
| "loss": 10.4609, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.5628259838786156, | |
| "grad_norm": 9.294745445251465, | |
| "learning_rate": 3.991719503517014e-05, | |
| "loss": 10.6322, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.5779990516832623, | |
| "grad_norm": 9.901968002319336, | |
| "learning_rate": 3.733021036942205e-05, | |
| "loss": 11.3513, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.593172119487909, | |
| "grad_norm": 9.366765975952148, | |
| "learning_rate": 3.481793309451e-05, | |
| "loss": 10.2632, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.6083451872925556, | |
| "grad_norm": 8.39588451385498, | |
| "learning_rate": 3.238202901349345e-05, | |
| "loss": 10.2529, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.6235182550972025, | |
| "grad_norm": 8.285764694213867, | |
| "learning_rate": 3.0024113289042094e-05, | |
| "loss": 9.9579, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.6386913229018494, | |
| "grad_norm": 8.389649391174316, | |
| "learning_rate": 2.774574937247831e-05, | |
| "loss": 10.3428, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.653864390706496, | |
| "grad_norm": 8.863457679748535, | |
| "learning_rate": 2.554844796710716e-05, | |
| "loss": 9.0607, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.6690374585111427, | |
| "grad_norm": 8.510146141052246, | |
| "learning_rate": 2.3433666026522153e-05, | |
| "loss": 9.3396, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 9.09020709991455, | |
| "learning_rate": 2.1402805788550138e-05, | |
| "loss": 9.223, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.6993835941204363, | |
| "grad_norm": 8.539032936096191, | |
| "learning_rate": 1.945721384547671e-05, | |
| "loss": 7.2793, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.714556661925083, | |
| "grad_norm": 9.459700584411621, | |
| "learning_rate": 1.759818025116787e-05, | |
| "loss": 7.6996, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.7297297297297298, | |
| "grad_norm": 11.580260276794434, | |
| "learning_rate": 1.5826937665680693e-05, | |
| "loss": 7.68, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.7449027975343765, | |
| "grad_norm": 8.748165130615234, | |
| "learning_rate": 1.4144660537929287e-05, | |
| "loss": 13.0615, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.7600758653390232, | |
| "grad_norm": 9.052087783813477, | |
| "learning_rate": 1.2552464326949302e-05, | |
| "loss": 13.9056, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.7752489331436698, | |
| "grad_norm": 9.413413047790527, | |
| "learning_rate": 1.105140476227575e-05, | |
| "loss": 13.1337, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.7904220009483167, | |
| "grad_norm": 8.633859634399414, | |
| "learning_rate": 9.64247714392597e-06, | |
| "loss": 11.1511, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.8055950687529636, | |
| "grad_norm": 7.859529972076416, | |
| "learning_rate": 8.32661568245081e-06, | |
| "loss": 10.06, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.8207681365576103, | |
| "grad_norm": 8.01181697845459, | |
| "learning_rate": 7.104692879492624e-06, | |
| "loss": 10.4743, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.835941204362257, | |
| "grad_norm": 9.660663604736328, | |
| "learning_rate": 5.977518949259735e-06, | |
| "loss": 11.0629, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.8511142721669036, | |
| "grad_norm": 8.536215782165527, | |
| "learning_rate": 4.945841281301943e-06, | |
| "loss": 10.3549, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.8662873399715505, | |
| "grad_norm": 8.264043807983398, | |
| "learning_rate": 4.010343944942618e-06, | |
| "loss": 9.8312, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.8814604077761974, | |
| "grad_norm": 8.763490676879883, | |
| "learning_rate": 3.1716472356963286e-06, | |
| "loss": 8.8429, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.896633475580844, | |
| "grad_norm": 9.253498077392578, | |
| "learning_rate": 2.430307263972547e-06, | |
| "loss": 10.0951, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.896633475580844, | |
| "eval_loss": 0.3835863471031189, | |
| "eval_runtime": 4.1958, | |
| "eval_samples_per_second": 11.917, | |
| "eval_steps_per_second": 11.917, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.9118065433854907, | |
| "grad_norm": 8.449151039123535, | |
| "learning_rate": 1.7868155863384415e-06, | |
| "loss": 9.1299, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.9269796111901374, | |
| "grad_norm": 8.359270095825195, | |
| "learning_rate": 1.2415988795847765e-06, | |
| "loss": 9.0518, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.9421526789947843, | |
| "grad_norm": 8.54788589477539, | |
| "learning_rate": 7.950186578116413e-07, | |
| "loss": 7.7242, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.9573257467994312, | |
| "grad_norm": 8.631213188171387, | |
| "learning_rate": 4.473710327209945e-07, | |
| "loss": 6.4852, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.9724988146040778, | |
| "grad_norm": 8.945975303649902, | |
| "learning_rate": 1.988865172754206e-07, | |
| "loss": 7.753, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.9876718824087245, | |
| "grad_norm": 8.31573486328125, | |
| "learning_rate": 4.972987285304375e-08, | |
| "loss": 11.2559, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.002844950213371, | |
| "grad_norm": 8.791767120361328, | |
| "learning_rate": 0.0, | |
| "loss": 9.4748, | |
| "step": 132 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 132, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "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": 1.8361400481231667e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |