| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9997807498355624, | |
| "eval_steps": 500, | |
| "global_step": 1140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008770006577504934, | |
| "grad_norm": 0.1337890625, | |
| "learning_rate": 1.7543859649122807e-06, | |
| "loss": 1.3755, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0043850032887524665, | |
| "grad_norm": 0.11865234375, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 1.37, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008770006577504933, | |
| "grad_norm": 0.12060546875, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 1.3508, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0131550098662574, | |
| "grad_norm": 0.1259765625, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.3572, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017540013155009866, | |
| "grad_norm": 0.1162109375, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 1.3438, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021925016443762334, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 1.3356, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0263100197325148, | |
| "grad_norm": 0.09814453125, | |
| "learning_rate": 5.2631578947368424e-05, | |
| "loss": 1.3111, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030695023021267268, | |
| "grad_norm": 0.095703125, | |
| "learning_rate": 6.140350877192983e-05, | |
| "loss": 1.2578, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03508002631001973, | |
| "grad_norm": 0.07421875, | |
| "learning_rate": 7.017543859649122e-05, | |
| "loss": 1.2393, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0394650295987722, | |
| "grad_norm": 0.064453125, | |
| "learning_rate": 7.894736842105263e-05, | |
| "loss": 1.2206, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04385003288752467, | |
| "grad_norm": 0.049072265625, | |
| "learning_rate": 8.771929824561403e-05, | |
| "loss": 1.1976, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.048235036176277134, | |
| "grad_norm": 0.044921875, | |
| "learning_rate": 9.649122807017544e-05, | |
| "loss": 1.1976, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0526200394650296, | |
| "grad_norm": 0.042724609375, | |
| "learning_rate": 0.00010526315789473685, | |
| "loss": 1.1789, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05700504275378206, | |
| "grad_norm": 0.042236328125, | |
| "learning_rate": 0.00011403508771929824, | |
| "loss": 1.1716, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.061390046042534535, | |
| "grad_norm": 0.044677734375, | |
| "learning_rate": 0.00012280701754385965, | |
| "loss": 1.1691, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.065775049331287, | |
| "grad_norm": 0.03857421875, | |
| "learning_rate": 0.00013157894736842108, | |
| "loss": 1.1533, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07016005262003946, | |
| "grad_norm": 0.041748046875, | |
| "learning_rate": 0.00014035087719298245, | |
| "loss": 1.1353, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07454505590879193, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 0.00014912280701754387, | |
| "loss": 1.1404, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0789300591975444, | |
| "grad_norm": 0.046142578125, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 1.1498, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08331506248629686, | |
| "grad_norm": 0.04443359375, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 1.1125, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.08770006577504934, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 0.00017543859649122806, | |
| "loss": 1.1447, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0920850690638018, | |
| "grad_norm": 0.05712890625, | |
| "learning_rate": 0.00018421052631578948, | |
| "loss": 1.1351, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.09647007235255427, | |
| "grad_norm": 0.04931640625, | |
| "learning_rate": 0.00019298245614035088, | |
| "loss": 1.1294, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.10085507564130673, | |
| "grad_norm": 0.05029296875, | |
| "learning_rate": 0.00019999953121394002, | |
| "loss": 1.1315, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.1052400789300592, | |
| "grad_norm": 0.060546875, | |
| "learning_rate": 0.00019998312416333227, | |
| "loss": 1.1284, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10962508221881166, | |
| "grad_norm": 0.04931640625, | |
| "learning_rate": 0.00019994328220474688, | |
| "loss": 1.136, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.11401008550756413, | |
| "grad_norm": 0.052001953125, | |
| "learning_rate": 0.0001998800146766861, | |
| "loss": 1.1213, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11839508879631659, | |
| "grad_norm": 0.064453125, | |
| "learning_rate": 0.00019979333640833947, | |
| "loss": 1.1152, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.12278009208506907, | |
| "grad_norm": 0.051513671875, | |
| "learning_rate": 0.00019968326771610797, | |
| "loss": 1.1193, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12716509537382154, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 0.0001995498343988421, | |
| "loss": 1.121, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.131550098662574, | |
| "grad_norm": 0.055419921875, | |
| "learning_rate": 0.00019939306773179497, | |
| "loss": 1.1291, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13593510195132646, | |
| "grad_norm": 0.04736328125, | |
| "learning_rate": 0.0001992130044592916, | |
| "loss": 1.122, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.14032010524007893, | |
| "grad_norm": 0.05078125, | |
| "learning_rate": 0.00019900968678611666, | |
| "loss": 1.1174, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1447051085288314, | |
| "grad_norm": 0.06298828125, | |
| "learning_rate": 0.00019878316236762196, | |
| "loss": 1.1205, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.14909011181758386, | |
| "grad_norm": 0.05615234375, | |
| "learning_rate": 0.00019853348429855672, | |
| "loss": 1.1086, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15347511510633632, | |
| "grad_norm": 0.053955078125, | |
| "learning_rate": 0.0001982607111006227, | |
| "loss": 1.1086, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1578601183950888, | |
| "grad_norm": 0.052978515625, | |
| "learning_rate": 0.0001979649067087574, | |
| "loss": 1.1202, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.16224512168384125, | |
| "grad_norm": 0.0517578125, | |
| "learning_rate": 0.00019764614045614836, | |
| "loss": 1.1248, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.16663012497259372, | |
| "grad_norm": 0.05615234375, | |
| "learning_rate": 0.00019730448705798239, | |
| "loss": 1.1231, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.17101512826134618, | |
| "grad_norm": 0.05810546875, | |
| "learning_rate": 0.00019694002659393305, | |
| "loss": 1.102, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.17540013155009868, | |
| "grad_norm": 0.056396484375, | |
| "learning_rate": 0.00019655284448939094, | |
| "loss": 1.1203, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17978513483885114, | |
| "grad_norm": 0.054931640625, | |
| "learning_rate": 0.00019614303149544102, | |
| "loss": 1.1073, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.1841701381276036, | |
| "grad_norm": 0.05029296875, | |
| "learning_rate": 0.00019571068366759143, | |
| "loss": 1.1082, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.18855514141635607, | |
| "grad_norm": 0.054443359375, | |
| "learning_rate": 0.00019525590234325933, | |
| "loss": 1.1114, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.19294014470510853, | |
| "grad_norm": 0.0576171875, | |
| "learning_rate": 0.00019477879411801844, | |
| "loss": 1.1007, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.197325147993861, | |
| "grad_norm": 0.051513671875, | |
| "learning_rate": 0.00019427947082061432, | |
| "loss": 1.0978, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.20171015128261346, | |
| "grad_norm": 0.05419921875, | |
| "learning_rate": 0.00019375804948675306, | |
| "loss": 1.0876, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.20609515457136593, | |
| "grad_norm": 0.050537109375, | |
| "learning_rate": 0.00019321465233166924, | |
| "loss": 1.1182, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.2104801578601184, | |
| "grad_norm": 0.05224609375, | |
| "learning_rate": 0.00019264940672148018, | |
| "loss": 1.0853, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.21486516114887086, | |
| "grad_norm": 0.05224609375, | |
| "learning_rate": 0.00019206244514333282, | |
| "loss": 1.1151, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.21925016443762332, | |
| "grad_norm": 0.050537109375, | |
| "learning_rate": 0.00019145390517435012, | |
| "loss": 1.111, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2236351677263758, | |
| "grad_norm": 0.048828125, | |
| "learning_rate": 0.00019082392944938466, | |
| "loss": 1.1262, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.22802017101512825, | |
| "grad_norm": 0.046875, | |
| "learning_rate": 0.00019017266562758659, | |
| "loss": 1.1036, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.23240517430388072, | |
| "grad_norm": 0.048095703125, | |
| "learning_rate": 0.00018950026635779397, | |
| "loss": 1.1162, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.23679017759263318, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 0.00018880688924275378, | |
| "loss": 1.102, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.24117518088138565, | |
| "grad_norm": 0.05419921875, | |
| "learning_rate": 0.00018809269680218136, | |
| "loss": 1.1, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.24556018417013814, | |
| "grad_norm": 0.050537109375, | |
| "learning_rate": 0.00018735785643466784, | |
| "loss": 1.1037, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2499451874588906, | |
| "grad_norm": 0.04931640625, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.0826, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.25433019074764307, | |
| "grad_norm": 0.053466796875, | |
| "learning_rate": 0.00018582692567100867, | |
| "loss": 1.1046, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.25871519403639553, | |
| "grad_norm": 0.05859375, | |
| "learning_rate": 0.0001850311941076346, | |
| "loss": 1.082, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.263100197325148, | |
| "grad_norm": 0.053955078125, | |
| "learning_rate": 0.00018421553219875658, | |
| "loss": 1.0945, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.26748520061390046, | |
| "grad_norm": 0.053955078125, | |
| "learning_rate": 0.00018338013112625587, | |
| "loss": 1.0985, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.27187020390265293, | |
| "grad_norm": 0.051513671875, | |
| "learning_rate": 0.00018252518669864936, | |
| "loss": 1.1186, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2762552071914054, | |
| "grad_norm": 0.0625, | |
| "learning_rate": 0.0001816508993051943, | |
| "loss": 1.1253, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.28064021048015786, | |
| "grad_norm": 0.05224609375, | |
| "learning_rate": 0.0001807574738689193, | |
| "loss": 1.0904, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.2850252137689103, | |
| "grad_norm": 0.0498046875, | |
| "learning_rate": 0.00017984511979859263, | |
| "loss": 1.109, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.2894102170576628, | |
| "grad_norm": 0.051513671875, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 1.1041, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.29379522034641525, | |
| "grad_norm": 0.052734375, | |
| "learning_rate": 0.00017796448552401825, | |
| "loss": 1.0927, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.2981802236351677, | |
| "grad_norm": 0.04931640625, | |
| "learning_rate": 0.00017699664611907072, | |
| "loss": 1.1041, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3025652269239202, | |
| "grad_norm": 0.0537109375, | |
| "learning_rate": 0.00017601075957535364, | |
| "loss": 1.1115, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.30695023021267265, | |
| "grad_norm": 0.047119140625, | |
| "learning_rate": 0.0001750070569734681, | |
| "loss": 1.1088, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3113352335014251, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 0.00017398577356989665, | |
| "loss": 1.0905, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.3157202367901776, | |
| "grad_norm": 0.04638671875, | |
| "learning_rate": 0.0001729471487418621, | |
| "loss": 1.1071, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.32010524007893004, | |
| "grad_norm": 0.052734375, | |
| "learning_rate": 0.00017189142593121993, | |
| "loss": 1.0872, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.3244902433676825, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 0.00017081885258739846, | |
| "loss": 1.1054, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.32887524665643497, | |
| "grad_norm": 0.049072265625, | |
| "learning_rate": 0.00016972968010939954, | |
| "loss": 1.1035, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.33326024994518744, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 0.0001686241637868734, | |
| "loss": 1.0976, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3376452532339399, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 0.00016750256274028152, | |
| "loss": 1.099, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.34203025652269237, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 0.00016636513986016213, | |
| "loss": 1.1267, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.34641525981144483, | |
| "grad_norm": 0.05224609375, | |
| "learning_rate": 0.0001652121617455113, | |
| "loss": 1.101, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.35080026310019735, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 0.00016404389864129533, | |
| "loss": 1.1005, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3551852663889498, | |
| "grad_norm": 0.049072265625, | |
| "learning_rate": 0.0001628606243751082, | |
| "loss": 1.0973, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.3595702696777023, | |
| "grad_norm": 0.04931640625, | |
| "learning_rate": 0.00016166261629298995, | |
| "loss": 1.1016, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.36395527296645475, | |
| "grad_norm": 0.05517578125, | |
| "learning_rate": 0.0001604501551944193, | |
| "loss": 1.0863, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.3683402762552072, | |
| "grad_norm": 0.05517578125, | |
| "learning_rate": 0.00015922352526649803, | |
| "loss": 1.1008, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3727252795439597, | |
| "grad_norm": 0.05517578125, | |
| "learning_rate": 0.0001579830140173403, | |
| "loss": 1.0999, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.37711028283271214, | |
| "grad_norm": 0.049072265625, | |
| "learning_rate": 0.00015672891220868432, | |
| "loss": 1.0944, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.3814952861214646, | |
| "grad_norm": 0.048095703125, | |
| "learning_rate": 0.00015546151378774086, | |
| "loss": 1.084, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.38588028941021707, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 0.00015418111581829574, | |
| "loss": 1.0957, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.39026529269896953, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 0.00015288801841108093, | |
| "loss": 1.0823, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.394650295987722, | |
| "grad_norm": 0.051025390625, | |
| "learning_rate": 0.00015158252465343242, | |
| "loss": 1.0925, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.39903529927647446, | |
| "grad_norm": 0.05029296875, | |
| "learning_rate": 0.00015026494053824982, | |
| "loss": 1.0917, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.40342030256522693, | |
| "grad_norm": 0.05029296875, | |
| "learning_rate": 0.00014893557489227517, | |
| "loss": 1.0935, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.4078053058539794, | |
| "grad_norm": 0.048095703125, | |
| "learning_rate": 0.00014759473930370736, | |
| "loss": 1.0795, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.41219030914273186, | |
| "grad_norm": 0.051025390625, | |
| "learning_rate": 0.00014624274804916958, | |
| "loss": 1.0943, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.4165753124314843, | |
| "grad_norm": 0.05322265625, | |
| "learning_rate": 0.00014487991802004623, | |
| "loss": 1.1022, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.4209603157202368, | |
| "grad_norm": 0.055419921875, | |
| "learning_rate": 0.00014350656864820733, | |
| "loss": 1.0849, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.42534531900898925, | |
| "grad_norm": 0.05224609375, | |
| "learning_rate": 0.00014212302183113732, | |
| "loss": 1.0865, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.4297303222977417, | |
| "grad_norm": 0.05224609375, | |
| "learning_rate": 0.00014072960185648577, | |
| "loss": 1.106, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.4341153255864942, | |
| "grad_norm": 0.04736328125, | |
| "learning_rate": 0.0001393266353260583, | |
| "loss": 1.0926, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.43850032887524665, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 0.00013791445107926478, | |
| "loss": 1.1091, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4428853321639991, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 0.0001364933801160428, | |
| "loss": 1.0858, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.4472703354527516, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 0.00013506375551927547, | |
| "loss": 1.0901, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.45165533874150404, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 0.0001336259123767203, | |
| "loss": 1.0852, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.4560403420302565, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 0.00013218018770246858, | |
| "loss": 1.0838, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.46042534531900897, | |
| "grad_norm": 0.052490234375, | |
| "learning_rate": 0.00013072692035795305, | |
| "loss": 1.0795, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.46481034860776144, | |
| "grad_norm": 0.048828125, | |
| "learning_rate": 0.0001292664509725226, | |
| "loss": 1.1038, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.4691953518965139, | |
| "grad_norm": 0.051513671875, | |
| "learning_rate": 0.00012779912186360268, | |
| "loss": 1.0937, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.47358035518526637, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 0.00012632527695645993, | |
| "loss": 1.08, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.47796535847401883, | |
| "grad_norm": 0.0498046875, | |
| "learning_rate": 0.00012484526170359012, | |
| "loss": 1.0642, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.4823503617627713, | |
| "grad_norm": 0.051513671875, | |
| "learning_rate": 0.00012335942300374788, | |
| "loss": 1.089, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.4867353650515238, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 0.0001218681091206376, | |
| "loss": 1.0893, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.4911203683402763, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 0.00012037166960128443, | |
| "loss": 1.0996, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.49550537162902875, | |
| "grad_norm": 0.04736328125, | |
| "learning_rate": 0.00011887045519410442, | |
| "loss": 1.0955, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.4998903749177812, | |
| "grad_norm": 0.050537109375, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 1.0904, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5042753782065337, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 0.00011585511022335142, | |
| "loss": 1.1074, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.5086603814952861, | |
| "grad_norm": 0.0498046875, | |
| "learning_rate": 0.00011434168642236964, | |
| "loss": 1.0855, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5130453847840386, | |
| "grad_norm": 0.052734375, | |
| "learning_rate": 0.00011282490109308633, | |
| "loss": 1.0872, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.5174303880727911, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 0.00011130510975274409, | |
| "loss": 1.0824, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.5218153913615435, | |
| "grad_norm": 0.049072265625, | |
| "learning_rate": 0.0001097826686231604, | |
| "loss": 1.1002, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.526200394650296, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 1.083, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5305853979390485, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 0.00010673126490530112, | |
| "loss": 1.1003, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.5349704012278009, | |
| "grad_norm": 0.049072265625, | |
| "learning_rate": 0.00010520301753137724, | |
| "loss": 1.0852, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.5393554045165534, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 0.00010367355062927726, | |
| "loss": 1.0904, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.5437404078053059, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 0.00010214322268866032, | |
| "loss": 1.0839, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.5481254110940583, | |
| "grad_norm": 0.053466796875, | |
| "learning_rate": 0.00010061239240100327, | |
| "loss": 1.079, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.5525104143828108, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 9.908141857552737e-05, | |
| "loss": 1.0987, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.5568954176715633, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 9.755066005509753e-05, | |
| "loss": 1.075, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.5612804209603157, | |
| "grad_norm": 0.04931640625, | |
| "learning_rate": 9.602047563211359e-05, | |
| "loss": 1.0803, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.5656654242490682, | |
| "grad_norm": 0.053466796875, | |
| "learning_rate": 9.449122396441345e-05, | |
| "loss": 1.1114, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.5700504275378206, | |
| "grad_norm": 0.048828125, | |
| "learning_rate": 9.296326349120785e-05, | |
| "loss": 1.0771, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.5744354308265731, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 9.143695234906611e-05, | |
| "loss": 1.0917, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.5788204341153256, | |
| "grad_norm": 0.049072265625, | |
| "learning_rate": 8.991264828797319e-05, | |
| "loss": 1.0843, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.583205437404078, | |
| "grad_norm": 0.0498046875, | |
| "learning_rate": 8.839070858747697e-05, | |
| "loss": 1.0863, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.5875904406928305, | |
| "grad_norm": 0.0517578125, | |
| "learning_rate": 8.687148997294621e-05, | |
| "loss": 1.086, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.591975443981583, | |
| "grad_norm": 0.05029296875, | |
| "learning_rate": 8.535534853195786e-05, | |
| "loss": 1.08, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.5963604472703354, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 8.384263963083453e-05, | |
| "loss": 1.0686, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.6007454505590879, | |
| "grad_norm": 0.051025390625, | |
| "learning_rate": 8.23337178313504e-05, | |
| "loss": 1.075, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.6051304538478404, | |
| "grad_norm": 0.052490234375, | |
| "learning_rate": 8.082893680762619e-05, | |
| "loss": 1.0926, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.6095154571365928, | |
| "grad_norm": 0.051025390625, | |
| "learning_rate": 7.932864926323161e-05, | |
| "loss": 1.079, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.6139004604253453, | |
| "grad_norm": 0.049072265625, | |
| "learning_rate": 7.783320684851614e-05, | |
| "loss": 1.0844, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6182854637140978, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 7.634296007818576e-05, | |
| "loss": 1.1056, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.6226704670028502, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 7.485825824914659e-05, | |
| "loss": 1.0851, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.6270554702916027, | |
| "grad_norm": 0.048828125, | |
| "learning_rate": 7.337944935863333e-05, | |
| "loss": 1.0786, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.6314404735803552, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 7.190688002264308e-05, | |
| "loss": 1.089, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.6358254768691076, | |
| "grad_norm": 0.05126953125, | |
| "learning_rate": 7.044089539469212e-05, | |
| "loss": 1.0826, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.6402104801578601, | |
| "grad_norm": 0.0517578125, | |
| "learning_rate": 6.898183908491617e-05, | |
| "loss": 1.1004, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.6445954834466125, | |
| "grad_norm": 0.050537109375, | |
| "learning_rate": 6.753005307953167e-05, | |
| "loss": 1.0722, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.648980486735365, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 6.608587766067852e-05, | |
| "loss": 1.0859, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.6533654900241175, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 6.464965132666163e-05, | |
| "loss": 1.1088, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.6577504933128699, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 6.322171071261071e-05, | |
| "loss": 1.0726, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6621354966016224, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 6.180239051157681e-05, | |
| "loss": 1.0897, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.6665204998903749, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 6.039202339608432e-05, | |
| "loss": 1.0972, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.6709055031791273, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 5.8990939940156e-05, | |
| "loss": 1.0884, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.6752905064678798, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 5.7599468541830356e-05, | |
| "loss": 1.086, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.6796755097566323, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 5.62179353461888e-05, | |
| "loss": 1.0921, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.6840605130453847, | |
| "grad_norm": 0.051025390625, | |
| "learning_rate": 5.484666416891109e-05, | |
| "loss": 1.0834, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.6884455163341372, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 5.3485976420376336e-05, | |
| "loss": 1.0827, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.6928305196228897, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 5.2136191030328455e-05, | |
| "loss": 1.0851, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.6972155229116422, | |
| "grad_norm": 0.0517578125, | |
| "learning_rate": 5.079762437312219e-05, | |
| "loss": 1.0834, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.7016005262003947, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 4.9470590193569044e-05, | |
| "loss": 1.1016, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7059855294891472, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 4.815539953339865e-05, | |
| "loss": 1.0686, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.7103705327778996, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 4.685236065835443e-05, | |
| "loss": 1.086, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.7147555360666521, | |
| "grad_norm": 0.0498046875, | |
| "learning_rate": 4.5561778985939366e-05, | |
| "loss": 1.0817, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.7191405393554046, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 4.4283957013829846e-05, | |
| "loss": 1.0837, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.723525542644157, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 4.301919424897338e-05, | |
| "loss": 1.0791, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.7279105459329095, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 4.176778713738787e-05, | |
| "loss": 1.0865, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.732295549221662, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 4.053002899467774e-05, | |
| "loss": 1.0842, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.7366805525104144, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 3.9306209937284346e-05, | |
| "loss": 1.0939, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.7410655557991669, | |
| "grad_norm": 0.048095703125, | |
| "learning_rate": 3.809661681448576e-05, | |
| "loss": 1.0941, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.7454505590879194, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 3.69015331411628e-05, | |
| "loss": 1.0664, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.7498355623766718, | |
| "grad_norm": 0.05029296875, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 1.0844, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.7542205656654243, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 3.455601113256073e-05, | |
| "loss": 1.1036, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.7586055689541767, | |
| "grad_norm": 0.048828125, | |
| "learning_rate": 3.340612256098316e-05, | |
| "loss": 1.0641, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.7629905722429292, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 1.087, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.7673755755316817, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 3.115343782416483e-05, | |
| "loss": 1.0992, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.7717605788204341, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 3.0051169662624225e-05, | |
| "loss": 1.0838, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.7761455821091866, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 2.89652967119336e-05, | |
| "loss": 1.0899, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.7805305853979391, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 2.789607348837153e-05, | |
| "loss": 1.0906, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.7849155886866915, | |
| "grad_norm": 0.04736328125, | |
| "learning_rate": 2.684375060570965e-05, | |
| "loss": 1.0897, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.789300591975444, | |
| "grad_norm": 0.04736328125, | |
| "learning_rate": 2.5808574716471856e-05, | |
| "loss": 1.0857, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.7936855952641965, | |
| "grad_norm": 0.050537109375, | |
| "learning_rate": 2.4790788454121584e-05, | |
| "loss": 1.0973, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.7980705985529489, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 2.379063037619146e-05, | |
| "loss": 1.0714, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.8024556018417014, | |
| "grad_norm": 0.048095703125, | |
| "learning_rate": 2.2808334908367914e-05, | |
| "loss": 1.0919, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.8068406051304539, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 2.184413228954468e-05, | |
| "loss": 1.082, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.8112256084192063, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 2.0898248517857256e-05, | |
| "loss": 1.091, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.8156106117079588, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 1.9970905297711606e-05, | |
| "loss": 1.0919, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.8199956149967113, | |
| "grad_norm": 0.050048828125, | |
| "learning_rate": 1.9062319987819067e-05, | |
| "loss": 1.0668, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.8243806182854637, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 1.8172705550250092e-05, | |
| "loss": 1.0912, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.8287656215742162, | |
| "grad_norm": 0.046630859375, | |
| "learning_rate": 1.7302270500518182e-05, | |
| "loss": 1.0886, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.8331506248629686, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 1.6451218858706374e-05, | |
| "loss": 1.0815, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.8375356281517211, | |
| "grad_norm": 0.0498046875, | |
| "learning_rate": 1.5619750101647114e-05, | |
| "loss": 1.1055, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.8419206314404736, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 1.4808059116167305e-05, | |
| "loss": 1.0854, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.846305634729226, | |
| "grad_norm": 0.048828125, | |
| "learning_rate": 1.4016336153408893e-05, | |
| "loss": 1.1044, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.8506906380179785, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 1.3244766784236307e-05, | |
| "loss": 1.103, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.855075641306731, | |
| "grad_norm": 0.048583984375, | |
| "learning_rate": 1.2493531855740625e-05, | |
| "loss": 1.0638, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.8594606445954834, | |
| "grad_norm": 0.047119140625, | |
| "learning_rate": 1.176280744885121e-05, | |
| "loss": 1.067, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.8638456478842359, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 1.1052764837064178e-05, | |
| "loss": 1.0787, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.8682306511729884, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 1.0363570446297999e-05, | |
| "loss": 1.0825, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.8726156544617408, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 9.695385815885016e-06, | |
| "loss": 1.0905, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.8770006577504933, | |
| "grad_norm": 0.048095703125, | |
| "learning_rate": 9.048367560708604e-06, | |
| "loss": 1.0723, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8813856610392458, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 8.422667334494249e-06, | |
| "loss": 1.1059, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.8857706643279982, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 7.818431794263836e-06, | |
| "loss": 1.1027, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.8901556676167507, | |
| "grad_norm": 0.048095703125, | |
| "learning_rate": 7.235802565960714e-06, | |
| "loss": 1.0733, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.8945406709055032, | |
| "grad_norm": 0.051025390625, | |
| "learning_rate": 6.674916211254289e-06, | |
| "loss": 1.0807, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.8989256741942556, | |
| "grad_norm": 0.05810546875, | |
| "learning_rate": 6.1359041955315725e-06, | |
| "loss": 1.0729, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.9033106774830081, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 5.618892857083069e-06, | |
| "loss": 1.0816, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.9076956807717605, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 5.124003377490582e-06, | |
| "loss": 1.0853, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.912080684060513, | |
| "grad_norm": 0.049560546875, | |
| "learning_rate": 4.65135175322361e-06, | |
| "loss": 1.0829, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.9164656873492655, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 4.20104876845111e-06, | |
| "loss": 1.0797, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.9208506906380179, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 3.7731999690749585e-06, | |
| "loss": 1.0908, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.9252356939267704, | |
| "grad_norm": 0.04736328125, | |
| "learning_rate": 3.367905637991142e-06, | |
| "loss": 1.0784, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.9296206972155229, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 2.9852607715846193e-06, | |
| "loss": 1.101, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.9340057005042753, | |
| "grad_norm": 0.048095703125, | |
| "learning_rate": 2.6253550574632303e-06, | |
| "loss": 1.1063, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.9383907037930278, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 2.288272853436013e-06, | |
| "loss": 1.0768, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.9427757070817803, | |
| "grad_norm": 0.049072265625, | |
| "learning_rate": 1.974093167740565e-06, | |
| "loss": 1.0755, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.9471607103705327, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 1.6828896405244988e-06, | |
| "loss": 1.0714, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.9515457136592852, | |
| "grad_norm": 0.047119140625, | |
| "learning_rate": 1.4147305265850175e-06, | |
| "loss": 1.085, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.9559307169480377, | |
| "grad_norm": 0.047119140625, | |
| "learning_rate": 1.1696786793707781e-06, | |
| "loss": 1.0816, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.9603157202367901, | |
| "grad_norm": 0.046875, | |
| "learning_rate": 9.477915362496758e-07, | |
| "loss": 1.0925, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.9647007235255426, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 7.491211050462798e-07, | |
| "loss": 1.0662, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.9690857268142951, | |
| "grad_norm": 0.048095703125, | |
| "learning_rate": 5.737139518517509e-07, | |
| "loss": 1.0941, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.9734707301030476, | |
| "grad_norm": 0.0498046875, | |
| "learning_rate": 4.216111901092501e-07, | |
| "loss": 1.086, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.9778557333918001, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 2.9284847097746923e-07, | |
| "loss": 1.0768, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.9822407366805526, | |
| "grad_norm": 0.04736328125, | |
| "learning_rate": 1.8745597497433765e-07, | |
| "loss": 1.0733, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.986625739969305, | |
| "grad_norm": 0.04833984375, | |
| "learning_rate": 1.0545840490313596e-07, | |
| "loss": 1.0981, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.9910107432580575, | |
| "grad_norm": 0.05029296875, | |
| "learning_rate": 4.687498006236135e-08, | |
| "loss": 1.1037, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.99539574654681, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 1.1719431740997433e-08, | |
| "loss": 1.0715, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.9997807498355624, | |
| "grad_norm": 0.0478515625, | |
| "learning_rate": 0.0, | |
| "loss": 1.0883, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.9997807498355624, | |
| "eval_loss": 1.089297890663147, | |
| "eval_runtime": 2048.9326, | |
| "eval_samples_per_second": 7.883, | |
| "eval_steps_per_second": 7.883, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.9997807498355624, | |
| "step": 1140, | |
| "total_flos": 3.167597749864497e+18, | |
| "train_loss": 0.80264539467661, | |
| "train_runtime": 53655.2232, | |
| "train_samples_per_second": 2.72, | |
| "train_steps_per_second": 0.021 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 3.167597749864497e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |