| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9661016949152543, | |
| "eval_steps": 500, | |
| "global_step": 1400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00211864406779661, | |
| "grad_norm": 6772.94736433113, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 5.4426, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0211864406779661, | |
| "grad_norm": 43.76552598391156, | |
| "learning_rate": 5.263157894736842e-05, | |
| "loss": 6.5697, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0423728813559322, | |
| "grad_norm": 1.4214989301078385, | |
| "learning_rate": 0.00010526315789473683, | |
| "loss": 5.8015, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0635593220338983, | |
| "grad_norm": 1.8559172078320925, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 4.6978, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0847457627118644, | |
| "grad_norm": 0.9523887604864526, | |
| "learning_rate": 0.00021052631578947367, | |
| "loss": 3.9616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1059322033898305, | |
| "grad_norm": 0.5313592686196623, | |
| "learning_rate": 0.0002631578947368421, | |
| "loss": 3.2816, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1271186440677966, | |
| "grad_norm": 0.9882421975844679, | |
| "learning_rate": 0.00031578947368421053, | |
| "loss": 2.9453, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1483050847457627, | |
| "grad_norm": 1.3764980998221854, | |
| "learning_rate": 0.00036842105263157896, | |
| "loss": 2.7478, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1694915254237288, | |
| "grad_norm": 0.6188567319965684, | |
| "learning_rate": 0.00042105263157894734, | |
| "loss": 2.6778, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1906779661016949, | |
| "grad_norm": 0.45391127998861047, | |
| "learning_rate": 0.00047368421052631577, | |
| "loss": 2.6651, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.211864406779661, | |
| "grad_norm": 0.3359651886818045, | |
| "learning_rate": 0.0004999904062938913, | |
| "loss": 2.6871, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2330508474576271, | |
| "grad_norm": 0.2538059916992196, | |
| "learning_rate": 0.0004999136610628463, | |
| "loss": 2.6047, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2542372881355932, | |
| "grad_norm": 0.7420239318499638, | |
| "learning_rate": 0.0004997601941609823, | |
| "loss": 2.6122, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2754237288135593, | |
| "grad_norm": 1.0130312150097984, | |
| "learning_rate": 0.0004995300527015189, | |
| "loss": 2.8314, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2966101694915254, | |
| "grad_norm": 0.45185267289061176, | |
| "learning_rate": 0.0004992233073362051, | |
| "loss": 2.7241, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3177966101694915, | |
| "grad_norm": 1.2647337895757225, | |
| "learning_rate": 0.0004988400522336304, | |
| "loss": 2.6269, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 1.8112639454685833, | |
| "learning_rate": 0.0004983804050503152, | |
| "loss": 2.5217, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3601694915254237, | |
| "grad_norm": 3.7153319991642295, | |
| "learning_rate": 0.0004978445068945918, | |
| "loss": 2.6363, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3813559322033898, | |
| "grad_norm": 1.791954534899048, | |
| "learning_rate": 0.0004972325222832848, | |
| "loss": 2.6156, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4025423728813559, | |
| "grad_norm": 0.30066185600399886, | |
| "learning_rate": 0.0004965446390912051, | |
| "loss": 2.5443, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.423728813559322, | |
| "grad_norm": 0.155337614316216, | |
| "learning_rate": 0.0004957810684934746, | |
| "loss": 2.4791, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4449152542372881, | |
| "grad_norm": 0.10527493629733332, | |
| "learning_rate": 0.0004949420449006968, | |
| "loss": 2.4345, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4661016949152542, | |
| "grad_norm": 0.06207368975658736, | |
| "learning_rate": 0.0004940278258869937, | |
| "loss": 2.4284, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4872881355932203, | |
| "grad_norm": 0.06174468192832609, | |
| "learning_rate": 0.0004930386921109333, | |
| "loss": 2.3855, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5084745762711864, | |
| "grad_norm": 0.04921797570119065, | |
| "learning_rate": 0.0004919749472293693, | |
| "loss": 2.3648, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5296610169491526, | |
| "grad_norm": 0.06272467077360039, | |
| "learning_rate": 0.00049083691780422, | |
| "loss": 2.3618, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5508474576271186, | |
| "grad_norm": 0.06952127682493715, | |
| "learning_rate": 0.0004896249532022172, | |
| "loss": 2.3344, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5720338983050848, | |
| "grad_norm": 0.05291425745739597, | |
| "learning_rate": 0.0004883394254876522, | |
| "loss": 2.3401, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5932203389830508, | |
| "grad_norm": 0.09403878675057362, | |
| "learning_rate": 0.0004869807293081555, | |
| "loss": 2.3351, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.614406779661017, | |
| "grad_norm": 0.07509078154330293, | |
| "learning_rate": 0.00048554928177354254, | |
| "loss": 2.3067, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.635593220338983, | |
| "grad_norm": 0.1705698396439175, | |
| "learning_rate": 0.0004840455223277639, | |
| "loss": 2.3114, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6567796610169492, | |
| "grad_norm": 0.09664349408312269, | |
| "learning_rate": 0.0004824699126139995, | |
| "loss": 2.3059, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 0.08308196121963289, | |
| "learning_rate": 0.0004808229363329374, | |
| "loss": 2.2926, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6991525423728814, | |
| "grad_norm": 0.0669444065304248, | |
| "learning_rate": 0.0004791050990942811, | |
| "loss": 2.2862, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7203389830508474, | |
| "grad_norm": 0.05853715985139967, | |
| "learning_rate": 0.0004773169282615311, | |
| "loss": 2.2736, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7415254237288136, | |
| "grad_norm": 0.056477614254721926, | |
| "learning_rate": 0.00047545897279008845, | |
| "loss": 2.2715, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7627118644067796, | |
| "grad_norm": 0.0870456690332402, | |
| "learning_rate": 0.000473531803058729, | |
| "loss": 2.2543, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7838983050847458, | |
| "grad_norm": 0.0954901066459511, | |
| "learning_rate": 0.0004715360106945015, | |
| "loss": 2.2752, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8050847457627118, | |
| "grad_norm": 0.06902843103766237, | |
| "learning_rate": 0.00046947220839110225, | |
| "loss": 2.2698, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.826271186440678, | |
| "grad_norm": 0.10925884550477084, | |
| "learning_rate": 0.00046734102972078326, | |
| "loss": 2.2433, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.847457627118644, | |
| "grad_norm": 0.0659931072508813, | |
| "learning_rate": 0.0004651431289398489, | |
| "loss": 2.2415, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8686440677966102, | |
| "grad_norm": 0.06263383305001168, | |
| "learning_rate": 0.00046287918078780554, | |
| "loss": 2.2388, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.8898305084745762, | |
| "grad_norm": 0.09782328625398208, | |
| "learning_rate": 0.00046054988028022007, | |
| "loss": 2.2408, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9110169491525424, | |
| "grad_norm": 0.10848225540509068, | |
| "learning_rate": 0.000458155942495356, | |
| "loss": 2.2337, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9322033898305084, | |
| "grad_norm": 0.07281471757622568, | |
| "learning_rate": 0.0004556981023546495, | |
| "loss": 2.2173, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9533898305084746, | |
| "grad_norm": 0.06260737865841007, | |
| "learning_rate": 0.00045317711439709377, | |
| "loss": 2.2175, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9745762711864406, | |
| "grad_norm": 0.05780118722032544, | |
| "learning_rate": 0.00045059375254760106, | |
| "loss": 2.2194, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9957627118644068, | |
| "grad_norm": 0.07389833905985468, | |
| "learning_rate": 0.0004479488098794134, | |
| "loss": 2.222, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0169491525423728, | |
| "grad_norm": 0.08596309367450944, | |
| "learning_rate": 0.0004452430983706351, | |
| "loss": 2.138, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.0381355932203389, | |
| "grad_norm": 0.0716327488863897, | |
| "learning_rate": 0.0004424774486549611, | |
| "loss": 2.1209, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.0593220338983051, | |
| "grad_norm": 0.1035432059054005, | |
| "learning_rate": 0.0004396527097666786, | |
| "loss": 2.129, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0805084745762712, | |
| "grad_norm": 0.09433176908109482, | |
| "learning_rate": 0.0004367697488800197, | |
| "loss": 2.1266, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1016949152542372, | |
| "grad_norm": 0.03811729650126105, | |
| "learning_rate": 0.00043382945104294534, | |
| "loss": 2.1261, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.1228813559322033, | |
| "grad_norm": 0.04741201646286949, | |
| "learning_rate": 0.0004308327189054421, | |
| "loss": 2.1076, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.1440677966101696, | |
| "grad_norm": 0.053484019027130486, | |
| "learning_rate": 0.0004277804724424146, | |
| "loss": 2.1056, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.1652542372881356, | |
| "grad_norm": 0.07045317524776837, | |
| "learning_rate": 0.0004246736486712611, | |
| "loss": 2.1283, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.1864406779661016, | |
| "grad_norm": 0.056991644556702734, | |
| "learning_rate": 0.0004215132013642149, | |
| "loss": 2.1073, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.207627118644068, | |
| "grad_norm": 0.10932907349389169, | |
| "learning_rate": 0.0004183001007555436, | |
| "loss": 2.0923, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.228813559322034, | |
| "grad_norm": 0.07565475345058699, | |
| "learning_rate": 0.0004150353332436945, | |
| "loss": 2.1304, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.04806730962026069, | |
| "learning_rate": 0.000411719901088477, | |
| "loss": 2.1019, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.271186440677966, | |
| "grad_norm": 0.12046348461315967, | |
| "learning_rate": 0.00040835482210337684, | |
| "loss": 2.1134, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.292372881355932, | |
| "grad_norm": 0.04785616035170302, | |
| "learning_rate": 0.00040494112934309393, | |
| "loss": 2.0899, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.3135593220338984, | |
| "grad_norm": 0.06950120638475274, | |
| "learning_rate": 0.0004014798707864026, | |
| "loss": 2.1022, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.3347457627118644, | |
| "grad_norm": 0.05764573408385284, | |
| "learning_rate": 0.00039797210901443004, | |
| "loss": 2.0954, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 0.05248977971434518, | |
| "learning_rate": 0.00039441892088445073, | |
| "loss": 2.1058, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.3771186440677967, | |
| "grad_norm": 0.08905978345074242, | |
| "learning_rate": 0.0003908213971993002, | |
| "loss": 2.1041, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3983050847457628, | |
| "grad_norm": 0.06873869897878389, | |
| "learning_rate": 0.0003871806423725056, | |
| "loss": 2.1069, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.4194915254237288, | |
| "grad_norm": 0.07051366599451443, | |
| "learning_rate": 0.0003834977740892396, | |
| "loss": 2.1065, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.4406779661016949, | |
| "grad_norm": 0.05550804358265807, | |
| "learning_rate": 0.00037977392296319814, | |
| "loss": 2.0909, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.461864406779661, | |
| "grad_norm": 0.05362391791941435, | |
| "learning_rate": 0.00037601023218951146, | |
| "loss": 2.0812, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.4830508474576272, | |
| "grad_norm": 0.07183191275199183, | |
| "learning_rate": 0.000372207857193791, | |
| "loss": 2.1006, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.5042372881355932, | |
| "grad_norm": 0.036702339330004795, | |
| "learning_rate": 0.0003683679652774219, | |
| "loss": 2.0801, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.5254237288135593, | |
| "grad_norm": 0.04503677538534475, | |
| "learning_rate": 0.00036449173525921033, | |
| "loss": 2.0985, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.5466101694915255, | |
| "grad_norm": 0.08571969684473545, | |
| "learning_rate": 0.0003605803571134947, | |
| "loss": 2.0963, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.5677966101694916, | |
| "grad_norm": 0.07028832284848355, | |
| "learning_rate": 0.00035663503160483214, | |
| "loss": 2.0901, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.5889830508474576, | |
| "grad_norm": 0.0460245424115982, | |
| "learning_rate": 0.0003526569699193726, | |
| "loss": 2.0747, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.6101694915254239, | |
| "grad_norm": 0.05695582523407322, | |
| "learning_rate": 0.0003486473932930333, | |
| "loss": 2.0926, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.6313559322033897, | |
| "grad_norm": 0.04729193051976345, | |
| "learning_rate": 0.0003446075326365887, | |
| "loss": 2.079, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.652542372881356, | |
| "grad_norm": 0.0440876523157918, | |
| "learning_rate": 0.0003405386281577892, | |
| "loss": 2.0936, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.673728813559322, | |
| "grad_norm": 0.03952017824612962, | |
| "learning_rate": 0.00033644192898062744, | |
| "loss": 2.0751, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "grad_norm": 0.043820899114424584, | |
| "learning_rate": 0.0003323186927618648, | |
| "loss": 2.1008, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.7161016949152543, | |
| "grad_norm": 0.041923143213303454, | |
| "learning_rate": 0.00032817018530494166, | |
| "loss": 2.0951, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.7372881355932204, | |
| "grad_norm": 0.051309887579675056, | |
| "learning_rate": 0.00032399768017138354, | |
| "loss": 2.0798, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.7584745762711864, | |
| "grad_norm": 0.0432756541973623, | |
| "learning_rate": 0.000319802458289828, | |
| "loss": 2.0775, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.7796610169491527, | |
| "grad_norm": 0.04478332673838983, | |
| "learning_rate": 0.0003155858075627886, | |
| "loss": 2.0739, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.8008474576271185, | |
| "grad_norm": 0.06738395966368808, | |
| "learning_rate": 0.00031134902247127765, | |
| "loss": 2.0845, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.8220338983050848, | |
| "grad_norm": 0.0493251207413769, | |
| "learning_rate": 0.00030709340367741103, | |
| "loss": 2.077, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.8432203389830508, | |
| "grad_norm": 0.04126164753701976, | |
| "learning_rate": 0.0003028202576251134, | |
| "loss": 2.0702, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.8644067796610169, | |
| "grad_norm": 0.040160774820697534, | |
| "learning_rate": 0.00029853089613905015, | |
| "loss": 2.0566, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.8855932203389831, | |
| "grad_norm": 0.05463141520142657, | |
| "learning_rate": 0.00029422663602190655, | |
| "loss": 2.0564, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.9067796610169492, | |
| "grad_norm": 0.05136378797370674, | |
| "learning_rate": 0.0002899087986501388, | |
| "loss": 2.0757, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.9279661016949152, | |
| "grad_norm": 0.0438175755611988, | |
| "learning_rate": 0.00028557870956832135, | |
| "loss": 2.0636, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.9491525423728815, | |
| "grad_norm": 0.04252018387450911, | |
| "learning_rate": 0.00028123769808221404, | |
| "loss": 2.0554, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.9703389830508473, | |
| "grad_norm": 0.05122593433878704, | |
| "learning_rate": 0.0002768870968506755, | |
| "loss": 2.0597, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.9915254237288136, | |
| "grad_norm": 0.07844445065272901, | |
| "learning_rate": 0.0002725282414765459, | |
| "loss": 2.0748, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.01271186440678, | |
| "grad_norm": 0.08602891741332974, | |
| "learning_rate": 0.0002681624700966272, | |
| "loss": 1.9986, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": 0.08403229732346643, | |
| "learning_rate": 0.00026379112297088454, | |
| "loss": 1.9663, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.055084745762712, | |
| "grad_norm": 0.04805601486638949, | |
| "learning_rate": 0.0002594155420709964, | |
| "loss": 1.9602, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.0762711864406778, | |
| "grad_norm": 0.04177748467643192, | |
| "learning_rate": 0.0002550370706683793, | |
| "loss": 1.9615, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.097457627118644, | |
| "grad_norm": 0.04712018323150014, | |
| "learning_rate": 0.00025065705292181244, | |
| "loss": 1.9685, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.1186440677966103, | |
| "grad_norm": 0.04036226172974584, | |
| "learning_rate": 0.0002462768334647919, | |
| "loss": 1.952, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.139830508474576, | |
| "grad_norm": 0.05659363087865909, | |
| "learning_rate": 0.00024189775699273692, | |
| "loss": 1.9628, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.1610169491525424, | |
| "grad_norm": 0.042136646622118364, | |
| "learning_rate": 0.0002375211678501792, | |
| "loss": 1.9385, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.1822033898305087, | |
| "grad_norm": 0.03941503529723361, | |
| "learning_rate": 0.00023314840961805803, | |
| "loss": 1.9554, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.2033898305084745, | |
| "grad_norm": 0.03700109577217643, | |
| "learning_rate": 0.0002287808247012513, | |
| "loss": 1.9642, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.2245762711864407, | |
| "grad_norm": 0.10375814997593234, | |
| "learning_rate": 0.00022441975391646662, | |
| "loss": 1.9369, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.2457627118644066, | |
| "grad_norm": 0.052752509354616346, | |
| "learning_rate": 0.0002200665360806211, | |
| "loss": 1.9559, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.266949152542373, | |
| "grad_norm": 0.03224571338131167, | |
| "learning_rate": 0.00021572250759983337, | |
| "loss": 1.9617, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.288135593220339, | |
| "grad_norm": 0.03288018024537444, | |
| "learning_rate": 0.00021138900205915702, | |
| "loss": 1.9699, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.309322033898305, | |
| "grad_norm": 0.037431680326990596, | |
| "learning_rate": 0.0002070673498131803, | |
| "loss": 1.9608, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.330508474576271, | |
| "grad_norm": 0.04394885552216967, | |
| "learning_rate": 0.00020275887757761603, | |
| "loss": 1.9412, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.3516949152542375, | |
| "grad_norm": 0.030864374934226058, | |
| "learning_rate": 0.00019846490802201004, | |
| "loss": 1.9565, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.3728813559322033, | |
| "grad_norm": 0.0376528236108464, | |
| "learning_rate": 0.00019418675936369118, | |
| "loss": 1.948, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.3940677966101696, | |
| "grad_norm": 0.03266857205638587, | |
| "learning_rate": 0.0001899257449630886, | |
| "loss": 1.9481, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.415254237288136, | |
| "grad_norm": 0.035295325605865485, | |
| "learning_rate": 0.00018568317292053894, | |
| "loss": 1.9402, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.4364406779661016, | |
| "grad_norm": 0.04817378053212362, | |
| "learning_rate": 0.0001814603456747094, | |
| "loss": 1.9535, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.457627118644068, | |
| "grad_norm": 0.04074945682830249, | |
| "learning_rate": 0.0001772585596027591, | |
| "loss": 1.9525, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.4788135593220337, | |
| "grad_norm": 0.035901200449676485, | |
| "learning_rate": 0.00017307910462235977, | |
| "loss": 1.9731, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.035662558321239934, | |
| "learning_rate": 0.0001689232637957013, | |
| "loss": 1.9362, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.5211864406779663, | |
| "grad_norm": 0.03973557868554537, | |
| "learning_rate": 0.00016479231293560032, | |
| "loss": 1.9374, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.542372881355932, | |
| "grad_norm": 0.03299325997458768, | |
| "learning_rate": 0.0001606875202138356, | |
| "loss": 1.9481, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.5635593220338984, | |
| "grad_norm": 0.04375441334168935, | |
| "learning_rate": 0.0001566101457718281, | |
| "loss": 1.9383, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.584745762711864, | |
| "grad_norm": 0.03880059687569579, | |
| "learning_rate": 0.00015256144133378696, | |
| "loss": 1.9605, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.6059322033898304, | |
| "grad_norm": 0.031915977851280856, | |
| "learning_rate": 0.0001485426498224392, | |
| "loss": 1.9685, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.6271186440677967, | |
| "grad_norm": 0.038809992830277334, | |
| "learning_rate": 0.0001445550049774617, | |
| "loss": 1.9492, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.648305084745763, | |
| "grad_norm": 0.041440483327853134, | |
| "learning_rate": 0.00014059973097673188, | |
| "loss": 1.9644, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.669491525423729, | |
| "grad_norm": 0.03266791279733371, | |
| "learning_rate": 0.00013667804206051392, | |
| "loss": 1.9503, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.690677966101695, | |
| "grad_norm": 0.03449869131827401, | |
| "learning_rate": 0.00013279114215869654, | |
| "loss": 1.9579, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.711864406779661, | |
| "grad_norm": 0.032938848631871014, | |
| "learning_rate": 0.0001289402245211944, | |
| "loss": 1.9452, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.733050847457627, | |
| "grad_norm": 0.050239168482732646, | |
| "learning_rate": 0.00012512647135162964, | |
| "loss": 1.9561, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.7542372881355934, | |
| "grad_norm": 0.0306200091807657, | |
| "learning_rate": 0.00012135105344440394, | |
| "loss": 1.9449, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.7754237288135593, | |
| "grad_norm": 0.03225814110229855, | |
| "learning_rate": 0.00011761512982527305, | |
| "loss": 1.9476, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.7966101694915255, | |
| "grad_norm": 0.03350710910144213, | |
| "learning_rate": 0.00011391984739553427, | |
| "loss": 1.9337, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.8177966101694913, | |
| "grad_norm": 0.03729852355842271, | |
| "learning_rate": 0.00011026634057993648, | |
| "loss": 1.9421, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.8389830508474576, | |
| "grad_norm": 0.028562510049380468, | |
| "learning_rate": 0.00010665573097841957, | |
| "loss": 1.9553, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.860169491525424, | |
| "grad_norm": 0.03292192919214765, | |
| "learning_rate": 0.00010308912702179166, | |
| "loss": 1.9531, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.8813559322033897, | |
| "grad_norm": 0.03463226481188989, | |
| "learning_rate": 9.956762363144892e-05, | |
| "loss": 1.9456, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.902542372881356, | |
| "grad_norm": 0.028278857959505636, | |
| "learning_rate": 9.609230188324286e-05, | |
| "loss": 1.9359, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.923728813559322, | |
| "grad_norm": 0.028175093698422474, | |
| "learning_rate": 9.266422867559753e-05, | |
| "loss": 1.9543, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.944915254237288, | |
| "grad_norm": 0.03450981182902969, | |
| "learning_rate": 8.928445640197971e-05, | |
| "loss": 1.9378, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.9661016949152543, | |
| "grad_norm": 0.029970639983241495, | |
| "learning_rate": 8.5954022627822e-05, | |
| "loss": 1.9465, | |
| "step": 1400 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1888, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.4703672906612736e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |