| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.031110004977600796, | |
| "eval_steps": 125, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024888003982080636, | |
| "grad_norm": 5.4410481452941895, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9282, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00024888003982080636, | |
| "eval_loss": 3.5097618103027344, | |
| "eval_runtime": 47.433, | |
| "eval_samples_per_second": 13.83, | |
| "eval_steps_per_second": 6.915, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004977600796416127, | |
| "grad_norm": 5.435488224029541, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0917, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007466401194624191, | |
| "grad_norm": 5.29222297668457, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9705, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009955201592832255, | |
| "grad_norm": 3.5290043354034424, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8213, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012444001991040318, | |
| "grad_norm": 1.9220443964004517, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7124, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014932802389248383, | |
| "grad_norm": 1.0480749607086182, | |
| "learning_rate": 0.00012, | |
| "loss": 3.2383, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017421602787456446, | |
| "grad_norm": 2.3310468196868896, | |
| "learning_rate": 0.00014, | |
| "loss": 3.2751, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001991040318566451, | |
| "grad_norm": 0.622734546661377, | |
| "learning_rate": 0.00016, | |
| "loss": 2.9144, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002239920358387257, | |
| "grad_norm": 1.5959340333938599, | |
| "learning_rate": 0.00018, | |
| "loss": 3.4992, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0024888003982080635, | |
| "grad_norm": 2.5492312908172607, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7241, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0027376804380288703, | |
| "grad_norm": 2.9819629192352295, | |
| "learning_rate": 0.0001999979446958366, | |
| "loss": 2.5479, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0029865604778496766, | |
| "grad_norm": 2.515784978866577, | |
| "learning_rate": 0.00019999177886783194, | |
| "loss": 2.9924, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003235440517670483, | |
| "grad_norm": 0.9300045371055603, | |
| "learning_rate": 0.00019998150276943902, | |
| "loss": 2.7006, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003484320557491289, | |
| "grad_norm": 3.067373275756836, | |
| "learning_rate": 0.000199967116823068, | |
| "loss": 2.735, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0037332005973120955, | |
| "grad_norm": 3.160754919052124, | |
| "learning_rate": 0.0001999486216200688, | |
| "loss": 2.8188, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003982080637132902, | |
| "grad_norm": 3.5078177452087402, | |
| "learning_rate": 0.00019992601792070679, | |
| "loss": 2.4545, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004230960676953708, | |
| "grad_norm": 1.3515621423721313, | |
| "learning_rate": 0.00019989930665413147, | |
| "loss": 2.4931, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004479840716774514, | |
| "grad_norm": 1.023354172706604, | |
| "learning_rate": 0.00019986848891833845, | |
| "loss": 2.6162, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004728720756595321, | |
| "grad_norm": 0.6757822036743164, | |
| "learning_rate": 0.0001998335659801241, | |
| "loss": 2.3384, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004977600796416127, | |
| "grad_norm": 2.4865520000457764, | |
| "learning_rate": 0.00019979453927503364, | |
| "loss": 2.0874, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005226480836236934, | |
| "grad_norm": 0.50606369972229, | |
| "learning_rate": 0.00019975141040730207, | |
| "loss": 2.2065, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0054753608760577405, | |
| "grad_norm": 0.5787423253059387, | |
| "learning_rate": 0.0001997041811497882, | |
| "loss": 2.1371, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005724240915878547, | |
| "grad_norm": 2.7240867614746094, | |
| "learning_rate": 0.00019965285344390184, | |
| "loss": 2.3011, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005973120955699353, | |
| "grad_norm": 0.5894359350204468, | |
| "learning_rate": 0.00019959742939952392, | |
| "loss": 2.2565, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0062220009955201595, | |
| "grad_norm": 0.47996145486831665, | |
| "learning_rate": 0.00019953791129491983, | |
| "loss": 2.1724, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006470881035340966, | |
| "grad_norm": 0.43773430585861206, | |
| "learning_rate": 0.00019947430157664576, | |
| "loss": 2.21, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006719761075161772, | |
| "grad_norm": 0.4364480972290039, | |
| "learning_rate": 0.00019940660285944803, | |
| "loss": 1.9883, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006968641114982578, | |
| "grad_norm": 0.42618849873542786, | |
| "learning_rate": 0.00019933481792615583, | |
| "loss": 1.8854, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007217521154803385, | |
| "grad_norm": 0.9404358267784119, | |
| "learning_rate": 0.0001992589497275665, | |
| "loss": 1.9978, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007466401194624191, | |
| "grad_norm": 0.4599241614341736, | |
| "learning_rate": 0.0001991790013823246, | |
| "loss": 2.1981, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007715281234444997, | |
| "grad_norm": 0.5835628509521484, | |
| "learning_rate": 0.00019909497617679348, | |
| "loss": 2.0446, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.007964161274265804, | |
| "grad_norm": 1.6969475746154785, | |
| "learning_rate": 0.0001990068775649202, | |
| "loss": 1.7206, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00821304131408661, | |
| "grad_norm": 1.1236441135406494, | |
| "learning_rate": 0.00019891470916809362, | |
| "loss": 2.3924, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008461921353907416, | |
| "grad_norm": 0.8025091886520386, | |
| "learning_rate": 0.00019881847477499557, | |
| "loss": 2.0218, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008710801393728223, | |
| "grad_norm": 1.1834402084350586, | |
| "learning_rate": 0.00019871817834144504, | |
| "loss": 2.3439, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008959681433549029, | |
| "grad_norm": 1.910337209701538, | |
| "learning_rate": 0.0001986138239902355, | |
| "loss": 2.174, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009208561473369835, | |
| "grad_norm": 2.081226348876953, | |
| "learning_rate": 0.0001985054160109657, | |
| "loss": 1.9232, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009457441513190641, | |
| "grad_norm": 0.8203554749488831, | |
| "learning_rate": 0.00019839295885986296, | |
| "loss": 2.3514, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.009706321553011448, | |
| "grad_norm": 0.6460116505622864, | |
| "learning_rate": 0.0001982764571596004, | |
| "loss": 2.0705, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009955201592832254, | |
| "grad_norm": 0.7928256988525391, | |
| "learning_rate": 0.00019815591569910654, | |
| "loss": 2.2336, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01020408163265306, | |
| "grad_norm": 0.5046447515487671, | |
| "learning_rate": 0.00019803133943336874, | |
| "loss": 2.3007, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010452961672473868, | |
| "grad_norm": 0.7800955772399902, | |
| "learning_rate": 0.0001979027334832293, | |
| "loss": 1.7504, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010701841712294675, | |
| "grad_norm": 0.4248393476009369, | |
| "learning_rate": 0.00019777010313517518, | |
| "loss": 2.1283, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.010950721752115481, | |
| "grad_norm": 0.4310763478279114, | |
| "learning_rate": 0.00019763345384112043, | |
| "loss": 2.1454, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011199601791936287, | |
| "grad_norm": 0.3514373302459717, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 2.0302, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011448481831757094, | |
| "grad_norm": 0.4506613612174988, | |
| "learning_rate": 0.00019734812104845047, | |
| "loss": 2.3444, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0116973618715779, | |
| "grad_norm": 0.823046088218689, | |
| "learning_rate": 0.00019719944927874881, | |
| "loss": 2.1397, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.011946241911398706, | |
| "grad_norm": 0.6662668585777283, | |
| "learning_rate": 0.0001970467820203915, | |
| "loss": 2.2086, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012195121951219513, | |
| "grad_norm": 1.1788537502288818, | |
| "learning_rate": 0.00019689012554893154, | |
| "loss": 1.9532, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012444001991040319, | |
| "grad_norm": 0.41714179515838623, | |
| "learning_rate": 0.00019672948630390294, | |
| "loss": 1.994, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012692882030861125, | |
| "grad_norm": 0.40183207392692566, | |
| "learning_rate": 0.00019656487088855592, | |
| "loss": 1.986, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.012941762070681932, | |
| "grad_norm": 0.6568073034286499, | |
| "learning_rate": 0.00019639628606958533, | |
| "loss": 1.9911, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.013190642110502738, | |
| "grad_norm": 0.40880608558654785, | |
| "learning_rate": 0.0001962237387768529, | |
| "loss": 2.2154, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.013439522150323544, | |
| "grad_norm": 0.3884672522544861, | |
| "learning_rate": 0.00019604723610310194, | |
| "loss": 1.9765, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.01368840219014435, | |
| "grad_norm": 0.3780982196331024, | |
| "learning_rate": 0.00019586678530366606, | |
| "loss": 2.0202, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.013937282229965157, | |
| "grad_norm": 0.4995989203453064, | |
| "learning_rate": 0.00019568239379617088, | |
| "loss": 1.8901, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.014186162269785963, | |
| "grad_norm": 0.3196570575237274, | |
| "learning_rate": 0.00019549406916022905, | |
| "loss": 2.3905, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.01443504230960677, | |
| "grad_norm": 0.3686681389808655, | |
| "learning_rate": 0.00019530181913712872, | |
| "loss": 2.184, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.014683922349427576, | |
| "grad_norm": 0.3581784963607788, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.8453, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.014932802389248382, | |
| "grad_norm": 0.3524768054485321, | |
| "learning_rate": 0.00019490557470106686, | |
| "loss": 2.0638, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.015181682429069188, | |
| "grad_norm": 0.344062864780426, | |
| "learning_rate": 0.00019470159657616215, | |
| "loss": 2.0319, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.015430562468889995, | |
| "grad_norm": 0.4052053391933441, | |
| "learning_rate": 0.00019449372563954293, | |
| "loss": 1.8948, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0156794425087108, | |
| "grad_norm": 0.40913650393486023, | |
| "learning_rate": 0.0001942819704359693, | |
| "loss": 2.2626, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.015928322548531607, | |
| "grad_norm": 0.3126090168952942, | |
| "learning_rate": 0.00019406633966986828, | |
| "loss": 2.1733, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.016177202588352414, | |
| "grad_norm": 0.35215505957603455, | |
| "learning_rate": 0.00019384684220497605, | |
| "loss": 2.2469, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01642608262817322, | |
| "grad_norm": 0.36992332339286804, | |
| "learning_rate": 0.00019362348706397373, | |
| "loss": 2.32, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.016674962667994026, | |
| "grad_norm": 0.3458121418952942, | |
| "learning_rate": 0.00019339628342811632, | |
| "loss": 2.0615, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.016923842707814832, | |
| "grad_norm": 0.33729124069213867, | |
| "learning_rate": 0.0001931652406368554, | |
| "loss": 2.1723, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.01717272274763564, | |
| "grad_norm": 0.46333789825439453, | |
| "learning_rate": 0.0001929303681874552, | |
| "loss": 2.2158, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.017421602787456445, | |
| "grad_norm": 0.3130255341529846, | |
| "learning_rate": 0.0001926916757346022, | |
| "loss": 1.991, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01767048282727725, | |
| "grad_norm": 0.3570137917995453, | |
| "learning_rate": 0.00019244917309000817, | |
| "loss": 1.922, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.017919362867098058, | |
| "grad_norm": 0.27171969413757324, | |
| "learning_rate": 0.00019220287022200707, | |
| "loss": 2.2815, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.018168242906918864, | |
| "grad_norm": 0.30303627252578735, | |
| "learning_rate": 0.0001919527772551451, | |
| "loss": 2.09, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.01841712294673967, | |
| "grad_norm": 0.45809829235076904, | |
| "learning_rate": 0.00019169890446976454, | |
| "loss": 2.0446, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.018666002986560477, | |
| "grad_norm": 0.29333075881004333, | |
| "learning_rate": 0.00019144126230158127, | |
| "loss": 1.9728, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.018914883026381283, | |
| "grad_norm": 0.2959883511066437, | |
| "learning_rate": 0.0001911798613412557, | |
| "loss": 2.0945, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.01916376306620209, | |
| "grad_norm": 0.31434130668640137, | |
| "learning_rate": 0.0001909147123339575, | |
| "loss": 2.1703, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.019412643106022896, | |
| "grad_norm": 0.3976629972457886, | |
| "learning_rate": 0.0001906458261789238, | |
| "loss": 2.1109, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.019661523145843702, | |
| "grad_norm": 0.678793728351593, | |
| "learning_rate": 0.00019037321392901136, | |
| "loss": 1.9291, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.019910403185664508, | |
| "grad_norm": 0.46012192964553833, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 2.265, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.020159283225485315, | |
| "grad_norm": 0.3698313534259796, | |
| "learning_rate": 0.0001898168561213419, | |
| "loss": 2.1672, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 0.3445495069026947, | |
| "learning_rate": 0.0001895331334332753, | |
| "loss": 2.0265, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.020657043305126927, | |
| "grad_norm": 0.38758572936058044, | |
| "learning_rate": 0.0001892457303887706, | |
| "loss": 2.1402, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.020905923344947737, | |
| "grad_norm": 0.40104663372039795, | |
| "learning_rate": 0.0001889546588018412, | |
| "loss": 2.2048, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.021154803384768543, | |
| "grad_norm": 0.42981839179992676, | |
| "learning_rate": 0.00018865993063730004, | |
| "loss": 2.2485, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.02140368342458935, | |
| "grad_norm": 0.3159562647342682, | |
| "learning_rate": 0.00018836155801026753, | |
| "loss": 1.8041, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.021652563464410156, | |
| "grad_norm": 0.415228009223938, | |
| "learning_rate": 0.0001880595531856738, | |
| "loss": 2.08, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.021901443504230962, | |
| "grad_norm": 0.31004348397254944, | |
| "learning_rate": 0.00018775392857775432, | |
| "loss": 2.0714, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.02215032354405177, | |
| "grad_norm": 0.3166860342025757, | |
| "learning_rate": 0.00018744469674953956, | |
| "loss": 2.1457, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.022399203583872575, | |
| "grad_norm": 0.3657294511795044, | |
| "learning_rate": 0.00018713187041233896, | |
| "loss": 2.1152, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02264808362369338, | |
| "grad_norm": 0.3469568192958832, | |
| "learning_rate": 0.00018681546242521786, | |
| "loss": 1.9196, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.022896963663514187, | |
| "grad_norm": 0.3438771665096283, | |
| "learning_rate": 0.00018649548579446936, | |
| "loss": 2.2341, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.023145843703334994, | |
| "grad_norm": 0.30898717045783997, | |
| "learning_rate": 0.0001861719536730795, | |
| "loss": 2.0978, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0233947237431558, | |
| "grad_norm": 0.27930477261543274, | |
| "learning_rate": 0.00018584487936018661, | |
| "loss": 2.0048, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.023643603782976606, | |
| "grad_norm": 0.32163354754447937, | |
| "learning_rate": 0.00018551427630053463, | |
| "loss": 1.9489, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.023892483822797413, | |
| "grad_norm": 0.3902042806148529, | |
| "learning_rate": 0.00018518015808392045, | |
| "loss": 1.9324, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.02414136386261822, | |
| "grad_norm": 0.35879242420196533, | |
| "learning_rate": 0.00018484253844463526, | |
| "loss": 2.0225, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.024390243902439025, | |
| "grad_norm": 0.33365774154663086, | |
| "learning_rate": 0.00018450143126090015, | |
| "loss": 2.0397, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.02463912394225983, | |
| "grad_norm": 0.35122770071029663, | |
| "learning_rate": 0.00018415685055429533, | |
| "loss": 2.03, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.024888003982080638, | |
| "grad_norm": 0.29391220211982727, | |
| "learning_rate": 0.00018380881048918405, | |
| "loss": 2.119, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.025136884021901444, | |
| "grad_norm": 0.4452991187572479, | |
| "learning_rate": 0.00018345732537213027, | |
| "loss": 1.9258, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.02538576406172225, | |
| "grad_norm": 0.38186201453208923, | |
| "learning_rate": 0.00018310240965131041, | |
| "loss": 1.6995, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.025634644101543057, | |
| "grad_norm": 0.3281259834766388, | |
| "learning_rate": 0.00018274407791591966, | |
| "loss": 1.7411, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.025883524141363863, | |
| "grad_norm": 0.29078221321105957, | |
| "learning_rate": 0.00018238234489557215, | |
| "loss": 1.8857, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.02613240418118467, | |
| "grad_norm": 0.2946663200855255, | |
| "learning_rate": 0.0001820172254596956, | |
| "loss": 1.8642, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.026381284221005476, | |
| "grad_norm": 0.38488832116127014, | |
| "learning_rate": 0.00018164873461691986, | |
| "loss": 2.0094, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.026630164260826282, | |
| "grad_norm": 0.33220160007476807, | |
| "learning_rate": 0.00018127688751446027, | |
| "loss": 2.1743, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.02687904430064709, | |
| "grad_norm": 0.3243928849697113, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.8538, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.027127924340467895, | |
| "grad_norm": 0.31402042508125305, | |
| "learning_rate": 0.0001805231858085356, | |
| "loss": 2.0906, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.0273768043802887, | |
| "grad_norm": 0.46022218465805054, | |
| "learning_rate": 0.00018014136218679567, | |
| "loss": 2.1055, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.027625684420109507, | |
| "grad_norm": 0.3270494341850281, | |
| "learning_rate": 0.00017975624426754848, | |
| "loss": 1.6856, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.027874564459930314, | |
| "grad_norm": 0.31129342317581177, | |
| "learning_rate": 0.00017936784788148328, | |
| "loss": 2.2389, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.02812344449975112, | |
| "grad_norm": 0.3763848543167114, | |
| "learning_rate": 0.00017897618899405423, | |
| "loss": 2.2251, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.028372324539571926, | |
| "grad_norm": 0.3961619436740875, | |
| "learning_rate": 0.00017858128370482426, | |
| "loss": 2.1523, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.028621204579392732, | |
| "grad_norm": 0.32675299048423767, | |
| "learning_rate": 0.000178183148246803, | |
| "loss": 1.8199, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.02887008461921354, | |
| "grad_norm": 0.39736902713775635, | |
| "learning_rate": 0.00017778179898577973, | |
| "loss": 2.0062, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.029118964659034345, | |
| "grad_norm": 0.3664799928665161, | |
| "learning_rate": 0.00017737725241965069, | |
| "loss": 2.2775, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.02936784469885515, | |
| "grad_norm": 0.3666561543941498, | |
| "learning_rate": 0.00017696952517774062, | |
| "loss": 1.9005, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.029616724738675958, | |
| "grad_norm": 0.2838401794433594, | |
| "learning_rate": 0.00017655863402011947, | |
| "loss": 2.0504, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.029865604778496764, | |
| "grad_norm": 0.3173494338989258, | |
| "learning_rate": 0.00017614459583691346, | |
| "loss": 1.9387, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03011448481831757, | |
| "grad_norm": 0.31382298469543457, | |
| "learning_rate": 0.00017572742764761055, | |
| "loss": 2.0618, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.030363364858138377, | |
| "grad_norm": 0.3865104019641876, | |
| "learning_rate": 0.00017530714660036112, | |
| "loss": 2.0401, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.030612244897959183, | |
| "grad_norm": 0.39169177412986755, | |
| "learning_rate": 0.00017488376997127283, | |
| "loss": 1.7495, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.03086112493777999, | |
| "grad_norm": 0.3588005602359772, | |
| "learning_rate": 0.0001744573151637007, | |
| "loss": 2.028, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.031110004977600796, | |
| "grad_norm": 0.46878084540367126, | |
| "learning_rate": 0.00017402779970753155, | |
| "loss": 1.6867, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.031110004977600796, | |
| "eval_loss": 2.049610137939453, | |
| "eval_runtime": 47.161, | |
| "eval_samples_per_second": 13.91, | |
| "eval_steps_per_second": 6.955, | |
| "step": 125 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 125, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6511065563136000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |