{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.079377678996666, "eval_steps": 100, "global_step": 1700, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006350214319733291, "grad_norm": 2.2047078609466553, "learning_rate": 0.0, "loss": 1.9032886028289795, "num_input_tokens_seen": 65418, "step": 1, "train_runtime": 52.1524, "train_tokens_per_second": 1254.363 }, { "epoch": 0.0012700428639466582, "grad_norm": 2.106402635574341, "learning_rate": 6.666666666666667e-06, "loss": 1.9484694004058838, "num_input_tokens_seen": 130868, "step": 2, "train_runtime": 73.0166, "train_tokens_per_second": 1792.304 }, { "epoch": 0.0019050642959199872, "grad_norm": 1.7872711420059204, "learning_rate": 1.3333333333333333e-05, "loss": 1.9148499965667725, "num_input_tokens_seen": 196386, "step": 3, "train_runtime": 94.8422, "train_tokens_per_second": 2070.66 }, { "epoch": 0.0025400857278933165, "grad_norm": 1.5992257595062256, "learning_rate": 2e-05, "loss": 1.7917773723602295, "num_input_tokens_seen": 261877, "step": 4, "train_runtime": 116.1906, "train_tokens_per_second": 2253.856 }, { "epoch": 0.0031751071598666455, "grad_norm": 1.6295161247253418, "learning_rate": 1.9999997786814746e-05, "loss": 1.847374439239502, "num_input_tokens_seen": 327396, "step": 5, "train_runtime": 137.0563, "train_tokens_per_second": 2388.77 }, { "epoch": 0.0038101285918399745, "grad_norm": 1.9761685132980347, "learning_rate": 1.9999991147259958e-05, "loss": 2.0062618255615234, "num_input_tokens_seen": 392921, "step": 6, "train_runtime": 159.409, "train_tokens_per_second": 2464.861 }, { "epoch": 0.004445150023813304, "grad_norm": 1.6813795566558838, "learning_rate": 1.999998008133858e-05, "loss": 1.6937804222106934, "num_input_tokens_seen": 458442, "step": 7, "train_runtime": 180.7042, "train_tokens_per_second": 2536.975 }, { "epoch": 0.005080171455786633, "grad_norm": 1.7407411336898804, "learning_rate": 1.9999964589055507e-05, "loss": 1.9401168823242188, "num_input_tokens_seen": 523911, "step": 8, "train_runtime": 202.0365, "train_tokens_per_second": 2593.15 }, { "epoch": 0.005715192887759962, "grad_norm": 1.6159989833831787, "learning_rate": 1.9999944670417598e-05, "loss": 1.8875402212142944, "num_input_tokens_seen": 589404, "step": 9, "train_runtime": 223.6789, "train_tokens_per_second": 2635.045 }, { "epoch": 0.006350214319733291, "grad_norm": 1.467363715171814, "learning_rate": 1.999992032543367e-05, "loss": 1.8875060081481934, "num_input_tokens_seen": 654844, "step": 10, "train_runtime": 245.0003, "train_tokens_per_second": 2672.83 }, { "epoch": 0.00698523575170662, "grad_norm": 1.2846120595932007, "learning_rate": 1.9999891554114494e-05, "loss": 1.6774990558624268, "num_input_tokens_seen": 720363, "step": 11, "train_runtime": 266.5381, "train_tokens_per_second": 2702.664 }, { "epoch": 0.007620257183679949, "grad_norm": 1.3400604724884033, "learning_rate": 1.999985835647281e-05, "loss": 1.613918662071228, "num_input_tokens_seen": 785856, "step": 12, "train_runtime": 287.9388, "train_tokens_per_second": 2729.247 }, { "epoch": 0.008255278615653278, "grad_norm": 1.2377521991729736, "learning_rate": 1.9999820732523318e-05, "loss": 1.665791630744934, "num_input_tokens_seen": 851296, "step": 13, "train_runtime": 308.087, "train_tokens_per_second": 2763.168 }, { "epoch": 0.008890300047626608, "grad_norm": 1.4463437795639038, "learning_rate": 1.9999778682282658e-05, "loss": 1.8669979572296143, "num_input_tokens_seen": 916795, "step": 14, "train_runtime": 330.4892, "train_tokens_per_second": 2774.054 }, { "epoch": 0.009525321479599936, "grad_norm": 1.453888177871704, "learning_rate": 1.9999732205769455e-05, "loss": 1.8316820859909058, "num_input_tokens_seen": 976012, "step": 15, "train_runtime": 350.7435, "train_tokens_per_second": 2782.695 }, { "epoch": 0.010160342911573266, "grad_norm": 1.275309681892395, "learning_rate": 1.9999681303004274e-05, "loss": 1.8200340270996094, "num_input_tokens_seen": 1041470, "step": 16, "train_runtime": 371.8145, "train_tokens_per_second": 2801.047 }, { "epoch": 0.010795364343546594, "grad_norm": 1.3687657117843628, "learning_rate": 1.999962597400965e-05, "loss": 1.8261315822601318, "num_input_tokens_seen": 1106961, "step": 17, "train_runtime": 393.3998, "train_tokens_per_second": 2813.832 }, { "epoch": 0.011430385775519924, "grad_norm": 1.1546250581741333, "learning_rate": 1.9999566218810075e-05, "loss": 1.6310349702835083, "num_input_tokens_seen": 1172491, "step": 18, "train_runtime": 413.7116, "train_tokens_per_second": 2834.078 }, { "epoch": 0.012065407207493254, "grad_norm": 1.3480795621871948, "learning_rate": 1.999950203743199e-05, "loss": 1.8222062587738037, "num_input_tokens_seen": 1237950, "step": 19, "train_runtime": 434.3029, "train_tokens_per_second": 2850.43 }, { "epoch": 0.012700428639466582, "grad_norm": 1.1805720329284668, "learning_rate": 1.9999433429903818e-05, "loss": 1.781423807144165, "num_input_tokens_seen": 1303407, "step": 20, "train_runtime": 455.1011, "train_tokens_per_second": 2863.995 }, { "epoch": 0.013335450071439912, "grad_norm": 1.414565920829773, "learning_rate": 1.999936039625592e-05, "loss": 1.86342191696167, "num_input_tokens_seen": 1368905, "step": 21, "train_runtime": 476.4884, "train_tokens_per_second": 2872.903 }, { "epoch": 0.01397047150341324, "grad_norm": 1.3225334882736206, "learning_rate": 1.999928293652062e-05, "loss": 1.691840648651123, "num_input_tokens_seen": 1434411, "step": 22, "train_runtime": 498.4909, "train_tokens_per_second": 2877.507 }, { "epoch": 0.01460549293538657, "grad_norm": 1.1990783214569092, "learning_rate": 1.9999201050732208e-05, "loss": 1.6896190643310547, "num_input_tokens_seen": 1499942, "step": 23, "train_runtime": 519.6817, "train_tokens_per_second": 2886.271 }, { "epoch": 0.015240514367359898, "grad_norm": 1.2034040689468384, "learning_rate": 1.9999114738926933e-05, "loss": 1.75850248336792, "num_input_tokens_seen": 1565382, "step": 24, "train_runtime": 540.9567, "train_tokens_per_second": 2893.729 }, { "epoch": 0.015875535799333228, "grad_norm": 1.1959084272384644, "learning_rate": 1.999902400114299e-05, "loss": 1.9181818962097168, "num_input_tokens_seen": 1630900, "step": 25, "train_runtime": 562.4004, "train_tokens_per_second": 2899.891 }, { "epoch": 0.016510557231306556, "grad_norm": 1.4459563493728638, "learning_rate": 1.9998928837420556e-05, "loss": 1.55326509475708, "num_input_tokens_seen": 1696413, "step": 26, "train_runtime": 584.3204, "train_tokens_per_second": 2903.224 }, { "epoch": 0.017145578663279884, "grad_norm": 1.210732102394104, "learning_rate": 1.9998829247801747e-05, "loss": 1.8107936382293701, "num_input_tokens_seen": 1761849, "step": 27, "train_runtime": 606.2359, "train_tokens_per_second": 2906.21 }, { "epoch": 0.017780600095253216, "grad_norm": 1.196833848953247, "learning_rate": 1.999872523233064e-05, "loss": 1.5606094598770142, "num_input_tokens_seen": 1827244, "step": 28, "train_runtime": 627.234, "train_tokens_per_second": 2913.178 }, { "epoch": 0.018415621527226544, "grad_norm": 1.4408690929412842, "learning_rate": 1.9998616791053288e-05, "loss": 1.8550925254821777, "num_input_tokens_seen": 1892668, "step": 29, "train_runtime": 648.6824, "train_tokens_per_second": 2917.711 }, { "epoch": 0.019050642959199872, "grad_norm": 1.406856656074524, "learning_rate": 1.999850392401768e-05, "loss": 1.9270943403244019, "num_input_tokens_seen": 1958107, "step": 30, "train_runtime": 669.7629, "train_tokens_per_second": 2923.582 }, { "epoch": 0.019685664391173203, "grad_norm": 1.4154108762741089, "learning_rate": 1.9998386631273784e-05, "loss": 1.9473741054534912, "num_input_tokens_seen": 2023502, "step": 31, "train_runtime": 690.6683, "train_tokens_per_second": 2929.774 }, { "epoch": 0.02032068582314653, "grad_norm": 1.1443977355957031, "learning_rate": 1.9998264912873512e-05, "loss": 1.6958041191101074, "num_input_tokens_seen": 2089018, "step": 32, "train_runtime": 712.0088, "train_tokens_per_second": 2933.978 }, { "epoch": 0.02095570725511986, "grad_norm": 1.3578585386276245, "learning_rate": 1.999813876887074e-05, "loss": 1.5945302248001099, "num_input_tokens_seen": 2154535, "step": 33, "train_runtime": 733.3648, "train_tokens_per_second": 2937.876 }, { "epoch": 0.021590728687093188, "grad_norm": 1.2425755262374878, "learning_rate": 1.999800819932131e-05, "loss": 1.7911380529403687, "num_input_tokens_seen": 2220005, "step": 34, "train_runtime": 754.5016, "train_tokens_per_second": 2942.346 }, { "epoch": 0.02222575011906652, "grad_norm": 1.4220023155212402, "learning_rate": 1.9997873204283015e-05, "loss": 1.8910640478134155, "num_input_tokens_seen": 2285457, "step": 35, "train_runtime": 776.1342, "train_tokens_per_second": 2944.667 }, { "epoch": 0.022860771551039848, "grad_norm": 1.288438081741333, "learning_rate": 1.9997733783815602e-05, "loss": 1.6949235200881958, "num_input_tokens_seen": 2350952, "step": 36, "train_runtime": 797.2695, "train_tokens_per_second": 2948.754 }, { "epoch": 0.023495792983013176, "grad_norm": 1.1847411394119263, "learning_rate": 1.9997589937980796e-05, "loss": 1.806897759437561, "num_input_tokens_seen": 2416464, "step": 37, "train_runtime": 818.2967, "train_tokens_per_second": 2953.041 }, { "epoch": 0.024130814414986507, "grad_norm": 1.372705340385437, "learning_rate": 1.9997441666842258e-05, "loss": 1.772993564605713, "num_input_tokens_seen": 2481874, "step": 38, "train_runtime": 840.3788, "train_tokens_per_second": 2953.28 }, { "epoch": 0.024765835846959836, "grad_norm": 1.2363430261611938, "learning_rate": 1.9997288970465624e-05, "loss": 1.8008148670196533, "num_input_tokens_seen": 2547398, "step": 39, "train_runtime": 862.1187, "train_tokens_per_second": 2954.811 }, { "epoch": 0.025400857278933164, "grad_norm": 1.2819244861602783, "learning_rate": 1.999713184891848e-05, "loss": 1.8114832639694214, "num_input_tokens_seen": 2612883, "step": 40, "train_runtime": 883.0527, "train_tokens_per_second": 2958.921 }, { "epoch": 0.026035878710906492, "grad_norm": 1.414847731590271, "learning_rate": 1.9996970302270378e-05, "loss": 1.915553092956543, "num_input_tokens_seen": 2678390, "step": 41, "train_runtime": 905.7838, "train_tokens_per_second": 2956.986 }, { "epoch": 0.026670900142879823, "grad_norm": 1.41985023021698, "learning_rate": 1.9996804330592815e-05, "loss": 1.8214459419250488, "num_input_tokens_seen": 2743818, "step": 42, "train_runtime": 927.1244, "train_tokens_per_second": 2959.493 }, { "epoch": 0.02730592157485315, "grad_norm": 1.3077317476272583, "learning_rate": 1.999663393395927e-05, "loss": 1.919937014579773, "num_input_tokens_seen": 2809311, "step": 43, "train_runtime": 949.1269, "train_tokens_per_second": 2959.89 }, { "epoch": 0.02794094300682648, "grad_norm": 1.3149712085723877, "learning_rate": 1.9996459112445157e-05, "loss": 1.8323410749435425, "num_input_tokens_seen": 2874768, "step": 44, "train_runtime": 971.1107, "train_tokens_per_second": 2960.289 }, { "epoch": 0.028575964438799808, "grad_norm": 1.3060548305511475, "learning_rate": 1.999627986612786e-05, "loss": 1.8535284996032715, "num_input_tokens_seen": 2940200, "step": 45, "train_runtime": 992.5648, "train_tokens_per_second": 2962.225 }, { "epoch": 0.02921098587077314, "grad_norm": 1.2914034128189087, "learning_rate": 1.999609619508672e-05, "loss": 1.825146198272705, "num_input_tokens_seen": 3005705, "step": 46, "train_runtime": 1014.3859, "train_tokens_per_second": 2963.079 }, { "epoch": 0.029846007302746468, "grad_norm": 1.2126020193099976, "learning_rate": 1.9995908099403045e-05, "loss": 1.8423736095428467, "num_input_tokens_seen": 3071149, "step": 47, "train_runtime": 1036.4405, "train_tokens_per_second": 2963.17 }, { "epoch": 0.030481028734719796, "grad_norm": 1.1393625736236572, "learning_rate": 1.999571557916008e-05, "loss": 1.696762204170227, "num_input_tokens_seen": 3136683, "step": 48, "train_runtime": 1057.7119, "train_tokens_per_second": 2965.536 }, { "epoch": 0.031116050166693127, "grad_norm": 1.2710328102111816, "learning_rate": 1.9995518634443044e-05, "loss": 1.7700999975204468, "num_input_tokens_seen": 3202187, "step": 49, "train_runtime": 1079.182, "train_tokens_per_second": 2967.235 }, { "epoch": 0.031751071598666455, "grad_norm": 1.326641321182251, "learning_rate": 1.999531726533912e-05, "loss": 1.8791651725769043, "num_input_tokens_seen": 3267665, "step": 50, "train_runtime": 1100.8935, "train_tokens_per_second": 2968.194 }, { "epoch": 0.03238609303063979, "grad_norm": 1.246381402015686, "learning_rate": 1.999511147193744e-05, "loss": 1.6314442157745361, "num_input_tokens_seen": 3333092, "step": 51, "train_runtime": 1121.9927, "train_tokens_per_second": 2970.69 }, { "epoch": 0.03302111446261311, "grad_norm": 1.3781269788742065, "learning_rate": 1.999490125432909e-05, "loss": 2.091547727584839, "num_input_tokens_seen": 3398601, "step": 52, "train_runtime": 1145.2172, "train_tokens_per_second": 2967.648 }, { "epoch": 0.03365613589458644, "grad_norm": 1.2652127742767334, "learning_rate": 1.9994686612607118e-05, "loss": 1.8145089149475098, "num_input_tokens_seen": 3464063, "step": 53, "train_runtime": 1166.5597, "train_tokens_per_second": 2969.469 }, { "epoch": 0.03429115732655977, "grad_norm": 1.218989372253418, "learning_rate": 1.9994467546866544e-05, "loss": 1.7496321201324463, "num_input_tokens_seen": 3529511, "step": 54, "train_runtime": 1187.3845, "train_tokens_per_second": 2972.509 }, { "epoch": 0.0349261787585331, "grad_norm": 1.273228406906128, "learning_rate": 1.9994244057204325e-05, "loss": 1.639212965965271, "num_input_tokens_seen": 3589359, "step": 55, "train_runtime": 1206.6164, "train_tokens_per_second": 2974.731 }, { "epoch": 0.03556120019050643, "grad_norm": 1.2228236198425293, "learning_rate": 1.999401614371939e-05, "loss": 1.6924388408660889, "num_input_tokens_seen": 3654802, "step": 56, "train_runtime": 1228.2182, "train_tokens_per_second": 2975.694 }, { "epoch": 0.036196221622479756, "grad_norm": 1.1091128587722778, "learning_rate": 1.9993783806512617e-05, "loss": 1.5724093914031982, "num_input_tokens_seen": 3720270, "step": 57, "train_runtime": 1248.7921, "train_tokens_per_second": 2979.095 }, { "epoch": 0.03683124305445309, "grad_norm": 1.3194984197616577, "learning_rate": 1.9993547045686856e-05, "loss": 1.7397781610488892, "num_input_tokens_seen": 3785762, "step": 58, "train_runtime": 1270.8719, "train_tokens_per_second": 2978.87 }, { "epoch": 0.03746626448642642, "grad_norm": 1.2371089458465576, "learning_rate": 1.99933058613469e-05, "loss": 1.6340949535369873, "num_input_tokens_seen": 3851219, "step": 59, "train_runtime": 1292.5111, "train_tokens_per_second": 2979.641 }, { "epoch": 0.038101285918399744, "grad_norm": 1.2318209409713745, "learning_rate": 1.9993060253599507e-05, "loss": 1.805337905883789, "num_input_tokens_seen": 3916698, "step": 60, "train_runtime": 1313.8982, "train_tokens_per_second": 2980.975 }, { "epoch": 0.038736307350373075, "grad_norm": 1.219114899635315, "learning_rate": 1.9992810222553387e-05, "loss": 1.7253416776657104, "num_input_tokens_seen": 3982213, "step": 61, "train_runtime": 1335.1942, "train_tokens_per_second": 2982.497 }, { "epoch": 0.03937132878234641, "grad_norm": 1.2166874408721924, "learning_rate": 1.999255576831922e-05, "loss": 1.8458857536315918, "num_input_tokens_seen": 4047606, "step": 62, "train_runtime": 1356.7151, "train_tokens_per_second": 2983.387 }, { "epoch": 0.04000635021431973, "grad_norm": 1.2280209064483643, "learning_rate": 1.9992296891009638e-05, "loss": 1.7642972469329834, "num_input_tokens_seen": 4113100, "step": 63, "train_runtime": 1378.229, "train_tokens_per_second": 2984.337 }, { "epoch": 0.04064137164629306, "grad_norm": 1.2459807395935059, "learning_rate": 1.9992033590739224e-05, "loss": 1.9079241752624512, "num_input_tokens_seen": 4178482, "step": 64, "train_runtime": 1399.112, "train_tokens_per_second": 2986.524 }, { "epoch": 0.041276393078266395, "grad_norm": 1.2489101886749268, "learning_rate": 1.999176586762453e-05, "loss": 1.6853039264678955, "num_input_tokens_seen": 4243925, "step": 65, "train_runtime": 1420.3094, "train_tokens_per_second": 2988.028 }, { "epoch": 0.04191141451023972, "grad_norm": 1.3452032804489136, "learning_rate": 1.9991493721784053e-05, "loss": 1.8580282926559448, "num_input_tokens_seen": 4309367, "step": 66, "train_runtime": 1441.6222, "train_tokens_per_second": 2989.249 }, { "epoch": 0.04254643594221305, "grad_norm": 1.3613409996032715, "learning_rate": 1.9991217153338262e-05, "loss": 1.81375253200531, "num_input_tokens_seen": 4374870, "step": 67, "train_runtime": 1463.6195, "train_tokens_per_second": 2989.076 }, { "epoch": 0.043181457374186376, "grad_norm": 1.1513803005218506, "learning_rate": 1.9990936162409573e-05, "loss": 1.7691857814788818, "num_input_tokens_seen": 4440330, "step": 68, "train_runtime": 1485.0083, "train_tokens_per_second": 2990.105 }, { "epoch": 0.04381647880615971, "grad_norm": 1.1990015506744385, "learning_rate": 1.999065074912236e-05, "loss": 1.6750696897506714, "num_input_tokens_seen": 4505806, "step": 69, "train_runtime": 1505.5036, "train_tokens_per_second": 2992.89 }, { "epoch": 0.04445150023813304, "grad_norm": 1.21749746799469, "learning_rate": 1.9990360913602966e-05, "loss": 1.8481522798538208, "num_input_tokens_seen": 4571276, "step": 70, "train_runtime": 1526.911, "train_tokens_per_second": 2993.806 }, { "epoch": 0.045086521670106364, "grad_norm": 1.1938972473144531, "learning_rate": 1.9990066655979672e-05, "loss": 1.8584399223327637, "num_input_tokens_seen": 4636632, "step": 71, "train_runtime": 1548.4803, "train_tokens_per_second": 2994.311 }, { "epoch": 0.045721543102079695, "grad_norm": 1.294428825378418, "learning_rate": 1.9989767976382738e-05, "loss": 1.8324646949768066, "num_input_tokens_seen": 4702109, "step": 72, "train_runtime": 1570.2093, "train_tokens_per_second": 2994.575 }, { "epoch": 0.04635656453405303, "grad_norm": 1.3631923198699951, "learning_rate": 1.9989464874944367e-05, "loss": 1.8890690803527832, "num_input_tokens_seen": 4767421, "step": 73, "train_runtime": 1591.5925, "train_tokens_per_second": 2995.378 }, { "epoch": 0.04699158596602635, "grad_norm": 1.2989964485168457, "learning_rate": 1.9989157351798716e-05, "loss": 1.8567942380905151, "num_input_tokens_seen": 4832933, "step": 74, "train_runtime": 1613.5103, "train_tokens_per_second": 2995.291 }, { "epoch": 0.04762660739799968, "grad_norm": 1.6361254453659058, "learning_rate": 1.9988845407081917e-05, "loss": 1.883217215538025, "num_input_tokens_seen": 4898451, "step": 75, "train_runtime": 1634.9809, "train_tokens_per_second": 2996.03 }, { "epoch": 0.048261628829973015, "grad_norm": 1.3786276578903198, "learning_rate": 1.9988529040932043e-05, "loss": 1.6334378719329834, "num_input_tokens_seen": 4963814, "step": 76, "train_runtime": 1655.5515, "train_tokens_per_second": 2998.284 }, { "epoch": 0.04889665026194634, "grad_norm": 1.1485087871551514, "learning_rate": 1.998820825348913e-05, "loss": 1.6451959609985352, "num_input_tokens_seen": 5029290, "step": 77, "train_runtime": 1676.2529, "train_tokens_per_second": 3000.317 }, { "epoch": 0.04953167169391967, "grad_norm": 1.1787889003753662, "learning_rate": 1.9987883044895168e-05, "loss": 1.6784790754318237, "num_input_tokens_seen": 5094741, "step": 78, "train_runtime": 1697.3972, "train_tokens_per_second": 3001.502 }, { "epoch": 0.050166693125892996, "grad_norm": 1.3979766368865967, "learning_rate": 1.9987553415294108e-05, "loss": 1.8475420475006104, "num_input_tokens_seen": 5160267, "step": 79, "train_runtime": 1719.5739, "train_tokens_per_second": 3000.899 }, { "epoch": 0.05080171455786633, "grad_norm": 1.3097904920578003, "learning_rate": 1.9987219364831855e-05, "loss": 1.8864269256591797, "num_input_tokens_seen": 5225778, "step": 80, "train_runtime": 1741.3083, "train_tokens_per_second": 3001.064 }, { "epoch": 0.05143673598983966, "grad_norm": 1.1950736045837402, "learning_rate": 1.998688089365628e-05, "loss": 1.7854126691818237, "num_input_tokens_seen": 5291227, "step": 81, "train_runtime": 1762.5919, "train_tokens_per_second": 3001.958 }, { "epoch": 0.052071757421812984, "grad_norm": 1.2001692056655884, "learning_rate": 1.998653800191719e-05, "loss": 1.7244755029678345, "num_input_tokens_seen": 5356714, "step": 82, "train_runtime": 1783.7698, "train_tokens_per_second": 3003.03 }, { "epoch": 0.052706778853786315, "grad_norm": 1.181144118309021, "learning_rate": 1.998619068976637e-05, "loss": 1.68143630027771, "num_input_tokens_seen": 5422148, "step": 83, "train_runtime": 1805.3185, "train_tokens_per_second": 3003.43 }, { "epoch": 0.05334180028575965, "grad_norm": 1.2638739347457886, "learning_rate": 1.9985838957357554e-05, "loss": 1.598170280456543, "num_input_tokens_seen": 5487625, "step": 84, "train_runtime": 1826.717, "train_tokens_per_second": 3004.092 }, { "epoch": 0.05397682171773297, "grad_norm": 1.4599838256835938, "learning_rate": 1.998548280484643e-05, "loss": 1.9064178466796875, "num_input_tokens_seen": 5553070, "step": 85, "train_runtime": 1847.6406, "train_tokens_per_second": 3005.493 }, { "epoch": 0.0546118431497063, "grad_norm": 1.2225652933120728, "learning_rate": 1.998512223239064e-05, "loss": 1.8231678009033203, "num_input_tokens_seen": 5618496, "step": 86, "train_runtime": 1868.5736, "train_tokens_per_second": 3006.837 }, { "epoch": 0.055246864581679635, "grad_norm": 1.1953356266021729, "learning_rate": 1.9984757240149793e-05, "loss": 1.6118935346603394, "num_input_tokens_seen": 5683998, "step": 87, "train_runtime": 1889.32, "train_tokens_per_second": 3008.489 }, { "epoch": 0.05588188601365296, "grad_norm": 1.0985076427459717, "learning_rate": 1.9984387828285444e-05, "loss": 1.6171131134033203, "num_input_tokens_seen": 5749471, "step": 88, "train_runtime": 1909.6743, "train_tokens_per_second": 3010.708 }, { "epoch": 0.05651690744562629, "grad_norm": 1.1837304830551147, "learning_rate": 1.998401399696111e-05, "loss": 1.6906073093414307, "num_input_tokens_seen": 5814978, "step": 89, "train_runtime": 1930.7044, "train_tokens_per_second": 3011.843 }, { "epoch": 0.057151928877599616, "grad_norm": 1.2545554637908936, "learning_rate": 1.998363574634226e-05, "loss": 1.8160617351531982, "num_input_tokens_seen": 5880489, "step": 90, "train_runtime": 1951.9888, "train_tokens_per_second": 3012.563 }, { "epoch": 0.05778695030957295, "grad_norm": 1.1284977197647095, "learning_rate": 1.9983253076596326e-05, "loss": 1.6487524509429932, "num_input_tokens_seen": 5945962, "step": 91, "train_runtime": 1973.236, "train_tokens_per_second": 3013.305 }, { "epoch": 0.05842197174154628, "grad_norm": 1.3070428371429443, "learning_rate": 1.9982865987892692e-05, "loss": 1.8845348358154297, "num_input_tokens_seen": 6011481, "step": 92, "train_runtime": 1995.1961, "train_tokens_per_second": 3012.978 }, { "epoch": 0.059056993173519604, "grad_norm": 1.1221034526824951, "learning_rate": 1.9982474480402694e-05, "loss": 1.6119194030761719, "num_input_tokens_seen": 6076994, "step": 93, "train_runtime": 2015.8951, "train_tokens_per_second": 3014.539 }, { "epoch": 0.059692014605492935, "grad_norm": 1.306772232055664, "learning_rate": 1.9982078554299627e-05, "loss": 1.8197511434555054, "num_input_tokens_seen": 6142468, "step": 94, "train_runtime": 2037.3903, "train_tokens_per_second": 3014.871 }, { "epoch": 0.06032703603746627, "grad_norm": 1.633568286895752, "learning_rate": 1.998167820975875e-05, "loss": 2.118601083755493, "num_input_tokens_seen": 6207855, "step": 95, "train_runtime": 2059.8826, "train_tokens_per_second": 3013.694 }, { "epoch": 0.06096205746943959, "grad_norm": 1.161680817604065, "learning_rate": 1.9981273446957264e-05, "loss": 1.6186292171478271, "num_input_tokens_seen": 6273384, "step": 96, "train_runtime": 2081.2287, "train_tokens_per_second": 3014.269 }, { "epoch": 0.06159707890141292, "grad_norm": 1.1545230150222778, "learning_rate": 1.998086426607433e-05, "loss": 1.741215705871582, "num_input_tokens_seen": 6338831, "step": 97, "train_runtime": 2102.1621, "train_tokens_per_second": 3015.386 }, { "epoch": 0.062232100333386255, "grad_norm": 1.2862167358398438, "learning_rate": 1.998045066729107e-05, "loss": 1.7474182844161987, "num_input_tokens_seen": 6404335, "step": 98, "train_runtime": 2123.5609, "train_tokens_per_second": 3015.847 }, { "epoch": 0.06286712176535958, "grad_norm": 1.4787105321884155, "learning_rate": 1.9980032650790564e-05, "loss": 1.846913456916809, "num_input_tokens_seen": 6469810, "step": 99, "train_runtime": 2145.0742, "train_tokens_per_second": 3016.124 }, { "epoch": 0.06350214319733291, "grad_norm": 1.201286792755127, "learning_rate": 1.9979610216757833e-05, "loss": 1.8038769960403442, "num_input_tokens_seen": 6535250, "step": 100, "train_runtime": 2166.0045, "train_tokens_per_second": 3017.191 }, { "epoch": 0.06350214319733291, "eval_loss": 1.6879364252090454, "eval_runtime": 13.4519, "eval_samples_per_second": 1.71, "eval_steps_per_second": 0.892, "num_input_tokens_seen": 6535250, "step": 100 }, { "epoch": 0.06413716462930624, "grad_norm": 1.1742924451828003, "learning_rate": 1.9979183365379863e-05, "loss": 1.6757558584213257, "num_input_tokens_seen": 6600729, "step": 101, "train_runtime": 2235.801, "train_tokens_per_second": 2952.288 }, { "epoch": 0.06477218606127957, "grad_norm": 1.1620787382125854, "learning_rate": 1.9978752096845595e-05, "loss": 1.6899117231369019, "num_input_tokens_seen": 6666181, "step": 102, "train_runtime": 2257.8254, "train_tokens_per_second": 2952.478 }, { "epoch": 0.06540720749325289, "grad_norm": 1.2335869073867798, "learning_rate": 1.9978316411345927e-05, "loss": 1.7893317937850952, "num_input_tokens_seen": 6731651, "step": 103, "train_runtime": 2279.2545, "train_tokens_per_second": 2953.444 }, { "epoch": 0.06604222892522622, "grad_norm": 1.288601279258728, "learning_rate": 1.9977876309073708e-05, "loss": 1.770186424255371, "num_input_tokens_seen": 6797079, "step": 104, "train_runtime": 2300.6927, "train_tokens_per_second": 2954.362 }, { "epoch": 0.06667725035719956, "grad_norm": 1.244727611541748, "learning_rate": 1.9977431790223743e-05, "loss": 1.735649824142456, "num_input_tokens_seen": 6862473, "step": 105, "train_runtime": 2322.4382, "train_tokens_per_second": 2954.857 }, { "epoch": 0.06731227178917289, "grad_norm": 1.195788860321045, "learning_rate": 1.9976982854992793e-05, "loss": 1.8027613162994385, "num_input_tokens_seen": 6927988, "step": 106, "train_runtime": 2344.4224, "train_tokens_per_second": 2955.094 }, { "epoch": 0.06794729322114622, "grad_norm": 1.2379858493804932, "learning_rate": 1.9976529503579573e-05, "loss": 1.7845849990844727, "num_input_tokens_seen": 6993451, "step": 107, "train_runtime": 2365.6756, "train_tokens_per_second": 2956.217 }, { "epoch": 0.06858231465311954, "grad_norm": 1.2615724802017212, "learning_rate": 1.997607173618475e-05, "loss": 1.6528323888778687, "num_input_tokens_seen": 7058929, "step": 108, "train_runtime": 2386.6317, "train_tokens_per_second": 2957.695 }, { "epoch": 0.06921733608509287, "grad_norm": 1.41945219039917, "learning_rate": 1.997560955301096e-05, "loss": 1.6923264265060425, "num_input_tokens_seen": 7124417, "step": 109, "train_runtime": 2408.5977, "train_tokens_per_second": 2957.911 }, { "epoch": 0.0698523575170662, "grad_norm": 1.1106904745101929, "learning_rate": 1.997514295426277e-05, "loss": 1.6578631401062012, "num_input_tokens_seen": 7189859, "step": 110, "train_runtime": 2429.1971, "train_tokens_per_second": 2959.768 }, { "epoch": 0.07048737894903953, "grad_norm": 1.1570007801055908, "learning_rate": 1.9974671940146718e-05, "loss": 1.6915464401245117, "num_input_tokens_seen": 7255347, "step": 111, "train_runtime": 2450.627, "train_tokens_per_second": 2960.609 }, { "epoch": 0.07112240038101286, "grad_norm": 1.2795872688293457, "learning_rate": 1.9974196510871295e-05, "loss": 1.584165096282959, "num_input_tokens_seen": 7320874, "step": 112, "train_runtime": 2472.0265, "train_tokens_per_second": 2961.487 }, { "epoch": 0.0717574218129862, "grad_norm": 1.3594739437103271, "learning_rate": 1.997371666664694e-05, "loss": 1.8469793796539307, "num_input_tokens_seen": 7386233, "step": 113, "train_runtime": 2493.1697, "train_tokens_per_second": 2962.587 }, { "epoch": 0.07239244324495951, "grad_norm": 1.218618392944336, "learning_rate": 1.9973232407686053e-05, "loss": 1.758280634880066, "num_input_tokens_seen": 7451743, "step": 114, "train_runtime": 2514.7503, "train_tokens_per_second": 2963.214 }, { "epoch": 0.07302746467693284, "grad_norm": 1.260719656944275, "learning_rate": 1.997274373420298e-05, "loss": 1.7773958444595337, "num_input_tokens_seen": 7517264, "step": 115, "train_runtime": 2536.3557, "train_tokens_per_second": 2963.805 }, { "epoch": 0.07366248610890617, "grad_norm": 1.3438708782196045, "learning_rate": 1.9972250646414032e-05, "loss": 1.8635667562484741, "num_input_tokens_seen": 7582609, "step": 116, "train_runtime": 2557.7604, "train_tokens_per_second": 2964.55 }, { "epoch": 0.0742975075408795, "grad_norm": 1.201453447341919, "learning_rate": 1.9971753144537464e-05, "loss": 1.6791876554489136, "num_input_tokens_seen": 7648123, "step": 117, "train_runtime": 2579.5743, "train_tokens_per_second": 2964.878 }, { "epoch": 0.07493252897285284, "grad_norm": 1.0665103197097778, "learning_rate": 1.997125122879349e-05, "loss": 1.6029027700424194, "num_input_tokens_seen": 7713503, "step": 118, "train_runtime": 2600.1961, "train_tokens_per_second": 2966.508 }, { "epoch": 0.07556755040482617, "grad_norm": 1.322712779045105, "learning_rate": 1.9970744899404275e-05, "loss": 1.666275143623352, "num_input_tokens_seen": 7779029, "step": 119, "train_runtime": 2622.0583, "train_tokens_per_second": 2966.764 }, { "epoch": 0.07620257183679949, "grad_norm": 1.221177577972412, "learning_rate": 1.9970234156593943e-05, "loss": 1.8089711666107178, "num_input_tokens_seen": 7844445, "step": 120, "train_runtime": 2643.0497, "train_tokens_per_second": 2967.952 }, { "epoch": 0.07683759326877282, "grad_norm": 1.136902093887329, "learning_rate": 1.9969719000588564e-05, "loss": 1.56723952293396, "num_input_tokens_seen": 7909898, "step": 121, "train_runtime": 2663.9037, "train_tokens_per_second": 2969.288 }, { "epoch": 0.07747261470074615, "grad_norm": 1.1760996580123901, "learning_rate": 1.9969199431616168e-05, "loss": 1.7701627016067505, "num_input_tokens_seen": 7975427, "step": 122, "train_runtime": 2685.2806, "train_tokens_per_second": 2970.053 }, { "epoch": 0.07810763613271948, "grad_norm": 1.3228759765625, "learning_rate": 1.9968675449906733e-05, "loss": 1.82855224609375, "num_input_tokens_seen": 8040902, "step": 123, "train_runtime": 2707.2681, "train_tokens_per_second": 2970.117 }, { "epoch": 0.07874265756469281, "grad_norm": 1.1714316606521606, "learning_rate": 1.9968147055692194e-05, "loss": 1.6516833305358887, "num_input_tokens_seen": 8106403, "step": 124, "train_runtime": 2729.21, "train_tokens_per_second": 2970.238 }, { "epoch": 0.07937767899666613, "grad_norm": 1.2140318155288696, "learning_rate": 1.9967614249206434e-05, "loss": 1.9301788806915283, "num_input_tokens_seen": 8171900, "step": 125, "train_runtime": 2749.9357, "train_tokens_per_second": 2971.67 }, { "epoch": 0.08001270042863946, "grad_norm": 1.3971279859542847, "learning_rate": 1.99670770306853e-05, "loss": 1.9210944175720215, "num_input_tokens_seen": 8237376, "step": 126, "train_runtime": 2771.6963, "train_tokens_per_second": 2971.962 }, { "epoch": 0.0806477218606128, "grad_norm": 1.2012810707092285, "learning_rate": 1.9966535400366584e-05, "loss": 1.6981947422027588, "num_input_tokens_seen": 8302883, "step": 127, "train_runtime": 2793.2605, "train_tokens_per_second": 2972.47 }, { "epoch": 0.08128274329258613, "grad_norm": 1.2293685674667358, "learning_rate": 1.9965989358490023e-05, "loss": 1.6696183681488037, "num_input_tokens_seen": 8368350, "step": 128, "train_runtime": 2815.2249, "train_tokens_per_second": 2972.533 }, { "epoch": 0.08191776472455946, "grad_norm": 1.2919025421142578, "learning_rate": 1.9965438905297322e-05, "loss": 1.8530497550964355, "num_input_tokens_seen": 8433870, "step": 129, "train_runtime": 2837.0888, "train_tokens_per_second": 2972.72 }, { "epoch": 0.08255278615653279, "grad_norm": 1.2325356006622314, "learning_rate": 1.9964884041032135e-05, "loss": 1.6828112602233887, "num_input_tokens_seen": 8499344, "step": 130, "train_runtime": 2858.131, "train_tokens_per_second": 2973.742 }, { "epoch": 0.08318780758850611, "grad_norm": 1.3253751993179321, "learning_rate": 1.9964324765940056e-05, "loss": 1.7412135601043701, "num_input_tokens_seen": 8564838, "step": 131, "train_runtime": 2880.3758, "train_tokens_per_second": 2973.514 }, { "epoch": 0.08382282902047944, "grad_norm": 1.2448545694351196, "learning_rate": 1.996376108026865e-05, "loss": 1.7128920555114746, "num_input_tokens_seen": 8622337, "step": 132, "train_runtime": 2898.9188, "train_tokens_per_second": 2974.329 }, { "epoch": 0.08445785045245277, "grad_norm": 1.1643942594528198, "learning_rate": 1.9963192984267423e-05, "loss": 1.4655694961547852, "num_input_tokens_seen": 8687862, "step": 133, "train_runtime": 2919.907, "train_tokens_per_second": 2975.39 }, { "epoch": 0.0850928718844261, "grad_norm": 1.189064383506775, "learning_rate": 1.996262047818783e-05, "loss": 1.697664499282837, "num_input_tokens_seen": 8753340, "step": 134, "train_runtime": 2941.3774, "train_tokens_per_second": 2975.932 }, { "epoch": 0.08572789331639943, "grad_norm": 1.255765676498413, "learning_rate": 1.9962043562283293e-05, "loss": 2.0268397331237793, "num_input_tokens_seen": 8818834, "step": 135, "train_runtime": 2963.5724, "train_tokens_per_second": 2975.744 }, { "epoch": 0.08636291474837275, "grad_norm": 1.1256183385849, "learning_rate": 1.9961462236809166e-05, "loss": 1.5301152467727661, "num_input_tokens_seen": 8884353, "step": 136, "train_runtime": 2984.759, "train_tokens_per_second": 2976.573 }, { "epoch": 0.08699793618034608, "grad_norm": 1.3555488586425781, "learning_rate": 1.9960876502022772e-05, "loss": 1.8166217803955078, "num_input_tokens_seen": 8949883, "step": 137, "train_runtime": 3007.8813, "train_tokens_per_second": 2975.477 }, { "epoch": 0.08763295761231941, "grad_norm": 1.221164345741272, "learning_rate": 1.9960286358183377e-05, "loss": 1.6045093536376953, "num_input_tokens_seen": 9015233, "step": 138, "train_runtime": 3028.5698, "train_tokens_per_second": 2976.729 }, { "epoch": 0.08826797904429275, "grad_norm": 1.4856220483779907, "learning_rate": 1.99596918055522e-05, "loss": 1.7944003343582153, "num_input_tokens_seen": 9080682, "step": 139, "train_runtime": 3050.2249, "train_tokens_per_second": 2977.053 }, { "epoch": 0.08890300047626608, "grad_norm": 1.1770105361938477, "learning_rate": 1.9959092844392415e-05, "loss": 1.6798094511032104, "num_input_tokens_seen": 9146157, "step": 140, "train_runtime": 3071.8536, "train_tokens_per_second": 2977.407 }, { "epoch": 0.08953802190823941, "grad_norm": 1.1725057363510132, "learning_rate": 1.9958489474969136e-05, "loss": 1.5733022689819336, "num_input_tokens_seen": 9211595, "step": 141, "train_runtime": 3092.5466, "train_tokens_per_second": 2978.644 }, { "epoch": 0.09017304334021273, "grad_norm": 1.3395828008651733, "learning_rate": 1.9957881697549446e-05, "loss": 1.718605399131775, "num_input_tokens_seen": 9276994, "step": 142, "train_runtime": 3113.1933, "train_tokens_per_second": 2979.897 }, { "epoch": 0.09080806477218606, "grad_norm": 1.2440860271453857, "learning_rate": 1.9957269512402368e-05, "loss": 1.675902009010315, "num_input_tokens_seen": 9342480, "step": 143, "train_runtime": 3134.2976, "train_tokens_per_second": 2980.725 }, { "epoch": 0.09144308620415939, "grad_norm": 1.235442042350769, "learning_rate": 1.9956652919798875e-05, "loss": 1.7457846403121948, "num_input_tokens_seen": 9407952, "step": 144, "train_runtime": 3155.5858, "train_tokens_per_second": 2981.365 }, { "epoch": 0.09207810763613272, "grad_norm": 1.244462013244629, "learning_rate": 1.995603192001189e-05, "loss": 1.7028682231903076, "num_input_tokens_seen": 9473423, "step": 145, "train_runtime": 3176.5628, "train_tokens_per_second": 2982.287 }, { "epoch": 0.09271312906810605, "grad_norm": 1.1975092887878418, "learning_rate": 1.9955406513316303e-05, "loss": 1.6798268556594849, "num_input_tokens_seen": 9538842, "step": 146, "train_runtime": 3197.2245, "train_tokens_per_second": 2983.476 }, { "epoch": 0.09334815050007937, "grad_norm": 1.3685848712921143, "learning_rate": 1.995477669998893e-05, "loss": 1.6967568397521973, "num_input_tokens_seen": 9600543, "step": 147, "train_runtime": 3217.5951, "train_tokens_per_second": 2983.764 }, { "epoch": 0.0939831719320527, "grad_norm": 1.256829857826233, "learning_rate": 1.9954142480308553e-05, "loss": 1.6899917125701904, "num_input_tokens_seen": 9665983, "step": 148, "train_runtime": 3238.5811, "train_tokens_per_second": 2984.635 }, { "epoch": 0.09461819336402603, "grad_norm": 1.2667938470840454, "learning_rate": 1.9953503854555904e-05, "loss": 1.758558750152588, "num_input_tokens_seen": 9731476, "step": 149, "train_runtime": 3260.9751, "train_tokens_per_second": 2984.223 }, { "epoch": 0.09525321479599937, "grad_norm": 1.2356078624725342, "learning_rate": 1.9952860823013665e-05, "loss": 1.62161123752594, "num_input_tokens_seen": 9796989, "step": 150, "train_runtime": 3282.0234, "train_tokens_per_second": 2985.045 }, { "epoch": 0.0958882362279727, "grad_norm": 1.2293976545333862, "learning_rate": 1.9952213385966453e-05, "loss": 1.4736192226409912, "num_input_tokens_seen": 9862464, "step": 151, "train_runtime": 3303.8063, "train_tokens_per_second": 2985.182 }, { "epoch": 0.09652325765994603, "grad_norm": 1.309288740158081, "learning_rate": 1.9951561543700864e-05, "loss": 1.722478985786438, "num_input_tokens_seen": 9927987, "step": 152, "train_runtime": 3325.9091, "train_tokens_per_second": 2985.045 }, { "epoch": 0.09715827909191935, "grad_norm": 1.1604773998260498, "learning_rate": 1.9950905296505417e-05, "loss": 1.6552201509475708, "num_input_tokens_seen": 9993326, "step": 153, "train_runtime": 3346.2293, "train_tokens_per_second": 2986.444 }, { "epoch": 0.09779330052389268, "grad_norm": 1.1349074840545654, "learning_rate": 1.9950244644670594e-05, "loss": 1.7063963413238525, "num_input_tokens_seen": 10058837, "step": 154, "train_runtime": 3367.5502, "train_tokens_per_second": 2986.99 }, { "epoch": 0.09842832195586601, "grad_norm": 1.2475574016571045, "learning_rate": 1.994957958848882e-05, "loss": 1.707419753074646, "num_input_tokens_seen": 10124325, "step": 155, "train_runtime": 3388.5194, "train_tokens_per_second": 2987.831 }, { "epoch": 0.09906334338783934, "grad_norm": 1.2250398397445679, "learning_rate": 1.9948910128254485e-05, "loss": 1.597198247909546, "num_input_tokens_seen": 10189792, "step": 156, "train_runtime": 3409.5181, "train_tokens_per_second": 2988.631 }, { "epoch": 0.09969836481981267, "grad_norm": 1.0934034585952759, "learning_rate": 1.9948236264263903e-05, "loss": 1.6081575155258179, "num_input_tokens_seen": 10255206, "step": 157, "train_runtime": 3430.4891, "train_tokens_per_second": 2989.43 }, { "epoch": 0.10033338625178599, "grad_norm": 1.3819937705993652, "learning_rate": 1.994755799681536e-05, "loss": 1.9763672351837158, "num_input_tokens_seen": 10320558, "step": 158, "train_runtime": 3452.5612, "train_tokens_per_second": 2989.247 }, { "epoch": 0.10096840768375932, "grad_norm": 1.223982334136963, "learning_rate": 1.994687532620908e-05, "loss": 1.7421683073043823, "num_input_tokens_seen": 10386075, "step": 159, "train_runtime": 3473.3582, "train_tokens_per_second": 2990.211 }, { "epoch": 0.10160342911573265, "grad_norm": 1.3765647411346436, "learning_rate": 1.9946188252747235e-05, "loss": 1.9410061836242676, "num_input_tokens_seen": 10451575, "step": 160, "train_runtime": 3495.0013, "train_tokens_per_second": 2990.435 }, { "epoch": 0.10223845054770599, "grad_norm": 1.4303128719329834, "learning_rate": 1.9945496776733956e-05, "loss": 1.8443822860717773, "num_input_tokens_seen": 10516935, "step": 161, "train_runtime": 3517.2901, "train_tokens_per_second": 2990.068 }, { "epoch": 0.10287347197967932, "grad_norm": 1.3349913358688354, "learning_rate": 1.994480089847531e-05, "loss": 1.748458743095398, "num_input_tokens_seen": 10582411, "step": 162, "train_runtime": 3539.0705, "train_tokens_per_second": 2990.167 }, { "epoch": 0.10350849341165265, "grad_norm": 1.3815348148345947, "learning_rate": 1.994410061827932e-05, "loss": 1.7189643383026123, "num_input_tokens_seen": 10647787, "step": 163, "train_runtime": 3560.0079, "train_tokens_per_second": 2990.945 }, { "epoch": 0.10414351484362597, "grad_norm": 1.1973050832748413, "learning_rate": 1.994339593645596e-05, "loss": 1.7068758010864258, "num_input_tokens_seen": 10713292, "step": 164, "train_runtime": 3581.4661, "train_tokens_per_second": 2991.315 }, { "epoch": 0.1047785362755993, "grad_norm": 1.2895262241363525, "learning_rate": 1.9942686853317142e-05, "loss": 1.8158377408981323, "num_input_tokens_seen": 10778817, "step": 165, "train_runtime": 3602.8105, "train_tokens_per_second": 2991.78 }, { "epoch": 0.10541355770757263, "grad_norm": 1.2750022411346436, "learning_rate": 1.9941973369176738e-05, "loss": 1.706038236618042, "num_input_tokens_seen": 10844212, "step": 166, "train_runtime": 3623.5521, "train_tokens_per_second": 2992.702 }, { "epoch": 0.10604857913954596, "grad_norm": 1.304460048675537, "learning_rate": 1.9941255484350558e-05, "loss": 1.7393312454223633, "num_input_tokens_seen": 10908157, "step": 167, "train_runtime": 3644.6008, "train_tokens_per_second": 2992.963 }, { "epoch": 0.1066836005715193, "grad_norm": 1.2512770891189575, "learning_rate": 1.9940533199156365e-05, "loss": 1.5460563898086548, "num_input_tokens_seen": 10973566, "step": 168, "train_runtime": 3666.7082, "train_tokens_per_second": 2992.757 }, { "epoch": 0.10731862200349261, "grad_norm": 1.1782184839248657, "learning_rate": 1.993980651391387e-05, "loss": 1.7100411653518677, "num_input_tokens_seen": 11038940, "step": 169, "train_runtime": 3687.9956, "train_tokens_per_second": 2993.209 }, { "epoch": 0.10795364343546594, "grad_norm": 1.363459825515747, "learning_rate": 1.9939075428944734e-05, "loss": 1.9897477626800537, "num_input_tokens_seen": 11104437, "step": 170, "train_runtime": 3709.7079, "train_tokens_per_second": 2993.345 }, { "epoch": 0.10858866486743927, "grad_norm": 1.305191159248352, "learning_rate": 1.9938339944572557e-05, "loss": 1.7270714044570923, "num_input_tokens_seen": 11169971, "step": 171, "train_runtime": 3731.1094, "train_tokens_per_second": 2993.74 }, { "epoch": 0.1092236862994126, "grad_norm": 1.2158015966415405, "learning_rate": 1.9937600061122897e-05, "loss": 1.6965951919555664, "num_input_tokens_seen": 11235445, "step": 172, "train_runtime": 3752.8546, "train_tokens_per_second": 2993.84 }, { "epoch": 0.10985870773138594, "grad_norm": 1.190920352935791, "learning_rate": 1.993685577892325e-05, "loss": 1.5332112312316895, "num_input_tokens_seen": 11300975, "step": 173, "train_runtime": 3774.2556, "train_tokens_per_second": 2994.226 }, { "epoch": 0.11049372916335927, "grad_norm": 1.2575087547302246, "learning_rate": 1.9936107098303062e-05, "loss": 1.7808482646942139, "num_input_tokens_seen": 11366331, "step": 174, "train_runtime": 3795.4586, "train_tokens_per_second": 2994.719 }, { "epoch": 0.11112875059533259, "grad_norm": 1.3175253868103027, "learning_rate": 1.9935354019593732e-05, "loss": 1.9778255224227905, "num_input_tokens_seen": 11431799, "step": 175, "train_runtime": 3817.3678, "train_tokens_per_second": 2994.681 }, { "epoch": 0.11176377202730592, "grad_norm": 1.373157262802124, "learning_rate": 1.9934596543128598e-05, "loss": 1.7144501209259033, "num_input_tokens_seen": 11497246, "step": 176, "train_runtime": 3839.2961, "train_tokens_per_second": 2994.623 }, { "epoch": 0.11239879345927925, "grad_norm": 1.3676069974899292, "learning_rate": 1.9933834669242943e-05, "loss": 1.8555576801300049, "num_input_tokens_seen": 11562725, "step": 177, "train_runtime": 3860.8715, "train_tokens_per_second": 2994.848 }, { "epoch": 0.11303381489125258, "grad_norm": 1.1868387460708618, "learning_rate": 1.9933068398274004e-05, "loss": 1.679984211921692, "num_input_tokens_seen": 11628135, "step": 178, "train_runtime": 3881.7963, "train_tokens_per_second": 2995.555 }, { "epoch": 0.11366883632322591, "grad_norm": 1.1381927728652954, "learning_rate": 1.993229773056096e-05, "loss": 1.4652128219604492, "num_input_tokens_seen": 11693633, "step": 179, "train_runtime": 3902.5353, "train_tokens_per_second": 2996.42 }, { "epoch": 0.11430385775519923, "grad_norm": 1.3684247732162476, "learning_rate": 1.993152266644494e-05, "loss": 1.8984899520874023, "num_input_tokens_seen": 11759080, "step": 180, "train_runtime": 3923.9527, "train_tokens_per_second": 2996.744 }, { "epoch": 0.11493887918717256, "grad_norm": 1.2045581340789795, "learning_rate": 1.9930743206269016e-05, "loss": 1.5347696542739868, "num_input_tokens_seen": 11824506, "step": 181, "train_runtime": 3944.8336, "train_tokens_per_second": 2997.466 }, { "epoch": 0.1155739006191459, "grad_norm": 1.2007551193237305, "learning_rate": 1.9929959350378203e-05, "loss": 1.6021254062652588, "num_input_tokens_seen": 11889995, "step": 182, "train_runtime": 3965.7699, "train_tokens_per_second": 2998.156 }, { "epoch": 0.11620892205111923, "grad_norm": 1.097260594367981, "learning_rate": 1.9929171099119463e-05, "loss": 1.5528969764709473, "num_input_tokens_seen": 11955518, "step": 183, "train_runtime": 3986.6309, "train_tokens_per_second": 2998.903 }, { "epoch": 0.11684394348309256, "grad_norm": 1.2147142887115479, "learning_rate": 1.992837845284171e-05, "loss": 1.6549015045166016, "num_input_tokens_seen": 12021022, "step": 184, "train_runtime": 4007.8961, "train_tokens_per_second": 2999.335 }, { "epoch": 0.11747896491506589, "grad_norm": 1.2402926683425903, "learning_rate": 1.99275814118958e-05, "loss": 1.6583211421966553, "num_input_tokens_seen": 12086527, "step": 185, "train_runtime": 4029.0291, "train_tokens_per_second": 2999.861 }, { "epoch": 0.11811398634703921, "grad_norm": 1.3354586362838745, "learning_rate": 1.9926779976634524e-05, "loss": 1.7751270532608032, "num_input_tokens_seen": 12152031, "step": 186, "train_runtime": 4050.859, "train_tokens_per_second": 2999.865 }, { "epoch": 0.11874900777901254, "grad_norm": 1.1910462379455566, "learning_rate": 1.9925974147412634e-05, "loss": 1.535996675491333, "num_input_tokens_seen": 12217507, "step": 187, "train_runtime": 4071.6826, "train_tokens_per_second": 3000.604 }, { "epoch": 0.11938402921098587, "grad_norm": 1.362522840499878, "learning_rate": 1.992516392458682e-05, "loss": 1.8042337894439697, "num_input_tokens_seen": 12283031, "step": 188, "train_runtime": 4093.3553, "train_tokens_per_second": 3000.724 }, { "epoch": 0.1200190506429592, "grad_norm": 1.3003349304199219, "learning_rate": 1.9924349308515714e-05, "loss": 1.850663661956787, "num_input_tokens_seen": 12348512, "step": 189, "train_runtime": 4115.562, "train_tokens_per_second": 3000.444 }, { "epoch": 0.12065407207493253, "grad_norm": 1.1523704528808594, "learning_rate": 1.9923530299559895e-05, "loss": 1.7297735214233398, "num_input_tokens_seen": 12414036, "step": 190, "train_runtime": 4136.8343, "train_tokens_per_second": 3000.854 }, { "epoch": 0.12128909350690585, "grad_norm": 1.2351033687591553, "learning_rate": 1.9922706898081886e-05, "loss": 1.7091602087020874, "num_input_tokens_seen": 12479505, "step": 191, "train_runtime": 4158.7406, "train_tokens_per_second": 3000.789 }, { "epoch": 0.12192411493887918, "grad_norm": 1.2485190629959106, "learning_rate": 1.992187910444616e-05, "loss": 1.6829520463943481, "num_input_tokens_seen": 12544994, "step": 192, "train_runtime": 4180.3494, "train_tokens_per_second": 3000.944 }, { "epoch": 0.12255913637085251, "grad_norm": 1.350883960723877, "learning_rate": 1.9921046919019123e-05, "loss": 1.825562834739685, "num_input_tokens_seen": 12610491, "step": 193, "train_runtime": 4202.3684, "train_tokens_per_second": 3000.806 }, { "epoch": 0.12319415780282585, "grad_norm": 1.1320747137069702, "learning_rate": 1.9920210342169137e-05, "loss": 1.5774811506271362, "num_input_tokens_seen": 12675873, "step": 194, "train_runtime": 4223.6849, "train_tokens_per_second": 3001.141 }, { "epoch": 0.12382917923479918, "grad_norm": 1.3208972215652466, "learning_rate": 1.9919369374266498e-05, "loss": 1.7433016300201416, "num_input_tokens_seen": 12741336, "step": 195, "train_runtime": 4245.4831, "train_tokens_per_second": 3001.151 }, { "epoch": 0.12446420066677251, "grad_norm": 1.2750117778778076, "learning_rate": 1.991852401568345e-05, "loss": 1.8887197971343994, "num_input_tokens_seen": 12806864, "step": 196, "train_runtime": 4267.476, "train_tokens_per_second": 3001.039 }, { "epoch": 0.12509922209874583, "grad_norm": 1.193264126777649, "learning_rate": 1.9917674266794182e-05, "loss": 1.703880786895752, "num_input_tokens_seen": 12872399, "step": 197, "train_runtime": 4289.9711, "train_tokens_per_second": 3000.579 }, { "epoch": 0.12573424353071916, "grad_norm": 1.115492820739746, "learning_rate": 1.9916820127974823e-05, "loss": 1.6341458559036255, "num_input_tokens_seen": 12937916, "step": 198, "train_runtime": 4311.5495, "train_tokens_per_second": 3000.758 }, { "epoch": 0.1263692649626925, "grad_norm": 1.2370837926864624, "learning_rate": 1.9915961599603446e-05, "loss": 1.7835971117019653, "num_input_tokens_seen": 13003423, "step": 199, "train_runtime": 4332.8336, "train_tokens_per_second": 3001.136 }, { "epoch": 0.12700428639466582, "grad_norm": 1.2685354948043823, "learning_rate": 1.9915098682060067e-05, "loss": 1.7696585655212402, "num_input_tokens_seen": 13068913, "step": 200, "train_runtime": 4353.5686, "train_tokens_per_second": 3001.885 }, { "epoch": 0.12700428639466582, "eval_loss": 1.6584253311157227, "eval_runtime": 12.9253, "eval_samples_per_second": 1.779, "eval_steps_per_second": 0.928, "num_input_tokens_seen": 13068913, "step": 200 }, { "epoch": 0.12763930782663915, "grad_norm": 1.3961360454559326, "learning_rate": 1.9914231375726646e-05, "loss": 1.9136781692504883, "num_input_tokens_seen": 13134291, "step": 201, "train_runtime": 4423.5201, "train_tokens_per_second": 2969.194 }, { "epoch": 0.12827432925861249, "grad_norm": 1.3090770244598389, "learning_rate": 1.9913359680987086e-05, "loss": 1.8277721405029297, "num_input_tokens_seen": 13199713, "step": 202, "train_runtime": 4444.4619, "train_tokens_per_second": 2969.924 }, { "epoch": 0.12890935069058582, "grad_norm": 1.1515687704086304, "learning_rate": 1.991248359822723e-05, "loss": 1.5782488584518433, "num_input_tokens_seen": 13265121, "step": 203, "train_runtime": 4465.6709, "train_tokens_per_second": 2970.465 }, { "epoch": 0.12954437212255915, "grad_norm": 1.2481768131256104, "learning_rate": 1.9911603127834865e-05, "loss": 1.6697371006011963, "num_input_tokens_seen": 13330597, "step": 204, "train_runtime": 4486.7917, "train_tokens_per_second": 2971.076 }, { "epoch": 0.13017939355453245, "grad_norm": 1.2351412773132324, "learning_rate": 1.9910718270199717e-05, "loss": 1.598862648010254, "num_input_tokens_seen": 13396074, "step": 205, "train_runtime": 4507.6551, "train_tokens_per_second": 2971.85 }, { "epoch": 0.13081441498650578, "grad_norm": 1.2481666803359985, "learning_rate": 1.9909829025713464e-05, "loss": 1.7631185054779053, "num_input_tokens_seen": 13461472, "step": 206, "train_runtime": 4528.4968, "train_tokens_per_second": 2972.614 }, { "epoch": 0.13144943641847912, "grad_norm": 1.2166751623153687, "learning_rate": 1.9908935394769714e-05, "loss": 1.7020601034164429, "num_input_tokens_seen": 13526956, "step": 207, "train_runtime": 4549.5938, "train_tokens_per_second": 2973.223 }, { "epoch": 0.13208445785045245, "grad_norm": 1.2323373556137085, "learning_rate": 1.990803737776402e-05, "loss": 1.8462514877319336, "num_input_tokens_seen": 13592425, "step": 208, "train_runtime": 4571.2155, "train_tokens_per_second": 2973.482 }, { "epoch": 0.13271947928242578, "grad_norm": 1.3750417232513428, "learning_rate": 1.990713497509388e-05, "loss": 1.9561266899108887, "num_input_tokens_seen": 13657893, "step": 209, "train_runtime": 4592.733, "train_tokens_per_second": 2973.805 }, { "epoch": 0.1333545007143991, "grad_norm": 1.064685344696045, "learning_rate": 1.9906228187158725e-05, "loss": 1.6156315803527832, "num_input_tokens_seen": 13723420, "step": 210, "train_runtime": 4613.9357, "train_tokens_per_second": 2974.341 }, { "epoch": 0.13398952214637244, "grad_norm": 1.15648353099823, "learning_rate": 1.9905317014359947e-05, "loss": 1.6246604919433594, "num_input_tokens_seen": 13788844, "step": 211, "train_runtime": 4635.3842, "train_tokens_per_second": 2974.693 }, { "epoch": 0.13462454357834577, "grad_norm": 1.347033143043518, "learning_rate": 1.990440145710085e-05, "loss": 1.863343358039856, "num_input_tokens_seen": 13854157, "step": 212, "train_runtime": 4656.5912, "train_tokens_per_second": 2975.171 }, { "epoch": 0.1352595650103191, "grad_norm": 1.4236644506454468, "learning_rate": 1.9903481515786698e-05, "loss": 1.964641809463501, "num_input_tokens_seen": 13919545, "step": 213, "train_runtime": 4678.0694, "train_tokens_per_second": 2975.489 }, { "epoch": 0.13589458644229244, "grad_norm": 1.2394276857376099, "learning_rate": 1.9902557190824696e-05, "loss": 1.7071361541748047, "num_input_tokens_seen": 13985008, "step": 214, "train_runtime": 4699.1659, "train_tokens_per_second": 2976.062 }, { "epoch": 0.13652960787426577, "grad_norm": 1.2650033235549927, "learning_rate": 1.9901628482623977e-05, "loss": 1.813634991645813, "num_input_tokens_seen": 14050435, "step": 215, "train_runtime": 4720.5405, "train_tokens_per_second": 2976.446 }, { "epoch": 0.13716462930623907, "grad_norm": 1.3260979652404785, "learning_rate": 1.990069539159563e-05, "loss": 1.7507274150848389, "num_input_tokens_seen": 14115947, "step": 216, "train_runtime": 4741.2396, "train_tokens_per_second": 2977.269 }, { "epoch": 0.1377996507382124, "grad_norm": 1.1742558479309082, "learning_rate": 1.9899757918152667e-05, "loss": 1.7127277851104736, "num_input_tokens_seen": 14181342, "step": 217, "train_runtime": 4761.9524, "train_tokens_per_second": 2978.052 }, { "epoch": 0.13843467217018574, "grad_norm": 1.323478102684021, "learning_rate": 1.9898816062710054e-05, "loss": 1.9001775979995728, "num_input_tokens_seen": 14246816, "step": 218, "train_runtime": 4783.3591, "train_tokens_per_second": 2978.412 }, { "epoch": 0.13906969360215907, "grad_norm": 1.2976070642471313, "learning_rate": 1.989786982568469e-05, "loss": 1.5497658252716064, "num_input_tokens_seen": 14312349, "step": 219, "train_runtime": 4804.3924, "train_tokens_per_second": 2979.013 }, { "epoch": 0.1397047150341324, "grad_norm": 1.436448097229004, "learning_rate": 1.9896919207495416e-05, "loss": 1.8721976280212402, "num_input_tokens_seen": 14377825, "step": 220, "train_runtime": 4825.6172, "train_tokens_per_second": 2979.479 }, { "epoch": 0.14033973646610573, "grad_norm": 1.3399673700332642, "learning_rate": 1.9895964208563007e-05, "loss": 1.6109317541122437, "num_input_tokens_seen": 14442047, "step": 221, "train_runtime": 4846.3783, "train_tokens_per_second": 2979.967 }, { "epoch": 0.14097475789807906, "grad_norm": 1.1578738689422607, "learning_rate": 1.9895004829310185e-05, "loss": 1.7460529804229736, "num_input_tokens_seen": 14507477, "step": 222, "train_runtime": 4868.173, "train_tokens_per_second": 2980.066 }, { "epoch": 0.1416097793300524, "grad_norm": 1.2187174558639526, "learning_rate": 1.9894041070161604e-05, "loss": 1.767241358757019, "num_input_tokens_seen": 14572924, "step": 223, "train_runtime": 4888.9283, "train_tokens_per_second": 2980.801 }, { "epoch": 0.14224480076202572, "grad_norm": 1.2083284854888916, "learning_rate": 1.9893072931543858e-05, "loss": 1.6362651586532593, "num_input_tokens_seen": 14638456, "step": 224, "train_runtime": 4910.5394, "train_tokens_per_second": 2981.028 }, { "epoch": 0.14287982219399906, "grad_norm": 1.251765489578247, "learning_rate": 1.9892100413885488e-05, "loss": 1.5002670288085938, "num_input_tokens_seen": 14703885, "step": 225, "train_runtime": 4932.1685, "train_tokens_per_second": 2981.221 }, { "epoch": 0.1435148436259724, "grad_norm": 1.1355936527252197, "learning_rate": 1.9891123517616955e-05, "loss": 1.7294487953186035, "num_input_tokens_seen": 14769309, "step": 226, "train_runtime": 4953.2174, "train_tokens_per_second": 2981.761 }, { "epoch": 0.1441498650579457, "grad_norm": 1.2095119953155518, "learning_rate": 1.9890142243170683e-05, "loss": 1.7133829593658447, "num_input_tokens_seen": 14834798, "step": 227, "train_runtime": 4975.2594, "train_tokens_per_second": 2981.713 }, { "epoch": 0.14478488648991902, "grad_norm": 1.150040864944458, "learning_rate": 1.988915659098101e-05, "loss": 1.4599276781082153, "num_input_tokens_seen": 14900280, "step": 228, "train_runtime": 4996.4584, "train_tokens_per_second": 2982.168 }, { "epoch": 0.14541990792189236, "grad_norm": 1.2972090244293213, "learning_rate": 1.9888166561484226e-05, "loss": 1.939143180847168, "num_input_tokens_seen": 14965759, "step": 229, "train_runtime": 5018.3972, "train_tokens_per_second": 2982.179 }, { "epoch": 0.1460549293538657, "grad_norm": 1.144862413406372, "learning_rate": 1.9887172155118555e-05, "loss": 1.7169311046600342, "num_input_tokens_seen": 15031229, "step": 230, "train_runtime": 5040.1973, "train_tokens_per_second": 2982.27 }, { "epoch": 0.14668995078583902, "grad_norm": 1.252683162689209, "learning_rate": 1.988617337232416e-05, "loss": 1.5853774547576904, "num_input_tokens_seen": 15096746, "step": 231, "train_runtime": 5061.643, "train_tokens_per_second": 2982.578 }, { "epoch": 0.14732497221781235, "grad_norm": 1.3370603322982788, "learning_rate": 1.9885170213543134e-05, "loss": 1.7477235794067383, "num_input_tokens_seen": 15162252, "step": 232, "train_runtime": 5083.4842, "train_tokens_per_second": 2982.65 }, { "epoch": 0.14795999364978568, "grad_norm": 1.2241421937942505, "learning_rate": 1.9884162679219513e-05, "loss": 1.6800278425216675, "num_input_tokens_seen": 15227698, "step": 233, "train_runtime": 5104.7841, "train_tokens_per_second": 2983.025 }, { "epoch": 0.148595015081759, "grad_norm": 1.2776237726211548, "learning_rate": 1.9883150769799276e-05, "loss": 1.6895530223846436, "num_input_tokens_seen": 15293165, "step": 234, "train_runtime": 5126.8977, "train_tokens_per_second": 2982.928 }, { "epoch": 0.14923003651373234, "grad_norm": 1.2778767347335815, "learning_rate": 1.9882134485730326e-05, "loss": 1.8440043926239014, "num_input_tokens_seen": 15358607, "step": 235, "train_runtime": 5148.6769, "train_tokens_per_second": 2983.02 }, { "epoch": 0.14986505794570568, "grad_norm": 1.2877593040466309, "learning_rate": 1.9881113827462506e-05, "loss": 1.7629938125610352, "num_input_tokens_seen": 15424125, "step": 236, "train_runtime": 5170.2081, "train_tokens_per_second": 2983.27 }, { "epoch": 0.150500079377679, "grad_norm": 1.3307561874389648, "learning_rate": 1.98800887954476e-05, "loss": 1.7095739841461182, "num_input_tokens_seen": 15484541, "step": 237, "train_runtime": 5190.4174, "train_tokens_per_second": 2983.294 }, { "epoch": 0.15113510080965234, "grad_norm": 1.3635913133621216, "learning_rate": 1.987905939013933e-05, "loss": 1.7196941375732422, "num_input_tokens_seen": 15549987, "step": 238, "train_runtime": 5211.4249, "train_tokens_per_second": 2983.826 }, { "epoch": 0.15177012224162564, "grad_norm": 1.1402523517608643, "learning_rate": 1.987802561199334e-05, "loss": 1.6328372955322266, "num_input_tokens_seen": 15615472, "step": 239, "train_runtime": 5232.2248, "train_tokens_per_second": 2984.48 }, { "epoch": 0.15240514367359898, "grad_norm": 1.0925745964050293, "learning_rate": 1.9876987461467223e-05, "loss": 1.5826640129089355, "num_input_tokens_seen": 15681001, "step": 240, "train_runtime": 5253.1382, "train_tokens_per_second": 2985.073 }, { "epoch": 0.1530401651055723, "grad_norm": 1.2668514251708984, "learning_rate": 1.9875944939020503e-05, "loss": 1.703583002090454, "num_input_tokens_seen": 15746457, "step": 241, "train_runtime": 5274.5971, "train_tokens_per_second": 2985.338 }, { "epoch": 0.15367518653754564, "grad_norm": 1.3007371425628662, "learning_rate": 1.9874898045114638e-05, "loss": 1.6043508052825928, "num_input_tokens_seen": 15811860, "step": 242, "train_runtime": 5296.5958, "train_tokens_per_second": 2985.287 }, { "epoch": 0.15431020796951897, "grad_norm": 1.1971044540405273, "learning_rate": 1.987384678021302e-05, "loss": 1.5910778045654297, "num_input_tokens_seen": 15877223, "step": 243, "train_runtime": 5317.7972, "train_tokens_per_second": 2985.677 }, { "epoch": 0.1549452294014923, "grad_norm": 1.2382798194885254, "learning_rate": 1.9872791144780986e-05, "loss": 1.6010921001434326, "num_input_tokens_seen": 15942676, "step": 244, "train_runtime": 5338.1138, "train_tokens_per_second": 2986.575 }, { "epoch": 0.15558025083346563, "grad_norm": 1.133172869682312, "learning_rate": 1.987173113928579e-05, "loss": 1.6570795774459839, "num_input_tokens_seen": 16008203, "step": 245, "train_runtime": 5359.8028, "train_tokens_per_second": 2986.715 }, { "epoch": 0.15621527226543896, "grad_norm": 1.1817882061004639, "learning_rate": 1.9870666764196635e-05, "loss": 1.6430494785308838, "num_input_tokens_seen": 16073735, "step": 246, "train_runtime": 5381.3672, "train_tokens_per_second": 2986.924 }, { "epoch": 0.1568502936974123, "grad_norm": 1.4080286026000977, "learning_rate": 1.986959801998465e-05, "loss": 1.7571600675582886, "num_input_tokens_seen": 16139257, "step": 247, "train_runtime": 5403.3535, "train_tokens_per_second": 2986.896 }, { "epoch": 0.15748531512938563, "grad_norm": 1.2879483699798584, "learning_rate": 1.98685249071229e-05, "loss": 1.7389273643493652, "num_input_tokens_seen": 16204672, "step": 248, "train_runtime": 5425.3892, "train_tokens_per_second": 2986.822 }, { "epoch": 0.15812033656135896, "grad_norm": 1.3632365465164185, "learning_rate": 1.986744742608639e-05, "loss": 1.9445626735687256, "num_input_tokens_seen": 16270000, "step": 249, "train_runtime": 5447.2465, "train_tokens_per_second": 2986.83 }, { "epoch": 0.15875535799333226, "grad_norm": 1.2984898090362549, "learning_rate": 1.986636557735205e-05, "loss": 1.6086424589157104, "num_input_tokens_seen": 16335455, "step": 250, "train_runtime": 5468.4894, "train_tokens_per_second": 2987.197 }, { "epoch": 0.1593903794253056, "grad_norm": 1.1770097017288208, "learning_rate": 1.9865279361398743e-05, "loss": 1.7368335723876953, "num_input_tokens_seen": 16400967, "step": 251, "train_runtime": 5490.3032, "train_tokens_per_second": 2987.261 }, { "epoch": 0.16002540085727893, "grad_norm": 1.3044664859771729, "learning_rate": 1.9864188778707274e-05, "loss": 1.8160865306854248, "num_input_tokens_seen": 16466445, "step": 252, "train_runtime": 5511.2961, "train_tokens_per_second": 2987.763 }, { "epoch": 0.16066042228925226, "grad_norm": 1.205988883972168, "learning_rate": 1.986309382976037e-05, "loss": 1.7866387367248535, "num_input_tokens_seen": 16531939, "step": 253, "train_runtime": 5532.1797, "train_tokens_per_second": 2988.323 }, { "epoch": 0.1612954437212256, "grad_norm": 1.1990302801132202, "learning_rate": 1.98619945150427e-05, "loss": 1.671930193901062, "num_input_tokens_seen": 16597351, "step": 254, "train_runtime": 5553.6688, "train_tokens_per_second": 2988.538 }, { "epoch": 0.16193046515319892, "grad_norm": 1.2952179908752441, "learning_rate": 1.986089083504086e-05, "loss": 1.7234110832214355, "num_input_tokens_seen": 16662820, "step": 255, "train_runtime": 5575.5912, "train_tokens_per_second": 2988.53 }, { "epoch": 0.16256548658517225, "grad_norm": 1.3268362283706665, "learning_rate": 1.985978279024338e-05, "loss": 1.8356882333755493, "num_input_tokens_seen": 16728286, "step": 256, "train_runtime": 5596.9242, "train_tokens_per_second": 2988.836 }, { "epoch": 0.16320050801714558, "grad_norm": 1.2780829668045044, "learning_rate": 1.9858670381140718e-05, "loss": 1.8297624588012695, "num_input_tokens_seen": 16793761, "step": 257, "train_runtime": 5618.1468, "train_tokens_per_second": 2989.199 }, { "epoch": 0.16383552944911892, "grad_norm": 1.2789195775985718, "learning_rate": 1.9857553608225275e-05, "loss": 1.7461109161376953, "num_input_tokens_seen": 16859074, "step": 258, "train_runtime": 5639.1128, "train_tokens_per_second": 2989.668 }, { "epoch": 0.16447055088109225, "grad_norm": 1.2320499420166016, "learning_rate": 1.985643247199137e-05, "loss": 1.8885860443115234, "num_input_tokens_seen": 16924566, "step": 259, "train_runtime": 5660.7877, "train_tokens_per_second": 2989.79 }, { "epoch": 0.16510557231306558, "grad_norm": 1.212741494178772, "learning_rate": 1.9855306972935263e-05, "loss": 1.5255699157714844, "num_input_tokens_seen": 16990077, "step": 260, "train_runtime": 5682.3032, "train_tokens_per_second": 2989.998 }, { "epoch": 0.16574059374503888, "grad_norm": 1.140660047531128, "learning_rate": 1.9854177111555138e-05, "loss": 1.7366960048675537, "num_input_tokens_seen": 17055491, "step": 261, "train_runtime": 5703.6384, "train_tokens_per_second": 2990.283 }, { "epoch": 0.16637561517701221, "grad_norm": 1.2353466749191284, "learning_rate": 1.985304288835112e-05, "loss": 1.7311375141143799, "num_input_tokens_seen": 17120990, "step": 262, "train_runtime": 5725.54, "train_tokens_per_second": 2990.284 }, { "epoch": 0.16701063660898555, "grad_norm": 1.2019364833831787, "learning_rate": 1.9851904303825246e-05, "loss": 1.7191755771636963, "num_input_tokens_seen": 17186297, "step": 263, "train_runtime": 5746.3244, "train_tokens_per_second": 2990.833 }, { "epoch": 0.16764565804095888, "grad_norm": 1.2103078365325928, "learning_rate": 1.985076135848151e-05, "loss": 1.7186452150344849, "num_input_tokens_seen": 17251762, "step": 264, "train_runtime": 5767.3993, "train_tokens_per_second": 2991.255 }, { "epoch": 0.1682806794729322, "grad_norm": 1.5583347082138062, "learning_rate": 1.984961405282581e-05, "loss": 1.6840529441833496, "num_input_tokens_seen": 17317234, "step": 265, "train_runtime": 5789.9218, "train_tokens_per_second": 2990.927 }, { "epoch": 0.16891570090490554, "grad_norm": 1.2468187808990479, "learning_rate": 1.9848462387365996e-05, "loss": 1.73769211769104, "num_input_tokens_seen": 17382716, "step": 266, "train_runtime": 5812.032, "train_tokens_per_second": 2990.816 }, { "epoch": 0.16955072233687887, "grad_norm": 1.2694332599639893, "learning_rate": 1.984730636261183e-05, "loss": 1.7091338634490967, "num_input_tokens_seen": 17448195, "step": 267, "train_runtime": 5833.0879, "train_tokens_per_second": 2991.245 }, { "epoch": 0.1701857437688522, "grad_norm": 1.4762763977050781, "learning_rate": 1.9846145979075015e-05, "loss": 1.7764711380004883, "num_input_tokens_seen": 17506838, "step": 268, "train_runtime": 5851.7502, "train_tokens_per_second": 2991.727 }, { "epoch": 0.17082076520082554, "grad_norm": 1.1765060424804688, "learning_rate": 1.984498123726918e-05, "loss": 1.6142239570617676, "num_input_tokens_seen": 17572284, "step": 269, "train_runtime": 5872.5318, "train_tokens_per_second": 2992.284 }, { "epoch": 0.17145578663279887, "grad_norm": 1.43293297290802, "learning_rate": 1.9843812137709882e-05, "loss": 1.750152587890625, "num_input_tokens_seen": 17632635, "step": 270, "train_runtime": 5892.5109, "train_tokens_per_second": 2992.381 }, { "epoch": 0.1720908080647722, "grad_norm": 1.4470365047454834, "learning_rate": 1.9842638680914607e-05, "loss": 1.9785759449005127, "num_input_tokens_seen": 17698067, "step": 271, "train_runtime": 5914.9001, "train_tokens_per_second": 2992.116 }, { "epoch": 0.1727258294967455, "grad_norm": 1.1478054523468018, "learning_rate": 1.9841460867402772e-05, "loss": 1.608659267425537, "num_input_tokens_seen": 17763594, "step": 272, "train_runtime": 5936.2127, "train_tokens_per_second": 2992.412 }, { "epoch": 0.17336085092871883, "grad_norm": 1.2717463970184326, "learning_rate": 1.984027869769572e-05, "loss": 1.7487612962722778, "num_input_tokens_seen": 17829106, "step": 273, "train_runtime": 5958.6924, "train_tokens_per_second": 2992.117 }, { "epoch": 0.17399587236069217, "grad_norm": 1.125026822090149, "learning_rate": 1.9839092172316726e-05, "loss": 1.6560773849487305, "num_input_tokens_seen": 17894631, "step": 274, "train_runtime": 5980.2127, "train_tokens_per_second": 2992.307 }, { "epoch": 0.1746308937926655, "grad_norm": 2.2201485633850098, "learning_rate": 1.9837901291790983e-05, "loss": 1.7257211208343506, "num_input_tokens_seen": 17960160, "step": 275, "train_runtime": 6001.6232, "train_tokens_per_second": 2992.55 }, { "epoch": 0.17526591522463883, "grad_norm": 1.2394345998764038, "learning_rate": 1.9836706056645626e-05, "loss": 1.7572481632232666, "num_input_tokens_seen": 18025587, "step": 276, "train_runtime": 6023.5118, "train_tokens_per_second": 2992.538 }, { "epoch": 0.17590093665661216, "grad_norm": 1.2280458211898804, "learning_rate": 1.9835506467409707e-05, "loss": 1.5706684589385986, "num_input_tokens_seen": 18091057, "step": 277, "train_runtime": 6045.4042, "train_tokens_per_second": 2992.531 }, { "epoch": 0.1765359580885855, "grad_norm": 1.2277950048446655, "learning_rate": 1.983430252461421e-05, "loss": 1.7581160068511963, "num_input_tokens_seen": 18156470, "step": 278, "train_runtime": 6066.5021, "train_tokens_per_second": 2992.906 }, { "epoch": 0.17717097952055882, "grad_norm": 1.2538114786148071, "learning_rate": 1.9833094228792044e-05, "loss": 1.816202163696289, "num_input_tokens_seen": 18221902, "step": 279, "train_runtime": 6088.0212, "train_tokens_per_second": 2993.075 }, { "epoch": 0.17780600095253216, "grad_norm": 1.3121562004089355, "learning_rate": 1.9831881580478045e-05, "loss": 1.7505748271942139, "num_input_tokens_seen": 18287365, "step": 280, "train_runtime": 6108.7432, "train_tokens_per_second": 2993.638 }, { "epoch": 0.1784410223845055, "grad_norm": 1.4255000352859497, "learning_rate": 1.9830664580208974e-05, "loss": 1.920577049255371, "num_input_tokens_seen": 18352861, "step": 281, "train_runtime": 6130.3635, "train_tokens_per_second": 2993.764 }, { "epoch": 0.17907604381647882, "grad_norm": 1.241868495941162, "learning_rate": 1.9829443228523527e-05, "loss": 1.8226219415664673, "num_input_tokens_seen": 18418305, "step": 282, "train_runtime": 6151.5914, "train_tokens_per_second": 2994.072 }, { "epoch": 0.17971106524845212, "grad_norm": 1.1412990093231201, "learning_rate": 1.9828217525962314e-05, "loss": 1.5397157669067383, "num_input_tokens_seen": 18483745, "step": 283, "train_runtime": 6172.0158, "train_tokens_per_second": 2994.766 }, { "epoch": 0.18034608668042545, "grad_norm": 1.2302041053771973, "learning_rate": 1.9826987473067877e-05, "loss": 1.8567686080932617, "num_input_tokens_seen": 18549240, "step": 284, "train_runtime": 6193.6518, "train_tokens_per_second": 2994.879 }, { "epoch": 0.1809811081123988, "grad_norm": 1.2513797283172607, "learning_rate": 1.9825753070384684e-05, "loss": 1.7334612607955933, "num_input_tokens_seen": 18614691, "step": 285, "train_runtime": 6215.0782, "train_tokens_per_second": 2995.086 }, { "epoch": 0.18161612954437212, "grad_norm": 1.4878193140029907, "learning_rate": 1.982451431845913e-05, "loss": 1.9252253770828247, "num_input_tokens_seen": 18680222, "step": 286, "train_runtime": 6237.8402, "train_tokens_per_second": 2994.662 }, { "epoch": 0.18225115097634545, "grad_norm": 1.1726562976837158, "learning_rate": 1.9823271217839525e-05, "loss": 1.5662771463394165, "num_input_tokens_seen": 18745666, "step": 287, "train_runtime": 6258.9927, "train_tokens_per_second": 2994.997 }, { "epoch": 0.18288617240831878, "grad_norm": 1.33396577835083, "learning_rate": 1.9822023769076118e-05, "loss": 1.9752568006515503, "num_input_tokens_seen": 18811157, "step": 288, "train_runtime": 6281.0843, "train_tokens_per_second": 2994.89 }, { "epoch": 0.1835211938402921, "grad_norm": 1.2141733169555664, "learning_rate": 1.982077197272108e-05, "loss": 1.4775030612945557, "num_input_tokens_seen": 18876517, "step": 289, "train_runtime": 6301.8575, "train_tokens_per_second": 2995.389 }, { "epoch": 0.18415621527226544, "grad_norm": 1.3062529563903809, "learning_rate": 1.9819515829328488e-05, "loss": 1.7334128618240356, "num_input_tokens_seen": 18942021, "step": 290, "train_runtime": 6323.4128, "train_tokens_per_second": 2995.538 }, { "epoch": 0.18479123670423878, "grad_norm": 1.2631479501724243, "learning_rate": 1.981825533945437e-05, "loss": 1.7885322570800781, "num_input_tokens_seen": 19007517, "step": 291, "train_runtime": 6344.6884, "train_tokens_per_second": 2995.816 }, { "epoch": 0.1854262581362121, "grad_norm": 1.3206216096878052, "learning_rate": 1.9816990503656662e-05, "loss": 1.6468619108200073, "num_input_tokens_seen": 19072919, "step": 292, "train_runtime": 6366.7774, "train_tokens_per_second": 2995.694 }, { "epoch": 0.18606127956818544, "grad_norm": 1.2572128772735596, "learning_rate": 1.9815721322495226e-05, "loss": 1.6276048421859741, "num_input_tokens_seen": 19138441, "step": 293, "train_runtime": 6388.8562, "train_tokens_per_second": 2995.597 }, { "epoch": 0.18669630100015874, "grad_norm": 1.2481616735458374, "learning_rate": 1.981444779653185e-05, "loss": 1.7619602680206299, "num_input_tokens_seen": 19203895, "step": 294, "train_runtime": 6410.3232, "train_tokens_per_second": 2995.776 }, { "epoch": 0.18733132243213207, "grad_norm": 1.1494519710540771, "learning_rate": 1.9813169926330244e-05, "loss": 1.7001312971115112, "num_input_tokens_seen": 19269385, "step": 295, "train_runtime": 6431.7697, "train_tokens_per_second": 2995.969 }, { "epoch": 0.1879663438641054, "grad_norm": 1.3237619400024414, "learning_rate": 1.9811887712456038e-05, "loss": 1.6893370151519775, "num_input_tokens_seen": 19334909, "step": 296, "train_runtime": 6454.1494, "train_tokens_per_second": 2995.733 }, { "epoch": 0.18860136529607874, "grad_norm": 1.260802149772644, "learning_rate": 1.981060115547679e-05, "loss": 1.590820550918579, "num_input_tokens_seen": 19399171, "step": 297, "train_runtime": 6474.7715, "train_tokens_per_second": 2996.117 }, { "epoch": 0.18923638672805207, "grad_norm": 1.1827691793441772, "learning_rate": 1.9809310255961977e-05, "loss": 1.6788431406021118, "num_input_tokens_seen": 19464583, "step": 298, "train_runtime": 6496.4803, "train_tokens_per_second": 2996.174 }, { "epoch": 0.1898714081600254, "grad_norm": 1.2904400825500488, "learning_rate": 1.9808015014482998e-05, "loss": 1.8209744691848755, "num_input_tokens_seen": 19530105, "step": 299, "train_runtime": 6518.9679, "train_tokens_per_second": 2995.889 }, { "epoch": 0.19050642959199873, "grad_norm": 1.2826987504959106, "learning_rate": 1.980671543161318e-05, "loss": 1.8550211191177368, "num_input_tokens_seen": 19595595, "step": 300, "train_runtime": 6541.1364, "train_tokens_per_second": 2995.748 }, { "epoch": 0.19050642959199873, "eval_loss": 1.6377630233764648, "eval_runtime": 12.902, "eval_samples_per_second": 1.783, "eval_steps_per_second": 0.93, "num_input_tokens_seen": 19595595, "step": 300 }, { "epoch": 0.19114145102397206, "grad_norm": 1.1849868297576904, "learning_rate": 1.9805411507927757e-05, "loss": 1.6177575588226318, "num_input_tokens_seen": 19661113, "step": 301, "train_runtime": 6611.6415, "train_tokens_per_second": 2973.711 }, { "epoch": 0.1917764724559454, "grad_norm": 1.1817234754562378, "learning_rate": 1.9804103244003904e-05, "loss": 1.9151599407196045, "num_input_tokens_seen": 19726625, "step": 302, "train_runtime": 6633.6739, "train_tokens_per_second": 2973.71 }, { "epoch": 0.19241149388791873, "grad_norm": 1.2573202848434448, "learning_rate": 1.9802790640420702e-05, "loss": 1.7247217893600464, "num_input_tokens_seen": 19792140, "step": 303, "train_runtime": 6655.6589, "train_tokens_per_second": 2973.731 }, { "epoch": 0.19304651531989206, "grad_norm": 1.3154996633529663, "learning_rate": 1.9801473697759158e-05, "loss": 1.7111718654632568, "num_input_tokens_seen": 19857643, "step": 304, "train_runtime": 6677.0456, "train_tokens_per_second": 2974.016 }, { "epoch": 0.19368153675186536, "grad_norm": 1.4009523391723633, "learning_rate": 1.9800152416602197e-05, "loss": 1.6432548761367798, "num_input_tokens_seen": 19919221, "step": 305, "train_runtime": 6697.975, "train_tokens_per_second": 2973.917 }, { "epoch": 0.1943165581838387, "grad_norm": 1.297940731048584, "learning_rate": 1.9798826797534675e-05, "loss": 1.8300228118896484, "num_input_tokens_seen": 19984601, "step": 306, "train_runtime": 6719.568, "train_tokens_per_second": 2974.09 }, { "epoch": 0.19495157961581203, "grad_norm": 1.2302095890045166, "learning_rate": 1.9797496841143355e-05, "loss": 1.7269471883773804, "num_input_tokens_seen": 20050127, "step": 307, "train_runtime": 6741.7345, "train_tokens_per_second": 2974.031 }, { "epoch": 0.19558660104778536, "grad_norm": 1.1743422746658325, "learning_rate": 1.9796162548016918e-05, "loss": 1.6196174621582031, "num_input_tokens_seen": 20115642, "step": 308, "train_runtime": 6762.9849, "train_tokens_per_second": 2974.373 }, { "epoch": 0.1962216224797587, "grad_norm": 1.226790189743042, "learning_rate": 1.9794823918745987e-05, "loss": 1.736101508140564, "num_input_tokens_seen": 20181156, "step": 309, "train_runtime": 6784.1986, "train_tokens_per_second": 2974.73 }, { "epoch": 0.19685664391173202, "grad_norm": 1.2415673732757568, "learning_rate": 1.979348095392308e-05, "loss": 1.5536975860595703, "num_input_tokens_seen": 20246418, "step": 310, "train_runtime": 6804.2969, "train_tokens_per_second": 2975.534 }, { "epoch": 0.19749166534370535, "grad_norm": 1.2843163013458252, "learning_rate": 1.979213365414264e-05, "loss": 1.778480052947998, "num_input_tokens_seen": 20311911, "step": 311, "train_runtime": 6825.6142, "train_tokens_per_second": 2975.836 }, { "epoch": 0.19812668677567868, "grad_norm": 1.2618283033370972, "learning_rate": 1.9790782020001034e-05, "loss": 1.6897977590560913, "num_input_tokens_seen": 20377417, "step": 312, "train_runtime": 6846.9377, "train_tokens_per_second": 2976.136 }, { "epoch": 0.19876170820765202, "grad_norm": 1.259351134300232, "learning_rate": 1.978942605209655e-05, "loss": 1.6949350833892822, "num_input_tokens_seen": 20442838, "step": 313, "train_runtime": 6868.2888, "train_tokens_per_second": 2976.409 }, { "epoch": 0.19939672963962535, "grad_norm": 1.2907503843307495, "learning_rate": 1.9788065751029385e-05, "loss": 1.6465318202972412, "num_input_tokens_seen": 20508289, "step": 314, "train_runtime": 6889.5373, "train_tokens_per_second": 2976.73 }, { "epoch": 0.20003175107159868, "grad_norm": 1.4399011135101318, "learning_rate": 1.9786701117401664e-05, "loss": 1.8713077306747437, "num_input_tokens_seen": 20573785, "step": 315, "train_runtime": 6911.7425, "train_tokens_per_second": 2976.642 }, { "epoch": 0.20066677250357198, "grad_norm": 1.3424291610717773, "learning_rate": 1.9785332151817414e-05, "loss": 1.8628621101379395, "num_input_tokens_seen": 20639263, "step": 316, "train_runtime": 6932.6641, "train_tokens_per_second": 2977.104 }, { "epoch": 0.20130179393554531, "grad_norm": 1.1921169757843018, "learning_rate": 1.9783958854882602e-05, "loss": 1.7153295278549194, "num_input_tokens_seen": 20704690, "step": 317, "train_runtime": 6954.614, "train_tokens_per_second": 2977.116 }, { "epoch": 0.20193681536751865, "grad_norm": 1.2544944286346436, "learning_rate": 1.9782581227205093e-05, "loss": 1.7692270278930664, "num_input_tokens_seen": 20770202, "step": 318, "train_runtime": 6976.745, "train_tokens_per_second": 2977.062 }, { "epoch": 0.20257183679949198, "grad_norm": 1.178011178970337, "learning_rate": 1.9781199269394675e-05, "loss": 1.6287401914596558, "num_input_tokens_seen": 20835594, "step": 319, "train_runtime": 6998.1484, "train_tokens_per_second": 2977.301 }, { "epoch": 0.2032068582314653, "grad_norm": 1.243483304977417, "learning_rate": 1.977981298206306e-05, "loss": 1.6748733520507812, "num_input_tokens_seen": 20901076, "step": 320, "train_runtime": 7020.3969, "train_tokens_per_second": 2977.193 }, { "epoch": 0.20384187966343864, "grad_norm": 1.1599174737930298, "learning_rate": 1.9778422365823867e-05, "loss": 1.6372716426849365, "num_input_tokens_seen": 20966523, "step": 321, "train_runtime": 7041.2371, "train_tokens_per_second": 2977.676 }, { "epoch": 0.20447690109541197, "grad_norm": 1.0967408418655396, "learning_rate": 1.977702742129263e-05, "loss": 1.506179690361023, "num_input_tokens_seen": 21032003, "step": 322, "train_runtime": 7061.7335, "train_tokens_per_second": 2978.306 }, { "epoch": 0.2051119225273853, "grad_norm": 1.2520591020584106, "learning_rate": 1.977562814908681e-05, "loss": 1.7974145412445068, "num_input_tokens_seen": 21097433, "step": 323, "train_runtime": 7083.387, "train_tokens_per_second": 2978.439 }, { "epoch": 0.20574694395935864, "grad_norm": 1.3147872686386108, "learning_rate": 1.977422454982577e-05, "loss": 1.5841758251190186, "num_input_tokens_seen": 21162766, "step": 324, "train_runtime": 7104.4487, "train_tokens_per_second": 2978.805 }, { "epoch": 0.20638196539133197, "grad_norm": 1.1941500902175903, "learning_rate": 1.9772816624130798e-05, "loss": 1.7142753601074219, "num_input_tokens_seen": 21228213, "step": 325, "train_runtime": 7126.1152, "train_tokens_per_second": 2978.932 }, { "epoch": 0.2070169868233053, "grad_norm": 1.200846552848816, "learning_rate": 1.9771404372625097e-05, "loss": 1.7394670248031616, "num_input_tokens_seen": 21293677, "step": 326, "train_runtime": 7147.6136, "train_tokens_per_second": 2979.131 }, { "epoch": 0.2076520082552786, "grad_norm": 1.3251256942749023, "learning_rate": 1.976998779593378e-05, "loss": 1.5978962182998657, "num_input_tokens_seen": 21359107, "step": 327, "train_runtime": 7168.4416, "train_tokens_per_second": 2979.603 }, { "epoch": 0.20828702968725193, "grad_norm": 1.193078637123108, "learning_rate": 1.9768566894683876e-05, "loss": 1.645488977432251, "num_input_tokens_seen": 21424549, "step": 328, "train_runtime": 7189.6914, "train_tokens_per_second": 2979.898 }, { "epoch": 0.20892205111922527, "grad_norm": 1.0956289768218994, "learning_rate": 1.976714166950433e-05, "loss": 1.4994324445724487, "num_input_tokens_seen": 21490059, "step": 329, "train_runtime": 7210.1636, "train_tokens_per_second": 2980.523 }, { "epoch": 0.2095570725511986, "grad_norm": 1.3797653913497925, "learning_rate": 1.9765712121025994e-05, "loss": 1.92220938205719, "num_input_tokens_seen": 21555554, "step": 330, "train_runtime": 7231.9725, "train_tokens_per_second": 2980.591 }, { "epoch": 0.21019209398317193, "grad_norm": 1.2837400436401367, "learning_rate": 1.9764278249881644e-05, "loss": 1.7548713684082031, "num_input_tokens_seen": 21621059, "step": 331, "train_runtime": 7253.403, "train_tokens_per_second": 2980.816 }, { "epoch": 0.21082711541514526, "grad_norm": 1.1955814361572266, "learning_rate": 1.976284005670596e-05, "loss": 1.7536017894744873, "num_input_tokens_seen": 21686550, "step": 332, "train_runtime": 7274.7088, "train_tokens_per_second": 2981.088 }, { "epoch": 0.2114621368471186, "grad_norm": 1.2386399507522583, "learning_rate": 1.9761397542135552e-05, "loss": 1.7835310697555542, "num_input_tokens_seen": 21750949, "step": 333, "train_runtime": 7296.4379, "train_tokens_per_second": 2981.037 }, { "epoch": 0.21209715827909192, "grad_norm": 1.0961004495620728, "learning_rate": 1.9759950706808917e-05, "loss": 1.5839016437530518, "num_input_tokens_seen": 21816432, "step": 334, "train_runtime": 7317.2013, "train_tokens_per_second": 2981.527 }, { "epoch": 0.21273217971106526, "grad_norm": 1.264935851097107, "learning_rate": 1.9758499551366483e-05, "loss": 1.7344300746917725, "num_input_tokens_seen": 21881819, "step": 335, "train_runtime": 7339.0493, "train_tokens_per_second": 2981.56 }, { "epoch": 0.2133672011430386, "grad_norm": 1.3662196397781372, "learning_rate": 1.9757044076450583e-05, "loss": 1.7930976152420044, "num_input_tokens_seen": 21947311, "step": 336, "train_runtime": 7360.883, "train_tokens_per_second": 2981.614 }, { "epoch": 0.21400222257501192, "grad_norm": 1.201227068901062, "learning_rate": 1.9755584282705466e-05, "loss": 1.6382478475570679, "num_input_tokens_seen": 22012826, "step": 337, "train_runtime": 7383.0843, "train_tokens_per_second": 2981.522 }, { "epoch": 0.21463724400698522, "grad_norm": 1.2808663845062256, "learning_rate": 1.975412017077729e-05, "loss": 1.7432152032852173, "num_input_tokens_seen": 22078204, "step": 338, "train_runtime": 7404.6823, "train_tokens_per_second": 2981.654 }, { "epoch": 0.21527226543895855, "grad_norm": 1.218616247177124, "learning_rate": 1.9752651741314126e-05, "loss": 1.7417330741882324, "num_input_tokens_seen": 22143709, "step": 339, "train_runtime": 7426.4348, "train_tokens_per_second": 2981.742 }, { "epoch": 0.21590728687093189, "grad_norm": 1.2358020544052124, "learning_rate": 1.9751178994965955e-05, "loss": 1.6878200769424438, "num_input_tokens_seen": 22209191, "step": 340, "train_runtime": 7447.6194, "train_tokens_per_second": 2982.052 }, { "epoch": 0.21654230830290522, "grad_norm": 1.190558671951294, "learning_rate": 1.974970193238467e-05, "loss": 1.7173357009887695, "num_input_tokens_seen": 22274725, "step": 341, "train_runtime": 7469.447, "train_tokens_per_second": 2982.112 }, { "epoch": 0.21717732973487855, "grad_norm": 1.153677225112915, "learning_rate": 1.9748220554224072e-05, "loss": 1.547133207321167, "num_input_tokens_seen": 22340200, "step": 342, "train_runtime": 7490.7375, "train_tokens_per_second": 2982.377 }, { "epoch": 0.21781235116685188, "grad_norm": 1.4609407186508179, "learning_rate": 1.9746734861139873e-05, "loss": 1.6282410621643066, "num_input_tokens_seen": 22405569, "step": 343, "train_runtime": 7512.7922, "train_tokens_per_second": 2982.322 }, { "epoch": 0.2184473725988252, "grad_norm": 1.152599573135376, "learning_rate": 1.97452448537897e-05, "loss": 1.5363428592681885, "num_input_tokens_seen": 22471035, "step": 344, "train_runtime": 7533.2617, "train_tokens_per_second": 2982.909 }, { "epoch": 0.21908239403079854, "grad_norm": 1.2215783596038818, "learning_rate": 1.974375053283308e-05, "loss": 1.6275227069854736, "num_input_tokens_seen": 22536509, "step": 345, "train_runtime": 7554.6022, "train_tokens_per_second": 2983.15 }, { "epoch": 0.21971741546277188, "grad_norm": 1.250752568244934, "learning_rate": 1.974225189893146e-05, "loss": 1.8564350605010986, "num_input_tokens_seen": 22602025, "step": 346, "train_runtime": 7575.8499, "train_tokens_per_second": 2983.431 }, { "epoch": 0.2203524368947452, "grad_norm": 1.2403333187103271, "learning_rate": 1.974074895274819e-05, "loss": 1.6470024585723877, "num_input_tokens_seen": 22667534, "step": 347, "train_runtime": 7597.5648, "train_tokens_per_second": 2983.526 }, { "epoch": 0.22098745832671854, "grad_norm": 1.1172963380813599, "learning_rate": 1.9739241694948525e-05, "loss": 1.6585588455200195, "num_input_tokens_seen": 22732955, "step": 348, "train_runtime": 7618.8856, "train_tokens_per_second": 2983.764 }, { "epoch": 0.22162247975869184, "grad_norm": 1.2316834926605225, "learning_rate": 1.9737730126199633e-05, "loss": 1.588835597038269, "num_input_tokens_seen": 22798421, "step": 349, "train_runtime": 7640.2346, "train_tokens_per_second": 2983.995 }, { "epoch": 0.22225750119066517, "grad_norm": 1.3581501245498657, "learning_rate": 1.9736214247170598e-05, "loss": 1.7437188625335693, "num_input_tokens_seen": 22863887, "step": 350, "train_runtime": 7663.0272, "train_tokens_per_second": 2983.663 }, { "epoch": 0.2228925226226385, "grad_norm": 1.1872146129608154, "learning_rate": 1.9734694058532402e-05, "loss": 1.621132731437683, "num_input_tokens_seen": 22929417, "step": 351, "train_runtime": 7685.1313, "train_tokens_per_second": 2983.608 }, { "epoch": 0.22352754405461184, "grad_norm": 1.1653684377670288, "learning_rate": 1.973316956095793e-05, "loss": 1.5930386781692505, "num_input_tokens_seen": 22994928, "step": 352, "train_runtime": 7705.6991, "train_tokens_per_second": 2984.146 }, { "epoch": 0.22416256548658517, "grad_norm": 1.3320719003677368, "learning_rate": 1.973164075512199e-05, "loss": 1.576480746269226, "num_input_tokens_seen": 23060290, "step": 353, "train_runtime": 7726.2166, "train_tokens_per_second": 2984.681 }, { "epoch": 0.2247975869185585, "grad_norm": 1.260028600692749, "learning_rate": 1.973010764170128e-05, "loss": 1.7380248308181763, "num_input_tokens_seen": 23125724, "step": 354, "train_runtime": 7747.9181, "train_tokens_per_second": 2984.766 }, { "epoch": 0.22543260835053183, "grad_norm": 1.365102767944336, "learning_rate": 1.972857022137442e-05, "loss": 1.5566322803497314, "num_input_tokens_seen": 23183764, "step": 355, "train_runtime": 7766.1965, "train_tokens_per_second": 2985.215 }, { "epoch": 0.22606762978250516, "grad_norm": 1.0785192251205444, "learning_rate": 1.9727028494821926e-05, "loss": 1.5785636901855469, "num_input_tokens_seen": 23249242, "step": 356, "train_runtime": 7787.1259, "train_tokens_per_second": 2985.6 }, { "epoch": 0.2267026512144785, "grad_norm": 1.1503260135650635, "learning_rate": 1.9725482462726222e-05, "loss": 1.625655174255371, "num_input_tokens_seen": 23314597, "step": 357, "train_runtime": 7808.5319, "train_tokens_per_second": 2985.785 }, { "epoch": 0.22733767264645183, "grad_norm": 1.1893843412399292, "learning_rate": 1.972393212577164e-05, "loss": 1.416221261024475, "num_input_tokens_seen": 23380081, "step": 358, "train_runtime": 7830.3379, "train_tokens_per_second": 2985.833 }, { "epoch": 0.22797269407842516, "grad_norm": 1.2536722421646118, "learning_rate": 1.972237748464442e-05, "loss": 1.7694891691207886, "num_input_tokens_seen": 23445519, "step": 359, "train_runtime": 7851.5298, "train_tokens_per_second": 2986.108 }, { "epoch": 0.22860771551039846, "grad_norm": 1.2836717367172241, "learning_rate": 1.9720818540032695e-05, "loss": 1.82590913772583, "num_input_tokens_seen": 23510956, "step": 360, "train_runtime": 7872.9377, "train_tokens_per_second": 2986.3 }, { "epoch": 0.2292427369423718, "grad_norm": 1.332735300064087, "learning_rate": 1.9719255292626522e-05, "loss": 1.8758111000061035, "num_input_tokens_seen": 23576428, "step": 361, "train_runtime": 7894.0139, "train_tokens_per_second": 2986.621 }, { "epoch": 0.22987775837434513, "grad_norm": 1.1739857196807861, "learning_rate": 1.971768774311784e-05, "loss": 1.4996858835220337, "num_input_tokens_seen": 23641840, "step": 362, "train_runtime": 7915.6619, "train_tokens_per_second": 2986.717 }, { "epoch": 0.23051277980631846, "grad_norm": 1.237807273864746, "learning_rate": 1.971611589220052e-05, "loss": 1.7763973474502563, "num_input_tokens_seen": 23707361, "step": 363, "train_runtime": 7937.0531, "train_tokens_per_second": 2986.922 }, { "epoch": 0.2311478012382918, "grad_norm": 1.171311378479004, "learning_rate": 1.971453974057031e-05, "loss": 1.6675125360488892, "num_input_tokens_seen": 23772880, "step": 364, "train_runtime": 7957.8171, "train_tokens_per_second": 2987.362 }, { "epoch": 0.23178282267026512, "grad_norm": 1.287043571472168, "learning_rate": 1.971295928892488e-05, "loss": 1.7743940353393555, "num_input_tokens_seen": 23838352, "step": 365, "train_runtime": 7979.3522, "train_tokens_per_second": 2987.505 }, { "epoch": 0.23241784410223845, "grad_norm": 1.5740326642990112, "learning_rate": 1.971137453796379e-05, "loss": 1.790032982826233, "num_input_tokens_seen": 23903783, "step": 366, "train_runtime": 8001.0854, "train_tokens_per_second": 2987.568 }, { "epoch": 0.23305286553421178, "grad_norm": 1.324499487876892, "learning_rate": 1.9709785488388512e-05, "loss": 1.7446973323822021, "num_input_tokens_seen": 23969297, "step": 367, "train_runtime": 8022.8616, "train_tokens_per_second": 2987.624 }, { "epoch": 0.23368788696618512, "grad_norm": 1.1111760139465332, "learning_rate": 1.970819214090242e-05, "loss": 1.6119712591171265, "num_input_tokens_seen": 24034723, "step": 368, "train_runtime": 8043.9911, "train_tokens_per_second": 2987.91 }, { "epoch": 0.23432290839815845, "grad_norm": 1.3691896200180054, "learning_rate": 1.9706594496210788e-05, "loss": 1.8662116527557373, "num_input_tokens_seen": 24100215, "step": 369, "train_runtime": 8065.6685, "train_tokens_per_second": 2988.0 }, { "epoch": 0.23495792983013178, "grad_norm": 1.341166615486145, "learning_rate": 1.970499255502079e-05, "loss": 1.538130521774292, "num_input_tokens_seen": 24165687, "step": 370, "train_runtime": 8087.3652, "train_tokens_per_second": 2988.079 }, { "epoch": 0.23559295126210508, "grad_norm": 1.1692298650741577, "learning_rate": 1.970338631804151e-05, "loss": 1.6026922464370728, "num_input_tokens_seen": 24231190, "step": 371, "train_runtime": 8108.3699, "train_tokens_per_second": 2988.417 }, { "epoch": 0.23622797269407841, "grad_norm": 1.1728874444961548, "learning_rate": 1.970177578598392e-05, "loss": 1.6345241069793701, "num_input_tokens_seen": 24296660, "step": 372, "train_runtime": 8129.4572, "train_tokens_per_second": 2988.719 }, { "epoch": 0.23686299412605175, "grad_norm": 1.3055860996246338, "learning_rate": 1.9700160959560907e-05, "loss": 1.8029078245162964, "num_input_tokens_seen": 24362076, "step": 373, "train_runtime": 8150.3428, "train_tokens_per_second": 2989.086 }, { "epoch": 0.23749801555802508, "grad_norm": 1.2350493669509888, "learning_rate": 1.9698541839487256e-05, "loss": 1.6736023426055908, "num_input_tokens_seen": 24427595, "step": 374, "train_runtime": 8171.6076, "train_tokens_per_second": 2989.326 }, { "epoch": 0.2381330369899984, "grad_norm": 1.1991095542907715, "learning_rate": 1.9696918426479643e-05, "loss": 1.6467081308364868, "num_input_tokens_seen": 24493054, "step": 375, "train_runtime": 8192.3384, "train_tokens_per_second": 2989.751 }, { "epoch": 0.23876805842197174, "grad_norm": 1.121171474456787, "learning_rate": 1.969529072125665e-05, "loss": 1.557102084159851, "num_input_tokens_seen": 24558470, "step": 376, "train_runtime": 8213.8879, "train_tokens_per_second": 2989.872 }, { "epoch": 0.23940307985394507, "grad_norm": 1.2667847871780396, "learning_rate": 1.9693658724538765e-05, "loss": 1.6966989040374756, "num_input_tokens_seen": 24619055, "step": 377, "train_runtime": 8233.1482, "train_tokens_per_second": 2990.236 }, { "epoch": 0.2400381012859184, "grad_norm": 1.2689175605773926, "learning_rate": 1.9692022437048364e-05, "loss": 1.8773455619812012, "num_input_tokens_seen": 24684424, "step": 378, "train_runtime": 8255.2463, "train_tokens_per_second": 2990.15 }, { "epoch": 0.24067312271789174, "grad_norm": 1.7243189811706543, "learning_rate": 1.969038185950974e-05, "loss": 1.676310420036316, "num_input_tokens_seen": 24749811, "step": 379, "train_runtime": 8276.8026, "train_tokens_per_second": 2990.262 }, { "epoch": 0.24130814414986507, "grad_norm": 1.2221910953521729, "learning_rate": 1.968873699264906e-05, "loss": 1.8023877143859863, "num_input_tokens_seen": 24815298, "step": 380, "train_runtime": 8298.37, "train_tokens_per_second": 2990.382 }, { "epoch": 0.2419431655818384, "grad_norm": 1.2936229705810547, "learning_rate": 1.9687087837194413e-05, "loss": 1.7302732467651367, "num_input_tokens_seen": 24880814, "step": 381, "train_runtime": 8319.8668, "train_tokens_per_second": 2990.53 }, { "epoch": 0.2425781870138117, "grad_norm": 1.1751914024353027, "learning_rate": 1.9685434393875768e-05, "loss": 1.6431725025177002, "num_input_tokens_seen": 24946314, "step": 382, "train_runtime": 8341.0152, "train_tokens_per_second": 2990.801 }, { "epoch": 0.24321320844578503, "grad_norm": 1.2523713111877441, "learning_rate": 1.9683776663425007e-05, "loss": 1.6747322082519531, "num_input_tokens_seen": 25011688, "step": 383, "train_runtime": 8361.7351, "train_tokens_per_second": 2991.208 }, { "epoch": 0.24384822987775837, "grad_norm": 1.4931941032409668, "learning_rate": 1.96821146465759e-05, "loss": 1.813281536102295, "num_input_tokens_seen": 25077127, "step": 384, "train_runtime": 8383.0278, "train_tokens_per_second": 2991.416 }, { "epoch": 0.2444832513097317, "grad_norm": 1.1760549545288086, "learning_rate": 1.9680448344064116e-05, "loss": 1.5900588035583496, "num_input_tokens_seen": 25142598, "step": 385, "train_runtime": 8404.7315, "train_tokens_per_second": 2991.481 }, { "epoch": 0.24511827274170503, "grad_norm": 1.3567248582839966, "learning_rate": 1.9678777756627226e-05, "loss": 1.8128783702850342, "num_input_tokens_seen": 25203499, "step": 386, "train_runtime": 8425.0306, "train_tokens_per_second": 2991.502 }, { "epoch": 0.24575329417367836, "grad_norm": 1.2726167440414429, "learning_rate": 1.967710288500469e-05, "loss": 1.851710557937622, "num_input_tokens_seen": 25268962, "step": 387, "train_runtime": 8447.1918, "train_tokens_per_second": 2991.404 }, { "epoch": 0.2463883156056517, "grad_norm": 1.2241957187652588, "learning_rate": 1.967542372993787e-05, "loss": 1.8468356132507324, "num_input_tokens_seen": 25334404, "step": 388, "train_runtime": 8469.3303, "train_tokens_per_second": 2991.311 }, { "epoch": 0.24702333703762502, "grad_norm": 1.2118529081344604, "learning_rate": 1.9673740292170023e-05, "loss": 1.8245325088500977, "num_input_tokens_seen": 25399923, "step": 389, "train_runtime": 8491.0119, "train_tokens_per_second": 2991.389 }, { "epoch": 0.24765835846959836, "grad_norm": 1.256900668144226, "learning_rate": 1.9672052572446302e-05, "loss": 1.739750623703003, "num_input_tokens_seen": 25465387, "step": 390, "train_runtime": 8512.4535, "train_tokens_per_second": 2991.545 }, { "epoch": 0.2482933799015717, "grad_norm": 1.1349424123764038, "learning_rate": 1.9670360571513747e-05, "loss": 1.553106427192688, "num_input_tokens_seen": 25530913, "step": 391, "train_runtime": 8534.4046, "train_tokens_per_second": 2991.528 }, { "epoch": 0.24892840133354502, "grad_norm": 1.2908211946487427, "learning_rate": 1.9668664290121312e-05, "loss": 1.5848177671432495, "num_input_tokens_seen": 25596379, "step": 392, "train_runtime": 8554.8014, "train_tokens_per_second": 2992.048 }, { "epoch": 0.24956342276551832, "grad_norm": 1.2031253576278687, "learning_rate": 1.9666963729019823e-05, "loss": 1.6172595024108887, "num_input_tokens_seen": 25661816, "step": 393, "train_runtime": 8575.8973, "train_tokens_per_second": 2992.318 }, { "epoch": 0.25019844419749165, "grad_norm": 2.9225566387176514, "learning_rate": 1.9665258888962018e-05, "loss": 1.619896411895752, "num_input_tokens_seen": 25727194, "step": 394, "train_runtime": 8597.4993, "train_tokens_per_second": 2992.404 }, { "epoch": 0.250833465629465, "grad_norm": 1.1566925048828125, "learning_rate": 1.966354977070252e-05, "loss": 1.5945792198181152, "num_input_tokens_seen": 25792674, "step": 395, "train_runtime": 8618.484, "train_tokens_per_second": 2992.716 }, { "epoch": 0.2514684870614383, "grad_norm": 1.2055672407150269, "learning_rate": 1.9661836374997848e-05, "loss": 1.6374666690826416, "num_input_tokens_seen": 25858178, "step": 396, "train_runtime": 8639.9077, "train_tokens_per_second": 2992.877 }, { "epoch": 0.2521035084934117, "grad_norm": 1.2328416109085083, "learning_rate": 1.9660118702606414e-05, "loss": 1.742633581161499, "num_input_tokens_seen": 25923673, "step": 397, "train_runtime": 8661.969, "train_tokens_per_second": 2992.815 }, { "epoch": 0.252738529925385, "grad_norm": 1.2754477262496948, "learning_rate": 1.9658396754288525e-05, "loss": 1.6841604709625244, "num_input_tokens_seen": 25989206, "step": 398, "train_runtime": 8683.8785, "train_tokens_per_second": 2992.811 }, { "epoch": 0.2533735513573583, "grad_norm": 1.288865089416504, "learning_rate": 1.9656670530806382e-05, "loss": 1.6269450187683105, "num_input_tokens_seen": 26054688, "step": 399, "train_runtime": 8705.0821, "train_tokens_per_second": 2993.043 }, { "epoch": 0.25400857278933164, "grad_norm": 1.2244617938995361, "learning_rate": 1.9654940032924066e-05, "loss": 1.86469566822052, "num_input_tokens_seen": 26120111, "step": 400, "train_runtime": 8726.7062, "train_tokens_per_second": 2993.124 }, { "epoch": 0.25400857278933164, "eval_loss": 1.6216791868209839, "eval_runtime": 12.9197, "eval_samples_per_second": 1.78, "eval_steps_per_second": 0.929, "num_input_tokens_seen": 26120111, "step": 400 }, { "epoch": 0.25464359422130495, "grad_norm": 1.3214870691299438, "learning_rate": 1.965320526140757e-05, "loss": 1.7646476030349731, "num_input_tokens_seen": 26185638, "step": 401, "train_runtime": 8796.7438, "train_tokens_per_second": 2976.742 }, { "epoch": 0.2552786156532783, "grad_norm": 1.2135201692581177, "learning_rate": 1.9651466217024763e-05, "loss": 1.6081857681274414, "num_input_tokens_seen": 26251158, "step": 402, "train_runtime": 8818.5928, "train_tokens_per_second": 2976.797 }, { "epoch": 0.2559136370852516, "grad_norm": 1.410855770111084, "learning_rate": 1.964972290054541e-05, "loss": 1.7097179889678955, "num_input_tokens_seen": 26310228, "step": 403, "train_runtime": 8838.3586, "train_tokens_per_second": 2976.823 }, { "epoch": 0.25654865851722497, "grad_norm": 1.2175610065460205, "learning_rate": 1.9647975312741167e-05, "loss": 1.6301252841949463, "num_input_tokens_seen": 26375711, "step": 404, "train_runtime": 8859.8889, "train_tokens_per_second": 2976.98 }, { "epoch": 0.2571836799491983, "grad_norm": 1.3450310230255127, "learning_rate": 1.964622345438558e-05, "loss": 1.5299708843231201, "num_input_tokens_seen": 26434991, "step": 405, "train_runtime": 8879.2746, "train_tokens_per_second": 2977.157 }, { "epoch": 0.25781870138117163, "grad_norm": 1.3080724477767944, "learning_rate": 1.9644467326254094e-05, "loss": 1.8319191932678223, "num_input_tokens_seen": 26500389, "step": 406, "train_runtime": 8900.0415, "train_tokens_per_second": 2977.558 }, { "epoch": 0.25845372281314494, "grad_norm": 1.248881459236145, "learning_rate": 1.964270692912403e-05, "loss": 1.7714515924453735, "num_input_tokens_seen": 26565910, "step": 407, "train_runtime": 8920.7215, "train_tokens_per_second": 2978.0 }, { "epoch": 0.2590887442451183, "grad_norm": 1.2445948123931885, "learning_rate": 1.964094226377461e-05, "loss": 1.7827095985412598, "num_input_tokens_seen": 26631346, "step": 408, "train_runtime": 8942.217, "train_tokens_per_second": 2978.159 }, { "epoch": 0.2597237656770916, "grad_norm": 1.2487560510635376, "learning_rate": 1.9639173330986933e-05, "loss": 1.6827641725540161, "num_input_tokens_seen": 26696845, "step": 409, "train_runtime": 8963.1609, "train_tokens_per_second": 2978.508 }, { "epoch": 0.2603587871090649, "grad_norm": 1.0650070905685425, "learning_rate": 1.9637400131544e-05, "loss": 1.5308676958084106, "num_input_tokens_seen": 26762318, "step": 410, "train_runtime": 8983.8974, "train_tokens_per_second": 2978.921 }, { "epoch": 0.26099380854103826, "grad_norm": 1.669959545135498, "learning_rate": 1.9635622666230687e-05, "loss": 2.0166032314300537, "num_input_tokens_seen": 26827757, "step": 411, "train_runtime": 9006.1641, "train_tokens_per_second": 2978.822 }, { "epoch": 0.26162882997301157, "grad_norm": 1.179023027420044, "learning_rate": 1.9633840935833775e-05, "loss": 1.7485339641571045, "num_input_tokens_seen": 26893256, "step": 412, "train_runtime": 9027.8313, "train_tokens_per_second": 2978.928 }, { "epoch": 0.2622638514049849, "grad_norm": 1.471362590789795, "learning_rate": 1.963205494114192e-05, "loss": 1.9037249088287354, "num_input_tokens_seen": 26958766, "step": 413, "train_runtime": 9049.611, "train_tokens_per_second": 2978.997 }, { "epoch": 0.26289887283695823, "grad_norm": 1.0852354764938354, "learning_rate": 1.9630264682945673e-05, "loss": 1.4683184623718262, "num_input_tokens_seen": 27024182, "step": 414, "train_runtime": 9070.0305, "train_tokens_per_second": 2979.503 }, { "epoch": 0.2635338942689316, "grad_norm": 1.3008357286453247, "learning_rate": 1.9628470162037465e-05, "loss": 1.7513959407806396, "num_input_tokens_seen": 27089696, "step": 415, "train_runtime": 9092.2071, "train_tokens_per_second": 2979.441 }, { "epoch": 0.2641689157009049, "grad_norm": 1.4250738620758057, "learning_rate": 1.9626671379211616e-05, "loss": 1.8499200344085693, "num_input_tokens_seen": 27155181, "step": 416, "train_runtime": 9114.2055, "train_tokens_per_second": 2979.435 }, { "epoch": 0.26480393713287825, "grad_norm": 1.1769659519195557, "learning_rate": 1.9624868335264336e-05, "loss": 1.6703150272369385, "num_input_tokens_seen": 27220524, "step": 417, "train_runtime": 9135.0367, "train_tokens_per_second": 2979.794 }, { "epoch": 0.26543895856485156, "grad_norm": 1.1132149696350098, "learning_rate": 1.9623061030993717e-05, "loss": 1.6635994911193848, "num_input_tokens_seen": 27285972, "step": 418, "train_runtime": 9156.0096, "train_tokens_per_second": 2980.116 }, { "epoch": 0.2660739799968249, "grad_norm": 1.280731201171875, "learning_rate": 1.9621249467199743e-05, "loss": 1.8380918502807617, "num_input_tokens_seen": 27351467, "step": 419, "train_runtime": 9177.5099, "train_tokens_per_second": 2980.271 }, { "epoch": 0.2667090014287982, "grad_norm": 1.300719976425171, "learning_rate": 1.961943364468428e-05, "loss": 1.7585670948028564, "num_input_tokens_seen": 27416978, "step": 420, "train_runtime": 9200.0691, "train_tokens_per_second": 2980.084 }, { "epoch": 0.2673440228607715, "grad_norm": 1.2629164457321167, "learning_rate": 1.961761356425107e-05, "loss": 1.8130794763565063, "num_input_tokens_seen": 27482401, "step": 421, "train_runtime": 9221.6952, "train_tokens_per_second": 2980.19 }, { "epoch": 0.2679790442927449, "grad_norm": 1.3606886863708496, "learning_rate": 1.9615789226705755e-05, "loss": 1.7881965637207031, "num_input_tokens_seen": 27547921, "step": 422, "train_runtime": 9244.0869, "train_tokens_per_second": 2980.059 }, { "epoch": 0.2686140657247182, "grad_norm": 1.1908453702926636, "learning_rate": 1.9613960632855855e-05, "loss": 1.69158935546875, "num_input_tokens_seen": 27613314, "step": 423, "train_runtime": 9265.2741, "train_tokens_per_second": 2980.302 }, { "epoch": 0.26924908715669155, "grad_norm": 1.1536837816238403, "learning_rate": 1.961212778351077e-05, "loss": 1.5742290019989014, "num_input_tokens_seen": 27678831, "step": 424, "train_runtime": 9286.4548, "train_tokens_per_second": 2980.559 }, { "epoch": 0.26988410858866485, "grad_norm": 1.1639869213104248, "learning_rate": 1.961029067948179e-05, "loss": 1.5892159938812256, "num_input_tokens_seen": 27744325, "step": 425, "train_runtime": 9307.7434, "train_tokens_per_second": 2980.779 }, { "epoch": 0.2705191300206382, "grad_norm": 1.2577472925186157, "learning_rate": 1.960844932158208e-05, "loss": 1.7973240613937378, "num_input_tokens_seen": 27809774, "step": 426, "train_runtime": 9329.5971, "train_tokens_per_second": 2980.812 }, { "epoch": 0.2711541514526115, "grad_norm": 1.4027931690216064, "learning_rate": 1.9606603710626698e-05, "loss": 1.8277831077575684, "num_input_tokens_seen": 27875042, "step": 427, "train_runtime": 9350.8727, "train_tokens_per_second": 2981.01 }, { "epoch": 0.2717891728845849, "grad_norm": 1.2829948663711548, "learning_rate": 1.960475384743258e-05, "loss": 1.8002760410308838, "num_input_tokens_seen": 27940529, "step": 428, "train_runtime": 9372.4042, "train_tokens_per_second": 2981.149 }, { "epoch": 0.2724241943165582, "grad_norm": 1.191817283630371, "learning_rate": 1.9602899732818542e-05, "loss": 1.5610756874084473, "num_input_tokens_seen": 28005954, "step": 429, "train_runtime": 9393.5522, "train_tokens_per_second": 2981.402 }, { "epoch": 0.27305921574853154, "grad_norm": 1.399361491203308, "learning_rate": 1.9601041367605282e-05, "loss": 1.8181368112564087, "num_input_tokens_seen": 28071436, "step": 430, "train_runtime": 9415.3704, "train_tokens_per_second": 2981.448 }, { "epoch": 0.27369423718050484, "grad_norm": 1.2037559747695923, "learning_rate": 1.9599178752615388e-05, "loss": 1.7649712562561035, "num_input_tokens_seen": 28136886, "step": 431, "train_runtime": 9436.2885, "train_tokens_per_second": 2981.775 }, { "epoch": 0.27432925861247814, "grad_norm": 1.2544466257095337, "learning_rate": 1.9597311888673314e-05, "loss": 1.7503705024719238, "num_input_tokens_seen": 28202392, "step": 432, "train_runtime": 9457.6457, "train_tokens_per_second": 2981.967 }, { "epoch": 0.2749642800444515, "grad_norm": 1.3544825315475464, "learning_rate": 1.959544077660541e-05, "loss": 1.7499384880065918, "num_input_tokens_seen": 28267842, "step": 433, "train_runtime": 9479.2527, "train_tokens_per_second": 2982.075 }, { "epoch": 0.2755993014764248, "grad_norm": 1.1661866903305054, "learning_rate": 1.9593565417239894e-05, "loss": 1.4562559127807617, "num_input_tokens_seen": 28333049, "step": 434, "train_runtime": 9499.3943, "train_tokens_per_second": 2982.616 }, { "epoch": 0.27623432290839817, "grad_norm": 1.174961805343628, "learning_rate": 1.9591685811406877e-05, "loss": 1.6057133674621582, "num_input_tokens_seen": 28398389, "step": 435, "train_runtime": 9519.9973, "train_tokens_per_second": 2983.025 }, { "epoch": 0.27686934434037147, "grad_norm": 1.3292787075042725, "learning_rate": 1.9589801959938332e-05, "loss": 1.7533601522445679, "num_input_tokens_seen": 28463907, "step": 436, "train_runtime": 9541.3628, "train_tokens_per_second": 2983.212 }, { "epoch": 0.27750436577234483, "grad_norm": 1.3003607988357544, "learning_rate": 1.958791386366813e-05, "loss": 1.6636080741882324, "num_input_tokens_seen": 28529370, "step": 437, "train_runtime": 9562.8823, "train_tokens_per_second": 2983.344 }, { "epoch": 0.27813938720431813, "grad_norm": 1.2192535400390625, "learning_rate": 1.958602152343201e-05, "loss": 1.7475457191467285, "num_input_tokens_seen": 28594892, "step": 438, "train_runtime": 9584.9746, "train_tokens_per_second": 2983.304 }, { "epoch": 0.2787744086362915, "grad_norm": 1.465795874595642, "learning_rate": 1.9584124940067587e-05, "loss": 1.8368146419525146, "num_input_tokens_seen": 28660272, "step": 439, "train_runtime": 9606.3575, "train_tokens_per_second": 2983.469 }, { "epoch": 0.2794094300682648, "grad_norm": 1.2360854148864746, "learning_rate": 1.9582224114414367e-05, "loss": 1.6112836599349976, "num_input_tokens_seen": 28725788, "step": 440, "train_runtime": 9627.7808, "train_tokens_per_second": 2983.635 }, { "epoch": 0.28004445150023816, "grad_norm": 1.233082890510559, "learning_rate": 1.9580319047313724e-05, "loss": 1.5489685535430908, "num_input_tokens_seen": 28791210, "step": 441, "train_runtime": 9648.4674, "train_tokens_per_second": 2984.019 }, { "epoch": 0.28067947293221146, "grad_norm": 1.1836196184158325, "learning_rate": 1.9578409739608902e-05, "loss": 1.6974899768829346, "num_input_tokens_seen": 28856672, "step": 442, "train_runtime": 9669.578, "train_tokens_per_second": 2984.274 }, { "epoch": 0.28131449436418476, "grad_norm": 1.250532865524292, "learning_rate": 1.9576496192145047e-05, "loss": 1.506308674812317, "num_input_tokens_seen": 28922079, "step": 443, "train_runtime": 9690.7438, "train_tokens_per_second": 2984.506 }, { "epoch": 0.2819495157961581, "grad_norm": 1.3529529571533203, "learning_rate": 1.9574578405769152e-05, "loss": 2.0464928150177, "num_input_tokens_seen": 28987599, "step": 444, "train_runtime": 9713.6662, "train_tokens_per_second": 2984.208 }, { "epoch": 0.2825845372281314, "grad_norm": 1.134677529335022, "learning_rate": 1.957265638133011e-05, "loss": 1.539945363998413, "num_input_tokens_seen": 29053094, "step": 445, "train_runtime": 9734.7801, "train_tokens_per_second": 2984.463 }, { "epoch": 0.2832195586601048, "grad_norm": 1.1093361377716064, "learning_rate": 1.9570730119678675e-05, "loss": 1.6372220516204834, "num_input_tokens_seen": 29118606, "step": 446, "train_runtime": 9755.6422, "train_tokens_per_second": 2984.796 }, { "epoch": 0.2838545800920781, "grad_norm": 1.3167163133621216, "learning_rate": 1.956879962166748e-05, "loss": 1.8077932596206665, "num_input_tokens_seen": 29184058, "step": 447, "train_runtime": 9776.5555, "train_tokens_per_second": 2985.106 }, { "epoch": 0.28448960152405145, "grad_norm": 1.1928576231002808, "learning_rate": 1.956686488815104e-05, "loss": 1.7519491910934448, "num_input_tokens_seen": 29249469, "step": 448, "train_runtime": 9797.8964, "train_tokens_per_second": 2985.281 }, { "epoch": 0.28512462295602475, "grad_norm": 1.367032527923584, "learning_rate": 1.956492591998574e-05, "loss": 1.7756125926971436, "num_input_tokens_seen": 29314946, "step": 449, "train_runtime": 9819.2993, "train_tokens_per_second": 2985.442 }, { "epoch": 0.2857596443879981, "grad_norm": 1.2131046056747437, "learning_rate": 1.9562982718029836e-05, "loss": 1.7029119729995728, "num_input_tokens_seen": 29380411, "step": 450, "train_runtime": 9840.4608, "train_tokens_per_second": 2985.674 }, { "epoch": 0.2863946658199714, "grad_norm": 1.156861662864685, "learning_rate": 1.956103528314346e-05, "loss": 1.6001571416854858, "num_input_tokens_seen": 29445731, "step": 451, "train_runtime": 9860.8029, "train_tokens_per_second": 2986.139 }, { "epoch": 0.2870296872519448, "grad_norm": 1.2008904218673706, "learning_rate": 1.9559083616188623e-05, "loss": 1.586685299873352, "num_input_tokens_seen": 29511253, "step": 452, "train_runtime": 9882.5802, "train_tokens_per_second": 2986.189 }, { "epoch": 0.2876647086839181, "grad_norm": 1.1775456666946411, "learning_rate": 1.95571277180292e-05, "loss": 1.6831676959991455, "num_input_tokens_seen": 29576760, "step": 453, "train_runtime": 9903.8991, "train_tokens_per_second": 2986.375 }, { "epoch": 0.2882997301158914, "grad_norm": 1.149344563484192, "learning_rate": 1.955516758953095e-05, "loss": 1.6375091075897217, "num_input_tokens_seen": 29642211, "step": 454, "train_runtime": 9924.9758, "train_tokens_per_second": 2986.628 }, { "epoch": 0.28893475154786474, "grad_norm": 1.1355571746826172, "learning_rate": 1.9553203231561494e-05, "loss": 1.5922412872314453, "num_input_tokens_seen": 29707732, "step": 455, "train_runtime": 9946.3806, "train_tokens_per_second": 2986.788 }, { "epoch": 0.28956977297983805, "grad_norm": 1.2442914247512817, "learning_rate": 1.9551234644990334e-05, "loss": 1.7037187814712524, "num_input_tokens_seen": 29773160, "step": 456, "train_runtime": 9967.6917, "train_tokens_per_second": 2986.966 }, { "epoch": 0.2902047944118114, "grad_norm": 1.2463210821151733, "learning_rate": 1.9549261830688833e-05, "loss": 1.5238230228424072, "num_input_tokens_seen": 29838666, "step": 457, "train_runtime": 9989.0965, "train_tokens_per_second": 2987.124 }, { "epoch": 0.2908398158437847, "grad_norm": 1.2468279600143433, "learning_rate": 1.954728478953024e-05, "loss": 1.7725987434387207, "num_input_tokens_seen": 29904151, "step": 458, "train_runtime": 10010.4093, "train_tokens_per_second": 2987.306 }, { "epoch": 0.29147483727575807, "grad_norm": 1.2968776226043701, "learning_rate": 1.9545303522389656e-05, "loss": 1.7080881595611572, "num_input_tokens_seen": 29969599, "step": 459, "train_runtime": 10032.7105, "train_tokens_per_second": 2987.189 }, { "epoch": 0.2921098587077314, "grad_norm": 1.5239629745483398, "learning_rate": 1.9543318030144072e-05, "loss": 1.9671045541763306, "num_input_tokens_seen": 30035021, "step": 460, "train_runtime": 10054.7502, "train_tokens_per_second": 2987.147 }, { "epoch": 0.29274488013970473, "grad_norm": 1.1882610321044922, "learning_rate": 1.9541328313672335e-05, "loss": 1.5505541563034058, "num_input_tokens_seen": 30100483, "step": 461, "train_runtime": 10076.0747, "train_tokens_per_second": 2987.322 }, { "epoch": 0.29337990157167804, "grad_norm": 1.197775959968567, "learning_rate": 1.9539334373855173e-05, "loss": 1.5393860340118408, "num_input_tokens_seen": 30164061, "step": 462, "train_runtime": 10096.0656, "train_tokens_per_second": 2987.705 }, { "epoch": 0.2940149230036514, "grad_norm": 1.0769984722137451, "learning_rate": 1.9537336211575175e-05, "loss": 1.4604722261428833, "num_input_tokens_seen": 30229518, "step": 463, "train_runtime": 10116.8532, "train_tokens_per_second": 2988.036 }, { "epoch": 0.2946499444356247, "grad_norm": 1.427704930305481, "learning_rate": 1.9535333827716797e-05, "loss": 1.9546077251434326, "num_input_tokens_seen": 30295016, "step": 464, "train_runtime": 10139.3772, "train_tokens_per_second": 2987.858 }, { "epoch": 0.295284965867598, "grad_norm": 1.2052375078201294, "learning_rate": 1.9533327223166377e-05, "loss": 1.6707539558410645, "num_input_tokens_seen": 30360517, "step": 465, "train_runtime": 10160.6474, "train_tokens_per_second": 2988.049 }, { "epoch": 0.29591998729957136, "grad_norm": 1.1346933841705322, "learning_rate": 1.9531316398812105e-05, "loss": 1.598318099975586, "num_input_tokens_seen": 30425999, "step": 466, "train_runtime": 10181.322, "train_tokens_per_second": 2988.413 }, { "epoch": 0.29655500873154467, "grad_norm": 1.279105305671692, "learning_rate": 1.952930135554405e-05, "loss": 1.7073347568511963, "num_input_tokens_seen": 30491368, "step": 467, "train_runtime": 10202.6432, "train_tokens_per_second": 2988.575 }, { "epoch": 0.297190030163518, "grad_norm": 1.2870451211929321, "learning_rate": 1.9527282094254143e-05, "loss": 1.933992862701416, "num_input_tokens_seen": 30556851, "step": 468, "train_runtime": 10224.7551, "train_tokens_per_second": 2988.517 }, { "epoch": 0.29782505159549133, "grad_norm": 1.3176647424697876, "learning_rate": 1.9525258615836185e-05, "loss": 1.8637299537658691, "num_input_tokens_seen": 30622012, "step": 469, "train_runtime": 10246.0069, "train_tokens_per_second": 2988.678 }, { "epoch": 0.2984600730274647, "grad_norm": 1.1291133165359497, "learning_rate": 1.9523230921185842e-05, "loss": 1.642372488975525, "num_input_tokens_seen": 30687524, "step": 470, "train_runtime": 10267.8188, "train_tokens_per_second": 2988.709 }, { "epoch": 0.299095094459438, "grad_norm": 1.3822917938232422, "learning_rate": 1.952119901120065e-05, "loss": 1.768362045288086, "num_input_tokens_seen": 30752837, "step": 471, "train_runtime": 10289.1813, "train_tokens_per_second": 2988.852 }, { "epoch": 0.29973011589141135, "grad_norm": 1.2381558418273926, "learning_rate": 1.9519162886780006e-05, "loss": 1.7972157001495361, "num_input_tokens_seen": 30818304, "step": 472, "train_runtime": 10310.782, "train_tokens_per_second": 2988.94 }, { "epoch": 0.30036513732338466, "grad_norm": 1.1346229314804077, "learning_rate": 1.9517122548825166e-05, "loss": 1.5688745975494385, "num_input_tokens_seen": 30883695, "step": 473, "train_runtime": 10332.2122, "train_tokens_per_second": 2989.069 }, { "epoch": 0.301000158755358, "grad_norm": 1.0715123414993286, "learning_rate": 1.951507799823927e-05, "loss": 1.5290358066558838, "num_input_tokens_seen": 30949202, "step": 474, "train_runtime": 10352.9637, "train_tokens_per_second": 2989.405 }, { "epoch": 0.3016351801873313, "grad_norm": 1.283875823020935, "learning_rate": 1.951302923592731e-05, "loss": 1.6874825954437256, "num_input_tokens_seen": 31014617, "step": 475, "train_runtime": 10374.4749, "train_tokens_per_second": 2989.512 }, { "epoch": 0.3022702016193047, "grad_norm": 1.261551022529602, "learning_rate": 1.951097626279614e-05, "loss": 1.7580422163009644, "num_input_tokens_seen": 31080036, "step": 476, "train_runtime": 10396.0849, "train_tokens_per_second": 2989.59 }, { "epoch": 0.302905223051278, "grad_norm": 1.2211933135986328, "learning_rate": 1.950891907975449e-05, "loss": 1.7568247318267822, "num_input_tokens_seen": 31145524, "step": 477, "train_runtime": 10416.6951, "train_tokens_per_second": 2989.962 }, { "epoch": 0.3035402444832513, "grad_norm": 1.2732092142105103, "learning_rate": 1.950685768771293e-05, "loss": 1.6463513374328613, "num_input_tokens_seen": 31210968, "step": 478, "train_runtime": 10438.5324, "train_tokens_per_second": 2989.977 }, { "epoch": 0.30417526591522465, "grad_norm": 1.2034863233566284, "learning_rate": 1.950479208758392e-05, "loss": 1.715547800064087, "num_input_tokens_seen": 31276445, "step": 479, "train_runtime": 10460.2911, "train_tokens_per_second": 2990.017 }, { "epoch": 0.30481028734719795, "grad_norm": 1.226557970046997, "learning_rate": 1.9502722280281775e-05, "loss": 1.629286527633667, "num_input_tokens_seen": 31341977, "step": 480, "train_runtime": 10481.9552, "train_tokens_per_second": 2990.089 }, { "epoch": 0.3054453087791713, "grad_norm": 1.2057313919067383, "learning_rate": 1.9500648266722658e-05, "loss": 1.7039220333099365, "num_input_tokens_seen": 31407494, "step": 481, "train_runtime": 10503.4525, "train_tokens_per_second": 2990.207 }, { "epoch": 0.3060803302111446, "grad_norm": 1.1838306188583374, "learning_rate": 1.949857004782461e-05, "loss": 1.622457504272461, "num_input_tokens_seen": 31473006, "step": 482, "train_runtime": 10524.9334, "train_tokens_per_second": 2990.328 }, { "epoch": 0.306715351643118, "grad_norm": 1.1867821216583252, "learning_rate": 1.9496487624507526e-05, "loss": 1.6854020357131958, "num_input_tokens_seen": 31538429, "step": 483, "train_runtime": 10545.7507, "train_tokens_per_second": 2990.629 }, { "epoch": 0.3073503730750913, "grad_norm": 1.278201937675476, "learning_rate": 1.949440099769316e-05, "loss": 1.8375623226165771, "num_input_tokens_seen": 31603907, "step": 484, "train_runtime": 10567.1905, "train_tokens_per_second": 2990.758 }, { "epoch": 0.30798539450706464, "grad_norm": 1.1826777458190918, "learning_rate": 1.9492310168305142e-05, "loss": 1.7093364000320435, "num_input_tokens_seen": 31669333, "step": 485, "train_runtime": 10588.2766, "train_tokens_per_second": 2990.981 }, { "epoch": 0.30862041593903794, "grad_norm": 1.2329716682434082, "learning_rate": 1.949021513726894e-05, "loss": 1.6076799631118774, "num_input_tokens_seen": 31734733, "step": 486, "train_runtime": 10609.9782, "train_tokens_per_second": 2991.027 }, { "epoch": 0.3092554373710113, "grad_norm": 1.333528995513916, "learning_rate": 1.9488115905511894e-05, "loss": 1.7189059257507324, "num_input_tokens_seen": 31800158, "step": 487, "train_runtime": 10631.8932, "train_tokens_per_second": 2991.016 }, { "epoch": 0.3098904588029846, "grad_norm": 1.2475364208221436, "learning_rate": 1.9486012473963204e-05, "loss": 1.6411858797073364, "num_input_tokens_seen": 31865668, "step": 488, "train_runtime": 10653.0215, "train_tokens_per_second": 2991.233 }, { "epoch": 0.3105254802349579, "grad_norm": 1.1999226808547974, "learning_rate": 1.9483904843553928e-05, "loss": 1.6517740488052368, "num_input_tokens_seen": 31931181, "step": 489, "train_runtime": 10675.2384, "train_tokens_per_second": 2991.145 }, { "epoch": 0.31116050166693127, "grad_norm": 1.2598960399627686, "learning_rate": 1.9481793015216975e-05, "loss": 1.7384450435638428, "num_input_tokens_seen": 31996704, "step": 490, "train_runtime": 10697.3217, "train_tokens_per_second": 2991.095 }, { "epoch": 0.31179552309890457, "grad_norm": 1.3259944915771484, "learning_rate": 1.9479676989887128e-05, "loss": 1.8411067724227905, "num_input_tokens_seen": 32062216, "step": 491, "train_runtime": 10719.818, "train_tokens_per_second": 2990.929 }, { "epoch": 0.31243054453087793, "grad_norm": 1.1669515371322632, "learning_rate": 1.947755676850101e-05, "loss": 1.529805302619934, "num_input_tokens_seen": 32127618, "step": 492, "train_runtime": 10740.9708, "train_tokens_per_second": 2991.128 }, { "epoch": 0.31306556596285123, "grad_norm": 1.2873071432113647, "learning_rate": 1.9475432351997115e-05, "loss": 1.6871657371520996, "num_input_tokens_seen": 32193035, "step": 493, "train_runtime": 10762.1838, "train_tokens_per_second": 2991.311 }, { "epoch": 0.3137005873948246, "grad_norm": 1.343780755996704, "learning_rate": 1.9473303741315782e-05, "loss": 1.8299542665481567, "num_input_tokens_seen": 32258483, "step": 494, "train_runtime": 10784.0127, "train_tokens_per_second": 2991.325 }, { "epoch": 0.3143356088267979, "grad_norm": 1.2278966903686523, "learning_rate": 1.947117093739922e-05, "loss": 1.508264422416687, "num_input_tokens_seen": 32317486, "step": 495, "train_runtime": 10802.7707, "train_tokens_per_second": 2991.592 }, { "epoch": 0.31497063025877126, "grad_norm": 1.3010315895080566, "learning_rate": 1.946903394119148e-05, "loss": 1.7676200866699219, "num_input_tokens_seen": 32383002, "step": 496, "train_runtime": 10825.7394, "train_tokens_per_second": 2991.297 }, { "epoch": 0.31560565169074456, "grad_norm": 1.3691797256469727, "learning_rate": 1.9466892753638484e-05, "loss": 1.7581708431243896, "num_input_tokens_seen": 32448467, "step": 497, "train_runtime": 10847.5814, "train_tokens_per_second": 2991.309 }, { "epoch": 0.3162406731227179, "grad_norm": 1.154229998588562, "learning_rate": 1.9464747375687995e-05, "loss": 1.5609402656555176, "num_input_tokens_seen": 32513840, "step": 498, "train_runtime": 10868.8031, "train_tokens_per_second": 2991.483 }, { "epoch": 0.3168756945546912, "grad_norm": 1.2690328359603882, "learning_rate": 1.9462597808289637e-05, "loss": 1.6706411838531494, "num_input_tokens_seen": 32579353, "step": 499, "train_runtime": 10890.0239, "train_tokens_per_second": 2991.67 }, { "epoch": 0.3175107159866645, "grad_norm": 1.1944035291671753, "learning_rate": 1.9460444052394888e-05, "loss": 1.7267487049102783, "num_input_tokens_seen": 32644824, "step": 500, "train_runtime": 10911.0857, "train_tokens_per_second": 2991.895 }, { "epoch": 0.3175107159866645, "eval_loss": 1.611861228942871, "eval_runtime": 12.9028, "eval_samples_per_second": 1.783, "eval_steps_per_second": 0.93, "num_input_tokens_seen": 32644824, "step": 500 }, { "epoch": 0.3181457374186379, "grad_norm": 1.2006933689117432, "learning_rate": 1.9458286108957085e-05, "loss": 1.7567520141601562, "num_input_tokens_seen": 32710317, "step": 501, "train_runtime": 10984.0718, "train_tokens_per_second": 2977.977 }, { "epoch": 0.3187807588506112, "grad_norm": 1.310566782951355, "learning_rate": 1.9456123978931408e-05, "loss": 1.6755163669586182, "num_input_tokens_seen": 32775713, "step": 502, "train_runtime": 11005.0349, "train_tokens_per_second": 2978.247 }, { "epoch": 0.31941578028258455, "grad_norm": 1.1448309421539307, "learning_rate": 1.9453957663274902e-05, "loss": 1.471497654914856, "num_input_tokens_seen": 32841186, "step": 503, "train_runtime": 11025.7179, "train_tokens_per_second": 2978.598 }, { "epoch": 0.32005080171455785, "grad_norm": 1.2365988492965698, "learning_rate": 1.9451787162946452e-05, "loss": 1.6598858833312988, "num_input_tokens_seen": 32906635, "step": 504, "train_runtime": 11046.762, "train_tokens_per_second": 2978.849 }, { "epoch": 0.3206858231465312, "grad_norm": 1.0902918577194214, "learning_rate": 1.9449612478906808e-05, "loss": 1.5768744945526123, "num_input_tokens_seen": 32972144, "step": 505, "train_runtime": 11068.616, "train_tokens_per_second": 2978.886 }, { "epoch": 0.3213208445785045, "grad_norm": 1.2584844827651978, "learning_rate": 1.9447433612118557e-05, "loss": 1.826557993888855, "num_input_tokens_seen": 33037643, "step": 506, "train_runtime": 11090.398, "train_tokens_per_second": 2978.941 }, { "epoch": 0.3219558660104779, "grad_norm": 1.2488008737564087, "learning_rate": 1.9445250563546153e-05, "loss": 1.6658670902252197, "num_input_tokens_seen": 33103002, "step": 507, "train_runtime": 11111.8589, "train_tokens_per_second": 2979.07 }, { "epoch": 0.3225908874424512, "grad_norm": 1.5790597200393677, "learning_rate": 1.9443063334155896e-05, "loss": 1.6499345302581787, "num_input_tokens_seen": 33168505, "step": 508, "train_runtime": 11133.7729, "train_tokens_per_second": 2979.089 }, { "epoch": 0.32322590887442454, "grad_norm": 1.2668297290802002, "learning_rate": 1.9440871924915932e-05, "loss": 1.7663946151733398, "num_input_tokens_seen": 33233908, "step": 509, "train_runtime": 11154.4255, "train_tokens_per_second": 2979.437 }, { "epoch": 0.32386093030639784, "grad_norm": 1.2979285717010498, "learning_rate": 1.9438676336796253e-05, "loss": 1.6815861463546753, "num_input_tokens_seen": 33299390, "step": 510, "train_runtime": 11175.4331, "train_tokens_per_second": 2979.696 }, { "epoch": 0.32449595173837115, "grad_norm": 1.2163091897964478, "learning_rate": 1.943647657076872e-05, "loss": 1.5642526149749756, "num_input_tokens_seen": 33364876, "step": 511, "train_runtime": 11196.4414, "train_tokens_per_second": 2979.954 }, { "epoch": 0.3251309731703445, "grad_norm": 1.196199655532837, "learning_rate": 1.9434272627807025e-05, "loss": 1.6472184658050537, "num_input_tokens_seen": 33430373, "step": 512, "train_runtime": 11218.1243, "train_tokens_per_second": 2980.032 }, { "epoch": 0.3257659946023178, "grad_norm": 1.1857134103775024, "learning_rate": 1.9432064508886713e-05, "loss": 1.7830053567886353, "num_input_tokens_seen": 33495797, "step": 513, "train_runtime": 11240.0919, "train_tokens_per_second": 2980.029 }, { "epoch": 0.32640101603429117, "grad_norm": 1.180471658706665, "learning_rate": 1.9429852214985182e-05, "loss": 1.6981847286224365, "num_input_tokens_seen": 33561268, "step": 514, "train_runtime": 11261.2791, "train_tokens_per_second": 2980.236 }, { "epoch": 0.3270360374662645, "grad_norm": 1.1835815906524658, "learning_rate": 1.9427635747081673e-05, "loss": 1.7831863164901733, "num_input_tokens_seen": 33626751, "step": 515, "train_runtime": 11283.0076, "train_tokens_per_second": 2980.3 }, { "epoch": 0.32767105889823783, "grad_norm": 1.3118810653686523, "learning_rate": 1.9425415106157277e-05, "loss": 1.9049441814422607, "num_input_tokens_seen": 33692265, "step": 516, "train_runtime": 11305.1283, "train_tokens_per_second": 2980.264 }, { "epoch": 0.32830608033021114, "grad_norm": 1.3030939102172852, "learning_rate": 1.9423190293194935e-05, "loss": 1.8822134733200073, "num_input_tokens_seen": 33757747, "step": 517, "train_runtime": 11327.7368, "train_tokens_per_second": 2980.096 }, { "epoch": 0.3289411017621845, "grad_norm": 1.2092723846435547, "learning_rate": 1.9420961309179432e-05, "loss": 1.5950736999511719, "num_input_tokens_seen": 33823261, "step": 518, "train_runtime": 11348.8869, "train_tokens_per_second": 2980.315 }, { "epoch": 0.3295761231941578, "grad_norm": 1.2174867391586304, "learning_rate": 1.9418728155097392e-05, "loss": 1.6014070510864258, "num_input_tokens_seen": 33888791, "step": 519, "train_runtime": 11369.6534, "train_tokens_per_second": 2980.635 }, { "epoch": 0.33021114462613116, "grad_norm": 1.3130896091461182, "learning_rate": 1.9416490831937298e-05, "loss": 1.7795541286468506, "num_input_tokens_seen": 33954232, "step": 520, "train_runtime": 11391.6893, "train_tokens_per_second": 2980.614 }, { "epoch": 0.33084616605810446, "grad_norm": 1.2099497318267822, "learning_rate": 1.9414249340689474e-05, "loss": 1.5879182815551758, "num_input_tokens_seen": 34019735, "step": 521, "train_runtime": 11413.4999, "train_tokens_per_second": 2980.658 }, { "epoch": 0.33148118749007777, "grad_norm": 1.203334093093872, "learning_rate": 1.9412003682346078e-05, "loss": 1.7318366765975952, "num_input_tokens_seen": 34085187, "step": 522, "train_runtime": 11434.4158, "train_tokens_per_second": 2980.929 }, { "epoch": 0.3321162089220511, "grad_norm": 1.187778353691101, "learning_rate": 1.9409753857901132e-05, "loss": 1.5854191780090332, "num_input_tokens_seen": 34150619, "step": 523, "train_runtime": 11455.6475, "train_tokens_per_second": 2981.116 }, { "epoch": 0.33275123035402443, "grad_norm": 1.275651216506958, "learning_rate": 1.9407499868350484e-05, "loss": 1.6546484231948853, "num_input_tokens_seen": 34216118, "step": 524, "train_runtime": 11477.4926, "train_tokens_per_second": 2981.149 }, { "epoch": 0.3333862517859978, "grad_norm": 1.3293884992599487, "learning_rate": 1.940524171469184e-05, "loss": 1.8582302331924438, "num_input_tokens_seen": 34281550, "step": 525, "train_runtime": 11498.682, "train_tokens_per_second": 2981.346 }, { "epoch": 0.3340212732179711, "grad_norm": 1.310368537902832, "learning_rate": 1.940297939792473e-05, "loss": 1.6926864385604858, "num_input_tokens_seen": 34347035, "step": 526, "train_runtime": 11520.6685, "train_tokens_per_second": 2981.34 }, { "epoch": 0.33465629464994445, "grad_norm": 1.4138693809509277, "learning_rate": 1.9400712919050556e-05, "loss": 1.976351261138916, "num_input_tokens_seen": 34412508, "step": 527, "train_runtime": 11542.3948, "train_tokens_per_second": 2981.401 }, { "epoch": 0.33529131608191776, "grad_norm": 1.1740741729736328, "learning_rate": 1.9398442279072537e-05, "loss": 1.5284154415130615, "num_input_tokens_seen": 34477957, "step": 528, "train_runtime": 11563.7309, "train_tokens_per_second": 2981.56 }, { "epoch": 0.3359263375138911, "grad_norm": 1.1872124671936035, "learning_rate": 1.939616747899574e-05, "loss": 1.71840500831604, "num_input_tokens_seen": 34543404, "step": 529, "train_runtime": 11584.7188, "train_tokens_per_second": 2981.808 }, { "epoch": 0.3365613589458644, "grad_norm": 1.2090320587158203, "learning_rate": 1.939388851982708e-05, "loss": 1.524856448173523, "num_input_tokens_seen": 34608814, "step": 530, "train_runtime": 11605.4143, "train_tokens_per_second": 2982.127 }, { "epoch": 0.3371963803778378, "grad_norm": 1.2077842950820923, "learning_rate": 1.9391605402575308e-05, "loss": 1.8087003231048584, "num_input_tokens_seen": 34674301, "step": 531, "train_runtime": 11628.1639, "train_tokens_per_second": 2981.924 }, { "epoch": 0.3378314018098111, "grad_norm": 1.1833808422088623, "learning_rate": 1.9389318128251014e-05, "loss": 1.7593588829040527, "num_input_tokens_seen": 34739752, "step": 532, "train_runtime": 11648.7904, "train_tokens_per_second": 2982.263 }, { "epoch": 0.3384664232417844, "grad_norm": 1.1537482738494873, "learning_rate": 1.938702669786663e-05, "loss": 1.5397192239761353, "num_input_tokens_seen": 34800556, "step": 533, "train_runtime": 11667.9641, "train_tokens_per_second": 2982.573 }, { "epoch": 0.33910144467375775, "grad_norm": 1.1541699171066284, "learning_rate": 1.9384731112436433e-05, "loss": 1.5981000661849976, "num_input_tokens_seen": 34866076, "step": 534, "train_runtime": 11688.9506, "train_tokens_per_second": 2982.823 }, { "epoch": 0.33973646610573105, "grad_norm": 1.142835021018982, "learning_rate": 1.938243137297653e-05, "loss": 1.4857022762298584, "num_input_tokens_seen": 34931565, "step": 535, "train_runtime": 11709.4599, "train_tokens_per_second": 2983.192 }, { "epoch": 0.3403714875377044, "grad_norm": 1.2448318004608154, "learning_rate": 1.9380127480504872e-05, "loss": 1.7701514959335327, "num_input_tokens_seen": 34996975, "step": 536, "train_runtime": 11730.164, "train_tokens_per_second": 2983.503 }, { "epoch": 0.3410065089696777, "grad_norm": 1.2667723894119263, "learning_rate": 1.937781943604125e-05, "loss": 1.8284798860549927, "num_input_tokens_seen": 35062463, "step": 537, "train_runtime": 11752.0439, "train_tokens_per_second": 2983.52 }, { "epoch": 0.3416415304016511, "grad_norm": 1.1474469900131226, "learning_rate": 1.937550724060728e-05, "loss": 1.6035630702972412, "num_input_tokens_seen": 35127969, "step": 538, "train_runtime": 11772.7616, "train_tokens_per_second": 2983.834 }, { "epoch": 0.3422765518336244, "grad_norm": 1.389029622077942, "learning_rate": 1.937319089522644e-05, "loss": 1.7087236642837524, "num_input_tokens_seen": 35193299, "step": 539, "train_runtime": 11793.5108, "train_tokens_per_second": 2984.124 }, { "epoch": 0.34291157326559774, "grad_norm": 1.0882956981658936, "learning_rate": 1.937087040092402e-05, "loss": 1.43813157081604, "num_input_tokens_seen": 35258813, "step": 540, "train_runtime": 11814.9305, "train_tokens_per_second": 2984.259 }, { "epoch": 0.34354659469757104, "grad_norm": 1.1827389001846313, "learning_rate": 1.9368545758727163e-05, "loss": 1.5703555345535278, "num_input_tokens_seen": 35318664, "step": 541, "train_runtime": 11833.6845, "train_tokens_per_second": 2984.587 }, { "epoch": 0.3441816161295444, "grad_norm": 1.2668019533157349, "learning_rate": 1.9366216969664834e-05, "loss": 1.578696608543396, "num_input_tokens_seen": 35384141, "step": 542, "train_runtime": 11855.2047, "train_tokens_per_second": 2984.693 }, { "epoch": 0.3448166375615177, "grad_norm": 1.1627490520477295, "learning_rate": 1.9363884034767845e-05, "loss": 1.409239411354065, "num_input_tokens_seen": 35449614, "step": 543, "train_runtime": 11876.5096, "train_tokens_per_second": 2984.851 }, { "epoch": 0.345451658993491, "grad_norm": 1.1801083087921143, "learning_rate": 1.9361546955068845e-05, "loss": 1.691254734992981, "num_input_tokens_seen": 35514977, "step": 544, "train_runtime": 11897.5366, "train_tokens_per_second": 2985.07 }, { "epoch": 0.34608668042546437, "grad_norm": 1.27998685836792, "learning_rate": 1.9359205731602305e-05, "loss": 1.769602656364441, "num_input_tokens_seen": 35580472, "step": 545, "train_runtime": 11919.3408, "train_tokens_per_second": 2985.104 }, { "epoch": 0.34672170185743767, "grad_norm": 1.1512547731399536, "learning_rate": 1.9356860365404536e-05, "loss": 1.7414482831954956, "num_input_tokens_seen": 35645853, "step": 546, "train_runtime": 11941.0533, "train_tokens_per_second": 2985.151 }, { "epoch": 0.34735672328941103, "grad_norm": 1.1945595741271973, "learning_rate": 1.9354510857513692e-05, "loss": 1.6399338245391846, "num_input_tokens_seen": 35711300, "step": 547, "train_runtime": 11962.8603, "train_tokens_per_second": 2985.181 }, { "epoch": 0.34799174472138433, "grad_norm": 1.237697958946228, "learning_rate": 1.9352157208969743e-05, "loss": 1.768818974494934, "num_input_tokens_seen": 35776750, "step": 548, "train_runtime": 11985.0994, "train_tokens_per_second": 2985.102 }, { "epoch": 0.3486267661533577, "grad_norm": 1.2128607034683228, "learning_rate": 1.934979942081451e-05, "loss": 1.7672767639160156, "num_input_tokens_seen": 35842213, "step": 549, "train_runtime": 12007.4467, "train_tokens_per_second": 2984.999 }, { "epoch": 0.349261787585331, "grad_norm": 1.2793915271759033, "learning_rate": 1.934743749409163e-05, "loss": 1.7676626443862915, "num_input_tokens_seen": 35907722, "step": 550, "train_runtime": 12028.5831, "train_tokens_per_second": 2985.2 }, { "epoch": 0.34989680901730436, "grad_norm": 1.325325608253479, "learning_rate": 1.9345071429846584e-05, "loss": 1.9678508043289185, "num_input_tokens_seen": 35973248, "step": 551, "train_runtime": 12050.9199, "train_tokens_per_second": 2985.104 }, { "epoch": 0.35053183044927766, "grad_norm": 1.2709769010543823, "learning_rate": 1.9342701229126678e-05, "loss": 1.5969877243041992, "num_input_tokens_seen": 36038693, "step": 552, "train_runtime": 12072.3331, "train_tokens_per_second": 2985.23 }, { "epoch": 0.351166851881251, "grad_norm": 1.1842825412750244, "learning_rate": 1.9340326892981052e-05, "loss": 1.5947227478027344, "num_input_tokens_seen": 36104199, "step": 553, "train_runtime": 12092.9537, "train_tokens_per_second": 2985.557 }, { "epoch": 0.3518018733132243, "grad_norm": 1.4047240018844604, "learning_rate": 1.9337948422460672e-05, "loss": 1.774885654449463, "num_input_tokens_seen": 36169688, "step": 554, "train_runtime": 12114.5199, "train_tokens_per_second": 2985.648 }, { "epoch": 0.3524368947451976, "grad_norm": 1.243829369544983, "learning_rate": 1.9335565818618342e-05, "loss": 1.6388245820999146, "num_input_tokens_seen": 36235029, "step": 555, "train_runtime": 12135.2099, "train_tokens_per_second": 2985.942 }, { "epoch": 0.353071916177171, "grad_norm": 1.1611407995224, "learning_rate": 1.9333179082508686e-05, "loss": 1.659615159034729, "num_input_tokens_seen": 36300440, "step": 556, "train_runtime": 12156.8328, "train_tokens_per_second": 2986.011 }, { "epoch": 0.3537069376091443, "grad_norm": 1.111165165901184, "learning_rate": 1.933078821518816e-05, "loss": 1.5117460489273071, "num_input_tokens_seen": 36365891, "step": 557, "train_runtime": 12178.6728, "train_tokens_per_second": 2986.031 }, { "epoch": 0.35434195904111765, "grad_norm": 1.2306760549545288, "learning_rate": 1.932839321771506e-05, "loss": 1.8715015649795532, "num_input_tokens_seen": 36431384, "step": 558, "train_runtime": 12200.5714, "train_tokens_per_second": 2986.039 }, { "epoch": 0.35497698047309095, "grad_norm": 1.26893949508667, "learning_rate": 1.9325994091149488e-05, "loss": 1.662410020828247, "num_input_tokens_seen": 36496713, "step": 559, "train_runtime": 12222.0502, "train_tokens_per_second": 2986.137 }, { "epoch": 0.3556120019050643, "grad_norm": 1.1608327627182007, "learning_rate": 1.93235908365534e-05, "loss": 1.7179193496704102, "num_input_tokens_seen": 36562040, "step": 560, "train_runtime": 12243.7066, "train_tokens_per_second": 2986.19 }, { "epoch": 0.3562470233370376, "grad_norm": 1.3496384620666504, "learning_rate": 1.9321183454990555e-05, "loss": 1.82929265499115, "num_input_tokens_seen": 36627535, "step": 561, "train_runtime": 12266.1053, "train_tokens_per_second": 2986.077 }, { "epoch": 0.356882044769011, "grad_norm": 1.502788782119751, "learning_rate": 1.9318771947526555e-05, "loss": 1.997536540031433, "num_input_tokens_seen": 36685616, "step": 562, "train_runtime": 12285.0217, "train_tokens_per_second": 2986.207 }, { "epoch": 0.3575170662009843, "grad_norm": 1.176728367805481, "learning_rate": 1.9316356315228817e-05, "loss": 1.547539234161377, "num_input_tokens_seen": 36751068, "step": 563, "train_runtime": 12306.2028, "train_tokens_per_second": 2986.386 }, { "epoch": 0.35815208763295764, "grad_norm": 1.253553032875061, "learning_rate": 1.9313936559166594e-05, "loss": 1.7746299505233765, "num_input_tokens_seen": 36816563, "step": 564, "train_runtime": 12328.0094, "train_tokens_per_second": 2986.416 }, { "epoch": 0.35878710906493094, "grad_norm": 1.214650273323059, "learning_rate": 1.931151268041096e-05, "loss": 1.5608528852462769, "num_input_tokens_seen": 36882060, "step": 565, "train_runtime": 12349.673, "train_tokens_per_second": 2986.481 }, { "epoch": 0.35942213049690425, "grad_norm": 1.4522053003311157, "learning_rate": 1.9309084680034812e-05, "loss": 2.0686373710632324, "num_input_tokens_seen": 36947557, "step": 566, "train_runtime": 12372.0002, "train_tokens_per_second": 2986.385 }, { "epoch": 0.3600571519288776, "grad_norm": 1.3277045488357544, "learning_rate": 1.930665255911287e-05, "loss": 1.8729265928268433, "num_input_tokens_seen": 37013076, "step": 567, "train_runtime": 12393.5582, "train_tokens_per_second": 2986.477 }, { "epoch": 0.3606921733608509, "grad_norm": 1.2331606149673462, "learning_rate": 1.9304216318721687e-05, "loss": 1.8049876689910889, "num_input_tokens_seen": 37078550, "step": 568, "train_runtime": 12415.1287, "train_tokens_per_second": 2986.562 }, { "epoch": 0.36132719479282427, "grad_norm": 1.2401715517044067, "learning_rate": 1.9301775959939627e-05, "loss": 1.7102479934692383, "num_input_tokens_seen": 37144019, "step": 569, "train_runtime": 12436.4668, "train_tokens_per_second": 2986.702 }, { "epoch": 0.3619622162247976, "grad_norm": 1.2024686336517334, "learning_rate": 1.9299331483846888e-05, "loss": 1.6246196031570435, "num_input_tokens_seen": 37209462, "step": 570, "train_runtime": 12457.2187, "train_tokens_per_second": 2986.98 }, { "epoch": 0.36259723765677093, "grad_norm": 1.3173614740371704, "learning_rate": 1.9296882891525483e-05, "loss": 1.6184743642807007, "num_input_tokens_seen": 37274921, "step": 571, "train_runtime": 12478.7784, "train_tokens_per_second": 2987.065 }, { "epoch": 0.36323225908874424, "grad_norm": 1.2194699048995972, "learning_rate": 1.9294430184059255e-05, "loss": 1.7177648544311523, "num_input_tokens_seen": 37340415, "step": 572, "train_runtime": 12500.6095, "train_tokens_per_second": 2987.088 }, { "epoch": 0.3638672805207176, "grad_norm": 1.1578280925750732, "learning_rate": 1.9291973362533853e-05, "loss": 1.772441029548645, "num_input_tokens_seen": 37405850, "step": 573, "train_runtime": 12522.0648, "train_tokens_per_second": 2987.195 }, { "epoch": 0.3645023019526909, "grad_norm": 1.1718555688858032, "learning_rate": 1.9289512428036765e-05, "loss": 1.5626075267791748, "num_input_tokens_seen": 37471348, "step": 574, "train_runtime": 12544.0612, "train_tokens_per_second": 2987.178 }, { "epoch": 0.36513732338466426, "grad_norm": 1.3974878787994385, "learning_rate": 1.928704738165729e-05, "loss": 1.810651183128357, "num_input_tokens_seen": 37536856, "step": 575, "train_runtime": 12566.5787, "train_tokens_per_second": 2987.039 }, { "epoch": 0.36577234481663756, "grad_norm": 1.3256324529647827, "learning_rate": 1.9284578224486548e-05, "loss": 1.6370811462402344, "num_input_tokens_seen": 37602260, "step": 576, "train_runtime": 12588.9358, "train_tokens_per_second": 2986.929 }, { "epoch": 0.36640736624861087, "grad_norm": 1.1405338048934937, "learning_rate": 1.9282104957617483e-05, "loss": 1.5094712972640991, "num_input_tokens_seen": 37667717, "step": 577, "train_runtime": 12609.9611, "train_tokens_per_second": 2987.14 }, { "epoch": 0.3670423876805842, "grad_norm": 1.189265489578247, "learning_rate": 1.9279627582144848e-05, "loss": 1.5577036142349243, "num_input_tokens_seen": 37733121, "step": 578, "train_runtime": 12631.3945, "train_tokens_per_second": 2987.249 }, { "epoch": 0.36767740911255753, "grad_norm": 1.1775341033935547, "learning_rate": 1.9277146099165228e-05, "loss": 1.625200629234314, "num_input_tokens_seen": 37798638, "step": 579, "train_runtime": 12652.4847, "train_tokens_per_second": 2987.448 }, { "epoch": 0.3683124305445309, "grad_norm": 1.1849297285079956, "learning_rate": 1.9274660509777012e-05, "loss": 1.6777620315551758, "num_input_tokens_seen": 37864147, "step": 580, "train_runtime": 12674.4642, "train_tokens_per_second": 2987.436 }, { "epoch": 0.3689474519765042, "grad_norm": 1.2345455884933472, "learning_rate": 1.927217081508042e-05, "loss": 1.7723565101623535, "num_input_tokens_seen": 37929608, "step": 581, "train_runtime": 12695.5535, "train_tokens_per_second": 2987.629 }, { "epoch": 0.36958247340847755, "grad_norm": 1.2125530242919922, "learning_rate": 1.9269677016177482e-05, "loss": 1.6151249408721924, "num_input_tokens_seen": 37995017, "step": 582, "train_runtime": 12717.4433, "train_tokens_per_second": 2987.63 }, { "epoch": 0.37021749484045086, "grad_norm": 1.2417640686035156, "learning_rate": 1.9267179114172045e-05, "loss": 1.6802257299423218, "num_input_tokens_seen": 38060513, "step": 583, "train_runtime": 12738.5658, "train_tokens_per_second": 2987.818 }, { "epoch": 0.3708525162724242, "grad_norm": 1.2617429494857788, "learning_rate": 1.9264677110169773e-05, "loss": 1.70926833152771, "num_input_tokens_seen": 38126028, "step": 584, "train_runtime": 12759.916, "train_tokens_per_second": 2987.953 }, { "epoch": 0.3714875377043975, "grad_norm": 1.2282451391220093, "learning_rate": 1.9262171005278144e-05, "loss": 1.6554392576217651, "num_input_tokens_seen": 38191524, "step": 585, "train_runtime": 12780.7547, "train_tokens_per_second": 2988.206 }, { "epoch": 0.3721225591363709, "grad_norm": 1.154738426208496, "learning_rate": 1.9259660800606457e-05, "loss": 1.6113886833190918, "num_input_tokens_seen": 38256936, "step": 586, "train_runtime": 12801.7939, "train_tokens_per_second": 2988.404 }, { "epoch": 0.3727575805683442, "grad_norm": 1.3415131568908691, "learning_rate": 1.9257146497265818e-05, "loss": 1.7256954908370972, "num_input_tokens_seen": 38322429, "step": 587, "train_runtime": 12824.083, "train_tokens_per_second": 2988.317 }, { "epoch": 0.3733926020003175, "grad_norm": 1.168307900428772, "learning_rate": 1.925462809636915e-05, "loss": 1.601723074913025, "num_input_tokens_seen": 38387940, "step": 588, "train_runtime": 12844.9646, "train_tokens_per_second": 2988.559 }, { "epoch": 0.37402762343229085, "grad_norm": 1.1340566873550415, "learning_rate": 1.9252105599031196e-05, "loss": 1.6380664110183716, "num_input_tokens_seen": 38453406, "step": 589, "train_runtime": 12865.8173, "train_tokens_per_second": 2988.804 }, { "epoch": 0.37466264486426415, "grad_norm": 1.3548359870910645, "learning_rate": 1.92495790063685e-05, "loss": 1.8079583644866943, "num_input_tokens_seen": 38518828, "step": 590, "train_runtime": 12887.3551, "train_tokens_per_second": 2988.885 }, { "epoch": 0.3752976662962375, "grad_norm": 1.1937540769577026, "learning_rate": 1.9247048319499434e-05, "loss": 1.7259982824325562, "num_input_tokens_seen": 38584330, "step": 591, "train_runtime": 12907.9989, "train_tokens_per_second": 2989.18 }, { "epoch": 0.3759326877282108, "grad_norm": 1.190756916999817, "learning_rate": 1.9244513539544166e-05, "loss": 1.5670702457427979, "num_input_tokens_seen": 38649860, "step": 592, "train_runtime": 12929.4734, "train_tokens_per_second": 2989.283 }, { "epoch": 0.37656770916018417, "grad_norm": 1.4960296154022217, "learning_rate": 1.9241974667624683e-05, "loss": 1.7481495141983032, "num_input_tokens_seen": 38715352, "step": 593, "train_runtime": 12951.2968, "train_tokens_per_second": 2989.303 }, { "epoch": 0.3772027305921575, "grad_norm": 1.2619426250457764, "learning_rate": 1.9239431704864788e-05, "loss": 1.6049119234085083, "num_input_tokens_seen": 38780873, "step": 594, "train_runtime": 12972.4998, "train_tokens_per_second": 2989.468 }, { "epoch": 0.37783775202413084, "grad_norm": 1.462855339050293, "learning_rate": 1.923688465239009e-05, "loss": 1.8467280864715576, "num_input_tokens_seen": 38846384, "step": 595, "train_runtime": 12994.1997, "train_tokens_per_second": 2989.517 }, { "epoch": 0.37847277345610414, "grad_norm": 1.2062766551971436, "learning_rate": 1.923433351132801e-05, "loss": 1.5466686487197876, "num_input_tokens_seen": 38911915, "step": 596, "train_runtime": 13015.9737, "train_tokens_per_second": 2989.551 }, { "epoch": 0.3791077948880775, "grad_norm": 1.1098756790161133, "learning_rate": 1.9231778282807775e-05, "loss": 1.5084699392318726, "num_input_tokens_seen": 38977417, "step": 597, "train_runtime": 13036.5124, "train_tokens_per_second": 2989.865 }, { "epoch": 0.3797428163200508, "grad_norm": 1.2782198190689087, "learning_rate": 1.9229218967960427e-05, "loss": 1.9394482374191284, "num_input_tokens_seen": 39042931, "step": 598, "train_runtime": 13058.5833, "train_tokens_per_second": 2989.829 }, { "epoch": 0.3803778377520241, "grad_norm": 1.3706765174865723, "learning_rate": 1.9226655567918807e-05, "loss": 1.8281477689743042, "num_input_tokens_seen": 39108426, "step": 599, "train_runtime": 13080.1274, "train_tokens_per_second": 2989.912 }, { "epoch": 0.38101285918399747, "grad_norm": 1.4147894382476807, "learning_rate": 1.9224088083817574e-05, "loss": 1.8181240558624268, "num_input_tokens_seen": 39173939, "step": 600, "train_runtime": 13102.6368, "train_tokens_per_second": 2989.775 }, { "epoch": 0.38101285918399747, "eval_loss": 1.6023149490356445, "eval_runtime": 12.8836, "eval_samples_per_second": 1.785, "eval_steps_per_second": 0.931, "num_input_tokens_seen": 39173939, "step": 600 }, { "epoch": 0.38164788061597077, "grad_norm": 1.1239864826202393, "learning_rate": 1.9221516516793198e-05, "loss": 1.4740206003189087, "num_input_tokens_seen": 39239457, "step": 601, "train_runtime": 13174.1569, "train_tokens_per_second": 2978.518 }, { "epoch": 0.38228290204794413, "grad_norm": 1.1363744735717773, "learning_rate": 1.921894086798394e-05, "loss": 1.654416799545288, "num_input_tokens_seen": 39304984, "step": 602, "train_runtime": 13195.1169, "train_tokens_per_second": 2978.752 }, { "epoch": 0.38291792347991743, "grad_norm": 1.2426832914352417, "learning_rate": 1.9216361138529885e-05, "loss": 1.6788179874420166, "num_input_tokens_seen": 39370241, "step": 603, "train_runtime": 13216.5117, "train_tokens_per_second": 2978.868 }, { "epoch": 0.3835529449118908, "grad_norm": 1.2609078884124756, "learning_rate": 1.9213777329572913e-05, "loss": 1.565816879272461, "num_input_tokens_seen": 39435589, "step": 604, "train_runtime": 13237.2747, "train_tokens_per_second": 2979.132 }, { "epoch": 0.3841879663438641, "grad_norm": 1.2511119842529297, "learning_rate": 1.921118944225671e-05, "loss": 1.6819827556610107, "num_input_tokens_seen": 39501092, "step": 605, "train_runtime": 13258.8331, "train_tokens_per_second": 2979.228 }, { "epoch": 0.38482298777583746, "grad_norm": 1.1400920152664185, "learning_rate": 1.920859747772678e-05, "loss": 1.5578478574752808, "num_input_tokens_seen": 39566610, "step": 606, "train_runtime": 13280.0445, "train_tokens_per_second": 2979.403 }, { "epoch": 0.38545800920781076, "grad_norm": 1.159310221672058, "learning_rate": 1.920600143713042e-05, "loss": 1.4654760360717773, "num_input_tokens_seen": 39632085, "step": 607, "train_runtime": 13301.4675, "train_tokens_per_second": 2979.527 }, { "epoch": 0.3860930306397841, "grad_norm": 1.270594835281372, "learning_rate": 1.920340132161673e-05, "loss": 1.8113888502120972, "num_input_tokens_seen": 39697563, "step": 608, "train_runtime": 13323.9876, "train_tokens_per_second": 2979.406 }, { "epoch": 0.3867280520717574, "grad_norm": 1.1603991985321045, "learning_rate": 1.9200797132336615e-05, "loss": 1.5610867738723755, "num_input_tokens_seen": 39763023, "step": 609, "train_runtime": 13345.5135, "train_tokens_per_second": 2979.505 }, { "epoch": 0.3873630735037307, "grad_norm": 1.1418390274047852, "learning_rate": 1.9198188870442792e-05, "loss": 1.6018608808517456, "num_input_tokens_seen": 39828524, "step": 610, "train_runtime": 13366.5215, "train_tokens_per_second": 2979.722 }, { "epoch": 0.3879980949357041, "grad_norm": 1.2298171520233154, "learning_rate": 1.919557653708977e-05, "loss": 1.8371180295944214, "num_input_tokens_seen": 39894053, "step": 611, "train_runtime": 13388.6004, "train_tokens_per_second": 2979.703 }, { "epoch": 0.3886331163676774, "grad_norm": 1.1404539346694946, "learning_rate": 1.919296013343387e-05, "loss": 1.5830326080322266, "num_input_tokens_seen": 39959553, "step": 612, "train_runtime": 13410.3214, "train_tokens_per_second": 2979.761 }, { "epoch": 0.38926813779965075, "grad_norm": 1.1720597743988037, "learning_rate": 1.9190339660633205e-05, "loss": 1.5383344888687134, "num_input_tokens_seen": 40024977, "step": 613, "train_runtime": 13430.8288, "train_tokens_per_second": 2980.082 }, { "epoch": 0.38990315923162405, "grad_norm": 1.2263305187225342, "learning_rate": 1.9187715119847695e-05, "loss": 1.706587791442871, "num_input_tokens_seen": 40090497, "step": 614, "train_runtime": 13452.0779, "train_tokens_per_second": 2980.246 }, { "epoch": 0.3905381806635974, "grad_norm": 1.3137065172195435, "learning_rate": 1.9185086512239054e-05, "loss": 1.7565215826034546, "num_input_tokens_seen": 40156016, "step": 615, "train_runtime": 13473.3049, "train_tokens_per_second": 2980.413 }, { "epoch": 0.3911732020955707, "grad_norm": 1.3017038106918335, "learning_rate": 1.918245383897081e-05, "loss": 1.7123578786849976, "num_input_tokens_seen": 40221498, "step": 616, "train_runtime": 13494.554, "train_tokens_per_second": 2980.573 }, { "epoch": 0.3918082235275441, "grad_norm": 1.198866367340088, "learning_rate": 1.9179817101208273e-05, "loss": 1.7331444025039673, "num_input_tokens_seen": 40286931, "step": 617, "train_runtime": 13515.5713, "train_tokens_per_second": 2980.779 }, { "epoch": 0.3924432449595174, "grad_norm": 1.2118556499481201, "learning_rate": 1.9177176300118567e-05, "loss": 1.628690242767334, "num_input_tokens_seen": 40350260, "step": 618, "train_runtime": 13536.5677, "train_tokens_per_second": 2980.834 }, { "epoch": 0.39307826639149074, "grad_norm": 1.1888890266418457, "learning_rate": 1.9174531436870608e-05, "loss": 1.6577727794647217, "num_input_tokens_seen": 40415667, "step": 619, "train_runtime": 13557.8315, "train_tokens_per_second": 2980.983 }, { "epoch": 0.39371328782346404, "grad_norm": 1.1074224710464478, "learning_rate": 1.9171882512635106e-05, "loss": 1.664634108543396, "num_input_tokens_seen": 40481174, "step": 620, "train_runtime": 13578.8635, "train_tokens_per_second": 2981.19 }, { "epoch": 0.39434830925543735, "grad_norm": 1.1584527492523193, "learning_rate": 1.9169229528584577e-05, "loss": 1.5138542652130127, "num_input_tokens_seen": 40546615, "step": 621, "train_runtime": 13599.4254, "train_tokens_per_second": 2981.495 }, { "epoch": 0.3949833306874107, "grad_norm": 1.3095943927764893, "learning_rate": 1.9166572485893325e-05, "loss": 1.881629467010498, "num_input_tokens_seen": 40608198, "step": 622, "train_runtime": 13619.6154, "train_tokens_per_second": 2981.597 }, { "epoch": 0.395618352119384, "grad_norm": 1.2584640979766846, "learning_rate": 1.9163911385737464e-05, "loss": 1.6625614166259766, "num_input_tokens_seen": 40673594, "step": 623, "train_runtime": 13640.831, "train_tokens_per_second": 2981.753 }, { "epoch": 0.39625337355135737, "grad_norm": 1.1438337564468384, "learning_rate": 1.916124622929489e-05, "loss": 1.677807331085205, "num_input_tokens_seen": 40738970, "step": 624, "train_runtime": 13661.6882, "train_tokens_per_second": 2981.987 }, { "epoch": 0.3968883949833307, "grad_norm": 1.3844584226608276, "learning_rate": 1.91585770177453e-05, "loss": 1.7913739681243896, "num_input_tokens_seen": 40804430, "step": 625, "train_runtime": 13683.2253, "train_tokens_per_second": 2982.077 }, { "epoch": 0.39752341641530403, "grad_norm": 1.1911158561706543, "learning_rate": 1.9155903752270183e-05, "loss": 1.7272874116897583, "num_input_tokens_seen": 40869871, "step": 626, "train_runtime": 13704.8452, "train_tokens_per_second": 2982.148 }, { "epoch": 0.39815843784727734, "grad_norm": 1.191954255104065, "learning_rate": 1.9153226434052838e-05, "loss": 1.5437203645706177, "num_input_tokens_seen": 40935343, "step": 627, "train_runtime": 13726.0521, "train_tokens_per_second": 2982.31 }, { "epoch": 0.3987934592792507, "grad_norm": 1.2314692735671997, "learning_rate": 1.9150545064278327e-05, "loss": 1.6189815998077393, "num_input_tokens_seen": 41000796, "step": 628, "train_runtime": 13747.188, "train_tokens_per_second": 2982.486 }, { "epoch": 0.399428480711224, "grad_norm": 1.1050629615783691, "learning_rate": 1.9147859644133538e-05, "loss": 1.5043137073516846, "num_input_tokens_seen": 41066255, "step": 629, "train_runtime": 13768.6083, "train_tokens_per_second": 2982.6 }, { "epoch": 0.40006350214319736, "grad_norm": 1.2343106269836426, "learning_rate": 1.914517017480713e-05, "loss": 1.8319555521011353, "num_input_tokens_seen": 41131754, "step": 630, "train_runtime": 13789.7833, "train_tokens_per_second": 2982.77 }, { "epoch": 0.40069852357517066, "grad_norm": 1.3467568159103394, "learning_rate": 1.9142476657489565e-05, "loss": 1.719996690750122, "num_input_tokens_seen": 41197217, "step": 631, "train_runtime": 13811.009, "train_tokens_per_second": 2982.926 }, { "epoch": 0.40133354500714397, "grad_norm": 1.2995868921279907, "learning_rate": 1.9139779093373096e-05, "loss": 1.7560290098190308, "num_input_tokens_seen": 41262539, "step": 632, "train_runtime": 13832.2171, "train_tokens_per_second": 2983.075 }, { "epoch": 0.4019685664391173, "grad_norm": 1.2793837785720825, "learning_rate": 1.9137077483651758e-05, "loss": 1.6472989320755005, "num_input_tokens_seen": 41327945, "step": 633, "train_runtime": 13853.3741, "train_tokens_per_second": 2983.24 }, { "epoch": 0.40260358787109063, "grad_norm": 1.2805460691452026, "learning_rate": 1.9134371829521386e-05, "loss": 1.546359658241272, "num_input_tokens_seen": 41393335, "step": 634, "train_runtime": 13874.1667, "train_tokens_per_second": 2983.483 }, { "epoch": 0.403238609303064, "grad_norm": 1.2807248830795288, "learning_rate": 1.9131662132179608e-05, "loss": 1.8756781816482544, "num_input_tokens_seen": 41458748, "step": 635, "train_runtime": 13895.3224, "train_tokens_per_second": 2983.648 }, { "epoch": 0.4038736307350373, "grad_norm": 1.2387492656707764, "learning_rate": 1.9128948392825828e-05, "loss": 1.8306283950805664, "num_input_tokens_seen": 41524238, "step": 636, "train_runtime": 13916.4699, "train_tokens_per_second": 2983.82 }, { "epoch": 0.40450865216701065, "grad_norm": 1.30656898021698, "learning_rate": 1.912623061266125e-05, "loss": 1.718113899230957, "num_input_tokens_seen": 41589764, "step": 637, "train_runtime": 13938.0347, "train_tokens_per_second": 2983.904 }, { "epoch": 0.40514367359898396, "grad_norm": 1.2116206884384155, "learning_rate": 1.9123508792888873e-05, "loss": 1.598541498184204, "num_input_tokens_seen": 41655111, "step": 638, "train_runtime": 13959.6691, "train_tokens_per_second": 2983.961 }, { "epoch": 0.4057786950309573, "grad_norm": 1.2342582941055298, "learning_rate": 1.9120782934713464e-05, "loss": 1.7163654565811157, "num_input_tokens_seen": 41720544, "step": 639, "train_runtime": 13980.6867, "train_tokens_per_second": 2984.156 }, { "epoch": 0.4064137164629306, "grad_norm": 1.1822842359542847, "learning_rate": 1.9118053039341594e-05, "loss": 1.6012420654296875, "num_input_tokens_seen": 41785890, "step": 640, "train_runtime": 14001.8348, "train_tokens_per_second": 2984.315 }, { "epoch": 0.407048737894904, "grad_norm": 1.1144788265228271, "learning_rate": 1.9115319107981615e-05, "loss": 1.4860775470733643, "num_input_tokens_seen": 41851373, "step": 641, "train_runtime": 14022.6273, "train_tokens_per_second": 2984.56 }, { "epoch": 0.4076837593268773, "grad_norm": 1.2760595083236694, "learning_rate": 1.911258114184367e-05, "loss": 1.6873953342437744, "num_input_tokens_seen": 41916783, "step": 642, "train_runtime": 14043.407, "train_tokens_per_second": 2984.802 }, { "epoch": 0.4083187807588506, "grad_norm": 1.2595187425613403, "learning_rate": 1.9109839142139672e-05, "loss": 1.6178433895111084, "num_input_tokens_seen": 41982145, "step": 643, "train_runtime": 14064.4331, "train_tokens_per_second": 2984.987 }, { "epoch": 0.40895380219082395, "grad_norm": 1.1418347358703613, "learning_rate": 1.9107093110083346e-05, "loss": 1.675748348236084, "num_input_tokens_seen": 42047631, "step": 644, "train_runtime": 14085.3252, "train_tokens_per_second": 2985.208 }, { "epoch": 0.40958882362279725, "grad_norm": 1.2502679824829102, "learning_rate": 1.9104343046890182e-05, "loss": 1.7241774797439575, "num_input_tokens_seen": 42113150, "step": 645, "train_runtime": 14106.5517, "train_tokens_per_second": 2985.361 }, { "epoch": 0.4102238450547706, "grad_norm": 1.1480166912078857, "learning_rate": 1.910158895377746e-05, "loss": 1.6948928833007812, "num_input_tokens_seen": 42178563, "step": 646, "train_runtime": 14127.5698, "train_tokens_per_second": 2985.55 }, { "epoch": 0.4108588664867439, "grad_norm": 1.2395899295806885, "learning_rate": 1.9098830831964237e-05, "loss": 1.8249480724334717, "num_input_tokens_seen": 42244004, "step": 647, "train_runtime": 14150.1746, "train_tokens_per_second": 2985.405 }, { "epoch": 0.41149388791871727, "grad_norm": 1.2350069284439087, "learning_rate": 1.9096068682671375e-05, "loss": 1.785935401916504, "num_input_tokens_seen": 42309509, "step": 648, "train_runtime": 14172.0775, "train_tokens_per_second": 2985.413 }, { "epoch": 0.4121289093506906, "grad_norm": 1.167199730873108, "learning_rate": 1.9093302507121493e-05, "loss": 1.5620925426483154, "num_input_tokens_seen": 42375033, "step": 649, "train_runtime": 14193.6256, "train_tokens_per_second": 2985.497 }, { "epoch": 0.41276393078266393, "grad_norm": 1.2266348600387573, "learning_rate": 1.9090532306538998e-05, "loss": 1.6124365329742432, "num_input_tokens_seen": 42440422, "step": 650, "train_runtime": 14214.758, "train_tokens_per_second": 2985.659 }, { "epoch": 0.41339895221463724, "grad_norm": 1.2210419178009033, "learning_rate": 1.9087758082150096e-05, "loss": 1.6581487655639648, "num_input_tokens_seen": 42505762, "step": 651, "train_runtime": 14236.363, "train_tokens_per_second": 2985.718 }, { "epoch": 0.4140339736466106, "grad_norm": 1.2767325639724731, "learning_rate": 1.9084979835182757e-05, "loss": 1.624700665473938, "num_input_tokens_seen": 42571169, "step": 652, "train_runtime": 14258.2387, "train_tokens_per_second": 2985.724 }, { "epoch": 0.4146689950785839, "grad_norm": 1.3285354375839233, "learning_rate": 1.908219756686673e-05, "loss": 1.84718656539917, "num_input_tokens_seen": 42636622, "step": 653, "train_runtime": 14279.6457, "train_tokens_per_second": 2985.832 }, { "epoch": 0.4153040165105572, "grad_norm": 1.1496446132659912, "learning_rate": 1.9079411278433556e-05, "loss": 1.6923606395721436, "num_input_tokens_seen": 42702121, "step": 654, "train_runtime": 14301.1159, "train_tokens_per_second": 2985.929 }, { "epoch": 0.41593903794253057, "grad_norm": 1.264366865158081, "learning_rate": 1.9076620971116546e-05, "loss": 1.7761634588241577, "num_input_tokens_seen": 42767626, "step": 655, "train_runtime": 14323.1888, "train_tokens_per_second": 2985.901 }, { "epoch": 0.41657405937450387, "grad_norm": 1.1018227338790894, "learning_rate": 1.9073826646150798e-05, "loss": 1.4974086284637451, "num_input_tokens_seen": 42833030, "step": 656, "train_runtime": 14343.6948, "train_tokens_per_second": 2986.192 }, { "epoch": 0.41720908080647723, "grad_norm": 1.1824525594711304, "learning_rate": 1.9071028304773182e-05, "loss": 1.6540337800979614, "num_input_tokens_seen": 42898501, "step": 657, "train_runtime": 14364.6171, "train_tokens_per_second": 2986.401 }, { "epoch": 0.41784410223845053, "grad_norm": 1.3015248775482178, "learning_rate": 1.9068225948222346e-05, "loss": 1.9127954244613647, "num_input_tokens_seen": 42963937, "step": 658, "train_runtime": 14385.4857, "train_tokens_per_second": 2986.617 }, { "epoch": 0.4184791236704239, "grad_norm": 1.1328892707824707, "learning_rate": 1.9065419577738718e-05, "loss": 1.7743442058563232, "num_input_tokens_seen": 43029438, "step": 659, "train_runtime": 14406.5374, "train_tokens_per_second": 2986.799 }, { "epoch": 0.4191141451023972, "grad_norm": 1.349426507949829, "learning_rate": 1.90626091945645e-05, "loss": 1.8938300609588623, "num_input_tokens_seen": 43094941, "step": 660, "train_runtime": 14428.2373, "train_tokens_per_second": 2986.847 }, { "epoch": 0.41974916653437055, "grad_norm": 1.1652508974075317, "learning_rate": 1.9059794799943676e-05, "loss": 1.5743685960769653, "num_input_tokens_seen": 43160431, "step": 661, "train_runtime": 14449.3527, "train_tokens_per_second": 2987.015 }, { "epoch": 0.42038418796634386, "grad_norm": 1.182570219039917, "learning_rate": 1.9056976395121993e-05, "loss": 1.6776577234268188, "num_input_tokens_seen": 43225821, "step": 662, "train_runtime": 14470.3467, "train_tokens_per_second": 2987.2 }, { "epoch": 0.4210192093983172, "grad_norm": 1.2168834209442139, "learning_rate": 1.905415398134699e-05, "loss": 1.6557209491729736, "num_input_tokens_seen": 43291297, "step": 663, "train_runtime": 14491.6803, "train_tokens_per_second": 2987.321 }, { "epoch": 0.4216542308302905, "grad_norm": 1.215775966644287, "learning_rate": 1.905132755986797e-05, "loss": 1.6890403032302856, "num_input_tokens_seen": 43356756, "step": 664, "train_runtime": 14514.2176, "train_tokens_per_second": 2987.192 }, { "epoch": 0.4222892522622638, "grad_norm": 1.1313507556915283, "learning_rate": 1.9048497131936008e-05, "loss": 1.5979100465774536, "num_input_tokens_seen": 43422151, "step": 665, "train_runtime": 14535.3599, "train_tokens_per_second": 2987.346 }, { "epoch": 0.4229242736942372, "grad_norm": 1.2499538660049438, "learning_rate": 1.904566269880396e-05, "loss": 1.651166558265686, "num_input_tokens_seen": 43487586, "step": 666, "train_runtime": 14556.5979, "train_tokens_per_second": 2987.483 }, { "epoch": 0.4235592951262105, "grad_norm": 1.1996853351593018, "learning_rate": 1.9042824261726447e-05, "loss": 1.5883830785751343, "num_input_tokens_seen": 43553079, "step": 667, "train_runtime": 14577.2151, "train_tokens_per_second": 2987.75 }, { "epoch": 0.42419431655818385, "grad_norm": 1.229203701019287, "learning_rate": 1.9039981821959873e-05, "loss": 1.782675862312317, "num_input_tokens_seen": 43618598, "step": 668, "train_runtime": 14599.2209, "train_tokens_per_second": 2987.735 }, { "epoch": 0.42482933799015715, "grad_norm": 1.2625747919082642, "learning_rate": 1.90371353807624e-05, "loss": 1.7550315856933594, "num_input_tokens_seen": 43684072, "step": 669, "train_runtime": 14621.1106, "train_tokens_per_second": 2987.74 }, { "epoch": 0.4254643594221305, "grad_norm": 1.1154868602752686, "learning_rate": 1.9034284939393977e-05, "loss": 1.6329772472381592, "num_input_tokens_seen": 43749538, "step": 670, "train_runtime": 14642.037, "train_tokens_per_second": 2987.941 }, { "epoch": 0.4260993808541038, "grad_norm": 1.224426507949829, "learning_rate": 1.9031430499116306e-05, "loss": 1.4513230323791504, "num_input_tokens_seen": 43809822, "step": 671, "train_runtime": 14660.7961, "train_tokens_per_second": 2988.229 }, { "epoch": 0.4267344022860772, "grad_norm": 1.2838040590286255, "learning_rate": 1.902857206119287e-05, "loss": 1.6864594221115112, "num_input_tokens_seen": 43875227, "step": 672, "train_runtime": 14682.2439, "train_tokens_per_second": 2988.319 }, { "epoch": 0.4273694237180505, "grad_norm": 1.3646972179412842, "learning_rate": 1.9025709626888926e-05, "loss": 1.6727664470672607, "num_input_tokens_seen": 43940677, "step": 673, "train_runtime": 14703.4179, "train_tokens_per_second": 2988.467 }, { "epoch": 0.42800444515002384, "grad_norm": 1.218150019645691, "learning_rate": 1.902284319747149e-05, "loss": 1.6565227508544922, "num_input_tokens_seen": 44006133, "step": 674, "train_runtime": 14724.7948, "train_tokens_per_second": 2988.574 }, { "epoch": 0.42863946658199714, "grad_norm": 1.2113889455795288, "learning_rate": 1.901997277420934e-05, "loss": 1.7047114372253418, "num_input_tokens_seen": 44071609, "step": 675, "train_runtime": 14746.247, "train_tokens_per_second": 2988.666 }, { "epoch": 0.42927448801397045, "grad_norm": 1.198797345161438, "learning_rate": 1.9017098358373046e-05, "loss": 1.7005865573883057, "num_input_tokens_seen": 44136995, "step": 676, "train_runtime": 14767.456, "train_tokens_per_second": 2988.802 }, { "epoch": 0.4299095094459438, "grad_norm": 1.0998094081878662, "learning_rate": 1.9014219951234927e-05, "loss": 1.5559282302856445, "num_input_tokens_seen": 44202429, "step": 677, "train_runtime": 14787.8492, "train_tokens_per_second": 2989.105 }, { "epoch": 0.4305445308779171, "grad_norm": 1.3126556873321533, "learning_rate": 1.9011337554069065e-05, "loss": 1.6878514289855957, "num_input_tokens_seen": 44267703, "step": 678, "train_runtime": 14809.0719, "train_tokens_per_second": 2989.229 }, { "epoch": 0.43117955230989047, "grad_norm": 1.109951138496399, "learning_rate": 1.9008451168151326e-05, "loss": 1.4558287858963013, "num_input_tokens_seen": 44333234, "step": 679, "train_runtime": 14830.6046, "train_tokens_per_second": 2989.307 }, { "epoch": 0.43181457374186377, "grad_norm": 1.1262229681015015, "learning_rate": 1.900556079475933e-05, "loss": 1.5890915393829346, "num_input_tokens_seen": 44398696, "step": 680, "train_runtime": 14851.5279, "train_tokens_per_second": 2989.504 }, { "epoch": 0.43244959517383713, "grad_norm": 1.3020323514938354, "learning_rate": 1.9002666435172454e-05, "loss": 1.6505653858184814, "num_input_tokens_seen": 44464152, "step": 681, "train_runtime": 14872.568, "train_tokens_per_second": 2989.675 }, { "epoch": 0.43308461660581044, "grad_norm": 1.237880825996399, "learning_rate": 1.8999768090671858e-05, "loss": 1.5984327793121338, "num_input_tokens_seen": 44529569, "step": 682, "train_runtime": 14894.2386, "train_tokens_per_second": 2989.718 }, { "epoch": 0.4337196380377838, "grad_norm": 1.2684986591339111, "learning_rate": 1.8996865762540454e-05, "loss": 1.6599512100219727, "num_input_tokens_seen": 44595004, "step": 683, "train_runtime": 14916.5454, "train_tokens_per_second": 2989.634 }, { "epoch": 0.4343546594697571, "grad_norm": 1.2017736434936523, "learning_rate": 1.899395945206292e-05, "loss": 1.5831366777420044, "num_input_tokens_seen": 44660505, "step": 684, "train_runtime": 14938.4718, "train_tokens_per_second": 2989.63 }, { "epoch": 0.43498968090173046, "grad_norm": 1.2811968326568604, "learning_rate": 1.8991049160525695e-05, "loss": 1.6225547790527344, "num_input_tokens_seen": 44725889, "step": 685, "train_runtime": 14959.621, "train_tokens_per_second": 2989.774 }, { "epoch": 0.43562470233370376, "grad_norm": 1.270664095878601, "learning_rate": 1.8988134889216985e-05, "loss": 1.6630172729492188, "num_input_tokens_seen": 44791351, "step": 686, "train_runtime": 14980.8601, "train_tokens_per_second": 2989.905 }, { "epoch": 0.43625972376567707, "grad_norm": 1.1795899868011475, "learning_rate": 1.8985216639426754e-05, "loss": 1.595244288444519, "num_input_tokens_seen": 44856865, "step": 687, "train_runtime": 15002.1451, "train_tokens_per_second": 2990.03 }, { "epoch": 0.4368947451976504, "grad_norm": 1.1972631216049194, "learning_rate": 1.8982294412446722e-05, "loss": 1.729773998260498, "num_input_tokens_seen": 44922206, "step": 688, "train_runtime": 15023.0385, "train_tokens_per_second": 2990.221 }, { "epoch": 0.43752976662962373, "grad_norm": 1.3636422157287598, "learning_rate": 1.8979368209570387e-05, "loss": 1.7189183235168457, "num_input_tokens_seen": 44987697, "step": 689, "train_runtime": 15044.9293, "train_tokens_per_second": 2990.223 }, { "epoch": 0.4381647880615971, "grad_norm": 1.2187294960021973, "learning_rate": 1.8976438032092978e-05, "loss": 1.6974906921386719, "num_input_tokens_seen": 45053170, "step": 690, "train_runtime": 15067.5207, "train_tokens_per_second": 2990.085 }, { "epoch": 0.4387998094935704, "grad_norm": 1.2542930841445923, "learning_rate": 1.8973503881311516e-05, "loss": 1.500214695930481, "num_input_tokens_seen": 45118607, "step": 691, "train_runtime": 15088.7945, "train_tokens_per_second": 2990.206 }, { "epoch": 0.43943483092554375, "grad_norm": 1.1953725814819336, "learning_rate": 1.8970565758524752e-05, "loss": 1.6246421337127686, "num_input_tokens_seen": 45183981, "step": 692, "train_runtime": 15110.1527, "train_tokens_per_second": 2990.306 }, { "epoch": 0.44006985235751706, "grad_norm": 1.2144370079040527, "learning_rate": 1.8967623665033218e-05, "loss": 1.5851233005523682, "num_input_tokens_seen": 45249501, "step": 693, "train_runtime": 15131.4459, "train_tokens_per_second": 2990.428 }, { "epoch": 0.4407048737894904, "grad_norm": 1.1146851778030396, "learning_rate": 1.896467760213919e-05, "loss": 1.5778491497039795, "num_input_tokens_seen": 45314970, "step": 694, "train_runtime": 15152.5583, "train_tokens_per_second": 2990.582 }, { "epoch": 0.4413398952214637, "grad_norm": 1.1544252634048462, "learning_rate": 1.8961727571146706e-05, "loss": 1.5860122442245483, "num_input_tokens_seen": 45380473, "step": 695, "train_runtime": 15173.7081, "train_tokens_per_second": 2990.731 }, { "epoch": 0.4419749166534371, "grad_norm": 1.198744297027588, "learning_rate": 1.8958773573361554e-05, "loss": 1.7827231884002686, "num_input_tokens_seen": 45445941, "step": 696, "train_runtime": 15194.3545, "train_tokens_per_second": 2990.975 }, { "epoch": 0.4426099380854104, "grad_norm": 1.0998142957687378, "learning_rate": 1.8955815610091286e-05, "loss": 1.597580075263977, "num_input_tokens_seen": 45511425, "step": 697, "train_runtime": 15215.5195, "train_tokens_per_second": 2991.119 }, { "epoch": 0.4432449595173837, "grad_norm": 1.2026375532150269, "learning_rate": 1.895285368264521e-05, "loss": 1.681767225265503, "num_input_tokens_seen": 45576851, "step": 698, "train_runtime": 15237.2056, "train_tokens_per_second": 2991.155 }, { "epoch": 0.44387998094935704, "grad_norm": 1.2529834508895874, "learning_rate": 1.8949887792334372e-05, "loss": 1.7382440567016602, "num_input_tokens_seen": 45642273, "step": 699, "train_runtime": 15258.2718, "train_tokens_per_second": 2991.313 }, { "epoch": 0.44451500238133035, "grad_norm": 1.2129409313201904, "learning_rate": 1.89469179404716e-05, "loss": 1.6030731201171875, "num_input_tokens_seen": 45707624, "step": 700, "train_runtime": 15279.4479, "train_tokens_per_second": 2991.445 }, { "epoch": 0.44451500238133035, "eval_loss": 1.5930854082107544, "eval_runtime": 12.9056, "eval_samples_per_second": 1.782, "eval_steps_per_second": 0.93, "num_input_tokens_seen": 45707624, "step": 700 }, { "epoch": 0.4451500238133037, "grad_norm": 1.1845513582229614, "learning_rate": 1.8943944128371455e-05, "loss": 1.474456548690796, "num_input_tokens_seen": 45773125, "step": 701, "train_runtime": 15351.373, "train_tokens_per_second": 2981.696 }, { "epoch": 0.445785045245277, "grad_norm": 1.2509832382202148, "learning_rate": 1.894096635735026e-05, "loss": 1.7385896444320679, "num_input_tokens_seen": 45838524, "step": 702, "train_runtime": 15372.3739, "train_tokens_per_second": 2981.877 }, { "epoch": 0.44642006667725037, "grad_norm": 1.1982194185256958, "learning_rate": 1.8937984628726075e-05, "loss": 1.6268261671066284, "num_input_tokens_seen": 45904041, "step": 703, "train_runtime": 15394.896, "train_tokens_per_second": 2981.77 }, { "epoch": 0.4470550881092237, "grad_norm": 1.2735662460327148, "learning_rate": 1.8934998943818735e-05, "loss": 1.8646092414855957, "num_input_tokens_seen": 45969472, "step": 704, "train_runtime": 15416.2046, "train_tokens_per_second": 2981.893 }, { "epoch": 0.44769010954119703, "grad_norm": 1.4837870597839355, "learning_rate": 1.893200930394981e-05, "loss": 1.8691989183425903, "num_input_tokens_seen": 46034891, "step": 705, "train_runtime": 15437.9122, "train_tokens_per_second": 2981.938 }, { "epoch": 0.44832513097317034, "grad_norm": 1.4715417623519897, "learning_rate": 1.892901571044263e-05, "loss": 1.8224748373031616, "num_input_tokens_seen": 46094387, "step": 706, "train_runtime": 15458.076, "train_tokens_per_second": 2981.897 }, { "epoch": 0.4489601524051437, "grad_norm": 1.157620906829834, "learning_rate": 1.892601816462226e-05, "loss": 1.6593180894851685, "num_input_tokens_seen": 46159815, "step": 707, "train_runtime": 15478.7155, "train_tokens_per_second": 2982.148 }, { "epoch": 0.449595173837117, "grad_norm": 1.1143702268600464, "learning_rate": 1.8923016667815536e-05, "loss": 1.6484774351119995, "num_input_tokens_seen": 46225193, "step": 708, "train_runtime": 15500.3073, "train_tokens_per_second": 2982.211 }, { "epoch": 0.4502301952690903, "grad_norm": 1.313664436340332, "learning_rate": 1.8920011221351026e-05, "loss": 1.9505550861358643, "num_input_tokens_seen": 46290680, "step": 709, "train_runtime": 15521.8221, "train_tokens_per_second": 2982.297 }, { "epoch": 0.45086521670106366, "grad_norm": 1.333551287651062, "learning_rate": 1.8917001826559054e-05, "loss": 1.6914691925048828, "num_input_tokens_seen": 46356154, "step": 710, "train_runtime": 15544.3319, "train_tokens_per_second": 2982.19 }, { "epoch": 0.45150023813303697, "grad_norm": 1.0558346509933472, "learning_rate": 1.891398848477169e-05, "loss": 1.493069052696228, "num_input_tokens_seen": 46421661, "step": 711, "train_runtime": 15564.7888, "train_tokens_per_second": 2982.479 }, { "epoch": 0.45213525956501033, "grad_norm": 1.2446181774139404, "learning_rate": 1.891097119732275e-05, "loss": 1.7564727067947388, "num_input_tokens_seen": 46487088, "step": 712, "train_runtime": 15586.4518, "train_tokens_per_second": 2982.532 }, { "epoch": 0.45277028099698363, "grad_norm": 1.075185775756836, "learning_rate": 1.8907949965547795e-05, "loss": 1.4975223541259766, "num_input_tokens_seen": 46552610, "step": 713, "train_runtime": 15607.8334, "train_tokens_per_second": 2982.644 }, { "epoch": 0.453405302428957, "grad_norm": 1.1005316972732544, "learning_rate": 1.8904924790784137e-05, "loss": 1.5494333505630493, "num_input_tokens_seen": 46618116, "step": 714, "train_runtime": 15628.7538, "train_tokens_per_second": 2982.843 }, { "epoch": 0.4540403238609303, "grad_norm": 1.1387957334518433, "learning_rate": 1.8901895674370826e-05, "loss": 1.6210975646972656, "num_input_tokens_seen": 46683582, "step": 715, "train_runtime": 15650.1605, "train_tokens_per_second": 2982.946 }, { "epoch": 0.45467534529290365, "grad_norm": 1.0457642078399658, "learning_rate": 1.889886261764867e-05, "loss": 1.5186172723770142, "num_input_tokens_seen": 46749103, "step": 716, "train_runtime": 15670.9608, "train_tokens_per_second": 2983.168 }, { "epoch": 0.45531036672487696, "grad_norm": 1.190995693206787, "learning_rate": 1.8895825621960204e-05, "loss": 1.5009349584579468, "num_input_tokens_seen": 46814530, "step": 717, "train_runtime": 15692.232, "train_tokens_per_second": 2983.293 }, { "epoch": 0.4559453881568503, "grad_norm": 1.2958688735961914, "learning_rate": 1.889278468864972e-05, "loss": 1.8649981021881104, "num_input_tokens_seen": 46880034, "step": 718, "train_runtime": 15713.7711, "train_tokens_per_second": 2983.373 }, { "epoch": 0.4565804095888236, "grad_norm": 1.2265032529830933, "learning_rate": 1.888973981906324e-05, "loss": 1.7380503416061401, "num_input_tokens_seen": 46945553, "step": 719, "train_runtime": 15735.2682, "train_tokens_per_second": 2983.461 }, { "epoch": 0.4572154310207969, "grad_norm": 1.2471983432769775, "learning_rate": 1.8886691014548545e-05, "loss": 1.648498773574829, "num_input_tokens_seen": 47011061, "step": 720, "train_runtime": 15757.2235, "train_tokens_per_second": 2983.461 }, { "epoch": 0.4578504524527703, "grad_norm": 1.20900297164917, "learning_rate": 1.8883638276455146e-05, "loss": 1.6542760133743286, "num_input_tokens_seen": 47076593, "step": 721, "train_runtime": 15778.6247, "train_tokens_per_second": 2983.568 }, { "epoch": 0.4584854738847436, "grad_norm": 1.2631803750991821, "learning_rate": 1.88805816061343e-05, "loss": 1.686745285987854, "num_input_tokens_seen": 47136758, "step": 722, "train_runtime": 15798.1497, "train_tokens_per_second": 2983.689 }, { "epoch": 0.45912049531671695, "grad_norm": 1.3930262327194214, "learning_rate": 1.8877521004938996e-05, "loss": 1.8087379932403564, "num_input_tokens_seen": 47202285, "step": 723, "train_runtime": 15819.4669, "train_tokens_per_second": 2983.81 }, { "epoch": 0.45975551674869025, "grad_norm": 1.097493052482605, "learning_rate": 1.8874456474223972e-05, "loss": 1.5503827333450317, "num_input_tokens_seen": 47267753, "step": 724, "train_runtime": 15840.1776, "train_tokens_per_second": 2984.042 }, { "epoch": 0.4603905381806636, "grad_norm": 1.2000843286514282, "learning_rate": 1.8871388015345707e-05, "loss": 1.6841744184494019, "num_input_tokens_seen": 47333267, "step": 725, "train_runtime": 15861.9136, "train_tokens_per_second": 2984.083 }, { "epoch": 0.4610255596126369, "grad_norm": 1.2394813299179077, "learning_rate": 1.8868315629662414e-05, "loss": 1.7665411233901978, "num_input_tokens_seen": 47398681, "step": 726, "train_runtime": 15883.968, "train_tokens_per_second": 2984.058 }, { "epoch": 0.4616605810446103, "grad_norm": 1.2254432439804077, "learning_rate": 1.8865239318534038e-05, "loss": 1.6328132152557373, "num_input_tokens_seen": 47464117, "step": 727, "train_runtime": 15904.8089, "train_tokens_per_second": 2984.262 }, { "epoch": 0.4622956024765836, "grad_norm": 1.2315398454666138, "learning_rate": 1.8862159083322277e-05, "loss": 1.6832059621810913, "num_input_tokens_seen": 47529584, "step": 728, "train_runtime": 15926.8926, "train_tokens_per_second": 2984.235 }, { "epoch": 0.46293062390855694, "grad_norm": 1.1260004043579102, "learning_rate": 1.885907492539055e-05, "loss": 1.6269546747207642, "num_input_tokens_seen": 47594959, "step": 729, "train_runtime": 15948.5694, "train_tokens_per_second": 2984.278 }, { "epoch": 0.46356564534053024, "grad_norm": 1.1520097255706787, "learning_rate": 1.8855986846104022e-05, "loss": 1.6224650144577026, "num_input_tokens_seen": 47660406, "step": 730, "train_runtime": 15969.7158, "train_tokens_per_second": 2984.424 }, { "epoch": 0.46420066677250355, "grad_norm": 1.1478601694107056, "learning_rate": 1.8852894846829596e-05, "loss": 1.5976405143737793, "num_input_tokens_seen": 47725857, "step": 731, "train_runtime": 15990.7569, "train_tokens_per_second": 2984.59 }, { "epoch": 0.4648356882044769, "grad_norm": 1.2234312295913696, "learning_rate": 1.88497989289359e-05, "loss": 1.5374412536621094, "num_input_tokens_seen": 47791379, "step": 732, "train_runtime": 16012.08, "train_tokens_per_second": 2984.708 }, { "epoch": 0.4654707096364502, "grad_norm": 1.339155673980713, "learning_rate": 1.88466990937933e-05, "loss": 1.8314937353134155, "num_input_tokens_seen": 47856878, "step": 733, "train_runtime": 16033.3585, "train_tokens_per_second": 2984.832 }, { "epoch": 0.46610573106842357, "grad_norm": 1.2936304807662964, "learning_rate": 1.8843595342773905e-05, "loss": 1.7719725370407104, "num_input_tokens_seen": 47922308, "step": 734, "train_runtime": 16054.7982, "train_tokens_per_second": 2984.921 }, { "epoch": 0.46674075250039687, "grad_norm": 1.2752960920333862, "learning_rate": 1.8840487677251544e-05, "loss": 1.699478030204773, "num_input_tokens_seen": 47987763, "step": 735, "train_runtime": 16076.088, "train_tokens_per_second": 2985.04 }, { "epoch": 0.46737577393237023, "grad_norm": 1.2339398860931396, "learning_rate": 1.883737609860179e-05, "loss": 1.660080909729004, "num_input_tokens_seen": 48053252, "step": 736, "train_runtime": 16097.0866, "train_tokens_per_second": 2985.214 }, { "epoch": 0.46801079536434353, "grad_norm": 1.2789933681488037, "learning_rate": 1.8834260608201936e-05, "loss": 1.650388479232788, "num_input_tokens_seen": 48118742, "step": 737, "train_runtime": 16119.3342, "train_tokens_per_second": 2985.157 }, { "epoch": 0.4686458167963169, "grad_norm": 1.3002099990844727, "learning_rate": 1.883114120743102e-05, "loss": 1.8870136737823486, "num_input_tokens_seen": 48184236, "step": 738, "train_runtime": 16141.1948, "train_tokens_per_second": 2985.172 }, { "epoch": 0.4692808382282902, "grad_norm": 1.1995718479156494, "learning_rate": 1.88280178976698e-05, "loss": 1.6416258811950684, "num_input_tokens_seen": 48249643, "step": 739, "train_runtime": 16161.8609, "train_tokens_per_second": 2985.401 }, { "epoch": 0.46991585966026356, "grad_norm": 1.0456730127334595, "learning_rate": 1.882489068030078e-05, "loss": 1.3791369199752808, "num_input_tokens_seen": 48315134, "step": 740, "train_runtime": 16182.7593, "train_tokens_per_second": 2985.593 }, { "epoch": 0.47055088109223686, "grad_norm": 1.3155725002288818, "learning_rate": 1.8821759556708164e-05, "loss": 1.7447264194488525, "num_input_tokens_seen": 48380570, "step": 741, "train_runtime": 16205.0357, "train_tokens_per_second": 2985.527 }, { "epoch": 0.47118590252421017, "grad_norm": 1.1905324459075928, "learning_rate": 1.8818624528277914e-05, "loss": 1.7162110805511475, "num_input_tokens_seen": 48446045, "step": 742, "train_runtime": 16226.8922, "train_tokens_per_second": 2985.541 }, { "epoch": 0.4718209239561835, "grad_norm": 1.1677783727645874, "learning_rate": 1.881548559639771e-05, "loss": 1.6344194412231445, "num_input_tokens_seen": 48511477, "step": 743, "train_runtime": 16247.8556, "train_tokens_per_second": 2985.716 }, { "epoch": 0.47245594538815683, "grad_norm": 1.3972853422164917, "learning_rate": 1.8812342762456956e-05, "loss": 1.7887351512908936, "num_input_tokens_seen": 48576788, "step": 744, "train_runtime": 16269.2442, "train_tokens_per_second": 2985.805 }, { "epoch": 0.4730909668201302, "grad_norm": 1.116284728050232, "learning_rate": 1.880919602784679e-05, "loss": 1.5459705591201782, "num_input_tokens_seen": 48642242, "step": 745, "train_runtime": 16290.8901, "train_tokens_per_second": 2985.855 }, { "epoch": 0.4737259882521035, "grad_norm": 1.2396882772445679, "learning_rate": 1.880604539396007e-05, "loss": 1.7985551357269287, "num_input_tokens_seen": 48707680, "step": 746, "train_runtime": 16311.8684, "train_tokens_per_second": 2986.027 }, { "epoch": 0.47436100968407685, "grad_norm": 1.201545238494873, "learning_rate": 1.8802890862191386e-05, "loss": 1.7587316036224365, "num_input_tokens_seen": 48773190, "step": 747, "train_runtime": 16333.2014, "train_tokens_per_second": 2986.138 }, { "epoch": 0.47499603111605015, "grad_norm": 1.1698883771896362, "learning_rate": 1.879973243393705e-05, "loss": 1.6758822202682495, "num_input_tokens_seen": 48838704, "step": 748, "train_runtime": 16354.713, "train_tokens_per_second": 2986.216 }, { "epoch": 0.4756310525480235, "grad_norm": 1.3068487644195557, "learning_rate": 1.8796570110595096e-05, "loss": 1.7629330158233643, "num_input_tokens_seen": 48904094, "step": 749, "train_runtime": 16376.0683, "train_tokens_per_second": 2986.315 }, { "epoch": 0.4762660739799968, "grad_norm": 1.1583774089813232, "learning_rate": 1.8793403893565295e-05, "loss": 1.5071194171905518, "num_input_tokens_seen": 48969413, "step": 750, "train_runtime": 16397.2778, "train_tokens_per_second": 2986.436 }, { "epoch": 0.4769010954119702, "grad_norm": 1.2189948558807373, "learning_rate": 1.8790233784249122e-05, "loss": 1.697182059288025, "num_input_tokens_seen": 49034870, "step": 751, "train_runtime": 16418.1079, "train_tokens_per_second": 2986.633 }, { "epoch": 0.4775361168439435, "grad_norm": 1.1322213411331177, "learning_rate": 1.878705978404979e-05, "loss": 1.5625226497650146, "num_input_tokens_seen": 49100351, "step": 752, "train_runtime": 16439.2871, "train_tokens_per_second": 2986.769 }, { "epoch": 0.4781711382759168, "grad_norm": 1.131733775138855, "learning_rate": 1.8783881894372226e-05, "loss": 1.6651335954666138, "num_input_tokens_seen": 49164113, "step": 753, "train_runtime": 16459.317, "train_tokens_per_second": 2987.008 }, { "epoch": 0.47880615970789014, "grad_norm": 1.2123531103134155, "learning_rate": 1.8780700116623082e-05, "loss": 1.7007124423980713, "num_input_tokens_seen": 49229599, "step": 754, "train_runtime": 16481.1849, "train_tokens_per_second": 2987.018 }, { "epoch": 0.47944118113986345, "grad_norm": 1.2879492044448853, "learning_rate": 1.8777514452210734e-05, "loss": 1.8706517219543457, "num_input_tokens_seen": 49295107, "step": 755, "train_runtime": 16503.4565, "train_tokens_per_second": 2986.957 }, { "epoch": 0.4800762025718368, "grad_norm": 1.214035153388977, "learning_rate": 1.877432490254527e-05, "loss": 1.562490463256836, "num_input_tokens_seen": 49360499, "step": 756, "train_runtime": 16524.4219, "train_tokens_per_second": 2987.124 }, { "epoch": 0.4807112240038101, "grad_norm": 1.157023310661316, "learning_rate": 1.877113146903851e-05, "loss": 1.493456244468689, "num_input_tokens_seen": 49425943, "step": 757, "train_runtime": 16546.0143, "train_tokens_per_second": 2987.181 }, { "epoch": 0.48134624543578347, "grad_norm": 1.248422622680664, "learning_rate": 1.876793415310398e-05, "loss": 1.6564724445343018, "num_input_tokens_seen": 49491336, "step": 758, "train_runtime": 16567.138, "train_tokens_per_second": 2987.32 }, { "epoch": 0.4819812668677568, "grad_norm": 1.1776666641235352, "learning_rate": 1.8764732956156928e-05, "loss": 1.5228925943374634, "num_input_tokens_seen": 49556858, "step": 759, "train_runtime": 16587.8006, "train_tokens_per_second": 2987.548 }, { "epoch": 0.48261628829973013, "grad_norm": 1.1781911849975586, "learning_rate": 1.876152787961433e-05, "loss": 1.5252885818481445, "num_input_tokens_seen": 49622220, "step": 760, "train_runtime": 16608.6655, "train_tokens_per_second": 2987.731 }, { "epoch": 0.48325130973170344, "grad_norm": 1.1582551002502441, "learning_rate": 1.875831892489487e-05, "loss": 1.477739930152893, "num_input_tokens_seen": 49687676, "step": 761, "train_runtime": 16630.0104, "train_tokens_per_second": 2987.832 }, { "epoch": 0.4838863311636768, "grad_norm": 1.3447563648223877, "learning_rate": 1.8755106093418948e-05, "loss": 1.659584403038025, "num_input_tokens_seen": 49753065, "step": 762, "train_runtime": 16651.1555, "train_tokens_per_second": 2987.965 }, { "epoch": 0.4845213525956501, "grad_norm": 1.2324005365371704, "learning_rate": 1.8751889386608682e-05, "loss": 1.6698360443115234, "num_input_tokens_seen": 49818541, "step": 763, "train_runtime": 16672.6916, "train_tokens_per_second": 2988.032 }, { "epoch": 0.4851563740276234, "grad_norm": 1.3328664302825928, "learning_rate": 1.874866880588791e-05, "loss": 1.6715598106384277, "num_input_tokens_seen": 49884029, "step": 764, "train_runtime": 16694.3694, "train_tokens_per_second": 2988.075 }, { "epoch": 0.48579139545959676, "grad_norm": 1.2458627223968506, "learning_rate": 1.8745444352682173e-05, "loss": 1.7024871110916138, "num_input_tokens_seen": 49949497, "step": 765, "train_runtime": 16715.858, "train_tokens_per_second": 2988.15 }, { "epoch": 0.48642641689157007, "grad_norm": 1.2013477087020874, "learning_rate": 1.8742216028418737e-05, "loss": 1.7305253744125366, "num_input_tokens_seen": 50014959, "step": 766, "train_runtime": 16736.8182, "train_tokens_per_second": 2988.319 }, { "epoch": 0.4870614383235434, "grad_norm": 1.1615386009216309, "learning_rate": 1.873898383452658e-05, "loss": 1.7694514989852905, "num_input_tokens_seen": 50080399, "step": 767, "train_runtime": 16757.7731, "train_tokens_per_second": 2988.488 }, { "epoch": 0.48769645975551673, "grad_norm": 1.2214106321334839, "learning_rate": 1.8735747772436385e-05, "loss": 1.4547046422958374, "num_input_tokens_seen": 50145929, "step": 768, "train_runtime": 16778.5875, "train_tokens_per_second": 2988.686 }, { "epoch": 0.4883314811874901, "grad_norm": 1.213811993598938, "learning_rate": 1.8732507843580563e-05, "loss": 1.7181422710418701, "num_input_tokens_seen": 50211383, "step": 769, "train_runtime": 16799.7106, "train_tokens_per_second": 2988.824 }, { "epoch": 0.4889665026194634, "grad_norm": 1.16287362575531, "learning_rate": 1.8729264049393217e-05, "loss": 1.4346309900283813, "num_input_tokens_seen": 50276786, "step": 770, "train_runtime": 16821.3469, "train_tokens_per_second": 2988.868 }, { "epoch": 0.48960152405143675, "grad_norm": 1.156175971031189, "learning_rate": 1.8726016391310174e-05, "loss": 1.499690055847168, "num_input_tokens_seen": 50342289, "step": 771, "train_runtime": 16842.404, "train_tokens_per_second": 2989.02 }, { "epoch": 0.49023654548341006, "grad_norm": 1.2046440839767456, "learning_rate": 1.872276487076897e-05, "loss": 1.6482629776000977, "num_input_tokens_seen": 50407787, "step": 772, "train_runtime": 16863.7699, "train_tokens_per_second": 2989.117 }, { "epoch": 0.4908715669153834, "grad_norm": 1.2672511339187622, "learning_rate": 1.8719509489208843e-05, "loss": 1.8870015144348145, "num_input_tokens_seen": 50473302, "step": 773, "train_runtime": 16885.415, "train_tokens_per_second": 2989.166 }, { "epoch": 0.4915065883473567, "grad_norm": 1.4525643587112427, "learning_rate": 1.871625024807075e-05, "loss": 1.7055423259735107, "num_input_tokens_seen": 50538750, "step": 774, "train_runtime": 16907.0608, "train_tokens_per_second": 2989.21 }, { "epoch": 0.49214160977933, "grad_norm": 1.2887977361679077, "learning_rate": 1.8712987148797353e-05, "loss": 1.549376130104065, "num_input_tokens_seen": 50599925, "step": 775, "train_runtime": 16926.8846, "train_tokens_per_second": 2989.323 }, { "epoch": 0.4927766312113034, "grad_norm": 1.2579213380813599, "learning_rate": 1.8709720192833016e-05, "loss": 1.5894683599472046, "num_input_tokens_seen": 50665424, "step": 776, "train_runtime": 16948.5166, "train_tokens_per_second": 2989.372 }, { "epoch": 0.4934116526432767, "grad_norm": 1.3963134288787842, "learning_rate": 1.8706449381623818e-05, "loss": 1.7772505283355713, "num_input_tokens_seen": 50725318, "step": 777, "train_runtime": 16968.7059, "train_tokens_per_second": 2989.345 }, { "epoch": 0.49404667407525005, "grad_norm": 1.2301675081253052, "learning_rate": 1.8703174716617537e-05, "loss": 1.6672552824020386, "num_input_tokens_seen": 50790696, "step": 778, "train_runtime": 16990.1521, "train_tokens_per_second": 2989.42 }, { "epoch": 0.49468169550722335, "grad_norm": 1.3189384937286377, "learning_rate": 1.869989619926367e-05, "loss": 1.727586030960083, "num_input_tokens_seen": 50856112, "step": 779, "train_runtime": 17011.4511, "train_tokens_per_second": 2989.522 }, { "epoch": 0.4953167169391967, "grad_norm": 1.3283629417419434, "learning_rate": 1.8696613831013398e-05, "loss": 1.7810163497924805, "num_input_tokens_seen": 50921562, "step": 780, "train_runtime": 17033.0167, "train_tokens_per_second": 2989.58 }, { "epoch": 0.49595173837117, "grad_norm": 1.1691691875457764, "learning_rate": 1.8693327613319633e-05, "loss": 1.6606265306472778, "num_input_tokens_seen": 50987052, "step": 781, "train_runtime": 17054.6368, "train_tokens_per_second": 2989.63 }, { "epoch": 0.4965867598031434, "grad_norm": 1.2004019021987915, "learning_rate": 1.8690037547636962e-05, "loss": 1.570719838142395, "num_input_tokens_seen": 51051937, "step": 782, "train_runtime": 17074.9014, "train_tokens_per_second": 2989.882 }, { "epoch": 0.4972217812351167, "grad_norm": 1.2759119272232056, "learning_rate": 1.8686743635421704e-05, "loss": 1.6609246730804443, "num_input_tokens_seen": 51117454, "step": 783, "train_runtime": 17096.3946, "train_tokens_per_second": 2989.955 }, { "epoch": 0.49785680266709004, "grad_norm": 1.0816632509231567, "learning_rate": 1.8683445878131855e-05, "loss": 1.582959771156311, "num_input_tokens_seen": 51182886, "step": 784, "train_runtime": 17117.3761, "train_tokens_per_second": 2990.113 }, { "epoch": 0.49849182409906334, "grad_norm": 1.3620115518569946, "learning_rate": 1.868014427722713e-05, "loss": 1.8587113618850708, "num_input_tokens_seen": 51248319, "step": 785, "train_runtime": 17139.2674, "train_tokens_per_second": 2990.111 }, { "epoch": 0.49912684553103664, "grad_norm": 1.257076621055603, "learning_rate": 1.867683883416894e-05, "loss": 1.6552889347076416, "num_input_tokens_seen": 51313692, "step": 786, "train_runtime": 17161.3501, "train_tokens_per_second": 2990.073 }, { "epoch": 0.49976186696301, "grad_norm": 1.1335843801498413, "learning_rate": 1.8673529550420392e-05, "loss": 1.4218899011611938, "num_input_tokens_seen": 51379131, "step": 787, "train_runtime": 17181.6348, "train_tokens_per_second": 2990.352 }, { "epoch": 0.5003968883949833, "grad_norm": 1.217240810394287, "learning_rate": 1.8670216427446303e-05, "loss": 1.881445288658142, "num_input_tokens_seen": 51444612, "step": 788, "train_runtime": 17203.1315, "train_tokens_per_second": 2990.421 }, { "epoch": 0.5010319098269567, "grad_norm": 1.2515164613723755, "learning_rate": 1.8666899466713185e-05, "loss": 1.8232492208480835, "num_input_tokens_seen": 51510102, "step": 789, "train_runtime": 17224.8415, "train_tokens_per_second": 2990.454 }, { "epoch": 0.50166693125893, "grad_norm": 1.2372289896011353, "learning_rate": 1.8663578669689244e-05, "loss": 1.682349681854248, "num_input_tokens_seen": 51575623, "step": 790, "train_runtime": 17246.2563, "train_tokens_per_second": 2990.54 }, { "epoch": 0.5023019526909033, "grad_norm": 1.1621671915054321, "learning_rate": 1.866025403784439e-05, "loss": 1.5169793367385864, "num_input_tokens_seen": 51641101, "step": 791, "train_runtime": 17266.9969, "train_tokens_per_second": 2990.74 }, { "epoch": 0.5029369741228766, "grad_norm": 1.0837198495864868, "learning_rate": 1.8656925572650223e-05, "loss": 1.5165597200393677, "num_input_tokens_seen": 51706532, "step": 792, "train_runtime": 17287.1577, "train_tokens_per_second": 2991.037 }, { "epoch": 0.50357199555485, "grad_norm": 1.3333399295806885, "learning_rate": 1.865359327558005e-05, "loss": 1.7581329345703125, "num_input_tokens_seen": 51771997, "step": 793, "train_runtime": 17309.1098, "train_tokens_per_second": 2991.026 }, { "epoch": 0.5042070169868234, "grad_norm": 1.1711653470993042, "learning_rate": 1.8650257148108873e-05, "loss": 1.6493700742721558, "num_input_tokens_seen": 51837467, "step": 794, "train_runtime": 17330.9274, "train_tokens_per_second": 2991.038 }, { "epoch": 0.5048420384187966, "grad_norm": 1.2611685991287231, "learning_rate": 1.8646917191713374e-05, "loss": 1.802978515625, "num_input_tokens_seen": 51902988, "step": 795, "train_runtime": 17352.6448, "train_tokens_per_second": 2991.071 }, { "epoch": 0.50547705985077, "grad_norm": 1.2185118198394775, "learning_rate": 1.864357340787195e-05, "loss": 1.5755525827407837, "num_input_tokens_seen": 51968412, "step": 796, "train_runtime": 17373.602, "train_tokens_per_second": 2991.228 }, { "epoch": 0.5061120812827433, "grad_norm": 1.252926230430603, "learning_rate": 1.8640225798064685e-05, "loss": 1.6072025299072266, "num_input_tokens_seen": 52033939, "step": 797, "train_runtime": 17395.367, "train_tokens_per_second": 2991.253 }, { "epoch": 0.5067471027147166, "grad_norm": 1.178357481956482, "learning_rate": 1.863687436377335e-05, "loss": 1.647375464439392, "num_input_tokens_seen": 52099370, "step": 798, "train_runtime": 17416.8587, "train_tokens_per_second": 2991.318 }, { "epoch": 0.5073821241466899, "grad_norm": 1.2811026573181152, "learning_rate": 1.8633519106481415e-05, "loss": 1.597472906112671, "num_input_tokens_seen": 52164890, "step": 799, "train_runtime": 17439.4691, "train_tokens_per_second": 2991.197 }, { "epoch": 0.5080171455786633, "grad_norm": 1.0949125289916992, "learning_rate": 1.8630160027674048e-05, "loss": 1.4616420269012451, "num_input_tokens_seen": 52230301, "step": 800, "train_runtime": 17460.4237, "train_tokens_per_second": 2991.354 }, { "epoch": 0.5080171455786633, "eval_loss": 1.5854319334030151, "eval_runtime": 12.9013, "eval_samples_per_second": 1.783, "eval_steps_per_second": 0.93, "num_input_tokens_seen": 52230301, "step": 800 }, { "epoch": 0.5086521670106366, "grad_norm": 1.3536535501480103, "learning_rate": 1.862679712883809e-05, "loss": 1.755056619644165, "num_input_tokens_seen": 52295801, "step": 801, "train_runtime": 17531.9485, "train_tokens_per_second": 2982.886 }, { "epoch": 0.5092871884426099, "grad_norm": 1.2398556470870972, "learning_rate": 1.862343041146209e-05, "loss": 1.745703935623169, "num_input_tokens_seen": 52361137, "step": 802, "train_runtime": 17553.0568, "train_tokens_per_second": 2983.021 }, { "epoch": 0.5099222098745833, "grad_norm": 1.3247095346450806, "learning_rate": 1.8620059877036287e-05, "loss": 1.6862590312957764, "num_input_tokens_seen": 52426553, "step": 803, "train_runtime": 17574.6399, "train_tokens_per_second": 2983.08 }, { "epoch": 0.5105572313065566, "grad_norm": 1.429020643234253, "learning_rate": 1.8616685527052597e-05, "loss": 1.8223949670791626, "num_input_tokens_seen": 52492041, "step": 804, "train_runtime": 17596.3434, "train_tokens_per_second": 2983.122 }, { "epoch": 0.51119225273853, "grad_norm": 1.1533238887786865, "learning_rate": 1.8613307363004636e-05, "loss": 1.603664517402649, "num_input_tokens_seen": 52557506, "step": 805, "train_runtime": 17617.3279, "train_tokens_per_second": 2983.285 }, { "epoch": 0.5118272741705032, "grad_norm": 1.3722541332244873, "learning_rate": 1.86099253863877e-05, "loss": 1.7633466720581055, "num_input_tokens_seen": 52621462, "step": 806, "train_runtime": 17638.2586, "train_tokens_per_second": 2983.371 }, { "epoch": 0.5124622956024766, "grad_norm": 1.2839484214782715, "learning_rate": 1.8606539598698786e-05, "loss": 1.5301331281661987, "num_input_tokens_seen": 52686973, "step": 807, "train_runtime": 17659.7606, "train_tokens_per_second": 2983.448 }, { "epoch": 0.5130973170344499, "grad_norm": 1.1101601123809814, "learning_rate": 1.8603150001436563e-05, "loss": 1.612715244293213, "num_input_tokens_seen": 52752501, "step": 808, "train_runtime": 17681.2179, "train_tokens_per_second": 2983.533 }, { "epoch": 0.5137323384664232, "grad_norm": 1.3005497455596924, "learning_rate": 1.859975659610139e-05, "loss": 1.6214991807937622, "num_input_tokens_seen": 52817881, "step": 809, "train_runtime": 17702.6392, "train_tokens_per_second": 2983.616 }, { "epoch": 0.5143673598983965, "grad_norm": 1.253796935081482, "learning_rate": 1.859635938419532e-05, "loss": 1.832932472229004, "num_input_tokens_seen": 52883389, "step": 810, "train_runtime": 17724.6724, "train_tokens_per_second": 2983.603 }, { "epoch": 0.5150023813303699, "grad_norm": 1.2106767892837524, "learning_rate": 1.859295836722208e-05, "loss": 1.7289974689483643, "num_input_tokens_seen": 52948889, "step": 811, "train_runtime": 17746.6934, "train_tokens_per_second": 2983.592 }, { "epoch": 0.5156374027623433, "grad_norm": 1.263581395149231, "learning_rate": 1.8589553546687092e-05, "loss": 1.6768531799316406, "num_input_tokens_seen": 53014277, "step": 812, "train_runtime": 17768.1845, "train_tokens_per_second": 2983.663 }, { "epoch": 0.5162724241943165, "grad_norm": 1.2896332740783691, "learning_rate": 1.858614492409745e-05, "loss": 1.7160520553588867, "num_input_tokens_seen": 53079711, "step": 813, "train_runtime": 17789.807, "train_tokens_per_second": 2983.715 }, { "epoch": 0.5169074456262899, "grad_norm": 1.1248377561569214, "learning_rate": 1.8582732500961938e-05, "loss": 1.749807596206665, "num_input_tokens_seen": 53145136, "step": 814, "train_runtime": 17811.047, "train_tokens_per_second": 2983.83 }, { "epoch": 0.5175424670582632, "grad_norm": 1.1905863285064697, "learning_rate": 1.857931627879102e-05, "loss": 1.7607266902923584, "num_input_tokens_seen": 53210570, "step": 815, "train_runtime": 17832.5614, "train_tokens_per_second": 2983.899 }, { "epoch": 0.5181774884902366, "grad_norm": 1.2590816020965576, "learning_rate": 1.8575896259096847e-05, "loss": 1.5389987230300903, "num_input_tokens_seen": 53273800, "step": 816, "train_runtime": 17852.3659, "train_tokens_per_second": 2984.131 }, { "epoch": 0.5188125099222098, "grad_norm": 1.113131046295166, "learning_rate": 1.8572472443393242e-05, "loss": 1.6334588527679443, "num_input_tokens_seen": 53339176, "step": 817, "train_runtime": 17873.1499, "train_tokens_per_second": 2984.319 }, { "epoch": 0.5194475313541832, "grad_norm": 1.1592390537261963, "learning_rate": 1.8569044833195714e-05, "loss": 1.5568379163742065, "num_input_tokens_seen": 53404621, "step": 818, "train_runtime": 17894.6457, "train_tokens_per_second": 2984.391 }, { "epoch": 0.5200825527861566, "grad_norm": 1.3886916637420654, "learning_rate": 1.8565613430021452e-05, "loss": 2.073988676071167, "num_input_tokens_seen": 53470005, "step": 819, "train_runtime": 17916.9606, "train_tokens_per_second": 2984.323 }, { "epoch": 0.5207175742181298, "grad_norm": 1.2580524682998657, "learning_rate": 1.8562178235389317e-05, "loss": 1.6919499635696411, "num_input_tokens_seen": 53535520, "step": 820, "train_runtime": 17938.9317, "train_tokens_per_second": 2984.32 }, { "epoch": 0.5213525956501032, "grad_norm": 1.180324912071228, "learning_rate": 1.855873925081986e-05, "loss": 1.7172216176986694, "num_input_tokens_seen": 53601056, "step": 821, "train_runtime": 17960.3825, "train_tokens_per_second": 2984.405 }, { "epoch": 0.5219876170820765, "grad_norm": 1.19493567943573, "learning_rate": 1.85552964778353e-05, "loss": 1.556361436843872, "num_input_tokens_seen": 53666460, "step": 822, "train_runtime": 17981.925, "train_tokens_per_second": 2984.467 }, { "epoch": 0.5226226385140499, "grad_norm": 1.2782498598098755, "learning_rate": 1.8551849917959534e-05, "loss": 1.6686198711395264, "num_input_tokens_seen": 53731898, "step": 823, "train_runtime": 18003.4337, "train_tokens_per_second": 2984.536 }, { "epoch": 0.5232576599460231, "grad_norm": 1.2933454513549805, "learning_rate": 1.854839957271814e-05, "loss": 1.623378038406372, "num_input_tokens_seen": 53797423, "step": 824, "train_runtime": 18024.3784, "train_tokens_per_second": 2984.703 }, { "epoch": 0.5238926813779965, "grad_norm": 1.2193788290023804, "learning_rate": 1.854494544363837e-05, "loss": 1.6454522609710693, "num_input_tokens_seen": 53862897, "step": 825, "train_runtime": 18045.4775, "train_tokens_per_second": 2984.842 }, { "epoch": 0.5245277028099699, "grad_norm": 1.24226713180542, "learning_rate": 1.8541487532249144e-05, "loss": 1.6687854528427124, "num_input_tokens_seen": 53928397, "step": 826, "train_runtime": 18066.5523, "train_tokens_per_second": 2984.986 }, { "epoch": 0.5251627242419432, "grad_norm": 1.2329124212265015, "learning_rate": 1.8538025840081063e-05, "loss": 1.6874608993530273, "num_input_tokens_seen": 53993884, "step": 827, "train_runtime": 18088.8758, "train_tokens_per_second": 2984.922 }, { "epoch": 0.5257977456739165, "grad_norm": 1.9632891416549683, "learning_rate": 1.853456036866641e-05, "loss": 1.7176363468170166, "num_input_tokens_seen": 54059361, "step": 828, "train_runtime": 18110.5411, "train_tokens_per_second": 2984.967 }, { "epoch": 0.5264327671058898, "grad_norm": 1.4039487838745117, "learning_rate": 1.8531091119539115e-05, "loss": 1.847132682800293, "num_input_tokens_seen": 54124878, "step": 829, "train_runtime": 18131.9038, "train_tokens_per_second": 2985.063 }, { "epoch": 0.5270677885378632, "grad_norm": 1.0862029790878296, "learning_rate": 1.852761809423481e-05, "loss": 1.494233250617981, "num_input_tokens_seen": 54190392, "step": 830, "train_runtime": 18153.2139, "train_tokens_per_second": 2985.168 }, { "epoch": 0.5277028099698364, "grad_norm": 1.1471846103668213, "learning_rate": 1.8524141294290772e-05, "loss": 1.5667330026626587, "num_input_tokens_seen": 54255856, "step": 831, "train_runtime": 18174.2292, "train_tokens_per_second": 2985.318 }, { "epoch": 0.5283378314018098, "grad_norm": 1.4770864248275757, "learning_rate": 1.8520660721245974e-05, "loss": 1.799121618270874, "num_input_tokens_seen": 54316297, "step": 832, "train_runtime": 18194.5421, "train_tokens_per_second": 2985.307 }, { "epoch": 0.5289728528337831, "grad_norm": 1.2511101961135864, "learning_rate": 1.8517176376641037e-05, "loss": 1.6154472827911377, "num_input_tokens_seen": 54381792, "step": 833, "train_runtime": 18215.0728, "train_tokens_per_second": 2985.538 }, { "epoch": 0.5296078742657565, "grad_norm": 1.3127743005752563, "learning_rate": 1.851368826201827e-05, "loss": 1.8334991931915283, "num_input_tokens_seen": 54447273, "step": 834, "train_runtime": 18237.2394, "train_tokens_per_second": 2985.5 }, { "epoch": 0.5302428956977298, "grad_norm": 1.226449966430664, "learning_rate": 1.8510196378921636e-05, "loss": 1.5978435277938843, "num_input_tokens_seen": 54512677, "step": 835, "train_runtime": 18258.1525, "train_tokens_per_second": 2985.662 }, { "epoch": 0.5308779171297031, "grad_norm": 1.2229406833648682, "learning_rate": 1.8506700728896768e-05, "loss": 1.707329511642456, "num_input_tokens_seen": 54578208, "step": 836, "train_runtime": 18279.7994, "train_tokens_per_second": 2985.712 }, { "epoch": 0.5315129385616765, "grad_norm": 1.2683526277542114, "learning_rate": 1.850320131349098e-05, "loss": 1.8282079696655273, "num_input_tokens_seen": 54643695, "step": 837, "train_runtime": 18301.3449, "train_tokens_per_second": 2985.775 }, { "epoch": 0.5321479599936498, "grad_norm": 1.433862328529358, "learning_rate": 1.8499698134253234e-05, "loss": 1.6846882104873657, "num_input_tokens_seen": 54709210, "step": 838, "train_runtime": 18323.5834, "train_tokens_per_second": 2985.727 }, { "epoch": 0.5327829814256231, "grad_norm": 1.177366018295288, "learning_rate": 1.849619119273417e-05, "loss": 1.6894900798797607, "num_input_tokens_seen": 54774694, "step": 839, "train_runtime": 18345.125, "train_tokens_per_second": 2985.79 }, { "epoch": 0.5334180028575964, "grad_norm": 1.3136048316955566, "learning_rate": 1.8492680490486095e-05, "loss": 1.8159725666046143, "num_input_tokens_seen": 54836097, "step": 840, "train_runtime": 18365.02, "train_tokens_per_second": 2985.899 }, { "epoch": 0.5340530242895698, "grad_norm": 1.2634954452514648, "learning_rate": 1.848916602906297e-05, "loss": 1.7802565097808838, "num_input_tokens_seen": 54901606, "step": 841, "train_runtime": 18385.7688, "train_tokens_per_second": 2986.092 }, { "epoch": 0.534688045721543, "grad_norm": 1.1449023485183716, "learning_rate": 1.848564781002043e-05, "loss": 1.6133557558059692, "num_input_tokens_seen": 54967037, "step": 842, "train_runtime": 18406.9108, "train_tokens_per_second": 2986.217 }, { "epoch": 0.5353230671535164, "grad_norm": 1.4267535209655762, "learning_rate": 1.8482125834915764e-05, "loss": 1.820896863937378, "num_input_tokens_seen": 55032507, "step": 843, "train_runtime": 18429.1124, "train_tokens_per_second": 2986.172 }, { "epoch": 0.5359580885854898, "grad_norm": 1.129217505455017, "learning_rate": 1.847860010530793e-05, "loss": 1.475502610206604, "num_input_tokens_seen": 55098032, "step": 844, "train_runtime": 18450.485, "train_tokens_per_second": 2986.265 }, { "epoch": 0.5365931100174631, "grad_norm": 1.0854958295822144, "learning_rate": 1.8475070622757552e-05, "loss": 1.5792135000228882, "num_input_tokens_seen": 55163527, "step": 845, "train_runtime": 18471.235, "train_tokens_per_second": 2986.456 }, { "epoch": 0.5372281314494364, "grad_norm": 1.1464428901672363, "learning_rate": 1.8471537388826902e-05, "loss": 1.513904094696045, "num_input_tokens_seen": 55229034, "step": 846, "train_runtime": 18491.9595, "train_tokens_per_second": 2986.651 }, { "epoch": 0.5378631528814097, "grad_norm": 1.2638070583343506, "learning_rate": 1.8468000405079927e-05, "loss": 1.6246402263641357, "num_input_tokens_seen": 55294449, "step": 847, "train_runtime": 18513.071, "train_tokens_per_second": 2986.779 }, { "epoch": 0.5384981743133831, "grad_norm": 1.2875018119812012, "learning_rate": 1.8464459673082223e-05, "loss": 1.7768898010253906, "num_input_tokens_seen": 55359912, "step": 848, "train_runtime": 18534.0528, "train_tokens_per_second": 2986.93 }, { "epoch": 0.5391331957453565, "grad_norm": 1.2976021766662598, "learning_rate": 1.8460915194401054e-05, "loss": 1.7490339279174805, "num_input_tokens_seen": 55425306, "step": 849, "train_runtime": 18555.5563, "train_tokens_per_second": 2986.992 }, { "epoch": 0.5397682171773297, "grad_norm": 1.1954325437545776, "learning_rate": 1.8457366970605328e-05, "loss": 1.6299269199371338, "num_input_tokens_seen": 55490798, "step": 850, "train_runtime": 18577.3998, "train_tokens_per_second": 2987.006 }, { "epoch": 0.5404032386093031, "grad_norm": 1.3066540956497192, "learning_rate": 1.8453815003265628e-05, "loss": 1.7678875923156738, "num_input_tokens_seen": 55556249, "step": 851, "train_runtime": 18599.4919, "train_tokens_per_second": 2986.977 }, { "epoch": 0.5410382600412764, "grad_norm": 1.3832465410232544, "learning_rate": 1.845025929395419e-05, "loss": 1.6354029178619385, "num_input_tokens_seen": 55621740, "step": 852, "train_runtime": 18621.0047, "train_tokens_per_second": 2987.043 }, { "epoch": 0.5416732814732497, "grad_norm": 1.1662276983261108, "learning_rate": 1.8446699844244885e-05, "loss": 1.562198281288147, "num_input_tokens_seen": 55687221, "step": 853, "train_runtime": 18642.6824, "train_tokens_per_second": 2987.082 }, { "epoch": 0.542308302905223, "grad_norm": 1.260831356048584, "learning_rate": 1.8443136655713278e-05, "loss": 1.685746192932129, "num_input_tokens_seen": 55752694, "step": 854, "train_runtime": 18664.1897, "train_tokens_per_second": 2987.148 }, { "epoch": 0.5429433243371964, "grad_norm": 1.2537134885787964, "learning_rate": 1.843956972993656e-05, "loss": 1.6185081005096436, "num_input_tokens_seen": 55818079, "step": 855, "train_runtime": 18686.1945, "train_tokens_per_second": 2987.129 }, { "epoch": 0.5435783457691697, "grad_norm": 1.1160502433776855, "learning_rate": 1.8435999068493583e-05, "loss": 1.726366639137268, "num_input_tokens_seen": 55883579, "step": 856, "train_runtime": 18707.8838, "train_tokens_per_second": 2987.167 }, { "epoch": 0.544213367201143, "grad_norm": 1.4116936922073364, "learning_rate": 1.8432424672964853e-05, "loss": 1.6808435916900635, "num_input_tokens_seen": 55948986, "step": 857, "train_runtime": 18729.0401, "train_tokens_per_second": 2987.285 }, { "epoch": 0.5448483886331164, "grad_norm": 1.2950479984283447, "learning_rate": 1.8428846544932536e-05, "loss": 1.7765827178955078, "num_input_tokens_seen": 56014484, "step": 858, "train_runtime": 18751.1774, "train_tokens_per_second": 2987.252 }, { "epoch": 0.5454834100650897, "grad_norm": 1.2940282821655273, "learning_rate": 1.8425264685980437e-05, "loss": 1.6217585802078247, "num_input_tokens_seen": 56079778, "step": 859, "train_runtime": 18772.9357, "train_tokens_per_second": 2987.267 }, { "epoch": 0.5461184314970631, "grad_norm": 1.2172383069992065, "learning_rate": 1.8421679097694025e-05, "loss": 1.5020008087158203, "num_input_tokens_seen": 56145231, "step": 860, "train_runtime": 18794.1777, "train_tokens_per_second": 2987.374 }, { "epoch": 0.5467534529290363, "grad_norm": 1.220463752746582, "learning_rate": 1.841808978166041e-05, "loss": 1.75851571559906, "num_input_tokens_seen": 56210729, "step": 861, "train_runtime": 18814.7319, "train_tokens_per_second": 2987.591 }, { "epoch": 0.5473884743610097, "grad_norm": 1.2828010320663452, "learning_rate": 1.8414496739468362e-05, "loss": 1.6543112993240356, "num_input_tokens_seen": 56276234, "step": 862, "train_runtime": 18836.4321, "train_tokens_per_second": 2987.627 }, { "epoch": 0.548023495792983, "grad_norm": 1.203323483467102, "learning_rate": 1.8410899972708287e-05, "loss": 1.6020294427871704, "num_input_tokens_seen": 56341640, "step": 863, "train_runtime": 18857.2491, "train_tokens_per_second": 2987.797 }, { "epoch": 0.5486585172249563, "grad_norm": 1.31858229637146, "learning_rate": 1.840729948297225e-05, "loss": 1.7719452381134033, "num_input_tokens_seen": 56407124, "step": 864, "train_runtime": 18879.8408, "train_tokens_per_second": 2987.691 }, { "epoch": 0.5492935386569296, "grad_norm": 1.2482800483703613, "learning_rate": 1.840369527185397e-05, "loss": 1.6299004554748535, "num_input_tokens_seen": 56472567, "step": 865, "train_runtime": 18901.5989, "train_tokens_per_second": 2987.714 }, { "epoch": 0.549928560088903, "grad_norm": 1.3306466341018677, "learning_rate": 1.8400087340948787e-05, "loss": 1.8672387599945068, "num_input_tokens_seen": 56538059, "step": 866, "train_runtime": 18922.8937, "train_tokens_per_second": 2987.813 }, { "epoch": 0.5505635815208764, "grad_norm": 1.2654379606246948, "learning_rate": 1.839647569185372e-05, "loss": 1.5744907855987549, "num_input_tokens_seen": 56603533, "step": 867, "train_runtime": 18944.5061, "train_tokens_per_second": 2987.86 }, { "epoch": 0.5511986029528496, "grad_norm": 1.0717333555221558, "learning_rate": 1.8392860326167413e-05, "loss": 1.4741780757904053, "num_input_tokens_seen": 56669054, "step": 868, "train_runtime": 18964.9226, "train_tokens_per_second": 2988.098 }, { "epoch": 0.551833624384823, "grad_norm": 1.2426769733428955, "learning_rate": 1.838924124549016e-05, "loss": 1.7729518413543701, "num_input_tokens_seen": 56734501, "step": 869, "train_runtime": 18986.4132, "train_tokens_per_second": 2988.163 }, { "epoch": 0.5524686458167963, "grad_norm": 1.3327053785324097, "learning_rate": 1.83856184514239e-05, "loss": 1.712024211883545, "num_input_tokens_seen": 56799992, "step": 870, "train_runtime": 19007.7358, "train_tokens_per_second": 2988.257 }, { "epoch": 0.5531036672487697, "grad_norm": 1.328661322593689, "learning_rate": 1.838199194557222e-05, "loss": 1.6702762842178345, "num_input_tokens_seen": 56865414, "step": 871, "train_runtime": 19029.1831, "train_tokens_per_second": 2988.327 }, { "epoch": 0.5537386886807429, "grad_norm": 1.2223938703536987, "learning_rate": 1.837836172954034e-05, "loss": 1.6849421262741089, "num_input_tokens_seen": 56930833, "step": 872, "train_runtime": 19050.6715, "train_tokens_per_second": 2988.39 }, { "epoch": 0.5543737101127163, "grad_norm": 1.0980511903762817, "learning_rate": 1.8374727804935135e-05, "loss": 1.5500750541687012, "num_input_tokens_seen": 56996366, "step": 873, "train_runtime": 19072.2134, "train_tokens_per_second": 2988.451 }, { "epoch": 0.5550087315446897, "grad_norm": 1.247796654701233, "learning_rate": 1.8371090173365103e-05, "loss": 1.6078271865844727, "num_input_tokens_seen": 57061715, "step": 874, "train_runtime": 19093.4075, "train_tokens_per_second": 2988.556 }, { "epoch": 0.5556437529766629, "grad_norm": 1.27554452419281, "learning_rate": 1.836744883644041e-05, "loss": 1.6340515613555908, "num_input_tokens_seen": 57127209, "step": 875, "train_runtime": 19114.8372, "train_tokens_per_second": 2988.632 }, { "epoch": 0.5562787744086363, "grad_norm": 1.2324373722076416, "learning_rate": 1.8363803795772838e-05, "loss": 1.426886796951294, "num_input_tokens_seen": 57192696, "step": 876, "train_runtime": 19136.4916, "train_tokens_per_second": 2988.672 }, { "epoch": 0.5569137958406096, "grad_norm": 1.2385352849960327, "learning_rate": 1.8360155052975813e-05, "loss": 1.666964054107666, "num_input_tokens_seen": 57258078, "step": 877, "train_runtime": 19157.1414, "train_tokens_per_second": 2988.863 }, { "epoch": 0.557548817272583, "grad_norm": 1.2496579885482788, "learning_rate": 1.8356502609664413e-05, "loss": 1.5946338176727295, "num_input_tokens_seen": 57323533, "step": 878, "train_runtime": 19177.965, "train_tokens_per_second": 2989.031 }, { "epoch": 0.5581838387045562, "grad_norm": 1.1482080221176147, "learning_rate": 1.835284646745534e-05, "loss": 1.4875060319900513, "num_input_tokens_seen": 57388942, "step": 879, "train_runtime": 19199.128, "train_tokens_per_second": 2989.143 }, { "epoch": 0.5588188601365296, "grad_norm": 1.3434103727340698, "learning_rate": 1.8349186627966936e-05, "loss": 1.7013845443725586, "num_input_tokens_seen": 57454307, "step": 880, "train_runtime": 19220.0356, "train_tokens_per_second": 2989.292 }, { "epoch": 0.559453881568503, "grad_norm": 1.1965104341506958, "learning_rate": 1.8345523092819187e-05, "loss": 1.677254557609558, "num_input_tokens_seen": 57519741, "step": 881, "train_runtime": 19241.0466, "train_tokens_per_second": 2989.429 }, { "epoch": 0.5600889030004763, "grad_norm": 1.3639832735061646, "learning_rate": 1.8341855863633707e-05, "loss": 1.7078135013580322, "num_input_tokens_seen": 57585094, "step": 882, "train_runtime": 19262.03, "train_tokens_per_second": 2989.565 }, { "epoch": 0.5607239244324496, "grad_norm": 1.0704243183135986, "learning_rate": 1.8338184942033743e-05, "loss": 1.4294049739837646, "num_input_tokens_seen": 57650517, "step": 883, "train_runtime": 19282.7036, "train_tokens_per_second": 2989.753 }, { "epoch": 0.5613589458644229, "grad_norm": 1.261847734451294, "learning_rate": 1.8334510329644192e-05, "loss": 1.7493603229522705, "num_input_tokens_seen": 57715950, "step": 884, "train_runtime": 19303.3156, "train_tokens_per_second": 2989.95 }, { "epoch": 0.5619939672963963, "grad_norm": 1.1357038021087646, "learning_rate": 1.8330832028091558e-05, "loss": 1.6444294452667236, "num_input_tokens_seen": 57781402, "step": 885, "train_runtime": 19324.3679, "train_tokens_per_second": 2990.08 }, { "epoch": 0.5626289887283695, "grad_norm": 1.2571749687194824, "learning_rate": 1.8327150039004003e-05, "loss": 1.5969388484954834, "num_input_tokens_seen": 57846844, "step": 886, "train_runtime": 19345.8448, "train_tokens_per_second": 2990.143 }, { "epoch": 0.5632640101603429, "grad_norm": 1.1962608098983765, "learning_rate": 1.8323464364011318e-05, "loss": 1.6788361072540283, "num_input_tokens_seen": 57912371, "step": 887, "train_runtime": 19367.9761, "train_tokens_per_second": 2990.11 }, { "epoch": 0.5638990315923162, "grad_norm": 1.195006012916565, "learning_rate": 1.8319775004744908e-05, "loss": 1.5552655458450317, "num_input_tokens_seen": 57977882, "step": 888, "train_runtime": 19389.0105, "train_tokens_per_second": 2990.244 }, { "epoch": 0.5645340530242896, "grad_norm": 1.2084866762161255, "learning_rate": 1.8316081962837822e-05, "loss": 1.7408967018127441, "num_input_tokens_seen": 58043231, "step": 889, "train_runtime": 19409.8199, "train_tokens_per_second": 2990.405 }, { "epoch": 0.5651690744562629, "grad_norm": 1.2447595596313477, "learning_rate": 1.831238523992474e-05, "loss": 1.8337657451629639, "num_input_tokens_seen": 58108704, "step": 890, "train_runtime": 19431.1974, "train_tokens_per_second": 2990.485 }, { "epoch": 0.5658040958882362, "grad_norm": 1.1290501356124878, "learning_rate": 1.830868483764197e-05, "loss": 1.5768780708312988, "num_input_tokens_seen": 58174132, "step": 891, "train_runtime": 19451.5065, "train_tokens_per_second": 2990.726 }, { "epoch": 0.5664391173202096, "grad_norm": 1.3462536334991455, "learning_rate": 1.830498075762744e-05, "loss": 1.6734869480133057, "num_input_tokens_seen": 58233017, "step": 892, "train_runtime": 19470.7513, "train_tokens_per_second": 2990.795 }, { "epoch": 0.5670741387521829, "grad_norm": 1.2129995822906494, "learning_rate": 1.8301273001520722e-05, "loss": 1.6365559101104736, "num_input_tokens_seen": 58298513, "step": 893, "train_runtime": 19492.303, "train_tokens_per_second": 2990.848 }, { "epoch": 0.5677091601841562, "grad_norm": 1.2671234607696533, "learning_rate": 1.8297561570963005e-05, "loss": 1.8751314878463745, "num_input_tokens_seen": 58364026, "step": 894, "train_runtime": 19514.2777, "train_tokens_per_second": 2990.837 }, { "epoch": 0.5683441816161295, "grad_norm": 1.2622026205062866, "learning_rate": 1.82938464675971e-05, "loss": 1.8223283290863037, "num_input_tokens_seen": 58429474, "step": 895, "train_runtime": 19535.6373, "train_tokens_per_second": 2990.917 }, { "epoch": 0.5689792030481029, "grad_norm": 1.1212767362594604, "learning_rate": 1.8290127693067453e-05, "loss": 1.5683250427246094, "num_input_tokens_seen": 58494984, "step": 896, "train_runtime": 19556.9569, "train_tokens_per_second": 2991.006 }, { "epoch": 0.5696142244800761, "grad_norm": 1.2453985214233398, "learning_rate": 1.8286405249020133e-05, "loss": 1.7896080017089844, "num_input_tokens_seen": 58560406, "step": 897, "train_runtime": 19578.5462, "train_tokens_per_second": 2991.05 }, { "epoch": 0.5702492459120495, "grad_norm": 1.154429316520691, "learning_rate": 1.8282679137102826e-05, "loss": 1.6435668468475342, "num_input_tokens_seen": 58625828, "step": 898, "train_runtime": 19599.5391, "train_tokens_per_second": 2991.184 }, { "epoch": 0.5708842673440229, "grad_norm": 1.1898986101150513, "learning_rate": 1.827894935896485e-05, "loss": 1.7202857732772827, "num_input_tokens_seen": 58691263, "step": 899, "train_runtime": 19620.2828, "train_tokens_per_second": 2991.357 }, { "epoch": 0.5715192887759962, "grad_norm": 1.2288399934768677, "learning_rate": 1.8275215916257144e-05, "loss": 1.5591511726379395, "num_input_tokens_seen": 58756697, "step": 900, "train_runtime": 19642.2113, "train_tokens_per_second": 2991.348 }, { "epoch": 0.5715192887759962, "eval_loss": 1.578905463218689, "eval_runtime": 12.9026, "eval_samples_per_second": 1.783, "eval_steps_per_second": 0.93, "num_input_tokens_seen": 58756697, "step": 900 }, { "epoch": 0.5721543102079695, "grad_norm": 1.2703169584274292, "learning_rate": 1.827147881063227e-05, "loss": 1.8026845455169678, "num_input_tokens_seen": 58822168, "step": 901, "train_runtime": 19714.8258, "train_tokens_per_second": 2983.651 }, { "epoch": 0.5727893316399428, "grad_norm": 1.1639988422393799, "learning_rate": 1.826773804374441e-05, "loss": 1.7242252826690674, "num_input_tokens_seen": 58887630, "step": 902, "train_runtime": 19736.4214, "train_tokens_per_second": 2983.704 }, { "epoch": 0.5734243530719162, "grad_norm": 1.2237472534179688, "learning_rate": 1.8263993617249352e-05, "loss": 1.6469194889068604, "num_input_tokens_seen": 58953151, "step": 903, "train_runtime": 19757.7664, "train_tokens_per_second": 2983.796 }, { "epoch": 0.5740593745038896, "grad_norm": 1.2097272872924805, "learning_rate": 1.826024553280454e-05, "loss": 1.4807771444320679, "num_input_tokens_seen": 59018398, "step": 904, "train_runtime": 19778.8969, "train_tokens_per_second": 2983.907 }, { "epoch": 0.5746943959358628, "grad_norm": 1.1682151556015015, "learning_rate": 1.8256493792069e-05, "loss": 1.6228805780410767, "num_input_tokens_seen": 59083864, "step": 905, "train_runtime": 19800.0131, "train_tokens_per_second": 2984.032 }, { "epoch": 0.5753294173678362, "grad_norm": 1.2460126876831055, "learning_rate": 1.8252738396703394e-05, "loss": 1.7085518836975098, "num_input_tokens_seen": 59149339, "step": 906, "train_runtime": 19821.4162, "train_tokens_per_second": 2984.113 }, { "epoch": 0.5759644387998095, "grad_norm": 1.2212719917297363, "learning_rate": 1.8248979348370004e-05, "loss": 1.5799574851989746, "num_input_tokens_seen": 59214835, "step": 907, "train_runtime": 19842.6386, "train_tokens_per_second": 2984.222 }, { "epoch": 0.5765994602317828, "grad_norm": 1.3733822107315063, "learning_rate": 1.824521664873272e-05, "loss": 1.640952229499817, "num_input_tokens_seen": 59280297, "step": 908, "train_runtime": 19864.861, "train_tokens_per_second": 2984.179 }, { "epoch": 0.5772344816637561, "grad_norm": 1.2553905248641968, "learning_rate": 1.824145029945705e-05, "loss": 1.8485217094421387, "num_input_tokens_seen": 59345811, "step": 909, "train_runtime": 19887.2638, "train_tokens_per_second": 2984.111 }, { "epoch": 0.5778695030957295, "grad_norm": 1.239286184310913, "learning_rate": 1.823768030221013e-05, "loss": 1.641860008239746, "num_input_tokens_seen": 59411260, "step": 910, "train_runtime": 19908.9303, "train_tokens_per_second": 2984.151 }, { "epoch": 0.5785045245277028, "grad_norm": 1.3074653148651123, "learning_rate": 1.8233906658660685e-05, "loss": 1.6893607378005981, "num_input_tokens_seen": 59476752, "step": 911, "train_runtime": 19929.9002, "train_tokens_per_second": 2984.298 }, { "epoch": 0.5791395459596761, "grad_norm": 1.1906800270080566, "learning_rate": 1.823012937047908e-05, "loss": 1.6355721950531006, "num_input_tokens_seen": 59542174, "step": 912, "train_runtime": 19951.4853, "train_tokens_per_second": 2984.348 }, { "epoch": 0.5797745673916495, "grad_norm": 1.0704611539840698, "learning_rate": 1.8226348439337284e-05, "loss": 1.5606117248535156, "num_input_tokens_seen": 59607689, "step": 913, "train_runtime": 19972.3729, "train_tokens_per_second": 2984.507 }, { "epoch": 0.5804095888236228, "grad_norm": 1.095720648765564, "learning_rate": 1.822256386690887e-05, "loss": 1.55155611038208, "num_input_tokens_seen": 59673166, "step": 914, "train_runtime": 19993.8241, "train_tokens_per_second": 2984.58 }, { "epoch": 0.5810446102555962, "grad_norm": 1.2371643781661987, "learning_rate": 1.8218775654869033e-05, "loss": 1.6757102012634277, "num_input_tokens_seen": 59738621, "step": 915, "train_runtime": 20015.1646, "train_tokens_per_second": 2984.668 }, { "epoch": 0.5816796316875694, "grad_norm": 1.2807358503341675, "learning_rate": 1.821498380489458e-05, "loss": 1.7406939268112183, "num_input_tokens_seen": 59804078, "step": 916, "train_runtime": 20036.5347, "train_tokens_per_second": 2984.752 }, { "epoch": 0.5823146531195428, "grad_norm": 1.184387445449829, "learning_rate": 1.821118831866392e-05, "loss": 1.709702730178833, "num_input_tokens_seen": 59869577, "step": 917, "train_runtime": 20058.2195, "train_tokens_per_second": 2984.79 }, { "epoch": 0.5829496745515161, "grad_norm": 1.2420024871826172, "learning_rate": 1.8207389197857072e-05, "loss": 1.641235113143921, "num_input_tokens_seen": 59935032, "step": 918, "train_runtime": 20079.7356, "train_tokens_per_second": 2984.852 }, { "epoch": 0.5835846959834894, "grad_norm": 1.2295753955841064, "learning_rate": 1.820358644415568e-05, "loss": 1.6101789474487305, "num_input_tokens_seen": 60000422, "step": 919, "train_runtime": 20100.9912, "train_tokens_per_second": 2984.948 }, { "epoch": 0.5842197174154627, "grad_norm": 1.0672054290771484, "learning_rate": 1.8199780059242972e-05, "loss": 1.3520578145980835, "num_input_tokens_seen": 60065882, "step": 920, "train_runtime": 20121.9133, "train_tokens_per_second": 2985.098 }, { "epoch": 0.5848547388474361, "grad_norm": 1.0597772598266602, "learning_rate": 1.8195970044803795e-05, "loss": 1.4193435907363892, "num_input_tokens_seen": 60131240, "step": 921, "train_runtime": 20142.2628, "train_tokens_per_second": 2985.327 }, { "epoch": 0.5854897602794095, "grad_norm": 1.2827397584915161, "learning_rate": 1.8192156402524613e-05, "loss": 1.6144992113113403, "num_input_tokens_seen": 60196706, "step": 922, "train_runtime": 20163.8504, "train_tokens_per_second": 2985.378 }, { "epoch": 0.5861247817113827, "grad_norm": 1.1635264158248901, "learning_rate": 1.8188339134093474e-05, "loss": 1.6249158382415771, "num_input_tokens_seen": 60255301, "step": 923, "train_runtime": 20182.3253, "train_tokens_per_second": 2985.548 }, { "epoch": 0.5867598031433561, "grad_norm": 1.2104166746139526, "learning_rate": 1.8184518241200053e-05, "loss": 1.6684389114379883, "num_input_tokens_seen": 60320652, "step": 924, "train_runtime": 20203.7693, "train_tokens_per_second": 2985.614 }, { "epoch": 0.5873948245753294, "grad_norm": 1.3124995231628418, "learning_rate": 1.818069372553561e-05, "loss": 1.7616199254989624, "num_input_tokens_seen": 60386025, "step": 925, "train_runtime": 20224.9172, "train_tokens_per_second": 2985.724 }, { "epoch": 0.5880298460073028, "grad_norm": 1.2242282629013062, "learning_rate": 1.817686558879302e-05, "loss": 1.633937120437622, "num_input_tokens_seen": 60451491, "step": 926, "train_runtime": 20245.8315, "train_tokens_per_second": 2985.873 }, { "epoch": 0.588664867439276, "grad_norm": 1.1996831893920898, "learning_rate": 1.8173033832666757e-05, "loss": 1.6071780920028687, "num_input_tokens_seen": 60516853, "step": 927, "train_runtime": 20267.1943, "train_tokens_per_second": 2985.951 }, { "epoch": 0.5892998888712494, "grad_norm": 1.2231245040893555, "learning_rate": 1.8169198458852903e-05, "loss": 1.6377036571502686, "num_input_tokens_seen": 60582373, "step": 928, "train_runtime": 20288.8584, "train_tokens_per_second": 2985.992 }, { "epoch": 0.5899349103032228, "grad_norm": 1.154331088066101, "learning_rate": 1.8165359469049135e-05, "loss": 1.5475856065750122, "num_input_tokens_seen": 60647860, "step": 929, "train_runtime": 20309.9465, "train_tokens_per_second": 2986.116 }, { "epoch": 0.590569931735196, "grad_norm": 1.1945346593856812, "learning_rate": 1.8161516864954727e-05, "loss": 1.6268062591552734, "num_input_tokens_seen": 60713200, "step": 930, "train_runtime": 20331.2568, "train_tokens_per_second": 2986.2 }, { "epoch": 0.5912049531671694, "grad_norm": 1.1857471466064453, "learning_rate": 1.815767064827056e-05, "loss": 1.5548986196517944, "num_input_tokens_seen": 60778670, "step": 931, "train_runtime": 20352.1943, "train_tokens_per_second": 2986.345 }, { "epoch": 0.5918399745991427, "grad_norm": 1.2082170248031616, "learning_rate": 1.8153820820699117e-05, "loss": 1.5594918727874756, "num_input_tokens_seen": 60844137, "step": 932, "train_runtime": 20373.4503, "train_tokens_per_second": 2986.442 }, { "epoch": 0.5924749960311161, "grad_norm": 1.287106990814209, "learning_rate": 1.814996738394447e-05, "loss": 1.6722062826156616, "num_input_tokens_seen": 60909580, "step": 933, "train_runtime": 20394.6296, "train_tokens_per_second": 2986.55 }, { "epoch": 0.5931100174630893, "grad_norm": 1.4167225360870361, "learning_rate": 1.8146110339712294e-05, "loss": 1.838668704032898, "num_input_tokens_seen": 60969805, "step": 934, "train_runtime": 20414.6646, "train_tokens_per_second": 2986.569 }, { "epoch": 0.5937450388950627, "grad_norm": 1.3285773992538452, "learning_rate": 1.814224968970986e-05, "loss": 1.7878844738006592, "num_input_tokens_seen": 61035333, "step": 935, "train_runtime": 20437.0326, "train_tokens_per_second": 2986.507 }, { "epoch": 0.594380060327036, "grad_norm": 1.2761421203613281, "learning_rate": 1.8138385435646034e-05, "loss": 1.8008780479431152, "num_input_tokens_seen": 61100803, "step": 936, "train_runtime": 20458.6347, "train_tokens_per_second": 2986.553 }, { "epoch": 0.5950150817590094, "grad_norm": 1.2028965950012207, "learning_rate": 1.8134517579231274e-05, "loss": 1.5899409055709839, "num_input_tokens_seen": 61166321, "step": 937, "train_runtime": 20480.1034, "train_tokens_per_second": 2986.622 }, { "epoch": 0.5956501031909827, "grad_norm": 1.1682966947555542, "learning_rate": 1.8130646122177643e-05, "loss": 1.6728297472000122, "num_input_tokens_seen": 61231723, "step": 938, "train_runtime": 20501.4497, "train_tokens_per_second": 2986.702 }, { "epoch": 0.596285124622956, "grad_norm": 1.2357678413391113, "learning_rate": 1.812677106619879e-05, "loss": 1.7841888666152954, "num_input_tokens_seen": 61297123, "step": 939, "train_runtime": 20522.7988, "train_tokens_per_second": 2986.782 }, { "epoch": 0.5969201460549294, "grad_norm": 1.170000433921814, "learning_rate": 1.812289241300996e-05, "loss": 1.5750359296798706, "num_input_tokens_seen": 61362539, "step": 940, "train_runtime": 20544.1388, "train_tokens_per_second": 2986.864 }, { "epoch": 0.5975551674869026, "grad_norm": 1.2149741649627686, "learning_rate": 1.811901016432798e-05, "loss": 1.4954372644424438, "num_input_tokens_seen": 61427178, "step": 941, "train_runtime": 20565.1007, "train_tokens_per_second": 2986.962 }, { "epoch": 0.598190188918876, "grad_norm": 1.2957196235656738, "learning_rate": 1.8115124321871288e-05, "loss": 1.760669231414795, "num_input_tokens_seen": 61492682, "step": 942, "train_runtime": 20586.7323, "train_tokens_per_second": 2987.005 }, { "epoch": 0.5988252103508493, "grad_norm": 1.1722432374954224, "learning_rate": 1.8111234887359895e-05, "loss": 1.7316545248031616, "num_input_tokens_seen": 61558177, "step": 943, "train_runtime": 20607.7581, "train_tokens_per_second": 2987.136 }, { "epoch": 0.5994602317828227, "grad_norm": 1.1700549125671387, "learning_rate": 1.810734186251541e-05, "loss": 1.7187702655792236, "num_input_tokens_seen": 61623708, "step": 944, "train_runtime": 20629.0809, "train_tokens_per_second": 2987.225 }, { "epoch": 0.600095253214796, "grad_norm": 1.3236360549926758, "learning_rate": 1.8103445249061032e-05, "loss": 1.7111748456954956, "num_input_tokens_seen": 61689186, "step": 945, "train_runtime": 20651.1946, "train_tokens_per_second": 2987.197 }, { "epoch": 0.6007302746467693, "grad_norm": 1.4203096628189087, "learning_rate": 1.8099545048721547e-05, "loss": 1.6051115989685059, "num_input_tokens_seen": 61754664, "step": 946, "train_runtime": 20672.0159, "train_tokens_per_second": 2987.356 }, { "epoch": 0.6013652960787427, "grad_norm": 1.2040796279907227, "learning_rate": 1.8095641263223324e-05, "loss": 1.580675482749939, "num_input_tokens_seen": 61820041, "step": 947, "train_runtime": 20692.9194, "train_tokens_per_second": 2987.497 }, { "epoch": 0.602000317510716, "grad_norm": 1.257405400276184, "learning_rate": 1.8091733894294328e-05, "loss": 1.601081371307373, "num_input_tokens_seen": 61885551, "step": 948, "train_runtime": 20713.8535, "train_tokens_per_second": 2987.641 }, { "epoch": 0.6026353389426893, "grad_norm": 1.2034975290298462, "learning_rate": 1.80878229436641e-05, "loss": 1.739466905593872, "num_input_tokens_seen": 61951003, "step": 949, "train_runtime": 20735.1271, "train_tokens_per_second": 2987.732 }, { "epoch": 0.6032703603746626, "grad_norm": 1.1956019401550293, "learning_rate": 1.8083908413063775e-05, "loss": 1.591802954673767, "num_input_tokens_seen": 62016418, "step": 950, "train_runtime": 20756.3054, "train_tokens_per_second": 2987.835 }, { "epoch": 0.603905381806636, "grad_norm": 1.3664159774780273, "learning_rate": 1.8079990304226068e-05, "loss": 1.7604827880859375, "num_input_tokens_seen": 62081859, "step": 951, "train_runtime": 20778.4279, "train_tokens_per_second": 2987.803 }, { "epoch": 0.6045404032386094, "grad_norm": 1.3408267498016357, "learning_rate": 1.8076068618885284e-05, "loss": 1.7823100090026855, "num_input_tokens_seen": 62147378, "step": 952, "train_runtime": 20800.5767, "train_tokens_per_second": 2987.772 }, { "epoch": 0.6051754246705826, "grad_norm": 1.2647091150283813, "learning_rate": 1.80721433587773e-05, "loss": 1.6251497268676758, "num_input_tokens_seen": 62212801, "step": 953, "train_runtime": 20822.7405, "train_tokens_per_second": 2987.734 }, { "epoch": 0.605810446102556, "grad_norm": 1.2706021070480347, "learning_rate": 1.8068214525639583e-05, "loss": 1.7341471910476685, "num_input_tokens_seen": 62276332, "step": 954, "train_runtime": 20843.4325, "train_tokens_per_second": 2987.816 }, { "epoch": 0.6064454675345293, "grad_norm": 1.108292818069458, "learning_rate": 1.806428212121118e-05, "loss": 1.4815716743469238, "num_input_tokens_seen": 62341844, "step": 955, "train_runtime": 20864.0616, "train_tokens_per_second": 2988.001 }, { "epoch": 0.6070804889665026, "grad_norm": 1.1325548887252808, "learning_rate": 1.806034614723272e-05, "loss": 1.7437481880187988, "num_input_tokens_seen": 62407328, "step": 956, "train_runtime": 20885.3407, "train_tokens_per_second": 2988.092 }, { "epoch": 0.6077155103984759, "grad_norm": 1.3073441982269287, "learning_rate": 1.8056406605446413e-05, "loss": 1.703741192817688, "num_input_tokens_seen": 62472689, "step": 957, "train_runtime": 20907.1393, "train_tokens_per_second": 2988.103 }, { "epoch": 0.6083505318304493, "grad_norm": 1.2873455286026, "learning_rate": 1.805246349759604e-05, "loss": 1.7925820350646973, "num_input_tokens_seen": 62538088, "step": 958, "train_runtime": 20928.9901, "train_tokens_per_second": 2988.108 }, { "epoch": 0.6089855532624227, "grad_norm": 1.2102411985397339, "learning_rate": 1.8048516825426975e-05, "loss": 1.6583542823791504, "num_input_tokens_seen": 62603515, "step": 959, "train_runtime": 20950.3509, "train_tokens_per_second": 2988.185 }, { "epoch": 0.6096205746943959, "grad_norm": 1.2056972980499268, "learning_rate": 1.8044566590686154e-05, "loss": 1.685369849205017, "num_input_tokens_seen": 62668868, "step": 960, "train_runtime": 20971.6254, "train_tokens_per_second": 2988.269 }, { "epoch": 0.6102555961263693, "grad_norm": 1.1861796379089355, "learning_rate": 1.80406127951221e-05, "loss": 1.5596857070922852, "num_input_tokens_seen": 62734244, "step": 961, "train_runtime": 20992.2031, "train_tokens_per_second": 2988.455 }, { "epoch": 0.6108906175583426, "grad_norm": 1.101020097732544, "learning_rate": 1.803665544048491e-05, "loss": 1.5094826221466064, "num_input_tokens_seen": 62799701, "step": 962, "train_runtime": 21012.9098, "train_tokens_per_second": 2988.625 }, { "epoch": 0.611525638990316, "grad_norm": 1.1770050525665283, "learning_rate": 1.8032694528526256e-05, "loss": 1.6692540645599365, "num_input_tokens_seen": 62865174, "step": 963, "train_runtime": 21035.0024, "train_tokens_per_second": 2988.598 }, { "epoch": 0.6121606604222892, "grad_norm": 1.1161710023880005, "learning_rate": 1.802873006099938e-05, "loss": 1.4970197677612305, "num_input_tokens_seen": 62930650, "step": 964, "train_runtime": 21056.267, "train_tokens_per_second": 2988.69 }, { "epoch": 0.6127956818542626, "grad_norm": 1.2846759557724, "learning_rate": 1.802476203965911e-05, "loss": 1.7148027420043945, "num_input_tokens_seen": 62996130, "step": 965, "train_runtime": 21078.2253, "train_tokens_per_second": 2988.683 }, { "epoch": 0.613430703286236, "grad_norm": 1.2024989128112793, "learning_rate": 1.8020790466261833e-05, "loss": 1.6253479719161987, "num_input_tokens_seen": 63061563, "step": 966, "train_runtime": 21099.7471, "train_tokens_per_second": 2988.735 }, { "epoch": 0.6140657247182092, "grad_norm": 1.2558481693267822, "learning_rate": 1.8016815342565516e-05, "loss": 1.8310896158218384, "num_input_tokens_seen": 63127036, "step": 967, "train_runtime": 21121.3827, "train_tokens_per_second": 2988.774 }, { "epoch": 0.6147007461501826, "grad_norm": 1.3237940073013306, "learning_rate": 1.8012836670329697e-05, "loss": 1.7532389163970947, "num_input_tokens_seen": 63192500, "step": 968, "train_runtime": 21142.8598, "train_tokens_per_second": 2988.834 }, { "epoch": 0.6153357675821559, "grad_norm": 1.215390920639038, "learning_rate": 1.8008854451315486e-05, "loss": 1.7572652101516724, "num_input_tokens_seen": 63257991, "step": 969, "train_runtime": 21164.0552, "train_tokens_per_second": 2988.935 }, { "epoch": 0.6159707890141293, "grad_norm": 1.1714352369308472, "learning_rate": 1.8004868687285556e-05, "loss": 1.611244559288025, "num_input_tokens_seen": 63323476, "step": 970, "train_runtime": 21184.7592, "train_tokens_per_second": 2989.105 }, { "epoch": 0.6166058104461025, "grad_norm": 1.076586127281189, "learning_rate": 1.8000879380004156e-05, "loss": 1.5876675844192505, "num_input_tokens_seen": 63388876, "step": 971, "train_runtime": 21206.0679, "train_tokens_per_second": 2989.186 }, { "epoch": 0.6172408318780759, "grad_norm": 1.2315163612365723, "learning_rate": 1.79968865312371e-05, "loss": 1.6396325826644897, "num_input_tokens_seen": 63454348, "step": 972, "train_runtime": 21228.2224, "train_tokens_per_second": 2989.15 }, { "epoch": 0.6178758533100492, "grad_norm": 1.1844291687011719, "learning_rate": 1.7992890142751775e-05, "loss": 1.6401664018630981, "num_input_tokens_seen": 63519867, "step": 973, "train_runtime": 21249.7195, "train_tokens_per_second": 2989.21 }, { "epoch": 0.6185108747420226, "grad_norm": 1.1418700218200684, "learning_rate": 1.7988890216317127e-05, "loss": 1.549231767654419, "num_input_tokens_seen": 63585263, "step": 974, "train_runtime": 21271.3135, "train_tokens_per_second": 2989.249 }, { "epoch": 0.6191458961739958, "grad_norm": 1.3555583953857422, "learning_rate": 1.798488675370367e-05, "loss": 1.686755657196045, "num_input_tokens_seen": 63650700, "step": 975, "train_runtime": 21292.4656, "train_tokens_per_second": 2989.353 }, { "epoch": 0.6197809176059692, "grad_norm": 1.2069623470306396, "learning_rate": 1.798087975668349e-05, "loss": 1.653988003730774, "num_input_tokens_seen": 63716231, "step": 976, "train_runtime": 21314.8479, "train_tokens_per_second": 2989.289 }, { "epoch": 0.6204159390379426, "grad_norm": 1.210541009902954, "learning_rate": 1.7976869227030226e-05, "loss": 1.8445706367492676, "num_input_tokens_seen": 63781753, "step": 977, "train_runtime": 21337.1375, "train_tokens_per_second": 2989.237 }, { "epoch": 0.6210509604699158, "grad_norm": 1.2466294765472412, "learning_rate": 1.797285516651909e-05, "loss": 1.5081185102462769, "num_input_tokens_seen": 63847200, "step": 978, "train_runtime": 21357.3134, "train_tokens_per_second": 2989.477 }, { "epoch": 0.6216859819018892, "grad_norm": 1.2948142290115356, "learning_rate": 1.7968837576926857e-05, "loss": 1.7094684839248657, "num_input_tokens_seen": 63912727, "step": 979, "train_runtime": 21379.5764, "train_tokens_per_second": 2989.429 }, { "epoch": 0.6223210033338625, "grad_norm": 1.1065584421157837, "learning_rate": 1.796481646003186e-05, "loss": 1.6455168724060059, "num_input_tokens_seen": 63978133, "step": 980, "train_runtime": 21400.3762, "train_tokens_per_second": 2989.58 }, { "epoch": 0.6229560247658359, "grad_norm": 1.2643057107925415, "learning_rate": 1.7960791817613987e-05, "loss": 2.011103630065918, "num_input_tokens_seen": 64043621, "step": 981, "train_runtime": 21423.0692, "train_tokens_per_second": 2989.47 }, { "epoch": 0.6235910461978091, "grad_norm": 1.1102105379104614, "learning_rate": 1.7956763651454703e-05, "loss": 1.5162402391433716, "num_input_tokens_seen": 64108990, "step": 982, "train_runtime": 21444.0871, "train_tokens_per_second": 2989.588 }, { "epoch": 0.6242260676297825, "grad_norm": 1.2584738731384277, "learning_rate": 1.795273196333702e-05, "loss": 1.6323060989379883, "num_input_tokens_seen": 64174434, "step": 983, "train_runtime": 21465.6133, "train_tokens_per_second": 2989.639 }, { "epoch": 0.6248610890617559, "grad_norm": 1.1731526851654053, "learning_rate": 1.7948696755045514e-05, "loss": 1.5967230796813965, "num_input_tokens_seen": 64239863, "step": 984, "train_runtime": 21486.5201, "train_tokens_per_second": 2989.775 }, { "epoch": 0.6254961104937292, "grad_norm": 1.0501291751861572, "learning_rate": 1.7944658028366313e-05, "loss": 1.5331518650054932, "num_input_tokens_seen": 64305285, "step": 985, "train_runtime": 21507.2865, "train_tokens_per_second": 2989.93 }, { "epoch": 0.6261311319257025, "grad_norm": 1.3055322170257568, "learning_rate": 1.7940615785087114e-05, "loss": 1.5567684173583984, "num_input_tokens_seen": 64370791, "step": 986, "train_runtime": 21528.4778, "train_tokens_per_second": 2990.03 }, { "epoch": 0.6267661533576758, "grad_norm": 1.2840485572814941, "learning_rate": 1.7936570026997158e-05, "loss": 1.8314558267593384, "num_input_tokens_seen": 64436225, "step": 987, "train_runtime": 21549.8485, "train_tokens_per_second": 2990.101 }, { "epoch": 0.6274011747896492, "grad_norm": 1.0825494527816772, "learning_rate": 1.7932520755887248e-05, "loss": 1.5874052047729492, "num_input_tokens_seen": 64501737, "step": 988, "train_runtime": 21571.7415, "train_tokens_per_second": 2990.103 }, { "epoch": 0.6280361962216224, "grad_norm": 1.2676244974136353, "learning_rate": 1.7928467973549745e-05, "loss": 1.6911749839782715, "num_input_tokens_seen": 64567245, "step": 989, "train_runtime": 21593.8139, "train_tokens_per_second": 2990.081 }, { "epoch": 0.6286712176535958, "grad_norm": 1.2345248460769653, "learning_rate": 1.7924411681778558e-05, "loss": 1.6137458086013794, "num_input_tokens_seen": 64632661, "step": 990, "train_runtime": 21615.7881, "train_tokens_per_second": 2990.067 }, { "epoch": 0.6293062390855692, "grad_norm": 1.256809115409851, "learning_rate": 1.7920351882369154e-05, "loss": 1.7635653018951416, "num_input_tokens_seen": 64698144, "step": 991, "train_runtime": 21637.0851, "train_tokens_per_second": 2990.151 }, { "epoch": 0.6299412605175425, "grad_norm": 1.1464389562606812, "learning_rate": 1.7916288577118547e-05, "loss": 1.562330961227417, "num_input_tokens_seen": 64763657, "step": 992, "train_runtime": 21658.7268, "train_tokens_per_second": 2990.188 }, { "epoch": 0.6305762819495158, "grad_norm": 1.162100911140442, "learning_rate": 1.791222176782531e-05, "loss": 1.5404597520828247, "num_input_tokens_seen": 64829187, "step": 993, "train_runtime": 21679.7821, "train_tokens_per_second": 2990.306 }, { "epoch": 0.6312113033814891, "grad_norm": 1.2966784238815308, "learning_rate": 1.7908151456289562e-05, "loss": 1.4936747550964355, "num_input_tokens_seen": 64892623, "step": 994, "train_runtime": 21700.524, "train_tokens_per_second": 2990.371 }, { "epoch": 0.6318463248134625, "grad_norm": 1.2895137071609497, "learning_rate": 1.7904077644312973e-05, "loss": 1.5271466970443726, "num_input_tokens_seen": 64958135, "step": 995, "train_runtime": 21721.8125, "train_tokens_per_second": 2990.456 }, { "epoch": 0.6324813462454358, "grad_norm": 1.1758875846862793, "learning_rate": 1.7900000333698765e-05, "loss": 1.569777011871338, "num_input_tokens_seen": 65023539, "step": 996, "train_runtime": 21742.7542, "train_tokens_per_second": 2990.584 }, { "epoch": 0.6331163676774091, "grad_norm": 1.3747013807296753, "learning_rate": 1.7895919526251705e-05, "loss": 1.7706882953643799, "num_input_tokens_seen": 65089012, "step": 997, "train_runtime": 21764.9871, "train_tokens_per_second": 2990.538 }, { "epoch": 0.6337513891093824, "grad_norm": 1.1068410873413086, "learning_rate": 1.789183522377811e-05, "loss": 1.5057177543640137, "num_input_tokens_seen": 65154536, "step": 998, "train_runtime": 21786.2382, "train_tokens_per_second": 2990.628 }, { "epoch": 0.6343864105413558, "grad_norm": 1.2707980871200562, "learning_rate": 1.7887747428085847e-05, "loss": 1.5859661102294922, "num_input_tokens_seen": 65220018, "step": 999, "train_runtime": 21807.4953, "train_tokens_per_second": 2990.716 }, { "epoch": 0.635021431973329, "grad_norm": 1.1370445489883423, "learning_rate": 1.788365614098432e-05, "loss": 1.5074493885040283, "num_input_tokens_seen": 65285456, "step": 1000, "train_runtime": 21828.7322, "train_tokens_per_second": 2990.804 }, { "epoch": 0.635021431973329, "eval_loss": 1.5744514465332031, "eval_runtime": 12.9087, "eval_samples_per_second": 1.782, "eval_steps_per_second": 0.93, "num_input_tokens_seen": 65285456, "step": 1000 }, { "epoch": 0.6356564534053024, "grad_norm": 1.4081034660339355, "learning_rate": 1.7879561364284487e-05, "loss": 1.6138274669647217, "num_input_tokens_seen": 65350956, "step": 1001, "train_runtime": 21901.0725, "train_tokens_per_second": 2983.916 }, { "epoch": 0.6362914748372758, "grad_norm": 1.373618721961975, "learning_rate": 1.7875463099798846e-05, "loss": 1.7973756790161133, "num_input_tokens_seen": 65416395, "step": 1002, "train_runtime": 21923.4384, "train_tokens_per_second": 2983.857 }, { "epoch": 0.6369264962692491, "grad_norm": 1.1985870599746704, "learning_rate": 1.7871361349341446e-05, "loss": 1.788582682609558, "num_input_tokens_seen": 65478522, "step": 1003, "train_runtime": 21943.5924, "train_tokens_per_second": 2983.947 }, { "epoch": 0.6375615177012224, "grad_norm": 1.1241302490234375, "learning_rate": 1.786725611472787e-05, "loss": 1.51654851436615, "num_input_tokens_seen": 65543956, "step": 1004, "train_runtime": 21964.1093, "train_tokens_per_second": 2984.139 }, { "epoch": 0.6381965391331957, "grad_norm": 1.2836878299713135, "learning_rate": 1.786314739777524e-05, "loss": 1.8144843578338623, "num_input_tokens_seen": 65609464, "step": 1005, "train_runtime": 21985.9204, "train_tokens_per_second": 2984.158 }, { "epoch": 0.6388315605651691, "grad_norm": 1.359499216079712, "learning_rate": 1.7859035200302244e-05, "loss": 1.6967709064483643, "num_input_tokens_seen": 65674937, "step": 1006, "train_runtime": 22007.5595, "train_tokens_per_second": 2984.199 }, { "epoch": 0.6394665819971425, "grad_norm": 1.2385913133621216, "learning_rate": 1.7854919524129076e-05, "loss": 1.758057951927185, "num_input_tokens_seen": 65740468, "step": 1007, "train_runtime": 22029.3957, "train_tokens_per_second": 2984.216 }, { "epoch": 0.6401016034291157, "grad_norm": 1.1557406187057495, "learning_rate": 1.7850800371077496e-05, "loss": 1.5375442504882812, "num_input_tokens_seen": 65805907, "step": 1008, "train_runtime": 22050.9192, "train_tokens_per_second": 2984.27 }, { "epoch": 0.6407366248610891, "grad_norm": 1.2048234939575195, "learning_rate": 1.7846677742970793e-05, "loss": 1.5736852884292603, "num_input_tokens_seen": 65871318, "step": 1009, "train_runtime": 22072.6671, "train_tokens_per_second": 2984.294 }, { "epoch": 0.6413716462930624, "grad_norm": 1.160200595855713, "learning_rate": 1.784255164163379e-05, "loss": 1.3823130130767822, "num_input_tokens_seen": 65936769, "step": 1010, "train_runtime": 22093.5549, "train_tokens_per_second": 2984.435 }, { "epoch": 0.6420066677250357, "grad_norm": 1.220790147781372, "learning_rate": 1.7838422068892854e-05, "loss": 1.6765527725219727, "num_input_tokens_seen": 66002282, "step": 1011, "train_runtime": 22114.9448, "train_tokens_per_second": 2984.51 }, { "epoch": 0.642641689157009, "grad_norm": 1.271561622619629, "learning_rate": 1.7834289026575892e-05, "loss": 1.7238364219665527, "num_input_tokens_seen": 66067607, "step": 1012, "train_runtime": 22136.3527, "train_tokens_per_second": 2984.575 }, { "epoch": 0.6432767105889824, "grad_norm": 1.2901325225830078, "learning_rate": 1.7830152516512336e-05, "loss": 1.6525951623916626, "num_input_tokens_seen": 66132974, "step": 1013, "train_runtime": 22157.6625, "train_tokens_per_second": 2984.655 }, { "epoch": 0.6439117320209558, "grad_norm": 1.2309448719024658, "learning_rate": 1.782601254053316e-05, "loss": 1.5341049432754517, "num_input_tokens_seen": 66198436, "step": 1014, "train_runtime": 22179.3966, "train_tokens_per_second": 2984.682 }, { "epoch": 0.644546753452929, "grad_norm": 1.2278183698654175, "learning_rate": 1.7821869100470872e-05, "loss": 1.5489648580551147, "num_input_tokens_seen": 66263841, "step": 1015, "train_runtime": 22200.6081, "train_tokens_per_second": 2984.776 }, { "epoch": 0.6451817748849024, "grad_norm": 1.2809088230133057, "learning_rate": 1.781772219815951e-05, "loss": 1.7674946784973145, "num_input_tokens_seen": 66329307, "step": 1016, "train_runtime": 22221.3922, "train_tokens_per_second": 2984.93 }, { "epoch": 0.6458167963168757, "grad_norm": 1.4474482536315918, "learning_rate": 1.781357183543465e-05, "loss": 1.7452384233474731, "num_input_tokens_seen": 66394783, "step": 1017, "train_runtime": 22242.6159, "train_tokens_per_second": 2985.026 }, { "epoch": 0.6464518177488491, "grad_norm": 1.1526806354522705, "learning_rate": 1.7809418014133394e-05, "loss": 1.5927096605300903, "num_input_tokens_seen": 66460231, "step": 1018, "train_runtime": 22263.0941, "train_tokens_per_second": 2985.22 }, { "epoch": 0.6470868391808223, "grad_norm": 1.2098994255065918, "learning_rate": 1.780526073609438e-05, "loss": 1.7357258796691895, "num_input_tokens_seen": 66525685, "step": 1019, "train_runtime": 22284.6316, "train_tokens_per_second": 2985.272 }, { "epoch": 0.6477218606127957, "grad_norm": 1.2825514078140259, "learning_rate": 1.7801100003157764e-05, "loss": 1.8544420003890991, "num_input_tokens_seen": 66590972, "step": 1020, "train_runtime": 22305.7278, "train_tokens_per_second": 2985.375 }, { "epoch": 0.648356882044769, "grad_norm": 1.036507248878479, "learning_rate": 1.7796935817165252e-05, "loss": 1.4495893716812134, "num_input_tokens_seen": 66656446, "step": 1021, "train_runtime": 22326.5576, "train_tokens_per_second": 2985.523 }, { "epoch": 0.6489919034767423, "grad_norm": 1.247038722038269, "learning_rate": 1.779276817996006e-05, "loss": 1.5942633152008057, "num_input_tokens_seen": 66721887, "step": 1022, "train_runtime": 22348.6798, "train_tokens_per_second": 2985.496 }, { "epoch": 0.6496269249087157, "grad_norm": 1.1716387271881104, "learning_rate": 1.7788597093386944e-05, "loss": 1.5590133666992188, "num_input_tokens_seen": 66787395, "step": 1023, "train_runtime": 22370.143, "train_tokens_per_second": 2985.56 }, { "epoch": 0.650261946340689, "grad_norm": 1.2463817596435547, "learning_rate": 1.7784422559292174e-05, "loss": 1.7219675779342651, "num_input_tokens_seen": 66852914, "step": 1024, "train_runtime": 22391.9571, "train_tokens_per_second": 2985.577 }, { "epoch": 0.6508969677726624, "grad_norm": 1.256004810333252, "learning_rate": 1.7780244579523564e-05, "loss": 1.7404109239578247, "num_input_tokens_seen": 66918382, "step": 1025, "train_runtime": 22413.3271, "train_tokens_per_second": 2985.651 }, { "epoch": 0.6515319892046356, "grad_norm": 1.3631622791290283, "learning_rate": 1.7776063155930434e-05, "loss": 1.4622517824172974, "num_input_tokens_seen": 66983747, "step": 1026, "train_runtime": 22434.0855, "train_tokens_per_second": 2985.802 }, { "epoch": 0.652167010636609, "grad_norm": 1.171278953552246, "learning_rate": 1.7771878290363638e-05, "loss": 1.6277798414230347, "num_input_tokens_seen": 67049255, "step": 1027, "train_runtime": 22455.2295, "train_tokens_per_second": 2985.908 }, { "epoch": 0.6528020320685823, "grad_norm": 1.162467122077942, "learning_rate": 1.7767689984675556e-05, "loss": 1.5448241233825684, "num_input_tokens_seen": 67114779, "step": 1028, "train_runtime": 22475.9433, "train_tokens_per_second": 2986.072 }, { "epoch": 0.6534370535005557, "grad_norm": 1.2189198732376099, "learning_rate": 1.7763498240720084e-05, "loss": 1.6949117183685303, "num_input_tokens_seen": 67180231, "step": 1029, "train_runtime": 22496.7693, "train_tokens_per_second": 2986.217 }, { "epoch": 0.654072074932529, "grad_norm": 1.2694834470748901, "learning_rate": 1.7759303060352645e-05, "loss": 1.7174391746520996, "num_input_tokens_seen": 67245765, "step": 1030, "train_runtime": 22518.549, "train_tokens_per_second": 2986.239 }, { "epoch": 0.6547070963645023, "grad_norm": 1.2671648263931274, "learning_rate": 1.775510444543018e-05, "loss": 1.6977587938308716, "num_input_tokens_seen": 67311151, "step": 1031, "train_runtime": 22539.8964, "train_tokens_per_second": 2986.311 }, { "epoch": 0.6553421177964757, "grad_norm": 1.3021472692489624, "learning_rate": 1.7750902397811157e-05, "loss": 1.6371755599975586, "num_input_tokens_seen": 67376617, "step": 1032, "train_runtime": 22560.4993, "train_tokens_per_second": 2986.486 }, { "epoch": 0.6559771392284489, "grad_norm": 1.1624938249588013, "learning_rate": 1.7746696919355547e-05, "loss": 1.562943696975708, "num_input_tokens_seen": 67442033, "step": 1033, "train_runtime": 22582.1102, "train_tokens_per_second": 2986.525 }, { "epoch": 0.6566121606604223, "grad_norm": 1.266553521156311, "learning_rate": 1.7742488011924857e-05, "loss": 1.7743167877197266, "num_input_tokens_seen": 67507481, "step": 1034, "train_runtime": 22602.9644, "train_tokens_per_second": 2986.665 }, { "epoch": 0.6572471820923956, "grad_norm": 1.2343145608901978, "learning_rate": 1.773827567738211e-05, "loss": 1.5097501277923584, "num_input_tokens_seen": 67573000, "step": 1035, "train_runtime": 22624.1758, "train_tokens_per_second": 2986.761 }, { "epoch": 0.657882203524369, "grad_norm": 1.2172027826309204, "learning_rate": 1.7734059917591837e-05, "loss": 1.6490685939788818, "num_input_tokens_seen": 67638388, "step": 1036, "train_runtime": 22645.9365, "train_tokens_per_second": 2986.778 }, { "epoch": 0.6585172249563422, "grad_norm": 1.17335045337677, "learning_rate": 1.7729840734420087e-05, "loss": 1.5883402824401855, "num_input_tokens_seen": 67703898, "step": 1037, "train_runtime": 22666.4751, "train_tokens_per_second": 2986.962 }, { "epoch": 0.6591522463883156, "grad_norm": 1.1863939762115479, "learning_rate": 1.7725618129734427e-05, "loss": 1.8019345998764038, "num_input_tokens_seen": 67769348, "step": 1038, "train_runtime": 22688.4697, "train_tokens_per_second": 2986.951 }, { "epoch": 0.659787267820289, "grad_norm": 1.2872259616851807, "learning_rate": 1.7721392105403944e-05, "loss": 1.5076353549957275, "num_input_tokens_seen": 67832654, "step": 1039, "train_runtime": 22708.4938, "train_tokens_per_second": 2987.105 }, { "epoch": 0.6604222892522623, "grad_norm": 1.2195680141448975, "learning_rate": 1.7717162663299226e-05, "loss": 1.6317731142044067, "num_input_tokens_seen": 67898085, "step": 1040, "train_runtime": 22729.4461, "train_tokens_per_second": 2987.23 }, { "epoch": 0.6610573106842356, "grad_norm": 1.1410696506500244, "learning_rate": 1.7712929805292387e-05, "loss": 1.5281741619110107, "num_input_tokens_seen": 67963550, "step": 1041, "train_runtime": 22750.9505, "train_tokens_per_second": 2987.284 }, { "epoch": 0.6616923321162089, "grad_norm": 1.2286241054534912, "learning_rate": 1.770869353325704e-05, "loss": 1.6099506616592407, "num_input_tokens_seen": 68028891, "step": 1042, "train_runtime": 22771.9213, "train_tokens_per_second": 2987.402 }, { "epoch": 0.6623273535481823, "grad_norm": 1.1716939210891724, "learning_rate": 1.770445384906832e-05, "loss": 1.5082722902297974, "num_input_tokens_seen": 68094336, "step": 1043, "train_runtime": 22792.8436, "train_tokens_per_second": 2987.531 }, { "epoch": 0.6629623749801555, "grad_norm": 1.222658634185791, "learning_rate": 1.770021075460287e-05, "loss": 1.567388653755188, "num_input_tokens_seen": 68159765, "step": 1044, "train_runtime": 22814.4042, "train_tokens_per_second": 2987.576 }, { "epoch": 0.6635973964121289, "grad_norm": 1.287484049797058, "learning_rate": 1.769596425173884e-05, "loss": 1.6032967567443848, "num_input_tokens_seen": 68225171, "step": 1045, "train_runtime": 22835.1505, "train_tokens_per_second": 2987.726 }, { "epoch": 0.6642324178441023, "grad_norm": 1.1729416847229004, "learning_rate": 1.7691714342355884e-05, "loss": 1.5608999729156494, "num_input_tokens_seen": 68290632, "step": 1046, "train_runtime": 22857.1337, "train_tokens_per_second": 2987.716 }, { "epoch": 0.6648674392760756, "grad_norm": 1.1071566343307495, "learning_rate": 1.768746102833518e-05, "loss": 1.617104411125183, "num_input_tokens_seen": 68356158, "step": 1047, "train_runtime": 22878.2311, "train_tokens_per_second": 2987.825 }, { "epoch": 0.6655024607080489, "grad_norm": 1.1854281425476074, "learning_rate": 1.7683204311559394e-05, "loss": 1.6395562887191772, "num_input_tokens_seen": 68421638, "step": 1048, "train_runtime": 22899.2021, "train_tokens_per_second": 2987.949 }, { "epoch": 0.6661374821400222, "grad_norm": 1.2193994522094727, "learning_rate": 1.7678944193912704e-05, "loss": 1.492754340171814, "num_input_tokens_seen": 68487163, "step": 1049, "train_runtime": 22920.2787, "train_tokens_per_second": 2988.06 }, { "epoch": 0.6667725035719956, "grad_norm": 1.3334109783172607, "learning_rate": 1.7674680677280803e-05, "loss": 1.7001582384109497, "num_input_tokens_seen": 68552557, "step": 1050, "train_runtime": 22941.7013, "train_tokens_per_second": 2988.12 }, { "epoch": 0.6674075250039689, "grad_norm": 1.2389566898345947, "learning_rate": 1.767041376355088e-05, "loss": 1.5771501064300537, "num_input_tokens_seen": 68618076, "step": 1051, "train_runtime": 22962.7004, "train_tokens_per_second": 2988.241 }, { "epoch": 0.6680425464359422, "grad_norm": 1.3194326162338257, "learning_rate": 1.766614345461163e-05, "loss": 1.7201976776123047, "num_input_tokens_seen": 68683577, "step": 1052, "train_runtime": 22983.7834, "train_tokens_per_second": 2988.349 }, { "epoch": 0.6686775678679155, "grad_norm": 1.4019582271575928, "learning_rate": 1.7661869752353244e-05, "loss": 1.732747197151184, "num_input_tokens_seen": 68749069, "step": 1053, "train_runtime": 23004.9966, "train_tokens_per_second": 2988.441 }, { "epoch": 0.6693125892998889, "grad_norm": 1.197283148765564, "learning_rate": 1.7657592658667426e-05, "loss": 1.5349360704421997, "num_input_tokens_seen": 68814559, "step": 1054, "train_runtime": 23025.6443, "train_tokens_per_second": 2988.605 }, { "epoch": 0.6699476107318622, "grad_norm": 1.2025116682052612, "learning_rate": 1.7653312175447376e-05, "loss": 1.6162474155426025, "num_input_tokens_seen": 68879975, "step": 1055, "train_runtime": 23047.0801, "train_tokens_per_second": 2988.664 }, { "epoch": 0.6705826321638355, "grad_norm": 1.2250332832336426, "learning_rate": 1.7649028304587793e-05, "loss": 1.7453131675720215, "num_input_tokens_seen": 68945357, "step": 1056, "train_runtime": 23069.4016, "train_tokens_per_second": 2988.606 }, { "epoch": 0.6712176535958089, "grad_norm": 1.2833397388458252, "learning_rate": 1.764474104798488e-05, "loss": 1.7759623527526855, "num_input_tokens_seen": 69010840, "step": 1057, "train_runtime": 23091.0627, "train_tokens_per_second": 2988.639 }, { "epoch": 0.6718526750277822, "grad_norm": 1.131779670715332, "learning_rate": 1.764045040753633e-05, "loss": 1.606437087059021, "num_input_tokens_seen": 69076341, "step": 1058, "train_runtime": 23111.742, "train_tokens_per_second": 2988.799 }, { "epoch": 0.6724876964597555, "grad_norm": 1.187504529953003, "learning_rate": 1.7636156385141346e-05, "loss": 1.623416543006897, "num_input_tokens_seen": 69141793, "step": 1059, "train_runtime": 23132.7455, "train_tokens_per_second": 2988.914 }, { "epoch": 0.6731227178917288, "grad_norm": 1.2265989780426025, "learning_rate": 1.7631858982700613e-05, "loss": 1.6538385152816772, "num_input_tokens_seen": 69207247, "step": 1060, "train_runtime": 23153.7807, "train_tokens_per_second": 2989.026 }, { "epoch": 0.6737577393237022, "grad_norm": 1.134220004081726, "learning_rate": 1.7627558202116327e-05, "loss": 1.5440289974212646, "num_input_tokens_seen": 69272655, "step": 1061, "train_runtime": 23174.4024, "train_tokens_per_second": 2989.188 }, { "epoch": 0.6743927607556756, "grad_norm": 1.1590619087219238, "learning_rate": 1.7623254045292175e-05, "loss": 1.5076624155044556, "num_input_tokens_seen": 69338036, "step": 1062, "train_runtime": 23195.4755, "train_tokens_per_second": 2989.291 }, { "epoch": 0.6750277821876488, "grad_norm": 1.2167314291000366, "learning_rate": 1.761894651413333e-05, "loss": 1.6847820281982422, "num_input_tokens_seen": 69403038, "step": 1063, "train_runtime": 23216.2477, "train_tokens_per_second": 2989.417 }, { "epoch": 0.6756628036196222, "grad_norm": 1.2278733253479004, "learning_rate": 1.761463561054647e-05, "loss": 1.6633338928222656, "num_input_tokens_seen": 69468553, "step": 1064, "train_runtime": 23237.2858, "train_tokens_per_second": 2989.53 }, { "epoch": 0.6762978250515955, "grad_norm": 1.3056930303573608, "learning_rate": 1.7610321336439756e-05, "loss": 1.7029366493225098, "num_input_tokens_seen": 69534018, "step": 1065, "train_runtime": 23259.4734, "train_tokens_per_second": 2989.492 }, { "epoch": 0.6769328464835688, "grad_norm": 1.213378667831421, "learning_rate": 1.7606003693722845e-05, "loss": 1.5696043968200684, "num_input_tokens_seen": 69599485, "step": 1066, "train_runtime": 23280.9469, "train_tokens_per_second": 2989.547 }, { "epoch": 0.6775678679155421, "grad_norm": 1.4373269081115723, "learning_rate": 1.7601682684306895e-05, "loss": 1.813807725906372, "num_input_tokens_seen": 69665007, "step": 1067, "train_runtime": 23302.9418, "train_tokens_per_second": 2989.537 }, { "epoch": 0.6782028893475155, "grad_norm": 1.1345027685165405, "learning_rate": 1.7597358310104536e-05, "loss": 1.4875801801681519, "num_input_tokens_seen": 69730465, "step": 1068, "train_runtime": 23323.656, "train_tokens_per_second": 2989.688 }, { "epoch": 0.6788379107794889, "grad_norm": 1.3063995838165283, "learning_rate": 1.7593030573029896e-05, "loss": 1.9003591537475586, "num_input_tokens_seen": 69795918, "step": 1069, "train_runtime": 23345.9212, "train_tokens_per_second": 2989.641 }, { "epoch": 0.6794729322114621, "grad_norm": 1.2104148864746094, "learning_rate": 1.7588699474998598e-05, "loss": 1.59560227394104, "num_input_tokens_seen": 69861322, "step": 1070, "train_runtime": 23366.746, "train_tokens_per_second": 2989.775 }, { "epoch": 0.6801079536434355, "grad_norm": 1.2709720134735107, "learning_rate": 1.758436501792774e-05, "loss": 1.7211076021194458, "num_input_tokens_seen": 69926763, "step": 1071, "train_runtime": 23387.2652, "train_tokens_per_second": 2989.95 }, { "epoch": 0.6807429750754088, "grad_norm": 1.342732548713684, "learning_rate": 1.7580027203735915e-05, "loss": 1.7233667373657227, "num_input_tokens_seen": 69992272, "step": 1072, "train_runtime": 23409.0698, "train_tokens_per_second": 2989.964 }, { "epoch": 0.6813779965073822, "grad_norm": 1.1021493673324585, "learning_rate": 1.7575686034343205e-05, "loss": 1.5838592052459717, "num_input_tokens_seen": 70057680, "step": 1073, "train_runtime": 23430.6505, "train_tokens_per_second": 2990.001 }, { "epoch": 0.6820130179393554, "grad_norm": 1.168402910232544, "learning_rate": 1.7571341511671164e-05, "loss": 1.6191195249557495, "num_input_tokens_seen": 70123110, "step": 1074, "train_runtime": 23452.2199, "train_tokens_per_second": 2990.041 }, { "epoch": 0.6826480393713288, "grad_norm": 1.2107210159301758, "learning_rate": 1.756699363764285e-05, "loss": 1.5360316038131714, "num_input_tokens_seen": 70188483, "step": 1075, "train_runtime": 23473.2078, "train_tokens_per_second": 2990.153 }, { "epoch": 0.6832830608033021, "grad_norm": 1.1719880104064941, "learning_rate": 1.7562642414182782e-05, "loss": 1.6717877388000488, "num_input_tokens_seen": 70253965, "step": 1076, "train_runtime": 23494.2844, "train_tokens_per_second": 2990.258 }, { "epoch": 0.6839180822352754, "grad_norm": 1.2214454412460327, "learning_rate": 1.7558287843216978e-05, "loss": 1.545119047164917, "num_input_tokens_seen": 70312938, "step": 1077, "train_runtime": 23513.3615, "train_tokens_per_second": 2990.34 }, { "epoch": 0.6845531036672488, "grad_norm": 1.2090907096862793, "learning_rate": 1.755392992667293e-05, "loss": 1.5406798124313354, "num_input_tokens_seen": 70378382, "step": 1078, "train_runtime": 23534.4351, "train_tokens_per_second": 2990.443 }, { "epoch": 0.6851881250992221, "grad_norm": 1.100635051727295, "learning_rate": 1.754956866647962e-05, "loss": 1.6171818971633911, "num_input_tokens_seen": 70443890, "step": 1079, "train_runtime": 23555.8933, "train_tokens_per_second": 2990.5 }, { "epoch": 0.6858231465311955, "grad_norm": 1.0422444343566895, "learning_rate": 1.7545204064567496e-05, "loss": 1.3619613647460938, "num_input_tokens_seen": 70509237, "step": 1080, "train_runtime": 23576.0855, "train_tokens_per_second": 2990.71 }, { "epoch": 0.6864581679631687, "grad_norm": 1.2996811866760254, "learning_rate": 1.7540836122868494e-05, "loss": 1.7817444801330566, "num_input_tokens_seen": 70574646, "step": 1081, "train_runtime": 23598.3876, "train_tokens_per_second": 2990.655 }, { "epoch": 0.6870931893951421, "grad_norm": 1.2253295183181763, "learning_rate": 1.7536464843316027e-05, "loss": 1.70640230178833, "num_input_tokens_seen": 70640082, "step": 1082, "train_runtime": 23618.6738, "train_tokens_per_second": 2990.857 }, { "epoch": 0.6877282108271154, "grad_norm": 1.1654495000839233, "learning_rate": 1.753209022784499e-05, "loss": 1.6604387760162354, "num_input_tokens_seen": 70705584, "step": 1083, "train_runtime": 23640.1958, "train_tokens_per_second": 2990.905 }, { "epoch": 0.6883632322590888, "grad_norm": 1.2590056657791138, "learning_rate": 1.752771227839174e-05, "loss": 1.5105881690979004, "num_input_tokens_seen": 70766358, "step": 1084, "train_runtime": 23659.925, "train_tokens_per_second": 2990.98 }, { "epoch": 0.688998253691062, "grad_norm": 1.191750407218933, "learning_rate": 1.7523330996894134e-05, "loss": 1.6118115186691284, "num_input_tokens_seen": 70831861, "step": 1085, "train_runtime": 23681.8211, "train_tokens_per_second": 2990.98 }, { "epoch": 0.6896332751230354, "grad_norm": 1.0991040468215942, "learning_rate": 1.7518946385291474e-05, "loss": 1.475611686706543, "num_input_tokens_seen": 70897284, "step": 1086, "train_runtime": 23702.664, "train_tokens_per_second": 2991.11 }, { "epoch": 0.6902682965550088, "grad_norm": 1.1669716835021973, "learning_rate": 1.751455844552456e-05, "loss": 1.5919618606567383, "num_input_tokens_seen": 70962750, "step": 1087, "train_runtime": 23724.0194, "train_tokens_per_second": 2991.177 }, { "epoch": 0.690903317986982, "grad_norm": 1.2294353246688843, "learning_rate": 1.751016717953566e-05, "loss": 1.6597485542297363, "num_input_tokens_seen": 71028238, "step": 1088, "train_runtime": 23745.3605, "train_tokens_per_second": 2991.247 }, { "epoch": 0.6915383394189554, "grad_norm": 1.185850739479065, "learning_rate": 1.75057725892685e-05, "loss": 1.5685203075408936, "num_input_tokens_seen": 71093732, "step": 1089, "train_runtime": 23766.7589, "train_tokens_per_second": 2991.31 }, { "epoch": 0.6921733608509287, "grad_norm": 1.2266243696212769, "learning_rate": 1.75013746766683e-05, "loss": 1.7553515434265137, "num_input_tokens_seen": 71159127, "step": 1090, "train_runtime": 23787.7971, "train_tokens_per_second": 2991.413 }, { "epoch": 0.6928083822829021, "grad_norm": 1.1773309707641602, "learning_rate": 1.749697344368173e-05, "loss": 1.5622196197509766, "num_input_tokens_seen": 71222430, "step": 1091, "train_runtime": 23808.0541, "train_tokens_per_second": 2991.527 }, { "epoch": 0.6934434037148753, "grad_norm": 1.2276185750961304, "learning_rate": 1.7492568892256946e-05, "loss": 1.7228922843933105, "num_input_tokens_seen": 71287942, "step": 1092, "train_runtime": 23829.9039, "train_tokens_per_second": 2991.533 }, { "epoch": 0.6940784251468487, "grad_norm": 1.2533584833145142, "learning_rate": 1.7488161024343564e-05, "loss": 1.7085745334625244, "num_input_tokens_seen": 71353390, "step": 1093, "train_runtime": 23851.3544, "train_tokens_per_second": 2991.587 }, { "epoch": 0.6947134465788221, "grad_norm": 1.1767328977584839, "learning_rate": 1.7483749841892664e-05, "loss": 1.763364315032959, "num_input_tokens_seen": 71418799, "step": 1094, "train_runtime": 23873.0963, "train_tokens_per_second": 2991.602 }, { "epoch": 0.6953484680107954, "grad_norm": 1.2864550352096558, "learning_rate": 1.7479335346856807e-05, "loss": 1.7044885158538818, "num_input_tokens_seen": 71484278, "step": 1095, "train_runtime": 23894.7944, "train_tokens_per_second": 2991.626 }, { "epoch": 0.6959834894427687, "grad_norm": 1.2417477369308472, "learning_rate": 1.7474917541190005e-05, "loss": 1.6381964683532715, "num_input_tokens_seen": 71549715, "step": 1096, "train_runtime": 23916.607, "train_tokens_per_second": 2991.633 }, { "epoch": 0.696618510874742, "grad_norm": 1.1731035709381104, "learning_rate": 1.7470496426847746e-05, "loss": 1.6449047327041626, "num_input_tokens_seen": 71615240, "step": 1097, "train_runtime": 23938.6996, "train_tokens_per_second": 2991.609 }, { "epoch": 0.6972535323067154, "grad_norm": 1.1643224954605103, "learning_rate": 1.7466072005786975e-05, "loss": 1.505788803100586, "num_input_tokens_seen": 71680754, "step": 1098, "train_runtime": 23960.1927, "train_tokens_per_second": 2991.66 }, { "epoch": 0.6978885537386886, "grad_norm": 1.1851141452789307, "learning_rate": 1.7461644279966113e-05, "loss": 1.7429203987121582, "num_input_tokens_seen": 71746260, "step": 1099, "train_runtime": 23981.798, "train_tokens_per_second": 2991.696 }, { "epoch": 0.698523575170662, "grad_norm": 1.2179996967315674, "learning_rate": 1.7457213251345028e-05, "loss": 1.587471842765808, "num_input_tokens_seen": 71811702, "step": 1100, "train_runtime": 24002.7516, "train_tokens_per_second": 2991.811 }, { "epoch": 0.698523575170662, "eval_loss": 1.5693105459213257, "eval_runtime": 12.9253, "eval_samples_per_second": 1.779, "eval_steps_per_second": 0.928, "num_input_tokens_seen": 71811702, "step": 1100 }, { "epoch": 0.6991585966026354, "grad_norm": 1.295261025428772, "learning_rate": 1.7452778921885062e-05, "loss": 1.5633983612060547, "num_input_tokens_seen": 71877129, "step": 1101, "train_runtime": 24072.7109, "train_tokens_per_second": 2985.834 }, { "epoch": 0.6997936180346087, "grad_norm": 1.2208771705627441, "learning_rate": 1.744834129354901e-05, "loss": 1.4800505638122559, "num_input_tokens_seen": 71942660, "step": 1102, "train_runtime": 24094.6089, "train_tokens_per_second": 2985.841 }, { "epoch": 0.700428639466582, "grad_norm": 1.6013885736465454, "learning_rate": 1.7443900368301134e-05, "loss": 1.7465744018554688, "num_input_tokens_seen": 72008080, "step": 1103, "train_runtime": 24116.7832, "train_tokens_per_second": 2985.808 }, { "epoch": 0.7010636608985553, "grad_norm": 1.2548054456710815, "learning_rate": 1.743945614810715e-05, "loss": 1.8370792865753174, "num_input_tokens_seen": 72073534, "step": 1104, "train_runtime": 24138.1702, "train_tokens_per_second": 2985.874 }, { "epoch": 0.7016986823305287, "grad_norm": 1.2381747961044312, "learning_rate": 1.7435008634934234e-05, "loss": 1.636812686920166, "num_input_tokens_seen": 72139035, "step": 1105, "train_runtime": 24159.6072, "train_tokens_per_second": 2985.936 }, { "epoch": 0.702333703762502, "grad_norm": 1.1529808044433594, "learning_rate": 1.7430557830751024e-05, "loss": 1.7126243114471436, "num_input_tokens_seen": 72204509, "step": 1106, "train_runtime": 24180.6524, "train_tokens_per_second": 2986.045 }, { "epoch": 0.7029687251944753, "grad_norm": 1.2222856283187866, "learning_rate": 1.7426103737527603e-05, "loss": 1.6573890447616577, "num_input_tokens_seen": 72270031, "step": 1107, "train_runtime": 24201.8084, "train_tokens_per_second": 2986.142 }, { "epoch": 0.7036037466264486, "grad_norm": 1.119737148284912, "learning_rate": 1.7421646357235524e-05, "loss": 1.5981706380844116, "num_input_tokens_seen": 72335529, "step": 1108, "train_runtime": 24223.7082, "train_tokens_per_second": 2986.146 }, { "epoch": 0.704238768058422, "grad_norm": 1.2408756017684937, "learning_rate": 1.7417185691847786e-05, "loss": 1.6356334686279297, "num_input_tokens_seen": 72400960, "step": 1109, "train_runtime": 24245.6433, "train_tokens_per_second": 2986.143 }, { "epoch": 0.7048737894903953, "grad_norm": 1.1145401000976562, "learning_rate": 1.7412721743338853e-05, "loss": 1.550475835800171, "num_input_tokens_seen": 72466474, "step": 1110, "train_runtime": 24266.884, "train_tokens_per_second": 2986.229 }, { "epoch": 0.7055088109223686, "grad_norm": 1.168805718421936, "learning_rate": 1.740825451368462e-05, "loss": 1.457287311553955, "num_input_tokens_seen": 72531995, "step": 1111, "train_runtime": 24287.5551, "train_tokens_per_second": 2986.385 }, { "epoch": 0.706143832354342, "grad_norm": 1.2099064588546753, "learning_rate": 1.7403784004862458e-05, "loss": 1.6360909938812256, "num_input_tokens_seen": 72597512, "step": 1112, "train_runtime": 24308.7006, "train_tokens_per_second": 2986.483 }, { "epoch": 0.7067788537863153, "grad_norm": 1.3281737565994263, "learning_rate": 1.7399310218851174e-05, "loss": 1.7166236639022827, "num_input_tokens_seen": 72663040, "step": 1113, "train_runtime": 24330.976, "train_tokens_per_second": 2986.442 }, { "epoch": 0.7074138752182886, "grad_norm": 1.1839128732681274, "learning_rate": 1.7394833157631038e-05, "loss": 1.5519146919250488, "num_input_tokens_seen": 72728524, "step": 1114, "train_runtime": 24352.7398, "train_tokens_per_second": 2986.462 }, { "epoch": 0.7080488966502619, "grad_norm": 1.235911250114441, "learning_rate": 1.739035282318376e-05, "loss": 1.5493528842926025, "num_input_tokens_seen": 72794046, "step": 1115, "train_runtime": 24374.8132, "train_tokens_per_second": 2986.445 }, { "epoch": 0.7086839180822353, "grad_norm": 1.2991691827774048, "learning_rate": 1.73858692174925e-05, "loss": 1.6848728656768799, "num_input_tokens_seen": 72859514, "step": 1116, "train_runtime": 24396.3505, "train_tokens_per_second": 2986.492 }, { "epoch": 0.7093189395142087, "grad_norm": 1.156447172164917, "learning_rate": 1.738138234254187e-05, "loss": 1.7153706550598145, "num_input_tokens_seen": 72924926, "step": 1117, "train_runtime": 24417.3276, "train_tokens_per_second": 2986.606 }, { "epoch": 0.7099539609461819, "grad_norm": 1.1663788557052612, "learning_rate": 1.737689220031793e-05, "loss": 1.7102993726730347, "num_input_tokens_seen": 72990453, "step": 1118, "train_runtime": 24438.7613, "train_tokens_per_second": 2986.667 }, { "epoch": 0.7105889823781553, "grad_norm": 1.2662683725357056, "learning_rate": 1.737239879280818e-05, "loss": 1.8382662534713745, "num_input_tokens_seen": 73055952, "step": 1119, "train_runtime": 24461.4139, "train_tokens_per_second": 2986.579 }, { "epoch": 0.7112240038101286, "grad_norm": 1.2842320203781128, "learning_rate": 1.7367902122001563e-05, "loss": 1.6834824085235596, "num_input_tokens_seen": 73121483, "step": 1120, "train_runtime": 24484.1418, "train_tokens_per_second": 2986.483 }, { "epoch": 0.7118590252421019, "grad_norm": 1.101065993309021, "learning_rate": 1.7363402189888482e-05, "loss": 1.5506384372711182, "num_input_tokens_seen": 73186987, "step": 1121, "train_runtime": 24505.0002, "train_tokens_per_second": 2986.614 }, { "epoch": 0.7124940466740752, "grad_norm": 1.212093472480774, "learning_rate": 1.735889899846077e-05, "loss": 1.5787973403930664, "num_input_tokens_seen": 73252483, "step": 1122, "train_runtime": 24525.4744, "train_tokens_per_second": 2986.792 }, { "epoch": 0.7131290681060486, "grad_norm": 1.1722640991210938, "learning_rate": 1.7354392549711704e-05, "loss": 1.6302618980407715, "num_input_tokens_seen": 73317950, "step": 1123, "train_runtime": 24546.312, "train_tokens_per_second": 2986.923 }, { "epoch": 0.713764089538022, "grad_norm": 1.198810338973999, "learning_rate": 1.734988284563601e-05, "loss": 1.718051791191101, "num_input_tokens_seen": 73383452, "step": 1124, "train_runtime": 24567.8942, "train_tokens_per_second": 2986.965 }, { "epoch": 0.7143991109699952, "grad_norm": 1.3587599992752075, "learning_rate": 1.734536988822985e-05, "loss": 1.5714460611343384, "num_input_tokens_seen": 73448961, "step": 1125, "train_runtime": 24590.2212, "train_tokens_per_second": 2986.917 }, { "epoch": 0.7150341324019686, "grad_norm": 1.236822485923767, "learning_rate": 1.7340853679490813e-05, "loss": 1.7903844118118286, "num_input_tokens_seen": 73514457, "step": 1126, "train_runtime": 24611.2923, "train_tokens_per_second": 2987.021 }, { "epoch": 0.7156691538339419, "grad_norm": 1.3578236103057861, "learning_rate": 1.733633422141796e-05, "loss": 1.8055593967437744, "num_input_tokens_seen": 73579967, "step": 1127, "train_runtime": 24632.902, "train_tokens_per_second": 2987.06 }, { "epoch": 0.7163041752659153, "grad_norm": 1.2027868032455444, "learning_rate": 1.733181151601176e-05, "loss": 1.7494920492172241, "num_input_tokens_seen": 73645414, "step": 1128, "train_runtime": 24654.5131, "train_tokens_per_second": 2987.097 }, { "epoch": 0.7169391966978885, "grad_norm": 1.2759559154510498, "learning_rate": 1.732728556527413e-05, "loss": 1.6936655044555664, "num_input_tokens_seen": 73710909, "step": 1129, "train_runtime": 24675.6032, "train_tokens_per_second": 2987.198 }, { "epoch": 0.7175742181298619, "grad_norm": 1.3704136610031128, "learning_rate": 1.7322756371208424e-05, "loss": 1.8719565868377686, "num_input_tokens_seen": 73776332, "step": 1130, "train_runtime": 24696.8878, "train_tokens_per_second": 2987.272 }, { "epoch": 0.7182092395618352, "grad_norm": 1.1437923908233643, "learning_rate": 1.7318223935819435e-05, "loss": 1.5957064628601074, "num_input_tokens_seen": 73841732, "step": 1131, "train_runtime": 24718.0991, "train_tokens_per_second": 2987.355 }, { "epoch": 0.7188442609938085, "grad_norm": 1.1600261926651, "learning_rate": 1.7313688261113383e-05, "loss": 1.585112452507019, "num_input_tokens_seen": 73907229, "step": 1132, "train_runtime": 24739.32, "train_tokens_per_second": 2987.44 }, { "epoch": 0.7194792824257819, "grad_norm": 1.1483548879623413, "learning_rate": 1.7309149349097925e-05, "loss": 1.5339149236679077, "num_input_tokens_seen": 73972714, "step": 1133, "train_runtime": 24761.0848, "train_tokens_per_second": 2987.459 }, { "epoch": 0.7201143038577552, "grad_norm": 1.1527099609375, "learning_rate": 1.7304607201782153e-05, "loss": 1.7859671115875244, "num_input_tokens_seen": 74038217, "step": 1134, "train_runtime": 24782.5324, "train_tokens_per_second": 2987.516 }, { "epoch": 0.7207493252897286, "grad_norm": 1.169255018234253, "learning_rate": 1.7300061821176593e-05, "loss": 1.651951789855957, "num_input_tokens_seen": 74103685, "step": 1135, "train_runtime": 24803.6692, "train_tokens_per_second": 2987.61 }, { "epoch": 0.7213843467217018, "grad_norm": 1.3222923278808594, "learning_rate": 1.729551320929319e-05, "loss": 1.8163373470306396, "num_input_tokens_seen": 74169133, "step": 1136, "train_runtime": 24825.3402, "train_tokens_per_second": 2987.638 }, { "epoch": 0.7220193681536752, "grad_norm": 1.1634544134140015, "learning_rate": 1.7290961368145338e-05, "loss": 1.5375972986221313, "num_input_tokens_seen": 74234612, "step": 1137, "train_runtime": 24846.9901, "train_tokens_per_second": 2987.67 }, { "epoch": 0.7226543895856485, "grad_norm": 1.1026252508163452, "learning_rate": 1.7286406299747847e-05, "loss": 1.5671879053115845, "num_input_tokens_seen": 74300113, "step": 1138, "train_runtime": 24867.7637, "train_tokens_per_second": 2987.808 }, { "epoch": 0.7232894110176219, "grad_norm": 1.1977182626724243, "learning_rate": 1.7281848006116956e-05, "loss": 1.6443982124328613, "num_input_tokens_seen": 74363798, "step": 1139, "train_runtime": 24888.1191, "train_tokens_per_second": 2987.924 }, { "epoch": 0.7239244324495951, "grad_norm": 1.1293811798095703, "learning_rate": 1.727728648927034e-05, "loss": 1.6159725189208984, "num_input_tokens_seen": 74429275, "step": 1140, "train_runtime": 24909.778, "train_tokens_per_second": 2987.954 }, { "epoch": 0.7245594538815685, "grad_norm": 1.2127673625946045, "learning_rate": 1.727272175122709e-05, "loss": 1.6393859386444092, "num_input_tokens_seen": 74494764, "step": 1141, "train_runtime": 24931.6266, "train_tokens_per_second": 2987.962 }, { "epoch": 0.7251944753135419, "grad_norm": 1.1108676195144653, "learning_rate": 1.7268153794007733e-05, "loss": 1.5870672464370728, "num_input_tokens_seen": 74560293, "step": 1142, "train_runtime": 24952.3775, "train_tokens_per_second": 2988.104 }, { "epoch": 0.7258294967455151, "grad_norm": 1.1701446771621704, "learning_rate": 1.7263582619634212e-05, "loss": 1.4773921966552734, "num_input_tokens_seen": 74625821, "step": 1143, "train_runtime": 24973.8685, "train_tokens_per_second": 2988.156 }, { "epoch": 0.7264645181774885, "grad_norm": 1.2904778718948364, "learning_rate": 1.7259008230129897e-05, "loss": 1.6860600709915161, "num_input_tokens_seen": 74691330, "step": 1144, "train_runtime": 24995.5735, "train_tokens_per_second": 2988.182 }, { "epoch": 0.7270995396094618, "grad_norm": 0.9875156283378601, "learning_rate": 1.725443062751959e-05, "loss": 1.341444969177246, "num_input_tokens_seen": 74756711, "step": 1145, "train_runtime": 25015.617, "train_tokens_per_second": 2988.402 }, { "epoch": 0.7277345610414352, "grad_norm": 1.226064920425415, "learning_rate": 1.7249849813829503e-05, "loss": 1.6948723793029785, "num_input_tokens_seen": 74816806, "step": 1146, "train_runtime": 25034.7173, "train_tokens_per_second": 2988.522 }, { "epoch": 0.7283695824734084, "grad_norm": 1.1381186246871948, "learning_rate": 1.7245265791087268e-05, "loss": 1.6331316232681274, "num_input_tokens_seen": 74882339, "step": 1147, "train_runtime": 25056.2704, "train_tokens_per_second": 2988.567 }, { "epoch": 0.7290046039053818, "grad_norm": 1.1162885427474976, "learning_rate": 1.7240678561321953e-05, "loss": 1.5634410381317139, "num_input_tokens_seen": 74947765, "step": 1148, "train_runtime": 25077.7301, "train_tokens_per_second": 2988.618 }, { "epoch": 0.7296396253373552, "grad_norm": 1.2979352474212646, "learning_rate": 1.7236088126564032e-05, "loss": 1.7809278964996338, "num_input_tokens_seen": 75013178, "step": 1149, "train_runtime": 25099.0675, "train_tokens_per_second": 2988.684 }, { "epoch": 0.7302746467693285, "grad_norm": 1.1594674587249756, "learning_rate": 1.72314944888454e-05, "loss": 1.6082767248153687, "num_input_tokens_seen": 75078676, "step": 1150, "train_runtime": 25120.072, "train_tokens_per_second": 2988.792 }, { "epoch": 0.7309096682013018, "grad_norm": 1.1305018663406372, "learning_rate": 1.722689765019937e-05, "loss": 1.4805809259414673, "num_input_tokens_seen": 75144059, "step": 1151, "train_runtime": 25140.9216, "train_tokens_per_second": 2988.914 }, { "epoch": 0.7315446896332751, "grad_norm": 1.3120954036712646, "learning_rate": 1.722229761266068e-05, "loss": 1.8116651773452759, "num_input_tokens_seen": 75209548, "step": 1152, "train_runtime": 25163.2748, "train_tokens_per_second": 2988.862 }, { "epoch": 0.7321797110652485, "grad_norm": 1.1406644582748413, "learning_rate": 1.7217694378265473e-05, "loss": 1.654213786125183, "num_input_tokens_seen": 75275023, "step": 1153, "train_runtime": 25184.3478, "train_tokens_per_second": 2988.961 }, { "epoch": 0.7328147324972217, "grad_norm": 1.137612223625183, "learning_rate": 1.7213087949051307e-05, "loss": 1.4937446117401123, "num_input_tokens_seen": 75340532, "step": 1154, "train_runtime": 25204.671, "train_tokens_per_second": 2989.15 }, { "epoch": 0.7334497539291951, "grad_norm": 1.216261386871338, "learning_rate": 1.7208478327057164e-05, "loss": 1.6190037727355957, "num_input_tokens_seen": 75406038, "step": 1155, "train_runtime": 25226.2743, "train_tokens_per_second": 2989.186 }, { "epoch": 0.7340847753611685, "grad_norm": 1.362540364265442, "learning_rate": 1.720386551432343e-05, "loss": 1.9372872114181519, "num_input_tokens_seen": 75471493, "step": 1156, "train_runtime": 25248.7405, "train_tokens_per_second": 2989.119 }, { "epoch": 0.7347197967931418, "grad_norm": 1.230650544166565, "learning_rate": 1.7199249512891914e-05, "loss": 1.713947057723999, "num_input_tokens_seen": 75536980, "step": 1157, "train_runtime": 25269.8045, "train_tokens_per_second": 2989.219 }, { "epoch": 0.7353548182251151, "grad_norm": 1.2470653057098389, "learning_rate": 1.7194630324805817e-05, "loss": 1.644666314125061, "num_input_tokens_seen": 75602494, "step": 1158, "train_runtime": 25291.6471, "train_tokens_per_second": 2989.228 }, { "epoch": 0.7359898396570884, "grad_norm": 1.2297940254211426, "learning_rate": 1.7190007952109772e-05, "loss": 1.6691648960113525, "num_input_tokens_seen": 75667949, "step": 1159, "train_runtime": 25313.3529, "train_tokens_per_second": 2989.25 }, { "epoch": 0.7366248610890618, "grad_norm": 1.2432506084442139, "learning_rate": 1.718538239684981e-05, "loss": 1.6217702627182007, "num_input_tokens_seen": 75733474, "step": 1160, "train_runtime": 25334.9012, "train_tokens_per_second": 2989.294 }, { "epoch": 0.7372598825210351, "grad_norm": 1.1800529956817627, "learning_rate": 1.7180753661073374e-05, "loss": 1.6413609981536865, "num_input_tokens_seen": 75798998, "step": 1161, "train_runtime": 25356.2957, "train_tokens_per_second": 2989.356 }, { "epoch": 0.7378949039530084, "grad_norm": 1.2216682434082031, "learning_rate": 1.717612174682931e-05, "loss": 1.598750114440918, "num_input_tokens_seen": 75864507, "step": 1162, "train_runtime": 25378.8741, "train_tokens_per_second": 2989.278 }, { "epoch": 0.7385299253849817, "grad_norm": 1.1953798532485962, "learning_rate": 1.7171486656167877e-05, "loss": 1.5652904510498047, "num_input_tokens_seen": 75929973, "step": 1163, "train_runtime": 25399.9282, "train_tokens_per_second": 2989.377 }, { "epoch": 0.7391649468169551, "grad_norm": 1.2957717180252075, "learning_rate": 1.716684839114074e-05, "loss": 1.75133216381073, "num_input_tokens_seen": 75995414, "step": 1164, "train_runtime": 25421.955, "train_tokens_per_second": 2989.362 }, { "epoch": 0.7397999682489284, "grad_norm": 1.2417618036270142, "learning_rate": 1.7162206953800965e-05, "loss": 1.7018978595733643, "num_input_tokens_seen": 76060902, "step": 1165, "train_runtime": 25443.7172, "train_tokens_per_second": 2989.379 }, { "epoch": 0.7404349896809017, "grad_norm": 1.1894347667694092, "learning_rate": 1.7157562346203026e-05, "loss": 1.8033052682876587, "num_input_tokens_seen": 76126401, "step": 1166, "train_runtime": 25465.1348, "train_tokens_per_second": 2989.436 }, { "epoch": 0.7410700111128751, "grad_norm": 1.2190451622009277, "learning_rate": 1.71529145704028e-05, "loss": 1.6639206409454346, "num_input_tokens_seen": 76191895, "step": 1167, "train_runtime": 25487.2153, "train_tokens_per_second": 2989.416 }, { "epoch": 0.7417050325448484, "grad_norm": 1.073970079421997, "learning_rate": 1.7148263628457557e-05, "loss": 1.609028935432434, "num_input_tokens_seen": 76257318, "step": 1168, "train_runtime": 25508.7716, "train_tokens_per_second": 2989.455 }, { "epoch": 0.7423400539768217, "grad_norm": 1.2671703100204468, "learning_rate": 1.7143609522425982e-05, "loss": 1.6318762302398682, "num_input_tokens_seen": 76322706, "step": 1169, "train_runtime": 25530.9965, "train_tokens_per_second": 2989.414 }, { "epoch": 0.742975075408795, "grad_norm": 1.2618039846420288, "learning_rate": 1.7138952254368156e-05, "loss": 1.611236333847046, "num_input_tokens_seen": 76388174, "step": 1170, "train_runtime": 25552.5226, "train_tokens_per_second": 2989.457 }, { "epoch": 0.7436100968407684, "grad_norm": 1.2988892793655396, "learning_rate": 1.7134291826345555e-05, "loss": 1.784924030303955, "num_input_tokens_seen": 76453660, "step": 1171, "train_runtime": 25574.6631, "train_tokens_per_second": 2989.43 }, { "epoch": 0.7442451182727418, "grad_norm": 1.158618450164795, "learning_rate": 1.712962824042106e-05, "loss": 1.6288857460021973, "num_input_tokens_seen": 76519124, "step": 1172, "train_runtime": 25596.7681, "train_tokens_per_second": 2989.406 }, { "epoch": 0.744880139704715, "grad_norm": 1.1659350395202637, "learning_rate": 1.712496149865894e-05, "loss": 1.7178728580474854, "num_input_tokens_seen": 76584616, "step": 1173, "train_runtime": 25617.8446, "train_tokens_per_second": 2989.503 }, { "epoch": 0.7455151611366884, "grad_norm": 1.216483473777771, "learning_rate": 1.712029160312488e-05, "loss": 1.6053004264831543, "num_input_tokens_seen": 76650138, "step": 1174, "train_runtime": 25639.521, "train_tokens_per_second": 2989.531 }, { "epoch": 0.7461501825686617, "grad_norm": 1.2167222499847412, "learning_rate": 1.711561855588594e-05, "loss": 1.6803908348083496, "num_input_tokens_seen": 76715638, "step": 1175, "train_runtime": 25660.3319, "train_tokens_per_second": 2989.659 }, { "epoch": 0.746785204000635, "grad_norm": 1.4188659191131592, "learning_rate": 1.7110942359010582e-05, "loss": 1.8676159381866455, "num_input_tokens_seen": 76780971, "step": 1176, "train_runtime": 25681.9743, "train_tokens_per_second": 2989.683 }, { "epoch": 0.7474202254326083, "grad_norm": 1.314558506011963, "learning_rate": 1.710626301456867e-05, "loss": 1.5649120807647705, "num_input_tokens_seen": 76846360, "step": 1177, "train_runtime": 25702.972, "train_tokens_per_second": 2989.785 }, { "epoch": 0.7480552468645817, "grad_norm": 1.4526519775390625, "learning_rate": 1.7101580524631453e-05, "loss": 1.6421772241592407, "num_input_tokens_seen": 76911750, "step": 1178, "train_runtime": 25724.3304, "train_tokens_per_second": 2989.845 }, { "epoch": 0.748690268296555, "grad_norm": 1.1719313859939575, "learning_rate": 1.7096894891271576e-05, "loss": 1.5618577003479004, "num_input_tokens_seen": 76977272, "step": 1179, "train_runtime": 25745.9137, "train_tokens_per_second": 2989.883 }, { "epoch": 0.7493252897285283, "grad_norm": 1.0776911973953247, "learning_rate": 1.709220611656307e-05, "loss": 1.5079256296157837, "num_input_tokens_seen": 77042722, "step": 1180, "train_runtime": 25766.7857, "train_tokens_per_second": 2990.001 }, { "epoch": 0.7499603111605017, "grad_norm": 1.1931848526000977, "learning_rate": 1.7087514202581364e-05, "loss": 1.7137017250061035, "num_input_tokens_seen": 77108215, "step": 1181, "train_runtime": 25787.7187, "train_tokens_per_second": 2990.114 }, { "epoch": 0.750595332592475, "grad_norm": 1.15322744846344, "learning_rate": 1.708281915140327e-05, "loss": 1.5892003774642944, "num_input_tokens_seen": 77173626, "step": 1182, "train_runtime": 25808.2533, "train_tokens_per_second": 2990.269 }, { "epoch": 0.7512303540244484, "grad_norm": 1.235175609588623, "learning_rate": 1.7078120965106995e-05, "loss": 1.637608528137207, "num_input_tokens_seen": 77239045, "step": 1183, "train_runtime": 25829.9853, "train_tokens_per_second": 2990.286 }, { "epoch": 0.7518653754564216, "grad_norm": 1.276642918586731, "learning_rate": 1.707341964577213e-05, "loss": 1.6492094993591309, "num_input_tokens_seen": 77304432, "step": 1184, "train_runtime": 25851.6836, "train_tokens_per_second": 2990.306 }, { "epoch": 0.752500396888395, "grad_norm": 1.2959368228912354, "learning_rate": 1.7068715195479652e-05, "loss": 1.6082063913345337, "num_input_tokens_seen": 77369884, "step": 1185, "train_runtime": 25873.055, "train_tokens_per_second": 2990.365 }, { "epoch": 0.7531354183203683, "grad_norm": 1.1449815034866333, "learning_rate": 1.7064007616311923e-05, "loss": 1.615535020828247, "num_input_tokens_seen": 77435223, "step": 1186, "train_runtime": 25894.1506, "train_tokens_per_second": 2990.452 }, { "epoch": 0.7537704397523416, "grad_norm": 1.2520631551742554, "learning_rate": 1.7059296910352696e-05, "loss": 1.7434202432632446, "num_input_tokens_seen": 77500732, "step": 1187, "train_runtime": 25916.3382, "train_tokens_per_second": 2990.42 }, { "epoch": 0.754405461184315, "grad_norm": 1.2378737926483154, "learning_rate": 1.70545830796871e-05, "loss": 1.5954339504241943, "num_input_tokens_seen": 77566190, "step": 1188, "train_runtime": 25937.0821, "train_tokens_per_second": 2990.552 }, { "epoch": 0.7550404826162883, "grad_norm": 1.1504629850387573, "learning_rate": 1.7049866126401654e-05, "loss": 1.6032394170761108, "num_input_tokens_seen": 77631579, "step": 1189, "train_runtime": 25958.1883, "train_tokens_per_second": 2990.639 }, { "epoch": 0.7556755040482617, "grad_norm": 1.3433746099472046, "learning_rate": 1.7045146052584252e-05, "loss": 1.6134144067764282, "num_input_tokens_seen": 77696983, "step": 1190, "train_runtime": 25979.43, "train_tokens_per_second": 2990.712 }, { "epoch": 0.7563105254802349, "grad_norm": 1.1124361753463745, "learning_rate": 1.704042286032418e-05, "loss": 1.474029541015625, "num_input_tokens_seen": 77762404, "step": 1191, "train_runtime": 25999.9347, "train_tokens_per_second": 2990.869 }, { "epoch": 0.7569455469122083, "grad_norm": 1.300791621208191, "learning_rate": 1.7035696551712094e-05, "loss": 1.8572360277175903, "num_input_tokens_seen": 77827839, "step": 1192, "train_runtime": 26021.543, "train_tokens_per_second": 2990.9 }, { "epoch": 0.7575805683441816, "grad_norm": 1.094913125038147, "learning_rate": 1.7030967128840033e-05, "loss": 1.5805400609970093, "num_input_tokens_seen": 77893292, "step": 1193, "train_runtime": 26042.6928, "train_tokens_per_second": 2990.985 }, { "epoch": 0.758215589776155, "grad_norm": 1.3573565483093262, "learning_rate": 1.7026234593801415e-05, "loss": 1.6534993648529053, "num_input_tokens_seen": 77958780, "step": 1194, "train_runtime": 26065.1365, "train_tokens_per_second": 2990.922 }, { "epoch": 0.7588506112081282, "grad_norm": 1.1429462432861328, "learning_rate": 1.702149894869104e-05, "loss": 1.5875544548034668, "num_input_tokens_seen": 78024146, "step": 1195, "train_runtime": 26085.9796, "train_tokens_per_second": 2991.038 }, { "epoch": 0.7594856326401016, "grad_norm": 1.3474183082580566, "learning_rate": 1.7016760195605075e-05, "loss": 1.7894747257232666, "num_input_tokens_seen": 78089572, "step": 1196, "train_runtime": 26108.1848, "train_tokens_per_second": 2991.0 }, { "epoch": 0.760120654072075, "grad_norm": 1.157567024230957, "learning_rate": 1.7012018336641066e-05, "loss": 1.6492719650268555, "num_input_tokens_seen": 78155094, "step": 1197, "train_runtime": 26130.039, "train_tokens_per_second": 2991.006 }, { "epoch": 0.7607556755040482, "grad_norm": 1.273320198059082, "learning_rate": 1.7007273373897943e-05, "loss": 1.6027660369873047, "num_input_tokens_seen": 78220595, "step": 1198, "train_runtime": 26152.046, "train_tokens_per_second": 2990.993 }, { "epoch": 0.7613906969360216, "grad_norm": 1.3888428211212158, "learning_rate": 1.7002525309475993e-05, "loss": 1.4299671649932861, "num_input_tokens_seen": 78282669, "step": 1199, "train_runtime": 26172.5905, "train_tokens_per_second": 2991.017 }, { "epoch": 0.7620257183679949, "grad_norm": 1.3179779052734375, "learning_rate": 1.6997774145476893e-05, "loss": 1.7852169275283813, "num_input_tokens_seen": 78348102, "step": 1200, "train_runtime": 26193.5944, "train_tokens_per_second": 2991.117 }, { "epoch": 0.7620257183679949, "eval_loss": 1.5651500225067139, "eval_runtime": 12.8901, "eval_samples_per_second": 1.784, "eval_steps_per_second": 0.931, "num_input_tokens_seen": 78348102, "step": 1200 }, { "epoch": 0.7626607397999683, "grad_norm": 1.312381386756897, "learning_rate": 1.6993019884003682e-05, "loss": 1.5609209537506104, "num_input_tokens_seen": 78413445, "step": 1201, "train_runtime": 26265.7804, "train_tokens_per_second": 2985.384 }, { "epoch": 0.7632957612319415, "grad_norm": 1.1749775409698486, "learning_rate": 1.6988262527160767e-05, "loss": 1.6105331182479858, "num_input_tokens_seen": 78478916, "step": 1202, "train_runtime": 26287.4454, "train_tokens_per_second": 2985.414 }, { "epoch": 0.7639307826639149, "grad_norm": 1.3377609252929688, "learning_rate": 1.6983502077053936e-05, "loss": 1.7994328737258911, "num_input_tokens_seen": 78544348, "step": 1203, "train_runtime": 26308.6638, "train_tokens_per_second": 2985.494 }, { "epoch": 0.7645658040958883, "grad_norm": 1.3644381761550903, "learning_rate": 1.6978738535790343e-05, "loss": 1.8165273666381836, "num_input_tokens_seen": 78609813, "step": 1204, "train_runtime": 26330.5989, "train_tokens_per_second": 2985.493 }, { "epoch": 0.7652008255278616, "grad_norm": 2.1155741214752197, "learning_rate": 1.69739719054785e-05, "loss": 1.4749194383621216, "num_input_tokens_seen": 78675259, "step": 1205, "train_runtime": 26352.6449, "train_tokens_per_second": 2985.479 }, { "epoch": 0.7658358469598349, "grad_norm": 1.337567925453186, "learning_rate": 1.6969202188228297e-05, "loss": 1.5919774770736694, "num_input_tokens_seen": 78740710, "step": 1206, "train_runtime": 26373.9688, "train_tokens_per_second": 2985.546 }, { "epoch": 0.7664708683918082, "grad_norm": 1.2168880701065063, "learning_rate": 1.6964429386150993e-05, "loss": 1.4873894453048706, "num_input_tokens_seen": 78806223, "step": 1207, "train_runtime": 26394.7094, "train_tokens_per_second": 2985.683 }, { "epoch": 0.7671058898237816, "grad_norm": 1.408265471458435, "learning_rate": 1.6959653501359202e-05, "loss": 1.646590232849121, "num_input_tokens_seen": 78871645, "step": 1208, "train_runtime": 26416.4468, "train_tokens_per_second": 2985.702 }, { "epoch": 0.7677409112557548, "grad_norm": 1.3120746612548828, "learning_rate": 1.695487453596691e-05, "loss": 1.7880266904830933, "num_input_tokens_seen": 78937077, "step": 1209, "train_runtime": 26438.6715, "train_tokens_per_second": 2985.667 }, { "epoch": 0.7683759326877282, "grad_norm": 1.4544944763183594, "learning_rate": 1.695009249208946e-05, "loss": 1.8115241527557373, "num_input_tokens_seen": 79002588, "step": 1210, "train_runtime": 26460.3147, "train_tokens_per_second": 2985.701 }, { "epoch": 0.7690109541197016, "grad_norm": 1.1706945896148682, "learning_rate": 1.6945307371843565e-05, "loss": 1.6292762756347656, "num_input_tokens_seen": 79068119, "step": 1211, "train_runtime": 26481.8813, "train_tokens_per_second": 2985.744 }, { "epoch": 0.7696459755516749, "grad_norm": 1.266564130783081, "learning_rate": 1.6940519177347296e-05, "loss": 1.7517547607421875, "num_input_tokens_seen": 79133644, "step": 1212, "train_runtime": 26503.6987, "train_tokens_per_second": 2985.759 }, { "epoch": 0.7702809969836482, "grad_norm": 1.0992093086242676, "learning_rate": 1.6935727910720086e-05, "loss": 1.563148856163025, "num_input_tokens_seen": 79199069, "step": 1213, "train_runtime": 26523.9524, "train_tokens_per_second": 2985.945 }, { "epoch": 0.7709160184156215, "grad_norm": 1.4030214548110962, "learning_rate": 1.6930933574082727e-05, "loss": 1.7576934099197388, "num_input_tokens_seen": 79260201, "step": 1214, "train_runtime": 26544.1324, "train_tokens_per_second": 2985.978 }, { "epoch": 0.7715510398475949, "grad_norm": 1.1335728168487549, "learning_rate": 1.692613616955737e-05, "loss": 1.6322156190872192, "num_input_tokens_seen": 79325708, "step": 1215, "train_runtime": 26564.9655, "train_tokens_per_second": 2986.102 }, { "epoch": 0.7721860612795682, "grad_norm": 1.3849544525146484, "learning_rate": 1.6921335699267524e-05, "loss": 1.768369436264038, "num_input_tokens_seen": 79391076, "step": 1216, "train_runtime": 26587.4015, "train_tokens_per_second": 2986.041 }, { "epoch": 0.7728210827115415, "grad_norm": 1.2144381999969482, "learning_rate": 1.6916532165338054e-05, "loss": 1.6885966062545776, "num_input_tokens_seen": 79456510, "step": 1217, "train_runtime": 26609.5593, "train_tokens_per_second": 2986.014 }, { "epoch": 0.7734561041435148, "grad_norm": 1.229613184928894, "learning_rate": 1.691172556989518e-05, "loss": 1.6214079856872559, "num_input_tokens_seen": 79522017, "step": 1218, "train_runtime": 26630.857, "train_tokens_per_second": 2986.086 }, { "epoch": 0.7740911255754882, "grad_norm": 1.2175713777542114, "learning_rate": 1.690691591506648e-05, "loss": 1.5240033864974976, "num_input_tokens_seen": 79581329, "step": 1219, "train_runtime": 26650.0599, "train_tokens_per_second": 2986.159 }, { "epoch": 0.7747261470074615, "grad_norm": 1.2493934631347656, "learning_rate": 1.6902103202980892e-05, "loss": 1.8106715679168701, "num_input_tokens_seen": 79646804, "step": 1220, "train_runtime": 26671.7941, "train_tokens_per_second": 2986.181 }, { "epoch": 0.7753611684394348, "grad_norm": 1.168334722518921, "learning_rate": 1.6897287435768693e-05, "loss": 1.7862391471862793, "num_input_tokens_seen": 79712250, "step": 1221, "train_runtime": 26694.0286, "train_tokens_per_second": 2986.145 }, { "epoch": 0.7759961898714082, "grad_norm": 1.3750452995300293, "learning_rate": 1.6892468615561527e-05, "loss": 1.882150650024414, "num_input_tokens_seen": 79777772, "step": 1222, "train_runtime": 26715.8181, "train_tokens_per_second": 2986.162 }, { "epoch": 0.7766312113033815, "grad_norm": 1.1517219543457031, "learning_rate": 1.6887646744492375e-05, "loss": 1.5750256776809692, "num_input_tokens_seen": 79843276, "step": 1223, "train_runtime": 26737.4616, "train_tokens_per_second": 2986.195 }, { "epoch": 0.7772662327353548, "grad_norm": 1.238277554512024, "learning_rate": 1.6882821824695578e-05, "loss": 1.7666220664978027, "num_input_tokens_seen": 79908683, "step": 1224, "train_runtime": 26758.49, "train_tokens_per_second": 2986.293 }, { "epoch": 0.7779012541673281, "grad_norm": 1.3575952053070068, "learning_rate": 1.6877993858306828e-05, "loss": 1.8039214611053467, "num_input_tokens_seen": 79974196, "step": 1225, "train_runtime": 26780.3372, "train_tokens_per_second": 2986.303 }, { "epoch": 0.7785362755993015, "grad_norm": 1.141220211982727, "learning_rate": 1.6873162847463158e-05, "loss": 1.6076710224151611, "num_input_tokens_seen": 80039708, "step": 1226, "train_runtime": 26802.1996, "train_tokens_per_second": 2986.311 }, { "epoch": 0.7791712970312749, "grad_norm": 1.1466668844223022, "learning_rate": 1.6868328794302953e-05, "loss": 1.5663903951644897, "num_input_tokens_seen": 80105202, "step": 1227, "train_runtime": 26823.3743, "train_tokens_per_second": 2986.395 }, { "epoch": 0.7798063184632481, "grad_norm": 1.3362377882003784, "learning_rate": 1.6863491700965945e-05, "loss": 1.6286017894744873, "num_input_tokens_seen": 80170511, "step": 1228, "train_runtime": 26844.434, "train_tokens_per_second": 2986.485 }, { "epoch": 0.7804413398952215, "grad_norm": 1.2567055225372314, "learning_rate": 1.6858651569593212e-05, "loss": 1.8560876846313477, "num_input_tokens_seen": 80235988, "step": 1229, "train_runtime": 26867.3161, "train_tokens_per_second": 2986.379 }, { "epoch": 0.7810763613271948, "grad_norm": 1.3014034032821655, "learning_rate": 1.685380840232717e-05, "loss": 1.865004539489746, "num_input_tokens_seen": 80301511, "step": 1230, "train_runtime": 26889.2092, "train_tokens_per_second": 2986.384 }, { "epoch": 0.7817113827591681, "grad_norm": 1.2584158182144165, "learning_rate": 1.6848962201311593e-05, "loss": 1.6989800930023193, "num_input_tokens_seen": 80366974, "step": 1231, "train_runtime": 26910.3256, "train_tokens_per_second": 2986.473 }, { "epoch": 0.7823464041911414, "grad_norm": 1.2816661596298218, "learning_rate": 1.684411296869158e-05, "loss": 1.7815369367599487, "num_input_tokens_seen": 80432472, "step": 1232, "train_runtime": 26931.8688, "train_tokens_per_second": 2986.517 }, { "epoch": 0.7829814256231148, "grad_norm": 1.3479686975479126, "learning_rate": 1.6839260706613588e-05, "loss": 1.8339190483093262, "num_input_tokens_seen": 80497991, "step": 1233, "train_runtime": 26953.8262, "train_tokens_per_second": 2986.514 }, { "epoch": 0.7836164470550882, "grad_norm": 1.0321340560913086, "learning_rate": 1.6834405417225404e-05, "loss": 1.508416771888733, "num_input_tokens_seen": 80563463, "step": 1234, "train_runtime": 26975.6047, "train_tokens_per_second": 2986.53 }, { "epoch": 0.7842514684870614, "grad_norm": 1.1963269710540771, "learning_rate": 1.682954710267616e-05, "loss": 1.7023202180862427, "num_input_tokens_seen": 80628986, "step": 1235, "train_runtime": 26996.4661, "train_tokens_per_second": 2986.65 }, { "epoch": 0.7848864899190348, "grad_norm": 1.198010802268982, "learning_rate": 1.6824685765116327e-05, "loss": 1.646315336227417, "num_input_tokens_seen": 80694513, "step": 1236, "train_runtime": 27017.5425, "train_tokens_per_second": 2986.745 }, { "epoch": 0.7855215113510081, "grad_norm": 1.4311589002609253, "learning_rate": 1.681982140669771e-05, "loss": 1.7920238971710205, "num_input_tokens_seen": 80753183, "step": 1237, "train_runtime": 27036.4392, "train_tokens_per_second": 2986.828 }, { "epoch": 0.7861565327829815, "grad_norm": 1.3395793437957764, "learning_rate": 1.681495402957346e-05, "loss": 1.6751585006713867, "num_input_tokens_seen": 80814713, "step": 1238, "train_runtime": 27057.0187, "train_tokens_per_second": 2986.83 }, { "epoch": 0.7867915542149547, "grad_norm": 1.2521098852157593, "learning_rate": 1.6810083635898053e-05, "loss": 1.5944206714630127, "num_input_tokens_seen": 80880188, "step": 1239, "train_runtime": 27078.1722, "train_tokens_per_second": 2986.915 }, { "epoch": 0.7874265756469281, "grad_norm": 1.2364412546157837, "learning_rate": 1.680521022782731e-05, "loss": 1.5841903686523438, "num_input_tokens_seen": 80945678, "step": 1240, "train_runtime": 27100.106, "train_tokens_per_second": 2986.914 }, { "epoch": 0.7880615970789014, "grad_norm": 1.1774665117263794, "learning_rate": 1.6800333807518375e-05, "loss": 1.7821561098098755, "num_input_tokens_seen": 81011190, "step": 1241, "train_runtime": 27121.7624, "train_tokens_per_second": 2986.944 }, { "epoch": 0.7886966185108747, "grad_norm": 1.2075756788253784, "learning_rate": 1.679545437712974e-05, "loss": 1.6827671527862549, "num_input_tokens_seen": 81076696, "step": 1242, "train_runtime": 27142.8557, "train_tokens_per_second": 2987.036 }, { "epoch": 0.789331639942848, "grad_norm": 1.149919867515564, "learning_rate": 1.679057193882122e-05, "loss": 1.640640139579773, "num_input_tokens_seen": 81142154, "step": 1243, "train_runtime": 27164.6706, "train_tokens_per_second": 2987.047 }, { "epoch": 0.7899666613748214, "grad_norm": 1.2288564443588257, "learning_rate": 1.678568649475396e-05, "loss": 1.7022038698196411, "num_input_tokens_seen": 81207601, "step": 1244, "train_runtime": 27186.4648, "train_tokens_per_second": 2987.06 }, { "epoch": 0.7906016828067948, "grad_norm": 1.2330366373062134, "learning_rate": 1.6780798047090443e-05, "loss": 1.6282153129577637, "num_input_tokens_seen": 81273118, "step": 1245, "train_runtime": 27207.7018, "train_tokens_per_second": 2987.136 }, { "epoch": 0.791236704238768, "grad_norm": 1.2372572422027588, "learning_rate": 1.6775906597994472e-05, "loss": 1.6529006958007812, "num_input_tokens_seen": 81338618, "step": 1246, "train_runtime": 27228.8736, "train_tokens_per_second": 2987.219 }, { "epoch": 0.7918717256707414, "grad_norm": 1.1890649795532227, "learning_rate": 1.6771012149631184e-05, "loss": 1.4711514711380005, "num_input_tokens_seen": 81404126, "step": 1247, "train_runtime": 27250.6557, "train_tokens_per_second": 2987.236 }, { "epoch": 0.7925067471027147, "grad_norm": 1.2887651920318604, "learning_rate": 1.6766114704167048e-05, "loss": 1.7577602863311768, "num_input_tokens_seen": 81469623, "step": 1248, "train_runtime": 27272.4085, "train_tokens_per_second": 2987.254 }, { "epoch": 0.7931417685346881, "grad_norm": 1.0924955606460571, "learning_rate": 1.676121426376985e-05, "loss": 1.5647505521774292, "num_input_tokens_seen": 81534997, "step": 1249, "train_runtime": 27294.2641, "train_tokens_per_second": 2987.258 }, { "epoch": 0.7937767899666613, "grad_norm": 1.058319330215454, "learning_rate": 1.6756310830608712e-05, "loss": 1.4895994663238525, "num_input_tokens_seen": 81600516, "step": 1250, "train_runtime": 27315.3321, "train_tokens_per_second": 2987.352 }, { "epoch": 0.7944118113986347, "grad_norm": 1.4924447536468506, "learning_rate": 1.675140440685407e-05, "loss": 1.6999953985214233, "num_input_tokens_seen": 81665965, "step": 1251, "train_runtime": 27337.3065, "train_tokens_per_second": 2987.345 }, { "epoch": 0.7950468328306081, "grad_norm": 1.1646952629089355, "learning_rate": 1.674649499467769e-05, "loss": 1.567253589630127, "num_input_tokens_seen": 81731487, "step": 1252, "train_runtime": 27358.1421, "train_tokens_per_second": 2987.465 }, { "epoch": 0.7956818542625813, "grad_norm": 1.0994065999984741, "learning_rate": 1.674158259625266e-05, "loss": 1.6164385080337524, "num_input_tokens_seen": 81796951, "step": 1253, "train_runtime": 27379.2945, "train_tokens_per_second": 2987.548 }, { "epoch": 0.7963168756945547, "grad_norm": 1.2298626899719238, "learning_rate": 1.673666721375339e-05, "loss": 1.8015060424804688, "num_input_tokens_seen": 81862473, "step": 1254, "train_runtime": 27401.7463, "train_tokens_per_second": 2987.491 }, { "epoch": 0.796951897126528, "grad_norm": 1.2882391214370728, "learning_rate": 1.6731748849355612e-05, "loss": 1.614694595336914, "num_input_tokens_seen": 81927975, "step": 1255, "train_runtime": 27423.1669, "train_tokens_per_second": 2987.546 }, { "epoch": 0.7975869185585014, "grad_norm": 1.2088836431503296, "learning_rate": 1.6726827505236374e-05, "loss": 1.5619288682937622, "num_input_tokens_seen": 81993414, "step": 1256, "train_runtime": 27444.9768, "train_tokens_per_second": 2987.556 }, { "epoch": 0.7982219399904746, "grad_norm": 1.2796486616134644, "learning_rate": 1.6721903183574047e-05, "loss": 1.7038719654083252, "num_input_tokens_seen": 82058911, "step": 1257, "train_runtime": 27466.9086, "train_tokens_per_second": 2987.555 }, { "epoch": 0.798856961422448, "grad_norm": 1.1458251476287842, "learning_rate": 1.6716975886548316e-05, "loss": 1.5019712448120117, "num_input_tokens_seen": 82124359, "step": 1258, "train_runtime": 27487.8157, "train_tokens_per_second": 2987.664 }, { "epoch": 0.7994919828544214, "grad_norm": 1.1762949228286743, "learning_rate": 1.6712045616340185e-05, "loss": 1.5062904357910156, "num_input_tokens_seen": 82189877, "step": 1259, "train_runtime": 27508.5845, "train_tokens_per_second": 2987.79 }, { "epoch": 0.8001270042863947, "grad_norm": 1.1920615434646606, "learning_rate": 1.6707112375131974e-05, "loss": 1.6119595766067505, "num_input_tokens_seen": 82255202, "step": 1260, "train_runtime": 27529.5181, "train_tokens_per_second": 2987.891 }, { "epoch": 0.800762025718368, "grad_norm": 1.27651047706604, "learning_rate": 1.6702176165107323e-05, "loss": 1.5035597085952759, "num_input_tokens_seen": 82320640, "step": 1261, "train_runtime": 27550.9416, "train_tokens_per_second": 2987.943 }, { "epoch": 0.8013970471503413, "grad_norm": 1.3193632364273071, "learning_rate": 1.6697236988451178e-05, "loss": 1.9242100715637207, "num_input_tokens_seen": 82386038, "step": 1262, "train_runtime": 27572.4368, "train_tokens_per_second": 2987.985 }, { "epoch": 0.8020320685823147, "grad_norm": 1.1570888757705688, "learning_rate": 1.6692294847349805e-05, "loss": 1.5902154445648193, "num_input_tokens_seen": 82451462, "step": 1263, "train_runtime": 27592.9451, "train_tokens_per_second": 2988.136 }, { "epoch": 0.8026670900142879, "grad_norm": 1.2497482299804688, "learning_rate": 1.6687349743990772e-05, "loss": 1.7665622234344482, "num_input_tokens_seen": 82516839, "step": 1264, "train_runtime": 27613.9617, "train_tokens_per_second": 2988.229 }, { "epoch": 0.8033021114462613, "grad_norm": 1.3595595359802246, "learning_rate": 1.6682401680562968e-05, "loss": 1.7922396659851074, "num_input_tokens_seen": 82582198, "step": 1265, "train_runtime": 27635.6537, "train_tokens_per_second": 2988.248 }, { "epoch": 0.8039371328782347, "grad_norm": 1.3385159969329834, "learning_rate": 1.6677450659256592e-05, "loss": 1.6821141242980957, "num_input_tokens_seen": 82647563, "step": 1266, "train_runtime": 27657.4849, "train_tokens_per_second": 2988.253 }, { "epoch": 0.804572154310208, "grad_norm": 1.2891932725906372, "learning_rate": 1.6672496682263147e-05, "loss": 1.8025237321853638, "num_input_tokens_seen": 82713062, "step": 1267, "train_runtime": 27679.7129, "train_tokens_per_second": 2988.22 }, { "epoch": 0.8052071757421813, "grad_norm": 1.3536304235458374, "learning_rate": 1.6667539751775445e-05, "loss": 1.608076810836792, "num_input_tokens_seen": 82778578, "step": 1268, "train_runtime": 27701.4668, "train_tokens_per_second": 2988.238 }, { "epoch": 0.8058421971741546, "grad_norm": 1.2194982767105103, "learning_rate": 1.6662579869987613e-05, "loss": 1.4990636110305786, "num_input_tokens_seen": 82844086, "step": 1269, "train_runtime": 27723.1664, "train_tokens_per_second": 2988.262 }, { "epoch": 0.806477218606128, "grad_norm": 1.2874890565872192, "learning_rate": 1.665761703909507e-05, "loss": 1.6820600032806396, "num_input_tokens_seen": 82909506, "step": 1270, "train_runtime": 27744.7036, "train_tokens_per_second": 2988.3 }, { "epoch": 0.8071122400381013, "grad_norm": 1.3991174697875977, "learning_rate": 1.665265126129456e-05, "loss": 1.9299030303955078, "num_input_tokens_seen": 82969609, "step": 1271, "train_runtime": 27764.4357, "train_tokens_per_second": 2988.341 }, { "epoch": 0.8077472614700746, "grad_norm": 1.322204351425171, "learning_rate": 1.664768253878411e-05, "loss": 1.9191280603408813, "num_input_tokens_seen": 83035067, "step": 1272, "train_runtime": 27786.482, "train_tokens_per_second": 2988.326 }, { "epoch": 0.8083822829020479, "grad_norm": 1.2407112121582031, "learning_rate": 1.664271087376306e-05, "loss": 1.5657415390014648, "num_input_tokens_seen": 83100593, "step": 1273, "train_runtime": 27807.4196, "train_tokens_per_second": 2988.432 }, { "epoch": 0.8090173043340213, "grad_norm": 1.135107398033142, "learning_rate": 1.6637736268432066e-05, "loss": 1.4943221807479858, "num_input_tokens_seen": 83166126, "step": 1274, "train_runtime": 27828.4275, "train_tokens_per_second": 2988.531 }, { "epoch": 0.8096523257659946, "grad_norm": 1.2906663417816162, "learning_rate": 1.663275872499306e-05, "loss": 1.7544257640838623, "num_input_tokens_seen": 83231605, "step": 1275, "train_runtime": 27850.1363, "train_tokens_per_second": 2988.553 }, { "epoch": 0.8102873471979679, "grad_norm": 1.2828094959259033, "learning_rate": 1.6627778245649292e-05, "loss": 1.69467031955719, "num_input_tokens_seen": 83297077, "step": 1276, "train_runtime": 27871.5999, "train_tokens_per_second": 2988.6 }, { "epoch": 0.8109223686299413, "grad_norm": 1.1692956686019897, "learning_rate": 1.6622794832605306e-05, "loss": 1.6615290641784668, "num_input_tokens_seen": 83362484, "step": 1277, "train_runtime": 27893.3376, "train_tokens_per_second": 2988.616 }, { "epoch": 0.8115573900619146, "grad_norm": 1.1478784084320068, "learning_rate": 1.6617808488066948e-05, "loss": 1.676509141921997, "num_input_tokens_seen": 83427890, "step": 1278, "train_runtime": 27914.4863, "train_tokens_per_second": 2988.695 }, { "epoch": 0.8121924114938879, "grad_norm": 1.3675271272659302, "learning_rate": 1.661281921424135e-05, "loss": 1.9708242416381836, "num_input_tokens_seen": 83493401, "step": 1279, "train_runtime": 27937.3605, "train_tokens_per_second": 2988.593 }, { "epoch": 0.8128274329258612, "grad_norm": 1.1068676710128784, "learning_rate": 1.660782701333696e-05, "loss": 1.556381106376648, "num_input_tokens_seen": 83558872, "step": 1280, "train_runtime": 27958.1557, "train_tokens_per_second": 2988.712 }, { "epoch": 0.8134624543578346, "grad_norm": 1.3497834205627441, "learning_rate": 1.6602831887563505e-05, "loss": 1.8224211931228638, "num_input_tokens_seen": 83618730, "step": 1281, "train_runtime": 27977.8164, "train_tokens_per_second": 2988.751 }, { "epoch": 0.814097475789808, "grad_norm": 1.2009332180023193, "learning_rate": 1.6597833839132016e-05, "loss": 1.5851670503616333, "num_input_tokens_seen": 83684198, "step": 1282, "train_runtime": 27998.8314, "train_tokens_per_second": 2988.846 }, { "epoch": 0.8147324972217812, "grad_norm": 1.2107536792755127, "learning_rate": 1.6592832870254812e-05, "loss": 1.6798611879348755, "num_input_tokens_seen": 83749612, "step": 1283, "train_runtime": 28020.2662, "train_tokens_per_second": 2988.894 }, { "epoch": 0.8153675186537546, "grad_norm": 1.3075658082962036, "learning_rate": 1.6587828983145508e-05, "loss": 1.7994623184204102, "num_input_tokens_seen": 83815047, "step": 1284, "train_runtime": 28040.7232, "train_tokens_per_second": 2989.047 }, { "epoch": 0.8160025400857279, "grad_norm": 1.3059418201446533, "learning_rate": 1.6582822180019014e-05, "loss": 1.7481187582015991, "num_input_tokens_seen": 83880450, "step": 1285, "train_runtime": 28062.6441, "train_tokens_per_second": 2989.043 }, { "epoch": 0.8166375615177012, "grad_norm": 1.273076057434082, "learning_rate": 1.6577812463091515e-05, "loss": 1.741666316986084, "num_input_tokens_seen": 83945952, "step": 1286, "train_runtime": 28085.0012, "train_tokens_per_second": 2988.996 }, { "epoch": 0.8172725829496745, "grad_norm": 1.3767509460449219, "learning_rate": 1.6572799834580508e-05, "loss": 1.6406422853469849, "num_input_tokens_seen": 84011419, "step": 1287, "train_runtime": 28106.8831, "train_tokens_per_second": 2988.998 }, { "epoch": 0.8179076043816479, "grad_norm": 1.1832706928253174, "learning_rate": 1.6567784296704766e-05, "loss": 1.7529786825180054, "num_input_tokens_seen": 84076923, "step": 1288, "train_runtime": 28128.8879, "train_tokens_per_second": 2988.989 }, { "epoch": 0.8185426258136212, "grad_norm": 1.186521291732788, "learning_rate": 1.656276585168435e-05, "loss": 1.6129510402679443, "num_input_tokens_seen": 84142382, "step": 1289, "train_runtime": 28150.228, "train_tokens_per_second": 2989.048 }, { "epoch": 0.8191776472455945, "grad_norm": 1.1043522357940674, "learning_rate": 1.655774450174061e-05, "loss": 1.4474200010299683, "num_input_tokens_seen": 84207803, "step": 1290, "train_runtime": 28170.4833, "train_tokens_per_second": 2989.221 }, { "epoch": 0.8198126686775679, "grad_norm": 1.2561585903167725, "learning_rate": 1.655272024909618e-05, "loss": 1.776313066482544, "num_input_tokens_seen": 84273193, "step": 1291, "train_runtime": 28192.0771, "train_tokens_per_second": 2989.251 }, { "epoch": 0.8204476901095412, "grad_norm": 1.2286479473114014, "learning_rate": 1.6547693095974984e-05, "loss": 1.4670372009277344, "num_input_tokens_seen": 84332588, "step": 1292, "train_runtime": 28211.1419, "train_tokens_per_second": 2989.336 }, { "epoch": 0.8210827115415146, "grad_norm": 1.1414320468902588, "learning_rate": 1.6542663044602226e-05, "loss": 1.521762490272522, "num_input_tokens_seen": 84397879, "step": 1293, "train_runtime": 28232.6662, "train_tokens_per_second": 2989.37 }, { "epoch": 0.8217177329734878, "grad_norm": 1.1995081901550293, "learning_rate": 1.6537630097204394e-05, "loss": 1.6333321332931519, "num_input_tokens_seen": 84462416, "step": 1294, "train_runtime": 28254.1617, "train_tokens_per_second": 2989.38 }, { "epoch": 0.8223527544054612, "grad_norm": 1.2290273904800415, "learning_rate": 1.653259425600925e-05, "loss": 1.5777403116226196, "num_input_tokens_seen": 84527868, "step": 1295, "train_runtime": 28275.8966, "train_tokens_per_second": 2989.397 }, { "epoch": 0.8229877758374345, "grad_norm": 1.2614649534225464, "learning_rate": 1.652755552324585e-05, "loss": 1.6035878658294678, "num_input_tokens_seen": 84593338, "step": 1296, "train_runtime": 28297.2763, "train_tokens_per_second": 2989.452 }, { "epoch": 0.8236227972694078, "grad_norm": 1.187262773513794, "learning_rate": 1.652251390114452e-05, "loss": 1.4856388568878174, "num_input_tokens_seen": 84658869, "step": 1297, "train_runtime": 28318.7486, "train_tokens_per_second": 2989.499 }, { "epoch": 0.8242578187013812, "grad_norm": 1.417344331741333, "learning_rate": 1.6517469391936877e-05, "loss": 1.7747267484664917, "num_input_tokens_seen": 84724399, "step": 1298, "train_runtime": 28341.088, "train_tokens_per_second": 2989.455 }, { "epoch": 0.8248928401333545, "grad_norm": 1.2225146293640137, "learning_rate": 1.6512421997855795e-05, "loss": 1.65933358669281, "num_input_tokens_seen": 84789830, "step": 1299, "train_runtime": 28362.3481, "train_tokens_per_second": 2989.521 }, { "epoch": 0.8255278615653279, "grad_norm": 1.1835964918136597, "learning_rate": 1.6507371721135446e-05, "loss": 1.6957616806030273, "num_input_tokens_seen": 84855342, "step": 1300, "train_runtime": 28383.4125, "train_tokens_per_second": 2989.61 }, { "epoch": 0.8255278615653279, "eval_loss": 1.5618761777877808, "eval_runtime": 12.8861, "eval_samples_per_second": 1.785, "eval_steps_per_second": 0.931, "num_input_tokens_seen": 84855342, "step": 1300 }, { "epoch": 0.8261628829973011, "grad_norm": 1.1076710224151611, "learning_rate": 1.6502318564011273e-05, "loss": 1.4719663858413696, "num_input_tokens_seen": 84920783, "step": 1301, "train_runtime": 28454.004, "train_tokens_per_second": 2984.493 }, { "epoch": 0.8267979044292745, "grad_norm": 1.2957171201705933, "learning_rate": 1.6497262528719983e-05, "loss": 1.5061016082763672, "num_input_tokens_seen": 84986291, "step": 1302, "train_runtime": 28475.4161, "train_tokens_per_second": 2984.55 }, { "epoch": 0.8274329258612478, "grad_norm": 1.1919105052947998, "learning_rate": 1.6492203617499564e-05, "loss": 1.668784737586975, "num_input_tokens_seen": 85051769, "step": 1303, "train_runtime": 28496.6821, "train_tokens_per_second": 2984.62 }, { "epoch": 0.8280679472932212, "grad_norm": 1.287354588508606, "learning_rate": 1.6487141832589283e-05, "loss": 1.5536274909973145, "num_input_tokens_seen": 85117197, "step": 1304, "train_runtime": 28517.4483, "train_tokens_per_second": 2984.741 }, { "epoch": 0.8287029687251944, "grad_norm": 1.1372796297073364, "learning_rate": 1.648207717622967e-05, "loss": 1.5321855545043945, "num_input_tokens_seen": 85182692, "step": 1305, "train_runtime": 28539.4111, "train_tokens_per_second": 2984.739 }, { "epoch": 0.8293379901571678, "grad_norm": 1.1721136569976807, "learning_rate": 1.6477009650662534e-05, "loss": 1.528187870979309, "num_input_tokens_seen": 85248173, "step": 1306, "train_runtime": 28560.9128, "train_tokens_per_second": 2984.785 }, { "epoch": 0.8299730115891412, "grad_norm": 1.2019554376602173, "learning_rate": 1.6471939258130943e-05, "loss": 1.6263927221298218, "num_input_tokens_seen": 85313530, "step": 1307, "train_runtime": 28581.3815, "train_tokens_per_second": 2984.934 }, { "epoch": 0.8306080330211144, "grad_norm": 1.3073972463607788, "learning_rate": 1.6466866000879247e-05, "loss": 1.451780915260315, "num_input_tokens_seen": 85379032, "step": 1308, "train_runtime": 28602.6622, "train_tokens_per_second": 2985.003 }, { "epoch": 0.8312430544530878, "grad_norm": 1.1336019039154053, "learning_rate": 1.6461789881153053e-05, "loss": 1.526977777481079, "num_input_tokens_seen": 85444519, "step": 1309, "train_runtime": 28624.1299, "train_tokens_per_second": 2985.052 }, { "epoch": 0.8318780758850611, "grad_norm": 1.3729013204574585, "learning_rate": 1.6456710901199242e-05, "loss": 1.9855623245239258, "num_input_tokens_seen": 85510040, "step": 1310, "train_runtime": 28646.6799, "train_tokens_per_second": 2984.99 }, { "epoch": 0.8325130973170345, "grad_norm": 1.1744439601898193, "learning_rate": 1.6451629063265958e-05, "loss": 1.4896063804626465, "num_input_tokens_seen": 85575524, "step": 1311, "train_runtime": 28667.3049, "train_tokens_per_second": 2985.126 }, { "epoch": 0.8331481187490077, "grad_norm": 1.2723675966262817, "learning_rate": 1.644654436960261e-05, "loss": 1.7052569389343262, "num_input_tokens_seen": 85640913, "step": 1312, "train_runtime": 28689.7032, "train_tokens_per_second": 2985.075 }, { "epoch": 0.8337831401809811, "grad_norm": 1.2678966522216797, "learning_rate": 1.644145682245987e-05, "loss": 1.8453712463378906, "num_input_tokens_seen": 85706393, "step": 1313, "train_runtime": 28710.8844, "train_tokens_per_second": 2985.153 }, { "epoch": 0.8344181616129545, "grad_norm": 1.3077635765075684, "learning_rate": 1.643636642408968e-05, "loss": 1.8033353090286255, "num_input_tokens_seen": 85771864, "step": 1314, "train_runtime": 28731.9005, "train_tokens_per_second": 2985.249 }, { "epoch": 0.8350531830449278, "grad_norm": 1.190349817276001, "learning_rate": 1.6431273176745235e-05, "loss": 1.6168700456619263, "num_input_tokens_seen": 85837321, "step": 1315, "train_runtime": 28753.0342, "train_tokens_per_second": 2985.331 }, { "epoch": 0.8356882044769011, "grad_norm": 1.262330412864685, "learning_rate": 1.6426177082681e-05, "loss": 1.7317169904708862, "num_input_tokens_seen": 85902714, "step": 1316, "train_runtime": 28774.5899, "train_tokens_per_second": 2985.367 }, { "epoch": 0.8363232259088744, "grad_norm": 1.1639440059661865, "learning_rate": 1.642107814415269e-05, "loss": 1.5706779956817627, "num_input_tokens_seen": 85968242, "step": 1317, "train_runtime": 28795.7368, "train_tokens_per_second": 2985.45 }, { "epoch": 0.8369582473408478, "grad_norm": 1.1002426147460938, "learning_rate": 1.641597636341728e-05, "loss": 1.4591947793960571, "num_input_tokens_seen": 86033763, "step": 1318, "train_runtime": 28816.5494, "train_tokens_per_second": 2985.568 }, { "epoch": 0.837593268772821, "grad_norm": 1.205950379371643, "learning_rate": 1.641087174273302e-05, "loss": 1.5801130533218384, "num_input_tokens_seen": 86099185, "step": 1319, "train_runtime": 28837.5286, "train_tokens_per_second": 2985.664 }, { "epoch": 0.8382282902047944, "grad_norm": 1.1967970132827759, "learning_rate": 1.6405764284359392e-05, "loss": 1.5719785690307617, "num_input_tokens_seen": 86164693, "step": 1320, "train_runtime": 28859.4119, "train_tokens_per_second": 2985.67 }, { "epoch": 0.8388633116367678, "grad_norm": 1.1665278673171997, "learning_rate": 1.6400653990557153e-05, "loss": 1.6266100406646729, "num_input_tokens_seen": 86230170, "step": 1321, "train_runtime": 28880.3808, "train_tokens_per_second": 2985.77 }, { "epoch": 0.8394983330687411, "grad_norm": 1.4086111783981323, "learning_rate": 1.639554086358831e-05, "loss": 1.7323397397994995, "num_input_tokens_seen": 86295584, "step": 1322, "train_runtime": 28901.7017, "train_tokens_per_second": 2985.831 }, { "epoch": 0.8401333545007144, "grad_norm": 1.2446383237838745, "learning_rate": 1.6390424905716112e-05, "loss": 1.6799335479736328, "num_input_tokens_seen": 86361097, "step": 1323, "train_runtime": 28923.2153, "train_tokens_per_second": 2985.875 }, { "epoch": 0.8407683759326877, "grad_norm": 1.2379130125045776, "learning_rate": 1.6385306119205085e-05, "loss": 1.6277016401290894, "num_input_tokens_seen": 86426559, "step": 1324, "train_runtime": 28945.0044, "train_tokens_per_second": 2985.889 }, { "epoch": 0.8414033973646611, "grad_norm": 1.2347009181976318, "learning_rate": 1.638018450632098e-05, "loss": 1.7338000535964966, "num_input_tokens_seen": 86492034, "step": 1325, "train_runtime": 28966.4642, "train_tokens_per_second": 2985.937 }, { "epoch": 0.8420384187966344, "grad_norm": 1.3265324831008911, "learning_rate": 1.6375060069330825e-05, "loss": 1.675961971282959, "num_input_tokens_seen": 86557401, "step": 1326, "train_runtime": 28987.4841, "train_tokens_per_second": 2986.027 }, { "epoch": 0.8426734402286077, "grad_norm": 1.240936517715454, "learning_rate": 1.636993281050288e-05, "loss": 1.7043980360031128, "num_input_tokens_seen": 86622924, "step": 1327, "train_runtime": 29008.9658, "train_tokens_per_second": 2986.074 }, { "epoch": 0.843308461660581, "grad_norm": 1.6735773086547852, "learning_rate": 1.6364802732106658e-05, "loss": 1.5160895586013794, "num_input_tokens_seen": 86688385, "step": 1328, "train_runtime": 29030.4071, "train_tokens_per_second": 2986.124 }, { "epoch": 0.8439434830925544, "grad_norm": 1.225588321685791, "learning_rate": 1.6359669836412927e-05, "loss": 1.6730724573135376, "num_input_tokens_seen": 86753831, "step": 1329, "train_runtime": 29051.8884, "train_tokens_per_second": 2986.168 }, { "epoch": 0.8445785045245277, "grad_norm": 1.2466785907745361, "learning_rate": 1.6354534125693693e-05, "loss": 1.6244277954101562, "num_input_tokens_seen": 86819261, "step": 1330, "train_runtime": 29073.6269, "train_tokens_per_second": 2986.186 }, { "epoch": 0.845213525956501, "grad_norm": 1.2641851902008057, "learning_rate": 1.6349395602222214e-05, "loss": 1.7641162872314453, "num_input_tokens_seen": 86884606, "step": 1331, "train_runtime": 29095.4139, "train_tokens_per_second": 2986.196 }, { "epoch": 0.8458485473884744, "grad_norm": 1.1948366165161133, "learning_rate": 1.6344254268272986e-05, "loss": 1.7126641273498535, "num_input_tokens_seen": 86949916, "step": 1332, "train_runtime": 29116.0947, "train_tokens_per_second": 2986.318 }, { "epoch": 0.8464835688204477, "grad_norm": 1.1855370998382568, "learning_rate": 1.6339110126121757e-05, "loss": 1.6367708444595337, "num_input_tokens_seen": 87015413, "step": 1333, "train_runtime": 29136.774, "train_tokens_per_second": 2986.446 }, { "epoch": 0.847118590252421, "grad_norm": 1.1273976564407349, "learning_rate": 1.6333963178045514e-05, "loss": 1.4205055236816406, "num_input_tokens_seen": 87080856, "step": 1334, "train_runtime": 29158.3152, "train_tokens_per_second": 2986.484 }, { "epoch": 0.8477536116843943, "grad_norm": 1.3170301914215088, "learning_rate": 1.6328813426322495e-05, "loss": 1.6798017024993896, "num_input_tokens_seen": 87146374, "step": 1335, "train_runtime": 29179.7624, "train_tokens_per_second": 2986.535 }, { "epoch": 0.8483886331163677, "grad_norm": 1.2930365800857544, "learning_rate": 1.6323660873232162e-05, "loss": 1.7223944664001465, "num_input_tokens_seen": 87211860, "step": 1336, "train_runtime": 29201.7707, "train_tokens_per_second": 2986.526 }, { "epoch": 0.8490236545483411, "grad_norm": 1.0963051319122314, "learning_rate": 1.6318505521055225e-05, "loss": 1.5434725284576416, "num_input_tokens_seen": 87277256, "step": 1337, "train_runtime": 29223.085, "train_tokens_per_second": 2986.586 }, { "epoch": 0.8496586759803143, "grad_norm": 1.2134546041488647, "learning_rate": 1.6313347372073636e-05, "loss": 1.627673864364624, "num_input_tokens_seen": 87342680, "step": 1338, "train_runtime": 29244.7548, "train_tokens_per_second": 2986.61 }, { "epoch": 0.8502936974122877, "grad_norm": 1.3764597177505493, "learning_rate": 1.6308186428570586e-05, "loss": 1.9239091873168945, "num_input_tokens_seen": 87408191, "step": 1339, "train_runtime": 29267.255, "train_tokens_per_second": 2986.552 }, { "epoch": 0.850928718844261, "grad_norm": 1.1671878099441528, "learning_rate": 1.6303022692830497e-05, "loss": 1.506710410118103, "num_input_tokens_seen": 87473633, "step": 1340, "train_runtime": 29288.3376, "train_tokens_per_second": 2986.637 }, { "epoch": 0.8515637402762343, "grad_norm": 1.2124080657958984, "learning_rate": 1.629785616713903e-05, "loss": 1.664752721786499, "num_input_tokens_seen": 87539126, "step": 1341, "train_runtime": 29309.3468, "train_tokens_per_second": 2986.731 }, { "epoch": 0.8521987617082076, "grad_norm": 1.259386420249939, "learning_rate": 1.629268685378308e-05, "loss": 1.641142725944519, "num_input_tokens_seen": 87604627, "step": 1342, "train_runtime": 29330.3531, "train_tokens_per_second": 2986.825 }, { "epoch": 0.852833783140181, "grad_norm": 1.2309238910675049, "learning_rate": 1.628751475505078e-05, "loss": 1.6924208402633667, "num_input_tokens_seen": 87670136, "step": 1343, "train_runtime": 29351.9699, "train_tokens_per_second": 2986.857 }, { "epoch": 0.8534688045721543, "grad_norm": 1.168581485748291, "learning_rate": 1.6282339873231488e-05, "loss": 1.6745104789733887, "num_input_tokens_seen": 87735651, "step": 1344, "train_runtime": 29373.4339, "train_tokens_per_second": 2986.905 }, { "epoch": 0.8541038260041276, "grad_norm": 1.3053003549575806, "learning_rate": 1.6277162210615803e-05, "loss": 1.6697930097579956, "num_input_tokens_seen": 87801055, "step": 1345, "train_runtime": 29394.0631, "train_tokens_per_second": 2987.034 }, { "epoch": 0.854738847436101, "grad_norm": 1.109248161315918, "learning_rate": 1.6271981769495545e-05, "loss": 1.5238828659057617, "num_input_tokens_seen": 87866559, "step": 1346, "train_runtime": 29415.5638, "train_tokens_per_second": 2987.077 }, { "epoch": 0.8553738688680743, "grad_norm": 1.183807134628296, "learning_rate": 1.6266798552163776e-05, "loss": 1.4986839294433594, "num_input_tokens_seen": 87931913, "step": 1347, "train_runtime": 29436.446, "train_tokens_per_second": 2987.178 }, { "epoch": 0.8560088903000477, "grad_norm": 1.317418098449707, "learning_rate": 1.6261612560914775e-05, "loss": 1.9908244609832764, "num_input_tokens_seen": 87997385, "step": 1348, "train_runtime": 29458.7446, "train_tokens_per_second": 2987.14 }, { "epoch": 0.8566439117320209, "grad_norm": 1.1845531463623047, "learning_rate": 1.6256423798044053e-05, "loss": 1.5445877313613892, "num_input_tokens_seen": 88062883, "step": 1349, "train_runtime": 29480.1588, "train_tokens_per_second": 2987.192 }, { "epoch": 0.8572789331639943, "grad_norm": 1.135180950164795, "learning_rate": 1.625123226584835e-05, "loss": 1.6529359817504883, "num_input_tokens_seen": 88128404, "step": 1350, "train_runtime": 29501.0503, "train_tokens_per_second": 2987.297 }, { "epoch": 0.8579139545959676, "grad_norm": 1.1730930805206299, "learning_rate": 1.6246037966625635e-05, "loss": 1.482163667678833, "num_input_tokens_seen": 88190431, "step": 1351, "train_runtime": 29521.1434, "train_tokens_per_second": 2987.365 }, { "epoch": 0.8585489760279409, "grad_norm": 1.2352490425109863, "learning_rate": 1.624084090267509e-05, "loss": 1.5616271495819092, "num_input_tokens_seen": 88255956, "step": 1352, "train_runtime": 29542.254, "train_tokens_per_second": 2987.448 }, { "epoch": 0.8591839974599143, "grad_norm": 1.1270248889923096, "learning_rate": 1.6235641076297133e-05, "loss": 1.4762673377990723, "num_input_tokens_seen": 88321469, "step": 1353, "train_runtime": 29562.537, "train_tokens_per_second": 2987.615 }, { "epoch": 0.8598190188918876, "grad_norm": 1.4346517324447632, "learning_rate": 1.62304384897934e-05, "loss": 1.8975937366485596, "num_input_tokens_seen": 88386985, "step": 1354, "train_runtime": 29585.1192, "train_tokens_per_second": 2987.549 }, { "epoch": 0.860454040323861, "grad_norm": 1.2154699563980103, "learning_rate": 1.6225233145466743e-05, "loss": 1.6523916721343994, "num_input_tokens_seen": 88452386, "step": 1355, "train_runtime": 29605.98, "train_tokens_per_second": 2987.653 }, { "epoch": 0.8610890617558342, "grad_norm": 1.3356943130493164, "learning_rate": 1.6220025045621248e-05, "loss": 1.819743037223816, "num_input_tokens_seen": 88517904, "step": 1356, "train_runtime": 29628.0728, "train_tokens_per_second": 2987.636 }, { "epoch": 0.8617240831878076, "grad_norm": 1.0867011547088623, "learning_rate": 1.6214814192562205e-05, "loss": 1.4805355072021484, "num_input_tokens_seen": 88583404, "step": 1357, "train_runtime": 29649.4462, "train_tokens_per_second": 2987.692 }, { "epoch": 0.8623591046197809, "grad_norm": 1.2487010955810547, "learning_rate": 1.6209600588596136e-05, "loss": 1.4818613529205322, "num_input_tokens_seen": 88643336, "step": 1358, "train_runtime": 29668.5242, "train_tokens_per_second": 2987.791 }, { "epoch": 0.8629941260517543, "grad_norm": 1.1976697444915771, "learning_rate": 1.6204384236030775e-05, "loss": 1.5792587995529175, "num_input_tokens_seen": 88708731, "step": 1359, "train_runtime": 29689.2091, "train_tokens_per_second": 2987.912 }, { "epoch": 0.8636291474837275, "grad_norm": 1.4960625171661377, "learning_rate": 1.619916513717507e-05, "loss": 1.7377954721450806, "num_input_tokens_seen": 88774262, "step": 1360, "train_runtime": 29711.3895, "train_tokens_per_second": 2987.887 }, { "epoch": 0.8642641689157009, "grad_norm": 1.1672487258911133, "learning_rate": 1.6193943294339194e-05, "loss": 1.546885371208191, "num_input_tokens_seen": 88839702, "step": 1361, "train_runtime": 29731.9572, "train_tokens_per_second": 2988.021 }, { "epoch": 0.8648991903476743, "grad_norm": 1.2378323078155518, "learning_rate": 1.618871870983452e-05, "loss": 1.5852235555648804, "num_input_tokens_seen": 88905227, "step": 1362, "train_runtime": 29753.8662, "train_tokens_per_second": 2988.023 }, { "epoch": 0.8655342117796475, "grad_norm": 1.173144817352295, "learning_rate": 1.618349138597365e-05, "loss": 1.5659672021865845, "num_input_tokens_seen": 88970640, "step": 1363, "train_runtime": 29775.413, "train_tokens_per_second": 2988.057 }, { "epoch": 0.8661692332116209, "grad_norm": 1.1964993476867676, "learning_rate": 1.6178261325070385e-05, "loss": 1.6361587047576904, "num_input_tokens_seen": 89033956, "step": 1364, "train_runtime": 29796.0336, "train_tokens_per_second": 2988.114 }, { "epoch": 0.8668042546435942, "grad_norm": 1.1622933149337769, "learning_rate": 1.6173028529439742e-05, "loss": 1.6387670040130615, "num_input_tokens_seen": 89099464, "step": 1365, "train_runtime": 29817.3677, "train_tokens_per_second": 2988.173 }, { "epoch": 0.8674392760755676, "grad_norm": 1.2270487546920776, "learning_rate": 1.616779300139796e-05, "loss": 1.641121506690979, "num_input_tokens_seen": 89164938, "step": 1366, "train_runtime": 29838.5949, "train_tokens_per_second": 2988.242 }, { "epoch": 0.8680742975075408, "grad_norm": 1.3078925609588623, "learning_rate": 1.616255474326247e-05, "loss": 1.755791425704956, "num_input_tokens_seen": 89230380, "step": 1367, "train_runtime": 29859.9244, "train_tokens_per_second": 2988.299 }, { "epoch": 0.8687093189395142, "grad_norm": 1.2974385023117065, "learning_rate": 1.6157313757351922e-05, "loss": 1.910410761833191, "num_input_tokens_seen": 89295868, "step": 1368, "train_runtime": 29881.4807, "train_tokens_per_second": 2988.335 }, { "epoch": 0.8693443403714876, "grad_norm": 1.1808948516845703, "learning_rate": 1.615207004598617e-05, "loss": 1.5027767419815063, "num_input_tokens_seen": 89361357, "step": 1369, "train_runtime": 29903.1905, "train_tokens_per_second": 2988.355 }, { "epoch": 0.8699793618034609, "grad_norm": 1.093862533569336, "learning_rate": 1.6146823611486277e-05, "loss": 1.4860442876815796, "num_input_tokens_seen": 89426863, "step": 1370, "train_runtime": 29925.3069, "train_tokens_per_second": 2988.336 }, { "epoch": 0.8706143832354342, "grad_norm": 1.183292031288147, "learning_rate": 1.6141574456174503e-05, "loss": 1.6439824104309082, "num_input_tokens_seen": 89492203, "step": 1371, "train_runtime": 29946.6759, "train_tokens_per_second": 2988.385 }, { "epoch": 0.8712494046674075, "grad_norm": 1.224752426147461, "learning_rate": 1.6136322582374325e-05, "loss": 1.6056336164474487, "num_input_tokens_seen": 89557681, "step": 1372, "train_runtime": 29968.6835, "train_tokens_per_second": 2988.376 }, { "epoch": 0.8718844260993809, "grad_norm": 1.1931042671203613, "learning_rate": 1.6131067992410413e-05, "loss": 1.592629075050354, "num_input_tokens_seen": 89623157, "step": 1373, "train_runtime": 29989.6382, "train_tokens_per_second": 2988.471 }, { "epoch": 0.8725194475313541, "grad_norm": 1.1969119310379028, "learning_rate": 1.6125810688608646e-05, "loss": 1.6258888244628906, "num_input_tokens_seen": 89688646, "step": 1374, "train_runtime": 30010.9715, "train_tokens_per_second": 2988.529 }, { "epoch": 0.8731544689633275, "grad_norm": 1.5633749961853027, "learning_rate": 1.6120550673296098e-05, "loss": 1.7962464094161987, "num_input_tokens_seen": 89754064, "step": 1375, "train_runtime": 30032.8743, "train_tokens_per_second": 2988.527 }, { "epoch": 0.8737894903953008, "grad_norm": 1.1762996912002563, "learning_rate": 1.611528794880105e-05, "loss": 1.6468944549560547, "num_input_tokens_seen": 89819524, "step": 1376, "train_runtime": 30053.8893, "train_tokens_per_second": 2988.616 }, { "epoch": 0.8744245118272742, "grad_norm": 1.186429500579834, "learning_rate": 1.611002251745298e-05, "loss": 1.6547763347625732, "num_input_tokens_seen": 89884929, "step": 1377, "train_runtime": 30074.8756, "train_tokens_per_second": 2988.705 }, { "epoch": 0.8750595332592475, "grad_norm": 1.178983211517334, "learning_rate": 1.6104754381582555e-05, "loss": 1.4201157093048096, "num_input_tokens_seen": 89944474, "step": 1378, "train_runtime": 30094.2785, "train_tokens_per_second": 2988.757 }, { "epoch": 0.8756945546912208, "grad_norm": 1.2685372829437256, "learning_rate": 1.609948354352166e-05, "loss": 1.6739003658294678, "num_input_tokens_seen": 90009975, "step": 1379, "train_runtime": 30116.3802, "train_tokens_per_second": 2988.738 }, { "epoch": 0.8763295761231942, "grad_norm": 1.2758243083953857, "learning_rate": 1.6094210005603353e-05, "loss": 1.8462116718292236, "num_input_tokens_seen": 90075469, "step": 1380, "train_runtime": 30137.8563, "train_tokens_per_second": 2988.782 }, { "epoch": 0.8769645975551675, "grad_norm": 1.2877352237701416, "learning_rate": 1.6088933770161903e-05, "loss": 1.574526309967041, "num_input_tokens_seen": 90140985, "step": 1381, "train_runtime": 30159.0585, "train_tokens_per_second": 2988.853 }, { "epoch": 0.8775996189871408, "grad_norm": 1.2091392278671265, "learning_rate": 1.6083654839532763e-05, "loss": 1.540607213973999, "num_input_tokens_seen": 90206468, "step": 1382, "train_runtime": 30180.463, "train_tokens_per_second": 2988.903 }, { "epoch": 0.8782346404191141, "grad_norm": 1.117343544960022, "learning_rate": 1.6078373216052583e-05, "loss": 1.5312988758087158, "num_input_tokens_seen": 90271983, "step": 1383, "train_runtime": 30201.5784, "train_tokens_per_second": 2988.982 }, { "epoch": 0.8788696618510875, "grad_norm": 1.2304761409759521, "learning_rate": 1.6073088902059207e-05, "loss": 1.6389150619506836, "num_input_tokens_seen": 90337513, "step": 1384, "train_runtime": 30222.6493, "train_tokens_per_second": 2989.067 }, { "epoch": 0.8795046832830608, "grad_norm": 1.399519681930542, "learning_rate": 1.6067801899891674e-05, "loss": 1.6643271446228027, "num_input_tokens_seen": 90403042, "step": 1385, "train_runtime": 30244.7054, "train_tokens_per_second": 2989.053 }, { "epoch": 0.8801397047150341, "grad_norm": 1.1554210186004639, "learning_rate": 1.6062512211890195e-05, "loss": 1.646287441253662, "num_input_tokens_seen": 90468564, "step": 1386, "train_runtime": 30265.4289, "train_tokens_per_second": 2989.172 }, { "epoch": 0.8807747261470075, "grad_norm": 1.2180747985839844, "learning_rate": 1.605721984039619e-05, "loss": 1.709868311882019, "num_input_tokens_seen": 90534096, "step": 1387, "train_runtime": 30286.6631, "train_tokens_per_second": 2989.24 }, { "epoch": 0.8814097475789808, "grad_norm": 1.0745465755462646, "learning_rate": 1.605192478775226e-05, "loss": 1.5324561595916748, "num_input_tokens_seen": 90599551, "step": 1388, "train_runtime": 30308.1834, "train_tokens_per_second": 2989.277 }, { "epoch": 0.8820447690109541, "grad_norm": 1.104804277420044, "learning_rate": 1.6046627056302185e-05, "loss": 1.5513473749160767, "num_input_tokens_seen": 90664989, "step": 1389, "train_runtime": 30328.535, "train_tokens_per_second": 2989.429 }, { "epoch": 0.8826797904429274, "grad_norm": 1.224424958229065, "learning_rate": 1.6041326648390944e-05, "loss": 1.5905680656433105, "num_input_tokens_seen": 90730346, "step": 1390, "train_runtime": 30349.7614, "train_tokens_per_second": 2989.491 }, { "epoch": 0.8833148118749008, "grad_norm": 1.162022590637207, "learning_rate": 1.603602356636469e-05, "loss": 1.6193220615386963, "num_input_tokens_seen": 90795834, "step": 1391, "train_runtime": 30371.5705, "train_tokens_per_second": 2989.501 }, { "epoch": 0.8839498333068742, "grad_norm": 1.1090010404586792, "learning_rate": 1.6030717812570763e-05, "loss": 1.3903436660766602, "num_input_tokens_seen": 90861329, "step": 1392, "train_runtime": 30392.5419, "train_tokens_per_second": 2989.593 }, { "epoch": 0.8845848547388474, "grad_norm": 1.1709803342819214, "learning_rate": 1.6025409389357687e-05, "loss": 1.5120112895965576, "num_input_tokens_seen": 90926757, "step": 1393, "train_runtime": 30413.4429, "train_tokens_per_second": 2989.69 }, { "epoch": 0.8852198761708208, "grad_norm": 1.242991328239441, "learning_rate": 1.6020098299075167e-05, "loss": 1.759932518005371, "num_input_tokens_seen": 90992233, "step": 1394, "train_runtime": 30434.5587, "train_tokens_per_second": 2989.767 }, { "epoch": 0.8858548976027941, "grad_norm": 1.1999226808547974, "learning_rate": 1.6014784544074088e-05, "loss": 1.658083438873291, "num_input_tokens_seen": 91057681, "step": 1395, "train_runtime": 30456.0614, "train_tokens_per_second": 2989.805 }, { "epoch": 0.8864899190347674, "grad_norm": 1.2423685789108276, "learning_rate": 1.600946812670652e-05, "loss": 1.6555284261703491, "num_input_tokens_seen": 91123202, "step": 1396, "train_runtime": 30477.17, "train_tokens_per_second": 2989.884 }, { "epoch": 0.8871249404667407, "grad_norm": 1.2035948038101196, "learning_rate": 1.60041490493257e-05, "loss": 1.494543433189392, "num_input_tokens_seen": 91188661, "step": 1397, "train_runtime": 30497.6011, "train_tokens_per_second": 2990.027 }, { "epoch": 0.8877599618987141, "grad_norm": 1.179108738899231, "learning_rate": 1.599882731428605e-05, "loss": 1.5301473140716553, "num_input_tokens_seen": 91254015, "step": 1398, "train_runtime": 30518.5475, "train_tokens_per_second": 2990.117 }, { "epoch": 0.8883949833306874, "grad_norm": 1.202866792678833, "learning_rate": 1.5993502923943164e-05, "loss": 1.4468257427215576, "num_input_tokens_seen": 91312682, "step": 1399, "train_runtime": 30537.5169, "train_tokens_per_second": 2990.18 }, { "epoch": 0.8890300047626607, "grad_norm": 1.2913744449615479, "learning_rate": 1.598817588065382e-05, "loss": 1.5839552879333496, "num_input_tokens_seen": 91378015, "step": 1400, "train_runtime": 30558.9808, "train_tokens_per_second": 2990.218 }, { "epoch": 0.8890300047626607, "eval_loss": 1.5578908920288086, "eval_runtime": 12.9173, "eval_samples_per_second": 1.781, "eval_steps_per_second": 0.929, "num_input_tokens_seen": 91378015, "step": 1400 }, { "epoch": 0.8896650261946341, "grad_norm": 1.224810242652893, "learning_rate": 1.5982846186775964e-05, "loss": 1.7096141576766968, "num_input_tokens_seen": 91443448, "step": 1401, "train_runtime": 30629.8609, "train_tokens_per_second": 2985.435 }, { "epoch": 0.8903000476266074, "grad_norm": 1.1970834732055664, "learning_rate": 1.5977513844668715e-05, "loss": 1.7050282955169678, "num_input_tokens_seen": 91508927, "step": 1402, "train_runtime": 30651.7692, "train_tokens_per_second": 2985.437 }, { "epoch": 0.8909350690585808, "grad_norm": 1.2015084028244019, "learning_rate": 1.5972178856692364e-05, "loss": 1.5553439855575562, "num_input_tokens_seen": 91574447, "step": 1403, "train_runtime": 30673.5969, "train_tokens_per_second": 2985.449 }, { "epoch": 0.891570090490554, "grad_norm": 1.2935794591903687, "learning_rate": 1.5966841225208378e-05, "loss": 1.7397605180740356, "num_input_tokens_seen": 91639871, "step": 1404, "train_runtime": 30695.8535, "train_tokens_per_second": 2985.415 }, { "epoch": 0.8922051119225274, "grad_norm": 1.2481372356414795, "learning_rate": 1.5961500952579388e-05, "loss": 1.7011173963546753, "num_input_tokens_seen": 91705398, "step": 1405, "train_runtime": 30717.7009, "train_tokens_per_second": 2985.425 }, { "epoch": 0.8928401333545007, "grad_norm": 1.2880439758300781, "learning_rate": 1.5956158041169193e-05, "loss": 1.6710225343704224, "num_input_tokens_seen": 91770887, "step": 1406, "train_runtime": 30739.1128, "train_tokens_per_second": 2985.476 }, { "epoch": 0.893475154786474, "grad_norm": 1.1648746728897095, "learning_rate": 1.5950812493342766e-05, "loss": 1.4622095823287964, "num_input_tokens_seen": 91836413, "step": 1407, "train_runtime": 30760.271, "train_tokens_per_second": 2985.553 }, { "epoch": 0.8941101762184474, "grad_norm": 1.2257875204086304, "learning_rate": 1.594546431146625e-05, "loss": 1.6405060291290283, "num_input_tokens_seen": 91901863, "step": 1408, "train_runtime": 30781.6868, "train_tokens_per_second": 2985.602 }, { "epoch": 0.8947451976504207, "grad_norm": 1.0783812999725342, "learning_rate": 1.5940113497906938e-05, "loss": 1.398075819015503, "num_input_tokens_seen": 91967380, "step": 1409, "train_runtime": 30802.2613, "train_tokens_per_second": 2985.735 }, { "epoch": 0.8953802190823941, "grad_norm": 1.0967961549758911, "learning_rate": 1.593476005503331e-05, "loss": 1.60178804397583, "num_input_tokens_seen": 92032908, "step": 1410, "train_runtime": 30823.5914, "train_tokens_per_second": 2985.794 }, { "epoch": 0.8960152405143673, "grad_norm": 1.6136630773544312, "learning_rate": 1.5929403985214987e-05, "loss": 1.5915685892105103, "num_input_tokens_seen": 92098439, "step": 1411, "train_runtime": 30845.5735, "train_tokens_per_second": 2985.791 }, { "epoch": 0.8966502619463407, "grad_norm": 1.118707537651062, "learning_rate": 1.592404529082277e-05, "loss": 1.4731324911117554, "num_input_tokens_seen": 92163919, "step": 1412, "train_runtime": 30866.7846, "train_tokens_per_second": 2985.861 }, { "epoch": 0.897285283378314, "grad_norm": 1.2183573246002197, "learning_rate": 1.5918683974228623e-05, "loss": 1.65106999874115, "num_input_tokens_seen": 92229377, "step": 1413, "train_runtime": 30889.2257, "train_tokens_per_second": 2985.811 }, { "epoch": 0.8979203048102874, "grad_norm": 1.2652151584625244, "learning_rate": 1.5913320037805646e-05, "loss": 1.6522307395935059, "num_input_tokens_seen": 92294728, "step": 1414, "train_runtime": 30911.0999, "train_tokens_per_second": 2985.812 }, { "epoch": 0.8985553262422606, "grad_norm": 1.2603758573532104, "learning_rate": 1.590795348392813e-05, "loss": 1.5698643922805786, "num_input_tokens_seen": 92360166, "step": 1415, "train_runtime": 30932.881, "train_tokens_per_second": 2985.825 }, { "epoch": 0.899190347674234, "grad_norm": 1.1413652896881104, "learning_rate": 1.59025843149715e-05, "loss": 1.62736177444458, "num_input_tokens_seen": 92425646, "step": 1416, "train_runtime": 30954.6535, "train_tokens_per_second": 2985.84 }, { "epoch": 0.8998253691062074, "grad_norm": 1.2476478815078735, "learning_rate": 1.589721253331236e-05, "loss": 1.553910493850708, "num_input_tokens_seen": 92491163, "step": 1417, "train_runtime": 30976.3223, "train_tokens_per_second": 2985.866 }, { "epoch": 0.9004603905381806, "grad_norm": 1.0806142091751099, "learning_rate": 1.5891838141328453e-05, "loss": 1.4731918573379517, "num_input_tokens_seen": 92556688, "step": 1418, "train_runtime": 30997.8322, "train_tokens_per_second": 2985.908 }, { "epoch": 0.901095411970154, "grad_norm": 1.2370136976242065, "learning_rate": 1.588646114139869e-05, "loss": 1.5761164426803589, "num_input_tokens_seen": 92622168, "step": 1419, "train_runtime": 31019.1921, "train_tokens_per_second": 2985.963 }, { "epoch": 0.9017304334021273, "grad_norm": 1.3521615266799927, "learning_rate": 1.588108153590312e-05, "loss": 1.6743037700653076, "num_input_tokens_seen": 92687698, "step": 1420, "train_runtime": 31041.3021, "train_tokens_per_second": 2985.947 }, { "epoch": 0.9023654548341007, "grad_norm": 1.2016637325286865, "learning_rate": 1.5875699327222968e-05, "loss": 1.5265069007873535, "num_input_tokens_seen": 92753194, "step": 1421, "train_runtime": 31061.9635, "train_tokens_per_second": 2986.07 }, { "epoch": 0.9030004762660739, "grad_norm": 1.0918463468551636, "learning_rate": 1.587031451774059e-05, "loss": 1.4155441522598267, "num_input_tokens_seen": 92818620, "step": 1422, "train_runtime": 31083.0713, "train_tokens_per_second": 2986.147 }, { "epoch": 0.9036354976980473, "grad_norm": 1.1186355352401733, "learning_rate": 1.58649271098395e-05, "loss": 1.532904863357544, "num_input_tokens_seen": 92884138, "step": 1423, "train_runtime": 31103.783, "train_tokens_per_second": 2986.265 }, { "epoch": 0.9042705191300207, "grad_norm": 1.219001054763794, "learning_rate": 1.5859537105904374e-05, "loss": 1.686702013015747, "num_input_tokens_seen": 92949560, "step": 1424, "train_runtime": 31125.618, "train_tokens_per_second": 2986.272 }, { "epoch": 0.904905540561994, "grad_norm": 1.2820521593093872, "learning_rate": 1.585414450832102e-05, "loss": 1.4583451747894287, "num_input_tokens_seen": 93014972, "step": 1425, "train_runtime": 31146.8096, "train_tokens_per_second": 2986.34 }, { "epoch": 0.9055405619939673, "grad_norm": 1.3479676246643066, "learning_rate": 1.5848749319476406e-05, "loss": 1.820181131362915, "num_input_tokens_seen": 93080374, "step": 1426, "train_runtime": 31168.0433, "train_tokens_per_second": 2986.404 }, { "epoch": 0.9061755834259406, "grad_norm": 1.2573659420013428, "learning_rate": 1.5843351541758642e-05, "loss": 1.690095067024231, "num_input_tokens_seen": 93145884, "step": 1427, "train_runtime": 31189.9336, "train_tokens_per_second": 2986.409 }, { "epoch": 0.906810604857914, "grad_norm": 1.3096868991851807, "learning_rate": 1.583795117755698e-05, "loss": 1.5249981880187988, "num_input_tokens_seen": 93206995, "step": 1428, "train_runtime": 31209.4896, "train_tokens_per_second": 2986.495 }, { "epoch": 0.9074456262898872, "grad_norm": 1.3192379474639893, "learning_rate": 1.583254822926183e-05, "loss": 1.9058783054351807, "num_input_tokens_seen": 93272453, "step": 1429, "train_runtime": 31231.1724, "train_tokens_per_second": 2986.518 }, { "epoch": 0.9080806477218606, "grad_norm": 1.1948630809783936, "learning_rate": 1.5827142699264727e-05, "loss": 1.5468857288360596, "num_input_tokens_seen": 93337928, "step": 1430, "train_runtime": 31252.763, "train_tokens_per_second": 2986.55 }, { "epoch": 0.908715669153834, "grad_norm": 1.105765700340271, "learning_rate": 1.5821734589958364e-05, "loss": 1.5582528114318848, "num_input_tokens_seen": 93403383, "step": 1431, "train_runtime": 31273.5541, "train_tokens_per_second": 2986.657 }, { "epoch": 0.9093506905858073, "grad_norm": 1.1528282165527344, "learning_rate": 1.581632390373657e-05, "loss": 1.5579206943511963, "num_input_tokens_seen": 93468887, "step": 1432, "train_runtime": 31295.2033, "train_tokens_per_second": 2986.684 }, { "epoch": 0.9099857120177806, "grad_norm": 1.114939570426941, "learning_rate": 1.5810910642994313e-05, "loss": 1.5237538814544678, "num_input_tokens_seen": 93534355, "step": 1433, "train_runtime": 31316.1028, "train_tokens_per_second": 2986.781 }, { "epoch": 0.9106207334497539, "grad_norm": 1.1428112983703613, "learning_rate": 1.5805494810127708e-05, "loss": 1.4386038780212402, "num_input_tokens_seen": 93599870, "step": 1434, "train_runtime": 31336.9773, "train_tokens_per_second": 2986.883 }, { "epoch": 0.9112557548817273, "grad_norm": 1.1805095672607422, "learning_rate": 1.5800076407534e-05, "loss": 1.4598370790481567, "num_input_tokens_seen": 93665374, "step": 1435, "train_runtime": 31357.7059, "train_tokens_per_second": 2986.997 }, { "epoch": 0.9118907763137006, "grad_norm": 1.2013835906982422, "learning_rate": 1.5794655437611573e-05, "loss": 1.640836477279663, "num_input_tokens_seen": 93725284, "step": 1436, "train_runtime": 31377.5523, "train_tokens_per_second": 2987.017 }, { "epoch": 0.9125257977456739, "grad_norm": 1.4924284219741821, "learning_rate": 1.5789231902759952e-05, "loss": 1.7687712907791138, "num_input_tokens_seen": 93790692, "step": 1437, "train_runtime": 31399.5068, "train_tokens_per_second": 2987.012 }, { "epoch": 0.9131608191776472, "grad_norm": 1.0432515144348145, "learning_rate": 1.5783805805379794e-05, "loss": 1.4591543674468994, "num_input_tokens_seen": 93856174, "step": 1438, "train_runtime": 31420.3615, "train_tokens_per_second": 2987.113 }, { "epoch": 0.9137958406096206, "grad_norm": 1.1938002109527588, "learning_rate": 1.577837714787289e-05, "loss": 1.5756727457046509, "num_input_tokens_seen": 93921561, "step": 1439, "train_runtime": 31440.859, "train_tokens_per_second": 2987.245 }, { "epoch": 0.9144308620415939, "grad_norm": 1.3137568235397339, "learning_rate": 1.5772945932642163e-05, "loss": 1.578053593635559, "num_input_tokens_seen": 93987074, "step": 1440, "train_runtime": 31461.8918, "train_tokens_per_second": 2987.331 }, { "epoch": 0.9150658834735672, "grad_norm": 1.3270983695983887, "learning_rate": 1.5767512162091674e-05, "loss": 1.7477320432662964, "num_input_tokens_seen": 94052380, "step": 1441, "train_runtime": 31483.6433, "train_tokens_per_second": 2987.341 }, { "epoch": 0.9157009049055406, "grad_norm": 1.1835259199142456, "learning_rate": 1.576207583862661e-05, "loss": 1.5187159776687622, "num_input_tokens_seen": 94117866, "step": 1442, "train_runtime": 31505.3943, "train_tokens_per_second": 2987.357 }, { "epoch": 0.9163359263375139, "grad_norm": 1.1760756969451904, "learning_rate": 1.5756636964653287e-05, "loss": 1.532760739326477, "num_input_tokens_seen": 94180161, "step": 1443, "train_runtime": 31525.5797, "train_tokens_per_second": 2987.42 }, { "epoch": 0.9169709477694872, "grad_norm": 1.123052716255188, "learning_rate": 1.5751195542579157e-05, "loss": 1.5924104452133179, "num_input_tokens_seen": 94245555, "step": 1444, "train_runtime": 31546.4931, "train_tokens_per_second": 2987.513 }, { "epoch": 0.9176059692014605, "grad_norm": 1.4965424537658691, "learning_rate": 1.574575157481279e-05, "loss": 1.7861711978912354, "num_input_tokens_seen": 94310998, "step": 1445, "train_runtime": 31568.379, "train_tokens_per_second": 2987.515 }, { "epoch": 0.9182409906334339, "grad_norm": 1.254258394241333, "learning_rate": 1.5740305063763887e-05, "loss": 1.6058135032653809, "num_input_tokens_seen": 94376504, "step": 1446, "train_runtime": 31589.928, "train_tokens_per_second": 2987.55 }, { "epoch": 0.9188760120654073, "grad_norm": 1.1509944200515747, "learning_rate": 1.573485601184328e-05, "loss": 1.6374658346176147, "num_input_tokens_seen": 94442018, "step": 1447, "train_runtime": 31610.9763, "train_tokens_per_second": 2987.634 }, { "epoch": 0.9195110334973805, "grad_norm": 1.100053071975708, "learning_rate": 1.572940442146292e-05, "loss": 1.4135502576828003, "num_input_tokens_seen": 94507481, "step": 1448, "train_runtime": 31631.7332, "train_tokens_per_second": 2987.743 }, { "epoch": 0.9201460549293539, "grad_norm": 1.2402117252349854, "learning_rate": 1.5723950295035887e-05, "loss": 1.5963473320007324, "num_input_tokens_seen": 94572970, "step": 1449, "train_runtime": 31653.7158, "train_tokens_per_second": 2987.737 }, { "epoch": 0.9207810763613272, "grad_norm": 1.3351091146469116, "learning_rate": 1.5718493634976368e-05, "loss": 1.6313556432724, "num_input_tokens_seen": 94638399, "step": 1450, "train_runtime": 31675.4629, "train_tokens_per_second": 2987.751 }, { "epoch": 0.9214160977933005, "grad_norm": 1.2633031606674194, "learning_rate": 1.5713034443699693e-05, "loss": 1.7941888570785522, "num_input_tokens_seen": 94703904, "step": 1451, "train_runtime": 31697.5366, "train_tokens_per_second": 2987.737 }, { "epoch": 0.9220511192252738, "grad_norm": 1.3135507106781006, "learning_rate": 1.57075727236223e-05, "loss": 1.8281452655792236, "num_input_tokens_seen": 94769358, "step": 1452, "train_runtime": 31718.886, "train_tokens_per_second": 2987.79 }, { "epoch": 0.9226861406572472, "grad_norm": 1.1740535497665405, "learning_rate": 1.5702108477161745e-05, "loss": 1.7444114685058594, "num_input_tokens_seen": 94834760, "step": 1453, "train_runtime": 31740.2619, "train_tokens_per_second": 2987.838 }, { "epoch": 0.9233211620892205, "grad_norm": 1.2649140357971191, "learning_rate": 1.569664170673671e-05, "loss": 1.6914887428283691, "num_input_tokens_seen": 94900229, "step": 1454, "train_runtime": 31762.9378, "train_tokens_per_second": 2987.766 }, { "epoch": 0.9239561835211938, "grad_norm": 1.399237871170044, "learning_rate": 1.5691172414766986e-05, "loss": 1.6980457305908203, "num_input_tokens_seen": 94965665, "step": 1455, "train_runtime": 31783.5013, "train_tokens_per_second": 2987.892 }, { "epoch": 0.9245912049531672, "grad_norm": 1.2873483896255493, "learning_rate": 1.568570060367349e-05, "loss": 1.696563720703125, "num_input_tokens_seen": 95031166, "step": 1456, "train_runtime": 31805.3611, "train_tokens_per_second": 2987.898 }, { "epoch": 0.9252262263851405, "grad_norm": 1.3132662773132324, "learning_rate": 1.5680226275878245e-05, "loss": 1.6637195348739624, "num_input_tokens_seen": 95096634, "step": 1457, "train_runtime": 31826.7799, "train_tokens_per_second": 2987.944 }, { "epoch": 0.9258612478171139, "grad_norm": 1.238887071609497, "learning_rate": 1.5674749433804392e-05, "loss": 1.6574492454528809, "num_input_tokens_seen": 95162135, "step": 1458, "train_runtime": 31848.2963, "train_tokens_per_second": 2987.982 }, { "epoch": 0.9264962692490871, "grad_norm": 1.1655179262161255, "learning_rate": 1.5669270079876183e-05, "loss": 1.55534827709198, "num_input_tokens_seen": 95227570, "step": 1459, "train_runtime": 31869.9705, "train_tokens_per_second": 2988.003 }, { "epoch": 0.9271312906810605, "grad_norm": 1.304463267326355, "learning_rate": 1.5663788216518983e-05, "loss": 1.7898145914077759, "num_input_tokens_seen": 95292982, "step": 1460, "train_runtime": 31891.6219, "train_tokens_per_second": 2988.026 }, { "epoch": 0.9277663121130338, "grad_norm": 1.2898730039596558, "learning_rate": 1.5658303846159274e-05, "loss": 1.7482997179031372, "num_input_tokens_seen": 95358475, "step": 1461, "train_runtime": 31912.6682, "train_tokens_per_second": 2988.107 }, { "epoch": 0.9284013335450071, "grad_norm": 1.3958109617233276, "learning_rate": 1.565281697122463e-05, "loss": 1.8598278760910034, "num_input_tokens_seen": 95423896, "step": 1462, "train_runtime": 31934.6346, "train_tokens_per_second": 2988.1 }, { "epoch": 0.9290363549769804, "grad_norm": 1.1978524923324585, "learning_rate": 1.564732759414376e-05, "loss": 1.6770942211151123, "num_input_tokens_seen": 95489413, "step": 1463, "train_runtime": 31956.6052, "train_tokens_per_second": 2988.096 }, { "epoch": 0.9296713764089538, "grad_norm": 1.321711778640747, "learning_rate": 1.564183571734645e-05, "loss": 1.6925501823425293, "num_input_tokens_seen": 95554882, "step": 1464, "train_runtime": 31978.0571, "train_tokens_per_second": 2988.139 }, { "epoch": 0.9303063978409272, "grad_norm": 1.2166297435760498, "learning_rate": 1.5636341343263616e-05, "loss": 1.3912417888641357, "num_input_tokens_seen": 95620376, "step": 1465, "train_runtime": 32000.0982, "train_tokens_per_second": 2988.128 }, { "epoch": 0.9309414192729004, "grad_norm": 1.3569281101226807, "learning_rate": 1.5630844474327273e-05, "loss": 1.716776967048645, "num_input_tokens_seen": 95685861, "step": 1466, "train_runtime": 32021.6545, "train_tokens_per_second": 2988.161 }, { "epoch": 0.9315764407048738, "grad_norm": 1.3171534538269043, "learning_rate": 1.5625345112970533e-05, "loss": 1.6351525783538818, "num_input_tokens_seen": 95751372, "step": 1467, "train_runtime": 32042.9189, "train_tokens_per_second": 2988.223 }, { "epoch": 0.9322114621368471, "grad_norm": 1.344931721687317, "learning_rate": 1.5619843261627624e-05, "loss": 1.694390058517456, "num_input_tokens_seen": 95816858, "step": 1468, "train_runtime": 32064.8593, "train_tokens_per_second": 2988.22 }, { "epoch": 0.9328464835688205, "grad_norm": 1.2935339212417603, "learning_rate": 1.5614338922733865e-05, "loss": 1.6205419301986694, "num_input_tokens_seen": 95882314, "step": 1469, "train_runtime": 32086.2504, "train_tokens_per_second": 2988.268 }, { "epoch": 0.9334815050007937, "grad_norm": 1.2030051946640015, "learning_rate": 1.5608832098725684e-05, "loss": 1.6530531644821167, "num_input_tokens_seen": 95947745, "step": 1470, "train_runtime": 32106.8461, "train_tokens_per_second": 2988.389 }, { "epoch": 0.9341165264327671, "grad_norm": 1.2547110319137573, "learning_rate": 1.5603322792040597e-05, "loss": 1.5847574472427368, "num_input_tokens_seen": 96013153, "step": 1471, "train_runtime": 32127.7525, "train_tokens_per_second": 2988.48 }, { "epoch": 0.9347515478647405, "grad_norm": 1.2542564868927002, "learning_rate": 1.559781100511724e-05, "loss": 1.650846004486084, "num_input_tokens_seen": 96078636, "step": 1472, "train_runtime": 32149.0314, "train_tokens_per_second": 2988.539 }, { "epoch": 0.9353865692967137, "grad_norm": 1.2087057828903198, "learning_rate": 1.559229674039532e-05, "loss": 1.4855659008026123, "num_input_tokens_seen": 96144128, "step": 1473, "train_runtime": 32169.9639, "train_tokens_per_second": 2988.63 }, { "epoch": 0.9360215907286871, "grad_norm": 1.0834147930145264, "learning_rate": 1.558678000031567e-05, "loss": 1.580356240272522, "num_input_tokens_seen": 96209501, "step": 1474, "train_runtime": 32190.7814, "train_tokens_per_second": 2988.728 }, { "epoch": 0.9366566121606604, "grad_norm": 1.1865200996398926, "learning_rate": 1.558126078732019e-05, "loss": 1.5911526679992676, "num_input_tokens_seen": 96274974, "step": 1475, "train_runtime": 32212.1677, "train_tokens_per_second": 2988.777 }, { "epoch": 0.9372916335926338, "grad_norm": 1.2146844863891602, "learning_rate": 1.5575739103851898e-05, "loss": 1.6680915355682373, "num_input_tokens_seen": 96340450, "step": 1476, "train_runtime": 32232.8515, "train_tokens_per_second": 2988.89 }, { "epoch": 0.937926655024607, "grad_norm": 1.2261842489242554, "learning_rate": 1.5570214952354884e-05, "loss": 1.5592046976089478, "num_input_tokens_seen": 96405868, "step": 1477, "train_runtime": 32255.0299, "train_tokens_per_second": 2988.863 }, { "epoch": 0.9385616764565804, "grad_norm": 1.1852805614471436, "learning_rate": 1.5564688335274357e-05, "loss": 1.6820030212402344, "num_input_tokens_seen": 96471248, "step": 1478, "train_runtime": 32275.5552, "train_tokens_per_second": 2988.988 }, { "epoch": 0.9391966978885538, "grad_norm": 1.283897876739502, "learning_rate": 1.5559159255056592e-05, "loss": 1.8013886213302612, "num_input_tokens_seen": 96536746, "step": 1479, "train_runtime": 32297.6836, "train_tokens_per_second": 2988.968 }, { "epoch": 0.9398317193205271, "grad_norm": 1.1908279657363892, "learning_rate": 1.5553627714148965e-05, "loss": 1.569469690322876, "num_input_tokens_seen": 96602062, "step": 1480, "train_runtime": 32319.0131, "train_tokens_per_second": 2989.016 }, { "epoch": 0.9404667407525004, "grad_norm": 1.2517815828323364, "learning_rate": 1.554809371499995e-05, "loss": 1.5523380041122437, "num_input_tokens_seen": 96667564, "step": 1481, "train_runtime": 32339.4774, "train_tokens_per_second": 2989.15 }, { "epoch": 0.9411017621844737, "grad_norm": 1.3838591575622559, "learning_rate": 1.5542557260059093e-05, "loss": 1.5853155851364136, "num_input_tokens_seen": 96733004, "step": 1482, "train_runtime": 32361.3458, "train_tokens_per_second": 2989.153 }, { "epoch": 0.9417367836164471, "grad_norm": 1.1474319696426392, "learning_rate": 1.553701835177703e-05, "loss": 1.6753023862838745, "num_input_tokens_seen": 96798487, "step": 1483, "train_runtime": 32382.5997, "train_tokens_per_second": 2989.213 }, { "epoch": 0.9423718050484203, "grad_norm": 1.2910668849945068, "learning_rate": 1.5531476992605496e-05, "loss": 1.5387349128723145, "num_input_tokens_seen": 96863956, "step": 1484, "train_runtime": 32404.1677, "train_tokens_per_second": 2989.244 }, { "epoch": 0.9430068264803937, "grad_norm": 1.1562992334365845, "learning_rate": 1.5525933184997298e-05, "loss": 1.5467102527618408, "num_input_tokens_seen": 96929478, "step": 1485, "train_runtime": 32425.5417, "train_tokens_per_second": 2989.294 }, { "epoch": 0.943641847912367, "grad_norm": 1.2693449258804321, "learning_rate": 1.5520386931406326e-05, "loss": 1.756213665008545, "num_input_tokens_seen": 96994928, "step": 1486, "train_runtime": 32446.3955, "train_tokens_per_second": 2989.39 }, { "epoch": 0.9442768693443404, "grad_norm": 1.1671946048736572, "learning_rate": 1.5514838234287565e-05, "loss": 1.5183056592941284, "num_input_tokens_seen": 97060445, "step": 1487, "train_runtime": 32467.7224, "train_tokens_per_second": 2989.444 }, { "epoch": 0.9449118907763137, "grad_norm": 1.1945501565933228, "learning_rate": 1.550928709609707e-05, "loss": 1.6978005170822144, "num_input_tokens_seen": 97125941, "step": 1488, "train_runtime": 32489.5765, "train_tokens_per_second": 2989.449 }, { "epoch": 0.945546912208287, "grad_norm": 1.188677430152893, "learning_rate": 1.5503733519291982e-05, "loss": 1.5113856792449951, "num_input_tokens_seen": 97191378, "step": 1489, "train_runtime": 32510.7509, "train_tokens_per_second": 2989.515 }, { "epoch": 0.9461819336402604, "grad_norm": 1.22895085811615, "learning_rate": 1.549817750633052e-05, "loss": 1.7457526922225952, "num_input_tokens_seen": 97256901, "step": 1490, "train_runtime": 32532.2039, "train_tokens_per_second": 2989.558 }, { "epoch": 0.9468169550722337, "grad_norm": 1.345982551574707, "learning_rate": 1.5492619059671977e-05, "loss": 1.6421630382537842, "num_input_tokens_seen": 97322299, "step": 1491, "train_runtime": 32553.6339, "train_tokens_per_second": 2989.599 }, { "epoch": 0.947451976504207, "grad_norm": 1.0749285221099854, "learning_rate": 1.5487058181776734e-05, "loss": 1.4318134784698486, "num_input_tokens_seen": 97387752, "step": 1492, "train_runtime": 32574.1469, "train_tokens_per_second": 2989.725 }, { "epoch": 0.9480869979361803, "grad_norm": 1.29539155960083, "learning_rate": 1.5481494875106236e-05, "loss": 1.7093379497528076, "num_input_tokens_seen": 97453103, "step": 1493, "train_runtime": 32595.2718, "train_tokens_per_second": 2989.793 }, { "epoch": 0.9487220193681537, "grad_norm": 1.1341874599456787, "learning_rate": 1.5475929142123012e-05, "loss": 1.6502695083618164, "num_input_tokens_seen": 97518454, "step": 1494, "train_runtime": 32617.2077, "train_tokens_per_second": 2989.785 }, { "epoch": 0.949357040800127, "grad_norm": 1.0835086107254028, "learning_rate": 1.5470360985290663e-05, "loss": 1.6409673690795898, "num_input_tokens_seen": 97583988, "step": 1495, "train_runtime": 32638.9186, "train_tokens_per_second": 2989.805 }, { "epoch": 0.9499920622321003, "grad_norm": 1.170890212059021, "learning_rate": 1.5464790407073854e-05, "loss": 1.6935462951660156, "num_input_tokens_seen": 97649454, "step": 1496, "train_runtime": 32659.9298, "train_tokens_per_second": 2989.886 }, { "epoch": 0.9506270836640737, "grad_norm": 1.241437554359436, "learning_rate": 1.5459217409938338e-05, "loss": 1.611081838607788, "num_input_tokens_seen": 97714973, "step": 1497, "train_runtime": 32681.4609, "train_tokens_per_second": 2989.921 }, { "epoch": 0.951262105096047, "grad_norm": 1.1566587686538696, "learning_rate": 1.5453641996350923e-05, "loss": 1.5407383441925049, "num_input_tokens_seen": 97780471, "step": 1498, "train_runtime": 32702.8009, "train_tokens_per_second": 2989.972 }, { "epoch": 0.9518971265280203, "grad_norm": 1.1561452150344849, "learning_rate": 1.54480641687795e-05, "loss": 1.6417179107666016, "num_input_tokens_seen": 97845921, "step": 1499, "train_runtime": 32724.5637, "train_tokens_per_second": 2989.984 }, { "epoch": 0.9525321479599936, "grad_norm": 1.3792335987091064, "learning_rate": 1.5442483929693022e-05, "loss": 1.7383780479431152, "num_input_tokens_seen": 97911367, "step": 1500, "train_runtime": 32746.7741, "train_tokens_per_second": 2989.955 }, { "epoch": 0.9525321479599936, "eval_loss": 1.5553393363952637, "eval_runtime": 12.8874, "eval_samples_per_second": 1.785, "eval_steps_per_second": 0.931, "num_input_tokens_seen": 97911367, "step": 1500 }, { "epoch": 0.953167169391967, "grad_norm": 1.2673313617706299, "learning_rate": 1.54369012815615e-05, "loss": 1.7193881273269653, "num_input_tokens_seen": 97976730, "step": 1501, "train_runtime": 32819.0744, "train_tokens_per_second": 2985.359 }, { "epoch": 0.9538021908239404, "grad_norm": 1.1732535362243652, "learning_rate": 1.5431316226856033e-05, "loss": 1.4943103790283203, "num_input_tokens_seen": 98042200, "step": 1502, "train_runtime": 32840.7045, "train_tokens_per_second": 2985.387 }, { "epoch": 0.9544372122559136, "grad_norm": 1.1796213388442993, "learning_rate": 1.5425728768048765e-05, "loss": 1.5433034896850586, "num_input_tokens_seen": 98107568, "step": 1503, "train_runtime": 32861.9491, "train_tokens_per_second": 2985.446 }, { "epoch": 0.955072233687887, "grad_norm": 1.176949381828308, "learning_rate": 1.5420138907612915e-05, "loss": 1.6452062129974365, "num_input_tokens_seen": 98172927, "step": 1504, "train_runtime": 32883.5992, "train_tokens_per_second": 2985.468 }, { "epoch": 0.9557072551198603, "grad_norm": 1.1955360174179077, "learning_rate": 1.5414546648022765e-05, "loss": 1.651239275932312, "num_input_tokens_seen": 98238353, "step": 1505, "train_runtime": 32904.7961, "train_tokens_per_second": 2985.533 }, { "epoch": 0.9563422765518336, "grad_norm": 1.148253083229065, "learning_rate": 1.5408951991753653e-05, "loss": 1.6550766229629517, "num_input_tokens_seen": 98303807, "step": 1506, "train_runtime": 32926.7376, "train_tokens_per_second": 2985.531 }, { "epoch": 0.9569772979838069, "grad_norm": 1.1681689023971558, "learning_rate": 1.5403354941281978e-05, "loss": 1.6043307781219482, "num_input_tokens_seen": 98369273, "step": 1507, "train_runtime": 32947.6311, "train_tokens_per_second": 2985.625 }, { "epoch": 0.9576123194157803, "grad_norm": 1.1978641748428345, "learning_rate": 1.539775549908521e-05, "loss": 1.5651787519454956, "num_input_tokens_seen": 98434740, "step": 1508, "train_runtime": 32968.1838, "train_tokens_per_second": 2985.75 }, { "epoch": 0.9582473408477536, "grad_norm": 1.307988166809082, "learning_rate": 1.5392153667641865e-05, "loss": 1.6945713758468628, "num_input_tokens_seen": 98500142, "step": 1509, "train_runtime": 32988.8517, "train_tokens_per_second": 2985.861 }, { "epoch": 0.9588823622797269, "grad_norm": 1.1929384469985962, "learning_rate": 1.538654944943152e-05, "loss": 1.59690260887146, "num_input_tokens_seen": 98565631, "step": 1510, "train_runtime": 33010.3495, "train_tokens_per_second": 2985.901 }, { "epoch": 0.9595173837117003, "grad_norm": 1.3789808750152588, "learning_rate": 1.5380942846934812e-05, "loss": 1.7432117462158203, "num_input_tokens_seen": 98631069, "step": 1511, "train_runtime": 33031.9423, "train_tokens_per_second": 2985.93 }, { "epoch": 0.9601524051436736, "grad_norm": 1.2309807538986206, "learning_rate": 1.537533386263343e-05, "loss": 1.5977863073349, "num_input_tokens_seen": 98696574, "step": 1512, "train_runtime": 33053.7193, "train_tokens_per_second": 2985.945 }, { "epoch": 0.960787426575647, "grad_norm": 1.3993467092514038, "learning_rate": 1.5369722499010114e-05, "loss": 1.6853654384613037, "num_input_tokens_seen": 98762039, "step": 1513, "train_runtime": 33075.3608, "train_tokens_per_second": 2985.97 }, { "epoch": 0.9614224480076202, "grad_norm": 1.267243504524231, "learning_rate": 1.5364108758548676e-05, "loss": 1.7298067808151245, "num_input_tokens_seen": 98827405, "step": 1514, "train_runtime": 33096.9881, "train_tokens_per_second": 2985.994 }, { "epoch": 0.9620574694395936, "grad_norm": 1.1360119581222534, "learning_rate": 1.5358492643733947e-05, "loss": 1.5605320930480957, "num_input_tokens_seen": 98892873, "step": 1515, "train_runtime": 33118.2771, "train_tokens_per_second": 2986.051 }, { "epoch": 0.9626924908715669, "grad_norm": 1.145632266998291, "learning_rate": 1.535287415705184e-05, "loss": 1.6702091693878174, "num_input_tokens_seen": 98958344, "step": 1516, "train_runtime": 33139.713, "train_tokens_per_second": 2986.095 }, { "epoch": 0.9633275123035402, "grad_norm": 1.2487884759902954, "learning_rate": 1.53472533009893e-05, "loss": 1.6685349941253662, "num_input_tokens_seen": 99023784, "step": 1517, "train_runtime": 33160.6799, "train_tokens_per_second": 2986.181 }, { "epoch": 0.9639625337355135, "grad_norm": 1.0518097877502441, "learning_rate": 1.5341630078034328e-05, "loss": 1.5740506649017334, "num_input_tokens_seen": 99089303, "step": 1518, "train_runtime": 33181.2602, "train_tokens_per_second": 2986.303 }, { "epoch": 0.9645975551674869, "grad_norm": 1.2479671239852905, "learning_rate": 1.533600449067597e-05, "loss": 1.5250425338745117, "num_input_tokens_seen": 99154700, "step": 1519, "train_runtime": 33202.3255, "train_tokens_per_second": 2986.378 }, { "epoch": 0.9652325765994603, "grad_norm": 1.1769769191741943, "learning_rate": 1.533037654140432e-05, "loss": 1.4560223817825317, "num_input_tokens_seen": 99220134, "step": 1520, "train_runtime": 33223.013, "train_tokens_per_second": 2986.488 }, { "epoch": 0.9658675980314335, "grad_norm": 1.222569465637207, "learning_rate": 1.5324746232710513e-05, "loss": 1.646465539932251, "num_input_tokens_seen": 99285445, "step": 1521, "train_runtime": 33244.5334, "train_tokens_per_second": 2986.519 }, { "epoch": 0.9665026194634069, "grad_norm": 1.2099145650863647, "learning_rate": 1.5319113567086738e-05, "loss": 1.6261463165283203, "num_input_tokens_seen": 99350929, "step": 1522, "train_runtime": 33266.0275, "train_tokens_per_second": 2986.558 }, { "epoch": 0.9671376408953802, "grad_norm": 1.3308309316635132, "learning_rate": 1.5313478547026222e-05, "loss": 1.7736749649047852, "num_input_tokens_seen": 99416420, "step": 1523, "train_runtime": 33287.3427, "train_tokens_per_second": 2986.613 }, { "epoch": 0.9677726623273536, "grad_norm": 1.3071508407592773, "learning_rate": 1.5307841175023226e-05, "loss": 1.5883828401565552, "num_input_tokens_seen": 99481858, "step": 1524, "train_runtime": 33308.9764, "train_tokens_per_second": 2986.638 }, { "epoch": 0.9684076837593268, "grad_norm": 1.1723953485488892, "learning_rate": 1.5302201453573072e-05, "loss": 1.499626874923706, "num_input_tokens_seen": 99547349, "step": 1525, "train_runtime": 33329.5515, "train_tokens_per_second": 2986.759 }, { "epoch": 0.9690427051913002, "grad_norm": 1.3596853017807007, "learning_rate": 1.5296559385172095e-05, "loss": 1.7035208940505981, "num_input_tokens_seen": 99612841, "step": 1526, "train_runtime": 33350.8848, "train_tokens_per_second": 2986.813 }, { "epoch": 0.9696777266232736, "grad_norm": 1.3595021963119507, "learning_rate": 1.5290914972317693e-05, "loss": 1.629455804824829, "num_input_tokens_seen": 99678292, "step": 1527, "train_runtime": 33372.3761, "train_tokens_per_second": 2986.85 }, { "epoch": 0.9703127480552468, "grad_norm": 1.1137535572052002, "learning_rate": 1.5285268217508293e-05, "loss": 1.4909162521362305, "num_input_tokens_seen": 99743806, "step": 1528, "train_runtime": 33393.3067, "train_tokens_per_second": 2986.94 }, { "epoch": 0.9709477694872202, "grad_norm": 1.306488037109375, "learning_rate": 1.527961912324335e-05, "loss": 1.805129885673523, "num_input_tokens_seen": 99809180, "step": 1529, "train_runtime": 33415.084, "train_tokens_per_second": 2986.95 }, { "epoch": 0.9715827909191935, "grad_norm": 1.1382601261138916, "learning_rate": 1.527396769202337e-05, "loss": 1.5146156549453735, "num_input_tokens_seen": 99874704, "step": 1530, "train_runtime": 33435.896, "train_tokens_per_second": 2987.05 }, { "epoch": 0.9722178123511669, "grad_norm": 1.2229446172714233, "learning_rate": 1.526831392634988e-05, "loss": 1.552220344543457, "num_input_tokens_seen": 99940207, "step": 1531, "train_runtime": 33457.0468, "train_tokens_per_second": 2987.12 }, { "epoch": 0.9728528337831401, "grad_norm": 1.4689013957977295, "learning_rate": 1.5262657828725456e-05, "loss": 1.7055665254592896, "num_input_tokens_seen": 100005743, "step": 1532, "train_runtime": 33479.4377, "train_tokens_per_second": 2987.08 }, { "epoch": 0.9734878552151135, "grad_norm": 1.141971468925476, "learning_rate": 1.5256999401653686e-05, "loss": 1.5310170650482178, "num_input_tokens_seen": 100071196, "step": 1533, "train_runtime": 33500.4516, "train_tokens_per_second": 2987.16 }, { "epoch": 0.9741228766470869, "grad_norm": 1.1805171966552734, "learning_rate": 1.5251338647639204e-05, "loss": 1.7018113136291504, "num_input_tokens_seen": 100136656, "step": 1534, "train_runtime": 33521.3171, "train_tokens_per_second": 2987.253 }, { "epoch": 0.9747578980790602, "grad_norm": 1.2682310342788696, "learning_rate": 1.524567556918767e-05, "loss": 1.695586919784546, "num_input_tokens_seen": 100202031, "step": 1535, "train_runtime": 33542.5597, "train_tokens_per_second": 2987.31 }, { "epoch": 0.9753929195110335, "grad_norm": 1.203750729560852, "learning_rate": 1.524001016880577e-05, "loss": 1.6259427070617676, "num_input_tokens_seen": 100267512, "step": 1536, "train_runtime": 33563.4112, "train_tokens_per_second": 2987.405 }, { "epoch": 0.9760279409430068, "grad_norm": 1.1942882537841797, "learning_rate": 1.523434244900122e-05, "loss": 1.7569286823272705, "num_input_tokens_seen": 100332965, "step": 1537, "train_runtime": 33584.724, "train_tokens_per_second": 2987.458 }, { "epoch": 0.9766629623749802, "grad_norm": 1.0562970638275146, "learning_rate": 1.5228672412282766e-05, "loss": 1.5012547969818115, "num_input_tokens_seen": 100398481, "step": 1538, "train_runtime": 33605.4895, "train_tokens_per_second": 2987.562 }, { "epoch": 0.9772979838069534, "grad_norm": 1.4606232643127441, "learning_rate": 1.5223000061160171e-05, "loss": 1.9040756225585938, "num_input_tokens_seen": 100463960, "step": 1539, "train_runtime": 33627.7115, "train_tokens_per_second": 2987.535 }, { "epoch": 0.9779330052389268, "grad_norm": 1.2031337022781372, "learning_rate": 1.5217325398144234e-05, "loss": 1.7428911924362183, "num_input_tokens_seen": 100529427, "step": 1540, "train_runtime": 33648.9408, "train_tokens_per_second": 2987.596 }, { "epoch": 0.9785680266709001, "grad_norm": 1.0443639755249023, "learning_rate": 1.5211648425746765e-05, "loss": 1.428243637084961, "num_input_tokens_seen": 100594897, "step": 1541, "train_runtime": 33670.3531, "train_tokens_per_second": 2987.64 }, { "epoch": 0.9792030481028735, "grad_norm": 1.138171672821045, "learning_rate": 1.5205969146480611e-05, "loss": 1.5734457969665527, "num_input_tokens_seen": 100660370, "step": 1542, "train_runtime": 33691.5189, "train_tokens_per_second": 2987.706 }, { "epoch": 0.9798380695348468, "grad_norm": 1.1998499631881714, "learning_rate": 1.5200287562859623e-05, "loss": 1.7624528408050537, "num_input_tokens_seen": 100725793, "step": 1543, "train_runtime": 33713.3848, "train_tokens_per_second": 2987.709 }, { "epoch": 0.9804730909668201, "grad_norm": 1.219166874885559, "learning_rate": 1.5194603677398682e-05, "loss": 1.5981107950210571, "num_input_tokens_seen": 100791292, "step": 1544, "train_runtime": 33734.6893, "train_tokens_per_second": 2987.764 }, { "epoch": 0.9811081123987935, "grad_norm": 1.213334321975708, "learning_rate": 1.518891749261369e-05, "loss": 1.4822207689285278, "num_input_tokens_seen": 100849371, "step": 1545, "train_runtime": 33753.7624, "train_tokens_per_second": 2987.796 }, { "epoch": 0.9817431338307668, "grad_norm": 1.1382685899734497, "learning_rate": 1.518322901102156e-05, "loss": 1.5227088928222656, "num_input_tokens_seen": 100914864, "step": 1546, "train_runtime": 33774.8659, "train_tokens_per_second": 2987.869 }, { "epoch": 0.9823781552627401, "grad_norm": 1.1113076210021973, "learning_rate": 1.5177538235140223e-05, "loss": 1.4511195421218872, "num_input_tokens_seen": 100980380, "step": 1547, "train_runtime": 33795.9657, "train_tokens_per_second": 2987.942 }, { "epoch": 0.9830131766947134, "grad_norm": 1.2835277318954468, "learning_rate": 1.5171845167488633e-05, "loss": 1.922048807144165, "num_input_tokens_seen": 101045836, "step": 1548, "train_runtime": 33818.6007, "train_tokens_per_second": 2987.877 }, { "epoch": 0.9836481981266868, "grad_norm": 1.2937633991241455, "learning_rate": 1.516614981058675e-05, "loss": 1.6357498168945312, "num_input_tokens_seen": 101111360, "step": 1549, "train_runtime": 33840.2891, "train_tokens_per_second": 2987.899 }, { "epoch": 0.98428321955866, "grad_norm": 1.2136776447296143, "learning_rate": 1.5160452166955546e-05, "loss": 1.7284423112869263, "num_input_tokens_seen": 101176747, "step": 1550, "train_runtime": 33862.2842, "train_tokens_per_second": 2987.889 }, { "epoch": 0.9849182409906334, "grad_norm": 1.115655541419983, "learning_rate": 1.5154752239117016e-05, "loss": 1.5805716514587402, "num_input_tokens_seen": 101242214, "step": 1551, "train_runtime": 33883.5382, "train_tokens_per_second": 2987.947 }, { "epoch": 0.9855532624226068, "grad_norm": 1.1898151636123657, "learning_rate": 1.5149050029594152e-05, "loss": 1.727461576461792, "num_input_tokens_seen": 101307563, "step": 1552, "train_runtime": 33904.3959, "train_tokens_per_second": 2988.036 }, { "epoch": 0.9861882838545801, "grad_norm": 1.2720509767532349, "learning_rate": 1.514334554091097e-05, "loss": 1.5841798782348633, "num_input_tokens_seen": 101373061, "step": 1553, "train_runtime": 33926.9562, "train_tokens_per_second": 2987.98 }, { "epoch": 0.9868233052865534, "grad_norm": 1.3013018369674683, "learning_rate": 1.5137638775592485e-05, "loss": 1.8153035640716553, "num_input_tokens_seen": 101438597, "step": 1554, "train_runtime": 33948.9682, "train_tokens_per_second": 2987.973 }, { "epoch": 0.9874583267185267, "grad_norm": 1.186911702156067, "learning_rate": 1.513192973616472e-05, "loss": 1.5644735097885132, "num_input_tokens_seen": 101504106, "step": 1555, "train_runtime": 33970.5008, "train_tokens_per_second": 2988.007 }, { "epoch": 0.9880933481505001, "grad_norm": 1.2172000408172607, "learning_rate": 1.512621842515471e-05, "loss": 1.6181455850601196, "num_input_tokens_seen": 101569484, "step": 1556, "train_runtime": 33991.073, "train_tokens_per_second": 2988.122 }, { "epoch": 0.9887283695824735, "grad_norm": 1.3154956102371216, "learning_rate": 1.5120504845090499e-05, "loss": 1.6071062088012695, "num_input_tokens_seen": 101634845, "step": 1557, "train_runtime": 34012.4054, "train_tokens_per_second": 2988.17 }, { "epoch": 0.9893633910144467, "grad_norm": 1.1360255479812622, "learning_rate": 1.5114788998501117e-05, "loss": 1.5865639448165894, "num_input_tokens_seen": 101700249, "step": 1558, "train_runtime": 34033.1646, "train_tokens_per_second": 2988.269 }, { "epoch": 0.9899984124464201, "grad_norm": 1.2220790386199951, "learning_rate": 1.5109070887916617e-05, "loss": 1.598193883895874, "num_input_tokens_seen": 101765681, "step": 1559, "train_runtime": 34054.7749, "train_tokens_per_second": 2988.294 }, { "epoch": 0.9906334338783934, "grad_norm": 1.168395757675171, "learning_rate": 1.5103350515868047e-05, "loss": 1.432114839553833, "num_input_tokens_seen": 101831189, "step": 1560, "train_runtime": 34075.8465, "train_tokens_per_second": 2988.369 }, { "epoch": 0.9912684553103667, "grad_norm": 1.2036036252975464, "learning_rate": 1.5097627884887454e-05, "loss": 1.592482566833496, "num_input_tokens_seen": 101896704, "step": 1561, "train_runtime": 34096.8847, "train_tokens_per_second": 2988.446 }, { "epoch": 0.99190347674234, "grad_norm": 1.237019419670105, "learning_rate": 1.5091902997507885e-05, "loss": 1.6210857629776, "num_input_tokens_seen": 101962103, "step": 1562, "train_runtime": 34117.7802, "train_tokens_per_second": 2988.533 }, { "epoch": 0.9925384981743134, "grad_norm": 1.2238926887512207, "learning_rate": 1.5086175856263392e-05, "loss": 1.775238275527954, "num_input_tokens_seen": 102027551, "step": 1563, "train_runtime": 34138.6936, "train_tokens_per_second": 2988.619 }, { "epoch": 0.9931735196062867, "grad_norm": 1.1951382160186768, "learning_rate": 1.5080446463689013e-05, "loss": 1.655987024307251, "num_input_tokens_seen": 102092981, "step": 1564, "train_runtime": 34160.2802, "train_tokens_per_second": 2988.646 }, { "epoch": 0.99380854103826, "grad_norm": 1.2390222549438477, "learning_rate": 1.5074714822320795e-05, "loss": 1.5980525016784668, "num_input_tokens_seen": 102158329, "step": 1565, "train_runtime": 34181.4818, "train_tokens_per_second": 2988.704 }, { "epoch": 0.9944435624702334, "grad_norm": 1.1187180280685425, "learning_rate": 1.5068980934695771e-05, "loss": 1.5614898204803467, "num_input_tokens_seen": 102223850, "step": 1566, "train_runtime": 34202.8121, "train_tokens_per_second": 2988.756 }, { "epoch": 0.9950785839022067, "grad_norm": 1.2935212850570679, "learning_rate": 1.5063244803351975e-05, "loss": 1.5013433694839478, "num_input_tokens_seen": 102281322, "step": 1567, "train_runtime": 34221.6314, "train_tokens_per_second": 2988.792 }, { "epoch": 0.9957136053341801, "grad_norm": 1.3575770854949951, "learning_rate": 1.5057506430828432e-05, "loss": 1.8241121768951416, "num_input_tokens_seen": 102346782, "step": 1568, "train_runtime": 34243.4099, "train_tokens_per_second": 2988.802 }, { "epoch": 0.9963486267661533, "grad_norm": 1.2143208980560303, "learning_rate": 1.5051765819665157e-05, "loss": 1.4342212677001953, "num_input_tokens_seen": 102412258, "step": 1569, "train_runtime": 34264.5486, "train_tokens_per_second": 2988.869 }, { "epoch": 0.9969836481981267, "grad_norm": 1.2767817974090576, "learning_rate": 1.5046022972403154e-05, "loss": 1.843186855316162, "num_input_tokens_seen": 102477716, "step": 1570, "train_runtime": 34287.147, "train_tokens_per_second": 2988.808 }, { "epoch": 0.9976186696301, "grad_norm": 1.3310022354125977, "learning_rate": 1.5040277891584423e-05, "loss": 1.7517282962799072, "num_input_tokens_seen": 102543200, "step": 1571, "train_runtime": 34309.4009, "train_tokens_per_second": 2988.779 }, { "epoch": 0.9982536910620733, "grad_norm": 1.4044839143753052, "learning_rate": 1.503453057975195e-05, "loss": 1.8000450134277344, "num_input_tokens_seen": 102608614, "step": 1572, "train_runtime": 34331.0637, "train_tokens_per_second": 2988.798 }, { "epoch": 0.9988887124940466, "grad_norm": 1.2700910568237305, "learning_rate": 1.502878103944971e-05, "loss": 1.7137657403945923, "num_input_tokens_seen": 102674022, "step": 1573, "train_runtime": 34352.4736, "train_tokens_per_second": 2988.839 }, { "epoch": 0.99952373392602, "grad_norm": 1.220262885093689, "learning_rate": 1.5023029273222655e-05, "loss": 1.7701143026351929, "num_input_tokens_seen": 102739520, "step": 1574, "train_runtime": 34374.2922, "train_tokens_per_second": 2988.848 }, { "epoch": 1.0, "grad_norm": 1.4758895635604858, "learning_rate": 1.5017275283616739e-05, "loss": 1.7390308380126953, "num_input_tokens_seen": 102780430, "step": 1575, "train_runtime": 34387.3308, "train_tokens_per_second": 2988.904 }, { "epoch": 1.0006350214319732, "grad_norm": 1.2351878881454468, "learning_rate": 1.5011519073178883e-05, "loss": 1.679036259651184, "num_input_tokens_seen": 102845922, "step": 1576, "train_runtime": 34408.6691, "train_tokens_per_second": 2988.954 }, { "epoch": 1.0012700428639467, "grad_norm": 1.2411237955093384, "learning_rate": 1.500576064445701e-05, "loss": 1.6666309833526611, "num_input_tokens_seen": 102911377, "step": 1577, "train_runtime": 34430.222, "train_tokens_per_second": 2988.984 }, { "epoch": 1.00190506429592, "grad_norm": 1.3057373762130737, "learning_rate": 1.5000000000000002e-05, "loss": 1.6563878059387207, "num_input_tokens_seen": 102976805, "step": 1578, "train_runtime": 34451.6787, "train_tokens_per_second": 2989.021 }, { "epoch": 1.0025400857278932, "grad_norm": 1.2846375703811646, "learning_rate": 1.499423714235774e-05, "loss": 1.6300139427185059, "num_input_tokens_seen": 103042196, "step": 1579, "train_runtime": 34472.1895, "train_tokens_per_second": 2989.14 }, { "epoch": 1.0031751071598667, "grad_norm": 1.119695782661438, "learning_rate": 1.4988472074081077e-05, "loss": 1.5153241157531738, "num_input_tokens_seen": 103107645, "step": 1580, "train_runtime": 34492.5738, "train_tokens_per_second": 2989.271 }, { "epoch": 1.00381012859184, "grad_norm": 1.2647494077682495, "learning_rate": 1.498270479772184e-05, "loss": 1.609708309173584, "num_input_tokens_seen": 103173095, "step": 1581, "train_runtime": 34514.7986, "train_tokens_per_second": 2989.242 }, { "epoch": 1.0044451500238134, "grad_norm": 1.2440853118896484, "learning_rate": 1.4976935315832853e-05, "loss": 1.7756319046020508, "num_input_tokens_seen": 103238567, "step": 1582, "train_runtime": 34536.6449, "train_tokens_per_second": 2989.247 }, { "epoch": 1.0050801714557867, "grad_norm": 1.2801777124404907, "learning_rate": 1.497116363096789e-05, "loss": 1.7450709342956543, "num_input_tokens_seen": 103304094, "step": 1583, "train_runtime": 34557.7587, "train_tokens_per_second": 2989.317 }, { "epoch": 1.00571519288776, "grad_norm": 1.3289743661880493, "learning_rate": 1.4965389745681717e-05, "loss": 1.8237676620483398, "num_input_tokens_seen": 103369482, "step": 1584, "train_runtime": 34578.9268, "train_tokens_per_second": 2989.378 }, { "epoch": 1.0063502143197334, "grad_norm": 1.1553007364273071, "learning_rate": 1.4959613662530073e-05, "loss": 1.5664927959442139, "num_input_tokens_seen": 103434987, "step": 1585, "train_runtime": 34600.5533, "train_tokens_per_second": 2989.403 }, { "epoch": 1.0069852357517066, "grad_norm": 1.150334119796753, "learning_rate": 1.495383538406966e-05, "loss": 1.502195119857788, "num_input_tokens_seen": 103500487, "step": 1586, "train_runtime": 34620.8844, "train_tokens_per_second": 2989.539 }, { "epoch": 1.0076202571836799, "grad_norm": 1.1992238759994507, "learning_rate": 1.494805491285816e-05, "loss": 1.4453227519989014, "num_input_tokens_seen": 103565927, "step": 1587, "train_runtime": 34641.5737, "train_tokens_per_second": 2989.643 }, { "epoch": 1.0082552786156533, "grad_norm": 1.297311544418335, "learning_rate": 1.4942272251454229e-05, "loss": 1.6076184511184692, "num_input_tokens_seen": 103631391, "step": 1588, "train_runtime": 34663.3319, "train_tokens_per_second": 2989.655 }, { "epoch": 1.0088903000476266, "grad_norm": 1.2569652795791626, "learning_rate": 1.4936487402417479e-05, "loss": 1.7367984056472778, "num_input_tokens_seen": 103696885, "step": 1589, "train_runtime": 34684.6895, "train_tokens_per_second": 2989.702 }, { "epoch": 1.0095253214795998, "grad_norm": 1.2011761665344238, "learning_rate": 1.4930700368308503e-05, "loss": 1.6911532878875732, "num_input_tokens_seen": 103762302, "step": 1590, "train_runtime": 34705.7804, "train_tokens_per_second": 2989.77 }, { "epoch": 1.0101603429115733, "grad_norm": 1.1629899740219116, "learning_rate": 1.4924911151688858e-05, "loss": 1.5432454347610474, "num_input_tokens_seen": 103827781, "step": 1591, "train_runtime": 34726.9634, "train_tokens_per_second": 2989.832 }, { "epoch": 1.0107953643435466, "grad_norm": 1.1750620603561401, "learning_rate": 1.4919119755121061e-05, "loss": 1.706943154335022, "num_input_tokens_seen": 103893205, "step": 1592, "train_runtime": 34748.6322, "train_tokens_per_second": 2989.85 }, { "epoch": 1.01143038577552, "grad_norm": 1.261691689491272, "learning_rate": 1.4913326181168604e-05, "loss": 1.5863590240478516, "num_input_tokens_seen": 103958721, "step": 1593, "train_runtime": 34770.9713, "train_tokens_per_second": 2989.814 }, { "epoch": 1.0120654072074933, "grad_norm": 1.2177708148956299, "learning_rate": 1.4907530432395937e-05, "loss": 1.5721261501312256, "num_input_tokens_seen": 104024250, "step": 1594, "train_runtime": 34792.9234, "train_tokens_per_second": 2989.811 }, { "epoch": 1.0127004286394665, "grad_norm": 1.068036675453186, "learning_rate": 1.4901732511368467e-05, "loss": 1.5228865146636963, "num_input_tokens_seen": 104089776, "step": 1595, "train_runtime": 34814.4807, "train_tokens_per_second": 2989.841 }, { "epoch": 1.01333545007144, "grad_norm": 1.1538450717926025, "learning_rate": 1.4895932420652574e-05, "loss": 1.647188425064087, "num_input_tokens_seen": 104155144, "step": 1596, "train_runtime": 34835.8918, "train_tokens_per_second": 2989.88 }, { "epoch": 1.0139704715034132, "grad_norm": 1.1731295585632324, "learning_rate": 1.4890130162815593e-05, "loss": 1.5406429767608643, "num_input_tokens_seen": 104220650, "step": 1597, "train_runtime": 34856.5969, "train_tokens_per_second": 2989.984 }, { "epoch": 1.0146054929353865, "grad_norm": 1.3417267799377441, "learning_rate": 1.4884325740425815e-05, "loss": 1.978516936302185, "num_input_tokens_seen": 104286063, "step": 1598, "train_runtime": 34877.6811, "train_tokens_per_second": 2990.052 }, { "epoch": 1.01524051436736, "grad_norm": 1.341231107711792, "learning_rate": 1.4878519156052497e-05, "loss": 1.7829097509384155, "num_input_tokens_seen": 104351535, "step": 1599, "train_runtime": 34899.442, "train_tokens_per_second": 2990.063 }, { "epoch": 1.0158755357993332, "grad_norm": 1.1410388946533203, "learning_rate": 1.4872710412265848e-05, "loss": 1.4773004055023193, "num_input_tokens_seen": 104416961, "step": 1600, "train_runtime": 34920.0932, "train_tokens_per_second": 2990.168 }, { "epoch": 1.0158755357993332, "eval_loss": 1.5527839660644531, "eval_runtime": 12.9297, "eval_samples_per_second": 1.779, "eval_steps_per_second": 0.928, "num_input_tokens_seen": 104416961, "step": 1600 }, { "epoch": 1.0165105572313065, "grad_norm": 1.26908278465271, "learning_rate": 1.4866899511637027e-05, "loss": 1.7471611499786377, "num_input_tokens_seen": 104482373, "step": 1601, "train_runtime": 34992.1401, "train_tokens_per_second": 2985.881 }, { "epoch": 1.01714557866328, "grad_norm": 1.1962084770202637, "learning_rate": 1.486108645673816e-05, "loss": 1.6922279596328735, "num_input_tokens_seen": 104547887, "step": 1602, "train_runtime": 35013.6882, "train_tokens_per_second": 2985.915 }, { "epoch": 1.0177806000952532, "grad_norm": 1.1056897640228271, "learning_rate": 1.485527125014232e-05, "loss": 1.44415283203125, "num_input_tokens_seen": 104613392, "step": 1603, "train_runtime": 35034.7316, "train_tokens_per_second": 2985.991 }, { "epoch": 1.0184156215272266, "grad_norm": 1.2718560695648193, "learning_rate": 1.4849453894423531e-05, "loss": 1.7169249057769775, "num_input_tokens_seen": 104678921, "step": 1604, "train_runtime": 35056.41, "train_tokens_per_second": 2986.014 }, { "epoch": 1.0190506429592, "grad_norm": 1.1977498531341553, "learning_rate": 1.4843634392156772e-05, "loss": 1.6017825603485107, "num_input_tokens_seen": 104744403, "step": 1605, "train_runtime": 35078.0693, "train_tokens_per_second": 2986.037 }, { "epoch": 1.0196856643911731, "grad_norm": 1.2779909372329712, "learning_rate": 1.4837812745917966e-05, "loss": 1.6553255319595337, "num_input_tokens_seen": 104809902, "step": 1606, "train_runtime": 35099.5911, "train_tokens_per_second": 2986.072 }, { "epoch": 1.0203206858231466, "grad_norm": 1.2458115816116333, "learning_rate": 1.4831988958283994e-05, "loss": 1.5539212226867676, "num_input_tokens_seen": 104875374, "step": 1607, "train_runtime": 35121.5063, "train_tokens_per_second": 2986.073 }, { "epoch": 1.0209557072551199, "grad_norm": 1.207543134689331, "learning_rate": 1.4826163031832676e-05, "loss": 1.6237242221832275, "num_input_tokens_seen": 104940864, "step": 1608, "train_runtime": 35142.2366, "train_tokens_per_second": 2986.175 }, { "epoch": 1.021590728687093, "grad_norm": 1.2580287456512451, "learning_rate": 1.4820334969142788e-05, "loss": 1.7777466773986816, "num_input_tokens_seen": 105006383, "step": 1609, "train_runtime": 35164.6119, "train_tokens_per_second": 2986.138 }, { "epoch": 1.0222257501190666, "grad_norm": 1.1056437492370605, "learning_rate": 1.4814504772794044e-05, "loss": 1.4852547645568848, "num_input_tokens_seen": 105071753, "step": 1610, "train_runtime": 35185.7329, "train_tokens_per_second": 2986.203 }, { "epoch": 1.0228607715510398, "grad_norm": 1.1559498310089111, "learning_rate": 1.4808672445367108e-05, "loss": 1.6014673709869385, "num_input_tokens_seen": 105137151, "step": 1611, "train_runtime": 35206.2462, "train_tokens_per_second": 2986.321 }, { "epoch": 1.023495792983013, "grad_norm": 1.2290174961090088, "learning_rate": 1.4802837989443576e-05, "loss": 1.6579078435897827, "num_input_tokens_seen": 105202608, "step": 1612, "train_runtime": 35227.7675, "train_tokens_per_second": 2986.355 }, { "epoch": 1.0241308144149865, "grad_norm": 1.2425943613052368, "learning_rate": 1.4797001407606003e-05, "loss": 1.5292117595672607, "num_input_tokens_seen": 105267991, "step": 1613, "train_runtime": 35249.7284, "train_tokens_per_second": 2986.349 }, { "epoch": 1.0247658358469598, "grad_norm": 1.063876748085022, "learning_rate": 1.4791162702437872e-05, "loss": 1.496103048324585, "num_input_tokens_seen": 105333411, "step": 1614, "train_runtime": 35270.8357, "train_tokens_per_second": 2986.417 }, { "epoch": 1.0254008572789333, "grad_norm": 1.2643406391143799, "learning_rate": 1.478532187652361e-05, "loss": 1.71074640750885, "num_input_tokens_seen": 105398941, "step": 1615, "train_runtime": 35292.8524, "train_tokens_per_second": 2986.41 }, { "epoch": 1.0260358787109065, "grad_norm": 1.1868398189544678, "learning_rate": 1.4779478932448586e-05, "loss": 1.5536144971847534, "num_input_tokens_seen": 105464415, "step": 1616, "train_runtime": 35314.6149, "train_tokens_per_second": 2986.424 }, { "epoch": 1.0266709001428798, "grad_norm": 1.3246710300445557, "learning_rate": 1.47736338727991e-05, "loss": 1.6179003715515137, "num_input_tokens_seen": 105529934, "step": 1617, "train_runtime": 35336.3298, "train_tokens_per_second": 2986.443 }, { "epoch": 1.0273059215748532, "grad_norm": 1.21632981300354, "learning_rate": 1.4767786700162392e-05, "loss": 1.6906241178512573, "num_input_tokens_seen": 105595448, "step": 1618, "train_runtime": 35357.5332, "train_tokens_per_second": 2986.505 }, { "epoch": 1.0279409430068265, "grad_norm": 1.6046143770217896, "learning_rate": 1.4761937417126641e-05, "loss": 1.867288589477539, "num_input_tokens_seen": 105660888, "step": 1619, "train_runtime": 35379.1138, "train_tokens_per_second": 2986.533 }, { "epoch": 1.0285759644387997, "grad_norm": 1.222497582435608, "learning_rate": 1.4756086026280957e-05, "loss": 1.7559646368026733, "num_input_tokens_seen": 105726153, "step": 1620, "train_runtime": 35400.184, "train_tokens_per_second": 2986.599 }, { "epoch": 1.0292109858707732, "grad_norm": 1.0854737758636475, "learning_rate": 1.4750232530215373e-05, "loss": 1.4358229637145996, "num_input_tokens_seen": 105791633, "step": 1621, "train_runtime": 35421.0816, "train_tokens_per_second": 2986.686 }, { "epoch": 1.0298460073027464, "grad_norm": 1.2262029647827148, "learning_rate": 1.4744376931520877e-05, "loss": 1.6959291696548462, "num_input_tokens_seen": 105857106, "step": 1622, "train_runtime": 35443.1576, "train_tokens_per_second": 2986.673 }, { "epoch": 1.0304810287347197, "grad_norm": 1.1692575216293335, "learning_rate": 1.4738519232789358e-05, "loss": 1.4649831056594849, "num_input_tokens_seen": 105922554, "step": 1623, "train_runtime": 35464.0466, "train_tokens_per_second": 2986.759 }, { "epoch": 1.0311160501666932, "grad_norm": 1.0932008028030396, "learning_rate": 1.4732659436613666e-05, "loss": 1.4976996183395386, "num_input_tokens_seen": 105987917, "step": 1624, "train_runtime": 35485.8239, "train_tokens_per_second": 2986.768 }, { "epoch": 1.0317510715986664, "grad_norm": 1.5080833435058594, "learning_rate": 1.4726797545587556e-05, "loss": 1.904201626777649, "num_input_tokens_seen": 106053418, "step": 1625, "train_runtime": 35508.2738, "train_tokens_per_second": 2986.724 }, { "epoch": 1.0323860930306399, "grad_norm": 1.3368273973464966, "learning_rate": 1.4720933562305719e-05, "loss": 1.657717227935791, "num_input_tokens_seen": 106118944, "step": 1626, "train_runtime": 35530.6418, "train_tokens_per_second": 2986.688 }, { "epoch": 1.0330211144626131, "grad_norm": 1.2590051889419556, "learning_rate": 1.4715067489363772e-05, "loss": 1.6773115396499634, "num_input_tokens_seen": 106184435, "step": 1627, "train_runtime": 35552.0827, "train_tokens_per_second": 2986.729 }, { "epoch": 1.0336561358945864, "grad_norm": 1.152134895324707, "learning_rate": 1.4709199329358255e-05, "loss": 1.4979584217071533, "num_input_tokens_seen": 106249965, "step": 1628, "train_runtime": 35573.9934, "train_tokens_per_second": 2986.731 }, { "epoch": 1.0342911573265599, "grad_norm": 1.1074349880218506, "learning_rate": 1.4703329084886635e-05, "loss": 1.4227030277252197, "num_input_tokens_seen": 106315311, "step": 1629, "train_runtime": 35595.1779, "train_tokens_per_second": 2986.79 }, { "epoch": 1.034926178758533, "grad_norm": 1.2573310136795044, "learning_rate": 1.4697456758547297e-05, "loss": 1.5824635028839111, "num_input_tokens_seen": 106380831, "step": 1630, "train_runtime": 35616.6373, "train_tokens_per_second": 2986.83 }, { "epoch": 1.0355612001905063, "grad_norm": 1.1071434020996094, "learning_rate": 1.4691582352939553e-05, "loss": 1.365567684173584, "num_input_tokens_seen": 106446356, "step": 1631, "train_runtime": 35637.2612, "train_tokens_per_second": 2986.94 }, { "epoch": 1.0361962216224798, "grad_norm": 1.2342650890350342, "learning_rate": 1.4685705870663631e-05, "loss": 1.530562400817871, "num_input_tokens_seen": 106511717, "step": 1632, "train_runtime": 35658.3471, "train_tokens_per_second": 2987.007 }, { "epoch": 1.036831243054453, "grad_norm": 1.2249360084533691, "learning_rate": 1.4679827314320681e-05, "loss": 1.7209339141845703, "num_input_tokens_seen": 106577161, "step": 1633, "train_runtime": 35679.5614, "train_tokens_per_second": 2987.065 }, { "epoch": 1.0374662644864263, "grad_norm": 1.2228280305862427, "learning_rate": 1.4673946686512766e-05, "loss": 1.6928932666778564, "num_input_tokens_seen": 106642541, "step": 1634, "train_runtime": 35700.3622, "train_tokens_per_second": 2987.156 }, { "epoch": 1.0381012859183998, "grad_norm": 1.1715635061264038, "learning_rate": 1.4668063989842875e-05, "loss": 1.695250153541565, "num_input_tokens_seen": 106708074, "step": 1635, "train_runtime": 35722.3042, "train_tokens_per_second": 2987.155 }, { "epoch": 1.038736307350373, "grad_norm": 1.313151478767395, "learning_rate": 1.4662179226914903e-05, "loss": 1.79249906539917, "num_input_tokens_seen": 106773514, "step": 1636, "train_runtime": 35743.9567, "train_tokens_per_second": 2987.177 }, { "epoch": 1.0393713287823465, "grad_norm": 1.4970169067382812, "learning_rate": 1.4656292400333672e-05, "loss": 1.8680500984191895, "num_input_tokens_seen": 106839008, "step": 1637, "train_runtime": 35766.1141, "train_tokens_per_second": 2987.157 }, { "epoch": 1.0400063502143198, "grad_norm": 1.208040714263916, "learning_rate": 1.4650403512704899e-05, "loss": 1.7263208627700806, "num_input_tokens_seen": 106904411, "step": 1638, "train_runtime": 35787.9225, "train_tokens_per_second": 2987.164 }, { "epoch": 1.040641371646293, "grad_norm": 1.248008131980896, "learning_rate": 1.464451256663523e-05, "loss": 1.658517837524414, "num_input_tokens_seen": 106969881, "step": 1639, "train_runtime": 35809.8204, "train_tokens_per_second": 2987.166 }, { "epoch": 1.0412763930782665, "grad_norm": 1.2053229808807373, "learning_rate": 1.4638619564732215e-05, "loss": 1.6572673320770264, "num_input_tokens_seen": 107035281, "step": 1640, "train_runtime": 35831.1604, "train_tokens_per_second": 2987.212 }, { "epoch": 1.0419114145102397, "grad_norm": 1.2892863750457764, "learning_rate": 1.4632724509604315e-05, "loss": 1.5868490934371948, "num_input_tokens_seen": 107100779, "step": 1641, "train_runtime": 35852.6981, "train_tokens_per_second": 2987.245 }, { "epoch": 1.042546435942213, "grad_norm": 1.220219373703003, "learning_rate": 1.4626827403860899e-05, "loss": 1.6582269668579102, "num_input_tokens_seen": 107166253, "step": 1642, "train_runtime": 35874.383, "train_tokens_per_second": 2987.264 }, { "epoch": 1.0431814573741864, "grad_norm": 1.2293729782104492, "learning_rate": 1.4620928250112245e-05, "loss": 1.7031878232955933, "num_input_tokens_seen": 107231695, "step": 1643, "train_runtime": 35895.454, "train_tokens_per_second": 2987.334 }, { "epoch": 1.0438164788061597, "grad_norm": 1.2782891988754272, "learning_rate": 1.4615027050969535e-05, "loss": 1.7489542961120605, "num_input_tokens_seen": 107297075, "step": 1644, "train_runtime": 35916.2918, "train_tokens_per_second": 2987.421 }, { "epoch": 1.044451500238133, "grad_norm": 1.2833324670791626, "learning_rate": 1.4609123809044863e-05, "loss": 1.5921560525894165, "num_input_tokens_seen": 107362570, "step": 1645, "train_runtime": 35938.3716, "train_tokens_per_second": 2987.408 }, { "epoch": 1.0450865216701064, "grad_norm": 1.162747859954834, "learning_rate": 1.4603218526951221e-05, "loss": 1.552615761756897, "num_input_tokens_seen": 107428087, "step": 1646, "train_runtime": 35959.7854, "train_tokens_per_second": 2987.451 }, { "epoch": 1.0457215431020797, "grad_norm": 1.2779514789581299, "learning_rate": 1.4597311207302505e-05, "loss": 1.6209907531738281, "num_input_tokens_seen": 107493594, "step": 1647, "train_runtime": 35981.5214, "train_tokens_per_second": 2987.467 }, { "epoch": 1.0463565645340531, "grad_norm": 1.268288254737854, "learning_rate": 1.4591401852713511e-05, "loss": 1.6945216655731201, "num_input_tokens_seen": 107559078, "step": 1648, "train_runtime": 36002.9544, "train_tokens_per_second": 2987.507 }, { "epoch": 1.0469915859660264, "grad_norm": 1.252448320388794, "learning_rate": 1.4585490465799939e-05, "loss": 1.7416963577270508, "num_input_tokens_seen": 107624595, "step": 1649, "train_runtime": 36024.39, "train_tokens_per_second": 2987.548 }, { "epoch": 1.0476266073979996, "grad_norm": 1.2486414909362793, "learning_rate": 1.4579577049178393e-05, "loss": 1.6725001335144043, "num_input_tokens_seen": 107690110, "step": 1650, "train_runtime": 36045.394, "train_tokens_per_second": 2987.625 }, { "epoch": 1.048261628829973, "grad_norm": 1.2379732131958008, "learning_rate": 1.4573661605466365e-05, "loss": 1.6051548719406128, "num_input_tokens_seen": 107755511, "step": 1651, "train_runtime": 36066.5365, "train_tokens_per_second": 2987.687 }, { "epoch": 1.0488966502619463, "grad_norm": 1.2063349485397339, "learning_rate": 1.4567744137282251e-05, "loss": 1.650442123413086, "num_input_tokens_seen": 107821028, "step": 1652, "train_runtime": 36087.8624, "train_tokens_per_second": 2987.737 }, { "epoch": 1.0495316716939196, "grad_norm": 1.1312670707702637, "learning_rate": 1.4561824647245343e-05, "loss": 1.546757459640503, "num_input_tokens_seen": 107886522, "step": 1653, "train_runtime": 36108.8865, "train_tokens_per_second": 2987.811 }, { "epoch": 1.050166693125893, "grad_norm": 1.3438280820846558, "learning_rate": 1.4555903137975827e-05, "loss": 1.8854103088378906, "num_input_tokens_seen": 107951992, "step": 1654, "train_runtime": 36130.6232, "train_tokens_per_second": 2987.825 }, { "epoch": 1.0508017145578663, "grad_norm": 1.331168293952942, "learning_rate": 1.454997961209478e-05, "loss": 1.5319336652755737, "num_input_tokens_seen": 108017480, "step": 1655, "train_runtime": 36152.2877, "train_tokens_per_second": 2987.846 }, { "epoch": 1.0514367359898396, "grad_norm": 1.2985996007919312, "learning_rate": 1.4544054072224171e-05, "loss": 1.707072138786316, "num_input_tokens_seen": 108082983, "step": 1656, "train_runtime": 36173.8937, "train_tokens_per_second": 2987.873 }, { "epoch": 1.052071757421813, "grad_norm": 1.101611852645874, "learning_rate": 1.4538126520986872e-05, "loss": 1.5695582628250122, "num_input_tokens_seen": 108148479, "step": 1657, "train_runtime": 36195.3407, "train_tokens_per_second": 2987.912 }, { "epoch": 1.0527067788537863, "grad_norm": 1.0714569091796875, "learning_rate": 1.4532196961006633e-05, "loss": 1.5591788291931152, "num_input_tokens_seen": 108213900, "step": 1658, "train_runtime": 36216.1093, "train_tokens_per_second": 2988.005 }, { "epoch": 1.0533418002857597, "grad_norm": 1.2343946695327759, "learning_rate": 1.4526265394908094e-05, "loss": 1.5842053890228271, "num_input_tokens_seen": 108279263, "step": 1659, "train_runtime": 36237.8545, "train_tokens_per_second": 2988.015 }, { "epoch": 1.053976821717733, "grad_norm": 1.3817476034164429, "learning_rate": 1.4520331825316786e-05, "loss": 1.7360044717788696, "num_input_tokens_seen": 108344606, "step": 1660, "train_runtime": 36259.8697, "train_tokens_per_second": 2988.003 }, { "epoch": 1.0546118431497062, "grad_norm": 1.1339952945709229, "learning_rate": 1.451439625485913e-05, "loss": 1.7075541019439697, "num_input_tokens_seen": 108410109, "step": 1661, "train_runtime": 36281.3848, "train_tokens_per_second": 2988.037 }, { "epoch": 1.0552468645816797, "grad_norm": 1.1839057207107544, "learning_rate": 1.4508458686162432e-05, "loss": 1.5227450132369995, "num_input_tokens_seen": 108475604, "step": 1662, "train_runtime": 36302.6058, "train_tokens_per_second": 2988.094 }, { "epoch": 1.055881886013653, "grad_norm": 1.360560655593872, "learning_rate": 1.4502519121854874e-05, "loss": 1.7801014184951782, "num_input_tokens_seen": 108541055, "step": 1663, "train_runtime": 36324.1998, "train_tokens_per_second": 2988.12 }, { "epoch": 1.0565169074456262, "grad_norm": 1.2817459106445312, "learning_rate": 1.449657756456553e-05, "loss": 1.6830878257751465, "num_input_tokens_seen": 108606509, "step": 1664, "train_runtime": 36344.9809, "train_tokens_per_second": 2988.212 }, { "epoch": 1.0571519288775997, "grad_norm": 1.233836054801941, "learning_rate": 1.4490634016924351e-05, "loss": 1.651782751083374, "num_input_tokens_seen": 108666459, "step": 1665, "train_runtime": 36364.811, "train_tokens_per_second": 2988.231 }, { "epoch": 1.057786950309573, "grad_norm": 1.4634878635406494, "learning_rate": 1.4484688481562175e-05, "loss": 1.513736367225647, "num_input_tokens_seen": 108731877, "step": 1666, "train_runtime": 36386.378, "train_tokens_per_second": 2988.258 }, { "epoch": 1.0584219717415462, "grad_norm": 1.277021884918213, "learning_rate": 1.4478740961110713e-05, "loss": 1.6299264430999756, "num_input_tokens_seen": 108792730, "step": 1667, "train_runtime": 36405.3782, "train_tokens_per_second": 2988.37 }, { "epoch": 1.0590569931735196, "grad_norm": 1.2012436389923096, "learning_rate": 1.447279145820256e-05, "loss": 1.6372265815734863, "num_input_tokens_seen": 108858221, "step": 1668, "train_runtime": 36426.1021, "train_tokens_per_second": 2988.467 }, { "epoch": 1.059692014605493, "grad_norm": 1.2336958646774292, "learning_rate": 1.4466839975471186e-05, "loss": 1.6322572231292725, "num_input_tokens_seen": 108923656, "step": 1669, "train_runtime": 36447.7723, "train_tokens_per_second": 2988.486 }, { "epoch": 1.0603270360374664, "grad_norm": 1.1761687994003296, "learning_rate": 1.4460886515550938e-05, "loss": 1.5849167108535767, "num_input_tokens_seen": 108989170, "step": 1670, "train_runtime": 36469.2798, "train_tokens_per_second": 2988.52 }, { "epoch": 1.0609620574694396, "grad_norm": 1.0942332744598389, "learning_rate": 1.4454931081077034e-05, "loss": 1.5099365711212158, "num_input_tokens_seen": 109054672, "step": 1671, "train_runtime": 36490.2163, "train_tokens_per_second": 2988.6 }, { "epoch": 1.0615970789014129, "grad_norm": 1.106965184211731, "learning_rate": 1.4448973674685581e-05, "loss": 1.5525872707366943, "num_input_tokens_seen": 109120166, "step": 1672, "train_runtime": 36511.3687, "train_tokens_per_second": 2988.663 }, { "epoch": 1.0622321003333863, "grad_norm": 1.3036341667175293, "learning_rate": 1.4443014299013536e-05, "loss": 1.5937780141830444, "num_input_tokens_seen": 109185535, "step": 1673, "train_runtime": 36533.1883, "train_tokens_per_second": 2988.667 }, { "epoch": 1.0628671217653596, "grad_norm": 1.3262038230895996, "learning_rate": 1.4437052956698743e-05, "loss": 1.570114254951477, "num_input_tokens_seen": 109250957, "step": 1674, "train_runtime": 36555.2121, "train_tokens_per_second": 2988.656 }, { "epoch": 1.0635021431973328, "grad_norm": 1.2316023111343384, "learning_rate": 1.4431089650379913e-05, "loss": 1.6425620317459106, "num_input_tokens_seen": 109316472, "step": 1675, "train_runtime": 36576.5253, "train_tokens_per_second": 2988.706 }, { "epoch": 1.0641371646293063, "grad_norm": 1.2834535837173462, "learning_rate": 1.4425124382696627e-05, "loss": 1.6329563856124878, "num_input_tokens_seen": 109381947, "step": 1676, "train_runtime": 36598.0288, "train_tokens_per_second": 2988.739 }, { "epoch": 1.0647721860612795, "grad_norm": 1.2365707159042358, "learning_rate": 1.4419157156289334e-05, "loss": 1.5297033786773682, "num_input_tokens_seen": 109447439, "step": 1677, "train_runtime": 36619.0343, "train_tokens_per_second": 2988.813 }, { "epoch": 1.0654072074932528, "grad_norm": 1.289372205734253, "learning_rate": 1.4413187973799352e-05, "loss": 1.4880504608154297, "num_input_tokens_seen": 109512931, "step": 1678, "train_runtime": 36640.4182, "train_tokens_per_second": 2988.856 }, { "epoch": 1.0660422289252263, "grad_norm": 1.305625081062317, "learning_rate": 1.4407216837868856e-05, "loss": 1.6940805912017822, "num_input_tokens_seen": 109578290, "step": 1679, "train_runtime": 36661.931, "train_tokens_per_second": 2988.885 }, { "epoch": 1.0666772503571995, "grad_norm": 1.2130919694900513, "learning_rate": 1.4401243751140896e-05, "loss": 1.432308316230774, "num_input_tokens_seen": 109643786, "step": 1680, "train_runtime": 36683.0842, "train_tokens_per_second": 2988.947 }, { "epoch": 1.067312271789173, "grad_norm": 1.1834911108016968, "learning_rate": 1.4395268716259383e-05, "loss": 1.6469775438308716, "num_input_tokens_seen": 109709199, "step": 1681, "train_runtime": 36704.0832, "train_tokens_per_second": 2989.019 }, { "epoch": 1.0679472932211462, "grad_norm": 1.3228960037231445, "learning_rate": 1.4389291735869084e-05, "loss": 1.5886292457580566, "num_input_tokens_seen": 109772599, "step": 1682, "train_runtime": 36724.8302, "train_tokens_per_second": 2989.057 }, { "epoch": 1.0685823146531195, "grad_norm": 1.0368915796279907, "learning_rate": 1.4383312812615637e-05, "loss": 1.3365815877914429, "num_input_tokens_seen": 109838108, "step": 1683, "train_runtime": 36745.2869, "train_tokens_per_second": 2989.175 }, { "epoch": 1.069217336085093, "grad_norm": 1.213375449180603, "learning_rate": 1.4377331949145532e-05, "loss": 1.653536081314087, "num_input_tokens_seen": 109903548, "step": 1684, "train_runtime": 36765.9219, "train_tokens_per_second": 2989.278 }, { "epoch": 1.0698523575170662, "grad_norm": 1.1055959463119507, "learning_rate": 1.4371349148106121e-05, "loss": 1.4953529834747314, "num_input_tokens_seen": 109969077, "step": 1685, "train_runtime": 36787.8148, "train_tokens_per_second": 2989.28 }, { "epoch": 1.0704873789490394, "grad_norm": 1.3415213823318481, "learning_rate": 1.4365364412145613e-05, "loss": 1.8018451929092407, "num_input_tokens_seen": 110034525, "step": 1686, "train_runtime": 36809.1464, "train_tokens_per_second": 2989.326 }, { "epoch": 1.071122400381013, "grad_norm": 1.2448625564575195, "learning_rate": 1.4359377743913075e-05, "loss": 1.4290659427642822, "num_input_tokens_seen": 110099938, "step": 1687, "train_runtime": 36830.7293, "train_tokens_per_second": 2989.35 }, { "epoch": 1.0717574218129862, "grad_norm": 1.2225661277770996, "learning_rate": 1.4353389146058427e-05, "loss": 1.607488989830017, "num_input_tokens_seen": 110165244, "step": 1688, "train_runtime": 36851.4638, "train_tokens_per_second": 2989.44 }, { "epoch": 1.0723924432449594, "grad_norm": 1.3601292371749878, "learning_rate": 1.434739862123245e-05, "loss": 1.596165418624878, "num_input_tokens_seen": 110230771, "step": 1689, "train_runtime": 36873.282, "train_tokens_per_second": 2989.448 }, { "epoch": 1.0730274646769329, "grad_norm": 1.183934211730957, "learning_rate": 1.4341406172086765e-05, "loss": 1.7947797775268555, "num_input_tokens_seen": 110296251, "step": 1690, "train_runtime": 36894.5048, "train_tokens_per_second": 2989.503 }, { "epoch": 1.0736624861089061, "grad_norm": 1.2265889644622803, "learning_rate": 1.433541180127385e-05, "loss": 1.480970859527588, "num_input_tokens_seen": 110361682, "step": 1691, "train_runtime": 36916.0366, "train_tokens_per_second": 2989.532 }, { "epoch": 1.0742975075408796, "grad_norm": 1.2902915477752686, "learning_rate": 1.4329415511447042e-05, "loss": 1.761509656906128, "num_input_tokens_seen": 110426746, "step": 1692, "train_runtime": 36937.6443, "train_tokens_per_second": 2989.545 }, { "epoch": 1.0749325289728529, "grad_norm": 1.19520103931427, "learning_rate": 1.432341730526052e-05, "loss": 1.533551812171936, "num_input_tokens_seen": 110492158, "step": 1693, "train_runtime": 36958.9712, "train_tokens_per_second": 2989.59 }, { "epoch": 1.075567550404826, "grad_norm": 1.219008445739746, "learning_rate": 1.4317417185369313e-05, "loss": 1.5359315872192383, "num_input_tokens_seen": 110557683, "step": 1694, "train_runtime": 36980.4577, "train_tokens_per_second": 2989.625 }, { "epoch": 1.0762025718367996, "grad_norm": 1.135317087173462, "learning_rate": 1.4311415154429293e-05, "loss": 1.5198243856430054, "num_input_tokens_seen": 110623180, "step": 1695, "train_runtime": 37001.8094, "train_tokens_per_second": 2989.669 }, { "epoch": 1.0768375932687728, "grad_norm": 1.1957629919052124, "learning_rate": 1.4305411215097185e-05, "loss": 1.4670770168304443, "num_input_tokens_seen": 110688676, "step": 1696, "train_runtime": 37022.7288, "train_tokens_per_second": 2989.749 }, { "epoch": 1.077472614700746, "grad_norm": 1.1021745204925537, "learning_rate": 1.4299405370030549e-05, "loss": 1.4447968006134033, "num_input_tokens_seen": 110754195, "step": 1697, "train_runtime": 37043.4262, "train_tokens_per_second": 2989.847 }, { "epoch": 1.0781076361327195, "grad_norm": 1.3796151876449585, "learning_rate": 1.4293397621887803e-05, "loss": 1.72990882396698, "num_input_tokens_seen": 110819584, "step": 1698, "train_runtime": 37065.1699, "train_tokens_per_second": 2989.858 }, { "epoch": 1.0787426575646928, "grad_norm": 1.2589199542999268, "learning_rate": 1.4287387973328193e-05, "loss": 1.6571866273880005, "num_input_tokens_seen": 110885094, "step": 1699, "train_runtime": 37087.312, "train_tokens_per_second": 2989.839 }, { "epoch": 1.079377678996666, "grad_norm": 1.0342669486999512, "learning_rate": 1.4281376427011812e-05, "loss": 1.3732528686523438, "num_input_tokens_seen": 110950604, "step": 1700, "train_runtime": 37107.9938, "train_tokens_per_second": 2989.938 }, { "epoch": 1.079377678996666, "eval_loss": 1.551364541053772, "eval_runtime": 12.8838, "eval_samples_per_second": 1.785, "eval_steps_per_second": 0.931, "num_input_tokens_seen": 110950604, "step": 1700 } ], "logging_steps": 1, "max_steps": 4725, "num_input_tokens_seen": 110950604, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 8.722984914199634e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }