{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 1548, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01937984496124031, "grad_norm": 3.024710206889159, "learning_rate": 5.806451612903227e-07, "loss": 0.581, "step": 10 }, { "epoch": 0.03875968992248062, "grad_norm": 1.5402360004650113, "learning_rate": 1.2258064516129033e-06, "loss": 0.5504, "step": 20 }, { "epoch": 0.05813953488372093, "grad_norm": 0.8470059178916516, "learning_rate": 1.870967741935484e-06, "loss": 0.5124, "step": 30 }, { "epoch": 0.07751937984496124, "grad_norm": 0.5184552103940687, "learning_rate": 2.5161290322580645e-06, "loss": 0.4698, "step": 40 }, { "epoch": 0.09689922480620156, "grad_norm": 0.4600811642482261, "learning_rate": 3.1612903225806453e-06, "loss": 0.4486, "step": 50 }, { "epoch": 0.11627906976744186, "grad_norm": 0.323482300837561, "learning_rate": 3.8064516129032257e-06, "loss": 0.4405, "step": 60 }, { "epoch": 0.13565891472868216, "grad_norm": 0.3255845459193703, "learning_rate": 4.451612903225807e-06, "loss": 0.4235, "step": 70 }, { "epoch": 0.15503875968992248, "grad_norm": 0.30110094189930176, "learning_rate": 5.096774193548387e-06, "loss": 0.421, "step": 80 }, { "epoch": 0.1744186046511628, "grad_norm": 0.3472582262303459, "learning_rate": 5.7419354838709685e-06, "loss": 0.4056, "step": 90 }, { "epoch": 0.1937984496124031, "grad_norm": 0.2834471087687218, "learning_rate": 6.3870967741935485e-06, "loss": 0.4068, "step": 100 }, { "epoch": 0.2131782945736434, "grad_norm": 0.3061797429978253, "learning_rate": 7.03225806451613e-06, "loss": 0.3963, "step": 110 }, { "epoch": 0.23255813953488372, "grad_norm": 0.32637029539406764, "learning_rate": 7.67741935483871e-06, "loss": 0.3951, "step": 120 }, { "epoch": 0.25193798449612403, "grad_norm": 0.3229985120370211, "learning_rate": 8.322580645161292e-06, "loss": 0.3882, "step": 130 }, { "epoch": 0.2713178294573643, "grad_norm": 0.3690058326721124, "learning_rate": 8.967741935483871e-06, "loss": 0.3906, "step": 140 }, { "epoch": 0.29069767441860467, "grad_norm": 0.2906195001306367, "learning_rate": 9.612903225806453e-06, "loss": 0.3897, "step": 150 }, { "epoch": 0.31007751937984496, "grad_norm": 0.4239631816664054, "learning_rate": 9.999796551468884e-06, "loss": 0.3826, "step": 160 }, { "epoch": 0.32945736434108525, "grad_norm": 0.34692538807102946, "learning_rate": 9.99750794563087e-06, "loss": 0.389, "step": 170 }, { "epoch": 0.3488372093023256, "grad_norm": 0.4007352767365137, "learning_rate": 9.992677591163695e-06, "loss": 0.3742, "step": 180 }, { "epoch": 0.3682170542635659, "grad_norm": 0.36518323602764685, "learning_rate": 9.985307944801193e-06, "loss": 0.375, "step": 190 }, { "epoch": 0.3875968992248062, "grad_norm": 0.30356394543129034, "learning_rate": 9.975402754769224e-06, "loss": 0.3792, "step": 200 }, { "epoch": 0.4069767441860465, "grad_norm": 0.2852713945073263, "learning_rate": 9.96296705887933e-06, "loss": 0.3743, "step": 210 }, { "epoch": 0.4263565891472868, "grad_norm": 0.30179106804473094, "learning_rate": 9.948007181966471e-06, "loss": 0.374, "step": 220 }, { "epoch": 0.44573643410852715, "grad_norm": 0.31336324870448984, "learning_rate": 9.930530732672206e-06, "loss": 0.3702, "step": 230 }, { "epoch": 0.46511627906976744, "grad_norm": 0.33409125982259624, "learning_rate": 9.910546599574903e-06, "loss": 0.3774, "step": 240 }, { "epoch": 0.4844961240310077, "grad_norm": 0.3665485316181777, "learning_rate": 9.88806494666899e-06, "loss": 0.3708, "step": 250 }, { "epoch": 0.5038759689922481, "grad_norm": 0.338344043578051, "learning_rate": 9.863097208195508e-06, "loss": 0.3745, "step": 260 }, { "epoch": 0.5232558139534884, "grad_norm": 0.3034912732218389, "learning_rate": 9.835656082826623e-06, "loss": 0.3713, "step": 270 }, { "epoch": 0.5426356589147286, "grad_norm": 0.30126794365887294, "learning_rate": 9.805755527207036e-06, "loss": 0.3673, "step": 280 }, { "epoch": 0.562015503875969, "grad_norm": 0.31497458659496597, "learning_rate": 9.773410748855585e-06, "loss": 0.376, "step": 290 }, { "epoch": 0.5813953488372093, "grad_norm": 0.3062365232795322, "learning_rate": 9.738638198430672e-06, "loss": 0.36, "step": 300 }, { "epoch": 0.6007751937984496, "grad_norm": 0.29595518548452066, "learning_rate": 9.701455561363378e-06, "loss": 0.3658, "step": 310 }, { "epoch": 0.6201550387596899, "grad_norm": 0.34813640927866357, "learning_rate": 9.661881748862618e-06, "loss": 0.3606, "step": 320 }, { "epoch": 0.6395348837209303, "grad_norm": 0.3261071482329525, "learning_rate": 9.619936888296822e-06, "loss": 0.3662, "step": 330 }, { "epoch": 0.6589147286821705, "grad_norm": 0.31972426712360247, "learning_rate": 9.575642312957107e-06, "loss": 0.362, "step": 340 }, { "epoch": 0.6782945736434108, "grad_norm": 0.3104726872415725, "learning_rate": 9.52902055120708e-06, "loss": 0.3692, "step": 350 }, { "epoch": 0.6976744186046512, "grad_norm": 0.3009349159975097, "learning_rate": 9.480095315024855e-06, "loss": 0.3577, "step": 360 }, { "epoch": 0.7170542635658915, "grad_norm": 0.3396149740587963, "learning_rate": 9.428891487943056e-06, "loss": 0.3678, "step": 370 }, { "epoch": 0.7364341085271318, "grad_norm": 0.28452945850141, "learning_rate": 9.37543511239297e-06, "loss": 0.3595, "step": 380 }, { "epoch": 0.7558139534883721, "grad_norm": 0.29432126357863087, "learning_rate": 9.319753376459289e-06, "loss": 0.3613, "step": 390 }, { "epoch": 0.7751937984496124, "grad_norm": 0.32109558327111826, "learning_rate": 9.261874600052159e-06, "loss": 0.358, "step": 400 }, { "epoch": 0.7945736434108527, "grad_norm": 0.30459515622425065, "learning_rate": 9.201828220503588e-06, "loss": 0.3523, "step": 410 }, { "epoch": 0.813953488372093, "grad_norm": 0.3029379165001461, "learning_rate": 9.139644777595514e-06, "loss": 0.3572, "step": 420 }, { "epoch": 0.8333333333333334, "grad_norm": 0.3184431589658449, "learning_rate": 9.07535589802718e-06, "loss": 0.3647, "step": 430 }, { "epoch": 0.8527131782945736, "grad_norm": 0.3285191809001309, "learning_rate": 9.008994279329695e-06, "loss": 0.3569, "step": 440 }, { "epoch": 0.872093023255814, "grad_norm": 0.30071181015912896, "learning_rate": 8.940593673235962e-06, "loss": 0.3447, "step": 450 }, { "epoch": 0.8914728682170543, "grad_norm": 0.293634789051238, "learning_rate": 8.870188868514434e-06, "loss": 0.3609, "step": 460 }, { "epoch": 0.9108527131782945, "grad_norm": 0.31663014520581295, "learning_rate": 8.797815673275441e-06, "loss": 0.3569, "step": 470 }, { "epoch": 0.9302325581395349, "grad_norm": 0.2922871433510901, "learning_rate": 8.723510896759064e-06, "loss": 0.3571, "step": 480 }, { "epoch": 0.9496124031007752, "grad_norm": 0.2900366588256224, "learning_rate": 8.647312330613845e-06, "loss": 0.3533, "step": 490 }, { "epoch": 0.9689922480620154, "grad_norm": 0.27174859845732824, "learning_rate": 8.56925872967582e-06, "loss": 0.3534, "step": 500 }, { "epoch": 0.9883720930232558, "grad_norm": 0.3242791388749644, "learning_rate": 8.4893897922577e-06, "loss": 0.3564, "step": 510 }, { "epoch": 1.0077519379844961, "grad_norm": 0.41930486160423347, "learning_rate": 8.40774613995817e-06, "loss": 0.3496, "step": 520 }, { "epoch": 1.0271317829457365, "grad_norm": 0.33960409797943286, "learning_rate": 8.324369297001616e-06, "loss": 0.3292, "step": 530 }, { "epoch": 1.0465116279069768, "grad_norm": 0.2883277794177794, "learning_rate": 8.239301669118776e-06, "loss": 0.3335, "step": 540 }, { "epoch": 1.0658914728682172, "grad_norm": 0.278024569033151, "learning_rate": 8.152586521979038e-06, "loss": 0.3281, "step": 550 }, { "epoch": 1.0852713178294573, "grad_norm": 0.29701005576786715, "learning_rate": 8.064267959185393e-06, "loss": 0.3254, "step": 560 }, { "epoch": 1.1046511627906976, "grad_norm": 0.28568736252968063, "learning_rate": 7.974390899843194e-06, "loss": 0.3293, "step": 570 }, { "epoch": 1.124031007751938, "grad_norm": 0.2963119155914095, "learning_rate": 7.883001055714155e-06, "loss": 0.3304, "step": 580 }, { "epoch": 1.1434108527131783, "grad_norm": 0.28891746465630497, "learning_rate": 7.7901449079672e-06, "loss": 0.3235, "step": 590 }, { "epoch": 1.1627906976744187, "grad_norm": 0.3068381315646611, "learning_rate": 7.695869683538003e-06, "loss": 0.334, "step": 600 }, { "epoch": 1.1821705426356588, "grad_norm": 0.2954947043166262, "learning_rate": 7.600223331109193e-06, "loss": 0.3272, "step": 610 }, { "epoch": 1.2015503875968991, "grad_norm": 0.3292488373940055, "learning_rate": 7.5032544967235244e-06, "loss": 0.3278, "step": 620 }, { "epoch": 1.2209302325581395, "grad_norm": 0.34189866382905837, "learning_rate": 7.405012499042328e-06, "loss": 0.3325, "step": 630 }, { "epoch": 1.2403100775193798, "grad_norm": 0.29867309861883884, "learning_rate": 7.305547304261886e-06, "loss": 0.3301, "step": 640 }, { "epoch": 1.2596899224806202, "grad_norm": 0.30833185416883796, "learning_rate": 7.204909500700464e-06, "loss": 0.3349, "step": 650 }, { "epoch": 1.2790697674418605, "grad_norm": 0.2899026781077889, "learning_rate": 7.103150273068922e-06, "loss": 0.3317, "step": 660 }, { "epoch": 1.2984496124031009, "grad_norm": 0.2999993491347847, "learning_rate": 7.000321376438022e-06, "loss": 0.3338, "step": 670 }, { "epoch": 1.3178294573643412, "grad_norm": 0.31616423531901156, "learning_rate": 6.896475109915619e-06, "loss": 0.3298, "step": 680 }, { "epoch": 1.3372093023255813, "grad_norm": 0.28212973123736484, "learning_rate": 6.791664290047165e-06, "loss": 0.3313, "step": 690 }, { "epoch": 1.3565891472868217, "grad_norm": 0.28915033542218266, "learning_rate": 6.6859422239530545e-06, "loss": 0.3216, "step": 700 }, { "epoch": 1.375968992248062, "grad_norm": 0.2896008415289824, "learning_rate": 6.5793626822164466e-06, "loss": 0.3325, "step": 710 }, { "epoch": 1.3953488372093024, "grad_norm": 0.3119505933455449, "learning_rate": 6.4719798715353676e-06, "loss": 0.3303, "step": 720 }, { "epoch": 1.4147286821705427, "grad_norm": 0.29835932589388153, "learning_rate": 6.363848407153017e-06, "loss": 0.3224, "step": 730 }, { "epoch": 1.4341085271317828, "grad_norm": 0.2886715830691158, "learning_rate": 6.255023285080276e-06, "loss": 0.3261, "step": 740 }, { "epoch": 1.4534883720930232, "grad_norm": 0.28164795191624437, "learning_rate": 6.1455598541245676e-06, "loss": 0.329, "step": 750 }, { "epoch": 1.4728682170542635, "grad_norm": 0.2625743581161518, "learning_rate": 6.035513787739254e-06, "loss": 0.3264, "step": 760 }, { "epoch": 1.4922480620155039, "grad_norm": 0.2750007352652477, "learning_rate": 5.924941055707965e-06, "loss": 0.3263, "step": 770 }, { "epoch": 1.5116279069767442, "grad_norm": 0.26378113717013907, "learning_rate": 5.813897895678164e-06, "loss": 0.3272, "step": 780 }, { "epoch": 1.5310077519379846, "grad_norm": 0.2815561800883907, "learning_rate": 5.702440784558517e-06, "loss": 0.3312, "step": 790 }, { "epoch": 1.550387596899225, "grad_norm": 0.2914139841744769, "learning_rate": 5.5906264097945405e-06, "loss": 0.324, "step": 800 }, { "epoch": 1.5697674418604652, "grad_norm": 0.26428007476263105, "learning_rate": 5.478511640537194e-06, "loss": 0.3264, "step": 810 }, { "epoch": 1.5891472868217056, "grad_norm": 0.31418088689469686, "learning_rate": 5.366153498719042e-06, "loss": 0.326, "step": 820 }, { "epoch": 1.6085271317829457, "grad_norm": 0.3060727974460338, "learning_rate": 5.253609130052718e-06, "loss": 0.3257, "step": 830 }, { "epoch": 1.627906976744186, "grad_norm": 0.30284340426746187, "learning_rate": 5.140935774966429e-06, "loss": 0.327, "step": 840 }, { "epoch": 1.6472868217054264, "grad_norm": 0.26699893667119545, "learning_rate": 5.028190739491291e-06, "loss": 0.3302, "step": 850 }, { "epoch": 1.6666666666666665, "grad_norm": 0.27681198241258764, "learning_rate": 4.915431366115295e-06, "loss": 0.3294, "step": 860 }, { "epoch": 1.6860465116279069, "grad_norm": 0.28796400194127436, "learning_rate": 4.802715004618737e-06, "loss": 0.3234, "step": 870 }, { "epoch": 1.7054263565891472, "grad_norm": 0.2890809518886021, "learning_rate": 4.6900989829059315e-06, "loss": 0.3254, "step": 880 }, { "epoch": 1.7248062015503876, "grad_norm": 0.3407732854582675, "learning_rate": 4.577640577848055e-06, "loss": 0.3301, "step": 890 }, { "epoch": 1.744186046511628, "grad_norm": 0.2840744301116043, "learning_rate": 4.465396986151946e-06, "loss": 0.3238, "step": 900 }, { "epoch": 1.7635658914728682, "grad_norm": 0.28087812582824156, "learning_rate": 4.353425295269682e-06, "loss": 0.3267, "step": 910 }, { "epoch": 1.7829457364341086, "grad_norm": 0.2705639936783464, "learning_rate": 4.241782454363699e-06, "loss": 0.3172, "step": 920 }, { "epoch": 1.802325581395349, "grad_norm": 0.27944583278178287, "learning_rate": 4.130525245342285e-06, "loss": 0.3245, "step": 930 }, { "epoch": 1.8217054263565893, "grad_norm": 0.2702464835545137, "learning_rate": 4.01971025398011e-06, "loss": 0.326, "step": 940 }, { "epoch": 1.8410852713178296, "grad_norm": 0.2829858201228807, "learning_rate": 3.909393841138517e-06, "loss": 0.3353, "step": 950 }, { "epoch": 1.8604651162790697, "grad_norm": 0.2691353343474597, "learning_rate": 3.799632114100207e-06, "loss": 0.3275, "step": 960 }, { "epoch": 1.87984496124031, "grad_norm": 0.2763189925577441, "learning_rate": 3.6904808980328988e-06, "loss": 0.3272, "step": 970 }, { "epoch": 1.8992248062015504, "grad_norm": 0.25705918083289864, "learning_rate": 3.5819957075964628e-06, "loss": 0.3198, "step": 980 }, { "epoch": 1.9186046511627906, "grad_norm": 0.2631500393579799, "learning_rate": 3.4742317187079965e-06, "loss": 0.319, "step": 990 }, { "epoch": 1.937984496124031, "grad_norm": 0.3054389644963815, "learning_rate": 3.3672437404791568e-06, "loss": 0.3247, "step": 1000 }, { "epoch": 1.9573643410852712, "grad_norm": 0.3250008081439114, "learning_rate": 3.2610861873400884e-06, "loss": 0.3208, "step": 1010 }, { "epoch": 1.9767441860465116, "grad_norm": 0.2655379268524276, "learning_rate": 3.155813051364064e-06, "loss": 0.3253, "step": 1020 }, { "epoch": 1.996124031007752, "grad_norm": 0.26805061070126973, "learning_rate": 3.0514778748069347e-06, "loss": 0.326, "step": 1030 }, { "epoch": 2.0155038759689923, "grad_norm": 0.2588360551598438, "learning_rate": 2.948133722875375e-06, "loss": 0.3102, "step": 1040 }, { "epoch": 2.0348837209302326, "grad_norm": 0.29212071359901065, "learning_rate": 2.845833156737742e-06, "loss": 0.2964, "step": 1050 }, { "epoch": 2.054263565891473, "grad_norm": 0.27475294625612784, "learning_rate": 2.7446282067913045e-06, "loss": 0.3048, "step": 1060 }, { "epoch": 2.0736434108527133, "grad_norm": 0.24718514011765463, "learning_rate": 2.6445703461993986e-06, "loss": 0.3022, "step": 1070 }, { "epoch": 2.0930232558139537, "grad_norm": 0.24748341008518124, "learning_rate": 2.5457104647120323e-06, "loss": 0.2953, "step": 1080 }, { "epoch": 2.112403100775194, "grad_norm": 0.2532318387348756, "learning_rate": 2.44809884278318e-06, "loss": 0.3037, "step": 1090 }, { "epoch": 2.1317829457364343, "grad_norm": 0.26267405021388773, "learning_rate": 2.351785125997985e-06, "loss": 0.3089, "step": 1100 }, { "epoch": 2.1511627906976742, "grad_norm": 0.27029146219566424, "learning_rate": 2.25681829982286e-06, "loss": 0.3076, "step": 1110 }, { "epoch": 2.1705426356589146, "grad_norm": 0.26162112043896607, "learning_rate": 2.163246664691313e-06, "loss": 0.3018, "step": 1120 }, { "epoch": 2.189922480620155, "grad_norm": 0.25708975624302893, "learning_rate": 2.0711178114382035e-06, "loss": 0.3081, "step": 1130 }, { "epoch": 2.2093023255813953, "grad_norm": 0.26120349850790636, "learning_rate": 1.9804785970948733e-06, "loss": 0.3078, "step": 1140 }, { "epoch": 2.2286821705426356, "grad_norm": 0.2745646814773546, "learning_rate": 1.8913751210575248e-06, "loss": 0.3055, "step": 1150 }, { "epoch": 2.248062015503876, "grad_norm": 0.26906918113057116, "learning_rate": 1.8038527016409135e-06, "loss": 0.3066, "step": 1160 }, { "epoch": 2.2674418604651163, "grad_norm": 0.25703646748291625, "learning_rate": 1.7179558530293073e-06, "loss": 0.3036, "step": 1170 }, { "epoch": 2.2868217054263567, "grad_norm": 0.24324389237190225, "learning_rate": 1.6337282626364304e-06, "loss": 0.3028, "step": 1180 }, { "epoch": 2.306201550387597, "grad_norm": 0.24286459010368208, "learning_rate": 1.5512127688859014e-06, "loss": 0.2973, "step": 1190 }, { "epoch": 2.3255813953488373, "grad_norm": 0.2988865330671064, "learning_rate": 1.4704513394234776e-06, "loss": 0.3065, "step": 1200 }, { "epoch": 2.3449612403100777, "grad_norm": 0.2488231150967903, "learning_rate": 1.3914850497721705e-06, "loss": 0.303, "step": 1210 }, { "epoch": 2.3643410852713176, "grad_norm": 0.244252494824691, "learning_rate": 1.314354062441106e-06, "loss": 0.3027, "step": 1220 }, { "epoch": 2.383720930232558, "grad_norm": 0.2529879369163313, "learning_rate": 1.239097606498741e-06, "loss": 0.3001, "step": 1230 }, { "epoch": 2.4031007751937983, "grad_norm": 0.27959948686853464, "learning_rate": 1.1657539576208344e-06, "loss": 0.3066, "step": 1240 }, { "epoch": 2.4224806201550386, "grad_norm": 0.23986776621156514, "learning_rate": 1.0943604186233132e-06, "loss": 0.302, "step": 1250 }, { "epoch": 2.441860465116279, "grad_norm": 0.24513583859125537, "learning_rate": 1.0249533004899426e-06, "loss": 0.3018, "step": 1260 }, { "epoch": 2.4612403100775193, "grad_norm": 0.24422017561684717, "learning_rate": 9.575679039044411e-07, "loss": 0.3063, "step": 1270 }, { "epoch": 2.4806201550387597, "grad_norm": 0.22744990222068934, "learning_rate": 8.922385012964391e-07, "loss": 0.3, "step": 1280 }, { "epoch": 2.5, "grad_norm": 0.24110629183340684, "learning_rate": 8.289983194104128e-07, "loss": 0.304, "step": 1290 }, { "epoch": 2.5193798449612403, "grad_norm": 0.25451639260797554, "learning_rate": 7.678795224064523e-07, "loss": 0.301, "step": 1300 }, { "epoch": 2.5387596899224807, "grad_norm": 0.24180452622866522, "learning_rate": 7.089131955014672e-07, "loss": 0.3016, "step": 1310 }, { "epoch": 2.558139534883721, "grad_norm": 0.26421567580062955, "learning_rate": 6.521293291591474e-07, "loss": 0.3017, "step": 1320 }, { "epoch": 2.5775193798449614, "grad_norm": 0.2485827641719469, "learning_rate": 5.975568038367124e-07, "loss": 0.3024, "step": 1330 }, { "epoch": 2.5968992248062017, "grad_norm": 0.2437325082173002, "learning_rate": 5.452233752962221e-07, "loss": 0.3095, "step": 1340 }, { "epoch": 2.616279069767442, "grad_norm": 0.24277261297072517, "learning_rate": 4.951556604879049e-07, "loss": 0.3029, "step": 1350 }, { "epoch": 2.6356589147286824, "grad_norm": 0.24670456985964445, "learning_rate": 4.47379124012689e-07, "loss": 0.3063, "step": 1360 }, { "epoch": 2.6550387596899228, "grad_norm": 0.24370768633669995, "learning_rate": 4.019180651708299e-07, "loss": 0.3048, "step": 1370 }, { "epoch": 2.6744186046511627, "grad_norm": 0.23513242406050985, "learning_rate": 3.587956056032027e-07, "loss": 0.2994, "step": 1380 }, { "epoch": 2.693798449612403, "grad_norm": 0.24659870896825767, "learning_rate": 3.180336775315629e-07, "loss": 0.3002, "step": 1390 }, { "epoch": 2.7131782945736433, "grad_norm": 0.23677102922562213, "learning_rate": 2.7965301260374943e-07, "loss": 0.3039, "step": 1400 }, { "epoch": 2.7325581395348837, "grad_norm": 0.23450061355333715, "learning_rate": 2.4367313134949997e-07, "loss": 0.3047, "step": 1410 }, { "epoch": 2.751937984496124, "grad_norm": 0.2427525542058839, "learning_rate": 2.10112333252247e-07, "loss": 0.3041, "step": 1420 }, { "epoch": 2.7713178294573644, "grad_norm": 0.24134579468603404, "learning_rate": 1.7898768744194163e-07, "loss": 0.3046, "step": 1430 }, { "epoch": 2.7906976744186047, "grad_norm": 0.23024540632519397, "learning_rate": 1.5031502401363973e-07, "loss": 0.3034, "step": 1440 }, { "epoch": 2.810077519379845, "grad_norm": 0.23021061548492067, "learning_rate": 1.2410892597626456e-07, "loss": 0.3069, "step": 1450 }, { "epoch": 2.8294573643410854, "grad_norm": 0.2454947252209154, "learning_rate": 1.0038272183564069e-07, "loss": 0.3047, "step": 1460 }, { "epoch": 2.8488372093023253, "grad_norm": 0.24376605561441253, "learning_rate": 7.91484788155733e-08, "loss": 0.302, "step": 1470 }, { "epoch": 2.8682170542635657, "grad_norm": 0.26944245390267824, "learning_rate": 6.04169967204199e-08, "loss": 0.3064, "step": 1480 }, { "epoch": 2.887596899224806, "grad_norm": 0.24111568899502445, "learning_rate": 4.4197802442275116e-08, "loss": 0.3008, "step": 1490 }, { "epoch": 2.9069767441860463, "grad_norm": 0.24352341032150696, "learning_rate": 3.049914511556118e-08, "loss": 0.3062, "step": 1500 }, { "epoch": 2.9263565891472867, "grad_norm": 0.23436619435707207, "learning_rate": 1.9327991921493374e-08, "loss": 0.3024, "step": 1510 }, { "epoch": 2.945736434108527, "grad_norm": 0.2289169080427513, "learning_rate": 1.0690024544548483e-08, "loss": 0.3073, "step": 1520 }, { "epoch": 2.9651162790697674, "grad_norm": 0.28662911889013803, "learning_rate": 4.589636282741339e-09, "loss": 0.3082, "step": 1530 }, { "epoch": 2.9844961240310077, "grad_norm": 0.233511639991065, "learning_rate": 1.0299298131816183e-09, "loss": 0.3057, "step": 1540 } ], "logging_steps": 10, "max_steps": 1548, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 10000000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5155937639727104.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }