{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.6, "eval_steps": 500, "global_step": 3000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "grad_norm": 0.5559354424476624, "learning_rate": 3.6e-06, "loss": 1.0823, "step": 10 }, { "grad_norm": 0.18485906720161438, "learning_rate": 7.6e-06, "loss": 1.069, "step": 20 }, { "grad_norm": 0.08647036552429199, "learning_rate": 1.16e-05, "loss": 1.0486, "step": 30 }, { "grad_norm": 0.07257135212421417, "learning_rate": 1.56e-05, "loss": 1.0473, "step": 40 }, { "grad_norm": 0.08415159583091736, "learning_rate": 1.9600000000000002e-05, "loss": 1.043, "step": 50 }, { "grad_norm": 0.06655513495206833, "learning_rate": 2.36e-05, "loss": 1.0373, "step": 60 }, { "grad_norm": 0.0863005742430687, "learning_rate": 2.7600000000000003e-05, "loss": 1.029, "step": 70 }, { "grad_norm": 0.12436088174581528, "learning_rate": 3.16e-05, "loss": 1.0279, "step": 80 }, { "grad_norm": 0.6764670014381409, "learning_rate": 3.56e-05, "loss": 1.0159, "step": 90 }, { "grad_norm": 0.2262982428073883, "learning_rate": 3.960000000000001e-05, "loss": 0.9873, "step": 100 }, { "grad_norm": 0.5042984485626221, "learning_rate": 4.36e-05, "loss": 0.9377, "step": 110 }, { "grad_norm": 0.6563258767127991, "learning_rate": 4.76e-05, "loss": 0.849, "step": 120 }, { "grad_norm": 0.7196201086044312, "learning_rate": 5.16e-05, "loss": 0.7659, "step": 130 }, { "grad_norm": 0.8339490294456482, "learning_rate": 5.560000000000001e-05, "loss": 0.6787, "step": 140 }, { "grad_norm": 0.6760191321372986, "learning_rate": 5.96e-05, "loss": 0.6034, "step": 150 }, { "grad_norm": 1.257449746131897, "learning_rate": 6.36e-05, "loss": 0.5337, "step": 160 }, { "grad_norm": 0.8350836634635925, "learning_rate": 6.76e-05, "loss": 0.4704, "step": 170 }, { "grad_norm": 0.7451810836791992, "learning_rate": 7.16e-05, "loss": 0.4174, "step": 180 }, { "grad_norm": 1.0491914749145508, "learning_rate": 7.560000000000001e-05, "loss": 0.378, "step": 190 }, { "grad_norm": 0.8344352841377258, "learning_rate": 7.960000000000001e-05, "loss": 0.3493, "step": 200 }, { "grad_norm": 1.2254072427749634, "learning_rate": 8.36e-05, "loss": 0.3153, "step": 210 }, { "grad_norm": 0.7592558860778809, "learning_rate": 8.76e-05, "loss": 0.2874, "step": 220 }, { "grad_norm": 1.0830541849136353, "learning_rate": 9.16e-05, "loss": 0.2624, "step": 230 }, { "grad_norm": 0.8931087255477905, "learning_rate": 9.56e-05, "loss": 0.237, "step": 240 }, { "grad_norm": 1.8609894514083862, "learning_rate": 9.960000000000001e-05, "loss": 0.2146, "step": 250 }, { "grad_norm": 0.9318896532058716, "learning_rate": 9.999911419878559e-05, "loss": 0.1964, "step": 260 }, { "grad_norm": 0.7143105864524841, "learning_rate": 9.999605221019081e-05, "loss": 0.1792, "step": 270 }, { "grad_norm": 0.6846148371696472, "learning_rate": 9.999080323230761e-05, "loss": 0.1651, "step": 280 }, { "grad_norm": 0.9225878119468689, "learning_rate": 9.998336749474329e-05, "loss": 0.162, "step": 290 }, { "grad_norm": 0.7997626662254333, "learning_rate": 9.997374532276107e-05, "loss": 0.151, "step": 300 }, { "grad_norm": 1.0227575302124023, "learning_rate": 9.996193713726596e-05, "loss": 0.1404, "step": 310 }, { "grad_norm": 0.87727952003479, "learning_rate": 9.994794345478624e-05, "loss": 0.1291, "step": 320 }, { "grad_norm": 0.6596595644950867, "learning_rate": 9.99317648874509e-05, "loss": 0.1247, "step": 330 }, { "grad_norm": 0.8926133513450623, "learning_rate": 9.991340214296292e-05, "loss": 0.1181, "step": 340 }, { "grad_norm": 1.250920295715332, "learning_rate": 9.989285602456819e-05, "loss": 0.1078, "step": 350 }, { "grad_norm": 0.8213496804237366, "learning_rate": 9.98701274310205e-05, "loss": 0.1036, "step": 360 }, { "grad_norm": 0.8651483058929443, "learning_rate": 9.984521735654218e-05, "loss": 0.0871, "step": 370 }, { "grad_norm": 0.8947259783744812, "learning_rate": 9.981812689078057e-05, "loss": 0.0835, "step": 380 }, { "grad_norm": 0.7791630625724792, "learning_rate": 9.978885721876041e-05, "loss": 0.0711, "step": 390 }, { "grad_norm": 0.6401210427284241, "learning_rate": 9.975740962083198e-05, "loss": 0.0685, "step": 400 }, { "grad_norm": 0.7891541123390198, "learning_rate": 9.972378547261504e-05, "loss": 0.0649, "step": 410 }, { "grad_norm": 0.8624171018600464, "learning_rate": 9.968798624493885e-05, "loss": 0.0608, "step": 420 }, { "grad_norm": 0.747508704662323, "learning_rate": 9.965001350377753e-05, "loss": 0.0655, "step": 430 }, { "grad_norm": 0.9979900121688843, "learning_rate": 9.960986891018183e-05, "loss": 0.061, "step": 440 }, { "grad_norm": 0.8667426705360413, "learning_rate": 9.95675542202063e-05, "loss": 0.0564, "step": 450 }, { "grad_norm": 0.794110894203186, "learning_rate": 9.952307128483256e-05, "loss": 0.0534, "step": 460 }, { "grad_norm": 0.9227981567382812, "learning_rate": 9.947642204988835e-05, "loss": 0.0536, "step": 470 }, { "grad_norm": 0.8375693559646606, "learning_rate": 9.942760855596226e-05, "loss": 0.0572, "step": 480 }, { "grad_norm": 0.7793428897857666, "learning_rate": 9.937663293831471e-05, "loss": 0.0567, "step": 490 }, { "grad_norm": 0.91439288854599, "learning_rate": 9.932349742678433e-05, "loss": 0.0589, "step": 500 }, { "grad_norm": 0.6325005888938904, "learning_rate": 9.926820434569051e-05, "loss": 0.054, "step": 510 }, { "grad_norm": 0.7945265769958496, "learning_rate": 9.921075611373179e-05, "loss": 0.0572, "step": 520 }, { "grad_norm": 0.6466599702835083, "learning_rate": 9.915115524387988e-05, "loss": 0.0514, "step": 530 }, { "grad_norm": 0.7136776447296143, "learning_rate": 9.908940434326997e-05, "loss": 0.0494, "step": 540 }, { "grad_norm": 0.6695866584777832, "learning_rate": 9.902550611308645e-05, "loss": 0.0508, "step": 550 }, { "grad_norm": 0.7268887758255005, "learning_rate": 9.895946334844494e-05, "loss": 0.0488, "step": 560 }, { "grad_norm": 0.6591328382492065, "learning_rate": 9.889127893826989e-05, "loss": 0.0523, "step": 570 }, { "grad_norm": 0.6082274913787842, "learning_rate": 9.882095586516831e-05, "loss": 0.0511, "step": 580 }, { "grad_norm": 0.6265851855278015, "learning_rate": 9.874849720529921e-05, "loss": 0.0495, "step": 590 }, { "grad_norm": 0.6399803161621094, "learning_rate": 9.867390612823914e-05, "loss": 0.0508, "step": 600 }, { "grad_norm": 0.69126296043396, "learning_rate": 9.859718589684344e-05, "loss": 0.045, "step": 610 }, { "grad_norm": 0.6693220734596252, "learning_rate": 9.851833986710353e-05, "loss": 0.0479, "step": 620 }, { "grad_norm": 0.6840260624885559, "learning_rate": 9.843737148800023e-05, "loss": 0.0455, "step": 630 }, { "grad_norm": 0.6354555487632751, "learning_rate": 9.835428430135271e-05, "loss": 0.0491, "step": 640 }, { "grad_norm": 0.6883493661880493, "learning_rate": 9.82690819416637e-05, "loss": 0.047, "step": 650 }, { "grad_norm": 0.5793970823287964, "learning_rate": 9.818176813596041e-05, "loss": 0.0472, "step": 660 }, { "grad_norm": 0.6782571077346802, "learning_rate": 9.809234670363159e-05, "loss": 0.0417, "step": 670 }, { "grad_norm": 0.6450523734092712, "learning_rate": 9.800082155626034e-05, "loss": 0.048, "step": 680 }, { "grad_norm": 0.8551111221313477, "learning_rate": 9.790719669745312e-05, "loss": 0.0427, "step": 690 }, { "grad_norm": 0.664426863193512, "learning_rate": 9.781147622266455e-05, "loss": 0.0411, "step": 700 }, { "grad_norm": 0.625340461730957, "learning_rate": 9.771366431901831e-05, "loss": 0.0407, "step": 710 }, { "grad_norm": 0.7012608647346497, "learning_rate": 9.761376526512394e-05, "loss": 0.0453, "step": 720 }, { "grad_norm": 0.5774393677711487, "learning_rate": 9.751178343088963e-05, "loss": 0.0414, "step": 730 }, { "grad_norm": 0.6276810765266418, "learning_rate": 9.740772327733123e-05, "loss": 0.0393, "step": 740 }, { "grad_norm": 0.6698007583618164, "learning_rate": 9.730158935637697e-05, "loss": 0.0418, "step": 750 }, { "grad_norm": 0.7352779507637024, "learning_rate": 9.719338631066834e-05, "loss": 0.0428, "step": 760 }, { "grad_norm": 0.6087306141853333, "learning_rate": 9.708311887335713e-05, "loss": 0.0416, "step": 770 }, { "grad_norm": 0.7178246378898621, "learning_rate": 9.697079186789823e-05, "loss": 0.0404, "step": 780 }, { "grad_norm": 0.6541343927383423, "learning_rate": 9.685641020783876e-05, "loss": 0.0416, "step": 790 }, { "grad_norm": 0.7868788838386536, "learning_rate": 9.67399788966031e-05, "loss": 0.0419, "step": 800 }, { "grad_norm": 0.6893565058708191, "learning_rate": 9.662150302727395e-05, "loss": 0.0384, "step": 810 }, { "grad_norm": 0.555400013923645, "learning_rate": 9.650098778236968e-05, "loss": 0.0416, "step": 820 }, { "grad_norm": 0.6447874307632446, "learning_rate": 9.637843843361749e-05, "loss": 0.0373, "step": 830 }, { "grad_norm": 0.536383867263794, "learning_rate": 9.62538603417229e-05, "loss": 0.0396, "step": 840 }, { "grad_norm": 0.7303484082221985, "learning_rate": 9.612725895613526e-05, "loss": 0.0408, "step": 850 }, { "grad_norm": 0.5790427923202515, "learning_rate": 9.599863981480926e-05, "loss": 0.0388, "step": 860 }, { "grad_norm": 0.5682157874107361, "learning_rate": 9.586800854396283e-05, "loss": 0.0374, "step": 870 }, { "grad_norm": 0.6473719477653503, "learning_rate": 9.573537085783095e-05, "loss": 0.0362, "step": 880 }, { "grad_norm": 0.6345632672309875, "learning_rate": 9.560073255841571e-05, "loss": 0.0424, "step": 890 }, { "grad_norm": 0.7409985661506653, "learning_rate": 9.546409953523247e-05, "loss": 0.0402, "step": 900 }, { "grad_norm": 0.5863397121429443, "learning_rate": 9.532547776505229e-05, "loss": 0.0383, "step": 910 }, { "grad_norm": 0.5814641118049622, "learning_rate": 9.518487331164048e-05, "loss": 0.0365, "step": 920 }, { "grad_norm": 0.6481305956840515, "learning_rate": 9.504229232549134e-05, "loss": 0.0366, "step": 930 }, { "grad_norm": 0.5147769451141357, "learning_rate": 9.489774104355909e-05, "loss": 0.0366, "step": 940 }, { "grad_norm": 0.5624653100967407, "learning_rate": 9.475122578898507e-05, "loss": 0.0366, "step": 950 }, { "grad_norm": 0.6372323632240295, "learning_rate": 9.460275297082119e-05, "loss": 0.0352, "step": 960 }, { "grad_norm": 0.7020699381828308, "learning_rate": 9.445232908374948e-05, "loss": 0.0393, "step": 970 }, { "grad_norm": 0.6161628365516663, "learning_rate": 9.429996070779808e-05, "loss": 0.0355, "step": 980 }, { "grad_norm": 0.603900134563446, "learning_rate": 9.414565450805333e-05, "loss": 0.0383, "step": 990 }, { "grad_norm": 0.6112933158874512, "learning_rate": 9.398941723436831e-05, "loss": 0.035, "step": 1000 }, { "grad_norm": 0.7074472904205322, "learning_rate": 9.383125572106752e-05, "loss": 0.0373, "step": 1010 }, { "grad_norm": 0.494828462600708, "learning_rate": 9.367117688664791e-05, "loss": 0.0351, "step": 1020 }, { "grad_norm": 0.5672491788864136, "learning_rate": 9.35091877334763e-05, "loss": 0.0372, "step": 1030 }, { "grad_norm": 0.6434159874916077, "learning_rate": 9.334529534748297e-05, "loss": 0.0362, "step": 1040 }, { "grad_norm": 0.6190149784088135, "learning_rate": 9.317950689785188e-05, "loss": 0.0374, "step": 1050 }, { "grad_norm": 0.603152334690094, "learning_rate": 9.301182963670688e-05, "loss": 0.0363, "step": 1060 }, { "grad_norm": 0.661074161529541, "learning_rate": 9.284227089879456e-05, "loss": 0.0379, "step": 1070 }, { "grad_norm": 0.5567871928215027, "learning_rate": 9.26708381011634e-05, "loss": 0.0333, "step": 1080 }, { "grad_norm": 0.5913634300231934, "learning_rate": 9.249753874283937e-05, "loss": 0.0368, "step": 1090 }, { "grad_norm": 0.502541184425354, "learning_rate": 9.232238040449779e-05, "loss": 0.0328, "step": 1100 }, { "grad_norm": 0.5475773215293884, "learning_rate": 9.214537074813181e-05, "loss": 0.0332, "step": 1110 }, { "grad_norm": 0.48871368169784546, "learning_rate": 9.196651751671724e-05, "loss": 0.0345, "step": 1120 }, { "grad_norm": 0.5380433201789856, "learning_rate": 9.178582853387384e-05, "loss": 0.0399, "step": 1130 }, { "grad_norm": 0.5141293406486511, "learning_rate": 9.160331170352304e-05, "loss": 0.036, "step": 1140 }, { "grad_norm": 0.5303184986114502, "learning_rate": 9.141897500954229e-05, "loss": 0.0328, "step": 1150 }, { "grad_norm": 0.7091088891029358, "learning_rate": 9.123282651541576e-05, "loss": 0.035, "step": 1160 }, { "grad_norm": 0.5543999671936035, "learning_rate": 9.104487436388161e-05, "loss": 0.0364, "step": 1170 }, { "grad_norm": 0.5627062916755676, "learning_rate": 9.085512677657582e-05, "loss": 0.0347, "step": 1180 }, { "grad_norm": 0.5156577825546265, "learning_rate": 9.066359205367258e-05, "loss": 0.0346, "step": 1190 }, { "grad_norm": 0.49538666009902954, "learning_rate": 9.047027857352112e-05, "loss": 0.034, "step": 1200 }, { "grad_norm": 0.5321311950683594, "learning_rate": 9.027519479227935e-05, "loss": 0.0318, "step": 1210 }, { "grad_norm": 0.5262922048568726, "learning_rate": 9.007834924354383e-05, "loss": 0.0334, "step": 1220 }, { "grad_norm": 0.5841954946517944, "learning_rate": 8.987975053797655e-05, "loss": 0.035, "step": 1230 }, { "grad_norm": 0.6468002200126648, "learning_rate": 8.967940736292825e-05, "loss": 0.0345, "step": 1240 }, { "grad_norm": 0.46627357602119446, "learning_rate": 8.947732848205846e-05, "loss": 0.0337, "step": 1250 }, { "grad_norm": 0.5673134326934814, "learning_rate": 8.927352273495204e-05, "loss": 0.0344, "step": 1260 }, { "grad_norm": 0.4791153371334076, "learning_rate": 8.906799903673265e-05, "loss": 0.0313, "step": 1270 }, { "grad_norm": 0.5575198531150818, "learning_rate": 8.88607663776726e-05, "loss": 0.0339, "step": 1280 }, { "grad_norm": 0.5566645860671997, "learning_rate": 8.865183382279978e-05, "loss": 0.0331, "step": 1290 }, { "grad_norm": 0.5976455807685852, "learning_rate": 8.844121051150096e-05, "loss": 0.0316, "step": 1300 }, { "grad_norm": 0.6168678402900696, "learning_rate": 8.822890565712211e-05, "loss": 0.0312, "step": 1310 }, { "grad_norm": 0.5337743163108826, "learning_rate": 8.801492854656536e-05, "loss": 0.0337, "step": 1320 }, { "grad_norm": 0.48274630308151245, "learning_rate": 8.779928853988268e-05, "loss": 0.0316, "step": 1330 }, { "grad_norm": 0.5677248239517212, "learning_rate": 8.758199506986655e-05, "loss": 0.0314, "step": 1340 }, { "grad_norm": 0.5900443196296692, "learning_rate": 8.73630576416373e-05, "loss": 0.0325, "step": 1350 }, { "grad_norm": 0.6770350337028503, "learning_rate": 8.714248583222726e-05, "loss": 0.0336, "step": 1360 }, { "grad_norm": 0.5382674932479858, "learning_rate": 8.692028929016196e-05, "loss": 0.0326, "step": 1370 }, { "grad_norm": 0.6602237224578857, "learning_rate": 8.669647773503797e-05, "loss": 0.0321, "step": 1380 }, { "grad_norm": 0.49021854996681213, "learning_rate": 8.647106095709773e-05, "loss": 0.0314, "step": 1390 }, { "grad_norm": 0.4499266445636749, "learning_rate": 8.624404881680139e-05, "loss": 0.0322, "step": 1400 }, { "grad_norm": 0.5155117511749268, "learning_rate": 8.601545124439535e-05, "loss": 0.0281, "step": 1410 }, { "grad_norm": 0.4751155376434326, "learning_rate": 8.5785278239478e-05, "loss": 0.0336, "step": 1420 }, { "grad_norm": 0.5017455816268921, "learning_rate": 8.555353987056224e-05, "loss": 0.0301, "step": 1430 }, { "grad_norm": 0.5961615443229675, "learning_rate": 8.532024627463505e-05, "loss": 0.0295, "step": 1440 }, { "grad_norm": 0.5489777326583862, "learning_rate": 8.508540765671407e-05, "loss": 0.0293, "step": 1450 }, { "grad_norm": 0.4945319890975952, "learning_rate": 8.484903428940121e-05, "loss": 0.0295, "step": 1460 }, { "grad_norm": 0.3737506866455078, "learning_rate": 8.461113651243334e-05, "loss": 0.0337, "step": 1470 }, { "grad_norm": 0.5633870959281921, "learning_rate": 8.437172473222987e-05, "loss": 0.0343, "step": 1480 }, { "grad_norm": 0.6242406368255615, "learning_rate": 8.413080942143767e-05, "loss": 0.0298, "step": 1490 }, { "grad_norm": 0.4667608439922333, "learning_rate": 8.388840111847288e-05, "loss": 0.0307, "step": 1500 }, { "grad_norm": 0.6139534115791321, "learning_rate": 8.364451042705998e-05, "loss": 0.0322, "step": 1510 }, { "grad_norm": 0.5110672116279602, "learning_rate": 8.33991480157679e-05, "loss": 0.0286, "step": 1520 }, { "grad_norm": 0.49589312076568604, "learning_rate": 8.315232461754338e-05, "loss": 0.0299, "step": 1530 }, { "grad_norm": 0.5107879042625427, "learning_rate": 8.290405102924144e-05, "loss": 0.0312, "step": 1540 }, { "grad_norm": 0.4434208869934082, "learning_rate": 8.265433811115316e-05, "loss": 0.0312, "step": 1550 }, { "grad_norm": 0.47019222378730774, "learning_rate": 8.240319678653049e-05, "loss": 0.0311, "step": 1560 }, { "grad_norm": 0.5786542892456055, "learning_rate": 8.215063804110857e-05, "loss": 0.0329, "step": 1570 }, { "grad_norm": 0.5275363326072693, "learning_rate": 8.189667292262512e-05, "loss": 0.0298, "step": 1580 }, { "grad_norm": 0.43545565009117126, "learning_rate": 8.164131254033716e-05, "loss": 0.0302, "step": 1590 }, { "grad_norm": 0.45718058943748474, "learning_rate": 8.138456806453503e-05, "loss": 0.031, "step": 1600 }, { "grad_norm": 0.4676479697227478, "learning_rate": 8.112645072605386e-05, "loss": 0.029, "step": 1610 }, { "grad_norm": 0.5057063102722168, "learning_rate": 8.086697181578222e-05, "loss": 0.0327, "step": 1620 }, { "grad_norm": 0.47432973980903625, "learning_rate": 8.060614268416823e-05, "loss": 0.0311, "step": 1630 }, { "grad_norm": 0.44880610704421997, "learning_rate": 8.034397474072309e-05, "loss": 0.0288, "step": 1640 }, { "grad_norm": 0.42829442024230957, "learning_rate": 8.008047945352193e-05, "loss": 0.0289, "step": 1650 }, { "grad_norm": 0.4990540146827698, "learning_rate": 7.981566834870225e-05, "loss": 0.0316, "step": 1660 }, { "grad_norm": 0.4872753322124481, "learning_rate": 7.954955300995961e-05, "loss": 0.0295, "step": 1670 }, { "grad_norm": 0.4374905526638031, "learning_rate": 7.928214507804104e-05, "loss": 0.0295, "step": 1680 }, { "grad_norm": 0.4577570855617523, "learning_rate": 7.901345625023576e-05, "loss": 0.0279, "step": 1690 }, { "grad_norm": 0.570063591003418, "learning_rate": 7.874349827986354e-05, "loss": 0.0313, "step": 1700 }, { "grad_norm": 0.5689144134521484, "learning_rate": 7.847228297576053e-05, "loss": 0.0314, "step": 1710 }, { "grad_norm": 0.6005192995071411, "learning_rate": 7.819982220176276e-05, "loss": 0.0293, "step": 1720 }, { "grad_norm": 0.48968422412872314, "learning_rate": 7.792612787618714e-05, "loss": 0.0283, "step": 1730 }, { "grad_norm": 0.5264543890953064, "learning_rate": 7.765121197131009e-05, "loss": 0.0322, "step": 1740 }, { "grad_norm": 0.45399144291877747, "learning_rate": 7.737508651284391e-05, "loss": 0.0282, "step": 1750 }, { "grad_norm": 0.46420109272003174, "learning_rate": 7.709776357941069e-05, "loss": 0.0303, "step": 1760 }, { "grad_norm": 0.5926071405410767, "learning_rate": 7.681925530201392e-05, "loss": 0.029, "step": 1770 }, { "grad_norm": 0.4228203594684601, "learning_rate": 7.65395738635079e-05, "loss": 0.0295, "step": 1780 }, { "grad_norm": 0.4261937439441681, "learning_rate": 7.62587314980648e-05, "loss": 0.0301, "step": 1790 }, { "grad_norm": 0.364317923784256, "learning_rate": 7.597674049063947e-05, "loss": 0.0273, "step": 1800 }, { "grad_norm": 0.5105056166648865, "learning_rate": 7.569361317643211e-05, "loss": 0.0274, "step": 1810 }, { "grad_norm": 0.4250337779521942, "learning_rate": 7.540936194034865e-05, "loss": 0.0287, "step": 1820 }, { "grad_norm": 0.508609414100647, "learning_rate": 7.512399921645901e-05, "loss": 0.0263, "step": 1830 }, { "grad_norm": 0.43374282121658325, "learning_rate": 7.483753748745317e-05, "loss": 0.0271, "step": 1840 }, { "grad_norm": 0.5021738409996033, "learning_rate": 7.454998928409516e-05, "loss": 0.0285, "step": 1850 }, { "grad_norm": 0.43334484100341797, "learning_rate": 7.426136718467493e-05, "loss": 0.0271, "step": 1860 }, { "grad_norm": 0.6424834132194519, "learning_rate": 7.397168381445812e-05, "loss": 0.0289, "step": 1870 }, { "grad_norm": 0.4178658723831177, "learning_rate": 7.368095184513377e-05, "loss": 0.0296, "step": 1880 }, { "grad_norm": 0.37668871879577637, "learning_rate": 7.338918399426005e-05, "loss": 0.0262, "step": 1890 }, { "grad_norm": 0.35139450430870056, "learning_rate": 7.309639302470801e-05, "loss": 0.0273, "step": 1900 }, { "grad_norm": 0.5204653739929199, "learning_rate": 7.280259174410312e-05, "loss": 0.0314, "step": 1910 }, { "grad_norm": 0.44355618953704834, "learning_rate": 7.250779300426517e-05, "loss": 0.0266, "step": 1920 }, { "grad_norm": 0.4035153090953827, "learning_rate": 7.22120097006461e-05, "loss": 0.029, "step": 1930 }, { "grad_norm": 0.38775312900543213, "learning_rate": 7.191525477176577e-05, "loss": 0.0264, "step": 1940 }, { "grad_norm": 0.48700636625289917, "learning_rate": 7.161754119864616e-05, "loss": 0.0311, "step": 1950 }, { "grad_norm": 0.5373815894126892, "learning_rate": 7.131888200424339e-05, "loss": 0.0309, "step": 1960 }, { "grad_norm": 0.469199538230896, "learning_rate": 7.101929025287816e-05, "loss": 0.0278, "step": 1970 }, { "grad_norm": 0.35309985280036926, "learning_rate": 7.071877904966423e-05, "loss": 0.0266, "step": 1980 }, { "grad_norm": 0.4618619680404663, "learning_rate": 7.04173615399351e-05, "loss": 0.0248, "step": 1990 }, { "grad_norm": 0.49200907349586487, "learning_rate": 7.011505090866913e-05, "loss": 0.0271, "step": 2000 }, { "grad_norm": 0.47308212518692017, "learning_rate": 6.981186037991271e-05, "loss": 0.025, "step": 2010 }, { "grad_norm": 0.4434255361557007, "learning_rate": 6.950780321620174e-05, "loss": 0.0268, "step": 2020 }, { "grad_norm": 0.41241246461868286, "learning_rate": 6.920289271798157e-05, "loss": 0.0273, "step": 2030 }, { "grad_norm": 0.39038220047950745, "learning_rate": 6.889714222302517e-05, "loss": 0.0249, "step": 2040 }, { "grad_norm": 0.3572078049182892, "learning_rate": 6.85905651058497e-05, "loss": 0.0246, "step": 2050 }, { "grad_norm": 0.5165647864341736, "learning_rate": 6.82831747771314e-05, "loss": 0.0287, "step": 2060 }, { "grad_norm": 0.4069594740867615, "learning_rate": 6.797498468311907e-05, "loss": 0.027, "step": 2070 }, { "grad_norm": 0.5012965798377991, "learning_rate": 6.766600830504585e-05, "loss": 0.026, "step": 2080 }, { "grad_norm": 0.44795289635658264, "learning_rate": 6.735625915853942e-05, "loss": 0.0282, "step": 2090 }, { "grad_norm": 0.4666174054145813, "learning_rate": 6.70457507930309e-05, "loss": 0.0268, "step": 2100 }, { "grad_norm": 0.3589176535606384, "learning_rate": 6.673449679116215e-05, "loss": 0.0248, "step": 2110 }, { "grad_norm": 0.5180903077125549, "learning_rate": 6.642251076819148e-05, "loss": 0.0249, "step": 2120 }, { "grad_norm": 0.46328508853912354, "learning_rate": 6.610980637139827e-05, "loss": 0.0266, "step": 2130 }, { "grad_norm": 0.5663616061210632, "learning_rate": 6.579639727948583e-05, "loss": 0.0261, "step": 2140 }, { "grad_norm": 0.520371675491333, "learning_rate": 6.548229720198315e-05, "loss": 0.0235, "step": 2150 }, { "grad_norm": 0.49466976523399353, "learning_rate": 6.516751987864517e-05, "loss": 0.026, "step": 2160 }, { "grad_norm": 0.4332965314388275, "learning_rate": 6.485207907885175e-05, "loss": 0.0257, "step": 2170 }, { "grad_norm": 0.33331456780433655, "learning_rate": 6.453598860100536e-05, "loss": 0.0273, "step": 2180 }, { "grad_norm": 0.45183008909225464, "learning_rate": 6.421926227192749e-05, "loss": 0.0277, "step": 2190 }, { "grad_norm": 0.5034352540969849, "learning_rate": 6.390191394625381e-05, "loss": 0.0288, "step": 2200 }, { "grad_norm": 0.4152516722679138, "learning_rate": 6.358395750582817e-05, "loss": 0.0264, "step": 2210 }, { "grad_norm": 0.3540273606777191, "learning_rate": 6.326540685909532e-05, "loss": 0.0249, "step": 2220 }, { "grad_norm": 0.4603210389614105, "learning_rate": 6.294627594049249e-05, "loss": 0.0261, "step": 2230 }, { "grad_norm": 0.47433316707611084, "learning_rate": 6.262657870983989e-05, "loss": 0.0245, "step": 2240 }, { "grad_norm": 0.46469366550445557, "learning_rate": 6.230632915173009e-05, "loss": 0.0267, "step": 2250 }, { "grad_norm": 0.4406663775444031, "learning_rate": 6.198554127491622e-05, "loss": 0.0235, "step": 2260 }, { "grad_norm": 0.41085439920425415, "learning_rate": 6.166422911169923e-05, "loss": 0.0256, "step": 2270 }, { "grad_norm": 0.41472023725509644, "learning_rate": 6.1342406717314e-05, "loss": 0.0241, "step": 2280 }, { "grad_norm": 0.4377051889896393, "learning_rate": 6.102008816931466e-05, "loss": 0.0258, "step": 2290 }, { "grad_norm": 0.34513914585113525, "learning_rate": 6.069728756695866e-05, "loss": 0.0263, "step": 2300 }, { "grad_norm": 0.3869786858558655, "learning_rate": 6.037401903059008e-05, "loss": 0.026, "step": 2310 }, { "grad_norm": 0.3966286778450012, "learning_rate": 6.005029670102195e-05, "loss": 0.0247, "step": 2320 }, { "grad_norm": 0.35494574904441833, "learning_rate": 5.972613473891766e-05, "loss": 0.0256, "step": 2330 }, { "grad_norm": 0.31937381625175476, "learning_rate": 5.940154732417158e-05, "loss": 0.0231, "step": 2340 }, { "grad_norm": 0.38585540652275085, "learning_rate": 5.907654865528876e-05, "loss": 0.0277, "step": 2350 }, { "grad_norm": 0.3926496207714081, "learning_rate": 5.875115294876381e-05, "loss": 0.0238, "step": 2360 }, { "grad_norm": 0.3543730676174164, "learning_rate": 5.842537443845908e-05, "loss": 0.0236, "step": 2370 }, { "grad_norm": 0.36009931564331055, "learning_rate": 5.809922737498198e-05, "loss": 0.0251, "step": 2380 }, { "grad_norm": 0.3577284514904022, "learning_rate": 5.777272602506165e-05, "loss": 0.0264, "step": 2390 }, { "grad_norm": 0.4154857397079468, "learning_rate": 5.744588467092483e-05, "loss": 0.0261, "step": 2400 }, { "grad_norm": 0.3121699094772339, "learning_rate": 5.7118717609671194e-05, "loss": 0.0232, "step": 2410 }, { "grad_norm": 0.44973379373550415, "learning_rate": 5.679123915264786e-05, "loss": 0.0232, "step": 2420 }, { "grad_norm": 0.3639560639858246, "learning_rate": 5.646346362482342e-05, "loss": 0.023, "step": 2430 }, { "grad_norm": 0.5088344812393188, "learning_rate": 5.613540536416132e-05, "loss": 0.0256, "step": 2440 }, { "grad_norm": 0.45135802030563354, "learning_rate": 5.5807078720992645e-05, "loss": 0.0242, "step": 2450 }, { "grad_norm": 0.39155149459838867, "learning_rate": 5.547849805738836e-05, "loss": 0.0239, "step": 2460 }, { "grad_norm": 0.37671616673469543, "learning_rate": 5.514967774653118e-05, "loss": 0.0242, "step": 2470 }, { "grad_norm": 0.43713143467903137, "learning_rate": 5.482063217208674e-05, "loss": 0.0256, "step": 2480 }, { "grad_norm": 0.3587101995944977, "learning_rate": 5.449137572757439e-05, "loss": 0.0243, "step": 2490 }, { "grad_norm": 0.3240886926651001, "learning_rate": 5.4161922815737696e-05, "loss": 0.0244, "step": 2500 }, { "grad_norm": 0.4713996946811676, "learning_rate": 5.3832287847914276e-05, "loss": 0.0244, "step": 2510 }, { "grad_norm": 0.41371750831604004, "learning_rate": 5.35024852434055e-05, "loss": 0.0222, "step": 2520 }, { "grad_norm": 0.47091564536094666, "learning_rate": 5.317252942884567e-05, "loss": 0.0258, "step": 2530 }, { "grad_norm": 0.34738633036613464, "learning_rate": 5.284243483757109e-05, "loss": 0.0231, "step": 2540 }, { "grad_norm": 0.3713128864765167, "learning_rate": 5.2512215908988484e-05, "loss": 0.0239, "step": 2550 }, { "grad_norm": 0.41222378611564636, "learning_rate": 5.218188708794357e-05, "loss": 0.0233, "step": 2560 }, { "grad_norm": 0.3636377155780792, "learning_rate": 5.18514628240891e-05, "loss": 0.0232, "step": 2570 }, { "grad_norm": 0.3390437066555023, "learning_rate": 5.1520957571252795e-05, "loss": 0.0237, "step": 2580 }, { "grad_norm": 0.4193287491798401, "learning_rate": 5.1190385786805106e-05, "loss": 0.0216, "step": 2590 }, { "grad_norm": 0.23783208429813385, "learning_rate": 5.085976193102677e-05, "loss": 0.0228, "step": 2600 }, { "grad_norm": 0.4361535310745239, "learning_rate": 5.052910046647634e-05, "loss": 0.0276, "step": 2610 }, { "grad_norm": 0.41962987184524536, "learning_rate": 5.0198415857357464e-05, "loss": 0.0224, "step": 2620 }, { "grad_norm": 0.40996408462524414, "learning_rate": 4.9867722568886223e-05, "loss": 0.023, "step": 2630 }, { "grad_norm": 0.36495038866996765, "learning_rate": 4.9537035066658314e-05, "loss": 0.0234, "step": 2640 }, { "grad_norm": 0.42483624815940857, "learning_rate": 4.920636781601638e-05, "loss": 0.0256, "step": 2650 }, { "grad_norm": 0.39142847061157227, "learning_rate": 4.88757352814172e-05, "loss": 0.0289, "step": 2660 }, { "grad_norm": 0.3761405348777771, "learning_rate": 4.8545151925798924e-05, "loss": 0.0242, "step": 2670 }, { "grad_norm": 0.323021799325943, "learning_rate": 4.821463220994848e-05, "loss": 0.0227, "step": 2680 }, { "grad_norm": 0.4299248158931732, "learning_rate": 4.788419059186895e-05, "loss": 0.0218, "step": 2690 }, { "grad_norm": 0.3656862676143646, "learning_rate": 4.7553841526147205e-05, "loss": 0.0217, "step": 2700 }, { "grad_norm": 0.4491414725780487, "learning_rate": 4.722359946332156e-05, "loss": 0.0224, "step": 2710 }, { "grad_norm": 0.3371823728084564, "learning_rate": 4.6893478849249654e-05, "loss": 0.0231, "step": 2720 }, { "grad_norm": 0.3152349591255188, "learning_rate": 4.656349412447664e-05, "loss": 0.0229, "step": 2730 }, { "grad_norm": 0.37586328387260437, "learning_rate": 4.623365972360337e-05, "loss": 0.0228, "step": 2740 }, { "grad_norm": 0.37701380252838135, "learning_rate": 4.590399007465503e-05, "loss": 0.0214, "step": 2750 }, { "grad_norm": 0.342559814453125, "learning_rate": 4.557449959845005e-05, "loss": 0.0241, "step": 2760 }, { "grad_norm": 0.32800132036209106, "learning_rate": 4.524520270796927e-05, "loss": 0.0226, "step": 2770 }, { "grad_norm": 0.32837751507759094, "learning_rate": 4.491611380772545e-05, "loss": 0.0222, "step": 2780 }, { "grad_norm": 0.2714412808418274, "learning_rate": 4.458724729313318e-05, "loss": 0.0211, "step": 2790 }, { "grad_norm": 0.2909301221370697, "learning_rate": 4.42586175498792e-05, "loss": 0.0221, "step": 2800 }, { "grad_norm": 0.36365005373954773, "learning_rate": 4.3930238953293094e-05, "loss": 0.0216, "step": 2810 }, { "grad_norm": 0.3241809010505676, "learning_rate": 4.360212586771847e-05, "loss": 0.0204, "step": 2820 }, { "grad_norm": 0.35609936714172363, "learning_rate": 4.327429264588463e-05, "loss": 0.0243, "step": 2830 }, { "grad_norm": 0.40654465556144714, "learning_rate": 4.2946753628278725e-05, "loss": 0.0213, "step": 2840 }, { "grad_norm": 0.418736070394516, "learning_rate": 4.2619523142518474e-05, "loss": 0.0204, "step": 2850 }, { "grad_norm": 0.36981862783432007, "learning_rate": 4.229261550272539e-05, "loss": 0.0215, "step": 2860 }, { "grad_norm": 0.33936744928359985, "learning_rate": 4.196604500889868e-05, "loss": 0.0224, "step": 2870 }, { "grad_norm": 0.32824283838272095, "learning_rate": 4.163982594628969e-05, "loss": 0.0217, "step": 2880 }, { "grad_norm": 0.37890446186065674, "learning_rate": 4.131397258477702e-05, "loss": 0.0222, "step": 2890 }, { "grad_norm": 0.3364039957523346, "learning_rate": 4.0988499178242315e-05, "loss": 0.0223, "step": 2900 }, { "grad_norm": 0.4417213499546051, "learning_rate": 4.066341996394678e-05, "loss": 0.0209, "step": 2910 }, { "grad_norm": 0.4310370683670044, "learning_rate": 4.033874916190833e-05, "loss": 0.023, "step": 2920 }, { "grad_norm": 0.3380214273929596, "learning_rate": 4.001450097427966e-05, "loss": 0.0231, "step": 2930 }, { "grad_norm": 0.35001277923583984, "learning_rate": 3.9690689584726894e-05, "loss": 0.0234, "step": 2940 }, { "grad_norm": 0.412845641374588, "learning_rate": 3.936732915780923e-05, "loss": 0.0215, "step": 2950 }, { "grad_norm": 0.37060216069221497, "learning_rate": 3.904443383835929e-05, "loss": 0.0216, "step": 2960 }, { "grad_norm": 0.3685567080974579, "learning_rate": 3.872201775086437e-05, "loss": 0.0214, "step": 2970 }, { "grad_norm": 0.3236818015575409, "learning_rate": 3.8400094998848616e-05, "loss": 0.0198, "step": 2980 }, { "grad_norm": 0.2800779640674591, "learning_rate": 3.807867966425611e-05, "loss": 0.0219, "step": 2990 }, { "grad_norm": 0.2978470027446747, "learning_rate": 3.775778580683481e-05, "loss": 0.0231, "step": 3000 } ], "logging_steps": 10, "max_steps": 5000, "num_input_tokens_seen": 0, "num_train_epochs": 9223372036854775807, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 96, "trial_name": null, "trial_params": null }