{ "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": 0.12638650834560394, "learning_rate": 3.6e-06, "loss": 1.1641, "step": 10 }, { "grad_norm": 0.1471242904663086, "learning_rate": 7.6e-06, "loss": 1.1535, "step": 20 }, { "grad_norm": 0.18666379153728485, "learning_rate": 1.16e-05, "loss": 1.1457, "step": 30 }, { "grad_norm": 0.14849230647087097, "learning_rate": 1.56e-05, "loss": 1.1223, "step": 40 }, { "grad_norm": 0.27684518694877625, "learning_rate": 1.9600000000000002e-05, "loss": 1.0957, "step": 50 }, { "grad_norm": 0.2600708305835724, "learning_rate": 2.36e-05, "loss": 1.0719, "step": 60 }, { "grad_norm": 0.5172604322433472, "learning_rate": 2.7600000000000003e-05, "loss": 1.0266, "step": 70 }, { "grad_norm": 0.44987690448760986, "learning_rate": 3.16e-05, "loss": 0.9682, "step": 80 }, { "grad_norm": 0.7133139967918396, "learning_rate": 3.56e-05, "loss": 0.9043, "step": 90 }, { "grad_norm": 0.652862548828125, "learning_rate": 3.960000000000001e-05, "loss": 0.8439, "step": 100 }, { "grad_norm": 0.6717215180397034, "learning_rate": 4.36e-05, "loss": 0.7908, "step": 110 }, { "grad_norm": 0.8351187109947205, "learning_rate": 4.76e-05, "loss": 0.7508, "step": 120 }, { "grad_norm": 0.951558530330658, "learning_rate": 5.16e-05, "loss": 0.7117, "step": 130 }, { "grad_norm": 0.7069472074508667, "learning_rate": 5.560000000000001e-05, "loss": 0.6824, "step": 140 }, { "grad_norm": 0.8377196788787842, "learning_rate": 5.96e-05, "loss": 0.6523, "step": 150 }, { "grad_norm": 0.7963162064552307, "learning_rate": 6.36e-05, "loss": 0.6193, "step": 160 }, { "grad_norm": 1.0922210216522217, "learning_rate": 6.76e-05, "loss": 0.5893, "step": 170 }, { "grad_norm": 1.2284756898880005, "learning_rate": 7.16e-05, "loss": 0.5648, "step": 180 }, { "grad_norm": 0.8342697024345398, "learning_rate": 7.560000000000001e-05, "loss": 0.5453, "step": 190 }, { "grad_norm": 1.121726155281067, "learning_rate": 7.960000000000001e-05, "loss": 0.5277, "step": 200 }, { "grad_norm": 0.8587872982025146, "learning_rate": 8.36e-05, "loss": 0.5082, "step": 210 }, { "grad_norm": 1.2177629470825195, "learning_rate": 8.76e-05, "loss": 0.4881, "step": 220 }, { "grad_norm": 1.0331931114196777, "learning_rate": 9.16e-05, "loss": 0.467, "step": 230 }, { "grad_norm": 1.178455114364624, "learning_rate": 9.56e-05, "loss": 0.4453, "step": 240 }, { "grad_norm": 1.0000393390655518, "learning_rate": 9.960000000000001e-05, "loss": 0.4235, "step": 250 }, { "grad_norm": 1.2453455924987793, "learning_rate": 9.999911419878559e-05, "loss": 0.4034, "step": 260 }, { "grad_norm": 1.474942684173584, "learning_rate": 9.999605221019081e-05, "loss": 0.3801, "step": 270 }, { "grad_norm": 0.9545984864234924, "learning_rate": 9.999080323230761e-05, "loss": 0.3551, "step": 280 }, { "grad_norm": 1.0123811960220337, "learning_rate": 9.998336749474329e-05, "loss": 0.329, "step": 290 }, { "grad_norm": 1.214898705482483, "learning_rate": 9.997374532276107e-05, "loss": 0.3039, "step": 300 }, { "grad_norm": 1.2700718641281128, "learning_rate": 9.996193713726596e-05, "loss": 0.2804, "step": 310 }, { "grad_norm": 1.0745455026626587, "learning_rate": 9.994794345478624e-05, "loss": 0.2604, "step": 320 }, { "grad_norm": 1.0220052003860474, "learning_rate": 9.99317648874509e-05, "loss": 0.2303, "step": 330 }, { "grad_norm": 0.9410139918327332, "learning_rate": 9.991340214296292e-05, "loss": 0.2094, "step": 340 }, { "grad_norm": 1.046053171157837, "learning_rate": 9.989285602456819e-05, "loss": 0.1971, "step": 350 }, { "grad_norm": 1.174741268157959, "learning_rate": 9.98701274310205e-05, "loss": 0.1773, "step": 360 }, { "grad_norm": 1.0372276306152344, "learning_rate": 9.984521735654218e-05, "loss": 0.1615, "step": 370 }, { "grad_norm": 1.0307488441467285, "learning_rate": 9.981812689078057e-05, "loss": 0.1429, "step": 380 }, { "grad_norm": 2.1818134784698486, "learning_rate": 9.978885721876041e-05, "loss": 0.1284, "step": 390 }, { "grad_norm": 0.9964090585708618, "learning_rate": 9.975740962083198e-05, "loss": 0.1258, "step": 400 }, { "grad_norm": 0.9651419520378113, "learning_rate": 9.972378547261504e-05, "loss": 0.1093, "step": 410 }, { "grad_norm": 1.0263780355453491, "learning_rate": 9.968798624493885e-05, "loss": 0.1062, "step": 420 }, { "grad_norm": 0.9092751741409302, "learning_rate": 9.965001350377753e-05, "loss": 0.1009, "step": 430 }, { "grad_norm": 1.1471643447875977, "learning_rate": 9.960986891018183e-05, "loss": 0.0967, "step": 440 }, { "grad_norm": 0.95041823387146, "learning_rate": 9.95675542202063e-05, "loss": 0.0941, "step": 450 }, { "grad_norm": 0.9787719249725342, "learning_rate": 9.952307128483256e-05, "loss": 0.0942, "step": 460 }, { "grad_norm": 0.9564359188079834, "learning_rate": 9.947642204988835e-05, "loss": 0.096, "step": 470 }, { "grad_norm": 0.9926328659057617, "learning_rate": 9.942760855596226e-05, "loss": 0.0931, "step": 480 }, { "grad_norm": 0.8731317520141602, "learning_rate": 9.937663293831471e-05, "loss": 0.0901, "step": 490 }, { "grad_norm": 1.1485458612442017, "learning_rate": 9.932349742678433e-05, "loss": 0.0875, "step": 500 }, { "grad_norm": 0.9461956024169922, "learning_rate": 9.926820434569051e-05, "loss": 0.0892, "step": 510 }, { "grad_norm": 0.8998910784721375, "learning_rate": 9.921075611373179e-05, "loss": 0.0853, "step": 520 }, { "grad_norm": 1.0842655897140503, "learning_rate": 9.915115524387988e-05, "loss": 0.0841, "step": 530 }, { "grad_norm": 1.0050004720687866, "learning_rate": 9.908940434326997e-05, "loss": 0.0864, "step": 540 }, { "grad_norm": 1.1228138208389282, "learning_rate": 9.902550611308645e-05, "loss": 0.0839, "step": 550 }, { "grad_norm": 0.8371630907058716, "learning_rate": 9.895946334844494e-05, "loss": 0.087, "step": 560 }, { "grad_norm": 0.9920855760574341, "learning_rate": 9.889127893826989e-05, "loss": 0.0833, "step": 570 }, { "grad_norm": 0.8540536165237427, "learning_rate": 9.882095586516831e-05, "loss": 0.0808, "step": 580 }, { "grad_norm": 1.0284672975540161, "learning_rate": 9.874849720529921e-05, "loss": 0.0778, "step": 590 }, { "grad_norm": 0.7409518361091614, "learning_rate": 9.867390612823914e-05, "loss": 0.0776, "step": 600 }, { "grad_norm": 0.7265949249267578, "learning_rate": 9.859718589684344e-05, "loss": 0.0775, "step": 610 }, { "grad_norm": 0.8303801417350769, "learning_rate": 9.851833986710353e-05, "loss": 0.0766, "step": 620 }, { "grad_norm": 0.846651017665863, "learning_rate": 9.843737148800023e-05, "loss": 0.0737, "step": 630 }, { "grad_norm": 0.8616825342178345, "learning_rate": 9.835428430135271e-05, "loss": 0.0761, "step": 640 }, { "grad_norm": 0.6212893724441528, "learning_rate": 9.82690819416637e-05, "loss": 0.0734, "step": 650 }, { "grad_norm": 0.950407862663269, "learning_rate": 9.818176813596041e-05, "loss": 0.0733, "step": 660 }, { "grad_norm": 0.8584088683128357, "learning_rate": 9.809234670363159e-05, "loss": 0.0729, "step": 670 }, { "grad_norm": 0.8692848682403564, "learning_rate": 9.800082155626034e-05, "loss": 0.0715, "step": 680 }, { "grad_norm": 0.813220202922821, "learning_rate": 9.790719669745312e-05, "loss": 0.0705, "step": 690 }, { "grad_norm": 0.9423041939735413, "learning_rate": 9.781147622266455e-05, "loss": 0.0696, "step": 700 }, { "grad_norm": 0.8096789121627808, "learning_rate": 9.771366431901831e-05, "loss": 0.0729, "step": 710 }, { "grad_norm": 0.949595034122467, "learning_rate": 9.761376526512394e-05, "loss": 0.0704, "step": 720 }, { "grad_norm": 0.8399985432624817, "learning_rate": 9.751178343088963e-05, "loss": 0.07, "step": 730 }, { "grad_norm": 0.708450198173523, "learning_rate": 9.740772327733123e-05, "loss": 0.0701, "step": 740 }, { "grad_norm": 0.8553755879402161, "learning_rate": 9.730158935637697e-05, "loss": 0.0696, "step": 750 }, { "grad_norm": 0.7043846845626831, "learning_rate": 9.719338631066834e-05, "loss": 0.0675, "step": 760 }, { "grad_norm": 0.8093163371086121, "learning_rate": 9.708311887335713e-05, "loss": 0.0656, "step": 770 }, { "grad_norm": 0.7058002352714539, "learning_rate": 9.697079186789823e-05, "loss": 0.0665, "step": 780 }, { "grad_norm": 0.6831558346748352, "learning_rate": 9.685641020783876e-05, "loss": 0.0641, "step": 790 }, { "grad_norm": 0.799716055393219, "learning_rate": 9.67399788966031e-05, "loss": 0.0627, "step": 800 }, { "grad_norm": 0.982138454914093, "learning_rate": 9.662150302727395e-05, "loss": 0.0637, "step": 810 }, { "grad_norm": 0.761420726776123, "learning_rate": 9.650098778236968e-05, "loss": 0.0653, "step": 820 }, { "grad_norm": 0.7208728790283203, "learning_rate": 9.637843843361749e-05, "loss": 0.0636, "step": 830 }, { "grad_norm": 0.8718505501747131, "learning_rate": 9.62538603417229e-05, "loss": 0.0619, "step": 840 }, { "grad_norm": 0.969348132610321, "learning_rate": 9.612725895613526e-05, "loss": 0.0615, "step": 850 }, { "grad_norm": 0.8718401789665222, "learning_rate": 9.599863981480926e-05, "loss": 0.0623, "step": 860 }, { "grad_norm": 0.6654447317123413, "learning_rate": 9.586800854396283e-05, "loss": 0.0608, "step": 870 }, { "grad_norm": 0.7654517889022827, "learning_rate": 9.573537085783095e-05, "loss": 0.0602, "step": 880 }, { "grad_norm": 0.8219175934791565, "learning_rate": 9.560073255841571e-05, "loss": 0.0594, "step": 890 }, { "grad_norm": 0.6851817965507507, "learning_rate": 9.546409953523247e-05, "loss": 0.0591, "step": 900 }, { "grad_norm": 0.7167078256607056, "learning_rate": 9.532547776505229e-05, "loss": 0.0574, "step": 910 }, { "grad_norm": 0.8798813819885254, "learning_rate": 9.518487331164048e-05, "loss": 0.0591, "step": 920 }, { "grad_norm": 0.5818827748298645, "learning_rate": 9.504229232549134e-05, "loss": 0.0574, "step": 930 }, { "grad_norm": 0.749271810054779, "learning_rate": 9.489774104355909e-05, "loss": 0.0574, "step": 940 }, { "grad_norm": 0.6833415031433105, "learning_rate": 9.475122578898507e-05, "loss": 0.0572, "step": 950 }, { "grad_norm": 0.6324511766433716, "learning_rate": 9.460275297082119e-05, "loss": 0.0554, "step": 960 }, { "grad_norm": 0.7919363975524902, "learning_rate": 9.445232908374948e-05, "loss": 0.0586, "step": 970 }, { "grad_norm": 0.6597112417221069, "learning_rate": 9.429996070779808e-05, "loss": 0.0561, "step": 980 }, { "grad_norm": 0.6228717565536499, "learning_rate": 9.414565450805333e-05, "loss": 0.0558, "step": 990 }, { "grad_norm": 0.7159019708633423, "learning_rate": 9.398941723436831e-05, "loss": 0.0575, "step": 1000 }, { "grad_norm": 0.8466086387634277, "learning_rate": 9.383125572106752e-05, "loss": 0.056, "step": 1010 }, { "grad_norm": 0.6202797293663025, "learning_rate": 9.367117688664791e-05, "loss": 0.0562, "step": 1020 }, { "grad_norm": 0.7398084402084351, "learning_rate": 9.35091877334763e-05, "loss": 0.0543, "step": 1030 }, { "grad_norm": 0.8202595114707947, "learning_rate": 9.334529534748297e-05, "loss": 0.0523, "step": 1040 }, { "grad_norm": 0.7353408932685852, "learning_rate": 9.317950689785188e-05, "loss": 0.0557, "step": 1050 }, { "grad_norm": 0.6730363368988037, "learning_rate": 9.301182963670688e-05, "loss": 0.0542, "step": 1060 }, { "grad_norm": 0.7827518582344055, "learning_rate": 9.284227089879456e-05, "loss": 0.0566, "step": 1070 }, { "grad_norm": 0.5198912024497986, "learning_rate": 9.26708381011634e-05, "loss": 0.0538, "step": 1080 }, { "grad_norm": 0.5192142128944397, "learning_rate": 9.249753874283937e-05, "loss": 0.0521, "step": 1090 }, { "grad_norm": 0.6771655678749084, "learning_rate": 9.232238040449779e-05, "loss": 0.0524, "step": 1100 }, { "grad_norm": 0.6441646218299866, "learning_rate": 9.214537074813181e-05, "loss": 0.0531, "step": 1110 }, { "grad_norm": 0.7039899826049805, "learning_rate": 9.196651751671724e-05, "loss": 0.054, "step": 1120 }, { "grad_norm": 0.7219718098640442, "learning_rate": 9.178582853387384e-05, "loss": 0.0522, "step": 1130 }, { "grad_norm": 0.5394071340560913, "learning_rate": 9.160331170352304e-05, "loss": 0.0522, "step": 1140 }, { "grad_norm": 0.6993072032928467, "learning_rate": 9.141897500954229e-05, "loss": 0.0525, "step": 1150 }, { "grad_norm": 0.694438636302948, "learning_rate": 9.123282651541576e-05, "loss": 0.0527, "step": 1160 }, { "grad_norm": 0.5264086127281189, "learning_rate": 9.104487436388161e-05, "loss": 0.0507, "step": 1170 }, { "grad_norm": 0.6317558288574219, "learning_rate": 9.085512677657582e-05, "loss": 0.0492, "step": 1180 }, { "grad_norm": 0.5922719836235046, "learning_rate": 9.066359205367258e-05, "loss": 0.0507, "step": 1190 }, { "grad_norm": 0.5283981561660767, "learning_rate": 9.047027857352112e-05, "loss": 0.0498, "step": 1200 }, { "grad_norm": 0.6506936550140381, "learning_rate": 9.027519479227935e-05, "loss": 0.0477, "step": 1210 }, { "grad_norm": 0.8326100707054138, "learning_rate": 9.007834924354383e-05, "loss": 0.0492, "step": 1220 }, { "grad_norm": 0.6938901543617249, "learning_rate": 8.987975053797655e-05, "loss": 0.05, "step": 1230 }, { "grad_norm": 0.6680724024772644, "learning_rate": 8.967940736292825e-05, "loss": 0.0504, "step": 1240 }, { "grad_norm": 0.6676413416862488, "learning_rate": 8.947732848205846e-05, "loss": 0.0505, "step": 1250 }, { "grad_norm": 0.6352572441101074, "learning_rate": 8.927352273495204e-05, "loss": 0.0516, "step": 1260 }, { "grad_norm": 0.5139537453651428, "learning_rate": 8.906799903673265e-05, "loss": 0.0481, "step": 1270 }, { "grad_norm": 0.5869550704956055, "learning_rate": 8.88607663776726e-05, "loss": 0.0472, "step": 1280 }, { "grad_norm": 0.7531103491783142, "learning_rate": 8.865183382279978e-05, "loss": 0.048, "step": 1290 }, { "grad_norm": 0.6038063764572144, "learning_rate": 8.844121051150096e-05, "loss": 0.0504, "step": 1300 }, { "grad_norm": 0.5663856267929077, "learning_rate": 8.822890565712211e-05, "loss": 0.0464, "step": 1310 }, { "grad_norm": 0.6821518540382385, "learning_rate": 8.801492854656536e-05, "loss": 0.0487, "step": 1320 }, { "grad_norm": 0.6302056908607483, "learning_rate": 8.779928853988268e-05, "loss": 0.0487, "step": 1330 }, { "grad_norm": 0.6849905848503113, "learning_rate": 8.758199506986655e-05, "loss": 0.0486, "step": 1340 }, { "grad_norm": 0.5426021218299866, "learning_rate": 8.73630576416373e-05, "loss": 0.049, "step": 1350 }, { "grad_norm": 0.6531778573989868, "learning_rate": 8.714248583222726e-05, "loss": 0.0497, "step": 1360 }, { "grad_norm": 0.7023406624794006, "learning_rate": 8.692028929016196e-05, "loss": 0.0472, "step": 1370 }, { "grad_norm": 0.7523959279060364, "learning_rate": 8.669647773503797e-05, "loss": 0.0465, "step": 1380 }, { "grad_norm": 0.6905308961868286, "learning_rate": 8.647106095709773e-05, "loss": 0.0496, "step": 1390 }, { "grad_norm": 0.48531508445739746, "learning_rate": 8.624404881680139e-05, "loss": 0.0466, "step": 1400 }, { "grad_norm": 0.4626646041870117, "learning_rate": 8.601545124439535e-05, "loss": 0.045, "step": 1410 }, { "grad_norm": 0.5854551196098328, "learning_rate": 8.5785278239478e-05, "loss": 0.0446, "step": 1420 }, { "grad_norm": 0.515155017375946, "learning_rate": 8.555353987056224e-05, "loss": 0.0465, "step": 1430 }, { "grad_norm": 0.6705062985420227, "learning_rate": 8.532024627463505e-05, "loss": 0.0473, "step": 1440 }, { "grad_norm": 0.6408502459526062, "learning_rate": 8.508540765671407e-05, "loss": 0.046, "step": 1450 }, { "grad_norm": 0.7304362058639526, "learning_rate": 8.484903428940121e-05, "loss": 0.0461, "step": 1460 }, { "grad_norm": 0.48894795775413513, "learning_rate": 8.461113651243334e-05, "loss": 0.0475, "step": 1470 }, { "grad_norm": 0.5249834060668945, "learning_rate": 8.437172473222987e-05, "loss": 0.0439, "step": 1480 }, { "grad_norm": 0.4411742091178894, "learning_rate": 8.413080942143767e-05, "loss": 0.0438, "step": 1490 }, { "grad_norm": 0.44417959451675415, "learning_rate": 8.388840111847288e-05, "loss": 0.0427, "step": 1500 }, { "grad_norm": 0.5642029047012329, "learning_rate": 8.364451042705998e-05, "loss": 0.0427, "step": 1510 }, { "grad_norm": 0.4869621694087982, "learning_rate": 8.33991480157679e-05, "loss": 0.0434, "step": 1520 }, { "grad_norm": 0.6327221393585205, "learning_rate": 8.315232461754338e-05, "loss": 0.0445, "step": 1530 }, { "grad_norm": 0.6919836401939392, "learning_rate": 8.290405102924144e-05, "loss": 0.0451, "step": 1540 }, { "grad_norm": 0.5408800840377808, "learning_rate": 8.265433811115316e-05, "loss": 0.0446, "step": 1550 }, { "grad_norm": 0.5201606750488281, "learning_rate": 8.240319678653049e-05, "loss": 0.0423, "step": 1560 }, { "grad_norm": 0.5895570516586304, "learning_rate": 8.215063804110857e-05, "loss": 0.0428, "step": 1570 }, { "grad_norm": 0.4627968966960907, "learning_rate": 8.189667292262512e-05, "loss": 0.042, "step": 1580 }, { "grad_norm": 0.7023901343345642, "learning_rate": 8.164131254033716e-05, "loss": 0.044, "step": 1590 }, { "grad_norm": 0.5879528522491455, "learning_rate": 8.138456806453503e-05, "loss": 0.0458, "step": 1600 }, { "grad_norm": 0.5253772735595703, "learning_rate": 8.112645072605386e-05, "loss": 0.0444, "step": 1610 }, { "grad_norm": 0.5280351638793945, "learning_rate": 8.086697181578222e-05, "loss": 0.0423, "step": 1620 }, { "grad_norm": 0.6314783096313477, "learning_rate": 8.060614268416823e-05, "loss": 0.0417, "step": 1630 }, { "grad_norm": 0.8157122731208801, "learning_rate": 8.034397474072309e-05, "loss": 0.0433, "step": 1640 }, { "grad_norm": 0.43822190165519714, "learning_rate": 8.008047945352193e-05, "loss": 0.0419, "step": 1650 }, { "grad_norm": 0.5351688265800476, "learning_rate": 7.981566834870225e-05, "loss": 0.0437, "step": 1660 }, { "grad_norm": 0.48337793350219727, "learning_rate": 7.954955300995961e-05, "loss": 0.042, "step": 1670 }, { "grad_norm": 0.5100006461143494, "learning_rate": 7.928214507804104e-05, "loss": 0.04, "step": 1680 }, { "grad_norm": 0.5312990546226501, "learning_rate": 7.901345625023576e-05, "loss": 0.0419, "step": 1690 }, { "grad_norm": 0.5234403610229492, "learning_rate": 7.874349827986354e-05, "loss": 0.0413, "step": 1700 }, { "grad_norm": 0.5953489542007446, "learning_rate": 7.847228297576053e-05, "loss": 0.0402, "step": 1710 }, { "grad_norm": 0.5609169006347656, "learning_rate": 7.819982220176276e-05, "loss": 0.0424, "step": 1720 }, { "grad_norm": 0.5080845355987549, "learning_rate": 7.792612787618714e-05, "loss": 0.0409, "step": 1730 }, { "grad_norm": 0.6321108341217041, "learning_rate": 7.765121197131009e-05, "loss": 0.0401, "step": 1740 }, { "grad_norm": 0.5982347130775452, "learning_rate": 7.737508651284391e-05, "loss": 0.0423, "step": 1750 }, { "grad_norm": 0.749245822429657, "learning_rate": 7.709776357941069e-05, "loss": 0.0414, "step": 1760 }, { "grad_norm": 0.46884486079216003, "learning_rate": 7.681925530201392e-05, "loss": 0.0419, "step": 1770 }, { "grad_norm": 0.5173981189727783, "learning_rate": 7.65395738635079e-05, "loss": 0.0405, "step": 1780 }, { "grad_norm": 0.4504048228263855, "learning_rate": 7.62587314980648e-05, "loss": 0.0397, "step": 1790 }, { "grad_norm": 0.4966204762458801, "learning_rate": 7.597674049063947e-05, "loss": 0.0396, "step": 1800 }, { "grad_norm": 0.37520983815193176, "learning_rate": 7.569361317643211e-05, "loss": 0.0391, "step": 1810 }, { "grad_norm": 0.4573592245578766, "learning_rate": 7.540936194034865e-05, "loss": 0.0396, "step": 1820 }, { "grad_norm": 0.39196085929870605, "learning_rate": 7.512399921645901e-05, "loss": 0.0394, "step": 1830 }, { "grad_norm": 0.5877107381820679, "learning_rate": 7.483753748745317e-05, "loss": 0.038, "step": 1840 }, { "grad_norm": 0.5072145462036133, "learning_rate": 7.454998928409516e-05, "loss": 0.0386, "step": 1850 }, { "grad_norm": 0.42455703020095825, "learning_rate": 7.426136718467493e-05, "loss": 0.0381, "step": 1860 }, { "grad_norm": 0.5039349794387817, "learning_rate": 7.397168381445812e-05, "loss": 0.04, "step": 1870 }, { "grad_norm": 0.5629942417144775, "learning_rate": 7.368095184513377e-05, "loss": 0.0391, "step": 1880 }, { "grad_norm": 0.7176268696784973, "learning_rate": 7.338918399426005e-05, "loss": 0.0411, "step": 1890 }, { "grad_norm": 0.4593715965747833, "learning_rate": 7.309639302470801e-05, "loss": 0.0413, "step": 1900 }, { "grad_norm": 0.3955693542957306, "learning_rate": 7.280259174410312e-05, "loss": 0.0387, "step": 1910 }, { "grad_norm": 0.5040004849433899, "learning_rate": 7.250779300426517e-05, "loss": 0.0385, "step": 1920 }, { "grad_norm": 0.5110053420066833, "learning_rate": 7.22120097006461e-05, "loss": 0.0393, "step": 1930 }, { "grad_norm": 0.48912274837493896, "learning_rate": 7.191525477176577e-05, "loss": 0.0378, "step": 1940 }, { "grad_norm": 0.549274742603302, "learning_rate": 7.161754119864616e-05, "loss": 0.0381, "step": 1950 }, { "grad_norm": 0.5900108218193054, "learning_rate": 7.131888200424339e-05, "loss": 0.0393, "step": 1960 }, { "grad_norm": 0.525826632976532, "learning_rate": 7.101929025287816e-05, "loss": 0.0389, "step": 1970 }, { "grad_norm": 0.5286293625831604, "learning_rate": 7.071877904966423e-05, "loss": 0.0385, "step": 1980 }, { "grad_norm": 0.5297350287437439, "learning_rate": 7.04173615399351e-05, "loss": 0.0384, "step": 1990 }, { "grad_norm": 0.47022709250450134, "learning_rate": 7.011505090866913e-05, "loss": 0.0383, "step": 2000 }, { "grad_norm": 0.38131898641586304, "learning_rate": 6.981186037991271e-05, "loss": 0.0368, "step": 2010 }, { "grad_norm": 0.5359529256820679, "learning_rate": 6.950780321620174e-05, "loss": 0.0364, "step": 2020 }, { "grad_norm": 0.4018920361995697, "learning_rate": 6.920289271798157e-05, "loss": 0.0382, "step": 2030 }, { "grad_norm": 0.38034963607788086, "learning_rate": 6.889714222302517e-05, "loss": 0.0376, "step": 2040 }, { "grad_norm": 0.4966801106929779, "learning_rate": 6.85905651058497e-05, "loss": 0.0363, "step": 2050 }, { "grad_norm": 0.3716416656970978, "learning_rate": 6.82831747771314e-05, "loss": 0.0354, "step": 2060 }, { "grad_norm": 0.5212883353233337, "learning_rate": 6.797498468311907e-05, "loss": 0.0367, "step": 2070 }, { "grad_norm": 0.7354364991188049, "learning_rate": 6.766600830504585e-05, "loss": 0.039, "step": 2080 }, { "grad_norm": 0.4120827615261078, "learning_rate": 6.735625915853942e-05, "loss": 0.0377, "step": 2090 }, { "grad_norm": 0.6581305265426636, "learning_rate": 6.70457507930309e-05, "loss": 0.0379, "step": 2100 }, { "grad_norm": 0.43628379702568054, "learning_rate": 6.673449679116215e-05, "loss": 0.0362, "step": 2110 }, { "grad_norm": 0.4119910001754761, "learning_rate": 6.642251076819148e-05, "loss": 0.0362, "step": 2120 }, { "grad_norm": 0.5746026635169983, "learning_rate": 6.610980637139827e-05, "loss": 0.0379, "step": 2130 }, { "grad_norm": 0.4867658317089081, "learning_rate": 6.579639727948583e-05, "loss": 0.0373, "step": 2140 }, { "grad_norm": 0.4590262770652771, "learning_rate": 6.548229720198315e-05, "loss": 0.0372, "step": 2150 }, { "grad_norm": 0.5440870523452759, "learning_rate": 6.516751987864517e-05, "loss": 0.0354, "step": 2160 }, { "grad_norm": 0.5225697755813599, "learning_rate": 6.485207907885175e-05, "loss": 0.0365, "step": 2170 }, { "grad_norm": 0.4947035610675812, "learning_rate": 6.453598860100536e-05, "loss": 0.0364, "step": 2180 }, { "grad_norm": 0.3744457960128784, "learning_rate": 6.421926227192749e-05, "loss": 0.0361, "step": 2190 }, { "grad_norm": 0.48017314076423645, "learning_rate": 6.390191394625381e-05, "loss": 0.0371, "step": 2200 }, { "grad_norm": 0.3859194219112396, "learning_rate": 6.358395750582817e-05, "loss": 0.0351, "step": 2210 }, { "grad_norm": 0.42149990797042847, "learning_rate": 6.326540685909532e-05, "loss": 0.0368, "step": 2220 }, { "grad_norm": 0.46686655282974243, "learning_rate": 6.294627594049249e-05, "loss": 0.036, "step": 2230 }, { "grad_norm": 0.5395793914794922, "learning_rate": 6.262657870983989e-05, "loss": 0.0358, "step": 2240 }, { "grad_norm": 0.36648452281951904, "learning_rate": 6.230632915173009e-05, "loss": 0.0344, "step": 2250 }, { "grad_norm": 0.3894996643066406, "learning_rate": 6.198554127491622e-05, "loss": 0.035, "step": 2260 }, { "grad_norm": 0.4819444417953491, "learning_rate": 6.166422911169923e-05, "loss": 0.0347, "step": 2270 }, { "grad_norm": 0.6196218132972717, "learning_rate": 6.1342406717314e-05, "loss": 0.0357, "step": 2280 }, { "grad_norm": 0.561904788017273, "learning_rate": 6.102008816931466e-05, "loss": 0.035, "step": 2290 }, { "grad_norm": 0.5268715620040894, "learning_rate": 6.069728756695866e-05, "loss": 0.0351, "step": 2300 }, { "grad_norm": 0.41774991154670715, "learning_rate": 6.037401903059008e-05, "loss": 0.0364, "step": 2310 }, { "grad_norm": 0.44381609559059143, "learning_rate": 6.005029670102195e-05, "loss": 0.0348, "step": 2320 }, { "grad_norm": 0.4341835379600525, "learning_rate": 5.972613473891766e-05, "loss": 0.0357, "step": 2330 }, { "grad_norm": 0.4438548982143402, "learning_rate": 5.940154732417158e-05, "loss": 0.0355, "step": 2340 }, { "grad_norm": 0.5221387147903442, "learning_rate": 5.907654865528876e-05, "loss": 0.0353, "step": 2350 }, { "grad_norm": 0.47114792466163635, "learning_rate": 5.875115294876381e-05, "loss": 0.0348, "step": 2360 }, { "grad_norm": 0.49710649251937866, "learning_rate": 5.842537443845908e-05, "loss": 0.0331, "step": 2370 }, { "grad_norm": 0.37483474612236023, "learning_rate": 5.809922737498198e-05, "loss": 0.0329, "step": 2380 }, { "grad_norm": 0.41048693656921387, "learning_rate": 5.777272602506165e-05, "loss": 0.034, "step": 2390 }, { "grad_norm": 0.6205533742904663, "learning_rate": 5.744588467092483e-05, "loss": 0.0349, "step": 2400 }, { "grad_norm": 0.6049986481666565, "learning_rate": 5.7118717609671194e-05, "loss": 0.0368, "step": 2410 }, { "grad_norm": 0.3437153995037079, "learning_rate": 5.679123915264786e-05, "loss": 0.035, "step": 2420 }, { "grad_norm": 0.4196714758872986, "learning_rate": 5.646346362482342e-05, "loss": 0.035, "step": 2430 }, { "grad_norm": 0.30259034037590027, "learning_rate": 5.613540536416132e-05, "loss": 0.0337, "step": 2440 }, { "grad_norm": 0.44949236512184143, "learning_rate": 5.5807078720992645e-05, "loss": 0.0335, "step": 2450 }, { "grad_norm": 0.4262710213661194, "learning_rate": 5.547849805738836e-05, "loss": 0.0344, "step": 2460 }, { "grad_norm": 0.378464013338089, "learning_rate": 5.514967774653118e-05, "loss": 0.0336, "step": 2470 }, { "grad_norm": 0.46783533692359924, "learning_rate": 5.482063217208674e-05, "loss": 0.0323, "step": 2480 }, { "grad_norm": 0.4644140899181366, "learning_rate": 5.449137572757439e-05, "loss": 0.0341, "step": 2490 }, { "grad_norm": 0.5068755745887756, "learning_rate": 5.4161922815737696e-05, "loss": 0.0342, "step": 2500 }, { "grad_norm": 0.4202300012111664, "learning_rate": 5.3832287847914276e-05, "loss": 0.0343, "step": 2510 }, { "grad_norm": 0.4912700951099396, "learning_rate": 5.35024852434055e-05, "loss": 0.0337, "step": 2520 }, { "grad_norm": 0.48302051424980164, "learning_rate": 5.317252942884567e-05, "loss": 0.0336, "step": 2530 }, { "grad_norm": 0.47471609711647034, "learning_rate": 5.284243483757109e-05, "loss": 0.0324, "step": 2540 }, { "grad_norm": 0.3633861839771271, "learning_rate": 5.2512215908988484e-05, "loss": 0.0314, "step": 2550 }, { "grad_norm": 0.3869474530220032, "learning_rate": 5.218188708794357e-05, "loss": 0.0322, "step": 2560 }, { "grad_norm": 0.32870373129844666, "learning_rate": 5.18514628240891e-05, "loss": 0.0323, "step": 2570 }, { "grad_norm": 0.42363566160202026, "learning_rate": 5.1520957571252795e-05, "loss": 0.0316, "step": 2580 }, { "grad_norm": 0.3828549385070801, "learning_rate": 5.1190385786805106e-05, "loss": 0.0322, "step": 2590 }, { "grad_norm": 0.35012924671173096, "learning_rate": 5.085976193102677e-05, "loss": 0.0326, "step": 2600 }, { "grad_norm": 0.3747711479663849, "learning_rate": 5.052910046647634e-05, "loss": 0.0314, "step": 2610 }, { "grad_norm": 0.5705577731132507, "learning_rate": 5.0198415857357464e-05, "loss": 0.0329, "step": 2620 }, { "grad_norm": 0.5018939971923828, "learning_rate": 4.9867722568886223e-05, "loss": 0.0317, "step": 2630 }, { "grad_norm": 0.5010145306587219, "learning_rate": 4.9537035066658314e-05, "loss": 0.0319, "step": 2640 }, { "grad_norm": 0.5248851776123047, "learning_rate": 4.920636781601638e-05, "loss": 0.0327, "step": 2650 }, { "grad_norm": 0.392741858959198, "learning_rate": 4.88757352814172e-05, "loss": 0.0331, "step": 2660 }, { "grad_norm": 0.34013861417770386, "learning_rate": 4.8545151925798924e-05, "loss": 0.0332, "step": 2670 }, { "grad_norm": 0.31544578075408936, "learning_rate": 4.821463220994848e-05, "loss": 0.032, "step": 2680 }, { "grad_norm": 0.4460863769054413, "learning_rate": 4.788419059186895e-05, "loss": 0.0319, "step": 2690 }, { "grad_norm": 0.3358592689037323, "learning_rate": 4.7553841526147205e-05, "loss": 0.0324, "step": 2700 }, { "grad_norm": 0.2845816910266876, "learning_rate": 4.722359946332156e-05, "loss": 0.0328, "step": 2710 }, { "grad_norm": 0.36149680614471436, "learning_rate": 4.6893478849249654e-05, "loss": 0.0318, "step": 2720 }, { "grad_norm": 0.317050576210022, "learning_rate": 4.656349412447664e-05, "loss": 0.0315, "step": 2730 }, { "grad_norm": 0.326821893453598, "learning_rate": 4.623365972360337e-05, "loss": 0.0316, "step": 2740 }, { "grad_norm": 0.40301528573036194, "learning_rate": 4.590399007465503e-05, "loss": 0.0306, "step": 2750 }, { "grad_norm": 0.31731849908828735, "learning_rate": 4.557449959845005e-05, "loss": 0.0298, "step": 2760 }, { "grad_norm": 0.38081982731819153, "learning_rate": 4.524520270796927e-05, "loss": 0.031, "step": 2770 }, { "grad_norm": 0.3864630162715912, "learning_rate": 4.491611380772545e-05, "loss": 0.0316, "step": 2780 }, { "grad_norm": 0.4013478755950928, "learning_rate": 4.458724729313318e-05, "loss": 0.0312, "step": 2790 }, { "grad_norm": 0.37432995438575745, "learning_rate": 4.42586175498792e-05, "loss": 0.0316, "step": 2800 }, { "grad_norm": 0.3317914605140686, "learning_rate": 4.3930238953293094e-05, "loss": 0.031, "step": 2810 }, { "grad_norm": 0.3005709946155548, "learning_rate": 4.360212586771847e-05, "loss": 0.0305, "step": 2820 }, { "grad_norm": 0.4643605351448059, "learning_rate": 4.327429264588463e-05, "loss": 0.0313, "step": 2830 }, { "grad_norm": 0.47143229842185974, "learning_rate": 4.2946753628278725e-05, "loss": 0.0311, "step": 2840 }, { "grad_norm": 0.45226556062698364, "learning_rate": 4.2619523142518474e-05, "loss": 0.0318, "step": 2850 }, { "grad_norm": 0.4073678255081177, "learning_rate": 4.229261550272539e-05, "loss": 0.0317, "step": 2860 }, { "grad_norm": 0.4119836091995239, "learning_rate": 4.196604500889868e-05, "loss": 0.0323, "step": 2870 }, { "grad_norm": 0.39866578578948975, "learning_rate": 4.163982594628969e-05, "loss": 0.0321, "step": 2880 }, { "grad_norm": 0.3677605986595154, "learning_rate": 4.131397258477702e-05, "loss": 0.0308, "step": 2890 }, { "grad_norm": 0.3429180085659027, "learning_rate": 4.0988499178242315e-05, "loss": 0.031, "step": 2900 }, { "grad_norm": 0.3174164295196533, "learning_rate": 4.066341996394678e-05, "loss": 0.0305, "step": 2910 }, { "grad_norm": 0.3029995560646057, "learning_rate": 4.033874916190833e-05, "loss": 0.0301, "step": 2920 }, { "grad_norm": 0.3135979175567627, "learning_rate": 4.001450097427966e-05, "loss": 0.0295, "step": 2930 }, { "grad_norm": 0.4622963070869446, "learning_rate": 3.9690689584726894e-05, "loss": 0.0292, "step": 2940 }, { "grad_norm": 0.48339372873306274, "learning_rate": 3.936732915780923e-05, "loss": 0.0318, "step": 2950 }, { "grad_norm": 0.3820773959159851, "learning_rate": 3.904443383835929e-05, "loss": 0.0309, "step": 2960 }, { "grad_norm": 0.3158888518810272, "learning_rate": 3.872201775086437e-05, "loss": 0.0303, "step": 2970 }, { "grad_norm": 0.30478447675704956, "learning_rate": 3.8400094998848616e-05, "loss": 0.0298, "step": 2980 }, { "grad_norm": 0.2526125907897949, "learning_rate": 3.807867966425611e-05, "loss": 0.0287, "step": 2990 }, { "grad_norm": 0.31405243277549744, "learning_rate": 3.775778580683481e-05, "loss": 0.0305, "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": 768, "trial_name": null, "trial_params": null }