Invalid JSON: Unexpected token 'N', ..."ad_norm": NaN,
"... is not valid JSON
| { | |
| "best_global_step": 82000, | |
| "best_metric": 3.5338425636291504, | |
| "best_model_checkpoint": "/scratch/cl5625/exceptions/models/resemble_to_push_frequency_1032/checkpoint-30000", | |
| "epoch": 29.703052190121156, | |
| "eval_steps": 1000, | |
| "global_step": 102000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014561975768872321, | |
| "grad_norm": 1.1883279085159302, | |
| "learning_rate": 0.000294, | |
| "loss": 8.4738, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.029123951537744643, | |
| "grad_norm": 0.5355018973350525, | |
| "learning_rate": 0.0005939999999999999, | |
| "loss": 6.7177, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04368592730661696, | |
| "grad_norm": 0.5124205946922302, | |
| "learning_rate": 0.0005998286713286713, | |
| "loss": 6.3373, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.058247903075489285, | |
| "grad_norm": 0.5119701027870178, | |
| "learning_rate": 0.0005996538461538461, | |
| "loss": 6.1315, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0728098788443616, | |
| "grad_norm": 0.5244374871253967, | |
| "learning_rate": 0.0005994790209790209, | |
| "loss": 5.989, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08737185461323392, | |
| "grad_norm": 0.4514008164405823, | |
| "learning_rate": 0.0005993041958041958, | |
| "loss": 5.855, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10193383038210624, | |
| "grad_norm": 0.41654127836227417, | |
| "learning_rate": 0.0005991293706293705, | |
| "loss": 5.7174, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.11649580615097857, | |
| "grad_norm": 0.4382358491420746, | |
| "learning_rate": 0.0005989545454545454, | |
| "loss": 5.5956, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.13105778191985087, | |
| "grad_norm": 0.549221932888031, | |
| "learning_rate": 0.0005987797202797202, | |
| "loss": 5.4909, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1456197576887232, | |
| "grad_norm": 0.4766194224357605, | |
| "learning_rate": 0.000598604895104895, | |
| "loss": 5.4, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16018173345759554, | |
| "grad_norm": 0.5269848704338074, | |
| "learning_rate": 0.0005984300699300698, | |
| "loss": 5.3285, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.17474370922646784, | |
| "grad_norm": 0.4068600535392761, | |
| "learning_rate": 0.0005982552447552447, | |
| "loss": 5.2405, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.18930568499534017, | |
| "grad_norm": 0.47763192653656006, | |
| "learning_rate": 0.0005980804195804195, | |
| "loss": 5.1842, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.20386766076421248, | |
| "grad_norm": 0.4301474392414093, | |
| "learning_rate": 0.0005979055944055943, | |
| "loss": 5.128, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.2184296365330848, | |
| "grad_norm": 0.39097562432289124, | |
| "learning_rate": 0.0005977307692307691, | |
| "loss": 5.0549, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.23299161230195714, | |
| "grad_norm": 0.4334748685359955, | |
| "learning_rate": 0.000597555944055944, | |
| "loss": 5.0117, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24755358807082944, | |
| "grad_norm": 0.48352745175361633, | |
| "learning_rate": 0.0005973811188811188, | |
| "loss": 4.9778, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.26211556383970175, | |
| "grad_norm": 0.5069511532783508, | |
| "learning_rate": 0.0005972062937062936, | |
| "loss": 4.929, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2766775396085741, | |
| "grad_norm": 0.47534990310668945, | |
| "learning_rate": 0.0005970314685314685, | |
| "loss": 4.8689, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.2912395153774464, | |
| "grad_norm": 0.41896557807922363, | |
| "learning_rate": 0.0005968566433566433, | |
| "loss": 4.8077, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2912395153774464, | |
| "eval_accuracy": 0.2569420831117012, | |
| "eval_loss": 4.736781120300293, | |
| "eval_runtime": 54.012, | |
| "eval_samples_per_second": 308.154, | |
| "eval_steps_per_second": 19.273, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3058014911463187, | |
| "grad_norm": 0.4391483664512634, | |
| "learning_rate": 0.0005966818181818181, | |
| "loss": 4.7635, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.3203634669151911, | |
| "grad_norm": 0.42747387290000916, | |
| "learning_rate": 0.0005965069930069929, | |
| "loss": 4.7166, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.3349254426840634, | |
| "grad_norm": 0.45990902185440063, | |
| "learning_rate": 0.0005963321678321677, | |
| "loss": 4.6916, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.3494874184529357, | |
| "grad_norm": 0.4686427414417267, | |
| "learning_rate": 0.0005961573426573425, | |
| "loss": 4.6507, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.36404939422180804, | |
| "grad_norm": 0.4218248128890991, | |
| "learning_rate": 0.0005959825174825174, | |
| "loss": 4.6193, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.37861136999068035, | |
| "grad_norm": 0.4387086033821106, | |
| "learning_rate": 0.0005958076923076922, | |
| "loss": 4.5909, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.39317334575955265, | |
| "grad_norm": 0.4904707372188568, | |
| "learning_rate": 0.000595632867132867, | |
| "loss": 4.5681, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.40773532152842495, | |
| "grad_norm": 0.4466973543167114, | |
| "learning_rate": 0.0005954580419580418, | |
| "loss": 4.5442, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.4222972972972973, | |
| "grad_norm": 0.39577051997184753, | |
| "learning_rate": 0.0005952832167832168, | |
| "loss": 4.5246, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.4368592730661696, | |
| "grad_norm": 0.4266783595085144, | |
| "learning_rate": 0.0005951083916083916, | |
| "loss": 4.4966, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4514212488350419, | |
| "grad_norm": 0.44683218002319336, | |
| "learning_rate": 0.0005949335664335664, | |
| "loss": 4.4784, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.4659832246039143, | |
| "grad_norm": 0.4334483742713928, | |
| "learning_rate": 0.0005947587412587413, | |
| "loss": 4.4545, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4805452003727866, | |
| "grad_norm": 0.4043181538581848, | |
| "learning_rate": 0.0005945839160839161, | |
| "loss": 4.4341, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.4951071761416589, | |
| "grad_norm": 0.39420944452285767, | |
| "learning_rate": 0.0005944090909090909, | |
| "loss": 4.4209, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5096691519105312, | |
| "grad_norm": 0.38630977272987366, | |
| "learning_rate": 0.0005942342657342657, | |
| "loss": 4.3946, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.5242311276794035, | |
| "grad_norm": 0.41390445828437805, | |
| "learning_rate": 0.0005940594405594406, | |
| "loss": 4.3856, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5387931034482759, | |
| "grad_norm": 0.42289671301841736, | |
| "learning_rate": 0.0005938846153846153, | |
| "loss": 4.3664, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.5533550792171482, | |
| "grad_norm": 0.4519951641559601, | |
| "learning_rate": 0.0005937097902097902, | |
| "loss": 4.3621, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5679170549860205, | |
| "grad_norm": 0.39452847838401794, | |
| "learning_rate": 0.000593534965034965, | |
| "loss": 4.3481, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.5824790307548928, | |
| "grad_norm": 0.42720577120780945, | |
| "learning_rate": 0.0005933601398601398, | |
| "loss": 4.3355, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5824790307548928, | |
| "eval_accuracy": 0.3001815149621097, | |
| "eval_loss": 4.278709411621094, | |
| "eval_runtime": 53.5915, | |
| "eval_samples_per_second": 310.572, | |
| "eval_steps_per_second": 19.425, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5970410065237651, | |
| "grad_norm": 0.41133683919906616, | |
| "learning_rate": 0.0005931853146853146, | |
| "loss": 4.3078, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.6116029822926374, | |
| "grad_norm": 0.4028146266937256, | |
| "learning_rate": 0.0005930104895104895, | |
| "loss": 4.2918, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.6261649580615097, | |
| "grad_norm": 0.39694148302078247, | |
| "learning_rate": 0.0005928356643356643, | |
| "loss": 4.3041, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.6407269338303822, | |
| "grad_norm": 0.3814305365085602, | |
| "learning_rate": 0.0005926608391608391, | |
| "loss": 4.2923, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6552889095992545, | |
| "grad_norm": 0.3657163679599762, | |
| "learning_rate": 0.000592486013986014, | |
| "loss": 4.2723, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.6698508853681268, | |
| "grad_norm": 0.38016071915626526, | |
| "learning_rate": 0.0005923111888111888, | |
| "loss": 4.2675, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6844128611369991, | |
| "grad_norm": 0.36959293484687805, | |
| "learning_rate": 0.0005921363636363636, | |
| "loss": 4.2591, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.6989748369058714, | |
| "grad_norm": 0.3834407925605774, | |
| "learning_rate": 0.0005919615384615384, | |
| "loss": 4.2461, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.7135368126747437, | |
| "grad_norm": 0.4075358510017395, | |
| "learning_rate": 0.0005917867132867133, | |
| "loss": 4.2657, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.7280987884436161, | |
| "grad_norm": 0.3681492805480957, | |
| "learning_rate": 0.0005916118881118881, | |
| "loss": 4.2323, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7426607642124884, | |
| "grad_norm": 0.3669564425945282, | |
| "learning_rate": 0.0005914370629370629, | |
| "loss": 4.228, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.7572227399813607, | |
| "grad_norm": 0.4404616057872772, | |
| "learning_rate": 0.0005912622377622377, | |
| "loss": 4.2063, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.771784715750233, | |
| "grad_norm": 0.3834710717201233, | |
| "learning_rate": 0.0005910874125874125, | |
| "loss": 4.1905, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.7863466915191053, | |
| "grad_norm": 0.3446391820907593, | |
| "learning_rate": 0.0005909125874125873, | |
| "loss": 4.189, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.8009086672879776, | |
| "grad_norm": 0.38983553647994995, | |
| "learning_rate": 0.0005907377622377622, | |
| "loss": 4.1879, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.8154706430568499, | |
| "grad_norm": 0.36041370034217834, | |
| "learning_rate": 0.000590562937062937, | |
| "loss": 4.1847, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.8300326188257223, | |
| "grad_norm": 0.37385591864585876, | |
| "learning_rate": 0.0005903881118881118, | |
| "loss": 4.1689, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.8445945945945946, | |
| "grad_norm": 0.389721542596817, | |
| "learning_rate": 0.0005902132867132867, | |
| "loss": 4.17, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.8591565703634669, | |
| "grad_norm": 0.33258622884750366, | |
| "learning_rate": 0.0005900384615384615, | |
| "loss": 4.1634, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.8737185461323392, | |
| "grad_norm": 0.37621429562568665, | |
| "learning_rate": 0.0005898636363636363, | |
| "loss": 4.1543, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8737185461323392, | |
| "eval_accuracy": 0.31520899734793917, | |
| "eval_loss": 4.0961079597473145, | |
| "eval_runtime": 53.531, | |
| "eval_samples_per_second": 310.923, | |
| "eval_steps_per_second": 19.447, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8882805219012115, | |
| "grad_norm": 0.3883044421672821, | |
| "learning_rate": 0.0005896888111888111, | |
| "loss": 4.1492, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.9028424976700838, | |
| "grad_norm": 0.35951223969459534, | |
| "learning_rate": 0.000589513986013986, | |
| "loss": 4.1353, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.9174044734389561, | |
| "grad_norm": 0.37769070267677307, | |
| "learning_rate": 0.0005893391608391608, | |
| "loss": 4.1325, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.9319664492078286, | |
| "grad_norm": 0.3636488616466522, | |
| "learning_rate": 0.0005891643356643356, | |
| "loss": 4.1155, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.9465284249767009, | |
| "grad_norm": 0.343472957611084, | |
| "learning_rate": 0.0005889895104895104, | |
| "loss": 4.1136, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.9610904007455732, | |
| "grad_norm": 0.3756231367588043, | |
| "learning_rate": 0.0005888146853146853, | |
| "loss": 4.1242, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9756523765144455, | |
| "grad_norm": 0.3466884195804596, | |
| "learning_rate": 0.00058863986013986, | |
| "loss": 4.1025, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.9902143522833178, | |
| "grad_norm": 0.34539276361465454, | |
| "learning_rate": 0.0005884650349650349, | |
| "loss": 4.0973, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.0046598322460392, | |
| "grad_norm": 0.35815510153770447, | |
| "learning_rate": 0.0005882902097902097, | |
| "loss": 4.0526, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.0192218080149114, | |
| "grad_norm": 0.35195082426071167, | |
| "learning_rate": 0.0005881153846153845, | |
| "loss": 4.0031, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0337837837837838, | |
| "grad_norm": 0.3461218774318695, | |
| "learning_rate": 0.0005879405594405594, | |
| "loss": 4.006, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.0483457595526562, | |
| "grad_norm": 0.39880794286727905, | |
| "learning_rate": 0.0005877657342657342, | |
| "loss": 4.0192, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.0629077353215284, | |
| "grad_norm": 0.34905946254730225, | |
| "learning_rate": 0.000587590909090909, | |
| "loss": 4.0175, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.0774697110904008, | |
| "grad_norm": 0.3371531367301941, | |
| "learning_rate": 0.0005874160839160838, | |
| "loss": 4.0141, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.092031686859273, | |
| "grad_norm": 0.3369714915752411, | |
| "learning_rate": 0.0005872412587412587, | |
| "loss": 3.9991, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.1065936626281454, | |
| "grad_norm": 0.3621531128883362, | |
| "learning_rate": 0.0005870664335664335, | |
| "loss": 3.9857, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.1211556383970178, | |
| "grad_norm": 0.34609004855155945, | |
| "learning_rate": 0.0005868916083916083, | |
| "loss": 4.0016, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.13571761416589, | |
| "grad_norm": 0.34326431155204773, | |
| "learning_rate": 0.0005867167832167831, | |
| "loss": 4.005, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.1502795899347624, | |
| "grad_norm": 0.3505842387676239, | |
| "learning_rate": 0.000586541958041958, | |
| "loss": 4.0129, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.1648415657036346, | |
| "grad_norm": 0.3398914635181427, | |
| "learning_rate": 0.0005863671328671328, | |
| "loss": 3.9969, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.1648415657036346, | |
| "eval_accuracy": 0.3254560448785691, | |
| "eval_loss": 3.988481283187866, | |
| "eval_runtime": 53.593, | |
| "eval_samples_per_second": 310.563, | |
| "eval_steps_per_second": 19.424, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.179403541472507, | |
| "grad_norm": 0.33963337540626526, | |
| "learning_rate": 0.0005861923076923076, | |
| "loss": 3.9891, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.1939655172413792, | |
| "grad_norm": 0.3412471115589142, | |
| "learning_rate": 0.0005860174825174824, | |
| "loss": 3.9894, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.2085274930102516, | |
| "grad_norm": 0.3301082253456116, | |
| "learning_rate": 0.0005858426573426573, | |
| "loss": 3.9921, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.2230894687791238, | |
| "grad_norm": 0.32301121950149536, | |
| "learning_rate": 0.000585667832167832, | |
| "loss": 3.9788, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.2376514445479962, | |
| "grad_norm": 0.32878032326698303, | |
| "learning_rate": 0.000585493006993007, | |
| "loss": 3.9755, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.2522134203168687, | |
| "grad_norm": 0.3783838748931885, | |
| "learning_rate": 0.0005853181818181817, | |
| "loss": 3.9738, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.2667753960857409, | |
| "grad_norm": 0.3759077191352844, | |
| "learning_rate": 0.0005851433566433565, | |
| "loss": 3.9662, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.2813373718546133, | |
| "grad_norm": 0.34620216488838196, | |
| "learning_rate": 0.0005849685314685315, | |
| "loss": 3.9784, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.2958993476234855, | |
| "grad_norm": 0.3216020166873932, | |
| "learning_rate": 0.0005847937062937063, | |
| "loss": 3.9534, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.3104613233923579, | |
| "grad_norm": 0.3530759811401367, | |
| "learning_rate": 0.0005846188811188811, | |
| "loss": 3.9602, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.3250232991612303, | |
| "grad_norm": 0.34322479367256165, | |
| "learning_rate": 0.0005844440559440559, | |
| "loss": 3.9551, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 1.3395852749301025, | |
| "grad_norm": 0.3483957350254059, | |
| "learning_rate": 0.0005842692307692308, | |
| "loss": 3.9348, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.354147250698975, | |
| "grad_norm": 0.33279702067375183, | |
| "learning_rate": 0.0005840944055944056, | |
| "loss": 3.9417, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.368709226467847, | |
| "grad_norm": 0.3175128698348999, | |
| "learning_rate": 0.0005839195804195804, | |
| "loss": 3.9446, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.3832712022367195, | |
| "grad_norm": 0.3718789219856262, | |
| "learning_rate": 0.0005837447552447552, | |
| "loss": 3.9483, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 1.397833178005592, | |
| "grad_norm": 0.33285394310951233, | |
| "learning_rate": 0.0005835699300699301, | |
| "loss": 3.9436, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.4123951537744641, | |
| "grad_norm": 0.3199831247329712, | |
| "learning_rate": 0.0005833951048951048, | |
| "loss": 3.9369, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 1.4269571295433363, | |
| "grad_norm": 0.3186275064945221, | |
| "learning_rate": 0.0005832202797202797, | |
| "loss": 3.9344, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.4415191053122087, | |
| "grad_norm": 0.34162044525146484, | |
| "learning_rate": 0.0005830454545454546, | |
| "loss": 3.9271, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.4560810810810811, | |
| "grad_norm": 0.32524988055229187, | |
| "learning_rate": 0.0005828706293706293, | |
| "loss": 3.9235, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.4560810810810811, | |
| "eval_accuracy": 0.33175510083145565, | |
| "eval_loss": 3.9142301082611084, | |
| "eval_runtime": 53.6459, | |
| "eval_samples_per_second": 310.257, | |
| "eval_steps_per_second": 19.405, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.4706430568499533, | |
| "grad_norm": 0.3223293721675873, | |
| "learning_rate": 0.0005826958041958042, | |
| "loss": 3.9109, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 1.4852050326188257, | |
| "grad_norm": 0.334349662065506, | |
| "learning_rate": 0.000582520979020979, | |
| "loss": 3.932, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.499767008387698, | |
| "grad_norm": 0.33222952485084534, | |
| "learning_rate": 0.0005823461538461538, | |
| "loss": 3.9152, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 1.5143289841565704, | |
| "grad_norm": 0.3161272406578064, | |
| "learning_rate": 0.0005821713286713286, | |
| "loss": 3.932, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.5288909599254428, | |
| "grad_norm": 0.3443957269191742, | |
| "learning_rate": 0.0005819965034965035, | |
| "loss": 3.9341, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 1.543452935694315, | |
| "grad_norm": 0.35085344314575195, | |
| "learning_rate": 0.0005818216783216783, | |
| "loss": 3.9098, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.5580149114631874, | |
| "grad_norm": 0.31371259689331055, | |
| "learning_rate": 0.0005816468531468531, | |
| "loss": 3.9094, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 1.5725768872320596, | |
| "grad_norm": 0.32282862067222595, | |
| "learning_rate": 0.0005814720279720279, | |
| "loss": 3.9211, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.587138863000932, | |
| "grad_norm": 0.3314749598503113, | |
| "learning_rate": 0.0005812972027972028, | |
| "loss": 3.9103, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 1.6017008387698044, | |
| "grad_norm": 0.3175921142101288, | |
| "learning_rate": 0.0005811223776223776, | |
| "loss": 3.901, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.6162628145386766, | |
| "grad_norm": 0.3080521523952484, | |
| "learning_rate": 0.0005809475524475524, | |
| "loss": 3.8964, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 1.6308247903075488, | |
| "grad_norm": 0.3255755305290222, | |
| "learning_rate": 0.0005807727272727272, | |
| "loss": 3.8989, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.6453867660764212, | |
| "grad_norm": 0.3227233290672302, | |
| "learning_rate": 0.0005805979020979021, | |
| "loss": 3.9009, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 1.6599487418452936, | |
| "grad_norm": 0.3223280906677246, | |
| "learning_rate": 0.0005804230769230769, | |
| "loss": 3.9062, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.674510717614166, | |
| "grad_norm": 0.32244929671287537, | |
| "learning_rate": 0.0005802482517482517, | |
| "loss": 3.8922, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 1.6890726933830382, | |
| "grad_norm": 0.3163047432899475, | |
| "learning_rate": 0.0005800734265734265, | |
| "loss": 3.894, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.7036346691519104, | |
| "grad_norm": 0.31790420413017273, | |
| "learning_rate": 0.0005798986013986013, | |
| "loss": 3.8831, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 1.7181966449207828, | |
| "grad_norm": 0.323431134223938, | |
| "learning_rate": 0.0005797237762237762, | |
| "loss": 3.8919, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.7327586206896552, | |
| "grad_norm": 0.3332827687263489, | |
| "learning_rate": 0.000579548951048951, | |
| "loss": 3.8789, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 1.7473205964585274, | |
| "grad_norm": 0.31257835030555725, | |
| "learning_rate": 0.0005793741258741258, | |
| "loss": 3.8897, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.7473205964585274, | |
| "eval_accuracy": 0.336940117228707, | |
| "eval_loss": 3.8567962646484375, | |
| "eval_runtime": 53.6231, | |
| "eval_samples_per_second": 310.389, | |
| "eval_steps_per_second": 19.413, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.7618825722273999, | |
| "grad_norm": 0.31113606691360474, | |
| "learning_rate": 0.0005791993006993006, | |
| "loss": 3.8798, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 1.776444547996272, | |
| "grad_norm": 0.34054034948349, | |
| "learning_rate": 0.0005790244755244755, | |
| "loss": 3.8707, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.7910065237651445, | |
| "grad_norm": 0.32504695653915405, | |
| "learning_rate": 0.0005788496503496503, | |
| "loss": 3.8798, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 1.8055684995340169, | |
| "grad_norm": 0.3181167244911194, | |
| "learning_rate": 0.0005786748251748251, | |
| "loss": 3.8682, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.820130475302889, | |
| "grad_norm": 0.33279845118522644, | |
| "learning_rate": 0.0005784999999999999, | |
| "loss": 3.8627, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 1.8346924510717613, | |
| "grad_norm": 0.3395768702030182, | |
| "learning_rate": 0.0005783251748251748, | |
| "loss": 3.8649, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.8492544268406337, | |
| "grad_norm": 0.34127599000930786, | |
| "learning_rate": 0.0005781503496503496, | |
| "loss": 3.8617, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 1.863816402609506, | |
| "grad_norm": 0.3437989354133606, | |
| "learning_rate": 0.0005779755244755244, | |
| "loss": 3.8601, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.8783783783783785, | |
| "grad_norm": 0.32382577657699585, | |
| "learning_rate": 0.0005778006993006993, | |
| "loss": 3.8475, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 1.8929403541472507, | |
| "grad_norm": 0.3303312659263611, | |
| "learning_rate": 0.000577625874125874, | |
| "loss": 3.8543, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.907502329916123, | |
| "grad_norm": 0.32527676224708557, | |
| "learning_rate": 0.0005774510489510489, | |
| "loss": 3.8602, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 1.9220643056849953, | |
| "grad_norm": 0.30908825993537903, | |
| "learning_rate": 0.0005772762237762237, | |
| "loss": 3.8526, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.9366262814538677, | |
| "grad_norm": 0.3196081817150116, | |
| "learning_rate": 0.0005771013986013985, | |
| "loss": 3.8611, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 1.9511882572227401, | |
| "grad_norm": 0.32832983136177063, | |
| "learning_rate": 0.0005769265734265733, | |
| "loss": 3.8493, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.9657502329916123, | |
| "grad_norm": 0.3023565411567688, | |
| "learning_rate": 0.0005767517482517482, | |
| "loss": 3.8493, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 1.9803122087604845, | |
| "grad_norm": 0.3191196024417877, | |
| "learning_rate": 0.000576576923076923, | |
| "loss": 3.8488, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.994874184529357, | |
| "grad_norm": 0.31798142194747925, | |
| "learning_rate": 0.0005764020979020978, | |
| "loss": 3.8442, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 2.0093196644920783, | |
| "grad_norm": 0.33970579504966736, | |
| "learning_rate": 0.0005762272727272726, | |
| "loss": 3.7736, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 2.0238816402609507, | |
| "grad_norm": 0.3101087808609009, | |
| "learning_rate": 0.0005760524475524475, | |
| "loss": 3.7549, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 2.0384436160298227, | |
| "grad_norm": 0.32137158513069153, | |
| "learning_rate": 0.0005758776223776223, | |
| "loss": 3.7427, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.0384436160298227, | |
| "eval_accuracy": 0.34147023121699915, | |
| "eval_loss": 3.8138842582702637, | |
| "eval_runtime": 53.7752, | |
| "eval_samples_per_second": 309.511, | |
| "eval_steps_per_second": 19.358, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.053005591798695, | |
| "grad_norm": 0.3288806974887848, | |
| "learning_rate": 0.0005757027972027971, | |
| "loss": 3.7408, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 2.0675675675675675, | |
| "grad_norm": 0.3187062740325928, | |
| "learning_rate": 0.000575527972027972, | |
| "loss": 3.7595, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 2.08212954333644, | |
| "grad_norm": 0.31951916217803955, | |
| "learning_rate": 0.0005753531468531468, | |
| "loss": 3.7586, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 2.0966915191053124, | |
| "grad_norm": 0.31987684965133667, | |
| "learning_rate": 0.0005751783216783216, | |
| "loss": 3.7384, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.1112534948741843, | |
| "grad_norm": 0.3017788529396057, | |
| "learning_rate": 0.0005750034965034964, | |
| "loss": 3.7678, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 2.1258154706430568, | |
| "grad_norm": 0.32916632294654846, | |
| "learning_rate": 0.0005748286713286712, | |
| "loss": 3.7579, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 2.140377446411929, | |
| "grad_norm": 0.3227897882461548, | |
| "learning_rate": 0.000574653846153846, | |
| "loss": 3.7496, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 2.1549394221808016, | |
| "grad_norm": 0.30625689029693604, | |
| "learning_rate": 0.000574479020979021, | |
| "loss": 3.7517, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 2.169501397949674, | |
| "grad_norm": 0.3217352032661438, | |
| "learning_rate": 0.0005743041958041958, | |
| "loss": 3.741, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 2.184063373718546, | |
| "grad_norm": 0.32221558690071106, | |
| "learning_rate": 0.0005741293706293706, | |
| "loss": 3.7483, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.1986253494874184, | |
| "grad_norm": 0.31215184926986694, | |
| "learning_rate": 0.0005739545454545454, | |
| "loss": 3.7611, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 2.213187325256291, | |
| "grad_norm": 0.3266601264476776, | |
| "learning_rate": 0.0005737797202797203, | |
| "loss": 3.7547, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.227749301025163, | |
| "grad_norm": 0.3010008931159973, | |
| "learning_rate": 0.0005736048951048951, | |
| "loss": 3.7511, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 2.2423112767940356, | |
| "grad_norm": 0.3031994700431824, | |
| "learning_rate": 0.0005734300699300699, | |
| "loss": 3.76, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 2.2568732525629076, | |
| "grad_norm": 0.32502564787864685, | |
| "learning_rate": 0.0005732552447552448, | |
| "loss": 3.7579, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 2.27143522833178, | |
| "grad_norm": 0.3163962960243225, | |
| "learning_rate": 0.0005730804195804196, | |
| "loss": 3.7531, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 2.2859972041006524, | |
| "grad_norm": 0.3225083649158478, | |
| "learning_rate": 0.0005729055944055944, | |
| "loss": 3.7468, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 2.300559179869525, | |
| "grad_norm": 0.3353878855705261, | |
| "learning_rate": 0.0005727307692307692, | |
| "loss": 3.7372, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 2.315121155638397, | |
| "grad_norm": 0.3147525191307068, | |
| "learning_rate": 0.0005725559440559441, | |
| "loss": 3.7397, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 2.3296831314072692, | |
| "grad_norm": 0.31996214389801025, | |
| "learning_rate": 0.0005723811188811188, | |
| "loss": 3.7463, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.3296831314072692, | |
| "eval_accuracy": 0.3446897173502343, | |
| "eval_loss": 3.7829577922821045, | |
| "eval_runtime": 53.5949, | |
| "eval_samples_per_second": 310.552, | |
| "eval_steps_per_second": 19.423, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.3442451071761417, | |
| "grad_norm": 0.329949289560318, | |
| "learning_rate": 0.0005722062937062937, | |
| "loss": 3.7594, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 2.358807082945014, | |
| "grad_norm": 0.3147149384021759, | |
| "learning_rate": 0.0005720314685314685, | |
| "loss": 3.7547, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 2.3733690587138865, | |
| "grad_norm": 0.299905925989151, | |
| "learning_rate": 0.0005718566433566433, | |
| "loss": 3.7459, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 2.3879310344827585, | |
| "grad_norm": 0.33270028233528137, | |
| "learning_rate": 0.0005716818181818181, | |
| "loss": 3.7605, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.402493010251631, | |
| "grad_norm": 0.34615278244018555, | |
| "learning_rate": 0.000571506993006993, | |
| "loss": 3.7527, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 2.4170549860205033, | |
| "grad_norm": 0.31800028681755066, | |
| "learning_rate": 0.0005713321678321678, | |
| "loss": 3.7431, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 2.4316169617893757, | |
| "grad_norm": 0.3355848789215088, | |
| "learning_rate": 0.0005711573426573426, | |
| "loss": 3.7401, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 2.4461789375582477, | |
| "grad_norm": 0.3147391080856323, | |
| "learning_rate": 0.0005709825174825175, | |
| "loss": 3.753, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.46074091332712, | |
| "grad_norm": 0.33956778049468994, | |
| "learning_rate": 0.0005708076923076923, | |
| "loss": 3.7509, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 2.4753028890959925, | |
| "grad_norm": 0.3316870927810669, | |
| "learning_rate": 0.0005706328671328671, | |
| "loss": 3.7459, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.489864864864865, | |
| "grad_norm": 0.3233761787414551, | |
| "learning_rate": 0.0005704580419580419, | |
| "loss": 3.7415, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 2.5044268406337373, | |
| "grad_norm": 0.31071245670318604, | |
| "learning_rate": 0.0005702832167832168, | |
| "loss": 3.7364, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 2.5189888164026097, | |
| "grad_norm": 0.3265255093574524, | |
| "learning_rate": 0.0005701083916083916, | |
| "loss": 3.7471, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 2.5335507921714817, | |
| "grad_norm": 0.3139096200466156, | |
| "learning_rate": 0.0005699335664335664, | |
| "loss": 3.7485, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 2.548112767940354, | |
| "grad_norm": 0.2998340427875519, | |
| "learning_rate": 0.0005697587412587412, | |
| "loss": 3.7417, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 2.5626747437092265, | |
| "grad_norm": 0.29732733964920044, | |
| "learning_rate": 0.000569583916083916, | |
| "loss": 3.7367, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.5772367194780985, | |
| "grad_norm": 0.3112543821334839, | |
| "learning_rate": 0.0005694090909090908, | |
| "loss": 3.7397, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 2.591798695246971, | |
| "grad_norm": 0.3016383647918701, | |
| "learning_rate": 0.0005692342657342657, | |
| "loss": 3.7537, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 2.6063606710158433, | |
| "grad_norm": 0.32809779047966003, | |
| "learning_rate": 0.0005690594405594405, | |
| "loss": 3.7348, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 2.6209226467847158, | |
| "grad_norm": 0.319830060005188, | |
| "learning_rate": 0.0005688846153846153, | |
| "loss": 3.7415, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.6209226467847158, | |
| "eval_accuracy": 0.3471662361006664, | |
| "eval_loss": 3.7527623176574707, | |
| "eval_runtime": 53.7475, | |
| "eval_samples_per_second": 309.67, | |
| "eval_steps_per_second": 19.368, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.635484622553588, | |
| "grad_norm": 0.32060742378234863, | |
| "learning_rate": 0.0005687097902097901, | |
| "loss": 3.7446, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 2.6500465983224606, | |
| "grad_norm": 0.3294517993927002, | |
| "learning_rate": 0.000568534965034965, | |
| "loss": 3.7421, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 2.6646085740913326, | |
| "grad_norm": 0.30391988158226013, | |
| "learning_rate": 0.0005683601398601398, | |
| "loss": 3.7342, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 2.679170549860205, | |
| "grad_norm": 0.3142305910587311, | |
| "learning_rate": 0.0005681853146853146, | |
| "loss": 3.7423, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.6937325256290774, | |
| "grad_norm": 0.3378458023071289, | |
| "learning_rate": 0.0005680104895104895, | |
| "loss": 3.7332, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 2.70829450139795, | |
| "grad_norm": 0.3309178054332733, | |
| "learning_rate": 0.0005678356643356643, | |
| "loss": 3.7415, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 2.7228564771668218, | |
| "grad_norm": 0.30197566747665405, | |
| "learning_rate": 0.0005676608391608391, | |
| "loss": 3.7353, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 2.737418452935694, | |
| "grad_norm": 0.2995157837867737, | |
| "learning_rate": 0.0005674860139860139, | |
| "loss": 3.7242, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.7519804287045666, | |
| "grad_norm": 0.3359026312828064, | |
| "learning_rate": 0.0005673111888111888, | |
| "loss": 3.7318, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 2.766542404473439, | |
| "grad_norm": 0.32080361247062683, | |
| "learning_rate": 0.0005671363636363635, | |
| "loss": 3.7254, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.7811043802423114, | |
| "grad_norm": 0.3272884786128998, | |
| "learning_rate": 0.0005669615384615384, | |
| "loss": 3.7415, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 2.795666356011184, | |
| "grad_norm": 0.31400012969970703, | |
| "learning_rate": 0.0005667867132867132, | |
| "loss": 3.7273, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.810228331780056, | |
| "grad_norm": 0.30123645067214966, | |
| "learning_rate": 0.000566611888111888, | |
| "loss": 3.7345, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 2.8247903075489282, | |
| "grad_norm": 0.33027133345603943, | |
| "learning_rate": 0.0005664370629370628, | |
| "loss": 3.7361, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 2.8393522833178007, | |
| "grad_norm": 0.30711743235588074, | |
| "learning_rate": 0.0005662622377622377, | |
| "loss": 3.7336, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 2.8539142590866726, | |
| "grad_norm": 0.31669116020202637, | |
| "learning_rate": 0.0005660874125874125, | |
| "loss": 3.7419, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.868476234855545, | |
| "grad_norm": 0.3051603138446808, | |
| "learning_rate": 0.0005659125874125873, | |
| "loss": 3.7307, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 2.8830382106244175, | |
| "grad_norm": 0.3133176267147064, | |
| "learning_rate": 0.0005657377622377622, | |
| "loss": 3.7137, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 2.89760018639329, | |
| "grad_norm": 0.3297509253025055, | |
| "learning_rate": 0.000565562937062937, | |
| "loss": 3.7195, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 2.9121621621621623, | |
| "grad_norm": 0.30900847911834717, | |
| "learning_rate": 0.0005653881118881118, | |
| "loss": 3.7289, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.9121621621621623, | |
| "eval_accuracy": 0.3495230617357806, | |
| "eval_loss": 3.728936195373535, | |
| "eval_runtime": 53.587, | |
| "eval_samples_per_second": 310.597, | |
| "eval_steps_per_second": 19.426, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.9267241379310347, | |
| "grad_norm": 0.318390816450119, | |
| "learning_rate": 0.0005652132867132866, | |
| "loss": 3.7109, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 2.9412861136999067, | |
| "grad_norm": 0.3189872205257416, | |
| "learning_rate": 0.0005650384615384615, | |
| "loss": 3.7119, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 2.955848089468779, | |
| "grad_norm": 0.30972564220428467, | |
| "learning_rate": 0.0005648636363636363, | |
| "loss": 3.7249, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 2.9704100652376515, | |
| "grad_norm": 0.31740841269493103, | |
| "learning_rate": 0.0005646888111888111, | |
| "loss": 3.716, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 2.984972041006524, | |
| "grad_norm": 0.3237694501876831, | |
| "learning_rate": 0.000564513986013986, | |
| "loss": 3.7168, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 2.999534016775396, | |
| "grad_norm": 0.3141046464443207, | |
| "learning_rate": 0.0005643391608391607, | |
| "loss": 3.7109, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 3.0139794967381173, | |
| "grad_norm": 0.3134516775608063, | |
| "learning_rate": 0.0005641643356643355, | |
| "loss": 3.6157, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 3.0285414725069897, | |
| "grad_norm": 0.32396963238716125, | |
| "learning_rate": 0.0005639895104895105, | |
| "loss": 3.6185, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 3.043103448275862, | |
| "grad_norm": 0.32163459062576294, | |
| "learning_rate": 0.0005638146853146853, | |
| "loss": 3.6242, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 3.0576654240447345, | |
| "grad_norm": 0.3513883054256439, | |
| "learning_rate": 0.0005636398601398601, | |
| "loss": 3.6147, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.072227399813607, | |
| "grad_norm": 0.3110412359237671, | |
| "learning_rate": 0.000563465034965035, | |
| "loss": 3.6164, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 3.086789375582479, | |
| "grad_norm": 0.3234538733959198, | |
| "learning_rate": 0.0005632902097902098, | |
| "loss": 3.6387, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 3.1013513513513513, | |
| "grad_norm": 0.3188924491405487, | |
| "learning_rate": 0.0005631153846153846, | |
| "loss": 3.6259, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 3.1159133271202237, | |
| "grad_norm": 0.32610708475112915, | |
| "learning_rate": 0.0005629405594405594, | |
| "loss": 3.6288, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 3.130475302889096, | |
| "grad_norm": 0.31207531690597534, | |
| "learning_rate": 0.0005627657342657343, | |
| "loss": 3.6214, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 3.145037278657968, | |
| "grad_norm": 0.30246466398239136, | |
| "learning_rate": 0.0005625909090909091, | |
| "loss": 3.6177, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 3.1595992544268405, | |
| "grad_norm": 0.3239559531211853, | |
| "learning_rate": 0.0005624160839160839, | |
| "loss": 3.6264, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 3.174161230195713, | |
| "grad_norm": 0.29902079701423645, | |
| "learning_rate": 0.0005622412587412587, | |
| "loss": 3.6267, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 3.1887232059645854, | |
| "grad_norm": 0.31506234407424927, | |
| "learning_rate": 0.0005620664335664336, | |
| "loss": 3.6461, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 3.2032851817334578, | |
| "grad_norm": 0.3308972418308258, | |
| "learning_rate": 0.0005618916083916083, | |
| "loss": 3.6325, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.2032851817334578, | |
| "eval_accuracy": 0.35166636802176204, | |
| "eval_loss": 3.715419292449951, | |
| "eval_runtime": 53.6089, | |
| "eval_samples_per_second": 310.471, | |
| "eval_steps_per_second": 19.418, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.2178471575023297, | |
| "grad_norm": 0.3090171217918396, | |
| "learning_rate": 0.0005617167832167832, | |
| "loss": 3.6222, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 3.232409133271202, | |
| "grad_norm": 0.3381396234035492, | |
| "learning_rate": 0.000561541958041958, | |
| "loss": 3.6412, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 3.2469711090400746, | |
| "grad_norm": 0.31572040915489197, | |
| "learning_rate": 0.0005613671328671328, | |
| "loss": 3.6387, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 3.261533084808947, | |
| "grad_norm": 0.3284361660480499, | |
| "learning_rate": 0.0005611923076923077, | |
| "loss": 3.6426, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 3.276095060577819, | |
| "grad_norm": 0.30892351269721985, | |
| "learning_rate": 0.0005610174825174825, | |
| "loss": 3.6434, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 3.2906570363466914, | |
| "grad_norm": 0.31443294882774353, | |
| "learning_rate": 0.0005608426573426573, | |
| "loss": 3.6351, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 3.305219012115564, | |
| "grad_norm": 0.32290583848953247, | |
| "learning_rate": 0.0005606678321678321, | |
| "loss": 3.6447, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 3.319780987884436, | |
| "grad_norm": 0.30862802267074585, | |
| "learning_rate": 0.000560493006993007, | |
| "loss": 3.634, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 3.3343429636533086, | |
| "grad_norm": 0.31837892532348633, | |
| "learning_rate": 0.0005603181818181818, | |
| "loss": 3.635, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 3.348904939422181, | |
| "grad_norm": 0.3183481693267822, | |
| "learning_rate": 0.0005601433566433566, | |
| "loss": 3.6532, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.363466915191053, | |
| "grad_norm": 0.334343284368515, | |
| "learning_rate": 0.0005599685314685314, | |
| "loss": 3.6394, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 3.3780288909599254, | |
| "grad_norm": 0.2964753806591034, | |
| "learning_rate": 0.0005597937062937063, | |
| "loss": 3.6397, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 3.392590866728798, | |
| "grad_norm": 0.34382757544517517, | |
| "learning_rate": 0.0005596188811188811, | |
| "loss": 3.6302, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 3.4071528424976703, | |
| "grad_norm": 0.31933602690696716, | |
| "learning_rate": 0.0005594440559440559, | |
| "loss": 3.631, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 3.4217148182665422, | |
| "grad_norm": 0.31780973076820374, | |
| "learning_rate": 0.0005592692307692307, | |
| "loss": 3.6434, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 3.4362767940354146, | |
| "grad_norm": 0.31436842679977417, | |
| "learning_rate": 0.0005590944055944055, | |
| "loss": 3.6434, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 3.450838769804287, | |
| "grad_norm": 0.3354842960834503, | |
| "learning_rate": 0.0005589195804195803, | |
| "loss": 3.6543, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 3.4654007455731595, | |
| "grad_norm": 0.3190697431564331, | |
| "learning_rate": 0.0005587447552447552, | |
| "loss": 3.6459, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 3.479962721342032, | |
| "grad_norm": 0.3107091188430786, | |
| "learning_rate": 0.00055856993006993, | |
| "loss": 3.637, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 3.494524697110904, | |
| "grad_norm": 0.30985352396965027, | |
| "learning_rate": 0.0005583951048951048, | |
| "loss": 3.6268, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.494524697110904, | |
| "eval_accuracy": 0.35349927172970896, | |
| "eval_loss": 3.69624400138855, | |
| "eval_runtime": 53.5399, | |
| "eval_samples_per_second": 310.871, | |
| "eval_steps_per_second": 19.443, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.5090866728797763, | |
| "grad_norm": 0.3227110505104065, | |
| "learning_rate": 0.0005582202797202797, | |
| "loss": 3.6509, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 3.5236486486486487, | |
| "grad_norm": 0.3478952944278717, | |
| "learning_rate": 0.0005580454545454545, | |
| "loss": 3.6505, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 3.538210624417521, | |
| "grad_norm": 0.30305859446525574, | |
| "learning_rate": 0.0005578706293706293, | |
| "loss": 3.6373, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 3.552772600186393, | |
| "grad_norm": 0.33472204208374023, | |
| "learning_rate": 0.0005576958041958041, | |
| "loss": 3.6524, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 3.5673345759552655, | |
| "grad_norm": 0.32605162262916565, | |
| "learning_rate": 0.000557520979020979, | |
| "loss": 3.6371, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 3.581896551724138, | |
| "grad_norm": 0.31411874294281006, | |
| "learning_rate": 0.0005573461538461538, | |
| "loss": 3.6274, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 3.5964585274930103, | |
| "grad_norm": 0.34198397397994995, | |
| "learning_rate": 0.0005571713286713286, | |
| "loss": 3.6404, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 3.6110205032618827, | |
| "grad_norm": 0.3327263295650482, | |
| "learning_rate": 0.0005569965034965034, | |
| "loss": 3.66, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 3.625582479030755, | |
| "grad_norm": 0.322231650352478, | |
| "learning_rate": 0.0005568216783216783, | |
| "loss": 3.6466, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 3.640144454799627, | |
| "grad_norm": 0.3001907765865326, | |
| "learning_rate": 0.000556646853146853, | |
| "loss": 3.6305, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.6547064305684995, | |
| "grad_norm": 0.3235301971435547, | |
| "learning_rate": 0.0005564720279720279, | |
| "loss": 3.6436, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 3.669268406337372, | |
| "grad_norm": 0.31615960597991943, | |
| "learning_rate": 0.0005562972027972027, | |
| "loss": 3.6461, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 3.683830382106244, | |
| "grad_norm": 0.31696444749832153, | |
| "learning_rate": 0.0005561223776223775, | |
| "loss": 3.6492, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 3.6983923578751163, | |
| "grad_norm": 0.33829542994499207, | |
| "learning_rate": 0.0005559475524475524, | |
| "loss": 3.6339, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 3.7129543336439887, | |
| "grad_norm": 0.3388734459877014, | |
| "learning_rate": 0.0005557727272727272, | |
| "loss": 3.6437, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 3.727516309412861, | |
| "grad_norm": 0.33483371138572693, | |
| "learning_rate": 0.000555597902097902, | |
| "loss": 3.6441, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 3.7420782851817336, | |
| "grad_norm": 0.3170323967933655, | |
| "learning_rate": 0.0005554230769230768, | |
| "loss": 3.653, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 3.756640260950606, | |
| "grad_norm": 0.3122214674949646, | |
| "learning_rate": 0.0005552482517482517, | |
| "loss": 3.6459, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 3.771202236719478, | |
| "grad_norm": 0.3186436891555786, | |
| "learning_rate": 0.0005550734265734265, | |
| "loss": 3.6363, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 3.7857642124883504, | |
| "grad_norm": 0.30622565746307373, | |
| "learning_rate": 0.0005548986013986013, | |
| "loss": 3.6435, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.7857642124883504, | |
| "eval_accuracy": 0.35488867599661567, | |
| "eval_loss": 3.6783316135406494, | |
| "eval_runtime": 53.7191, | |
| "eval_samples_per_second": 309.834, | |
| "eval_steps_per_second": 19.379, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.800326188257223, | |
| "grad_norm": 0.3129367232322693, | |
| "learning_rate": 0.0005547237762237761, | |
| "loss": 3.6207, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 3.814888164026095, | |
| "grad_norm": 0.32513627409935, | |
| "learning_rate": 0.000554548951048951, | |
| "loss": 3.6369, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 3.829450139794967, | |
| "grad_norm": 0.30402615666389465, | |
| "learning_rate": 0.0005543741258741258, | |
| "loss": 3.6543, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 3.8440121155638396, | |
| "grad_norm": 0.3050006330013275, | |
| "learning_rate": 0.0005541993006993006, | |
| "loss": 3.6357, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 3.858574091332712, | |
| "grad_norm": 0.2974061071872711, | |
| "learning_rate": 0.0005540244755244756, | |
| "loss": 3.6411, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 3.8731360671015844, | |
| "grad_norm": 0.3141818046569824, | |
| "learning_rate": 0.0005538496503496502, | |
| "loss": 3.6407, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 3.887698042870457, | |
| "grad_norm": 0.3138577938079834, | |
| "learning_rate": 0.0005536748251748252, | |
| "loss": 3.6346, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 3.9022600186393293, | |
| "grad_norm": 0.3083747625350952, | |
| "learning_rate": 0.0005535, | |
| "loss": 3.6563, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 3.9168219944082012, | |
| "grad_norm": 0.3096838593482971, | |
| "learning_rate": 0.0005533251748251748, | |
| "loss": 3.6473, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 3.9313839701770736, | |
| "grad_norm": 0.30454158782958984, | |
| "learning_rate": 0.0005531503496503496, | |
| "loss": 3.6444, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 3.945945945945946, | |
| "grad_norm": 0.3204196095466614, | |
| "learning_rate": 0.0005529755244755245, | |
| "loss": 3.6318, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 3.960507921714818, | |
| "grad_norm": 0.32237592339515686, | |
| "learning_rate": 0.0005528006993006993, | |
| "loss": 3.6528, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 3.9750698974836904, | |
| "grad_norm": 0.3079224228858948, | |
| "learning_rate": 0.0005526258741258741, | |
| "loss": 3.6209, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 3.989631873252563, | |
| "grad_norm": 0.31364694237709045, | |
| "learning_rate": 0.0005524510489510489, | |
| "loss": 3.6271, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 4.004077353215284, | |
| "grad_norm": 0.3244830369949341, | |
| "learning_rate": 0.0005522762237762238, | |
| "loss": 3.6119, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 4.018639328984157, | |
| "grad_norm": 0.3311712443828583, | |
| "learning_rate": 0.0005521013986013986, | |
| "loss": 3.5161, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 4.033201304753029, | |
| "grad_norm": 0.323055237531662, | |
| "learning_rate": 0.0005519265734265734, | |
| "loss": 3.5338, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 4.0477632805219015, | |
| "grad_norm": 0.3451452851295471, | |
| "learning_rate": 0.0005517517482517482, | |
| "loss": 3.5432, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 4.062325256290774, | |
| "grad_norm": 0.3319436311721802, | |
| "learning_rate": 0.0005515769230769231, | |
| "loss": 3.5317, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 4.076887232059645, | |
| "grad_norm": 0.311636745929718, | |
| "learning_rate": 0.0005514020979020979, | |
| "loss": 3.5409, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.076887232059645, | |
| "eval_accuracy": 0.3559829626609214, | |
| "eval_loss": 3.6699917316436768, | |
| "eval_runtime": 53.6105, | |
| "eval_samples_per_second": 310.462, | |
| "eval_steps_per_second": 19.418, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.091449207828518, | |
| "grad_norm": 0.32985007762908936, | |
| "learning_rate": 0.0005512272727272727, | |
| "loss": 3.5268, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 4.10601118359739, | |
| "grad_norm": 0.32016435265541077, | |
| "learning_rate": 0.0005510524475524475, | |
| "loss": 3.5445, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 4.120573159366263, | |
| "grad_norm": 0.3203654885292053, | |
| "learning_rate": 0.0005508776223776223, | |
| "loss": 3.5486, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 4.135135135135135, | |
| "grad_norm": 0.33023160696029663, | |
| "learning_rate": 0.0005507027972027972, | |
| "loss": 3.5481, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 4.1496971109040075, | |
| "grad_norm": 0.3284917175769806, | |
| "learning_rate": 0.000550527972027972, | |
| "loss": 3.537, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 4.16425908667288, | |
| "grad_norm": 0.3125667870044708, | |
| "learning_rate": 0.0005503531468531468, | |
| "loss": 3.5498, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 4.178821062441752, | |
| "grad_norm": 0.35497283935546875, | |
| "learning_rate": 0.0005501783216783216, | |
| "loss": 3.5459, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 4.193383038210625, | |
| "grad_norm": 0.3228631913661957, | |
| "learning_rate": 0.0005500034965034965, | |
| "loss": 3.5677, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 4.207945013979497, | |
| "grad_norm": 0.3228815197944641, | |
| "learning_rate": 0.0005498286713286713, | |
| "loss": 3.57, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 4.222506989748369, | |
| "grad_norm": 0.32745644450187683, | |
| "learning_rate": 0.0005496538461538461, | |
| "loss": 3.5578, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.237068965517241, | |
| "grad_norm": 0.3445773124694824, | |
| "learning_rate": 0.0005494790209790209, | |
| "loss": 3.5642, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 4.2516309412861135, | |
| "grad_norm": 0.3111281991004944, | |
| "learning_rate": 0.0005493041958041958, | |
| "loss": 3.5579, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 4.266192917054986, | |
| "grad_norm": 0.2998022139072418, | |
| "learning_rate": 0.0005491293706293706, | |
| "loss": 3.5598, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 4.280754892823858, | |
| "grad_norm": 0.30128976702690125, | |
| "learning_rate": 0.0005489545454545454, | |
| "loss": 3.5697, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 4.295316868592731, | |
| "grad_norm": 0.3182757794857025, | |
| "learning_rate": 0.0005487797202797203, | |
| "loss": 3.562, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 4.309878844361603, | |
| "grad_norm": 0.30610358715057373, | |
| "learning_rate": 0.000548604895104895, | |
| "loss": 3.5624, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 4.324440820130476, | |
| "grad_norm": 0.3180147409439087, | |
| "learning_rate": 0.0005484300699300699, | |
| "loss": 3.5558, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 4.339002795899348, | |
| "grad_norm": 0.31451013684272766, | |
| "learning_rate": 0.0005482552447552447, | |
| "loss": 3.5662, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 4.3535647716682195, | |
| "grad_norm": 0.3290238678455353, | |
| "learning_rate": 0.0005480804195804195, | |
| "loss": 3.5619, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 4.368126747437092, | |
| "grad_norm": 0.33237355947494507, | |
| "learning_rate": 0.0005479055944055943, | |
| "loss": 3.5812, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.368126747437092, | |
| "eval_accuracy": 0.35728536014459117, | |
| "eval_loss": 3.6612935066223145, | |
| "eval_runtime": 53.7257, | |
| "eval_samples_per_second": 309.796, | |
| "eval_steps_per_second": 19.376, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.382688723205964, | |
| "grad_norm": 0.32442939281463623, | |
| "learning_rate": 0.0005477307692307692, | |
| "loss": 3.576, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 4.397250698974837, | |
| "grad_norm": 0.31378301978111267, | |
| "learning_rate": 0.000547555944055944, | |
| "loss": 3.5708, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 4.411812674743709, | |
| "grad_norm": 0.32099053263664246, | |
| "learning_rate": 0.0005473811188811188, | |
| "loss": 3.5733, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 4.426374650512582, | |
| "grad_norm": 0.34932631254196167, | |
| "learning_rate": 0.0005472062937062936, | |
| "loss": 3.5663, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 4.440936626281454, | |
| "grad_norm": 0.31164199113845825, | |
| "learning_rate": 0.0005470314685314685, | |
| "loss": 3.5757, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 4.455498602050326, | |
| "grad_norm": 0.3159792721271515, | |
| "learning_rate": 0.0005468566433566433, | |
| "loss": 3.5567, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 4.470060577819199, | |
| "grad_norm": 0.34067076444625854, | |
| "learning_rate": 0.0005466818181818181, | |
| "loss": 3.5713, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 4.484622553588071, | |
| "grad_norm": 0.32717546820640564, | |
| "learning_rate": 0.000546506993006993, | |
| "loss": 3.5756, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 4.499184529356943, | |
| "grad_norm": 0.32357490062713623, | |
| "learning_rate": 0.0005463321678321678, | |
| "loss": 3.5765, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 4.513746505125815, | |
| "grad_norm": 0.3132951855659485, | |
| "learning_rate": 0.0005461573426573426, | |
| "loss": 3.5823, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 4.528308480894688, | |
| "grad_norm": 0.31881314516067505, | |
| "learning_rate": 0.0005459825174825174, | |
| "loss": 3.5746, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 4.54287045666356, | |
| "grad_norm": 0.3236841857433319, | |
| "learning_rate": 0.0005458076923076922, | |
| "loss": 3.5769, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 4.5574324324324325, | |
| "grad_norm": 0.31546154618263245, | |
| "learning_rate": 0.000545632867132867, | |
| "loss": 3.573, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 4.571994408201305, | |
| "grad_norm": 0.3234204053878784, | |
| "learning_rate": 0.0005454580419580419, | |
| "loss": 3.5809, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 4.586556383970177, | |
| "grad_norm": 0.3184894621372223, | |
| "learning_rate": 0.0005452832167832167, | |
| "loss": 3.5782, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 4.60111835973905, | |
| "grad_norm": 0.3175009787082672, | |
| "learning_rate": 0.0005451083916083915, | |
| "loss": 3.5773, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 4.615680335507921, | |
| "grad_norm": 0.3093114197254181, | |
| "learning_rate": 0.0005449335664335663, | |
| "loss": 3.5604, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 4.630242311276794, | |
| "grad_norm": 0.30245575308799744, | |
| "learning_rate": 0.0005447587412587412, | |
| "loss": 3.5744, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 4.644804287045666, | |
| "grad_norm": 0.31706503033638, | |
| "learning_rate": 0.000544583916083916, | |
| "loss": 3.5589, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 4.6593662628145385, | |
| "grad_norm": 0.31915611028671265, | |
| "learning_rate": 0.0005444090909090908, | |
| "loss": 3.5711, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.6593662628145385, | |
| "eval_accuracy": 0.35867029649560195, | |
| "eval_loss": 3.646385431289673, | |
| "eval_runtime": 53.6836, | |
| "eval_samples_per_second": 310.039, | |
| "eval_steps_per_second": 19.391, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.673928238583411, | |
| "grad_norm": 0.3159019649028778, | |
| "learning_rate": 0.0005442342657342657, | |
| "loss": 3.5764, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 4.688490214352283, | |
| "grad_norm": 0.33272585272789, | |
| "learning_rate": 0.0005440594405594405, | |
| "loss": 3.5754, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 4.703052190121156, | |
| "grad_norm": 0.3211807310581207, | |
| "learning_rate": 0.0005438846153846153, | |
| "loss": 3.573, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 4.717614165890028, | |
| "grad_norm": 0.3272148072719574, | |
| "learning_rate": 0.0005437097902097901, | |
| "loss": 3.5809, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 4.7321761416589005, | |
| "grad_norm": 0.33305129408836365, | |
| "learning_rate": 0.0005435349650349651, | |
| "loss": 3.5727, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 4.746738117427773, | |
| "grad_norm": 0.3019855320453644, | |
| "learning_rate": 0.0005433601398601397, | |
| "loss": 3.5914, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 4.761300093196645, | |
| "grad_norm": 0.313298761844635, | |
| "learning_rate": 0.0005431853146853147, | |
| "loss": 3.5713, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 4.775862068965517, | |
| "grad_norm": 0.31281420588493347, | |
| "learning_rate": 0.0005430104895104895, | |
| "loss": 3.5721, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 4.790424044734389, | |
| "grad_norm": 0.31018730998039246, | |
| "learning_rate": 0.0005428356643356643, | |
| "loss": 3.5829, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 4.804986020503262, | |
| "grad_norm": 0.3040141463279724, | |
| "learning_rate": 0.0005426608391608391, | |
| "loss": 3.5814, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 4.819547996272134, | |
| "grad_norm": 0.3142719268798828, | |
| "learning_rate": 0.000542486013986014, | |
| "loss": 3.5669, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 4.834109972041007, | |
| "grad_norm": 0.31050989031791687, | |
| "learning_rate": 0.0005423111888111888, | |
| "loss": 3.5895, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 4.848671947809879, | |
| "grad_norm": 0.31738415360450745, | |
| "learning_rate": 0.0005421363636363636, | |
| "loss": 3.5803, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 4.863233923578751, | |
| "grad_norm": 0.33238860964775085, | |
| "learning_rate": 0.0005419615384615385, | |
| "loss": 3.5689, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 4.877795899347624, | |
| "grad_norm": 0.3258155584335327, | |
| "learning_rate": 0.0005417867132867133, | |
| "loss": 3.5834, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 4.892357875116495, | |
| "grad_norm": 0.34824496507644653, | |
| "learning_rate": 0.0005416118881118881, | |
| "loss": 3.5846, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 4.906919850885368, | |
| "grad_norm": 0.3015121519565582, | |
| "learning_rate": 0.0005414370629370629, | |
| "loss": 3.5757, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 4.92148182665424, | |
| "grad_norm": 0.3203749358654022, | |
| "learning_rate": 0.0005412622377622378, | |
| "loss": 3.5841, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 4.936043802423113, | |
| "grad_norm": 0.2977421283721924, | |
| "learning_rate": 0.0005410874125874126, | |
| "loss": 3.5783, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 4.950605778191985, | |
| "grad_norm": 0.318941205739975, | |
| "learning_rate": 0.0005409125874125874, | |
| "loss": 3.5748, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.950605778191985, | |
| "eval_accuracy": 0.359580693147769, | |
| "eval_loss": 3.63466477394104, | |
| "eval_runtime": 53.7564, | |
| "eval_samples_per_second": 309.619, | |
| "eval_steps_per_second": 19.365, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.965167753960857, | |
| "grad_norm": 0.31237950921058655, | |
| "learning_rate": 0.0005407377622377622, | |
| "loss": 3.5748, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 4.97972972972973, | |
| "grad_norm": 0.3048698306083679, | |
| "learning_rate": 0.000540562937062937, | |
| "loss": 3.5694, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 4.994291705498602, | |
| "grad_norm": 0.31058716773986816, | |
| "learning_rate": 0.0005403881118881118, | |
| "loss": 3.5876, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 5.008737185461324, | |
| "grad_norm": 0.3176633417606354, | |
| "learning_rate": 0.0005402132867132867, | |
| "loss": 3.519, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 5.023299161230196, | |
| "grad_norm": 0.32644349336624146, | |
| "learning_rate": 0.0005400384615384615, | |
| "loss": 3.464, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 5.0378611369990685, | |
| "grad_norm": 0.31298401951789856, | |
| "learning_rate": 0.0005398636363636363, | |
| "loss": 3.4716, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 5.05242311276794, | |
| "grad_norm": 0.33144500851631165, | |
| "learning_rate": 0.0005396888111888111, | |
| "loss": 3.4736, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 5.066985088536812, | |
| "grad_norm": 0.3371279537677765, | |
| "learning_rate": 0.000539513986013986, | |
| "loss": 3.4803, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 5.081547064305685, | |
| "grad_norm": 0.30339860916137695, | |
| "learning_rate": 0.0005393391608391608, | |
| "loss": 3.4797, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 5.096109040074557, | |
| "grad_norm": 0.3512382209300995, | |
| "learning_rate": 0.0005391643356643356, | |
| "loss": 3.4856, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 5.11067101584343, | |
| "grad_norm": 0.32866692543029785, | |
| "learning_rate": 0.0005389895104895105, | |
| "loss": 3.4985, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 5.125232991612302, | |
| "grad_norm": 0.3049773871898651, | |
| "learning_rate": 0.0005388146853146853, | |
| "loss": 3.4957, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 5.1397949673811745, | |
| "grad_norm": 0.3084123730659485, | |
| "learning_rate": 0.0005386398601398601, | |
| "loss": 3.4944, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 5.154356943150047, | |
| "grad_norm": 0.3339555263519287, | |
| "learning_rate": 0.0005384650349650349, | |
| "loss": 3.5047, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 5.168918918918919, | |
| "grad_norm": 0.32437944412231445, | |
| "learning_rate": 0.0005382902097902098, | |
| "loss": 3.4957, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 5.183480894687791, | |
| "grad_norm": 0.32889071106910706, | |
| "learning_rate": 0.0005381153846153845, | |
| "loss": 3.5004, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 5.198042870456663, | |
| "grad_norm": 0.3491978943347931, | |
| "learning_rate": 0.0005379405594405594, | |
| "loss": 3.4958, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 5.212604846225536, | |
| "grad_norm": 0.3071553409099579, | |
| "learning_rate": 0.0005377657342657342, | |
| "loss": 3.4968, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 5.227166821994408, | |
| "grad_norm": 0.3152475953102112, | |
| "learning_rate": 0.000537590909090909, | |
| "loss": 3.4914, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 5.2417287977632805, | |
| "grad_norm": 0.3133900761604309, | |
| "learning_rate": 0.0005374160839160838, | |
| "loss": 3.5007, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 5.2417287977632805, | |
| "eval_accuracy": 0.3599717533653989, | |
| "eval_loss": 3.636350393295288, | |
| "eval_runtime": 53.8447, | |
| "eval_samples_per_second": 309.111, | |
| "eval_steps_per_second": 19.333, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 5.256290773532153, | |
| "grad_norm": 0.3083953261375427, | |
| "learning_rate": 0.0005372412587412587, | |
| "loss": 3.5021, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 5.270852749301025, | |
| "grad_norm": 0.34414270520210266, | |
| "learning_rate": 0.0005370664335664335, | |
| "loss": 3.516, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 5.285414725069898, | |
| "grad_norm": 0.3216901123523712, | |
| "learning_rate": 0.0005368916083916083, | |
| "loss": 3.5161, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 5.29997670083877, | |
| "grad_norm": 0.3427264392375946, | |
| "learning_rate": 0.0005367167832167832, | |
| "loss": 3.5075, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 5.314538676607642, | |
| "grad_norm": 0.3271310031414032, | |
| "learning_rate": 0.000536541958041958, | |
| "loss": 3.506, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 5.329100652376514, | |
| "grad_norm": 0.32501789927482605, | |
| "learning_rate": 0.0005363671328671328, | |
| "loss": 3.5099, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 5.3436626281453865, | |
| "grad_norm": 0.3126375079154968, | |
| "learning_rate": 0.0005361923076923076, | |
| "loss": 3.516, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 5.358224603914259, | |
| "grad_norm": 0.3329120874404907, | |
| "learning_rate": 0.0005360174825174825, | |
| "loss": 3.5009, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 5.372786579683131, | |
| "grad_norm": 0.34138381481170654, | |
| "learning_rate": 0.0005358426573426573, | |
| "loss": 3.5186, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 5.387348555452004, | |
| "grad_norm": 0.3538558781147003, | |
| "learning_rate": 0.0005356678321678321, | |
| "loss": 3.5156, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 5.401910531220876, | |
| "grad_norm": 0.3556719422340393, | |
| "learning_rate": 0.0005354930069930069, | |
| "loss": 3.513, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 5.416472506989749, | |
| "grad_norm": 0.32848823070526123, | |
| "learning_rate": 0.0005353181818181817, | |
| "loss": 3.5206, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 5.431034482758621, | |
| "grad_norm": 0.31033194065093994, | |
| "learning_rate": 0.0005351433566433565, | |
| "loss": 3.5212, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 5.445596458527493, | |
| "grad_norm": 0.32916679978370667, | |
| "learning_rate": 0.0005349685314685314, | |
| "loss": 3.5122, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 5.460158434296365, | |
| "grad_norm": 0.3248915672302246, | |
| "learning_rate": 0.0005347937062937062, | |
| "loss": 3.5116, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 5.474720410065237, | |
| "grad_norm": 0.316643089056015, | |
| "learning_rate": 0.000534618881118881, | |
| "loss": 3.5131, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 5.48928238583411, | |
| "grad_norm": 0.3165883719921112, | |
| "learning_rate": 0.0005344440559440559, | |
| "loss": 3.5206, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 5.503844361602982, | |
| "grad_norm": 0.31263893842697144, | |
| "learning_rate": 0.0005342692307692307, | |
| "loss": 3.515, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 5.518406337371855, | |
| "grad_norm": 0.31926199793815613, | |
| "learning_rate": 0.0005340944055944055, | |
| "loss": 3.5238, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 5.532968313140727, | |
| "grad_norm": 0.33692145347595215, | |
| "learning_rate": 0.0005339195804195803, | |
| "loss": 3.5337, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 5.532968313140727, | |
| "eval_accuracy": 0.36116574510022476, | |
| "eval_loss": 3.6262943744659424, | |
| "eval_runtime": 53.8294, | |
| "eval_samples_per_second": 309.199, | |
| "eval_steps_per_second": 19.339, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 5.547530288909599, | |
| "grad_norm": 0.3566485345363617, | |
| "learning_rate": 0.0005337447552447552, | |
| "loss": 3.5197, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 5.562092264678472, | |
| "grad_norm": 0.3133227825164795, | |
| "learning_rate": 0.00053356993006993, | |
| "loss": 3.523, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 5.576654240447344, | |
| "grad_norm": 0.31186652183532715, | |
| "learning_rate": 0.0005333951048951048, | |
| "loss": 3.5221, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 5.591216216216216, | |
| "grad_norm": 0.3436189591884613, | |
| "learning_rate": 0.0005332202797202796, | |
| "loss": 3.5373, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 5.605778191985088, | |
| "grad_norm": 0.3185917139053345, | |
| "learning_rate": 0.0005330454545454546, | |
| "loss": 3.5197, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 5.620340167753961, | |
| "grad_norm": 0.3546905517578125, | |
| "learning_rate": 0.0005328706293706292, | |
| "loss": 3.5303, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 5.634902143522833, | |
| "grad_norm": 0.33124232292175293, | |
| "learning_rate": 0.0005326958041958042, | |
| "loss": 3.5286, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 5.649464119291705, | |
| "grad_norm": 0.30169352889060974, | |
| "learning_rate": 0.000532520979020979, | |
| "loss": 3.519, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 5.664026095060578, | |
| "grad_norm": 0.3323482871055603, | |
| "learning_rate": 0.0005323461538461538, | |
| "loss": 3.5369, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 5.67858807082945, | |
| "grad_norm": 0.31857866048812866, | |
| "learning_rate": 0.0005321713286713287, | |
| "loss": 3.535, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 5.693150046598323, | |
| "grad_norm": 0.3306872248649597, | |
| "learning_rate": 0.0005319965034965035, | |
| "loss": 3.5327, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 5.707712022367195, | |
| "grad_norm": 0.3332788050174713, | |
| "learning_rate": 0.0005318216783216783, | |
| "loss": 3.5268, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 5.7222739981360675, | |
| "grad_norm": 0.3307408392429352, | |
| "learning_rate": 0.0005316468531468531, | |
| "loss": 3.5251, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 5.736835973904939, | |
| "grad_norm": 0.3280176818370819, | |
| "learning_rate": 0.000531472027972028, | |
| "loss": 3.5273, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 5.7513979496738115, | |
| "grad_norm": 0.33305320143699646, | |
| "learning_rate": 0.0005312972027972028, | |
| "loss": 3.522, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 5.765959925442684, | |
| "grad_norm": 0.29962897300720215, | |
| "learning_rate": 0.0005311223776223776, | |
| "loss": 3.5329, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 5.780521901211556, | |
| "grad_norm": 0.3109263479709625, | |
| "learning_rate": 0.0005309475524475524, | |
| "loss": 3.5426, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 5.795083876980429, | |
| "grad_norm": 0.3340068757534027, | |
| "learning_rate": 0.0005307727272727273, | |
| "loss": 3.5345, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 5.809645852749301, | |
| "grad_norm": 0.32446378469467163, | |
| "learning_rate": 0.0005305979020979021, | |
| "loss": 3.5408, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 5.8242078285181735, | |
| "grad_norm": 0.32898879051208496, | |
| "learning_rate": 0.0005304230769230769, | |
| "loss": 3.5421, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 5.8242078285181735, | |
| "eval_accuracy": 0.3620535670194439, | |
| "eval_loss": 3.6150898933410645, | |
| "eval_runtime": 53.8523, | |
| "eval_samples_per_second": 309.067, | |
| "eval_steps_per_second": 19.331, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 5.838769804287046, | |
| "grad_norm": 0.3129737377166748, | |
| "learning_rate": 0.0005302482517482517, | |
| "loss": 3.5318, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 5.853331780055918, | |
| "grad_norm": 0.3082195222377777, | |
| "learning_rate": 0.0005300734265734265, | |
| "loss": 3.5251, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 5.86789375582479, | |
| "grad_norm": 0.30648788809776306, | |
| "learning_rate": 0.0005298986013986013, | |
| "loss": 3.5338, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 5.882455731593662, | |
| "grad_norm": 0.3134007453918457, | |
| "learning_rate": 0.0005297237762237762, | |
| "loss": 3.5169, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 5.897017707362535, | |
| "grad_norm": 0.3222978115081787, | |
| "learning_rate": 0.000529548951048951, | |
| "loss": 3.5412, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 5.911579683131407, | |
| "grad_norm": 0.3065994381904602, | |
| "learning_rate": 0.0005293741258741258, | |
| "loss": 3.5197, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 5.9261416589002796, | |
| "grad_norm": 0.3118910789489746, | |
| "learning_rate": 0.0005291993006993007, | |
| "loss": 3.519, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 5.940703634669152, | |
| "grad_norm": 0.3327983021736145, | |
| "learning_rate": 0.0005290244755244755, | |
| "loss": 3.5199, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 5.955265610438024, | |
| "grad_norm": 0.33203497529029846, | |
| "learning_rate": 0.0005288496503496503, | |
| "loss": 3.5236, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 5.969827586206897, | |
| "grad_norm": 0.3465798497200012, | |
| "learning_rate": 0.0005286748251748251, | |
| "loss": 3.524, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 5.984389561975769, | |
| "grad_norm": 0.31439685821533203, | |
| "learning_rate": 0.0005285, | |
| "loss": 3.5324, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 5.998951537744642, | |
| "grad_norm": 0.32758834958076477, | |
| "learning_rate": 0.0005283251748251748, | |
| "loss": 3.5191, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 6.013397017707362, | |
| "grad_norm": 0.3180631995201111, | |
| "learning_rate": 0.0005281503496503496, | |
| "loss": 3.4261, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 6.0279589934762345, | |
| "grad_norm": 0.3253958225250244, | |
| "learning_rate": 0.0005279755244755244, | |
| "loss": 3.4226, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 6.042520969245107, | |
| "grad_norm": 0.31996259093284607, | |
| "learning_rate": 0.0005278006993006993, | |
| "loss": 3.4179, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 6.057082945013979, | |
| "grad_norm": 0.349447101354599, | |
| "learning_rate": 0.000527625874125874, | |
| "loss": 3.4317, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 6.071644920782852, | |
| "grad_norm": 0.3400956392288208, | |
| "learning_rate": 0.0005274510489510489, | |
| "loss": 3.4253, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 6.086206896551724, | |
| "grad_norm": 0.31208309531211853, | |
| "learning_rate": 0.0005272762237762238, | |
| "loss": 3.4351, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 6.100768872320597, | |
| "grad_norm": 0.3292507231235504, | |
| "learning_rate": 0.0005271013986013985, | |
| "loss": 3.4399, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 6.115330848089469, | |
| "grad_norm": 0.338582307100296, | |
| "learning_rate": 0.0005269265734265734, | |
| "loss": 3.4317, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 6.115330848089469, | |
| "eval_accuracy": 0.362383840065542, | |
| "eval_loss": 3.6184234619140625, | |
| "eval_runtime": 53.6626, | |
| "eval_samples_per_second": 310.16, | |
| "eval_steps_per_second": 19.399, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 6.129892823858341, | |
| "grad_norm": 0.3549116849899292, | |
| "learning_rate": 0.0005267517482517482, | |
| "loss": 3.448, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 6.144454799627214, | |
| "grad_norm": 0.3466671407222748, | |
| "learning_rate": 0.000526576923076923, | |
| "loss": 3.4531, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 6.159016775396085, | |
| "grad_norm": 0.33880236744880676, | |
| "learning_rate": 0.0005264020979020978, | |
| "loss": 3.4532, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 6.173578751164958, | |
| "grad_norm": 0.3429170846939087, | |
| "learning_rate": 0.0005262272727272727, | |
| "loss": 3.4504, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 6.18814072693383, | |
| "grad_norm": 0.3074339032173157, | |
| "learning_rate": 0.0005260524475524475, | |
| "loss": 3.4359, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 6.202702702702703, | |
| "grad_norm": 0.3143917918205261, | |
| "learning_rate": 0.0005258776223776223, | |
| "loss": 3.4509, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 6.217264678471575, | |
| "grad_norm": 0.3545181155204773, | |
| "learning_rate": 0.0005257027972027971, | |
| "loss": 3.4566, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 6.2318266542404475, | |
| "grad_norm": 0.322401762008667, | |
| "learning_rate": 0.000525527972027972, | |
| "loss": 3.4592, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 6.24638863000932, | |
| "grad_norm": 0.33117911219596863, | |
| "learning_rate": 0.0005253531468531468, | |
| "loss": 3.4598, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 6.260950605778192, | |
| "grad_norm": 0.34444600343704224, | |
| "learning_rate": 0.0005251783216783216, | |
| "loss": 3.4582, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 6.275512581547065, | |
| "grad_norm": 0.3065207302570343, | |
| "learning_rate": 0.0005250034965034965, | |
| "loss": 3.47, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 6.290074557315936, | |
| "grad_norm": 0.34848421812057495, | |
| "learning_rate": 0.0005248286713286712, | |
| "loss": 3.4732, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 6.304636533084809, | |
| "grad_norm": 0.3056810796260834, | |
| "learning_rate": 0.0005246538461538461, | |
| "loss": 3.4529, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 6.319198508853681, | |
| "grad_norm": 0.33891788125038147, | |
| "learning_rate": 0.0005244790209790209, | |
| "loss": 3.4678, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 6.3337604846225535, | |
| "grad_norm": 0.3220604956150055, | |
| "learning_rate": 0.0005243041958041957, | |
| "loss": 3.4709, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 6.348322460391426, | |
| "grad_norm": 0.30562639236450195, | |
| "learning_rate": 0.0005241293706293705, | |
| "loss": 3.4767, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 6.362884436160298, | |
| "grad_norm": 0.32998815178871155, | |
| "learning_rate": 0.0005239545454545454, | |
| "loss": 3.4829, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 6.377446411929171, | |
| "grad_norm": 0.34016919136047363, | |
| "learning_rate": 0.0005237797202797202, | |
| "loss": 3.4699, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 6.392008387698043, | |
| "grad_norm": 0.3256104290485382, | |
| "learning_rate": 0.000523604895104895, | |
| "loss": 3.4741, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 6.4065703634669156, | |
| "grad_norm": 0.33402830362319946, | |
| "learning_rate": 0.0005234300699300698, | |
| "loss": 3.4691, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 6.4065703634669156, | |
| "eval_accuracy": 0.3631490294510907, | |
| "eval_loss": 3.6099016666412354, | |
| "eval_runtime": 53.7802, | |
| "eval_samples_per_second": 309.482, | |
| "eval_steps_per_second": 19.357, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 6.421132339235788, | |
| "grad_norm": 0.32157817482948303, | |
| "learning_rate": 0.0005232552447552447, | |
| "loss": 3.4586, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 6.4356943150046595, | |
| "grad_norm": 0.307766854763031, | |
| "learning_rate": 0.0005230804195804195, | |
| "loss": 3.4756, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 6.450256290773532, | |
| "grad_norm": 0.33260318636894226, | |
| "learning_rate": 0.0005229055944055943, | |
| "loss": 3.4764, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 6.464818266542404, | |
| "grad_norm": 0.3042699098587036, | |
| "learning_rate": 0.0005227307692307691, | |
| "loss": 3.4875, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 6.479380242311277, | |
| "grad_norm": 0.31879618763923645, | |
| "learning_rate": 0.0005225559440559441, | |
| "loss": 3.4849, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 6.493942218080149, | |
| "grad_norm": 0.33056700229644775, | |
| "learning_rate": 0.0005223811188811189, | |
| "loss": 3.4723, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 6.508504193849022, | |
| "grad_norm": 0.3173615336418152, | |
| "learning_rate": 0.0005222062937062937, | |
| "loss": 3.4772, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 6.523066169617894, | |
| "grad_norm": 0.33287325501441956, | |
| "learning_rate": 0.0005220314685314686, | |
| "loss": 3.4774, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 6.537628145386766, | |
| "grad_norm": 0.32694077491760254, | |
| "learning_rate": 0.0005218566433566433, | |
| "loss": 3.4902, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 6.552190121155638, | |
| "grad_norm": 0.35262542963027954, | |
| "learning_rate": 0.0005216818181818182, | |
| "loss": 3.4779, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 6.56675209692451, | |
| "grad_norm": 0.3070398271083832, | |
| "learning_rate": 0.000521506993006993, | |
| "loss": 3.4911, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 6.581314072693383, | |
| "grad_norm": 0.33605894446372986, | |
| "learning_rate": 0.0005213321678321678, | |
| "loss": 3.4823, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 6.595876048462255, | |
| "grad_norm": 0.3233272135257721, | |
| "learning_rate": 0.0005211573426573426, | |
| "loss": 3.4815, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 6.610438024231128, | |
| "grad_norm": 0.3428344428539276, | |
| "learning_rate": 0.0005209825174825175, | |
| "loss": 3.4917, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 6.625, | |
| "grad_norm": 0.3113822340965271, | |
| "learning_rate": 0.0005208076923076923, | |
| "loss": 3.484, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 6.639561975768872, | |
| "grad_norm": 0.31913211941719055, | |
| "learning_rate": 0.0005206328671328671, | |
| "loss": 3.4862, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 6.654123951537745, | |
| "grad_norm": 0.3375007212162018, | |
| "learning_rate": 0.0005204580419580419, | |
| "loss": 3.4915, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 6.668685927306617, | |
| "grad_norm": 0.3295234143733978, | |
| "learning_rate": 0.0005202832167832168, | |
| "loss": 3.4898, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 6.68324790307549, | |
| "grad_norm": 0.32532602548599243, | |
| "learning_rate": 0.0005201083916083916, | |
| "loss": 3.4951, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 6.697809878844362, | |
| "grad_norm": 0.3587338328361511, | |
| "learning_rate": 0.0005199335664335664, | |
| "loss": 3.4836, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 6.697809878844362, | |
| "eval_accuracy": 0.3637184535743562, | |
| "eval_loss": 3.599292755126953, | |
| "eval_runtime": 53.6472, | |
| "eval_samples_per_second": 310.249, | |
| "eval_steps_per_second": 19.405, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 6.712371854613234, | |
| "grad_norm": 0.32595306634902954, | |
| "learning_rate": 0.0005197587412587413, | |
| "loss": 3.4882, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 6.726933830382106, | |
| "grad_norm": 0.337817907333374, | |
| "learning_rate": 0.0005195839160839161, | |
| "loss": 3.4846, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 6.741495806150978, | |
| "grad_norm": 0.3214098811149597, | |
| "learning_rate": 0.0005194090909090909, | |
| "loss": 3.4951, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 6.756057781919851, | |
| "grad_norm": 0.31647759675979614, | |
| "learning_rate": 0.0005192342657342657, | |
| "loss": 3.4814, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 6.770619757688723, | |
| "grad_norm": 0.31576162576675415, | |
| "learning_rate": 0.0005190594405594405, | |
| "loss": 3.4945, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 6.785181733457596, | |
| "grad_norm": 0.32426100969314575, | |
| "learning_rate": 0.0005188846153846153, | |
| "loss": 3.4875, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 6.799743709226468, | |
| "grad_norm": 0.32514530420303345, | |
| "learning_rate": 0.0005187097902097902, | |
| "loss": 3.491, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 6.8143056849953405, | |
| "grad_norm": 0.3201660215854645, | |
| "learning_rate": 0.000518534965034965, | |
| "loss": 3.4882, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 6.828867660764212, | |
| "grad_norm": 0.32947874069213867, | |
| "learning_rate": 0.0005183601398601398, | |
| "loss": 3.4996, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 6.8434296365330844, | |
| "grad_norm": 0.34106481075286865, | |
| "learning_rate": 0.0005181853146853146, | |
| "loss": 3.4961, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 6.857991612301957, | |
| "grad_norm": 0.36824700236320496, | |
| "learning_rate": 0.0005180104895104895, | |
| "loss": 3.4847, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 6.872553588070829, | |
| "grad_norm": 0.3059179186820984, | |
| "learning_rate": 0.0005178356643356643, | |
| "loss": 3.5004, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 6.887115563839702, | |
| "grad_norm": 0.31658226251602173, | |
| "learning_rate": 0.0005176608391608391, | |
| "loss": 3.4822, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 6.901677539608574, | |
| "grad_norm": 0.3481607437133789, | |
| "learning_rate": 0.000517486013986014, | |
| "loss": 3.4975, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 6.9162395153774465, | |
| "grad_norm": 0.340072900056839, | |
| "learning_rate": 0.0005173111888111888, | |
| "loss": 3.4979, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 6.930801491146319, | |
| "grad_norm": 0.3230604827404022, | |
| "learning_rate": 0.0005171363636363636, | |
| "loss": 3.4972, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 6.945363466915191, | |
| "grad_norm": 0.32332488894462585, | |
| "learning_rate": 0.0005169615384615384, | |
| "loss": 3.4911, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 6.959925442684064, | |
| "grad_norm": 0.3132401406764984, | |
| "learning_rate": 0.0005167867132867133, | |
| "loss": 3.4979, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 6.974487418452936, | |
| "grad_norm": 0.30957671999931335, | |
| "learning_rate": 0.000516611888111888, | |
| "loss": 3.4941, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 6.989049394221808, | |
| "grad_norm": 0.32135453820228577, | |
| "learning_rate": 0.0005164370629370629, | |
| "loss": 3.4874, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 6.989049394221808, | |
| "eval_accuracy": 0.36465554014516494, | |
| "eval_loss": 3.590451240539551, | |
| "eval_runtime": 53.7639, | |
| "eval_samples_per_second": 309.576, | |
| "eval_steps_per_second": 19.362, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 7.003494874184529, | |
| "grad_norm": 0.3334214985370636, | |
| "learning_rate": 0.0005162622377622377, | |
| "loss": 3.4636, | |
| "step": 24050 | |
| }, | |
| { | |
| "epoch": 7.0180568499534015, | |
| "grad_norm": 0.3495422899723053, | |
| "learning_rate": 0.0005160874125874125, | |
| "loss": 3.3781, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 7.032618825722274, | |
| "grad_norm": 0.3541470468044281, | |
| "learning_rate": 0.0005159125874125873, | |
| "loss": 3.38, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 7.047180801491146, | |
| "grad_norm": 0.333109974861145, | |
| "learning_rate": 0.0005157377622377622, | |
| "loss": 3.3921, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 7.061742777260019, | |
| "grad_norm": 0.31906047463417053, | |
| "learning_rate": 0.000515562937062937, | |
| "loss": 3.405, | |
| "step": 24250 | |
| }, | |
| { | |
| "epoch": 7.076304753028891, | |
| "grad_norm": 0.3586280345916748, | |
| "learning_rate": 0.0005153881118881118, | |
| "loss": 3.3985, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 7.090866728797764, | |
| "grad_norm": 0.3500705659389496, | |
| "learning_rate": 0.0005152132867132867, | |
| "loss": 3.4048, | |
| "step": 24350 | |
| }, | |
| { | |
| "epoch": 7.105428704566636, | |
| "grad_norm": 0.33212336897850037, | |
| "learning_rate": 0.0005150384615384615, | |
| "loss": 3.4119, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 7.1199906803355075, | |
| "grad_norm": 0.3508271276950836, | |
| "learning_rate": 0.0005148636363636363, | |
| "loss": 3.4001, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 7.13455265610438, | |
| "grad_norm": 0.3221181035041809, | |
| "learning_rate": 0.0005146888111888111, | |
| "loss": 3.393, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 7.149114631873252, | |
| "grad_norm": 0.3389952480792999, | |
| "learning_rate": 0.000514513986013986, | |
| "loss": 3.4187, | |
| "step": 24550 | |
| }, | |
| { | |
| "epoch": 7.163676607642125, | |
| "grad_norm": 0.34659498929977417, | |
| "learning_rate": 0.0005143391608391608, | |
| "loss": 3.4227, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 7.178238583410997, | |
| "grad_norm": 0.3916986286640167, | |
| "learning_rate": 0.0005141643356643356, | |
| "loss": 3.414, | |
| "step": 24650 | |
| }, | |
| { | |
| "epoch": 7.19280055917987, | |
| "grad_norm": 0.31232357025146484, | |
| "learning_rate": 0.0005139895104895104, | |
| "loss": 3.4161, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 7.207362534948742, | |
| "grad_norm": 0.315341979265213, | |
| "learning_rate": 0.0005138146853146852, | |
| "loss": 3.4145, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 7.221924510717614, | |
| "grad_norm": 0.32361841201782227, | |
| "learning_rate": 0.00051363986013986, | |
| "loss": 3.4221, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 7.236486486486487, | |
| "grad_norm": 0.3259839415550232, | |
| "learning_rate": 0.0005134650349650349, | |
| "loss": 3.4284, | |
| "step": 24850 | |
| }, | |
| { | |
| "epoch": 7.251048462255358, | |
| "grad_norm": 0.34261107444763184, | |
| "learning_rate": 0.0005132902097902097, | |
| "loss": 3.4087, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 7.265610438024231, | |
| "grad_norm": 0.3521381914615631, | |
| "learning_rate": 0.0005131153846153845, | |
| "loss": 3.4345, | |
| "step": 24950 | |
| }, | |
| { | |
| "epoch": 7.280172413793103, | |
| "grad_norm": 0.32308435440063477, | |
| "learning_rate": 0.0005129405594405594, | |
| "loss": 3.4321, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 7.280172413793103, | |
| "eval_accuracy": 0.3645800558818702, | |
| "eval_loss": 3.598625898361206, | |
| "eval_runtime": 53.8267, | |
| "eval_samples_per_second": 309.215, | |
| "eval_steps_per_second": 19.34, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 7.294734389561976, | |
| "grad_norm": 0.3033270239830017, | |
| "learning_rate": 0.0005127657342657342, | |
| "loss": 3.4391, | |
| "step": 25050 | |
| }, | |
| { | |
| "epoch": 7.309296365330848, | |
| "grad_norm": 0.332119882106781, | |
| "learning_rate": 0.000512590909090909, | |
| "loss": 3.4345, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 7.3238583410997204, | |
| "grad_norm": 0.3105907738208771, | |
| "learning_rate": 0.0005124160839160838, | |
| "loss": 3.4386, | |
| "step": 25150 | |
| }, | |
| { | |
| "epoch": 7.338420316868593, | |
| "grad_norm": 0.33971258997917175, | |
| "learning_rate": 0.0005122412587412588, | |
| "loss": 3.424, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 7.352982292637465, | |
| "grad_norm": 0.34061726927757263, | |
| "learning_rate": 0.0005120664335664336, | |
| "loss": 3.4281, | |
| "step": 25250 | |
| }, | |
| { | |
| "epoch": 7.367544268406338, | |
| "grad_norm": 0.3410240709781647, | |
| "learning_rate": 0.0005118916083916084, | |
| "loss": 3.4452, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 7.38210624417521, | |
| "grad_norm": 0.3339107036590576, | |
| "learning_rate": 0.0005117167832167832, | |
| "loss": 3.4366, | |
| "step": 25350 | |
| }, | |
| { | |
| "epoch": 7.396668219944082, | |
| "grad_norm": 0.34466513991355896, | |
| "learning_rate": 0.0005115419580419581, | |
| "loss": 3.4326, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 7.411230195712954, | |
| "grad_norm": 0.32572296261787415, | |
| "learning_rate": 0.0005113671328671328, | |
| "loss": 3.4348, | |
| "step": 25450 | |
| }, | |
| { | |
| "epoch": 7.4257921714818265, | |
| "grad_norm": 0.33211272954940796, | |
| "learning_rate": 0.0005111923076923077, | |
| "loss": 3.4413, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 7.440354147250699, | |
| "grad_norm": 0.331061452627182, | |
| "learning_rate": 0.0005110174825174825, | |
| "loss": 3.4274, | |
| "step": 25550 | |
| }, | |
| { | |
| "epoch": 7.454916123019571, | |
| "grad_norm": 0.3294326961040497, | |
| "learning_rate": 0.0005108426573426573, | |
| "loss": 3.4472, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 7.469478098788444, | |
| "grad_norm": 0.32842373847961426, | |
| "learning_rate": 0.0005106678321678321, | |
| "loss": 3.4361, | |
| "step": 25650 | |
| }, | |
| { | |
| "epoch": 7.484040074557316, | |
| "grad_norm": 0.32948267459869385, | |
| "learning_rate": 0.000510493006993007, | |
| "loss": 3.4361, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 7.4986020503261885, | |
| "grad_norm": 0.3331805467605591, | |
| "learning_rate": 0.0005103181818181818, | |
| "loss": 3.4412, | |
| "step": 25750 | |
| }, | |
| { | |
| "epoch": 7.513164026095061, | |
| "grad_norm": 0.3543056845664978, | |
| "learning_rate": 0.0005101433566433566, | |
| "loss": 3.4501, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 7.5277260018639325, | |
| "grad_norm": 0.31350502371788025, | |
| "learning_rate": 0.0005099685314685315, | |
| "loss": 3.4454, | |
| "step": 25850 | |
| }, | |
| { | |
| "epoch": 7.542287977632805, | |
| "grad_norm": 0.3373096287250519, | |
| "learning_rate": 0.0005097937062937063, | |
| "loss": 3.453, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 7.556849953401677, | |
| "grad_norm": 0.33655133843421936, | |
| "learning_rate": 0.0005096188811188811, | |
| "loss": 3.4609, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 7.57141192917055, | |
| "grad_norm": 0.31745684146881104, | |
| "learning_rate": 0.0005094440559440559, | |
| "loss": 3.4369, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 7.57141192917055, | |
| "eval_accuracy": 0.3652601197119276, | |
| "eval_loss": 3.591218948364258, | |
| "eval_runtime": 53.6938, | |
| "eval_samples_per_second": 309.98, | |
| "eval_steps_per_second": 19.388, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 7.585973904939422, | |
| "grad_norm": 0.35504648089408875, | |
| "learning_rate": 0.0005092692307692308, | |
| "loss": 3.4682, | |
| "step": 26050 | |
| }, | |
| { | |
| "epoch": 7.600535880708295, | |
| "grad_norm": 0.33637967705726624, | |
| "learning_rate": 0.0005090944055944056, | |
| "loss": 3.4509, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 7.615097856477167, | |
| "grad_norm": 0.33597350120544434, | |
| "learning_rate": 0.0005089195804195804, | |
| "loss": 3.4583, | |
| "step": 26150 | |
| }, | |
| { | |
| "epoch": 7.629659832246039, | |
| "grad_norm": 0.3214302361011505, | |
| "learning_rate": 0.0005087447552447552, | |
| "loss": 3.4457, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 7.644221808014912, | |
| "grad_norm": 0.365751177072525, | |
| "learning_rate": 0.00050856993006993, | |
| "loss": 3.4516, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 7.658783783783784, | |
| "grad_norm": 0.34353286027908325, | |
| "learning_rate": 0.0005083951048951048, | |
| "loss": 3.4569, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 7.673345759552656, | |
| "grad_norm": 0.3380644917488098, | |
| "learning_rate": 0.0005082202797202797, | |
| "loss": 3.4491, | |
| "step": 26350 | |
| }, | |
| { | |
| "epoch": 7.687907735321528, | |
| "grad_norm": 0.33947882056236267, | |
| "learning_rate": 0.0005080454545454545, | |
| "loss": 3.4516, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 7.702469711090401, | |
| "grad_norm": 0.31728804111480713, | |
| "learning_rate": 0.0005078706293706293, | |
| "loss": 3.454, | |
| "step": 26450 | |
| }, | |
| { | |
| "epoch": 7.717031686859273, | |
| "grad_norm": 0.3451788127422333, | |
| "learning_rate": 0.0005076958041958042, | |
| "loss": 3.457, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 7.731593662628145, | |
| "grad_norm": 0.38292965292930603, | |
| "learning_rate": 0.000507520979020979, | |
| "loss": 3.4644, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 7.746155638397018, | |
| "grad_norm": 0.3145500421524048, | |
| "learning_rate": 0.0005073461538461538, | |
| "loss": 3.4548, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 7.76071761416589, | |
| "grad_norm": 0.34711846709251404, | |
| "learning_rate": 0.0005071713286713286, | |
| "loss": 3.4643, | |
| "step": 26650 | |
| }, | |
| { | |
| "epoch": 7.775279589934763, | |
| "grad_norm": 0.3363344371318817, | |
| "learning_rate": 0.0005069965034965035, | |
| "loss": 3.4566, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 7.789841565703634, | |
| "grad_norm": 0.31343647837638855, | |
| "learning_rate": 0.0005068216783216783, | |
| "loss": 3.4551, | |
| "step": 26750 | |
| }, | |
| { | |
| "epoch": 7.804403541472507, | |
| "grad_norm": 0.31084564328193665, | |
| "learning_rate": 0.0005066468531468531, | |
| "loss": 3.4569, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 7.818965517241379, | |
| "grad_norm": 0.3759641647338867, | |
| "learning_rate": 0.0005064720279720279, | |
| "loss": 3.4614, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 7.833527493010251, | |
| "grad_norm": 0.3450261652469635, | |
| "learning_rate": 0.0005062972027972028, | |
| "loss": 3.4614, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 7.848089468779124, | |
| "grad_norm": 0.32384663820266724, | |
| "learning_rate": 0.0005061223776223775, | |
| "loss": 3.4693, | |
| "step": 26950 | |
| }, | |
| { | |
| "epoch": 7.862651444547996, | |
| "grad_norm": 0.3452761471271515, | |
| "learning_rate": 0.0005059475524475524, | |
| "loss": 3.4537, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 7.862651444547996, | |
| "eval_accuracy": 0.3661786291587479, | |
| "eval_loss": 3.5794222354888916, | |
| "eval_runtime": 53.6328, | |
| "eval_samples_per_second": 310.333, | |
| "eval_steps_per_second": 19.41, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 7.877213420316869, | |
| "grad_norm": 0.315171480178833, | |
| "learning_rate": 0.0005057727272727272, | |
| "loss": 3.4653, | |
| "step": 27050 | |
| }, | |
| { | |
| "epoch": 7.891775396085741, | |
| "grad_norm": 0.31368204951286316, | |
| "learning_rate": 0.000505597902097902, | |
| "loss": 3.4675, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 7.9063373718546135, | |
| "grad_norm": 0.3297800123691559, | |
| "learning_rate": 0.0005054230769230769, | |
| "loss": 3.4458, | |
| "step": 27150 | |
| }, | |
| { | |
| "epoch": 7.920899347623486, | |
| "grad_norm": 0.3278055489063263, | |
| "learning_rate": 0.0005052482517482517, | |
| "loss": 3.4738, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 7.935461323392358, | |
| "grad_norm": 0.3137778639793396, | |
| "learning_rate": 0.0005050734265734265, | |
| "loss": 3.4677, | |
| "step": 27250 | |
| }, | |
| { | |
| "epoch": 7.95002329916123, | |
| "grad_norm": 0.3212771713733673, | |
| "learning_rate": 0.0005048986013986013, | |
| "loss": 3.4704, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 7.964585274930102, | |
| "grad_norm": 0.31689706444740295, | |
| "learning_rate": 0.0005047237762237762, | |
| "loss": 3.4477, | |
| "step": 27350 | |
| }, | |
| { | |
| "epoch": 7.979147250698975, | |
| "grad_norm": 0.3310457170009613, | |
| "learning_rate": 0.000504548951048951, | |
| "loss": 3.4605, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 7.993709226467847, | |
| "grad_norm": 0.33040231466293335, | |
| "learning_rate": 0.0005043741258741258, | |
| "loss": 3.4611, | |
| "step": 27450 | |
| }, | |
| { | |
| "epoch": 8.008154706430568, | |
| "grad_norm": 0.34095948934555054, | |
| "learning_rate": 0.0005041993006993006, | |
| "loss": 3.394, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 8.022716682199441, | |
| "grad_norm": 0.3549644649028778, | |
| "learning_rate": 0.0005040244755244755, | |
| "loss": 3.3429, | |
| "step": 27550 | |
| }, | |
| { | |
| "epoch": 8.037278657968313, | |
| "grad_norm": 0.33670076727867126, | |
| "learning_rate": 0.0005038496503496503, | |
| "loss": 3.3604, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 8.051840633737186, | |
| "grad_norm": 0.31921789050102234, | |
| "learning_rate": 0.0005036748251748251, | |
| "loss": 3.361, | |
| "step": 27650 | |
| }, | |
| { | |
| "epoch": 8.066402609506058, | |
| "grad_norm": 0.3673897385597229, | |
| "learning_rate": 0.0005034999999999999, | |
| "loss": 3.3655, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 8.08096458527493, | |
| "grad_norm": 0.3496399521827698, | |
| "learning_rate": 0.0005033251748251747, | |
| "loss": 3.3547, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 8.095526561043803, | |
| "grad_norm": 0.3243163228034973, | |
| "learning_rate": 0.0005031503496503496, | |
| "loss": 3.3708, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 8.110088536812675, | |
| "grad_norm": 0.3277808427810669, | |
| "learning_rate": 0.0005029755244755244, | |
| "loss": 3.3714, | |
| "step": 27850 | |
| }, | |
| { | |
| "epoch": 8.124650512581548, | |
| "grad_norm": 0.338352769613266, | |
| "learning_rate": 0.0005028006993006992, | |
| "loss": 3.3882, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 8.13921248835042, | |
| "grad_norm": 0.33708006143569946, | |
| "learning_rate": 0.000502625874125874, | |
| "loss": 3.3723, | |
| "step": 27950 | |
| }, | |
| { | |
| "epoch": 8.15377446411929, | |
| "grad_norm": 0.32670241594314575, | |
| "learning_rate": 0.000502451048951049, | |
| "loss": 3.3668, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 8.15377446411929, | |
| "eval_accuracy": 0.3660947969473317, | |
| "eval_loss": 3.591442108154297, | |
| "eval_runtime": 53.554, | |
| "eval_samples_per_second": 310.789, | |
| "eval_steps_per_second": 19.438, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 8.168336439888163, | |
| "grad_norm": 0.35390371084213257, | |
| "learning_rate": 0.0005022762237762237, | |
| "loss": 3.3826, | |
| "step": 28050 | |
| }, | |
| { | |
| "epoch": 8.182898415657036, | |
| "grad_norm": 0.31787583231925964, | |
| "learning_rate": 0.0005021013986013985, | |
| "loss": 3.386, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 8.197460391425908, | |
| "grad_norm": 0.36148154735565186, | |
| "learning_rate": 0.0005019265734265733, | |
| "loss": 3.3822, | |
| "step": 28150 | |
| }, | |
| { | |
| "epoch": 8.21202236719478, | |
| "grad_norm": 0.33843347430229187, | |
| "learning_rate": 0.0005017517482517483, | |
| "loss": 3.3855, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 8.226584342963653, | |
| "grad_norm": 0.3566340208053589, | |
| "learning_rate": 0.0005015769230769231, | |
| "loss": 3.3842, | |
| "step": 28250 | |
| }, | |
| { | |
| "epoch": 8.241146318732525, | |
| "grad_norm": 0.3228391110897064, | |
| "learning_rate": 0.0005014020979020979, | |
| "loss": 3.3911, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 8.255708294501398, | |
| "grad_norm": 0.38596999645233154, | |
| "learning_rate": 0.0005012272727272727, | |
| "loss": 3.3901, | |
| "step": 28350 | |
| }, | |
| { | |
| "epoch": 8.27027027027027, | |
| "grad_norm": 0.33675438165664673, | |
| "learning_rate": 0.0005010524475524476, | |
| "loss": 3.3946, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 8.284832246039143, | |
| "grad_norm": 0.33514130115509033, | |
| "learning_rate": 0.0005008776223776223, | |
| "loss": 3.3954, | |
| "step": 28450 | |
| }, | |
| { | |
| "epoch": 8.299394221808015, | |
| "grad_norm": 0.3307504951953888, | |
| "learning_rate": 0.0005007027972027972, | |
| "loss": 3.4104, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 8.313956197576887, | |
| "grad_norm": 0.3365596830844879, | |
| "learning_rate": 0.000500527972027972, | |
| "loss": 3.4066, | |
| "step": 28550 | |
| }, | |
| { | |
| "epoch": 8.32851817334576, | |
| "grad_norm": 0.34331199526786804, | |
| "learning_rate": 0.0005003531468531468, | |
| "loss": 3.3985, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 8.343080149114632, | |
| "grad_norm": 0.3220767080783844, | |
| "learning_rate": 0.0005001783216783217, | |
| "loss": 3.4101, | |
| "step": 28650 | |
| }, | |
| { | |
| "epoch": 8.357642124883505, | |
| "grad_norm": 0.34586459398269653, | |
| "learning_rate": 0.0005000034965034965, | |
| "loss": 3.4083, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 8.372204100652377, | |
| "grad_norm": 0.35441240668296814, | |
| "learning_rate": 0.0004998286713286713, | |
| "loss": 3.423, | |
| "step": 28750 | |
| }, | |
| { | |
| "epoch": 8.38676607642125, | |
| "grad_norm": 0.32183533906936646, | |
| "learning_rate": 0.0004996538461538461, | |
| "loss": 3.4064, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 8.401328052190122, | |
| "grad_norm": 0.3539142906665802, | |
| "learning_rate": 0.000499479020979021, | |
| "loss": 3.4067, | |
| "step": 28850 | |
| }, | |
| { | |
| "epoch": 8.415890027958994, | |
| "grad_norm": 0.3181823790073395, | |
| "learning_rate": 0.0004993041958041958, | |
| "loss": 3.4163, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 8.430452003727865, | |
| "grad_norm": 0.3841262459754944, | |
| "learning_rate": 0.0004991293706293706, | |
| "loss": 3.42, | |
| "step": 28950 | |
| }, | |
| { | |
| "epoch": 8.445013979496737, | |
| "grad_norm": 0.32062074542045593, | |
| "learning_rate": 0.0004989545454545454, | |
| "loss": 3.4093, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 8.445013979496737, | |
| "eval_accuracy": 0.36640719832984603, | |
| "eval_loss": 3.584610939025879, | |
| "eval_runtime": 53.8487, | |
| "eval_samples_per_second": 309.088, | |
| "eval_steps_per_second": 19.332, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 8.45957595526561, | |
| "grad_norm": 0.33427077531814575, | |
| "learning_rate": 0.0004987797202797203, | |
| "loss": 3.4135, | |
| "step": 29050 | |
| }, | |
| { | |
| "epoch": 8.474137931034482, | |
| "grad_norm": 0.3367469608783722, | |
| "learning_rate": 0.0004986048951048951, | |
| "loss": 3.428, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 8.488699906803355, | |
| "grad_norm": 0.33394715189933777, | |
| "learning_rate": 0.0004984300699300699, | |
| "loss": 3.4095, | |
| "step": 29150 | |
| }, | |
| { | |
| "epoch": 8.503261882572227, | |
| "grad_norm": 0.3207018971443176, | |
| "learning_rate": 0.0004982552447552448, | |
| "loss": 3.4179, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 8.5178238583411, | |
| "grad_norm": 0.34231436252593994, | |
| "learning_rate": 0.0004980804195804195, | |
| "loss": 3.4238, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 8.532385834109972, | |
| "grad_norm": 0.3377602994441986, | |
| "learning_rate": 0.0004979055944055944, | |
| "loss": 3.4226, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 8.546947809878844, | |
| "grad_norm": 0.3428233563899994, | |
| "learning_rate": 0.0004977307692307692, | |
| "loss": 3.426, | |
| "step": 29350 | |
| }, | |
| { | |
| "epoch": 8.561509785647717, | |
| "grad_norm": 0.3227432668209076, | |
| "learning_rate": 0.000497555944055944, | |
| "loss": 3.4268, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 8.57607176141659, | |
| "grad_norm": 0.3025504946708679, | |
| "learning_rate": 0.0004973811188811188, | |
| "loss": 3.4094, | |
| "step": 29450 | |
| }, | |
| { | |
| "epoch": 8.590633737185462, | |
| "grad_norm": 0.3185526132583618, | |
| "learning_rate": 0.0004972062937062937, | |
| "loss": 3.4223, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 8.605195712954334, | |
| "grad_norm": 0.33054155111312866, | |
| "learning_rate": 0.0004970314685314685, | |
| "loss": 3.4258, | |
| "step": 29550 | |
| }, | |
| { | |
| "epoch": 8.619757688723206, | |
| "grad_norm": 0.32079461216926575, | |
| "learning_rate": 0.0004968566433566433, | |
| "loss": 3.4117, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 8.634319664492079, | |
| "grad_norm": 0.3708074390888214, | |
| "learning_rate": 0.0004966818181818181, | |
| "loss": 3.4194, | |
| "step": 29650 | |
| }, | |
| { | |
| "epoch": 8.648881640260951, | |
| "grad_norm": 0.31600895524024963, | |
| "learning_rate": 0.000496506993006993, | |
| "loss": 3.4229, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 8.663443616029824, | |
| "grad_norm": 0.357805460691452, | |
| "learning_rate": 0.0004963321678321678, | |
| "loss": 3.4078, | |
| "step": 29750 | |
| }, | |
| { | |
| "epoch": 8.678005591798696, | |
| "grad_norm": 0.3140498399734497, | |
| "learning_rate": 0.0004961573426573426, | |
| "loss": 3.4176, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 8.692567567567568, | |
| "grad_norm": 0.33390533924102783, | |
| "learning_rate": 0.0004959825174825175, | |
| "loss": 3.4325, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 8.707129543336439, | |
| "grad_norm": 0.33709651231765747, | |
| "learning_rate": 0.0004958076923076923, | |
| "loss": 3.4354, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 8.721691519105311, | |
| "grad_norm": 0.3508022129535675, | |
| "learning_rate": 0.0004956328671328671, | |
| "loss": 3.4322, | |
| "step": 29950 | |
| }, | |
| { | |
| "epoch": 8.736253494874184, | |
| "grad_norm": 0.3267257511615753, | |
| "learning_rate": 0.0004954580419580419, | |
| "loss": 3.431, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 8.736253494874184, | |
| "eval_accuracy": 0.3671072502047011, | |
| "eval_loss": 3.5762174129486084, | |
| "eval_runtime": 53.741, | |
| "eval_samples_per_second": 309.707, | |
| "eval_steps_per_second": 19.371, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 8.750815470643056, | |
| "grad_norm": 0.3560209274291992, | |
| "learning_rate": 0.0004952832167832167, | |
| "loss": 3.4339, | |
| "step": 30050 | |
| }, | |
| { | |
| "epoch": 8.765377446411929, | |
| "grad_norm": 0.3457399904727936, | |
| "learning_rate": 0.0004951083916083915, | |
| "loss": 3.4385, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 8.779939422180801, | |
| "grad_norm": 0.35111910104751587, | |
| "learning_rate": 0.0004949335664335664, | |
| "loss": 3.436, | |
| "step": 30150 | |
| }, | |
| { | |
| "epoch": 8.794501397949674, | |
| "grad_norm": 0.3317621946334839, | |
| "learning_rate": 0.0004947587412587412, | |
| "loss": 3.4257, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 8.809063373718546, | |
| "grad_norm": 0.3555958569049835, | |
| "learning_rate": 0.000494583916083916, | |
| "loss": 3.427, | |
| "step": 30250 | |
| }, | |
| { | |
| "epoch": 8.823625349487418, | |
| "grad_norm": 0.3580514192581177, | |
| "learning_rate": 0.0004944090909090908, | |
| "loss": 3.4433, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 8.83818732525629, | |
| "grad_norm": 0.3721309304237366, | |
| "learning_rate": 0.0004942342657342657, | |
| "loss": 3.4303, | |
| "step": 30350 | |
| }, | |
| { | |
| "epoch": 8.852749301025163, | |
| "grad_norm": 0.33837392926216125, | |
| "learning_rate": 0.0004940594405594405, | |
| "loss": 3.4396, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 8.867311276794036, | |
| "grad_norm": 0.3344026505947113, | |
| "learning_rate": 0.0004938846153846153, | |
| "loss": 3.4392, | |
| "step": 30450 | |
| }, | |
| { | |
| "epoch": 8.881873252562908, | |
| "grad_norm": 0.3359682559967041, | |
| "learning_rate": 0.0004937097902097901, | |
| "loss": 3.4327, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 8.89643522833178, | |
| "grad_norm": 0.3363666236400604, | |
| "learning_rate": 0.000493534965034965, | |
| "loss": 3.4385, | |
| "step": 30550 | |
| }, | |
| { | |
| "epoch": 8.910997204100653, | |
| "grad_norm": 0.31655505299568176, | |
| "learning_rate": 0.0004933601398601398, | |
| "loss": 3.4258, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 8.925559179869525, | |
| "grad_norm": 0.3216507136821747, | |
| "learning_rate": 0.0004931853146853146, | |
| "loss": 3.4292, | |
| "step": 30650 | |
| }, | |
| { | |
| "epoch": 8.940121155638398, | |
| "grad_norm": 0.3542217016220093, | |
| "learning_rate": 0.0004930104895104895, | |
| "loss": 3.4478, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 8.95468313140727, | |
| "grad_norm": 0.3227326273918152, | |
| "learning_rate": 0.0004928356643356642, | |
| "loss": 3.4315, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 8.969245107176143, | |
| "grad_norm": 0.33713215589523315, | |
| "learning_rate": 0.0004926608391608391, | |
| "loss": 3.4332, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 8.983807082945013, | |
| "grad_norm": 0.31681111454963684, | |
| "learning_rate": 0.0004924860139860139, | |
| "loss": 3.4466, | |
| "step": 30850 | |
| }, | |
| { | |
| "epoch": 8.998369058713886, | |
| "grad_norm": 0.3436877131462097, | |
| "learning_rate": 0.0004923111888111887, | |
| "loss": 3.4311, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 9.012814538676608, | |
| "grad_norm": 0.3397812843322754, | |
| "learning_rate": 0.0004921363636363635, | |
| "loss": 3.3401, | |
| "step": 30950 | |
| }, | |
| { | |
| "epoch": 9.02737651444548, | |
| "grad_norm": 0.32249370217323303, | |
| "learning_rate": 0.0004919615384615384, | |
| "loss": 3.3184, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 9.02737651444548, | |
| "eval_accuracy": 0.3673554546903946, | |
| "eval_loss": 3.5798304080963135, | |
| "eval_runtime": 53.6682, | |
| "eval_samples_per_second": 310.128, | |
| "eval_steps_per_second": 19.397, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 9.041938490214353, | |
| "grad_norm": 0.34547701478004456, | |
| "learning_rate": 0.0004917867132867132, | |
| "loss": 3.3374, | |
| "step": 31050 | |
| }, | |
| { | |
| "epoch": 9.056500465983225, | |
| "grad_norm": 0.33244821429252625, | |
| "learning_rate": 0.000491611888111888, | |
| "loss": 3.3453, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 9.071062441752098, | |
| "grad_norm": 0.32689371705055237, | |
| "learning_rate": 0.0004914370629370628, | |
| "loss": 3.3282, | |
| "step": 31150 | |
| }, | |
| { | |
| "epoch": 9.08562441752097, | |
| "grad_norm": 0.36178383231163025, | |
| "learning_rate": 0.0004912622377622378, | |
| "loss": 3.3424, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 9.100186393289842, | |
| "grad_norm": 0.3325725793838501, | |
| "learning_rate": 0.0004910874125874126, | |
| "loss": 3.342, | |
| "step": 31250 | |
| }, | |
| { | |
| "epoch": 9.114748369058713, | |
| "grad_norm": 0.3469438850879669, | |
| "learning_rate": 0.0004909125874125874, | |
| "loss": 3.3563, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 9.129310344827585, | |
| "grad_norm": 0.3236953318119049, | |
| "learning_rate": 0.0004907377622377623, | |
| "loss": 3.3446, | |
| "step": 31350 | |
| }, | |
| { | |
| "epoch": 9.143872320596458, | |
| "grad_norm": 0.3355654180049896, | |
| "learning_rate": 0.0004905629370629371, | |
| "loss": 3.3484, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 9.15843429636533, | |
| "grad_norm": 0.34349188208580017, | |
| "learning_rate": 0.0004903881118881119, | |
| "loss": 3.359, | |
| "step": 31450 | |
| }, | |
| { | |
| "epoch": 9.172996272134203, | |
| "grad_norm": 0.35089704394340515, | |
| "learning_rate": 0.0004902132867132867, | |
| "loss": 3.3577, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 9.187558247903075, | |
| "grad_norm": 0.3498465418815613, | |
| "learning_rate": 0.0004900384615384615, | |
| "loss": 3.342, | |
| "step": 31550 | |
| }, | |
| { | |
| "epoch": 9.202120223671947, | |
| "grad_norm": 0.3578391671180725, | |
| "learning_rate": 0.0004898636363636363, | |
| "loss": 3.3676, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 9.21668219944082, | |
| "grad_norm": 0.3580490052700043, | |
| "learning_rate": 0.0004896888111888112, | |
| "loss": 3.3645, | |
| "step": 31650 | |
| }, | |
| { | |
| "epoch": 9.231244175209692, | |
| "grad_norm": 0.3216322362422943, | |
| "learning_rate": 0.000489513986013986, | |
| "loss": 3.3669, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 9.245806150978565, | |
| "grad_norm": 0.35393744707107544, | |
| "learning_rate": 0.0004893391608391608, | |
| "loss": 3.3599, | |
| "step": 31750 | |
| }, | |
| { | |
| "epoch": 9.260368126747437, | |
| "grad_norm": 0.3496459126472473, | |
| "learning_rate": 0.0004891643356643356, | |
| "loss": 3.3759, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 9.27493010251631, | |
| "grad_norm": 0.34132808446884155, | |
| "learning_rate": 0.0004889895104895105, | |
| "loss": 3.3837, | |
| "step": 31850 | |
| }, | |
| { | |
| "epoch": 9.289492078285182, | |
| "grad_norm": 0.32651665806770325, | |
| "learning_rate": 0.0004888146853146853, | |
| "loss": 3.3847, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 9.304054054054054, | |
| "grad_norm": 0.3654690086841583, | |
| "learning_rate": 0.0004886398601398601, | |
| "loss": 3.3735, | |
| "step": 31950 | |
| }, | |
| { | |
| "epoch": 9.318616029822927, | |
| "grad_norm": 0.34119266271591187, | |
| "learning_rate": 0.000488465034965035, | |
| "loss": 3.377, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 9.318616029822927, | |
| "eval_accuracy": 0.3671819114308571, | |
| "eval_loss": 3.580883502960205, | |
| "eval_runtime": 53.5153, | |
| "eval_samples_per_second": 311.014, | |
| "eval_steps_per_second": 19.452, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 9.3331780055918, | |
| "grad_norm": 0.3433147966861725, | |
| "learning_rate": 0.0004882902097902098, | |
| "loss": 3.3882, | |
| "step": 32050 | |
| }, | |
| { | |
| "epoch": 9.347739981360672, | |
| "grad_norm": 0.34038546681404114, | |
| "learning_rate": 0.0004881153846153846, | |
| "loss": 3.3923, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 9.362301957129544, | |
| "grad_norm": 0.34648334980010986, | |
| "learning_rate": 0.0004879405594405594, | |
| "loss": 3.378, | |
| "step": 32150 | |
| }, | |
| { | |
| "epoch": 9.376863932898416, | |
| "grad_norm": 0.367409348487854, | |
| "learning_rate": 0.00048776573426573424, | |
| "loss": 3.3755, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 9.391425908667287, | |
| "grad_norm": 0.3667387068271637, | |
| "learning_rate": 0.00048759090909090904, | |
| "loss": 3.3698, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 9.40598788443616, | |
| "grad_norm": 0.3343542814254761, | |
| "learning_rate": 0.0004874160839160839, | |
| "loss": 3.3945, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 9.420549860205032, | |
| "grad_norm": 0.3317640423774719, | |
| "learning_rate": 0.0004872412587412587, | |
| "loss": 3.379, | |
| "step": 32350 | |
| }, | |
| { | |
| "epoch": 9.435111835973904, | |
| "grad_norm": 0.3385464549064636, | |
| "learning_rate": 0.00048706643356643354, | |
| "loss": 3.3775, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 9.449673811742777, | |
| "grad_norm": 0.332550048828125, | |
| "learning_rate": 0.00048689160839160834, | |
| "loss": 3.3821, | |
| "step": 32450 | |
| }, | |
| { | |
| "epoch": 9.46423578751165, | |
| "grad_norm": 0.37024253606796265, | |
| "learning_rate": 0.0004867167832167832, | |
| "loss": 3.3938, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 9.478797763280522, | |
| "grad_norm": 0.32912054657936096, | |
| "learning_rate": 0.00048654195804195794, | |
| "loss": 3.4036, | |
| "step": 32550 | |
| }, | |
| { | |
| "epoch": 9.493359739049394, | |
| "grad_norm": 0.3475010097026825, | |
| "learning_rate": 0.00048636713286713285, | |
| "loss": 3.3911, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 9.507921714818266, | |
| "grad_norm": 0.33058643341064453, | |
| "learning_rate": 0.0004861923076923077, | |
| "loss": 3.3881, | |
| "step": 32650 | |
| }, | |
| { | |
| "epoch": 9.522483690587139, | |
| "grad_norm": 0.35297462344169617, | |
| "learning_rate": 0.00048601748251748245, | |
| "loss": 3.3969, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 9.537045666356011, | |
| "grad_norm": 0.32153356075286865, | |
| "learning_rate": 0.0004858426573426573, | |
| "loss": 3.3882, | |
| "step": 32750 | |
| }, | |
| { | |
| "epoch": 9.551607642124884, | |
| "grad_norm": 0.3378690481185913, | |
| "learning_rate": 0.0004856678321678321, | |
| "loss": 3.3999, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 9.566169617893756, | |
| "grad_norm": 0.36066606640815735, | |
| "learning_rate": 0.00048549300699300696, | |
| "loss": 3.4033, | |
| "step": 32850 | |
| }, | |
| { | |
| "epoch": 9.580731593662628, | |
| "grad_norm": 0.33761295676231384, | |
| "learning_rate": 0.00048531818181818176, | |
| "loss": 3.389, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 9.595293569431501, | |
| "grad_norm": 0.34147173166275024, | |
| "learning_rate": 0.0004851433566433566, | |
| "loss": 3.3877, | |
| "step": 32950 | |
| }, | |
| { | |
| "epoch": 9.609855545200373, | |
| "grad_norm": 0.33251672983169556, | |
| "learning_rate": 0.0004849685314685314, | |
| "loss": 3.3939, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 9.609855545200373, | |
| "eval_accuracy": 0.36782082340397815, | |
| "eval_loss": 3.5724120140075684, | |
| "eval_runtime": 53.6826, | |
| "eval_samples_per_second": 310.045, | |
| "eval_steps_per_second": 19.392, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 9.624417520969246, | |
| "grad_norm": 0.37161070108413696, | |
| "learning_rate": 0.00048479370629370627, | |
| "loss": 3.3929, | |
| "step": 33050 | |
| }, | |
| { | |
| "epoch": 9.638979496738118, | |
| "grad_norm": 0.37724238634109497, | |
| "learning_rate": 0.00048461888111888106, | |
| "loss": 3.3984, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 9.65354147250699, | |
| "grad_norm": 0.32887575030326843, | |
| "learning_rate": 0.0004844440559440559, | |
| "loss": 3.3922, | |
| "step": 33150 | |
| }, | |
| { | |
| "epoch": 9.668103448275861, | |
| "grad_norm": 0.34217751026153564, | |
| "learning_rate": 0.0004842692307692307, | |
| "loss": 3.3963, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 9.682665424044734, | |
| "grad_norm": 0.34450656175613403, | |
| "learning_rate": 0.00048409440559440557, | |
| "loss": 3.4125, | |
| "step": 33250 | |
| }, | |
| { | |
| "epoch": 9.697227399813606, | |
| "grad_norm": 0.30637916922569275, | |
| "learning_rate": 0.0004839195804195803, | |
| "loss": 3.41, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 9.711789375582478, | |
| "grad_norm": 0.37624505162239075, | |
| "learning_rate": 0.0004837447552447552, | |
| "loss": 3.412, | |
| "step": 33350 | |
| }, | |
| { | |
| "epoch": 9.72635135135135, | |
| "grad_norm": 0.32816216349601746, | |
| "learning_rate": 0.0004835699300699301, | |
| "loss": 3.4044, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 9.740913327120223, | |
| "grad_norm": 0.3651433289051056, | |
| "learning_rate": 0.0004833951048951048, | |
| "loss": 3.3991, | |
| "step": 33450 | |
| }, | |
| { | |
| "epoch": 9.755475302889096, | |
| "grad_norm": 0.33466917276382446, | |
| "learning_rate": 0.0004832202797202797, | |
| "loss": 3.3992, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 9.770037278657968, | |
| "grad_norm": 0.32142600417137146, | |
| "learning_rate": 0.0004830454545454545, | |
| "loss": 3.4052, | |
| "step": 33550 | |
| }, | |
| { | |
| "epoch": 9.78459925442684, | |
| "grad_norm": 0.3309042453765869, | |
| "learning_rate": 0.00048287062937062933, | |
| "loss": 3.4094, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 9.799161230195713, | |
| "grad_norm": 0.3519335687160492, | |
| "learning_rate": 0.00048269580419580413, | |
| "loss": 3.4076, | |
| "step": 33650 | |
| }, | |
| { | |
| "epoch": 9.813723205964585, | |
| "grad_norm": 0.3344794511795044, | |
| "learning_rate": 0.000482520979020979, | |
| "loss": 3.4003, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 9.828285181733458, | |
| "grad_norm": 0.3368070721626282, | |
| "learning_rate": 0.0004823461538461538, | |
| "loss": 3.4049, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 9.84284715750233, | |
| "grad_norm": 0.33322641253471375, | |
| "learning_rate": 0.00048217132867132864, | |
| "loss": 3.4159, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 9.857409133271203, | |
| "grad_norm": 0.3441433012485504, | |
| "learning_rate": 0.00048199650349650344, | |
| "loss": 3.405, | |
| "step": 33850 | |
| }, | |
| { | |
| "epoch": 9.871971109040075, | |
| "grad_norm": 0.33350870013237, | |
| "learning_rate": 0.0004818216783216783, | |
| "loss": 3.4204, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 9.886533084808947, | |
| "grad_norm": 0.32797157764434814, | |
| "learning_rate": 0.0004816468531468531, | |
| "loss": 3.4159, | |
| "step": 33950 | |
| }, | |
| { | |
| "epoch": 9.90109506057782, | |
| "grad_norm": 0.3108486831188202, | |
| "learning_rate": 0.00048147202797202795, | |
| "loss": 3.4109, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 9.90109506057782, | |
| "eval_accuracy": 0.3685346317567234, | |
| "eval_loss": 3.5610878467559814, | |
| "eval_runtime": 53.686, | |
| "eval_samples_per_second": 310.025, | |
| "eval_steps_per_second": 19.391, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 9.915657036346692, | |
| "grad_norm": 0.3304729163646698, | |
| "learning_rate": 0.0004812972027972028, | |
| "loss": 3.4239, | |
| "step": 34050 | |
| }, | |
| { | |
| "epoch": 9.930219012115565, | |
| "grad_norm": 0.3313955068588257, | |
| "learning_rate": 0.0004811223776223776, | |
| "loss": 3.4181, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 9.944780987884435, | |
| "grad_norm": 0.3772457242012024, | |
| "learning_rate": 0.00048094755244755245, | |
| "loss": 3.4151, | |
| "step": 34150 | |
| }, | |
| { | |
| "epoch": 9.959342963653308, | |
| "grad_norm": 0.3140145540237427, | |
| "learning_rate": 0.0004807727272727272, | |
| "loss": 3.4049, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 9.97390493942218, | |
| "grad_norm": 0.3574320375919342, | |
| "learning_rate": 0.00048059790209790205, | |
| "loss": 3.4028, | |
| "step": 34250 | |
| }, | |
| { | |
| "epoch": 9.988466915191053, | |
| "grad_norm": 0.34361740946769714, | |
| "learning_rate": 0.00048042307692307685, | |
| "loss": 3.416, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 10.002912395153775, | |
| "grad_norm": 0.35159480571746826, | |
| "learning_rate": 0.0004802482517482517, | |
| "loss": 3.388, | |
| "step": 34350 | |
| }, | |
| { | |
| "epoch": 10.017474370922647, | |
| "grad_norm": 0.3495783805847168, | |
| "learning_rate": 0.0004800734265734265, | |
| "loss": 3.3064, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 10.03203634669152, | |
| "grad_norm": 0.32195907831192017, | |
| "learning_rate": 0.00047989860139860136, | |
| "loss": 3.3047, | |
| "step": 34450 | |
| }, | |
| { | |
| "epoch": 10.046598322460392, | |
| "grad_norm": 0.33187875151634216, | |
| "learning_rate": 0.00047972377622377616, | |
| "loss": 3.3059, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 10.061160298229264, | |
| "grad_norm": 0.3763480484485626, | |
| "learning_rate": 0.000479548951048951, | |
| "loss": 3.3148, | |
| "step": 34550 | |
| }, | |
| { | |
| "epoch": 10.075722273998137, | |
| "grad_norm": 0.338958740234375, | |
| "learning_rate": 0.0004793741258741258, | |
| "loss": 3.313, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 10.090284249767008, | |
| "grad_norm": 0.3450896739959717, | |
| "learning_rate": 0.00047919930069930067, | |
| "loss": 3.304, | |
| "step": 34650 | |
| }, | |
| { | |
| "epoch": 10.10484622553588, | |
| "grad_norm": 0.33590009808540344, | |
| "learning_rate": 0.0004790244755244755, | |
| "loss": 3.3238, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 10.119408201304752, | |
| "grad_norm": 0.3487749993801117, | |
| "learning_rate": 0.0004788496503496503, | |
| "loss": 3.3386, | |
| "step": 34750 | |
| }, | |
| { | |
| "epoch": 10.133970177073625, | |
| "grad_norm": 0.35672515630722046, | |
| "learning_rate": 0.0004786748251748252, | |
| "loss": 3.328, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 10.148532152842497, | |
| "grad_norm": 0.39034461975097656, | |
| "learning_rate": 0.0004785, | |
| "loss": 3.3355, | |
| "step": 34850 | |
| }, | |
| { | |
| "epoch": 10.16309412861137, | |
| "grad_norm": 0.3186233937740326, | |
| "learning_rate": 0.00047832517482517483, | |
| "loss": 3.3368, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 10.177656104380242, | |
| "grad_norm": 0.3687865734100342, | |
| "learning_rate": 0.0004781503496503496, | |
| "loss": 3.328, | |
| "step": 34950 | |
| }, | |
| { | |
| "epoch": 10.192218080149114, | |
| "grad_norm": 0.34652620553970337, | |
| "learning_rate": 0.00047797552447552443, | |
| "loss": 3.3373, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 10.192218080149114, | |
| "eval_accuracy": 0.36815674013331323, | |
| "eval_loss": 3.577220916748047, | |
| "eval_runtime": 53.6882, | |
| "eval_samples_per_second": 310.012, | |
| "eval_steps_per_second": 19.39, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 10.206780055917987, | |
| "grad_norm": 0.3340875208377838, | |
| "learning_rate": 0.00047780069930069923, | |
| "loss": 3.3462, | |
| "step": 35050 | |
| }, | |
| { | |
| "epoch": 10.22134203168686, | |
| "grad_norm": 0.3590002655982971, | |
| "learning_rate": 0.0004776258741258741, | |
| "loss": 3.3337, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 10.235904007455732, | |
| "grad_norm": 0.35122376680374146, | |
| "learning_rate": 0.0004774510489510489, | |
| "loss": 3.3435, | |
| "step": 35150 | |
| }, | |
| { | |
| "epoch": 10.250465983224604, | |
| "grad_norm": 0.32970312237739563, | |
| "learning_rate": 0.00047727622377622374, | |
| "loss": 3.35, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 10.265027958993477, | |
| "grad_norm": 0.3339228332042694, | |
| "learning_rate": 0.00047710139860139854, | |
| "loss": 3.3482, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 10.279589934762349, | |
| "grad_norm": 0.3375256657600403, | |
| "learning_rate": 0.0004769265734265734, | |
| "loss": 3.3569, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 10.294151910531221, | |
| "grad_norm": 0.35364654660224915, | |
| "learning_rate": 0.0004767517482517482, | |
| "loss": 3.355, | |
| "step": 35350 | |
| }, | |
| { | |
| "epoch": 10.308713886300094, | |
| "grad_norm": 0.34699511528015137, | |
| "learning_rate": 0.00047657692307692304, | |
| "loss": 3.3481, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 10.323275862068966, | |
| "grad_norm": 0.3622118830680847, | |
| "learning_rate": 0.0004764020979020979, | |
| "loss": 3.3501, | |
| "step": 35450 | |
| }, | |
| { | |
| "epoch": 10.337837837837839, | |
| "grad_norm": 0.3498924970626831, | |
| "learning_rate": 0.0004762272727272727, | |
| "loss": 3.3644, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 10.35239981360671, | |
| "grad_norm": 0.3727911114692688, | |
| "learning_rate": 0.00047605244755244755, | |
| "loss": 3.3639, | |
| "step": 35550 | |
| }, | |
| { | |
| "epoch": 10.366961789375582, | |
| "grad_norm": 0.3646833300590515, | |
| "learning_rate": 0.00047587762237762235, | |
| "loss": 3.3655, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 10.381523765144454, | |
| "grad_norm": 0.36712172627449036, | |
| "learning_rate": 0.0004757027972027972, | |
| "loss": 3.3527, | |
| "step": 35650 | |
| }, | |
| { | |
| "epoch": 10.396085740913326, | |
| "grad_norm": 0.347441703081131, | |
| "learning_rate": 0.00047552797202797195, | |
| "loss": 3.3624, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 10.410647716682199, | |
| "grad_norm": 0.32130295038223267, | |
| "learning_rate": 0.0004753531468531468, | |
| "loss": 3.3592, | |
| "step": 35750 | |
| }, | |
| { | |
| "epoch": 10.425209692451071, | |
| "grad_norm": 0.33343687653541565, | |
| "learning_rate": 0.0004751783216783216, | |
| "loss": 3.3741, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 10.439771668219944, | |
| "grad_norm": 0.3670390248298645, | |
| "learning_rate": 0.00047500349650349646, | |
| "loss": 3.3689, | |
| "step": 35850 | |
| }, | |
| { | |
| "epoch": 10.454333643988816, | |
| "grad_norm": 0.3569272458553314, | |
| "learning_rate": 0.00047482867132867126, | |
| "loss": 3.3685, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 10.468895619757689, | |
| "grad_norm": 0.34055817127227783, | |
| "learning_rate": 0.0004746538461538461, | |
| "loss": 3.3634, | |
| "step": 35950 | |
| }, | |
| { | |
| "epoch": 10.483457595526561, | |
| "grad_norm": 0.33791208267211914, | |
| "learning_rate": 0.0004744790209790209, | |
| "loss": 3.3609, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 10.483457595526561, | |
| "eval_accuracy": 0.3684646735999315, | |
| "eval_loss": 3.568392753601074, | |
| "eval_runtime": 53.7009, | |
| "eval_samples_per_second": 309.939, | |
| "eval_steps_per_second": 19.385, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 10.498019571295433, | |
| "grad_norm": 0.32268309593200684, | |
| "learning_rate": 0.00047430419580419576, | |
| "loss": 3.3688, | |
| "step": 36050 | |
| }, | |
| { | |
| "epoch": 10.512581547064306, | |
| "grad_norm": 0.33770951628685, | |
| "learning_rate": 0.0004741293706293706, | |
| "loss": 3.3606, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 10.527143522833178, | |
| "grad_norm": 0.35543033480644226, | |
| "learning_rate": 0.0004739545454545454, | |
| "loss": 3.3651, | |
| "step": 36150 | |
| }, | |
| { | |
| "epoch": 10.54170549860205, | |
| "grad_norm": 0.36934471130371094, | |
| "learning_rate": 0.00047377972027972027, | |
| "loss": 3.3687, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 10.556267474370923, | |
| "grad_norm": 0.35115522146224976, | |
| "learning_rate": 0.00047360489510489507, | |
| "loss": 3.3592, | |
| "step": 36250 | |
| }, | |
| { | |
| "epoch": 10.570829450139795, | |
| "grad_norm": 0.3395870327949524, | |
| "learning_rate": 0.0004734300699300699, | |
| "loss": 3.3721, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 10.585391425908668, | |
| "grad_norm": 0.33614251017570496, | |
| "learning_rate": 0.0004732552447552447, | |
| "loss": 3.3549, | |
| "step": 36350 | |
| }, | |
| { | |
| "epoch": 10.59995340167754, | |
| "grad_norm": 0.36550241708755493, | |
| "learning_rate": 0.0004730804195804196, | |
| "loss": 3.3782, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 10.614515377446413, | |
| "grad_norm": 0.36166924238204956, | |
| "learning_rate": 0.0004729055944055943, | |
| "loss": 3.3783, | |
| "step": 36450 | |
| }, | |
| { | |
| "epoch": 10.629077353215283, | |
| "grad_norm": 0.3547736406326294, | |
| "learning_rate": 0.0004727307692307692, | |
| "loss": 3.3818, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 10.643639328984156, | |
| "grad_norm": 0.3256096839904785, | |
| "learning_rate": 0.000472555944055944, | |
| "loss": 3.3684, | |
| "step": 36550 | |
| }, | |
| { | |
| "epoch": 10.658201304753028, | |
| "grad_norm": 0.3733418583869934, | |
| "learning_rate": 0.00047238111888111883, | |
| "loss": 3.374, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 10.6727632805219, | |
| "grad_norm": 0.3601815700531006, | |
| "learning_rate": 0.00047220629370629363, | |
| "loss": 3.3792, | |
| "step": 36650 | |
| }, | |
| { | |
| "epoch": 10.687325256290773, | |
| "grad_norm": 0.35017862915992737, | |
| "learning_rate": 0.0004720314685314685, | |
| "loss": 3.3813, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 10.701887232059645, | |
| "grad_norm": 0.34967872500419617, | |
| "learning_rate": 0.0004718566433566433, | |
| "loss": 3.3885, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 10.716449207828518, | |
| "grad_norm": 0.34832727909088135, | |
| "learning_rate": 0.00047168181818181814, | |
| "loss": 3.3882, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 10.73101118359739, | |
| "grad_norm": 0.3380468189716339, | |
| "learning_rate": 0.000471506993006993, | |
| "loss": 3.3771, | |
| "step": 36850 | |
| }, | |
| { | |
| "epoch": 10.745573159366263, | |
| "grad_norm": 0.31330186128616333, | |
| "learning_rate": 0.0004713321678321678, | |
| "loss": 3.378, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 10.760135135135135, | |
| "grad_norm": 0.35074543952941895, | |
| "learning_rate": 0.00047115734265734265, | |
| "loss": 3.3779, | |
| "step": 36950 | |
| }, | |
| { | |
| "epoch": 10.774697110904008, | |
| "grad_norm": 0.33050093054771423, | |
| "learning_rate": 0.00047098251748251745, | |
| "loss": 3.4038, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 10.774697110904008, | |
| "eval_accuracy": 0.36911640143706986, | |
| "eval_loss": 3.5599007606506348, | |
| "eval_runtime": 53.6294, | |
| "eval_samples_per_second": 310.352, | |
| "eval_steps_per_second": 19.411, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 10.78925908667288, | |
| "grad_norm": 0.3579956293106079, | |
| "learning_rate": 0.0004708076923076923, | |
| "loss": 3.3911, | |
| "step": 37050 | |
| }, | |
| { | |
| "epoch": 10.803821062441752, | |
| "grad_norm": 0.35300689935684204, | |
| "learning_rate": 0.0004706328671328671, | |
| "loss": 3.3969, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 10.818383038210625, | |
| "grad_norm": 0.3623140752315521, | |
| "learning_rate": 0.00047045804195804195, | |
| "loss": 3.3748, | |
| "step": 37150 | |
| }, | |
| { | |
| "epoch": 10.832945013979497, | |
| "grad_norm": 0.3329179584980011, | |
| "learning_rate": 0.0004702832167832167, | |
| "loss": 3.3935, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 10.84750698974837, | |
| "grad_norm": 0.33512651920318604, | |
| "learning_rate": 0.00047010839160839155, | |
| "loss": 3.3956, | |
| "step": 37250 | |
| }, | |
| { | |
| "epoch": 10.862068965517242, | |
| "grad_norm": 0.3599680960178375, | |
| "learning_rate": 0.00046993356643356635, | |
| "loss": 3.3912, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 10.876630941286114, | |
| "grad_norm": 0.3267347514629364, | |
| "learning_rate": 0.0004697587412587412, | |
| "loss": 3.3887, | |
| "step": 37350 | |
| }, | |
| { | |
| "epoch": 10.891192917054987, | |
| "grad_norm": 0.34810012578964233, | |
| "learning_rate": 0.000469583916083916, | |
| "loss": 3.3945, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 10.905754892823857, | |
| "grad_norm": 0.337226539850235, | |
| "learning_rate": 0.00046940909090909086, | |
| "loss": 3.3896, | |
| "step": 37450 | |
| }, | |
| { | |
| "epoch": 10.92031686859273, | |
| "grad_norm": 0.3359721302986145, | |
| "learning_rate": 0.0004692342657342657, | |
| "loss": 3.3856, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 10.934878844361602, | |
| "grad_norm": 0.3451782166957855, | |
| "learning_rate": 0.0004690594405594405, | |
| "loss": 3.399, | |
| "step": 37550 | |
| }, | |
| { | |
| "epoch": 10.949440820130475, | |
| "grad_norm": 0.33843597769737244, | |
| "learning_rate": 0.00046888461538461537, | |
| "loss": 3.3997, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 10.964002795899347, | |
| "grad_norm": 0.34089478850364685, | |
| "learning_rate": 0.00046870979020979017, | |
| "loss": 3.3971, | |
| "step": 37650 | |
| }, | |
| { | |
| "epoch": 10.97856477166822, | |
| "grad_norm": 0.3247876763343811, | |
| "learning_rate": 0.000468534965034965, | |
| "loss": 3.3987, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 10.993126747437092, | |
| "grad_norm": 0.37552350759506226, | |
| "learning_rate": 0.0004683601398601398, | |
| "loss": 3.3995, | |
| "step": 37750 | |
| }, | |
| { | |
| "epoch": 11.007572227399814, | |
| "grad_norm": 0.347272127866745, | |
| "learning_rate": 0.0004681853146853147, | |
| "loss": 3.3177, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 11.022134203168687, | |
| "grad_norm": 0.32849717140197754, | |
| "learning_rate": 0.0004680104895104895, | |
| "loss": 3.2835, | |
| "step": 37850 | |
| }, | |
| { | |
| "epoch": 11.036696178937559, | |
| "grad_norm": 0.3299245834350586, | |
| "learning_rate": 0.00046783566433566433, | |
| "loss": 3.2808, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 11.05125815470643, | |
| "grad_norm": 0.365369975566864, | |
| "learning_rate": 0.0004676608391608391, | |
| "loss": 3.287, | |
| "step": 37950 | |
| }, | |
| { | |
| "epoch": 11.065820130475302, | |
| "grad_norm": 0.3561994433403015, | |
| "learning_rate": 0.00046748601398601393, | |
| "loss": 3.2944, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 11.065820130475302, | |
| "eval_accuracy": 0.3690345680301335, | |
| "eval_loss": 3.572451591491699, | |
| "eval_runtime": 53.7621, | |
| "eval_samples_per_second": 309.586, | |
| "eval_steps_per_second": 19.363, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 11.080382106244175, | |
| "grad_norm": 0.3286043107509613, | |
| "learning_rate": 0.00046731118881118873, | |
| "loss": 3.2934, | |
| "step": 38050 | |
| }, | |
| { | |
| "epoch": 11.094944082013047, | |
| "grad_norm": 0.3433077037334442, | |
| "learning_rate": 0.0004671363636363636, | |
| "loss": 3.3118, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 11.10950605778192, | |
| "grad_norm": 0.3572927713394165, | |
| "learning_rate": 0.00046696153846153844, | |
| "loss": 3.3082, | |
| "step": 38150 | |
| }, | |
| { | |
| "epoch": 11.124068033550792, | |
| "grad_norm": 0.3482791483402252, | |
| "learning_rate": 0.00046678671328671324, | |
| "loss": 3.2973, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 11.138630009319664, | |
| "grad_norm": 0.34981897473335266, | |
| "learning_rate": 0.0004666118881118881, | |
| "loss": 3.3193, | |
| "step": 38250 | |
| }, | |
| { | |
| "epoch": 11.153191985088537, | |
| "grad_norm": 0.3662327527999878, | |
| "learning_rate": 0.0004664370629370629, | |
| "loss": 3.3112, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 11.167753960857409, | |
| "grad_norm": 0.34621360898017883, | |
| "learning_rate": 0.00046626223776223774, | |
| "loss": 3.3105, | |
| "step": 38350 | |
| }, | |
| { | |
| "epoch": 11.182315936626281, | |
| "grad_norm": 0.3586236834526062, | |
| "learning_rate": 0.00046608741258741254, | |
| "loss": 3.3078, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 11.196877912395154, | |
| "grad_norm": 0.3501543402671814, | |
| "learning_rate": 0.0004659125874125874, | |
| "loss": 3.323, | |
| "step": 38450 | |
| }, | |
| { | |
| "epoch": 11.211439888164026, | |
| "grad_norm": 0.3348871171474457, | |
| "learning_rate": 0.0004657377622377622, | |
| "loss": 3.3324, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 11.226001863932899, | |
| "grad_norm": 0.405658483505249, | |
| "learning_rate": 0.00046556293706293705, | |
| "loss": 3.322, | |
| "step": 38550 | |
| }, | |
| { | |
| "epoch": 11.240563839701771, | |
| "grad_norm": 0.3457586169242859, | |
| "learning_rate": 0.00046538811188811185, | |
| "loss": 3.3267, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 11.255125815470644, | |
| "grad_norm": 0.33291178941726685, | |
| "learning_rate": 0.0004652132867132867, | |
| "loss": 3.3245, | |
| "step": 38650 | |
| }, | |
| { | |
| "epoch": 11.269687791239516, | |
| "grad_norm": 0.34564632177352905, | |
| "learning_rate": 0.00046503846153846145, | |
| "loss": 3.3361, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 11.284249767008388, | |
| "grad_norm": 0.3823041021823883, | |
| "learning_rate": 0.0004648636363636363, | |
| "loss": 3.3214, | |
| "step": 38750 | |
| }, | |
| { | |
| "epoch": 11.29881174277726, | |
| "grad_norm": 0.32795125246047974, | |
| "learning_rate": 0.0004646888111888111, | |
| "loss": 3.3323, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 11.313373718546133, | |
| "grad_norm": 0.35187655687332153, | |
| "learning_rate": 0.00046451398601398596, | |
| "loss": 3.3299, | |
| "step": 38850 | |
| }, | |
| { | |
| "epoch": 11.327935694315004, | |
| "grad_norm": 0.3160579204559326, | |
| "learning_rate": 0.0004643391608391608, | |
| "loss": 3.3431, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 11.342497670083876, | |
| "grad_norm": 0.38711971044540405, | |
| "learning_rate": 0.0004641643356643356, | |
| "loss": 3.332, | |
| "step": 38950 | |
| }, | |
| { | |
| "epoch": 11.357059645852749, | |
| "grad_norm": 0.37961405515670776, | |
| "learning_rate": 0.00046398951048951046, | |
| "loss": 3.3442, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 11.357059645852749, | |
| "eval_accuracy": 0.36912874699415077, | |
| "eval_loss": 3.5660009384155273, | |
| "eval_runtime": 53.5851, | |
| "eval_samples_per_second": 310.609, | |
| "eval_steps_per_second": 19.427, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 11.371621621621621, | |
| "grad_norm": 0.33141857385635376, | |
| "learning_rate": 0.00046381468531468526, | |
| "loss": 3.3419, | |
| "step": 39050 | |
| }, | |
| { | |
| "epoch": 11.386183597390493, | |
| "grad_norm": 0.3561297059059143, | |
| "learning_rate": 0.0004636398601398601, | |
| "loss": 3.3425, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 11.400745573159366, | |
| "grad_norm": 0.35019031167030334, | |
| "learning_rate": 0.0004634650349650349, | |
| "loss": 3.3343, | |
| "step": 39150 | |
| }, | |
| { | |
| "epoch": 11.415307548928238, | |
| "grad_norm": 0.3231639862060547, | |
| "learning_rate": 0.00046329020979020977, | |
| "loss": 3.3429, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 11.42986952469711, | |
| "grad_norm": 0.3577631115913391, | |
| "learning_rate": 0.00046311538461538457, | |
| "loss": 3.3387, | |
| "step": 39250 | |
| }, | |
| { | |
| "epoch": 11.444431500465983, | |
| "grad_norm": 0.34335488080978394, | |
| "learning_rate": 0.0004629405594405594, | |
| "loss": 3.3505, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 11.458993476234856, | |
| "grad_norm": 0.3327701985836029, | |
| "learning_rate": 0.0004627657342657342, | |
| "loss": 3.3466, | |
| "step": 39350 | |
| }, | |
| { | |
| "epoch": 11.473555452003728, | |
| "grad_norm": 0.3649628758430481, | |
| "learning_rate": 0.0004625909090909091, | |
| "loss": 3.3514, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 11.4881174277726, | |
| "grad_norm": 0.35762521624565125, | |
| "learning_rate": 0.0004624160839160838, | |
| "loss": 3.3553, | |
| "step": 39450 | |
| }, | |
| { | |
| "epoch": 11.502679403541473, | |
| "grad_norm": 0.34466105699539185, | |
| "learning_rate": 0.0004622412587412587, | |
| "loss": 3.343, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 11.517241379310345, | |
| "grad_norm": 0.3552060127258301, | |
| "learning_rate": 0.00046206643356643353, | |
| "loss": 3.3465, | |
| "step": 39550 | |
| }, | |
| { | |
| "epoch": 11.531803355079218, | |
| "grad_norm": 0.3663930892944336, | |
| "learning_rate": 0.00046189160839160833, | |
| "loss": 3.3511, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 11.54636533084809, | |
| "grad_norm": 0.3702998161315918, | |
| "learning_rate": 0.0004617167832167832, | |
| "loss": 3.355, | |
| "step": 39650 | |
| }, | |
| { | |
| "epoch": 11.560927306616962, | |
| "grad_norm": 0.35928207635879517, | |
| "learning_rate": 0.000461541958041958, | |
| "loss": 3.3474, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 11.575489282385835, | |
| "grad_norm": 0.3266322910785675, | |
| "learning_rate": 0.00046136713286713284, | |
| "loss": 3.3541, | |
| "step": 39750 | |
| }, | |
| { | |
| "epoch": 11.590051258154705, | |
| "grad_norm": 0.3636510968208313, | |
| "learning_rate": 0.00046119230769230764, | |
| "loss": 3.3663, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 11.60461323392358, | |
| "grad_norm": 0.3514472544193268, | |
| "learning_rate": 0.0004610174825174825, | |
| "loss": 3.3469, | |
| "step": 39850 | |
| }, | |
| { | |
| "epoch": 11.61917520969245, | |
| "grad_norm": 0.32494455575942993, | |
| "learning_rate": 0.0004608426573426573, | |
| "loss": 3.3513, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 11.633737185461323, | |
| "grad_norm": 0.382254958152771, | |
| "learning_rate": 0.00046066783216783215, | |
| "loss": 3.3608, | |
| "step": 39950 | |
| }, | |
| { | |
| "epoch": 11.648299161230195, | |
| "grad_norm": 0.34891214966773987, | |
| "learning_rate": 0.00046049300699300695, | |
| "loss": 3.3584, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 11.648299161230195, | |
| "eval_accuracy": 0.3698353831661157, | |
| "eval_loss": 3.5602543354034424, | |
| "eval_runtime": 53.7409, | |
| "eval_samples_per_second": 309.708, | |
| "eval_steps_per_second": 19.371, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 11.662861136999068, | |
| "grad_norm": 0.37278759479522705, | |
| "learning_rate": 0.0004603181818181818, | |
| "loss": 3.3542, | |
| "step": 40050 | |
| }, | |
| { | |
| "epoch": 11.67742311276794, | |
| "grad_norm": 0.34679147601127625, | |
| "learning_rate": 0.0004601433566433566, | |
| "loss": 3.3569, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 11.691985088536812, | |
| "grad_norm": 0.3317880630493164, | |
| "learning_rate": 0.00045996853146853145, | |
| "loss": 3.3661, | |
| "step": 40150 | |
| }, | |
| { | |
| "epoch": 11.706547064305685, | |
| "grad_norm": 0.3492712676525116, | |
| "learning_rate": 0.0004597937062937062, | |
| "loss": 3.3572, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 11.721109040074557, | |
| "grad_norm": 0.34208858013153076, | |
| "learning_rate": 0.00045961888111888105, | |
| "loss": 3.3631, | |
| "step": 40250 | |
| }, | |
| { | |
| "epoch": 11.73567101584343, | |
| "grad_norm": 0.33355712890625, | |
| "learning_rate": 0.0004594440559440559, | |
| "loss": 3.3765, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 11.750232991612302, | |
| "grad_norm": 0.3657315671443939, | |
| "learning_rate": 0.0004592692307692307, | |
| "loss": 3.3711, | |
| "step": 40350 | |
| }, | |
| { | |
| "epoch": 11.764794967381174, | |
| "grad_norm": 0.3430049419403076, | |
| "learning_rate": 0.00045909440559440556, | |
| "loss": 3.3704, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 11.779356943150047, | |
| "grad_norm": 0.3502923250198364, | |
| "learning_rate": 0.00045891958041958036, | |
| "loss": 3.3644, | |
| "step": 40450 | |
| }, | |
| { | |
| "epoch": 11.79391891891892, | |
| "grad_norm": 0.34256404638290405, | |
| "learning_rate": 0.0004587447552447552, | |
| "loss": 3.3691, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 11.808480894687792, | |
| "grad_norm": 0.3291017711162567, | |
| "learning_rate": 0.00045856993006993, | |
| "loss": 3.3617, | |
| "step": 40550 | |
| }, | |
| { | |
| "epoch": 11.823042870456664, | |
| "grad_norm": 0.3593076467514038, | |
| "learning_rate": 0.00045839510489510487, | |
| "loss": 3.3738, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 11.837604846225537, | |
| "grad_norm": 0.32617098093032837, | |
| "learning_rate": 0.00045822027972027967, | |
| "loss": 3.3535, | |
| "step": 40650 | |
| }, | |
| { | |
| "epoch": 11.852166821994409, | |
| "grad_norm": 0.3508724868297577, | |
| "learning_rate": 0.0004580454545454545, | |
| "loss": 3.3876, | |
| "step": 40700 | |
| }, | |
| { | |
| "epoch": 11.86672879776328, | |
| "grad_norm": 0.3479333519935608, | |
| "learning_rate": 0.0004578706293706293, | |
| "loss": 3.3695, | |
| "step": 40750 | |
| }, | |
| { | |
| "epoch": 11.881290773532152, | |
| "grad_norm": 0.32733118534088135, | |
| "learning_rate": 0.0004576958041958042, | |
| "loss": 3.3708, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 11.895852749301024, | |
| "grad_norm": 0.3198227882385254, | |
| "learning_rate": 0.000457520979020979, | |
| "loss": 3.3678, | |
| "step": 40850 | |
| }, | |
| { | |
| "epoch": 11.910414725069897, | |
| "grad_norm": 0.36628979444503784, | |
| "learning_rate": 0.00045734615384615383, | |
| "loss": 3.38, | |
| "step": 40900 | |
| }, | |
| { | |
| "epoch": 11.92497670083877, | |
| "grad_norm": 0.3251120448112488, | |
| "learning_rate": 0.0004571713286713287, | |
| "loss": 3.377, | |
| "step": 40950 | |
| }, | |
| { | |
| "epoch": 11.939538676607642, | |
| "grad_norm": 0.3339826166629791, | |
| "learning_rate": 0.00045699650349650343, | |
| "loss": 3.3727, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 11.939538676607642, | |
| "eval_accuracy": 0.3699530774769538, | |
| "eval_loss": 3.551804542541504, | |
| "eval_runtime": 53.6416, | |
| "eval_samples_per_second": 310.282, | |
| "eval_steps_per_second": 19.407, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 11.954100652376514, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004568216783216783, | |
| "loss": 3.375, | |
| "step": 41050 | |
| }, | |
| { | |
| "epoch": 11.968662628145387, | |
| "grad_norm": 0.34985795617103577, | |
| "learning_rate": 0.0004566468531468531, | |
| "loss": 3.3771, | |
| "step": 41100 | |
| }, | |
| { | |
| "epoch": 11.983224603914259, | |
| "grad_norm": 0.349457323551178, | |
| "learning_rate": 0.00045647202797202794, | |
| "loss": 3.3705, | |
| "step": 41150 | |
| }, | |
| { | |
| "epoch": 11.997786579683131, | |
| "grad_norm": 0.37310871481895447, | |
| "learning_rate": 0.00045629720279720274, | |
| "loss": 3.3731, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 12.012232059645854, | |
| "grad_norm": 0.355582594871521, | |
| "learning_rate": 0.0004561223776223776, | |
| "loss": 3.2841, | |
| "step": 41250 | |
| }, | |
| { | |
| "epoch": 12.026794035414724, | |
| "grad_norm": 0.3613288700580597, | |
| "learning_rate": 0.0004559475524475524, | |
| "loss": 3.2708, | |
| "step": 41300 | |
| }, | |
| { | |
| "epoch": 12.041356011183597, | |
| "grad_norm": 0.3537559509277344, | |
| "learning_rate": 0.00045577272727272724, | |
| "loss": 3.2653, | |
| "step": 41350 | |
| }, | |
| { | |
| "epoch": 12.055917986952469, | |
| "grad_norm": 0.3575269281864166, | |
| "learning_rate": 0.00045559790209790204, | |
| "loss": 3.2662, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 12.070479962721341, | |
| "grad_norm": 0.35903748869895935, | |
| "learning_rate": 0.0004554230769230769, | |
| "loss": 3.2705, | |
| "step": 41450 | |
| }, | |
| { | |
| "epoch": 12.085041938490214, | |
| "grad_norm": 0.34469369053840637, | |
| "learning_rate": 0.0004552482517482517, | |
| "loss": 3.2761, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 12.099603914259086, | |
| "grad_norm": 0.36321061849594116, | |
| "learning_rate": 0.00045507342657342655, | |
| "loss": 3.2873, | |
| "step": 41550 | |
| }, | |
| { | |
| "epoch": 12.114165890027959, | |
| "grad_norm": 0.3258301317691803, | |
| "learning_rate": 0.00045489860139860135, | |
| "loss": 3.29, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 12.128727865796831, | |
| "grad_norm": 0.3304847776889801, | |
| "learning_rate": 0.0004547237762237762, | |
| "loss": 3.293, | |
| "step": 41650 | |
| }, | |
| { | |
| "epoch": 12.143289841565704, | |
| "grad_norm": 0.34567683935165405, | |
| "learning_rate": 0.00045454895104895106, | |
| "loss": 3.2915, | |
| "step": 41700 | |
| }, | |
| { | |
| "epoch": 12.157851817334576, | |
| "grad_norm": 0.356577068567276, | |
| "learning_rate": 0.0004543741258741258, | |
| "loss": 3.2912, | |
| "step": 41750 | |
| }, | |
| { | |
| "epoch": 12.172413793103448, | |
| "grad_norm": 0.37577152252197266, | |
| "learning_rate": 0.00045419930069930066, | |
| "loss": 3.2981, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 12.18697576887232, | |
| "grad_norm": 0.36569955945014954, | |
| "learning_rate": 0.00045402447552447546, | |
| "loss": 3.2971, | |
| "step": 41850 | |
| }, | |
| { | |
| "epoch": 12.201537744641193, | |
| "grad_norm": 0.33984923362731934, | |
| "learning_rate": 0.0004538496503496503, | |
| "loss": 3.3024, | |
| "step": 41900 | |
| }, | |
| { | |
| "epoch": 12.216099720410066, | |
| "grad_norm": 0.3310795724391937, | |
| "learning_rate": 0.0004536748251748251, | |
| "loss": 3.3037, | |
| "step": 41950 | |
| }, | |
| { | |
| "epoch": 12.230661696178938, | |
| "grad_norm": 0.3288843631744385, | |
| "learning_rate": 0.00045349999999999996, | |
| "loss": 3.2891, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 12.230661696178938, | |
| "eval_accuracy": 0.36970757725614467, | |
| "eval_loss": 3.565706491470337, | |
| "eval_runtime": 53.7928, | |
| "eval_samples_per_second": 309.409, | |
| "eval_steps_per_second": 19.352, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 12.24522367194781, | |
| "grad_norm": 0.3533994257450104, | |
| "learning_rate": 0.00045332517482517476, | |
| "loss": 3.306, | |
| "step": 42050 | |
| }, | |
| { | |
| "epoch": 12.259785647716683, | |
| "grad_norm": 0.3744911849498749, | |
| "learning_rate": 0.0004531503496503496, | |
| "loss": 3.3153, | |
| "step": 42100 | |
| }, | |
| { | |
| "epoch": 12.274347623485555, | |
| "grad_norm": 0.33848461508750916, | |
| "learning_rate": 0.0004529755244755244, | |
| "loss": 3.3241, | |
| "step": 42150 | |
| }, | |
| { | |
| "epoch": 12.288909599254428, | |
| "grad_norm": 0.3552786111831665, | |
| "learning_rate": 0.00045280069930069927, | |
| "loss": 3.304, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 12.303471575023298, | |
| "grad_norm": 0.3374313414096832, | |
| "learning_rate": 0.00045262587412587407, | |
| "loss": 3.3176, | |
| "step": 42250 | |
| }, | |
| { | |
| "epoch": 12.31803355079217, | |
| "grad_norm": 0.3446204364299774, | |
| "learning_rate": 0.0004524510489510489, | |
| "loss": 3.316, | |
| "step": 42300 | |
| }, | |
| { | |
| "epoch": 12.332595526561043, | |
| "grad_norm": 0.33028316497802734, | |
| "learning_rate": 0.0004522762237762238, | |
| "loss": 3.3309, | |
| "step": 42350 | |
| }, | |
| { | |
| "epoch": 12.347157502329916, | |
| "grad_norm": 0.3592996299266815, | |
| "learning_rate": 0.0004521013986013986, | |
| "loss": 3.3166, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 12.361719478098788, | |
| "grad_norm": 0.32952797412872314, | |
| "learning_rate": 0.00045192657342657343, | |
| "loss": 3.3313, | |
| "step": 42450 | |
| }, | |
| { | |
| "epoch": 12.37628145386766, | |
| "grad_norm": 0.3635094165802002, | |
| "learning_rate": 0.0004517517482517482, | |
| "loss": 3.3239, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 12.390843429636533, | |
| "grad_norm": 0.34926414489746094, | |
| "learning_rate": 0.00045157692307692303, | |
| "loss": 3.3094, | |
| "step": 42550 | |
| }, | |
| { | |
| "epoch": 12.405405405405405, | |
| "grad_norm": 0.3685735762119293, | |
| "learning_rate": 0.00045140209790209783, | |
| "loss": 3.3258, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 12.419967381174278, | |
| "grad_norm": 0.39783161878585815, | |
| "learning_rate": 0.0004512272727272727, | |
| "loss": 3.3241, | |
| "step": 42650 | |
| }, | |
| { | |
| "epoch": 12.43452935694315, | |
| "grad_norm": 0.3684312701225281, | |
| "learning_rate": 0.0004510524475524475, | |
| "loss": 3.33, | |
| "step": 42700 | |
| }, | |
| { | |
| "epoch": 12.449091332712023, | |
| "grad_norm": 0.3377741873264313, | |
| "learning_rate": 0.00045087762237762234, | |
| "loss": 3.3362, | |
| "step": 42750 | |
| }, | |
| { | |
| "epoch": 12.463653308480895, | |
| "grad_norm": 0.3300979733467102, | |
| "learning_rate": 0.00045070279720279714, | |
| "loss": 3.3443, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 12.478215284249767, | |
| "grad_norm": 0.34091269969940186, | |
| "learning_rate": 0.000450527972027972, | |
| "loss": 3.3248, | |
| "step": 42850 | |
| }, | |
| { | |
| "epoch": 12.49277726001864, | |
| "grad_norm": 0.36633142828941345, | |
| "learning_rate": 0.0004503531468531468, | |
| "loss": 3.3339, | |
| "step": 42900 | |
| }, | |
| { | |
| "epoch": 12.507339235787512, | |
| "grad_norm": 0.3405598998069763, | |
| "learning_rate": 0.00045017832167832165, | |
| "loss": 3.3359, | |
| "step": 42950 | |
| }, | |
| { | |
| "epoch": 12.521901211556385, | |
| "grad_norm": 0.34523844718933105, | |
| "learning_rate": 0.0004500034965034965, | |
| "loss": 3.3365, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 12.521901211556385, | |
| "eval_accuracy": 0.3699521368630809, | |
| "eval_loss": 3.558289051055908, | |
| "eval_runtime": 53.8081, | |
| "eval_samples_per_second": 309.321, | |
| "eval_steps_per_second": 19.347, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 12.536463187325257, | |
| "grad_norm": 0.33098194003105164, | |
| "learning_rate": 0.0004498286713286713, | |
| "loss": 3.3353, | |
| "step": 43050 | |
| }, | |
| { | |
| "epoch": 12.55102516309413, | |
| "grad_norm": 0.3387551009654999, | |
| "learning_rate": 0.00044965384615384615, | |
| "loss": 3.3402, | |
| "step": 43100 | |
| }, | |
| { | |
| "epoch": 12.565587138863002, | |
| "grad_norm": 0.4029315114021301, | |
| "learning_rate": 0.00044947902097902095, | |
| "loss": 3.337, | |
| "step": 43150 | |
| }, | |
| { | |
| "epoch": 12.580149114631872, | |
| "grad_norm": 0.3447522521018982, | |
| "learning_rate": 0.0004493041958041958, | |
| "loss": 3.3323, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 12.594711090400745, | |
| "grad_norm": 0.36428382992744446, | |
| "learning_rate": 0.00044912937062937055, | |
| "loss": 3.3395, | |
| "step": 43250 | |
| }, | |
| { | |
| "epoch": 12.609273066169617, | |
| "grad_norm": 0.33712589740753174, | |
| "learning_rate": 0.0004489545454545454, | |
| "loss": 3.3474, | |
| "step": 43300 | |
| }, | |
| { | |
| "epoch": 12.62383504193849, | |
| "grad_norm": 0.3448302149772644, | |
| "learning_rate": 0.0004487797202797202, | |
| "loss": 3.3336, | |
| "step": 43350 | |
| }, | |
| { | |
| "epoch": 12.638397017707362, | |
| "grad_norm": 0.3623657822608948, | |
| "learning_rate": 0.00044860489510489506, | |
| "loss": 3.3303, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 12.652958993476235, | |
| "grad_norm": 0.36065393686294556, | |
| "learning_rate": 0.00044843006993006986, | |
| "loss": 3.338, | |
| "step": 43450 | |
| }, | |
| { | |
| "epoch": 12.667520969245107, | |
| "grad_norm": 0.3675295412540436, | |
| "learning_rate": 0.0004482552447552447, | |
| "loss": 3.3405, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 12.68208294501398, | |
| "grad_norm": 0.33962827920913696, | |
| "learning_rate": 0.0004480804195804195, | |
| "loss": 3.3462, | |
| "step": 43550 | |
| }, | |
| { | |
| "epoch": 12.696644920782852, | |
| "grad_norm": 0.33174002170562744, | |
| "learning_rate": 0.00044790559440559437, | |
| "loss": 3.3458, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 12.711206896551724, | |
| "grad_norm": 0.35363972187042236, | |
| "learning_rate": 0.00044773076923076917, | |
| "loss": 3.3467, | |
| "step": 43650 | |
| }, | |
| { | |
| "epoch": 12.725768872320597, | |
| "grad_norm": 0.3485361933708191, | |
| "learning_rate": 0.000447555944055944, | |
| "loss": 3.3544, | |
| "step": 43700 | |
| }, | |
| { | |
| "epoch": 12.740330848089469, | |
| "grad_norm": 0.3747612535953522, | |
| "learning_rate": 0.0004473811188811189, | |
| "loss": 3.3621, | |
| "step": 43750 | |
| }, | |
| { | |
| "epoch": 12.754892823858341, | |
| "grad_norm": 0.35302239656448364, | |
| "learning_rate": 0.0004472062937062937, | |
| "loss": 3.3544, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 12.769454799627214, | |
| "grad_norm": 0.3448193371295929, | |
| "learning_rate": 0.00044703146853146853, | |
| "loss": 3.3471, | |
| "step": 43850 | |
| }, | |
| { | |
| "epoch": 12.784016775396086, | |
| "grad_norm": 0.34541070461273193, | |
| "learning_rate": 0.00044685664335664333, | |
| "loss": 3.3338, | |
| "step": 43900 | |
| }, | |
| { | |
| "epoch": 12.798578751164959, | |
| "grad_norm": 0.3578779101371765, | |
| "learning_rate": 0.0004466818181818182, | |
| "loss": 3.3472, | |
| "step": 43950 | |
| }, | |
| { | |
| "epoch": 12.813140726933831, | |
| "grad_norm": 0.3638927936553955, | |
| "learning_rate": 0.00044650699300699293, | |
| "loss": 3.3517, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 12.813140726933831, | |
| "eval_accuracy": 0.3705229719071558, | |
| "eval_loss": 3.551844358444214, | |
| "eval_runtime": 53.6548, | |
| "eval_samples_per_second": 310.205, | |
| "eval_steps_per_second": 19.402, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 12.827702702702704, | |
| "grad_norm": 0.36279812455177307, | |
| "learning_rate": 0.0004463321678321678, | |
| "loss": 3.3503, | |
| "step": 44050 | |
| }, | |
| { | |
| "epoch": 12.842264678471576, | |
| "grad_norm": 0.3644449710845947, | |
| "learning_rate": 0.0004461573426573426, | |
| "loss": 3.3355, | |
| "step": 44100 | |
| }, | |
| { | |
| "epoch": 12.856826654240447, | |
| "grad_norm": 0.3525535762310028, | |
| "learning_rate": 0.00044598251748251744, | |
| "loss": 3.3563, | |
| "step": 44150 | |
| }, | |
| { | |
| "epoch": 12.871388630009319, | |
| "grad_norm": 0.35456639528274536, | |
| "learning_rate": 0.00044580769230769224, | |
| "loss": 3.3572, | |
| "step": 44200 | |
| }, | |
| { | |
| "epoch": 12.885950605778191, | |
| "grad_norm": 0.34489408135414124, | |
| "learning_rate": 0.0004456328671328671, | |
| "loss": 3.3531, | |
| "step": 44250 | |
| }, | |
| { | |
| "epoch": 12.900512581547064, | |
| "grad_norm": 0.35041430592536926, | |
| "learning_rate": 0.0004454580419580419, | |
| "loss": 3.3423, | |
| "step": 44300 | |
| }, | |
| { | |
| "epoch": 12.915074557315936, | |
| "grad_norm": 0.32889389991760254, | |
| "learning_rate": 0.00044528321678321674, | |
| "loss": 3.3624, | |
| "step": 44350 | |
| }, | |
| { | |
| "epoch": 12.929636533084809, | |
| "grad_norm": 0.3557213544845581, | |
| "learning_rate": 0.0004451083916083916, | |
| "loss": 3.3462, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 12.944198508853681, | |
| "grad_norm": 0.3788115680217743, | |
| "learning_rate": 0.0004449335664335664, | |
| "loss": 3.3618, | |
| "step": 44450 | |
| }, | |
| { | |
| "epoch": 12.958760484622553, | |
| "grad_norm": 0.36202603578567505, | |
| "learning_rate": 0.00044475874125874125, | |
| "loss": 3.3527, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 12.973322460391426, | |
| "grad_norm": 0.3443240821361542, | |
| "learning_rate": 0.00044458391608391605, | |
| "loss": 3.361, | |
| "step": 44550 | |
| }, | |
| { | |
| "epoch": 12.987884436160298, | |
| "grad_norm": 0.3382508158683777, | |
| "learning_rate": 0.0004444090909090909, | |
| "loss": 3.3559, | |
| "step": 44600 | |
| }, | |
| { | |
| "epoch": 13.002329916123019, | |
| "grad_norm": 0.3703657388687134, | |
| "learning_rate": 0.0004442342657342657, | |
| "loss": 3.3453, | |
| "step": 44650 | |
| }, | |
| { | |
| "epoch": 13.016891891891891, | |
| "grad_norm": 0.3575532138347626, | |
| "learning_rate": 0.00044405944055944056, | |
| "loss": 3.235, | |
| "step": 44700 | |
| }, | |
| { | |
| "epoch": 13.031453867660764, | |
| "grad_norm": 0.33988216519355774, | |
| "learning_rate": 0.0004438846153846153, | |
| "loss": 3.2558, | |
| "step": 44750 | |
| }, | |
| { | |
| "epoch": 13.046015843429636, | |
| "grad_norm": 0.3483348488807678, | |
| "learning_rate": 0.00044370979020979016, | |
| "loss": 3.2569, | |
| "step": 44800 | |
| }, | |
| { | |
| "epoch": 13.060577819198508, | |
| "grad_norm": 0.3623815178871155, | |
| "learning_rate": 0.00044353496503496496, | |
| "loss": 3.2566, | |
| "step": 44850 | |
| }, | |
| { | |
| "epoch": 13.07513979496738, | |
| "grad_norm": 0.3875901699066162, | |
| "learning_rate": 0.0004433601398601398, | |
| "loss": 3.2659, | |
| "step": 44900 | |
| }, | |
| { | |
| "epoch": 13.089701770736253, | |
| "grad_norm": 0.3628861606121063, | |
| "learning_rate": 0.0004431853146853146, | |
| "loss": 3.2644, | |
| "step": 44950 | |
| }, | |
| { | |
| "epoch": 13.104263746505126, | |
| "grad_norm": 0.35806170105934143, | |
| "learning_rate": 0.00044301048951048946, | |
| "loss": 3.2635, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 13.104263746505126, | |
| "eval_accuracy": 0.37037071003649114, | |
| "eval_loss": 3.5615053176879883, | |
| "eval_runtime": 53.6575, | |
| "eval_samples_per_second": 310.189, | |
| "eval_steps_per_second": 19.401, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 13.118825722273998, | |
| "grad_norm": 0.3943418562412262, | |
| "learning_rate": 0.00044283566433566426, | |
| "loss": 3.2745, | |
| "step": 45050 | |
| }, | |
| { | |
| "epoch": 13.13338769804287, | |
| "grad_norm": 0.3521541953086853, | |
| "learning_rate": 0.0004426608391608391, | |
| "loss": 3.2742, | |
| "step": 45100 | |
| }, | |
| { | |
| "epoch": 13.147949673811743, | |
| "grad_norm": 0.4016038477420807, | |
| "learning_rate": 0.00044248601398601397, | |
| "loss": 3.2754, | |
| "step": 45150 | |
| }, | |
| { | |
| "epoch": 13.162511649580615, | |
| "grad_norm": 0.35581544041633606, | |
| "learning_rate": 0.00044231118881118877, | |
| "loss": 3.2855, | |
| "step": 45200 | |
| }, | |
| { | |
| "epoch": 13.177073625349488, | |
| "grad_norm": 0.3793915808200836, | |
| "learning_rate": 0.0004421363636363636, | |
| "loss": 3.2848, | |
| "step": 45250 | |
| }, | |
| { | |
| "epoch": 13.19163560111836, | |
| "grad_norm": 0.3508451581001282, | |
| "learning_rate": 0.0004419615384615384, | |
| "loss": 3.2707, | |
| "step": 45300 | |
| }, | |
| { | |
| "epoch": 13.206197576887233, | |
| "grad_norm": 0.34674158692359924, | |
| "learning_rate": 0.0004417867132867133, | |
| "loss": 3.2974, | |
| "step": 45350 | |
| }, | |
| { | |
| "epoch": 13.220759552656105, | |
| "grad_norm": 0.350559264421463, | |
| "learning_rate": 0.0004416118881118881, | |
| "loss": 3.2866, | |
| "step": 45400 | |
| }, | |
| { | |
| "epoch": 13.235321528424977, | |
| "grad_norm": 0.34364110231399536, | |
| "learning_rate": 0.00044143706293706293, | |
| "loss": 3.3051, | |
| "step": 45450 | |
| }, | |
| { | |
| "epoch": 13.24988350419385, | |
| "grad_norm": 0.35101890563964844, | |
| "learning_rate": 0.0004412622377622377, | |
| "loss": 3.2928, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 13.26444547996272, | |
| "grad_norm": 0.3574727177619934, | |
| "learning_rate": 0.00044108741258741253, | |
| "loss": 3.302, | |
| "step": 45550 | |
| }, | |
| { | |
| "epoch": 13.279007455731593, | |
| "grad_norm": 0.34663891792297363, | |
| "learning_rate": 0.00044091258741258733, | |
| "loss": 3.2942, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 13.293569431500465, | |
| "grad_norm": 0.3441726863384247, | |
| "learning_rate": 0.0004407377622377622, | |
| "loss": 3.2919, | |
| "step": 45650 | |
| }, | |
| { | |
| "epoch": 13.308131407269338, | |
| "grad_norm": 0.3620011508464813, | |
| "learning_rate": 0.000440562937062937, | |
| "loss": 3.2929, | |
| "step": 45700 | |
| }, | |
| { | |
| "epoch": 13.32269338303821, | |
| "grad_norm": 0.3525831401348114, | |
| "learning_rate": 0.00044038811188811184, | |
| "loss": 3.2914, | |
| "step": 45750 | |
| }, | |
| { | |
| "epoch": 13.337255358807083, | |
| "grad_norm": 0.34323644638061523, | |
| "learning_rate": 0.0004402132867132867, | |
| "loss": 3.3014, | |
| "step": 45800 | |
| }, | |
| { | |
| "epoch": 13.351817334575955, | |
| "grad_norm": 0.36165276169776917, | |
| "learning_rate": 0.0004400384615384615, | |
| "loss": 3.306, | |
| "step": 45850 | |
| }, | |
| { | |
| "epoch": 13.366379310344827, | |
| "grad_norm": 0.37652528285980225, | |
| "learning_rate": 0.00043986363636363635, | |
| "loss": 3.2961, | |
| "step": 45900 | |
| }, | |
| { | |
| "epoch": 13.3809412861137, | |
| "grad_norm": 0.36313024163246155, | |
| "learning_rate": 0.00043968881118881115, | |
| "loss": 3.301, | |
| "step": 45950 | |
| }, | |
| { | |
| "epoch": 13.395503261882572, | |
| "grad_norm": 0.3545302748680115, | |
| "learning_rate": 0.000439513986013986, | |
| "loss": 3.3246, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 13.395503261882572, | |
| "eval_accuracy": 0.37051732822391875, | |
| "eval_loss": 3.5548934936523438, | |
| "eval_runtime": 53.6644, | |
| "eval_samples_per_second": 310.15, | |
| "eval_steps_per_second": 19.398, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 13.410065237651445, | |
| "grad_norm": 0.3664780855178833, | |
| "learning_rate": 0.0004393391608391608, | |
| "loss": 3.3072, | |
| "step": 46050 | |
| }, | |
| { | |
| "epoch": 13.424627213420317, | |
| "grad_norm": 0.37858885526657104, | |
| "learning_rate": 0.00043916433566433565, | |
| "loss": 3.303, | |
| "step": 46100 | |
| }, | |
| { | |
| "epoch": 13.43918918918919, | |
| "grad_norm": 0.35305213928222656, | |
| "learning_rate": 0.00043898951048951045, | |
| "loss": 3.3141, | |
| "step": 46150 | |
| }, | |
| { | |
| "epoch": 13.453751164958062, | |
| "grad_norm": 0.36375489830970764, | |
| "learning_rate": 0.0004388146853146853, | |
| "loss": 3.3084, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 13.468313140726934, | |
| "grad_norm": 0.35223737359046936, | |
| "learning_rate": 0.00043863986013986005, | |
| "loss": 3.3056, | |
| "step": 46250 | |
| }, | |
| { | |
| "epoch": 13.482875116495807, | |
| "grad_norm": 0.34370267391204834, | |
| "learning_rate": 0.0004384650349650349, | |
| "loss": 3.3067, | |
| "step": 46300 | |
| }, | |
| { | |
| "epoch": 13.49743709226468, | |
| "grad_norm": 0.3426927626132965, | |
| "learning_rate": 0.0004382902097902097, | |
| "loss": 3.3176, | |
| "step": 46350 | |
| }, | |
| { | |
| "epoch": 13.511999068033552, | |
| "grad_norm": 0.3586205542087555, | |
| "learning_rate": 0.00043811538461538456, | |
| "loss": 3.3078, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 13.526561043802424, | |
| "grad_norm": 0.3668364882469177, | |
| "learning_rate": 0.0004379405594405594, | |
| "loss": 3.3185, | |
| "step": 46450 | |
| }, | |
| { | |
| "epoch": 13.541123019571295, | |
| "grad_norm": 0.3667503297328949, | |
| "learning_rate": 0.0004377657342657342, | |
| "loss": 3.3165, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 13.555684995340167, | |
| "grad_norm": 0.3611725866794586, | |
| "learning_rate": 0.00043759090909090907, | |
| "loss": 3.3153, | |
| "step": 46550 | |
| }, | |
| { | |
| "epoch": 13.57024697110904, | |
| "grad_norm": 0.3535501956939697, | |
| "learning_rate": 0.00043741608391608387, | |
| "loss": 3.3249, | |
| "step": 46600 | |
| }, | |
| { | |
| "epoch": 13.584808946877912, | |
| "grad_norm": 0.35195192694664, | |
| "learning_rate": 0.0004372412587412587, | |
| "loss": 3.3254, | |
| "step": 46650 | |
| }, | |
| { | |
| "epoch": 13.599370922646784, | |
| "grad_norm": 0.379182368516922, | |
| "learning_rate": 0.0004370664335664335, | |
| "loss": 3.3217, | |
| "step": 46700 | |
| }, | |
| { | |
| "epoch": 13.613932898415657, | |
| "grad_norm": 0.3737790882587433, | |
| "learning_rate": 0.0004368916083916084, | |
| "loss": 3.324, | |
| "step": 46750 | |
| }, | |
| { | |
| "epoch": 13.628494874184529, | |
| "grad_norm": 0.35494062304496765, | |
| "learning_rate": 0.0004367167832167832, | |
| "loss": 3.3244, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 13.643056849953402, | |
| "grad_norm": 0.33564329147338867, | |
| "learning_rate": 0.00043654195804195803, | |
| "loss": 3.3224, | |
| "step": 46850 | |
| }, | |
| { | |
| "epoch": 13.657618825722274, | |
| "grad_norm": 0.3607423007488251, | |
| "learning_rate": 0.00043636713286713283, | |
| "loss": 3.3325, | |
| "step": 46900 | |
| }, | |
| { | |
| "epoch": 13.672180801491146, | |
| "grad_norm": 0.36061540246009827, | |
| "learning_rate": 0.0004361923076923077, | |
| "loss": 3.3232, | |
| "step": 46950 | |
| }, | |
| { | |
| "epoch": 13.686742777260019, | |
| "grad_norm": 0.36729174852371216, | |
| "learning_rate": 0.00043601748251748243, | |
| "loss": 3.326, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 13.686742777260019, | |
| "eval_accuracy": 0.3709420153875023, | |
| "eval_loss": 3.5490164756774902, | |
| "eval_runtime": 53.6923, | |
| "eval_samples_per_second": 309.989, | |
| "eval_steps_per_second": 19.388, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 13.701304753028891, | |
| "grad_norm": 0.34589728713035583, | |
| "learning_rate": 0.00043584265734265734, | |
| "loss": 3.3293, | |
| "step": 47050 | |
| }, | |
| { | |
| "epoch": 13.715866728797764, | |
| "grad_norm": 0.3353387415409088, | |
| "learning_rate": 0.0004356678321678321, | |
| "loss": 3.338, | |
| "step": 47100 | |
| }, | |
| { | |
| "epoch": 13.730428704566636, | |
| "grad_norm": 0.32900935411453247, | |
| "learning_rate": 0.00043549300699300694, | |
| "loss": 3.3287, | |
| "step": 47150 | |
| }, | |
| { | |
| "epoch": 13.744990680335508, | |
| "grad_norm": 0.33722198009490967, | |
| "learning_rate": 0.0004353181818181818, | |
| "loss": 3.335, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 13.75955265610438, | |
| "grad_norm": 0.34776055812835693, | |
| "learning_rate": 0.0004351433566433566, | |
| "loss": 3.3368, | |
| "step": 47250 | |
| }, | |
| { | |
| "epoch": 13.774114631873253, | |
| "grad_norm": 0.34321945905685425, | |
| "learning_rate": 0.00043496853146853144, | |
| "loss": 3.3447, | |
| "step": 47300 | |
| }, | |
| { | |
| "epoch": 13.788676607642126, | |
| "grad_norm": 0.3597453832626343, | |
| "learning_rate": 0.00043479370629370624, | |
| "loss": 3.3474, | |
| "step": 47350 | |
| }, | |
| { | |
| "epoch": 13.803238583410998, | |
| "grad_norm": 0.3584977388381958, | |
| "learning_rate": 0.0004346188811188811, | |
| "loss": 3.3419, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 13.817800559179869, | |
| "grad_norm": 0.3313165009021759, | |
| "learning_rate": 0.0004344440559440559, | |
| "loss": 3.3364, | |
| "step": 47450 | |
| }, | |
| { | |
| "epoch": 13.832362534948741, | |
| "grad_norm": 0.3603111207485199, | |
| "learning_rate": 0.00043426923076923075, | |
| "loss": 3.3367, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 13.846924510717614, | |
| "grad_norm": 0.35369378328323364, | |
| "learning_rate": 0.00043409440559440555, | |
| "loss": 3.3415, | |
| "step": 47550 | |
| }, | |
| { | |
| "epoch": 13.861486486486486, | |
| "grad_norm": 0.37278762459754944, | |
| "learning_rate": 0.0004339195804195804, | |
| "loss": 3.3248, | |
| "step": 47600 | |
| }, | |
| { | |
| "epoch": 13.876048462255358, | |
| "grad_norm": 0.33600765466690063, | |
| "learning_rate": 0.0004337447552447552, | |
| "loss": 3.3372, | |
| "step": 47650 | |
| }, | |
| { | |
| "epoch": 13.89061043802423, | |
| "grad_norm": 0.3594343364238739, | |
| "learning_rate": 0.00043356993006993006, | |
| "loss": 3.3325, | |
| "step": 47700 | |
| }, | |
| { | |
| "epoch": 13.905172413793103, | |
| "grad_norm": 0.34375789761543274, | |
| "learning_rate": 0.0004333951048951048, | |
| "loss": 3.3424, | |
| "step": 47750 | |
| }, | |
| { | |
| "epoch": 13.919734389561976, | |
| "grad_norm": 0.349744975566864, | |
| "learning_rate": 0.0004332202797202797, | |
| "loss": 3.3309, | |
| "step": 47800 | |
| }, | |
| { | |
| "epoch": 13.934296365330848, | |
| "grad_norm": 0.343473345041275, | |
| "learning_rate": 0.00043304545454545456, | |
| "loss": 3.3392, | |
| "step": 47850 | |
| }, | |
| { | |
| "epoch": 13.94885834109972, | |
| "grad_norm": 0.35148507356643677, | |
| "learning_rate": 0.0004328706293706293, | |
| "loss": 3.3318, | |
| "step": 47900 | |
| }, | |
| { | |
| "epoch": 13.963420316868593, | |
| "grad_norm": 0.37654560804367065, | |
| "learning_rate": 0.00043269580419580416, | |
| "loss": 3.3446, | |
| "step": 47950 | |
| }, | |
| { | |
| "epoch": 13.977982292637465, | |
| "grad_norm": 0.3372819423675537, | |
| "learning_rate": 0.00043252097902097896, | |
| "loss": 3.3341, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 13.977982292637465, | |
| "eval_accuracy": 0.37139445066033444, | |
| "eval_loss": 3.543229103088379, | |
| "eval_runtime": 53.7768, | |
| "eval_samples_per_second": 309.502, | |
| "eval_steps_per_second": 19.358, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 13.992544268406338, | |
| "grad_norm": 0.35655635595321655, | |
| "learning_rate": 0.0004323461538461538, | |
| "loss": 3.3439, | |
| "step": 48050 | |
| }, | |
| { | |
| "epoch": 14.006989748369058, | |
| "grad_norm": 0.3547080457210541, | |
| "learning_rate": 0.0004321713286713286, | |
| "loss": 3.2918, | |
| "step": 48100 | |
| }, | |
| { | |
| "epoch": 14.02155172413793, | |
| "grad_norm": 0.33806321024894714, | |
| "learning_rate": 0.00043199650349650347, | |
| "loss": 3.2325, | |
| "step": 48150 | |
| }, | |
| { | |
| "epoch": 14.036113699906803, | |
| "grad_norm": 0.36164820194244385, | |
| "learning_rate": 0.00043182167832167827, | |
| "loss": 3.2547, | |
| "step": 48200 | |
| }, | |
| { | |
| "epoch": 14.050675675675675, | |
| "grad_norm": 0.33799758553504944, | |
| "learning_rate": 0.0004316468531468531, | |
| "loss": 3.2453, | |
| "step": 48250 | |
| }, | |
| { | |
| "epoch": 14.065237651444548, | |
| "grad_norm": 0.3774013817310333, | |
| "learning_rate": 0.0004314720279720279, | |
| "loss": 3.2307, | |
| "step": 48300 | |
| }, | |
| { | |
| "epoch": 14.07979962721342, | |
| "grad_norm": 0.3361668884754181, | |
| "learning_rate": 0.0004312972027972028, | |
| "loss": 3.2379, | |
| "step": 48350 | |
| }, | |
| { | |
| "epoch": 14.094361602982293, | |
| "grad_norm": 0.3815077841281891, | |
| "learning_rate": 0.0004311223776223776, | |
| "loss": 3.2621, | |
| "step": 48400 | |
| }, | |
| { | |
| "epoch": 14.108923578751165, | |
| "grad_norm": 0.37621423602104187, | |
| "learning_rate": 0.00043094755244755243, | |
| "loss": 3.2474, | |
| "step": 48450 | |
| }, | |
| { | |
| "epoch": 14.123485554520038, | |
| "grad_norm": 0.36258870363235474, | |
| "learning_rate": 0.0004307727272727272, | |
| "loss": 3.2517, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 14.13804753028891, | |
| "grad_norm": 0.3932361602783203, | |
| "learning_rate": 0.0004305979020979021, | |
| "loss": 3.2658, | |
| "step": 48550 | |
| }, | |
| { | |
| "epoch": 14.152609506057782, | |
| "grad_norm": 0.3555769920349121, | |
| "learning_rate": 0.00043042307692307694, | |
| "loss": 3.2742, | |
| "step": 48600 | |
| }, | |
| { | |
| "epoch": 14.167171481826655, | |
| "grad_norm": 0.35345563292503357, | |
| "learning_rate": 0.0004302482517482517, | |
| "loss": 3.2624, | |
| "step": 48650 | |
| }, | |
| { | |
| "epoch": 14.181733457595527, | |
| "grad_norm": 0.37088289856910706, | |
| "learning_rate": 0.00043007342657342654, | |
| "loss": 3.2776, | |
| "step": 48700 | |
| }, | |
| { | |
| "epoch": 14.1962954333644, | |
| "grad_norm": 0.36062613129615784, | |
| "learning_rate": 0.00042989860139860134, | |
| "loss": 3.2636, | |
| "step": 48750 | |
| }, | |
| { | |
| "epoch": 14.210857409133272, | |
| "grad_norm": 0.3612150251865387, | |
| "learning_rate": 0.0004297237762237762, | |
| "loss": 3.2603, | |
| "step": 48800 | |
| }, | |
| { | |
| "epoch": 14.225419384902143, | |
| "grad_norm": 0.34834256768226624, | |
| "learning_rate": 0.000429548951048951, | |
| "loss": 3.259, | |
| "step": 48850 | |
| }, | |
| { | |
| "epoch": 14.239981360671015, | |
| "grad_norm": 0.36643290519714355, | |
| "learning_rate": 0.00042937412587412585, | |
| "loss": 3.2726, | |
| "step": 48900 | |
| }, | |
| { | |
| "epoch": 14.254543336439887, | |
| "grad_norm": 0.4372047185897827, | |
| "learning_rate": 0.00042919930069930065, | |
| "loss": 3.2699, | |
| "step": 48950 | |
| }, | |
| { | |
| "epoch": 14.26910531220876, | |
| "grad_norm": 0.3443453311920166, | |
| "learning_rate": 0.0004290244755244755, | |
| "loss": 3.2913, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 14.26910531220876, | |
| "eval_accuracy": 0.37089275073591277, | |
| "eval_loss": 3.5589487552642822, | |
| "eval_runtime": 53.6734, | |
| "eval_samples_per_second": 310.098, | |
| "eval_steps_per_second": 19.395, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 14.283667287977632, | |
| "grad_norm": 0.38753968477249146, | |
| "learning_rate": 0.0004288496503496503, | |
| "loss": 3.2774, | |
| "step": 49050 | |
| }, | |
| { | |
| "epoch": 14.298229263746505, | |
| "grad_norm": 0.35234200954437256, | |
| "learning_rate": 0.00042867482517482515, | |
| "loss": 3.2762, | |
| "step": 49100 | |
| }, | |
| { | |
| "epoch": 14.312791239515377, | |
| "grad_norm": 0.38150152564048767, | |
| "learning_rate": 0.00042849999999999995, | |
| "loss": 3.2947, | |
| "step": 49150 | |
| }, | |
| { | |
| "epoch": 14.32735321528425, | |
| "grad_norm": 0.3585006296634674, | |
| "learning_rate": 0.0004283251748251748, | |
| "loss": 3.2861, | |
| "step": 49200 | |
| }, | |
| { | |
| "epoch": 14.341915191053122, | |
| "grad_norm": 0.340561181306839, | |
| "learning_rate": 0.00042815034965034966, | |
| "loss": 3.2793, | |
| "step": 49250 | |
| }, | |
| { | |
| "epoch": 14.356477166821994, | |
| "grad_norm": 0.3703455626964569, | |
| "learning_rate": 0.00042797552447552446, | |
| "loss": 3.289, | |
| "step": 49300 | |
| }, | |
| { | |
| "epoch": 14.371039142590867, | |
| "grad_norm": 0.38863709568977356, | |
| "learning_rate": 0.0004278006993006993, | |
| "loss": 3.2819, | |
| "step": 49350 | |
| }, | |
| { | |
| "epoch": 14.38560111835974, | |
| "grad_norm": 0.37331631779670715, | |
| "learning_rate": 0.00042762587412587406, | |
| "loss": 3.2992, | |
| "step": 49400 | |
| }, | |
| { | |
| "epoch": 14.400163094128612, | |
| "grad_norm": 0.35026001930236816, | |
| "learning_rate": 0.0004274510489510489, | |
| "loss": 3.3023, | |
| "step": 49450 | |
| }, | |
| { | |
| "epoch": 14.414725069897484, | |
| "grad_norm": 0.3765786588191986, | |
| "learning_rate": 0.0004272762237762237, | |
| "loss": 3.2869, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 14.429287045666356, | |
| "grad_norm": 0.4198647141456604, | |
| "learning_rate": 0.00042710139860139857, | |
| "loss": 3.299, | |
| "step": 49550 | |
| }, | |
| { | |
| "epoch": 14.443849021435229, | |
| "grad_norm": 0.37420520186424255, | |
| "learning_rate": 0.00042692657342657337, | |
| "loss": 3.3011, | |
| "step": 49600 | |
| }, | |
| { | |
| "epoch": 14.458410997204101, | |
| "grad_norm": 0.36429670453071594, | |
| "learning_rate": 0.0004267517482517482, | |
| "loss": 3.288, | |
| "step": 49650 | |
| }, | |
| { | |
| "epoch": 14.472972972972974, | |
| "grad_norm": 0.3489975035190582, | |
| "learning_rate": 0.000426576923076923, | |
| "loss": 3.3109, | |
| "step": 49700 | |
| }, | |
| { | |
| "epoch": 14.487534948741846, | |
| "grad_norm": 0.3541027903556824, | |
| "learning_rate": 0.0004264020979020979, | |
| "loss": 3.2971, | |
| "step": 49750 | |
| }, | |
| { | |
| "epoch": 14.502096924510717, | |
| "grad_norm": 0.3759947717189789, | |
| "learning_rate": 0.0004262272727272727, | |
| "loss": 3.313, | |
| "step": 49800 | |
| }, | |
| { | |
| "epoch": 14.51665890027959, | |
| "grad_norm": 0.35864460468292236, | |
| "learning_rate": 0.00042605244755244753, | |
| "loss": 3.3117, | |
| "step": 49850 | |
| }, | |
| { | |
| "epoch": 14.531220876048462, | |
| "grad_norm": 0.35375118255615234, | |
| "learning_rate": 0.00042587762237762233, | |
| "loss": 3.3131, | |
| "step": 49900 | |
| }, | |
| { | |
| "epoch": 14.545782851817334, | |
| "grad_norm": 0.3452862501144409, | |
| "learning_rate": 0.0004257027972027972, | |
| "loss": 3.2948, | |
| "step": 49950 | |
| }, | |
| { | |
| "epoch": 14.560344827586206, | |
| "grad_norm": 0.36372438073158264, | |
| "learning_rate": 0.00042552797202797204, | |
| "loss": 3.2971, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 14.560344827586206, | |
| "eval_accuracy": 0.37094483722912086, | |
| "eval_loss": 3.5522592067718506, | |
| "eval_runtime": 53.8803, | |
| "eval_samples_per_second": 308.907, | |
| "eval_steps_per_second": 19.321, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 14.574906803355079, | |
| "grad_norm": 0.34010276198387146, | |
| "learning_rate": 0.00042535314685314684, | |
| "loss": 3.3026, | |
| "step": 50050 | |
| }, | |
| { | |
| "epoch": 14.589468779123951, | |
| "grad_norm": 0.33550965785980225, | |
| "learning_rate": 0.0004251783216783217, | |
| "loss": 3.3004, | |
| "step": 50100 | |
| }, | |
| { | |
| "epoch": 14.604030754892824, | |
| "grad_norm": 0.3614843785762787, | |
| "learning_rate": 0.00042500349650349643, | |
| "loss": 3.3071, | |
| "step": 50150 | |
| }, | |
| { | |
| "epoch": 14.618592730661696, | |
| "grad_norm": 0.34630846977233887, | |
| "learning_rate": 0.0004248286713286713, | |
| "loss": 3.2983, | |
| "step": 50200 | |
| }, | |
| { | |
| "epoch": 14.633154706430568, | |
| "grad_norm": 0.34411928057670593, | |
| "learning_rate": 0.0004246538461538461, | |
| "loss": 3.3064, | |
| "step": 50250 | |
| }, | |
| { | |
| "epoch": 14.647716682199441, | |
| "grad_norm": 0.3575693368911743, | |
| "learning_rate": 0.00042447902097902094, | |
| "loss": 3.2985, | |
| "step": 50300 | |
| }, | |
| { | |
| "epoch": 14.662278657968313, | |
| "grad_norm": 0.3505471646785736, | |
| "learning_rate": 0.00042430419580419574, | |
| "loss": 3.3178, | |
| "step": 50350 | |
| }, | |
| { | |
| "epoch": 14.676840633737186, | |
| "grad_norm": 0.3225877583026886, | |
| "learning_rate": 0.0004241293706293706, | |
| "loss": 3.3121, | |
| "step": 50400 | |
| }, | |
| { | |
| "epoch": 14.691402609506058, | |
| "grad_norm": 0.33646827936172485, | |
| "learning_rate": 0.0004239545454545454, | |
| "loss": 3.3233, | |
| "step": 50450 | |
| }, | |
| { | |
| "epoch": 14.70596458527493, | |
| "grad_norm": 0.34578248858451843, | |
| "learning_rate": 0.00042377972027972025, | |
| "loss": 3.3137, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 14.720526561043803, | |
| "grad_norm": 0.35833966732025146, | |
| "learning_rate": 0.00042360489510489505, | |
| "loss": 3.3105, | |
| "step": 50550 | |
| }, | |
| { | |
| "epoch": 14.735088536812675, | |
| "grad_norm": 0.3806699812412262, | |
| "learning_rate": 0.0004234300699300699, | |
| "loss": 3.3273, | |
| "step": 50600 | |
| }, | |
| { | |
| "epoch": 14.749650512581548, | |
| "grad_norm": 0.37561845779418945, | |
| "learning_rate": 0.00042325524475524476, | |
| "loss": 3.3159, | |
| "step": 50650 | |
| }, | |
| { | |
| "epoch": 14.76421248835042, | |
| "grad_norm": 0.37811514735221863, | |
| "learning_rate": 0.00042308041958041956, | |
| "loss": 3.3263, | |
| "step": 50700 | |
| }, | |
| { | |
| "epoch": 14.77877446411929, | |
| "grad_norm": 0.36160987615585327, | |
| "learning_rate": 0.0004229055944055944, | |
| "loss": 3.3082, | |
| "step": 50750 | |
| }, | |
| { | |
| "epoch": 14.793336439888163, | |
| "grad_norm": 0.3447883129119873, | |
| "learning_rate": 0.0004227307692307692, | |
| "loss": 3.31, | |
| "step": 50800 | |
| }, | |
| { | |
| "epoch": 14.807898415657036, | |
| "grad_norm": 0.39840012788772583, | |
| "learning_rate": 0.00042255594405594406, | |
| "loss": 3.3142, | |
| "step": 50850 | |
| }, | |
| { | |
| "epoch": 14.822460391425908, | |
| "grad_norm": 0.37650975584983826, | |
| "learning_rate": 0.0004223811188811188, | |
| "loss": 3.3239, | |
| "step": 50900 | |
| }, | |
| { | |
| "epoch": 14.83702236719478, | |
| "grad_norm": 0.3962187170982361, | |
| "learning_rate": 0.00042220629370629366, | |
| "loss": 3.3275, | |
| "step": 50950 | |
| }, | |
| { | |
| "epoch": 14.851584342963653, | |
| "grad_norm": 0.3631623387336731, | |
| "learning_rate": 0.00042203146853146846, | |
| "loss": 3.3271, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 14.851584342963653, | |
| "eval_accuracy": 0.3713922167023865, | |
| "eval_loss": 3.5445010662078857, | |
| "eval_runtime": 53.7519, | |
| "eval_samples_per_second": 309.645, | |
| "eval_steps_per_second": 19.367, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 14.866146318732525, | |
| "grad_norm": 0.3710850775241852, | |
| "learning_rate": 0.0004218566433566433, | |
| "loss": 3.3204, | |
| "step": 51050 | |
| }, | |
| { | |
| "epoch": 14.880708294501398, | |
| "grad_norm": 0.36191123723983765, | |
| "learning_rate": 0.0004216818181818181, | |
| "loss": 3.3346, | |
| "step": 51100 | |
| }, | |
| { | |
| "epoch": 14.89527027027027, | |
| "grad_norm": 0.3745746910572052, | |
| "learning_rate": 0.00042150699300699297, | |
| "loss": 3.3167, | |
| "step": 51150 | |
| }, | |
| { | |
| "epoch": 14.909832246039143, | |
| "grad_norm": 0.3422452211380005, | |
| "learning_rate": 0.00042133216783216777, | |
| "loss": 3.3211, | |
| "step": 51200 | |
| }, | |
| { | |
| "epoch": 14.924394221808015, | |
| "grad_norm": 0.348006010055542, | |
| "learning_rate": 0.0004211573426573426, | |
| "loss": 3.3234, | |
| "step": 51250 | |
| }, | |
| { | |
| "epoch": 14.938956197576887, | |
| "grad_norm": 0.33569449186325073, | |
| "learning_rate": 0.0004209825174825175, | |
| "loss": 3.3362, | |
| "step": 51300 | |
| }, | |
| { | |
| "epoch": 14.95351817334576, | |
| "grad_norm": 0.34915322065353394, | |
| "learning_rate": 0.0004208076923076923, | |
| "loss": 3.326, | |
| "step": 51350 | |
| }, | |
| { | |
| "epoch": 14.968080149114632, | |
| "grad_norm": 0.3519541621208191, | |
| "learning_rate": 0.00042063286713286713, | |
| "loss": 3.3145, | |
| "step": 51400 | |
| }, | |
| { | |
| "epoch": 14.982642124883505, | |
| "grad_norm": 0.3761986494064331, | |
| "learning_rate": 0.00042045804195804193, | |
| "loss": 3.3318, | |
| "step": 51450 | |
| }, | |
| { | |
| "epoch": 14.997204100652377, | |
| "grad_norm": 0.3359870910644531, | |
| "learning_rate": 0.0004202832167832168, | |
| "loss": 3.3319, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 15.011649580615098, | |
| "grad_norm": 0.37047114968299866, | |
| "learning_rate": 0.0004201083916083916, | |
| "loss": 3.2483, | |
| "step": 51550 | |
| }, | |
| { | |
| "epoch": 15.02621155638397, | |
| "grad_norm": 0.36424553394317627, | |
| "learning_rate": 0.00041993356643356644, | |
| "loss": 3.2183, | |
| "step": 51600 | |
| }, | |
| { | |
| "epoch": 15.040773532152842, | |
| "grad_norm": 0.35980352759361267, | |
| "learning_rate": 0.0004197587412587412, | |
| "loss": 3.2262, | |
| "step": 51650 | |
| }, | |
| { | |
| "epoch": 15.055335507921715, | |
| "grad_norm": 0.37826991081237793, | |
| "learning_rate": 0.00041958391608391604, | |
| "loss": 3.2198, | |
| "step": 51700 | |
| }, | |
| { | |
| "epoch": 15.069897483690587, | |
| "grad_norm": 0.33697888255119324, | |
| "learning_rate": 0.00041940909090909084, | |
| "loss": 3.2334, | |
| "step": 51750 | |
| }, | |
| { | |
| "epoch": 15.08445945945946, | |
| "grad_norm": 0.38942408561706543, | |
| "learning_rate": 0.0004192342657342657, | |
| "loss": 3.2307, | |
| "step": 51800 | |
| }, | |
| { | |
| "epoch": 15.099021435228332, | |
| "grad_norm": 0.37160614132881165, | |
| "learning_rate": 0.0004190594405594405, | |
| "loss": 3.2336, | |
| "step": 51850 | |
| }, | |
| { | |
| "epoch": 15.113583410997204, | |
| "grad_norm": 0.37960243225097656, | |
| "learning_rate": 0.00041888461538461535, | |
| "loss": 3.2344, | |
| "step": 51900 | |
| }, | |
| { | |
| "epoch": 15.128145386766077, | |
| "grad_norm": 0.3533761501312256, | |
| "learning_rate": 0.00041870979020979015, | |
| "loss": 3.2452, | |
| "step": 51950 | |
| }, | |
| { | |
| "epoch": 15.14270736253495, | |
| "grad_norm": 0.36656302213668823, | |
| "learning_rate": 0.000418534965034965, | |
| "loss": 3.2435, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 15.14270736253495, | |
| "eval_accuracy": 0.3713126172533981, | |
| "eval_loss": 3.5588560104370117, | |
| "eval_runtime": 53.7438, | |
| "eval_samples_per_second": 309.691, | |
| "eval_steps_per_second": 19.37, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 15.157269338303822, | |
| "grad_norm": 0.37083372473716736, | |
| "learning_rate": 0.00041836013986013985, | |
| "loss": 3.2411, | |
| "step": 52050 | |
| }, | |
| { | |
| "epoch": 15.171831314072694, | |
| "grad_norm": 0.35016798973083496, | |
| "learning_rate": 0.00041818531468531465, | |
| "loss": 3.2433, | |
| "step": 52100 | |
| }, | |
| { | |
| "epoch": 15.186393289841567, | |
| "grad_norm": 0.34692856669425964, | |
| "learning_rate": 0.0004180104895104895, | |
| "loss": 3.2586, | |
| "step": 52150 | |
| }, | |
| { | |
| "epoch": 15.200955265610437, | |
| "grad_norm": 0.3626892864704132, | |
| "learning_rate": 0.0004178356643356643, | |
| "loss": 3.271, | |
| "step": 52200 | |
| }, | |
| { | |
| "epoch": 15.21551724137931, | |
| "grad_norm": 0.3602758049964905, | |
| "learning_rate": 0.00041766083916083916, | |
| "loss": 3.2612, | |
| "step": 52250 | |
| }, | |
| { | |
| "epoch": 15.230079217148182, | |
| "grad_norm": 0.40110644698143005, | |
| "learning_rate": 0.00041748601398601396, | |
| "loss": 3.2565, | |
| "step": 52300 | |
| }, | |
| { | |
| "epoch": 15.244641192917054, | |
| "grad_norm": 0.3626898527145386, | |
| "learning_rate": 0.0004173111888111888, | |
| "loss": 3.2693, | |
| "step": 52350 | |
| }, | |
| { | |
| "epoch": 15.259203168685927, | |
| "grad_norm": 0.37451228499412537, | |
| "learning_rate": 0.00041713636363636356, | |
| "loss": 3.259, | |
| "step": 52400 | |
| }, | |
| { | |
| "epoch": 15.2737651444548, | |
| "grad_norm": 0.36757326126098633, | |
| "learning_rate": 0.0004169615384615384, | |
| "loss": 3.2615, | |
| "step": 52450 | |
| }, | |
| { | |
| "epoch": 15.288327120223672, | |
| "grad_norm": 0.401369571685791, | |
| "learning_rate": 0.0004167867132867132, | |
| "loss": 3.257, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 15.302889095992544, | |
| "grad_norm": 0.35822781920433044, | |
| "learning_rate": 0.00041661188811188807, | |
| "loss": 3.2813, | |
| "step": 52550 | |
| }, | |
| { | |
| "epoch": 15.317451071761417, | |
| "grad_norm": 0.3864552676677704, | |
| "learning_rate": 0.00041643706293706287, | |
| "loss": 3.2849, | |
| "step": 52600 | |
| }, | |
| { | |
| "epoch": 15.332013047530289, | |
| "grad_norm": 0.41683146357536316, | |
| "learning_rate": 0.0004162622377622377, | |
| "loss": 3.268, | |
| "step": 52650 | |
| }, | |
| { | |
| "epoch": 15.346575023299161, | |
| "grad_norm": 0.3629013001918793, | |
| "learning_rate": 0.0004160874125874126, | |
| "loss": 3.2752, | |
| "step": 52700 | |
| }, | |
| { | |
| "epoch": 15.361136999068034, | |
| "grad_norm": 0.35468605160713196, | |
| "learning_rate": 0.0004159125874125874, | |
| "loss": 3.2849, | |
| "step": 52750 | |
| }, | |
| { | |
| "epoch": 15.375698974836906, | |
| "grad_norm": 0.3459469974040985, | |
| "learning_rate": 0.00041573776223776223, | |
| "loss": 3.2712, | |
| "step": 52800 | |
| }, | |
| { | |
| "epoch": 15.390260950605779, | |
| "grad_norm": 0.39700445532798767, | |
| "learning_rate": 0.00041556293706293703, | |
| "loss": 3.2843, | |
| "step": 52850 | |
| }, | |
| { | |
| "epoch": 15.404822926374651, | |
| "grad_norm": 0.35506534576416016, | |
| "learning_rate": 0.0004153881118881119, | |
| "loss": 3.2844, | |
| "step": 52900 | |
| }, | |
| { | |
| "epoch": 15.419384902143523, | |
| "grad_norm": 0.38613244891166687, | |
| "learning_rate": 0.0004152132867132867, | |
| "loss": 3.2746, | |
| "step": 52950 | |
| }, | |
| { | |
| "epoch": 15.433946877912396, | |
| "grad_norm": 0.3591909110546112, | |
| "learning_rate": 0.00041503846153846154, | |
| "loss": 3.281, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 15.433946877912396, | |
| "eval_accuracy": 0.371552238637502, | |
| "eval_loss": 3.555067539215088, | |
| "eval_runtime": 54.0003, | |
| "eval_samples_per_second": 308.221, | |
| "eval_steps_per_second": 19.278, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 15.448508853681268, | |
| "grad_norm": 0.35899174213409424, | |
| "learning_rate": 0.00041486363636363634, | |
| "loss": 3.2965, | |
| "step": 53050 | |
| }, | |
| { | |
| "epoch": 15.463070829450139, | |
| "grad_norm": 0.37865790724754333, | |
| "learning_rate": 0.0004146888111888112, | |
| "loss": 3.2903, | |
| "step": 53100 | |
| }, | |
| { | |
| "epoch": 15.477632805219011, | |
| "grad_norm": 0.34430116415023804, | |
| "learning_rate": 0.00041451398601398593, | |
| "loss": 3.2766, | |
| "step": 53150 | |
| }, | |
| { | |
| "epoch": 15.492194780987884, | |
| "grad_norm": 0.3497706651687622, | |
| "learning_rate": 0.0004143391608391608, | |
| "loss": 3.277, | |
| "step": 53200 | |
| }, | |
| { | |
| "epoch": 15.506756756756756, | |
| "grad_norm": 0.3752337396144867, | |
| "learning_rate": 0.0004141643356643356, | |
| "loss": 3.2805, | |
| "step": 53250 | |
| }, | |
| { | |
| "epoch": 15.521318732525629, | |
| "grad_norm": 0.39002713561058044, | |
| "learning_rate": 0.00041398951048951044, | |
| "loss": 3.2833, | |
| "step": 53300 | |
| }, | |
| { | |
| "epoch": 15.535880708294501, | |
| "grad_norm": 0.3368464410305023, | |
| "learning_rate": 0.00041381468531468524, | |
| "loss": 3.2913, | |
| "step": 53350 | |
| }, | |
| { | |
| "epoch": 15.550442684063373, | |
| "grad_norm": 0.3738703727722168, | |
| "learning_rate": 0.0004136398601398601, | |
| "loss": 3.2898, | |
| "step": 53400 | |
| }, | |
| { | |
| "epoch": 15.565004659832246, | |
| "grad_norm": 0.3517080545425415, | |
| "learning_rate": 0.00041346503496503495, | |
| "loss": 3.2909, | |
| "step": 53450 | |
| }, | |
| { | |
| "epoch": 15.579566635601118, | |
| "grad_norm": 0.3623846769332886, | |
| "learning_rate": 0.00041329020979020975, | |
| "loss": 3.2804, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 15.59412861136999, | |
| "grad_norm": 0.3643958270549774, | |
| "learning_rate": 0.0004131153846153846, | |
| "loss": 3.2919, | |
| "step": 53550 | |
| }, | |
| { | |
| "epoch": 15.608690587138863, | |
| "grad_norm": 0.3840982913970947, | |
| "learning_rate": 0.0004129405594405594, | |
| "loss": 3.2904, | |
| "step": 53600 | |
| }, | |
| { | |
| "epoch": 15.623252562907735, | |
| "grad_norm": 0.3870510756969452, | |
| "learning_rate": 0.00041276573426573426, | |
| "loss": 3.304, | |
| "step": 53650 | |
| }, | |
| { | |
| "epoch": 15.637814538676608, | |
| "grad_norm": 0.3654141426086426, | |
| "learning_rate": 0.00041259090909090906, | |
| "loss": 3.2927, | |
| "step": 53700 | |
| }, | |
| { | |
| "epoch": 15.65237651444548, | |
| "grad_norm": 0.36212411522865295, | |
| "learning_rate": 0.0004124160839160839, | |
| "loss": 3.2895, | |
| "step": 53750 | |
| }, | |
| { | |
| "epoch": 15.666938490214353, | |
| "grad_norm": 0.3940054476261139, | |
| "learning_rate": 0.0004122412587412587, | |
| "loss": 3.3188, | |
| "step": 53800 | |
| }, | |
| { | |
| "epoch": 15.681500465983225, | |
| "grad_norm": 0.35793691873550415, | |
| "learning_rate": 0.00041206643356643356, | |
| "loss": 3.3, | |
| "step": 53850 | |
| }, | |
| { | |
| "epoch": 15.696062441752098, | |
| "grad_norm": 0.38477155566215515, | |
| "learning_rate": 0.0004118916083916083, | |
| "loss": 3.2999, | |
| "step": 53900 | |
| }, | |
| { | |
| "epoch": 15.71062441752097, | |
| "grad_norm": 0.35515347123146057, | |
| "learning_rate": 0.00041171678321678316, | |
| "loss": 3.2988, | |
| "step": 53950 | |
| }, | |
| { | |
| "epoch": 15.725186393289842, | |
| "grad_norm": 0.3534596860408783, | |
| "learning_rate": 0.00041154195804195796, | |
| "loss": 3.3023, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 15.725186393289842, | |
| "eval_accuracy": 0.37190861371857115, | |
| "eval_loss": 3.544243812561035, | |
| "eval_runtime": 53.5815, | |
| "eval_samples_per_second": 310.629, | |
| "eval_steps_per_second": 19.428, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 15.739748369058713, | |
| "grad_norm": 0.3302527964115143, | |
| "learning_rate": 0.0004113671328671328, | |
| "loss": 3.3066, | |
| "step": 54050 | |
| }, | |
| { | |
| "epoch": 15.754310344827585, | |
| "grad_norm": 0.3625675141811371, | |
| "learning_rate": 0.00041119230769230767, | |
| "loss": 3.3, | |
| "step": 54100 | |
| }, | |
| { | |
| "epoch": 15.768872320596458, | |
| "grad_norm": 0.34582090377807617, | |
| "learning_rate": 0.00041101748251748247, | |
| "loss": 3.3056, | |
| "step": 54150 | |
| }, | |
| { | |
| "epoch": 15.78343429636533, | |
| "grad_norm": 0.35482490062713623, | |
| "learning_rate": 0.0004108426573426573, | |
| "loss": 3.3043, | |
| "step": 54200 | |
| }, | |
| { | |
| "epoch": 15.797996272134203, | |
| "grad_norm": 0.3603096604347229, | |
| "learning_rate": 0.0004106678321678321, | |
| "loss": 3.3053, | |
| "step": 54250 | |
| }, | |
| { | |
| "epoch": 15.812558247903075, | |
| "grad_norm": 0.3536098897457123, | |
| "learning_rate": 0.000410493006993007, | |
| "loss": 3.3112, | |
| "step": 54300 | |
| }, | |
| { | |
| "epoch": 15.827120223671947, | |
| "grad_norm": 0.41206008195877075, | |
| "learning_rate": 0.0004103181818181818, | |
| "loss": 3.3086, | |
| "step": 54350 | |
| }, | |
| { | |
| "epoch": 15.84168219944082, | |
| "grad_norm": 0.35738715529441833, | |
| "learning_rate": 0.00041014335664335663, | |
| "loss": 3.312, | |
| "step": 54400 | |
| }, | |
| { | |
| "epoch": 15.856244175209692, | |
| "grad_norm": 0.375002384185791, | |
| "learning_rate": 0.00040996853146853143, | |
| "loss": 3.3148, | |
| "step": 54450 | |
| }, | |
| { | |
| "epoch": 15.870806150978565, | |
| "grad_norm": 0.3635875880718231, | |
| "learning_rate": 0.0004097937062937063, | |
| "loss": 3.3177, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 15.885368126747437, | |
| "grad_norm": 0.3630351722240448, | |
| "learning_rate": 0.0004096188811188811, | |
| "loss": 3.3109, | |
| "step": 54550 | |
| }, | |
| { | |
| "epoch": 15.89993010251631, | |
| "grad_norm": 0.39034175872802734, | |
| "learning_rate": 0.00040944405594405594, | |
| "loss": 3.3014, | |
| "step": 54600 | |
| }, | |
| { | |
| "epoch": 15.914492078285182, | |
| "grad_norm": 0.34750694036483765, | |
| "learning_rate": 0.0004092692307692307, | |
| "loss": 3.3082, | |
| "step": 54650 | |
| }, | |
| { | |
| "epoch": 15.929054054054054, | |
| "grad_norm": 0.4042045474052429, | |
| "learning_rate": 0.00040909440559440554, | |
| "loss": 3.3119, | |
| "step": 54700 | |
| }, | |
| { | |
| "epoch": 15.943616029822927, | |
| "grad_norm": 0.3563961386680603, | |
| "learning_rate": 0.00040891958041958034, | |
| "loss": 3.3132, | |
| "step": 54750 | |
| }, | |
| { | |
| "epoch": 15.9581780055918, | |
| "grad_norm": 0.35997897386550903, | |
| "learning_rate": 0.0004087447552447552, | |
| "loss": 3.3179, | |
| "step": 54800 | |
| }, | |
| { | |
| "epoch": 15.972739981360672, | |
| "grad_norm": 0.33496615290641785, | |
| "learning_rate": 0.00040856993006993005, | |
| "loss": 3.314, | |
| "step": 54850 | |
| }, | |
| { | |
| "epoch": 15.987301957129544, | |
| "grad_norm": 0.3893013000488281, | |
| "learning_rate": 0.00040839510489510485, | |
| "loss": 3.3048, | |
| "step": 54900 | |
| }, | |
| { | |
| "epoch": 16.001747437092266, | |
| "grad_norm": 0.3888099491596222, | |
| "learning_rate": 0.0004082202797202797, | |
| "loss": 3.295, | |
| "step": 54950 | |
| }, | |
| { | |
| "epoch": 16.016309412861137, | |
| "grad_norm": 0.3761426508426666, | |
| "learning_rate": 0.0004080454545454545, | |
| "loss": 3.2045, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 16.016309412861137, | |
| "eval_accuracy": 0.3716526491684268, | |
| "eval_loss": 3.552569627761841, | |
| "eval_runtime": 53.7366, | |
| "eval_samples_per_second": 309.733, | |
| "eval_steps_per_second": 19.372, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 16.030871388630008, | |
| "grad_norm": 0.3669045865535736, | |
| "learning_rate": 0.00040787062937062935, | |
| "loss": 3.2014, | |
| "step": 55050 | |
| }, | |
| { | |
| "epoch": 16.045433364398882, | |
| "grad_norm": 0.37650567293167114, | |
| "learning_rate": 0.00040769580419580415, | |
| "loss": 3.2067, | |
| "step": 55100 | |
| }, | |
| { | |
| "epoch": 16.059995340167752, | |
| "grad_norm": 0.37726104259490967, | |
| "learning_rate": 0.000407520979020979, | |
| "loss": 3.2181, | |
| "step": 55150 | |
| }, | |
| { | |
| "epoch": 16.074557315936627, | |
| "grad_norm": 0.3812066614627838, | |
| "learning_rate": 0.0004073461538461538, | |
| "loss": 3.213, | |
| "step": 55200 | |
| }, | |
| { | |
| "epoch": 16.089119291705497, | |
| "grad_norm": 0.3624626100063324, | |
| "learning_rate": 0.00040717132867132866, | |
| "loss": 3.224, | |
| "step": 55250 | |
| }, | |
| { | |
| "epoch": 16.10368126747437, | |
| "grad_norm": 0.36346620321273804, | |
| "learning_rate": 0.00040699650349650346, | |
| "loss": 3.235, | |
| "step": 55300 | |
| }, | |
| { | |
| "epoch": 16.118243243243242, | |
| "grad_norm": 0.37540963292121887, | |
| "learning_rate": 0.0004068216783216783, | |
| "loss": 3.2326, | |
| "step": 55350 | |
| }, | |
| { | |
| "epoch": 16.132805219012116, | |
| "grad_norm": 0.3593809902667999, | |
| "learning_rate": 0.00040664685314685306, | |
| "loss": 3.2304, | |
| "step": 55400 | |
| }, | |
| { | |
| "epoch": 16.147367194780987, | |
| "grad_norm": 0.381249338388443, | |
| "learning_rate": 0.0004064720279720279, | |
| "loss": 3.228, | |
| "step": 55450 | |
| }, | |
| { | |
| "epoch": 16.16192917054986, | |
| "grad_norm": 0.3877742886543274, | |
| "learning_rate": 0.00040629720279720277, | |
| "loss": 3.231, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 16.17649114631873, | |
| "grad_norm": 0.38962066173553467, | |
| "learning_rate": 0.00040612237762237757, | |
| "loss": 3.2386, | |
| "step": 55550 | |
| }, | |
| { | |
| "epoch": 16.191053122087606, | |
| "grad_norm": 0.3545854091644287, | |
| "learning_rate": 0.0004059475524475524, | |
| "loss": 3.2417, | |
| "step": 55600 | |
| }, | |
| { | |
| "epoch": 16.205615097856477, | |
| "grad_norm": 0.37691715359687805, | |
| "learning_rate": 0.0004057727272727272, | |
| "loss": 3.2418, | |
| "step": 55650 | |
| }, | |
| { | |
| "epoch": 16.22017707362535, | |
| "grad_norm": 0.37831491231918335, | |
| "learning_rate": 0.0004055979020979021, | |
| "loss": 3.2338, | |
| "step": 55700 | |
| }, | |
| { | |
| "epoch": 16.23473904939422, | |
| "grad_norm": 0.37360233068466187, | |
| "learning_rate": 0.0004054230769230769, | |
| "loss": 3.2526, | |
| "step": 55750 | |
| }, | |
| { | |
| "epoch": 16.249301025163096, | |
| "grad_norm": 0.4056057035923004, | |
| "learning_rate": 0.00040524825174825173, | |
| "loss": 3.2549, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 16.263863000931966, | |
| "grad_norm": 0.37376824021339417, | |
| "learning_rate": 0.00040507342657342653, | |
| "loss": 3.2509, | |
| "step": 55850 | |
| }, | |
| { | |
| "epoch": 16.27842497670084, | |
| "grad_norm": 0.3650595545768738, | |
| "learning_rate": 0.0004048986013986014, | |
| "loss": 3.2494, | |
| "step": 55900 | |
| }, | |
| { | |
| "epoch": 16.29298695246971, | |
| "grad_norm": 0.3548644483089447, | |
| "learning_rate": 0.0004047237762237762, | |
| "loss": 3.2429, | |
| "step": 55950 | |
| }, | |
| { | |
| "epoch": 16.30754892823858, | |
| "grad_norm": 0.38068774342536926, | |
| "learning_rate": 0.00040454895104895104, | |
| "loss": 3.2608, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 16.30754892823858, | |
| "eval_accuracy": 0.3716091457768083, | |
| "eval_loss": 3.552886724472046, | |
| "eval_runtime": 53.7187, | |
| "eval_samples_per_second": 309.836, | |
| "eval_steps_per_second": 19.379, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 16.322110904007456, | |
| "grad_norm": 0.3673131465911865, | |
| "learning_rate": 0.00040437412587412583, | |
| "loss": 3.2607, | |
| "step": 56050 | |
| }, | |
| { | |
| "epoch": 16.336672879776327, | |
| "grad_norm": 0.3998847007751465, | |
| "learning_rate": 0.0004041993006993007, | |
| "loss": 3.2589, | |
| "step": 56100 | |
| }, | |
| { | |
| "epoch": 16.3512348555452, | |
| "grad_norm": 0.4015873670578003, | |
| "learning_rate": 0.00040402447552447554, | |
| "loss": 3.2677, | |
| "step": 56150 | |
| }, | |
| { | |
| "epoch": 16.36579683131407, | |
| "grad_norm": 0.3576182723045349, | |
| "learning_rate": 0.0004038496503496503, | |
| "loss": 3.2537, | |
| "step": 56200 | |
| }, | |
| { | |
| "epoch": 16.380358807082946, | |
| "grad_norm": 0.3824199140071869, | |
| "learning_rate": 0.00040367482517482514, | |
| "loss": 3.2587, | |
| "step": 56250 | |
| }, | |
| { | |
| "epoch": 16.394920782851816, | |
| "grad_norm": 0.3755083680152893, | |
| "learning_rate": 0.00040349999999999994, | |
| "loss": 3.2559, | |
| "step": 56300 | |
| }, | |
| { | |
| "epoch": 16.40948275862069, | |
| "grad_norm": 0.37745600938796997, | |
| "learning_rate": 0.0004033251748251748, | |
| "loss": 3.2651, | |
| "step": 56350 | |
| }, | |
| { | |
| "epoch": 16.42404473438956, | |
| "grad_norm": 0.3472992777824402, | |
| "learning_rate": 0.0004031503496503496, | |
| "loss": 3.2705, | |
| "step": 56400 | |
| }, | |
| { | |
| "epoch": 16.438606710158435, | |
| "grad_norm": 0.3721696138381958, | |
| "learning_rate": 0.00040297552447552445, | |
| "loss": 3.2709, | |
| "step": 56450 | |
| }, | |
| { | |
| "epoch": 16.453168685927306, | |
| "grad_norm": 0.44224095344543457, | |
| "learning_rate": 0.00040280069930069925, | |
| "loss": 3.2753, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 16.46773066169618, | |
| "grad_norm": 0.3655279874801636, | |
| "learning_rate": 0.0004026258741258741, | |
| "loss": 3.2718, | |
| "step": 56550 | |
| }, | |
| { | |
| "epoch": 16.48229263746505, | |
| "grad_norm": 0.4208175837993622, | |
| "learning_rate": 0.0004024510489510489, | |
| "loss": 3.2723, | |
| "step": 56600 | |
| }, | |
| { | |
| "epoch": 16.496854613233925, | |
| "grad_norm": 0.36009299755096436, | |
| "learning_rate": 0.00040227622377622376, | |
| "loss": 3.2746, | |
| "step": 56650 | |
| }, | |
| { | |
| "epoch": 16.511416589002796, | |
| "grad_norm": 0.3603965938091278, | |
| "learning_rate": 0.00040210139860139856, | |
| "loss": 3.2668, | |
| "step": 56700 | |
| }, | |
| { | |
| "epoch": 16.52597856477167, | |
| "grad_norm": 0.35173988342285156, | |
| "learning_rate": 0.0004019265734265734, | |
| "loss": 3.2793, | |
| "step": 56750 | |
| }, | |
| { | |
| "epoch": 16.54054054054054, | |
| "grad_norm": 0.36199483275413513, | |
| "learning_rate": 0.0004017517482517482, | |
| "loss": 3.2773, | |
| "step": 56800 | |
| }, | |
| { | |
| "epoch": 16.555102516309415, | |
| "grad_norm": 0.41115614771842957, | |
| "learning_rate": 0.00040157692307692306, | |
| "loss": 3.2808, | |
| "step": 56850 | |
| }, | |
| { | |
| "epoch": 16.569664492078285, | |
| "grad_norm": 0.3796447515487671, | |
| "learning_rate": 0.0004014020979020979, | |
| "loss": 3.2859, | |
| "step": 56900 | |
| }, | |
| { | |
| "epoch": 16.584226467847156, | |
| "grad_norm": 0.35656216740608215, | |
| "learning_rate": 0.00040122727272727266, | |
| "loss": 3.2721, | |
| "step": 56950 | |
| }, | |
| { | |
| "epoch": 16.59878844361603, | |
| "grad_norm": 0.38244813680648804, | |
| "learning_rate": 0.0004010524475524475, | |
| "loss": 3.2856, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 16.59878844361603, | |
| "eval_accuracy": 0.3720420633117792, | |
| "eval_loss": 3.5462512969970703, | |
| "eval_runtime": 53.7179, | |
| "eval_samples_per_second": 309.841, | |
| "eval_steps_per_second": 19.379, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 16.6133504193849, | |
| "grad_norm": 0.3651905059814453, | |
| "learning_rate": 0.0004008776223776223, | |
| "loss": 3.2915, | |
| "step": 57050 | |
| }, | |
| { | |
| "epoch": 16.627912395153775, | |
| "grad_norm": 0.39289090037345886, | |
| "learning_rate": 0.00040070279720279717, | |
| "loss": 3.2943, | |
| "step": 57100 | |
| }, | |
| { | |
| "epoch": 16.642474370922645, | |
| "grad_norm": 0.36119070649147034, | |
| "learning_rate": 0.00040052797202797197, | |
| "loss": 3.2677, | |
| "step": 57150 | |
| }, | |
| { | |
| "epoch": 16.65703634669152, | |
| "grad_norm": 0.3775008022785187, | |
| "learning_rate": 0.0004003531468531468, | |
| "loss": 3.2877, | |
| "step": 57200 | |
| }, | |
| { | |
| "epoch": 16.67159832246039, | |
| "grad_norm": 0.3913573920726776, | |
| "learning_rate": 0.0004001783216783216, | |
| "loss": 3.2814, | |
| "step": 57250 | |
| }, | |
| { | |
| "epoch": 16.686160298229264, | |
| "grad_norm": 0.3607911467552185, | |
| "learning_rate": 0.0004000034965034965, | |
| "loss": 3.3019, | |
| "step": 57300 | |
| }, | |
| { | |
| "epoch": 16.700722273998135, | |
| "grad_norm": 0.3782852292060852, | |
| "learning_rate": 0.0003998286713286713, | |
| "loss": 3.2801, | |
| "step": 57350 | |
| }, | |
| { | |
| "epoch": 16.71528424976701, | |
| "grad_norm": 0.365681916475296, | |
| "learning_rate": 0.00039965384615384613, | |
| "loss": 3.2835, | |
| "step": 57400 | |
| }, | |
| { | |
| "epoch": 16.72984622553588, | |
| "grad_norm": 0.34979718923568726, | |
| "learning_rate": 0.00039947902097902093, | |
| "loss": 3.2942, | |
| "step": 57450 | |
| }, | |
| { | |
| "epoch": 16.744408201304754, | |
| "grad_norm": 0.3606526553630829, | |
| "learning_rate": 0.0003993041958041958, | |
| "loss": 3.2869, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 16.758970177073625, | |
| "grad_norm": 0.4020101726055145, | |
| "learning_rate": 0.00039912937062937064, | |
| "loss": 3.2722, | |
| "step": 57550 | |
| }, | |
| { | |
| "epoch": 16.7735321528425, | |
| "grad_norm": 0.3851315975189209, | |
| "learning_rate": 0.00039895454545454544, | |
| "loss": 3.3015, | |
| "step": 57600 | |
| }, | |
| { | |
| "epoch": 16.78809412861137, | |
| "grad_norm": 0.3507918119430542, | |
| "learning_rate": 0.0003987797202797203, | |
| "loss": 3.2921, | |
| "step": 57650 | |
| }, | |
| { | |
| "epoch": 16.802656104380244, | |
| "grad_norm": 0.39337655901908875, | |
| "learning_rate": 0.00039860489510489504, | |
| "loss": 3.2917, | |
| "step": 57700 | |
| }, | |
| { | |
| "epoch": 16.817218080149114, | |
| "grad_norm": 0.3827846050262451, | |
| "learning_rate": 0.0003984300699300699, | |
| "loss": 3.3008, | |
| "step": 57750 | |
| }, | |
| { | |
| "epoch": 16.83178005591799, | |
| "grad_norm": 0.3798079490661621, | |
| "learning_rate": 0.0003982552447552447, | |
| "loss": 3.3022, | |
| "step": 57800 | |
| }, | |
| { | |
| "epoch": 16.84634203168686, | |
| "grad_norm": 0.3755364716053009, | |
| "learning_rate": 0.00039808041958041955, | |
| "loss": 3.3025, | |
| "step": 57850 | |
| }, | |
| { | |
| "epoch": 16.86090400745573, | |
| "grad_norm": 0.37088385224342346, | |
| "learning_rate": 0.00039790559440559435, | |
| "loss": 3.291, | |
| "step": 57900 | |
| }, | |
| { | |
| "epoch": 16.875465983224604, | |
| "grad_norm": 0.3381931781768799, | |
| "learning_rate": 0.0003977307692307692, | |
| "loss": 3.3046, | |
| "step": 57950 | |
| }, | |
| { | |
| "epoch": 16.890027958993475, | |
| "grad_norm": 0.3929003179073334, | |
| "learning_rate": 0.000397555944055944, | |
| "loss": 3.2891, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 16.890027958993475, | |
| "eval_accuracy": 0.37263147547984243, | |
| "eval_loss": 3.53983998298645, | |
| "eval_runtime": 53.8555, | |
| "eval_samples_per_second": 309.049, | |
| "eval_steps_per_second": 19.329, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 16.90458993476235, | |
| "grad_norm": 0.3901415467262268, | |
| "learning_rate": 0.00039738111888111885, | |
| "loss": 3.2989, | |
| "step": 58050 | |
| }, | |
| { | |
| "epoch": 16.91915191053122, | |
| "grad_norm": 0.39257511496543884, | |
| "learning_rate": 0.00039720629370629365, | |
| "loss": 3.3008, | |
| "step": 58100 | |
| }, | |
| { | |
| "epoch": 16.933713886300094, | |
| "grad_norm": 0.4112852215766907, | |
| "learning_rate": 0.0003970314685314685, | |
| "loss": 3.2988, | |
| "step": 58150 | |
| }, | |
| { | |
| "epoch": 16.948275862068964, | |
| "grad_norm": 0.333914190530777, | |
| "learning_rate": 0.0003968566433566433, | |
| "loss": 3.309, | |
| "step": 58200 | |
| }, | |
| { | |
| "epoch": 16.96283783783784, | |
| "grad_norm": 0.3521735966205597, | |
| "learning_rate": 0.00039668181818181816, | |
| "loss": 3.2993, | |
| "step": 58250 | |
| }, | |
| { | |
| "epoch": 16.97739981360671, | |
| "grad_norm": 0.3785235285758972, | |
| "learning_rate": 0.000396506993006993, | |
| "loss": 3.3071, | |
| "step": 58300 | |
| }, | |
| { | |
| "epoch": 16.991961789375583, | |
| "grad_norm": 0.37092772126197815, | |
| "learning_rate": 0.0003963321678321678, | |
| "loss": 3.2962, | |
| "step": 58350 | |
| }, | |
| { | |
| "epoch": 17.006407269338304, | |
| "grad_norm": 0.36320120096206665, | |
| "learning_rate": 0.00039615734265734267, | |
| "loss": 3.2517, | |
| "step": 58400 | |
| }, | |
| { | |
| "epoch": 17.020969245107175, | |
| "grad_norm": 0.3834632933139801, | |
| "learning_rate": 0.0003959825174825174, | |
| "loss": 3.1924, | |
| "step": 58450 | |
| }, | |
| { | |
| "epoch": 17.03553122087605, | |
| "grad_norm": 0.37915751338005066, | |
| "learning_rate": 0.00039580769230769227, | |
| "loss": 3.1932, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 17.05009319664492, | |
| "grad_norm": 0.39746683835983276, | |
| "learning_rate": 0.00039563286713286707, | |
| "loss": 3.2142, | |
| "step": 58550 | |
| }, | |
| { | |
| "epoch": 17.064655172413794, | |
| "grad_norm": 0.3451356291770935, | |
| "learning_rate": 0.0003954580419580419, | |
| "loss": 3.1985, | |
| "step": 58600 | |
| }, | |
| { | |
| "epoch": 17.079217148182664, | |
| "grad_norm": 0.3739311993122101, | |
| "learning_rate": 0.0003952832167832167, | |
| "loss": 3.1925, | |
| "step": 58650 | |
| }, | |
| { | |
| "epoch": 17.09377912395154, | |
| "grad_norm": 0.3468732535839081, | |
| "learning_rate": 0.0003951083916083916, | |
| "loss": 3.222, | |
| "step": 58700 | |
| }, | |
| { | |
| "epoch": 17.10834109972041, | |
| "grad_norm": 0.45381662249565125, | |
| "learning_rate": 0.0003949335664335664, | |
| "loss": 3.2193, | |
| "step": 58750 | |
| }, | |
| { | |
| "epoch": 17.122903075489283, | |
| "grad_norm": 0.3815675377845764, | |
| "learning_rate": 0.00039475874125874123, | |
| "loss": 3.208, | |
| "step": 58800 | |
| }, | |
| { | |
| "epoch": 17.137465051258154, | |
| "grad_norm": 0.36168697476387024, | |
| "learning_rate": 0.00039458391608391603, | |
| "loss": 3.2273, | |
| "step": 58850 | |
| }, | |
| { | |
| "epoch": 17.152027027027028, | |
| "grad_norm": 0.374543696641922, | |
| "learning_rate": 0.0003944090909090909, | |
| "loss": 3.2288, | |
| "step": 58900 | |
| }, | |
| { | |
| "epoch": 17.1665890027959, | |
| "grad_norm": 0.40095534920692444, | |
| "learning_rate": 0.00039423426573426573, | |
| "loss": 3.2166, | |
| "step": 58950 | |
| }, | |
| { | |
| "epoch": 17.181150978564773, | |
| "grad_norm": 0.3500742018222809, | |
| "learning_rate": 0.00039405944055944053, | |
| "loss": 3.2247, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 17.181150978564773, | |
| "eval_accuracy": 0.37181478748475616, | |
| "eval_loss": 3.5555620193481445, | |
| "eval_runtime": 53.7354, | |
| "eval_samples_per_second": 309.74, | |
| "eval_steps_per_second": 19.373, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 17.195712954333644, | |
| "grad_norm": 0.36379897594451904, | |
| "learning_rate": 0.0003938846153846154, | |
| "loss": 3.2339, | |
| "step": 59050 | |
| }, | |
| { | |
| "epoch": 17.210274930102518, | |
| "grad_norm": 0.4176549017429352, | |
| "learning_rate": 0.0003937097902097902, | |
| "loss": 3.235, | |
| "step": 59100 | |
| }, | |
| { | |
| "epoch": 17.22483690587139, | |
| "grad_norm": 0.3799380958080292, | |
| "learning_rate": 0.00039353496503496504, | |
| "loss": 3.2303, | |
| "step": 59150 | |
| }, | |
| { | |
| "epoch": 17.239398881640263, | |
| "grad_norm": 0.3564260005950928, | |
| "learning_rate": 0.0003933601398601398, | |
| "loss": 3.2433, | |
| "step": 59200 | |
| }, | |
| { | |
| "epoch": 17.253960857409133, | |
| "grad_norm": 0.3839263319969177, | |
| "learning_rate": 0.00039318531468531464, | |
| "loss": 3.2311, | |
| "step": 59250 | |
| }, | |
| { | |
| "epoch": 17.268522833178004, | |
| "grad_norm": 0.3948262929916382, | |
| "learning_rate": 0.00039301048951048944, | |
| "loss": 3.246, | |
| "step": 59300 | |
| }, | |
| { | |
| "epoch": 17.283084808946878, | |
| "grad_norm": 0.3694395124912262, | |
| "learning_rate": 0.0003928356643356643, | |
| "loss": 3.2422, | |
| "step": 59350 | |
| }, | |
| { | |
| "epoch": 17.29764678471575, | |
| "grad_norm": 0.3637319803237915, | |
| "learning_rate": 0.0003926608391608391, | |
| "loss": 3.2391, | |
| "step": 59400 | |
| }, | |
| { | |
| "epoch": 17.312208760484623, | |
| "grad_norm": 0.3916648030281067, | |
| "learning_rate": 0.00039248601398601395, | |
| "loss": 3.2335, | |
| "step": 59450 | |
| }, | |
| { | |
| "epoch": 17.326770736253494, | |
| "grad_norm": 0.3760225474834442, | |
| "learning_rate": 0.00039231118881118875, | |
| "loss": 3.2372, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 17.341332712022368, | |
| "grad_norm": 0.3617111146450043, | |
| "learning_rate": 0.0003921363636363636, | |
| "loss": 3.2481, | |
| "step": 59550 | |
| }, | |
| { | |
| "epoch": 17.35589468779124, | |
| "grad_norm": 0.37129026651382446, | |
| "learning_rate": 0.00039196153846153846, | |
| "loss": 3.2402, | |
| "step": 59600 | |
| }, | |
| { | |
| "epoch": 17.370456663560113, | |
| "grad_norm": 0.3965758681297302, | |
| "learning_rate": 0.00039178671328671326, | |
| "loss": 3.2444, | |
| "step": 59650 | |
| }, | |
| { | |
| "epoch": 17.385018639328983, | |
| "grad_norm": 0.37022677063941956, | |
| "learning_rate": 0.0003916118881118881, | |
| "loss": 3.2543, | |
| "step": 59700 | |
| }, | |
| { | |
| "epoch": 17.399580615097857, | |
| "grad_norm": 0.378451406955719, | |
| "learning_rate": 0.0003914370629370629, | |
| "loss": 3.2477, | |
| "step": 59750 | |
| }, | |
| { | |
| "epoch": 17.414142590866728, | |
| "grad_norm": 0.37330615520477295, | |
| "learning_rate": 0.00039126223776223776, | |
| "loss": 3.2527, | |
| "step": 59800 | |
| }, | |
| { | |
| "epoch": 17.428704566635602, | |
| "grad_norm": 0.4043675363063812, | |
| "learning_rate": 0.00039108741258741256, | |
| "loss": 3.2679, | |
| "step": 59850 | |
| }, | |
| { | |
| "epoch": 17.443266542404473, | |
| "grad_norm": 0.4179072082042694, | |
| "learning_rate": 0.0003909125874125874, | |
| "loss": 3.2596, | |
| "step": 59900 | |
| }, | |
| { | |
| "epoch": 17.457828518173347, | |
| "grad_norm": 0.3811803460121155, | |
| "learning_rate": 0.00039073776223776216, | |
| "loss": 3.2562, | |
| "step": 59950 | |
| }, | |
| { | |
| "epoch": 17.472390493942218, | |
| "grad_norm": 0.35742607712745667, | |
| "learning_rate": 0.000390562937062937, | |
| "loss": 3.2549, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 17.472390493942218, | |
| "eval_accuracy": 0.3721059074783976, | |
| "eval_loss": 3.546649932861328, | |
| "eval_runtime": 53.6803, | |
| "eval_samples_per_second": 310.058, | |
| "eval_steps_per_second": 19.393, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 17.486952469711092, | |
| "grad_norm": 0.3788129687309265, | |
| "learning_rate": 0.0003903881118881118, | |
| "loss": 3.255, | |
| "step": 60050 | |
| }, | |
| { | |
| "epoch": 17.501514445479962, | |
| "grad_norm": 0.3589966297149658, | |
| "learning_rate": 0.00039021328671328667, | |
| "loss": 3.2656, | |
| "step": 60100 | |
| }, | |
| { | |
| "epoch": 17.516076421248837, | |
| "grad_norm": 0.3915586471557617, | |
| "learning_rate": 0.00039003846153846147, | |
| "loss": 3.2637, | |
| "step": 60150 | |
| }, | |
| { | |
| "epoch": 17.530638397017707, | |
| "grad_norm": 0.4009389281272888, | |
| "learning_rate": 0.0003898636363636363, | |
| "loss": 3.252, | |
| "step": 60200 | |
| }, | |
| { | |
| "epoch": 17.54520037278658, | |
| "grad_norm": 0.364738404750824, | |
| "learning_rate": 0.0003896888111888111, | |
| "loss": 3.2702, | |
| "step": 60250 | |
| }, | |
| { | |
| "epoch": 17.559762348555452, | |
| "grad_norm": 0.37006139755249023, | |
| "learning_rate": 0.000389513986013986, | |
| "loss": 3.2781, | |
| "step": 60300 | |
| }, | |
| { | |
| "epoch": 17.574324324324323, | |
| "grad_norm": 0.35005587339401245, | |
| "learning_rate": 0.00038933916083916083, | |
| "loss": 3.2608, | |
| "step": 60350 | |
| }, | |
| { | |
| "epoch": 17.588886300093197, | |
| "grad_norm": 0.3852754831314087, | |
| "learning_rate": 0.00038916433566433563, | |
| "loss": 3.2687, | |
| "step": 60400 | |
| }, | |
| { | |
| "epoch": 17.603448275862068, | |
| "grad_norm": 0.37562867999076843, | |
| "learning_rate": 0.0003889895104895105, | |
| "loss": 3.2753, | |
| "step": 60450 | |
| }, | |
| { | |
| "epoch": 17.618010251630942, | |
| "grad_norm": 0.37529560923576355, | |
| "learning_rate": 0.0003888146853146853, | |
| "loss": 3.2747, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 17.632572227399812, | |
| "grad_norm": 0.3818197548389435, | |
| "learning_rate": 0.00038863986013986014, | |
| "loss": 3.268, | |
| "step": 60550 | |
| }, | |
| { | |
| "epoch": 17.647134203168687, | |
| "grad_norm": 0.395130455493927, | |
| "learning_rate": 0.00038846503496503494, | |
| "loss": 3.2721, | |
| "step": 60600 | |
| }, | |
| { | |
| "epoch": 17.661696178937557, | |
| "grad_norm": 0.3846796751022339, | |
| "learning_rate": 0.0003882902097902098, | |
| "loss": 3.2643, | |
| "step": 60650 | |
| }, | |
| { | |
| "epoch": 17.67625815470643, | |
| "grad_norm": 0.3665049970149994, | |
| "learning_rate": 0.00038811538461538454, | |
| "loss": 3.28, | |
| "step": 60700 | |
| }, | |
| { | |
| "epoch": 17.690820130475302, | |
| "grad_norm": 0.3482495844364166, | |
| "learning_rate": 0.0003879405594405594, | |
| "loss": 3.2701, | |
| "step": 60750 | |
| }, | |
| { | |
| "epoch": 17.705382106244176, | |
| "grad_norm": 0.36692333221435547, | |
| "learning_rate": 0.0003877657342657342, | |
| "loss": 3.2761, | |
| "step": 60800 | |
| }, | |
| { | |
| "epoch": 17.719944082013047, | |
| "grad_norm": 0.3555540144443512, | |
| "learning_rate": 0.00038759090909090905, | |
| "loss": 3.2739, | |
| "step": 60850 | |
| }, | |
| { | |
| "epoch": 17.73450605778192, | |
| "grad_norm": 0.3915589451789856, | |
| "learning_rate": 0.00038741608391608384, | |
| "loss": 3.2764, | |
| "step": 60900 | |
| }, | |
| { | |
| "epoch": 17.74906803355079, | |
| "grad_norm": 0.38231101632118225, | |
| "learning_rate": 0.0003872412587412587, | |
| "loss": 3.2891, | |
| "step": 60950 | |
| }, | |
| { | |
| "epoch": 17.763630009319666, | |
| "grad_norm": 0.3909893333911896, | |
| "learning_rate": 0.00038706643356643355, | |
| "loss": 3.2807, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 17.763630009319666, | |
| "eval_accuracy": 0.3726736855273857, | |
| "eval_loss": 3.5406863689422607, | |
| "eval_runtime": 53.8444, | |
| "eval_samples_per_second": 309.113, | |
| "eval_steps_per_second": 19.333, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 17.778191985088537, | |
| "grad_norm": 0.37381458282470703, | |
| "learning_rate": 0.00038689160839160835, | |
| "loss": 3.2855, | |
| "step": 61050 | |
| }, | |
| { | |
| "epoch": 17.79275396085741, | |
| "grad_norm": 0.36098214983940125, | |
| "learning_rate": 0.0003867167832167832, | |
| "loss": 3.2747, | |
| "step": 61100 | |
| }, | |
| { | |
| "epoch": 17.80731593662628, | |
| "grad_norm": 0.3577144742012024, | |
| "learning_rate": 0.000386541958041958, | |
| "loss": 3.275, | |
| "step": 61150 | |
| }, | |
| { | |
| "epoch": 17.821877912395152, | |
| "grad_norm": 0.3942639231681824, | |
| "learning_rate": 0.00038636713286713286, | |
| "loss": 3.2853, | |
| "step": 61200 | |
| }, | |
| { | |
| "epoch": 17.836439888164026, | |
| "grad_norm": 0.39560213685035706, | |
| "learning_rate": 0.00038619230769230766, | |
| "loss": 3.2937, | |
| "step": 61250 | |
| }, | |
| { | |
| "epoch": 17.851001863932897, | |
| "grad_norm": 0.37834152579307556, | |
| "learning_rate": 0.0003860174825174825, | |
| "loss": 3.2795, | |
| "step": 61300 | |
| }, | |
| { | |
| "epoch": 17.86556383970177, | |
| "grad_norm": 0.37762266397476196, | |
| "learning_rate": 0.0003858426573426573, | |
| "loss": 3.2938, | |
| "step": 61350 | |
| }, | |
| { | |
| "epoch": 17.88012581547064, | |
| "grad_norm": 0.38189753890037537, | |
| "learning_rate": 0.00038566783216783217, | |
| "loss": 3.2825, | |
| "step": 61400 | |
| }, | |
| { | |
| "epoch": 17.894687791239516, | |
| "grad_norm": 0.3447355031967163, | |
| "learning_rate": 0.0003854930069930069, | |
| "loss": 3.281, | |
| "step": 61450 | |
| }, | |
| { | |
| "epoch": 17.909249767008387, | |
| "grad_norm": 0.37258729338645935, | |
| "learning_rate": 0.00038531818181818177, | |
| "loss": 3.2896, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 17.92381174277726, | |
| "grad_norm": 0.3561316728591919, | |
| "learning_rate": 0.00038514335664335657, | |
| "loss": 3.2814, | |
| "step": 61550 | |
| }, | |
| { | |
| "epoch": 17.93837371854613, | |
| "grad_norm": 0.38559871912002563, | |
| "learning_rate": 0.0003849685314685314, | |
| "loss": 3.2816, | |
| "step": 61600 | |
| }, | |
| { | |
| "epoch": 17.952935694315006, | |
| "grad_norm": 0.37410980463027954, | |
| "learning_rate": 0.0003847937062937062, | |
| "loss": 3.2903, | |
| "step": 61650 | |
| }, | |
| { | |
| "epoch": 17.967497670083876, | |
| "grad_norm": 0.3895050287246704, | |
| "learning_rate": 0.0003846188811188811, | |
| "loss": 3.2849, | |
| "step": 61700 | |
| }, | |
| { | |
| "epoch": 17.98205964585275, | |
| "grad_norm": 0.36890658736228943, | |
| "learning_rate": 0.00038444405594405593, | |
| "loss": 3.2858, | |
| "step": 61750 | |
| }, | |
| { | |
| "epoch": 17.99662162162162, | |
| "grad_norm": 0.37519824504852295, | |
| "learning_rate": 0.00038426923076923073, | |
| "loss": 3.2881, | |
| "step": 61800 | |
| }, | |
| { | |
| "epoch": 18.01106710158434, | |
| "grad_norm": 0.3875732719898224, | |
| "learning_rate": 0.0003840944055944056, | |
| "loss": 3.2087, | |
| "step": 61850 | |
| }, | |
| { | |
| "epoch": 18.025629077353216, | |
| "grad_norm": 0.38909807801246643, | |
| "learning_rate": 0.0003839195804195804, | |
| "loss": 3.1766, | |
| "step": 61900 | |
| }, | |
| { | |
| "epoch": 18.040191053122086, | |
| "grad_norm": 0.37911364436149597, | |
| "learning_rate": 0.00038374475524475523, | |
| "loss": 3.1851, | |
| "step": 61950 | |
| }, | |
| { | |
| "epoch": 18.05475302889096, | |
| "grad_norm": 0.38040152192115784, | |
| "learning_rate": 0.00038356993006993003, | |
| "loss": 3.1888, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 18.05475302889096, | |
| "eval_accuracy": 0.3723371809143802, | |
| "eval_loss": 3.5530009269714355, | |
| "eval_runtime": 53.6091, | |
| "eval_samples_per_second": 310.47, | |
| "eval_steps_per_second": 19.418, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 18.06931500465983, | |
| "grad_norm": 0.38925114274024963, | |
| "learning_rate": 0.0003833951048951049, | |
| "loss": 3.2002, | |
| "step": 62050 | |
| }, | |
| { | |
| "epoch": 18.083876980428705, | |
| "grad_norm": 0.3732377886772156, | |
| "learning_rate": 0.0003832202797202797, | |
| "loss": 3.1865, | |
| "step": 62100 | |
| }, | |
| { | |
| "epoch": 18.098438956197576, | |
| "grad_norm": 0.36380213499069214, | |
| "learning_rate": 0.00038304545454545454, | |
| "loss": 3.2032, | |
| "step": 62150 | |
| }, | |
| { | |
| "epoch": 18.11300093196645, | |
| "grad_norm": 0.40389272570610046, | |
| "learning_rate": 0.0003828706293706293, | |
| "loss": 3.1982, | |
| "step": 62200 | |
| }, | |
| { | |
| "epoch": 18.12756290773532, | |
| "grad_norm": 0.3760923445224762, | |
| "learning_rate": 0.00038269580419580414, | |
| "loss": 3.1936, | |
| "step": 62250 | |
| }, | |
| { | |
| "epoch": 18.142124883504195, | |
| "grad_norm": 0.4106809198856354, | |
| "learning_rate": 0.00038252097902097894, | |
| "loss": 3.2135, | |
| "step": 62300 | |
| }, | |
| { | |
| "epoch": 18.156686859273066, | |
| "grad_norm": 0.38382473587989807, | |
| "learning_rate": 0.0003823461538461538, | |
| "loss": 3.2054, | |
| "step": 62350 | |
| }, | |
| { | |
| "epoch": 18.17124883504194, | |
| "grad_norm": 0.3982684314250946, | |
| "learning_rate": 0.00038217132867132865, | |
| "loss": 3.208, | |
| "step": 62400 | |
| }, | |
| { | |
| "epoch": 18.18581081081081, | |
| "grad_norm": 0.3854241669178009, | |
| "learning_rate": 0.00038199650349650345, | |
| "loss": 3.2146, | |
| "step": 62450 | |
| }, | |
| { | |
| "epoch": 18.200372786579685, | |
| "grad_norm": 0.3876630663871765, | |
| "learning_rate": 0.0003818216783216783, | |
| "loss": 3.2161, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 18.214934762348555, | |
| "grad_norm": 0.3796238303184509, | |
| "learning_rate": 0.0003816468531468531, | |
| "loss": 3.2252, | |
| "step": 62550 | |
| }, | |
| { | |
| "epoch": 18.229496738117426, | |
| "grad_norm": 0.38117191195487976, | |
| "learning_rate": 0.00038147202797202796, | |
| "loss": 3.2236, | |
| "step": 62600 | |
| }, | |
| { | |
| "epoch": 18.2440587138863, | |
| "grad_norm": 0.4064529240131378, | |
| "learning_rate": 0.00038129720279720276, | |
| "loss": 3.2123, | |
| "step": 62650 | |
| }, | |
| { | |
| "epoch": 18.25862068965517, | |
| "grad_norm": 0.3822717070579529, | |
| "learning_rate": 0.0003811223776223776, | |
| "loss": 3.2287, | |
| "step": 62700 | |
| }, | |
| { | |
| "epoch": 18.273182665424045, | |
| "grad_norm": 0.4065398573875427, | |
| "learning_rate": 0.0003809475524475524, | |
| "loss": 3.2333, | |
| "step": 62750 | |
| }, | |
| { | |
| "epoch": 18.287744641192916, | |
| "grad_norm": 0.35962507128715515, | |
| "learning_rate": 0.00038077272727272726, | |
| "loss": 3.2236, | |
| "step": 62800 | |
| }, | |
| { | |
| "epoch": 18.30230661696179, | |
| "grad_norm": 0.3704201281070709, | |
| "learning_rate": 0.00038059790209790206, | |
| "loss": 3.2315, | |
| "step": 62850 | |
| }, | |
| { | |
| "epoch": 18.31686859273066, | |
| "grad_norm": 0.36879655718803406, | |
| "learning_rate": 0.0003804230769230769, | |
| "loss": 3.2353, | |
| "step": 62900 | |
| }, | |
| { | |
| "epoch": 18.331430568499535, | |
| "grad_norm": 0.37170055508613586, | |
| "learning_rate": 0.00038024825174825166, | |
| "loss": 3.2381, | |
| "step": 62950 | |
| }, | |
| { | |
| "epoch": 18.345992544268405, | |
| "grad_norm": 0.3680242896080017, | |
| "learning_rate": 0.0003800734265734265, | |
| "loss": 3.2371, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 18.345992544268405, | |
| "eval_accuracy": 0.37224582379198135, | |
| "eval_loss": 3.550691843032837, | |
| "eval_runtime": 53.6468, | |
| "eval_samples_per_second": 310.251, | |
| "eval_steps_per_second": 19.405, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 18.36055452003728, | |
| "grad_norm": 0.355370432138443, | |
| "learning_rate": 0.0003798986013986013, | |
| "loss": 3.2253, | |
| "step": 63050 | |
| }, | |
| { | |
| "epoch": 18.37511649580615, | |
| "grad_norm": 0.4078480303287506, | |
| "learning_rate": 0.00037972377622377617, | |
| "loss": 3.2362, | |
| "step": 63100 | |
| }, | |
| { | |
| "epoch": 18.389678471575024, | |
| "grad_norm": 0.3773263394832611, | |
| "learning_rate": 0.000379548951048951, | |
| "loss": 3.2418, | |
| "step": 63150 | |
| }, | |
| { | |
| "epoch": 18.404240447343895, | |
| "grad_norm": 0.3944302499294281, | |
| "learning_rate": 0.0003793741258741258, | |
| "loss": 3.2532, | |
| "step": 63200 | |
| }, | |
| { | |
| "epoch": 18.41880242311277, | |
| "grad_norm": 0.39704012870788574, | |
| "learning_rate": 0.0003791993006993007, | |
| "loss": 3.2447, | |
| "step": 63250 | |
| }, | |
| { | |
| "epoch": 18.43336439888164, | |
| "grad_norm": 0.36326536536216736, | |
| "learning_rate": 0.0003790244755244755, | |
| "loss": 3.2419, | |
| "step": 63300 | |
| }, | |
| { | |
| "epoch": 18.447926374650514, | |
| "grad_norm": 0.3721631169319153, | |
| "learning_rate": 0.00037884965034965033, | |
| "loss": 3.2484, | |
| "step": 63350 | |
| }, | |
| { | |
| "epoch": 18.462488350419385, | |
| "grad_norm": 0.39378708600997925, | |
| "learning_rate": 0.00037867482517482513, | |
| "loss": 3.2457, | |
| "step": 63400 | |
| }, | |
| { | |
| "epoch": 18.47705032618826, | |
| "grad_norm": 0.3788743019104004, | |
| "learning_rate": 0.0003785, | |
| "loss": 3.2521, | |
| "step": 63450 | |
| }, | |
| { | |
| "epoch": 18.49161230195713, | |
| "grad_norm": 0.3708218038082123, | |
| "learning_rate": 0.0003783251748251748, | |
| "loss": 3.263, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 18.506174277726004, | |
| "grad_norm": 0.37706801295280457, | |
| "learning_rate": 0.00037815034965034964, | |
| "loss": 3.247, | |
| "step": 63550 | |
| }, | |
| { | |
| "epoch": 18.520736253494874, | |
| "grad_norm": 0.4102998971939087, | |
| "learning_rate": 0.00037797552447552444, | |
| "loss": 3.2465, | |
| "step": 63600 | |
| }, | |
| { | |
| "epoch": 18.535298229263745, | |
| "grad_norm": 0.41490569710731506, | |
| "learning_rate": 0.0003778006993006993, | |
| "loss": 3.2588, | |
| "step": 63650 | |
| }, | |
| { | |
| "epoch": 18.54986020503262, | |
| "grad_norm": 0.3888053894042969, | |
| "learning_rate": 0.00037762587412587404, | |
| "loss": 3.254, | |
| "step": 63700 | |
| }, | |
| { | |
| "epoch": 18.56442218080149, | |
| "grad_norm": 0.4218922257423401, | |
| "learning_rate": 0.0003774510489510489, | |
| "loss": 3.2644, | |
| "step": 63750 | |
| }, | |
| { | |
| "epoch": 18.578984156570364, | |
| "grad_norm": 0.3588375747203827, | |
| "learning_rate": 0.0003772762237762238, | |
| "loss": 3.258, | |
| "step": 63800 | |
| }, | |
| { | |
| "epoch": 18.593546132339235, | |
| "grad_norm": 0.3538081645965576, | |
| "learning_rate": 0.00037710139860139854, | |
| "loss": 3.263, | |
| "step": 63850 | |
| }, | |
| { | |
| "epoch": 18.60810810810811, | |
| "grad_norm": 0.38032105565071106, | |
| "learning_rate": 0.0003769265734265734, | |
| "loss": 3.2679, | |
| "step": 63900 | |
| }, | |
| { | |
| "epoch": 18.62267008387698, | |
| "grad_norm": 0.37946024537086487, | |
| "learning_rate": 0.0003767517482517482, | |
| "loss": 3.2503, | |
| "step": 63950 | |
| }, | |
| { | |
| "epoch": 18.637232059645854, | |
| "grad_norm": 0.37310442328453064, | |
| "learning_rate": 0.00037657692307692305, | |
| "loss": 3.2615, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 18.637232059645854, | |
| "eval_accuracy": 0.37308696774776123, | |
| "eval_loss": 3.542891025543213, | |
| "eval_runtime": 53.6472, | |
| "eval_samples_per_second": 310.249, | |
| "eval_steps_per_second": 19.405, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 18.651794035414724, | |
| "grad_norm": 0.3829942047595978, | |
| "learning_rate": 0.00037640209790209785, | |
| "loss": 3.2537, | |
| "step": 64050 | |
| }, | |
| { | |
| "epoch": 18.6663560111836, | |
| "grad_norm": 0.38445472717285156, | |
| "learning_rate": 0.0003762272727272727, | |
| "loss": 3.2592, | |
| "step": 64100 | |
| }, | |
| { | |
| "epoch": 18.68091798695247, | |
| "grad_norm": 0.3823604881763458, | |
| "learning_rate": 0.0003760524475524475, | |
| "loss": 3.2438, | |
| "step": 64150 | |
| }, | |
| { | |
| "epoch": 18.695479962721343, | |
| "grad_norm": 0.3722836673259735, | |
| "learning_rate": 0.00037587762237762236, | |
| "loss": 3.2596, | |
| "step": 64200 | |
| }, | |
| { | |
| "epoch": 18.710041938490214, | |
| "grad_norm": 0.35490530729293823, | |
| "learning_rate": 0.00037570279720279716, | |
| "loss": 3.2636, | |
| "step": 64250 | |
| }, | |
| { | |
| "epoch": 18.724603914259088, | |
| "grad_norm": 0.36468833684921265, | |
| "learning_rate": 0.000375527972027972, | |
| "loss": 3.269, | |
| "step": 64300 | |
| }, | |
| { | |
| "epoch": 18.73916589002796, | |
| "grad_norm": 0.3716800808906555, | |
| "learning_rate": 0.0003753531468531468, | |
| "loss": 3.268, | |
| "step": 64350 | |
| }, | |
| { | |
| "epoch": 18.753727865796833, | |
| "grad_norm": 0.3842315077781677, | |
| "learning_rate": 0.00037517832167832167, | |
| "loss": 3.2724, | |
| "step": 64400 | |
| }, | |
| { | |
| "epoch": 18.768289841565704, | |
| "grad_norm": 0.4173533320426941, | |
| "learning_rate": 0.0003750034965034965, | |
| "loss": 3.2614, | |
| "step": 64450 | |
| }, | |
| { | |
| "epoch": 18.782851817334574, | |
| "grad_norm": 0.36763879656791687, | |
| "learning_rate": 0.00037482867132867127, | |
| "loss": 3.2677, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 18.79741379310345, | |
| "grad_norm": 0.3957614600658417, | |
| "learning_rate": 0.0003746538461538462, | |
| "loss": 3.2671, | |
| "step": 64550 | |
| }, | |
| { | |
| "epoch": 18.81197576887232, | |
| "grad_norm": 0.37960317730903625, | |
| "learning_rate": 0.0003744790209790209, | |
| "loss": 3.2856, | |
| "step": 64600 | |
| }, | |
| { | |
| "epoch": 18.826537744641193, | |
| "grad_norm": 0.3816615045070648, | |
| "learning_rate": 0.0003743041958041958, | |
| "loss": 3.2665, | |
| "step": 64650 | |
| }, | |
| { | |
| "epoch": 18.841099720410064, | |
| "grad_norm": 0.34941965341567993, | |
| "learning_rate": 0.0003741293706293706, | |
| "loss": 3.2813, | |
| "step": 64700 | |
| }, | |
| { | |
| "epoch": 18.855661696178938, | |
| "grad_norm": 0.411423921585083, | |
| "learning_rate": 0.0003739545454545454, | |
| "loss": 3.2731, | |
| "step": 64750 | |
| }, | |
| { | |
| "epoch": 18.87022367194781, | |
| "grad_norm": 0.368845671415329, | |
| "learning_rate": 0.0003737797202797202, | |
| "loss": 3.2698, | |
| "step": 64800 | |
| }, | |
| { | |
| "epoch": 18.884785647716683, | |
| "grad_norm": 0.41026976704597473, | |
| "learning_rate": 0.0003736048951048951, | |
| "loss": 3.2827, | |
| "step": 64850 | |
| }, | |
| { | |
| "epoch": 18.899347623485554, | |
| "grad_norm": 0.34741586446762085, | |
| "learning_rate": 0.0003734300699300699, | |
| "loss": 3.2883, | |
| "step": 64900 | |
| }, | |
| { | |
| "epoch": 18.913909599254428, | |
| "grad_norm": 0.36796513199806213, | |
| "learning_rate": 0.00037325524475524473, | |
| "loss": 3.2757, | |
| "step": 64950 | |
| }, | |
| { | |
| "epoch": 18.9284715750233, | |
| "grad_norm": 0.4108026921749115, | |
| "learning_rate": 0.00037308041958041953, | |
| "loss": 3.2662, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 18.9284715750233, | |
| "eval_accuracy": 0.37334457837218304, | |
| "eval_loss": 3.5351333618164062, | |
| "eval_runtime": 53.5478, | |
| "eval_samples_per_second": 310.825, | |
| "eval_steps_per_second": 19.441, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 18.943033550792173, | |
| "grad_norm": 0.35917073488235474, | |
| "learning_rate": 0.0003729055944055944, | |
| "loss": 3.2701, | |
| "step": 65050 | |
| }, | |
| { | |
| "epoch": 18.957595526561043, | |
| "grad_norm": 0.35945555567741394, | |
| "learning_rate": 0.0003727307692307692, | |
| "loss": 3.2814, | |
| "step": 65100 | |
| }, | |
| { | |
| "epoch": 18.972157502329917, | |
| "grad_norm": 0.37766772508621216, | |
| "learning_rate": 0.00037255594405594404, | |
| "loss": 3.2783, | |
| "step": 65150 | |
| }, | |
| { | |
| "epoch": 18.986719478098788, | |
| "grad_norm": 0.3846476078033447, | |
| "learning_rate": 0.0003723811188811189, | |
| "loss": 3.2838, | |
| "step": 65200 | |
| }, | |
| { | |
| "epoch": 19.00116495806151, | |
| "grad_norm": 0.41956663131713867, | |
| "learning_rate": 0.00037220629370629364, | |
| "loss": 3.2632, | |
| "step": 65250 | |
| }, | |
| { | |
| "epoch": 19.015726933830383, | |
| "grad_norm": 0.3777720630168915, | |
| "learning_rate": 0.00037203146853146855, | |
| "loss": 3.1728, | |
| "step": 65300 | |
| }, | |
| { | |
| "epoch": 19.030288909599253, | |
| "grad_norm": 0.36135587096214294, | |
| "learning_rate": 0.0003718566433566433, | |
| "loss": 3.178, | |
| "step": 65350 | |
| }, | |
| { | |
| "epoch": 19.044850885368128, | |
| "grad_norm": 0.3920912742614746, | |
| "learning_rate": 0.00037168181818181815, | |
| "loss": 3.1806, | |
| "step": 65400 | |
| }, | |
| { | |
| "epoch": 19.059412861136998, | |
| "grad_norm": 0.39687469601631165, | |
| "learning_rate": 0.00037150699300699295, | |
| "loss": 3.1745, | |
| "step": 65450 | |
| }, | |
| { | |
| "epoch": 19.073974836905872, | |
| "grad_norm": 0.39901939034461975, | |
| "learning_rate": 0.0003713321678321678, | |
| "loss": 3.1879, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 19.088536812674743, | |
| "grad_norm": 0.37469103932380676, | |
| "learning_rate": 0.0003711573426573426, | |
| "loss": 3.1825, | |
| "step": 65550 | |
| }, | |
| { | |
| "epoch": 19.103098788443617, | |
| "grad_norm": 0.40531569719314575, | |
| "learning_rate": 0.00037098251748251746, | |
| "loss": 3.1891, | |
| "step": 65600 | |
| }, | |
| { | |
| "epoch": 19.117660764212488, | |
| "grad_norm": 0.39202824234962463, | |
| "learning_rate": 0.00037080769230769226, | |
| "loss": 3.2018, | |
| "step": 65650 | |
| }, | |
| { | |
| "epoch": 19.132222739981362, | |
| "grad_norm": 0.37663426995277405, | |
| "learning_rate": 0.0003706328671328671, | |
| "loss": 3.1906, | |
| "step": 65700 | |
| }, | |
| { | |
| "epoch": 19.146784715750233, | |
| "grad_norm": 0.37909311056137085, | |
| "learning_rate": 0.0003704580419580419, | |
| "loss": 3.2038, | |
| "step": 65750 | |
| }, | |
| { | |
| "epoch": 19.161346691519107, | |
| "grad_norm": 0.3874996602535248, | |
| "learning_rate": 0.00037028321678321676, | |
| "loss": 3.2037, | |
| "step": 65800 | |
| }, | |
| { | |
| "epoch": 19.175908667287977, | |
| "grad_norm": 0.4042704701423645, | |
| "learning_rate": 0.0003701083916083916, | |
| "loss": 3.1917, | |
| "step": 65850 | |
| }, | |
| { | |
| "epoch": 19.19047064305685, | |
| "grad_norm": 0.3726341128349304, | |
| "learning_rate": 0.0003699335664335664, | |
| "loss": 3.2, | |
| "step": 65900 | |
| }, | |
| { | |
| "epoch": 19.205032618825722, | |
| "grad_norm": 0.4252948462963104, | |
| "learning_rate": 0.00036975874125874127, | |
| "loss": 3.2133, | |
| "step": 65950 | |
| }, | |
| { | |
| "epoch": 19.219594594594593, | |
| "grad_norm": 0.3802109360694885, | |
| "learning_rate": 0.00036958391608391607, | |
| "loss": 3.2062, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 19.219594594594593, | |
| "eval_accuracy": 0.3728054890463163, | |
| "eval_loss": 3.5497379302978516, | |
| "eval_runtime": 53.6654, | |
| "eval_samples_per_second": 310.144, | |
| "eval_steps_per_second": 19.398, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 19.234156570363467, | |
| "grad_norm": 0.4133206307888031, | |
| "learning_rate": 0.0003694090909090909, | |
| "loss": 3.2076, | |
| "step": 66050 | |
| }, | |
| { | |
| "epoch": 19.248718546132338, | |
| "grad_norm": 0.38479116559028625, | |
| "learning_rate": 0.00036923426573426567, | |
| "loss": 3.2175, | |
| "step": 66100 | |
| }, | |
| { | |
| "epoch": 19.263280521901212, | |
| "grad_norm": 0.41108012199401855, | |
| "learning_rate": 0.0003690594405594405, | |
| "loss": 3.2145, | |
| "step": 66150 | |
| }, | |
| { | |
| "epoch": 19.277842497670083, | |
| "grad_norm": 0.4138273596763611, | |
| "learning_rate": 0.0003688846153846153, | |
| "loss": 3.2205, | |
| "step": 66200 | |
| }, | |
| { | |
| "epoch": 19.292404473438957, | |
| "grad_norm": 0.37386050820350647, | |
| "learning_rate": 0.0003687097902097902, | |
| "loss": 3.2188, | |
| "step": 66250 | |
| }, | |
| { | |
| "epoch": 19.306966449207827, | |
| "grad_norm": 0.3839118182659149, | |
| "learning_rate": 0.000368534965034965, | |
| "loss": 3.2226, | |
| "step": 66300 | |
| }, | |
| { | |
| "epoch": 19.3215284249767, | |
| "grad_norm": 0.40011078119277954, | |
| "learning_rate": 0.00036836013986013983, | |
| "loss": 3.2172, | |
| "step": 66350 | |
| }, | |
| { | |
| "epoch": 19.336090400745572, | |
| "grad_norm": 0.3948891758918762, | |
| "learning_rate": 0.00036818531468531463, | |
| "loss": 3.2176, | |
| "step": 66400 | |
| }, | |
| { | |
| "epoch": 19.350652376514446, | |
| "grad_norm": 0.36948251724243164, | |
| "learning_rate": 0.0003680104895104895, | |
| "loss": 3.2251, | |
| "step": 66450 | |
| }, | |
| { | |
| "epoch": 19.365214352283317, | |
| "grad_norm": 0.3812604546546936, | |
| "learning_rate": 0.0003678356643356643, | |
| "loss": 3.2263, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 19.37977632805219, | |
| "grad_norm": 0.4402337074279785, | |
| "learning_rate": 0.00036766083916083914, | |
| "loss": 3.233, | |
| "step": 66550 | |
| }, | |
| { | |
| "epoch": 19.394338303821062, | |
| "grad_norm": 0.3661404550075531, | |
| "learning_rate": 0.000367486013986014, | |
| "loss": 3.2324, | |
| "step": 66600 | |
| }, | |
| { | |
| "epoch": 19.408900279589936, | |
| "grad_norm": 0.362842857837677, | |
| "learning_rate": 0.0003673111888111888, | |
| "loss": 3.2284, | |
| "step": 66650 | |
| }, | |
| { | |
| "epoch": 19.423462255358807, | |
| "grad_norm": 0.4055345952510834, | |
| "learning_rate": 0.00036713636363636365, | |
| "loss": 3.2299, | |
| "step": 66700 | |
| }, | |
| { | |
| "epoch": 19.43802423112768, | |
| "grad_norm": 0.3992021083831787, | |
| "learning_rate": 0.00036696153846153844, | |
| "loss": 3.244, | |
| "step": 66750 | |
| }, | |
| { | |
| "epoch": 19.45258620689655, | |
| "grad_norm": 0.3800589442253113, | |
| "learning_rate": 0.0003667867132867133, | |
| "loss": 3.2337, | |
| "step": 66800 | |
| }, | |
| { | |
| "epoch": 19.467148182665426, | |
| "grad_norm": 0.3811376392841339, | |
| "learning_rate": 0.00036661188811188804, | |
| "loss": 3.2337, | |
| "step": 66850 | |
| }, | |
| { | |
| "epoch": 19.481710158434296, | |
| "grad_norm": 0.3804425597190857, | |
| "learning_rate": 0.0003664370629370629, | |
| "loss": 3.2338, | |
| "step": 66900 | |
| }, | |
| { | |
| "epoch": 19.496272134203167, | |
| "grad_norm": 0.36933010816574097, | |
| "learning_rate": 0.0003662622377622377, | |
| "loss": 3.2523, | |
| "step": 66950 | |
| }, | |
| { | |
| "epoch": 19.51083410997204, | |
| "grad_norm": 0.38615190982818604, | |
| "learning_rate": 0.00036608741258741255, | |
| "loss": 3.242, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 19.51083410997204, | |
| "eval_accuracy": 0.3726040801007962, | |
| "eval_loss": 3.5483808517456055, | |
| "eval_runtime": 53.4497, | |
| "eval_samples_per_second": 311.395, | |
| "eval_steps_per_second": 19.476, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 19.525396085740912, | |
| "grad_norm": 0.4136638641357422, | |
| "learning_rate": 0.00036591258741258735, | |
| "loss": 3.2398, | |
| "step": 67050 | |
| }, | |
| { | |
| "epoch": 19.539958061509786, | |
| "grad_norm": 0.41616570949554443, | |
| "learning_rate": 0.0003657377622377622, | |
| "loss": 3.2418, | |
| "step": 67100 | |
| }, | |
| { | |
| "epoch": 19.554520037278657, | |
| "grad_norm": 0.38881203532218933, | |
| "learning_rate": 0.000365562937062937, | |
| "loss": 3.2485, | |
| "step": 67150 | |
| }, | |
| { | |
| "epoch": 19.56908201304753, | |
| "grad_norm": 0.3823322057723999, | |
| "learning_rate": 0.00036538811188811186, | |
| "loss": 3.2523, | |
| "step": 67200 | |
| }, | |
| { | |
| "epoch": 19.5836439888164, | |
| "grad_norm": 0.40406888723373413, | |
| "learning_rate": 0.0003652132867132867, | |
| "loss": 3.2513, | |
| "step": 67250 | |
| }, | |
| { | |
| "epoch": 19.598205964585276, | |
| "grad_norm": 0.39410239458084106, | |
| "learning_rate": 0.0003650384615384615, | |
| "loss": 3.2452, | |
| "step": 67300 | |
| }, | |
| { | |
| "epoch": 19.612767940354146, | |
| "grad_norm": 0.3842507600784302, | |
| "learning_rate": 0.00036486363636363637, | |
| "loss": 3.2548, | |
| "step": 67350 | |
| }, | |
| { | |
| "epoch": 19.62732991612302, | |
| "grad_norm": 0.3869752883911133, | |
| "learning_rate": 0.00036468881118881117, | |
| "loss": 3.2466, | |
| "step": 67400 | |
| }, | |
| { | |
| "epoch": 19.64189189189189, | |
| "grad_norm": 0.41032785177230835, | |
| "learning_rate": 0.000364513986013986, | |
| "loss": 3.2446, | |
| "step": 67450 | |
| }, | |
| { | |
| "epoch": 19.656453867660765, | |
| "grad_norm": 0.38462066650390625, | |
| "learning_rate": 0.0003643391608391608, | |
| "loss": 3.2495, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 19.671015843429636, | |
| "grad_norm": 0.39043310284614563, | |
| "learning_rate": 0.0003641643356643357, | |
| "loss": 3.2456, | |
| "step": 67550 | |
| }, | |
| { | |
| "epoch": 19.68557781919851, | |
| "grad_norm": 0.40164053440093994, | |
| "learning_rate": 0.0003639895104895104, | |
| "loss": 3.2385, | |
| "step": 67600 | |
| }, | |
| { | |
| "epoch": 19.70013979496738, | |
| "grad_norm": 0.41391077637672424, | |
| "learning_rate": 0.0003638146853146853, | |
| "loss": 3.2571, | |
| "step": 67650 | |
| }, | |
| { | |
| "epoch": 19.714701770736255, | |
| "grad_norm": 0.4099098742008209, | |
| "learning_rate": 0.00036363986013986007, | |
| "loss": 3.2434, | |
| "step": 67700 | |
| }, | |
| { | |
| "epoch": 19.729263746505126, | |
| "grad_norm": 0.38578134775161743, | |
| "learning_rate": 0.0003634650349650349, | |
| "loss": 3.2451, | |
| "step": 67750 | |
| }, | |
| { | |
| "epoch": 19.743825722273996, | |
| "grad_norm": 0.37067756056785583, | |
| "learning_rate": 0.0003632902097902097, | |
| "loss": 3.2473, | |
| "step": 67800 | |
| }, | |
| { | |
| "epoch": 19.75838769804287, | |
| "grad_norm": 0.39515194296836853, | |
| "learning_rate": 0.0003631153846153846, | |
| "loss": 3.2602, | |
| "step": 67850 | |
| }, | |
| { | |
| "epoch": 19.77294967381174, | |
| "grad_norm": 0.3894272446632385, | |
| "learning_rate": 0.00036294055944055943, | |
| "loss": 3.2439, | |
| "step": 67900 | |
| }, | |
| { | |
| "epoch": 19.787511649580615, | |
| "grad_norm": 0.36319202184677124, | |
| "learning_rate": 0.00036276573426573423, | |
| "loss": 3.2531, | |
| "step": 67950 | |
| }, | |
| { | |
| "epoch": 19.802073625349486, | |
| "grad_norm": 0.3721925914287567, | |
| "learning_rate": 0.0003625909090909091, | |
| "loss": 3.2734, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 19.802073625349486, | |
| "eval_accuracy": 0.37333822922854143, | |
| "eval_loss": 3.538437604904175, | |
| "eval_runtime": 53.8392, | |
| "eval_samples_per_second": 309.143, | |
| "eval_steps_per_second": 19.335, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 19.81663560111836, | |
| "grad_norm": 0.39392781257629395, | |
| "learning_rate": 0.0003624160839160839, | |
| "loss": 3.2668, | |
| "step": 68050 | |
| }, | |
| { | |
| "epoch": 19.83119757688723, | |
| "grad_norm": 0.41753748059272766, | |
| "learning_rate": 0.00036224125874125874, | |
| "loss": 3.2599, | |
| "step": 68100 | |
| }, | |
| { | |
| "epoch": 19.845759552656105, | |
| "grad_norm": 0.39892056584358215, | |
| "learning_rate": 0.00036206643356643354, | |
| "loss": 3.2604, | |
| "step": 68150 | |
| }, | |
| { | |
| "epoch": 19.860321528424976, | |
| "grad_norm": 0.38567325472831726, | |
| "learning_rate": 0.0003618916083916084, | |
| "loss": 3.2723, | |
| "step": 68200 | |
| }, | |
| { | |
| "epoch": 19.87488350419385, | |
| "grad_norm": 0.3812924027442932, | |
| "learning_rate": 0.0003617167832167832, | |
| "loss": 3.2558, | |
| "step": 68250 | |
| }, | |
| { | |
| "epoch": 19.88944547996272, | |
| "grad_norm": 0.382830411195755, | |
| "learning_rate": 0.00036154195804195805, | |
| "loss": 3.2611, | |
| "step": 68300 | |
| }, | |
| { | |
| "epoch": 19.904007455731595, | |
| "grad_norm": 0.4037676155567169, | |
| "learning_rate": 0.0003613671328671328, | |
| "loss": 3.2651, | |
| "step": 68350 | |
| }, | |
| { | |
| "epoch": 19.918569431500465, | |
| "grad_norm": 0.37967729568481445, | |
| "learning_rate": 0.00036119230769230765, | |
| "loss": 3.2734, | |
| "step": 68400 | |
| }, | |
| { | |
| "epoch": 19.93313140726934, | |
| "grad_norm": 0.3941499590873718, | |
| "learning_rate": 0.00036101748251748245, | |
| "loss": 3.2649, | |
| "step": 68450 | |
| }, | |
| { | |
| "epoch": 19.94769338303821, | |
| "grad_norm": 0.40444591641426086, | |
| "learning_rate": 0.0003608426573426573, | |
| "loss": 3.2642, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 19.962255358807084, | |
| "grad_norm": 0.375336617231369, | |
| "learning_rate": 0.0003606678321678321, | |
| "loss": 3.2692, | |
| "step": 68550 | |
| }, | |
| { | |
| "epoch": 19.976817334575955, | |
| "grad_norm": 0.4084981083869934, | |
| "learning_rate": 0.00036049300699300696, | |
| "loss": 3.2645, | |
| "step": 68600 | |
| }, | |
| { | |
| "epoch": 19.99137931034483, | |
| "grad_norm": 0.37530145049095154, | |
| "learning_rate": 0.0003603181818181818, | |
| "loss": 3.2563, | |
| "step": 68650 | |
| }, | |
| { | |
| "epoch": 20.00582479030755, | |
| "grad_norm": 0.40279820561408997, | |
| "learning_rate": 0.0003601433566433566, | |
| "loss": 3.2205, | |
| "step": 68700 | |
| }, | |
| { | |
| "epoch": 20.02038676607642, | |
| "grad_norm": 0.3879990577697754, | |
| "learning_rate": 0.00035996853146853146, | |
| "loss": 3.1578, | |
| "step": 68750 | |
| }, | |
| { | |
| "epoch": 20.034948741845295, | |
| "grad_norm": 0.439457505941391, | |
| "learning_rate": 0.00035979370629370626, | |
| "loss": 3.1662, | |
| "step": 68800 | |
| }, | |
| { | |
| "epoch": 20.049510717614165, | |
| "grad_norm": 0.4187467694282532, | |
| "learning_rate": 0.0003596188811188811, | |
| "loss": 3.1751, | |
| "step": 68850 | |
| }, | |
| { | |
| "epoch": 20.06407269338304, | |
| "grad_norm": 0.38843098282814026, | |
| "learning_rate": 0.0003594440559440559, | |
| "loss": 3.1713, | |
| "step": 68900 | |
| }, | |
| { | |
| "epoch": 20.07863466915191, | |
| "grad_norm": 0.38127413392066956, | |
| "learning_rate": 0.00035926923076923077, | |
| "loss": 3.1732, | |
| "step": 68950 | |
| }, | |
| { | |
| "epoch": 20.093196644920784, | |
| "grad_norm": 0.42359402775764465, | |
| "learning_rate": 0.00035909440559440557, | |
| "loss": 3.1755, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 20.093196644920784, | |
| "eval_accuracy": 0.3727432909539753, | |
| "eval_loss": 3.554373025894165, | |
| "eval_runtime": 53.6419, | |
| "eval_samples_per_second": 310.28, | |
| "eval_steps_per_second": 19.406, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 20.107758620689655, | |
| "grad_norm": 0.379149854183197, | |
| "learning_rate": 0.0003589195804195804, | |
| "loss": 3.177, | |
| "step": 69050 | |
| }, | |
| { | |
| "epoch": 20.12232059645853, | |
| "grad_norm": 0.37855619192123413, | |
| "learning_rate": 0.00035874475524475517, | |
| "loss": 3.1842, | |
| "step": 69100 | |
| }, | |
| { | |
| "epoch": 20.1368825722274, | |
| "grad_norm": 0.4195460081100464, | |
| "learning_rate": 0.00035856993006993, | |
| "loss": 3.1919, | |
| "step": 69150 | |
| }, | |
| { | |
| "epoch": 20.151444547996274, | |
| "grad_norm": 0.38967326283454895, | |
| "learning_rate": 0.0003583951048951048, | |
| "loss": 3.1964, | |
| "step": 69200 | |
| }, | |
| { | |
| "epoch": 20.166006523765144, | |
| "grad_norm": 0.4318048655986786, | |
| "learning_rate": 0.0003582202797202797, | |
| "loss": 3.1925, | |
| "step": 69250 | |
| }, | |
| { | |
| "epoch": 20.180568499534015, | |
| "grad_norm": 0.39629480242729187, | |
| "learning_rate": 0.00035804545454545453, | |
| "loss": 3.205, | |
| "step": 69300 | |
| }, | |
| { | |
| "epoch": 20.19513047530289, | |
| "grad_norm": 0.3838287889957428, | |
| "learning_rate": 0.00035787062937062933, | |
| "loss": 3.1975, | |
| "step": 69350 | |
| }, | |
| { | |
| "epoch": 20.20969245107176, | |
| "grad_norm": 0.4163590967655182, | |
| "learning_rate": 0.0003576958041958042, | |
| "loss": 3.1989, | |
| "step": 69400 | |
| }, | |
| { | |
| "epoch": 20.224254426840634, | |
| "grad_norm": 0.40171295404434204, | |
| "learning_rate": 0.000357520979020979, | |
| "loss": 3.2048, | |
| "step": 69450 | |
| }, | |
| { | |
| "epoch": 20.238816402609505, | |
| "grad_norm": 0.3948460519313812, | |
| "learning_rate": 0.00035734615384615384, | |
| "loss": 3.2049, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 20.25337837837838, | |
| "grad_norm": 0.39959606528282166, | |
| "learning_rate": 0.00035717132867132864, | |
| "loss": 3.2079, | |
| "step": 69550 | |
| }, | |
| { | |
| "epoch": 20.26794035414725, | |
| "grad_norm": 0.3934629261493683, | |
| "learning_rate": 0.0003569965034965035, | |
| "loss": 3.2002, | |
| "step": 69600 | |
| }, | |
| { | |
| "epoch": 20.282502329916124, | |
| "grad_norm": 0.41200846433639526, | |
| "learning_rate": 0.0003568216783216783, | |
| "loss": 3.2036, | |
| "step": 69650 | |
| }, | |
| { | |
| "epoch": 20.297064305684994, | |
| "grad_norm": 0.41301435232162476, | |
| "learning_rate": 0.00035664685314685314, | |
| "loss": 3.2147, | |
| "step": 69700 | |
| }, | |
| { | |
| "epoch": 20.31162628145387, | |
| "grad_norm": 0.4042994976043701, | |
| "learning_rate": 0.00035647202797202794, | |
| "loss": 3.219, | |
| "step": 69750 | |
| }, | |
| { | |
| "epoch": 20.32618825722274, | |
| "grad_norm": 0.4100610613822937, | |
| "learning_rate": 0.0003562972027972028, | |
| "loss": 3.2105, | |
| "step": 69800 | |
| }, | |
| { | |
| "epoch": 20.340750232991613, | |
| "grad_norm": 0.3665405511856079, | |
| "learning_rate": 0.00035612237762237754, | |
| "loss": 3.2183, | |
| "step": 69850 | |
| }, | |
| { | |
| "epoch": 20.355312208760484, | |
| "grad_norm": 0.42888033390045166, | |
| "learning_rate": 0.0003559475524475524, | |
| "loss": 3.2236, | |
| "step": 69900 | |
| }, | |
| { | |
| "epoch": 20.36987418452936, | |
| "grad_norm": 0.3644813001155853, | |
| "learning_rate": 0.0003557727272727272, | |
| "loss": 3.2221, | |
| "step": 69950 | |
| }, | |
| { | |
| "epoch": 20.38443616029823, | |
| "grad_norm": 0.3995056450366974, | |
| "learning_rate": 0.00035559790209790205, | |
| "loss": 3.2174, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 20.38443616029823, | |
| "eval_accuracy": 0.3727511685951603, | |
| "eval_loss": 3.5511600971221924, | |
| "eval_runtime": 53.5518, | |
| "eval_samples_per_second": 310.802, | |
| "eval_steps_per_second": 19.439, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 20.398998136067103, | |
| "grad_norm": 0.37608620524406433, | |
| "learning_rate": 0.0003554230769230769, | |
| "loss": 3.2234, | |
| "step": 70050 | |
| }, | |
| { | |
| "epoch": 20.413560111835974, | |
| "grad_norm": 0.37095916271209717, | |
| "learning_rate": 0.0003552482517482517, | |
| "loss": 3.2267, | |
| "step": 70100 | |
| }, | |
| { | |
| "epoch": 20.428122087604848, | |
| "grad_norm": 0.40074586868286133, | |
| "learning_rate": 0.00035507342657342656, | |
| "loss": 3.2143, | |
| "step": 70150 | |
| }, | |
| { | |
| "epoch": 20.44268406337372, | |
| "grad_norm": 0.3774716854095459, | |
| "learning_rate": 0.00035489860139860136, | |
| "loss": 3.2161, | |
| "step": 70200 | |
| }, | |
| { | |
| "epoch": 20.45724603914259, | |
| "grad_norm": 0.38591891527175903, | |
| "learning_rate": 0.0003547237762237762, | |
| "loss": 3.2136, | |
| "step": 70250 | |
| }, | |
| { | |
| "epoch": 20.471808014911463, | |
| "grad_norm": 0.3808690011501312, | |
| "learning_rate": 0.000354548951048951, | |
| "loss": 3.2343, | |
| "step": 70300 | |
| }, | |
| { | |
| "epoch": 20.486369990680334, | |
| "grad_norm": 0.41351810097694397, | |
| "learning_rate": 0.00035437412587412587, | |
| "loss": 3.2146, | |
| "step": 70350 | |
| }, | |
| { | |
| "epoch": 20.50093196644921, | |
| "grad_norm": 0.3997446596622467, | |
| "learning_rate": 0.00035419930069930067, | |
| "loss": 3.2265, | |
| "step": 70400 | |
| }, | |
| { | |
| "epoch": 20.51549394221808, | |
| "grad_norm": 0.36297866702079773, | |
| "learning_rate": 0.0003540244755244755, | |
| "loss": 3.2354, | |
| "step": 70450 | |
| }, | |
| { | |
| "epoch": 20.530055917986953, | |
| "grad_norm": 0.38284286856651306, | |
| "learning_rate": 0.0003538496503496503, | |
| "loss": 3.2386, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 20.544617893755824, | |
| "grad_norm": 0.38133928179740906, | |
| "learning_rate": 0.0003536748251748252, | |
| "loss": 3.2329, | |
| "step": 70550 | |
| }, | |
| { | |
| "epoch": 20.559179869524698, | |
| "grad_norm": 0.385995477437973, | |
| "learning_rate": 0.0003534999999999999, | |
| "loss": 3.2371, | |
| "step": 70600 | |
| }, | |
| { | |
| "epoch": 20.57374184529357, | |
| "grad_norm": 0.4186258912086487, | |
| "learning_rate": 0.00035332517482517477, | |
| "loss": 3.2257, | |
| "step": 70650 | |
| }, | |
| { | |
| "epoch": 20.588303821062443, | |
| "grad_norm": 0.390411376953125, | |
| "learning_rate": 0.0003531503496503496, | |
| "loss": 3.2255, | |
| "step": 70700 | |
| }, | |
| { | |
| "epoch": 20.602865796831313, | |
| "grad_norm": 0.38977673649787903, | |
| "learning_rate": 0.0003529755244755244, | |
| "loss": 3.2293, | |
| "step": 70750 | |
| }, | |
| { | |
| "epoch": 20.617427772600188, | |
| "grad_norm": 0.40031591057777405, | |
| "learning_rate": 0.0003528006993006993, | |
| "loss": 3.2441, | |
| "step": 70800 | |
| }, | |
| { | |
| "epoch": 20.631989748369058, | |
| "grad_norm": 0.37329474091529846, | |
| "learning_rate": 0.0003526258741258741, | |
| "loss": 3.2423, | |
| "step": 70850 | |
| }, | |
| { | |
| "epoch": 20.646551724137932, | |
| "grad_norm": 0.4275941252708435, | |
| "learning_rate": 0.00035245104895104893, | |
| "loss": 3.2377, | |
| "step": 70900 | |
| }, | |
| { | |
| "epoch": 20.661113699906803, | |
| "grad_norm": 0.38450363278388977, | |
| "learning_rate": 0.00035227622377622373, | |
| "loss": 3.2387, | |
| "step": 70950 | |
| }, | |
| { | |
| "epoch": 20.675675675675677, | |
| "grad_norm": 0.3979182243347168, | |
| "learning_rate": 0.0003521013986013986, | |
| "loss": 3.2381, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 20.675675675675677, | |
| "eval_accuracy": 0.3735670335531078, | |
| "eval_loss": 3.5422792434692383, | |
| "eval_runtime": 53.7212, | |
| "eval_samples_per_second": 309.822, | |
| "eval_steps_per_second": 19.378, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 20.690237651444548, | |
| "grad_norm": 0.40853452682495117, | |
| "learning_rate": 0.0003519265734265734, | |
| "loss": 3.2331, | |
| "step": 71050 | |
| }, | |
| { | |
| "epoch": 20.70479962721342, | |
| "grad_norm": 0.39112091064453125, | |
| "learning_rate": 0.00035175174825174824, | |
| "loss": 3.2512, | |
| "step": 71100 | |
| }, | |
| { | |
| "epoch": 20.719361602982293, | |
| "grad_norm": 0.3723371624946594, | |
| "learning_rate": 0.00035157692307692304, | |
| "loss": 3.2462, | |
| "step": 71150 | |
| }, | |
| { | |
| "epoch": 20.733923578751163, | |
| "grad_norm": 0.42912352085113525, | |
| "learning_rate": 0.0003514020979020979, | |
| "loss": 3.2412, | |
| "step": 71200 | |
| }, | |
| { | |
| "epoch": 20.748485554520038, | |
| "grad_norm": 0.40721452236175537, | |
| "learning_rate": 0.0003512272727272727, | |
| "loss": 3.2465, | |
| "step": 71250 | |
| }, | |
| { | |
| "epoch": 20.763047530288908, | |
| "grad_norm": 0.42458590865135193, | |
| "learning_rate": 0.00035105244755244755, | |
| "loss": 3.2518, | |
| "step": 71300 | |
| }, | |
| { | |
| "epoch": 20.777609506057782, | |
| "grad_norm": 0.37446263432502747, | |
| "learning_rate": 0.0003508776223776223, | |
| "loss": 3.2493, | |
| "step": 71350 | |
| }, | |
| { | |
| "epoch": 20.792171481826653, | |
| "grad_norm": 0.39642587304115295, | |
| "learning_rate": 0.00035070279720279715, | |
| "loss": 3.247, | |
| "step": 71400 | |
| }, | |
| { | |
| "epoch": 20.806733457595527, | |
| "grad_norm": 0.4110299348831177, | |
| "learning_rate": 0.000350527972027972, | |
| "loss": 3.2551, | |
| "step": 71450 | |
| }, | |
| { | |
| "epoch": 20.821295433364398, | |
| "grad_norm": 0.36979174613952637, | |
| "learning_rate": 0.0003503531468531468, | |
| "loss": 3.2441, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 20.835857409133272, | |
| "grad_norm": 0.3842044770717621, | |
| "learning_rate": 0.00035017832167832166, | |
| "loss": 3.2428, | |
| "step": 71550 | |
| }, | |
| { | |
| "epoch": 20.850419384902143, | |
| "grad_norm": 0.3942607045173645, | |
| "learning_rate": 0.00035000349650349645, | |
| "loss": 3.2425, | |
| "step": 71600 | |
| }, | |
| { | |
| "epoch": 20.864981360671017, | |
| "grad_norm": 0.400119423866272, | |
| "learning_rate": 0.0003498286713286713, | |
| "loss": 3.2444, | |
| "step": 71650 | |
| }, | |
| { | |
| "epoch": 20.879543336439887, | |
| "grad_norm": 0.3815798759460449, | |
| "learning_rate": 0.0003496538461538461, | |
| "loss": 3.2592, | |
| "step": 71700 | |
| }, | |
| { | |
| "epoch": 20.89410531220876, | |
| "grad_norm": 0.3906811773777008, | |
| "learning_rate": 0.00034947902097902096, | |
| "loss": 3.2483, | |
| "step": 71750 | |
| }, | |
| { | |
| "epoch": 20.908667287977632, | |
| "grad_norm": 0.367766797542572, | |
| "learning_rate": 0.00034930419580419576, | |
| "loss": 3.2491, | |
| "step": 71800 | |
| }, | |
| { | |
| "epoch": 20.923229263746506, | |
| "grad_norm": 0.4095619022846222, | |
| "learning_rate": 0.0003491293706293706, | |
| "loss": 3.2504, | |
| "step": 71850 | |
| }, | |
| { | |
| "epoch": 20.937791239515377, | |
| "grad_norm": 0.3742462694644928, | |
| "learning_rate": 0.0003489545454545454, | |
| "loss": 3.2566, | |
| "step": 71900 | |
| }, | |
| { | |
| "epoch": 20.95235321528425, | |
| "grad_norm": 0.39355388283729553, | |
| "learning_rate": 0.00034877972027972027, | |
| "loss": 3.25, | |
| "step": 71950 | |
| }, | |
| { | |
| "epoch": 20.966915191053122, | |
| "grad_norm": 0.4069824516773224, | |
| "learning_rate": 0.00034860489510489507, | |
| "loss": 3.2437, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 20.966915191053122, | |
| "eval_accuracy": 0.3738097119322984, | |
| "eval_loss": 3.5342633724212646, | |
| "eval_runtime": 53.8776, | |
| "eval_samples_per_second": 308.923, | |
| "eval_steps_per_second": 19.322, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 20.981477166821996, | |
| "grad_norm": 0.3976595401763916, | |
| "learning_rate": 0.0003484300699300699, | |
| "loss": 3.2602, | |
| "step": 72050 | |
| }, | |
| { | |
| "epoch": 20.996039142590867, | |
| "grad_norm": 0.396127849817276, | |
| "learning_rate": 0.0003482552447552448, | |
| "loss": 3.2456, | |
| "step": 72100 | |
| }, | |
| { | |
| "epoch": 21.010484622553587, | |
| "grad_norm": 0.39420220255851746, | |
| "learning_rate": 0.0003480804195804195, | |
| "loss": 3.1874, | |
| "step": 72150 | |
| }, | |
| { | |
| "epoch": 21.02504659832246, | |
| "grad_norm": 0.393216609954834, | |
| "learning_rate": 0.0003479055944055944, | |
| "loss": 3.1555, | |
| "step": 72200 | |
| }, | |
| { | |
| "epoch": 21.039608574091332, | |
| "grad_norm": 0.3881584405899048, | |
| "learning_rate": 0.0003477307692307692, | |
| "loss": 3.1586, | |
| "step": 72250 | |
| }, | |
| { | |
| "epoch": 21.054170549860206, | |
| "grad_norm": 0.3874966502189636, | |
| "learning_rate": 0.00034755594405594403, | |
| "loss": 3.1575, | |
| "step": 72300 | |
| }, | |
| { | |
| "epoch": 21.068732525629077, | |
| "grad_norm": 0.4072263836860657, | |
| "learning_rate": 0.00034738111888111883, | |
| "loss": 3.1657, | |
| "step": 72350 | |
| }, | |
| { | |
| "epoch": 21.08329450139795, | |
| "grad_norm": 0.39619114995002747, | |
| "learning_rate": 0.0003472062937062937, | |
| "loss": 3.1553, | |
| "step": 72400 | |
| }, | |
| { | |
| "epoch": 21.09785647716682, | |
| "grad_norm": 0.41326701641082764, | |
| "learning_rate": 0.0003470314685314685, | |
| "loss": 3.1683, | |
| "step": 72450 | |
| }, | |
| { | |
| "epoch": 21.112418452935696, | |
| "grad_norm": 0.4170162081718445, | |
| "learning_rate": 0.00034685664335664334, | |
| "loss": 3.1696, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 21.126980428704567, | |
| "grad_norm": 0.393693745136261, | |
| "learning_rate": 0.00034668181818181814, | |
| "loss": 3.1703, | |
| "step": 72550 | |
| }, | |
| { | |
| "epoch": 21.141542404473437, | |
| "grad_norm": 0.3787849545478821, | |
| "learning_rate": 0.000346506993006993, | |
| "loss": 3.1926, | |
| "step": 72600 | |
| }, | |
| { | |
| "epoch": 21.15610438024231, | |
| "grad_norm": 0.38826873898506165, | |
| "learning_rate": 0.0003463321678321678, | |
| "loss": 3.1892, | |
| "step": 72650 | |
| }, | |
| { | |
| "epoch": 21.170666356011182, | |
| "grad_norm": 0.3828301727771759, | |
| "learning_rate": 0.00034615734265734264, | |
| "loss": 3.1898, | |
| "step": 72700 | |
| }, | |
| { | |
| "epoch": 21.185228331780056, | |
| "grad_norm": 0.40055036544799805, | |
| "learning_rate": 0.0003459825174825175, | |
| "loss": 3.179, | |
| "step": 72750 | |
| }, | |
| { | |
| "epoch": 21.199790307548927, | |
| "grad_norm": 0.3872724175453186, | |
| "learning_rate": 0.0003458076923076923, | |
| "loss": 3.1851, | |
| "step": 72800 | |
| }, | |
| { | |
| "epoch": 21.2143522833178, | |
| "grad_norm": 0.4158056378364563, | |
| "learning_rate": 0.00034563286713286715, | |
| "loss": 3.1998, | |
| "step": 72850 | |
| }, | |
| { | |
| "epoch": 21.22891425908667, | |
| "grad_norm": 0.41352295875549316, | |
| "learning_rate": 0.0003454580419580419, | |
| "loss": 3.2048, | |
| "step": 72900 | |
| }, | |
| { | |
| "epoch": 21.243476234855546, | |
| "grad_norm": 0.3767777383327484, | |
| "learning_rate": 0.00034528321678321675, | |
| "loss": 3.1816, | |
| "step": 72950 | |
| }, | |
| { | |
| "epoch": 21.258038210624417, | |
| "grad_norm": 0.38860374689102173, | |
| "learning_rate": 0.00034510839160839155, | |
| "loss": 3.204, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 21.258038210624417, | |
| "eval_accuracy": 0.37261219289544933, | |
| "eval_loss": 3.5535717010498047, | |
| "eval_runtime": 53.6505, | |
| "eval_samples_per_second": 310.23, | |
| "eval_steps_per_second": 19.403, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 21.27260018639329, | |
| "grad_norm": 0.42040345072746277, | |
| "learning_rate": 0.0003449335664335664, | |
| "loss": 3.2045, | |
| "step": 73050 | |
| }, | |
| { | |
| "epoch": 21.28716216216216, | |
| "grad_norm": 0.4155707061290741, | |
| "learning_rate": 0.0003447587412587412, | |
| "loss": 3.1881, | |
| "step": 73100 | |
| }, | |
| { | |
| "epoch": 21.301724137931036, | |
| "grad_norm": 0.4353258013725281, | |
| "learning_rate": 0.00034458391608391606, | |
| "loss": 3.2045, | |
| "step": 73150 | |
| }, | |
| { | |
| "epoch": 21.316286113699906, | |
| "grad_norm": 0.4045839011669159, | |
| "learning_rate": 0.00034440909090909086, | |
| "loss": 3.1805, | |
| "step": 73200 | |
| }, | |
| { | |
| "epoch": 21.33084808946878, | |
| "grad_norm": 0.4096652865409851, | |
| "learning_rate": 0.0003442342657342657, | |
| "loss": 3.1998, | |
| "step": 73250 | |
| }, | |
| { | |
| "epoch": 21.34541006523765, | |
| "grad_norm": 0.4016556143760681, | |
| "learning_rate": 0.0003440594405594405, | |
| "loss": 3.2029, | |
| "step": 73300 | |
| }, | |
| { | |
| "epoch": 21.359972041006525, | |
| "grad_norm": 0.4026934802532196, | |
| "learning_rate": 0.00034388461538461537, | |
| "loss": 3.2031, | |
| "step": 73350 | |
| }, | |
| { | |
| "epoch": 21.374534016775396, | |
| "grad_norm": 0.3856440484523773, | |
| "learning_rate": 0.00034370979020979017, | |
| "loss": 3.2018, | |
| "step": 73400 | |
| }, | |
| { | |
| "epoch": 21.38909599254427, | |
| "grad_norm": 0.37840890884399414, | |
| "learning_rate": 0.000343534965034965, | |
| "loss": 3.2169, | |
| "step": 73450 | |
| }, | |
| { | |
| "epoch": 21.40365796831314, | |
| "grad_norm": 0.4057793915271759, | |
| "learning_rate": 0.0003433601398601399, | |
| "loss": 3.2167, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 21.41821994408201, | |
| "grad_norm": 0.4393506646156311, | |
| "learning_rate": 0.0003431853146853147, | |
| "loss": 3.2073, | |
| "step": 73550 | |
| }, | |
| { | |
| "epoch": 21.432781919850886, | |
| "grad_norm": 0.4116910398006439, | |
| "learning_rate": 0.0003430104895104895, | |
| "loss": 3.217, | |
| "step": 73600 | |
| }, | |
| { | |
| "epoch": 21.447343895619756, | |
| "grad_norm": 0.4329574406147003, | |
| "learning_rate": 0.00034283566433566427, | |
| "loss": 3.219, | |
| "step": 73650 | |
| }, | |
| { | |
| "epoch": 21.46190587138863, | |
| "grad_norm": 0.3817179203033447, | |
| "learning_rate": 0.0003426608391608391, | |
| "loss": 3.2151, | |
| "step": 73700 | |
| }, | |
| { | |
| "epoch": 21.4764678471575, | |
| "grad_norm": 0.4023750126361847, | |
| "learning_rate": 0.0003424860139860139, | |
| "loss": 3.2181, | |
| "step": 73750 | |
| }, | |
| { | |
| "epoch": 21.491029822926375, | |
| "grad_norm": 0.39865052700042725, | |
| "learning_rate": 0.0003423111888111888, | |
| "loss": 3.1973, | |
| "step": 73800 | |
| }, | |
| { | |
| "epoch": 21.505591798695246, | |
| "grad_norm": 0.39138761162757874, | |
| "learning_rate": 0.0003421363636363636, | |
| "loss": 3.2162, | |
| "step": 73850 | |
| }, | |
| { | |
| "epoch": 21.52015377446412, | |
| "grad_norm": 0.3885617256164551, | |
| "learning_rate": 0.00034196153846153843, | |
| "loss": 3.2203, | |
| "step": 73900 | |
| }, | |
| { | |
| "epoch": 21.53471575023299, | |
| "grad_norm": 0.3830677568912506, | |
| "learning_rate": 0.00034178671328671323, | |
| "loss": 3.2268, | |
| "step": 73950 | |
| }, | |
| { | |
| "epoch": 21.549277726001865, | |
| "grad_norm": 0.3745560944080353, | |
| "learning_rate": 0.0003416118881118881, | |
| "loss": 3.2134, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 21.549277726001865, | |
| "eval_accuracy": 0.37313223479039126, | |
| "eval_loss": 3.546206474304199, | |
| "eval_runtime": 53.7466, | |
| "eval_samples_per_second": 309.675, | |
| "eval_steps_per_second": 19.369, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 21.563839701770736, | |
| "grad_norm": 0.4401836097240448, | |
| "learning_rate": 0.0003414370629370629, | |
| "loss": 3.2201, | |
| "step": 74050 | |
| }, | |
| { | |
| "epoch": 21.57840167753961, | |
| "grad_norm": 0.42541825771331787, | |
| "learning_rate": 0.00034126223776223774, | |
| "loss": 3.2306, | |
| "step": 74100 | |
| }, | |
| { | |
| "epoch": 21.59296365330848, | |
| "grad_norm": 0.3805076777935028, | |
| "learning_rate": 0.0003410874125874126, | |
| "loss": 3.2298, | |
| "step": 74150 | |
| }, | |
| { | |
| "epoch": 21.607525629077355, | |
| "grad_norm": 0.44168519973754883, | |
| "learning_rate": 0.0003409125874125874, | |
| "loss": 3.2304, | |
| "step": 74200 | |
| }, | |
| { | |
| "epoch": 21.622087604846225, | |
| "grad_norm": 0.41441184282302856, | |
| "learning_rate": 0.00034073776223776225, | |
| "loss": 3.2218, | |
| "step": 74250 | |
| }, | |
| { | |
| "epoch": 21.6366495806151, | |
| "grad_norm": 0.37558814883232117, | |
| "learning_rate": 0.00034056293706293705, | |
| "loss": 3.2153, | |
| "step": 74300 | |
| }, | |
| { | |
| "epoch": 21.65121155638397, | |
| "grad_norm": 0.3728470504283905, | |
| "learning_rate": 0.0003403881118881119, | |
| "loss": 3.2388, | |
| "step": 74350 | |
| }, | |
| { | |
| "epoch": 21.665773532152844, | |
| "grad_norm": 0.4029659628868103, | |
| "learning_rate": 0.00034021328671328665, | |
| "loss": 3.2296, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 21.680335507921715, | |
| "grad_norm": 0.38797706365585327, | |
| "learning_rate": 0.0003400384615384615, | |
| "loss": 3.2351, | |
| "step": 74450 | |
| }, | |
| { | |
| "epoch": 21.694897483690585, | |
| "grad_norm": 0.3840591609477997, | |
| "learning_rate": 0.0003398636363636363, | |
| "loss": 3.2306, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 21.70945945945946, | |
| "grad_norm": 0.40627843141555786, | |
| "learning_rate": 0.00033968881118881115, | |
| "loss": 3.2432, | |
| "step": 74550 | |
| }, | |
| { | |
| "epoch": 21.72402143522833, | |
| "grad_norm": 0.3884592652320862, | |
| "learning_rate": 0.00033951398601398595, | |
| "loss": 3.2281, | |
| "step": 74600 | |
| }, | |
| { | |
| "epoch": 21.738583410997204, | |
| "grad_norm": 0.4909214377403259, | |
| "learning_rate": 0.0003393391608391608, | |
| "loss": 3.2371, | |
| "step": 74650 | |
| }, | |
| { | |
| "epoch": 21.753145386766075, | |
| "grad_norm": 0.4191752076148987, | |
| "learning_rate": 0.0003391643356643356, | |
| "loss": 3.2308, | |
| "step": 74700 | |
| }, | |
| { | |
| "epoch": 21.76770736253495, | |
| "grad_norm": 0.41994035243988037, | |
| "learning_rate": 0.00033898951048951046, | |
| "loss": 3.2297, | |
| "step": 74750 | |
| }, | |
| { | |
| "epoch": 21.78226933830382, | |
| "grad_norm": 0.40065521001815796, | |
| "learning_rate": 0.00033881468531468526, | |
| "loss": 3.2387, | |
| "step": 74800 | |
| }, | |
| { | |
| "epoch": 21.796831314072694, | |
| "grad_norm": 0.39243024587631226, | |
| "learning_rate": 0.0003386398601398601, | |
| "loss": 3.2371, | |
| "step": 74850 | |
| }, | |
| { | |
| "epoch": 21.811393289841565, | |
| "grad_norm": 0.3721027076244354, | |
| "learning_rate": 0.00033846503496503497, | |
| "loss": 3.2413, | |
| "step": 74900 | |
| }, | |
| { | |
| "epoch": 21.82595526561044, | |
| "grad_norm": 0.41749846935272217, | |
| "learning_rate": 0.00033829020979020977, | |
| "loss": 3.2357, | |
| "step": 74950 | |
| }, | |
| { | |
| "epoch": 21.84051724137931, | |
| "grad_norm": 0.3856858015060425, | |
| "learning_rate": 0.0003381153846153846, | |
| "loss": 3.2241, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 21.84051724137931, | |
| "eval_accuracy": 0.3736914297377898, | |
| "eval_loss": 3.539247512817383, | |
| "eval_runtime": 53.6014, | |
| "eval_samples_per_second": 310.514, | |
| "eval_steps_per_second": 19.421, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 21.855079217148184, | |
| "grad_norm": 0.3717370927333832, | |
| "learning_rate": 0.0003379405594405594, | |
| "loss": 3.2297, | |
| "step": 75050 | |
| }, | |
| { | |
| "epoch": 21.869641192917054, | |
| "grad_norm": 0.406404048204422, | |
| "learning_rate": 0.0003377657342657343, | |
| "loss": 3.2443, | |
| "step": 75100 | |
| }, | |
| { | |
| "epoch": 21.88420316868593, | |
| "grad_norm": 0.42060935497283936, | |
| "learning_rate": 0.000337590909090909, | |
| "loss": 3.2396, | |
| "step": 75150 | |
| }, | |
| { | |
| "epoch": 21.8987651444548, | |
| "grad_norm": 0.40486958622932434, | |
| "learning_rate": 0.0003374160839160839, | |
| "loss": 3.2437, | |
| "step": 75200 | |
| }, | |
| { | |
| "epoch": 21.913327120223673, | |
| "grad_norm": 0.3771274983882904, | |
| "learning_rate": 0.0003372412587412587, | |
| "loss": 3.253, | |
| "step": 75250 | |
| }, | |
| { | |
| "epoch": 21.927889095992544, | |
| "grad_norm": 0.380912721157074, | |
| "learning_rate": 0.00033706643356643353, | |
| "loss": 3.2551, | |
| "step": 75300 | |
| }, | |
| { | |
| "epoch": 21.94245107176142, | |
| "grad_norm": 0.4271264374256134, | |
| "learning_rate": 0.00033689160839160833, | |
| "loss": 3.2422, | |
| "step": 75350 | |
| }, | |
| { | |
| "epoch": 21.95701304753029, | |
| "grad_norm": 0.3783544898033142, | |
| "learning_rate": 0.0003367167832167832, | |
| "loss": 3.2409, | |
| "step": 75400 | |
| }, | |
| { | |
| "epoch": 21.97157502329916, | |
| "grad_norm": 0.3998122811317444, | |
| "learning_rate": 0.000336541958041958, | |
| "loss": 3.2439, | |
| "step": 75450 | |
| }, | |
| { | |
| "epoch": 21.986136999068034, | |
| "grad_norm": 0.38411828875541687, | |
| "learning_rate": 0.00033636713286713284, | |
| "loss": 3.2554, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 22.000582479030754, | |
| "grad_norm": 0.4125036895275116, | |
| "learning_rate": 0.0003361923076923077, | |
| "loss": 3.2221, | |
| "step": 75550 | |
| }, | |
| { | |
| "epoch": 22.01514445479963, | |
| "grad_norm": 0.4056716561317444, | |
| "learning_rate": 0.0003360174825174825, | |
| "loss": 3.1341, | |
| "step": 75600 | |
| }, | |
| { | |
| "epoch": 22.0297064305685, | |
| "grad_norm": 0.44730907678604126, | |
| "learning_rate": 0.00033584265734265734, | |
| "loss": 3.1374, | |
| "step": 75650 | |
| }, | |
| { | |
| "epoch": 22.044268406337373, | |
| "grad_norm": 0.37317419052124023, | |
| "learning_rate": 0.00033566783216783214, | |
| "loss": 3.1469, | |
| "step": 75700 | |
| }, | |
| { | |
| "epoch": 22.058830382106244, | |
| "grad_norm": 0.4454713761806488, | |
| "learning_rate": 0.000335493006993007, | |
| "loss": 3.1495, | |
| "step": 75750 | |
| }, | |
| { | |
| "epoch": 22.073392357875118, | |
| "grad_norm": 0.40124979615211487, | |
| "learning_rate": 0.0003353181818181818, | |
| "loss": 3.1522, | |
| "step": 75800 | |
| }, | |
| { | |
| "epoch": 22.08795433364399, | |
| "grad_norm": 0.4181446135044098, | |
| "learning_rate": 0.00033514335664335665, | |
| "loss": 3.1621, | |
| "step": 75850 | |
| }, | |
| { | |
| "epoch": 22.10251630941286, | |
| "grad_norm": 0.3863363265991211, | |
| "learning_rate": 0.0003349685314685314, | |
| "loss": 3.1557, | |
| "step": 75900 | |
| }, | |
| { | |
| "epoch": 22.117078285181734, | |
| "grad_norm": 0.4252418577671051, | |
| "learning_rate": 0.00033479370629370625, | |
| "loss": 3.1556, | |
| "step": 75950 | |
| }, | |
| { | |
| "epoch": 22.131640260950604, | |
| "grad_norm": 0.3969983458518982, | |
| "learning_rate": 0.00033461888111888105, | |
| "loss": 3.1705, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 22.131640260950604, | |
| "eval_accuracy": 0.3732756784059981, | |
| "eval_loss": 3.551520347595215, | |
| "eval_runtime": 53.6444, | |
| "eval_samples_per_second": 310.265, | |
| "eval_steps_per_second": 19.406, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 22.14620223671948, | |
| "grad_norm": 0.3937150835990906, | |
| "learning_rate": 0.0003344440559440559, | |
| "loss": 3.1621, | |
| "step": 76050 | |
| }, | |
| { | |
| "epoch": 22.16076421248835, | |
| "grad_norm": 0.3968026638031006, | |
| "learning_rate": 0.0003342692307692307, | |
| "loss": 3.1649, | |
| "step": 76100 | |
| }, | |
| { | |
| "epoch": 22.175326188257223, | |
| "grad_norm": 0.3895382881164551, | |
| "learning_rate": 0.00033409440559440556, | |
| "loss": 3.1622, | |
| "step": 76150 | |
| }, | |
| { | |
| "epoch": 22.189888164026094, | |
| "grad_norm": 0.3964536190032959, | |
| "learning_rate": 0.00033391958041958036, | |
| "loss": 3.185, | |
| "step": 76200 | |
| }, | |
| { | |
| "epoch": 22.204450139794968, | |
| "grad_norm": 0.41914913058280945, | |
| "learning_rate": 0.0003337447552447552, | |
| "loss": 3.1825, | |
| "step": 76250 | |
| }, | |
| { | |
| "epoch": 22.21901211556384, | |
| "grad_norm": 0.39592286944389343, | |
| "learning_rate": 0.00033356993006993007, | |
| "loss": 3.1869, | |
| "step": 76300 | |
| }, | |
| { | |
| "epoch": 22.233574091332713, | |
| "grad_norm": 0.39550790190696716, | |
| "learning_rate": 0.00033339510489510487, | |
| "loss": 3.1796, | |
| "step": 76350 | |
| }, | |
| { | |
| "epoch": 22.248136067101584, | |
| "grad_norm": 0.43073078989982605, | |
| "learning_rate": 0.0003332202797202797, | |
| "loss": 3.1802, | |
| "step": 76400 | |
| }, | |
| { | |
| "epoch": 22.262698042870458, | |
| "grad_norm": 0.39744439721107483, | |
| "learning_rate": 0.0003330454545454545, | |
| "loss": 3.1891, | |
| "step": 76450 | |
| }, | |
| { | |
| "epoch": 22.27726001863933, | |
| "grad_norm": 0.41097643971443176, | |
| "learning_rate": 0.0003328706293706294, | |
| "loss": 3.1963, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 22.291821994408203, | |
| "grad_norm": 0.4132195711135864, | |
| "learning_rate": 0.00033269580419580417, | |
| "loss": 3.1976, | |
| "step": 76550 | |
| }, | |
| { | |
| "epoch": 22.306383970177073, | |
| "grad_norm": 0.39138537645339966, | |
| "learning_rate": 0.000332520979020979, | |
| "loss": 3.1897, | |
| "step": 76600 | |
| }, | |
| { | |
| "epoch": 22.320945945945947, | |
| "grad_norm": 0.41629618406295776, | |
| "learning_rate": 0.00033234615384615377, | |
| "loss": 3.193, | |
| "step": 76650 | |
| }, | |
| { | |
| "epoch": 22.335507921714818, | |
| "grad_norm": 0.3976675570011139, | |
| "learning_rate": 0.0003321713286713286, | |
| "loss": 3.1897, | |
| "step": 76700 | |
| }, | |
| { | |
| "epoch": 22.350069897483692, | |
| "grad_norm": 0.3983791470527649, | |
| "learning_rate": 0.0003319965034965034, | |
| "loss": 3.2127, | |
| "step": 76750 | |
| }, | |
| { | |
| "epoch": 22.364631873252563, | |
| "grad_norm": 0.4043506681919098, | |
| "learning_rate": 0.0003318216783216783, | |
| "loss": 3.2072, | |
| "step": 76800 | |
| }, | |
| { | |
| "epoch": 22.379193849021433, | |
| "grad_norm": 0.4207497835159302, | |
| "learning_rate": 0.0003316468531468531, | |
| "loss": 3.2042, | |
| "step": 76850 | |
| }, | |
| { | |
| "epoch": 22.393755824790308, | |
| "grad_norm": 0.4057113528251648, | |
| "learning_rate": 0.00033147202797202793, | |
| "loss": 3.2052, | |
| "step": 76900 | |
| }, | |
| { | |
| "epoch": 22.40831780055918, | |
| "grad_norm": 0.44642117619514465, | |
| "learning_rate": 0.0003312972027972028, | |
| "loss": 3.2106, | |
| "step": 76950 | |
| }, | |
| { | |
| "epoch": 22.422879776328053, | |
| "grad_norm": 0.40626928210258484, | |
| "learning_rate": 0.0003311223776223776, | |
| "loss": 3.2019, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 22.422879776328053, | |
| "eval_accuracy": 0.3736867266684256, | |
| "eval_loss": 3.5471279621124268, | |
| "eval_runtime": 53.8269, | |
| "eval_samples_per_second": 309.213, | |
| "eval_steps_per_second": 19.34, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 22.437441752096923, | |
| "grad_norm": 0.4069664478302002, | |
| "learning_rate": 0.00033094755244755244, | |
| "loss": 3.2164, | |
| "step": 77050 | |
| }, | |
| { | |
| "epoch": 22.452003727865797, | |
| "grad_norm": 0.4306388795375824, | |
| "learning_rate": 0.00033077272727272724, | |
| "loss": 3.1861, | |
| "step": 77100 | |
| }, | |
| { | |
| "epoch": 22.466565703634668, | |
| "grad_norm": 0.4088691174983978, | |
| "learning_rate": 0.0003305979020979021, | |
| "loss": 3.2014, | |
| "step": 77150 | |
| }, | |
| { | |
| "epoch": 22.481127679403542, | |
| "grad_norm": 0.42260071635246277, | |
| "learning_rate": 0.0003304230769230769, | |
| "loss": 3.2185, | |
| "step": 77200 | |
| }, | |
| { | |
| "epoch": 22.495689655172413, | |
| "grad_norm": 0.3822173774242401, | |
| "learning_rate": 0.00033024825174825175, | |
| "loss": 3.1988, | |
| "step": 77250 | |
| }, | |
| { | |
| "epoch": 22.510251630941287, | |
| "grad_norm": 0.3947815001010895, | |
| "learning_rate": 0.00033007342657342655, | |
| "loss": 3.2037, | |
| "step": 77300 | |
| }, | |
| { | |
| "epoch": 22.524813606710158, | |
| "grad_norm": 0.4035757780075073, | |
| "learning_rate": 0.0003298986013986014, | |
| "loss": 3.2042, | |
| "step": 77350 | |
| }, | |
| { | |
| "epoch": 22.539375582479032, | |
| "grad_norm": 0.39407262206077576, | |
| "learning_rate": 0.00032972377622377615, | |
| "loss": 3.1987, | |
| "step": 77400 | |
| }, | |
| { | |
| "epoch": 22.553937558247902, | |
| "grad_norm": 0.4021145701408386, | |
| "learning_rate": 0.000329548951048951, | |
| "loss": 3.213, | |
| "step": 77450 | |
| }, | |
| { | |
| "epoch": 22.568499534016777, | |
| "grad_norm": 0.4199064075946808, | |
| "learning_rate": 0.0003293741258741258, | |
| "loss": 3.2167, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 22.583061509785647, | |
| "grad_norm": 0.4025714099407196, | |
| "learning_rate": 0.00032919930069930065, | |
| "loss": 3.222, | |
| "step": 77550 | |
| }, | |
| { | |
| "epoch": 22.59762348555452, | |
| "grad_norm": 0.4109303653240204, | |
| "learning_rate": 0.0003290244755244755, | |
| "loss": 3.2103, | |
| "step": 77600 | |
| }, | |
| { | |
| "epoch": 22.612185461323392, | |
| "grad_norm": 0.3831614851951599, | |
| "learning_rate": 0.0003288496503496503, | |
| "loss": 3.2133, | |
| "step": 77650 | |
| }, | |
| { | |
| "epoch": 22.626747437092266, | |
| "grad_norm": 0.38504159450531006, | |
| "learning_rate": 0.00032867482517482516, | |
| "loss": 3.2155, | |
| "step": 77700 | |
| }, | |
| { | |
| "epoch": 22.641309412861137, | |
| "grad_norm": 0.3741070330142975, | |
| "learning_rate": 0.00032849999999999996, | |
| "loss": 3.211, | |
| "step": 77750 | |
| }, | |
| { | |
| "epoch": 22.655871388630008, | |
| "grad_norm": 0.42629310488700867, | |
| "learning_rate": 0.0003283251748251748, | |
| "loss": 3.2188, | |
| "step": 77800 | |
| }, | |
| { | |
| "epoch": 22.670433364398882, | |
| "grad_norm": 0.42940154671669006, | |
| "learning_rate": 0.0003281503496503496, | |
| "loss": 3.2274, | |
| "step": 77850 | |
| }, | |
| { | |
| "epoch": 22.684995340167752, | |
| "grad_norm": 0.3877221345901489, | |
| "learning_rate": 0.00032797552447552447, | |
| "loss": 3.2277, | |
| "step": 77900 | |
| }, | |
| { | |
| "epoch": 22.699557315936627, | |
| "grad_norm": 0.40116119384765625, | |
| "learning_rate": 0.00032780069930069927, | |
| "loss": 3.2121, | |
| "step": 77950 | |
| }, | |
| { | |
| "epoch": 22.714119291705497, | |
| "grad_norm": 0.37814322113990784, | |
| "learning_rate": 0.0003276258741258741, | |
| "loss": 3.2065, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 22.714119291705497, | |
| "eval_accuracy": 0.37389765932940816, | |
| "eval_loss": 3.5403106212615967, | |
| "eval_runtime": 53.5367, | |
| "eval_samples_per_second": 310.889, | |
| "eval_steps_per_second": 19.445, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 22.72868126747437, | |
| "grad_norm": 0.4460028409957886, | |
| "learning_rate": 0.0003274510489510489, | |
| "loss": 3.2265, | |
| "step": 78050 | |
| }, | |
| { | |
| "epoch": 22.743243243243242, | |
| "grad_norm": 0.39633312821388245, | |
| "learning_rate": 0.0003272762237762238, | |
| "loss": 3.2329, | |
| "step": 78100 | |
| }, | |
| { | |
| "epoch": 22.757805219012116, | |
| "grad_norm": 0.42298927903175354, | |
| "learning_rate": 0.0003271013986013985, | |
| "loss": 3.234, | |
| "step": 78150 | |
| }, | |
| { | |
| "epoch": 22.772367194780987, | |
| "grad_norm": 0.4159824252128601, | |
| "learning_rate": 0.0003269265734265734, | |
| "loss": 3.2266, | |
| "step": 78200 | |
| }, | |
| { | |
| "epoch": 22.78692917054986, | |
| "grad_norm": 0.41692405939102173, | |
| "learning_rate": 0.0003267517482517482, | |
| "loss": 3.2213, | |
| "step": 78250 | |
| }, | |
| { | |
| "epoch": 22.80149114631873, | |
| "grad_norm": 0.41382187604904175, | |
| "learning_rate": 0.00032657692307692303, | |
| "loss": 3.2392, | |
| "step": 78300 | |
| }, | |
| { | |
| "epoch": 22.816053122087606, | |
| "grad_norm": 0.41410788893699646, | |
| "learning_rate": 0.0003264020979020979, | |
| "loss": 3.2321, | |
| "step": 78350 | |
| }, | |
| { | |
| "epoch": 22.830615097856477, | |
| "grad_norm": 0.4324868619441986, | |
| "learning_rate": 0.0003262272727272727, | |
| "loss": 3.2236, | |
| "step": 78400 | |
| }, | |
| { | |
| "epoch": 22.84517707362535, | |
| "grad_norm": 0.38736671209335327, | |
| "learning_rate": 0.00032605244755244754, | |
| "loss": 3.2303, | |
| "step": 78450 | |
| }, | |
| { | |
| "epoch": 22.85973904939422, | |
| "grad_norm": 0.4221399128437042, | |
| "learning_rate": 0.00032587762237762234, | |
| "loss": 3.2348, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 22.874301025163096, | |
| "grad_norm": 0.38114288449287415, | |
| "learning_rate": 0.0003257027972027972, | |
| "loss": 3.2253, | |
| "step": 78550 | |
| }, | |
| { | |
| "epoch": 22.888863000931966, | |
| "grad_norm": 0.3975285589694977, | |
| "learning_rate": 0.000325527972027972, | |
| "loss": 3.2262, | |
| "step": 78600 | |
| }, | |
| { | |
| "epoch": 22.90342497670084, | |
| "grad_norm": 0.40540263056755066, | |
| "learning_rate": 0.00032535314685314684, | |
| "loss": 3.2257, | |
| "step": 78650 | |
| }, | |
| { | |
| "epoch": 22.91798695246971, | |
| "grad_norm": 0.3953773081302643, | |
| "learning_rate": 0.00032517832167832164, | |
| "loss": 3.2365, | |
| "step": 78700 | |
| }, | |
| { | |
| "epoch": 22.93254892823858, | |
| "grad_norm": 0.3982967138290405, | |
| "learning_rate": 0.0003250034965034965, | |
| "loss": 3.2219, | |
| "step": 78750 | |
| }, | |
| { | |
| "epoch": 22.947110904007456, | |
| "grad_norm": 0.41824063658714294, | |
| "learning_rate": 0.0003248286713286713, | |
| "loss": 3.2344, | |
| "step": 78800 | |
| }, | |
| { | |
| "epoch": 22.961672879776327, | |
| "grad_norm": 0.40607979893684387, | |
| "learning_rate": 0.00032465384615384615, | |
| "loss": 3.2305, | |
| "step": 78850 | |
| }, | |
| { | |
| "epoch": 22.9762348555452, | |
| "grad_norm": 0.4212436079978943, | |
| "learning_rate": 0.0003244790209790209, | |
| "loss": 3.2386, | |
| "step": 78900 | |
| }, | |
| { | |
| "epoch": 22.99079683131407, | |
| "grad_norm": 0.4023859202861786, | |
| "learning_rate": 0.00032430419580419575, | |
| "loss": 3.2445, | |
| "step": 78950 | |
| }, | |
| { | |
| "epoch": 23.005242311276795, | |
| "grad_norm": 0.38621482253074646, | |
| "learning_rate": 0.00032412937062937066, | |
| "loss": 3.194, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 23.005242311276795, | |
| "eval_accuracy": 0.37375503875094, | |
| "eval_loss": 3.5451126098632812, | |
| "eval_runtime": 53.8234, | |
| "eval_samples_per_second": 309.233, | |
| "eval_steps_per_second": 19.341, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 23.019804287045666, | |
| "grad_norm": 0.45066943764686584, | |
| "learning_rate": 0.0003239545454545454, | |
| "loss": 3.1238, | |
| "step": 79050 | |
| }, | |
| { | |
| "epoch": 23.03436626281454, | |
| "grad_norm": 0.3973267078399658, | |
| "learning_rate": 0.00032377972027972026, | |
| "loss": 3.1312, | |
| "step": 79100 | |
| }, | |
| { | |
| "epoch": 23.04892823858341, | |
| "grad_norm": 0.4207251965999603, | |
| "learning_rate": 0.00032360489510489506, | |
| "loss": 3.1431, | |
| "step": 79150 | |
| }, | |
| { | |
| "epoch": 23.063490214352285, | |
| "grad_norm": 0.4109000861644745, | |
| "learning_rate": 0.0003234300699300699, | |
| "loss": 3.133, | |
| "step": 79200 | |
| }, | |
| { | |
| "epoch": 23.078052190121156, | |
| "grad_norm": 0.39351069927215576, | |
| "learning_rate": 0.0003232552447552447, | |
| "loss": 3.1474, | |
| "step": 79250 | |
| }, | |
| { | |
| "epoch": 23.092614165890026, | |
| "grad_norm": 0.4133410155773163, | |
| "learning_rate": 0.00032308041958041957, | |
| "loss": 3.1619, | |
| "step": 79300 | |
| }, | |
| { | |
| "epoch": 23.1071761416589, | |
| "grad_norm": 0.45815539360046387, | |
| "learning_rate": 0.00032290559440559437, | |
| "loss": 3.1522, | |
| "step": 79350 | |
| }, | |
| { | |
| "epoch": 23.12173811742777, | |
| "grad_norm": 0.4205847680568695, | |
| "learning_rate": 0.0003227307692307692, | |
| "loss": 3.1542, | |
| "step": 79400 | |
| }, | |
| { | |
| "epoch": 23.136300093196645, | |
| "grad_norm": 0.38456612825393677, | |
| "learning_rate": 0.000322555944055944, | |
| "loss": 3.1557, | |
| "step": 79450 | |
| }, | |
| { | |
| "epoch": 23.150862068965516, | |
| "grad_norm": 0.40150612592697144, | |
| "learning_rate": 0.00032238111888111887, | |
| "loss": 3.1687, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 23.16542404473439, | |
| "grad_norm": 0.4437256455421448, | |
| "learning_rate": 0.00032220629370629367, | |
| "loss": 3.1614, | |
| "step": 79550 | |
| }, | |
| { | |
| "epoch": 23.17998602050326, | |
| "grad_norm": 0.4081536829471588, | |
| "learning_rate": 0.0003220314685314685, | |
| "loss": 3.1674, | |
| "step": 79600 | |
| }, | |
| { | |
| "epoch": 23.194547996272135, | |
| "grad_norm": 0.41392892599105835, | |
| "learning_rate": 0.00032185664335664327, | |
| "loss": 3.1684, | |
| "step": 79650 | |
| }, | |
| { | |
| "epoch": 23.209109972041006, | |
| "grad_norm": 0.38823989033699036, | |
| "learning_rate": 0.0003216818181818181, | |
| "loss": 3.1682, | |
| "step": 79700 | |
| }, | |
| { | |
| "epoch": 23.22367194780988, | |
| "grad_norm": 0.4122358560562134, | |
| "learning_rate": 0.00032150699300699303, | |
| "loss": 3.1736, | |
| "step": 79750 | |
| }, | |
| { | |
| "epoch": 23.23823392357875, | |
| "grad_norm": 0.4099797308444977, | |
| "learning_rate": 0.0003213321678321678, | |
| "loss": 3.1803, | |
| "step": 79800 | |
| }, | |
| { | |
| "epoch": 23.252795899347625, | |
| "grad_norm": 0.4234201908111572, | |
| "learning_rate": 0.00032115734265734263, | |
| "loss": 3.1737, | |
| "step": 79850 | |
| }, | |
| { | |
| "epoch": 23.267357875116495, | |
| "grad_norm": 0.41463881731033325, | |
| "learning_rate": 0.00032098251748251743, | |
| "loss": 3.179, | |
| "step": 79900 | |
| }, | |
| { | |
| "epoch": 23.28191985088537, | |
| "grad_norm": 0.40318965911865234, | |
| "learning_rate": 0.0003208076923076923, | |
| "loss": 3.1699, | |
| "step": 79950 | |
| }, | |
| { | |
| "epoch": 23.29648182665424, | |
| "grad_norm": 0.40535327792167664, | |
| "learning_rate": 0.0003206328671328671, | |
| "loss": 3.1815, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 23.29648182665424, | |
| "eval_accuracy": 0.3734642714875009, | |
| "eval_loss": 3.5514914989471436, | |
| "eval_runtime": 53.816, | |
| "eval_samples_per_second": 309.276, | |
| "eval_steps_per_second": 19.344, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 23.311043802423114, | |
| "grad_norm": 0.3818470239639282, | |
| "learning_rate": 0.00032045804195804194, | |
| "loss": 3.1755, | |
| "step": 80050 | |
| }, | |
| { | |
| "epoch": 23.325605778191985, | |
| "grad_norm": 0.41949790716171265, | |
| "learning_rate": 0.00032028321678321674, | |
| "loss": 3.1716, | |
| "step": 80100 | |
| }, | |
| { | |
| "epoch": 23.340167753960856, | |
| "grad_norm": 0.4188728928565979, | |
| "learning_rate": 0.0003201083916083916, | |
| "loss": 3.1978, | |
| "step": 80150 | |
| }, | |
| { | |
| "epoch": 23.35472972972973, | |
| "grad_norm": 0.40345263481140137, | |
| "learning_rate": 0.0003199335664335664, | |
| "loss": 3.1794, | |
| "step": 80200 | |
| }, | |
| { | |
| "epoch": 23.3692917054986, | |
| "grad_norm": 0.42796680331230164, | |
| "learning_rate": 0.00031975874125874125, | |
| "loss": 3.1957, | |
| "step": 80250 | |
| }, | |
| { | |
| "epoch": 23.383853681267475, | |
| "grad_norm": 0.39610591530799866, | |
| "learning_rate": 0.00031958391608391605, | |
| "loss": 3.1904, | |
| "step": 80300 | |
| }, | |
| { | |
| "epoch": 23.398415657036345, | |
| "grad_norm": 0.4445754885673523, | |
| "learning_rate": 0.0003194090909090909, | |
| "loss": 3.1841, | |
| "step": 80350 | |
| }, | |
| { | |
| "epoch": 23.41297763280522, | |
| "grad_norm": 0.4124175012111664, | |
| "learning_rate": 0.00031923426573426576, | |
| "loss": 3.1849, | |
| "step": 80400 | |
| }, | |
| { | |
| "epoch": 23.42753960857409, | |
| "grad_norm": 0.4136520028114319, | |
| "learning_rate": 0.0003190594405594405, | |
| "loss": 3.1927, | |
| "step": 80450 | |
| }, | |
| { | |
| "epoch": 23.442101584342964, | |
| "grad_norm": 0.4014403223991394, | |
| "learning_rate": 0.0003188846153846154, | |
| "loss": 3.1989, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 23.456663560111835, | |
| "grad_norm": 0.42746081948280334, | |
| "learning_rate": 0.00031870979020979015, | |
| "loss": 3.2109, | |
| "step": 80550 | |
| }, | |
| { | |
| "epoch": 23.47122553588071, | |
| "grad_norm": 0.3877197504043579, | |
| "learning_rate": 0.000318534965034965, | |
| "loss": 3.191, | |
| "step": 80600 | |
| }, | |
| { | |
| "epoch": 23.48578751164958, | |
| "grad_norm": 0.42082786560058594, | |
| "learning_rate": 0.0003183601398601398, | |
| "loss": 3.2043, | |
| "step": 80650 | |
| }, | |
| { | |
| "epoch": 23.500349487418454, | |
| "grad_norm": 0.3994758129119873, | |
| "learning_rate": 0.00031818531468531466, | |
| "loss": 3.1973, | |
| "step": 80700 | |
| }, | |
| { | |
| "epoch": 23.514911463187325, | |
| "grad_norm": 0.42390763759613037, | |
| "learning_rate": 0.00031801048951048946, | |
| "loss": 3.2018, | |
| "step": 80750 | |
| }, | |
| { | |
| "epoch": 23.5294734389562, | |
| "grad_norm": 0.4568711519241333, | |
| "learning_rate": 0.0003178356643356643, | |
| "loss": 3.1995, | |
| "step": 80800 | |
| }, | |
| { | |
| "epoch": 23.54403541472507, | |
| "grad_norm": 0.4177471101284027, | |
| "learning_rate": 0.0003176608391608391, | |
| "loss": 3.1894, | |
| "step": 80850 | |
| }, | |
| { | |
| "epoch": 23.558597390493944, | |
| "grad_norm": 0.42740505933761597, | |
| "learning_rate": 0.00031748601398601397, | |
| "loss": 3.1983, | |
| "step": 80900 | |
| }, | |
| { | |
| "epoch": 23.573159366262814, | |
| "grad_norm": 0.4288630187511444, | |
| "learning_rate": 0.00031731118881118877, | |
| "loss": 3.2102, | |
| "step": 80950 | |
| }, | |
| { | |
| "epoch": 23.58772134203169, | |
| "grad_norm": 0.42180898785591125, | |
| "learning_rate": 0.0003171363636363636, | |
| "loss": 3.218, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 23.58772134203169, | |
| "eval_accuracy": 0.37408472391336756, | |
| "eval_loss": 3.5433216094970703, | |
| "eval_runtime": 53.7335, | |
| "eval_samples_per_second": 309.751, | |
| "eval_steps_per_second": 19.373, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 23.60228331780056, | |
| "grad_norm": 0.3826054632663727, | |
| "learning_rate": 0.0003169615384615385, | |
| "loss": 3.2049, | |
| "step": 81050 | |
| }, | |
| { | |
| "epoch": 23.616845293569433, | |
| "grad_norm": 0.43105751276016235, | |
| "learning_rate": 0.0003167867132867133, | |
| "loss": 3.2022, | |
| "step": 81100 | |
| }, | |
| { | |
| "epoch": 23.631407269338304, | |
| "grad_norm": 0.4408121705055237, | |
| "learning_rate": 0.00031661188811188813, | |
| "loss": 3.2094, | |
| "step": 81150 | |
| }, | |
| { | |
| "epoch": 23.645969245107175, | |
| "grad_norm": 0.4172849655151367, | |
| "learning_rate": 0.0003164370629370629, | |
| "loss": 3.2015, | |
| "step": 81200 | |
| }, | |
| { | |
| "epoch": 23.66053122087605, | |
| "grad_norm": 0.4063512682914734, | |
| "learning_rate": 0.0003162622377622378, | |
| "loss": 3.2081, | |
| "step": 81250 | |
| }, | |
| { | |
| "epoch": 23.67509319664492, | |
| "grad_norm": 0.4677945673465729, | |
| "learning_rate": 0.00031608741258741253, | |
| "loss": 3.1941, | |
| "step": 81300 | |
| }, | |
| { | |
| "epoch": 23.689655172413794, | |
| "grad_norm": 0.40490514039993286, | |
| "learning_rate": 0.0003159125874125874, | |
| "loss": 3.2041, | |
| "step": 81350 | |
| }, | |
| { | |
| "epoch": 23.704217148182664, | |
| "grad_norm": 0.41468971967697144, | |
| "learning_rate": 0.0003157377622377622, | |
| "loss": 3.213, | |
| "step": 81400 | |
| }, | |
| { | |
| "epoch": 23.71877912395154, | |
| "grad_norm": 0.4094548523426056, | |
| "learning_rate": 0.00031556293706293704, | |
| "loss": 3.2095, | |
| "step": 81450 | |
| }, | |
| { | |
| "epoch": 23.73334109972041, | |
| "grad_norm": 0.39661234617233276, | |
| "learning_rate": 0.00031538811188811184, | |
| "loss": 3.2104, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 23.747903075489283, | |
| "grad_norm": 0.37781253457069397, | |
| "learning_rate": 0.0003152132867132867, | |
| "loss": 3.2234, | |
| "step": 81550 | |
| }, | |
| { | |
| "epoch": 23.762465051258154, | |
| "grad_norm": 0.4035096764564514, | |
| "learning_rate": 0.0003150384615384615, | |
| "loss": 3.2082, | |
| "step": 81600 | |
| }, | |
| { | |
| "epoch": 23.777027027027028, | |
| "grad_norm": 0.4032893180847168, | |
| "learning_rate": 0.00031486363636363634, | |
| "loss": 3.2254, | |
| "step": 81650 | |
| }, | |
| { | |
| "epoch": 23.7915890027959, | |
| "grad_norm": 0.4168602228164673, | |
| "learning_rate": 0.00031468881118881114, | |
| "loss": 3.2216, | |
| "step": 81700 | |
| }, | |
| { | |
| "epoch": 23.806150978564773, | |
| "grad_norm": 0.4204430878162384, | |
| "learning_rate": 0.000314513986013986, | |
| "loss": 3.2252, | |
| "step": 81750 | |
| }, | |
| { | |
| "epoch": 23.820712954333644, | |
| "grad_norm": 0.3943716287612915, | |
| "learning_rate": 0.00031433916083916085, | |
| "loss": 3.2147, | |
| "step": 81800 | |
| }, | |
| { | |
| "epoch": 23.835274930102518, | |
| "grad_norm": 0.42684200406074524, | |
| "learning_rate": 0.00031416433566433565, | |
| "loss": 3.2144, | |
| "step": 81850 | |
| }, | |
| { | |
| "epoch": 23.84983690587139, | |
| "grad_norm": 0.4027450680732727, | |
| "learning_rate": 0.0003139895104895105, | |
| "loss": 3.2226, | |
| "step": 81900 | |
| }, | |
| { | |
| "epoch": 23.864398881640263, | |
| "grad_norm": 0.3920784294605255, | |
| "learning_rate": 0.00031381468531468525, | |
| "loss": 3.2226, | |
| "step": 81950 | |
| }, | |
| { | |
| "epoch": 23.878960857409133, | |
| "grad_norm": 0.41487202048301697, | |
| "learning_rate": 0.00031363986013986016, | |
| "loss": 3.2422, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 23.878960857409133, | |
| "eval_accuracy": 0.37429424565354086, | |
| "eval_loss": 3.5338425636291504, | |
| "eval_runtime": 53.8113, | |
| "eval_samples_per_second": 309.303, | |
| "eval_steps_per_second": 19.345, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 23.893522833178004, | |
| "grad_norm": 0.3978407680988312, | |
| "learning_rate": 0.0003134650349650349, | |
| "loss": 3.2213, | |
| "step": 82050 | |
| }, | |
| { | |
| "epoch": 23.908084808946878, | |
| "grad_norm": 0.4096793532371521, | |
| "learning_rate": 0.00031329020979020976, | |
| "loss": 3.2204, | |
| "step": 82100 | |
| }, | |
| { | |
| "epoch": 23.92264678471575, | |
| "grad_norm": 0.41329044103622437, | |
| "learning_rate": 0.00031311538461538456, | |
| "loss": 3.2204, | |
| "step": 82150 | |
| }, | |
| { | |
| "epoch": 23.937208760484623, | |
| "grad_norm": 0.4152350425720215, | |
| "learning_rate": 0.0003129405594405594, | |
| "loss": 3.2261, | |
| "step": 82200 | |
| }, | |
| { | |
| "epoch": 23.951770736253494, | |
| "grad_norm": 0.40401697158813477, | |
| "learning_rate": 0.0003127657342657342, | |
| "loss": 3.2322, | |
| "step": 82250 | |
| }, | |
| { | |
| "epoch": 23.966332712022368, | |
| "grad_norm": 0.4095125198364258, | |
| "learning_rate": 0.00031259090909090907, | |
| "loss": 3.2234, | |
| "step": 82300 | |
| }, | |
| { | |
| "epoch": 23.98089468779124, | |
| "grad_norm": 0.4391355812549591, | |
| "learning_rate": 0.00031241608391608386, | |
| "loss": 3.2262, | |
| "step": 82350 | |
| }, | |
| { | |
| "epoch": 23.995456663560113, | |
| "grad_norm": 0.42681077122688293, | |
| "learning_rate": 0.0003122412587412587, | |
| "loss": 3.2344, | |
| "step": 82400 | |
| }, | |
| { | |
| "epoch": 24.009902143522833, | |
| "grad_norm": 0.4587476849555969, | |
| "learning_rate": 0.00031206643356643357, | |
| "loss": 3.1612, | |
| "step": 82450 | |
| }, | |
| { | |
| "epoch": 24.024464119291707, | |
| "grad_norm": 0.4497005045413971, | |
| "learning_rate": 0.00031189160839160837, | |
| "loss": 3.1218, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 24.039026095060578, | |
| "grad_norm": 0.3948291540145874, | |
| "learning_rate": 0.0003117167832167832, | |
| "loss": 3.1221, | |
| "step": 82550 | |
| }, | |
| { | |
| "epoch": 24.05358807082945, | |
| "grad_norm": 0.4125128388404846, | |
| "learning_rate": 0.000311541958041958, | |
| "loss": 3.1346, | |
| "step": 82600 | |
| }, | |
| { | |
| "epoch": 24.068150046598323, | |
| "grad_norm": 0.3803099989891052, | |
| "learning_rate": 0.0003113671328671329, | |
| "loss": 3.1386, | |
| "step": 82650 | |
| }, | |
| { | |
| "epoch": 24.082712022367193, | |
| "grad_norm": 0.4099292457103729, | |
| "learning_rate": 0.0003111923076923076, | |
| "loss": 3.1414, | |
| "step": 82700 | |
| }, | |
| { | |
| "epoch": 24.097273998136068, | |
| "grad_norm": 0.43308761715888977, | |
| "learning_rate": 0.00031101748251748253, | |
| "loss": 3.1423, | |
| "step": 82750 | |
| }, | |
| { | |
| "epoch": 24.111835973904938, | |
| "grad_norm": 0.4209023118019104, | |
| "learning_rate": 0.0003108426573426573, | |
| "loss": 3.1439, | |
| "step": 82800 | |
| }, | |
| { | |
| "epoch": 24.126397949673812, | |
| "grad_norm": 0.42245200276374817, | |
| "learning_rate": 0.00031066783216783213, | |
| "loss": 3.1285, | |
| "step": 82850 | |
| }, | |
| { | |
| "epoch": 24.140959925442683, | |
| "grad_norm": 0.43536925315856934, | |
| "learning_rate": 0.00031049300699300693, | |
| "loss": 3.1439, | |
| "step": 82900 | |
| }, | |
| { | |
| "epoch": 24.155521901211557, | |
| "grad_norm": 0.4053642451763153, | |
| "learning_rate": 0.0003103181818181818, | |
| "loss": 3.1508, | |
| "step": 82950 | |
| }, | |
| { | |
| "epoch": 24.170083876980428, | |
| "grad_norm": 0.4120132625102997, | |
| "learning_rate": 0.0003101433566433566, | |
| "loss": 3.1459, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 24.170083876980428, | |
| "eval_accuracy": 0.3734714436682812, | |
| "eval_loss": 3.5529048442840576, | |
| "eval_runtime": 53.7547, | |
| "eval_samples_per_second": 309.629, | |
| "eval_steps_per_second": 19.366, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 24.184645852749302, | |
| "grad_norm": 0.42911526560783386, | |
| "learning_rate": 0.00030996853146853144, | |
| "loss": 3.1493, | |
| "step": 83050 | |
| }, | |
| { | |
| "epoch": 24.199207828518173, | |
| "grad_norm": 0.41745200753211975, | |
| "learning_rate": 0.00030979370629370624, | |
| "loss": 3.1569, | |
| "step": 83100 | |
| }, | |
| { | |
| "epoch": 24.213769804287047, | |
| "grad_norm": 0.4385972321033478, | |
| "learning_rate": 0.0003096188811188811, | |
| "loss": 3.1605, | |
| "step": 83150 | |
| }, | |
| { | |
| "epoch": 24.228331780055917, | |
| "grad_norm": 0.40563392639160156, | |
| "learning_rate": 0.00030944405594405595, | |
| "loss": 3.1664, | |
| "step": 83200 | |
| }, | |
| { | |
| "epoch": 24.24289375582479, | |
| "grad_norm": 0.40807583928108215, | |
| "learning_rate": 0.00030926923076923075, | |
| "loss": 3.1623, | |
| "step": 83250 | |
| }, | |
| { | |
| "epoch": 24.257455731593662, | |
| "grad_norm": 0.4392421841621399, | |
| "learning_rate": 0.0003090944055944056, | |
| "loss": 3.1665, | |
| "step": 83300 | |
| }, | |
| { | |
| "epoch": 24.272017707362536, | |
| "grad_norm": 0.4189673662185669, | |
| "learning_rate": 0.0003089195804195804, | |
| "loss": 3.1699, | |
| "step": 83350 | |
| }, | |
| { | |
| "epoch": 24.286579683131407, | |
| "grad_norm": 0.44244757294654846, | |
| "learning_rate": 0.00030874475524475525, | |
| "loss": 3.1737, | |
| "step": 83400 | |
| }, | |
| { | |
| "epoch": 24.30114165890028, | |
| "grad_norm": 0.46909067034721375, | |
| "learning_rate": 0.00030856993006993, | |
| "loss": 3.1885, | |
| "step": 83450 | |
| }, | |
| { | |
| "epoch": 24.315703634669152, | |
| "grad_norm": 0.45255881547927856, | |
| "learning_rate": 0.0003083951048951049, | |
| "loss": 3.1687, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 24.330265610438023, | |
| "grad_norm": 0.4203416705131531, | |
| "learning_rate": 0.00030822027972027965, | |
| "loss": 3.1754, | |
| "step": 83550 | |
| }, | |
| { | |
| "epoch": 24.344827586206897, | |
| "grad_norm": 0.4178505539894104, | |
| "learning_rate": 0.0003080454545454545, | |
| "loss": 3.1703, | |
| "step": 83600 | |
| }, | |
| { | |
| "epoch": 24.359389561975767, | |
| "grad_norm": 0.4160827696323395, | |
| "learning_rate": 0.0003078706293706293, | |
| "loss": 3.1656, | |
| "step": 83650 | |
| }, | |
| { | |
| "epoch": 24.37395153774464, | |
| "grad_norm": 0.401161253452301, | |
| "learning_rate": 0.00030769580419580416, | |
| "loss": 3.1885, | |
| "step": 83700 | |
| }, | |
| { | |
| "epoch": 24.388513513513512, | |
| "grad_norm": 0.4042643904685974, | |
| "learning_rate": 0.00030752097902097896, | |
| "loss": 3.1816, | |
| "step": 83750 | |
| }, | |
| { | |
| "epoch": 24.403075489282386, | |
| "grad_norm": 0.4274575412273407, | |
| "learning_rate": 0.0003073461538461538, | |
| "loss": 3.1821, | |
| "step": 83800 | |
| }, | |
| { | |
| "epoch": 24.417637465051257, | |
| "grad_norm": 0.45580828189849854, | |
| "learning_rate": 0.00030717132867132867, | |
| "loss": 3.1833, | |
| "step": 83850 | |
| }, | |
| { | |
| "epoch": 24.43219944082013, | |
| "grad_norm": 0.39442870020866394, | |
| "learning_rate": 0.00030699650349650347, | |
| "loss": 3.1932, | |
| "step": 83900 | |
| }, | |
| { | |
| "epoch": 24.446761416589002, | |
| "grad_norm": 0.3898670971393585, | |
| "learning_rate": 0.0003068216783216783, | |
| "loss": 3.2083, | |
| "step": 83950 | |
| }, | |
| { | |
| "epoch": 24.461323392357876, | |
| "grad_norm": 0.4018656611442566, | |
| "learning_rate": 0.0003066468531468531, | |
| "loss": 3.1993, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 24.461323392357876, | |
| "eval_accuracy": 0.3736348753286858, | |
| "eval_loss": 3.550642251968384, | |
| "eval_runtime": 53.7874, | |
| "eval_samples_per_second": 309.441, | |
| "eval_steps_per_second": 19.354, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 24.475885368126747, | |
| "grad_norm": 0.41906172037124634, | |
| "learning_rate": 0.000306472027972028, | |
| "loss": 3.1734, | |
| "step": 84050 | |
| }, | |
| { | |
| "epoch": 24.49044734389562, | |
| "grad_norm": 0.43437841534614563, | |
| "learning_rate": 0.0003062972027972028, | |
| "loss": 3.197, | |
| "step": 84100 | |
| }, | |
| { | |
| "epoch": 24.50500931966449, | |
| "grad_norm": 0.43843838572502136, | |
| "learning_rate": 0.00030612237762237763, | |
| "loss": 3.1891, | |
| "step": 84150 | |
| }, | |
| { | |
| "epoch": 24.519571295433366, | |
| "grad_norm": 0.41096222400665283, | |
| "learning_rate": 0.0003059475524475524, | |
| "loss": 3.1952, | |
| "step": 84200 | |
| }, | |
| { | |
| "epoch": 24.534133271202236, | |
| "grad_norm": 0.3851706087589264, | |
| "learning_rate": 0.0003057727272727273, | |
| "loss": 3.1918, | |
| "step": 84250 | |
| }, | |
| { | |
| "epoch": 24.54869524697111, | |
| "grad_norm": 0.4225330650806427, | |
| "learning_rate": 0.00030559790209790203, | |
| "loss": 3.1952, | |
| "step": 84300 | |
| }, | |
| { | |
| "epoch": 24.56325722273998, | |
| "grad_norm": 0.411729633808136, | |
| "learning_rate": 0.0003054230769230769, | |
| "loss": 3.1816, | |
| "step": 84350 | |
| }, | |
| { | |
| "epoch": 24.577819198508855, | |
| "grad_norm": 0.42367714643478394, | |
| "learning_rate": 0.0003052482517482517, | |
| "loss": 3.1886, | |
| "step": 84400 | |
| }, | |
| { | |
| "epoch": 24.592381174277726, | |
| "grad_norm": 0.3968988060951233, | |
| "learning_rate": 0.00030507342657342654, | |
| "loss": 3.1871, | |
| "step": 84450 | |
| }, | |
| { | |
| "epoch": 24.606943150046597, | |
| "grad_norm": 0.4362886846065521, | |
| "learning_rate": 0.00030489860139860134, | |
| "loss": 3.1957, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 24.62150512581547, | |
| "grad_norm": 0.43027788400650024, | |
| "learning_rate": 0.0003047237762237762, | |
| "loss": 3.2085, | |
| "step": 84550 | |
| }, | |
| { | |
| "epoch": 24.63606710158434, | |
| "grad_norm": 0.42857909202575684, | |
| "learning_rate": 0.00030454895104895104, | |
| "loss": 3.2013, | |
| "step": 84600 | |
| }, | |
| { | |
| "epoch": 24.650629077353216, | |
| "grad_norm": 0.4252914488315582, | |
| "learning_rate": 0.00030437412587412584, | |
| "loss": 3.1985, | |
| "step": 84650 | |
| }, | |
| { | |
| "epoch": 24.665191053122086, | |
| "grad_norm": 0.44467562437057495, | |
| "learning_rate": 0.0003041993006993007, | |
| "loss": 3.2045, | |
| "step": 84700 | |
| }, | |
| { | |
| "epoch": 24.67975302889096, | |
| "grad_norm": 0.4184528887271881, | |
| "learning_rate": 0.0003040244755244755, | |
| "loss": 3.2113, | |
| "step": 84750 | |
| }, | |
| { | |
| "epoch": 24.69431500465983, | |
| "grad_norm": 0.386417955160141, | |
| "learning_rate": 0.00030384965034965035, | |
| "loss": 3.2107, | |
| "step": 84800 | |
| }, | |
| { | |
| "epoch": 24.708876980428705, | |
| "grad_norm": 0.40415215492248535, | |
| "learning_rate": 0.00030367482517482515, | |
| "loss": 3.2079, | |
| "step": 84850 | |
| }, | |
| { | |
| "epoch": 24.723438956197576, | |
| "grad_norm": 0.40872862935066223, | |
| "learning_rate": 0.0003035, | |
| "loss": 3.2053, | |
| "step": 84900 | |
| }, | |
| { | |
| "epoch": 24.73800093196645, | |
| "grad_norm": 0.38416963815689087, | |
| "learning_rate": 0.00030332517482517475, | |
| "loss": 3.2088, | |
| "step": 84950 | |
| }, | |
| { | |
| "epoch": 24.75256290773532, | |
| "grad_norm": 0.4279167652130127, | |
| "learning_rate": 0.00030315034965034966, | |
| "loss": 3.2121, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 24.75256290773532, | |
| "eval_accuracy": 0.3745151723369222, | |
| "eval_loss": 3.5380096435546875, | |
| "eval_runtime": 53.8009, | |
| "eval_samples_per_second": 309.363, | |
| "eval_steps_per_second": 19.349, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 24.767124883504195, | |
| "grad_norm": 0.4610745310783386, | |
| "learning_rate": 0.0003029755244755244, | |
| "loss": 3.2114, | |
| "step": 85050 | |
| }, | |
| { | |
| "epoch": 24.781686859273066, | |
| "grad_norm": 0.4009937345981598, | |
| "learning_rate": 0.00030280069930069926, | |
| "loss": 3.2105, | |
| "step": 85100 | |
| }, | |
| { | |
| "epoch": 24.79624883504194, | |
| "grad_norm": 0.43339040875434875, | |
| "learning_rate": 0.00030262587412587406, | |
| "loss": 3.1943, | |
| "step": 85150 | |
| }, | |
| { | |
| "epoch": 24.81081081081081, | |
| "grad_norm": 0.46495065093040466, | |
| "learning_rate": 0.0003024510489510489, | |
| "loss": 3.2136, | |
| "step": 85200 | |
| }, | |
| { | |
| "epoch": 24.825372786579685, | |
| "grad_norm": 0.4479699730873108, | |
| "learning_rate": 0.00030227622377622377, | |
| "loss": 3.2088, | |
| "step": 85250 | |
| }, | |
| { | |
| "epoch": 24.839934762348555, | |
| "grad_norm": 0.4210740923881531, | |
| "learning_rate": 0.00030210139860139856, | |
| "loss": 3.2095, | |
| "step": 85300 | |
| }, | |
| { | |
| "epoch": 24.854496738117426, | |
| "grad_norm": 0.4120892584323883, | |
| "learning_rate": 0.0003019265734265734, | |
| "loss": 3.2034, | |
| "step": 85350 | |
| }, | |
| { | |
| "epoch": 24.8690587138863, | |
| "grad_norm": 0.42725127935409546, | |
| "learning_rate": 0.0003017517482517482, | |
| "loss": 3.2062, | |
| "step": 85400 | |
| }, | |
| { | |
| "epoch": 24.88362068965517, | |
| "grad_norm": 0.4295431077480316, | |
| "learning_rate": 0.00030157692307692307, | |
| "loss": 3.2098, | |
| "step": 85450 | |
| }, | |
| { | |
| "epoch": 24.898182665424045, | |
| "grad_norm": 0.4166405200958252, | |
| "learning_rate": 0.00030140209790209787, | |
| "loss": 3.2043, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 24.912744641192916, | |
| "grad_norm": 0.4288575351238251, | |
| "learning_rate": 0.0003012272727272727, | |
| "loss": 3.2116, | |
| "step": 85550 | |
| }, | |
| { | |
| "epoch": 24.92730661696179, | |
| "grad_norm": 0.41819635033607483, | |
| "learning_rate": 0.0003010524475524475, | |
| "loss": 3.2256, | |
| "step": 85600 | |
| }, | |
| { | |
| "epoch": 24.94186859273066, | |
| "grad_norm": 0.39592012763023376, | |
| "learning_rate": 0.0003008776223776224, | |
| "loss": 3.2045, | |
| "step": 85650 | |
| }, | |
| { | |
| "epoch": 24.956430568499535, | |
| "grad_norm": 0.4047764241695404, | |
| "learning_rate": 0.0003007027972027972, | |
| "loss": 3.2122, | |
| "step": 85700 | |
| }, | |
| { | |
| "epoch": 24.970992544268405, | |
| "grad_norm": 0.4179820716381073, | |
| "learning_rate": 0.00030052797202797203, | |
| "loss": 3.2178, | |
| "step": 85750 | |
| }, | |
| { | |
| "epoch": 24.98555452003728, | |
| "grad_norm": 0.40104392170906067, | |
| "learning_rate": 0.0003003531468531468, | |
| "loss": 3.2109, | |
| "step": 85800 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 0.5622439384460449, | |
| "learning_rate": 0.00030017832167832163, | |
| "loss": 3.2232, | |
| "step": 85850 | |
| }, | |
| { | |
| "epoch": 25.01456197576887, | |
| "grad_norm": 0.4549800157546997, | |
| "learning_rate": 0.0003000034965034965, | |
| "loss": 3.1134, | |
| "step": 85900 | |
| }, | |
| { | |
| "epoch": 25.029123951537745, | |
| "grad_norm": 0.4355591833591461, | |
| "learning_rate": 0.0002998286713286713, | |
| "loss": 3.1201, | |
| "step": 85950 | |
| }, | |
| { | |
| "epoch": 25.043685927306615, | |
| "grad_norm": 0.409805566072464, | |
| "learning_rate": 0.00029965384615384614, | |
| "loss": 3.1188, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 25.043685927306615, | |
| "eval_accuracy": 0.37394857005527515, | |
| "eval_loss": 3.552666425704956, | |
| "eval_runtime": 53.5077, | |
| "eval_samples_per_second": 311.058, | |
| "eval_steps_per_second": 19.455, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 25.05824790307549, | |
| "grad_norm": 0.4548097848892212, | |
| "learning_rate": 0.00029947902097902094, | |
| "loss": 3.127, | |
| "step": 86050 | |
| }, | |
| { | |
| "epoch": 25.07280987884436, | |
| "grad_norm": 0.4102542996406555, | |
| "learning_rate": 0.0002993041958041958, | |
| "loss": 3.1309, | |
| "step": 86100 | |
| }, | |
| { | |
| "epoch": 25.087371854613234, | |
| "grad_norm": 0.43193888664245605, | |
| "learning_rate": 0.0002991293706293706, | |
| "loss": 3.1349, | |
| "step": 86150 | |
| }, | |
| { | |
| "epoch": 25.101933830382105, | |
| "grad_norm": 0.4661305844783783, | |
| "learning_rate": 0.0002989545454545454, | |
| "loss": 3.1198, | |
| "step": 86200 | |
| }, | |
| { | |
| "epoch": 25.11649580615098, | |
| "grad_norm": 0.43192169070243835, | |
| "learning_rate": 0.00029877972027972025, | |
| "loss": 3.1369, | |
| "step": 86250 | |
| }, | |
| { | |
| "epoch": 25.13105778191985, | |
| "grad_norm": 0.44566482305526733, | |
| "learning_rate": 0.0002986048951048951, | |
| "loss": 3.1434, | |
| "step": 86300 | |
| }, | |
| { | |
| "epoch": 25.145619757688724, | |
| "grad_norm": 0.41159921884536743, | |
| "learning_rate": 0.0002984300699300699, | |
| "loss": 3.1485, | |
| "step": 86350 | |
| }, | |
| { | |
| "epoch": 25.160181733457595, | |
| "grad_norm": 0.42221495509147644, | |
| "learning_rate": 0.00029825524475524475, | |
| "loss": 3.143, | |
| "step": 86400 | |
| }, | |
| { | |
| "epoch": 25.17474370922647, | |
| "grad_norm": 0.4047253727912903, | |
| "learning_rate": 0.00029808041958041955, | |
| "loss": 3.1483, | |
| "step": 86450 | |
| }, | |
| { | |
| "epoch": 25.18930568499534, | |
| "grad_norm": 0.420423686504364, | |
| "learning_rate": 0.0002979055944055944, | |
| "loss": 3.1678, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 25.203867660764214, | |
| "grad_norm": 0.41166287660598755, | |
| "learning_rate": 0.0002977307692307692, | |
| "loss": 3.1539, | |
| "step": 86550 | |
| }, | |
| { | |
| "epoch": 25.218429636533084, | |
| "grad_norm": 0.4156063497066498, | |
| "learning_rate": 0.000297555944055944, | |
| "loss": 3.1652, | |
| "step": 86600 | |
| }, | |
| { | |
| "epoch": 25.23299161230196, | |
| "grad_norm": 0.4309043884277344, | |
| "learning_rate": 0.00029738111888111886, | |
| "loss": 3.1514, | |
| "step": 86650 | |
| }, | |
| { | |
| "epoch": 25.24755358807083, | |
| "grad_norm": 0.40342429280281067, | |
| "learning_rate": 0.00029720629370629366, | |
| "loss": 3.1473, | |
| "step": 86700 | |
| }, | |
| { | |
| "epoch": 25.262115563839703, | |
| "grad_norm": 0.4230315387248993, | |
| "learning_rate": 0.0002970314685314685, | |
| "loss": 3.1495, | |
| "step": 86750 | |
| }, | |
| { | |
| "epoch": 25.276677539608574, | |
| "grad_norm": 0.4255284070968628, | |
| "learning_rate": 0.0002968566433566433, | |
| "loss": 3.1535, | |
| "step": 86800 | |
| }, | |
| { | |
| "epoch": 25.291239515377445, | |
| "grad_norm": 0.43190792202949524, | |
| "learning_rate": 0.00029668181818181817, | |
| "loss": 3.1664, | |
| "step": 86850 | |
| }, | |
| { | |
| "epoch": 25.30580149114632, | |
| "grad_norm": 0.41948994994163513, | |
| "learning_rate": 0.00029650699300699297, | |
| "loss": 3.1693, | |
| "step": 86900 | |
| }, | |
| { | |
| "epoch": 25.32036346691519, | |
| "grad_norm": 0.4156516194343567, | |
| "learning_rate": 0.0002963321678321678, | |
| "loss": 3.1674, | |
| "step": 86950 | |
| }, | |
| { | |
| "epoch": 25.334925442684064, | |
| "grad_norm": 0.43022507429122925, | |
| "learning_rate": 0.0002961573426573426, | |
| "loss": 3.1541, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 25.334925442684064, | |
| "eval_accuracy": 0.37386814756914805, | |
| "eval_loss": 3.5510289669036865, | |
| "eval_runtime": 53.6269, | |
| "eval_samples_per_second": 310.367, | |
| "eval_steps_per_second": 19.412, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 25.349487418452934, | |
| "grad_norm": 0.43121078610420227, | |
| "learning_rate": 0.0002959825174825175, | |
| "loss": 3.1686, | |
| "step": 87050 | |
| }, | |
| { | |
| "epoch": 25.36404939422181, | |
| "grad_norm": 0.42564132809638977, | |
| "learning_rate": 0.0002958076923076923, | |
| "loss": 3.1656, | |
| "step": 87100 | |
| }, | |
| { | |
| "epoch": 25.37861136999068, | |
| "grad_norm": 0.41207486391067505, | |
| "learning_rate": 0.00029563286713286713, | |
| "loss": 3.1703, | |
| "step": 87150 | |
| }, | |
| { | |
| "epoch": 25.393173345759553, | |
| "grad_norm": 0.43623030185699463, | |
| "learning_rate": 0.00029545804195804193, | |
| "loss": 3.169, | |
| "step": 87200 | |
| }, | |
| { | |
| "epoch": 25.407735321528424, | |
| "grad_norm": 0.44384080171585083, | |
| "learning_rate": 0.0002952832167832168, | |
| "loss": 3.1754, | |
| "step": 87250 | |
| }, | |
| { | |
| "epoch": 25.4222972972973, | |
| "grad_norm": 0.4300347864627838, | |
| "learning_rate": 0.0002951083916083916, | |
| "loss": 3.1774, | |
| "step": 87300 | |
| }, | |
| { | |
| "epoch": 25.43685927306617, | |
| "grad_norm": 0.4289652109146118, | |
| "learning_rate": 0.0002949335664335664, | |
| "loss": 3.1638, | |
| "step": 87350 | |
| }, | |
| { | |
| "epoch": 25.451421248835043, | |
| "grad_norm": 0.4287082850933075, | |
| "learning_rate": 0.00029475874125874124, | |
| "loss": 3.1745, | |
| "step": 87400 | |
| }, | |
| { | |
| "epoch": 25.465983224603914, | |
| "grad_norm": 0.39625516533851624, | |
| "learning_rate": 0.00029458391608391604, | |
| "loss": 3.1731, | |
| "step": 87450 | |
| }, | |
| { | |
| "epoch": 25.480545200372788, | |
| "grad_norm": 0.4283997416496277, | |
| "learning_rate": 0.0002944090909090909, | |
| "loss": 3.182, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 25.49510717614166, | |
| "grad_norm": 0.4386811852455139, | |
| "learning_rate": 0.0002942342657342657, | |
| "loss": 3.177, | |
| "step": 87550 | |
| }, | |
| { | |
| "epoch": 25.509669151910533, | |
| "grad_norm": 0.42211535573005676, | |
| "learning_rate": 0.00029405944055944054, | |
| "loss": 3.175, | |
| "step": 87600 | |
| }, | |
| { | |
| "epoch": 25.524231127679403, | |
| "grad_norm": 0.4209630787372589, | |
| "learning_rate": 0.0002938846153846154, | |
| "loss": 3.1778, | |
| "step": 87650 | |
| }, | |
| { | |
| "epoch": 25.538793103448278, | |
| "grad_norm": 0.44520241022109985, | |
| "learning_rate": 0.0002937097902097902, | |
| "loss": 3.1704, | |
| "step": 87700 | |
| }, | |
| { | |
| "epoch": 25.553355079217148, | |
| "grad_norm": 0.4534125030040741, | |
| "learning_rate": 0.000293534965034965, | |
| "loss": 3.1802, | |
| "step": 87750 | |
| }, | |
| { | |
| "epoch": 25.56791705498602, | |
| "grad_norm": 0.40445277094841003, | |
| "learning_rate": 0.00029336013986013985, | |
| "loss": 3.1892, | |
| "step": 87800 | |
| }, | |
| { | |
| "epoch": 25.582479030754893, | |
| "grad_norm": 0.38358354568481445, | |
| "learning_rate": 0.00029318531468531465, | |
| "loss": 3.1797, | |
| "step": 87850 | |
| }, | |
| { | |
| "epoch": 25.597041006523764, | |
| "grad_norm": 0.4403440058231354, | |
| "learning_rate": 0.0002930104895104895, | |
| "loss": 3.1851, | |
| "step": 87900 | |
| }, | |
| { | |
| "epoch": 25.611602982292638, | |
| "grad_norm": 0.4246091842651367, | |
| "learning_rate": 0.0002928356643356643, | |
| "loss": 3.1896, | |
| "step": 87950 | |
| }, | |
| { | |
| "epoch": 25.62616495806151, | |
| "grad_norm": 0.43709608912467957, | |
| "learning_rate": 0.00029266083916083916, | |
| "loss": 3.182, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 25.62616495806151, | |
| "eval_accuracy": 0.37425403441047733, | |
| "eval_loss": 3.543616533279419, | |
| "eval_runtime": 53.8799, | |
| "eval_samples_per_second": 308.909, | |
| "eval_steps_per_second": 19.321, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 25.640726933830383, | |
| "grad_norm": 0.42380014061927795, | |
| "learning_rate": 0.00029248601398601396, | |
| "loss": 3.192, | |
| "step": 88050 | |
| }, | |
| { | |
| "epoch": 25.655288909599253, | |
| "grad_norm": 0.42167308926582336, | |
| "learning_rate": 0.00029231118881118876, | |
| "loss": 3.1922, | |
| "step": 88100 | |
| }, | |
| { | |
| "epoch": 25.669850885368128, | |
| "grad_norm": 0.4025057852268219, | |
| "learning_rate": 0.0002921363636363636, | |
| "loss": 3.1967, | |
| "step": 88150 | |
| }, | |
| { | |
| "epoch": 25.684412861136998, | |
| "grad_norm": 0.4348795413970947, | |
| "learning_rate": 0.0002919615384615384, | |
| "loss": 3.1959, | |
| "step": 88200 | |
| }, | |
| { | |
| "epoch": 25.698974836905872, | |
| "grad_norm": 0.4117673635482788, | |
| "learning_rate": 0.00029178671328671326, | |
| "loss": 3.197, | |
| "step": 88250 | |
| }, | |
| { | |
| "epoch": 25.713536812674743, | |
| "grad_norm": 0.40845316648483276, | |
| "learning_rate": 0.00029161188811188806, | |
| "loss": 3.201, | |
| "step": 88300 | |
| }, | |
| { | |
| "epoch": 25.728098788443617, | |
| "grad_norm": 0.44190987944602966, | |
| "learning_rate": 0.0002914370629370629, | |
| "loss": 3.1909, | |
| "step": 88350 | |
| }, | |
| { | |
| "epoch": 25.742660764212488, | |
| "grad_norm": 0.4156600832939148, | |
| "learning_rate": 0.00029126223776223777, | |
| "loss": 3.2135, | |
| "step": 88400 | |
| }, | |
| { | |
| "epoch": 25.757222739981362, | |
| "grad_norm": 0.4604335427284241, | |
| "learning_rate": 0.00029108741258741257, | |
| "loss": 3.1903, | |
| "step": 88450 | |
| }, | |
| { | |
| "epoch": 25.771784715750233, | |
| "grad_norm": 0.5294921398162842, | |
| "learning_rate": 0.00029091258741258737, | |
| "loss": 3.2009, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 25.786346691519107, | |
| "grad_norm": 0.45587196946144104, | |
| "learning_rate": 0.0002907377622377622, | |
| "loss": 3.189, | |
| "step": 88550 | |
| }, | |
| { | |
| "epoch": 25.800908667287977, | |
| "grad_norm": 0.43664881587028503, | |
| "learning_rate": 0.000290562937062937, | |
| "loss": 3.2097, | |
| "step": 88600 | |
| }, | |
| { | |
| "epoch": 25.815470643056848, | |
| "grad_norm": 0.43888285756111145, | |
| "learning_rate": 0.0002903881118881119, | |
| "loss": 3.1963, | |
| "step": 88650 | |
| }, | |
| { | |
| "epoch": 25.830032618825722, | |
| "grad_norm": 0.4586959779262543, | |
| "learning_rate": 0.0002902132867132867, | |
| "loss": 3.2004, | |
| "step": 88700 | |
| }, | |
| { | |
| "epoch": 25.844594594594593, | |
| "grad_norm": 0.4349871873855591, | |
| "learning_rate": 0.00029003846153846153, | |
| "loss": 3.205, | |
| "step": 88750 | |
| }, | |
| { | |
| "epoch": 25.859156570363467, | |
| "grad_norm": 0.4294140934944153, | |
| "learning_rate": 0.00028986363636363633, | |
| "loss": 3.2124, | |
| "step": 88800 | |
| }, | |
| { | |
| "epoch": 25.873718546132338, | |
| "grad_norm": 0.3970581293106079, | |
| "learning_rate": 0.00028968881118881113, | |
| "loss": 3.2041, | |
| "step": 88850 | |
| }, | |
| { | |
| "epoch": 25.888280521901212, | |
| "grad_norm": 0.42786160111427307, | |
| "learning_rate": 0.000289513986013986, | |
| "loss": 3.2013, | |
| "step": 88900 | |
| }, | |
| { | |
| "epoch": 25.902842497670083, | |
| "grad_norm": 0.453769326210022, | |
| "learning_rate": 0.0002893391608391608, | |
| "loss": 3.1962, | |
| "step": 88950 | |
| }, | |
| { | |
| "epoch": 25.917404473438957, | |
| "grad_norm": 0.45318394899368286, | |
| "learning_rate": 0.00028916433566433564, | |
| "loss": 3.2141, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 25.917404473438957, | |
| "eval_accuracy": 0.3747393911688585, | |
| "eval_loss": 3.534339427947998, | |
| "eval_runtime": 53.6851, | |
| "eval_samples_per_second": 310.03, | |
| "eval_steps_per_second": 19.391, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 25.931966449207827, | |
| "grad_norm": 0.4190371036529541, | |
| "learning_rate": 0.0002889895104895105, | |
| "loss": 3.2111, | |
| "step": 89050 | |
| }, | |
| { | |
| "epoch": 25.9465284249767, | |
| "grad_norm": 0.4242444336414337, | |
| "learning_rate": 0.0002888146853146853, | |
| "loss": 3.2154, | |
| "step": 89100 | |
| }, | |
| { | |
| "epoch": 25.961090400745572, | |
| "grad_norm": 0.43644312024116516, | |
| "learning_rate": 0.00028863986013986015, | |
| "loss": 3.2004, | |
| "step": 89150 | |
| }, | |
| { | |
| "epoch": 25.975652376514446, | |
| "grad_norm": 0.41194868087768555, | |
| "learning_rate": 0.00028846503496503495, | |
| "loss": 3.1978, | |
| "step": 89200 | |
| }, | |
| { | |
| "epoch": 25.990214352283317, | |
| "grad_norm": 0.38906967639923096, | |
| "learning_rate": 0.00028829020979020975, | |
| "loss": 3.2196, | |
| "step": 89250 | |
| }, | |
| { | |
| "epoch": 26.004659832246038, | |
| "grad_norm": 0.4650445282459259, | |
| "learning_rate": 0.0002881153846153846, | |
| "loss": 3.1695, | |
| "step": 89300 | |
| }, | |
| { | |
| "epoch": 26.019221808014912, | |
| "grad_norm": 0.45053941011428833, | |
| "learning_rate": 0.0002879405594405594, | |
| "loss": 3.099, | |
| "step": 89350 | |
| }, | |
| { | |
| "epoch": 26.033783783783782, | |
| "grad_norm": 0.4252159595489502, | |
| "learning_rate": 0.00028776573426573425, | |
| "loss": 3.1137, | |
| "step": 89400 | |
| }, | |
| { | |
| "epoch": 26.048345759552657, | |
| "grad_norm": 0.4305402338504791, | |
| "learning_rate": 0.00028759090909090905, | |
| "loss": 3.1096, | |
| "step": 89450 | |
| }, | |
| { | |
| "epoch": 26.062907735321527, | |
| "grad_norm": 0.40122270584106445, | |
| "learning_rate": 0.0002874160839160839, | |
| "loss": 3.1085, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 26.0774697110904, | |
| "grad_norm": 0.4272627532482147, | |
| "learning_rate": 0.0002872412587412587, | |
| "loss": 3.1185, | |
| "step": 89550 | |
| }, | |
| { | |
| "epoch": 26.092031686859272, | |
| "grad_norm": 0.4182010293006897, | |
| "learning_rate": 0.0002870664335664335, | |
| "loss": 3.1124, | |
| "step": 89600 | |
| }, | |
| { | |
| "epoch": 26.106593662628146, | |
| "grad_norm": 0.4463525414466858, | |
| "learning_rate": 0.00028689160839160836, | |
| "loss": 3.1189, | |
| "step": 89650 | |
| }, | |
| { | |
| "epoch": 26.121155638397017, | |
| "grad_norm": 0.4242148995399475, | |
| "learning_rate": 0.0002867167832167832, | |
| "loss": 3.1286, | |
| "step": 89700 | |
| }, | |
| { | |
| "epoch": 26.13571761416589, | |
| "grad_norm": 0.46834519505500793, | |
| "learning_rate": 0.000286541958041958, | |
| "loss": 3.1437, | |
| "step": 89750 | |
| }, | |
| { | |
| "epoch": 26.15027958993476, | |
| "grad_norm": 0.4111859202384949, | |
| "learning_rate": 0.00028636713286713287, | |
| "loss": 3.1388, | |
| "step": 89800 | |
| }, | |
| { | |
| "epoch": 26.164841565703636, | |
| "grad_norm": 0.45419996976852417, | |
| "learning_rate": 0.00028619230769230767, | |
| "loss": 3.1428, | |
| "step": 89850 | |
| }, | |
| { | |
| "epoch": 26.179403541472507, | |
| "grad_norm": 0.42230865359306335, | |
| "learning_rate": 0.0002860174825174825, | |
| "loss": 3.1496, | |
| "step": 89900 | |
| }, | |
| { | |
| "epoch": 26.19396551724138, | |
| "grad_norm": 0.4368692636489868, | |
| "learning_rate": 0.0002858426573426573, | |
| "loss": 3.1308, | |
| "step": 89950 | |
| }, | |
| { | |
| "epoch": 26.20852749301025, | |
| "grad_norm": 0.40982940793037415, | |
| "learning_rate": 0.0002856678321678321, | |
| "loss": 3.1395, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 26.20852749301025, | |
| "eval_accuracy": 0.37377961228836776, | |
| "eval_loss": 3.556647300720215, | |
| "eval_runtime": 53.6833, | |
| "eval_samples_per_second": 310.041, | |
| "eval_steps_per_second": 19.392, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 26.223089468779126, | |
| "grad_norm": 0.44282498955726624, | |
| "learning_rate": 0.000285493006993007, | |
| "loss": 3.1518, | |
| "step": 90050 | |
| }, | |
| { | |
| "epoch": 26.237651444547996, | |
| "grad_norm": 0.4250069260597229, | |
| "learning_rate": 0.0002853181818181818, | |
| "loss": 3.147, | |
| "step": 90100 | |
| }, | |
| { | |
| "epoch": 26.252213420316867, | |
| "grad_norm": 0.4652498662471771, | |
| "learning_rate": 0.00028514335664335663, | |
| "loss": 3.144, | |
| "step": 90150 | |
| }, | |
| { | |
| "epoch": 26.26677539608574, | |
| "grad_norm": 0.41768208146095276, | |
| "learning_rate": 0.00028496853146853143, | |
| "loss": 3.1613, | |
| "step": 90200 | |
| }, | |
| { | |
| "epoch": 26.28133737185461, | |
| "grad_norm": 0.4293578565120697, | |
| "learning_rate": 0.0002847937062937063, | |
| "loss": 3.1477, | |
| "step": 90250 | |
| }, | |
| { | |
| "epoch": 26.295899347623486, | |
| "grad_norm": 0.43309634923934937, | |
| "learning_rate": 0.0002846188811188811, | |
| "loss": 3.16, | |
| "step": 90300 | |
| }, | |
| { | |
| "epoch": 26.310461323392357, | |
| "grad_norm": 0.4498419463634491, | |
| "learning_rate": 0.0002844440559440559, | |
| "loss": 3.1534, | |
| "step": 90350 | |
| }, | |
| { | |
| "epoch": 26.32502329916123, | |
| "grad_norm": 0.45427951216697693, | |
| "learning_rate": 0.00028426923076923074, | |
| "loss": 3.1634, | |
| "step": 90400 | |
| }, | |
| { | |
| "epoch": 26.3395852749301, | |
| "grad_norm": 0.43068617582321167, | |
| "learning_rate": 0.0002840944055944056, | |
| "loss": 3.1627, | |
| "step": 90450 | |
| }, | |
| { | |
| "epoch": 26.354147250698976, | |
| "grad_norm": 0.42055797576904297, | |
| "learning_rate": 0.0002839195804195804, | |
| "loss": 3.1581, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 26.368709226467846, | |
| "grad_norm": 0.4183354675769806, | |
| "learning_rate": 0.00028374475524475524, | |
| "loss": 3.1586, | |
| "step": 90550 | |
| }, | |
| { | |
| "epoch": 26.38327120223672, | |
| "grad_norm": 0.43487775325775146, | |
| "learning_rate": 0.00028356993006993004, | |
| "loss": 3.156, | |
| "step": 90600 | |
| }, | |
| { | |
| "epoch": 26.39783317800559, | |
| "grad_norm": 0.42014575004577637, | |
| "learning_rate": 0.0002833951048951049, | |
| "loss": 3.1716, | |
| "step": 90650 | |
| }, | |
| { | |
| "epoch": 26.412395153774465, | |
| "grad_norm": 0.42945271730422974, | |
| "learning_rate": 0.0002832202797202797, | |
| "loss": 3.1736, | |
| "step": 90700 | |
| }, | |
| { | |
| "epoch": 26.426957129543336, | |
| "grad_norm": 0.41654732823371887, | |
| "learning_rate": 0.0002830454545454545, | |
| "loss": 3.1642, | |
| "step": 90750 | |
| }, | |
| { | |
| "epoch": 26.44151910531221, | |
| "grad_norm": 0.4265001118183136, | |
| "learning_rate": 0.00028287062937062935, | |
| "loss": 3.1667, | |
| "step": 90800 | |
| }, | |
| { | |
| "epoch": 26.45608108108108, | |
| "grad_norm": 0.4233382046222687, | |
| "learning_rate": 0.00028269580419580415, | |
| "loss": 3.163, | |
| "step": 90850 | |
| }, | |
| { | |
| "epoch": 26.470643056849955, | |
| "grad_norm": 0.4084939658641815, | |
| "learning_rate": 0.000282520979020979, | |
| "loss": 3.1625, | |
| "step": 90900 | |
| }, | |
| { | |
| "epoch": 26.485205032618826, | |
| "grad_norm": 0.45396101474761963, | |
| "learning_rate": 0.0002823461538461538, | |
| "loss": 3.1666, | |
| "step": 90950 | |
| }, | |
| { | |
| "epoch": 26.4997670083877, | |
| "grad_norm": 0.42796140909194946, | |
| "learning_rate": 0.00028217132867132866, | |
| "loss": 3.1696, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 26.4997670083877, | |
| "eval_accuracy": 0.3743129403542634, | |
| "eval_loss": 3.5446956157684326, | |
| "eval_runtime": 53.4825, | |
| "eval_samples_per_second": 311.205, | |
| "eval_steps_per_second": 19.464, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 26.51432898415657, | |
| "grad_norm": 0.46724438667297363, | |
| "learning_rate": 0.00028199650349650346, | |
| "loss": 3.1759, | |
| "step": 91050 | |
| }, | |
| { | |
| "epoch": 26.52889095992544, | |
| "grad_norm": 0.41262003779411316, | |
| "learning_rate": 0.0002818216783216783, | |
| "loss": 3.1775, | |
| "step": 91100 | |
| }, | |
| { | |
| "epoch": 26.543452935694315, | |
| "grad_norm": 0.3990762233734131, | |
| "learning_rate": 0.0002816468531468531, | |
| "loss": 3.179, | |
| "step": 91150 | |
| }, | |
| { | |
| "epoch": 26.558014911463186, | |
| "grad_norm": 0.4612864553928375, | |
| "learning_rate": 0.00028147202797202796, | |
| "loss": 3.1815, | |
| "step": 91200 | |
| }, | |
| { | |
| "epoch": 26.57257688723206, | |
| "grad_norm": 0.4417341947555542, | |
| "learning_rate": 0.00028129720279720276, | |
| "loss": 3.1754, | |
| "step": 91250 | |
| }, | |
| { | |
| "epoch": 26.58713886300093, | |
| "grad_norm": 0.4242549538612366, | |
| "learning_rate": 0.0002811223776223776, | |
| "loss": 3.1781, | |
| "step": 91300 | |
| }, | |
| { | |
| "epoch": 26.601700838769805, | |
| "grad_norm": 0.4152440130710602, | |
| "learning_rate": 0.0002809475524475524, | |
| "loss": 3.173, | |
| "step": 91350 | |
| }, | |
| { | |
| "epoch": 26.616262814538675, | |
| "grad_norm": 0.407860666513443, | |
| "learning_rate": 0.00028077272727272727, | |
| "loss": 3.1779, | |
| "step": 91400 | |
| }, | |
| { | |
| "epoch": 26.63082479030755, | |
| "grad_norm": 0.42334768176078796, | |
| "learning_rate": 0.00028059790209790207, | |
| "loss": 3.1807, | |
| "step": 91450 | |
| }, | |
| { | |
| "epoch": 26.64538676607642, | |
| "grad_norm": 0.41385746002197266, | |
| "learning_rate": 0.00028042307692307687, | |
| "loss": 3.184, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 26.659948741845295, | |
| "grad_norm": 0.4681982696056366, | |
| "learning_rate": 0.0002802482517482517, | |
| "loss": 3.1806, | |
| "step": 91550 | |
| }, | |
| { | |
| "epoch": 26.674510717614165, | |
| "grad_norm": 0.44684475660324097, | |
| "learning_rate": 0.0002800734265734265, | |
| "loss": 3.1788, | |
| "step": 91600 | |
| }, | |
| { | |
| "epoch": 26.68907269338304, | |
| "grad_norm": 0.45268094539642334, | |
| "learning_rate": 0.0002798986013986014, | |
| "loss": 3.1951, | |
| "step": 91650 | |
| }, | |
| { | |
| "epoch": 26.70363466915191, | |
| "grad_norm": 0.4566771984100342, | |
| "learning_rate": 0.0002797237762237762, | |
| "loss": 3.1857, | |
| "step": 91700 | |
| }, | |
| { | |
| "epoch": 26.718196644920784, | |
| "grad_norm": 0.4360271394252777, | |
| "learning_rate": 0.00027954895104895103, | |
| "loss": 3.1925, | |
| "step": 91750 | |
| }, | |
| { | |
| "epoch": 26.732758620689655, | |
| "grad_norm": 0.41877779364585876, | |
| "learning_rate": 0.0002793741258741259, | |
| "loss": 3.1743, | |
| "step": 91800 | |
| }, | |
| { | |
| "epoch": 26.74732059645853, | |
| "grad_norm": 0.451029509305954, | |
| "learning_rate": 0.0002791993006993007, | |
| "loss": 3.1816, | |
| "step": 91850 | |
| }, | |
| { | |
| "epoch": 26.7618825722274, | |
| "grad_norm": 0.42223063111305237, | |
| "learning_rate": 0.0002790244755244755, | |
| "loss": 3.1882, | |
| "step": 91900 | |
| }, | |
| { | |
| "epoch": 26.776444547996274, | |
| "grad_norm": 0.44341567158699036, | |
| "learning_rate": 0.00027884965034965034, | |
| "loss": 3.1878, | |
| "step": 91950 | |
| }, | |
| { | |
| "epoch": 26.791006523765144, | |
| "grad_norm": 0.4176470935344696, | |
| "learning_rate": 0.00027867482517482514, | |
| "loss": 3.1961, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 26.791006523765144, | |
| "eval_accuracy": 0.3744488590588876, | |
| "eval_loss": 3.5415284633636475, | |
| "eval_runtime": 53.6177, | |
| "eval_samples_per_second": 310.42, | |
| "eval_steps_per_second": 19.415, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 26.805568499534015, | |
| "grad_norm": 0.4171764850616455, | |
| "learning_rate": 0.0002785, | |
| "loss": 3.1802, | |
| "step": 92050 | |
| }, | |
| { | |
| "epoch": 26.82013047530289, | |
| "grad_norm": 0.42712369561195374, | |
| "learning_rate": 0.0002783251748251748, | |
| "loss": 3.195, | |
| "step": 92100 | |
| }, | |
| { | |
| "epoch": 26.83469245107176, | |
| "grad_norm": 0.4453660547733307, | |
| "learning_rate": 0.00027815034965034965, | |
| "loss": 3.1924, | |
| "step": 92150 | |
| }, | |
| { | |
| "epoch": 26.849254426840634, | |
| "grad_norm": 0.42237964272499084, | |
| "learning_rate": 0.00027797552447552445, | |
| "loss": 3.1995, | |
| "step": 92200 | |
| }, | |
| { | |
| "epoch": 26.863816402609505, | |
| "grad_norm": 0.4148341417312622, | |
| "learning_rate": 0.00027780069930069925, | |
| "loss": 3.1963, | |
| "step": 92250 | |
| }, | |
| { | |
| "epoch": 26.87837837837838, | |
| "grad_norm": 0.4194555878639221, | |
| "learning_rate": 0.0002776258741258741, | |
| "loss": 3.1966, | |
| "step": 92300 | |
| }, | |
| { | |
| "epoch": 26.89294035414725, | |
| "grad_norm": 0.4421636164188385, | |
| "learning_rate": 0.0002774510489510489, | |
| "loss": 3.2083, | |
| "step": 92350 | |
| }, | |
| { | |
| "epoch": 26.907502329916124, | |
| "grad_norm": 0.42861008644104004, | |
| "learning_rate": 0.00027727622377622375, | |
| "loss": 3.1808, | |
| "step": 92400 | |
| }, | |
| { | |
| "epoch": 26.922064305684994, | |
| "grad_norm": 0.4487074017524719, | |
| "learning_rate": 0.00027710139860139855, | |
| "loss": 3.2002, | |
| "step": 92450 | |
| }, | |
| { | |
| "epoch": 26.93662628145387, | |
| "grad_norm": 0.4668884873390198, | |
| "learning_rate": 0.0002769265734265734, | |
| "loss": 3.1858, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 26.95118825722274, | |
| "grad_norm": 0.4213342070579529, | |
| "learning_rate": 0.00027675174825174826, | |
| "loss": 3.2018, | |
| "step": 92550 | |
| }, | |
| { | |
| "epoch": 26.965750232991613, | |
| "grad_norm": 0.4327002167701721, | |
| "learning_rate": 0.00027657692307692306, | |
| "loss": 3.1964, | |
| "step": 92600 | |
| }, | |
| { | |
| "epoch": 26.980312208760484, | |
| "grad_norm": 0.43151915073394775, | |
| "learning_rate": 0.00027640209790209786, | |
| "loss": 3.2008, | |
| "step": 92650 | |
| }, | |
| { | |
| "epoch": 26.99487418452936, | |
| "grad_norm": 0.45595821738243103, | |
| "learning_rate": 0.0002762272727272727, | |
| "loss": 3.197, | |
| "step": 92700 | |
| }, | |
| { | |
| "epoch": 27.00931966449208, | |
| "grad_norm": 0.43289080262184143, | |
| "learning_rate": 0.0002760524475524475, | |
| "loss": 3.1388, | |
| "step": 92750 | |
| }, | |
| { | |
| "epoch": 27.02388164026095, | |
| "grad_norm": 0.4297803044319153, | |
| "learning_rate": 0.00027587762237762237, | |
| "loss": 3.1002, | |
| "step": 92800 | |
| }, | |
| { | |
| "epoch": 27.038443616029824, | |
| "grad_norm": 0.44579535722732544, | |
| "learning_rate": 0.00027570279720279717, | |
| "loss": 3.0885, | |
| "step": 92850 | |
| }, | |
| { | |
| "epoch": 27.053005591798694, | |
| "grad_norm": 0.43222174048423767, | |
| "learning_rate": 0.000275527972027972, | |
| "loss": 3.1066, | |
| "step": 92900 | |
| }, | |
| { | |
| "epoch": 27.06756756756757, | |
| "grad_norm": 0.4319220185279846, | |
| "learning_rate": 0.0002753531468531468, | |
| "loss": 3.0927, | |
| "step": 92950 | |
| }, | |
| { | |
| "epoch": 27.08212954333644, | |
| "grad_norm": 0.4116879999637604, | |
| "learning_rate": 0.0002751783216783216, | |
| "loss": 3.1084, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 27.08212954333644, | |
| "eval_accuracy": 0.3740686159007953, | |
| "eval_loss": 3.5531694889068604, | |
| "eval_runtime": 53.7303, | |
| "eval_samples_per_second": 309.769, | |
| "eval_steps_per_second": 19.375, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 27.096691519105313, | |
| "grad_norm": 0.4252121150493622, | |
| "learning_rate": 0.0002750034965034965, | |
| "loss": 3.1168, | |
| "step": 93050 | |
| }, | |
| { | |
| "epoch": 27.111253494874184, | |
| "grad_norm": 0.4439890682697296, | |
| "learning_rate": 0.0002748286713286713, | |
| "loss": 3.1125, | |
| "step": 93100 | |
| }, | |
| { | |
| "epoch": 27.125815470643058, | |
| "grad_norm": 0.4510648250579834, | |
| "learning_rate": 0.00027465384615384613, | |
| "loss": 3.1169, | |
| "step": 93150 | |
| }, | |
| { | |
| "epoch": 27.14037744641193, | |
| "grad_norm": 0.4003378748893738, | |
| "learning_rate": 0.000274479020979021, | |
| "loss": 3.1248, | |
| "step": 93200 | |
| }, | |
| { | |
| "epoch": 27.154939422180803, | |
| "grad_norm": 0.43054619431495667, | |
| "learning_rate": 0.0002743041958041958, | |
| "loss": 3.116, | |
| "step": 93250 | |
| }, | |
| { | |
| "epoch": 27.169501397949674, | |
| "grad_norm": 0.4461906850337982, | |
| "learning_rate": 0.00027412937062937064, | |
| "loss": 3.1239, | |
| "step": 93300 | |
| }, | |
| { | |
| "epoch": 27.184063373718548, | |
| "grad_norm": 0.4158555269241333, | |
| "learning_rate": 0.00027395454545454544, | |
| "loss": 3.1211, | |
| "step": 93350 | |
| }, | |
| { | |
| "epoch": 27.19862534948742, | |
| "grad_norm": 0.444968581199646, | |
| "learning_rate": 0.00027377972027972024, | |
| "loss": 3.1313, | |
| "step": 93400 | |
| }, | |
| { | |
| "epoch": 27.21318732525629, | |
| "grad_norm": 0.42571595311164856, | |
| "learning_rate": 0.0002736048951048951, | |
| "loss": 3.1396, | |
| "step": 93450 | |
| }, | |
| { | |
| "epoch": 27.227749301025163, | |
| "grad_norm": 0.45029646158218384, | |
| "learning_rate": 0.0002734300699300699, | |
| "loss": 3.141, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 27.242311276794034, | |
| "grad_norm": 0.4302981197834015, | |
| "learning_rate": 0.00027325524475524474, | |
| "loss": 3.1396, | |
| "step": 93550 | |
| }, | |
| { | |
| "epoch": 27.256873252562908, | |
| "grad_norm": 0.4424735903739929, | |
| "learning_rate": 0.00027308041958041954, | |
| "loss": 3.1427, | |
| "step": 93600 | |
| }, | |
| { | |
| "epoch": 27.27143522833178, | |
| "grad_norm": 0.4379088580608368, | |
| "learning_rate": 0.0002729055944055944, | |
| "loss": 3.1474, | |
| "step": 93650 | |
| }, | |
| { | |
| "epoch": 27.285997204100653, | |
| "grad_norm": 0.428368479013443, | |
| "learning_rate": 0.0002727307692307692, | |
| "loss": 3.1487, | |
| "step": 93700 | |
| }, | |
| { | |
| "epoch": 27.300559179869524, | |
| "grad_norm": 0.4178659915924072, | |
| "learning_rate": 0.000272555944055944, | |
| "loss": 3.1444, | |
| "step": 93750 | |
| }, | |
| { | |
| "epoch": 27.315121155638398, | |
| "grad_norm": 0.42984670400619507, | |
| "learning_rate": 0.00027238111888111885, | |
| "loss": 3.1458, | |
| "step": 93800 | |
| }, | |
| { | |
| "epoch": 27.32968313140727, | |
| "grad_norm": 0.4429548680782318, | |
| "learning_rate": 0.0002722062937062937, | |
| "loss": 3.146, | |
| "step": 93850 | |
| }, | |
| { | |
| "epoch": 27.344245107176143, | |
| "grad_norm": 0.475292444229126, | |
| "learning_rate": 0.0002720314685314685, | |
| "loss": 3.1438, | |
| "step": 93900 | |
| }, | |
| { | |
| "epoch": 27.358807082945013, | |
| "grad_norm": 0.4281918406486511, | |
| "learning_rate": 0.00027185664335664336, | |
| "loss": 3.1511, | |
| "step": 93950 | |
| }, | |
| { | |
| "epoch": 27.373369058713887, | |
| "grad_norm": 0.40582549571990967, | |
| "learning_rate": 0.00027168181818181816, | |
| "loss": 3.1561, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 27.373369058713887, | |
| "eval_accuracy": 0.374502474049639, | |
| "eval_loss": 3.548748254776001, | |
| "eval_runtime": 53.6868, | |
| "eval_samples_per_second": 310.02, | |
| "eval_steps_per_second": 19.39, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 27.387931034482758, | |
| "grad_norm": 0.47851642966270447, | |
| "learning_rate": 0.000271506993006993, | |
| "loss": 3.1493, | |
| "step": 94050 | |
| }, | |
| { | |
| "epoch": 27.402493010251632, | |
| "grad_norm": 0.45141974091529846, | |
| "learning_rate": 0.0002713321678321678, | |
| "loss": 3.1604, | |
| "step": 94100 | |
| }, | |
| { | |
| "epoch": 27.417054986020503, | |
| "grad_norm": 0.44606834650039673, | |
| "learning_rate": 0.0002711573426573426, | |
| "loss": 3.1586, | |
| "step": 94150 | |
| }, | |
| { | |
| "epoch": 27.431616961789377, | |
| "grad_norm": 0.4571624994277954, | |
| "learning_rate": 0.00027098251748251746, | |
| "loss": 3.1612, | |
| "step": 94200 | |
| }, | |
| { | |
| "epoch": 27.446178937558248, | |
| "grad_norm": 0.4431142807006836, | |
| "learning_rate": 0.00027080769230769226, | |
| "loss": 3.1489, | |
| "step": 94250 | |
| }, | |
| { | |
| "epoch": 27.460740913327122, | |
| "grad_norm": 0.4453687071800232, | |
| "learning_rate": 0.0002706328671328671, | |
| "loss": 3.1676, | |
| "step": 94300 | |
| }, | |
| { | |
| "epoch": 27.475302889095992, | |
| "grad_norm": 0.44453132152557373, | |
| "learning_rate": 0.0002704580419580419, | |
| "loss": 3.1509, | |
| "step": 94350 | |
| }, | |
| { | |
| "epoch": 27.489864864864863, | |
| "grad_norm": 0.45242783427238464, | |
| "learning_rate": 0.00027028321678321677, | |
| "loss": 3.1541, | |
| "step": 94400 | |
| }, | |
| { | |
| "epoch": 27.504426840633737, | |
| "grad_norm": 0.4506557583808899, | |
| "learning_rate": 0.00027010839160839157, | |
| "loss": 3.1683, | |
| "step": 94450 | |
| }, | |
| { | |
| "epoch": 27.518988816402608, | |
| "grad_norm": 0.4558444321155548, | |
| "learning_rate": 0.00026993356643356637, | |
| "loss": 3.1673, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 27.533550792171482, | |
| "grad_norm": 0.4382563531398773, | |
| "learning_rate": 0.0002697587412587412, | |
| "loss": 3.1651, | |
| "step": 94550 | |
| }, | |
| { | |
| "epoch": 27.548112767940353, | |
| "grad_norm": 0.41427773237228394, | |
| "learning_rate": 0.0002695839160839161, | |
| "loss": 3.1763, | |
| "step": 94600 | |
| }, | |
| { | |
| "epoch": 27.562674743709227, | |
| "grad_norm": 0.4399355351924896, | |
| "learning_rate": 0.0002694090909090909, | |
| "loss": 3.1505, | |
| "step": 94650 | |
| }, | |
| { | |
| "epoch": 27.577236719478098, | |
| "grad_norm": 0.4320809841156006, | |
| "learning_rate": 0.00026923426573426573, | |
| "loss": 3.1723, | |
| "step": 94700 | |
| }, | |
| { | |
| "epoch": 27.591798695246972, | |
| "grad_norm": 0.4338119328022003, | |
| "learning_rate": 0.00026905944055944053, | |
| "loss": 3.1757, | |
| "step": 94750 | |
| }, | |
| { | |
| "epoch": 27.606360671015842, | |
| "grad_norm": 0.42641645669937134, | |
| "learning_rate": 0.0002688846153846154, | |
| "loss": 3.1758, | |
| "step": 94800 | |
| }, | |
| { | |
| "epoch": 27.620922646784717, | |
| "grad_norm": 0.4421967566013336, | |
| "learning_rate": 0.0002687097902097902, | |
| "loss": 3.1772, | |
| "step": 94850 | |
| }, | |
| { | |
| "epoch": 27.635484622553587, | |
| "grad_norm": 0.46785882115364075, | |
| "learning_rate": 0.000268534965034965, | |
| "loss": 3.1662, | |
| "step": 94900 | |
| }, | |
| { | |
| "epoch": 27.65004659832246, | |
| "grad_norm": 0.4574052095413208, | |
| "learning_rate": 0.00026836013986013984, | |
| "loss": 3.1755, | |
| "step": 94950 | |
| }, | |
| { | |
| "epoch": 27.664608574091332, | |
| "grad_norm": 0.4320479929447174, | |
| "learning_rate": 0.00026818531468531464, | |
| "loss": 3.1751, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 27.664608574091332, | |
| "eval_accuracy": 0.3745143492997835, | |
| "eval_loss": 3.5431621074676514, | |
| "eval_runtime": 53.7035, | |
| "eval_samples_per_second": 309.924, | |
| "eval_steps_per_second": 19.384, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 27.679170549860206, | |
| "grad_norm": 0.43245890736579895, | |
| "learning_rate": 0.0002680104895104895, | |
| "loss": 3.1758, | |
| "step": 95050 | |
| }, | |
| { | |
| "epoch": 27.693732525629077, | |
| "grad_norm": 0.4555778503417969, | |
| "learning_rate": 0.0002678356643356643, | |
| "loss": 3.1862, | |
| "step": 95100 | |
| }, | |
| { | |
| "epoch": 27.70829450139795, | |
| "grad_norm": 0.4318227171897888, | |
| "learning_rate": 0.00026766083916083915, | |
| "loss": 3.1614, | |
| "step": 95150 | |
| }, | |
| { | |
| "epoch": 27.72285647716682, | |
| "grad_norm": 0.44459792971611023, | |
| "learning_rate": 0.00026748601398601395, | |
| "loss": 3.1822, | |
| "step": 95200 | |
| }, | |
| { | |
| "epoch": 27.737418452935696, | |
| "grad_norm": 0.42615237832069397, | |
| "learning_rate": 0.0002673111888111888, | |
| "loss": 3.1924, | |
| "step": 95250 | |
| }, | |
| { | |
| "epoch": 27.751980428704567, | |
| "grad_norm": 0.46632900834083557, | |
| "learning_rate": 0.0002671363636363636, | |
| "loss": 3.1863, | |
| "step": 95300 | |
| }, | |
| { | |
| "epoch": 27.766542404473437, | |
| "grad_norm": 0.4340624213218689, | |
| "learning_rate": 0.00026696153846153845, | |
| "loss": 3.1919, | |
| "step": 95350 | |
| }, | |
| { | |
| "epoch": 27.78110438024231, | |
| "grad_norm": 0.44297027587890625, | |
| "learning_rate": 0.00026678671328671325, | |
| "loss": 3.1803, | |
| "step": 95400 | |
| }, | |
| { | |
| "epoch": 27.795666356011182, | |
| "grad_norm": 0.4163863956928253, | |
| "learning_rate": 0.0002666118881118881, | |
| "loss": 3.1778, | |
| "step": 95450 | |
| }, | |
| { | |
| "epoch": 27.810228331780056, | |
| "grad_norm": 0.4271012842655182, | |
| "learning_rate": 0.0002664370629370629, | |
| "loss": 3.1921, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 27.824790307548927, | |
| "grad_norm": 0.4465010464191437, | |
| "learning_rate": 0.00026626223776223776, | |
| "loss": 3.1824, | |
| "step": 95550 | |
| }, | |
| { | |
| "epoch": 27.8393522833178, | |
| "grad_norm": 0.44772741198539734, | |
| "learning_rate": 0.00026608741258741256, | |
| "loss": 3.1743, | |
| "step": 95600 | |
| }, | |
| { | |
| "epoch": 27.85391425908667, | |
| "grad_norm": 0.42869317531585693, | |
| "learning_rate": 0.00026591258741258736, | |
| "loss": 3.1881, | |
| "step": 95650 | |
| }, | |
| { | |
| "epoch": 27.868476234855546, | |
| "grad_norm": 0.4499087631702423, | |
| "learning_rate": 0.0002657377622377622, | |
| "loss": 3.1821, | |
| "step": 95700 | |
| }, | |
| { | |
| "epoch": 27.883038210624417, | |
| "grad_norm": 0.43807747960090637, | |
| "learning_rate": 0.000265562937062937, | |
| "loss": 3.1826, | |
| "step": 95750 | |
| }, | |
| { | |
| "epoch": 27.89760018639329, | |
| "grad_norm": 0.42944756150245667, | |
| "learning_rate": 0.00026538811188811187, | |
| "loss": 3.1834, | |
| "step": 95800 | |
| }, | |
| { | |
| "epoch": 27.91216216216216, | |
| "grad_norm": 0.44492489099502563, | |
| "learning_rate": 0.00026521328671328667, | |
| "loss": 3.1759, | |
| "step": 95850 | |
| }, | |
| { | |
| "epoch": 27.926724137931036, | |
| "grad_norm": 0.44922009110450745, | |
| "learning_rate": 0.0002650384615384615, | |
| "loss": 3.191, | |
| "step": 95900 | |
| }, | |
| { | |
| "epoch": 27.941286113699906, | |
| "grad_norm": 0.4366289973258972, | |
| "learning_rate": 0.0002648636363636364, | |
| "loss": 3.2052, | |
| "step": 95950 | |
| }, | |
| { | |
| "epoch": 27.95584808946878, | |
| "grad_norm": 0.4741586446762085, | |
| "learning_rate": 0.0002646888111888112, | |
| "loss": 3.1853, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 27.95584808946878, | |
| "eval_accuracy": 0.3749015294851879, | |
| "eval_loss": 3.535959005355835, | |
| "eval_runtime": 53.7399, | |
| "eval_samples_per_second": 309.714, | |
| "eval_steps_per_second": 19.371, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 27.97041006523765, | |
| "grad_norm": 0.4826781153678894, | |
| "learning_rate": 0.000264513986013986, | |
| "loss": 3.2059, | |
| "step": 96050 | |
| }, | |
| { | |
| "epoch": 27.984972041006525, | |
| "grad_norm": 0.42744797468185425, | |
| "learning_rate": 0.00026433916083916083, | |
| "loss": 3.1952, | |
| "step": 96100 | |
| }, | |
| { | |
| "epoch": 27.999534016775396, | |
| "grad_norm": 0.4376899302005768, | |
| "learning_rate": 0.00026416433566433563, | |
| "loss": 3.1929, | |
| "step": 96150 | |
| }, | |
| { | |
| "epoch": 28.013979496738116, | |
| "grad_norm": 0.4622137248516083, | |
| "learning_rate": 0.0002639895104895105, | |
| "loss": 3.0896, | |
| "step": 96200 | |
| }, | |
| { | |
| "epoch": 28.02854147250699, | |
| "grad_norm": 0.44420769810676575, | |
| "learning_rate": 0.0002638146853146853, | |
| "loss": 3.1003, | |
| "step": 96250 | |
| }, | |
| { | |
| "epoch": 28.04310344827586, | |
| "grad_norm": 0.4357249438762665, | |
| "learning_rate": 0.00026363986013986014, | |
| "loss": 3.0941, | |
| "step": 96300 | |
| }, | |
| { | |
| "epoch": 28.057665424044735, | |
| "grad_norm": 0.4448012113571167, | |
| "learning_rate": 0.00026346503496503494, | |
| "loss": 3.0897, | |
| "step": 96350 | |
| }, | |
| { | |
| "epoch": 28.072227399813606, | |
| "grad_norm": 0.4402657151222229, | |
| "learning_rate": 0.00026329020979020974, | |
| "loss": 3.1048, | |
| "step": 96400 | |
| }, | |
| { | |
| "epoch": 28.08678937558248, | |
| "grad_norm": 0.4506484270095825, | |
| "learning_rate": 0.0002631153846153846, | |
| "loss": 3.1187, | |
| "step": 96450 | |
| }, | |
| { | |
| "epoch": 28.10135135135135, | |
| "grad_norm": 0.44956478476524353, | |
| "learning_rate": 0.0002629405594405594, | |
| "loss": 3.1123, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 28.115913327120225, | |
| "grad_norm": 0.4638758599758148, | |
| "learning_rate": 0.00026276573426573424, | |
| "loss": 3.1151, | |
| "step": 96550 | |
| }, | |
| { | |
| "epoch": 28.130475302889096, | |
| "grad_norm": 0.4638550877571106, | |
| "learning_rate": 0.00026259090909090904, | |
| "loss": 3.1031, | |
| "step": 96600 | |
| }, | |
| { | |
| "epoch": 28.14503727865797, | |
| "grad_norm": 0.4719196856021881, | |
| "learning_rate": 0.0002624160839160839, | |
| "loss": 3.1213, | |
| "step": 96650 | |
| }, | |
| { | |
| "epoch": 28.15959925442684, | |
| "grad_norm": 0.4546055495738983, | |
| "learning_rate": 0.00026224125874125875, | |
| "loss": 3.1215, | |
| "step": 96700 | |
| }, | |
| { | |
| "epoch": 28.174161230195715, | |
| "grad_norm": 0.4388442635536194, | |
| "learning_rate": 0.00026206643356643355, | |
| "loss": 3.1116, | |
| "step": 96750 | |
| }, | |
| { | |
| "epoch": 28.188723205964585, | |
| "grad_norm": 0.4409039318561554, | |
| "learning_rate": 0.00026189160839160835, | |
| "loss": 3.1271, | |
| "step": 96800 | |
| }, | |
| { | |
| "epoch": 28.203285181733456, | |
| "grad_norm": 0.47931012511253357, | |
| "learning_rate": 0.0002617167832167832, | |
| "loss": 3.1201, | |
| "step": 96850 | |
| }, | |
| { | |
| "epoch": 28.21784715750233, | |
| "grad_norm": 0.49225330352783203, | |
| "learning_rate": 0.000261541958041958, | |
| "loss": 3.1317, | |
| "step": 96900 | |
| }, | |
| { | |
| "epoch": 28.2324091332712, | |
| "grad_norm": 0.46105310320854187, | |
| "learning_rate": 0.00026136713286713286, | |
| "loss": 3.1278, | |
| "step": 96950 | |
| }, | |
| { | |
| "epoch": 28.246971109040075, | |
| "grad_norm": 0.4445840120315552, | |
| "learning_rate": 0.00026119230769230766, | |
| "loss": 3.139, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 28.246971109040075, | |
| "eval_accuracy": 0.3739401045304197, | |
| "eval_loss": 3.554464340209961, | |
| "eval_runtime": 53.4624, | |
| "eval_samples_per_second": 311.322, | |
| "eval_steps_per_second": 19.472, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 28.261533084808946, | |
| "grad_norm": 0.4632137417793274, | |
| "learning_rate": 0.0002610174825174825, | |
| "loss": 3.1351, | |
| "step": 97050 | |
| }, | |
| { | |
| "epoch": 28.27609506057782, | |
| "grad_norm": 0.4355744421482086, | |
| "learning_rate": 0.0002608426573426573, | |
| "loss": 3.1259, | |
| "step": 97100 | |
| }, | |
| { | |
| "epoch": 28.29065703634669, | |
| "grad_norm": 0.42398175597190857, | |
| "learning_rate": 0.0002606678321678321, | |
| "loss": 3.1389, | |
| "step": 97150 | |
| }, | |
| { | |
| "epoch": 28.305219012115565, | |
| "grad_norm": 0.42285165190696716, | |
| "learning_rate": 0.00026049300699300696, | |
| "loss": 3.1449, | |
| "step": 97200 | |
| }, | |
| { | |
| "epoch": 28.319780987884435, | |
| "grad_norm": 0.4170607924461365, | |
| "learning_rate": 0.00026031818181818176, | |
| "loss": 3.135, | |
| "step": 97250 | |
| }, | |
| { | |
| "epoch": 28.33434296365331, | |
| "grad_norm": 0.4427075684070587, | |
| "learning_rate": 0.0002601433566433566, | |
| "loss": 3.1346, | |
| "step": 97300 | |
| }, | |
| { | |
| "epoch": 28.34890493942218, | |
| "grad_norm": 0.4347171485424042, | |
| "learning_rate": 0.00025996853146853147, | |
| "loss": 3.1472, | |
| "step": 97350 | |
| }, | |
| { | |
| "epoch": 28.363466915191054, | |
| "grad_norm": 0.44221243262290955, | |
| "learning_rate": 0.00025979370629370627, | |
| "loss": 3.1354, | |
| "step": 97400 | |
| }, | |
| { | |
| "epoch": 28.378028890959925, | |
| "grad_norm": 0.45819225907325745, | |
| "learning_rate": 0.0002596188811188811, | |
| "loss": 3.1474, | |
| "step": 97450 | |
| }, | |
| { | |
| "epoch": 28.3925908667288, | |
| "grad_norm": 0.44699475169181824, | |
| "learning_rate": 0.0002594440559440559, | |
| "loss": 3.1431, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 28.40715284249767, | |
| "grad_norm": 0.45074644684791565, | |
| "learning_rate": 0.0002592692307692307, | |
| "loss": 3.1619, | |
| "step": 97550 | |
| }, | |
| { | |
| "epoch": 28.421714818266544, | |
| "grad_norm": 0.42600199580192566, | |
| "learning_rate": 0.0002590944055944056, | |
| "loss": 3.1447, | |
| "step": 97600 | |
| }, | |
| { | |
| "epoch": 28.436276794035415, | |
| "grad_norm": 0.44456231594085693, | |
| "learning_rate": 0.0002589195804195804, | |
| "loss": 3.1499, | |
| "step": 97650 | |
| }, | |
| { | |
| "epoch": 28.450838769804285, | |
| "grad_norm": 0.4862534701824188, | |
| "learning_rate": 0.00025874475524475523, | |
| "loss": 3.1513, | |
| "step": 97700 | |
| }, | |
| { | |
| "epoch": 28.46540074557316, | |
| "grad_norm": 0.45727989077568054, | |
| "learning_rate": 0.00025856993006993003, | |
| "loss": 3.1476, | |
| "step": 97750 | |
| }, | |
| { | |
| "epoch": 28.47996272134203, | |
| "grad_norm": 0.48387905955314636, | |
| "learning_rate": 0.0002583951048951049, | |
| "loss": 3.1551, | |
| "step": 97800 | |
| }, | |
| { | |
| "epoch": 28.494524697110904, | |
| "grad_norm": 0.4310111701488495, | |
| "learning_rate": 0.0002582202797202797, | |
| "loss": 3.1528, | |
| "step": 97850 | |
| }, | |
| { | |
| "epoch": 28.509086672879775, | |
| "grad_norm": 0.4387485086917877, | |
| "learning_rate": 0.0002580454545454545, | |
| "loss": 3.1557, | |
| "step": 97900 | |
| }, | |
| { | |
| "epoch": 28.52364864864865, | |
| "grad_norm": 0.43874770402908325, | |
| "learning_rate": 0.00025787062937062934, | |
| "loss": 3.1688, | |
| "step": 97950 | |
| }, | |
| { | |
| "epoch": 28.53821062441752, | |
| "grad_norm": 0.44133517146110535, | |
| "learning_rate": 0.0002576958041958042, | |
| "loss": 3.1499, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 28.53821062441752, | |
| "eval_accuracy": 0.37463698183345395, | |
| "eval_loss": 3.5472443103790283, | |
| "eval_runtime": 53.6248, | |
| "eval_samples_per_second": 310.379, | |
| "eval_steps_per_second": 19.413, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 28.552772600186394, | |
| "grad_norm": 0.45987606048583984, | |
| "learning_rate": 0.000257520979020979, | |
| "loss": 3.1609, | |
| "step": 98050 | |
| }, | |
| { | |
| "epoch": 28.567334575955265, | |
| "grad_norm": 0.4473000764846802, | |
| "learning_rate": 0.00025734615384615385, | |
| "loss": 3.1625, | |
| "step": 98100 | |
| }, | |
| { | |
| "epoch": 28.58189655172414, | |
| "grad_norm": 0.4264574646949768, | |
| "learning_rate": 0.00025717132867132865, | |
| "loss": 3.1542, | |
| "step": 98150 | |
| }, | |
| { | |
| "epoch": 28.59645852749301, | |
| "grad_norm": 0.44503456354141235, | |
| "learning_rate": 0.0002569965034965035, | |
| "loss": 3.1588, | |
| "step": 98200 | |
| }, | |
| { | |
| "epoch": 28.611020503261884, | |
| "grad_norm": 0.4370170831680298, | |
| "learning_rate": 0.0002568216783216783, | |
| "loss": 3.1678, | |
| "step": 98250 | |
| }, | |
| { | |
| "epoch": 28.625582479030754, | |
| "grad_norm": 0.46959516406059265, | |
| "learning_rate": 0.0002566468531468531, | |
| "loss": 3.1704, | |
| "step": 98300 | |
| }, | |
| { | |
| "epoch": 28.64014445479963, | |
| "grad_norm": 0.43134886026382446, | |
| "learning_rate": 0.00025647202797202795, | |
| "loss": 3.1791, | |
| "step": 98350 | |
| }, | |
| { | |
| "epoch": 28.6547064305685, | |
| "grad_norm": 0.4523867666721344, | |
| "learning_rate": 0.00025629720279720275, | |
| "loss": 3.1619, | |
| "step": 98400 | |
| }, | |
| { | |
| "epoch": 28.669268406337373, | |
| "grad_norm": 0.4620450437068939, | |
| "learning_rate": 0.0002561223776223776, | |
| "loss": 3.166, | |
| "step": 98450 | |
| }, | |
| { | |
| "epoch": 28.683830382106244, | |
| "grad_norm": 0.44689565896987915, | |
| "learning_rate": 0.0002559475524475524, | |
| "loss": 3.1708, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 28.698392357875118, | |
| "grad_norm": 0.4532458782196045, | |
| "learning_rate": 0.00025577272727272726, | |
| "loss": 3.1625, | |
| "step": 98550 | |
| }, | |
| { | |
| "epoch": 28.71295433364399, | |
| "grad_norm": 0.4778449833393097, | |
| "learning_rate": 0.00025559790209790206, | |
| "loss": 3.1719, | |
| "step": 98600 | |
| }, | |
| { | |
| "epoch": 28.727516309412863, | |
| "grad_norm": 0.445504367351532, | |
| "learning_rate": 0.00025542307692307686, | |
| "loss": 3.1564, | |
| "step": 98650 | |
| }, | |
| { | |
| "epoch": 28.742078285181734, | |
| "grad_norm": 0.4707012474536896, | |
| "learning_rate": 0.00025524825174825177, | |
| "loss": 3.1772, | |
| "step": 98700 | |
| }, | |
| { | |
| "epoch": 28.756640260950604, | |
| "grad_norm": 0.44212526082992554, | |
| "learning_rate": 0.00025507342657342657, | |
| "loss": 3.1779, | |
| "step": 98750 | |
| }, | |
| { | |
| "epoch": 28.77120223671948, | |
| "grad_norm": 0.43493756651878357, | |
| "learning_rate": 0.00025489860139860137, | |
| "loss": 3.1706, | |
| "step": 98800 | |
| }, | |
| { | |
| "epoch": 28.78576421248835, | |
| "grad_norm": 0.4900915324687958, | |
| "learning_rate": 0.0002547237762237762, | |
| "loss": 3.1682, | |
| "step": 98850 | |
| }, | |
| { | |
| "epoch": 28.800326188257223, | |
| "grad_norm": 0.4247000515460968, | |
| "learning_rate": 0.000254548951048951, | |
| "loss": 3.172, | |
| "step": 98900 | |
| }, | |
| { | |
| "epoch": 28.814888164026094, | |
| "grad_norm": 0.449750691652298, | |
| "learning_rate": 0.0002543741258741259, | |
| "loss": 3.1795, | |
| "step": 98950 | |
| }, | |
| { | |
| "epoch": 28.829450139794968, | |
| "grad_norm": 0.45670533180236816, | |
| "learning_rate": 0.0002541993006993007, | |
| "loss": 3.1747, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 28.829450139794968, | |
| "eval_accuracy": 0.37490458648027464, | |
| "eval_loss": 3.5373735427856445, | |
| "eval_runtime": 53.7663, | |
| "eval_samples_per_second": 309.562, | |
| "eval_steps_per_second": 19.362, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 28.84401211556384, | |
| "grad_norm": 0.4435442090034485, | |
| "learning_rate": 0.0002540244755244755, | |
| "loss": 3.1754, | |
| "step": 99050 | |
| }, | |
| { | |
| "epoch": 28.858574091332713, | |
| "grad_norm": 0.4304124116897583, | |
| "learning_rate": 0.00025384965034965033, | |
| "loss": 3.1627, | |
| "step": 99100 | |
| }, | |
| { | |
| "epoch": 28.873136067101584, | |
| "grad_norm": 0.45406800508499146, | |
| "learning_rate": 0.00025367482517482513, | |
| "loss": 3.1713, | |
| "step": 99150 | |
| }, | |
| { | |
| "epoch": 28.887698042870458, | |
| "grad_norm": 0.44807180762290955, | |
| "learning_rate": 0.0002535, | |
| "loss": 3.169, | |
| "step": 99200 | |
| }, | |
| { | |
| "epoch": 28.90226001863933, | |
| "grad_norm": 0.4605872333049774, | |
| "learning_rate": 0.0002533251748251748, | |
| "loss": 3.1823, | |
| "step": 99250 | |
| }, | |
| { | |
| "epoch": 28.916821994408203, | |
| "grad_norm": 0.43984824419021606, | |
| "learning_rate": 0.00025315034965034964, | |
| "loss": 3.1692, | |
| "step": 99300 | |
| }, | |
| { | |
| "epoch": 28.931383970177073, | |
| "grad_norm": 0.4410223662853241, | |
| "learning_rate": 0.00025297552447552444, | |
| "loss": 3.1781, | |
| "step": 99350 | |
| }, | |
| { | |
| "epoch": 28.945945945945947, | |
| "grad_norm": 0.43068429827690125, | |
| "learning_rate": 0.0002528006993006993, | |
| "loss": 3.1835, | |
| "step": 99400 | |
| }, | |
| { | |
| "epoch": 28.960507921714818, | |
| "grad_norm": 0.447227418422699, | |
| "learning_rate": 0.00025262587412587414, | |
| "loss": 3.1843, | |
| "step": 99450 | |
| }, | |
| { | |
| "epoch": 28.975069897483692, | |
| "grad_norm": 0.4420487880706787, | |
| "learning_rate": 0.00025245104895104894, | |
| "loss": 3.1755, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 28.989631873252563, | |
| "grad_norm": 0.4623829424381256, | |
| "learning_rate": 0.00025227622377622374, | |
| "loss": 3.1737, | |
| "step": 99550 | |
| }, | |
| { | |
| "epoch": 29.004077353215283, | |
| "grad_norm": 0.44582149386405945, | |
| "learning_rate": 0.0002521013986013986, | |
| "loss": 3.1614, | |
| "step": 99600 | |
| }, | |
| { | |
| "epoch": 29.018639328984158, | |
| "grad_norm": 0.4791642129421234, | |
| "learning_rate": 0.0002519265734265734, | |
| "loss": 3.0798, | |
| "step": 99650 | |
| }, | |
| { | |
| "epoch": 29.033201304753028, | |
| "grad_norm": 0.44250455498695374, | |
| "learning_rate": 0.00025175174825174825, | |
| "loss": 3.0932, | |
| "step": 99700 | |
| }, | |
| { | |
| "epoch": 29.047763280521902, | |
| "grad_norm": 0.46487218141555786, | |
| "learning_rate": 0.00025157692307692305, | |
| "loss": 3.093, | |
| "step": 99750 | |
| }, | |
| { | |
| "epoch": 29.062325256290773, | |
| "grad_norm": 0.4407868981361389, | |
| "learning_rate": 0.0002514020979020979, | |
| "loss": 3.0993, | |
| "step": 99800 | |
| }, | |
| { | |
| "epoch": 29.076887232059647, | |
| "grad_norm": 0.43440374732017517, | |
| "learning_rate": 0.0002512272727272727, | |
| "loss": 3.0946, | |
| "step": 99850 | |
| }, | |
| { | |
| "epoch": 29.091449207828518, | |
| "grad_norm": 0.45058801770210266, | |
| "learning_rate": 0.0002510524475524475, | |
| "loss": 3.0925, | |
| "step": 99900 | |
| }, | |
| { | |
| "epoch": 29.106011183597392, | |
| "grad_norm": 0.46985459327697754, | |
| "learning_rate": 0.00025087762237762236, | |
| "loss": 3.1015, | |
| "step": 99950 | |
| }, | |
| { | |
| "epoch": 29.120573159366263, | |
| "grad_norm": 0.4654427170753479, | |
| "learning_rate": 0.00025070279720279716, | |
| "loss": 3.1073, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 29.120573159366263, | |
| "eval_accuracy": 0.3739781993922694, | |
| "eval_loss": 3.5579988956451416, | |
| "eval_runtime": 53.6538, | |
| "eval_samples_per_second": 310.211, | |
| "eval_steps_per_second": 19.402, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 29.135135135135137, | |
| "grad_norm": 0.4768226444721222, | |
| "learning_rate": 0.000250527972027972, | |
| "loss": 3.1043, | |
| "step": 100050 | |
| }, | |
| { | |
| "epoch": 29.149697110904008, | |
| "grad_norm": 0.43046435713768005, | |
| "learning_rate": 0.00025035314685314686, | |
| "loss": 3.1163, | |
| "step": 100100 | |
| }, | |
| { | |
| "epoch": 29.164259086672878, | |
| "grad_norm": 0.5126052498817444, | |
| "learning_rate": 0.00025017832167832166, | |
| "loss": 3.1186, | |
| "step": 100150 | |
| }, | |
| { | |
| "epoch": 29.178821062441752, | |
| "grad_norm": 0.4530967175960541, | |
| "learning_rate": 0.0002500034965034965, | |
| "loss": 3.1141, | |
| "step": 100200 | |
| }, | |
| { | |
| "epoch": 29.193383038210623, | |
| "grad_norm": 0.46856310963630676, | |
| "learning_rate": 0.0002498286713286713, | |
| "loss": 3.1029, | |
| "step": 100250 | |
| }, | |
| { | |
| "epoch": 29.207945013979497, | |
| "grad_norm": 0.47363170981407166, | |
| "learning_rate": 0.0002496538461538461, | |
| "loss": 3.1104, | |
| "step": 100300 | |
| }, | |
| { | |
| "epoch": 29.222506989748368, | |
| "grad_norm": 0.4353318214416504, | |
| "learning_rate": 0.00024947902097902097, | |
| "loss": 3.1185, | |
| "step": 100350 | |
| }, | |
| { | |
| "epoch": 29.237068965517242, | |
| "grad_norm": 0.4660615921020508, | |
| "learning_rate": 0.00024930419580419577, | |
| "loss": 3.123, | |
| "step": 100400 | |
| }, | |
| { | |
| "epoch": 29.251630941286113, | |
| "grad_norm": 0.450541615486145, | |
| "learning_rate": 0.0002491293706293706, | |
| "loss": 3.1216, | |
| "step": 100450 | |
| }, | |
| { | |
| "epoch": 29.266192917054987, | |
| "grad_norm": 0.47547033429145813, | |
| "learning_rate": 0.0002489545454545454, | |
| "loss": 3.1252, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 29.280754892823857, | |
| "grad_norm": 0.4383224844932556, | |
| "learning_rate": 0.0002487797202797203, | |
| "loss": 3.1223, | |
| "step": 100550 | |
| }, | |
| { | |
| "epoch": 29.29531686859273, | |
| "grad_norm": 0.4649880826473236, | |
| "learning_rate": 0.0002486048951048951, | |
| "loss": 3.1273, | |
| "step": 100600 | |
| }, | |
| { | |
| "epoch": 29.309878844361602, | |
| "grad_norm": 0.44201621413230896, | |
| "learning_rate": 0.0002484300699300699, | |
| "loss": 3.1335, | |
| "step": 100650 | |
| }, | |
| { | |
| "epoch": 29.324440820130476, | |
| "grad_norm": 0.4683978855609894, | |
| "learning_rate": 0.00024825524475524473, | |
| "loss": 3.1405, | |
| "step": 100700 | |
| }, | |
| { | |
| "epoch": 29.339002795899347, | |
| "grad_norm": 0.4427500069141388, | |
| "learning_rate": 0.00024808041958041953, | |
| "loss": 3.1324, | |
| "step": 100750 | |
| }, | |
| { | |
| "epoch": 29.35356477166822, | |
| "grad_norm": 0.49367576837539673, | |
| "learning_rate": 0.0002479055944055944, | |
| "loss": 3.1266, | |
| "step": 100800 | |
| }, | |
| { | |
| "epoch": 29.368126747437092, | |
| "grad_norm": 0.4418413043022156, | |
| "learning_rate": 0.00024773076923076924, | |
| "loss": 3.1186, | |
| "step": 100850 | |
| }, | |
| { | |
| "epoch": 29.382688723205966, | |
| "grad_norm": 0.46410617232322693, | |
| "learning_rate": 0.00024755594405594404, | |
| "loss": 3.1535, | |
| "step": 100900 | |
| }, | |
| { | |
| "epoch": 29.397250698974837, | |
| "grad_norm": 0.46582889556884766, | |
| "learning_rate": 0.0002473811188811189, | |
| "loss": 3.1423, | |
| "step": 100950 | |
| }, | |
| { | |
| "epoch": 29.41181267474371, | |
| "grad_norm": 0.46468058228492737, | |
| "learning_rate": 0.0002472062937062937, | |
| "loss": 3.1268, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 29.41181267474371, | |
| "eval_accuracy": 0.37427896067810734, | |
| "eval_loss": 3.5532479286193848, | |
| "eval_runtime": 53.662, | |
| "eval_samples_per_second": 310.164, | |
| "eval_steps_per_second": 19.399, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 29.42637465051258, | |
| "grad_norm": 0.47465112805366516, | |
| "learning_rate": 0.0002470314685314685, | |
| "loss": 3.1535, | |
| "step": 101050 | |
| }, | |
| { | |
| "epoch": 29.440936626281452, | |
| "grad_norm": 0.44461822509765625, | |
| "learning_rate": 0.00024685664335664335, | |
| "loss": 3.1444, | |
| "step": 101100 | |
| }, | |
| { | |
| "epoch": 29.455498602050326, | |
| "grad_norm": 0.44391322135925293, | |
| "learning_rate": 0.00024668181818181815, | |
| "loss": 3.152, | |
| "step": 101150 | |
| }, | |
| { | |
| "epoch": 29.470060577819197, | |
| "grad_norm": 0.44190195202827454, | |
| "learning_rate": 0.000246506993006993, | |
| "loss": 3.1346, | |
| "step": 101200 | |
| }, | |
| { | |
| "epoch": 29.48462255358807, | |
| "grad_norm": 0.4293469488620758, | |
| "learning_rate": 0.0002463321678321678, | |
| "loss": 3.1397, | |
| "step": 101250 | |
| }, | |
| { | |
| "epoch": 29.499184529356942, | |
| "grad_norm": 0.4673719108104706, | |
| "learning_rate": 0.00024615734265734265, | |
| "loss": 3.1422, | |
| "step": 101300 | |
| }, | |
| { | |
| "epoch": 29.513746505125816, | |
| "grad_norm": 0.4394907057285309, | |
| "learning_rate": 0.00024598251748251745, | |
| "loss": 3.1516, | |
| "step": 101350 | |
| }, | |
| { | |
| "epoch": 29.528308480894687, | |
| "grad_norm": 0.46596258878707886, | |
| "learning_rate": 0.00024580769230769225, | |
| "loss": 3.1471, | |
| "step": 101400 | |
| }, | |
| { | |
| "epoch": 29.54287045666356, | |
| "grad_norm": 0.46689680218696594, | |
| "learning_rate": 0.0002456328671328671, | |
| "loss": 3.1483, | |
| "step": 101450 | |
| }, | |
| { | |
| "epoch": 29.55743243243243, | |
| "grad_norm": 0.4656352996826172, | |
| "learning_rate": 0.00024545804195804196, | |
| "loss": 3.1602, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 29.571994408201306, | |
| "grad_norm": 0.46260908246040344, | |
| "learning_rate": 0.00024528321678321676, | |
| "loss": 3.1436, | |
| "step": 101550 | |
| }, | |
| { | |
| "epoch": 29.586556383970176, | |
| "grad_norm": 0.43992796540260315, | |
| "learning_rate": 0.0002451083916083916, | |
| "loss": 3.1595, | |
| "step": 101600 | |
| }, | |
| { | |
| "epoch": 29.60111835973905, | |
| "grad_norm": 0.463177353143692, | |
| "learning_rate": 0.0002449335664335664, | |
| "loss": 3.1497, | |
| "step": 101650 | |
| }, | |
| { | |
| "epoch": 29.61568033550792, | |
| "grad_norm": 0.44098642468452454, | |
| "learning_rate": 0.00024475874125874127, | |
| "loss": 3.1578, | |
| "step": 101700 | |
| }, | |
| { | |
| "epoch": 29.630242311276795, | |
| "grad_norm": 0.4605831801891327, | |
| "learning_rate": 0.00024458391608391607, | |
| "loss": 3.1564, | |
| "step": 101750 | |
| }, | |
| { | |
| "epoch": 29.644804287045666, | |
| "grad_norm": 0.4362461268901825, | |
| "learning_rate": 0.00024440909090909087, | |
| "loss": 3.149, | |
| "step": 101800 | |
| }, | |
| { | |
| "epoch": 29.65936626281454, | |
| "grad_norm": 0.45928579568862915, | |
| "learning_rate": 0.0002442342657342657, | |
| "loss": 3.1544, | |
| "step": 101850 | |
| }, | |
| { | |
| "epoch": 29.67392823858341, | |
| "grad_norm": 0.4574165642261505, | |
| "learning_rate": 0.00024405944055944052, | |
| "loss": 3.1615, | |
| "step": 101900 | |
| }, | |
| { | |
| "epoch": 29.688490214352285, | |
| "grad_norm": 0.4415947198867798, | |
| "learning_rate": 0.00024388461538461535, | |
| "loss": 3.1512, | |
| "step": 101950 | |
| }, | |
| { | |
| "epoch": 29.703052190121156, | |
| "grad_norm": 0.45984649658203125, | |
| "learning_rate": 0.00024370979020979017, | |
| "loss": 3.1554, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 29.703052190121156, | |
| "eval_accuracy": 0.3748505011825868, | |
| "eval_loss": 3.5421435832977295, | |
| "eval_runtime": 53.7157, | |
| "eval_samples_per_second": 309.853, | |
| "eval_steps_per_second": 19.38, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 29.703052190121156, | |
| "step": 102000, | |
| "total_flos": 2.13187776970752e+18, | |
| "train_loss": 3.386132829703537, | |
| "train_runtime": 45304.3422, | |
| "train_samples_per_second": 303.155, | |
| "train_steps_per_second": 3.79 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 171700, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 20, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 18 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.13187776970752e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |