| { | |
| "best_metric": 2.6793947219848633, | |
| "best_model_checkpoint": "data/paligemma2-3b-pt-224-sft-lora-magicsoup_no_cfiphone_no_insta_sub5/checkpoint-3580", | |
| "epoch": 1.0, | |
| "eval_steps": 1790, | |
| "global_step": 7159, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001396843134515994, | |
| "grad_norm": 11.714253425598145, | |
| "learning_rate": 1.3966480446927375e-07, | |
| "loss": 15.8723, | |
| "mean_token_accuracy": 0.051948051899671555, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027936862690319877, | |
| "grad_norm": 11.453227996826172, | |
| "learning_rate": 2.7932960893854746e-06, | |
| "loss": 15.6868, | |
| "mean_token_accuracy": 0.04536910433518259, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0055873725380639755, | |
| "grad_norm": 14.288809776306152, | |
| "learning_rate": 5.586592178770949e-06, | |
| "loss": 15.2233, | |
| "mean_token_accuracy": 0.04797077886760235, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008381058807095963, | |
| "grad_norm": 15.974210739135742, | |
| "learning_rate": 8.379888268156424e-06, | |
| "loss": 12.5816, | |
| "mean_token_accuracy": 0.06761363632977009, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.011174745076127951, | |
| "grad_norm": 8.255433082580566, | |
| "learning_rate": 1.1173184357541899e-05, | |
| "loss": 8.1704, | |
| "mean_token_accuracy": 0.019724026112817226, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013968431345159939, | |
| "grad_norm": 4.060810565948486, | |
| "learning_rate": 1.3966480446927374e-05, | |
| "loss": 5.8302, | |
| "mean_token_accuracy": 0.0771915590390563, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.016762117614191926, | |
| "grad_norm": 5.3958940505981445, | |
| "learning_rate": 1.675977653631285e-05, | |
| "loss": 5.1183, | |
| "mean_token_accuracy": 0.09870129823684692, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.019555803883223914, | |
| "grad_norm": 6.21713924407959, | |
| "learning_rate": 1.9553072625698323e-05, | |
| "loss": 4.6938, | |
| "mean_token_accuracy": 0.11225649379193783, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.022349490152255902, | |
| "grad_norm": 10.742652893066406, | |
| "learning_rate": 2.2346368715083797e-05, | |
| "loss": 4.375, | |
| "mean_token_accuracy": 0.12938311770558358, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.02514317642128789, | |
| "grad_norm": 14.718498229980469, | |
| "learning_rate": 2.5139664804469275e-05, | |
| "loss": 4.1989, | |
| "mean_token_accuracy": 0.16461038812994958, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.027936862690319877, | |
| "grad_norm": 10.117100715637207, | |
| "learning_rate": 2.793296089385475e-05, | |
| "loss": 3.8056, | |
| "mean_token_accuracy": 0.2379870109260082, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.030730548959351865, | |
| "grad_norm": 6.335511207580566, | |
| "learning_rate": 3.0726256983240227e-05, | |
| "loss": 3.5194, | |
| "mean_token_accuracy": 0.2828733794391155, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.03352423522838385, | |
| "grad_norm": 8.714235305786133, | |
| "learning_rate": 3.35195530726257e-05, | |
| "loss": 3.4042, | |
| "mean_token_accuracy": 0.2905844166874886, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.03631792149741584, | |
| "grad_norm": 28.925806045532227, | |
| "learning_rate": 3.6312849162011175e-05, | |
| "loss": 3.3014, | |
| "mean_token_accuracy": 0.30211039036512377, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.03911160776644783, | |
| "grad_norm": 7.385269641876221, | |
| "learning_rate": 3.9106145251396646e-05, | |
| "loss": 3.2824, | |
| "mean_token_accuracy": 0.2980519443750381, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.041905294035479816, | |
| "grad_norm": 26.001882553100586, | |
| "learning_rate": 4.1899441340782123e-05, | |
| "loss": 3.2237, | |
| "mean_token_accuracy": 0.3021103873848915, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.044698980304511804, | |
| "grad_norm": 6.193004131317139, | |
| "learning_rate": 4.4692737430167594e-05, | |
| "loss": 3.1911, | |
| "mean_token_accuracy": 0.3050324633717537, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.04749266657354379, | |
| "grad_norm": 10.755631446838379, | |
| "learning_rate": 4.748603351955307e-05, | |
| "loss": 3.1985, | |
| "mean_token_accuracy": 0.30081168562173843, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.05028635284257578, | |
| "grad_norm": 13.610740661621094, | |
| "learning_rate": 5.027932960893855e-05, | |
| "loss": 3.1074, | |
| "mean_token_accuracy": 0.31006493270397184, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.05308003911160777, | |
| "grad_norm": 7.772305011749268, | |
| "learning_rate": 5.307262569832403e-05, | |
| "loss": 3.0981, | |
| "mean_token_accuracy": 0.3107142850756645, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.055873725380639755, | |
| "grad_norm": 8.072247505187988, | |
| "learning_rate": 5.58659217877095e-05, | |
| "loss": 3.0943, | |
| "mean_token_accuracy": 0.31095779240131377, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05866741164967174, | |
| "grad_norm": 7.870853900909424, | |
| "learning_rate": 5.8659217877094976e-05, | |
| "loss": 3.0422, | |
| "mean_token_accuracy": 0.31168831288814547, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.06146109791870373, | |
| "grad_norm": 19.650827407836914, | |
| "learning_rate": 6.145251396648045e-05, | |
| "loss": 3.085, | |
| "mean_token_accuracy": 0.31087662279605865, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.06425478418773571, | |
| "grad_norm": 17.583972930908203, | |
| "learning_rate": 6.424581005586592e-05, | |
| "loss": 3.0207, | |
| "mean_token_accuracy": 0.3114448055624962, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.0670484704567677, | |
| "grad_norm": 8.581819534301758, | |
| "learning_rate": 6.70391061452514e-05, | |
| "loss": 3.0396, | |
| "mean_token_accuracy": 0.31160714030265807, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.06984215672579969, | |
| "grad_norm": 10.295416831970215, | |
| "learning_rate": 6.983240223463688e-05, | |
| "loss": 3.0311, | |
| "mean_token_accuracy": 0.3094155818223953, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07263584299483168, | |
| "grad_norm": 11.54842472076416, | |
| "learning_rate": 7.262569832402235e-05, | |
| "loss": 2.9806, | |
| "mean_token_accuracy": 0.3171266242861748, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.07542952926386366, | |
| "grad_norm": 6.4206743240356445, | |
| "learning_rate": 7.541899441340783e-05, | |
| "loss": 3.0046, | |
| "mean_token_accuracy": 0.3163961052894592, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.07822321553289566, | |
| "grad_norm": 6.957503795623779, | |
| "learning_rate": 7.821229050279329e-05, | |
| "loss": 2.9919, | |
| "mean_token_accuracy": 0.31185064762830733, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.08101690180192764, | |
| "grad_norm": 4.134042263031006, | |
| "learning_rate": 8.100558659217878e-05, | |
| "loss": 3.0287, | |
| "mean_token_accuracy": 0.3153409093618393, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.08381058807095963, | |
| "grad_norm": 5.571300029754639, | |
| "learning_rate": 8.379888268156425e-05, | |
| "loss": 2.9836, | |
| "mean_token_accuracy": 0.31599026173353195, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.08660427433999161, | |
| "grad_norm": 5.823517799377441, | |
| "learning_rate": 8.659217877094973e-05, | |
| "loss": 2.9693, | |
| "mean_token_accuracy": 0.3173701331019402, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.08939796060902361, | |
| "grad_norm": 5.942770004272461, | |
| "learning_rate": 8.938547486033519e-05, | |
| "loss": 2.957, | |
| "mean_token_accuracy": 0.32094155699014665, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.09219164687805559, | |
| "grad_norm": 5.494757175445557, | |
| "learning_rate": 9.217877094972067e-05, | |
| "loss": 2.9391, | |
| "mean_token_accuracy": 0.3202922075986862, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.09498533314708758, | |
| "grad_norm": 3.7874789237976074, | |
| "learning_rate": 9.497206703910614e-05, | |
| "loss": 2.9662, | |
| "mean_token_accuracy": 0.318506495654583, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.09777901941611956, | |
| "grad_norm": 4.3834733963012695, | |
| "learning_rate": 9.776536312849163e-05, | |
| "loss": 2.9742, | |
| "mean_token_accuracy": 0.315259738266468, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.10057270568515156, | |
| "grad_norm": 3.8033530712127686, | |
| "learning_rate": 9.999990489938263e-05, | |
| "loss": 2.9255, | |
| "mean_token_accuracy": 0.3217532455921173, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.10336639195418354, | |
| "grad_norm": 5.953765869140625, | |
| "learning_rate": 9.99965764157593e-05, | |
| "loss": 2.8773, | |
| "mean_token_accuracy": 0.32402597516775133, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.10616007822321553, | |
| "grad_norm": 8.89194107055664, | |
| "learning_rate": 9.998849326302563e-05, | |
| "loss": 2.9062, | |
| "mean_token_accuracy": 0.3172889605164528, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.10895376449224752, | |
| "grad_norm": 4.883932113647461, | |
| "learning_rate": 9.997565620988856e-05, | |
| "loss": 2.889, | |
| "mean_token_accuracy": 0.324594159424305, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.11174745076127951, | |
| "grad_norm": 6.9450297355651855, | |
| "learning_rate": 9.995806647715047e-05, | |
| "loss": 2.902, | |
| "mean_token_accuracy": 0.319155840575695, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.11454113703031149, | |
| "grad_norm": 3.826904296875, | |
| "learning_rate": 9.99357257375931e-05, | |
| "loss": 2.845, | |
| "mean_token_accuracy": 0.32288961112499237, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.11733482329934349, | |
| "grad_norm": 3.4276959896087646, | |
| "learning_rate": 9.99086361158184e-05, | |
| "loss": 2.8776, | |
| "mean_token_accuracy": 0.31899350732564924, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.12012850956837547, | |
| "grad_norm": 4.847935199737549, | |
| "learning_rate": 9.987680018804652e-05, | |
| "loss": 2.8714, | |
| "mean_token_accuracy": 0.32126623690128325, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.12292219583740746, | |
| "grad_norm": 3.4353716373443604, | |
| "learning_rate": 9.984022098187083e-05, | |
| "loss": 2.8408, | |
| "mean_token_accuracy": 0.3215097412467003, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.12571588210643944, | |
| "grad_norm": 4.255288600921631, | |
| "learning_rate": 9.979890197596993e-05, | |
| "loss": 2.887, | |
| "mean_token_accuracy": 0.3237824708223343, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.12850956837547142, | |
| "grad_norm": 4.189087867736816, | |
| "learning_rate": 9.97528470997769e-05, | |
| "loss": 2.8593, | |
| "mean_token_accuracy": 0.324756495654583, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.13130325464450343, | |
| "grad_norm": 2.641284227371216, | |
| "learning_rate": 9.97020607331056e-05, | |
| "loss": 2.8606, | |
| "mean_token_accuracy": 0.32142857313156126, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.1340969409135354, | |
| "grad_norm": 2.688258171081543, | |
| "learning_rate": 9.964654770573408e-05, | |
| "loss": 2.8676, | |
| "mean_token_accuracy": 0.32646103799343107, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.1368906271825674, | |
| "grad_norm": 3.801523208618164, | |
| "learning_rate": 9.958631329694537e-05, | |
| "loss": 2.8623, | |
| "mean_token_accuracy": 0.3244318202137947, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.13968431345159937, | |
| "grad_norm": 3.528196334838867, | |
| "learning_rate": 9.952136323502536e-05, | |
| "loss": 2.865, | |
| "mean_token_accuracy": 0.32459415644407275, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.14247799972063138, | |
| "grad_norm": 3.970863103866577, | |
| "learning_rate": 9.945170369671802e-05, | |
| "loss": 2.8762, | |
| "mean_token_accuracy": 0.32102272659540176, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.14527168598966336, | |
| "grad_norm": 4.364096641540527, | |
| "learning_rate": 9.937734130663807e-05, | |
| "loss": 2.8521, | |
| "mean_token_accuracy": 0.321185065805912, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.14806537225869534, | |
| "grad_norm": 2.6619839668273926, | |
| "learning_rate": 9.92982831366409e-05, | |
| "loss": 2.8557, | |
| "mean_token_accuracy": 0.32167208194732666, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.15085905852772732, | |
| "grad_norm": 2.8934223651885986, | |
| "learning_rate": 9.921453670515009e-05, | |
| "loss": 2.8138, | |
| "mean_token_accuracy": 0.3263798728585243, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.15365274479675933, | |
| "grad_norm": 3.3745875358581543, | |
| "learning_rate": 9.91261099764424e-05, | |
| "loss": 2.8387, | |
| "mean_token_accuracy": 0.3244318187236786, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.1564464310657913, | |
| "grad_norm": 3.961806297302246, | |
| "learning_rate": 9.903301135989032e-05, | |
| "loss": 2.833, | |
| "mean_token_accuracy": 0.324918831884861, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.1592401173348233, | |
| "grad_norm": 2.1680517196655273, | |
| "learning_rate": 9.893524970916242e-05, | |
| "loss": 2.8295, | |
| "mean_token_accuracy": 0.3221590921282768, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.16203380360385528, | |
| "grad_norm": 2.9997398853302, | |
| "learning_rate": 9.883283432138129e-05, | |
| "loss": 2.8284, | |
| "mean_token_accuracy": 0.32670454382896424, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.16482748987288728, | |
| "grad_norm": 6.048096656799316, | |
| "learning_rate": 9.872577493623945e-05, | |
| "loss": 2.814, | |
| "mean_token_accuracy": 0.3250811696052551, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.16762117614191926, | |
| "grad_norm": 2.815396547317505, | |
| "learning_rate": 9.861408173507304e-05, | |
| "loss": 2.8529, | |
| "mean_token_accuracy": 0.32467532753944395, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.17041486241095125, | |
| "grad_norm": 4.112369537353516, | |
| "learning_rate": 9.849776533989369e-05, | |
| "loss": 2.7942, | |
| "mean_token_accuracy": 0.327272729575634, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.17320854867998323, | |
| "grad_norm": 2.6627895832061768, | |
| "learning_rate": 9.837683681237819e-05, | |
| "loss": 2.8087, | |
| "mean_token_accuracy": 0.3275974065065384, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.17600223494901523, | |
| "grad_norm": 3.526514768600464, | |
| "learning_rate": 9.825130765281668e-05, | |
| "loss": 2.8224, | |
| "mean_token_accuracy": 0.32508117258548735, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.17879592121804722, | |
| "grad_norm": 3.236506938934326, | |
| "learning_rate": 9.812118979901891e-05, | |
| "loss": 2.8373, | |
| "mean_token_accuracy": 0.32394480556249616, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.1815896074870792, | |
| "grad_norm": 3.168816566467285, | |
| "learning_rate": 9.7986495625179e-05, | |
| "loss": 2.8059, | |
| "mean_token_accuracy": 0.3279220789670944, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.18438329375611118, | |
| "grad_norm": 4.702609062194824, | |
| "learning_rate": 9.784723794069852e-05, | |
| "loss": 2.7648, | |
| "mean_token_accuracy": 0.33125000149011613, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.18717698002514319, | |
| "grad_norm": 3.00978684425354, | |
| "learning_rate": 9.770342998896851e-05, | |
| "loss": 2.8123, | |
| "mean_token_accuracy": 0.32670454680919647, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.18997066629417517, | |
| "grad_norm": 5.219450950622559, | |
| "learning_rate": 9.755508544610994e-05, | |
| "loss": 2.7966, | |
| "mean_token_accuracy": 0.3340097412467003, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.19276435256320715, | |
| "grad_norm": 2.8464038372039795, | |
| "learning_rate": 9.740221841967307e-05, | |
| "loss": 2.7738, | |
| "mean_token_accuracy": 0.32849026173353196, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.19555803883223913, | |
| "grad_norm": 3.846038341522217, | |
| "learning_rate": 9.72448434472959e-05, | |
| "loss": 2.7938, | |
| "mean_token_accuracy": 0.3283279240131378, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.19835172510127114, | |
| "grad_norm": 2.432882070541382, | |
| "learning_rate": 9.708297549532157e-05, | |
| "loss": 2.7805, | |
| "mean_token_accuracy": 0.329788963496685, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.20114541137030312, | |
| "grad_norm": 2.405036687850952, | |
| "learning_rate": 9.691662995737516e-05, | |
| "loss": 2.7497, | |
| "mean_token_accuracy": 0.327353897690773, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.2039390976393351, | |
| "grad_norm": 2.1323699951171875, | |
| "learning_rate": 9.674582265289967e-05, | |
| "loss": 2.7859, | |
| "mean_token_accuracy": 0.3321428596973419, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.20673278390836708, | |
| "grad_norm": 4.102099418640137, | |
| "learning_rate": 9.657056982565161e-05, | |
| "loss": 2.8042, | |
| "mean_token_accuracy": 0.3272727280855179, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.2095264701773991, | |
| "grad_norm": 3.1227469444274902, | |
| "learning_rate": 9.639088814215627e-05, | |
| "loss": 2.774, | |
| "mean_token_accuracy": 0.32987013161182405, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.21232015644643107, | |
| "grad_norm": 2.4661705493927, | |
| "learning_rate": 9.620679469012266e-05, | |
| "loss": 2.7377, | |
| "mean_token_accuracy": 0.3315746784210205, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.21511384271546305, | |
| "grad_norm": 3.3351097106933594, | |
| "learning_rate": 9.601830697681853e-05, | |
| "loss": 2.7786, | |
| "mean_token_accuracy": 0.3308441549539566, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.21790752898449503, | |
| "grad_norm": 2.9032342433929443, | |
| "learning_rate": 9.582544292740542e-05, | |
| "loss": 2.7485, | |
| "mean_token_accuracy": 0.33076298981904984, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.22070121525352704, | |
| "grad_norm": 2.4244565963745117, | |
| "learning_rate": 9.562822088323396e-05, | |
| "loss": 2.765, | |
| "mean_token_accuracy": 0.3307629868388176, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.22349490152255902, | |
| "grad_norm": 2.1915383338928223, | |
| "learning_rate": 9.542665960009959e-05, | |
| "loss": 2.7455, | |
| "mean_token_accuracy": 0.33303571343421934, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.226288587791591, | |
| "grad_norm": 4.944774150848389, | |
| "learning_rate": 9.522077824645896e-05, | |
| "loss": 2.7786, | |
| "mean_token_accuracy": 0.3247564971446991, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.22908227406062298, | |
| "grad_norm": 3.094341993331909, | |
| "learning_rate": 9.501059640160696e-05, | |
| "loss": 2.7678, | |
| "mean_token_accuracy": 0.32930195033550264, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.231875960329655, | |
| "grad_norm": 3.0549888610839844, | |
| "learning_rate": 9.479613405381474e-05, | |
| "loss": 2.7392, | |
| "mean_token_accuracy": 0.33157467693090437, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.23466964659868697, | |
| "grad_norm": 2.4436118602752686, | |
| "learning_rate": 9.457741159842875e-05, | |
| "loss": 2.7619, | |
| "mean_token_accuracy": 0.32897727340459826, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.23746333286771895, | |
| "grad_norm": 2.174079179763794, | |
| "learning_rate": 9.435444983593133e-05, | |
| "loss": 2.7419, | |
| "mean_token_accuracy": 0.33214285373687746, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.24025701913675093, | |
| "grad_norm": 2.1228203773498535, | |
| "learning_rate": 9.412726996996242e-05, | |
| "loss": 2.711, | |
| "mean_token_accuracy": 0.3351461037993431, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.24305070540578294, | |
| "grad_norm": 2.5232136249542236, | |
| "learning_rate": 9.389589360530315e-05, | |
| "loss": 2.7503, | |
| "mean_token_accuracy": 0.33506493717432023, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.24584439167481492, | |
| "grad_norm": 2.0878124237060547, | |
| "learning_rate": 9.366034274582125e-05, | |
| "loss": 2.7578, | |
| "mean_token_accuracy": 0.33417208194732667, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.2486380779438469, | |
| "grad_norm": 2.1424570083618164, | |
| "learning_rate": 9.342063979237846e-05, | |
| "loss": 2.7409, | |
| "mean_token_accuracy": 0.3298701301217079, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.2500349210783629, | |
| "eval_loss": 2.7205357551574707, | |
| "eval_mean_token_accuracy": 0.33310290950003457, | |
| "eval_runtime": 1163.4728, | |
| "eval_samples_per_second": 84.514, | |
| "eval_steps_per_second": 1.509, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.2514317642128789, | |
| "grad_norm": 2.787091016769409, | |
| "learning_rate": 9.317680754070017e-05, | |
| "loss": 2.7103, | |
| "mean_token_accuracy": 0.3347402632236481, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.25422545048191086, | |
| "grad_norm": 2.668544292449951, | |
| "learning_rate": 9.29288691792077e-05, | |
| "loss": 2.7083, | |
| "mean_token_accuracy": 0.3347402587532997, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.25701913675094284, | |
| "grad_norm": 1.573211669921875, | |
| "learning_rate": 9.267684828681286e-05, | |
| "loss": 2.7137, | |
| "mean_token_accuracy": 0.33206168860197066, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.2598128230199749, | |
| "grad_norm": 2.3701252937316895, | |
| "learning_rate": 9.242076883067579e-05, | |
| "loss": 2.7062, | |
| "mean_token_accuracy": 0.3372564911842346, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.26260650928900686, | |
| "grad_norm": 2.19620418548584, | |
| "learning_rate": 9.216065516392555e-05, | |
| "loss": 2.7239, | |
| "mean_token_accuracy": 0.33417207896709444, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.26540019555803884, | |
| "grad_norm": 2.424910306930542, | |
| "learning_rate": 9.18965320233443e-05, | |
| "loss": 2.7034, | |
| "mean_token_accuracy": 0.33741882890462876, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.2681938818270708, | |
| "grad_norm": 1.7149094343185425, | |
| "learning_rate": 9.162842452701463e-05, | |
| "loss": 2.7212, | |
| "mean_token_accuracy": 0.3329545482993126, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.2709875680961028, | |
| "grad_norm": 2.663922071456909, | |
| "learning_rate": 9.1356358171931e-05, | |
| "loss": 2.7237, | |
| "mean_token_accuracy": 0.33019480258226397, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.2737812543651348, | |
| "grad_norm": 2.727353811264038, | |
| "learning_rate": 9.10803588315749e-05, | |
| "loss": 2.7267, | |
| "mean_token_accuracy": 0.33165584653615954, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.27657494063416677, | |
| "grad_norm": 2.4968833923339844, | |
| "learning_rate": 9.080045275345429e-05, | |
| "loss": 2.7363, | |
| "mean_token_accuracy": 0.33368506729602815, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.27936862690319875, | |
| "grad_norm": 2.447314977645874, | |
| "learning_rate": 9.051666655660752e-05, | |
| "loss": 2.691, | |
| "mean_token_accuracy": 0.33392857313156127, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2821623131722308, | |
| "grad_norm": 3.4394643306732178, | |
| "learning_rate": 9.022902722907173e-05, | |
| "loss": 2.7273, | |
| "mean_token_accuracy": 0.33084415793418886, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.28495599944126276, | |
| "grad_norm": 1.788519024848938, | |
| "learning_rate": 8.99375621253165e-05, | |
| "loss": 2.7005, | |
| "mean_token_accuracy": 0.3343344137072563, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.28774968571029474, | |
| "grad_norm": 2.173936367034912, | |
| "learning_rate": 8.964229896364223e-05, | |
| "loss": 2.6749, | |
| "mean_token_accuracy": 0.33271104097366333, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.2905433719793267, | |
| "grad_norm": 2.7031307220458984, | |
| "learning_rate": 8.934326582354426e-05, | |
| "loss": 2.7266, | |
| "mean_token_accuracy": 0.3330357104539871, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.2933370582483587, | |
| "grad_norm": 1.726846694946289, | |
| "learning_rate": 8.904049114304247e-05, | |
| "loss": 2.7049, | |
| "mean_token_accuracy": 0.33628246933221817, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.2961307445173907, | |
| "grad_norm": 2.3227744102478027, | |
| "learning_rate": 8.873400371597685e-05, | |
| "loss": 2.7019, | |
| "mean_token_accuracy": 0.3343344181776047, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.29892443078642267, | |
| "grad_norm": 2.884831190109253, | |
| "learning_rate": 8.842383268926917e-05, | |
| "loss": 2.7492, | |
| "mean_token_accuracy": 0.3277597427368164, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.30171811705545465, | |
| "grad_norm": 2.0531013011932373, | |
| "learning_rate": 8.811000756015115e-05, | |
| "loss": 2.7191, | |
| "mean_token_accuracy": 0.3326298698782921, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.3045118033244867, | |
| "grad_norm": 2.0113601684570312, | |
| "learning_rate": 8.779255817335927e-05, | |
| "loss": 2.6986, | |
| "mean_token_accuracy": 0.3370129883289337, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.30730548959351867, | |
| "grad_norm": 2.0892691612243652, | |
| "learning_rate": 8.74715147182965e-05, | |
| "loss": 2.7063, | |
| "mean_token_accuracy": 0.3331980526447296, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.31009917586255065, | |
| "grad_norm": 1.9228285551071167, | |
| "learning_rate": 8.714690772616134e-05, | |
| "loss": 2.6696, | |
| "mean_token_accuracy": 0.3384740263223648, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.3128928621315826, | |
| "grad_norm": 2.699789524078369, | |
| "learning_rate": 8.681876806704431e-05, | |
| "loss": 2.6917, | |
| "mean_token_accuracy": 0.33693181574344633, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.3156865484006146, | |
| "grad_norm": 2.43989896774292, | |
| "learning_rate": 8.648712694699214e-05, | |
| "loss": 2.6816, | |
| "mean_token_accuracy": 0.3405032455921173, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.3184802346696466, | |
| "grad_norm": 1.8896594047546387, | |
| "learning_rate": 8.615201590504017e-05, | |
| "loss": 2.6781, | |
| "mean_token_accuracy": 0.33904220908880234, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.32127392093867857, | |
| "grad_norm": 2.3167271614074707, | |
| "learning_rate": 8.58134668102129e-05, | |
| "loss": 2.6755, | |
| "mean_token_accuracy": 0.33563312143087387, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.32406760720771055, | |
| "grad_norm": 2.3568389415740967, | |
| "learning_rate": 8.547151185849332e-05, | |
| "loss": 2.6837, | |
| "mean_token_accuracy": 0.3358766257762909, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.3268612934767426, | |
| "grad_norm": 2.21427845954895, | |
| "learning_rate": 8.512618356976103e-05, | |
| "loss": 2.6701, | |
| "mean_token_accuracy": 0.3395292177796364, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.32965497974577457, | |
| "grad_norm": 2.3978805541992188, | |
| "learning_rate": 8.477751478469964e-05, | |
| "loss": 2.7054, | |
| "mean_token_accuracy": 0.3341720774769783, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.33244866601480655, | |
| "grad_norm": 2.3003275394439697, | |
| "learning_rate": 8.442553866167362e-05, | |
| "loss": 2.6831, | |
| "mean_token_accuracy": 0.3353896141052246, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.33524235228383853, | |
| "grad_norm": 2.208958625793457, | |
| "learning_rate": 8.40702886735749e-05, | |
| "loss": 2.7123, | |
| "mean_token_accuracy": 0.33327922224998474, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.3380360385528705, | |
| "grad_norm": 2.9336678981781006, | |
| "learning_rate": 8.371179860463962e-05, | |
| "loss": 2.6517, | |
| "mean_token_accuracy": 0.33806818127632143, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.3408297248219025, | |
| "grad_norm": 2.476029634475708, | |
| "learning_rate": 8.335010254723532e-05, | |
| "loss": 2.6725, | |
| "mean_token_accuracy": 0.3363636344671249, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.34362341109093447, | |
| "grad_norm": 2.220250129699707, | |
| "learning_rate": 8.298523489861864e-05, | |
| "loss": 2.6884, | |
| "mean_token_accuracy": 0.3369318187236786, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.34641709735996645, | |
| "grad_norm": 2.475471258163452, | |
| "learning_rate": 8.261723035766424e-05, | |
| "loss": 2.6657, | |
| "mean_token_accuracy": 0.3395292192697525, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.3492107836289985, | |
| "grad_norm": 2.1862926483154297, | |
| "learning_rate": 8.224612392156492e-05, | |
| "loss": 2.6489, | |
| "mean_token_accuracy": 0.33928571343421937, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.35200446989803047, | |
| "grad_norm": 3.5017824172973633, | |
| "learning_rate": 8.187195088250334e-05, | |
| "loss": 2.6563, | |
| "mean_token_accuracy": 0.3419642835855484, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.35479815616706245, | |
| "grad_norm": 2.0507349967956543, | |
| "learning_rate": 8.149474682429581e-05, | |
| "loss": 2.6305, | |
| "mean_token_accuracy": 0.3375, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.35759184243609443, | |
| "grad_norm": 2.558877468109131, | |
| "learning_rate": 8.111454761900823e-05, | |
| "loss": 2.6551, | |
| "mean_token_accuracy": 0.3370129868388176, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.3603855287051264, | |
| "grad_norm": 2.8872764110565186, | |
| "learning_rate": 8.073138942354468e-05, | |
| "loss": 2.6755, | |
| "mean_token_accuracy": 0.3384740278124809, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.3631792149741584, | |
| "grad_norm": 2.2422327995300293, | |
| "learning_rate": 8.034530867620884e-05, | |
| "loss": 2.6338, | |
| "mean_token_accuracy": 0.34042208045721056, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.3659729012431904, | |
| "grad_norm": 3.2413196563720703, | |
| "learning_rate": 7.995634209323886e-05, | |
| "loss": 2.659, | |
| "mean_token_accuracy": 0.33839286118745804, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.36876658751222235, | |
| "grad_norm": 1.9311487674713135, | |
| "learning_rate": 7.956452666531543e-05, | |
| "loss": 2.6735, | |
| "mean_token_accuracy": 0.3370129868388176, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.3715602737812544, | |
| "grad_norm": 2.613398313522339, | |
| "learning_rate": 7.91698996540442e-05, | |
| "loss": 2.6615, | |
| "mean_token_accuracy": 0.3362824648618698, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.37435396005028637, | |
| "grad_norm": 2.089853048324585, | |
| "learning_rate": 7.877249858841205e-05, | |
| "loss": 2.6745, | |
| "mean_token_accuracy": 0.3379058450460434, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.37714764631931835, | |
| "grad_norm": 2.8007054328918457, | |
| "learning_rate": 7.837236126121813e-05, | |
| "loss": 2.6291, | |
| "mean_token_accuracy": 0.3419642895460129, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.37994133258835033, | |
| "grad_norm": 2.5469701290130615, | |
| "learning_rate": 7.796952572547979e-05, | |
| "loss": 2.6565, | |
| "mean_token_accuracy": 0.33522727340459824, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.3827350188573823, | |
| "grad_norm": 2.698303461074829, | |
| "learning_rate": 7.756403029081371e-05, | |
| "loss": 2.6347, | |
| "mean_token_accuracy": 0.34009740352630613, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.3855287051264143, | |
| "grad_norm": 2.7376692295074463, | |
| "learning_rate": 7.71559135197927e-05, | |
| "loss": 2.6732, | |
| "mean_token_accuracy": 0.33725649267435076, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.3883223913954463, | |
| "grad_norm": 2.4188475608825684, | |
| "learning_rate": 7.674521422427837e-05, | |
| "loss": 2.6648, | |
| "mean_token_accuracy": 0.33855519592761996, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.39111607766447826, | |
| "grad_norm": 2.3172502517700195, | |
| "learning_rate": 7.633197146173011e-05, | |
| "loss": 2.6581, | |
| "mean_token_accuracy": 0.33376623392105104, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.3939097639335103, | |
| "grad_norm": 2.007584810256958, | |
| "learning_rate": 7.591622453149078e-05, | |
| "loss": 2.6422, | |
| "mean_token_accuracy": 0.3401785731315613, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.3967034502025423, | |
| "grad_norm": 2.598574161529541, | |
| "learning_rate": 7.549801297104935e-05, | |
| "loss": 2.6408, | |
| "mean_token_accuracy": 0.33725649267435076, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.39949713647157425, | |
| "grad_norm": 2.0446927547454834, | |
| "learning_rate": 7.50773765522808e-05, | |
| "loss": 2.6269, | |
| "mean_token_accuracy": 0.3426136389374733, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.40229082274060624, | |
| "grad_norm": 2.690002918243408, | |
| "learning_rate": 7.465435527766389e-05, | |
| "loss": 2.5858, | |
| "mean_token_accuracy": 0.34058441370725634, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.4050845090096382, | |
| "grad_norm": 2.8425843715667725, | |
| "learning_rate": 7.422898937647695e-05, | |
| "loss": 2.5586, | |
| "mean_token_accuracy": 0.3442370146512985, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.4078781952786702, | |
| "grad_norm": 2.089576482772827, | |
| "learning_rate": 7.380131930097206e-05, | |
| "loss": 2.6763, | |
| "mean_token_accuracy": 0.333441561460495, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.4106718815477022, | |
| "grad_norm": 2.146989107131958, | |
| "learning_rate": 7.337138572252797e-05, | |
| "loss": 2.5974, | |
| "mean_token_accuracy": 0.3448863625526428, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.41346556781673416, | |
| "grad_norm": 1.8725186586380005, | |
| "learning_rate": 7.293922952778239e-05, | |
| "loss": 2.6124, | |
| "mean_token_accuracy": 0.3443993508815765, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.4162592540857662, | |
| "grad_norm": 2.520397186279297, | |
| "learning_rate": 7.250489181474351e-05, | |
| "loss": 2.6684, | |
| "mean_token_accuracy": 0.3356331169605255, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.4190529403547982, | |
| "grad_norm": 2.551262378692627, | |
| "learning_rate": 7.206841388888183e-05, | |
| "loss": 2.6146, | |
| "mean_token_accuracy": 0.3406655803322792, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.42184662662383016, | |
| "grad_norm": 2.6218693256378174, | |
| "learning_rate": 7.16298372592017e-05, | |
| "loss": 2.6026, | |
| "mean_token_accuracy": 0.3432629868388176, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.42464031289286214, | |
| "grad_norm": 1.9419686794281006, | |
| "learning_rate": 7.118920363429405e-05, | |
| "loss": 2.6163, | |
| "mean_token_accuracy": 0.34115259498357775, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.4274339991618941, | |
| "grad_norm": 2.822739601135254, | |
| "learning_rate": 7.074655491836988e-05, | |
| "loss": 2.6081, | |
| "mean_token_accuracy": 0.34123376458883287, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.4302276854309261, | |
| "grad_norm": 2.17193341255188, | |
| "learning_rate": 7.030193320727508e-05, | |
| "loss": 2.5796, | |
| "mean_token_accuracy": 0.3430194780230522, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.4330213716999581, | |
| "grad_norm": 2.2731964588165283, | |
| "learning_rate": 6.985538078448714e-05, | |
| "loss": 2.6235, | |
| "mean_token_accuracy": 0.3362012967467308, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.43581505796899006, | |
| "grad_norm": 2.6764817237854004, | |
| "learning_rate": 6.940694011709411e-05, | |
| "loss": 2.626, | |
| "mean_token_accuracy": 0.3414772734045982, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.4386087442380221, | |
| "grad_norm": 2.273409366607666, | |
| "learning_rate": 6.895665385175587e-05, | |
| "loss": 2.571, | |
| "mean_token_accuracy": 0.3428571432828903, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.4414024305070541, | |
| "grad_norm": 2.117824077606201, | |
| "learning_rate": 6.850456481064841e-05, | |
| "loss": 2.6061, | |
| "mean_token_accuracy": 0.34269480109214784, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.44419611677608606, | |
| "grad_norm": 2.7593703269958496, | |
| "learning_rate": 6.80507159873916e-05, | |
| "loss": 2.5878, | |
| "mean_token_accuracy": 0.34480519592761993, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.44698980304511804, | |
| "grad_norm": 2.5217463970184326, | |
| "learning_rate": 6.759515054296033e-05, | |
| "loss": 2.5867, | |
| "mean_token_accuracy": 0.3475649327039719, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.44978348931415, | |
| "grad_norm": 2.5164499282836914, | |
| "learning_rate": 6.713791180158004e-05, | |
| "loss": 2.6199, | |
| "mean_token_accuracy": 0.3417207792401314, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.452577175583182, | |
| "grad_norm": 4.4600701332092285, | |
| "learning_rate": 6.667904324660648e-05, | |
| "loss": 2.5562, | |
| "mean_token_accuracy": 0.3468344137072563, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.455370861852214, | |
| "grad_norm": 2.2503256797790527, | |
| "learning_rate": 6.621858851639052e-05, | |
| "loss": 2.598, | |
| "mean_token_accuracy": 0.33928571343421937, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.45816454812124596, | |
| "grad_norm": 2.7074501514434814, | |
| "learning_rate": 6.575659140012813e-05, | |
| "loss": 2.5749, | |
| "mean_token_accuracy": 0.34350649267435074, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.460958234390278, | |
| "grad_norm": 2.3996992111206055, | |
| "learning_rate": 6.529309583369605e-05, | |
| "loss": 2.5655, | |
| "mean_token_accuracy": 0.3461850643157959, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.46375192065931, | |
| "grad_norm": 2.124371290206909, | |
| "learning_rate": 6.482814589547343e-05, | |
| "loss": 2.5734, | |
| "mean_token_accuracy": 0.3435064911842346, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.46654560692834196, | |
| "grad_norm": 2.760023832321167, | |
| "learning_rate": 6.436178580215006e-05, | |
| "loss": 2.5831, | |
| "mean_token_accuracy": 0.34821428507566454, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.46933929319737394, | |
| "grad_norm": 2.2467293739318848, | |
| "learning_rate": 6.389405990452131e-05, | |
| "loss": 2.5386, | |
| "mean_token_accuracy": 0.34837662279605863, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.4721329794664059, | |
| "grad_norm": 2.895301342010498, | |
| "learning_rate": 6.342501268327036e-05, | |
| "loss": 2.608, | |
| "mean_token_accuracy": 0.34366882890462874, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.4749266657354379, | |
| "grad_norm": 2.8437559604644775, | |
| "learning_rate": 6.295468874473824e-05, | |
| "loss": 2.5744, | |
| "mean_token_accuracy": 0.34375, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.4777203520044699, | |
| "grad_norm": 2.2013747692108154, | |
| "learning_rate": 6.248313281668151e-05, | |
| "loss": 2.5572, | |
| "mean_token_accuracy": 0.34269480407238007, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.48051403827350186, | |
| "grad_norm": 2.285017728805542, | |
| "learning_rate": 6.201038974401893e-05, | |
| "loss": 2.5755, | |
| "mean_token_accuracy": 0.3433441549539566, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.4833077245425339, | |
| "grad_norm": 3.0466742515563965, | |
| "learning_rate": 6.15365044845665e-05, | |
| "loss": 2.5605, | |
| "mean_token_accuracy": 0.34318181723356245, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.4861014108115659, | |
| "grad_norm": 2.7282652854919434, | |
| "learning_rate": 6.10615221047621e-05, | |
| "loss": 2.5826, | |
| "mean_token_accuracy": 0.34439935386180875, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.48889509708059786, | |
| "grad_norm": 2.5899875164031982, | |
| "learning_rate": 6.0585487775379634e-05, | |
| "loss": 2.569, | |
| "mean_token_accuracy": 0.3461850628256798, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.49168878334962984, | |
| "grad_norm": 2.2856500148773193, | |
| "learning_rate": 6.0108446767233304e-05, | |
| "loss": 2.5432, | |
| "mean_token_accuracy": 0.3460227265954018, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.4944824696186618, | |
| "grad_norm": 2.4979193210601807, | |
| "learning_rate": 5.963044444687235e-05, | |
| "loss": 2.5524, | |
| "mean_token_accuracy": 0.3460227265954018, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.4972761558876938, | |
| "grad_norm": 3.4747583866119385, | |
| "learning_rate": 5.91515262722667e-05, | |
| "loss": 2.5506, | |
| "mean_token_accuracy": 0.34025973826646805, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.5000698421567258, | |
| "grad_norm": 2.0753846168518066, | |
| "learning_rate": 5.867173778848394e-05, | |
| "loss": 2.5333, | |
| "mean_token_accuracy": 0.34845779091119766, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.5000698421567258, | |
| "eval_loss": 2.6793947219848633, | |
| "eval_mean_token_accuracy": 0.3425768423901875, | |
| "eval_runtime": 994.8268, | |
| "eval_samples_per_second": 98.841, | |
| "eval_steps_per_second": 1.765, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.5028635284257578, | |
| "grad_norm": 2.6756086349487305, | |
| "learning_rate": 5.819112462335792e-05, | |
| "loss": 2.5148, | |
| "mean_token_accuracy": 0.34748376458883284, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.5056572146947897, | |
| "grad_norm": 2.5338103771209717, | |
| "learning_rate": 5.770973248314965e-05, | |
| "loss": 2.5498, | |
| "mean_token_accuracy": 0.3452110379934311, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.5084509009638217, | |
| "grad_norm": 2.2562379837036133, | |
| "learning_rate": 5.722760714820057e-05, | |
| "loss": 2.5533, | |
| "mean_token_accuracy": 0.34634740203619, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.5112445872328537, | |
| "grad_norm": 2.7285821437835693, | |
| "learning_rate": 5.674479446857885e-05, | |
| "loss": 2.5056, | |
| "mean_token_accuracy": 0.3499999985098839, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.5140382735018857, | |
| "grad_norm": 2.5474276542663574, | |
| "learning_rate": 5.626134035971908e-05, | |
| "loss": 2.5642, | |
| "mean_token_accuracy": 0.34456168711185453, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.5168319597709177, | |
| "grad_norm": 2.749859094619751, | |
| "learning_rate": 5.577729079805569e-05, | |
| "loss": 2.5206, | |
| "mean_token_accuracy": 0.34821428507566454, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.5196256460399498, | |
| "grad_norm": 3.221196413040161, | |
| "learning_rate": 5.529269181665064e-05, | |
| "loss": 2.5129, | |
| "mean_token_accuracy": 0.3448051944375038, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.5224193323089817, | |
| "grad_norm": 3.7197160720825195, | |
| "learning_rate": 5.4807589500815606e-05, | |
| "loss": 2.5394, | |
| "mean_token_accuracy": 0.3462662324309349, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.5252130185780137, | |
| "grad_norm": 2.5209450721740723, | |
| "learning_rate": 5.432202998372932e-05, | |
| "loss": 2.521, | |
| "mean_token_accuracy": 0.3460227236151695, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.5280067048470457, | |
| "grad_norm": 2.6848323345184326, | |
| "learning_rate": 5.383605944205033e-05, | |
| "loss": 2.5506, | |
| "mean_token_accuracy": 0.3453733742237091, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.5308003911160777, | |
| "grad_norm": 2.5749640464782715, | |
| "learning_rate": 5.334972409152559e-05, | |
| "loss": 2.5357, | |
| "mean_token_accuracy": 0.34399350732564926, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.5335940773851097, | |
| "grad_norm": 2.7281625270843506, | |
| "learning_rate": 5.286307018259529e-05, | |
| "loss": 2.5287, | |
| "mean_token_accuracy": 0.3456168845295906, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.5363877636541416, | |
| "grad_norm": 2.868173122406006, | |
| "learning_rate": 5.237614399599451e-05, | |
| "loss": 2.5066, | |
| "mean_token_accuracy": 0.3488636389374733, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.5391814499231736, | |
| "grad_norm": 2.461381673812866, | |
| "learning_rate": 5.1888991838351916e-05, | |
| "loss": 2.52, | |
| "mean_token_accuracy": 0.34163961112499236, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.5419751361922056, | |
| "grad_norm": 2.8189141750335693, | |
| "learning_rate": 5.140166003778603e-05, | |
| "loss": 2.5391, | |
| "mean_token_accuracy": 0.34618506133556365, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.5447688224612376, | |
| "grad_norm": 2.760181427001953, | |
| "learning_rate": 5.091419493949929e-05, | |
| "loss": 2.5464, | |
| "mean_token_accuracy": 0.34740259647369387, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.5475625087302696, | |
| "grad_norm": 3.0051541328430176, | |
| "learning_rate": 5.042664290137086e-05, | |
| "loss": 2.5276, | |
| "mean_token_accuracy": 0.3481331169605255, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.5503561949993016, | |
| "grad_norm": 2.959178924560547, | |
| "learning_rate": 4.993905028954778e-05, | |
| "loss": 2.5281, | |
| "mean_token_accuracy": 0.34642857015132905, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.5531498812683335, | |
| "grad_norm": 2.7471230030059814, | |
| "learning_rate": 4.94514634740357e-05, | |
| "loss": 2.5127, | |
| "mean_token_accuracy": 0.34821428507566454, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.5559435675373655, | |
| "grad_norm": 3.817932605743408, | |
| "learning_rate": 4.896392882428901e-05, | |
| "loss": 2.5538, | |
| "mean_token_accuracy": 0.3424512967467308, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.5587372538063975, | |
| "grad_norm": 2.950193166732788, | |
| "learning_rate": 4.847649270480117e-05, | |
| "loss": 2.4831, | |
| "mean_token_accuracy": 0.34951298832893374, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.5615309400754295, | |
| "grad_norm": 3.4689207077026367, | |
| "learning_rate": 4.7989201470695396e-05, | |
| "loss": 2.4955, | |
| "mean_token_accuracy": 0.34439934939146044, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.5643246263444616, | |
| "grad_norm": 2.9318456649780273, | |
| "learning_rate": 4.750210146331632e-05, | |
| "loss": 2.5267, | |
| "mean_token_accuracy": 0.34691558331251143, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.5671183126134935, | |
| "grad_norm": 2.702409505844116, | |
| "learning_rate": 4.701523900582295e-05, | |
| "loss": 2.5095, | |
| "mean_token_accuracy": 0.34829545617103574, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.5699119988825255, | |
| "grad_norm": 2.8087456226348877, | |
| "learning_rate": 4.6528660398783326e-05, | |
| "loss": 2.4989, | |
| "mean_token_accuracy": 0.3536525994539261, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.5727056851515575, | |
| "grad_norm": 2.8514254093170166, | |
| "learning_rate": 4.6042411915771306e-05, | |
| "loss": 2.5446, | |
| "mean_token_accuracy": 0.34764610081911085, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.5754993714205895, | |
| "grad_norm": 2.71073317527771, | |
| "learning_rate": 4.555653979896603e-05, | |
| "loss": 2.503, | |
| "mean_token_accuracy": 0.34829545170068743, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.5782930576896215, | |
| "grad_norm": 2.834017753601074, | |
| "learning_rate": 4.507109025475423e-05, | |
| "loss": 2.4925, | |
| "mean_token_accuracy": 0.34853895753622055, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.5810867439586535, | |
| "grad_norm": 2.7667429447174072, | |
| "learning_rate": 4.4586109449336045e-05, | |
| "loss": 2.4791, | |
| "mean_token_accuracy": 0.34967532455921174, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.5838804302276854, | |
| "grad_norm": 2.7539703845977783, | |
| "learning_rate": 4.410164350433457e-05, | |
| "loss": 2.481, | |
| "mean_token_accuracy": 0.3508928567171097, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.5866741164967174, | |
| "grad_norm": 2.7576351165771484, | |
| "learning_rate": 4.361773849240977e-05, | |
| "loss": 2.5077, | |
| "mean_token_accuracy": 0.3529220804572105, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.5894678027657494, | |
| "grad_norm": 2.8457632064819336, | |
| "learning_rate": 4.313444043287691e-05, | |
| "loss": 2.5038, | |
| "mean_token_accuracy": 0.34740259796380996, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.5922614890347814, | |
| "grad_norm": 3.2245895862579346, | |
| "learning_rate": 4.265179528733017e-05, | |
| "loss": 2.5013, | |
| "mean_token_accuracy": 0.3470779210329056, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.5950551753038134, | |
| "grad_norm": 2.93704891204834, | |
| "learning_rate": 4.2169848955271624e-05, | |
| "loss": 2.4865, | |
| "mean_token_accuracy": 0.3499188289046288, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.5978488615728453, | |
| "grad_norm": 2.9629595279693604, | |
| "learning_rate": 4.1688647269746324e-05, | |
| "loss": 2.5028, | |
| "mean_token_accuracy": 0.3491883099079132, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.6006425478418773, | |
| "grad_norm": 3.764291286468506, | |
| "learning_rate": 4.120823599298349e-05, | |
| "loss": 2.4974, | |
| "mean_token_accuracy": 0.3502435013651848, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.6034362341109093, | |
| "grad_norm": 3.1387903690338135, | |
| "learning_rate": 4.0728660812044536e-05, | |
| "loss": 2.4754, | |
| "mean_token_accuracy": 0.3487012982368469, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.6062299203799413, | |
| "grad_norm": 3.713451385498047, | |
| "learning_rate": 4.0249967334478266e-05, | |
| "loss": 2.4594, | |
| "mean_token_accuracy": 0.35519480258226394, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.6090236066489734, | |
| "grad_norm": 3.5359973907470703, | |
| "learning_rate": 3.9772201083983596e-05, | |
| "loss": 2.4914, | |
| "mean_token_accuracy": 0.34983766078948975, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.6118172929180054, | |
| "grad_norm": 3.2408080101013184, | |
| "learning_rate": 3.929540749608024e-05, | |
| "loss": 2.4659, | |
| "mean_token_accuracy": 0.3521103858947754, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.6146109791870373, | |
| "grad_norm": 3.0888562202453613, | |
| "learning_rate": 3.881963191378778e-05, | |
| "loss": 2.4789, | |
| "mean_token_accuracy": 0.3471590906381607, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.6174046654560693, | |
| "grad_norm": 3.0336287021636963, | |
| "learning_rate": 3.83449195833136e-05, | |
| "loss": 2.4546, | |
| "mean_token_accuracy": 0.34886363446712493, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.6201983517251013, | |
| "grad_norm": 3.150221347808838, | |
| "learning_rate": 3.7871315649749953e-05, | |
| "loss": 2.4682, | |
| "mean_token_accuracy": 0.3517857164144516, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.6229920379941333, | |
| "grad_norm": 2.995313882827759, | |
| "learning_rate": 3.739886515278066e-05, | |
| "loss": 2.4592, | |
| "mean_token_accuracy": 0.35413961112499237, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.6257857242631653, | |
| "grad_norm": 3.334155321121216, | |
| "learning_rate": 3.692761302239779e-05, | |
| "loss": 2.4621, | |
| "mean_token_accuracy": 0.3563311696052551, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.6285794105321972, | |
| "grad_norm": 3.2132041454315186, | |
| "learning_rate": 3.645760407462896e-05, | |
| "loss": 2.4589, | |
| "mean_token_accuracy": 0.35081168860197065, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.6313730968012292, | |
| "grad_norm": 3.1528499126434326, | |
| "learning_rate": 3.598888300727521e-05, | |
| "loss": 2.4256, | |
| "mean_token_accuracy": 0.3550324648618698, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.6341667830702612, | |
| "grad_norm": 3.3648734092712402, | |
| "learning_rate": 3.552149439566029e-05, | |
| "loss": 2.4552, | |
| "mean_token_accuracy": 0.35657467097043993, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.6369604693392932, | |
| "grad_norm": 3.0252137184143066, | |
| "learning_rate": 3.505548268839155e-05, | |
| "loss": 2.4769, | |
| "mean_token_accuracy": 0.3514610409736633, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.6397541556083252, | |
| "grad_norm": 2.9841442108154297, | |
| "learning_rate": 3.45908922031329e-05, | |
| "loss": 2.4483, | |
| "mean_token_accuracy": 0.3573863670229912, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.6425478418773571, | |
| "grad_norm": 3.206582546234131, | |
| "learning_rate": 3.412776712239016e-05, | |
| "loss": 2.4437, | |
| "mean_token_accuracy": 0.3538961037993431, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.6453415281463891, | |
| "grad_norm": 2.9362432956695557, | |
| "learning_rate": 3.3666151489309364e-05, | |
| "loss": 2.4284, | |
| "mean_token_accuracy": 0.35787337720394136, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.6481352144154211, | |
| "grad_norm": 3.4137799739837646, | |
| "learning_rate": 3.32060892034882e-05, | |
| "loss": 2.4621, | |
| "mean_token_accuracy": 0.35308441519737244, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.6509289006844531, | |
| "grad_norm": 3.3628833293914795, | |
| "learning_rate": 3.274762401680124e-05, | |
| "loss": 2.4417, | |
| "mean_token_accuracy": 0.35600649267435075, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.6537225869534852, | |
| "grad_norm": 3.157782793045044, | |
| "learning_rate": 3.229079952923908e-05, | |
| "loss": 2.4363, | |
| "mean_token_accuracy": 0.3574675336480141, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.6565162732225172, | |
| "grad_norm": 3.448489189147949, | |
| "learning_rate": 3.183565918476198e-05, | |
| "loss": 2.4261, | |
| "mean_token_accuracy": 0.3572240278124809, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.6593099594915491, | |
| "grad_norm": 3.607093572616577, | |
| "learning_rate": 3.1382246267168386e-05, | |
| "loss": 2.4279, | |
| "mean_token_accuracy": 0.35633117109537127, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.6621036457605811, | |
| "grad_norm": 3.165947914123535, | |
| "learning_rate": 3.093060389597865e-05, | |
| "loss": 2.4558, | |
| "mean_token_accuracy": 0.3527597412467003, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.6648973320296131, | |
| "grad_norm": 3.2351622581481934, | |
| "learning_rate": 3.048077502233434e-05, | |
| "loss": 2.4079, | |
| "mean_token_accuracy": 0.35860389471054077, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.6676910182986451, | |
| "grad_norm": 3.320864677429199, | |
| "learning_rate": 3.0032802424913563e-05, | |
| "loss": 2.4491, | |
| "mean_token_accuracy": 0.3559253215789795, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.6704847045676771, | |
| "grad_norm": 3.1946163177490234, | |
| "learning_rate": 2.9586728705862813e-05, | |
| "loss": 2.4654, | |
| "mean_token_accuracy": 0.3549513012170792, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.673278390836709, | |
| "grad_norm": 3.2893896102905273, | |
| "learning_rate": 2.914259628674542e-05, | |
| "loss": 2.4384, | |
| "mean_token_accuracy": 0.35592532306909563, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.676072077105741, | |
| "grad_norm": 3.068572521209717, | |
| "learning_rate": 2.870044740450729e-05, | |
| "loss": 2.4351, | |
| "mean_token_accuracy": 0.356168831884861, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.678865763374773, | |
| "grad_norm": 3.2332894802093506, | |
| "learning_rate": 2.8260324107460197e-05, | |
| "loss": 2.4432, | |
| "mean_token_accuracy": 0.35292208194732666, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.681659449643805, | |
| "grad_norm": 3.183605194091797, | |
| "learning_rate": 2.7822268251282975e-05, | |
| "loss": 2.4073, | |
| "mean_token_accuracy": 0.3563311696052551, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.684453135912837, | |
| "grad_norm": 3.625239133834839, | |
| "learning_rate": 2.7386321495041047e-05, | |
| "loss": 2.4071, | |
| "mean_token_accuracy": 0.35738636553287506, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.6872468221818689, | |
| "grad_norm": 3.204867362976074, | |
| "learning_rate": 2.695252529722467e-05, | |
| "loss": 2.415, | |
| "mean_token_accuracy": 0.3589285746216774, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.6900405084509009, | |
| "grad_norm": 3.107151985168457, | |
| "learning_rate": 2.65209209118062e-05, | |
| "loss": 2.4391, | |
| "mean_token_accuracy": 0.35519480854272845, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.6928341947199329, | |
| "grad_norm": 3.3900489807128906, | |
| "learning_rate": 2.6091549384316883e-05, | |
| "loss": 2.4317, | |
| "mean_token_accuracy": 0.3538961037993431, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.6956278809889649, | |
| "grad_norm": 3.0111920833587646, | |
| "learning_rate": 2.566445154794341e-05, | |
| "loss": 2.4185, | |
| "mean_token_accuracy": 0.3533279225230217, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.698421567257997, | |
| "grad_norm": 3.488588809967041, | |
| "learning_rate": 2.523966801964468e-05, | |
| "loss": 2.4098, | |
| "mean_token_accuracy": 0.3501623347401619, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.701215253527029, | |
| "grad_norm": 3.103729724884033, | |
| "learning_rate": 2.481723919628916e-05, | |
| "loss": 2.4228, | |
| "mean_token_accuracy": 0.35275974273681643, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.7040089397960609, | |
| "grad_norm": 3.421889305114746, | |
| "learning_rate": 2.4397205250813104e-05, | |
| "loss": 2.4011, | |
| "mean_token_accuracy": 0.3581980481743813, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.7068026260650929, | |
| "grad_norm": 3.167423725128174, | |
| "learning_rate": 2.3979606128400162e-05, | |
| "loss": 2.4235, | |
| "mean_token_accuracy": 0.3530844137072563, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.7095963123341249, | |
| "grad_norm": 3.6433827877044678, | |
| "learning_rate": 2.3564481542682516e-05, | |
| "loss": 2.4054, | |
| "mean_token_accuracy": 0.3555194824934006, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.7123899986031569, | |
| "grad_norm": 3.3545353412628174, | |
| "learning_rate": 2.3151870971964224e-05, | |
| "loss": 2.431, | |
| "mean_token_accuracy": 0.35308441519737244, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.7151836848721889, | |
| "grad_norm": 3.181476593017578, | |
| "learning_rate": 2.2741813655466758e-05, | |
| "loss": 2.39, | |
| "mean_token_accuracy": 0.3538961037993431, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.7179773711412208, | |
| "grad_norm": 3.6350057125091553, | |
| "learning_rate": 2.2334348589597404e-05, | |
| "loss": 2.4131, | |
| "mean_token_accuracy": 0.35202922075986864, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.7207710574102528, | |
| "grad_norm": 4.146636962890625, | |
| "learning_rate": 2.1929514524240667e-05, | |
| "loss": 2.4173, | |
| "mean_token_accuracy": 0.3597402602434158, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.7235647436792848, | |
| "grad_norm": 4.2176384925842285, | |
| "learning_rate": 2.15273499590732e-05, | |
| "loss": 2.4013, | |
| "mean_token_accuracy": 0.3566558465361595, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.7263584299483168, | |
| "grad_norm": 3.659813165664673, | |
| "learning_rate": 2.112789313990246e-05, | |
| "loss": 2.4012, | |
| "mean_token_accuracy": 0.35600649416446684, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.7291521162173488, | |
| "grad_norm": 3.0530693531036377, | |
| "learning_rate": 2.073118205502957e-05, | |
| "loss": 2.4082, | |
| "mean_token_accuracy": 0.3566558450460434, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.7319458024863807, | |
| "grad_norm": 4.101310729980469, | |
| "learning_rate": 2.0337254431636548e-05, | |
| "loss": 2.4011, | |
| "mean_token_accuracy": 0.3585227280855179, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.7347394887554127, | |
| "grad_norm": 4.217702388763428, | |
| "learning_rate": 1.99461477321986e-05, | |
| "loss": 2.3857, | |
| "mean_token_accuracy": 0.35884740203619003, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.7375331750244447, | |
| "grad_norm": 3.2049005031585693, | |
| "learning_rate": 1.9557899150921317e-05, | |
| "loss": 2.3847, | |
| "mean_token_accuracy": 0.35649350583553313, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.7403268612934767, | |
| "grad_norm": 3.6392228603363037, | |
| "learning_rate": 1.9172545610203575e-05, | |
| "loss": 2.435, | |
| "mean_token_accuracy": 0.35349026024341584, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.7431205475625088, | |
| "grad_norm": 3.226102352142334, | |
| "learning_rate": 1.8790123757126195e-05, | |
| "loss": 2.3908, | |
| "mean_token_accuracy": 0.3583603873848915, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.7459142338315408, | |
| "grad_norm": 3.2937116622924805, | |
| "learning_rate": 1.84106699599668e-05, | |
| "loss": 2.3964, | |
| "mean_token_accuracy": 0.3568181827664375, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.7487079201005727, | |
| "grad_norm": 3.6983494758605957, | |
| "learning_rate": 1.803422030474126e-05, | |
| "loss": 2.3886, | |
| "mean_token_accuracy": 0.35698052048683165, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.7501047632350887, | |
| "eval_loss": 2.7606494426727295, | |
| "eval_mean_token_accuracy": 0.3412951716176516, | |
| "eval_runtime": 989.3775, | |
| "eval_samples_per_second": 99.386, | |
| "eval_steps_per_second": 1.775, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 0.7515016063696047, | |
| "grad_norm": 3.6565871238708496, | |
| "learning_rate": 1.7660810591771785e-05, | |
| "loss": 2.4133, | |
| "mean_token_accuracy": 0.36103896498680116, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.7542952926386367, | |
| "grad_norm": 3.315748691558838, | |
| "learning_rate": 1.7290476332282468e-05, | |
| "loss": 2.3908, | |
| "mean_token_accuracy": 0.36071428656578064, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.7570889789076687, | |
| "grad_norm": 3.21600604057312, | |
| "learning_rate": 1.6923252745022062e-05, | |
| "loss": 2.3913, | |
| "mean_token_accuracy": 0.3598214253783226, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.7598826651767007, | |
| "grad_norm": 4.019015312194824, | |
| "learning_rate": 1.6559174752914754e-05, | |
| "loss": 2.394, | |
| "mean_token_accuracy": 0.35957791954278945, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.7626763514457326, | |
| "grad_norm": 3.757371664047241, | |
| "learning_rate": 1.6198276979738942e-05, | |
| "loss": 2.4179, | |
| "mean_token_accuracy": 0.35170454531908035, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.7654700377147646, | |
| "grad_norm": 3.8441550731658936, | |
| "learning_rate": 1.5840593746834546e-05, | |
| "loss": 2.3617, | |
| "mean_token_accuracy": 0.3576298698782921, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.7682637239837966, | |
| "grad_norm": 3.4171853065490723, | |
| "learning_rate": 1.5486159069839058e-05, | |
| "loss": 2.3991, | |
| "mean_token_accuracy": 0.3582792207598686, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.7710574102528286, | |
| "grad_norm": 3.999089002609253, | |
| "learning_rate": 1.5135006655452644e-05, | |
| "loss": 2.385, | |
| "mean_token_accuracy": 0.35746753215789795, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.7738510965218606, | |
| "grad_norm": 3.6210405826568604, | |
| "learning_rate": 1.4787169898232618e-05, | |
| "loss": 2.3821, | |
| "mean_token_accuracy": 0.3604707822203636, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.7766447827908926, | |
| "grad_norm": 3.676494836807251, | |
| "learning_rate": 1.4442681877417686e-05, | |
| "loss": 2.3897, | |
| "mean_token_accuracy": 0.35560064762830734, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.7794384690599245, | |
| "grad_norm": 3.83720326423645, | |
| "learning_rate": 1.410157535378206e-05, | |
| "loss": 2.3225, | |
| "mean_token_accuracy": 0.3604707807302475, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.7822321553289565, | |
| "grad_norm": 3.8904194831848145, | |
| "learning_rate": 1.3763882766519926e-05, | |
| "loss": 2.3878, | |
| "mean_token_accuracy": 0.35600649267435075, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.7850258415979885, | |
| "grad_norm": 3.4765756130218506, | |
| "learning_rate": 1.3429636230160498e-05, | |
| "loss": 2.3814, | |
| "mean_token_accuracy": 0.3632305219769478, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.7878195278670206, | |
| "grad_norm": 3.398759126663208, | |
| "learning_rate": 1.3098867531513903e-05, | |
| "loss": 2.3775, | |
| "mean_token_accuracy": 0.3590909048914909, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.7906132141360526, | |
| "grad_norm": 3.791919231414795, | |
| "learning_rate": 1.2771608126648293e-05, | |
| "loss": 2.3942, | |
| "mean_token_accuracy": 0.3641233786940575, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.7934069004050845, | |
| "grad_norm": 3.9098916053771973, | |
| "learning_rate": 1.2447889137898293e-05, | |
| "loss": 2.3438, | |
| "mean_token_accuracy": 0.36055194288492204, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.7962005866741165, | |
| "grad_norm": 3.677560567855835, | |
| "learning_rate": 1.2127741350905397e-05, | |
| "loss": 2.3837, | |
| "mean_token_accuracy": 0.3632305219769478, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.7989942729431485, | |
| "grad_norm": 3.279231548309326, | |
| "learning_rate": 1.1811195211690169e-05, | |
| "loss": 2.3939, | |
| "mean_token_accuracy": 0.3599026009440422, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.8017879592121805, | |
| "grad_norm": 3.5640265941619873, | |
| "learning_rate": 1.1498280823756841e-05, | |
| "loss": 2.3774, | |
| "mean_token_accuracy": 0.3581980511546135, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.8045816454812125, | |
| "grad_norm": 3.7095561027526855, | |
| "learning_rate": 1.1189027945230496e-05, | |
| "loss": 2.3944, | |
| "mean_token_accuracy": 0.35584415346384046, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.8073753317502445, | |
| "grad_norm": 3.6211345195770264, | |
| "learning_rate": 1.0883465986027059e-05, | |
| "loss": 2.3879, | |
| "mean_token_accuracy": 0.3619318217039108, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.8101690180192764, | |
| "grad_norm": 3.5692007541656494, | |
| "learning_rate": 1.0581624005056424e-05, | |
| "loss": 2.3611, | |
| "mean_token_accuracy": 0.36030844151973723, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.8129627042883084, | |
| "grad_norm": 3.9471545219421387, | |
| "learning_rate": 1.0283530707458922e-05, | |
| "loss": 2.4062, | |
| "mean_token_accuracy": 0.356331168115139, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 0.8157563905573404, | |
| "grad_norm": 4.07960844039917, | |
| "learning_rate": 9.989214441875522e-06, | |
| "loss": 2.3634, | |
| "mean_token_accuracy": 0.36566558480262756, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.8185500768263724, | |
| "grad_norm": 3.9245829582214355, | |
| "learning_rate": 9.698703197751851e-06, | |
| "loss": 2.332, | |
| "mean_token_accuracy": 0.3642857164144516, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 0.8213437630954044, | |
| "grad_norm": 3.7653911113739014, | |
| "learning_rate": 9.412024602676378e-06, | |
| "loss": 2.3998, | |
| "mean_token_accuracy": 0.35511363595724105, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.8241374493644363, | |
| "grad_norm": 3.9197909832000732, | |
| "learning_rate": 9.129205919753075e-06, | |
| "loss": 2.3641, | |
| "mean_token_accuracy": 0.3629870146512985, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.8269311356334683, | |
| "grad_norm": 3.7501025199890137, | |
| "learning_rate": 8.850274045008666e-06, | |
| "loss": 2.3705, | |
| "mean_token_accuracy": 0.36079545617103576, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.8297248219025003, | |
| "grad_norm": 3.8063013553619385, | |
| "learning_rate": 8.575255504834827e-06, | |
| "loss": 2.3993, | |
| "mean_token_accuracy": 0.36266233772039413, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 0.8325185081715324, | |
| "grad_norm": 3.9794483184814453, | |
| "learning_rate": 8.304176453465556e-06, | |
| "loss": 2.3816, | |
| "mean_token_accuracy": 0.3581168860197067, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.8353121944405644, | |
| "grad_norm": 3.6001126766204834, | |
| "learning_rate": 8.037062670489842e-06, | |
| "loss": 2.3807, | |
| "mean_token_accuracy": 0.3580357149243355, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 0.8381058807095964, | |
| "grad_norm": 3.5399417877197266, | |
| "learning_rate": 7.773939558400101e-06, | |
| "loss": 2.3788, | |
| "mean_token_accuracy": 0.3605519488453865, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.8408995669786283, | |
| "grad_norm": 3.753068208694458, | |
| "learning_rate": 7.51483214017637e-06, | |
| "loss": 2.3517, | |
| "mean_token_accuracy": 0.3618506520986557, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 0.8436932532476603, | |
| "grad_norm": 4.195340156555176, | |
| "learning_rate": 7.259765056906609e-06, | |
| "loss": 2.3818, | |
| "mean_token_accuracy": 0.3603896126151085, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 0.8464869395166923, | |
| "grad_norm": 4.046124458312988, | |
| "learning_rate": 7.008762565443378e-06, | |
| "loss": 2.3566, | |
| "mean_token_accuracy": 0.3603896081447601, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 0.8492806257857243, | |
| "grad_norm": 3.6873440742492676, | |
| "learning_rate": 6.76184853609696e-06, | |
| "loss": 2.3539, | |
| "mean_token_accuracy": 0.35795454531908033, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 0.8520743120547563, | |
| "grad_norm": 3.5705506801605225, | |
| "learning_rate": 6.519046450365346e-06, | |
| "loss": 2.3515, | |
| "mean_token_accuracy": 0.3608766242861748, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.8548679983237882, | |
| "grad_norm": 3.630878448486328, | |
| "learning_rate": 6.280379398701114e-06, | |
| "loss": 2.3596, | |
| "mean_token_accuracy": 0.3606331154704094, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 0.8576616845928202, | |
| "grad_norm": 3.789283514022827, | |
| "learning_rate": 6.045870078315541e-06, | |
| "loss": 2.3504, | |
| "mean_token_accuracy": 0.36233766227960584, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 0.8604553708618522, | |
| "grad_norm": 3.9113943576812744, | |
| "learning_rate": 5.8155407910201135e-06, | |
| "loss": 2.3738, | |
| "mean_token_accuracy": 0.36241883486509324, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 0.8632490571308842, | |
| "grad_norm": 3.61296010017395, | |
| "learning_rate": 5.5894134411055955e-06, | |
| "loss": 2.3907, | |
| "mean_token_accuracy": 0.35900974124670026, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 0.8660427433999162, | |
| "grad_norm": 3.8162384033203125, | |
| "learning_rate": 5.367509533258969e-06, | |
| "loss": 2.3164, | |
| "mean_token_accuracy": 0.3629870146512985, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.8688364296689481, | |
| "grad_norm": 3.9131879806518555, | |
| "learning_rate": 5.149850170518328e-06, | |
| "loss": 2.3605, | |
| "mean_token_accuracy": 0.360146102309227, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 0.8716301159379801, | |
| "grad_norm": 3.934457540512085, | |
| "learning_rate": 4.9364560522659365e-06, | |
| "loss": 2.3576, | |
| "mean_token_accuracy": 0.3599025964736938, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 0.8744238022070121, | |
| "grad_norm": 3.8578693866729736, | |
| "learning_rate": 4.727347472259813e-06, | |
| "loss": 2.3573, | |
| "mean_token_accuracy": 0.36201298981904984, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 0.8772174884760442, | |
| "grad_norm": 3.8296849727630615, | |
| "learning_rate": 4.522544316703709e-06, | |
| "loss": 2.3431, | |
| "mean_token_accuracy": 0.3612824693322182, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 0.8800111747450762, | |
| "grad_norm": 3.58001971244812, | |
| "learning_rate": 4.322066062355984e-06, | |
| "loss": 2.3756, | |
| "mean_token_accuracy": 0.3618506506085396, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.8828048610141082, | |
| "grad_norm": 3.9927351474761963, | |
| "learning_rate": 4.125931774677349e-06, | |
| "loss": 2.3874, | |
| "mean_token_accuracy": 0.358766233921051, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 0.8855985472831401, | |
| "grad_norm": 3.5192744731903076, | |
| "learning_rate": 3.934160106017748e-06, | |
| "loss": 2.3473, | |
| "mean_token_accuracy": 0.36599026024341585, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 0.8883922335521721, | |
| "grad_norm": 3.695925235748291, | |
| "learning_rate": 3.7467692938425057e-06, | |
| "loss": 2.36, | |
| "mean_token_accuracy": 0.3630681812763214, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 0.8911859198212041, | |
| "grad_norm": 3.908273696899414, | |
| "learning_rate": 3.563777158997977e-06, | |
| "loss": 2.3429, | |
| "mean_token_accuracy": 0.3662337675690651, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 0.8939796060902361, | |
| "grad_norm": 3.800147294998169, | |
| "learning_rate": 3.3852011040167607e-06, | |
| "loss": 2.3469, | |
| "mean_token_accuracy": 0.3615259721875191, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.8967732923592681, | |
| "grad_norm": 3.7554497718811035, | |
| "learning_rate": 3.2110581114627225e-06, | |
| "loss": 2.3629, | |
| "mean_token_accuracy": 0.3570616886019707, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 0.8995669786283, | |
| "grad_norm": 3.9945056438446045, | |
| "learning_rate": 3.041364742315983e-06, | |
| "loss": 2.3897, | |
| "mean_token_accuracy": 0.3580357149243355, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 0.902360664897332, | |
| "grad_norm": 3.705796003341675, | |
| "learning_rate": 2.8761371343979273e-06, | |
| "loss": 2.3326, | |
| "mean_token_accuracy": 0.3644480526447296, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 0.905154351166364, | |
| "grad_norm": 3.556757688522339, | |
| "learning_rate": 2.7153910008365368e-06, | |
| "loss": 2.3759, | |
| "mean_token_accuracy": 0.3582792192697525, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 0.907948037435396, | |
| "grad_norm": 3.859874963760376, | |
| "learning_rate": 2.5591416285720424e-06, | |
| "loss": 2.3236, | |
| "mean_token_accuracy": 0.36079545617103576, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.910741723704428, | |
| "grad_norm": 4.084688186645508, | |
| "learning_rate": 2.4074038769031803e-06, | |
| "loss": 2.3757, | |
| "mean_token_accuracy": 0.36030844002962115, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 0.9135354099734599, | |
| "grad_norm": 3.861067295074463, | |
| "learning_rate": 2.2601921760740107e-06, | |
| "loss": 2.3407, | |
| "mean_token_accuracy": 0.3633116871118546, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 0.9163290962424919, | |
| "grad_norm": 4.909350395202637, | |
| "learning_rate": 2.1175205259016563e-06, | |
| "loss": 2.3366, | |
| "mean_token_accuracy": 0.3625811696052551, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 0.9191227825115239, | |
| "grad_norm": 3.506558895111084, | |
| "learning_rate": 1.979402494444915e-06, | |
| "loss": 2.3384, | |
| "mean_token_accuracy": 0.3619318187236786, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 0.921916468780556, | |
| "grad_norm": 3.9836270809173584, | |
| "learning_rate": 1.845851216713912e-06, | |
| "loss": 2.3518, | |
| "mean_token_accuracy": 0.3620129883289337, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.924710155049588, | |
| "grad_norm": 3.8005995750427246, | |
| "learning_rate": 1.7168793934209893e-06, | |
| "loss": 2.3505, | |
| "mean_token_accuracy": 0.3646915599703789, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 0.92750384131862, | |
| "grad_norm": 3.654874801635742, | |
| "learning_rate": 1.5924992897728475e-06, | |
| "loss": 2.3256, | |
| "mean_token_accuracy": 0.36566558480262756, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 0.9302975275876519, | |
| "grad_norm": 3.704705238342285, | |
| "learning_rate": 1.472722734304144e-06, | |
| "loss": 2.305, | |
| "mean_token_accuracy": 0.3631493508815765, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 0.9330912138566839, | |
| "grad_norm": 4.282053470611572, | |
| "learning_rate": 1.3575611177525926e-06, | |
| "loss": 2.3599, | |
| "mean_token_accuracy": 0.35868506878614426, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 0.9358849001257159, | |
| "grad_norm": 4.226362228393555, | |
| "learning_rate": 1.247025391975698e-06, | |
| "loss": 2.3347, | |
| "mean_token_accuracy": 0.36542207896709444, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.9386785863947479, | |
| "grad_norm": 3.9076080322265625, | |
| "learning_rate": 1.1411260689092484e-06, | |
| "loss": 2.3658, | |
| "mean_token_accuracy": 0.35722402632236483, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 0.9414722726637799, | |
| "grad_norm": 4.407858371734619, | |
| "learning_rate": 1.0398732195676331e-06, | |
| "loss": 2.32, | |
| "mean_token_accuracy": 0.3650974050164223, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 0.9442659589328118, | |
| "grad_norm": 3.794746160507202, | |
| "learning_rate": 9.432764730860744e-07, | |
| "loss": 2.3404, | |
| "mean_token_accuracy": 0.3632305204868317, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 0.9470596452018438, | |
| "grad_norm": 3.419100046157837, | |
| "learning_rate": 8.513450158049108e-07, | |
| "loss": 2.2942, | |
| "mean_token_accuracy": 0.3678571432828903, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 0.9498533314708758, | |
| "grad_norm": 3.609236001968384, | |
| "learning_rate": 7.640875903959732e-07, | |
| "loss": 2.3246, | |
| "mean_token_accuracy": 0.36477272808551786, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.9526470177399078, | |
| "grad_norm": 3.939943313598633, | |
| "learning_rate": 6.815124950311557e-07, | |
| "loss": 2.326, | |
| "mean_token_accuracy": 0.36209415793418886, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 0.9554407040089398, | |
| "grad_norm": 4.04728364944458, | |
| "learning_rate": 6.036275825932525e-07, | |
| "loss": 2.3391, | |
| "mean_token_accuracy": 0.3649350643157959, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 0.9582343902779717, | |
| "grad_norm": 4.012794494628906, | |
| "learning_rate": 5.304402599291824e-07, | |
| "loss": 2.3555, | |
| "mean_token_accuracy": 0.3619318202137947, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 0.9610280765470037, | |
| "grad_norm": 3.5218493938446045, | |
| "learning_rate": 4.61957487145559e-07, | |
| "loss": 2.3352, | |
| "mean_token_accuracy": 0.36607143133878706, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 0.9638217628160357, | |
| "grad_norm": 3.5637614727020264, | |
| "learning_rate": 3.981857769468023e-07, | |
| "loss": 2.3506, | |
| "mean_token_accuracy": 0.363879868388176, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.9666154490850678, | |
| "grad_norm": 4.030181407928467, | |
| "learning_rate": 3.391311940157904e-07, | |
| "loss": 2.3287, | |
| "mean_token_accuracy": 0.36655843555927276, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 0.9694091353540998, | |
| "grad_norm": 3.6736109256744385, | |
| "learning_rate": 2.8479935443708197e-07, | |
| "loss": 2.3548, | |
| "mean_token_accuracy": 0.36728896349668505, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 0.9722028216231318, | |
| "grad_norm": 3.6947691440582275, | |
| "learning_rate": 2.3519542516285965e-07, | |
| "loss": 2.3318, | |
| "mean_token_accuracy": 0.3616071417927742, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 0.9749965078921637, | |
| "grad_norm": 4.099936008453369, | |
| "learning_rate": 1.9032412352153473e-07, | |
| "loss": 2.3518, | |
| "mean_token_accuracy": 0.3631493508815765, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 0.9777901941611957, | |
| "grad_norm": 3.852231502532959, | |
| "learning_rate": 1.501897167691224e-07, | |
| "loss": 2.3392, | |
| "mean_token_accuracy": 0.3645292207598686, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.9805838804302277, | |
| "grad_norm": 3.9510109424591064, | |
| "learning_rate": 1.1479602168344983e-07, | |
| "loss": 2.3554, | |
| "mean_token_accuracy": 0.3650162324309349, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 0.9833775666992597, | |
| "grad_norm": 3.799307107925415, | |
| "learning_rate": 8.414640420116305e-08, | |
| "loss": 2.3089, | |
| "mean_token_accuracy": 0.362662336230278, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 0.9861712529682917, | |
| "grad_norm": 3.7856054306030273, | |
| "learning_rate": 5.824377909763312e-08, | |
| "loss": 2.3135, | |
| "mean_token_accuracy": 0.3685876622796059, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 0.9889649392373236, | |
| "grad_norm": 3.702875852584839, | |
| "learning_rate": 3.709060970975564e-08, | |
| "loss": 2.3606, | |
| "mean_token_accuracy": 0.36176948100328443, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 0.9917586255063556, | |
| "grad_norm": 3.9700822830200195, | |
| "learning_rate": 2.068890770169363e-08, | |
| "loss": 2.3494, | |
| "mean_token_accuracy": 0.3568993493914604, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.9945523117753876, | |
| "grad_norm": 3.895416736602783, | |
| "learning_rate": 9.040232873569477e-09, | |
| "loss": 2.3314, | |
| "mean_token_accuracy": 0.3663149356842041, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 0.9973459980444196, | |
| "grad_norm": 3.7410225868225098, | |
| "learning_rate": 2.145693013116956e-09, | |
| "loss": 2.3568, | |
| "mean_token_accuracy": 0.3575487032532692, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "mean_token_accuracy": 0.36799384575141103, | |
| "step": 7159, | |
| "total_flos": 1.6530020885331968e+18, | |
| "train_loss": 2.734565882330451, | |
| "train_runtime": 21227.811, | |
| "train_samples_per_second": 18.884, | |
| "train_steps_per_second": 0.337 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 7159, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1790, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.6530020885331968e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |