| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2002, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004995004995004995, | |
| "grad_norm": 1.1599862583346459, | |
| "learning_rate": 9.950248756218906e-08, | |
| "loss": 2.4381, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024975024975024975, | |
| "grad_norm": 1.3646452392145616, | |
| "learning_rate": 4.975124378109453e-07, | |
| "loss": 2.3925, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004995004995004995, | |
| "grad_norm": 1.050547128080392, | |
| "learning_rate": 9.950248756218907e-07, | |
| "loss": 2.3899, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007492507492507493, | |
| "grad_norm": 1.1106843586026567, | |
| "learning_rate": 1.4925373134328358e-06, | |
| "loss": 2.3606, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00999000999000999, | |
| "grad_norm": 1.0868632779387772, | |
| "learning_rate": 1.9900497512437813e-06, | |
| "loss": 2.3782, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012487512487512488, | |
| "grad_norm": 0.8822872185142195, | |
| "learning_rate": 2.4875621890547264e-06, | |
| "loss": 2.3681, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014985014985014986, | |
| "grad_norm": 0.6990472283962801, | |
| "learning_rate": 2.9850746268656716e-06, | |
| "loss": 2.3332, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017482517482517484, | |
| "grad_norm": 0.6640215974826378, | |
| "learning_rate": 3.4825870646766175e-06, | |
| "loss": 2.3265, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01998001998001998, | |
| "grad_norm": 0.6451421174329706, | |
| "learning_rate": 3.980099502487563e-06, | |
| "loss": 2.2609, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022477522477522476, | |
| "grad_norm": 0.4613452178440462, | |
| "learning_rate": 4.477611940298508e-06, | |
| "loss": 2.1835, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.024975024975024976, | |
| "grad_norm": 0.36216302524794514, | |
| "learning_rate": 4.975124378109453e-06, | |
| "loss": 2.1793, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.027472527472527472, | |
| "grad_norm": 0.29388450685747625, | |
| "learning_rate": 5.472636815920398e-06, | |
| "loss": 2.1195, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.029970029970029972, | |
| "grad_norm": 0.25381832457288017, | |
| "learning_rate": 5.970149253731343e-06, | |
| "loss": 2.065, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.032467532467532464, | |
| "grad_norm": 0.23481350483234162, | |
| "learning_rate": 6.46766169154229e-06, | |
| "loss": 2.1047, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03496503496503497, | |
| "grad_norm": 0.20628569151997012, | |
| "learning_rate": 6.965174129353235e-06, | |
| "loss": 2.0828, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.037462537462537464, | |
| "grad_norm": 0.19709869224218293, | |
| "learning_rate": 7.46268656716418e-06, | |
| "loss": 2.0265, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03996003996003996, | |
| "grad_norm": 0.2006237162245652, | |
| "learning_rate": 7.960199004975125e-06, | |
| "loss": 2.0299, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.042457542457542456, | |
| "grad_norm": 0.18543831140294761, | |
| "learning_rate": 8.45771144278607e-06, | |
| "loss": 2.0171, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.04495504495504495, | |
| "grad_norm": 0.18480210061309715, | |
| "learning_rate": 8.955223880597016e-06, | |
| "loss": 2.0388, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.047452547452547456, | |
| "grad_norm": 0.18002159323152245, | |
| "learning_rate": 9.45273631840796e-06, | |
| "loss": 2.0161, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.04995004995004995, | |
| "grad_norm": 0.18038747124195287, | |
| "learning_rate": 9.950248756218906e-06, | |
| "loss": 1.9666, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05244755244755245, | |
| "grad_norm": 0.18508558771562467, | |
| "learning_rate": 1.0447761194029851e-05, | |
| "loss": 1.9788, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.054945054945054944, | |
| "grad_norm": 0.1753326294106231, | |
| "learning_rate": 1.0945273631840796e-05, | |
| "loss": 1.9935, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05744255744255744, | |
| "grad_norm": 0.17338505913330995, | |
| "learning_rate": 1.1442786069651741e-05, | |
| "loss": 1.982, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.059940059940059943, | |
| "grad_norm": 0.17069633894083674, | |
| "learning_rate": 1.1940298507462686e-05, | |
| "loss": 1.9677, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06243756243756244, | |
| "grad_norm": 0.17033240645669973, | |
| "learning_rate": 1.2437810945273631e-05, | |
| "loss": 1.9579, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06493506493506493, | |
| "grad_norm": 0.16801885256509916, | |
| "learning_rate": 1.293532338308458e-05, | |
| "loss": 1.9328, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06743256743256744, | |
| "grad_norm": 0.16854179300669697, | |
| "learning_rate": 1.3432835820895525e-05, | |
| "loss": 1.9424, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.06993006993006994, | |
| "grad_norm": 0.16787976921679182, | |
| "learning_rate": 1.393034825870647e-05, | |
| "loss": 1.9229, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07242757242757243, | |
| "grad_norm": 0.167368866372539, | |
| "learning_rate": 1.4427860696517415e-05, | |
| "loss": 1.9537, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.07492507492507493, | |
| "grad_norm": 0.16524535846346908, | |
| "learning_rate": 1.492537313432836e-05, | |
| "loss": 1.911, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07742257742257742, | |
| "grad_norm": 0.16714889916639722, | |
| "learning_rate": 1.5422885572139307e-05, | |
| "loss": 1.9399, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.07992007992007992, | |
| "grad_norm": 0.16617978712852743, | |
| "learning_rate": 1.592039800995025e-05, | |
| "loss": 1.9203, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08241758241758242, | |
| "grad_norm": 0.16512217331592868, | |
| "learning_rate": 1.6417910447761197e-05, | |
| "loss": 1.923, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.08491508491508491, | |
| "grad_norm": 0.16496696956998044, | |
| "learning_rate": 1.691542288557214e-05, | |
| "loss": 1.9442, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.08741258741258741, | |
| "grad_norm": 0.16376024451930163, | |
| "learning_rate": 1.7412935323383088e-05, | |
| "loss": 1.931, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.0899100899100899, | |
| "grad_norm": 0.1640420678366522, | |
| "learning_rate": 1.791044776119403e-05, | |
| "loss": 1.908, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0924075924075924, | |
| "grad_norm": 0.160666099150629, | |
| "learning_rate": 1.8407960199004978e-05, | |
| "loss": 1.9139, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.09490509490509491, | |
| "grad_norm": 0.16238948145763205, | |
| "learning_rate": 1.890547263681592e-05, | |
| "loss": 1.8926, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.09740259740259741, | |
| "grad_norm": 0.163531659071721, | |
| "learning_rate": 1.9402985074626868e-05, | |
| "loss": 1.899, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.0999000999000999, | |
| "grad_norm": 0.16286090035138232, | |
| "learning_rate": 1.990049751243781e-05, | |
| "loss": 1.9091, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1023976023976024, | |
| "grad_norm": 0.16060757439288406, | |
| "learning_rate": 1.9999756577597317e-05, | |
| "loss": 1.8851, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.1048951048951049, | |
| "grad_norm": 0.16221564755663112, | |
| "learning_rate": 1.9998767694397236e-05, | |
| "loss": 1.8779, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.10739260739260739, | |
| "grad_norm": 0.158639070485282, | |
| "learning_rate": 1.99970182116654e-05, | |
| "loss": 1.8574, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.10989010989010989, | |
| "grad_norm": 0.1602764625642043, | |
| "learning_rate": 1.9994508262483786e-05, | |
| "loss": 1.8777, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.11238761238761238, | |
| "grad_norm": 0.16307835969521423, | |
| "learning_rate": 1.999123803778254e-05, | |
| "loss": 1.9083, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.11488511488511488, | |
| "grad_norm": 0.1628647640219108, | |
| "learning_rate": 1.998720778632546e-05, | |
| "loss": 1.8748, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.11738261738261738, | |
| "grad_norm": 0.16061369451851806, | |
| "learning_rate": 1.9982417814691048e-05, | |
| "loss": 1.8514, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.11988011988011989, | |
| "grad_norm": 0.1623492271600646, | |
| "learning_rate": 1.997686848724924e-05, | |
| "loss": 1.8334, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.12237762237762238, | |
| "grad_norm": 0.16052653488024277, | |
| "learning_rate": 1.997056022613363e-05, | |
| "loss": 1.8828, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.12487512487512488, | |
| "grad_norm": 0.16186662472616486, | |
| "learning_rate": 1.9963493511209405e-05, | |
| "loss": 1.8689, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.12737262737262736, | |
| "grad_norm": 0.15814062813935195, | |
| "learning_rate": 1.9955668880036812e-05, | |
| "loss": 1.8633, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.12987012987012986, | |
| "grad_norm": 0.16042937756824743, | |
| "learning_rate": 1.9947086927830277e-05, | |
| "loss": 1.859, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.13236763236763235, | |
| "grad_norm": 0.15749320226952399, | |
| "learning_rate": 1.9937748307413134e-05, | |
| "loss": 1.8324, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.13486513486513488, | |
| "grad_norm": 0.15932775031704177, | |
| "learning_rate": 1.9927653729167957e-05, | |
| "loss": 1.8403, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.13736263736263737, | |
| "grad_norm": 0.15539081264737326, | |
| "learning_rate": 1.9916803960982518e-05, | |
| "loss": 1.8352, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.13986013986013987, | |
| "grad_norm": 0.1616390225384804, | |
| "learning_rate": 1.9905199828191385e-05, | |
| "loss": 1.8703, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.14235764235764237, | |
| "grad_norm": 0.1608186724233932, | |
| "learning_rate": 1.9892842213513135e-05, | |
| "loss": 1.8503, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.14485514485514486, | |
| "grad_norm": 0.15963816595377592, | |
| "learning_rate": 1.98797320569832e-05, | |
| "loss": 1.8459, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.14735264735264736, | |
| "grad_norm": 0.1582839014078666, | |
| "learning_rate": 1.986587035588237e-05, | |
| "loss": 1.8553, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.14985014985014986, | |
| "grad_norm": 0.15947984158782932, | |
| "learning_rate": 1.985125816466092e-05, | |
| "loss": 1.8418, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15234765234765235, | |
| "grad_norm": 0.15926277299896913, | |
| "learning_rate": 1.9835896594858405e-05, | |
| "loss": 1.8398, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.15484515484515485, | |
| "grad_norm": 0.1619303456318674, | |
| "learning_rate": 1.9819786815019108e-05, | |
| "loss": 1.8453, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.15734265734265734, | |
| "grad_norm": 0.15663126843033132, | |
| "learning_rate": 1.9802930050603143e-05, | |
| "loss": 1.7968, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.15984015984015984, | |
| "grad_norm": 0.15428142491915428, | |
| "learning_rate": 1.9785327583893233e-05, | |
| "loss": 1.7914, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.16233766233766234, | |
| "grad_norm": 0.1535269165426423, | |
| "learning_rate": 1.9766980753897186e-05, | |
| "loss": 1.8398, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.16483516483516483, | |
| "grad_norm": 0.1566922978711067, | |
| "learning_rate": 1.974789095624601e-05, | |
| "loss": 1.8197, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.16733266733266733, | |
| "grad_norm": 0.16077008857885935, | |
| "learning_rate": 1.972805964308778e-05, | |
| "loss": 1.827, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.16983016983016982, | |
| "grad_norm": 0.1595092032589525, | |
| "learning_rate": 1.9707488322977137e-05, | |
| "loss": 1.8202, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.17232767232767232, | |
| "grad_norm": 0.16187621193128984, | |
| "learning_rate": 1.968617856076056e-05, | |
| "loss": 1.8462, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.17482517482517482, | |
| "grad_norm": 0.15740467422342347, | |
| "learning_rate": 1.9664131977457334e-05, | |
| "loss": 1.8285, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1773226773226773, | |
| "grad_norm": 0.15653103603511576, | |
| "learning_rate": 1.964135025013621e-05, | |
| "loss": 1.8524, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.1798201798201798, | |
| "grad_norm": 0.16162833026081047, | |
| "learning_rate": 1.9617835111787867e-05, | |
| "loss": 1.8384, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.1823176823176823, | |
| "grad_norm": 0.15473723241970383, | |
| "learning_rate": 1.9593588351193052e-05, | |
| "loss": 1.8139, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.1848151848151848, | |
| "grad_norm": 0.15885275250786435, | |
| "learning_rate": 1.9568611812786532e-05, | |
| "loss": 1.8218, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.18731268731268733, | |
| "grad_norm": 0.1568218347795679, | |
| "learning_rate": 1.9542907396516785e-05, | |
| "loss": 1.8099, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.18981018981018982, | |
| "grad_norm": 0.15705793055606954, | |
| "learning_rate": 1.9516477057701466e-05, | |
| "loss": 1.8264, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 0.15732378505813635, | |
| "learning_rate": 1.9489322806878656e-05, | |
| "loss": 1.7763, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.19480519480519481, | |
| "grad_norm": 0.16123492252157817, | |
| "learning_rate": 1.9461446709653957e-05, | |
| "loss": 1.8205, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.1973026973026973, | |
| "grad_norm": 0.15737920869870928, | |
| "learning_rate": 1.9432850886543326e-05, | |
| "loss": 1.8145, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.1998001998001998, | |
| "grad_norm": 0.15899572770709094, | |
| "learning_rate": 1.9403537512811787e-05, | |
| "loss": 1.8273, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2022977022977023, | |
| "grad_norm": 0.15657272543340842, | |
| "learning_rate": 1.9373508818307968e-05, | |
| "loss": 1.7994, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.2047952047952048, | |
| "grad_norm": 0.15774961567754203, | |
| "learning_rate": 1.934276708729445e-05, | |
| "loss": 1.8152, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.2072927072927073, | |
| "grad_norm": 0.1597456026863612, | |
| "learning_rate": 1.931131465827403e-05, | |
| "loss": 1.8067, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.2097902097902098, | |
| "grad_norm": 0.15874324914863305, | |
| "learning_rate": 1.927915392381183e-05, | |
| "loss": 1.8113, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.2122877122877123, | |
| "grad_norm": 0.15739095253831112, | |
| "learning_rate": 1.924628733035327e-05, | |
| "loss": 1.7572, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.21478521478521478, | |
| "grad_norm": 0.15745037871244488, | |
| "learning_rate": 1.921271737803802e-05, | |
| "loss": 1.7815, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.21728271728271728, | |
| "grad_norm": 0.1574617354946401, | |
| "learning_rate": 1.9178446620509762e-05, | |
| "loss": 1.8072, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.21978021978021978, | |
| "grad_norm": 0.16217729499687356, | |
| "learning_rate": 1.9143477664721958e-05, | |
| "loss": 1.8034, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.22227772227772227, | |
| "grad_norm": 0.16044737049383317, | |
| "learning_rate": 1.910781317073956e-05, | |
| "loss": 1.8369, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.22477522477522477, | |
| "grad_norm": 0.1573797424088386, | |
| "learning_rate": 1.9071455851536624e-05, | |
| "loss": 1.7681, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 0.15944418619813316, | |
| "learning_rate": 1.9034408472789966e-05, | |
| "loss": 1.8018, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.22977022977022976, | |
| "grad_norm": 0.1567957354310453, | |
| "learning_rate": 1.899667385266876e-05, | |
| "loss": 1.8262, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.23226773226773226, | |
| "grad_norm": 0.15732076579865928, | |
| "learning_rate": 1.8958254861620175e-05, | |
| "loss": 1.8065, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.23476523476523475, | |
| "grad_norm": 0.155336816664159, | |
| "learning_rate": 1.891915442215101e-05, | |
| "loss": 1.8053, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.23726273726273725, | |
| "grad_norm": 0.1597669648163907, | |
| "learning_rate": 1.88793755086054e-05, | |
| "loss": 1.8183, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.23976023976023977, | |
| "grad_norm": 0.15788615176295445, | |
| "learning_rate": 1.8838921146938523e-05, | |
| "loss": 1.8216, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.24225774225774227, | |
| "grad_norm": 0.15554518751652616, | |
| "learning_rate": 1.8797794414486464e-05, | |
| "loss": 1.8177, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.24475524475524477, | |
| "grad_norm": 0.15599244982971106, | |
| "learning_rate": 1.8755998439732092e-05, | |
| "loss": 1.7595, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.24725274725274726, | |
| "grad_norm": 0.1565896274442155, | |
| "learning_rate": 1.8713536402067084e-05, | |
| "loss": 1.7927, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.24975024975024976, | |
| "grad_norm": 0.15811536697664205, | |
| "learning_rate": 1.8670411531550078e-05, | |
| "loss": 1.774, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.25224775224775225, | |
| "grad_norm": 0.156281445500983, | |
| "learning_rate": 1.8626627108660967e-05, | |
| "loss": 1.7896, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.2547452547452547, | |
| "grad_norm": 0.16199506703702074, | |
| "learning_rate": 1.858218646405134e-05, | |
| "loss": 1.7957, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.25724275724275725, | |
| "grad_norm": 0.15409864113956373, | |
| "learning_rate": 1.853709297829113e-05, | |
| "loss": 1.7681, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 0.15595897376396248, | |
| "learning_rate": 1.8491350081611476e-05, | |
| "loss": 1.7821, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.26223776223776224, | |
| "grad_norm": 0.15981459835452744, | |
| "learning_rate": 1.8444961253643735e-05, | |
| "loss": 1.8, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.2647352647352647, | |
| "grad_norm": 0.1598175484696389, | |
| "learning_rate": 1.839793002315486e-05, | |
| "loss": 1.798, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.26723276723276723, | |
| "grad_norm": 0.15880648153398907, | |
| "learning_rate": 1.8350259967778904e-05, | |
| "loss": 1.8151, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.26973026973026976, | |
| "grad_norm": 0.16237848244779185, | |
| "learning_rate": 1.8301954713744913e-05, | |
| "loss": 1.8267, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.2722277722277722, | |
| "grad_norm": 0.15519746128863732, | |
| "learning_rate": 1.825301793560106e-05, | |
| "loss": 1.7678, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.27472527472527475, | |
| "grad_norm": 0.15889605012099542, | |
| "learning_rate": 1.8203453355935138e-05, | |
| "loss": 1.7552, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.2772227772227772, | |
| "grad_norm": 0.15715544258244915, | |
| "learning_rate": 1.8153264745091376e-05, | |
| "loss": 1.7906, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.27972027972027974, | |
| "grad_norm": 0.15630976676944236, | |
| "learning_rate": 1.8102455920883638e-05, | |
| "loss": 1.7698, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.2822177822177822, | |
| "grad_norm": 0.15690924431151737, | |
| "learning_rate": 1.8051030748304995e-05, | |
| "loss": 1.7676, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.28471528471528473, | |
| "grad_norm": 0.15783500931857442, | |
| "learning_rate": 1.7998993139233733e-05, | |
| "loss": 1.768, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.2872127872127872, | |
| "grad_norm": 0.1567537339747436, | |
| "learning_rate": 1.7946347052135765e-05, | |
| "loss": 1.766, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.2897102897102897, | |
| "grad_norm": 0.16054044236045276, | |
| "learning_rate": 1.7893096491763516e-05, | |
| "loss": 1.7679, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.2922077922077922, | |
| "grad_norm": 0.1559143042109544, | |
| "learning_rate": 1.783924550885129e-05, | |
| "loss": 1.7702, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.2947052947052947, | |
| "grad_norm": 0.1576160782660945, | |
| "learning_rate": 1.7784798199807128e-05, | |
| "loss": 1.7615, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.2972027972027972, | |
| "grad_norm": 0.15642650102699018, | |
| "learning_rate": 1.7729758706401198e-05, | |
| "loss": 1.7765, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.2997002997002997, | |
| "grad_norm": 0.1559306633293477, | |
| "learning_rate": 1.7674131215450737e-05, | |
| "loss": 1.771, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3021978021978022, | |
| "grad_norm": 0.15795527293903494, | |
| "learning_rate": 1.761791995850156e-05, | |
| "loss": 1.7941, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.3046953046953047, | |
| "grad_norm": 0.15804826082822157, | |
| "learning_rate": 1.756112921150616e-05, | |
| "loss": 1.7846, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.30719280719280717, | |
| "grad_norm": 0.15566746006494162, | |
| "learning_rate": 1.7503763294498457e-05, | |
| "loss": 1.7756, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.3096903096903097, | |
| "grad_norm": 0.1575042305833722, | |
| "learning_rate": 1.744582657126517e-05, | |
| "loss": 1.7905, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.31218781218781216, | |
| "grad_norm": 0.16032862889097663, | |
| "learning_rate": 1.7387323449013847e-05, | |
| "loss": 1.7862, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.3146853146853147, | |
| "grad_norm": 0.15809033799977093, | |
| "learning_rate": 1.732825837803765e-05, | |
| "loss": 1.7702, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.31718281718281716, | |
| "grad_norm": 0.15672979108179055, | |
| "learning_rate": 1.7268635851376785e-05, | |
| "loss": 1.76, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.3196803196803197, | |
| "grad_norm": 0.1554900829598635, | |
| "learning_rate": 1.7208460404476745e-05, | |
| "loss": 1.7411, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.3221778221778222, | |
| "grad_norm": 0.15739315261539163, | |
| "learning_rate": 1.7147736614843297e-05, | |
| "loss": 1.7954, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.3246753246753247, | |
| "grad_norm": 0.15852054226953874, | |
| "learning_rate": 1.7086469101694256e-05, | |
| "loss": 1.7627, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3271728271728272, | |
| "grad_norm": 0.1596482505865284, | |
| "learning_rate": 1.7024662525608138e-05, | |
| "loss": 1.751, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.32967032967032966, | |
| "grad_norm": 0.15871675517321407, | |
| "learning_rate": 1.6962321588169598e-05, | |
| "loss": 1.7434, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.3321678321678322, | |
| "grad_norm": 0.15766920664878184, | |
| "learning_rate": 1.6899451031611814e-05, | |
| "loss": 1.7639, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.33466533466533466, | |
| "grad_norm": 0.155044210346668, | |
| "learning_rate": 1.6836055638455722e-05, | |
| "loss": 1.7703, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.3371628371628372, | |
| "grad_norm": 0.1554119105318693, | |
| "learning_rate": 1.677214023114623e-05, | |
| "loss": 1.75, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.33966033966033965, | |
| "grad_norm": 0.15802877535499618, | |
| "learning_rate": 1.670770967168537e-05, | |
| "loss": 1.7771, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.3421578421578422, | |
| "grad_norm": 0.15628665794752747, | |
| "learning_rate": 1.664276886126246e-05, | |
| "loss": 1.7738, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.34465534465534464, | |
| "grad_norm": 0.15746939136953078, | |
| "learning_rate": 1.6577322739881255e-05, | |
| "loss": 1.76, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.34715284715284717, | |
| "grad_norm": 0.1563776125400448, | |
| "learning_rate": 1.6511376285984178e-05, | |
| "loss": 1.7815, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.34965034965034963, | |
| "grad_norm": 0.15612599803803687, | |
| "learning_rate": 1.6444934516073616e-05, | |
| "loss": 1.7325, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.35214785214785216, | |
| "grad_norm": 0.15539555825333878, | |
| "learning_rate": 1.6378002484330302e-05, | |
| "loss": 1.7267, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.3546453546453546, | |
| "grad_norm": 0.15742718718893856, | |
| "learning_rate": 1.631058528222886e-05, | |
| "loss": 1.7677, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 0.15722376923699383, | |
| "learning_rate": 1.6242688038150506e-05, | |
| "loss": 1.7593, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.3596403596403596, | |
| "grad_norm": 0.15692354412727902, | |
| "learning_rate": 1.617431591699291e-05, | |
| "loss": 1.7681, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.36213786213786214, | |
| "grad_norm": 0.15962277561047927, | |
| "learning_rate": 1.610547411977734e-05, | |
| "loss": 1.75, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.3646353646353646, | |
| "grad_norm": 0.15692940824376528, | |
| "learning_rate": 1.6036167883252988e-05, | |
| "loss": 1.7444, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.36713286713286714, | |
| "grad_norm": 0.15649627153834378, | |
| "learning_rate": 1.5966402479498642e-05, | |
| "loss": 1.7191, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.3696303696303696, | |
| "grad_norm": 0.1573682637472189, | |
| "learning_rate": 1.589618321552163e-05, | |
| "loss": 1.78, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.37212787212787213, | |
| "grad_norm": 0.15762121053782066, | |
| "learning_rate": 1.5825515432854125e-05, | |
| "loss": 1.7795, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.37462537462537465, | |
| "grad_norm": 0.15776485071561994, | |
| "learning_rate": 1.575440450714681e-05, | |
| "loss": 1.7656, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3771228771228771, | |
| "grad_norm": 0.15837437348496275, | |
| "learning_rate": 1.5682855847759965e-05, | |
| "loss": 1.7684, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.37962037962037964, | |
| "grad_norm": 0.16037425169330838, | |
| "learning_rate": 1.561087489735197e-05, | |
| "loss": 1.7368, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.3821178821178821, | |
| "grad_norm": 0.15513596949144706, | |
| "learning_rate": 1.55384671314653e-05, | |
| "loss": 1.7818, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 0.15507828031304494, | |
| "learning_rate": 1.5465638058109998e-05, | |
| "loss": 1.7796, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.3871128871128871, | |
| "grad_norm": 0.1554815328421005, | |
| "learning_rate": 1.5392393217344666e-05, | |
| "loss": 1.755, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.38961038961038963, | |
| "grad_norm": 0.15688136225119317, | |
| "learning_rate": 1.5318738180855073e-05, | |
| "loss": 1.7387, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.3921078921078921, | |
| "grad_norm": 0.1582625776474904, | |
| "learning_rate": 1.5244678551530294e-05, | |
| "loss": 1.7603, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.3946053946053946, | |
| "grad_norm": 0.15701117307543766, | |
| "learning_rate": 1.5170219963036501e-05, | |
| "loss": 1.7182, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.3971028971028971, | |
| "grad_norm": 0.15766319963371506, | |
| "learning_rate": 1.5095368079388433e-05, | |
| "loss": 1.7295, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.3996003996003996, | |
| "grad_norm": 0.1587394631264011, | |
| "learning_rate": 1.5020128594518521e-05, | |
| "loss": 1.7914, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.4020979020979021, | |
| "grad_norm": 0.15654000030100182, | |
| "learning_rate": 1.4944507231843756e-05, | |
| "loss": 1.7202, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.4045954045954046, | |
| "grad_norm": 0.15292942125756898, | |
| "learning_rate": 1.4868509743830332e-05, | |
| "loss": 1.7901, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.4070929070929071, | |
| "grad_norm": 0.15560456619792792, | |
| "learning_rate": 1.4792141911556027e-05, | |
| "loss": 1.7716, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.4095904095904096, | |
| "grad_norm": 0.15543386661085493, | |
| "learning_rate": 1.4715409544270462e-05, | |
| "loss": 1.7203, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.41208791208791207, | |
| "grad_norm": 0.15809116648034297, | |
| "learning_rate": 1.4638318478953202e-05, | |
| "loss": 1.7382, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.4145854145854146, | |
| "grad_norm": 0.1557252652086651, | |
| "learning_rate": 1.4560874579869716e-05, | |
| "loss": 1.7729, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.41708291708291706, | |
| "grad_norm": 0.1558675093074507, | |
| "learning_rate": 1.4483083738125312e-05, | |
| "loss": 1.7453, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.4195804195804196, | |
| "grad_norm": 0.15507446312985207, | |
| "learning_rate": 1.440495187121698e-05, | |
| "loss": 1.7678, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.42207792207792205, | |
| "grad_norm": 0.1553337193710422, | |
| "learning_rate": 1.4326484922583277e-05, | |
| "loss": 1.7709, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.4245754245754246, | |
| "grad_norm": 0.15761636621288116, | |
| "learning_rate": 1.4247688861152195e-05, | |
| "loss": 1.7315, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4270729270729271, | |
| "grad_norm": 0.15356881599814767, | |
| "learning_rate": 1.4168569680887115e-05, | |
| "loss": 1.6987, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.42957042957042957, | |
| "grad_norm": 0.15728107221945523, | |
| "learning_rate": 1.4089133400330851e-05, | |
| "loss": 1.741, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.4320679320679321, | |
| "grad_norm": 0.1548348784145128, | |
| "learning_rate": 1.4009386062147829e-05, | |
| "loss": 1.7323, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.43456543456543456, | |
| "grad_norm": 0.15572598457585934, | |
| "learning_rate": 1.3929333732664405e-05, | |
| "loss": 1.727, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.4370629370629371, | |
| "grad_norm": 0.15491152138136058, | |
| "learning_rate": 1.3848982501407433e-05, | |
| "loss": 1.7137, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 0.15288889483520682, | |
| "learning_rate": 1.376833848064102e-05, | |
| "loss": 1.7241, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.4420579420579421, | |
| "grad_norm": 0.15423204666405854, | |
| "learning_rate": 1.3687407804901562e-05, | |
| "loss": 1.7536, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.44455544455544455, | |
| "grad_norm": 0.15495163216179897, | |
| "learning_rate": 1.3606196630531125e-05, | |
| "loss": 1.7184, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.44705294705294707, | |
| "grad_norm": 0.15761280747235365, | |
| "learning_rate": 1.3524711135209106e-05, | |
| "loss": 1.7751, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.44955044955044954, | |
| "grad_norm": 0.15841771000224297, | |
| "learning_rate": 1.344295751748231e-05, | |
| "loss": 1.7514, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.45204795204795206, | |
| "grad_norm": 0.15428205907298273, | |
| "learning_rate": 1.3360941996293439e-05, | |
| "loss": 1.716, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.15303631590090105, | |
| "learning_rate": 1.3278670810508016e-05, | |
| "loss": 1.7083, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.45704295704295705, | |
| "grad_norm": 0.152891460359696, | |
| "learning_rate": 1.3196150218439791e-05, | |
| "loss": 1.711, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.4595404595404595, | |
| "grad_norm": 0.1541097644604054, | |
| "learning_rate": 1.3113386497374691e-05, | |
| "loss": 1.7352, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.46203796203796205, | |
| "grad_norm": 0.1581983359025658, | |
| "learning_rate": 1.303038594309329e-05, | |
| "loss": 1.7367, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.4645354645354645, | |
| "grad_norm": 0.15475095934873914, | |
| "learning_rate": 1.294715486939192e-05, | |
| "loss": 1.7169, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.46703296703296704, | |
| "grad_norm": 0.15844968557859115, | |
| "learning_rate": 1.2863699607602358e-05, | |
| "loss": 1.7208, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.4695304695304695, | |
| "grad_norm": 0.15639170445946177, | |
| "learning_rate": 1.2780026506110225e-05, | |
| "loss": 1.7242, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.47202797202797203, | |
| "grad_norm": 0.15698004903219, | |
| "learning_rate": 1.2696141929872064e-05, | |
| "loss": 1.754, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.4745254745254745, | |
| "grad_norm": 0.15510251460198132, | |
| "learning_rate": 1.2612052259931146e-05, | |
| "loss": 1.7437, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.477022977022977, | |
| "grad_norm": 0.1569119958304332, | |
| "learning_rate": 1.2527763892932098e-05, | |
| "loss": 1.7334, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.47952047952047955, | |
| "grad_norm": 0.15742453447805246, | |
| "learning_rate": 1.2443283240634295e-05, | |
| "loss": 1.7468, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.482017982017982, | |
| "grad_norm": 0.15752206416220757, | |
| "learning_rate": 1.2358616729424113e-05, | |
| "loss": 1.7285, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.48451548451548454, | |
| "grad_norm": 0.15404918669113854, | |
| "learning_rate": 1.2273770799826104e-05, | |
| "loss": 1.6984, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.487012987012987, | |
| "grad_norm": 0.15592357368342188, | |
| "learning_rate": 1.2188751906013054e-05, | |
| "loss": 1.7329, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.48951048951048953, | |
| "grad_norm": 0.156094008256334, | |
| "learning_rate": 1.2103566515315015e-05, | |
| "loss": 1.7513, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.492007992007992, | |
| "grad_norm": 0.1563990934117787, | |
| "learning_rate": 1.2018221107727348e-05, | |
| "loss": 1.7353, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.4945054945054945, | |
| "grad_norm": 0.1562707992028513, | |
| "learning_rate": 1.1932722175417796e-05, | |
| "loss": 1.7572, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.497002997002997, | |
| "grad_norm": 0.1535470008052979, | |
| "learning_rate": 1.1847076222232614e-05, | |
| "loss": 1.7176, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.4995004995004995, | |
| "grad_norm": 0.1582614864687129, | |
| "learning_rate": 1.1761289763201843e-05, | |
| "loss": 1.7784, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.501998001998002, | |
| "grad_norm": 0.155758931237908, | |
| "learning_rate": 1.1675369324043711e-05, | |
| "loss": 1.7144, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.5044955044955045, | |
| "grad_norm": 0.15984802366682394, | |
| "learning_rate": 1.1589321440668215e-05, | |
| "loss": 1.7144, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.506993006993007, | |
| "grad_norm": 0.1593119494177456, | |
| "learning_rate": 1.150315265867996e-05, | |
| "loss": 1.6995, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.5094905094905094, | |
| "grad_norm": 0.15572494789848285, | |
| "learning_rate": 1.1416869532880219e-05, | |
| "loss": 1.7289, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.511988011988012, | |
| "grad_norm": 0.15289377290260284, | |
| "learning_rate": 1.1330478626768322e-05, | |
| "loss": 1.7166, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.5144855144855145, | |
| "grad_norm": 0.15398889595667828, | |
| "learning_rate": 1.1243986512042377e-05, | |
| "loss": 1.7163, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.516983016983017, | |
| "grad_norm": 0.15490392246805634, | |
| "learning_rate": 1.1157399768099366e-05, | |
| "loss": 1.7134, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 0.15500679881154095, | |
| "learning_rate": 1.1070724981534647e-05, | |
| "loss": 1.7396, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.521978021978022, | |
| "grad_norm": 0.1560235269544757, | |
| "learning_rate": 1.0983968745640923e-05, | |
| "loss": 1.6969, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.5244755244755245, | |
| "grad_norm": 0.15453453742882894, | |
| "learning_rate": 1.0897137659906688e-05, | |
| "loss": 1.7426, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.526973026973027, | |
| "grad_norm": 0.15599081676361193, | |
| "learning_rate": 1.0810238329514225e-05, | |
| "loss": 1.7457, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.5294705294705294, | |
| "grad_norm": 0.15738103416797297, | |
| "learning_rate": 1.072327736483713e-05, | |
| "loss": 1.7159, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.531968031968032, | |
| "grad_norm": 0.15854287836067726, | |
| "learning_rate": 1.0636261380937483e-05, | |
| "loss": 1.7684, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.5344655344655345, | |
| "grad_norm": 0.15666913409437308, | |
| "learning_rate": 1.0549196997062636e-05, | |
| "loss": 1.7533, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.5369630369630369, | |
| "grad_norm": 0.15513752052678667, | |
| "learning_rate": 1.0462090836141705e-05, | |
| "loss": 1.7485, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.5394605394605395, | |
| "grad_norm": 0.15606650567355096, | |
| "learning_rate": 1.0374949524281741e-05, | |
| "loss": 1.7112, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.541958041958042, | |
| "grad_norm": 0.15696280237552776, | |
| "learning_rate": 1.0287779690263718e-05, | |
| "loss": 1.7299, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.5444555444555444, | |
| "grad_norm": 0.15466947191164923, | |
| "learning_rate": 1.020058796503826e-05, | |
| "loss": 1.7416, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.5469530469530469, | |
| "grad_norm": 0.15659516724914946, | |
| "learning_rate": 1.0113380981221251e-05, | |
| "loss": 1.7309, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.5494505494505495, | |
| "grad_norm": 0.15698307016673457, | |
| "learning_rate": 1.0026165372589278e-05, | |
| "loss": 1.7416, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.551948051948052, | |
| "grad_norm": 0.15747483213576682, | |
| "learning_rate": 9.938947773575014e-06, | |
| "loss": 1.7354, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.5544455544455544, | |
| "grad_norm": 0.1548555078024705, | |
| "learning_rate": 9.85173481876254e-06, | |
| "loss": 1.7285, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.5569430569430569, | |
| "grad_norm": 0.1576329932512269, | |
| "learning_rate": 9.76453314238266e-06, | |
| "loss": 1.7295, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.5594405594405595, | |
| "grad_norm": 0.15518997199188608, | |
| "learning_rate": 9.677349377808223e-06, | |
| "loss": 1.7252, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.561938061938062, | |
| "grad_norm": 0.15573012190773938, | |
| "learning_rate": 9.59019015704955e-06, | |
| "loss": 1.7257, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.5644355644355644, | |
| "grad_norm": 0.15100601160295765, | |
| "learning_rate": 9.50306211024993e-06, | |
| "loss": 1.6836, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.5669330669330669, | |
| "grad_norm": 0.15501908738813838, | |
| "learning_rate": 9.415971865181262e-06, | |
| "loss": 1.7429, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.5694305694305695, | |
| "grad_norm": 0.15812904061992633, | |
| "learning_rate": 9.328926046739899e-06, | |
| "loss": 1.7084, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.5719280719280719, | |
| "grad_norm": 0.15627757158949415, | |
| "learning_rate": 9.241931276442692e-06, | |
| "loss": 1.7214, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.5744255744255744, | |
| "grad_norm": 0.1558930669628705, | |
| "learning_rate": 9.154994171923285e-06, | |
| "loss": 1.7109, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 0.15441900101502826, | |
| "learning_rate": 9.068121346428735e-06, | |
| "loss": 1.7376, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.5794205794205795, | |
| "grad_norm": 0.15623145805295774, | |
| "learning_rate": 8.981319408316435e-06, | |
| "loss": 1.736, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.5819180819180819, | |
| "grad_norm": 0.15421994986436063, | |
| "learning_rate": 8.894594960551417e-06, | |
| "loss": 1.7484, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.5844155844155844, | |
| "grad_norm": 0.15562604285522325, | |
| "learning_rate": 8.807954600204079e-06, | |
| "loss": 1.7608, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.586913086913087, | |
| "grad_norm": 0.15592693727619433, | |
| "learning_rate": 8.721404917948343e-06, | |
| "loss": 1.7358, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.5894105894105894, | |
| "grad_norm": 0.15213420323940668, | |
| "learning_rate": 8.634952497560311e-06, | |
| "loss": 1.6824, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.5919080919080919, | |
| "grad_norm": 0.15353479909518586, | |
| "learning_rate": 8.548603915417445e-06, | |
| "loss": 1.7362, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.5944055944055944, | |
| "grad_norm": 0.1568536405873683, | |
| "learning_rate": 8.462365739998293e-06, | |
| "loss": 1.7144, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.596903096903097, | |
| "grad_norm": 0.15792171997932242, | |
| "learning_rate": 8.37624453138284e-06, | |
| "loss": 1.7364, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.5994005994005994, | |
| "grad_norm": 0.1559386534693386, | |
| "learning_rate": 8.29024684075349e-06, | |
| "loss": 1.7593, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6018981018981019, | |
| "grad_norm": 0.15715611634818757, | |
| "learning_rate": 8.204379209896712e-06, | |
| "loss": 1.7032, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.6043956043956044, | |
| "grad_norm": 0.15372344898616952, | |
| "learning_rate": 8.118648170705418e-06, | |
| "loss": 1.6978, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.6068931068931069, | |
| "grad_norm": 0.15810145378733176, | |
| "learning_rate": 8.033060244682079e-06, | |
| "loss": 1.7396, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.6093906093906094, | |
| "grad_norm": 0.1557299319735277, | |
| "learning_rate": 7.947621942442651e-06, | |
| "loss": 1.7232, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.6118881118881119, | |
| "grad_norm": 0.1557147874512252, | |
| "learning_rate": 7.86233976322131e-06, | |
| "loss": 1.71, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.6143856143856143, | |
| "grad_norm": 0.1554308477187568, | |
| "learning_rate": 7.777220194376047e-06, | |
| "loss": 1.7177, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.6168831168831169, | |
| "grad_norm": 0.1564865748636126, | |
| "learning_rate": 7.692269710895204e-06, | |
| "loss": 1.705, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.6193806193806194, | |
| "grad_norm": 0.1540720670994077, | |
| "learning_rate": 7.6074947749049085e-06, | |
| "loss": 1.7039, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.6218781218781219, | |
| "grad_norm": 0.15756506692256836, | |
| "learning_rate": 7.522901835177506e-06, | |
| "loss": 1.7217, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.6243756243756243, | |
| "grad_norm": 0.15371879475088404, | |
| "learning_rate": 7.438497326641012e-06, | |
| "loss": 1.6895, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.6268731268731269, | |
| "grad_norm": 0.15945775556289293, | |
| "learning_rate": 7.354287669889606e-06, | |
| "loss": 1.7366, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.6293706293706294, | |
| "grad_norm": 0.15778707821642424, | |
| "learning_rate": 7.270279270695224e-06, | |
| "loss": 1.7303, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.6318681318681318, | |
| "grad_norm": 0.1586505017667703, | |
| "learning_rate": 7.186478519520279e-06, | |
| "loss": 1.7147, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.6343656343656343, | |
| "grad_norm": 0.15789741519311937, | |
| "learning_rate": 7.10289179103153e-06, | |
| "loss": 1.7146, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.6368631368631369, | |
| "grad_norm": 0.15184374761336888, | |
| "learning_rate": 7.019525443615181e-06, | |
| "loss": 1.7195, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.6393606393606394, | |
| "grad_norm": 0.15637777552677476, | |
| "learning_rate": 6.936385818893197e-06, | |
| "loss": 1.7471, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.6418581418581418, | |
| "grad_norm": 0.1567686671030996, | |
| "learning_rate": 6.853479241240895e-06, | |
| "loss": 1.7436, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.6443556443556444, | |
| "grad_norm": 0.15591409064699058, | |
| "learning_rate": 6.770812017305862e-06, | |
| "loss": 1.7252, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.6468531468531469, | |
| "grad_norm": 0.15804342302479574, | |
| "learning_rate": 6.688390435528209e-06, | |
| "loss": 1.7334, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.6493506493506493, | |
| "grad_norm": 0.15436002266775298, | |
| "learning_rate": 6.606220765662209e-06, | |
| "loss": 1.7165, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6518481518481518, | |
| "grad_norm": 0.15531296312132536, | |
| "learning_rate": 6.524309258299368e-06, | |
| "loss": 1.7605, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.6543456543456544, | |
| "grad_norm": 0.1565211383258821, | |
| "learning_rate": 6.4426621443929505e-06, | |
| "loss": 1.7061, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.6568431568431569, | |
| "grad_norm": 0.1582362713382269, | |
| "learning_rate": 6.361285634783976e-06, | |
| "loss": 1.7196, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.6593406593406593, | |
| "grad_norm": 0.15521707003590374, | |
| "learning_rate": 6.280185919728784e-06, | |
| "loss": 1.6963, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.6618381618381618, | |
| "grad_norm": 0.15705101318113973, | |
| "learning_rate": 6.199369168428143e-06, | |
| "loss": 1.742, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.6643356643356644, | |
| "grad_norm": 0.15356334771300495, | |
| "learning_rate": 6.11884152855795e-06, | |
| "loss": 1.7011, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.6668331668331668, | |
| "grad_norm": 0.15700312151436902, | |
| "learning_rate": 6.0386091258015965e-06, | |
| "loss": 1.6928, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.6693306693306693, | |
| "grad_norm": 0.15784510931828966, | |
| "learning_rate": 5.95867806338398e-06, | |
| "loss": 1.7009, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.6718281718281718, | |
| "grad_norm": 0.15746608991343575, | |
| "learning_rate": 5.879054421607248e-06, | |
| "loss": 1.7397, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.6743256743256744, | |
| "grad_norm": 0.15620423042692408, | |
| "learning_rate": 5.79974425738826e-06, | |
| "loss": 1.7045, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6768231768231768, | |
| "grad_norm": 0.15370013592929113, | |
| "learning_rate": 5.720753603797855e-06, | |
| "loss": 1.7015, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.6793206793206793, | |
| "grad_norm": 0.15590449648570684, | |
| "learning_rate": 5.6420884696019085e-06, | |
| "loss": 1.6937, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.6818181818181818, | |
| "grad_norm": 0.15510936819450175, | |
| "learning_rate": 5.563754838804252e-06, | |
| "loss": 1.7019, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.6843156843156843, | |
| "grad_norm": 0.1527676787399584, | |
| "learning_rate": 5.485758670191486e-06, | |
| "loss": 1.7051, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.6868131868131868, | |
| "grad_norm": 0.15546653572707683, | |
| "learning_rate": 5.408105896879684e-06, | |
| "loss": 1.7296, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.6893106893106893, | |
| "grad_norm": 0.15309923322143176, | |
| "learning_rate": 5.330802425863064e-06, | |
| "loss": 1.6989, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.6918081918081919, | |
| "grad_norm": 0.15308524124271006, | |
| "learning_rate": 5.2538541375646675e-06, | |
| "loss": 1.6826, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.6943056943056943, | |
| "grad_norm": 0.1538371045270346, | |
| "learning_rate": 5.177266885389016e-06, | |
| "loss": 1.6983, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.6968031968031968, | |
| "grad_norm": 0.15413826922713267, | |
| "learning_rate": 5.101046495276852e-06, | |
| "loss": 1.724, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.6993006993006993, | |
| "grad_norm": 0.15297221612329867, | |
| "learning_rate": 5.025198765261981e-06, | |
| "loss": 1.7201, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.7017982017982018, | |
| "grad_norm": 0.15512908248946458, | |
| "learning_rate": 4.949729465030193e-06, | |
| "loss": 1.6795, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.7042957042957043, | |
| "grad_norm": 0.15505906851804813, | |
| "learning_rate": 4.874644335480383e-06, | |
| "loss": 1.707, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.7067932067932068, | |
| "grad_norm": 0.15397133300096347, | |
| "learning_rate": 4.799949088287849e-06, | |
| "loss": 1.7008, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.7092907092907093, | |
| "grad_norm": 0.15813016475329747, | |
| "learning_rate": 4.725649405469786e-06, | |
| "loss": 1.7325, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.7117882117882118, | |
| "grad_norm": 0.15446637709842673, | |
| "learning_rate": 4.65175093895308e-06, | |
| "loss": 1.7215, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.1561588030182068, | |
| "learning_rate": 4.57825931014437e-06, | |
| "loss": 1.7184, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.7167832167832168, | |
| "grad_norm": 0.15772322144743187, | |
| "learning_rate": 4.50518010950241e-06, | |
| "loss": 1.7166, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.7192807192807192, | |
| "grad_norm": 0.15727583874213139, | |
| "learning_rate": 4.432518896112831e-06, | |
| "loss": 1.7034, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.7217782217782218, | |
| "grad_norm": 0.153411598788086, | |
| "learning_rate": 4.360281197265249e-06, | |
| "loss": 1.695, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.7242757242757243, | |
| "grad_norm": 0.15655819818705863, | |
| "learning_rate": 4.2884725080328245e-06, | |
| "loss": 1.7411, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.7267732267732268, | |
| "grad_norm": 0.15649221553246048, | |
| "learning_rate": 4.217098290854234e-06, | |
| "loss": 1.6852, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.7292707292707292, | |
| "grad_norm": 0.15608752112425878, | |
| "learning_rate": 4.146163975118154e-06, | |
| "loss": 1.7158, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.7317682317682318, | |
| "grad_norm": 0.156378012901712, | |
| "learning_rate": 4.0756749567502704e-06, | |
| "loss": 1.7141, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.7342657342657343, | |
| "grad_norm": 0.15573008458523765, | |
| "learning_rate": 4.005636597802785e-06, | |
| "loss": 1.7316, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.7367632367632367, | |
| "grad_norm": 0.15624579822166534, | |
| "learning_rate": 3.936054226046539e-06, | |
| "loss": 1.7275, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.7392607392607392, | |
| "grad_norm": 0.15708652587903585, | |
| "learning_rate": 3.866933134565747e-06, | |
| "loss": 1.7146, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.7417582417582418, | |
| "grad_norm": 0.15685542138951347, | |
| "learning_rate": 3.7982785813553335e-06, | |
| "loss": 1.7009, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.7442557442557443, | |
| "grad_norm": 0.15672884263951484, | |
| "learning_rate": 3.730095788920969e-06, | |
| "loss": 1.7273, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.7467532467532467, | |
| "grad_norm": 0.15717150554726544, | |
| "learning_rate": 3.662389943881811e-06, | |
| "loss": 1.7223, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.7492507492507493, | |
| "grad_norm": 0.153594301470774, | |
| "learning_rate": 3.5951661965759376e-06, | |
| "loss": 1.7232, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7517482517482518, | |
| "grad_norm": 0.15489817985281926, | |
| "learning_rate": 3.5284296606685788e-06, | |
| "loss": 1.7198, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.7542457542457542, | |
| "grad_norm": 0.15650041684511018, | |
| "learning_rate": 3.4621854127631293e-06, | |
| "loss": 1.7427, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.7567432567432567, | |
| "grad_norm": 0.15414035664901124, | |
| "learning_rate": 3.3964384920149574e-06, | |
| "loss": 1.6846, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.7592407592407593, | |
| "grad_norm": 0.15583094131363653, | |
| "learning_rate": 3.331193899748091e-06, | |
| "loss": 1.726, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.7617382617382618, | |
| "grad_norm": 0.1554155623994627, | |
| "learning_rate": 3.2664565990747733e-06, | |
| "loss": 1.7206, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.7642357642357642, | |
| "grad_norm": 0.15305845088804462, | |
| "learning_rate": 3.202231514517913e-06, | |
| "loss": 1.7028, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.7667332667332667, | |
| "grad_norm": 0.15291334769441534, | |
| "learning_rate": 3.1385235316364805e-06, | |
| "loss": 1.7322, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.15661260187424764, | |
| "learning_rate": 3.0753374966538807e-06, | |
| "loss": 1.6848, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.7717282717282717, | |
| "grad_norm": 0.15809358800271614, | |
| "learning_rate": 3.012678216089281e-06, | |
| "loss": 1.6997, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.7742257742257742, | |
| "grad_norm": 0.155978034855165, | |
| "learning_rate": 2.9505504563920005e-06, | |
| "loss": 1.7356, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.7767232767232767, | |
| "grad_norm": 0.15604151355576693, | |
| "learning_rate": 2.888958943578919e-06, | |
| "loss": 1.7165, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.7792207792207793, | |
| "grad_norm": 0.1550171550409355, | |
| "learning_rate": 2.827908362874986e-06, | |
| "loss": 1.7025, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.7817182817182817, | |
| "grad_norm": 0.15527890651905346, | |
| "learning_rate": 2.7674033583568004e-06, | |
| "loss": 1.687, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.7842157842157842, | |
| "grad_norm": 0.15537639424177968, | |
| "learning_rate": 2.7074485325993482e-06, | |
| "loss": 1.7126, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.7867132867132867, | |
| "grad_norm": 0.15244961389707662, | |
| "learning_rate": 2.648048446325894e-06, | |
| "loss": 1.6943, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.7892107892107892, | |
| "grad_norm": 0.15407223657879413, | |
| "learning_rate": 2.5892076180610372e-06, | |
| "loss": 1.7077, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.7917082917082917, | |
| "grad_norm": 0.15395383095089893, | |
| "learning_rate": 2.5309305237869953e-06, | |
| "loss": 1.7428, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.7942057942057942, | |
| "grad_norm": 0.15693221036515126, | |
| "learning_rate": 2.473221596603127e-06, | |
| "loss": 1.7003, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.7967032967032966, | |
| "grad_norm": 0.15202864145333894, | |
| "learning_rate": 2.416085226388699e-06, | |
| "loss": 1.7062, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.7992007992007992, | |
| "grad_norm": 0.15438777267790824, | |
| "learning_rate": 2.3595257594689504e-06, | |
| "loss": 1.716, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.8016983016983017, | |
| "grad_norm": 0.15408101244601666, | |
| "learning_rate": 2.303547498284483e-06, | |
| "loss": 1.74, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.8041958041958042, | |
| "grad_norm": 0.1529673037596131, | |
| "learning_rate": 2.2481547010639648e-06, | |
| "loss": 1.724, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.8066933066933067, | |
| "grad_norm": 0.15429371566399036, | |
| "learning_rate": 2.1933515815002115e-06, | |
| "loss": 1.7058, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.8091908091908092, | |
| "grad_norm": 0.1553802340727305, | |
| "learning_rate": 2.1391423084296627e-06, | |
| "loss": 1.7044, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.8116883116883117, | |
| "grad_norm": 0.15552250374029558, | |
| "learning_rate": 2.08553100551525e-06, | |
| "loss": 1.7294, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.8141858141858141, | |
| "grad_norm": 0.15556388073981073, | |
| "learning_rate": 2.0325217509327145e-06, | |
| "loss": 1.6825, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.8166833166833167, | |
| "grad_norm": 0.1534237780794405, | |
| "learning_rate": 1.980118577060397e-06, | |
| "loss": 1.7258, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.8191808191808192, | |
| "grad_norm": 0.1556601065527979, | |
| "learning_rate": 1.9283254701724742e-06, | |
| "loss": 1.6938, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.8216783216783217, | |
| "grad_norm": 0.156089780593886, | |
| "learning_rate": 1.8771463701357428e-06, | |
| "loss": 1.7357, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.8241758241758241, | |
| "grad_norm": 0.15554888194693464, | |
| "learning_rate": 1.8265851701099146e-06, | |
| "loss": 1.7063, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.8266733266733267, | |
| "grad_norm": 0.15466801254433934, | |
| "learning_rate": 1.7766457162514594e-06, | |
| "loss": 1.7435, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.8291708291708292, | |
| "grad_norm": 0.15476788949201128, | |
| "learning_rate": 1.7273318074210298e-06, | |
| "loss": 1.7059, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.8316683316683317, | |
| "grad_norm": 0.15219152100759303, | |
| "learning_rate": 1.6786471948944994e-06, | |
| "loss": 1.6964, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.8341658341658341, | |
| "grad_norm": 0.1548313560211368, | |
| "learning_rate": 1.630595582077591e-06, | |
| "loss": 1.7, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.8366633366633367, | |
| "grad_norm": 0.15585812651840628, | |
| "learning_rate": 1.5831806242241632e-06, | |
| "loss": 1.7028, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.8391608391608392, | |
| "grad_norm": 0.15443911839682758, | |
| "learning_rate": 1.5364059281581566e-06, | |
| "loss": 1.7176, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.8416583416583416, | |
| "grad_norm": 0.1605017036197551, | |
| "learning_rate": 1.4902750519992392e-06, | |
| "loss": 1.7156, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.8441558441558441, | |
| "grad_norm": 0.1538258207387918, | |
| "learning_rate": 1.4447915048921224e-06, | |
| "loss": 1.6744, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.8466533466533467, | |
| "grad_norm": 0.15406565385641532, | |
| "learning_rate": 1.3999587467396336e-06, | |
| "loss": 1.6946, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.8491508491508492, | |
| "grad_norm": 0.1536094454245134, | |
| "learning_rate": 1.3557801879395283e-06, | |
| "loss": 1.7148, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8516483516483516, | |
| "grad_norm": 0.15544099947612952, | |
| "learning_rate": 1.3122591891250492e-06, | |
| "loss": 1.6875, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.8541458541458542, | |
| "grad_norm": 0.16188709049635025, | |
| "learning_rate": 1.2693990609092965e-06, | |
| "loss": 1.7387, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.8566433566433567, | |
| "grad_norm": 0.15363848054893653, | |
| "learning_rate": 1.227203063633393e-06, | |
| "loss": 1.7277, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.8591408591408591, | |
| "grad_norm": 0.15554467350943088, | |
| "learning_rate": 1.185674407118461e-06, | |
| "loss": 1.6892, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.8616383616383616, | |
| "grad_norm": 0.15618845824953714, | |
| "learning_rate": 1.1448162504214621e-06, | |
| "loss": 1.7413, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.8641358641358642, | |
| "grad_norm": 0.15459131494726566, | |
| "learning_rate": 1.1046317015948904e-06, | |
| "loss": 1.7133, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.8666333666333667, | |
| "grad_norm": 0.1552140715983614, | |
| "learning_rate": 1.0651238174503408e-06, | |
| "loss": 1.7147, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.8691308691308691, | |
| "grad_norm": 0.15520848465047085, | |
| "learning_rate": 1.0262956033259775e-06, | |
| "loss": 1.7367, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.8716283716283716, | |
| "grad_norm": 0.15402498238996434, | |
| "learning_rate": 9.881500128579314e-07, | |
| "loss": 1.6949, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.8741258741258742, | |
| "grad_norm": 0.15820953048710004, | |
| "learning_rate": 9.506899477556042e-07, | |
| "loss": 1.6936, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.8766233766233766, | |
| "grad_norm": 0.15475714836078286, | |
| "learning_rate": 9.139182575809446e-07, | |
| "loss": 1.7216, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.15320851876078712, | |
| "learning_rate": 8.778377395316906e-07, | |
| "loss": 1.6875, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.8816183816183816, | |
| "grad_norm": 0.1559111566296162, | |
| "learning_rate": 8.424511382285749e-07, | |
| "loss": 1.7169, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.8841158841158842, | |
| "grad_norm": 0.15776692471495612, | |
| "learning_rate": 8.077611455065493e-07, | |
| "loss": 1.7276, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.8866133866133866, | |
| "grad_norm": 0.15457624124158628, | |
| "learning_rate": 7.737704002100255e-07, | |
| "loss": 1.6813, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.8891108891108891, | |
| "grad_norm": 0.1542971837033228, | |
| "learning_rate": 7.404814879921296e-07, | |
| "loss": 1.7033, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.8916083916083916, | |
| "grad_norm": 0.15193831756852316, | |
| "learning_rate": 7.078969411180159e-07, | |
| "loss": 1.6647, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.8941058941058941, | |
| "grad_norm": 0.15247095933972296, | |
| "learning_rate": 6.760192382722485e-07, | |
| "loss": 1.7022, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.8966033966033966, | |
| "grad_norm": 0.15342741598547197, | |
| "learning_rate": 6.44850804370234e-07, | |
| "loss": 1.7011, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.8991008991008991, | |
| "grad_norm": 0.15441584662597227, | |
| "learning_rate": 6.143940103737689e-07, | |
| "loss": 1.7223, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.9015984015984015, | |
| "grad_norm": 0.15544328956589934, | |
| "learning_rate": 5.846511731106864e-07, | |
| "loss": 1.7176, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.9040959040959041, | |
| "grad_norm": 0.15335771344533347, | |
| "learning_rate": 5.556245550986051e-07, | |
| "loss": 1.7273, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.9065934065934066, | |
| "grad_norm": 0.15533326348626406, | |
| "learning_rate": 5.273163643728296e-07, | |
| "loss": 1.6976, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.1516521943992359, | |
| "learning_rate": 4.997287543183815e-07, | |
| "loss": 1.6956, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.9115884115884116, | |
| "grad_norm": 0.15363897561993292, | |
| "learning_rate": 4.728638235062022e-07, | |
| "loss": 1.6807, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.9140859140859141, | |
| "grad_norm": 0.15398450709114828, | |
| "learning_rate": 4.4672361553350307e-07, | |
| "loss": 1.7005, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.9165834165834166, | |
| "grad_norm": 0.15239411554319313, | |
| "learning_rate": 4.213101188683155e-07, | |
| "loss": 1.6957, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.919080919080919, | |
| "grad_norm": 0.15568622874699023, | |
| "learning_rate": 3.9662526669823954e-07, | |
| "loss": 1.7054, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.9215784215784216, | |
| "grad_norm": 0.15485180274139432, | |
| "learning_rate": 3.7267093678336807e-07, | |
| "loss": 1.7272, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.9240759240759241, | |
| "grad_norm": 0.15780700441318615, | |
| "learning_rate": 3.4944895131346355e-07, | |
| "loss": 1.6873, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.9265734265734266, | |
| "grad_norm": 0.15379026482093777, | |
| "learning_rate": 3.2696107676933874e-07, | |
| "loss": 1.6611, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.929070929070929, | |
| "grad_norm": 0.1548358187558438, | |
| "learning_rate": 3.052090237884808e-07, | |
| "loss": 1.7334, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.9315684315684316, | |
| "grad_norm": 0.15404474230711981, | |
| "learning_rate": 2.841944470349256e-07, | |
| "loss": 1.7395, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.9340659340659341, | |
| "grad_norm": 0.15245851102095165, | |
| "learning_rate": 2.6391894507339036e-07, | |
| "loss": 1.6845, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.9365634365634365, | |
| "grad_norm": 0.15457664788214828, | |
| "learning_rate": 2.443840602476666e-07, | |
| "loss": 1.7197, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.939060939060939, | |
| "grad_norm": 0.15619921990085028, | |
| "learning_rate": 2.2559127856330187e-07, | |
| "loss": 1.7138, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.9415584415584416, | |
| "grad_norm": 0.15465495381686764, | |
| "learning_rate": 2.075420295745567e-07, | |
| "loss": 1.7034, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.9440559440559441, | |
| "grad_norm": 0.15413725828913954, | |
| "learning_rate": 1.902376862756583e-07, | |
| "loss": 1.7132, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.9465534465534465, | |
| "grad_norm": 0.1553239253397568, | |
| "learning_rate": 1.7367956499635963e-07, | |
| "loss": 1.7267, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.949050949050949, | |
| "grad_norm": 0.15270107237353941, | |
| "learning_rate": 1.578689253018062e-07, | |
| "loss": 1.7124, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.9515484515484516, | |
| "grad_norm": 0.15613663746353207, | |
| "learning_rate": 1.4280696989672383e-07, | |
| "loss": 1.6997, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.954045954045954, | |
| "grad_norm": 0.15490386612035345, | |
| "learning_rate": 1.2849484453392624e-07, | |
| "loss": 1.7035, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.9565434565434565, | |
| "grad_norm": 0.15328450998495585, | |
| "learning_rate": 1.1493363792716262e-07, | |
| "loss": 1.7039, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 0.9590409590409591, | |
| "grad_norm": 0.15356789205414245, | |
| "learning_rate": 1.0212438166829375e-07, | |
| "loss": 1.7214, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.9615384615384616, | |
| "grad_norm": 0.15318911423373824, | |
| "learning_rate": 9.006805014882825e-08, | |
| "loss": 1.6622, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.964035964035964, | |
| "grad_norm": 0.15361081252860728, | |
| "learning_rate": 7.876556048579287e-08, | |
| "loss": 1.6955, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.9665334665334665, | |
| "grad_norm": 0.15466222218440107, | |
| "learning_rate": 6.82177724519717e-08, | |
| "loss": 1.6808, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.9690309690309691, | |
| "grad_norm": 0.1551486540401332, | |
| "learning_rate": 5.8425488410505107e-08, | |
| "loss": 1.7217, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.9715284715284715, | |
| "grad_norm": 0.15270102301709607, | |
| "learning_rate": 4.9389453253850806e-08, | |
| "loss": 1.674, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 0.974025974025974, | |
| "grad_norm": 0.15535594613189269, | |
| "learning_rate": 4.111035434712585e-08, | |
| "loss": 1.7045, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.9765234765234765, | |
| "grad_norm": 0.15346069144811603, | |
| "learning_rate": 3.35888214758151e-08, | |
| "loss": 1.714, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 0.9790209790209791, | |
| "grad_norm": 0.1535377723271678, | |
| "learning_rate": 2.682542679786071e-08, | |
| "loss": 1.7105, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.9815184815184815, | |
| "grad_norm": 0.153091026718829, | |
| "learning_rate": 2.0820684800147983e-08, | |
| "loss": 1.6672, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 0.984015984015984, | |
| "grad_norm": 0.15163180759905762, | |
| "learning_rate": 1.557505225936118e-08, | |
| "loss": 1.7388, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.9865134865134865, | |
| "grad_norm": 0.15480094009362919, | |
| "learning_rate": 1.1088928207236837e-08, | |
| "loss": 1.6973, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.989010989010989, | |
| "grad_norm": 0.15658829069949848, | |
| "learning_rate": 7.362653900215844e-09, | |
| "loss": 1.7533, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.9915084915084915, | |
| "grad_norm": 0.15216671113258667, | |
| "learning_rate": 4.396512793475305e-09, | |
| "loss": 1.6998, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 0.994005994005994, | |
| "grad_norm": 0.15475133859641596, | |
| "learning_rate": 2.1907305193757944e-09, | |
| "loss": 1.7031, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.9965034965034965, | |
| "grad_norm": 0.15399579527373794, | |
| "learning_rate": 7.454748702895309e-10, | |
| "loss": 1.6964, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 0.999000999000999, | |
| "grad_norm": 0.157143946266898, | |
| "learning_rate": 6.085578584280604e-11, | |
| "loss": 1.7337, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.7156749963760376, | |
| "eval_runtime": 110.9741, | |
| "eval_samples_per_second": 127.76, | |
| "eval_steps_per_second": 2.0, | |
| "step": 2002 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 2002, | |
| "total_flos": 145100101386240.0, | |
| "train_loss": 1.7762367073948924, | |
| "train_runtime": 4136.0894, | |
| "train_samples_per_second": 30.978, | |
| "train_steps_per_second": 0.484 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2002, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 145100101386240.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |