| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.996777029006739, | |
| "eval_steps": 500, | |
| "global_step": 1278, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023439789041898623, | |
| "grad_norm": 9.967006175549518, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6132, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.046879578083797245, | |
| "grad_norm": 1.708901732081446, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5268, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07031936712569586, | |
| "grad_norm": 1.6601249126276376, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4939, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09375915616759449, | |
| "grad_norm": 0.9058674995172575, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4729, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11719894520949312, | |
| "grad_norm": 1.1831753366659354, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4606, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14063873425139173, | |
| "grad_norm": 0.6857017193079774, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4448, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16407852329329037, | |
| "grad_norm": 0.665824933523209, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4416, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18751831233518898, | |
| "grad_norm": 1.5098116393031806, | |
| "learning_rate": 5e-06, | |
| "loss": 0.436, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2109581013770876, | |
| "grad_norm": 0.8814351421187862, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4249, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23439789041898623, | |
| "grad_norm": 0.5818056460875761, | |
| "learning_rate": 5e-06, | |
| "loss": 0.416, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25783767946088487, | |
| "grad_norm": 0.6332178617430071, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4143, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28127746850278346, | |
| "grad_norm": 0.6385133089285979, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4142, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3047172575446821, | |
| "grad_norm": 0.5190122301041274, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4054, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.32815704658658074, | |
| "grad_norm": 0.72677604074983, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4061, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3515968356284793, | |
| "grad_norm": 0.5862867262610982, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4002, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.37503662467037796, | |
| "grad_norm": 0.4943669370299919, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4078, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3984764137122766, | |
| "grad_norm": 0.617733036177013, | |
| "learning_rate": 5e-06, | |
| "loss": 0.396, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4219162027541752, | |
| "grad_norm": 0.501523217408356, | |
| "learning_rate": 5e-06, | |
| "loss": 0.398, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4453559917960738, | |
| "grad_norm": 0.5513765393124738, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3915, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.46879578083797246, | |
| "grad_norm": 0.48423414375531915, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3928, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4922355698798711, | |
| "grad_norm": 0.6668034319234166, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3897, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5156753589217697, | |
| "grad_norm": 0.6844513719684475, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3943, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5391151479636683, | |
| "grad_norm": 0.5634978239261383, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3867, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5625549370055669, | |
| "grad_norm": 0.48253201050555344, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3951, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5859947260474656, | |
| "grad_norm": 0.5583859071799139, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3896, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6094345150893642, | |
| "grad_norm": 0.5725388703107269, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3888, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6328743041312628, | |
| "grad_norm": 0.8156082811133835, | |
| "learning_rate": 5e-06, | |
| "loss": 0.379, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6563140931731615, | |
| "grad_norm": 0.5966575531920639, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3864, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6797538822150601, | |
| "grad_norm": 0.48850438172794114, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3873, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7031936712569586, | |
| "grad_norm": 0.5962793861443083, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3869, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7266334602988573, | |
| "grad_norm": 0.5171258822649074, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3818, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7500732493407559, | |
| "grad_norm": 0.5592073208479841, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3755, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7735130383826545, | |
| "grad_norm": 0.533904690846359, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3745, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7969528274245532, | |
| "grad_norm": 0.548421936851489, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3794, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8203926164664518, | |
| "grad_norm": 0.5826483187799658, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3729, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8438324055083504, | |
| "grad_norm": 0.65088471853365, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3728, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8672721945502491, | |
| "grad_norm": 0.7534193430854838, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3763, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8907119835921476, | |
| "grad_norm": 0.6782662978614515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3794, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9141517726340463, | |
| "grad_norm": 0.4771544648840299, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3702, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9375915616759449, | |
| "grad_norm": 0.5535379054118112, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3768, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9610313507178435, | |
| "grad_norm": 0.4608571118764034, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3788, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9844711397597422, | |
| "grad_norm": 0.5668677920657946, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3673, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9985350131848814, | |
| "eval_loss": 0.37145182490348816, | |
| "eval_runtime": 299.8322, | |
| "eval_samples_per_second": 38.341, | |
| "eval_steps_per_second": 0.6, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.0084969235276882, | |
| "grad_norm": 0.6984558481581081, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3801, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0319367125695869, | |
| "grad_norm": 0.5239390968899379, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3221, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0553765016114856, | |
| "grad_norm": 0.5695148407791144, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3257, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.078816290653384, | |
| "grad_norm": 0.5709165769711674, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3205, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1022560796952827, | |
| "grad_norm": 0.5285237377857552, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3267, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1256958687371814, | |
| "grad_norm": 0.5164839735723259, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3269, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1491356577790799, | |
| "grad_norm": 0.4651823010378352, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3299, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1725754468209786, | |
| "grad_norm": 0.4611493940935449, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3307, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1960152358628773, | |
| "grad_norm": 0.5290456767213961, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3338, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.219455024904776, | |
| "grad_norm": 0.49326918332510095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3253, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2428948139466744, | |
| "grad_norm": 0.551961171965543, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3296, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2663346029885731, | |
| "grad_norm": 0.49768749823200925, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3256, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2897743920304716, | |
| "grad_norm": 0.5626038647037341, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3255, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3132141810723703, | |
| "grad_norm": 0.5103540222464168, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3225, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.336653970114269, | |
| "grad_norm": 0.540424196440726, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3264, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3600937591561677, | |
| "grad_norm": 0.5745930638703757, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3196, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3835335481980662, | |
| "grad_norm": 0.6445462088875488, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3244, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4069733372399649, | |
| "grad_norm": 0.481096562270643, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3224, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4304131262818633, | |
| "grad_norm": 0.5092132313164293, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3251, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.453852915323762, | |
| "grad_norm": 0.5067387262720331, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3265, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4772927043656607, | |
| "grad_norm": 0.48943368667359805, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3279, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5007324934075594, | |
| "grad_norm": 0.5183176032348761, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3227, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.524172282449458, | |
| "grad_norm": 0.5247150397228669, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3181, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5476120714913566, | |
| "grad_norm": 0.5298290612904054, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3275, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.571051860533255, | |
| "grad_norm": 0.5335846082176007, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3228, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5944916495751538, | |
| "grad_norm": 0.49588298624982247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3199, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6179314386170525, | |
| "grad_norm": 0.5142614839866478, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3317, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.6413712276589512, | |
| "grad_norm": 0.4957666564649026, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3239, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6648110167008499, | |
| "grad_norm": 0.5027765035894468, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3208, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6882508057427483, | |
| "grad_norm": 0.6791514332148134, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3184, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7116905947846468, | |
| "grad_norm": 0.4925105147109606, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3252, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.7351303838265455, | |
| "grad_norm": 0.5049447941188098, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3201, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7585701728684442, | |
| "grad_norm": 0.544693187707417, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3258, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7820099619103429, | |
| "grad_norm": 0.4756047714296392, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3231, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.8054497509522416, | |
| "grad_norm": 0.5599548628855956, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3246, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.82888953999414, | |
| "grad_norm": 0.4756090546668893, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3219, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8523293290360385, | |
| "grad_norm": 0.6124115056884903, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3217, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8757691180779372, | |
| "grad_norm": 0.46580289937046976, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3259, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.899208907119836, | |
| "grad_norm": 0.5943245513187589, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3197, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.9226486961617346, | |
| "grad_norm": 0.49042860120039294, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3226, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.9460884852036333, | |
| "grad_norm": 0.5267257339110174, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3221, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9695282742455318, | |
| "grad_norm": 0.717669514593216, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3282, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.9929680632874303, | |
| "grad_norm": 0.46905846352186026, | |
| "learning_rate": 5e-06, | |
| "loss": 0.319, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.99765602109581, | |
| "eval_loss": 0.36132651567459106, | |
| "eval_runtime": 296.4899, | |
| "eval_samples_per_second": 38.774, | |
| "eval_steps_per_second": 0.607, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 2.0169938470553763, | |
| "grad_norm": 0.6240807456372731, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3065, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.040433636097275, | |
| "grad_norm": 0.6288943822511728, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2738, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.0638734251391737, | |
| "grad_norm": 0.5311356208759552, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2731, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0873132141810724, | |
| "grad_norm": 0.56075413432555, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2744, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.110753003222971, | |
| "grad_norm": 0.5639112603035239, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2751, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.13419279226487, | |
| "grad_norm": 0.5591523409924748, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2765, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.157632581306768, | |
| "grad_norm": 0.5663817052316904, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2737, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1810723703486667, | |
| "grad_norm": 0.623581090691007, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2741, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.2045121593905654, | |
| "grad_norm": 0.47856596919111055, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2756, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.227951948432464, | |
| "grad_norm": 0.48512193272255605, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2737, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.251391737474363, | |
| "grad_norm": 0.5099859245096886, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2796, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.2748315265162615, | |
| "grad_norm": 0.5305125040779604, | |
| "learning_rate": 5e-06, | |
| "loss": 0.273, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.2982713155581598, | |
| "grad_norm": 0.557582967315411, | |
| "learning_rate": 5e-06, | |
| "loss": 0.273, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.3217111046000585, | |
| "grad_norm": 0.5807484141453545, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2755, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.345150893641957, | |
| "grad_norm": 0.49544753860231366, | |
| "learning_rate": 5e-06, | |
| "loss": 0.281, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.368590682683856, | |
| "grad_norm": 0.5035116546897159, | |
| "learning_rate": 5e-06, | |
| "loss": 0.275, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.3920304717257546, | |
| "grad_norm": 0.5229341109864724, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2778, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.4154702607676533, | |
| "grad_norm": 0.5788744389040322, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2843, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.438910049809552, | |
| "grad_norm": 0.587705401996759, | |
| "learning_rate": 5e-06, | |
| "loss": 0.278, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.46234983885145, | |
| "grad_norm": 0.526667348496211, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2758, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.485789627893349, | |
| "grad_norm": 0.5557320228470611, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2749, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5092294169352476, | |
| "grad_norm": 0.5455334258984845, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2829, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.5326692059771463, | |
| "grad_norm": 0.6049156598816975, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2792, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.556108995019045, | |
| "grad_norm": 0.6063878997150756, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2768, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.5795487840609432, | |
| "grad_norm": 0.5807051957808216, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2837, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.602988573102842, | |
| "grad_norm": 0.48690825278368993, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2732, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.6264283621447406, | |
| "grad_norm": 0.47298208429795785, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2838, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.6498681511866393, | |
| "grad_norm": 0.5117446887050897, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2799, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.673307940228538, | |
| "grad_norm": 0.5788651437910809, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2831, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.6967477292704367, | |
| "grad_norm": 0.48115847246690635, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2795, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.7201875183123354, | |
| "grad_norm": 0.4752829940802366, | |
| "learning_rate": 5e-06, | |
| "loss": 0.282, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.7436273073542337, | |
| "grad_norm": 0.4817048174863979, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2798, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.7670670963961324, | |
| "grad_norm": 0.5163232884368958, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2785, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.790506885438031, | |
| "grad_norm": 0.49724121376113645, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2871, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.8139466744799297, | |
| "grad_norm": 0.575214274563183, | |
| "learning_rate": 5e-06, | |
| "loss": 0.277, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.8373864635218284, | |
| "grad_norm": 0.49524252636931043, | |
| "learning_rate": 5e-06, | |
| "loss": 0.284, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.8608262525637267, | |
| "grad_norm": 0.5731018313488945, | |
| "learning_rate": 5e-06, | |
| "loss": 0.279, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.8842660416056254, | |
| "grad_norm": 0.5359950242882849, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2805, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.907705830647524, | |
| "grad_norm": 0.5534733032853985, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2819, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.9311456196894228, | |
| "grad_norm": 0.5653588586425916, | |
| "learning_rate": 5e-06, | |
| "loss": 0.276, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.9545854087313215, | |
| "grad_norm": 0.5400026090208886, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2795, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.97802519777322, | |
| "grad_norm": 0.5145229483499503, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2817, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.996777029006739, | |
| "eval_loss": 0.3670854866504669, | |
| "eval_runtime": 285.3181, | |
| "eval_samples_per_second": 40.292, | |
| "eval_steps_per_second": 0.631, | |
| "step": 1278 | |
| }, | |
| { | |
| "epoch": 2.996777029006739, | |
| "step": 1278, | |
| "total_flos": 2140488220016640.0, | |
| "train_loss": 0.33715206393986613, | |
| "train_runtime": 42576.9653, | |
| "train_samples_per_second": 15.39, | |
| "train_steps_per_second": 0.03 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1278, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2140488220016640.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |