| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.7583963425356075, | |
| "eval_steps": 500, | |
| "global_step": 40000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.3358560800552368, | |
| "learning_rate": 2.9999642387366694e-06, | |
| "loss": 1.8182, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.0696768760681152, | |
| "learning_rate": 2.999856956651834e-06, | |
| "loss": 1.5829, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.1315983533859253, | |
| "learning_rate": 2.9996781588608853e-06, | |
| "loss": 1.5088, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.2688828706741333, | |
| "learning_rate": 2.9994278538892026e-06, | |
| "loss": 1.4755, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.3950492143630981, | |
| "learning_rate": 2.999106053671749e-06, | |
| "loss": 1.44, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.4453312158584595, | |
| "eval_runtime": 1866.1237, | |
| "eval_samples_per_second": 5.137, | |
| "eval_steps_per_second": 0.643, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.4245915412902832, | |
| "learning_rate": 2.9987127735525e-06, | |
| "loss": 1.428, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.3934013843536377, | |
| "learning_rate": 2.9982480322837146e-06, | |
| "loss": 1.4205, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.345449447631836, | |
| "learning_rate": 2.99771185202504e-06, | |
| "loss": 1.4117, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.4815948009490967, | |
| "learning_rate": 2.9971042583424534e-06, | |
| "loss": 1.4029, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.416758418083191, | |
| "learning_rate": 2.996425280207045e-06, | |
| "loss": 1.4103, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.4033704996109009, | |
| "eval_runtime": 1866.432, | |
| "eval_samples_per_second": 5.136, | |
| "eval_steps_per_second": 0.642, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.5439317226409912, | |
| "learning_rate": 2.995674949993636e-06, | |
| "loss": 1.3992, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.6817480325698853, | |
| "learning_rate": 2.9948533034792356e-06, | |
| "loss": 1.3857, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 1.5548583269119263, | |
| "learning_rate": 2.993960379841333e-06, | |
| "loss": 1.3889, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 1.800005316734314, | |
| "learning_rate": 2.992996221656031e-06, | |
| "loss": 1.3798, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 1.5900113582611084, | |
| "learning_rate": 2.9919608748960165e-06, | |
| "loss": 1.3915, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.3856122493743896, | |
| "eval_runtime": 1867.7341, | |
| "eval_samples_per_second": 5.132, | |
| "eval_steps_per_second": 0.642, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 1.593215823173523, | |
| "learning_rate": 2.990854388928367e-06, | |
| "loss": 1.3707, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 1.6342238187789917, | |
| "learning_rate": 2.9896768165121967e-06, | |
| "loss": 1.3909, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.7908762693405151, | |
| "learning_rate": 2.9884282137961426e-06, | |
| "loss": 1.3758, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.5925847291946411, | |
| "learning_rate": 2.987108640315685e-06, | |
| "loss": 1.3816, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 1.8841816186904907, | |
| "learning_rate": 2.9857181589903103e-06, | |
| "loss": 1.383, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.3752671480178833, | |
| "eval_runtime": 1867.3688, | |
| "eval_samples_per_second": 5.133, | |
| "eval_steps_per_second": 0.642, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 1.688745379447937, | |
| "learning_rate": 2.984256836120511e-06, | |
| "loss": 1.3796, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 1.676340103149414, | |
| "learning_rate": 2.9827247413846217e-06, | |
| "loss": 1.3742, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 2.0635907649993896, | |
| "learning_rate": 2.981121947835501e-06, | |
| "loss": 1.3712, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 1.799085021018982, | |
| "learning_rate": 2.979448531897045e-06, | |
| "loss": 1.3694, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 1.8315014839172363, | |
| "learning_rate": 2.9777045733605437e-06, | |
| "loss": 1.3558, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.3671655654907227, | |
| "eval_runtime": 1867.272, | |
| "eval_samples_per_second": 5.134, | |
| "eval_steps_per_second": 0.642, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 1.8167532682418823, | |
| "learning_rate": 2.9758901553808787e-06, | |
| "loss": 1.3579, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.8836266994476318, | |
| "learning_rate": 2.9740053644725552e-06, | |
| "loss": 1.3714, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.823400855064392, | |
| "learning_rate": 2.972050290505579e-06, | |
| "loss": 1.3609, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 1.8716390132904053, | |
| "learning_rate": 2.970025026701169e-06, | |
| "loss": 1.3685, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 1.7368168830871582, | |
| "learning_rate": 2.967929669627316e-06, | |
| "loss": 1.3665, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.3610810041427612, | |
| "eval_runtime": 1867.7829, | |
| "eval_samples_per_second": 5.132, | |
| "eval_steps_per_second": 0.642, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 1.8250432014465332, | |
| "learning_rate": 2.9657643191941737e-06, | |
| "loss": 1.3549, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 1.9420477151870728, | |
| "learning_rate": 2.9635290786492985e-06, | |
| "loss": 1.3531, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 2.0373518466949463, | |
| "learning_rate": 2.9612240545727255e-06, | |
| "loss": 1.3619, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 1.9139854907989502, | |
| "learning_rate": 2.9588493568718843e-06, | |
| "loss": 1.3665, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 1.9374817609786987, | |
| "learning_rate": 2.9564050987763614e-06, | |
| "loss": 1.3619, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.3560757637023926, | |
| "eval_runtime": 1867.3981, | |
| "eval_samples_per_second": 5.133, | |
| "eval_steps_per_second": 0.642, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.8168325424194336, | |
| "learning_rate": 2.9538913968325007e-06, | |
| "loss": 1.3527, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.948146939277649, | |
| "learning_rate": 2.951308370897845e-06, | |
| "loss": 1.3496, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 2.068612575531006, | |
| "learning_rate": 2.948656144135421e-06, | |
| "loss": 1.358, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 1.9631004333496094, | |
| "learning_rate": 2.945934843007869e-06, | |
| "loss": 1.3504, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 2.0034778118133545, | |
| "learning_rate": 2.9431445972714102e-06, | |
| "loss": 1.3582, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.3521347045898438, | |
| "eval_runtime": 1867.5478, | |
| "eval_samples_per_second": 5.133, | |
| "eval_steps_per_second": 0.642, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 1.872603178024292, | |
| "learning_rate": 2.940285539969662e-06, | |
| "loss": 1.3483, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 1.8477139472961426, | |
| "learning_rate": 2.9373578074272917e-06, | |
| "loss": 1.3623, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 2.0872058868408203, | |
| "learning_rate": 2.9343615392435187e-06, | |
| "loss": 1.3483, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 1.931931495666504, | |
| "learning_rate": 2.931296878285457e-06, | |
| "loss": 1.3499, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.9555952548980713, | |
| "learning_rate": 2.928163970681304e-06, | |
| "loss": 1.3525, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.348177433013916, | |
| "eval_runtime": 1865.9442, | |
| "eval_samples_per_second": 5.137, | |
| "eval_steps_per_second": 0.643, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.9107462167739868, | |
| "learning_rate": 2.9249629658133703e-06, | |
| "loss": 1.3446, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 2.1549768447875977, | |
| "learning_rate": 2.9216940163109613e-06, | |
| "loss": 1.3485, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 1.9788259267807007, | |
| "learning_rate": 2.9183572780430938e-06, | |
| "loss": 1.3386, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 2.008772850036621, | |
| "learning_rate": 2.9149529101110707e-06, | |
| "loss": 1.3449, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.932020664215088, | |
| "learning_rate": 2.9114810748408887e-06, | |
| "loss": 1.3471, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.3448920249938965, | |
| "eval_runtime": 1866.903, | |
| "eval_samples_per_second": 5.135, | |
| "eval_steps_per_second": 0.642, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.780934453010559, | |
| "learning_rate": 2.9079419377755016e-06, | |
| "loss": 1.3408, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 2.0991992950439453, | |
| "learning_rate": 2.904335667666926e-06, | |
| "loss": 1.3377, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 1.7961390018463135, | |
| "learning_rate": 2.9006624364681955e-06, | |
| "loss": 1.3446, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.951217770576477, | |
| "learning_rate": 2.896922419325161e-06, | |
| "loss": 1.3434, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.9937087297439575, | |
| "learning_rate": 2.89311579456814e-06, | |
| "loss": 1.3383, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.3420648574829102, | |
| "eval_runtime": 1864.5499, | |
| "eval_samples_per_second": 5.141, | |
| "eval_steps_per_second": 0.643, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.9863967895507812, | |
| "learning_rate": 2.889242743703412e-06, | |
| "loss": 1.3553, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 2.026629686355591, | |
| "learning_rate": 2.8853034514045667e-06, | |
| "loss": 1.3384, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 2.1524720191955566, | |
| "learning_rate": 2.8812981055036967e-06, | |
| "loss": 1.339, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 2.011669635772705, | |
| "learning_rate": 2.8772268969824412e-06, | |
| "loss": 1.3449, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 1.96876060962677, | |
| "learning_rate": 2.87309001996288e-06, | |
| "loss": 1.3352, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.3392791748046875, | |
| "eval_runtime": 1863.5996, | |
| "eval_samples_per_second": 5.144, | |
| "eval_steps_per_second": 0.643, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 2.030050754547119, | |
| "learning_rate": 2.868887671698278e-06, | |
| "loss": 1.3473, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 1.9417366981506348, | |
| "learning_rate": 2.8646200525636784e-06, | |
| "loss": 1.3467, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 1.8963119983673096, | |
| "learning_rate": 2.860287366046351e-06, | |
| "loss": 1.3298, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 2.0446488857269287, | |
| "learning_rate": 2.855889818736086e-06, | |
| "loss": 1.3364, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 1.9520761966705322, | |
| "learning_rate": 2.8514276203153476e-06, | |
| "loss": 1.3328, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.3369933366775513, | |
| "eval_runtime": 1864.5392, | |
| "eval_samples_per_second": 5.141, | |
| "eval_steps_per_second": 0.643, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 1.9833135604858398, | |
| "learning_rate": 2.846900983549272e-06, | |
| "loss": 1.3461, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 1.8837144374847412, | |
| "learning_rate": 2.8423101242755264e-06, | |
| "loss": 1.3354, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 1.9261667728424072, | |
| "learning_rate": 2.837655261394013e-06, | |
| "loss": 1.3349, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 1.8928134441375732, | |
| "learning_rate": 2.832936616856434e-06, | |
| "loss": 1.3247, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 2.0842361450195312, | |
| "learning_rate": 2.828154415655711e-06, | |
| "loss": 1.3396, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.3346595764160156, | |
| "eval_runtime": 1864.6191, | |
| "eval_samples_per_second": 5.141, | |
| "eval_steps_per_second": 0.643, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 2.0268609523773193, | |
| "learning_rate": 2.823308885815251e-06, | |
| "loss": 1.3577, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.9914246797561646, | |
| "learning_rate": 2.8184002583780802e-06, | |
| "loss": 1.3273, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 2.065075159072876, | |
| "learning_rate": 2.813428767395822e-06, | |
| "loss": 1.3449, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 2.0914437770843506, | |
| "learning_rate": 2.8083946499175413e-06, | |
| "loss": 1.3415, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 1.9424386024475098, | |
| "learning_rate": 2.803298145978439e-06, | |
| "loss": 1.3316, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.3324897289276123, | |
| "eval_runtime": 1864.3018, | |
| "eval_samples_per_second": 5.142, | |
| "eval_steps_per_second": 0.643, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 2.083033561706543, | |
| "learning_rate": 2.7981394985884074e-06, | |
| "loss": 1.3213, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 1.8912067413330078, | |
| "learning_rate": 2.792918953720444e-06, | |
| "loss": 1.3284, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 1.8995610475540161, | |
| "learning_rate": 2.7876367602989206e-06, | |
| "loss": 1.3256, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 1.9921075105667114, | |
| "learning_rate": 2.7822931701877186e-06, | |
| "loss": 1.3339, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 1.9593900442123413, | |
| "learning_rate": 2.7768884381782147e-06, | |
| "loss": 1.3357, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.3304702043533325, | |
| "eval_runtime": 1863.8735, | |
| "eval_samples_per_second": 5.143, | |
| "eval_steps_per_second": 0.643, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 2.0294156074523926, | |
| "learning_rate": 2.7714228219771354e-06, | |
| "loss": 1.3248, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 1.9358181953430176, | |
| "learning_rate": 2.765896582194267e-06, | |
| "loss": 1.3321, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 1.9804461002349854, | |
| "learning_rate": 2.7603099823300316e-06, | |
| "loss": 1.328, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 1.9724797010421753, | |
| "learning_rate": 2.754663288762921e-06, | |
| "loss": 1.3313, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 2.1071040630340576, | |
| "learning_rate": 2.748956770736796e-06, | |
| "loss": 1.3164, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.3289612531661987, | |
| "eval_runtime": 1864.6483, | |
| "eval_samples_per_second": 5.141, | |
| "eval_steps_per_second": 0.643, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 1.8682750463485718, | |
| "learning_rate": 2.743190700348048e-06, | |
| "loss": 1.3318, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 2.1705667972564697, | |
| "learning_rate": 2.7373653525326257e-06, | |
| "loss": 1.3203, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 2.2123374938964844, | |
| "learning_rate": 2.7314810050529265e-06, | |
| "loss": 1.3279, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 2.0958218574523926, | |
| "learning_rate": 2.7255379384845483e-06, | |
| "loss": 1.332, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.0944671630859375, | |
| "learning_rate": 2.7195364362029173e-06, | |
| "loss": 1.3231, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.3273080587387085, | |
| "eval_runtime": 1864.6036, | |
| "eval_samples_per_second": 5.141, | |
| "eval_steps_per_second": 0.643, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.045405149459839, | |
| "learning_rate": 2.713476784369771e-06, | |
| "loss": 1.3179, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.985823392868042, | |
| "learning_rate": 2.7073592719195155e-06, | |
| "loss": 1.3318, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 2.064948081970215, | |
| "learning_rate": 2.7011841905454495e-06, | |
| "loss": 1.3181, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 2.136582612991333, | |
| "learning_rate": 2.694951834685854e-06, | |
| "loss": 1.3181, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 2.394834041595459, | |
| "learning_rate": 2.6886625015099553e-06, | |
| "loss": 1.3287, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.3257533311843872, | |
| "eval_runtime": 1871.6529, | |
| "eval_samples_per_second": 5.122, | |
| "eval_steps_per_second": 0.641, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 2.0295205116271973, | |
| "learning_rate": 2.682316490903753e-06, | |
| "loss": 1.3316, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 1.883170247077942, | |
| "learning_rate": 2.6759141054557214e-06, | |
| "loss": 1.345, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 2.172785997390747, | |
| "learning_rate": 2.6694556504423836e-06, | |
| "loss": 1.3197, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 2.065781354904175, | |
| "learning_rate": 2.662941433813754e-06, | |
| "loss": 1.3165, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 1.825239896774292, | |
| "learning_rate": 2.6563717661786536e-06, | |
| "loss": 1.3308, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.324156641960144, | |
| "eval_runtime": 1865.6117, | |
| "eval_samples_per_second": 5.138, | |
| "eval_steps_per_second": 0.643, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 2.128471612930298, | |
| "learning_rate": 2.649746960789902e-06, | |
| "loss": 1.3176, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 1.994718074798584, | |
| "learning_rate": 2.6430673335293788e-06, | |
| "loss": 1.3245, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 2.0164434909820557, | |
| "learning_rate": 2.6363332028929633e-06, | |
| "loss": 1.3179, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 1.879969835281372, | |
| "learning_rate": 2.629544889975348e-06, | |
| "loss": 1.3346, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 1.9689232110977173, | |
| "learning_rate": 2.6227027184547265e-06, | |
| "loss": 1.311, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.3230102062225342, | |
| "eval_runtime": 1865.9111, | |
| "eval_samples_per_second": 5.137, | |
| "eval_steps_per_second": 0.643, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 2.0227608680725098, | |
| "learning_rate": 2.615807014577363e-06, | |
| "loss": 1.3226, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 1.9242812395095825, | |
| "learning_rate": 2.608858107142033e-06, | |
| "loss": 1.3254, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 1.9587324857711792, | |
| "learning_rate": 2.601856327484348e-06, | |
| "loss": 1.3219, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 2.0176897048950195, | |
| "learning_rate": 2.594802009460957e-06, | |
| "loss": 1.3133, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.871654987335205, | |
| "learning_rate": 2.5876954894336257e-06, | |
| "loss": 1.3242, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.321611762046814, | |
| "eval_runtime": 1864.3465, | |
| "eval_samples_per_second": 5.142, | |
| "eval_steps_per_second": 0.643, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 2.1732594966888428, | |
| "learning_rate": 2.580537106253199e-06, | |
| "loss": 1.3123, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 1.9368730783462524, | |
| "learning_rate": 2.5733272012434456e-06, | |
| "loss": 1.323, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 2.197732448577881, | |
| "learning_rate": 2.56606611818478e-06, | |
| "loss": 1.316, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 2.0765159130096436, | |
| "learning_rate": 2.5587542032978735e-06, | |
| "loss": 1.326, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 1.9759124517440796, | |
| "learning_rate": 2.551391805227145e-06, | |
| "loss": 1.319, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.3201991319656372, | |
| "eval_runtime": 1867.1093, | |
| "eval_samples_per_second": 5.134, | |
| "eval_steps_per_second": 0.642, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 2.119062900543213, | |
| "learning_rate": 2.5439792750241362e-06, | |
| "loss": 1.319, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 1.9623346328735352, | |
| "learning_rate": 2.5365169661307723e-06, | |
| "loss": 1.3188, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 2.069474935531616, | |
| "learning_rate": 2.529005234362512e-06, | |
| "loss": 1.3236, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 1.8530821800231934, | |
| "learning_rate": 2.521444437891378e-06, | |
| "loss": 1.3172, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 2.1172099113464355, | |
| "learning_rate": 2.513834937228883e-06, | |
| "loss": 1.3183, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.31929349899292, | |
| "eval_runtime": 1867.4942, | |
| "eval_samples_per_second": 5.133, | |
| "eval_steps_per_second": 0.642, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 1.981194019317627, | |
| "learning_rate": 2.5061770952088354e-06, | |
| "loss": 1.3278, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 1.9915848970413208, | |
| "learning_rate": 2.4984712769700423e-06, | |
| "loss": 1.3143, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 2.114997625350952, | |
| "learning_rate": 2.490717849938897e-06, | |
| "loss": 1.3207, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 1.9648516178131104, | |
| "learning_rate": 2.4829171838118613e-06, | |
| "loss": 1.3129, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 1.9119199514389038, | |
| "learning_rate": 2.4750696505378355e-06, | |
| "loss": 1.3211, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.3180123567581177, | |
| "eval_runtime": 1866.9983, | |
| "eval_samples_per_second": 5.134, | |
| "eval_steps_per_second": 0.642, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 2.158143997192383, | |
| "learning_rate": 2.4671756243004243e-06, | |
| "loss": 1.3124, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 2.059196949005127, | |
| "learning_rate": 2.4592354815000963e-06, | |
| "loss": 1.3229, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 1.9812512397766113, | |
| "learning_rate": 2.451249600736235e-06, | |
| "loss": 1.3159, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 1.9367738962173462, | |
| "learning_rate": 2.4432183627890867e-06, | |
| "loss": 1.3101, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 2.1279842853546143, | |
| "learning_rate": 2.4351421506016047e-06, | |
| "loss": 1.3158, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.3169833421707153, | |
| "eval_runtime": 1870.0395, | |
| "eval_samples_per_second": 5.126, | |
| "eval_steps_per_second": 0.641, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 2.213517189025879, | |
| "learning_rate": 2.4270213492611903e-06, | |
| "loss": 1.3113, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 2.060974597930908, | |
| "learning_rate": 2.41885634598133e-06, | |
| "loss": 1.3248, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 2.004950523376465, | |
| "learning_rate": 2.4106475300831343e-06, | |
| "loss": 1.321, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 2.081263303756714, | |
| "learning_rate": 2.402395292976772e-06, | |
| "loss": 1.3058, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 2.141289472579956, | |
| "learning_rate": 2.394100028142809e-06, | |
| "loss": 1.3054, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.3159672021865845, | |
| "eval_runtime": 1868.4185, | |
| "eval_samples_per_second": 5.131, | |
| "eval_steps_per_second": 0.642, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.041181802749634, | |
| "learning_rate": 2.3857621311134457e-06, | |
| "loss": 1.324, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 1.9553183317184448, | |
| "learning_rate": 2.3773819994536564e-06, | |
| "loss": 1.3115, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 2.0408129692077637, | |
| "learning_rate": 2.368960032742235e-06, | |
| "loss": 1.3007, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 2.0877633094787598, | |
| "learning_rate": 2.36049663255274e-06, | |
| "loss": 1.3174, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 2.013047218322754, | |
| "learning_rate": 2.35199220243435e-06, | |
| "loss": 1.3249, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.3149954080581665, | |
| "eval_runtime": 1864.575, | |
| "eval_samples_per_second": 5.141, | |
| "eval_steps_per_second": 0.643, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 1.9625511169433594, | |
| "learning_rate": 2.3434471478926168e-06, | |
| "loss": 1.3053, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 1.9895579814910889, | |
| "learning_rate": 2.334861876370135e-06, | |
| "loss": 1.3097, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 2.0086371898651123, | |
| "learning_rate": 2.3262367972271126e-06, | |
| "loss": 1.3075, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 2.0822415351867676, | |
| "learning_rate": 2.317572321721851e-06, | |
| "loss": 1.3122, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 2.1191747188568115, | |
| "learning_rate": 2.3088688629911378e-06, | |
| "loss": 1.3029, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.313984990119934, | |
| "eval_runtime": 1868.3094, | |
| "eval_samples_per_second": 5.131, | |
| "eval_steps_per_second": 0.642, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 2.0153069496154785, | |
| "learning_rate": 2.3001268360305446e-06, | |
| "loss": 1.31, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 2.031879425048828, | |
| "learning_rate": 2.2913466576746433e-06, | |
| "loss": 1.3113, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 1.9688141345977783, | |
| "learning_rate": 2.2825287465771276e-06, | |
| "loss": 1.3114, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 2.0744152069091797, | |
| "learning_rate": 2.2736735231908515e-06, | |
| "loss": 1.3068, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 2.004817485809326, | |
| "learning_rate": 2.2647814097477816e-06, | |
| "loss": 1.3148, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.3130929470062256, | |
| "eval_runtime": 1864.9246, | |
| "eval_samples_per_second": 5.14, | |
| "eval_steps_per_second": 0.643, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 2.018002510070801, | |
| "learning_rate": 2.2558528302388663e-06, | |
| "loss": 1.318, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 2.0592522621154785, | |
| "learning_rate": 2.2468882103938155e-06, | |
| "loss": 1.3139, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 1.9203455448150635, | |
| "learning_rate": 2.237887977660804e-06, | |
| "loss": 1.3163, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 2.1021227836608887, | |
| "learning_rate": 2.2288525611860886e-06, | |
| "loss": 1.3182, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 2.050011396408081, | |
| "learning_rate": 2.219782391793547e-06, | |
| "loss": 1.3036, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.312229871749878, | |
| "eval_runtime": 1865.3014, | |
| "eval_samples_per_second": 5.139, | |
| "eval_steps_per_second": 0.643, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 2.0257480144500732, | |
| "learning_rate": 2.2106779019641336e-06, | |
| "loss": 1.2984, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 1.9984742403030396, | |
| "learning_rate": 2.2015395258152596e-06, | |
| "loss": 1.3206, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 2.094935417175293, | |
| "learning_rate": 2.1923676990800927e-06, | |
| "loss": 1.3157, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 2.0469040870666504, | |
| "learning_rate": 2.1831628590867812e-06, | |
| "loss": 1.3048, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 2.0622622966766357, | |
| "learning_rate": 2.1739254447376006e-06, | |
| "loss": 1.3138, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.3114036321640015, | |
| "eval_runtime": 1865.761, | |
| "eval_samples_per_second": 5.138, | |
| "eval_steps_per_second": 0.643, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 2.0791163444519043, | |
| "learning_rate": 2.1646558964880277e-06, | |
| "loss": 1.3108, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 2.027860403060913, | |
| "learning_rate": 2.1553546563257362e-06, | |
| "loss": 1.3116, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 2.0047738552093506, | |
| "learning_rate": 2.146022167749525e-06, | |
| "loss": 1.3048, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 2.213186025619507, | |
| "learning_rate": 2.136658875748169e-06, | |
| "loss": 1.3071, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 2.0164272785186768, | |
| "learning_rate": 2.1272652267792036e-06, | |
| "loss": 1.314, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.310592532157898, | |
| "eval_runtime": 1865.0707, | |
| "eval_samples_per_second": 5.14, | |
| "eval_steps_per_second": 0.643, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 2.063606023788452, | |
| "learning_rate": 2.117841668747633e-06, | |
| "loss": 1.3171, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 2.066218137741089, | |
| "learning_rate": 2.1083886509845794e-06, | |
| "loss": 1.3095, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 2.00728702545166, | |
| "learning_rate": 2.098906624225852e-06, | |
| "loss": 1.3082, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 1.946075439453125, | |
| "learning_rate": 2.089396040590459e-06, | |
| "loss": 1.3106, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 2.2883059978485107, | |
| "learning_rate": 2.079857353559047e-06, | |
| "loss": 1.3045, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.3099678754806519, | |
| "eval_runtime": 1865.3447, | |
| "eval_samples_per_second": 5.139, | |
| "eval_steps_per_second": 0.643, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 1.9902862310409546, | |
| "learning_rate": 2.070291017952282e-06, | |
| "loss": 1.3188, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.0283963680267334, | |
| "learning_rate": 2.0606974899091596e-06, | |
| "loss": 1.3115, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.249575138092041, | |
| "learning_rate": 2.0510772268652563e-06, | |
| "loss": 1.3095, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.022587537765503, | |
| "learning_rate": 2.0414306875309195e-06, | |
| "loss": 1.2989, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 2.3016037940979004, | |
| "learning_rate": 2.0317583318693924e-06, | |
| "loss": 1.303, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.3091822862625122, | |
| "eval_runtime": 1863.7921, | |
| "eval_samples_per_second": 5.143, | |
| "eval_steps_per_second": 0.643, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 2.1690895557403564, | |
| "learning_rate": 2.022060621074887e-06, | |
| "loss": 1.3057, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 2.1167852878570557, | |
| "learning_rate": 2.012338017550587e-06, | |
| "loss": 1.297, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 2.035123109817505, | |
| "learning_rate": 2.0025909848866085e-06, | |
| "loss": 1.305, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 1.931913137435913, | |
| "learning_rate": 1.9928199878378854e-06, | |
| "loss": 1.2938, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 2.0481088161468506, | |
| "learning_rate": 1.983025492302016e-06, | |
| "loss": 1.2977, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.3084911108016968, | |
| "eval_runtime": 1866.3126, | |
| "eval_samples_per_second": 5.136, | |
| "eval_steps_per_second": 0.642, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.9030753374099731, | |
| "learning_rate": 1.973207965297045e-06, | |
| "loss": 1.3115, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.9687721729278564, | |
| "learning_rate": 1.963367874939198e-06, | |
| "loss": 1.3026, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 2.2594008445739746, | |
| "learning_rate": 1.9535056904205588e-06, | |
| "loss": 1.3134, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 2.038999080657959, | |
| "learning_rate": 1.943621881986696e-06, | |
| "loss": 1.3039, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 1.9501850605010986, | |
| "learning_rate": 1.933716920914245e-06, | |
| "loss": 1.3096, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.3078255653381348, | |
| "eval_runtime": 1865.4912, | |
| "eval_samples_per_second": 5.139, | |
| "eval_steps_per_second": 0.643, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 2.107854127883911, | |
| "learning_rate": 1.923791279488435e-06, | |
| "loss": 1.307, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 2.067185640335083, | |
| "learning_rate": 1.913845430980567e-06, | |
| "loss": 1.3225, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 1.9632668495178223, | |
| "learning_rate": 1.9038798496254518e-06, | |
| "loss": 1.3095, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 2.140648603439331, | |
| "learning_rate": 1.8938950105987948e-06, | |
| "loss": 1.2998, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 1.9392528533935547, | |
| "learning_rate": 1.8838913899945394e-06, | |
| "loss": 1.3073, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.3071683645248413, | |
| "eval_runtime": 1864.0962, | |
| "eval_samples_per_second": 5.142, | |
| "eval_steps_per_second": 0.643, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 2.2147011756896973, | |
| "learning_rate": 1.8738694648021666e-06, | |
| "loss": 1.3017, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 2.112633228302002, | |
| "learning_rate": 1.863829712883951e-06, | |
| "loss": 1.312, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 2.0416507720947266, | |
| "learning_rate": 1.8537726129521755e-06, | |
| "loss": 1.3036, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 1.988303303718567, | |
| "learning_rate": 1.8436986445463049e-06, | |
| "loss": 1.3009, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 2.023023843765259, | |
| "learning_rate": 1.8336082880101228e-06, | |
| "loss": 1.3137, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.3065180778503418, | |
| "eval_runtime": 1866.3466, | |
| "eval_samples_per_second": 5.136, | |
| "eval_steps_per_second": 0.642, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 2.112020254135132, | |
| "learning_rate": 1.8235020244688246e-06, | |
| "loss": 1.3037, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 2.056504249572754, | |
| "learning_rate": 1.8133803358060798e-06, | |
| "loss": 1.3141, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 2.0338857173919678, | |
| "learning_rate": 1.8032437046410528e-06, | |
| "loss": 1.3012, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 2.071561098098755, | |
| "learning_rate": 1.7930926143053926e-06, | |
| "loss": 1.3063, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 2.080360174179077, | |
| "learning_rate": 1.7829275488201849e-06, | |
| "loss": 1.3083, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.3060280084609985, | |
| "eval_runtime": 1870.2241, | |
| "eval_samples_per_second": 5.126, | |
| "eval_steps_per_second": 0.641, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 2.0536909103393555, | |
| "learning_rate": 1.7727489928728747e-06, | |
| "loss": 1.3115, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 2.07513689994812, | |
| "learning_rate": 1.762557431794155e-06, | |
| "loss": 1.3028, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 2.2155916690826416, | |
| "learning_rate": 1.7523533515348249e-06, | |
| "loss": 1.3061, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 2.2243480682373047, | |
| "learning_rate": 1.7421372386426185e-06, | |
| "loss": 1.312, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 2.010845184326172, | |
| "learning_rate": 1.7319095802390087e-06, | |
| "loss": 1.3199, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.3053687810897827, | |
| "eval_runtime": 1865.2464, | |
| "eval_samples_per_second": 5.139, | |
| "eval_steps_per_second": 0.643, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 1.9459248781204224, | |
| "learning_rate": 1.7216708639959744e-06, | |
| "loss": 1.3091, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 2.0189294815063477, | |
| "learning_rate": 1.711421578112754e-06, | |
| "loss": 1.2958, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 2.0753591060638428, | |
| "learning_rate": 1.701162211292561e-06, | |
| "loss": 1.3041, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 2.1882078647613525, | |
| "learning_rate": 1.6908932527192886e-06, | |
| "loss": 1.3104, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 2.0360772609710693, | |
| "learning_rate": 1.6806151920341779e-06, | |
| "loss": 1.31, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.3050304651260376, | |
| "eval_runtime": 1868.8769, | |
| "eval_samples_per_second": 5.129, | |
| "eval_steps_per_second": 0.642, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 2.137718439102173, | |
| "learning_rate": 1.6703285193124748e-06, | |
| "loss": 1.3027, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 2.0401344299316406, | |
| "learning_rate": 1.660033725040063e-06, | |
| "loss": 1.3037, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 1.9637211561203003, | |
| "learning_rate": 1.649731300090074e-06, | |
| "loss": 1.2974, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 2.090510368347168, | |
| "learning_rate": 1.6394217356994827e-06, | |
| "loss": 1.2934, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 2.3479647636413574, | |
| "learning_rate": 1.6291055234456859e-06, | |
| "loss": 1.3201, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.3043450117111206, | |
| "eval_runtime": 1866.4601, | |
| "eval_samples_per_second": 5.136, | |
| "eval_steps_per_second": 0.642, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 2.1579744815826416, | |
| "learning_rate": 1.6187831552230603e-06, | |
| "loss": 1.2983, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 2.2169971466064453, | |
| "learning_rate": 1.608455123219511e-06, | |
| "loss": 1.3011, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.9283170700073242, | |
| "learning_rate": 1.5981219198929995e-06, | |
| "loss": 1.3036, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.9650486707687378, | |
| "learning_rate": 1.5877840379480678e-06, | |
| "loss": 1.3017, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 2.2148048877716064, | |
| "learning_rate": 1.5774419703123393e-06, | |
| "loss": 1.3118, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.303900122642517, | |
| "eval_runtime": 1863.2857, | |
| "eval_samples_per_second": 5.145, | |
| "eval_steps_per_second": 0.643, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 2.119337558746338, | |
| "learning_rate": 1.56709621011302e-06, | |
| "loss": 1.3038, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 2.062990427017212, | |
| "learning_rate": 1.5567472506533827e-06, | |
| "loss": 1.2878, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 2.1745545864105225, | |
| "learning_rate": 1.546395585389247e-06, | |
| "loss": 1.2964, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 2.1263065338134766, | |
| "learning_rate": 1.5360417079054494e-06, | |
| "loss": 1.295, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 2.044600248336792, | |
| "learning_rate": 1.5256861118923083e-06, | |
| "loss": 1.3049, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.303480625152588, | |
| "eval_runtime": 1862.9597, | |
| "eval_samples_per_second": 5.146, | |
| "eval_steps_per_second": 0.644, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 2.0431716442108154, | |
| "learning_rate": 1.5153292911220858e-06, | |
| "loss": 1.2992, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.1952879428863525, | |
| "learning_rate": 1.5049717394254412e-06, | |
| "loss": 1.2952, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.9967477321624756, | |
| "learning_rate": 1.4946139506678864e-06, | |
| "loss": 1.2967, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 2.1949024200439453, | |
| "learning_rate": 1.4842564187262365e-06, | |
| "loss": 1.3107, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 2.114365339279175, | |
| "learning_rate": 1.47389963746506e-06, | |
| "loss": 1.2946, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.3029588460922241, | |
| "eval_runtime": 1862.6203, | |
| "eval_samples_per_second": 5.147, | |
| "eval_steps_per_second": 0.644, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 2.3793764114379883, | |
| "learning_rate": 1.4635441007131343e-06, | |
| "loss": 1.3098, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 2.0778090953826904, | |
| "learning_rate": 1.453190302239894e-06, | |
| "loss": 1.3051, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 2.019946336746216, | |
| "learning_rate": 1.442838735731892e-06, | |
| "loss": 1.2966, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 2.1698460578918457, | |
| "learning_rate": 1.432489894769254e-06, | |
| "loss": 1.3029, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 2.034184217453003, | |
| "learning_rate": 1.4221442728021506e-06, | |
| "loss": 1.316, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 1.3026907444000244, | |
| "eval_runtime": 1863.5533, | |
| "eval_samples_per_second": 5.144, | |
| "eval_steps_per_second": 0.643, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 2.025113582611084, | |
| "learning_rate": 1.4118023631272633e-06, | |
| "loss": 1.2935, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 2.073225259780884, | |
| "learning_rate": 1.4014646588642656e-06, | |
| "loss": 1.2967, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 2.120889186859131, | |
| "learning_rate": 1.391131652932311e-06, | |
| "loss": 1.3013, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 2.005122423171997, | |
| "learning_rate": 1.3808038380265258e-06, | |
| "loss": 1.2928, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 2.147322654724121, | |
| "learning_rate": 1.3704817065945235e-06, | |
| "loss": 1.3059, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 1.3021385669708252, | |
| "eval_runtime": 1865.741, | |
| "eval_samples_per_second": 5.138, | |
| "eval_steps_per_second": 0.643, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 2.336851119995117, | |
| "learning_rate": 1.360165750812916e-06, | |
| "loss": 1.2986, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 2.077028274536133, | |
| "learning_rate": 1.3498564625638525e-06, | |
| "loss": 1.3062, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 2.137953519821167, | |
| "learning_rate": 1.3395543334115616e-06, | |
| "loss": 1.3071, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 2.054823875427246, | |
| "learning_rate": 1.3292598545789157e-06, | |
| "loss": 1.2981, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 2.045687198638916, | |
| "learning_rate": 1.3189735169240044e-06, | |
| "loss": 1.2971, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 1.3017216920852661, | |
| "eval_runtime": 1863.3072, | |
| "eval_samples_per_second": 5.145, | |
| "eval_steps_per_second": 0.643, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 2.2879574298858643, | |
| "learning_rate": 1.308695810916735e-06, | |
| "loss": 1.2943, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 2.1517672538757324, | |
| "learning_rate": 1.2984272266154414e-06, | |
| "loss": 1.3083, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 2.0498697757720947, | |
| "learning_rate": 1.288168253643521e-06, | |
| "loss": 1.2873, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 2.1879069805145264, | |
| "learning_rate": 1.2779193811660837e-06, | |
| "loss": 1.2902, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 2.2728075981140137, | |
| "learning_rate": 1.2676810978666353e-06, | |
| "loss": 1.3001, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 1.3014191389083862, | |
| "eval_runtime": 1863.092, | |
| "eval_samples_per_second": 5.145, | |
| "eval_steps_per_second": 0.644, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 2.2328622341156006, | |
| "learning_rate": 1.2574538919237673e-06, | |
| "loss": 1.3028, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 2.2706058025360107, | |
| "learning_rate": 1.2472382509878873e-06, | |
| "loss": 1.2931, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 2.234330892562866, | |
| "learning_rate": 1.2370346621579623e-06, | |
| "loss": 1.3025, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 2.125455379486084, | |
| "learning_rate": 1.2268436119582958e-06, | |
| "loss": 1.3031, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 2.0227627754211426, | |
| "learning_rate": 1.2166655863153263e-06, | |
| "loss": 1.2743, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 1.3010908365249634, | |
| "eval_runtime": 1862.8931, | |
| "eval_samples_per_second": 5.146, | |
| "eval_steps_per_second": 0.644, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 2.0580368041992188, | |
| "learning_rate": 1.2065010705344618e-06, | |
| "loss": 1.3054, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 2.1647911071777344, | |
| "learning_rate": 1.1963505492769355e-06, | |
| "loss": 1.2916, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 2.0057008266448975, | |
| "learning_rate": 1.1862145065366998e-06, | |
| "loss": 1.3016, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 2.097618341445923, | |
| "learning_rate": 1.1760934256173447e-06, | |
| "loss": 1.2946, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 2.1340222358703613, | |
| "learning_rate": 1.1659877891090587e-06, | |
| "loss": 1.2983, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 1.300696849822998, | |
| "eval_runtime": 1862.6712, | |
| "eval_samples_per_second": 5.146, | |
| "eval_steps_per_second": 0.644, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 2.054945468902588, | |
| "learning_rate": 1.155898078865611e-06, | |
| "loss": 1.3035, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 2.0940968990325928, | |
| "learning_rate": 1.1458247759813828e-06, | |
| "loss": 1.2955, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 2.199674129486084, | |
| "learning_rate": 1.135768360768423e-06, | |
| "loss": 1.3013, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 2.2380006313323975, | |
| "learning_rate": 1.125729312733549e-06, | |
| "loss": 1.3017, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 2.0469789505004883, | |
| "learning_rate": 1.1157081105554801e-06, | |
| "loss": 1.3048, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 1.3003997802734375, | |
| "eval_runtime": 1862.5897, | |
| "eval_samples_per_second": 5.147, | |
| "eval_steps_per_second": 0.644, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 2.136064052581787, | |
| "learning_rate": 1.1057052320620172e-06, | |
| "loss": 1.2849, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 2.2330269813537598, | |
| "learning_rate": 1.0957211542072556e-06, | |
| "loss": 1.2946, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 2.45259690284729, | |
| "learning_rate": 1.085756353048846e-06, | |
| "loss": 1.2956, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 2.133361339569092, | |
| "learning_rate": 1.0758113037252912e-06, | |
| "loss": 1.3041, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 2.1824896335601807, | |
| "learning_rate": 1.065886480433296e-06, | |
| "loss": 1.2945, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 1.2999972105026245, | |
| "eval_runtime": 1863.119, | |
| "eval_samples_per_second": 5.145, | |
| "eval_steps_per_second": 0.644, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 2.218424081802368, | |
| "learning_rate": 1.0559823564051523e-06, | |
| "loss": 1.3011, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.0408236980438232, | |
| "learning_rate": 1.0460994038861768e-06, | |
| "loss": 1.2935, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.0885488986968994, | |
| "learning_rate": 1.0362380941121925e-06, | |
| "loss": 1.3001, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.130805015563965, | |
| "learning_rate": 1.0263988972870613e-06, | |
| "loss": 1.3081, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 2.0574839115142822, | |
| "learning_rate": 1.0165822825602596e-06, | |
| "loss": 1.3071, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 1.2996830940246582, | |
| "eval_runtime": 1863.286, | |
| "eval_samples_per_second": 5.145, | |
| "eval_steps_per_second": 0.643, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 2.075486421585083, | |
| "learning_rate": 1.0067887180045145e-06, | |
| "loss": 1.296, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 2.07733154296875, | |
| "learning_rate": 9.970186705934803e-07, | |
| "loss": 1.3015, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 2.1551625728607178, | |
| "learning_rate": 9.872726061794744e-07, | |
| "loss": 1.2951, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 2.174243927001953, | |
| "learning_rate": 9.775509894712656e-07, | |
| "loss": 1.3052, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 2.11954665184021, | |
| "learning_rate": 9.678542840119123e-07, | |
| "loss": 1.294, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 1.2994180917739868, | |
| "eval_runtime": 1864.2204, | |
| "eval_samples_per_second": 5.142, | |
| "eval_steps_per_second": 0.643, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 2.0479559898376465, | |
| "learning_rate": 9.581829521566663e-07, | |
| "loss": 1.3078, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 2.1119577884674072, | |
| "learning_rate": 9.485374550509197e-07, | |
| "loss": 1.2878, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 2.1557509899139404, | |
| "learning_rate": 9.389182526082229e-07, | |
| "loss": 1.2866, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 2.226323127746582, | |
| "learning_rate": 9.293258034883504e-07, | |
| "loss": 1.2977, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 2.1167123317718506, | |
| "learning_rate": 9.197605650754353e-07, | |
| "loss": 1.2937, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 1.2991981506347656, | |
| "eval_runtime": 1863.4013, | |
| "eval_samples_per_second": 5.144, | |
| "eval_steps_per_second": 0.643, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 2.254310131072998, | |
| "learning_rate": 9.10222993456156e-07, | |
| "loss": 1.3016, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 2.0988237857818604, | |
| "learning_rate": 9.007135433979935e-07, | |
| "loss": 1.3, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 2.0965945720672607, | |
| "learning_rate": 8.912326683275442e-07, | |
| "loss": 1.2877, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 2.037484884262085, | |
| "learning_rate": 8.817808203089022e-07, | |
| "loss": 1.3084, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 2.0629284381866455, | |
| "learning_rate": 8.723584500221013e-07, | |
| "loss": 1.2857, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.298945426940918, | |
| "eval_runtime": 1863.2462, | |
| "eval_samples_per_second": 5.145, | |
| "eval_steps_per_second": 0.644, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 2.1192641258239746, | |
| "learning_rate": 8.62966006741628e-07, | |
| "loss": 1.3011, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 2.2492525577545166, | |
| "learning_rate": 8.536039383150001e-07, | |
| "loss": 1.2882, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 2.1896586418151855, | |
| "learning_rate": 8.442726911414094e-07, | |
| "loss": 1.2933, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 2.073396921157837, | |
| "learning_rate": 8.349727101504388e-07, | |
| "loss": 1.3119, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 2.1311280727386475, | |
| "learning_rate": 8.257044387808482e-07, | |
| "loss": 1.2921, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 1.2986724376678467, | |
| "eval_runtime": 1862.6142, | |
| "eval_samples_per_second": 5.147, | |
| "eval_steps_per_second": 0.644, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 2.1984448432922363, | |
| "learning_rate": 8.164683189594269e-07, | |
| "loss": 1.2933, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 2.1039230823516846, | |
| "learning_rate": 8.072647910799269e-07, | |
| "loss": 1.3129, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 1.9746812582015991, | |
| "learning_rate": 7.980942939820596e-07, | |
| "loss": 1.305, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 2.099011182785034, | |
| "learning_rate": 7.889572649305736e-07, | |
| "loss": 1.2956, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 2.3024837970733643, | |
| "learning_rate": 7.798541395944053e-07, | |
| "loss": 1.2794, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 1.2984648942947388, | |
| "eval_runtime": 1861.962, | |
| "eval_samples_per_second": 5.148, | |
| "eval_steps_per_second": 0.644, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 2.1850967407226562, | |
| "learning_rate": 7.707853520259052e-07, | |
| "loss": 1.2854, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 2.239342212677002, | |
| "learning_rate": 7.617513346401388e-07, | |
| "loss": 1.2919, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 2.3949005603790283, | |
| "learning_rate": 7.527525181942738e-07, | |
| "loss": 1.3048, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 2.2545089721679688, | |
| "learning_rate": 7.437893317670351e-07, | |
| "loss": 1.2909, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 2.2839066982269287, | |
| "learning_rate": 7.348622027382499e-07, | |
| "loss": 1.299, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 1.2982053756713867, | |
| "eval_runtime": 1862.6374, | |
| "eval_samples_per_second": 5.146, | |
| "eval_steps_per_second": 0.644, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 2.43034029006958, | |
| "learning_rate": 7.259715567684677e-07, | |
| "loss": 1.2973, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 2.251255989074707, | |
| "learning_rate": 7.171178177786646e-07, | |
| "loss": 1.2973, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 2.132671356201172, | |
| "learning_rate": 7.083014079300282e-07, | |
| "loss": 1.2931, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 2.243849277496338, | |
| "learning_rate": 6.995227476038316e-07, | |
| "loss": 1.2967, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 2.284914016723633, | |
| "learning_rate": 6.907822553813857e-07, | |
| "loss": 1.2925, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 1.2980060577392578, | |
| "eval_runtime": 1862.987, | |
| "eval_samples_per_second": 5.146, | |
| "eval_steps_per_second": 0.644, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 2.1762306690216064, | |
| "learning_rate": 6.820803480240832e-07, | |
| "loss": 1.3035, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 2.1974294185638428, | |
| "learning_rate": 6.734174404535233e-07, | |
| "loss": 1.2982, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 2.1154937744140625, | |
| "learning_rate": 6.647939457317332e-07, | |
| "loss": 1.2987, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 2.2262349128723145, | |
| "learning_rate": 6.562102750414655e-07, | |
| "loss": 1.2894, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 2.2507781982421875, | |
| "learning_rate": 6.476668376665978e-07, | |
| "loss": 1.3024, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 1.2977538108825684, | |
| "eval_runtime": 1863.5376, | |
| "eval_samples_per_second": 5.144, | |
| "eval_steps_per_second": 0.643, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 2.0441462993621826, | |
| "learning_rate": 6.391640409726157e-07, | |
| "loss": 1.2939, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 2.172423839569092, | |
| "learning_rate": 6.307022903871869e-07, | |
| "loss": 1.3002, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 1.932667851448059, | |
| "learning_rate": 6.222819893808335e-07, | |
| "loss": 1.292, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 2.173680305480957, | |
| "learning_rate": 6.139035394476905e-07, | |
| "loss": 1.3025, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 2.1886558532714844, | |
| "learning_rate": 6.055673400863636e-07, | |
| "loss": 1.3103, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 1.2976477146148682, | |
| "eval_runtime": 1862.7508, | |
| "eval_samples_per_second": 5.146, | |
| "eval_steps_per_second": 0.644, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 2.3404366970062256, | |
| "learning_rate": 5.972737887808805e-07, | |
| "loss": 1.2915, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 2.2503886222839355, | |
| "learning_rate": 5.890232809817378e-07, | |
| "loss": 1.2887, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 2.1247682571411133, | |
| "learning_rate": 5.808162100870441e-07, | |
| "loss": 1.297, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 2.1436526775360107, | |
| "learning_rate": 5.72652967423765e-07, | |
| "loss": 1.3008, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 2.1058590412139893, | |
| "learning_rate": 5.645339422290599e-07, | |
| "loss": 1.2956, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 1.2974357604980469, | |
| "eval_runtime": 1866.987, | |
| "eval_samples_per_second": 5.134, | |
| "eval_steps_per_second": 0.642, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 2.1536617279052734, | |
| "learning_rate": 5.564595216317266e-07, | |
| "loss": 1.299, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 2.031917095184326, | |
| "learning_rate": 5.484300906337403e-07, | |
| "loss": 1.2828, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 1.9297816753387451, | |
| "learning_rate": 5.404460320918966e-07, | |
| "loss": 1.2937, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 2.253413677215576, | |
| "learning_rate": 5.325077266995542e-07, | |
| "loss": 1.3078, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 2.250991106033325, | |
| "learning_rate": 5.24615552968487e-07, | |
| "loss": 1.2788, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 1.297324776649475, | |
| "eval_runtime": 1864.5246, | |
| "eval_samples_per_second": 5.141, | |
| "eval_steps_per_second": 0.643, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 2.186206579208374, | |
| "learning_rate": 5.167698872108312e-07, | |
| "loss": 1.3048, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 2.1334028244018555, | |
| "learning_rate": 5.089711035211465e-07, | |
| "loss": 1.279, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 2.334712266921997, | |
| "learning_rate": 5.012195737585756e-07, | |
| "loss": 1.2949, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 2.2277867794036865, | |
| "learning_rate": 4.935156675291152e-07, | |
| "loss": 1.2998, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 2.1463205814361572, | |
| "learning_rate": 4.858597521679899e-07, | |
| "loss": 1.2878, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.2971347570419312, | |
| "eval_runtime": 1865.0446, | |
| "eval_samples_per_second": 5.14, | |
| "eval_steps_per_second": 0.643, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 2.0899240970611572, | |
| "learning_rate": 4.782521927221414e-07, | |
| "loss": 1.2927, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 2.1801438331604004, | |
| "learning_rate": 4.70693351932817e-07, | |
| "loss": 1.2822, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 2.0565810203552246, | |
| "learning_rate": 4.631835902182795e-07, | |
| "loss": 1.2998, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 2.0865461826324463, | |
| "learning_rate": 4.55723265656616e-07, | |
| "loss": 1.2912, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 2.186192750930786, | |
| "learning_rate": 4.483127339686686e-07, | |
| "loss": 1.2893, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 1.297006368637085, | |
| "eval_runtime": 1864.1525, | |
| "eval_samples_per_second": 5.142, | |
| "eval_steps_per_second": 0.643, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 2.418661594390869, | |
| "learning_rate": 4.409523485010707e-07, | |
| "loss": 1.2823, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 2.213181972503662, | |
| "learning_rate": 4.3364246020940003e-07, | |
| "loss": 1.2921, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 2.1837573051452637, | |
| "learning_rate": 4.263834176414426e-07, | |
| "loss": 1.2834, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 2.2444188594818115, | |
| "learning_rate": 4.191755669205763e-07, | |
| "loss": 1.3072, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.1974008083343506, | |
| "learning_rate": 4.120192517292637e-07, | |
| "loss": 1.295, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.2968517541885376, | |
| "eval_runtime": 1863.4227, | |
| "eval_samples_per_second": 5.144, | |
| "eval_steps_per_second": 0.643, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.2060582637786865, | |
| "learning_rate": 4.0491481329266823e-07, | |
| "loss": 1.294, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 2.2055234909057617, | |
| "learning_rate": 3.978625903623813e-07, | |
| "loss": 1.301, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 2.3005611896514893, | |
| "learning_rate": 3.9086291920027183e-07, | |
| "loss": 1.2909, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 2.2892158031463623, | |
| "learning_rate": 3.839161335624504e-07, | |
| "loss": 1.2898, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 2.2120680809020996, | |
| "learning_rate": 3.7702256468335877e-07, | |
| "loss": 1.2937, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 1.2967385053634644, | |
| "eval_runtime": 1863.4438, | |
| "eval_samples_per_second": 5.144, | |
| "eval_steps_per_second": 0.643, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 2.06485652923584, | |
| "learning_rate": 3.7018254125997167e-07, | |
| "loss": 1.3034, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 2.2690818309783936, | |
| "learning_rate": 3.6339638943612876e-07, | |
| "loss": 1.2816, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 2.1384482383728027, | |
| "learning_rate": 3.566644327869784e-07, | |
| "loss": 1.2958, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 2.262807607650757, | |
| "learning_rate": 3.4998699230355445e-07, | |
| "loss": 1.2906, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 2.1555404663085938, | |
| "learning_rate": 3.4336438637746716e-07, | |
| "loss": 1.2911, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 1.2966289520263672, | |
| "eval_runtime": 1863.3587, | |
| "eval_samples_per_second": 5.144, | |
| "eval_steps_per_second": 0.643, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 2.088890552520752, | |
| "learning_rate": 3.3679693078572135e-07, | |
| "loss": 1.2905, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 2.362851142883301, | |
| "learning_rate": 3.302849386756631e-07, | |
| "loss": 1.2877, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 2.3154048919677734, | |
| "learning_rate": 3.2382872055004437e-07, | |
| "loss": 1.288, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 2.204124927520752, | |
| "learning_rate": 3.1742858425222153e-07, | |
| "loss": 1.2888, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 2.0219850540161133, | |
| "learning_rate": 3.1108483495147276e-07, | |
| "loss": 1.2962, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 1.2965224981307983, | |
| "eval_runtime": 1863.8916, | |
| "eval_samples_per_second": 5.143, | |
| "eval_steps_per_second": 0.643, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 2.456171989440918, | |
| "learning_rate": 3.0479777512845107e-07, | |
| "loss": 1.291, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 2.043088674545288, | |
| "learning_rate": 2.9856770456075904e-07, | |
| "loss": 1.2926, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.3121893405914307, | |
| "learning_rate": 2.9239492030865573e-07, | |
| "loss": 1.2933, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.117414712905884, | |
| "learning_rate": 2.862797167008913e-07, | |
| "loss": 1.2842, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.2130415439605713, | |
| "learning_rate": 2.802223853206752e-07, | |
| "loss": 1.2952, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.2964164018630981, | |
| "eval_runtime": 1863.5413, | |
| "eval_samples_per_second": 5.144, | |
| "eval_steps_per_second": 0.643, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 2.1747307777404785, | |
| "learning_rate": 2.7422321499177006e-07, | |
| "loss": 1.2953, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 2.238208293914795, | |
| "learning_rate": 2.6828249176472284e-07, | |
| "loss": 1.2901, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 2.170766830444336, | |
| "learning_rate": 2.624004989032238e-07, | |
| "loss": 1.3061, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 2.2250659465789795, | |
| "learning_rate": 2.565775168706008e-07, | |
| "loss": 1.3015, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 2.16519832611084, | |
| "learning_rate": 2.5081382331644484e-07, | |
| "loss": 1.3065, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 1.2963379621505737, | |
| "eval_runtime": 1863.6216, | |
| "eval_samples_per_second": 5.144, | |
| "eval_steps_per_second": 0.643, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 2.3075404167175293, | |
| "learning_rate": 2.451096930633741e-07, | |
| "loss": 1.2933, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 2.204376459121704, | |
| "learning_rate": 2.3946539809392637e-07, | |
| "loss": 1.2938, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 2.1348817348480225, | |
| "learning_rate": 2.33881207537594e-07, | |
| "loss": 1.2975, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 2.2030017375946045, | |
| "learning_rate": 2.283573876579882e-07, | |
| "loss": 1.2873, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 2.280266523361206, | |
| "learning_rate": 2.2289420184014636e-07, | |
| "loss": 1.2862, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 1.2962608337402344, | |
| "eval_runtime": 1864.1974, | |
| "eval_samples_per_second": 5.142, | |
| "eval_steps_per_second": 0.643, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 2.2561440467834473, | |
| "learning_rate": 2.1749191057796996e-07, | |
| "loss": 1.2926, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 2.064223289489746, | |
| "learning_rate": 2.1215077146180688e-07, | |
| "loss": 1.2911, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 2.0723884105682373, | |
| "learning_rate": 2.0687103916616612e-07, | |
| "loss": 1.2927, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 2.1863532066345215, | |
| "learning_rate": 2.0165296543757777e-07, | |
| "loss": 1.2958, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 2.242121458053589, | |
| "learning_rate": 1.9649679908258606e-07, | |
| "loss": 1.2856, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 1.2961931228637695, | |
| "eval_runtime": 1863.7107, | |
| "eval_samples_per_second": 5.144, | |
| "eval_steps_per_second": 0.643, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 2.2258660793304443, | |
| "learning_rate": 1.914027859558884e-07, | |
| "loss": 1.2895, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 2.194655418395996, | |
| "learning_rate": 1.8637116894861117e-07, | |
| "loss": 1.299, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 2.083817958831787, | |
| "learning_rate": 1.8140218797672898e-07, | |
| "loss": 1.2868, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 2.1037402153015137, | |
| "learning_rate": 1.7649607996962425e-07, | |
| "loss": 1.2833, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 2.3146462440490723, | |
| "learning_rate": 1.71653078858791e-07, | |
| "loss": 1.295, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 1.2961418628692627, | |
| "eval_runtime": 1863.9344, | |
| "eval_samples_per_second": 5.143, | |
| "eval_steps_per_second": 0.643, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 2.178917646408081, | |
| "learning_rate": 1.6687341556667956e-07, | |
| "loss": 1.2967, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 2.230252742767334, | |
| "learning_rate": 1.6215731799568707e-07, | |
| "loss": 1.2912, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 2.027996301651001, | |
| "learning_rate": 1.575050110172896e-07, | |
| "loss": 1.2931, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 2.343449831008911, | |
| "learning_rate": 1.5291671646132082e-07, | |
| "loss": 1.2896, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 2.1190574169158936, | |
| "learning_rate": 1.483926531053933e-07, | |
| "loss": 1.2926, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 1.2960731983184814, | |
| "eval_runtime": 1864.8274, | |
| "eval_samples_per_second": 5.14, | |
| "eval_steps_per_second": 0.643, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 2.0614373683929443, | |
| "learning_rate": 1.4393303666446873e-07, | |
| "loss": 1.2939, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 2.185314178466797, | |
| "learning_rate": 1.395380797805706e-07, | |
| "loss": 1.293, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 2.1229093074798584, | |
| "learning_rate": 1.3520799201264644e-07, | |
| "loss": 1.3041, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 2.213289976119995, | |
| "learning_rate": 1.3094297982657484e-07, | |
| "loss": 1.2956, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 2.1949591636657715, | |
| "learning_rate": 1.267432465853209e-07, | |
| "loss": 1.2928, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 1.2960156202316284, | |
| "eval_runtime": 1862.2042, | |
| "eval_samples_per_second": 5.148, | |
| "eval_steps_per_second": 0.644, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 2.0892333984375, | |
| "learning_rate": 1.2260899253924008e-07, | |
| "loss": 1.2991, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 2.1460952758789062, | |
| "learning_rate": 1.1854041481652849e-07, | |
| "loss": 1.2949, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 2.241546630859375, | |
| "learning_rate": 1.1453770741382607e-07, | |
| "loss": 1.2836, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 2.225529670715332, | |
| "learning_rate": 1.1060106118696345e-07, | |
| "loss": 1.2923, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 2.106523036956787, | |
| "learning_rate": 1.0673066384186425e-07, | |
| "loss": 1.2966, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 1.295967698097229, | |
| "eval_runtime": 1866.8915, | |
| "eval_samples_per_second": 5.135, | |
| "eval_steps_per_second": 0.642, | |
| "step": 40000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 45496, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1000, | |
| "total_flos": 1.403599875735552e+19, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |