{ "best_metric": 3.9751081466674805, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/passive/lstm/0/checkpoints/checkpoint-3052726", "epoch": 0.024976365386215466, "eval_steps": 10, "global_step": 3052726, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 10.8198, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 7.5522, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 7.0566, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.995, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 6.9475, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 6.9066, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 6.7464, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 6.6405, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993292879871958e-05, "loss": 6.5391, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992454285120906e-05, "loss": 6.457, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.991615690369854e-05, "loss": 6.4004, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990777095618801e-05, "loss": 6.3311, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 6.2652, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 6.1988, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 6.1445, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 6.0779, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 6.0424, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.9952, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.9566, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.9196, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.8897, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 5.8524, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 5.8257, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 5.785, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798786396158716e-05, "loss": 5.7734, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790400448648195e-05, "loss": 5.7366, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 5.7188, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 5.6818, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 5.6646, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 5.6459, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748470711095595e-05, "loss": 5.6213, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.974008476358507e-05, "loss": 5.6129, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 5.5862, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 5.5697, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714943299857244e-05, "loss": 5.5626, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.9706557352346724e-05, "loss": 5.5386, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.9698171404836204e-05, "loss": 5.5296, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968980183612942e-05, "loss": 5.4843, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 5.4893, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 5.4519, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 5.4571, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965625804608733e-05, "loss": 5.4336, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964787209857681e-05, "loss": 5.4322, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963948615106629e-05, "loss": 5.4024, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963110020355577e-05, "loss": 5.4078, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962273063484898e-05, "loss": 5.3962, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.961434468733847e-05, "loss": 5.3903, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960595873982795e-05, "loss": 5.3811, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959757279231743e-05, "loss": 5.3518, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958920322361064e-05, "loss": 5.3426, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958081727610012e-05, "loss": 5.3434, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.95724313285896e-05, "loss": 5.3293, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956404538107908e-05, "loss": 5.324, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 5.2998, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954728986486177e-05, "loss": 5.2981, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953890391735125e-05, "loss": 5.2777, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530517969840727e-05, "loss": 5.298, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 5.2524, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951376245362342e-05, "loss": 5.2679, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.95053765061129e-05, "loss": 5.2567, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949699055860238e-05, "loss": 5.2381, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 5.2352, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948023504238507e-05, "loss": 5.2224, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947184909487455e-05, "loss": 5.2119, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946346314736403e-05, "loss": 5.2041, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945507719985351e-05, "loss": 5.2186, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 5.1918, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.94383216836362e-05, "loss": 5.1825, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942993573612568e-05, "loss": 5.1742, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942154978861516e-05, "loss": 5.1712, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 5.1775, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404794272397856e-05, "loss": 5.1722, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396408324887336e-05, "loss": 5.148, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388022377376816e-05, "loss": 5.1631, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379636429866296e-05, "loss": 5.1554, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 5.1293, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 5.1272, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 5.1171, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 5.1092, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 5.1037, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 5.1087, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 5.1041, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 5.1052, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 5.0813, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 5.0642, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.928744014366177e-05, "loss": 5.0683, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927905419615125e-05, "loss": 5.0714, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927066824864073e-05, "loss": 5.0689, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.92622823011302e-05, "loss": 5.0524, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925389635361968e-05, "loss": 5.0499, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.92455267849129e-05, "loss": 5.0496, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923714083740238e-05, "loss": 5.0403, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922875488989185e-05, "loss": 5.0311, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922036894238133e-05, "loss": 5.0276, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921199937367455e-05, "loss": 5.0154, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920361342616403e-05, "loss": 5.0273, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919522747865351e-05, "loss": 5.0144, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918684153114299e-05, "loss": 4.9927, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917845558363247e-05, "loss": 4.997, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.9953, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 5.0038, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 4.9853, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.9823, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.9665, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.9707, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.9517, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111400761155765e-05, "loss": 4.9615, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910303119244898e-05, "loss": 4.95, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909464524493846e-05, "loss": 4.9536, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908625929742794e-05, "loss": 4.9399, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.9436, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.9305, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906110145489638e-05, "loss": 4.9334, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905271550738586e-05, "loss": 4.926, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904432955987534e-05, "loss": 4.9192, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.9306, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.9147, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901920447495124e-05, "loss": 4.9128, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901081852744072e-05, "loss": 4.9028, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.9081, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.9029, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.8958, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977274737398646e-05, "loss": 4.8996, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968888789888125e-05, "loss": 4.8859, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960502842377605e-05, "loss": 4.8855, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952116894867085e-05, "loss": 4.8663, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.8723, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.8737, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926975431139254e-05, "loss": 4.8637, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918589483628734e-05, "loss": 4.8563, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910203536118214e-05, "loss": 4.878, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.8603, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.8522, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.8518, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887667612487986e-05, "loss": 4.8461, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886829017736934e-05, "loss": 4.8473, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.8439, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885153466115204e-05, "loss": 4.8398, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884314871364151e-05, "loss": 4.8412, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883476276613099e-05, "loss": 4.8394, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882637681862047e-05, "loss": 4.8276, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.8178, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.8285, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.8157, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879284940738212e-05, "loss": 4.8194, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.81, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.8071, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876772432245803e-05, "loss": 4.8133, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875933837494751e-05, "loss": 4.7999, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.7967, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.765356540679932, "eval_runtime": 295.2513, "eval_samples_per_second": 1292.428, "eval_steps_per_second": 40.389, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.785, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.7835, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.8069, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717408637394906e-05, "loss": 4.7913, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709022689884386e-05, "loss": 4.7825, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700653121177595e-05, "loss": 4.7796, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692267173667075e-05, "loss": 4.7803, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.7619, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867549527864604e-05, "loss": 4.7708, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866710933113552e-05, "loss": 4.7703, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658723383625e-05, "loss": 4.7729, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865035381491821e-05, "loss": 4.7724, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864198424621142e-05, "loss": 4.754, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.86335982987009e-05, "loss": 4.7539, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862521235119038e-05, "loss": 4.7427, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861682640367986e-05, "loss": 4.7441, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860844045616934e-05, "loss": 4.7515, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860005450865882e-05, "loss": 4.7408, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859168493995203e-05, "loss": 4.7454, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858329899244151e-05, "loss": 4.7588, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574913044930995e-05, "loss": 4.7402, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.7456, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.7272, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549755202399435e-05, "loss": 4.746, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541385633692644e-05, "loss": 4.7239, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532999686182124e-05, "loss": 4.7276, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.7133, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.7231, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.8507841843650564e-05, "loss": 4.714, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.8499455896140044e-05, "loss": 4.7107, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.8491069948629524e-05, "loss": 4.7158, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.8482684001119e-05, "loss": 4.7195, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847431443241221e-05, "loss": 4.7115, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846592848490169e-05, "loss": 4.7133, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845754253739117e-05, "loss": 4.7049, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844915658988065e-05, "loss": 4.7127, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844078702117387e-05, "loss": 4.6846, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843240107366335e-05, "loss": 4.7, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842401512615282e-05, "loss": 4.6753, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.84156291786423e-05, "loss": 4.6969, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840724323113178e-05, "loss": 4.6798, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839885728362126e-05, "loss": 4.6931, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839048771491447e-05, "loss": 4.6707, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838210176740395e-05, "loss": 4.6883, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.8373732198697167e-05, "loss": 4.6851, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.8365346251186646e-05, "loss": 4.6823, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.8356960303676126e-05, "loss": 4.6896, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.8348574356165606e-05, "loss": 4.6592, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.8340188408655086e-05, "loss": 4.6627, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331802461144566e-05, "loss": 4.6764, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.8323416513634046e-05, "loss": 4.6683, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.8315030566123526e-05, "loss": 4.6661, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.8306644618613006e-05, "loss": 4.6588, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298258671102486e-05, "loss": 4.6525, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289872723591966e-05, "loss": 4.6464, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281486776081446e-05, "loss": 4.6638, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273117207374655e-05, "loss": 4.6391, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.826474763866787e-05, "loss": 4.6505, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825636169115735e-05, "loss": 4.6565, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.824797574364683e-05, "loss": 4.6378, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823958979613631e-05, "loss": 4.639, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823120384862579e-05, "loss": 4.6387, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822281790111527e-05, "loss": 4.6248, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821443195360475e-05, "loss": 4.6308, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820604600609423e-05, "loss": 4.6469, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819767643738744e-05, "loss": 4.6288, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818929048987692e-05, "loss": 4.6233, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.81809045423664e-05, "loss": 4.6215, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817253497365961e-05, "loss": 4.6225, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816414902614909e-05, "loss": 4.6368, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815576307863857e-05, "loss": 4.6287, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814737713112805e-05, "loss": 4.6186, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8138991183617535e-05, "loss": 4.6339, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813060523610701e-05, "loss": 4.6298, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812221928859649e-05, "loss": 4.6157, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.8113849719889704e-05, "loss": 4.6125, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.8105463772379184e-05, "loss": 4.6117, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809707782486866e-05, "loss": 4.6085, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808869187735814e-05, "loss": 4.6052, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808030592984762e-05, "loss": 4.6101, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.80719199823371e-05, "loss": 4.6155, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.8063550413630307e-05, "loss": 4.6164, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.8055164466119786e-05, "loss": 4.6042, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804677851860927e-05, "loss": 4.5821, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803839257109875e-05, "loss": 4.5978, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803000662358823e-05, "loss": 4.6017, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802162067607771e-05, "loss": 4.6037, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801323472856719e-05, "loss": 4.5955, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.80048651598604e-05, "loss": 4.5924, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799647921234988e-05, "loss": 4.5976, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798809326483936e-05, "loss": 4.5901, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797970731732884e-05, "loss": 4.5851, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797132136981832e-05, "loss": 4.5917, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.79629354223078e-05, "loss": 4.5754, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795454947479728e-05, "loss": 4.5956, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794616352728676e-05, "loss": 4.5863, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793777757977624e-05, "loss": 4.5659, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792940801106946e-05, "loss": 4.5785, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792103844236267e-05, "loss": 4.5765, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791265249485215e-05, "loss": 4.5881, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790426654734163e-05, "loss": 4.5757, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.7895880599831107e-05, "loss": 4.571, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887494652320587e-05, "loss": 4.5641, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879108704810067e-05, "loss": 4.573, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870722757299546e-05, "loss": 4.5551, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862353188592756e-05, "loss": 4.5646, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7853967241082236e-05, "loss": 4.5609, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845581293571715e-05, "loss": 4.5635, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837195346061195e-05, "loss": 4.5525, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828809398550675e-05, "loss": 4.5622, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820423451040155e-05, "loss": 4.5551, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812037503529635e-05, "loss": 4.5553, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803651556019115e-05, "loss": 4.5572, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795265608508595e-05, "loss": 4.5466, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786896039801804e-05, "loss": 4.5705, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.7778510092291284e-05, "loss": 4.5544, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.7770124144780764e-05, "loss": 4.5537, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761738197270244e-05, "loss": 4.5438, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.7753352249759724e-05, "loss": 4.5499, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774498268105293e-05, "loss": 4.5502, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773659673354241e-05, "loss": 4.5402, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772821078603189e-05, "loss": 4.5556, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771982483852137e-05, "loss": 4.5424, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771145526981459e-05, "loss": 4.5371, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770306932230407e-05, "loss": 4.5334, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769468337479355e-05, "loss": 4.5353, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768629742728303e-05, "loss": 4.5338, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767792785857624e-05, "loss": 4.5353, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766955828986945e-05, "loss": 4.5217, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766117234235893e-05, "loss": 4.5502, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765278639484841e-05, "loss": 4.5402, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764440044733789e-05, "loss": 4.5306, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763601449982737e-05, "loss": 4.5287, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762762855231685e-05, "loss": 4.5234, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761924260480633e-05, "loss": 4.5343, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610856657295813e-05, "loss": 4.5312, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602470709785293e-05, "loss": 4.5271, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.75941011410785e-05, "loss": 4.532, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758571519356798e-05, "loss": 4.528, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757732924605746e-05, "loss": 4.5252, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.756894329854694e-05, "loss": 4.5177, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756055735103642e-05, "loss": 4.5303, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755218778232963e-05, "loss": 4.5181, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.754380183481911e-05, "loss": 4.5205, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753541588730859e-05, "loss": 4.5149, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752702993979807e-05, "loss": 4.5163, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751864399228755e-05, "loss": 4.5176, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751025804477703e-05, "loss": 4.5059, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750188847607025e-05, "loss": 4.5105, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.484802722930908, "eval_runtime": 296.4897, "eval_samples_per_second": 1287.029, "eval_steps_per_second": 40.221, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749350252855973e-05, "loss": 4.4981, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748511658104921e-05, "loss": 4.4961, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747673063353868e-05, "loss": 4.5236, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746834468602816e-05, "loss": 4.5142, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.745995873851764e-05, "loss": 4.5038, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745157279100712e-05, "loss": 4.5012, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.74431868434966e-05, "loss": 4.506, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743480089598608e-05, "loss": 4.4896, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742641494847556e-05, "loss": 4.5071, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741802900096504e-05, "loss": 4.5003, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740964305345452e-05, "loss": 4.5039, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401273484747736e-05, "loss": 4.5054, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.7392887537237216e-05, "loss": 4.4864, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.7384501589726696e-05, "loss": 4.4917, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.7376115642216176e-05, "loss": 4.4858, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.7367729694705656e-05, "loss": 4.4861, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.7359343747195135e-05, "loss": 4.4895, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.7350974178488345e-05, "loss": 4.482, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.7342588230977825e-05, "loss": 4.4888, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.7334202283467305e-05, "loss": 4.5077, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.7325816335956784e-05, "loss": 4.4862, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.7317430388446264e-05, "loss": 4.4911, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730904444093574e-05, "loss": 4.4839, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730065849342522e-05, "loss": 4.4964, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.7292272545914704e-05, "loss": 4.4743, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.7283886598404184e-05, "loss": 4.487, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.7275500650893664e-05, "loss": 4.4695, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.7267114703383144e-05, "loss": 4.4742, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258728755872624e-05, "loss": 4.4732, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250342808362104e-05, "loss": 4.4694, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7241956860851584e-05, "loss": 4.4769, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233570913341064e-05, "loss": 4.4819, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225184965830544e-05, "loss": 4.4747, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721681539712375e-05, "loss": 4.4808, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720844582841696e-05, "loss": 4.4664, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720005988090644e-05, "loss": 4.4834, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719169031219965e-05, "loss": 4.4518, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718330436468914e-05, "loss": 4.4728, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717491841717862e-05, "loss": 4.4466, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.71665324696681e-05, "loss": 4.4688, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715814652215758e-05, "loss": 4.4563, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714976057464706e-05, "loss": 4.4698, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714137462713654e-05, "loss": 4.4504, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713298867962602e-05, "loss": 4.4623, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.71246027321155e-05, "loss": 4.4651, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711623316340871e-05, "loss": 4.4636, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710784721589819e-05, "loss": 4.4675, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099461268387667e-05, "loss": 4.4449, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091075320877147e-05, "loss": 4.4427, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082705752170356e-05, "loss": 4.4636, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074319804659836e-05, "loss": 4.4548, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706593385714932e-05, "loss": 4.4496, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.70575479096388e-05, "loss": 4.4486, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704916196212828e-05, "loss": 4.4431, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704079239342149e-05, "loss": 4.4343, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703240644591097e-05, "loss": 4.4506, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702402049840045e-05, "loss": 4.4322, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015634550889924e-05, "loss": 4.4423, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007248603379404e-05, "loss": 4.4528, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998862655868884e-05, "loss": 4.4318, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.69904930871621e-05, "loss": 4.4342, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982107139651573e-05, "loss": 4.438, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697372119214106e-05, "loss": 4.4226, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696533524463054e-05, "loss": 4.4251, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695694929712002e-05, "loss": 4.4461, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.69485633496095e-05, "loss": 4.4319, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694019378090271e-05, "loss": 4.4243, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693180783339219e-05, "loss": 4.4247, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692342188588167e-05, "loss": 4.4279, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691503593837115e-05, "loss": 4.4411, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690664999086063e-05, "loss": 4.4358, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689828042215384e-05, "loss": 4.424, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.688989447464332e-05, "loss": 4.4405, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.68815085271328e-05, "loss": 4.4339, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687312257962228e-05, "loss": 4.4245, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686473663211176e-05, "loss": 4.4208, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856367063404974e-05, "loss": 4.4274, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6847981115894454e-05, "loss": 4.4217, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683961154718766e-05, "loss": 4.4193, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683122559967714e-05, "loss": 4.4202, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682283965216662e-05, "loss": 4.4273, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.68144537046561e-05, "loss": 4.4322, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680606775714558e-05, "loss": 4.418, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679768180963506e-05, "loss": 4.4032, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678929586212454e-05, "loss": 4.4109, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678090991461402e-05, "loss": 4.4159, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.67725239671035e-05, "loss": 4.423, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676415439839671e-05, "loss": 4.4125, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675576845088619e-05, "loss": 4.4107, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674738250337568e-05, "loss": 4.4209, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673899655586516e-05, "loss": 4.407, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673062698715837e-05, "loss": 4.4078, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722257418451576e-05, "loss": 4.412, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6713871470941056e-05, "loss": 4.4042, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.6705485523430536e-05, "loss": 4.4219, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697099575920016e-05, "loss": 4.4067, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688713628409496e-05, "loss": 4.3949, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.6680327680898976e-05, "loss": 4.4056, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6671958112192185e-05, "loss": 4.4026, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663572164681665e-05, "loss": 4.4202, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655186217171145e-05, "loss": 4.4087, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664680026966063e-05, "loss": 4.3994, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663841432215011e-05, "loss": 4.3899, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663002837463959e-05, "loss": 4.404, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621642427129065e-05, "loss": 4.3874, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.6613256479618545e-05, "loss": 4.3986, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6604870532108025e-05, "loss": 4.3942, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596484584597505e-05, "loss": 4.3958, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588115015890714e-05, "loss": 4.3849, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579729068380194e-05, "loss": 4.4033, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571343120869674e-05, "loss": 4.3877, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6562957173359154e-05, "loss": 4.3884, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554571225848634e-05, "loss": 4.3971, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654620165714185e-05, "loss": 4.3843, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653781570963133e-05, "loss": 4.4062, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652944614092454e-05, "loss": 4.3935, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652106019341402e-05, "loss": 4.3938, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.65126742459035e-05, "loss": 4.3856, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650428829839298e-05, "loss": 4.3896, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649590235088246e-05, "loss": 4.3915, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648753278217567e-05, "loss": 4.3804, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647914683466515e-05, "loss": 4.3956, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647076088715463e-05, "loss": 4.3881, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646237493964411e-05, "loss": 4.3805, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645398899213359e-05, "loss": 4.3823, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644560304462307e-05, "loss": 4.3803, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437217097112554e-05, "loss": 4.3731, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642884752840576e-05, "loss": 4.3875, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642046158089524e-05, "loss": 4.371, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641207563338472e-05, "loss": 4.3925, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.64036896858742e-05, "loss": 4.3894, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639530373836368e-05, "loss": 4.3771, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638691779085316e-05, "loss": 4.3755, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637853184334264e-05, "loss": 4.3741, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637014589583212e-05, "loss": 4.3834, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6361759948321596e-05, "loss": 4.3815, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635339037961481e-05, "loss": 4.3775, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634502081090802e-05, "loss": 4.3807, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633663486339751e-05, "loss": 4.3795, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632824891588699e-05, "loss": 4.3808, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.631986296837647e-05, "loss": 4.3689, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631147702086595e-05, "loss": 4.387, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630309107335542e-05, "loss": 4.3739, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.62947051258449e-05, "loss": 4.3712, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628633555713812e-05, "loss": 4.3726, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6277949609627597e-05, "loss": 4.3748, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626956366211707e-05, "loss": 4.3699, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626117771460655e-05, "loss": 4.3608, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625279176709603e-05, "loss": 4.364, "step": 228864 }, { "epoch": 0.03, "eval_loss": 4.348752975463867, "eval_runtime": 286.9409, "eval_samples_per_second": 1329.859, "eval_steps_per_second": 41.559, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.6244422198389246e-05, "loss": 4.366, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.6236036250878726e-05, "loss": 4.3528, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622766668217194e-05, "loss": 4.3814, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621928073466142e-05, "loss": 4.3731, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.6210894787150895e-05, "loss": 4.3682, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.6202508839640374e-05, "loss": 4.357, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.6194122892129854e-05, "loss": 4.3695, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.6185736944619334e-05, "loss": 4.3493, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.6177350997108814e-05, "loss": 4.3695, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6168965049598294e-05, "loss": 4.3651, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.61605954808915e-05, "loss": 4.3624, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615220953338098e-05, "loss": 4.3725, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614382358587046e-05, "loss": 4.349, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613543763835994e-05, "loss": 4.3587, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612705169084942e-05, "loss": 4.3471, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611866574333891e-05, "loss": 4.3542, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611027979582839e-05, "loss": 4.3514, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610189384831787e-05, "loss": 4.3499, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609350790080735e-05, "loss": 4.3532, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608512195329683e-05, "loss": 4.3726, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607673600578631e-05, "loss": 4.3523, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606835005827578e-05, "loss": 4.3582, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.605999686837273e-05, "loss": 4.3521, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605161092086221e-05, "loss": 4.3643, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604322497335169e-05, "loss": 4.344, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603483902584117e-05, "loss": 4.3524, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602645307833065e-05, "loss": 4.3407, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601806713082013e-05, "loss": 4.3423, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600968118330961e-05, "loss": 4.3412, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600129523579909e-05, "loss": 4.3459, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599290928828857e-05, "loss": 4.3437, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598452334077805e-05, "loss": 4.3541, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597613739326753e-05, "loss": 4.3464, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596775144575701e-05, "loss": 4.3502, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595939825585395e-05, "loss": 4.3434, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595101230834343e-05, "loss": 4.3531, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.5942626360832906e-05, "loss": 4.3323, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593425679212612e-05, "loss": 4.3451, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.59258708446156e-05, "loss": 4.3213, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591748489710508e-05, "loss": 4.3408, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590909894959456e-05, "loss": 4.3355, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590071300208404e-05, "loss": 4.3473, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589232705457352e-05, "loss": 4.3288, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5883941107063e-05, "loss": 4.3392, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587555515955248e-05, "loss": 4.3421, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586718559084569e-05, "loss": 4.3452, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585879964333517e-05, "loss": 4.3392, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585041369582465e-05, "loss": 4.3278, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584202774831413e-05, "loss": 4.319, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583364180080361e-05, "loss": 4.3424, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582527223209682e-05, "loss": 4.337, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.58168862845863e-05, "loss": 4.3304, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.5808516715879515e-05, "loss": 4.327, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.5800130768368995e-05, "loss": 4.3281, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.5791744820858475e-05, "loss": 4.3115, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.5783375252151684e-05, "loss": 4.3353, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.5774989304641164e-05, "loss": 4.3112, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.5766603357130644e-05, "loss": 4.3256, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.5758217409620124e-05, "loss": 4.3326, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.5749831462109604e-05, "loss": 4.3201, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741445514599084e-05, "loss": 4.3135, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733059567088564e-05, "loss": 4.3226, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.5724673619578044e-05, "loss": 4.3064, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716287672067524e-05, "loss": 4.314, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570791810336074e-05, "loss": 4.3265, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569953215585022e-05, "loss": 4.318, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.56911462083397e-05, "loss": 4.3102, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568276026082918e-05, "loss": 4.306, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567437431331866e-05, "loss": 4.3142, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566598836580814e-05, "loss": 4.3224, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565760241829762e-05, "loss": 4.3221, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564921647078709e-05, "loss": 4.315, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564084690208031e-05, "loss": 4.3246, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563246095456979e-05, "loss": 4.3248, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562407500705927e-05, "loss": 4.3102, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561568905954874e-05, "loss": 4.309, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560730311203822e-05, "loss": 4.3175, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559891716452771e-05, "loss": 4.3128, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559053121701719e-05, "loss": 4.311, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558214526950667e-05, "loss": 4.3075, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557377570079988e-05, "loss": 4.315, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556538975328936e-05, "loss": 4.321, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555700380577884e-05, "loss": 4.3115, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554861785826832e-05, "loss": 4.2955, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.5540248289561526e-05, "loss": 4.2983, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.5531862342051006e-05, "loss": 4.3058, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.5523476394540486e-05, "loss": 4.3146, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.5515090447029966e-05, "loss": 4.3093, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.5506720878323175e-05, "loss": 4.2987, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498334930812655e-05, "loss": 4.3116, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.548996536210587e-05, "loss": 4.3041, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548157941459535e-05, "loss": 4.3001, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547319346708483e-05, "loss": 4.3022, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546480751957431e-05, "loss": 4.3061, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545642157206379e-05, "loss": 4.3153, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544803562455327e-05, "loss": 4.2963, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543964967704275e-05, "loss": 4.2864, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543126372953223e-05, "loss": 4.3042, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542287778202171e-05, "loss": 4.2981, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541450821331492e-05, "loss": 4.3129, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.54061222658044e-05, "loss": 4.3055, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539773631829388e-05, "loss": 4.2937, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538935037078336e-05, "loss": 4.2878, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538096442327284e-05, "loss": 4.3039, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.5372594854566055e-05, "loss": 4.2841, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.5364208907055535e-05, "loss": 4.2963, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.5355822959545015e-05, "loss": 4.2889, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.5347437012034495e-05, "loss": 4.2973, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.5339051064523975e-05, "loss": 4.2819, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.5330665117013455e-05, "loss": 4.3016, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.5322295548306664e-05, "loss": 4.2872, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.5313909600796144e-05, "loss": 4.2846, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.5305523653285624e-05, "loss": 4.2996, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.5297137705775104e-05, "loss": 4.2831, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528875175826458e-05, "loss": 4.309, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528038218955779e-05, "loss": 4.2958, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527201262085101e-05, "loss": 4.2937, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526362667334049e-05, "loss": 4.2863, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525524072582997e-05, "loss": 4.2901, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524685477831945e-05, "loss": 4.2905, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523846883080893e-05, "loss": 4.2849, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.52300828832984e-05, "loss": 4.295, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522169693578788e-05, "loss": 4.2888, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521331098827736e-05, "loss": 4.2837, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520494141957057e-05, "loss": 4.2852, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519655547206005e-05, "loss": 4.2854, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518816952454953e-05, "loss": 4.2779, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517978357703902e-05, "loss": 4.293, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517141400833223e-05, "loss": 4.2739, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516302806082171e-05, "loss": 4.293, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515465849211492e-05, "loss": 4.2889, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.51462725446044e-05, "loss": 4.2874, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.5137886597093876e-05, "loss": 4.278, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.5129500649583356e-05, "loss": 4.2803, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.5121114702072836e-05, "loss": 4.2898, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.5112728754562316e-05, "loss": 4.2893, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.5104342807051795e-05, "loss": 4.2788, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5095956859541275e-05, "loss": 4.286, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087570912030755e-05, "loss": 4.2844, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079184964520235e-05, "loss": 4.2908, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.5070799017009715e-05, "loss": 4.2756, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062413069499195e-05, "loss": 4.2918, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505402712198868e-05, "loss": 4.2837, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504565755328189e-05, "loss": 4.2786, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503727160577137e-05, "loss": 4.2777, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502888565826085e-05, "loss": 4.2852, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502049971075033e-05, "loss": 4.2756, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501211376323981e-05, "loss": 4.2644, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500374419453302e-05, "loss": 4.2808, "step": 305152 }, { "epoch": 1.03, "eval_loss": 4.265576362609863, "eval_runtime": 284.2057, "eval_samples_per_second": 1342.658, "eval_steps_per_second": 41.959, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.49953582470225e-05, "loss": 4.2686, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498697229951198e-05, "loss": 4.2613, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497858635200146e-05, "loss": 4.2868, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497020040449093e-05, "loss": 4.2825, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.496181445698042e-05, "loss": 4.2788, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.49534285094699e-05, "loss": 4.2714, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.494504256195938e-05, "loss": 4.2755, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493665661444886e-05, "loss": 4.2564, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492827066693834e-05, "loss": 4.2801, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.491988471942782e-05, "loss": 4.2775, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.49114987719173e-05, "loss": 4.2703, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.490311282440678e-05, "loss": 4.2825, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.489474325569999e-05, "loss": 4.2615, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.488635730818947e-05, "loss": 4.2711, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.487797136067895e-05, "loss": 4.2626, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.486958541316843e-05, "loss": 4.2605, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.486119946565791e-05, "loss": 4.2641, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485281351814739e-05, "loss": 4.2616, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.484442757063687e-05, "loss": 4.2669, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.483604162312635e-05, "loss": 4.2819, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.4827672054419564e-05, "loss": 4.2703, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.4819286106909044e-05, "loss": 4.2753, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.4810900159398524e-05, "loss": 4.2647, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.4802514211888004e-05, "loss": 4.2747, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479412826437748e-05, "loss": 4.26, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478575869567069e-05, "loss": 4.2663, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477737274816017e-05, "loss": 4.2586, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476898680064965e-05, "loss": 4.2541, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.4760600853139126e-05, "loss": 4.2539, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.4752214905628606e-05, "loss": 4.261, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474384533692182e-05, "loss": 4.2595, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.47354593894113e-05, "loss": 4.2697, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472707344190078e-05, "loss": 4.2638, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471868749439026e-05, "loss": 4.2664, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.471031792568348e-05, "loss": 4.2563, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470193197817295e-05, "loss": 4.2709, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469354603066243e-05, "loss": 4.252, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.468516008315191e-05, "loss": 4.2576, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.467677413564139e-05, "loss": 4.2414, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.466838818813087e-05, "loss": 4.2553, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.466000224062035e-05, "loss": 4.2538, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.465161629310983e-05, "loss": 4.2635, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464324672440304e-05, "loss": 4.2469, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.4634860776892526e-05, "loss": 4.2577, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.4626474829382006e-05, "loss": 4.2597, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.4618088881871486e-05, "loss": 4.262, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.4609702934360966e-05, "loss": 4.2588, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.4601333365654175e-05, "loss": 4.2439, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.4592947418143655e-05, "loss": 4.2358, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.4584577849436864e-05, "loss": 4.2622, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.4576191901926344e-05, "loss": 4.2546, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.4567805954415824e-05, "loss": 4.2488, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.4559420006905304e-05, "loss": 4.2493, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.4551034059394784e-05, "loss": 4.2469, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4542648111884264e-05, "loss": 4.2312, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.4534262164373744e-05, "loss": 4.2499, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.4525876216863224e-05, "loss": 4.2348, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.4517490269352704e-05, "loss": 4.2431, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450912070064592e-05, "loss": 4.2552, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.45007347531354e-05, "loss": 4.2395, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.449234880562488e-05, "loss": 4.2344, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.448397923691809e-05, "loss": 4.2484, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.447559328940757e-05, "loss": 4.2262, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446720734189705e-05, "loss": 4.2383, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445882139438653e-05, "loss": 4.2451, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445043544687601e-05, "loss": 4.2433, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444204949936548e-05, "loss": 4.2332, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443366355185496e-05, "loss": 4.2317, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442527760434444e-05, "loss": 4.2337, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441689165683393e-05, "loss": 4.2447, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.440850570932341e-05, "loss": 4.2441, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440013614061662e-05, "loss": 4.2392, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.43917501931061e-05, "loss": 4.2473, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438336424559558e-05, "loss": 4.2494, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437497829808506e-05, "loss": 4.2365, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436659235057454e-05, "loss": 4.2291, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435820640306402e-05, "loss": 4.2465, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.4349836834357227e-05, "loss": 4.2391, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.4341450886846707e-05, "loss": 4.2317, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.4333064939336186e-05, "loss": 4.2336, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.4324678991825666e-05, "loss": 4.2407, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.4316293044315146e-05, "loss": 4.248, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.4307907096804626e-05, "loss": 4.2341, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.429952114929411e-05, "loss": 4.2216, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.429115158058732e-05, "loss": 4.2305, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.42827656330768e-05, "loss": 4.2251, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427437968556628e-05, "loss": 4.2401, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426599373805576e-05, "loss": 4.2359, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.425760779054524e-05, "loss": 4.2232, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.424923822183845e-05, "loss": 4.239, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424085227432793e-05, "loss": 4.2286, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423246632681741e-05, "loss": 4.2319, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422408037930689e-05, "loss": 4.2252, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421569443179637e-05, "loss": 4.2309, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420730848428585e-05, "loss": 4.2442, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419892253677533e-05, "loss": 4.229, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.4190569346872276e-05, "loss": 4.2115, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.4182183399361756e-05, "loss": 4.2284, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.4173797451851236e-05, "loss": 4.228, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.4165411504340716e-05, "loss": 4.2352, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.4157025556830196e-05, "loss": 4.2376, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.4148639609319676e-05, "loss": 4.2229, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.414025366180915e-05, "loss": 4.2179, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.413186771429863e-05, "loss": 4.2312, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123498145591845e-05, "loss": 4.2083, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.411511219808132e-05, "loss": 4.2252, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.4106726250570805e-05, "loss": 4.2173, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.4098340303060284e-05, "loss": 4.2269, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.4089954355549764e-05, "loss": 4.2133, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.4081584786842974e-05, "loss": 4.2298, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.407321521813619e-05, "loss": 4.2157, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406482927062567e-05, "loss": 4.2143, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.405644332311514e-05, "loss": 4.2289, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404805737560462e-05, "loss": 4.2173, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.40396714280941e-05, "loss": 4.2373, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403128548058358e-05, "loss": 4.2256, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402291591187679e-05, "loss": 4.2195, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401452996436627e-05, "loss": 4.2261, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400614401685576e-05, "loss": 4.2136, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399775806934524e-05, "loss": 4.223, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398938850063845e-05, "loss": 4.216, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.398100255312793e-05, "loss": 4.2279, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.397261660561741e-05, "loss": 4.2168, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396423065810689e-05, "loss": 4.2133, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.395584471059637e-05, "loss": 4.2162, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394745876308585e-05, "loss": 4.2193, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393907281557533e-05, "loss": 4.2096, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393068686806481e-05, "loss": 4.2229, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392230092055429e-05, "loss": 4.2092, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.3913931351847496e-05, "loss": 4.2254, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905545404336976e-05, "loss": 4.2192, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.3897159456826456e-05, "loss": 4.2202, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.3888773509315936e-05, "loss": 4.2113, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388040394060915e-05, "loss": 4.2122, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.387201799309863e-05, "loss": 4.2254, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386364842439184e-05, "loss": 4.2173, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385526247688132e-05, "loss": 4.2123, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.38468765293708e-05, "loss": 4.2219, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383849058186028e-05, "loss": 4.2171, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383010463434976e-05, "loss": 4.2248, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382173506564297e-05, "loss": 4.2127, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381334911813245e-05, "loss": 4.2229, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380496317062193e-05, "loss": 4.2153, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379657722311141e-05, "loss": 4.2126, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378819127560089e-05, "loss": 4.2145, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.3779805328090376e-05, "loss": 4.2153, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.3771419380579856e-05, "loss": 4.2131, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.3763033433069336e-05, "loss": 4.2008, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.375464748555881e-05, "loss": 4.2147, "step": 381440 }, { "epoch": 0.03, "eval_loss": 4.208554267883301, "eval_runtime": 299.6848, "eval_samples_per_second": 1273.308, "eval_steps_per_second": 39.792, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.374626153804829e-05, "loss": 4.2084, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.373787559053777e-05, "loss": 4.1978, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.372948964302725e-05, "loss": 4.22, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.372112007432046e-05, "loss": 4.22, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.371273412680994e-05, "loss": 4.2119, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.370434817929942e-05, "loss": 4.2075, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.36959622317889e-05, "loss": 4.2095, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.368757628427838e-05, "loss": 4.1966, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.367919033676786e-05, "loss": 4.2111, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.3670820768061074e-05, "loss": 4.2163, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.3662434820550554e-05, "loss": 4.2065, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365406525184376e-05, "loss": 4.2147, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364567930433324e-05, "loss": 4.1994, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363729335682272e-05, "loss": 4.2089, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.36289074093122e-05, "loss": 4.1973, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362052146180168e-05, "loss": 4.1983, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.361213551429116e-05, "loss": 4.1998, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.360374956678064e-05, "loss": 4.1997, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359536361927012e-05, "loss": 4.205, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.358699405056333e-05, "loss": 4.2149, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.357860810305281e-05, "loss": 4.2128, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.35702221555423e-05, "loss": 4.2126, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.356183620803178e-05, "loss": 4.2013, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.355345026052126e-05, "loss": 4.2152, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.354506431301074e-05, "loss": 4.1951, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.353667836550022e-05, "loss": 4.2078, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352829241798969e-05, "loss": 4.1973, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.351990647047917e-05, "loss": 4.1897, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351153690177239e-05, "loss": 4.1963, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.3503167333065596e-05, "loss": 4.1975, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.3494781385555076e-05, "loss": 4.2015, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.3486395438044556e-05, "loss": 4.2058, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.3478009490534036e-05, "loss": 4.2071, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.3469623543023516e-05, "loss": 4.2053, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.346125397431673e-05, "loss": 4.1949, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.345286802680621e-05, "loss": 4.2069, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.344448207929569e-05, "loss": 4.1948, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.3436096131785165e-05, "loss": 4.1915, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.3427710184274645e-05, "loss": 4.1868, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.3419324236764125e-05, "loss": 4.1923, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.3410938289253605e-05, "loss": 4.1977, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.3402552341743085e-05, "loss": 4.2024, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.3394182773036294e-05, "loss": 4.1899, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.3385796825525774e-05, "loss": 4.1967, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.3377410878015254e-05, "loss": 4.2019, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.3369024930504734e-05, "loss": 4.2004, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.3360638982994214e-05, "loss": 4.2021, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.335226941428743e-05, "loss": 4.1864, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.334388346677691e-05, "loss": 4.1742, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333551389807012e-05, "loss": 4.2047, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.33271279505596e-05, "loss": 4.196, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.331874200304908e-05, "loss": 4.1941, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331035605553856e-05, "loss": 4.1921, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.330197010802804e-05, "loss": 4.1828, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329358416051752e-05, "loss": 4.176, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.328521459181073e-05, "loss": 4.188, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.327684502310394e-05, "loss": 4.1776, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.3268459075593424e-05, "loss": 4.1862, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.3260073128082904e-05, "loss": 4.1972, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.3251687180572383e-05, "loss": 4.182, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.3243301233061863e-05, "loss": 4.1755, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.323491528555134e-05, "loss": 4.1911, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.322654571684455e-05, "loss": 4.1713, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.321815976933403e-05, "loss": 4.178, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.320977382182351e-05, "loss": 4.1891, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320138787431299e-05, "loss": 4.1864, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319300192680247e-05, "loss": 4.1772, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.318463235809568e-05, "loss": 4.1774, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317624641058516e-05, "loss": 4.1746, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.316786046307464e-05, "loss": 4.185, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.315947451556412e-05, "loss": 4.1906, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.315108856805361e-05, "loss": 4.18, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314270262054309e-05, "loss": 4.1883, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313431667303257e-05, "loss": 4.1934, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.312593072552205e-05, "loss": 4.1876, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.311754477801153e-05, "loss": 4.1702, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.3109158830501e-05, "loss": 4.188, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310077288299048e-05, "loss": 4.1867, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.30924033142837e-05, "loss": 4.1714, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.308401736677318e-05, "loss": 4.1835, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.3075647798066386e-05, "loss": 4.1798, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.3067261850555866e-05, "loss": 4.1925, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.3058875903045346e-05, "loss": 4.1805, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.3050489955534826e-05, "loss": 4.1607, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.3042104008024306e-05, "loss": 4.1785, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.3033718060513786e-05, "loss": 4.1714, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.3025332113003266e-05, "loss": 4.1816, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.3016946165492746e-05, "loss": 4.1795, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.3008560217982226e-05, "loss": 4.1717, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.3000174270471705e-05, "loss": 4.1788, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.2991804701764915e-05, "loss": 4.1784, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.2983418754254395e-05, "loss": 4.1699, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.2975032806743874e-05, "loss": 4.1764, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.2966646859233354e-05, "loss": 4.1805, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.2958260911722834e-05, "loss": 4.1882, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.2949874964212314e-05, "loss": 4.175, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294150539550553e-05, "loss": 4.1616, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293311944799501e-05, "loss": 4.1736, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292473350048449e-05, "loss": 4.1742, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.291634755297397e-05, "loss": 4.1843, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290797798426718e-05, "loss": 4.1837, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.289959203675666e-05, "loss": 4.1643, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289120608924614e-05, "loss": 4.1665, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.288282014173562e-05, "loss": 4.1805, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.28744341942251e-05, "loss": 4.1551, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.286606462551831e-05, "loss": 4.1731, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.285767867800779e-05, "loss": 4.1598, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284929273049727e-05, "loss": 4.1748, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.284090678298675e-05, "loss": 4.1611, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.283252083547623e-05, "loss": 4.1747, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.282413488796571e-05, "loss": 4.1682, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.2815765319258924e-05, "loss": 4.1583, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.2807379371748404e-05, "loss": 4.1774, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.2798993424237884e-05, "loss": 4.1622, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.2790607476727364e-05, "loss": 4.1849, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.278222152921684e-05, "loss": 4.1779, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.277385196051005e-05, "loss": 4.1654, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.276546601299953e-05, "loss": 4.1767, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.275708006548901e-05, "loss": 4.1612, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.2748694117978486e-05, "loss": 4.1697, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.2740308170467966e-05, "loss": 4.1671, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.273193860176118e-05, "loss": 4.175, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.272355265425066e-05, "loss": 4.1666, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.271516670674014e-05, "loss": 4.1616, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.270678075922962e-05, "loss": 4.1684, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.26983948117191e-05, "loss": 4.1671, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.269000886420858e-05, "loss": 4.1573, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.268163929550179e-05, "loss": 4.1715, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.267325334799127e-05, "loss": 4.1561, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.266486740048075e-05, "loss": 4.1811, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.265648145297023e-05, "loss": 4.1627, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264809550545971e-05, "loss": 4.1719, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.263972593675292e-05, "loss": 4.1592, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.26313399892424e-05, "loss": 4.1656, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.2622954041731886e-05, "loss": 4.174, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.2614568094221366e-05, "loss": 4.165, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.2606182146710846e-05, "loss": 4.1625, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.2597796199200326e-05, "loss": 4.1734, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.2589426630493535e-05, "loss": 4.168, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.2581040682983015e-05, "loss": 4.1733, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.2572654735472495e-05, "loss": 4.1591, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.2564268787961975e-05, "loss": 4.1729, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.2555882840451455e-05, "loss": 4.1651, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.2547496892940935e-05, "loss": 4.1642, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.253914370303787e-05, "loss": 4.1654, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.253075775552735e-05, "loss": 4.1648, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.252237180801684e-05, "loss": 4.1705, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.251398586050632e-05, "loss": 4.144, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.25055999129958e-05, "loss": 4.1698, "step": 457728 }, { "epoch": 1.03, "eval_loss": 4.167238235473633, "eval_runtime": 299.0901, "eval_samples_per_second": 1275.84, "eval_steps_per_second": 39.871, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.249721396548528e-05, "loss": 4.1583, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.248882801797476e-05, "loss": 4.1501, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.248044207046424e-05, "loss": 4.1675, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.247205612295372e-05, "loss": 4.1729, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.24636701754432e-05, "loss": 4.1636, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.245528422793267e-05, "loss": 4.1567, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.244689828042215e-05, "loss": 4.1611, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.243851233291163e-05, "loss": 4.1507, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.243012638540111e-05, "loss": 4.1634, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.242174043789059e-05, "loss": 4.1648, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241335449038007e-05, "loss": 4.1639, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.240496854286955e-05, "loss": 4.1652, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.239659897416277e-05, "loss": 4.1566, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.238821302665225e-05, "loss": 4.1577, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.237982707914173e-05, "loss": 4.1509, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.237144113163121e-05, "loss": 4.145, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.236305518412069e-05, "loss": 4.1554, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.235466923661017e-05, "loss": 4.1498, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234628328909965e-05, "loss": 4.1573, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.233789734158913e-05, "loss": 4.1668, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.232951139407861e-05, "loss": 4.1684, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.232112544656809e-05, "loss": 4.1627, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.231273949905756e-05, "loss": 4.1549, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.230436993035078e-05, "loss": 4.1659, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.229598398284026e-05, "loss": 4.1489, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.228759803532974e-05, "loss": 4.1633, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.227921208781922e-05, "loss": 4.1503, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.22708261403087e-05, "loss": 4.139, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.226244019279818e-05, "loss": 4.1513, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.2254054245287657e-05, "loss": 4.1498, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.2245684676580866e-05, "loss": 4.1496, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.2237298729070346e-05, "loss": 4.1603, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.2228912781559826e-05, "loss": 4.1577, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.2220526834049306e-05, "loss": 4.1577, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.2212157265342515e-05, "loss": 4.1485, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.2203771317831995e-05, "loss": 4.1666, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.2195385370321475e-05, "loss": 4.1465, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.2186999422810955e-05, "loss": 4.1408, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.217861347530044e-05, "loss": 4.1469, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.217022752778992e-05, "loss": 4.1416, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.21618415802794e-05, "loss": 4.1515, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.215345563276888e-05, "loss": 4.1594, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.214506968525836e-05, "loss": 4.1397, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.21367164953553e-05, "loss": 4.1488, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.212833054784478e-05, "loss": 4.1564, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.211994460033426e-05, "loss": 4.1581, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.211155865282374e-05, "loss": 4.1564, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.210317270531322e-05, "loss": 4.1432, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.20947867578027e-05, "loss": 4.1193, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.208640081029218e-05, "loss": 4.1624, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.2078031241585395e-05, "loss": 4.1506, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.2069645294074875e-05, "loss": 4.1502, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.2061259346564355e-05, "loss": 4.1437, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.2052873399053835e-05, "loss": 4.1376, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.2044487451543315e-05, "loss": 4.1336, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.2036101504032795e-05, "loss": 4.1403, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.2027715556522275e-05, "loss": 4.1368, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201932960901175e-05, "loss": 4.1404, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.201097641910869e-05, "loss": 4.1537, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.200259047159817e-05, "loss": 4.1341, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.199420452408765e-05, "loss": 4.1312, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.198581857657713e-05, "loss": 4.1484, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.197744900787035e-05, "loss": 4.1325, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.196906306035983e-05, "loss": 4.1342, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.196067711284931e-05, "loss": 4.1404, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.195229116533879e-05, "loss": 4.1426, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.194390521782827e-05, "loss": 4.1315, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.193551927031775e-05, "loss": 4.129, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.192713332280722e-05, "loss": 4.1297, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.19187473752967e-05, "loss": 4.1445, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.191036142778618e-05, "loss": 4.1419, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.190197548027566e-05, "loss": 4.139, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.189358953276514e-05, "loss": 4.1401, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188520358525462e-05, "loss": 4.15, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.18768176377441e-05, "loss": 4.1453, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186844806903731e-05, "loss": 4.129, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.18600621215268e-05, "loss": 4.1402, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.1851692552820006e-05, "loss": 4.1447, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.1843306605309486e-05, "loss": 4.1243, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.1834920657798966e-05, "loss": 4.1412, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.1826534710288446e-05, "loss": 4.139, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.1818148762777926e-05, "loss": 4.1465, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.1809762815267406e-05, "loss": 4.1387, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.1801393246560615e-05, "loss": 4.1184, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.1793007299050095e-05, "loss": 4.1333, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.1784621351539575e-05, "loss": 4.129, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.1776235404029055e-05, "loss": 4.1427, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.1767849456518535e-05, "loss": 4.1329, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.1759463509008015e-05, "loss": 4.1291, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175109394030123e-05, "loss": 4.1343, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.174270799279071e-05, "loss": 4.1385, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.173432204528019e-05, "loss": 4.1243, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.172593609776967e-05, "loss": 4.1328, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.171755015025915e-05, "loss": 4.1406, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.170916420274863e-05, "loss": 4.1436, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.170079463404184e-05, "loss": 4.1332, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.169240868653132e-05, "loss": 4.1203, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.16840227390208e-05, "loss": 4.1299, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.167563679151028e-05, "loss": 4.1302, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.166725084399975e-05, "loss": 4.1413, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.165886489648923e-05, "loss": 4.1434, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.165047894897872e-05, "loss": 4.1261, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.1642109380271935e-05, "loss": 4.124, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.163372343276141e-05, "loss": 4.1334, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.162533748525089e-05, "loss": 4.1169, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.161695153774037e-05, "loss": 4.1322, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.160856559022985e-05, "loss": 4.1144, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.160017964271933e-05, "loss": 4.1342, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.159179369520881e-05, "loss": 4.1211, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.158340774769829e-05, "loss": 4.1294, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.1575054557795226e-05, "loss": 4.128, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.1566668610284706e-05, "loss": 4.1226, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.1558282662774186e-05, "loss": 4.1317, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.154989671526367e-05, "loss": 4.1206, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154151076775315e-05, "loss": 4.144, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.153312482024263e-05, "loss": 4.1354, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.152473887273211e-05, "loss": 4.1256, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151636930402532e-05, "loss": 4.135, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.15079833565148e-05, "loss": 4.1189, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.149959740900428e-05, "loss": 4.1292, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.149121146149376e-05, "loss": 4.1272, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148282551398324e-05, "loss": 4.1294, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147443956647272e-05, "loss": 4.1277, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.146606999776593e-05, "loss": 4.1235, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.145768405025541e-05, "loss": 4.1282, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144929810274489e-05, "loss": 4.1248, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.144092853403811e-05, "loss": 4.1187, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.1432542586527587e-05, "loss": 4.1315, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.1424156639017067e-05, "loss": 4.1123, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.1415770691506546e-05, "loss": 4.1399, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.1407384743996026e-05, "loss": 4.1255, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.1398998796485506e-05, "loss": 4.1314, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.1390612848974986e-05, "loss": 4.1148, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.1382226901464466e-05, "loss": 4.1296, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.1373840953953946e-05, "loss": 4.1317, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.136545500644342e-05, "loss": 4.1284, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.13570690589329e-05, "loss": 4.1198, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.134868311142238e-05, "loss": 4.1344, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.1340313542715595e-05, "loss": 4.126, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.1331927595205075e-05, "loss": 4.1367, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.1323541647694555e-05, "loss": 4.1169, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.1315155700184035e-05, "loss": 4.1351, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.1306786131477244e-05, "loss": 4.1254, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.1298400183966724e-05, "loss": 4.1232, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.1290014236456204e-05, "loss": 4.1264, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.1281628288945684e-05, "loss": 4.1263, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.127325872023889e-05, "loss": 4.1284, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.126487277272837e-05, "loss": 4.1105, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.125651958282532e-05, "loss": 4.1303, "step": 534016 }, { "epoch": 0.03, "eval_loss": 4.135540008544922, "eval_runtime": 296.2728, "eval_samples_per_second": 1287.972, "eval_steps_per_second": 40.25, "step": 534240 }, { "epoch": 0.0, "learning_rate": 4.12481336353148e-05, "loss": 4.1206, "step": 534528 }, { "epoch": 0.0, "learning_rate": 4.123974768780428e-05, "loss": 4.1101, "step": 535040 }, { "epoch": 0.0, "learning_rate": 4.123136174029376e-05, "loss": 4.1271, "step": 535552 }, { "epoch": 0.0, "learning_rate": 4.1222975792783245e-05, "loss": 4.1317, "step": 536064 }, { "epoch": 0.0, "learning_rate": 4.121458984527272e-05, "loss": 4.1237, "step": 536576 }, { "epoch": 0.0, "learning_rate": 4.12062038977622e-05, "loss": 4.1192, "step": 537088 }, { "epoch": 0.0, "learning_rate": 4.119781795025168e-05, "loss": 4.1264, "step": 537600 }, { "epoch": 0.0, "learning_rate": 4.118943200274116e-05, "loss": 4.112, "step": 538112 }, { "epoch": 0.0, "learning_rate": 4.118104605523064e-05, "loss": 4.1241, "step": 538624 }, { "epoch": 0.0, "learning_rate": 4.117266010772012e-05, "loss": 4.1264, "step": 539136 }, { "epoch": 0.0, "learning_rate": 4.11642741602096e-05, "loss": 4.1231, "step": 539648 }, { "epoch": 0.0, "learning_rate": 4.115588821269908e-05, "loss": 4.1266, "step": 540160 }, { "epoch": 0.0, "learning_rate": 4.114751864399229e-05, "loss": 4.1149, "step": 540672 }, { "epoch": 0.0, "learning_rate": 4.113913269648177e-05, "loss": 4.1181, "step": 541184 }, { "epoch": 0.0, "learning_rate": 4.1130746748971247e-05, "loss": 4.1156, "step": 541696 }, { "epoch": 0.0, "learning_rate": 4.1122360801460727e-05, "loss": 4.1065, "step": 542208 }, { "epoch": 0.0, "learning_rate": 4.111397485395021e-05, "loss": 4.117, "step": 542720 }, { "epoch": 0.0, "learning_rate": 4.110558890643969e-05, "loss": 4.1127, "step": 543232 }, { "epoch": 0.0, "learning_rate": 4.109720295892917e-05, "loss": 4.117, "step": 543744 }, { "epoch": 0.0, "learning_rate": 4.108881701141865e-05, "loss": 4.1254, "step": 544256 }, { "epoch": 0.0, "learning_rate": 4.108043106390813e-05, "loss": 4.1315, "step": 544768 }, { "epoch": 0.0, "learning_rate": 4.1072045116397606e-05, "loss": 4.1301, "step": 545280 }, { "epoch": 0.0, "learning_rate": 4.1063659168887086e-05, "loss": 4.1134, "step": 545792 }, { "epoch": 0.0, "learning_rate": 4.10552896001803e-05, "loss": 4.1251, "step": 546304 }, { "epoch": 0.0, "learning_rate": 4.1046903652669775e-05, "loss": 4.1151, "step": 546816 }, { "epoch": 0.0, "learning_rate": 4.1038517705159255e-05, "loss": 4.1219, "step": 547328 }, { "epoch": 0.0, "learning_rate": 4.1030131757648735e-05, "loss": 4.1155, "step": 547840 }, { "epoch": 0.0, "learning_rate": 4.1021745810138215e-05, "loss": 4.1031, "step": 548352 }, { "epoch": 0.0, "learning_rate": 4.1013359862627695e-05, "loss": 4.1157, "step": 548864 }, { "epoch": 0.0, "learning_rate": 4.100497391511718e-05, "loss": 4.1065, "step": 549376 }, { "epoch": 0.01, "learning_rate": 4.099658796760666e-05, "loss": 4.1135, "step": 549888 }, { "epoch": 0.01, "learning_rate": 4.098821839889987e-05, "loss": 4.1235, "step": 550400 }, { "epoch": 0.01, "learning_rate": 4.097983245138935e-05, "loss": 4.1188, "step": 550912 }, { "epoch": 0.01, "learning_rate": 4.097144650387883e-05, "loss": 4.1186, "step": 551424 }, { "epoch": 0.01, "learning_rate": 4.096306055636831e-05, "loss": 4.109, "step": 551936 }, { "epoch": 0.01, "learning_rate": 4.095469098766152e-05, "loss": 4.1307, "step": 552448 }, { "epoch": 0.01, "learning_rate": 4.0946305040151e-05, "loss": 4.1139, "step": 552960 }, { "epoch": 0.01, "learning_rate": 4.093791909264048e-05, "loss": 4.1029, "step": 553472 }, { "epoch": 0.01, "learning_rate": 4.092953314512996e-05, "loss": 4.1115, "step": 553984 }, { "epoch": 0.01, "learning_rate": 4.092114719761944e-05, "loss": 4.1041, "step": 554496 }, { "epoch": 0.01, "learning_rate": 4.091276125010892e-05, "loss": 4.1126, "step": 555008 }, { "epoch": 0.01, "learning_rate": 4.09043753025984e-05, "loss": 4.1165, "step": 555520 }, { "epoch": 0.01, "learning_rate": 4.089598935508788e-05, "loss": 4.1105, "step": 556032 }, { "epoch": 0.01, "learning_rate": 4.0887619786381095e-05, "loss": 4.1088, "step": 556544 }, { "epoch": 0.01, "learning_rate": 4.0879233838870575e-05, "loss": 4.1221, "step": 557056 }, { "epoch": 0.01, "learning_rate": 4.0870864270163784e-05, "loss": 4.1185, "step": 557568 }, { "epoch": 0.01, "learning_rate": 4.0862478322653264e-05, "loss": 4.1225, "step": 558080 }, { "epoch": 0.01, "learning_rate": 4.0854092375142744e-05, "loss": 4.1048, "step": 558592 }, { "epoch": 0.01, "learning_rate": 4.0845706427632224e-05, "loss": 4.0816, "step": 559104 }, { "epoch": 0.01, "learning_rate": 4.0837336858925433e-05, "loss": 4.1292, "step": 559616 }, { "epoch": 0.01, "learning_rate": 4.0828950911414913e-05, "loss": 4.111, "step": 560128 }, { "epoch": 0.01, "learning_rate": 4.082056496390439e-05, "loss": 4.118, "step": 560640 }, { "epoch": 0.01, "learning_rate": 4.081217901639387e-05, "loss": 4.1082, "step": 561152 }, { "epoch": 0.01, "learning_rate": 4.080379306888335e-05, "loss": 4.0983, "step": 561664 }, { "epoch": 0.01, "learning_rate": 4.079540712137283e-05, "loss": 4.0986, "step": 562176 }, { "epoch": 0.01, "learning_rate": 4.078702117386231e-05, "loss": 4.1043, "step": 562688 }, { "epoch": 0.01, "learning_rate": 4.077863522635179e-05, "loss": 4.0977, "step": 563200 }, { "epoch": 0.01, "learning_rate": 4.077026565764501e-05, "loss": 4.1022, "step": 563712 }, { "epoch": 0.01, "learning_rate": 4.076189608893822e-05, "loss": 4.1214, "step": 564224 }, { "epoch": 0.01, "learning_rate": 4.07535101414277e-05, "loss": 4.0966, "step": 564736 }, { "epoch": 0.01, "learning_rate": 4.074512419391718e-05, "loss": 4.0936, "step": 565248 }, { "epoch": 0.01, "learning_rate": 4.073673824640666e-05, "loss": 4.1154, "step": 565760 }, { "epoch": 0.01, "learning_rate": 4.072835229889614e-05, "loss": 4.0919, "step": 566272 }, { "epoch": 0.01, "learning_rate": 4.071996635138561e-05, "loss": 4.0971, "step": 566784 }, { "epoch": 0.01, "learning_rate": 4.071159678267883e-05, "loss": 4.1057, "step": 567296 }, { "epoch": 0.01, "learning_rate": 4.070321083516831e-05, "loss": 4.1069, "step": 567808 }, { "epoch": 0.01, "learning_rate": 4.069482488765779e-05, "loss": 4.0943, "step": 568320 }, { "epoch": 0.01, "learning_rate": 4.068643894014727e-05, "loss": 4.1012, "step": 568832 }, { "epoch": 0.01, "learning_rate": 4.067805299263675e-05, "loss": 4.0887, "step": 569344 }, { "epoch": 0.01, "learning_rate": 4.066966704512623e-05, "loss": 4.1083, "step": 569856 }, { "epoch": 0.01, "learning_rate": 4.066128109761571e-05, "loss": 4.1076, "step": 570368 }, { "epoch": 0.01, "learning_rate": 4.065289515010519e-05, "loss": 4.1034, "step": 570880 }, { "epoch": 0.01, "learning_rate": 4.064450920259467e-05, "loss": 4.1054, "step": 571392 }, { "epoch": 0.01, "learning_rate": 4.0636139633887876e-05, "loss": 4.11, "step": 571904 }, { "epoch": 0.01, "learning_rate": 4.0627753686377356e-05, "loss": 4.1147, "step": 572416 }, { "epoch": 0.01, "learning_rate": 4.0619367738866836e-05, "loss": 4.0942, "step": 572928 }, { "epoch": 0.01, "learning_rate": 4.0610998170160045e-05, "loss": 4.1048, "step": 573440 }, { "epoch": 0.01, "learning_rate": 4.0602612222649525e-05, "loss": 4.1102, "step": 573952 }, { "epoch": 0.01, "learning_rate": 4.0594226275139005e-05, "loss": 4.0878, "step": 574464 }, { "epoch": 0.01, "learning_rate": 4.058584032762849e-05, "loss": 4.1087, "step": 574976 }, { "epoch": 0.01, "learning_rate": 4.057745438011797e-05, "loss": 4.1003, "step": 575488 }, { "epoch": 0.01, "learning_rate": 4.056906843260745e-05, "loss": 4.1126, "step": 576000 }, { "epoch": 0.01, "learning_rate": 4.056069886390066e-05, "loss": 4.1069, "step": 576512 }, { "epoch": 0.01, "learning_rate": 4.055231291639014e-05, "loss": 4.087, "step": 577024 }, { "epoch": 0.01, "learning_rate": 4.054392696887962e-05, "loss": 4.0899, "step": 577536 }, { "epoch": 0.01, "learning_rate": 4.05355410213691e-05, "loss": 4.0972, "step": 578048 }, { "epoch": 0.01, "learning_rate": 4.052717145266231e-05, "loss": 4.1098, "step": 578560 }, { "epoch": 0.01, "learning_rate": 4.051878550515179e-05, "loss": 4.0956, "step": 579072 }, { "epoch": 0.01, "learning_rate": 4.051039955764127e-05, "loss": 4.0953, "step": 579584 }, { "epoch": 0.02, "learning_rate": 4.050202998893448e-05, "loss": 4.0994, "step": 580096 }, { "epoch": 0.02, "learning_rate": 4.049364404142396e-05, "loss": 4.1026, "step": 580608 }, { "epoch": 0.02, "learning_rate": 4.0485258093913445e-05, "loss": 4.0927, "step": 581120 }, { "epoch": 0.02, "learning_rate": 4.0476872146402925e-05, "loss": 4.0963, "step": 581632 }, { "epoch": 0.02, "learning_rate": 4.0468486198892405e-05, "loss": 4.1055, "step": 582144 }, { "epoch": 0.02, "learning_rate": 4.0460100251381885e-05, "loss": 4.108, "step": 582656 }, { "epoch": 0.02, "learning_rate": 4.0451714303871365e-05, "loss": 4.1004, "step": 583168 }, { "epoch": 0.02, "learning_rate": 4.0443328356360845e-05, "loss": 4.0875, "step": 583680 }, { "epoch": 0.02, "learning_rate": 4.0434942408850325e-05, "loss": 4.0993, "step": 584192 }, { "epoch": 0.02, "learning_rate": 4.04265564613398e-05, "loss": 4.093, "step": 584704 }, { "epoch": 0.02, "learning_rate": 4.0418186892633014e-05, "loss": 4.1081, "step": 585216 }, { "epoch": 0.02, "learning_rate": 4.0409800945122494e-05, "loss": 4.1034, "step": 585728 }, { "epoch": 0.02, "learning_rate": 4.0401414997611974e-05, "loss": 4.0964, "step": 586240 }, { "epoch": 0.02, "learning_rate": 4.039302905010145e-05, "loss": 4.0943, "step": 586752 }, { "epoch": 0.02, "learning_rate": 4.038464310259093e-05, "loss": 4.0938, "step": 587264 }, { "epoch": 0.02, "learning_rate": 4.0376257155080414e-05, "loss": 4.0871, "step": 587776 }, { "epoch": 0.02, "learning_rate": 4.0367871207569894e-05, "loss": 4.0964, "step": 588288 }, { "epoch": 0.02, "learning_rate": 4.0359485260059374e-05, "loss": 4.0822, "step": 588800 }, { "epoch": 0.02, "learning_rate": 4.0351099312548853e-05, "loss": 4.1021, "step": 589312 }, { "epoch": 0.02, "learning_rate": 4.03427461226458e-05, "loss": 4.0901, "step": 589824 }, { "epoch": 0.02, "learning_rate": 4.033436017513527e-05, "loss": 4.0931, "step": 590336 }, { "epoch": 0.02, "learning_rate": 4.032597422762475e-05, "loss": 4.0916, "step": 590848 }, { "epoch": 0.02, "learning_rate": 4.031758828011423e-05, "loss": 4.0887, "step": 591360 }, { "epoch": 0.02, "learning_rate": 4.030920233260371e-05, "loss": 4.1008, "step": 591872 }, { "epoch": 0.02, "learning_rate": 4.030081638509319e-05, "loss": 4.0889, "step": 592384 }, { "epoch": 0.02, "learning_rate": 4.029243043758267e-05, "loss": 4.1114, "step": 592896 }, { "epoch": 0.02, "learning_rate": 4.028404449007215e-05, "loss": 4.1029, "step": 593408 }, { "epoch": 0.02, "learning_rate": 4.027567492136537e-05, "loss": 4.0925, "step": 593920 }, { "epoch": 0.02, "learning_rate": 4.0267305352658576e-05, "loss": 4.0986, "step": 594432 }, { "epoch": 0.02, "learning_rate": 4.0258919405148056e-05, "loss": 4.0883, "step": 594944 }, { "epoch": 0.02, "learning_rate": 4.0250533457637536e-05, "loss": 4.0947, "step": 595456 }, { "epoch": 0.02, "learning_rate": 4.0242147510127016e-05, "loss": 4.1, "step": 595968 }, { "epoch": 0.02, "learning_rate": 4.0233761562616496e-05, "loss": 4.0946, "step": 596480 }, { "epoch": 0.02, "learning_rate": 4.0225391993909705e-05, "loss": 4.0945, "step": 596992 }, { "epoch": 0.02, "learning_rate": 4.0217006046399185e-05, "loss": 4.0928, "step": 597504 }, { "epoch": 0.02, "learning_rate": 4.0208620098888665e-05, "loss": 4.0957, "step": 598016 }, { "epoch": 0.02, "learning_rate": 4.0200234151378145e-05, "loss": 4.0944, "step": 598528 }, { "epoch": 0.02, "learning_rate": 4.0191848203867625e-05, "loss": 4.083, "step": 599040 }, { "epoch": 0.02, "learning_rate": 4.0183478635160834e-05, "loss": 4.0973, "step": 599552 }, { "epoch": 0.02, "learning_rate": 4.0175092687650314e-05, "loss": 4.0848, "step": 600064 }, { "epoch": 0.02, "learning_rate": 4.01667067401398e-05, "loss": 4.1054, "step": 600576 }, { "epoch": 0.02, "learning_rate": 4.015833717143301e-05, "loss": 4.0927, "step": 601088 }, { "epoch": 0.02, "learning_rate": 4.014995122392249e-05, "loss": 4.0958, "step": 601600 }, { "epoch": 0.02, "learning_rate": 4.014156527641197e-05, "loss": 4.0835, "step": 602112 }, { "epoch": 0.02, "learning_rate": 4.013317932890145e-05, "loss": 4.0966, "step": 602624 }, { "epoch": 0.02, "learning_rate": 4.012479338139093e-05, "loss": 4.0983, "step": 603136 }, { "epoch": 0.02, "learning_rate": 4.011640743388041e-05, "loss": 4.0946, "step": 603648 }, { "epoch": 0.02, "learning_rate": 4.010802148636989e-05, "loss": 4.0901, "step": 604160 }, { "epoch": 0.02, "learning_rate": 4.009963553885937e-05, "loss": 4.0998, "step": 604672 }, { "epoch": 0.02, "learning_rate": 4.009124959134885e-05, "loss": 4.0931, "step": 605184 }, { "epoch": 0.02, "learning_rate": 4.008286364383833e-05, "loss": 4.1085, "step": 605696 }, { "epoch": 0.02, "learning_rate": 4.007449407513154e-05, "loss": 4.0846, "step": 606208 }, { "epoch": 0.02, "learning_rate": 4.006610812762102e-05, "loss": 4.1023, "step": 606720 }, { "epoch": 0.02, "learning_rate": 4.00577221801105e-05, "loss": 4.0927, "step": 607232 }, { "epoch": 0.02, "learning_rate": 4.0049336232599985e-05, "loss": 4.0912, "step": 607744 }, { "epoch": 0.02, "learning_rate": 4.0040950285089465e-05, "loss": 4.0925, "step": 608256 }, { "epoch": 0.02, "learning_rate": 4.003256433757894e-05, "loss": 4.093, "step": 608768 }, { "epoch": 0.02, "learning_rate": 4.0024194768872154e-05, "loss": 4.0957, "step": 609280 }, { "epoch": 0.02, "learning_rate": 4.0015808821361634e-05, "loss": 4.0795, "step": 609792 }, { "epoch": 0.02, "learning_rate": 4.000742287385111e-05, "loss": 4.0968, "step": 610304 }, { "epoch": 0.03, "eval_loss": 4.111083984375, "eval_runtime": 297.8115, "eval_samples_per_second": 1281.317, "eval_steps_per_second": 40.042, "step": 610560 }, { "epoch": 1.0, "learning_rate": 3.999903692634059e-05, "loss": 4.084, "step": 610816 }, { "epoch": 1.0, "learning_rate": 3.999065097883007e-05, "loss": 4.0795, "step": 611328 }, { "epoch": 1.0, "learning_rate": 3.998226503131955e-05, "loss": 4.0928, "step": 611840 }, { "epoch": 1.0, "learning_rate": 3.997387908380903e-05, "loss": 4.103, "step": 612352 }, { "epoch": 1.0, "learning_rate": 3.9965509515102236e-05, "loss": 4.0929, "step": 612864 }, { "epoch": 1.0, "learning_rate": 3.995712356759172e-05, "loss": 4.0862, "step": 613376 }, { "epoch": 1.0, "learning_rate": 3.99487376200812e-05, "loss": 4.0994, "step": 613888 }, { "epoch": 1.0, "learning_rate": 3.994035167257068e-05, "loss": 4.0776, "step": 614400 }, { "epoch": 1.0, "learning_rate": 3.993196572506016e-05, "loss": 4.0895, "step": 614912 }, { "epoch": 1.0, "learning_rate": 3.992357977754964e-05, "loss": 4.0988, "step": 615424 }, { "epoch": 1.0, "learning_rate": 3.991519383003912e-05, "loss": 4.0917, "step": 615936 }, { "epoch": 1.0, "learning_rate": 3.990682426133233e-05, "loss": 4.0938, "step": 616448 }, { "epoch": 1.0, "learning_rate": 3.989843831382181e-05, "loss": 4.0911, "step": 616960 }, { "epoch": 1.0, "learning_rate": 3.989005236631129e-05, "loss": 4.0823, "step": 617472 }, { "epoch": 1.0, "learning_rate": 3.988166641880077e-05, "loss": 4.08, "step": 617984 }, { "epoch": 1.0, "learning_rate": 3.987329685009398e-05, "loss": 4.0772, "step": 618496 }, { "epoch": 1.0, "learning_rate": 3.986491090258346e-05, "loss": 4.0845, "step": 619008 }, { "epoch": 1.0, "learning_rate": 3.985652495507294e-05, "loss": 4.0847, "step": 619520 }, { "epoch": 1.0, "learning_rate": 3.984813900756242e-05, "loss": 4.0828, "step": 620032 }, { "epoch": 1.0, "learning_rate": 3.983975306005191e-05, "loss": 4.0927, "step": 620544 }, { "epoch": 1.0, "learning_rate": 3.983136711254139e-05, "loss": 4.1026, "step": 621056 }, { "epoch": 1.0, "learning_rate": 3.982298116503087e-05, "loss": 4.0971, "step": 621568 }, { "epoch": 1.0, "learning_rate": 3.981459521752035e-05, "loss": 4.0868, "step": 622080 }, { "epoch": 1.0, "learning_rate": 3.9806242027617286e-05, "loss": 4.0901, "step": 622592 }, { "epoch": 1.0, "learning_rate": 3.9797856080106766e-05, "loss": 4.091, "step": 623104 }, { "epoch": 1.0, "learning_rate": 3.9789470132596246e-05, "loss": 4.0863, "step": 623616 }, { "epoch": 1.0, "learning_rate": 3.9781084185085726e-05, "loss": 4.086, "step": 624128 }, { "epoch": 1.0, "learning_rate": 3.9772698237575205e-05, "loss": 4.0752, "step": 624640 }, { "epoch": 1.0, "learning_rate": 3.9764312290064685e-05, "loss": 4.0834, "step": 625152 }, { "epoch": 1.0, "learning_rate": 3.9755926342554165e-05, "loss": 4.0786, "step": 625664 }, { "epoch": 1.01, "learning_rate": 3.9747540395043645e-05, "loss": 4.08, "step": 626176 }, { "epoch": 1.01, "learning_rate": 3.973917082633686e-05, "loss": 4.0918, "step": 626688 }, { "epoch": 1.01, "learning_rate": 3.973078487882634e-05, "loss": 4.091, "step": 627200 }, { "epoch": 1.01, "learning_rate": 3.972239893131582e-05, "loss": 4.0872, "step": 627712 }, { "epoch": 1.01, "learning_rate": 3.9714012983805294e-05, "loss": 4.0834, "step": 628224 }, { "epoch": 1.01, "learning_rate": 3.9705627036294774e-05, "loss": 4.0927, "step": 628736 }, { "epoch": 1.01, "learning_rate": 3.9697241088784254e-05, "loss": 4.0845, "step": 629248 }, { "epoch": 1.01, "learning_rate": 3.968887152007747e-05, "loss": 4.0758, "step": 629760 }, { "epoch": 1.01, "learning_rate": 3.968048557256694e-05, "loss": 4.0822, "step": 630272 }, { "epoch": 1.01, "learning_rate": 3.967209962505642e-05, "loss": 4.0731, "step": 630784 }, { "epoch": 1.01, "learning_rate": 3.96637136775459e-05, "loss": 4.079, "step": 631296 }, { "epoch": 1.01, "learning_rate": 3.965534410883912e-05, "loss": 4.0884, "step": 631808 }, { "epoch": 1.01, "learning_rate": 3.96469581613286e-05, "loss": 4.0774, "step": 632320 }, { "epoch": 1.01, "learning_rate": 3.963857221381808e-05, "loss": 4.0834, "step": 632832 }, { "epoch": 1.01, "learning_rate": 3.963018626630756e-05, "loss": 4.0928, "step": 633344 }, { "epoch": 1.01, "learning_rate": 3.962180031879704e-05, "loss": 4.0858, "step": 633856 }, { "epoch": 1.01, "learning_rate": 3.961341437128652e-05, "loss": 4.0904, "step": 634368 }, { "epoch": 1.01, "learning_rate": 3.9605028423776e-05, "loss": 4.0796, "step": 634880 }, { "epoch": 1.01, "learning_rate": 3.959664247626548e-05, "loss": 4.0535, "step": 635392 }, { "epoch": 1.01, "learning_rate": 3.958825652875496e-05, "loss": 4.096, "step": 635904 }, { "epoch": 1.01, "learning_rate": 3.957988696004817e-05, "loss": 4.0806, "step": 636416 }, { "epoch": 1.01, "learning_rate": 3.957150101253765e-05, "loss": 4.0858, "step": 636928 }, { "epoch": 1.01, "learning_rate": 3.956311506502713e-05, "loss": 4.0814, "step": 637440 }, { "epoch": 1.01, "learning_rate": 3.955472911751661e-05, "loss": 4.0698, "step": 637952 }, { "epoch": 1.01, "learning_rate": 3.954635954880982e-05, "loss": 4.0667, "step": 638464 }, { "epoch": 1.01, "learning_rate": 3.95379736012993e-05, "loss": 4.0762, "step": 638976 }, { "epoch": 1.01, "learning_rate": 3.952958765378878e-05, "loss": 4.0701, "step": 639488 }, { "epoch": 1.01, "learning_rate": 3.9521201706278263e-05, "loss": 4.07, "step": 640000 }, { "epoch": 1.01, "learning_rate": 3.95128485163752e-05, "loss": 4.0924, "step": 640512 }, { "epoch": 1.01, "learning_rate": 3.950446256886468e-05, "loss": 4.0702, "step": 641024 }, { "epoch": 1.01, "learning_rate": 3.949607662135416e-05, "loss": 4.0643, "step": 641536 }, { "epoch": 1.01, "learning_rate": 3.948769067384364e-05, "loss": 4.0889, "step": 642048 }, { "epoch": 1.01, "learning_rate": 3.947930472633312e-05, "loss": 4.058, "step": 642560 }, { "epoch": 1.01, "learning_rate": 3.94709187788226e-05, "loss": 4.0658, "step": 643072 }, { "epoch": 1.01, "learning_rate": 3.946253283131208e-05, "loss": 4.0791, "step": 643584 }, { "epoch": 1.01, "learning_rate": 3.945414688380156e-05, "loss": 4.0783, "step": 644096 }, { "epoch": 1.01, "learning_rate": 3.944577731509477e-05, "loss": 4.0663, "step": 644608 }, { "epoch": 1.01, "learning_rate": 3.9437407746387986e-05, "loss": 4.0691, "step": 645120 }, { "epoch": 1.01, "learning_rate": 3.9429038177681195e-05, "loss": 4.0639, "step": 645632 }, { "epoch": 1.01, "learning_rate": 3.9420652230170675e-05, "loss": 4.0772, "step": 646144 }, { "epoch": 1.01, "learning_rate": 3.9412266282660155e-05, "loss": 4.0761, "step": 646656 }, { "epoch": 1.01, "learning_rate": 3.9403880335149635e-05, "loss": 4.0739, "step": 647168 }, { "epoch": 1.01, "learning_rate": 3.9395494387639115e-05, "loss": 4.0768, "step": 647680 }, { "epoch": 1.01, "learning_rate": 3.9387108440128595e-05, "loss": 4.0801, "step": 648192 }, { "epoch": 1.01, "learning_rate": 3.9378722492618075e-05, "loss": 4.0861, "step": 648704 }, { "epoch": 1.01, "learning_rate": 3.9370336545107555e-05, "loss": 4.0644, "step": 649216 }, { "epoch": 1.01, "learning_rate": 3.9361950597597035e-05, "loss": 4.0784, "step": 649728 }, { "epoch": 1.01, "learning_rate": 3.9353564650086515e-05, "loss": 4.0801, "step": 650240 }, { "epoch": 1.01, "learning_rate": 3.9345178702575995e-05, "loss": 4.0546, "step": 650752 }, { "epoch": 1.01, "learning_rate": 3.9336792755065475e-05, "loss": 4.0782, "step": 651264 }, { "epoch": 1.01, "learning_rate": 3.9328423186358684e-05, "loss": 4.076, "step": 651776 }, { "epoch": 1.01, "learning_rate": 3.932003723884817e-05, "loss": 4.0847, "step": 652288 }, { "epoch": 1.01, "learning_rate": 3.931166767014138e-05, "loss": 4.0783, "step": 652800 }, { "epoch": 1.01, "learning_rate": 3.930328172263086e-05, "loss": 4.0615, "step": 653312 }, { "epoch": 1.01, "learning_rate": 3.929489577512034e-05, "loss": 4.0576, "step": 653824 }, { "epoch": 1.01, "learning_rate": 3.928650982760982e-05, "loss": 4.0713, "step": 654336 }, { "epoch": 1.01, "learning_rate": 3.92781238800993e-05, "loss": 4.08, "step": 654848 }, { "epoch": 1.01, "learning_rate": 3.926975431139251e-05, "loss": 4.0703, "step": 655360 }, { "epoch": 1.01, "learning_rate": 3.926136836388199e-05, "loss": 4.0658, "step": 655872 }, { "epoch": 1.02, "learning_rate": 3.925298241637147e-05, "loss": 4.0694, "step": 656384 }, { "epoch": 1.02, "learning_rate": 3.924459646886095e-05, "loss": 4.0778, "step": 656896 }, { "epoch": 1.02, "learning_rate": 3.923621052135042e-05, "loss": 4.0655, "step": 657408 }, { "epoch": 1.02, "learning_rate": 3.922782457383991e-05, "loss": 4.0687, "step": 657920 }, { "epoch": 1.02, "learning_rate": 3.921943862632939e-05, "loss": 4.0735, "step": 658432 }, { "epoch": 1.02, "learning_rate": 3.921105267881887e-05, "loss": 4.0797, "step": 658944 }, { "epoch": 1.02, "learning_rate": 3.920268311011208e-05, "loss": 4.0711, "step": 659456 }, { "epoch": 1.02, "learning_rate": 3.919429716260156e-05, "loss": 4.062, "step": 659968 }, { "epoch": 1.02, "learning_rate": 3.918591121509104e-05, "loss": 4.0647, "step": 660480 }, { "epoch": 1.02, "learning_rate": 3.917754164638425e-05, "loss": 4.0666, "step": 660992 }, { "epoch": 1.02, "learning_rate": 3.9169155698873727e-05, "loss": 4.0792, "step": 661504 }, { "epoch": 1.02, "learning_rate": 3.9160769751363206e-05, "loss": 4.0775, "step": 662016 }, { "epoch": 1.02, "learning_rate": 3.9152383803852686e-05, "loss": 4.0692, "step": 662528 }, { "epoch": 1.02, "learning_rate": 3.9143997856342166e-05, "loss": 4.0656, "step": 663040 }, { "epoch": 1.02, "learning_rate": 3.9135611908831646e-05, "loss": 4.061, "step": 663552 }, { "epoch": 1.02, "learning_rate": 3.9127225961321126e-05, "loss": 4.0659, "step": 664064 }, { "epoch": 1.02, "learning_rate": 3.911885639261434e-05, "loss": 4.0663, "step": 664576 }, { "epoch": 1.02, "learning_rate": 3.911047044510382e-05, "loss": 4.0537, "step": 665088 }, { "epoch": 1.02, "learning_rate": 3.91020844975933e-05, "loss": 4.0753, "step": 665600 }, { "epoch": 1.02, "learning_rate": 3.909369855008278e-05, "loss": 4.0616, "step": 666112 }, { "epoch": 1.02, "learning_rate": 3.908531260257226e-05, "loss": 4.0636, "step": 666624 }, { "epoch": 1.02, "learning_rate": 3.907694303386547e-05, "loss": 4.0623, "step": 667136 }, { "epoch": 1.02, "learning_rate": 3.906855708635495e-05, "loss": 4.0582, "step": 667648 }, { "epoch": 1.02, "learning_rate": 3.906017113884443e-05, "loss": 4.0748, "step": 668160 }, { "epoch": 1.02, "learning_rate": 3.905178519133391e-05, "loss": 4.0591, "step": 668672 }, { "epoch": 1.02, "learning_rate": 3.904339924382339e-05, "loss": 4.0847, "step": 669184 }, { "epoch": 1.02, "learning_rate": 3.903501329631287e-05, "loss": 4.0748, "step": 669696 }, { "epoch": 1.02, "learning_rate": 3.902662734880235e-05, "loss": 4.0673, "step": 670208 }, { "epoch": 1.02, "learning_rate": 3.901825778009556e-05, "loss": 4.071, "step": 670720 }, { "epoch": 1.02, "learning_rate": 3.900987183258504e-05, "loss": 4.0641, "step": 671232 }, { "epoch": 1.02, "learning_rate": 3.9001485885074527e-05, "loss": 4.0662, "step": 671744 }, { "epoch": 1.02, "learning_rate": 3.8993099937564007e-05, "loss": 4.0729, "step": 672256 }, { "epoch": 1.02, "learning_rate": 3.8984713990053487e-05, "loss": 4.0644, "step": 672768 }, { "epoch": 1.02, "learning_rate": 3.8976344421346696e-05, "loss": 4.0704, "step": 673280 }, { "epoch": 1.02, "learning_rate": 3.8967958473836176e-05, "loss": 4.0602, "step": 673792 }, { "epoch": 1.02, "learning_rate": 3.8959572526325656e-05, "loss": 4.068, "step": 674304 }, { "epoch": 1.02, "learning_rate": 3.8951186578815135e-05, "loss": 4.0665, "step": 674816 }, { "epoch": 1.02, "learning_rate": 3.8942800631304615e-05, "loss": 4.0552, "step": 675328 }, { "epoch": 1.02, "learning_rate": 3.893441468379409e-05, "loss": 4.0711, "step": 675840 }, { "epoch": 1.02, "learning_rate": 3.8926045115087304e-05, "loss": 4.0577, "step": 676352 }, { "epoch": 1.02, "learning_rate": 3.8917659167576784e-05, "loss": 4.0791, "step": 676864 }, { "epoch": 1.02, "learning_rate": 3.8909273220066264e-05, "loss": 4.0658, "step": 677376 }, { "epoch": 1.02, "learning_rate": 3.8900887272555744e-05, "loss": 4.0689, "step": 677888 }, { "epoch": 1.02, "learning_rate": 3.8892501325045224e-05, "loss": 4.0553, "step": 678400 }, { "epoch": 1.02, "learning_rate": 3.8884115377534704e-05, "loss": 4.0728, "step": 678912 }, { "epoch": 1.02, "learning_rate": 3.8875729430024184e-05, "loss": 4.0628, "step": 679424 }, { "epoch": 1.02, "learning_rate": 3.8867343482513664e-05, "loss": 4.0685, "step": 679936 }, { "epoch": 1.02, "learning_rate": 3.885897391380687e-05, "loss": 4.0644, "step": 680448 }, { "epoch": 1.02, "learning_rate": 3.885058796629635e-05, "loss": 4.0719, "step": 680960 }, { "epoch": 1.02, "learning_rate": 3.884220201878583e-05, "loss": 4.0658, "step": 681472 }, { "epoch": 1.02, "learning_rate": 3.883381607127531e-05, "loss": 4.0823, "step": 681984 }, { "epoch": 1.02, "learning_rate": 3.882543012376479e-05, "loss": 4.0557, "step": 682496 }, { "epoch": 1.02, "learning_rate": 3.8817060555058e-05, "loss": 4.0742, "step": 683008 }, { "epoch": 1.02, "learning_rate": 3.880867460754748e-05, "loss": 4.0677, "step": 683520 }, { "epoch": 1.02, "learning_rate": 3.88003050388407e-05, "loss": 4.0683, "step": 684032 }, { "epoch": 1.02, "learning_rate": 3.879191909133018e-05, "loss": 4.0594, "step": 684544 }, { "epoch": 1.02, "learning_rate": 3.878353314381966e-05, "loss": 4.0686, "step": 685056 }, { "epoch": 1.02, "learning_rate": 3.877514719630914e-05, "loss": 4.0655, "step": 685568 }, { "epoch": 1.02, "learning_rate": 3.876676124879862e-05, "loss": 4.0597, "step": 686080 }, { "epoch": 1.02, "learning_rate": 3.87583753012881e-05, "loss": 4.0683, "step": 686592 }, { "epoch": 1.03, "eval_loss": 4.091145992279053, "eval_runtime": 296.5858, "eval_samples_per_second": 1286.612, "eval_steps_per_second": 40.208, "step": 686880 }, { "epoch": 0.0, "learning_rate": 3.874998935377758e-05, "loss": 4.0588, "step": 687104 }, { "epoch": 0.0, "learning_rate": 3.874160340626706e-05, "loss": 4.0519, "step": 687616 }, { "epoch": 0.0, "learning_rate": 3.873321745875654e-05, "loss": 4.0654, "step": 688128 }, { "epoch": 0.0, "learning_rate": 3.872483151124602e-05, "loss": 4.0749, "step": 688640 }, { "epoch": 0.0, "learning_rate": 3.87164455637355e-05, "loss": 4.0704, "step": 689152 }, { "epoch": 0.0, "learning_rate": 3.870805961622497e-05, "loss": 4.0567, "step": 689664 }, { "epoch": 0.0, "learning_rate": 3.869967366871445e-05, "loss": 4.0735, "step": 690176 }, { "epoch": 0.0, "learning_rate": 3.869128772120393e-05, "loss": 4.0532, "step": 690688 }, { "epoch": 0.0, "learning_rate": 3.868290177369342e-05, "loss": 4.0624, "step": 691200 }, { "epoch": 0.0, "learning_rate": 3.86745158261829e-05, "loss": 4.0739, "step": 691712 }, { "epoch": 0.0, "learning_rate": 3.866612987867238e-05, "loss": 4.0631, "step": 692224 }, { "epoch": 0.0, "learning_rate": 3.865774393116186e-05, "loss": 4.0678, "step": 692736 }, { "epoch": 0.0, "learning_rate": 3.8649374362455066e-05, "loss": 4.0673, "step": 693248 }, { "epoch": 0.0, "learning_rate": 3.8640988414944546e-05, "loss": 4.0565, "step": 693760 }, { "epoch": 0.0, "learning_rate": 3.8632602467434026e-05, "loss": 4.0534, "step": 694272 }, { "epoch": 0.0, "learning_rate": 3.8624216519923506e-05, "loss": 4.0525, "step": 694784 }, { "epoch": 0.0, "learning_rate": 3.8615830572412986e-05, "loss": 4.0558, "step": 695296 }, { "epoch": 0.0, "learning_rate": 3.8607444624902466e-05, "loss": 4.0596, "step": 695808 }, { "epoch": 0.0, "learning_rate": 3.8599058677391946e-05, "loss": 4.0539, "step": 696320 }, { "epoch": 0.0, "learning_rate": 3.8590689108685155e-05, "loss": 4.0663, "step": 696832 }, { "epoch": 0.0, "learning_rate": 3.8582303161174635e-05, "loss": 4.073, "step": 697344 }, { "epoch": 0.0, "learning_rate": 3.8573917213664115e-05, "loss": 4.0727, "step": 697856 }, { "epoch": 0.0, "learning_rate": 3.8565531266153595e-05, "loss": 4.062, "step": 698368 }, { "epoch": 0.0, "learning_rate": 3.855714531864308e-05, "loss": 4.0592, "step": 698880 }, { "epoch": 0.0, "learning_rate": 3.854875937113256e-05, "loss": 4.067, "step": 699392 }, { "epoch": 0.0, "learning_rate": 3.854037342362204e-05, "loss": 4.0583, "step": 699904 }, { "epoch": 0.0, "learning_rate": 3.8531987476111515e-05, "loss": 4.0562, "step": 700416 }, { "epoch": 0.0, "learning_rate": 3.852361790740473e-05, "loss": 4.0543, "step": 700928 }, { "epoch": 0.0, "learning_rate": 3.851523195989421e-05, "loss": 4.055, "step": 701440 }, { "epoch": 0.0, "learning_rate": 3.850684601238369e-05, "loss": 4.0527, "step": 701952 }, { "epoch": 0.01, "learning_rate": 3.8498460064873164e-05, "loss": 4.0545, "step": 702464 }, { "epoch": 0.01, "learning_rate": 3.8490074117362644e-05, "loss": 4.0642, "step": 702976 }, { "epoch": 0.01, "learning_rate": 3.8481688169852124e-05, "loss": 4.0693, "step": 703488 }, { "epoch": 0.01, "learning_rate": 3.8473302222341604e-05, "loss": 4.0602, "step": 704000 }, { "epoch": 0.01, "learning_rate": 3.8464916274831084e-05, "loss": 4.061, "step": 704512 }, { "epoch": 0.01, "learning_rate": 3.8456530327320564e-05, "loss": 4.0577, "step": 705024 }, { "epoch": 0.01, "learning_rate": 3.844816075861378e-05, "loss": 4.0653, "step": 705536 }, { "epoch": 0.01, "learning_rate": 3.843977481110326e-05, "loss": 4.0488, "step": 706048 }, { "epoch": 0.01, "learning_rate": 3.843138886359274e-05, "loss": 4.0566, "step": 706560 }, { "epoch": 0.01, "learning_rate": 3.842300291608222e-05, "loss": 4.0454, "step": 707072 }, { "epoch": 0.01, "learning_rate": 3.84146169685717e-05, "loss": 4.057, "step": 707584 }, { "epoch": 0.01, "learning_rate": 3.840623102106118e-05, "loss": 4.0583, "step": 708096 }, { "epoch": 0.01, "learning_rate": 3.839784507355066e-05, "loss": 4.0532, "step": 708608 }, { "epoch": 0.01, "learning_rate": 3.838945912604014e-05, "loss": 4.058, "step": 709120 }, { "epoch": 0.01, "learning_rate": 3.838108955733335e-05, "loss": 4.064, "step": 709632 }, { "epoch": 0.01, "learning_rate": 3.837270360982283e-05, "loss": 4.0599, "step": 710144 }, { "epoch": 0.01, "learning_rate": 3.836431766231231e-05, "loss": 4.0645, "step": 710656 }, { "epoch": 0.01, "learning_rate": 3.835593171480179e-05, "loss": 4.0572, "step": 711168 }, { "epoch": 0.01, "learning_rate": 3.834754576729127e-05, "loss": 4.0266, "step": 711680 }, { "epoch": 0.01, "learning_rate": 3.833915981978075e-05, "loss": 4.0685, "step": 712192 }, { "epoch": 0.01, "learning_rate": 3.8330790251073964e-05, "loss": 4.0555, "step": 712704 }, { "epoch": 0.01, "learning_rate": 3.8322404303563444e-05, "loss": 4.0629, "step": 713216 }, { "epoch": 0.01, "learning_rate": 3.8314018356052924e-05, "loss": 4.0563, "step": 713728 }, { "epoch": 0.01, "learning_rate": 3.8305632408542404e-05, "loss": 4.0449, "step": 714240 }, { "epoch": 0.01, "learning_rate": 3.829729559744307e-05, "loss": 4.0413, "step": 714752 }, { "epoch": 0.01, "learning_rate": 3.828890964993255e-05, "loss": 4.0476, "step": 715264 }, { "epoch": 0.01, "learning_rate": 3.828052370242203e-05, "loss": 4.0484, "step": 715776 }, { "epoch": 0.01, "learning_rate": 3.827213775491151e-05, "loss": 4.0416, "step": 716288 }, { "epoch": 0.01, "learning_rate": 3.826375180740099e-05, "loss": 4.0663, "step": 716800 }, { "epoch": 0.01, "learning_rate": 3.825536585989047e-05, "loss": 4.0483, "step": 717312 }, { "epoch": 0.01, "learning_rate": 3.824697991237996e-05, "loss": 4.034, "step": 717824 }, { "epoch": 0.01, "learning_rate": 3.823859396486944e-05, "loss": 4.0664, "step": 718336 }, { "epoch": 0.01, "learning_rate": 3.823020801735892e-05, "loss": 4.0366, "step": 718848 }, { "epoch": 0.01, "learning_rate": 3.82218220698484e-05, "loss": 4.0395, "step": 719360 }, { "epoch": 0.01, "learning_rate": 3.821343612233788e-05, "loss": 4.0551, "step": 719872 }, { "epoch": 0.01, "learning_rate": 3.820505017482735e-05, "loss": 4.0496, "step": 720384 }, { "epoch": 0.01, "learning_rate": 3.8196680606120567e-05, "loss": 4.0445, "step": 720896 }, { "epoch": 0.01, "learning_rate": 3.8188311037413776e-05, "loss": 4.0442, "step": 721408 }, { "epoch": 0.01, "learning_rate": 3.8179925089903256e-05, "loss": 4.0392, "step": 721920 }, { "epoch": 0.01, "learning_rate": 3.8171539142392736e-05, "loss": 4.0515, "step": 722432 }, { "epoch": 0.01, "learning_rate": 3.8163153194882216e-05, "loss": 4.0516, "step": 722944 }, { "epoch": 0.01, "learning_rate": 3.8154767247371695e-05, "loss": 4.0522, "step": 723456 }, { "epoch": 0.01, "learning_rate": 3.8146381299861175e-05, "loss": 4.05, "step": 723968 }, { "epoch": 0.01, "learning_rate": 3.8137995352350655e-05, "loss": 4.0539, "step": 724480 }, { "epoch": 0.01, "learning_rate": 3.8129609404840135e-05, "loss": 4.0641, "step": 724992 }, { "epoch": 0.01, "learning_rate": 3.812123983613335e-05, "loss": 4.0376, "step": 725504 }, { "epoch": 0.01, "learning_rate": 3.8112853888622824e-05, "loss": 4.05, "step": 726016 }, { "epoch": 0.01, "learning_rate": 3.810448431991604e-05, "loss": 4.0589, "step": 726528 }, { "epoch": 0.01, "learning_rate": 3.809609837240552e-05, "loss": 4.0332, "step": 727040 }, { "epoch": 0.01, "learning_rate": 3.8087712424894993e-05, "loss": 4.0482, "step": 727552 }, { "epoch": 0.01, "learning_rate": 3.807932647738447e-05, "loss": 4.0552, "step": 728064 }, { "epoch": 0.01, "learning_rate": 3.807095690867769e-05, "loss": 4.0572, "step": 728576 }, { "epoch": 0.01, "learning_rate": 3.806257096116717e-05, "loss": 4.0584, "step": 729088 }, { "epoch": 0.01, "learning_rate": 3.805418501365665e-05, "loss": 4.0343, "step": 729600 }, { "epoch": 0.01, "learning_rate": 3.804579906614613e-05, "loss": 4.032, "step": 730112 }, { "epoch": 0.01, "learning_rate": 3.803741311863561e-05, "loss": 4.0487, "step": 730624 }, { "epoch": 0.01, "learning_rate": 3.802902717112509e-05, "loss": 4.0529, "step": 731136 }, { "epoch": 0.01, "learning_rate": 3.802064122361457e-05, "loss": 4.0416, "step": 731648 }, { "epoch": 0.01, "learning_rate": 3.801227165490778e-05, "loss": 4.046, "step": 732160 }, { "epoch": 0.02, "learning_rate": 3.800388570739726e-05, "loss": 4.0429, "step": 732672 }, { "epoch": 0.02, "learning_rate": 3.799549975988674e-05, "loss": 4.0523, "step": 733184 }, { "epoch": 0.02, "learning_rate": 3.798711381237622e-05, "loss": 4.0456, "step": 733696 }, { "epoch": 0.02, "learning_rate": 3.79787278648657e-05, "loss": 4.0431, "step": 734208 }, { "epoch": 0.02, "learning_rate": 3.797034191735518e-05, "loss": 4.0458, "step": 734720 }, { "epoch": 0.02, "learning_rate": 3.796195596984466e-05, "loss": 4.0551, "step": 735232 }, { "epoch": 0.02, "learning_rate": 3.795357002233414e-05, "loss": 4.05, "step": 735744 }, { "epoch": 0.02, "learning_rate": 3.794518407482362e-05, "loss": 4.039, "step": 736256 }, { "epoch": 0.02, "learning_rate": 3.793681450611683e-05, "loss": 4.0388, "step": 736768 }, { "epoch": 0.02, "learning_rate": 3.7928428558606314e-05, "loss": 4.0434, "step": 737280 }, { "epoch": 0.02, "learning_rate": 3.7920042611095793e-05, "loss": 4.0532, "step": 737792 }, { "epoch": 0.02, "learning_rate": 3.7911656663585273e-05, "loss": 4.0511, "step": 738304 }, { "epoch": 0.02, "learning_rate": 3.7903270716074753e-05, "loss": 4.0427, "step": 738816 }, { "epoch": 0.02, "learning_rate": 3.789490114736796e-05, "loss": 4.0446, "step": 739328 }, { "epoch": 0.02, "learning_rate": 3.788651519985744e-05, "loss": 4.0355, "step": 739840 }, { "epoch": 0.02, "learning_rate": 3.787812925234692e-05, "loss": 4.0433, "step": 740352 }, { "epoch": 0.02, "learning_rate": 3.78697433048364e-05, "loss": 4.0372, "step": 740864 }, { "epoch": 0.02, "learning_rate": 3.786139011493334e-05, "loss": 4.0327, "step": 741376 }, { "epoch": 0.02, "learning_rate": 3.785300416742282e-05, "loss": 4.0502, "step": 741888 }, { "epoch": 0.02, "learning_rate": 3.78446182199123e-05, "loss": 4.037, "step": 742400 }, { "epoch": 0.02, "learning_rate": 3.783623227240178e-05, "loss": 4.0389, "step": 742912 }, { "epoch": 0.02, "learning_rate": 3.782784632489127e-05, "loss": 4.0381, "step": 743424 }, { "epoch": 0.02, "learning_rate": 3.781946037738075e-05, "loss": 4.0349, "step": 743936 }, { "epoch": 0.02, "learning_rate": 3.7811090808673956e-05, "loss": 4.0493, "step": 744448 }, { "epoch": 0.02, "learning_rate": 3.7802704861163436e-05, "loss": 4.0379, "step": 744960 }, { "epoch": 0.02, "learning_rate": 3.7794318913652916e-05, "loss": 4.059, "step": 745472 }, { "epoch": 0.02, "learning_rate": 3.7785932966142396e-05, "loss": 4.0512, "step": 745984 }, { "epoch": 0.02, "learning_rate": 3.7777547018631876e-05, "loss": 4.0443, "step": 746496 }, { "epoch": 0.02, "learning_rate": 3.7769177449925085e-05, "loss": 4.0464, "step": 747008 }, { "epoch": 0.02, "learning_rate": 3.7760791502414565e-05, "loss": 4.0424, "step": 747520 }, { "epoch": 0.02, "learning_rate": 3.7752405554904045e-05, "loss": 4.0411, "step": 748032 }, { "epoch": 0.02, "learning_rate": 3.7744019607393525e-05, "loss": 4.052, "step": 748544 }, { "epoch": 0.02, "learning_rate": 3.7735633659883005e-05, "loss": 4.046, "step": 749056 }, { "epoch": 0.02, "learning_rate": 3.7727247712372485e-05, "loss": 4.0431, "step": 749568 }, { "epoch": 0.02, "learning_rate": 3.7718861764861965e-05, "loss": 4.0358, "step": 750080 }, { "epoch": 0.02, "learning_rate": 3.7710475817351445e-05, "loss": 4.0449, "step": 750592 }, { "epoch": 0.02, "learning_rate": 3.7702089869840925e-05, "loss": 4.0407, "step": 751104 }, { "epoch": 0.02, "learning_rate": 3.7693720301134134e-05, "loss": 4.0335, "step": 751616 }, { "epoch": 0.02, "learning_rate": 3.768535073242735e-05, "loss": 4.0483, "step": 752128 }, { "epoch": 0.02, "learning_rate": 3.767696478491683e-05, "loss": 4.0264, "step": 752640 }, { "epoch": 0.02, "learning_rate": 3.76685788374063e-05, "loss": 4.0597, "step": 753152 }, { "epoch": 0.02, "learning_rate": 3.766019288989578e-05, "loss": 4.0393, "step": 753664 }, { "epoch": 0.02, "learning_rate": 3.7651823321189e-05, "loss": 4.0458, "step": 754176 }, { "epoch": 0.02, "learning_rate": 3.764343737367848e-05, "loss": 4.0329, "step": 754688 }, { "epoch": 0.02, "learning_rate": 3.763505142616796e-05, "loss": 4.0502, "step": 755200 }, { "epoch": 0.02, "learning_rate": 3.762666547865744e-05, "loss": 4.0411, "step": 755712 }, { "epoch": 0.02, "learning_rate": 3.761827953114692e-05, "loss": 4.0456, "step": 756224 }, { "epoch": 0.02, "learning_rate": 3.76098935836364e-05, "loss": 4.0428, "step": 756736 }, { "epoch": 0.02, "learning_rate": 3.760150763612588e-05, "loss": 4.0444, "step": 757248 }, { "epoch": 0.02, "learning_rate": 3.759313806741909e-05, "loss": 4.0436, "step": 757760 }, { "epoch": 0.02, "learning_rate": 3.758475211990857e-05, "loss": 4.061, "step": 758272 }, { "epoch": 0.02, "learning_rate": 3.757636617239805e-05, "loss": 4.0313, "step": 758784 }, { "epoch": 0.02, "learning_rate": 3.756798022488753e-05, "loss": 4.0517, "step": 759296 }, { "epoch": 0.02, "learning_rate": 3.755959427737701e-05, "loss": 4.0474, "step": 759808 }, { "epoch": 0.02, "learning_rate": 3.755120832986649e-05, "loss": 4.0444, "step": 760320 }, { "epoch": 0.02, "learning_rate": 3.754282238235597e-05, "loss": 4.0347, "step": 760832 }, { "epoch": 0.02, "learning_rate": 3.753443643484545e-05, "loss": 4.0475, "step": 761344 }, { "epoch": 0.02, "learning_rate": 3.7526066866138656e-05, "loss": 4.0399, "step": 761856 }, { "epoch": 0.02, "learning_rate": 3.751769729743187e-05, "loss": 4.0383, "step": 762368 }, { "epoch": 0.02, "learning_rate": 3.750931134992135e-05, "loss": 4.0422, "step": 762880 }, { "epoch": 0.03, "eval_loss": 4.075286388397217, "eval_runtime": 297.3176, "eval_samples_per_second": 1283.446, "eval_steps_per_second": 40.109, "step": 763200 }, { "epoch": 1.0, "learning_rate": 3.750092540241083e-05, "loss": 4.0338, "step": 763392 }, { "epoch": 1.0, "learning_rate": 3.749253945490031e-05, "loss": 4.0269, "step": 763904 }, { "epoch": 1.0, "learning_rate": 3.748415350738979e-05, "loss": 4.0427, "step": 764416 }, { "epoch": 1.0, "learning_rate": 3.747576755987927e-05, "loss": 4.0521, "step": 764928 }, { "epoch": 1.0, "learning_rate": 3.746738161236875e-05, "loss": 4.049, "step": 765440 }, { "epoch": 1.0, "learning_rate": 3.745899566485823e-05, "loss": 4.0356, "step": 765952 }, { "epoch": 1.0, "learning_rate": 3.745062609615144e-05, "loss": 4.0442, "step": 766464 }, { "epoch": 1.0, "learning_rate": 3.744224014864092e-05, "loss": 4.0339, "step": 766976 }, { "epoch": 1.0, "learning_rate": 3.74338542011304e-05, "loss": 4.0371, "step": 767488 }, { "epoch": 1.0, "learning_rate": 3.742548463242361e-05, "loss": 4.0504, "step": 768000 }, { "epoch": 1.0, "learning_rate": 3.741709868491309e-05, "loss": 4.0417, "step": 768512 }, { "epoch": 1.0, "learning_rate": 3.740871273740258e-05, "loss": 4.047, "step": 769024 }, { "epoch": 1.0, "learning_rate": 3.7400343168695786e-05, "loss": 4.0457, "step": 769536 }, { "epoch": 1.0, "learning_rate": 3.7391957221185266e-05, "loss": 4.0314, "step": 770048 }, { "epoch": 1.0, "learning_rate": 3.7383571273674746e-05, "loss": 4.0305, "step": 770560 }, { "epoch": 1.0, "learning_rate": 3.7375185326164226e-05, "loss": 4.0254, "step": 771072 }, { "epoch": 1.0, "learning_rate": 3.7366799378653706e-05, "loss": 4.0383, "step": 771584 }, { "epoch": 1.0, "learning_rate": 3.7358413431143186e-05, "loss": 4.0374, "step": 772096 }, { "epoch": 1.0, "learning_rate": 3.7350027483632666e-05, "loss": 4.0283, "step": 772608 }, { "epoch": 1.0, "learning_rate": 3.734164153612214e-05, "loss": 4.0437, "step": 773120 }, { "epoch": 1.0, "learning_rate": 3.733325558861162e-05, "loss": 4.0503, "step": 773632 }, { "epoch": 1.0, "learning_rate": 3.7324886019904835e-05, "loss": 4.0462, "step": 774144 }, { "epoch": 1.0, "learning_rate": 3.7316500072394315e-05, "loss": 4.0425, "step": 774656 }, { "epoch": 1.0, "learning_rate": 3.7308114124883794e-05, "loss": 4.04, "step": 775168 }, { "epoch": 1.0, "learning_rate": 3.7299728177373274e-05, "loss": 4.044, "step": 775680 }, { "epoch": 1.0, "learning_rate": 3.7291342229862754e-05, "loss": 4.0401, "step": 776192 }, { "epoch": 1.0, "learning_rate": 3.7282972661155963e-05, "loss": 4.0302, "step": 776704 }, { "epoch": 1.0, "learning_rate": 3.7274586713645443e-05, "loss": 4.0281, "step": 777216 }, { "epoch": 1.0, "learning_rate": 3.726620076613492e-05, "loss": 4.0358, "step": 777728 }, { "epoch": 1.0, "learning_rate": 3.72578148186244e-05, "loss": 4.0317, "step": 778240 }, { "epoch": 1.01, "learning_rate": 3.724942887111388e-05, "loss": 4.033, "step": 778752 }, { "epoch": 1.01, "learning_rate": 3.724104292360336e-05, "loss": 4.0397, "step": 779264 }, { "epoch": 1.01, "learning_rate": 3.723265697609284e-05, "loss": 4.0427, "step": 779776 }, { "epoch": 1.01, "learning_rate": 3.722427102858232e-05, "loss": 4.0437, "step": 780288 }, { "epoch": 1.01, "learning_rate": 3.721590145987553e-05, "loss": 4.0313, "step": 780800 }, { "epoch": 1.01, "learning_rate": 3.720753189116875e-05, "loss": 4.0414, "step": 781312 }, { "epoch": 1.01, "learning_rate": 3.719914594365823e-05, "loss": 4.0454, "step": 781824 }, { "epoch": 1.01, "learning_rate": 3.719075999614771e-05, "loss": 4.0211, "step": 782336 }, { "epoch": 1.01, "learning_rate": 3.718237404863719e-05, "loss": 4.0352, "step": 782848 }, { "epoch": 1.01, "learning_rate": 3.717398810112667e-05, "loss": 4.0257, "step": 783360 }, { "epoch": 1.01, "learning_rate": 3.716560215361615e-05, "loss": 4.0348, "step": 783872 }, { "epoch": 1.01, "learning_rate": 3.715721620610563e-05, "loss": 4.0329, "step": 784384 }, { "epoch": 1.01, "learning_rate": 3.714883025859511e-05, "loss": 4.0312, "step": 784896 }, { "epoch": 1.01, "learning_rate": 3.714046068988832e-05, "loss": 4.0374, "step": 785408 }, { "epoch": 1.01, "learning_rate": 3.7132091121181526e-05, "loss": 4.0429, "step": 785920 }, { "epoch": 1.01, "learning_rate": 3.7123705173671006e-05, "loss": 4.0402, "step": 786432 }, { "epoch": 1.01, "learning_rate": 3.7115319226160486e-05, "loss": 4.0448, "step": 786944 }, { "epoch": 1.01, "learning_rate": 3.7106933278649966e-05, "loss": 4.0326, "step": 787456 }, { "epoch": 1.01, "learning_rate": 3.709854733113945e-05, "loss": 4.0076, "step": 787968 }, { "epoch": 1.01, "learning_rate": 3.709017776243266e-05, "loss": 4.0449, "step": 788480 }, { "epoch": 1.01, "learning_rate": 3.708179181492214e-05, "loss": 4.0339, "step": 788992 }, { "epoch": 1.01, "learning_rate": 3.707340586741162e-05, "loss": 4.0415, "step": 789504 }, { "epoch": 1.01, "learning_rate": 3.70650199199011e-05, "loss": 4.032, "step": 790016 }, { "epoch": 1.01, "learning_rate": 3.705663397239058e-05, "loss": 4.025, "step": 790528 }, { "epoch": 1.01, "learning_rate": 3.704824802488006e-05, "loss": 4.0191, "step": 791040 }, { "epoch": 1.01, "learning_rate": 3.703987845617327e-05, "loss": 4.0247, "step": 791552 }, { "epoch": 1.01, "learning_rate": 3.703149250866275e-05, "loss": 4.0296, "step": 792064 }, { "epoch": 1.01, "learning_rate": 3.702310656115223e-05, "loss": 4.0167, "step": 792576 }, { "epoch": 1.01, "learning_rate": 3.701472061364171e-05, "loss": 4.0447, "step": 793088 }, { "epoch": 1.01, "learning_rate": 3.700633466613119e-05, "loss": 4.0274, "step": 793600 }, { "epoch": 1.01, "learning_rate": 3.699794871862067e-05, "loss": 4.0142, "step": 794112 }, { "epoch": 1.01, "learning_rate": 3.698956277111015e-05, "loss": 4.0412, "step": 794624 }, { "epoch": 1.01, "learning_rate": 3.698117682359963e-05, "loss": 4.0169, "step": 795136 }, { "epoch": 1.01, "learning_rate": 3.6972807254892846e-05, "loss": 4.0194, "step": 795648 }, { "epoch": 1.01, "learning_rate": 3.6964421307382326e-05, "loss": 4.0336, "step": 796160 }, { "epoch": 1.01, "learning_rate": 3.69560353598718e-05, "loss": 4.0288, "step": 796672 }, { "epoch": 1.01, "learning_rate": 3.694764941236128e-05, "loss": 4.0223, "step": 797184 }, { "epoch": 1.01, "learning_rate": 3.6939279843654495e-05, "loss": 4.0231, "step": 797696 }, { "epoch": 1.01, "learning_rate": 3.6930893896143975e-05, "loss": 4.0204, "step": 798208 }, { "epoch": 1.01, "learning_rate": 3.6922524327437184e-05, "loss": 4.0274, "step": 798720 }, { "epoch": 1.01, "learning_rate": 3.6914138379926664e-05, "loss": 4.0352, "step": 799232 }, { "epoch": 1.01, "learning_rate": 3.690576881121987e-05, "loss": 4.0277, "step": 799744 }, { "epoch": 1.01, "learning_rate": 3.689739924251309e-05, "loss": 4.0289, "step": 800256 }, { "epoch": 1.01, "learning_rate": 3.688901329500257e-05, "loss": 4.028, "step": 800768 }, { "epoch": 1.01, "learning_rate": 3.688062734749205e-05, "loss": 4.0449, "step": 801280 }, { "epoch": 1.01, "learning_rate": 3.687224139998153e-05, "loss": 4.0193, "step": 801792 }, { "epoch": 1.01, "learning_rate": 3.686385545247101e-05, "loss": 4.0304, "step": 802304 }, { "epoch": 1.01, "learning_rate": 3.685546950496049e-05, "loss": 4.0318, "step": 802816 }, { "epoch": 1.01, "learning_rate": 3.684708355744997e-05, "loss": 4.017, "step": 803328 }, { "epoch": 1.01, "learning_rate": 3.683869760993945e-05, "loss": 4.0282, "step": 803840 }, { "epoch": 1.01, "learning_rate": 3.683031166242892e-05, "loss": 4.0334, "step": 804352 }, { "epoch": 1.01, "learning_rate": 3.68219257149184e-05, "loss": 4.0373, "step": 804864 }, { "epoch": 1.01, "learning_rate": 3.681353976740788e-05, "loss": 4.04, "step": 805376 }, { "epoch": 1.01, "learning_rate": 3.680515381989736e-05, "loss": 4.0103, "step": 805888 }, { "epoch": 1.01, "learning_rate": 3.679676787238684e-05, "loss": 4.012, "step": 806400 }, { "epoch": 1.01, "learning_rate": 3.6788414682483794e-05, "loss": 4.0264, "step": 806912 }, { "epoch": 1.01, "learning_rate": 3.6780028734973274e-05, "loss": 4.0324, "step": 807424 }, { "epoch": 1.01, "learning_rate": 3.677164278746275e-05, "loss": 4.0199, "step": 807936 }, { "epoch": 1.01, "learning_rate": 3.676325683995223e-05, "loss": 4.0247, "step": 808448 }, { "epoch": 1.01, "learning_rate": 3.675487089244171e-05, "loss": 4.0235, "step": 808960 }, { "epoch": 1.02, "learning_rate": 3.6746484944931187e-05, "loss": 4.0315, "step": 809472 }, { "epoch": 1.02, "learning_rate": 3.6738098997420667e-05, "loss": 4.0224, "step": 809984 }, { "epoch": 1.02, "learning_rate": 3.6729713049910146e-05, "loss": 4.0218, "step": 810496 }, { "epoch": 1.02, "learning_rate": 3.6721327102399626e-05, "loss": 4.0283, "step": 811008 }, { "epoch": 1.02, "learning_rate": 3.6712941154889106e-05, "loss": 4.0338, "step": 811520 }, { "epoch": 1.02, "learning_rate": 3.6704555207378586e-05, "loss": 4.0309, "step": 812032 }, { "epoch": 1.02, "learning_rate": 3.6696169259868066e-05, "loss": 4.0172, "step": 812544 }, { "epoch": 1.02, "learning_rate": 3.6687799691161275e-05, "loss": 4.0177, "step": 813056 }, { "epoch": 1.02, "learning_rate": 3.667941374365076e-05, "loss": 4.026, "step": 813568 }, { "epoch": 1.02, "learning_rate": 3.667104417494397e-05, "loss": 4.0313, "step": 814080 }, { "epoch": 1.02, "learning_rate": 3.666265822743345e-05, "loss": 4.0337, "step": 814592 }, { "epoch": 1.02, "learning_rate": 3.665427227992293e-05, "loss": 4.0209, "step": 815104 }, { "epoch": 1.02, "learning_rate": 3.664588633241241e-05, "loss": 4.0229, "step": 815616 }, { "epoch": 1.02, "learning_rate": 3.663751676370562e-05, "loss": 4.0166, "step": 816128 }, { "epoch": 1.02, "learning_rate": 3.66291308161951e-05, "loss": 4.0225, "step": 816640 }, { "epoch": 1.02, "learning_rate": 3.662074486868458e-05, "loss": 4.0165, "step": 817152 }, { "epoch": 1.02, "learning_rate": 3.661235892117406e-05, "loss": 4.0161, "step": 817664 }, { "epoch": 1.02, "learning_rate": 3.660397297366354e-05, "loss": 4.0286, "step": 818176 }, { "epoch": 1.02, "learning_rate": 3.659558702615302e-05, "loss": 4.0175, "step": 818688 }, { "epoch": 1.02, "learning_rate": 3.65872010786425e-05, "loss": 4.0172, "step": 819200 }, { "epoch": 1.02, "learning_rate": 3.657881513113198e-05, "loss": 4.0171, "step": 819712 }, { "epoch": 1.02, "learning_rate": 3.6570445562425196e-05, "loss": 4.0163, "step": 820224 }, { "epoch": 1.02, "learning_rate": 3.6562059614914676e-05, "loss": 4.0274, "step": 820736 }, { "epoch": 1.02, "learning_rate": 3.6553673667404156e-05, "loss": 4.0225, "step": 821248 }, { "epoch": 1.02, "learning_rate": 3.6545287719893636e-05, "loss": 4.0328, "step": 821760 }, { "epoch": 1.02, "learning_rate": 3.6536918151186845e-05, "loss": 4.029, "step": 822272 }, { "epoch": 1.02, "learning_rate": 3.6528532203676325e-05, "loss": 4.0265, "step": 822784 }, { "epoch": 1.02, "learning_rate": 3.6520162634969534e-05, "loss": 4.0261, "step": 823296 }, { "epoch": 1.02, "learning_rate": 3.6511776687459014e-05, "loss": 4.0206, "step": 823808 }, { "epoch": 1.02, "learning_rate": 3.650340711875222e-05, "loss": 4.0222, "step": 824320 }, { "epoch": 1.02, "learning_rate": 3.64950211712417e-05, "loss": 4.0304, "step": 824832 }, { "epoch": 1.02, "learning_rate": 3.648663522373118e-05, "loss": 4.0222, "step": 825344 }, { "epoch": 1.02, "learning_rate": 3.647824927622067e-05, "loss": 4.0269, "step": 825856 }, { "epoch": 1.02, "learning_rate": 3.646986332871015e-05, "loss": 4.0125, "step": 826368 }, { "epoch": 1.02, "learning_rate": 3.646147738119963e-05, "loss": 4.0272, "step": 826880 }, { "epoch": 1.02, "learning_rate": 3.645309143368911e-05, "loss": 4.0178, "step": 827392 }, { "epoch": 1.02, "learning_rate": 3.644470548617858e-05, "loss": 4.0154, "step": 827904 }, { "epoch": 1.02, "learning_rate": 3.643631953866806e-05, "loss": 4.0251, "step": 828416 }, { "epoch": 1.02, "learning_rate": 3.642793359115754e-05, "loss": 4.0065, "step": 828928 }, { "epoch": 1.02, "learning_rate": 3.641954764364702e-05, "loss": 4.0434, "step": 829440 }, { "epoch": 1.02, "learning_rate": 3.64111616961365e-05, "loss": 4.017, "step": 829952 }, { "epoch": 1.02, "learning_rate": 3.640277574862598e-05, "loss": 4.0275, "step": 830464 }, { "epoch": 1.02, "learning_rate": 3.639438980111546e-05, "loss": 4.0121, "step": 830976 }, { "epoch": 1.02, "learning_rate": 3.638602023240867e-05, "loss": 4.0273, "step": 831488 }, { "epoch": 1.02, "learning_rate": 3.637763428489815e-05, "loss": 4.0201, "step": 832000 }, { "epoch": 1.02, "learning_rate": 3.636924833738764e-05, "loss": 4.027, "step": 832512 }, { "epoch": 1.02, "learning_rate": 3.636087876868085e-05, "loss": 4.0221, "step": 833024 }, { "epoch": 1.02, "learning_rate": 3.635249282117033e-05, "loss": 4.0222, "step": 833536 }, { "epoch": 1.02, "learning_rate": 3.634410687365981e-05, "loss": 4.0234, "step": 834048 }, { "epoch": 1.02, "learning_rate": 3.633572092614929e-05, "loss": 4.0428, "step": 834560 }, { "epoch": 1.02, "learning_rate": 3.632733497863877e-05, "loss": 4.008, "step": 835072 }, { "epoch": 1.02, "learning_rate": 3.631894903112825e-05, "loss": 4.0352, "step": 835584 }, { "epoch": 1.02, "learning_rate": 3.631056308361773e-05, "loss": 4.029, "step": 836096 }, { "epoch": 1.02, "learning_rate": 3.630217713610721e-05, "loss": 4.0215, "step": 836608 }, { "epoch": 1.02, "learning_rate": 3.629379118859669e-05, "loss": 4.0154, "step": 837120 }, { "epoch": 1.02, "learning_rate": 3.6285421619889896e-05, "loss": 4.0262, "step": 837632 }, { "epoch": 1.02, "learning_rate": 3.6277035672379376e-05, "loss": 4.0205, "step": 838144 }, { "epoch": 1.02, "learning_rate": 3.626866610367259e-05, "loss": 4.0221, "step": 838656 }, { "epoch": 1.02, "learning_rate": 3.626028015616207e-05, "loss": 4.0192, "step": 839168 }, { "epoch": 1.03, "eval_loss": 4.062204360961914, "eval_runtime": 293.2429, "eval_samples_per_second": 1301.28, "eval_steps_per_second": 40.666, "step": 839520 }, { "epoch": 0.0, "learning_rate": 3.625189420865155e-05, "loss": 4.0161, "step": 839680 }, { "epoch": 0.0, "learning_rate": 3.624350826114103e-05, "loss": 4.0081, "step": 840192 }, { "epoch": 0.0, "learning_rate": 3.623512231363051e-05, "loss": 4.0203, "step": 840704 }, { "epoch": 0.0, "learning_rate": 3.622673636611999e-05, "loss": 4.0317, "step": 841216 }, { "epoch": 0.0, "learning_rate": 3.621835041860947e-05, "loss": 4.0298, "step": 841728 }, { "epoch": 0.0, "learning_rate": 3.6209964471098945e-05, "loss": 4.0174, "step": 842240 }, { "epoch": 0.0, "learning_rate": 3.6201578523588425e-05, "loss": 4.028, "step": 842752 }, { "epoch": 0.0, "learning_rate": 3.6193192576077905e-05, "loss": 4.0164, "step": 843264 }, { "epoch": 0.0, "learning_rate": 3.6184806628567384e-05, "loss": 4.0147, "step": 843776 }, { "epoch": 0.0, "learning_rate": 3.6176420681056864e-05, "loss": 4.026, "step": 844288 }, { "epoch": 0.0, "learning_rate": 3.6168034733546344e-05, "loss": 4.0278, "step": 844800 }, { "epoch": 0.0, "learning_rate": 3.6159648786035824e-05, "loss": 4.028, "step": 845312 }, { "epoch": 0.0, "learning_rate": 3.6151262838525304e-05, "loss": 4.0231, "step": 845824 }, { "epoch": 0.0, "learning_rate": 3.6142876891014784e-05, "loss": 4.0132, "step": 846336 }, { "epoch": 0.0, "learning_rate": 3.613449094350427e-05, "loss": 4.015, "step": 846848 }, { "epoch": 0.0, "learning_rate": 3.612610499599375e-05, "loss": 4.0014, "step": 847360 }, { "epoch": 0.0, "learning_rate": 3.611771904848323e-05, "loss": 4.0204, "step": 847872 }, { "epoch": 0.0, "learning_rate": 3.610934947977644e-05, "loss": 4.0179, "step": 848384 }, { "epoch": 0.0, "learning_rate": 3.610096353226592e-05, "loss": 4.0092, "step": 848896 }, { "epoch": 0.0, "learning_rate": 3.60925775847554e-05, "loss": 4.0231, "step": 849408 }, { "epoch": 0.0, "learning_rate": 3.608419163724488e-05, "loss": 4.0314, "step": 849920 }, { "epoch": 0.0, "learning_rate": 3.607580568973436e-05, "loss": 4.0262, "step": 850432 }, { "epoch": 0.0, "learning_rate": 3.606741974222383e-05, "loss": 4.0249, "step": 850944 }, { "epoch": 0.0, "learning_rate": 3.605903379471331e-05, "loss": 4.0198, "step": 851456 }, { "epoch": 0.0, "learning_rate": 3.605064784720279e-05, "loss": 4.0236, "step": 851968 }, { "epoch": 0.0, "learning_rate": 3.604227827849601e-05, "loss": 4.0201, "step": 852480 }, { "epoch": 0.0, "learning_rate": 3.603389233098549e-05, "loss": 4.0106, "step": 852992 }, { "epoch": 0.0, "learning_rate": 3.602550638347497e-05, "loss": 4.0076, "step": 853504 }, { "epoch": 0.0, "learning_rate": 3.601712043596445e-05, "loss": 4.0178, "step": 854016 }, { "epoch": 0.0, "learning_rate": 3.600875086725766e-05, "loss": 4.0124, "step": 854528 }, { "epoch": 0.01, "learning_rate": 3.600036491974714e-05, "loss": 4.0175, "step": 855040 }, { "epoch": 0.01, "learning_rate": 3.599197897223662e-05, "loss": 4.0181, "step": 855552 }, { "epoch": 0.01, "learning_rate": 3.59835930247261e-05, "loss": 4.0189, "step": 856064 }, { "epoch": 0.01, "learning_rate": 3.597522345601931e-05, "loss": 4.028, "step": 856576 }, { "epoch": 0.01, "learning_rate": 3.596683750850879e-05, "loss": 4.0104, "step": 857088 }, { "epoch": 0.01, "learning_rate": 3.5958467939802e-05, "loss": 4.0215, "step": 857600 }, { "epoch": 0.01, "learning_rate": 3.5950081992291476e-05, "loss": 4.0249, "step": 858112 }, { "epoch": 0.01, "learning_rate": 3.594169604478096e-05, "loss": 4.0016, "step": 858624 }, { "epoch": 0.01, "learning_rate": 3.593332647607418e-05, "loss": 4.0188, "step": 859136 }, { "epoch": 0.01, "learning_rate": 3.592494052856366e-05, "loss": 4.009, "step": 859648 }, { "epoch": 0.01, "learning_rate": 3.591655458105313e-05, "loss": 4.0113, "step": 860160 }, { "epoch": 0.01, "learning_rate": 3.590816863354261e-05, "loss": 4.0161, "step": 860672 }, { "epoch": 0.01, "learning_rate": 3.589978268603209e-05, "loss": 4.0133, "step": 861184 }, { "epoch": 0.01, "learning_rate": 3.589139673852157e-05, "loss": 4.0176, "step": 861696 }, { "epoch": 0.01, "learning_rate": 3.588301079101105e-05, "loss": 4.0235, "step": 862208 }, { "epoch": 0.01, "learning_rate": 3.587462484350053e-05, "loss": 4.0219, "step": 862720 }, { "epoch": 0.01, "learning_rate": 3.586623889599001e-05, "loss": 4.0241, "step": 863232 }, { "epoch": 0.01, "learning_rate": 3.585785294847949e-05, "loss": 4.0142, "step": 863744 }, { "epoch": 0.01, "learning_rate": 3.584946700096897e-05, "loss": 3.9888, "step": 864256 }, { "epoch": 0.01, "learning_rate": 3.584108105345845e-05, "loss": 4.0248, "step": 864768 }, { "epoch": 0.01, "learning_rate": 3.5832727863555396e-05, "loss": 4.0127, "step": 865280 }, { "epoch": 0.01, "learning_rate": 3.5824341916044876e-05, "loss": 4.0241, "step": 865792 }, { "epoch": 0.01, "learning_rate": 3.5815955968534356e-05, "loss": 4.0131, "step": 866304 }, { "epoch": 0.01, "learning_rate": 3.5807570021023836e-05, "loss": 4.0026, "step": 866816 }, { "epoch": 0.01, "learning_rate": 3.5799184073513316e-05, "loss": 4.0073, "step": 867328 }, { "epoch": 0.01, "learning_rate": 3.5790798126002796e-05, "loss": 4.0006, "step": 867840 }, { "epoch": 0.01, "learning_rate": 3.5782412178492276e-05, "loss": 4.0122, "step": 868352 }, { "epoch": 0.01, "learning_rate": 3.5774042609785485e-05, "loss": 3.9934, "step": 868864 }, { "epoch": 0.01, "learning_rate": 3.5765656662274965e-05, "loss": 4.0311, "step": 869376 }, { "epoch": 0.01, "learning_rate": 3.5757270714764445e-05, "loss": 4.0111, "step": 869888 }, { "epoch": 0.01, "learning_rate": 3.5748884767253925e-05, "loss": 3.9913, "step": 870400 }, { "epoch": 0.01, "learning_rate": 3.5740515198547134e-05, "loss": 4.0199, "step": 870912 }, { "epoch": 0.01, "learning_rate": 3.5732129251036614e-05, "loss": 3.9995, "step": 871424 }, { "epoch": 0.01, "learning_rate": 3.5723743303526094e-05, "loss": 4.0023, "step": 871936 }, { "epoch": 0.01, "learning_rate": 3.571535735601558e-05, "loss": 4.0097, "step": 872448 }, { "epoch": 0.01, "learning_rate": 3.570698778730879e-05, "loss": 4.0104, "step": 872960 }, { "epoch": 0.01, "learning_rate": 3.569860183979827e-05, "loss": 4.0038, "step": 873472 }, { "epoch": 0.01, "learning_rate": 3.569021589228775e-05, "loss": 4.0086, "step": 873984 }, { "epoch": 0.01, "learning_rate": 3.568182994477723e-05, "loss": 3.9977, "step": 874496 }, { "epoch": 0.01, "learning_rate": 3.567344399726671e-05, "loss": 4.0084, "step": 875008 }, { "epoch": 0.01, "learning_rate": 3.566505804975619e-05, "loss": 4.0159, "step": 875520 }, { "epoch": 0.01, "learning_rate": 3.565667210224566e-05, "loss": 4.0083, "step": 876032 }, { "epoch": 0.01, "learning_rate": 3.564828615473514e-05, "loss": 4.015, "step": 876544 }, { "epoch": 0.01, "learning_rate": 3.563990020722462e-05, "loss": 4.0046, "step": 877056 }, { "epoch": 0.01, "learning_rate": 3.56315142597141e-05, "loss": 4.0298, "step": 877568 }, { "epoch": 0.01, "learning_rate": 3.562314469100732e-05, "loss": 3.9983, "step": 878080 }, { "epoch": 0.01, "learning_rate": 3.56147587434968e-05, "loss": 4.0142, "step": 878592 }, { "epoch": 0.01, "learning_rate": 3.560637279598628e-05, "loss": 4.0047, "step": 879104 }, { "epoch": 0.01, "learning_rate": 3.5598003227279494e-05, "loss": 4.0062, "step": 879616 }, { "epoch": 0.01, "learning_rate": 3.558961727976897e-05, "loss": 4.0054, "step": 880128 }, { "epoch": 0.01, "learning_rate": 3.558123133225845e-05, "loss": 4.0155, "step": 880640 }, { "epoch": 0.01, "learning_rate": 3.557284538474793e-05, "loss": 4.0175, "step": 881152 }, { "epoch": 0.01, "learning_rate": 3.556445943723741e-05, "loss": 4.019, "step": 881664 }, { "epoch": 0.01, "learning_rate": 3.555607348972689e-05, "loss": 3.9923, "step": 882176 }, { "epoch": 0.01, "learning_rate": 3.554768754221637e-05, "loss": 3.9937, "step": 882688 }, { "epoch": 0.01, "learning_rate": 3.553930159470585e-05, "loss": 4.006, "step": 883200 }, { "epoch": 0.01, "learning_rate": 3.5530932025999056e-05, "loss": 4.0142, "step": 883712 }, { "epoch": 0.01, "learning_rate": 3.5522546078488536e-05, "loss": 4.001, "step": 884224 }, { "epoch": 0.01, "learning_rate": 3.551417650978175e-05, "loss": 4.0042, "step": 884736 }, { "epoch": 0.01, "learning_rate": 3.550579056227123e-05, "loss": 4.0089, "step": 885248 }, { "epoch": 0.02, "learning_rate": 3.549740461476071e-05, "loss": 4.0077, "step": 885760 }, { "epoch": 0.02, "learning_rate": 3.548901866725019e-05, "loss": 4.0072, "step": 886272 }, { "epoch": 0.02, "learning_rate": 3.548063271973967e-05, "loss": 4.0046, "step": 886784 }, { "epoch": 0.02, "learning_rate": 3.547226315103288e-05, "loss": 4.0097, "step": 887296 }, { "epoch": 0.02, "learning_rate": 3.546387720352236e-05, "loss": 4.0122, "step": 887808 }, { "epoch": 0.02, "learning_rate": 3.545549125601184e-05, "loss": 4.016, "step": 888320 }, { "epoch": 0.02, "learning_rate": 3.544710530850132e-05, "loss": 3.9962, "step": 888832 }, { "epoch": 0.02, "learning_rate": 3.54387193609908e-05, "loss": 3.9984, "step": 889344 }, { "epoch": 0.02, "learning_rate": 3.543033341348028e-05, "loss": 4.0086, "step": 889856 }, { "epoch": 0.02, "learning_rate": 3.542196384477349e-05, "loss": 4.0111, "step": 890368 }, { "epoch": 0.02, "learning_rate": 3.541357789726297e-05, "loss": 4.0167, "step": 890880 }, { "epoch": 0.02, "learning_rate": 3.5405191949752456e-05, "loss": 4.0034, "step": 891392 }, { "epoch": 0.02, "learning_rate": 3.5396806002241936e-05, "loss": 4.0081, "step": 891904 }, { "epoch": 0.02, "learning_rate": 3.5388420054731416e-05, "loss": 3.9983, "step": 892416 }, { "epoch": 0.02, "learning_rate": 3.5380034107220896e-05, "loss": 4.0032, "step": 892928 }, { "epoch": 0.02, "learning_rate": 3.5371648159710376e-05, "loss": 4.0, "step": 893440 }, { "epoch": 0.02, "learning_rate": 3.5363278591003585e-05, "loss": 3.9973, "step": 893952 }, { "epoch": 0.02, "learning_rate": 3.5354892643493065e-05, "loss": 4.0059, "step": 894464 }, { "epoch": 0.02, "learning_rate": 3.5346506695982545e-05, "loss": 4.0015, "step": 894976 }, { "epoch": 0.02, "learning_rate": 3.5338120748472025e-05, "loss": 3.9986, "step": 895488 }, { "epoch": 0.02, "learning_rate": 3.53297348009615e-05, "loss": 3.9998, "step": 896000 }, { "epoch": 0.02, "learning_rate": 3.532134885345098e-05, "loss": 3.9966, "step": 896512 }, { "epoch": 0.02, "learning_rate": 3.5312979284744194e-05, "loss": 4.0101, "step": 897024 }, { "epoch": 0.02, "learning_rate": 3.5304593337233674e-05, "loss": 4.0037, "step": 897536 }, { "epoch": 0.02, "learning_rate": 3.5296207389723154e-05, "loss": 4.013, "step": 898048 }, { "epoch": 0.02, "learning_rate": 3.5287821442212634e-05, "loss": 4.0066, "step": 898560 }, { "epoch": 0.02, "learning_rate": 3.5279435494702114e-05, "loss": 4.0125, "step": 899072 }, { "epoch": 0.02, "learning_rate": 3.527106592599532e-05, "loss": 4.0091, "step": 899584 }, { "epoch": 0.02, "learning_rate": 3.52626799784848e-05, "loss": 3.9967, "step": 900096 }, { "epoch": 0.02, "learning_rate": 3.525429403097428e-05, "loss": 4.0097, "step": 900608 }, { "epoch": 0.02, "learning_rate": 3.524590808346376e-05, "loss": 4.0065, "step": 901120 }, { "epoch": 0.02, "learning_rate": 3.523752213595324e-05, "loss": 4.0034, "step": 901632 }, { "epoch": 0.02, "learning_rate": 3.522913618844272e-05, "loss": 4.0128, "step": 902144 }, { "epoch": 0.02, "learning_rate": 3.52207502409322e-05, "loss": 3.9994, "step": 902656 }, { "epoch": 0.02, "learning_rate": 3.521236429342168e-05, "loss": 4.0046, "step": 903168 }, { "epoch": 0.02, "learning_rate": 3.520397834591116e-05, "loss": 3.9991, "step": 903680 }, { "epoch": 0.02, "learning_rate": 3.519559239840064e-05, "loss": 4.0001, "step": 904192 }, { "epoch": 0.02, "learning_rate": 3.518722282969386e-05, "loss": 4.0033, "step": 904704 }, { "epoch": 0.02, "learning_rate": 3.517883688218334e-05, "loss": 3.9941, "step": 905216 }, { "epoch": 0.02, "learning_rate": 3.517045093467282e-05, "loss": 4.0219, "step": 905728 }, { "epoch": 0.02, "learning_rate": 3.51620649871623e-05, "loss": 4.0043, "step": 906240 }, { "epoch": 0.02, "learning_rate": 3.515369541845551e-05, "loss": 4.0093, "step": 906752 }, { "epoch": 0.02, "learning_rate": 3.514530947094499e-05, "loss": 3.9958, "step": 907264 }, { "epoch": 0.02, "learning_rate": 3.513692352343447e-05, "loss": 4.0089, "step": 907776 }, { "epoch": 0.02, "learning_rate": 3.512853757592395e-05, "loss": 4.0056, "step": 908288 }, { "epoch": 0.02, "learning_rate": 3.512015162841343e-05, "loss": 4.0099, "step": 908800 }, { "epoch": 0.02, "learning_rate": 3.5111782059706636e-05, "loss": 4.0034, "step": 909312 }, { "epoch": 0.02, "learning_rate": 3.5103396112196116e-05, "loss": 4.0028, "step": 909824 }, { "epoch": 0.02, "learning_rate": 3.5095010164685596e-05, "loss": 4.0035, "step": 910336 }, { "epoch": 0.02, "learning_rate": 3.5086624217175076e-05, "loss": 4.0256, "step": 910848 }, { "epoch": 0.02, "learning_rate": 3.507825464846829e-05, "loss": 3.9957, "step": 911360 }, { "epoch": 0.02, "learning_rate": 3.506986870095777e-05, "loss": 4.0164, "step": 911872 }, { "epoch": 0.02, "learning_rate": 3.506148275344725e-05, "loss": 4.0115, "step": 912384 }, { "epoch": 0.02, "learning_rate": 3.505309680593673e-05, "loss": 4.001, "step": 912896 }, { "epoch": 0.02, "learning_rate": 3.504471085842621e-05, "loss": 4.005, "step": 913408 }, { "epoch": 0.02, "learning_rate": 3.5036324910915685e-05, "loss": 4.0036, "step": 913920 }, { "epoch": 0.02, "learning_rate": 3.5027938963405165e-05, "loss": 4.0025, "step": 914432 }, { "epoch": 0.02, "learning_rate": 3.501956939469838e-05, "loss": 4.0033, "step": 914944 }, { "epoch": 0.02, "learning_rate": 3.501118344718786e-05, "loss": 4.0024, "step": 915456 }, { "epoch": 0.03, "eval_loss": 4.050577640533447, "eval_runtime": 287.2056, "eval_samples_per_second": 1328.634, "eval_steps_per_second": 41.521, "step": 915840 }, { "epoch": 1.0, "learning_rate": 3.5002797499677334e-05, "loss": 4.0017, "step": 915968 }, { "epoch": 1.0, "learning_rate": 3.4994411552166814e-05, "loss": 3.9868, "step": 916480 }, { "epoch": 1.0, "learning_rate": 3.4986025604656294e-05, "loss": 4.0009, "step": 916992 }, { "epoch": 1.0, "learning_rate": 3.4977672414753246e-05, "loss": 4.019, "step": 917504 }, { "epoch": 1.0, "learning_rate": 3.4969286467242726e-05, "loss": 4.0082, "step": 918016 }, { "epoch": 1.0, "learning_rate": 3.4960900519732206e-05, "loss": 4.0008, "step": 918528 }, { "epoch": 1.0, "learning_rate": 3.4952514572221686e-05, "loss": 4.0154, "step": 919040 }, { "epoch": 1.0, "learning_rate": 3.494412862471116e-05, "loss": 3.9952, "step": 919552 }, { "epoch": 1.0, "learning_rate": 3.4935759056004375e-05, "loss": 3.9963, "step": 920064 }, { "epoch": 1.0, "learning_rate": 3.4927373108493855e-05, "loss": 4.0112, "step": 920576 }, { "epoch": 1.0, "learning_rate": 3.4918987160983335e-05, "loss": 4.0104, "step": 921088 }, { "epoch": 1.0, "learning_rate": 3.491060121347281e-05, "loss": 4.0069, "step": 921600 }, { "epoch": 1.0, "learning_rate": 3.4902231644766024e-05, "loss": 4.0124, "step": 922112 }, { "epoch": 1.0, "learning_rate": 3.4893845697255504e-05, "loss": 3.9931, "step": 922624 }, { "epoch": 1.0, "learning_rate": 3.4885459749744984e-05, "loss": 3.995, "step": 923136 }, { "epoch": 1.0, "learning_rate": 3.4877073802234464e-05, "loss": 3.9869, "step": 923648 }, { "epoch": 1.0, "learning_rate": 3.4868687854723944e-05, "loss": 4.0029, "step": 924160 }, { "epoch": 1.0, "learning_rate": 3.4860301907213424e-05, "loss": 4.0024, "step": 924672 }, { "epoch": 1.0, "learning_rate": 3.4851915959702903e-05, "loss": 3.9923, "step": 925184 }, { "epoch": 1.0, "learning_rate": 3.4843530012192383e-05, "loss": 3.998, "step": 925696 }, { "epoch": 1.0, "learning_rate": 3.4835144064681863e-05, "loss": 4.021, "step": 926208 }, { "epoch": 1.0, "learning_rate": 3.482675811717134e-05, "loss": 4.0037, "step": 926720 }, { "epoch": 1.0, "learning_rate": 3.481837216966082e-05, "loss": 4.0079, "step": 927232 }, { "epoch": 1.0, "learning_rate": 3.48099862221503e-05, "loss": 4.0045, "step": 927744 }, { "epoch": 1.0, "learning_rate": 3.480161665344351e-05, "loss": 4.0083, "step": 928256 }, { "epoch": 1.0, "learning_rate": 3.479324708473672e-05, "loss": 4.0017, "step": 928768 }, { "epoch": 1.0, "learning_rate": 3.47848611372262e-05, "loss": 3.9965, "step": 929280 }, { "epoch": 1.0, "learning_rate": 3.477647518971569e-05, "loss": 3.9888, "step": 929792 }, { "epoch": 1.0, "learning_rate": 3.476808924220517e-05, "loss": 4.0023, "step": 930304 }, { "epoch": 1.0, "learning_rate": 3.475970329469465e-05, "loss": 3.9913, "step": 930816 }, { "epoch": 1.01, "learning_rate": 3.475131734718413e-05, "loss": 4.0015, "step": 931328 }, { "epoch": 1.01, "learning_rate": 3.474293139967361e-05, "loss": 3.9989, "step": 931840 }, { "epoch": 1.01, "learning_rate": 3.473454545216309e-05, "loss": 4.0087, "step": 932352 }, { "epoch": 1.01, "learning_rate": 3.47261758834563e-05, "loss": 4.007, "step": 932864 }, { "epoch": 1.01, "learning_rate": 3.471778993594578e-05, "loss": 3.9983, "step": 933376 }, { "epoch": 1.01, "learning_rate": 3.4709420367238986e-05, "loss": 4.006, "step": 933888 }, { "epoch": 1.01, "learning_rate": 3.4701034419728466e-05, "loss": 4.0079, "step": 934400 }, { "epoch": 1.01, "learning_rate": 3.4692648472217946e-05, "loss": 3.9825, "step": 934912 }, { "epoch": 1.01, "learning_rate": 3.4684262524707426e-05, "loss": 3.9996, "step": 935424 }, { "epoch": 1.01, "learning_rate": 3.4675876577196906e-05, "loss": 3.9942, "step": 935936 }, { "epoch": 1.01, "learning_rate": 3.4667490629686386e-05, "loss": 3.9905, "step": 936448 }, { "epoch": 1.01, "learning_rate": 3.4659104682175866e-05, "loss": 4.0021, "step": 936960 }, { "epoch": 1.01, "learning_rate": 3.465073511346908e-05, "loss": 3.9985, "step": 937472 }, { "epoch": 1.01, "learning_rate": 3.464234916595856e-05, "loss": 4.0001, "step": 937984 }, { "epoch": 1.01, "learning_rate": 3.463396321844804e-05, "loss": 4.0041, "step": 938496 }, { "epoch": 1.01, "learning_rate": 3.462557727093752e-05, "loss": 4.0054, "step": 939008 }, { "epoch": 1.01, "learning_rate": 3.4617191323426995e-05, "loss": 4.0068, "step": 939520 }, { "epoch": 1.01, "learning_rate": 3.4608805375916475e-05, "loss": 4.0013, "step": 940032 }, { "epoch": 1.01, "learning_rate": 3.460043580720969e-05, "loss": 3.9728, "step": 940544 }, { "epoch": 1.01, "learning_rate": 3.459204985969917e-05, "loss": 4.0036, "step": 941056 }, { "epoch": 1.01, "learning_rate": 3.4583663912188644e-05, "loss": 4.0002, "step": 941568 }, { "epoch": 1.01, "learning_rate": 3.4575277964678124e-05, "loss": 4.0072, "step": 942080 }, { "epoch": 1.01, "learning_rate": 3.4566892017167604e-05, "loss": 3.9976, "step": 942592 }, { "epoch": 1.01, "learning_rate": 3.455850606965709e-05, "loss": 3.9897, "step": 943104 }, { "epoch": 1.01, "learning_rate": 3.455012012214657e-05, "loss": 3.9853, "step": 943616 }, { "epoch": 1.01, "learning_rate": 3.454173417463605e-05, "loss": 3.9868, "step": 944128 }, { "epoch": 1.01, "learning_rate": 3.453334822712553e-05, "loss": 3.9946, "step": 944640 }, { "epoch": 1.01, "learning_rate": 3.452499503722247e-05, "loss": 3.9769, "step": 945152 }, { "epoch": 1.01, "learning_rate": 3.451660908971195e-05, "loss": 4.0137, "step": 945664 }, { "epoch": 1.01, "learning_rate": 3.450822314220143e-05, "loss": 3.9961, "step": 946176 }, { "epoch": 1.01, "learning_rate": 3.449983719469091e-05, "loss": 3.977, "step": 946688 }, { "epoch": 1.01, "learning_rate": 3.449145124718039e-05, "loss": 4.0023, "step": 947200 }, { "epoch": 1.01, "learning_rate": 3.448306529966987e-05, "loss": 3.9848, "step": 947712 }, { "epoch": 1.01, "learning_rate": 3.447467935215935e-05, "loss": 3.9848, "step": 948224 }, { "epoch": 1.01, "learning_rate": 3.446629340464883e-05, "loss": 3.9936, "step": 948736 }, { "epoch": 1.01, "learning_rate": 3.445790745713831e-05, "loss": 3.9955, "step": 949248 }, { "epoch": 1.01, "learning_rate": 3.4449537888431524e-05, "loss": 3.9822, "step": 949760 }, { "epoch": 1.01, "learning_rate": 3.444116831972473e-05, "loss": 3.9975, "step": 950272 }, { "epoch": 1.01, "learning_rate": 3.443278237221421e-05, "loss": 3.9815, "step": 950784 }, { "epoch": 1.01, "learning_rate": 3.442441280350742e-05, "loss": 3.9907, "step": 951296 }, { "epoch": 1.01, "learning_rate": 3.44160268559969e-05, "loss": 3.9997, "step": 951808 }, { "epoch": 1.01, "learning_rate": 3.440764090848638e-05, "loss": 3.9957, "step": 952320 }, { "epoch": 1.01, "learning_rate": 3.439925496097586e-05, "loss": 3.995, "step": 952832 }, { "epoch": 1.01, "learning_rate": 3.439086901346534e-05, "loss": 3.9905, "step": 953344 }, { "epoch": 1.01, "learning_rate": 3.438248306595482e-05, "loss": 4.0148, "step": 953856 }, { "epoch": 1.01, "learning_rate": 3.43740971184443e-05, "loss": 3.9805, "step": 954368 }, { "epoch": 1.01, "learning_rate": 3.436571117093378e-05, "loss": 3.9982, "step": 954880 }, { "epoch": 1.01, "learning_rate": 3.435732522342326e-05, "loss": 3.9877, "step": 955392 }, { "epoch": 1.01, "learning_rate": 3.434897203352021e-05, "loss": 3.9905, "step": 955904 }, { "epoch": 1.01, "learning_rate": 3.434058608600969e-05, "loss": 3.9926, "step": 956416 }, { "epoch": 1.01, "learning_rate": 3.433220013849917e-05, "loss": 3.9935, "step": 956928 }, { "epoch": 1.01, "learning_rate": 3.432381419098865e-05, "loss": 4.0052, "step": 957440 }, { "epoch": 1.01, "learning_rate": 3.4315428243478127e-05, "loss": 4.0035, "step": 957952 }, { "epoch": 1.01, "learning_rate": 3.4307042295967607e-05, "loss": 3.9781, "step": 958464 }, { "epoch": 1.01, "learning_rate": 3.4298672727260816e-05, "loss": 3.979, "step": 958976 }, { "epoch": 1.01, "learning_rate": 3.4290286779750296e-05, "loss": 3.9829, "step": 959488 }, { "epoch": 1.01, "learning_rate": 3.4281900832239776e-05, "loss": 3.9991, "step": 960000 }, { "epoch": 1.01, "learning_rate": 3.4273514884729256e-05, "loss": 3.9872, "step": 960512 }, { "epoch": 1.01, "learning_rate": 3.4265128937218735e-05, "loss": 3.9853, "step": 961024 }, { "epoch": 1.01, "learning_rate": 3.4256742989708215e-05, "loss": 3.9986, "step": 961536 }, { "epoch": 1.02, "learning_rate": 3.4248357042197695e-05, "loss": 3.988, "step": 962048 }, { "epoch": 1.02, "learning_rate": 3.423997109468718e-05, "loss": 3.9933, "step": 962560 }, { "epoch": 1.02, "learning_rate": 3.4231585147176655e-05, "loss": 3.9854, "step": 963072 }, { "epoch": 1.02, "learning_rate": 3.4223199199666135e-05, "loss": 3.9952, "step": 963584 }, { "epoch": 1.02, "learning_rate": 3.4214813252155615e-05, "loss": 3.9959, "step": 964096 }, { "epoch": 1.02, "learning_rate": 3.4206427304645095e-05, "loss": 3.9989, "step": 964608 }, { "epoch": 1.02, "learning_rate": 3.4198057735938304e-05, "loss": 3.9811, "step": 965120 }, { "epoch": 1.02, "learning_rate": 3.418968816723152e-05, "loss": 3.9826, "step": 965632 }, { "epoch": 1.02, "learning_rate": 3.4181302219721e-05, "loss": 3.9928, "step": 966144 }, { "epoch": 1.02, "learning_rate": 3.417291627221048e-05, "loss": 3.9921, "step": 966656 }, { "epoch": 1.02, "learning_rate": 3.416453032469995e-05, "loss": 4.006, "step": 967168 }, { "epoch": 1.02, "learning_rate": 3.415614437718943e-05, "loss": 3.9856, "step": 967680 }, { "epoch": 1.02, "learning_rate": 3.414775842967892e-05, "loss": 3.9892, "step": 968192 }, { "epoch": 1.02, "learning_rate": 3.41393724821684e-05, "loss": 3.9862, "step": 968704 }, { "epoch": 1.02, "learning_rate": 3.413098653465788e-05, "loss": 3.9813, "step": 969216 }, { "epoch": 1.02, "learning_rate": 3.412261696595109e-05, "loss": 3.988, "step": 969728 }, { "epoch": 1.02, "learning_rate": 3.411423101844057e-05, "loss": 3.9868, "step": 970240 }, { "epoch": 1.02, "learning_rate": 3.410584507093005e-05, "loss": 3.9891, "step": 970752 }, { "epoch": 1.02, "learning_rate": 3.409745912341953e-05, "loss": 3.9849, "step": 971264 }, { "epoch": 1.02, "learning_rate": 3.408908955471274e-05, "loss": 3.9817, "step": 971776 }, { "epoch": 1.02, "learning_rate": 3.408070360720222e-05, "loss": 3.9857, "step": 972288 }, { "epoch": 1.02, "learning_rate": 3.40723176596917e-05, "loss": 3.9785, "step": 972800 }, { "epoch": 1.02, "learning_rate": 3.406394809098491e-05, "loss": 3.9928, "step": 973312 }, { "epoch": 1.02, "learning_rate": 3.405556214347439e-05, "loss": 3.9927, "step": 973824 }, { "epoch": 1.02, "learning_rate": 3.4047176195963874e-05, "loss": 3.9924, "step": 974336 }, { "epoch": 1.02, "learning_rate": 3.4038790248453354e-05, "loss": 3.996, "step": 974848 }, { "epoch": 1.02, "learning_rate": 3.4030404300942833e-05, "loss": 3.995, "step": 975360 }, { "epoch": 1.02, "learning_rate": 3.402203473223604e-05, "loss": 3.992, "step": 975872 }, { "epoch": 1.02, "learning_rate": 3.401364878472552e-05, "loss": 3.9818, "step": 976384 }, { "epoch": 1.02, "learning_rate": 3.4005262837215e-05, "loss": 3.995, "step": 976896 }, { "epoch": 1.02, "learning_rate": 3.399687688970448e-05, "loss": 3.9892, "step": 977408 }, { "epoch": 1.02, "learning_rate": 3.398849094219396e-05, "loss": 3.9875, "step": 977920 }, { "epoch": 1.02, "learning_rate": 3.398010499468344e-05, "loss": 3.9969, "step": 978432 }, { "epoch": 1.02, "learning_rate": 3.397171904717292e-05, "loss": 3.9827, "step": 978944 }, { "epoch": 1.02, "learning_rate": 3.39633330996624e-05, "loss": 3.9911, "step": 979456 }, { "epoch": 1.02, "learning_rate": 3.395496353095561e-05, "loss": 3.9808, "step": 979968 }, { "epoch": 1.02, "learning_rate": 3.394657758344509e-05, "loss": 3.9862, "step": 980480 }, { "epoch": 1.02, "learning_rate": 3.393820801473831e-05, "loss": 3.9898, "step": 980992 }, { "epoch": 1.02, "learning_rate": 3.392982206722779e-05, "loss": 3.9807, "step": 981504 }, { "epoch": 1.02, "learning_rate": 3.392143611971727e-05, "loss": 4.0008, "step": 982016 }, { "epoch": 1.02, "learning_rate": 3.391305017220675e-05, "loss": 3.9909, "step": 982528 }, { "epoch": 1.02, "learning_rate": 3.390466422469623e-05, "loss": 3.9914, "step": 983040 }, { "epoch": 1.02, "learning_rate": 3.389627827718571e-05, "loss": 3.9848, "step": 983552 }, { "epoch": 1.02, "learning_rate": 3.388789232967519e-05, "loss": 3.9902, "step": 984064 }, { "epoch": 1.02, "learning_rate": 3.387950638216467e-05, "loss": 3.9937, "step": 984576 }, { "epoch": 1.02, "learning_rate": 3.387112043465414e-05, "loss": 3.9945, "step": 985088 }, { "epoch": 1.02, "learning_rate": 3.3862750865947356e-05, "loss": 3.9897, "step": 985600 }, { "epoch": 1.02, "learning_rate": 3.3854364918436836e-05, "loss": 3.9857, "step": 986112 }, { "epoch": 1.02, "learning_rate": 3.384597897092631e-05, "loss": 3.9912, "step": 986624 }, { "epoch": 1.02, "learning_rate": 3.383759302341579e-05, "loss": 4.0064, "step": 987136 }, { "epoch": 1.02, "learning_rate": 3.3829223454709005e-05, "loss": 3.9869, "step": 987648 }, { "epoch": 1.02, "learning_rate": 3.382083750719849e-05, "loss": 3.995, "step": 988160 }, { "epoch": 1.02, "learning_rate": 3.3812451559687965e-05, "loss": 3.9991, "step": 988672 }, { "epoch": 1.02, "learning_rate": 3.3804065612177445e-05, "loss": 3.9879, "step": 989184 }, { "epoch": 1.02, "learning_rate": 3.379569604347066e-05, "loss": 3.9897, "step": 989696 }, { "epoch": 1.02, "learning_rate": 3.378732647476387e-05, "loss": 3.9866, "step": 990208 }, { "epoch": 1.02, "learning_rate": 3.377894052725335e-05, "loss": 3.9882, "step": 990720 }, { "epoch": 1.02, "learning_rate": 3.377055457974283e-05, "loss": 3.9926, "step": 991232 }, { "epoch": 1.02, "learning_rate": 3.376216863223231e-05, "loss": 3.9838, "step": 991744 }, { "epoch": 1.03, "eval_loss": 4.041832447052002, "eval_runtime": 287.974, "eval_samples_per_second": 1325.088, "eval_steps_per_second": 41.41, "step": 992160 }, { "epoch": 0.0, "learning_rate": 3.375378268472178e-05, "loss": 4.0028, "step": 992256 }, { "epoch": 0.0, "learning_rate": 3.374539673721126e-05, "loss": 3.9708, "step": 992768 }, { "epoch": 0.0, "learning_rate": 3.373701078970074e-05, "loss": 3.9857, "step": 993280 }, { "epoch": 0.0, "learning_rate": 3.372862484219023e-05, "loss": 4.0051, "step": 993792 }, { "epoch": 0.0, "learning_rate": 3.372023889467971e-05, "loss": 3.9917, "step": 994304 }, { "epoch": 0.0, "learning_rate": 3.371185294716919e-05, "loss": 3.9877, "step": 994816 }, { "epoch": 0.0, "learning_rate": 3.370346699965867e-05, "loss": 3.9926, "step": 995328 }, { "epoch": 0.0, "learning_rate": 3.369508105214815e-05, "loss": 3.986, "step": 995840 }, { "epoch": 0.0, "learning_rate": 3.368669510463763e-05, "loss": 3.9783, "step": 996352 }, { "epoch": 0.0, "learning_rate": 3.367830915712711e-05, "loss": 3.9989, "step": 996864 }, { "epoch": 0.0, "learning_rate": 3.366992320961659e-05, "loss": 3.99, "step": 997376 }, { "epoch": 0.0, "learning_rate": 3.366153726210607e-05, "loss": 3.9941, "step": 997888 }, { "epoch": 0.0, "learning_rate": 3.365316769339928e-05, "loss": 3.9969, "step": 998400 }, { "epoch": 0.0, "learning_rate": 3.364478174588876e-05, "loss": 3.9775, "step": 998912 }, { "epoch": 0.0, "learning_rate": 3.363639579837824e-05, "loss": 3.9822, "step": 999424 }, { "epoch": 0.0, "learning_rate": 3.362800985086772e-05, "loss": 3.9705, "step": 999936 }, { "epoch": 0.0, "learning_rate": 3.36196239033572e-05, "loss": 3.989, "step": 1000448 }, { "epoch": 0.0, "learning_rate": 3.361123795584668e-05, "loss": 3.9861, "step": 1000960 }, { "epoch": 0.0, "learning_rate": 3.360285200833616e-05, "loss": 3.9792, "step": 1001472 }, { "epoch": 0.0, "learning_rate": 3.359446606082564e-05, "loss": 3.9833, "step": 1001984 }, { "epoch": 0.0, "learning_rate": 3.3586096492118854e-05, "loss": 4.0079, "step": 1002496 }, { "epoch": 0.0, "learning_rate": 3.357771054460833e-05, "loss": 3.987, "step": 1003008 }, { "epoch": 0.0, "learning_rate": 3.356932459709781e-05, "loss": 3.9921, "step": 1003520 }, { "epoch": 0.0, "learning_rate": 3.356093864958729e-05, "loss": 3.991, "step": 1004032 }, { "epoch": 0.0, "learning_rate": 3.355255270207677e-05, "loss": 3.9947, "step": 1004544 }, { "epoch": 0.0, "learning_rate": 3.354416675456625e-05, "loss": 3.9857, "step": 1005056 }, { "epoch": 0.0, "learning_rate": 3.353578080705573e-05, "loss": 3.9815, "step": 1005568 }, { "epoch": 0.0, "learning_rate": 3.3527411238348936e-05, "loss": 3.9807, "step": 1006080 }, { "epoch": 0.0, "learning_rate": 3.3519025290838416e-05, "loss": 3.9811, "step": 1006592 }, { "epoch": 0.0, "learning_rate": 3.3510639343327896e-05, "loss": 3.9781, "step": 1007104 }, { "epoch": 0.01, "learning_rate": 3.3502253395817376e-05, "loss": 3.9867, "step": 1007616 }, { "epoch": 0.01, "learning_rate": 3.349386744830686e-05, "loss": 3.9811, "step": 1008128 }, { "epoch": 0.01, "learning_rate": 3.348548150079634e-05, "loss": 3.9977, "step": 1008640 }, { "epoch": 0.01, "learning_rate": 3.347709555328582e-05, "loss": 3.9898, "step": 1009152 }, { "epoch": 0.01, "learning_rate": 3.34687096057753e-05, "loss": 3.9854, "step": 1009664 }, { "epoch": 0.01, "learning_rate": 3.346034003706851e-05, "loss": 3.9948, "step": 1010176 }, { "epoch": 0.01, "learning_rate": 3.345195408955799e-05, "loss": 3.9921, "step": 1010688 }, { "epoch": 0.01, "learning_rate": 3.344356814204747e-05, "loss": 3.9669, "step": 1011200 }, { "epoch": 0.01, "learning_rate": 3.343518219453695e-05, "loss": 3.9862, "step": 1011712 }, { "epoch": 0.01, "learning_rate": 3.342679624702643e-05, "loss": 3.9785, "step": 1012224 }, { "epoch": 0.01, "learning_rate": 3.341842667831964e-05, "loss": 3.9766, "step": 1012736 }, { "epoch": 0.01, "learning_rate": 3.341004073080912e-05, "loss": 3.9885, "step": 1013248 }, { "epoch": 0.01, "learning_rate": 3.34016547832986e-05, "loss": 3.9862, "step": 1013760 }, { "epoch": 0.01, "learning_rate": 3.339326883578808e-05, "loss": 3.9821, "step": 1014272 }, { "epoch": 0.01, "learning_rate": 3.338488288827756e-05, "loss": 3.9925, "step": 1014784 }, { "epoch": 0.01, "learning_rate": 3.337649694076704e-05, "loss": 3.9884, "step": 1015296 }, { "epoch": 0.01, "learning_rate": 3.336811099325652e-05, "loss": 3.9903, "step": 1015808 }, { "epoch": 0.01, "learning_rate": 3.3359725045746e-05, "loss": 3.9874, "step": 1016320 }, { "epoch": 0.01, "learning_rate": 3.3351355477039216e-05, "loss": 3.9609, "step": 1016832 }, { "epoch": 0.01, "learning_rate": 3.3342985908332425e-05, "loss": 3.9849, "step": 1017344 }, { "epoch": 0.01, "learning_rate": 3.3334599960821905e-05, "loss": 3.9907, "step": 1017856 }, { "epoch": 0.01, "learning_rate": 3.3326214013311385e-05, "loss": 3.989, "step": 1018368 }, { "epoch": 0.01, "learning_rate": 3.331782806580086e-05, "loss": 3.981, "step": 1018880 }, { "epoch": 0.01, "learning_rate": 3.3309458497094074e-05, "loss": 3.976, "step": 1019392 }, { "epoch": 0.01, "learning_rate": 3.330108892838728e-05, "loss": 3.9717, "step": 1019904 }, { "epoch": 0.01, "learning_rate": 3.329270298087677e-05, "loss": 3.9692, "step": 1020416 }, { "epoch": 0.01, "learning_rate": 3.328431703336625e-05, "loss": 3.984, "step": 1020928 }, { "epoch": 0.01, "learning_rate": 3.327593108585573e-05, "loss": 3.9643, "step": 1021440 }, { "epoch": 0.01, "learning_rate": 3.326754513834521e-05, "loss": 3.9921, "step": 1021952 }, { "epoch": 0.01, "learning_rate": 3.325915919083469e-05, "loss": 3.9842, "step": 1022464 }, { "epoch": 0.01, "learning_rate": 3.325077324332416e-05, "loss": 3.9656, "step": 1022976 }, { "epoch": 0.01, "learning_rate": 3.324238729581364e-05, "loss": 3.9857, "step": 1023488 }, { "epoch": 0.01, "learning_rate": 3.323400134830312e-05, "loss": 3.9677, "step": 1024000 }, { "epoch": 0.01, "learning_rate": 3.32256154007926e-05, "loss": 3.9718, "step": 1024512 }, { "epoch": 0.01, "learning_rate": 3.321724583208581e-05, "loss": 3.975, "step": 1025024 }, { "epoch": 0.01, "learning_rate": 3.320885988457529e-05, "loss": 3.9853, "step": 1025536 }, { "epoch": 0.01, "learning_rate": 3.320047393706477e-05, "loss": 3.9687, "step": 1026048 }, { "epoch": 0.01, "learning_rate": 3.319208798955425e-05, "loss": 3.9805, "step": 1026560 }, { "epoch": 0.01, "learning_rate": 3.318370204204374e-05, "loss": 3.9656, "step": 1027072 }, { "epoch": 0.01, "learning_rate": 3.317533247333695e-05, "loss": 3.9767, "step": 1027584 }, { "epoch": 0.01, "learning_rate": 3.316694652582643e-05, "loss": 3.9841, "step": 1028096 }, { "epoch": 0.01, "learning_rate": 3.315856057831591e-05, "loss": 3.9826, "step": 1028608 }, { "epoch": 0.01, "learning_rate": 3.315017463080539e-05, "loss": 3.9786, "step": 1029120 }, { "epoch": 0.01, "learning_rate": 3.314178868329487e-05, "loss": 3.9798, "step": 1029632 }, { "epoch": 0.01, "learning_rate": 3.313340273578435e-05, "loss": 3.9966, "step": 1030144 }, { "epoch": 0.01, "learning_rate": 3.312501678827383e-05, "loss": 3.9655, "step": 1030656 }, { "epoch": 0.01, "learning_rate": 3.3116647219567036e-05, "loss": 3.9861, "step": 1031168 }, { "epoch": 0.01, "learning_rate": 3.3108261272056516e-05, "loss": 3.9765, "step": 1031680 }, { "epoch": 0.01, "learning_rate": 3.3099875324545996e-05, "loss": 3.971, "step": 1032192 }, { "epoch": 0.01, "learning_rate": 3.3091489377035476e-05, "loss": 3.9747, "step": 1032704 }, { "epoch": 0.01, "learning_rate": 3.3083103429524956e-05, "loss": 3.9791, "step": 1033216 }, { "epoch": 0.01, "learning_rate": 3.307473386081817e-05, "loss": 3.9883, "step": 1033728 }, { "epoch": 0.01, "learning_rate": 3.306634791330765e-05, "loss": 3.9916, "step": 1034240 }, { "epoch": 0.01, "learning_rate": 3.305797834460086e-05, "loss": 3.9667, "step": 1034752 }, { "epoch": 0.01, "learning_rate": 3.304959239709034e-05, "loss": 3.9632, "step": 1035264 }, { "epoch": 0.01, "learning_rate": 3.304120644957982e-05, "loss": 3.9689, "step": 1035776 }, { "epoch": 0.01, "learning_rate": 3.30328205020693e-05, "loss": 3.9834, "step": 1036288 }, { "epoch": 0.01, "learning_rate": 3.302443455455878e-05, "loss": 3.973, "step": 1036800 }, { "epoch": 0.01, "learning_rate": 3.301604860704826e-05, "loss": 3.971, "step": 1037312 }, { "epoch": 0.01, "learning_rate": 3.300766265953774e-05, "loss": 3.9826, "step": 1037824 }, { "epoch": 0.02, "learning_rate": 3.299927671202722e-05, "loss": 3.9721, "step": 1038336 }, { "epoch": 0.02, "learning_rate": 3.299092352212416e-05, "loss": 3.9818, "step": 1038848 }, { "epoch": 0.02, "learning_rate": 3.2982537574613646e-05, "loss": 3.9677, "step": 1039360 }, { "epoch": 0.02, "learning_rate": 3.2974151627103126e-05, "loss": 3.9822, "step": 1039872 }, { "epoch": 0.02, "learning_rate": 3.2965765679592606e-05, "loss": 3.9761, "step": 1040384 }, { "epoch": 0.02, "learning_rate": 3.2957379732082085e-05, "loss": 3.9904, "step": 1040896 }, { "epoch": 0.02, "learning_rate": 3.2949010163375295e-05, "loss": 3.9638, "step": 1041408 }, { "epoch": 0.02, "learning_rate": 3.2940624215864775e-05, "loss": 3.9687, "step": 1041920 }, { "epoch": 0.02, "learning_rate": 3.2932238268354254e-05, "loss": 3.982, "step": 1042432 }, { "epoch": 0.02, "learning_rate": 3.2923852320843734e-05, "loss": 3.9771, "step": 1042944 }, { "epoch": 0.02, "learning_rate": 3.2915466373333214e-05, "loss": 3.9873, "step": 1043456 }, { "epoch": 0.02, "learning_rate": 3.2907080425822694e-05, "loss": 3.9716, "step": 1043968 }, { "epoch": 0.02, "learning_rate": 3.2898710857115903e-05, "loss": 3.974, "step": 1044480 }, { "epoch": 0.02, "learning_rate": 3.2890324909605383e-05, "loss": 3.9708, "step": 1044992 }, { "epoch": 0.02, "learning_rate": 3.288193896209486e-05, "loss": 3.9725, "step": 1045504 }, { "epoch": 0.02, "learning_rate": 3.287355301458434e-05, "loss": 3.9707, "step": 1046016 }, { "epoch": 0.02, "learning_rate": 3.286518344587756e-05, "loss": 3.9699, "step": 1046528 }, { "epoch": 0.02, "learning_rate": 3.285679749836704e-05, "loss": 3.9748, "step": 1047040 }, { "epoch": 0.02, "learning_rate": 3.284841155085652e-05, "loss": 3.969, "step": 1047552 }, { "epoch": 0.02, "learning_rate": 3.284002560334599e-05, "loss": 3.9695, "step": 1048064 }, { "epoch": 0.02, "learning_rate": 3.283163965583547e-05, "loss": 3.9712, "step": 1048576 }, { "epoch": 0.02, "learning_rate": 3.282325370832495e-05, "loss": 3.9617, "step": 1049088 }, { "epoch": 0.02, "learning_rate": 3.281488413961817e-05, "loss": 3.9833, "step": 1049600 }, { "epoch": 0.02, "learning_rate": 3.280649819210764e-05, "loss": 3.9736, "step": 1050112 }, { "epoch": 0.02, "learning_rate": 3.279811224459712e-05, "loss": 3.9783, "step": 1050624 }, { "epoch": 0.02, "learning_rate": 3.27897262970866e-05, "loss": 3.984, "step": 1051136 }, { "epoch": 0.02, "learning_rate": 3.278134034957608e-05, "loss": 3.9813, "step": 1051648 }, { "epoch": 0.02, "learning_rate": 3.27729707808693e-05, "loss": 3.9752, "step": 1052160 }, { "epoch": 0.02, "learning_rate": 3.276458483335878e-05, "loss": 3.9694, "step": 1052672 }, { "epoch": 0.02, "learning_rate": 3.275619888584826e-05, "loss": 3.9806, "step": 1053184 }, { "epoch": 0.02, "learning_rate": 3.274781293833774e-05, "loss": 3.9762, "step": 1053696 }, { "epoch": 0.02, "learning_rate": 3.2739443369630946e-05, "loss": 3.9705, "step": 1054208 }, { "epoch": 0.02, "learning_rate": 3.2731057422120426e-05, "loss": 3.9821, "step": 1054720 }, { "epoch": 0.02, "learning_rate": 3.2722671474609906e-05, "loss": 3.971, "step": 1055232 }, { "epoch": 0.02, "learning_rate": 3.2714285527099386e-05, "loss": 3.9763, "step": 1055744 }, { "epoch": 0.02, "learning_rate": 3.2705899579588866e-05, "loss": 3.9672, "step": 1056256 }, { "epoch": 0.02, "learning_rate": 3.2697513632078346e-05, "loss": 3.9677, "step": 1056768 }, { "epoch": 0.02, "learning_rate": 3.2689144063371555e-05, "loss": 3.9778, "step": 1057280 }, { "epoch": 0.02, "learning_rate": 3.2680758115861035e-05, "loss": 3.9666, "step": 1057792 }, { "epoch": 0.02, "learning_rate": 3.2672372168350515e-05, "loss": 3.9809, "step": 1058304 }, { "epoch": 0.02, "learning_rate": 3.266398622084e-05, "loss": 3.983, "step": 1058816 }, { "epoch": 0.02, "learning_rate": 3.265560027332948e-05, "loss": 3.9744, "step": 1059328 }, { "epoch": 0.02, "learning_rate": 3.264721432581896e-05, "loss": 3.9679, "step": 1059840 }, { "epoch": 0.02, "learning_rate": 3.263882837830844e-05, "loss": 3.981, "step": 1060352 }, { "epoch": 0.02, "learning_rate": 3.263044243079792e-05, "loss": 3.9757, "step": 1060864 }, { "epoch": 0.02, "learning_rate": 3.26220564832874e-05, "loss": 3.9793, "step": 1061376 }, { "epoch": 0.02, "learning_rate": 3.261368691458061e-05, "loss": 3.9722, "step": 1061888 }, { "epoch": 0.02, "learning_rate": 3.260531734587382e-05, "loss": 3.9706, "step": 1062400 }, { "epoch": 0.02, "learning_rate": 3.25969313983633e-05, "loss": 3.9811, "step": 1062912 }, { "epoch": 0.02, "learning_rate": 3.258854545085278e-05, "loss": 3.9925, "step": 1063424 }, { "epoch": 0.02, "learning_rate": 3.258015950334226e-05, "loss": 3.9686, "step": 1063936 }, { "epoch": 0.02, "learning_rate": 3.257177355583174e-05, "loss": 3.9804, "step": 1064448 }, { "epoch": 0.02, "learning_rate": 3.256338760832122e-05, "loss": 3.9833, "step": 1064960 }, { "epoch": 0.02, "learning_rate": 3.25550016608107e-05, "loss": 3.9728, "step": 1065472 }, { "epoch": 0.02, "learning_rate": 3.2546615713300186e-05, "loss": 3.977, "step": 1065984 }, { "epoch": 0.02, "learning_rate": 3.2538246144593395e-05, "loss": 3.9717, "step": 1066496 }, { "epoch": 0.02, "learning_rate": 3.2529860197082875e-05, "loss": 3.9714, "step": 1067008 }, { "epoch": 0.02, "learning_rate": 3.2521490628376084e-05, "loss": 3.985, "step": 1067520 }, { "epoch": 0.02, "learning_rate": 3.2513104680865564e-05, "loss": 3.9649, "step": 1068032 }, { "epoch": 0.03, "eval_loss": 4.033089637756348, "eval_runtime": 285.2648, "eval_samples_per_second": 1337.673, "eval_steps_per_second": 41.803, "step": 1068480 }, { "epoch": 1.0, "learning_rate": 3.2504718733355044e-05, "loss": 3.974, "step": 1068544 }, { "epoch": 1.0, "learning_rate": 3.2496332785844524e-05, "loss": 3.9612, "step": 1069056 }, { "epoch": 1.0, "learning_rate": 3.2487946838334004e-05, "loss": 3.9697, "step": 1069568 }, { "epoch": 1.0, "learning_rate": 3.247956089082348e-05, "loss": 3.9866, "step": 1070080 }, { "epoch": 1.0, "learning_rate": 3.247117494331296e-05, "loss": 3.9825, "step": 1070592 }, { "epoch": 1.0, "learning_rate": 3.246278899580244e-05, "loss": 3.9718, "step": 1071104 }, { "epoch": 1.0, "learning_rate": 3.245441942709565e-05, "loss": 3.9793, "step": 1071616 }, { "epoch": 1.0, "learning_rate": 3.244603347958513e-05, "loss": 3.9693, "step": 1072128 }, { "epoch": 1.0, "learning_rate": 3.243764753207461e-05, "loss": 3.9653, "step": 1072640 }, { "epoch": 1.0, "learning_rate": 3.242926158456409e-05, "loss": 3.9833, "step": 1073152 }, { "epoch": 1.0, "learning_rate": 3.24208920158573e-05, "loss": 3.9772, "step": 1073664 }, { "epoch": 1.0, "learning_rate": 3.241250606834678e-05, "loss": 3.9814, "step": 1074176 }, { "epoch": 1.0, "learning_rate": 3.240413649964e-05, "loss": 3.9843, "step": 1074688 }, { "epoch": 1.0, "learning_rate": 3.239575055212948e-05, "loss": 3.9648, "step": 1075200 }, { "epoch": 1.0, "learning_rate": 3.238736460461895e-05, "loss": 3.9658, "step": 1075712 }, { "epoch": 1.0, "learning_rate": 3.237897865710843e-05, "loss": 3.9587, "step": 1076224 }, { "epoch": 1.0, "learning_rate": 3.237059270959791e-05, "loss": 3.9766, "step": 1076736 }, { "epoch": 1.0, "learning_rate": 3.236220676208739e-05, "loss": 3.9697, "step": 1077248 }, { "epoch": 1.0, "learning_rate": 3.235382081457688e-05, "loss": 3.967, "step": 1077760 }, { "epoch": 1.0, "learning_rate": 3.234543486706636e-05, "loss": 3.9715, "step": 1078272 }, { "epoch": 1.0, "learning_rate": 3.233704891955584e-05, "loss": 3.9892, "step": 1078784 }, { "epoch": 1.0, "learning_rate": 3.2328679350849046e-05, "loss": 3.9795, "step": 1079296 }, { "epoch": 1.0, "learning_rate": 3.2320309782142255e-05, "loss": 3.9736, "step": 1079808 }, { "epoch": 1.0, "learning_rate": 3.2311923834631735e-05, "loss": 3.9775, "step": 1080320 }, { "epoch": 1.0, "learning_rate": 3.2303537887121215e-05, "loss": 3.9791, "step": 1080832 }, { "epoch": 1.0, "learning_rate": 3.2295151939610695e-05, "loss": 3.9739, "step": 1081344 }, { "epoch": 1.0, "learning_rate": 3.2286765992100175e-05, "loss": 3.9656, "step": 1081856 }, { "epoch": 1.0, "learning_rate": 3.2278396423393384e-05, "loss": 3.9666, "step": 1082368 }, { "epoch": 1.0, "learning_rate": 3.2270010475882864e-05, "loss": 3.9635, "step": 1082880 }, { "epoch": 1.0, "learning_rate": 3.2261624528372344e-05, "loss": 3.9684, "step": 1083392 }, { "epoch": 1.01, "learning_rate": 3.2253238580861824e-05, "loss": 3.9705, "step": 1083904 }, { "epoch": 1.01, "learning_rate": 3.224485263335131e-05, "loss": 3.9699, "step": 1084416 }, { "epoch": 1.01, "learning_rate": 3.223648306464452e-05, "loss": 3.9764, "step": 1084928 }, { "epoch": 1.01, "learning_rate": 3.2228097117134e-05, "loss": 3.9774, "step": 1085440 }, { "epoch": 1.01, "learning_rate": 3.221971116962348e-05, "loss": 3.9718, "step": 1085952 }, { "epoch": 1.01, "learning_rate": 3.221132522211296e-05, "loss": 3.9783, "step": 1086464 }, { "epoch": 1.01, "learning_rate": 3.220293927460244e-05, "loss": 3.9792, "step": 1086976 }, { "epoch": 1.01, "learning_rate": 3.219455332709192e-05, "loss": 3.9534, "step": 1087488 }, { "epoch": 1.01, "learning_rate": 3.218618375838513e-05, "loss": 3.9777, "step": 1088000 }, { "epoch": 1.01, "learning_rate": 3.217779781087461e-05, "loss": 3.9566, "step": 1088512 }, { "epoch": 1.01, "learning_rate": 3.216941186336409e-05, "loss": 3.9664, "step": 1089024 }, { "epoch": 1.01, "learning_rate": 3.216102591585357e-05, "loss": 3.9702, "step": 1089536 }, { "epoch": 1.01, "learning_rate": 3.215263996834305e-05, "loss": 3.9787, "step": 1090048 }, { "epoch": 1.01, "learning_rate": 3.214425402083253e-05, "loss": 3.967, "step": 1090560 }, { "epoch": 1.01, "learning_rate": 3.2135884452125745e-05, "loss": 3.9744, "step": 1091072 }, { "epoch": 1.01, "learning_rate": 3.2127498504615225e-05, "loss": 3.9775, "step": 1091584 }, { "epoch": 1.01, "learning_rate": 3.2119112557104705e-05, "loss": 3.9735, "step": 1092096 }, { "epoch": 1.01, "learning_rate": 3.2110726609594184e-05, "loss": 3.9773, "step": 1092608 }, { "epoch": 1.01, "learning_rate": 3.2102357040887394e-05, "loss": 3.9467, "step": 1093120 }, { "epoch": 1.01, "learning_rate": 3.2093971093376874e-05, "loss": 3.9692, "step": 1093632 }, { "epoch": 1.01, "learning_rate": 3.2085585145866353e-05, "loss": 3.9774, "step": 1094144 }, { "epoch": 1.01, "learning_rate": 3.2077199198355833e-05, "loss": 3.9746, "step": 1094656 }, { "epoch": 1.01, "learning_rate": 3.206881325084531e-05, "loss": 3.9687, "step": 1095168 }, { "epoch": 1.01, "learning_rate": 3.206044368213852e-05, "loss": 3.9596, "step": 1095680 }, { "epoch": 1.01, "learning_rate": 3.2052057734628e-05, "loss": 3.9638, "step": 1096192 }, { "epoch": 1.01, "learning_rate": 3.204367178711748e-05, "loss": 3.951, "step": 1096704 }, { "epoch": 1.01, "learning_rate": 3.203528583960696e-05, "loss": 3.9767, "step": 1097216 }, { "epoch": 1.01, "learning_rate": 3.202689989209644e-05, "loss": 3.9479, "step": 1097728 }, { "epoch": 1.01, "learning_rate": 3.201851394458592e-05, "loss": 3.9755, "step": 1098240 }, { "epoch": 1.01, "learning_rate": 3.201014437587914e-05, "loss": 3.9706, "step": 1098752 }, { "epoch": 1.01, "learning_rate": 3.200175842836861e-05, "loss": 3.9541, "step": 1099264 }, { "epoch": 1.01, "learning_rate": 3.199337248085809e-05, "loss": 3.9712, "step": 1099776 }, { "epoch": 1.01, "learning_rate": 3.198498653334757e-05, "loss": 3.9556, "step": 1100288 }, { "epoch": 1.01, "learning_rate": 3.197660058583705e-05, "loss": 3.9598, "step": 1100800 }, { "epoch": 1.01, "learning_rate": 3.196821463832653e-05, "loss": 3.9613, "step": 1101312 }, { "epoch": 1.01, "learning_rate": 3.195982869081601e-05, "loss": 3.9718, "step": 1101824 }, { "epoch": 1.01, "learning_rate": 3.195144274330549e-05, "loss": 3.9556, "step": 1102336 }, { "epoch": 1.01, "learning_rate": 3.19430731745987e-05, "loss": 3.9674, "step": 1102848 }, { "epoch": 1.01, "learning_rate": 3.193468722708819e-05, "loss": 3.9534, "step": 1103360 }, { "epoch": 1.01, "learning_rate": 3.192630127957767e-05, "loss": 3.961, "step": 1103872 }, { "epoch": 1.01, "learning_rate": 3.191791533206715e-05, "loss": 3.973, "step": 1104384 }, { "epoch": 1.01, "learning_rate": 3.1909545763360356e-05, "loss": 3.9712, "step": 1104896 }, { "epoch": 1.01, "learning_rate": 3.1901159815849836e-05, "loss": 3.9631, "step": 1105408 }, { "epoch": 1.01, "learning_rate": 3.1892773868339316e-05, "loss": 3.9688, "step": 1105920 }, { "epoch": 1.01, "learning_rate": 3.1884387920828796e-05, "loss": 3.9797, "step": 1106432 }, { "epoch": 1.01, "learning_rate": 3.1876001973318276e-05, "loss": 3.9562, "step": 1106944 }, { "epoch": 1.01, "learning_rate": 3.1867632404611485e-05, "loss": 3.9724, "step": 1107456 }, { "epoch": 1.01, "learning_rate": 3.1859246457100965e-05, "loss": 3.9599, "step": 1107968 }, { "epoch": 1.01, "learning_rate": 3.1850860509590445e-05, "loss": 3.9627, "step": 1108480 }, { "epoch": 1.01, "learning_rate": 3.1842490940883654e-05, "loss": 3.9601, "step": 1108992 }, { "epoch": 1.01, "learning_rate": 3.183410499337314e-05, "loss": 3.9663, "step": 1109504 }, { "epoch": 1.01, "learning_rate": 3.182571904586262e-05, "loss": 3.978, "step": 1110016 }, { "epoch": 1.01, "learning_rate": 3.18173330983521e-05, "loss": 3.9763, "step": 1110528 }, { "epoch": 1.01, "learning_rate": 3.180894715084158e-05, "loss": 3.9622, "step": 1111040 }, { "epoch": 1.01, "learning_rate": 3.180056120333106e-05, "loss": 3.9447, "step": 1111552 }, { "epoch": 1.01, "learning_rate": 3.179217525582054e-05, "loss": 3.9563, "step": 1112064 }, { "epoch": 1.01, "learning_rate": 3.178380568711375e-05, "loss": 3.9697, "step": 1112576 }, { "epoch": 1.01, "learning_rate": 3.177541973960323e-05, "loss": 3.9617, "step": 1113088 }, { "epoch": 1.01, "learning_rate": 3.176705017089644e-05, "loss": 3.9592, "step": 1113600 }, { "epoch": 1.01, "learning_rate": 3.175866422338592e-05, "loss": 3.9699, "step": 1114112 }, { "epoch": 1.02, "learning_rate": 3.17502782758754e-05, "loss": 3.9634, "step": 1114624 }, { "epoch": 1.02, "learning_rate": 3.174189232836488e-05, "loss": 3.964, "step": 1115136 }, { "epoch": 1.02, "learning_rate": 3.173350638085436e-05, "loss": 3.9577, "step": 1115648 }, { "epoch": 1.02, "learning_rate": 3.172512043334384e-05, "loss": 3.9728, "step": 1116160 }, { "epoch": 1.02, "learning_rate": 3.171673448583332e-05, "loss": 3.9592, "step": 1116672 }, { "epoch": 1.02, "learning_rate": 3.17083485383228e-05, "loss": 3.9757, "step": 1117184 }, { "epoch": 1.02, "learning_rate": 3.169996259081228e-05, "loss": 3.9537, "step": 1117696 }, { "epoch": 1.02, "learning_rate": 3.169157664330176e-05, "loss": 3.9569, "step": 1118208 }, { "epoch": 1.02, "learning_rate": 3.168319069579124e-05, "loss": 3.9713, "step": 1118720 }, { "epoch": 1.02, "learning_rate": 3.167482112708445e-05, "loss": 3.9635, "step": 1119232 }, { "epoch": 1.02, "learning_rate": 3.166643517957393e-05, "loss": 3.974, "step": 1119744 }, { "epoch": 1.02, "learning_rate": 3.165804923206341e-05, "loss": 3.9617, "step": 1120256 }, { "epoch": 1.02, "learning_rate": 3.164966328455289e-05, "loss": 3.9618, "step": 1120768 }, { "epoch": 1.02, "learning_rate": 3.164127733704237e-05, "loss": 3.9579, "step": 1121280 }, { "epoch": 1.02, "learning_rate": 3.1632907768335576e-05, "loss": 3.9635, "step": 1121792 }, { "epoch": 1.02, "learning_rate": 3.1624521820825056e-05, "loss": 3.955, "step": 1122304 }, { "epoch": 1.02, "learning_rate": 3.161613587331454e-05, "loss": 3.9608, "step": 1122816 }, { "epoch": 1.02, "learning_rate": 3.160774992580402e-05, "loss": 3.9621, "step": 1123328 }, { "epoch": 1.02, "learning_rate": 3.15993639782935e-05, "loss": 3.9565, "step": 1123840 }, { "epoch": 1.02, "learning_rate": 3.159099440958671e-05, "loss": 3.9562, "step": 1124352 }, { "epoch": 1.02, "learning_rate": 3.158260846207619e-05, "loss": 3.9637, "step": 1124864 }, { "epoch": 1.02, "learning_rate": 3.157422251456567e-05, "loss": 3.9489, "step": 1125376 }, { "epoch": 1.02, "learning_rate": 3.156583656705515e-05, "loss": 3.9684, "step": 1125888 }, { "epoch": 1.02, "learning_rate": 3.155745061954463e-05, "loss": 3.961, "step": 1126400 }, { "epoch": 1.02, "learning_rate": 3.154908105083784e-05, "loss": 3.9674, "step": 1126912 }, { "epoch": 1.02, "learning_rate": 3.154069510332732e-05, "loss": 3.9707, "step": 1127424 }, { "epoch": 1.02, "learning_rate": 3.15323091558168e-05, "loss": 3.9715, "step": 1127936 }, { "epoch": 1.02, "learning_rate": 3.152393958711001e-05, "loss": 3.9636, "step": 1128448 }, { "epoch": 1.02, "learning_rate": 3.1515553639599496e-05, "loss": 3.9592, "step": 1128960 }, { "epoch": 1.02, "learning_rate": 3.1507167692088976e-05, "loss": 3.9649, "step": 1129472 }, { "epoch": 1.02, "learning_rate": 3.1498781744578456e-05, "loss": 3.9635, "step": 1129984 }, { "epoch": 1.02, "learning_rate": 3.1490395797067936e-05, "loss": 3.9548, "step": 1130496 }, { "epoch": 1.02, "learning_rate": 3.1482009849557416e-05, "loss": 3.9741, "step": 1131008 }, { "epoch": 1.02, "learning_rate": 3.1473623902046896e-05, "loss": 3.9586, "step": 1131520 }, { "epoch": 1.02, "learning_rate": 3.1465237954536376e-05, "loss": 3.9659, "step": 1132032 }, { "epoch": 1.02, "learning_rate": 3.1456852007025856e-05, "loss": 3.9564, "step": 1132544 }, { "epoch": 1.02, "learning_rate": 3.1448466059515336e-05, "loss": 3.9549, "step": 1133056 }, { "epoch": 1.02, "learning_rate": 3.1440096490808545e-05, "loss": 3.9691, "step": 1133568 }, { "epoch": 1.02, "learning_rate": 3.1431710543298025e-05, "loss": 3.9564, "step": 1134080 }, { "epoch": 1.02, "learning_rate": 3.1423324595787505e-05, "loss": 3.9614, "step": 1134592 }, { "epoch": 1.02, "learning_rate": 3.141493864827698e-05, "loss": 3.9718, "step": 1135104 }, { "epoch": 1.02, "learning_rate": 3.1406552700766465e-05, "loss": 3.9604, "step": 1135616 }, { "epoch": 1.02, "learning_rate": 3.1398166753255945e-05, "loss": 3.9574, "step": 1136128 }, { "epoch": 1.02, "learning_rate": 3.1389780805745425e-05, "loss": 3.9674, "step": 1136640 }, { "epoch": 1.02, "learning_rate": 3.1381394858234905e-05, "loss": 3.9645, "step": 1137152 }, { "epoch": 1.02, "learning_rate": 3.1373025289528114e-05, "loss": 3.9668, "step": 1137664 }, { "epoch": 1.02, "learning_rate": 3.1364639342017594e-05, "loss": 3.957, "step": 1138176 }, { "epoch": 1.02, "learning_rate": 3.1356253394507074e-05, "loss": 3.9603, "step": 1138688 }, { "epoch": 1.02, "learning_rate": 3.1347867446996554e-05, "loss": 3.9742, "step": 1139200 }, { "epoch": 1.02, "learning_rate": 3.1339481499486034e-05, "loss": 3.9765, "step": 1139712 }, { "epoch": 1.02, "learning_rate": 3.133111193077924e-05, "loss": 3.9609, "step": 1140224 }, { "epoch": 1.02, "learning_rate": 3.132272598326872e-05, "loss": 3.964, "step": 1140736 }, { "epoch": 1.02, "learning_rate": 3.13143400357582e-05, "loss": 3.9705, "step": 1141248 }, { "epoch": 1.02, "learning_rate": 3.130595408824768e-05, "loss": 3.9638, "step": 1141760 }, { "epoch": 1.02, "learning_rate": 3.12975845195409e-05, "loss": 3.9641, "step": 1142272 }, { "epoch": 1.02, "learning_rate": 3.128919857203038e-05, "loss": 3.9608, "step": 1142784 }, { "epoch": 1.02, "learning_rate": 3.128081262451986e-05, "loss": 3.9589, "step": 1143296 }, { "epoch": 1.02, "learning_rate": 3.127242667700934e-05, "loss": 3.9732, "step": 1143808 }, { "epoch": 1.02, "learning_rate": 3.126405710830255e-05, "loss": 3.9532, "step": 1144320 }, { "epoch": 1.03, "eval_loss": 4.026190757751465, "eval_runtime": 286.2894, "eval_samples_per_second": 1332.885, "eval_steps_per_second": 41.654, "step": 1144800 }, { "epoch": 0.0, "learning_rate": 3.125567116079203e-05, "loss": 3.9427, "step": 1144832 }, { "epoch": 0.0, "learning_rate": 3.124728521328151e-05, "loss": 3.9537, "step": 1145344 }, { "epoch": 0.0, "learning_rate": 3.123889926577099e-05, "loss": 3.9551, "step": 1145856 }, { "epoch": 0.0, "learning_rate": 3.123051331826047e-05, "loss": 3.9768, "step": 1146368 }, { "epoch": 0.0, "learning_rate": 3.122212737074995e-05, "loss": 3.9733, "step": 1146880 }, { "epoch": 0.0, "learning_rate": 3.121374142323943e-05, "loss": 3.96, "step": 1147392 }, { "epoch": 0.0, "learning_rate": 3.120535547572891e-05, "loss": 3.9664, "step": 1147904 }, { "epoch": 0.0, "learning_rate": 3.119696952821839e-05, "loss": 3.9591, "step": 1148416 }, { "epoch": 0.0, "learning_rate": 3.118858358070787e-05, "loss": 3.9582, "step": 1148928 }, { "epoch": 0.0, "learning_rate": 3.118019763319735e-05, "loss": 3.9687, "step": 1149440 }, { "epoch": 0.0, "learning_rate": 3.117181168568683e-05, "loss": 3.9626, "step": 1149952 }, { "epoch": 0.0, "learning_rate": 3.116342573817631e-05, "loss": 3.9681, "step": 1150464 }, { "epoch": 0.0, "learning_rate": 3.115505616946952e-05, "loss": 3.9731, "step": 1150976 }, { "epoch": 0.0, "learning_rate": 3.1146670221958996e-05, "loss": 3.9544, "step": 1151488 }, { "epoch": 0.0, "learning_rate": 3.1138284274448476e-05, "loss": 3.9538, "step": 1152000 }, { "epoch": 0.0, "learning_rate": 3.1129898326937956e-05, "loss": 3.9472, "step": 1152512 }, { "epoch": 0.0, "learning_rate": 3.1121512379427436e-05, "loss": 3.9625, "step": 1153024 }, { "epoch": 0.0, "learning_rate": 3.1113126431916916e-05, "loss": 3.9611, "step": 1153536 }, { "epoch": 0.0, "learning_rate": 3.1104740484406396e-05, "loss": 3.9541, "step": 1154048 }, { "epoch": 0.0, "learning_rate": 3.1096354536895876e-05, "loss": 3.9595, "step": 1154560 }, { "epoch": 0.0, "learning_rate": 3.1087968589385356e-05, "loss": 3.9762, "step": 1155072 }, { "epoch": 0.0, "learning_rate": 3.1079582641874836e-05, "loss": 3.9631, "step": 1155584 }, { "epoch": 0.0, "learning_rate": 3.1071196694364316e-05, "loss": 3.9669, "step": 1156096 }, { "epoch": 0.0, "learning_rate": 3.1062810746853796e-05, "loss": 3.962, "step": 1156608 }, { "epoch": 0.0, "learning_rate": 3.105442479934328e-05, "loss": 3.9725, "step": 1157120 }, { "epoch": 0.0, "learning_rate": 3.104607160944022e-05, "loss": 3.9598, "step": 1157632 }, { "epoch": 0.0, "learning_rate": 3.10376856619297e-05, "loss": 3.9582, "step": 1158144 }, { "epoch": 0.0, "learning_rate": 3.102929971441918e-05, "loss": 3.9548, "step": 1158656 }, { "epoch": 0.0, "learning_rate": 3.102091376690866e-05, "loss": 3.9524, "step": 1159168 }, { "epoch": 0.0, "learning_rate": 3.101252781939814e-05, "loss": 3.9581, "step": 1159680 }, { "epoch": 0.01, "learning_rate": 3.100414187188762e-05, "loss": 3.9565, "step": 1160192 }, { "epoch": 0.01, "learning_rate": 3.099577230318083e-05, "loss": 3.9615, "step": 1160704 }, { "epoch": 0.01, "learning_rate": 3.098738635567031e-05, "loss": 3.9649, "step": 1161216 }, { "epoch": 0.01, "learning_rate": 3.097900040815979e-05, "loss": 3.9637, "step": 1161728 }, { "epoch": 0.01, "learning_rate": 3.097061446064927e-05, "loss": 3.9653, "step": 1162240 }, { "epoch": 0.01, "learning_rate": 3.0962244891942485e-05, "loss": 3.963, "step": 1162752 }, { "epoch": 0.01, "learning_rate": 3.0953858944431965e-05, "loss": 3.9669, "step": 1163264 }, { "epoch": 0.01, "learning_rate": 3.0945472996921445e-05, "loss": 3.9445, "step": 1163776 }, { "epoch": 0.01, "learning_rate": 3.0937087049410925e-05, "loss": 3.9675, "step": 1164288 }, { "epoch": 0.01, "learning_rate": 3.0928701101900405e-05, "loss": 3.941, "step": 1164800 }, { "epoch": 0.01, "learning_rate": 3.0920315154389885e-05, "loss": 3.956, "step": 1165312 }, { "epoch": 0.01, "learning_rate": 3.091192920687936e-05, "loss": 3.9592, "step": 1165824 }, { "epoch": 0.01, "learning_rate": 3.0903559638172574e-05, "loss": 3.9657, "step": 1166336 }, { "epoch": 0.01, "learning_rate": 3.0895173690662054e-05, "loss": 3.9537, "step": 1166848 }, { "epoch": 0.01, "learning_rate": 3.088678774315153e-05, "loss": 3.966, "step": 1167360 }, { "epoch": 0.01, "learning_rate": 3.087840179564101e-05, "loss": 3.9648, "step": 1167872 }, { "epoch": 0.01, "learning_rate": 3.087003222693422e-05, "loss": 3.9636, "step": 1168384 }, { "epoch": 0.01, "learning_rate": 3.08616462794237e-05, "loss": 3.9633, "step": 1168896 }, { "epoch": 0.01, "learning_rate": 3.085326033191318e-05, "loss": 3.9394, "step": 1169408 }, { "epoch": 0.01, "learning_rate": 3.084487438440266e-05, "loss": 3.9554, "step": 1169920 }, { "epoch": 0.01, "learning_rate": 3.083648843689214e-05, "loss": 3.9673, "step": 1170432 }, { "epoch": 0.01, "learning_rate": 3.082810248938162e-05, "loss": 3.9608, "step": 1170944 }, { "epoch": 0.01, "learning_rate": 3.08197165418711e-05, "loss": 3.9576, "step": 1171456 }, { "epoch": 0.01, "learning_rate": 3.081134697316431e-05, "loss": 3.9478, "step": 1171968 }, { "epoch": 0.01, "learning_rate": 3.080296102565379e-05, "loss": 3.9533, "step": 1172480 }, { "epoch": 0.01, "learning_rate": 3.079457507814327e-05, "loss": 3.9385, "step": 1172992 }, { "epoch": 0.01, "learning_rate": 3.078618913063275e-05, "loss": 3.968, "step": 1173504 }, { "epoch": 0.01, "learning_rate": 3.077780318312223e-05, "loss": 3.9358, "step": 1174016 }, { "epoch": 0.01, "learning_rate": 3.076941723561171e-05, "loss": 3.9622, "step": 1174528 }, { "epoch": 0.01, "learning_rate": 3.076103128810119e-05, "loss": 3.9589, "step": 1175040 }, { "epoch": 0.01, "learning_rate": 3.075264534059067e-05, "loss": 3.9482, "step": 1175552 }, { "epoch": 0.01, "learning_rate": 3.074427577188389e-05, "loss": 3.9548, "step": 1176064 }, { "epoch": 0.01, "learning_rate": 3.073588982437337e-05, "loss": 3.9462, "step": 1176576 }, { "epoch": 0.01, "learning_rate": 3.072750387686285e-05, "loss": 3.9477, "step": 1177088 }, { "epoch": 0.01, "learning_rate": 3.071911792935233e-05, "loss": 3.9435, "step": 1177600 }, { "epoch": 0.01, "learning_rate": 3.071073198184181e-05, "loss": 3.9656, "step": 1178112 }, { "epoch": 0.01, "learning_rate": 3.070234603433129e-05, "loss": 3.949, "step": 1178624 }, { "epoch": 0.01, "learning_rate": 3.0693976465624496e-05, "loss": 3.948, "step": 1179136 }, { "epoch": 0.01, "learning_rate": 3.0685590518113976e-05, "loss": 3.9427, "step": 1179648 }, { "epoch": 0.01, "learning_rate": 3.0677204570603456e-05, "loss": 3.9512, "step": 1180160 }, { "epoch": 0.01, "learning_rate": 3.0668818623092936e-05, "loss": 3.9646, "step": 1180672 }, { "epoch": 0.01, "learning_rate": 3.0660449054386145e-05, "loss": 3.9576, "step": 1181184 }, { "epoch": 0.01, "learning_rate": 3.0652063106875625e-05, "loss": 3.9497, "step": 1181696 }, { "epoch": 0.01, "learning_rate": 3.0643677159365105e-05, "loss": 3.96, "step": 1182208 }, { "epoch": 0.01, "learning_rate": 3.063530759065832e-05, "loss": 3.968, "step": 1182720 }, { "epoch": 0.01, "learning_rate": 3.06269216431478e-05, "loss": 3.9434, "step": 1183232 }, { "epoch": 0.01, "learning_rate": 3.061853569563728e-05, "loss": 3.9611, "step": 1183744 }, { "epoch": 0.01, "learning_rate": 3.061014974812676e-05, "loss": 3.9501, "step": 1184256 }, { "epoch": 0.01, "learning_rate": 3.060176380061624e-05, "loss": 3.9516, "step": 1184768 }, { "epoch": 0.01, "learning_rate": 3.059337785310572e-05, "loss": 3.9484, "step": 1185280 }, { "epoch": 0.01, "learning_rate": 3.058500828439893e-05, "loss": 3.9564, "step": 1185792 }, { "epoch": 0.01, "learning_rate": 3.057662233688841e-05, "loss": 3.9654, "step": 1186304 }, { "epoch": 0.01, "learning_rate": 3.056823638937789e-05, "loss": 3.9648, "step": 1186816 }, { "epoch": 0.01, "learning_rate": 3.055985044186736e-05, "loss": 3.9514, "step": 1187328 }, { "epoch": 0.01, "learning_rate": 3.055146449435684e-05, "loss": 3.9293, "step": 1187840 }, { "epoch": 0.01, "learning_rate": 3.054307854684633e-05, "loss": 3.9511, "step": 1188352 }, { "epoch": 0.01, "learning_rate": 3.053469259933581e-05, "loss": 3.9552, "step": 1188864 }, { "epoch": 0.01, "learning_rate": 3.052632303062902e-05, "loss": 3.9555, "step": 1189376 }, { "epoch": 0.01, "learning_rate": 3.05179370831185e-05, "loss": 3.9415, "step": 1189888 }, { "epoch": 0.01, "learning_rate": 3.0509567514411715e-05, "loss": 3.959, "step": 1190400 }, { "epoch": 0.02, "learning_rate": 3.0501181566901188e-05, "loss": 3.9521, "step": 1190912 }, { "epoch": 0.02, "learning_rate": 3.0492795619390668e-05, "loss": 3.9547, "step": 1191424 }, { "epoch": 0.02, "learning_rate": 3.0484409671880148e-05, "loss": 3.9442, "step": 1191936 }, { "epoch": 0.02, "learning_rate": 3.0476023724369628e-05, "loss": 3.9608, "step": 1192448 }, { "epoch": 0.02, "learning_rate": 3.046763777685911e-05, "loss": 3.9465, "step": 1192960 }, { "epoch": 0.02, "learning_rate": 3.045926820815232e-05, "loss": 3.9649, "step": 1193472 }, { "epoch": 0.02, "learning_rate": 3.04508822606418e-05, "loss": 3.9484, "step": 1193984 }, { "epoch": 0.02, "learning_rate": 3.044249631313128e-05, "loss": 3.9417, "step": 1194496 }, { "epoch": 0.02, "learning_rate": 3.043411036562076e-05, "loss": 3.9559, "step": 1195008 }, { "epoch": 0.02, "learning_rate": 3.042572441811024e-05, "loss": 3.9532, "step": 1195520 }, { "epoch": 0.02, "learning_rate": 3.041733847059972e-05, "loss": 3.9603, "step": 1196032 }, { "epoch": 0.02, "learning_rate": 3.04089525230892e-05, "loss": 3.9508, "step": 1196544 }, { "epoch": 0.02, "learning_rate": 3.0400566575578683e-05, "loss": 3.9503, "step": 1197056 }, { "epoch": 0.02, "learning_rate": 3.0392180628068163e-05, "loss": 3.9449, "step": 1197568 }, { "epoch": 0.02, "learning_rate": 3.0383794680557643e-05, "loss": 3.9546, "step": 1198080 }, { "epoch": 0.02, "learning_rate": 3.0375408733047123e-05, "loss": 3.9407, "step": 1198592 }, { "epoch": 0.02, "learning_rate": 3.0367039164340332e-05, "loss": 3.9528, "step": 1199104 }, { "epoch": 0.02, "learning_rate": 3.0358653216829812e-05, "loss": 3.9506, "step": 1199616 }, { "epoch": 0.02, "learning_rate": 3.0350267269319292e-05, "loss": 3.949, "step": 1200128 }, { "epoch": 0.02, "learning_rate": 3.0341881321808775e-05, "loss": 3.9392, "step": 1200640 }, { "epoch": 0.02, "learning_rate": 3.0333495374298255e-05, "loss": 3.9517, "step": 1201152 }, { "epoch": 0.02, "learning_rate": 3.032510942678773e-05, "loss": 3.9413, "step": 1201664 }, { "epoch": 0.02, "learning_rate": 3.031672347927721e-05, "loss": 3.9563, "step": 1202176 }, { "epoch": 0.02, "learning_rate": 3.030833753176669e-05, "loss": 3.9504, "step": 1202688 }, { "epoch": 0.02, "learning_rate": 3.0299967963059904e-05, "loss": 3.9523, "step": 1203200 }, { "epoch": 0.02, "learning_rate": 3.029158201554938e-05, "loss": 3.9612, "step": 1203712 }, { "epoch": 0.02, "learning_rate": 3.028319606803886e-05, "loss": 3.9598, "step": 1204224 }, { "epoch": 0.02, "learning_rate": 3.0274826499332077e-05, "loss": 3.9559, "step": 1204736 }, { "epoch": 0.02, "learning_rate": 3.026644055182155e-05, "loss": 3.9449, "step": 1205248 }, { "epoch": 0.02, "learning_rate": 3.025805460431103e-05, "loss": 3.9565, "step": 1205760 }, { "epoch": 0.02, "learning_rate": 3.0249668656800513e-05, "loss": 3.9537, "step": 1206272 }, { "epoch": 0.02, "learning_rate": 3.0241282709289993e-05, "loss": 3.9443, "step": 1206784 }, { "epoch": 0.02, "learning_rate": 3.0232896761779473e-05, "loss": 3.9588, "step": 1207296 }, { "epoch": 0.02, "learning_rate": 3.0224510814268953e-05, "loss": 3.9492, "step": 1207808 }, { "epoch": 0.02, "learning_rate": 3.0216124866758433e-05, "loss": 3.9558, "step": 1208320 }, { "epoch": 0.02, "learning_rate": 3.0207738919247913e-05, "loss": 3.9448, "step": 1208832 }, { "epoch": 0.02, "learning_rate": 3.0199369350541122e-05, "loss": 3.947, "step": 1209344 }, { "epoch": 0.02, "learning_rate": 3.0190983403030605e-05, "loss": 3.952, "step": 1209856 }, { "epoch": 0.02, "learning_rate": 3.0182597455520085e-05, "loss": 3.946, "step": 1210368 }, { "epoch": 0.02, "learning_rate": 3.0174211508009565e-05, "loss": 3.9461, "step": 1210880 }, { "epoch": 0.02, "learning_rate": 3.0165841939302774e-05, "loss": 3.965, "step": 1211392 }, { "epoch": 0.02, "learning_rate": 3.0157455991792254e-05, "loss": 3.9537, "step": 1211904 }, { "epoch": 0.02, "learning_rate": 3.0149070044281734e-05, "loss": 3.9451, "step": 1212416 }, { "epoch": 0.02, "learning_rate": 3.0140684096771214e-05, "loss": 3.9553, "step": 1212928 }, { "epoch": 0.02, "learning_rate": 3.0132314528064427e-05, "loss": 3.9541, "step": 1213440 }, { "epoch": 0.02, "learning_rate": 3.0123928580553907e-05, "loss": 3.9555, "step": 1213952 }, { "epoch": 0.02, "learning_rate": 3.0115542633043387e-05, "loss": 3.951, "step": 1214464 }, { "epoch": 0.02, "learning_rate": 3.0107156685532867e-05, "loss": 3.9485, "step": 1214976 }, { "epoch": 0.02, "learning_rate": 3.0098787116826076e-05, "loss": 3.9608, "step": 1215488 }, { "epoch": 0.02, "learning_rate": 3.0090417548119288e-05, "loss": 3.9648, "step": 1216000 }, { "epoch": 0.02, "learning_rate": 3.0082031600608768e-05, "loss": 3.9508, "step": 1216512 }, { "epoch": 0.02, "learning_rate": 3.0073645653098248e-05, "loss": 3.9528, "step": 1217024 }, { "epoch": 0.02, "learning_rate": 3.0065259705587728e-05, "loss": 3.9629, "step": 1217536 }, { "epoch": 0.02, "learning_rate": 3.0056873758077208e-05, "loss": 3.9475, "step": 1218048 }, { "epoch": 0.02, "learning_rate": 3.0048487810566688e-05, "loss": 3.9541, "step": 1218560 }, { "epoch": 0.02, "learning_rate": 3.0040101863056168e-05, "loss": 3.9485, "step": 1219072 }, { "epoch": 0.02, "learning_rate": 3.003171591554565e-05, "loss": 3.9489, "step": 1219584 }, { "epoch": 0.02, "learning_rate": 3.002334634683886e-05, "loss": 3.9603, "step": 1220096 }, { "epoch": 0.02, "learning_rate": 3.001496039932834e-05, "loss": 3.9436, "step": 1220608 }, { "epoch": 0.03, "learning_rate": 3.000657445181782e-05, "loss": 3.9473, "step": 1221120 }, { "epoch": 0.03, "eval_loss": 4.020456314086914, "eval_runtime": 280.3059, "eval_samples_per_second": 1361.338, "eval_steps_per_second": 42.543, "step": 1221120 }, { "epoch": 1.0, "learning_rate": 2.99981885043073e-05, "loss": 3.9407, "step": 1221632 }, { "epoch": 1.0, "learning_rate": 2.9989818935600513e-05, "loss": 3.9426, "step": 1222144 }, { "epoch": 1.0, "learning_rate": 2.9981432988089993e-05, "loss": 3.9642, "step": 1222656 }, { "epoch": 1.0, "learning_rate": 2.9973047040579473e-05, "loss": 3.9625, "step": 1223168 }, { "epoch": 1.0, "learning_rate": 2.9964661093068953e-05, "loss": 3.9492, "step": 1223680 }, { "epoch": 1.0, "learning_rate": 2.9956275145558432e-05, "loss": 3.9541, "step": 1224192 }, { "epoch": 1.0, "learning_rate": 2.9947889198047912e-05, "loss": 3.948, "step": 1224704 }, { "epoch": 1.0, "learning_rate": 2.993950325053739e-05, "loss": 3.9407, "step": 1225216 }, { "epoch": 1.0, "learning_rate": 2.993111730302687e-05, "loss": 3.9616, "step": 1225728 }, { "epoch": 1.0, "learning_rate": 2.9922747734320085e-05, "loss": 3.9499, "step": 1226240 }, { "epoch": 1.0, "learning_rate": 2.9914378165613294e-05, "loss": 3.959, "step": 1226752 }, { "epoch": 1.0, "learning_rate": 2.9906008596906503e-05, "loss": 3.9571, "step": 1227264 }, { "epoch": 1.0, "learning_rate": 2.9897639028199716e-05, "loss": 3.9502, "step": 1227776 }, { "epoch": 1.0, "learning_rate": 2.9889253080689195e-05, "loss": 3.9434, "step": 1228288 }, { "epoch": 1.0, "learning_rate": 2.9880867133178675e-05, "loss": 3.9339, "step": 1228800 }, { "epoch": 1.0, "learning_rate": 2.9872481185668155e-05, "loss": 3.9468, "step": 1229312 }, { "epoch": 1.0, "learning_rate": 2.9864095238157635e-05, "loss": 3.9489, "step": 1229824 }, { "epoch": 1.0, "learning_rate": 2.9855709290647115e-05, "loss": 3.9441, "step": 1230336 }, { "epoch": 1.0, "learning_rate": 2.9847323343136595e-05, "loss": 3.9483, "step": 1230848 }, { "epoch": 1.0, "learning_rate": 2.9838937395626075e-05, "loss": 3.9689, "step": 1231360 }, { "epoch": 1.0, "learning_rate": 2.9830551448115555e-05, "loss": 3.9523, "step": 1231872 }, { "epoch": 1.0, "learning_rate": 2.982216550060504e-05, "loss": 3.9544, "step": 1232384 }, { "epoch": 1.0, "learning_rate": 2.981377955309451e-05, "loss": 3.9493, "step": 1232896 }, { "epoch": 1.0, "learning_rate": 2.980539360558399e-05, "loss": 3.964, "step": 1233408 }, { "epoch": 1.0, "learning_rate": 2.979700765807347e-05, "loss": 3.9418, "step": 1233920 }, { "epoch": 1.0, "learning_rate": 2.978862171056295e-05, "loss": 3.9478, "step": 1234432 }, { "epoch": 1.0, "learning_rate": 2.978023576305243e-05, "loss": 3.9422, "step": 1234944 }, { "epoch": 1.0, "learning_rate": 2.9771866194345644e-05, "loss": 3.9444, "step": 1235456 }, { "epoch": 1.0, "learning_rate": 2.9763480246835124e-05, "loss": 3.9458, "step": 1235968 }, { "epoch": 1.01, "learning_rate": 2.9755094299324604e-05, "loss": 3.9443, "step": 1236480 }, { "epoch": 1.01, "learning_rate": 2.9746708351814084e-05, "loss": 3.9461, "step": 1236992 }, { "epoch": 1.01, "learning_rate": 2.9738322404303564e-05, "loss": 3.9557, "step": 1237504 }, { "epoch": 1.01, "learning_rate": 2.972996921440051e-05, "loss": 3.9484, "step": 1238016 }, { "epoch": 1.01, "learning_rate": 2.9721583266889985e-05, "loss": 3.9575, "step": 1238528 }, { "epoch": 1.01, "learning_rate": 2.9713197319379465e-05, "loss": 3.9498, "step": 1239040 }, { "epoch": 1.01, "learning_rate": 2.9704811371868945e-05, "loss": 3.9571, "step": 1239552 }, { "epoch": 1.01, "learning_rate": 2.9696441803162154e-05, "loss": 3.9329, "step": 1240064 }, { "epoch": 1.01, "learning_rate": 2.9688055855651638e-05, "loss": 3.9573, "step": 1240576 }, { "epoch": 1.01, "learning_rate": 2.9679669908141118e-05, "loss": 3.9314, "step": 1241088 }, { "epoch": 1.01, "learning_rate": 2.9671283960630598e-05, "loss": 3.9481, "step": 1241600 }, { "epoch": 1.01, "learning_rate": 2.9662898013120078e-05, "loss": 3.9444, "step": 1242112 }, { "epoch": 1.01, "learning_rate": 2.9654512065609558e-05, "loss": 3.9541, "step": 1242624 }, { "epoch": 1.01, "learning_rate": 2.9646142496902767e-05, "loss": 3.9393, "step": 1243136 }, { "epoch": 1.01, "learning_rate": 2.9637756549392247e-05, "loss": 3.9576, "step": 1243648 }, { "epoch": 1.01, "learning_rate": 2.962937060188173e-05, "loss": 3.9504, "step": 1244160 }, { "epoch": 1.01, "learning_rate": 2.962098465437121e-05, "loss": 3.9518, "step": 1244672 }, { "epoch": 1.01, "learning_rate": 2.961259870686069e-05, "loss": 3.9532, "step": 1245184 }, { "epoch": 1.01, "learning_rate": 2.96042291381539e-05, "loss": 3.9283, "step": 1245696 }, { "epoch": 1.01, "learning_rate": 2.9595859569447108e-05, "loss": 3.9478, "step": 1246208 }, { "epoch": 1.01, "learning_rate": 2.958747362193659e-05, "loss": 3.9553, "step": 1246720 }, { "epoch": 1.01, "learning_rate": 2.957908767442607e-05, "loss": 3.9497, "step": 1247232 }, { "epoch": 1.01, "learning_rate": 2.957070172691555e-05, "loss": 3.9492, "step": 1247744 }, { "epoch": 1.01, "learning_rate": 2.956231577940503e-05, "loss": 3.938, "step": 1248256 }, { "epoch": 1.01, "learning_rate": 2.955392983189451e-05, "loss": 3.9428, "step": 1248768 }, { "epoch": 1.01, "learning_rate": 2.954554388438399e-05, "loss": 3.9282, "step": 1249280 }, { "epoch": 1.01, "learning_rate": 2.953715793687347e-05, "loss": 3.9565, "step": 1249792 }, { "epoch": 1.01, "learning_rate": 2.9528788368166684e-05, "loss": 3.9253, "step": 1250304 }, { "epoch": 1.01, "learning_rate": 2.9520402420656164e-05, "loss": 3.9534, "step": 1250816 }, { "epoch": 1.01, "learning_rate": 2.9512016473145644e-05, "loss": 3.9484, "step": 1251328 }, { "epoch": 1.01, "learning_rate": 2.9503630525635123e-05, "loss": 3.9352, "step": 1251840 }, { "epoch": 1.01, "learning_rate": 2.9495244578124603e-05, "loss": 3.9411, "step": 1252352 }, { "epoch": 1.01, "learning_rate": 2.9486858630614083e-05, "loss": 3.9393, "step": 1252864 }, { "epoch": 1.01, "learning_rate": 2.9478472683103563e-05, "loss": 3.9372, "step": 1253376 }, { "epoch": 1.01, "learning_rate": 2.9470086735593043e-05, "loss": 3.933, "step": 1253888 }, { "epoch": 1.01, "learning_rate": 2.9461717166886256e-05, "loss": 3.9533, "step": 1254400 }, { "epoch": 1.01, "learning_rate": 2.9453347598179465e-05, "loss": 3.939, "step": 1254912 }, { "epoch": 1.01, "learning_rate": 2.9444961650668945e-05, "loss": 3.9362, "step": 1255424 }, { "epoch": 1.01, "learning_rate": 2.9436575703158425e-05, "loss": 3.9336, "step": 1255936 }, { "epoch": 1.01, "learning_rate": 2.9428189755647905e-05, "loss": 3.9391, "step": 1256448 }, { "epoch": 1.01, "learning_rate": 2.9419820186941117e-05, "loss": 3.9527, "step": 1256960 }, { "epoch": 1.01, "learning_rate": 2.9411434239430597e-05, "loss": 3.9491, "step": 1257472 }, { "epoch": 1.01, "learning_rate": 2.9403048291920077e-05, "loss": 3.9385, "step": 1257984 }, { "epoch": 1.01, "learning_rate": 2.9394662344409557e-05, "loss": 3.9505, "step": 1258496 }, { "epoch": 1.01, "learning_rate": 2.9386292775702766e-05, "loss": 3.9541, "step": 1259008 }, { "epoch": 1.01, "learning_rate": 2.9377906828192246e-05, "loss": 3.9333, "step": 1259520 }, { "epoch": 1.01, "learning_rate": 2.936952088068173e-05, "loss": 3.9492, "step": 1260032 }, { "epoch": 1.01, "learning_rate": 2.936113493317121e-05, "loss": 3.9425, "step": 1260544 }, { "epoch": 1.01, "learning_rate": 2.935274898566069e-05, "loss": 3.942, "step": 1261056 }, { "epoch": 1.01, "learning_rate": 2.934436303815017e-05, "loss": 3.9388, "step": 1261568 }, { "epoch": 1.01, "learning_rate": 2.9335977090639643e-05, "loss": 3.9421, "step": 1262080 }, { "epoch": 1.01, "learning_rate": 2.9327591143129123e-05, "loss": 3.9516, "step": 1262592 }, { "epoch": 1.01, "learning_rate": 2.9319205195618606e-05, "loss": 3.9599, "step": 1263104 }, { "epoch": 1.01, "learning_rate": 2.9310835626911815e-05, "loss": 3.9363, "step": 1263616 }, { "epoch": 1.01, "learning_rate": 2.9302449679401295e-05, "loss": 3.9185, "step": 1264128 }, { "epoch": 1.01, "learning_rate": 2.929408011069451e-05, "loss": 3.9402, "step": 1264640 }, { "epoch": 1.01, "learning_rate": 2.928569416318399e-05, "loss": 3.9431, "step": 1265152 }, { "epoch": 1.01, "learning_rate": 2.9277308215673467e-05, "loss": 3.9446, "step": 1265664 }, { "epoch": 1.01, "learning_rate": 2.9268922268162947e-05, "loss": 3.9366, "step": 1266176 }, { "epoch": 1.01, "learning_rate": 2.9260569078259892e-05, "loss": 3.9467, "step": 1266688 }, { "epoch": 1.02, "learning_rate": 2.9252183130749372e-05, "loss": 3.944, "step": 1267200 }, { "epoch": 1.02, "learning_rate": 2.9243797183238852e-05, "loss": 3.9404, "step": 1267712 }, { "epoch": 1.02, "learning_rate": 2.9235411235728332e-05, "loss": 3.9346, "step": 1268224 }, { "epoch": 1.02, "learning_rate": 2.9227025288217812e-05, "loss": 3.9511, "step": 1268736 }, { "epoch": 1.02, "learning_rate": 2.921863934070729e-05, "loss": 3.9361, "step": 1269248 }, { "epoch": 1.02, "learning_rate": 2.921025339319677e-05, "loss": 3.9527, "step": 1269760 }, { "epoch": 1.02, "learning_rate": 2.920186744568625e-05, "loss": 3.9422, "step": 1270272 }, { "epoch": 1.02, "learning_rate": 2.919348149817573e-05, "loss": 3.9289, "step": 1270784 }, { "epoch": 1.02, "learning_rate": 2.918509555066521e-05, "loss": 3.9428, "step": 1271296 }, { "epoch": 1.02, "learning_rate": 2.917670960315469e-05, "loss": 3.9436, "step": 1271808 }, { "epoch": 1.02, "learning_rate": 2.91683400344479e-05, "loss": 3.9522, "step": 1272320 }, { "epoch": 1.02, "learning_rate": 2.915995408693738e-05, "loss": 3.9405, "step": 1272832 }, { "epoch": 1.02, "learning_rate": 2.915156813942686e-05, "loss": 3.9414, "step": 1273344 }, { "epoch": 1.02, "learning_rate": 2.914318219191634e-05, "loss": 3.9342, "step": 1273856 }, { "epoch": 1.02, "learning_rate": 2.913481262320955e-05, "loss": 3.9456, "step": 1274368 }, { "epoch": 1.02, "learning_rate": 2.912642667569903e-05, "loss": 3.9284, "step": 1274880 }, { "epoch": 1.02, "learning_rate": 2.911804072818851e-05, "loss": 3.9385, "step": 1275392 }, { "epoch": 1.02, "learning_rate": 2.9109654780677993e-05, "loss": 3.9416, "step": 1275904 }, { "epoch": 1.02, "learning_rate": 2.9101268833167473e-05, "loss": 3.9402, "step": 1276416 }, { "epoch": 1.02, "learning_rate": 2.9092882885656953e-05, "loss": 3.9312, "step": 1276928 }, { "epoch": 1.02, "learning_rate": 2.9084496938146433e-05, "loss": 3.9384, "step": 1277440 }, { "epoch": 1.02, "learning_rate": 2.9076110990635913e-05, "loss": 3.9356, "step": 1277952 }, { "epoch": 1.02, "learning_rate": 2.9067741421929122e-05, "loss": 3.9445, "step": 1278464 }, { "epoch": 1.02, "learning_rate": 2.9059355474418602e-05, "loss": 3.9358, "step": 1278976 }, { "epoch": 1.02, "learning_rate": 2.9050969526908085e-05, "loss": 3.9382, "step": 1279488 }, { "epoch": 1.02, "learning_rate": 2.9042583579397565e-05, "loss": 3.9522, "step": 1280000 }, { "epoch": 1.02, "learning_rate": 2.9034214010690774e-05, "loss": 3.9492, "step": 1280512 }, { "epoch": 1.02, "learning_rate": 2.9025844441983984e-05, "loss": 3.9423, "step": 1281024 }, { "epoch": 1.02, "learning_rate": 2.9017458494473463e-05, "loss": 3.9341, "step": 1281536 }, { "epoch": 1.02, "learning_rate": 2.9009072546962947e-05, "loss": 3.9443, "step": 1282048 }, { "epoch": 1.02, "learning_rate": 2.9000686599452427e-05, "loss": 3.9399, "step": 1282560 }, { "epoch": 1.02, "learning_rate": 2.8992317030745636e-05, "loss": 3.9364, "step": 1283072 }, { "epoch": 1.02, "learning_rate": 2.8983931083235116e-05, "loss": 3.9526, "step": 1283584 }, { "epoch": 1.02, "learning_rate": 2.8975545135724596e-05, "loss": 3.9367, "step": 1284096 }, { "epoch": 1.02, "learning_rate": 2.8967159188214076e-05, "loss": 3.9458, "step": 1284608 }, { "epoch": 1.02, "learning_rate": 2.8958773240703556e-05, "loss": 3.9307, "step": 1285120 }, { "epoch": 1.02, "learning_rate": 2.895038729319304e-05, "loss": 3.9362, "step": 1285632 }, { "epoch": 1.02, "learning_rate": 2.8942017724486248e-05, "loss": 3.9432, "step": 1286144 }, { "epoch": 1.02, "learning_rate": 2.8933631776975728e-05, "loss": 3.9368, "step": 1286656 }, { "epoch": 1.02, "learning_rate": 2.8925245829465208e-05, "loss": 3.9305, "step": 1287168 }, { "epoch": 1.02, "learning_rate": 2.8916859881954688e-05, "loss": 3.957, "step": 1287680 }, { "epoch": 1.02, "learning_rate": 2.89084903132479e-05, "loss": 3.9431, "step": 1288192 }, { "epoch": 1.02, "learning_rate": 2.890010436573738e-05, "loss": 3.9399, "step": 1288704 }, { "epoch": 1.02, "learning_rate": 2.889171841822686e-05, "loss": 3.9391, "step": 1289216 }, { "epoch": 1.02, "learning_rate": 2.888333247071634e-05, "loss": 3.9393, "step": 1289728 }, { "epoch": 1.02, "learning_rate": 2.887494652320582e-05, "loss": 3.9461, "step": 1290240 }, { "epoch": 1.02, "learning_rate": 2.88665605756953e-05, "loss": 3.9446, "step": 1290752 }, { "epoch": 1.02, "learning_rate": 2.8858174628184777e-05, "loss": 3.9382, "step": 1291264 }, { "epoch": 1.02, "learning_rate": 2.8849788680674257e-05, "loss": 3.9531, "step": 1291776 }, { "epoch": 1.02, "learning_rate": 2.8841402733163737e-05, "loss": 3.9482, "step": 1292288 }, { "epoch": 1.02, "learning_rate": 2.8833016785653217e-05, "loss": 3.9447, "step": 1292800 }, { "epoch": 1.02, "learning_rate": 2.8824647216946426e-05, "loss": 3.9431, "step": 1293312 }, { "epoch": 1.02, "learning_rate": 2.8816261269435906e-05, "loss": 3.9477, "step": 1293824 }, { "epoch": 1.02, "learning_rate": 2.8807875321925386e-05, "loss": 3.9418, "step": 1294336 }, { "epoch": 1.02, "learning_rate": 2.879948937441487e-05, "loss": 3.9443, "step": 1294848 }, { "epoch": 1.02, "learning_rate": 2.879110342690435e-05, "loss": 3.9413, "step": 1295360 }, { "epoch": 1.02, "learning_rate": 2.8782733858197558e-05, "loss": 3.9408, "step": 1295872 }, { "epoch": 1.02, "learning_rate": 2.8774347910687038e-05, "loss": 3.9497, "step": 1296384 }, { "epoch": 1.02, "learning_rate": 2.8765961963176518e-05, "loss": 3.9345, "step": 1296896 }, { "epoch": 1.02, "learning_rate": 2.8757576015665998e-05, "loss": 3.9366, "step": 1297408 }, { "epoch": 1.03, "eval_loss": 4.0154266357421875, "eval_runtime": 318.4816, "eval_samples_per_second": 1198.157, "eval_steps_per_second": 37.443, "step": 1297440 }, { "epoch": 0.0, "learning_rate": 2.8749190068155478e-05, "loss": 3.9305, "step": 1297920 }, { "epoch": 0.0, "learning_rate": 2.874080412064496e-05, "loss": 3.9325, "step": 1298432 }, { "epoch": 0.0, "learning_rate": 2.873241817313444e-05, "loss": 3.9575, "step": 1298944 }, { "epoch": 0.0, "learning_rate": 2.872403222562392e-05, "loss": 3.9487, "step": 1299456 }, { "epoch": 0.0, "learning_rate": 2.87156462781134e-05, "loss": 3.9429, "step": 1299968 }, { "epoch": 0.0, "learning_rate": 2.870726033060288e-05, "loss": 3.9417, "step": 1300480 }, { "epoch": 0.0, "learning_rate": 2.869887438309236e-05, "loss": 3.9402, "step": 1300992 }, { "epoch": 0.0, "learning_rate": 2.8690488435581838e-05, "loss": 3.932, "step": 1301504 }, { "epoch": 0.0, "learning_rate": 2.8682102488071318e-05, "loss": 3.9463, "step": 1302016 }, { "epoch": 0.0, "learning_rate": 2.8673716540560798e-05, "loss": 3.9441, "step": 1302528 }, { "epoch": 0.0, "learning_rate": 2.8665330593050277e-05, "loss": 3.947, "step": 1303040 }, { "epoch": 0.0, "learning_rate": 2.8656944645539757e-05, "loss": 3.9494, "step": 1303552 }, { "epoch": 0.0, "learning_rate": 2.8648575076832967e-05, "loss": 3.9361, "step": 1304064 }, { "epoch": 0.0, "learning_rate": 2.8640189129322446e-05, "loss": 3.9357, "step": 1304576 }, { "epoch": 0.0, "learning_rate": 2.8631803181811926e-05, "loss": 3.9304, "step": 1305088 }, { "epoch": 0.0, "learning_rate": 2.862341723430141e-05, "loss": 3.9301, "step": 1305600 }, { "epoch": 0.0, "learning_rate": 2.861503128679089e-05, "loss": 3.9409, "step": 1306112 }, { "epoch": 0.0, "learning_rate": 2.860664533928037e-05, "loss": 3.932, "step": 1306624 }, { "epoch": 0.0, "learning_rate": 2.859825939176985e-05, "loss": 3.9401, "step": 1307136 }, { "epoch": 0.0, "learning_rate": 2.858987344425933e-05, "loss": 3.9608, "step": 1307648 }, { "epoch": 0.0, "learning_rate": 2.858148749674881e-05, "loss": 3.941, "step": 1308160 }, { "epoch": 0.0, "learning_rate": 2.857310154923829e-05, "loss": 3.9472, "step": 1308672 }, { "epoch": 0.0, "learning_rate": 2.856471560172777e-05, "loss": 3.9376, "step": 1309184 }, { "epoch": 0.0, "learning_rate": 2.855632965421725e-05, "loss": 3.9511, "step": 1309696 }, { "epoch": 0.0, "learning_rate": 2.8547943706706726e-05, "loss": 3.9354, "step": 1310208 }, { "epoch": 0.0, "learning_rate": 2.8539574137999942e-05, "loss": 3.9398, "step": 1310720 }, { "epoch": 0.0, "learning_rate": 2.8531188190489422e-05, "loss": 3.9321, "step": 1311232 }, { "epoch": 0.0, "learning_rate": 2.8522802242978902e-05, "loss": 3.9379, "step": 1311744 }, { "epoch": 0.0, "learning_rate": 2.851441629546838e-05, "loss": 3.9335, "step": 1312256 }, { "epoch": 0.01, "learning_rate": 2.8506046726761594e-05, "loss": 3.9339, "step": 1312768 }, { "epoch": 0.01, "learning_rate": 2.8497677158054803e-05, "loss": 3.9377, "step": 1313280 }, { "epoch": 0.01, "learning_rate": 2.8489291210544283e-05, "loss": 3.9481, "step": 1313792 }, { "epoch": 0.01, "learning_rate": 2.8480905263033763e-05, "loss": 3.938, "step": 1314304 }, { "epoch": 0.01, "learning_rate": 2.8472519315523243e-05, "loss": 3.9451, "step": 1314816 }, { "epoch": 0.01, "learning_rate": 2.8464149746816456e-05, "loss": 3.9382, "step": 1315328 }, { "epoch": 0.01, "learning_rate": 2.8455763799305936e-05, "loss": 3.9487, "step": 1315840 }, { "epoch": 0.01, "learning_rate": 2.8447377851795416e-05, "loss": 3.9265, "step": 1316352 }, { "epoch": 0.01, "learning_rate": 2.8438991904284896e-05, "loss": 3.9437, "step": 1316864 }, { "epoch": 0.01, "learning_rate": 2.8430605956774375e-05, "loss": 3.9225, "step": 1317376 }, { "epoch": 0.01, "learning_rate": 2.842222000926385e-05, "loss": 3.9429, "step": 1317888 }, { "epoch": 0.01, "learning_rate": 2.8413834061753332e-05, "loss": 3.9326, "step": 1318400 }, { "epoch": 0.01, "learning_rate": 2.8405448114242812e-05, "loss": 3.9467, "step": 1318912 }, { "epoch": 0.01, "learning_rate": 2.8397078545536028e-05, "loss": 3.9295, "step": 1319424 }, { "epoch": 0.01, "learning_rate": 2.8388708976829237e-05, "loss": 3.9463, "step": 1319936 }, { "epoch": 0.01, "learning_rate": 2.8380323029318717e-05, "loss": 3.9426, "step": 1320448 }, { "epoch": 0.01, "learning_rate": 2.8371937081808197e-05, "loss": 3.9414, "step": 1320960 }, { "epoch": 0.01, "learning_rate": 2.8363551134297673e-05, "loss": 3.9482, "step": 1321472 }, { "epoch": 0.01, "learning_rate": 2.8355165186787153e-05, "loss": 3.9207, "step": 1321984 }, { "epoch": 0.01, "learning_rate": 2.8346779239276633e-05, "loss": 3.9318, "step": 1322496 }, { "epoch": 0.01, "learning_rate": 2.8338393291766113e-05, "loss": 3.9429, "step": 1323008 }, { "epoch": 0.01, "learning_rate": 2.8330023723059322e-05, "loss": 3.9411, "step": 1323520 }, { "epoch": 0.01, "learning_rate": 2.8321637775548802e-05, "loss": 3.9347, "step": 1324032 }, { "epoch": 0.01, "learning_rate": 2.8313251828038286e-05, "loss": 3.9336, "step": 1324544 }, { "epoch": 0.01, "learning_rate": 2.8304865880527766e-05, "loss": 3.9313, "step": 1325056 }, { "epoch": 0.01, "learning_rate": 2.8296479933017246e-05, "loss": 3.9239, "step": 1325568 }, { "epoch": 0.01, "learning_rate": 2.8288093985506726e-05, "loss": 3.9388, "step": 1326080 }, { "epoch": 0.01, "learning_rate": 2.8279708037996205e-05, "loss": 3.9206, "step": 1326592 }, { "epoch": 0.01, "learning_rate": 2.8271338469289415e-05, "loss": 3.9359, "step": 1327104 }, { "epoch": 0.01, "learning_rate": 2.8262952521778895e-05, "loss": 3.9435, "step": 1327616 }, { "epoch": 0.01, "learning_rate": 2.8254566574268378e-05, "loss": 3.9261, "step": 1328128 }, { "epoch": 0.01, "learning_rate": 2.8246180626757858e-05, "loss": 3.9275, "step": 1328640 }, { "epoch": 0.01, "learning_rate": 2.8237794679247338e-05, "loss": 3.9334, "step": 1329152 }, { "epoch": 0.01, "learning_rate": 2.8229441489344276e-05, "loss": 3.9226, "step": 1329664 }, { "epoch": 0.01, "learning_rate": 2.8221055541833756e-05, "loss": 3.9247, "step": 1330176 }, { "epoch": 0.01, "learning_rate": 2.821266959432324e-05, "loss": 3.9449, "step": 1330688 }, { "epoch": 0.01, "learning_rate": 2.820428364681272e-05, "loss": 3.9309, "step": 1331200 }, { "epoch": 0.01, "learning_rate": 2.81958976993022e-05, "loss": 3.9274, "step": 1331712 }, { "epoch": 0.01, "learning_rate": 2.818751175179168e-05, "loss": 3.9243, "step": 1332224 }, { "epoch": 0.01, "learning_rate": 2.817912580428116e-05, "loss": 3.9277, "step": 1332736 }, { "epoch": 0.01, "learning_rate": 2.817073985677064e-05, "loss": 3.9405, "step": 1333248 }, { "epoch": 0.01, "learning_rate": 2.8162370288063848e-05, "loss": 3.9362, "step": 1333760 }, { "epoch": 0.01, "learning_rate": 2.815398434055333e-05, "loss": 3.9302, "step": 1334272 }, { "epoch": 0.01, "learning_rate": 2.814559839304281e-05, "loss": 3.9421, "step": 1334784 }, { "epoch": 0.01, "learning_rate": 2.813721244553229e-05, "loss": 3.9428, "step": 1335296 }, { "epoch": 0.01, "learning_rate": 2.812882649802177e-05, "loss": 3.9276, "step": 1335808 }, { "epoch": 0.01, "learning_rate": 2.812045692931498e-05, "loss": 3.9369, "step": 1336320 }, { "epoch": 0.01, "learning_rate": 2.811207098180446e-05, "loss": 3.9329, "step": 1336832 }, { "epoch": 0.01, "learning_rate": 2.810368503429394e-05, "loss": 3.9325, "step": 1337344 }, { "epoch": 0.01, "learning_rate": 2.8095315465587153e-05, "loss": 3.9292, "step": 1337856 }, { "epoch": 0.01, "learning_rate": 2.8086929518076633e-05, "loss": 3.9309, "step": 1338368 }, { "epoch": 0.01, "learning_rate": 2.8078543570566113e-05, "loss": 3.944, "step": 1338880 }, { "epoch": 0.01, "learning_rate": 2.8070157623055593e-05, "loss": 3.9415, "step": 1339392 }, { "epoch": 0.01, "learning_rate": 2.8061771675545073e-05, "loss": 3.9333, "step": 1339904 }, { "epoch": 0.01, "learning_rate": 2.8053385728034553e-05, "loss": 3.91, "step": 1340416 }, { "epoch": 0.01, "learning_rate": 2.8044999780524033e-05, "loss": 3.9293, "step": 1340928 }, { "epoch": 0.01, "learning_rate": 2.803661383301351e-05, "loss": 3.9341, "step": 1341440 }, { "epoch": 0.01, "learning_rate": 2.8028244264306725e-05, "loss": 3.9348, "step": 1341952 }, { "epoch": 0.01, "learning_rate": 2.8019858316796205e-05, "loss": 3.9316, "step": 1342464 }, { "epoch": 0.01, "learning_rate": 2.8011488748089414e-05, "loss": 3.9316, "step": 1342976 }, { "epoch": 0.02, "learning_rate": 2.8003102800578894e-05, "loss": 3.9348, "step": 1343488 }, { "epoch": 0.02, "learning_rate": 2.7994716853068374e-05, "loss": 3.9287, "step": 1344000 }, { "epoch": 0.02, "learning_rate": 2.7986330905557857e-05, "loss": 3.9231, "step": 1344512 }, { "epoch": 0.02, "learning_rate": 2.797794495804733e-05, "loss": 3.9409, "step": 1345024 }, { "epoch": 0.02, "learning_rate": 2.796955901053681e-05, "loss": 3.9232, "step": 1345536 }, { "epoch": 0.02, "learning_rate": 2.796117306302629e-05, "loss": 3.9438, "step": 1346048 }, { "epoch": 0.02, "learning_rate": 2.795278711551577e-05, "loss": 3.9365, "step": 1346560 }, { "epoch": 0.02, "learning_rate": 2.7944417546808983e-05, "loss": 3.9181, "step": 1347072 }, { "epoch": 0.02, "learning_rate": 2.79360479781022e-05, "loss": 3.9334, "step": 1347584 }, { "epoch": 0.02, "learning_rate": 2.792766203059168e-05, "loss": 3.9324, "step": 1348096 }, { "epoch": 0.02, "learning_rate": 2.791927608308116e-05, "loss": 3.9428, "step": 1348608 }, { "epoch": 0.02, "learning_rate": 2.7910890135570632e-05, "loss": 3.9343, "step": 1349120 }, { "epoch": 0.02, "learning_rate": 2.7902504188060112e-05, "loss": 3.9312, "step": 1349632 }, { "epoch": 0.02, "learning_rate": 2.7894118240549595e-05, "loss": 3.9231, "step": 1350144 }, { "epoch": 0.02, "learning_rate": 2.7885732293039075e-05, "loss": 3.9374, "step": 1350656 }, { "epoch": 0.02, "learning_rate": 2.7877362724332284e-05, "loss": 3.9182, "step": 1351168 }, { "epoch": 0.02, "learning_rate": 2.7868976776821764e-05, "loss": 3.9273, "step": 1351680 }, { "epoch": 0.02, "learning_rate": 2.7860590829311244e-05, "loss": 3.9329, "step": 1352192 }, { "epoch": 0.02, "learning_rate": 2.7852204881800724e-05, "loss": 3.9309, "step": 1352704 }, { "epoch": 0.02, "learning_rate": 2.7843818934290204e-05, "loss": 3.9197, "step": 1353216 }, { "epoch": 0.02, "learning_rate": 2.7835449365583417e-05, "loss": 3.931, "step": 1353728 }, { "epoch": 0.02, "learning_rate": 2.7827063418072897e-05, "loss": 3.9271, "step": 1354240 }, { "epoch": 0.02, "learning_rate": 2.7818677470562376e-05, "loss": 3.93, "step": 1354752 }, { "epoch": 0.02, "learning_rate": 2.7810291523051856e-05, "loss": 3.9297, "step": 1355264 }, { "epoch": 0.02, "learning_rate": 2.7801905575541336e-05, "loss": 3.9244, "step": 1355776 }, { "epoch": 0.02, "learning_rate": 2.7793519628030816e-05, "loss": 3.95, "step": 1356288 }, { "epoch": 0.02, "learning_rate": 2.7785133680520296e-05, "loss": 3.9402, "step": 1356800 }, { "epoch": 0.02, "learning_rate": 2.777676411181351e-05, "loss": 3.9334, "step": 1357312 }, { "epoch": 0.02, "learning_rate": 2.776837816430299e-05, "loss": 3.9242, "step": 1357824 }, { "epoch": 0.02, "learning_rate": 2.775999221679247e-05, "loss": 3.9333, "step": 1358336 }, { "epoch": 0.02, "learning_rate": 2.775160626928195e-05, "loss": 3.9319, "step": 1358848 }, { "epoch": 0.02, "learning_rate": 2.774322032177143e-05, "loss": 3.9233, "step": 1359360 }, { "epoch": 0.02, "learning_rate": 2.773483437426091e-05, "loss": 3.9438, "step": 1359872 }, { "epoch": 0.02, "learning_rate": 2.772644842675039e-05, "loss": 3.9322, "step": 1360384 }, { "epoch": 0.02, "learning_rate": 2.7718062479239872e-05, "loss": 3.9304, "step": 1360896 }, { "epoch": 0.02, "learning_rate": 2.7709676531729345e-05, "loss": 3.9265, "step": 1361408 }, { "epoch": 0.02, "learning_rate": 2.770132334182629e-05, "loss": 3.929, "step": 1361920 }, { "epoch": 0.02, "learning_rate": 2.769293739431577e-05, "loss": 3.9291, "step": 1362432 }, { "epoch": 0.02, "learning_rate": 2.768455144680525e-05, "loss": 3.9306, "step": 1362944 }, { "epoch": 0.02, "learning_rate": 2.7676165499294733e-05, "loss": 3.9171, "step": 1363456 }, { "epoch": 0.02, "learning_rate": 2.7667779551784213e-05, "loss": 3.9468, "step": 1363968 }, { "epoch": 0.02, "learning_rate": 2.7659409983077422e-05, "loss": 3.9398, "step": 1364480 }, { "epoch": 0.02, "learning_rate": 2.7651024035566902e-05, "loss": 3.9304, "step": 1364992 }, { "epoch": 0.02, "learning_rate": 2.7642638088056382e-05, "loss": 3.9289, "step": 1365504 }, { "epoch": 0.02, "learning_rate": 2.7634252140545862e-05, "loss": 3.9252, "step": 1366016 }, { "epoch": 0.02, "learning_rate": 2.7625866193035342e-05, "loss": 3.9389, "step": 1366528 }, { "epoch": 0.02, "learning_rate": 2.761748024552482e-05, "loss": 3.9367, "step": 1367040 }, { "epoch": 0.02, "learning_rate": 2.7609110676818035e-05, "loss": 3.9273, "step": 1367552 }, { "epoch": 0.02, "learning_rate": 2.7600724729307515e-05, "loss": 3.9444, "step": 1368064 }, { "epoch": 0.02, "learning_rate": 2.7592338781796995e-05, "loss": 3.9357, "step": 1368576 }, { "epoch": 0.02, "learning_rate": 2.758395283428647e-05, "loss": 3.9375, "step": 1369088 }, { "epoch": 0.02, "learning_rate": 2.757556688677595e-05, "loss": 3.9325, "step": 1369600 }, { "epoch": 0.02, "learning_rate": 2.756718093926543e-05, "loss": 3.9396, "step": 1370112 }, { "epoch": 0.02, "learning_rate": 2.755881137055864e-05, "loss": 3.9334, "step": 1370624 }, { "epoch": 0.02, "learning_rate": 2.755042542304812e-05, "loss": 3.9314, "step": 1371136 }, { "epoch": 0.02, "learning_rate": 2.75420394755376e-05, "loss": 3.9322, "step": 1371648 }, { "epoch": 0.02, "learning_rate": 2.7533669906830816e-05, "loss": 3.9343, "step": 1372160 }, { "epoch": 0.02, "learning_rate": 2.7525283959320292e-05, "loss": 3.9366, "step": 1372672 }, { "epoch": 0.02, "learning_rate": 2.7516898011809772e-05, "loss": 3.9246, "step": 1373184 }, { "epoch": 0.02, "learning_rate": 2.7508512064299252e-05, "loss": 3.9278, "step": 1373696 }, { "epoch": 0.03, "eval_loss": 4.011216640472412, "eval_runtime": 289.5858, "eval_samples_per_second": 1317.713, "eval_steps_per_second": 41.18, "step": 1373760 }, { "epoch": 1.0, "learning_rate": 2.7500126116788732e-05, "loss": 3.9221, "step": 1374208 }, { "epoch": 1.0, "learning_rate": 2.7491740169278212e-05, "loss": 3.9217, "step": 1374720 }, { "epoch": 1.0, "learning_rate": 2.7483354221767692e-05, "loss": 3.9482, "step": 1375232 }, { "epoch": 1.0, "learning_rate": 2.7474968274257172e-05, "loss": 3.9406, "step": 1375744 }, { "epoch": 1.0, "learning_rate": 2.7466582326746652e-05, "loss": 3.9329, "step": 1376256 }, { "epoch": 1.0, "learning_rate": 2.7458196379236135e-05, "loss": 3.9299, "step": 1376768 }, { "epoch": 1.0, "learning_rate": 2.7449810431725615e-05, "loss": 3.9329, "step": 1377280 }, { "epoch": 1.0, "learning_rate": 2.7441424484215095e-05, "loss": 3.9205, "step": 1377792 }, { "epoch": 1.0, "learning_rate": 2.7433071294312034e-05, "loss": 3.9401, "step": 1378304 }, { "epoch": 1.0, "learning_rate": 2.7424685346801514e-05, "loss": 3.9346, "step": 1378816 }, { "epoch": 1.0, "learning_rate": 2.7416299399290997e-05, "loss": 3.936, "step": 1379328 }, { "epoch": 1.0, "learning_rate": 2.7407913451780477e-05, "loss": 3.9396, "step": 1379840 }, { "epoch": 1.0, "learning_rate": 2.7399543883073686e-05, "loss": 3.9265, "step": 1380352 }, { "epoch": 1.0, "learning_rate": 2.7391157935563166e-05, "loss": 3.9259, "step": 1380864 }, { "epoch": 1.0, "learning_rate": 2.7382771988052646e-05, "loss": 3.9236, "step": 1381376 }, { "epoch": 1.0, "learning_rate": 2.7374386040542126e-05, "loss": 3.9245, "step": 1381888 }, { "epoch": 1.0, "learning_rate": 2.7366000093031606e-05, "loss": 3.9272, "step": 1382400 }, { "epoch": 1.0, "learning_rate": 2.735761414552109e-05, "loss": 3.9224, "step": 1382912 }, { "epoch": 1.0, "learning_rate": 2.734922819801057e-05, "loss": 3.93, "step": 1383424 }, { "epoch": 1.0, "learning_rate": 2.734084225050005e-05, "loss": 3.9553, "step": 1383936 }, { "epoch": 1.0, "learning_rate": 2.7332472681793258e-05, "loss": 3.9324, "step": 1384448 }, { "epoch": 1.0, "learning_rate": 2.7324086734282738e-05, "loss": 3.9338, "step": 1384960 }, { "epoch": 1.0, "learning_rate": 2.7315700786772218e-05, "loss": 3.9338, "step": 1385472 }, { "epoch": 1.0, "learning_rate": 2.7307314839261698e-05, "loss": 3.9399, "step": 1385984 }, { "epoch": 1.0, "learning_rate": 2.729892889175118e-05, "loss": 3.9254, "step": 1386496 }, { "epoch": 1.0, "learning_rate": 2.7290542944240655e-05, "loss": 3.9333, "step": 1387008 }, { "epoch": 1.0, "learning_rate": 2.7282156996730134e-05, "loss": 3.922, "step": 1387520 }, { "epoch": 1.0, "learning_rate": 2.7273771049219614e-05, "loss": 3.927, "step": 1388032 }, { "epoch": 1.0, "learning_rate": 2.7265401480512827e-05, "loss": 3.9229, "step": 1388544 }, { "epoch": 1.01, "learning_rate": 2.7257015533002307e-05, "loss": 3.9248, "step": 1389056 }, { "epoch": 1.01, "learning_rate": 2.7248629585491787e-05, "loss": 3.9266, "step": 1389568 }, { "epoch": 1.01, "learning_rate": 2.7240243637981267e-05, "loss": 3.9399, "step": 1390080 }, { "epoch": 1.01, "learning_rate": 2.7231857690470747e-05, "loss": 3.9309, "step": 1390592 }, { "epoch": 1.01, "learning_rate": 2.7223488121763956e-05, "loss": 3.9386, "step": 1391104 }, { "epoch": 1.01, "learning_rate": 2.7215118553057172e-05, "loss": 3.923, "step": 1391616 }, { "epoch": 1.01, "learning_rate": 2.720673260554665e-05, "loss": 3.9444, "step": 1392128 }, { "epoch": 1.01, "learning_rate": 2.7198346658036128e-05, "loss": 3.9137, "step": 1392640 }, { "epoch": 1.01, "learning_rate": 2.7189960710525608e-05, "loss": 3.9368, "step": 1393152 }, { "epoch": 1.01, "learning_rate": 2.7181574763015088e-05, "loss": 3.9143, "step": 1393664 }, { "epoch": 1.01, "learning_rate": 2.7173188815504568e-05, "loss": 3.932, "step": 1394176 }, { "epoch": 1.01, "learning_rate": 2.716481924679778e-05, "loss": 3.9223, "step": 1394688 }, { "epoch": 1.01, "learning_rate": 2.715643329928726e-05, "loss": 3.9399, "step": 1395200 }, { "epoch": 1.01, "learning_rate": 2.7148063730580476e-05, "loss": 3.9223, "step": 1395712 }, { "epoch": 1.01, "learning_rate": 2.713967778306995e-05, "loss": 3.9318, "step": 1396224 }, { "epoch": 1.01, "learning_rate": 2.713129183555943e-05, "loss": 3.9343, "step": 1396736 }, { "epoch": 1.01, "learning_rate": 2.712290588804891e-05, "loss": 3.9369, "step": 1397248 }, { "epoch": 1.01, "learning_rate": 2.711451994053839e-05, "loss": 3.9363, "step": 1397760 }, { "epoch": 1.01, "learning_rate": 2.7106133993027873e-05, "loss": 3.9163, "step": 1398272 }, { "epoch": 1.01, "learning_rate": 2.7097748045517353e-05, "loss": 3.9181, "step": 1398784 }, { "epoch": 1.01, "learning_rate": 2.7089362098006833e-05, "loss": 3.9361, "step": 1399296 }, { "epoch": 1.01, "learning_rate": 2.7080976150496313e-05, "loss": 3.9329, "step": 1399808 }, { "epoch": 1.01, "learning_rate": 2.7072590202985793e-05, "loss": 3.9233, "step": 1400320 }, { "epoch": 1.01, "learning_rate": 2.7064204255475273e-05, "loss": 3.925, "step": 1400832 }, { "epoch": 1.01, "learning_rate": 2.7055834686768482e-05, "loss": 3.9244, "step": 1401344 }, { "epoch": 1.01, "learning_rate": 2.7047448739257965e-05, "loss": 3.9121, "step": 1401856 }, { "epoch": 1.01, "learning_rate": 2.7039062791747445e-05, "loss": 3.9266, "step": 1402368 }, { "epoch": 1.01, "learning_rate": 2.7030676844236925e-05, "loss": 3.9141, "step": 1402880 }, { "epoch": 1.01, "learning_rate": 2.7022290896726405e-05, "loss": 3.9265, "step": 1403392 }, { "epoch": 1.01, "learning_rate": 2.7013904949215885e-05, "loss": 3.936, "step": 1403904 }, { "epoch": 1.01, "learning_rate": 2.7005519001705365e-05, "loss": 3.9175, "step": 1404416 }, { "epoch": 1.01, "learning_rate": 2.6997149432998574e-05, "loss": 3.92, "step": 1404928 }, { "epoch": 1.01, "learning_rate": 2.6988763485488054e-05, "loss": 3.9237, "step": 1405440 }, { "epoch": 1.01, "learning_rate": 2.6980377537977537e-05, "loss": 3.9135, "step": 1405952 }, { "epoch": 1.01, "learning_rate": 2.697199159046701e-05, "loss": 3.9119, "step": 1406464 }, { "epoch": 1.01, "learning_rate": 2.696360564295649e-05, "loss": 3.9347, "step": 1406976 }, { "epoch": 1.01, "learning_rate": 2.695521969544597e-05, "loss": 3.9223, "step": 1407488 }, { "epoch": 1.01, "learning_rate": 2.694683374793545e-05, "loss": 3.9174, "step": 1408000 }, { "epoch": 1.01, "learning_rate": 2.693844780042493e-05, "loss": 3.9154, "step": 1408512 }, { "epoch": 1.01, "learning_rate": 2.6930078231718143e-05, "loss": 3.922, "step": 1409024 }, { "epoch": 1.01, "learning_rate": 2.6921692284207623e-05, "loss": 3.9313, "step": 1409536 }, { "epoch": 1.01, "learning_rate": 2.6913306336697103e-05, "loss": 3.9295, "step": 1410048 }, { "epoch": 1.01, "learning_rate": 2.6904920389186583e-05, "loss": 3.9199, "step": 1410560 }, { "epoch": 1.01, "learning_rate": 2.689655082047979e-05, "loss": 3.9325, "step": 1411072 }, { "epoch": 1.01, "learning_rate": 2.6888164872969275e-05, "loss": 3.9304, "step": 1411584 }, { "epoch": 1.01, "learning_rate": 2.6879778925458755e-05, "loss": 3.921, "step": 1412096 }, { "epoch": 1.01, "learning_rate": 2.6871392977948235e-05, "loss": 3.9258, "step": 1412608 }, { "epoch": 1.01, "learning_rate": 2.6863007030437715e-05, "loss": 3.9283, "step": 1413120 }, { "epoch": 1.01, "learning_rate": 2.6854637461730924e-05, "loss": 3.9243, "step": 1413632 }, { "epoch": 1.01, "learning_rate": 2.6846251514220404e-05, "loss": 3.9229, "step": 1414144 }, { "epoch": 1.01, "learning_rate": 2.6837865566709884e-05, "loss": 3.922, "step": 1414656 }, { "epoch": 1.01, "learning_rate": 2.6829479619199367e-05, "loss": 3.9316, "step": 1415168 }, { "epoch": 1.01, "learning_rate": 2.6821093671688847e-05, "loss": 3.934, "step": 1415680 }, { "epoch": 1.01, "learning_rate": 2.6812724102982056e-05, "loss": 3.9211, "step": 1416192 }, { "epoch": 1.01, "learning_rate": 2.6804338155471536e-05, "loss": 3.908, "step": 1416704 }, { "epoch": 1.01, "learning_rate": 2.6795952207961016e-05, "loss": 3.9167, "step": 1417216 }, { "epoch": 1.01, "learning_rate": 2.6787566260450496e-05, "loss": 3.9244, "step": 1417728 }, { "epoch": 1.01, "learning_rate": 2.677919669174371e-05, "loss": 3.9275, "step": 1418240 }, { "epoch": 1.01, "learning_rate": 2.677081074423319e-05, "loss": 3.9213, "step": 1418752 }, { "epoch": 1.01, "learning_rate": 2.6762441175526398e-05, "loss": 3.9231, "step": 1419264 }, { "epoch": 1.02, "learning_rate": 2.6754055228015878e-05, "loss": 3.9295, "step": 1419776 }, { "epoch": 1.02, "learning_rate": 2.6745669280505358e-05, "loss": 3.9152, "step": 1420288 }, { "epoch": 1.02, "learning_rate": 2.6737283332994838e-05, "loss": 3.9176, "step": 1420800 }, { "epoch": 1.02, "learning_rate": 2.672889738548432e-05, "loss": 3.9299, "step": 1421312 }, { "epoch": 1.02, "learning_rate": 2.67205114379738e-05, "loss": 3.9184, "step": 1421824 }, { "epoch": 1.02, "learning_rate": 2.671214186926701e-05, "loss": 3.9364, "step": 1422336 }, { "epoch": 1.02, "learning_rate": 2.670375592175649e-05, "loss": 3.9237, "step": 1422848 }, { "epoch": 1.02, "learning_rate": 2.669536997424597e-05, "loss": 3.9097, "step": 1423360 }, { "epoch": 1.02, "learning_rate": 2.668698402673545e-05, "loss": 3.9251, "step": 1423872 }, { "epoch": 1.02, "learning_rate": 2.667859807922493e-05, "loss": 3.9221, "step": 1424384 }, { "epoch": 1.02, "learning_rate": 2.6670212131714413e-05, "loss": 3.9355, "step": 1424896 }, { "epoch": 1.02, "learning_rate": 2.6661826184203893e-05, "loss": 3.9295, "step": 1425408 }, { "epoch": 1.02, "learning_rate": 2.6653440236693373e-05, "loss": 3.9193, "step": 1425920 }, { "epoch": 1.02, "learning_rate": 2.6645070667986582e-05, "loss": 3.9113, "step": 1426432 }, { "epoch": 1.02, "learning_rate": 2.6636684720476062e-05, "loss": 3.9293, "step": 1426944 }, { "epoch": 1.02, "learning_rate": 2.6628315151769275e-05, "loss": 3.9104, "step": 1427456 }, { "epoch": 1.02, "learning_rate": 2.6619929204258755e-05, "loss": 3.922, "step": 1427968 }, { "epoch": 1.02, "learning_rate": 2.6611543256748234e-05, "loss": 3.9222, "step": 1428480 }, { "epoch": 1.02, "learning_rate": 2.6603157309237714e-05, "loss": 3.9192, "step": 1428992 }, { "epoch": 1.02, "learning_rate": 2.6594771361727194e-05, "loss": 3.9086, "step": 1429504 }, { "epoch": 1.02, "learning_rate": 2.6586385414216674e-05, "loss": 3.9286, "step": 1430016 }, { "epoch": 1.02, "learning_rate": 2.657799946670615e-05, "loss": 3.9155, "step": 1430528 }, { "epoch": 1.02, "learning_rate": 2.656961351919563e-05, "loss": 3.9185, "step": 1431040 }, { "epoch": 1.02, "learning_rate": 2.656122757168511e-05, "loss": 3.922, "step": 1431552 }, { "epoch": 1.02, "learning_rate": 2.655285800297832e-05, "loss": 3.9155, "step": 1432064 }, { "epoch": 1.02, "learning_rate": 2.65444720554678e-05, "loss": 3.9388, "step": 1432576 }, { "epoch": 1.02, "learning_rate": 2.653608610795728e-05, "loss": 3.9286, "step": 1433088 }, { "epoch": 1.02, "learning_rate": 2.652770016044676e-05, "loss": 3.9279, "step": 1433600 }, { "epoch": 1.02, "learning_rate": 2.6519330591739972e-05, "loss": 3.915, "step": 1434112 }, { "epoch": 1.02, "learning_rate": 2.6510944644229452e-05, "loss": 3.9227, "step": 1434624 }, { "epoch": 1.02, "learning_rate": 2.6502575075522668e-05, "loss": 3.9268, "step": 1435136 }, { "epoch": 1.02, "learning_rate": 2.6494189128012148e-05, "loss": 3.9114, "step": 1435648 }, { "epoch": 1.02, "learning_rate": 2.648580318050162e-05, "loss": 3.9312, "step": 1436160 }, { "epoch": 1.02, "learning_rate": 2.6477417232991105e-05, "loss": 3.9243, "step": 1436672 }, { "epoch": 1.02, "learning_rate": 2.646904766428432e-05, "loss": 3.9191, "step": 1437184 }, { "epoch": 1.02, "learning_rate": 2.6460661716773794e-05, "loss": 3.9217, "step": 1437696 }, { "epoch": 1.02, "learning_rate": 2.6452275769263274e-05, "loss": 3.9204, "step": 1438208 }, { "epoch": 1.02, "learning_rate": 2.6443889821752754e-05, "loss": 3.9144, "step": 1438720 }, { "epoch": 1.02, "learning_rate": 2.6435503874242233e-05, "loss": 3.925, "step": 1439232 }, { "epoch": 1.02, "learning_rate": 2.6427117926731713e-05, "loss": 3.9108, "step": 1439744 }, { "epoch": 1.02, "learning_rate": 2.6418731979221197e-05, "loss": 3.9332, "step": 1440256 }, { "epoch": 1.02, "learning_rate": 2.6410346031710677e-05, "loss": 3.9335, "step": 1440768 }, { "epoch": 1.02, "learning_rate": 2.6401960084200157e-05, "loss": 3.9188, "step": 1441280 }, { "epoch": 1.02, "learning_rate": 2.6393590515493366e-05, "loss": 3.9197, "step": 1441792 }, { "epoch": 1.02, "learning_rate": 2.6385204567982846e-05, "loss": 3.9183, "step": 1442304 }, { "epoch": 1.02, "learning_rate": 2.6376818620472326e-05, "loss": 3.9269, "step": 1442816 }, { "epoch": 1.02, "learning_rate": 2.6368449051765538e-05, "loss": 3.9253, "step": 1443328 }, { "epoch": 1.02, "learning_rate": 2.6360063104255018e-05, "loss": 3.9216, "step": 1443840 }, { "epoch": 1.02, "learning_rate": 2.6351677156744498e-05, "loss": 3.932, "step": 1444352 }, { "epoch": 1.02, "learning_rate": 2.6343291209233978e-05, "loss": 3.9271, "step": 1444864 }, { "epoch": 1.02, "learning_rate": 2.6334905261723458e-05, "loss": 3.9293, "step": 1445376 }, { "epoch": 1.02, "learning_rate": 2.6326519314212938e-05, "loss": 3.9194, "step": 1445888 }, { "epoch": 1.02, "learning_rate": 2.6318149745506147e-05, "loss": 3.9362, "step": 1446400 }, { "epoch": 1.02, "learning_rate": 2.630976379799563e-05, "loss": 3.9243, "step": 1446912 }, { "epoch": 1.02, "learning_rate": 2.630137785048511e-05, "loss": 3.9192, "step": 1447424 }, { "epoch": 1.02, "learning_rate": 2.629299190297459e-05, "loss": 3.9258, "step": 1447936 }, { "epoch": 1.02, "learning_rate": 2.62846223342678e-05, "loss": 3.9275, "step": 1448448 }, { "epoch": 1.02, "learning_rate": 2.627623638675728e-05, "loss": 3.9244, "step": 1448960 }, { "epoch": 1.02, "learning_rate": 2.626785043924676e-05, "loss": 3.914, "step": 1449472 }, { "epoch": 1.02, "learning_rate": 2.625946449173624e-05, "loss": 3.9154, "step": 1449984 }, { "epoch": 1.03, "eval_loss": 4.0067596435546875, "eval_runtime": 286.5064, "eval_samples_per_second": 1331.876, "eval_steps_per_second": 41.622, "step": 1450080 }, { "epoch": 0.0, "learning_rate": 2.6251078544225723e-05, "loss": 3.9131, "step": 1450496 }, { "epoch": 0.0, "learning_rate": 2.6242692596715203e-05, "loss": 3.913, "step": 1451008 }, { "epoch": 0.0, "learning_rate": 2.6234306649204683e-05, "loss": 3.9352, "step": 1451520 }, { "epoch": 0.0, "learning_rate": 2.6225920701694156e-05, "loss": 3.9316, "step": 1452032 }, { "epoch": 0.0, "learning_rate": 2.6217534754183636e-05, "loss": 3.9316, "step": 1452544 }, { "epoch": 0.0, "learning_rate": 2.6209148806673116e-05, "loss": 3.9153, "step": 1453056 }, { "epoch": 0.0, "learning_rate": 2.62007628591626e-05, "loss": 3.9263, "step": 1453568 }, { "epoch": 0.0, "learning_rate": 2.619237691165208e-05, "loss": 3.911, "step": 1454080 }, { "epoch": 0.0, "learning_rate": 2.618399096414156e-05, "loss": 3.9317, "step": 1454592 }, { "epoch": 0.0, "learning_rate": 2.617560501663104e-05, "loss": 3.9257, "step": 1455104 }, { "epoch": 0.0, "learning_rate": 2.616721906912052e-05, "loss": 3.9232, "step": 1455616 }, { "epoch": 0.0, "learning_rate": 2.615883312161e-05, "loss": 3.9334, "step": 1456128 }, { "epoch": 0.0, "learning_rate": 2.6150463552903208e-05, "loss": 3.915, "step": 1456640 }, { "epoch": 0.0, "learning_rate": 2.614207760539269e-05, "loss": 3.9222, "step": 1457152 }, { "epoch": 0.0, "learning_rate": 2.613369165788217e-05, "loss": 3.9114, "step": 1457664 }, { "epoch": 0.0, "learning_rate": 2.612530571037165e-05, "loss": 3.9204, "step": 1458176 }, { "epoch": 0.0, "learning_rate": 2.611691976286113e-05, "loss": 3.9152, "step": 1458688 }, { "epoch": 0.0, "learning_rate": 2.610853381535061e-05, "loss": 3.9162, "step": 1459200 }, { "epoch": 0.0, "learning_rate": 2.610014786784009e-05, "loss": 3.9183, "step": 1459712 }, { "epoch": 0.0, "learning_rate": 2.609176192032957e-05, "loss": 3.9426, "step": 1460224 }, { "epoch": 0.0, "learning_rate": 2.6083392351622783e-05, "loss": 3.9225, "step": 1460736 }, { "epoch": 0.0, "learning_rate": 2.6075006404112263e-05, "loss": 3.9272, "step": 1461248 }, { "epoch": 0.0, "learning_rate": 2.6066620456601743e-05, "loss": 3.9241, "step": 1461760 }, { "epoch": 0.0, "learning_rate": 2.6058234509091223e-05, "loss": 3.9329, "step": 1462272 }, { "epoch": 0.0, "learning_rate": 2.6049848561580696e-05, "loss": 3.9166, "step": 1462784 }, { "epoch": 0.0, "learning_rate": 2.6041478992873912e-05, "loss": 3.9232, "step": 1463296 }, { "epoch": 0.0, "learning_rate": 2.6033093045363392e-05, "loss": 3.914, "step": 1463808 }, { "epoch": 0.0, "learning_rate": 2.602470709785287e-05, "loss": 3.9137, "step": 1464320 }, { "epoch": 0.0, "learning_rate": 2.601632115034235e-05, "loss": 3.9139, "step": 1464832 }, { "epoch": 0.01, "learning_rate": 2.600793520283183e-05, "loss": 3.9209, "step": 1465344 }, { "epoch": 0.01, "learning_rate": 2.599954925532131e-05, "loss": 3.9174, "step": 1465856 }, { "epoch": 0.01, "learning_rate": 2.599116330781079e-05, "loss": 3.9289, "step": 1466368 }, { "epoch": 0.01, "learning_rate": 2.598277736030027e-05, "loss": 3.9227, "step": 1466880 }, { "epoch": 0.01, "learning_rate": 2.597440779159348e-05, "loss": 3.9272, "step": 1467392 }, { "epoch": 0.01, "learning_rate": 2.5966038222886697e-05, "loss": 3.9178, "step": 1467904 }, { "epoch": 0.01, "learning_rate": 2.595765227537617e-05, "loss": 3.9295, "step": 1468416 }, { "epoch": 0.01, "learning_rate": 2.594926632786565e-05, "loss": 3.9115, "step": 1468928 }, { "epoch": 0.01, "learning_rate": 2.594088038035513e-05, "loss": 3.9254, "step": 1469440 }, { "epoch": 0.01, "learning_rate": 2.5932494432844613e-05, "loss": 3.9042, "step": 1469952 }, { "epoch": 0.01, "learning_rate": 2.5924124864137823e-05, "loss": 3.9201, "step": 1470464 }, { "epoch": 0.01, "learning_rate": 2.5915738916627302e-05, "loss": 3.9158, "step": 1470976 }, { "epoch": 0.01, "learning_rate": 2.590736934792052e-05, "loss": 3.9317, "step": 1471488 }, { "epoch": 0.01, "learning_rate": 2.589898340040999e-05, "loss": 3.9149, "step": 1472000 }, { "epoch": 0.01, "learning_rate": 2.5890597452899475e-05, "loss": 3.9238, "step": 1472512 }, { "epoch": 0.01, "learning_rate": 2.5882211505388955e-05, "loss": 3.9255, "step": 1473024 }, { "epoch": 0.01, "learning_rate": 2.5873825557878435e-05, "loss": 3.9293, "step": 1473536 }, { "epoch": 0.01, "learning_rate": 2.5865439610367915e-05, "loss": 3.9221, "step": 1474048 }, { "epoch": 0.01, "learning_rate": 2.5857070041661124e-05, "loss": 3.9117, "step": 1474560 }, { "epoch": 0.01, "learning_rate": 2.5848684094150604e-05, "loss": 3.9052, "step": 1475072 }, { "epoch": 0.01, "learning_rate": 2.5840314525443816e-05, "loss": 3.928, "step": 1475584 }, { "epoch": 0.01, "learning_rate": 2.5831928577933296e-05, "loss": 3.9263, "step": 1476096 }, { "epoch": 0.01, "learning_rate": 2.5823542630422776e-05, "loss": 3.9184, "step": 1476608 }, { "epoch": 0.01, "learning_rate": 2.5815156682912256e-05, "loss": 3.9123, "step": 1477120 }, { "epoch": 0.01, "learning_rate": 2.5806770735401736e-05, "loss": 3.9185, "step": 1477632 }, { "epoch": 0.01, "learning_rate": 2.5798384787891216e-05, "loss": 3.901, "step": 1478144 }, { "epoch": 0.01, "learning_rate": 2.5789998840380696e-05, "loss": 3.9234, "step": 1478656 }, { "epoch": 0.01, "learning_rate": 2.5781612892870176e-05, "loss": 3.9028, "step": 1479168 }, { "epoch": 0.01, "learning_rate": 2.5773226945359656e-05, "loss": 3.9192, "step": 1479680 }, { "epoch": 0.01, "learning_rate": 2.576484099784914e-05, "loss": 3.9248, "step": 1480192 }, { "epoch": 0.01, "learning_rate": 2.575645505033862e-05, "loss": 3.9123, "step": 1480704 }, { "epoch": 0.01, "learning_rate": 2.57480691028281e-05, "loss": 3.9075, "step": 1481216 }, { "epoch": 0.01, "learning_rate": 2.573968315531758e-05, "loss": 3.9182, "step": 1481728 }, { "epoch": 0.01, "learning_rate": 2.5731297207807052e-05, "loss": 3.9033, "step": 1482240 }, { "epoch": 0.01, "learning_rate": 2.5722911260296532e-05, "loss": 3.9094, "step": 1482752 }, { "epoch": 0.01, "learning_rate": 2.5714541691589748e-05, "loss": 3.9222, "step": 1483264 }, { "epoch": 0.01, "learning_rate": 2.570615574407923e-05, "loss": 3.9172, "step": 1483776 }, { "epoch": 0.01, "learning_rate": 2.5697769796568705e-05, "loss": 3.9092, "step": 1484288 }, { "epoch": 0.01, "learning_rate": 2.5689383849058185e-05, "loss": 3.9039, "step": 1484800 }, { "epoch": 0.01, "learning_rate": 2.5680997901547665e-05, "loss": 3.9148, "step": 1485312 }, { "epoch": 0.01, "learning_rate": 2.5672611954037145e-05, "loss": 3.9171, "step": 1485824 }, { "epoch": 0.01, "learning_rate": 2.5664226006526624e-05, "loss": 3.921, "step": 1486336 }, { "epoch": 0.01, "learning_rate": 2.5655840059016108e-05, "loss": 3.9152, "step": 1486848 }, { "epoch": 0.01, "learning_rate": 2.5647486869113053e-05, "loss": 3.9214, "step": 1487360 }, { "epoch": 0.01, "learning_rate": 2.5639100921602526e-05, "loss": 3.9239, "step": 1487872 }, { "epoch": 0.01, "learning_rate": 2.5630714974092006e-05, "loss": 3.9117, "step": 1488384 }, { "epoch": 0.01, "learning_rate": 2.5622329026581486e-05, "loss": 3.9151, "step": 1488896 }, { "epoch": 0.01, "learning_rate": 2.561394307907097e-05, "loss": 3.9194, "step": 1489408 }, { "epoch": 0.01, "learning_rate": 2.560555713156045e-05, "loss": 3.9177, "step": 1489920 }, { "epoch": 0.01, "learning_rate": 2.559717118404993e-05, "loss": 3.9145, "step": 1490432 }, { "epoch": 0.01, "learning_rate": 2.5588801615343138e-05, "loss": 3.9135, "step": 1490944 }, { "epoch": 0.01, "learning_rate": 2.5580415667832618e-05, "loss": 3.9204, "step": 1491456 }, { "epoch": 0.01, "learning_rate": 2.5572029720322098e-05, "loss": 3.927, "step": 1491968 }, { "epoch": 0.01, "learning_rate": 2.5563643772811578e-05, "loss": 3.9182, "step": 1492480 }, { "epoch": 0.01, "learning_rate": 2.555525782530106e-05, "loss": 3.9021, "step": 1492992 }, { "epoch": 0.01, "learning_rate": 2.554687187779054e-05, "loss": 3.9039, "step": 1493504 }, { "epoch": 0.01, "learning_rate": 2.553848593028002e-05, "loss": 3.9133, "step": 1494016 }, { "epoch": 0.01, "learning_rate": 2.553011636157323e-05, "loss": 3.9209, "step": 1494528 }, { "epoch": 0.01, "learning_rate": 2.552173041406271e-05, "loss": 3.9167, "step": 1495040 }, { "epoch": 0.01, "learning_rate": 2.5513360845355923e-05, "loss": 3.9083, "step": 1495552 }, { "epoch": 0.02, "learning_rate": 2.5504974897845403e-05, "loss": 3.9211, "step": 1496064 }, { "epoch": 0.02, "learning_rate": 2.5496588950334883e-05, "loss": 3.9115, "step": 1496576 }, { "epoch": 0.02, "learning_rate": 2.5488203002824363e-05, "loss": 3.9096, "step": 1497088 }, { "epoch": 0.02, "learning_rate": 2.5479817055313843e-05, "loss": 3.9146, "step": 1497600 }, { "epoch": 0.02, "learning_rate": 2.5471431107803323e-05, "loss": 3.9199, "step": 1498112 }, { "epoch": 0.02, "learning_rate": 2.5463045160292803e-05, "loss": 3.9277, "step": 1498624 }, { "epoch": 0.02, "learning_rate": 2.5454659212782283e-05, "loss": 3.9089, "step": 1499136 }, { "epoch": 0.02, "learning_rate": 2.5446273265271763e-05, "loss": 3.8997, "step": 1499648 }, { "epoch": 0.02, "learning_rate": 2.5437887317761243e-05, "loss": 3.9192, "step": 1500160 }, { "epoch": 0.02, "learning_rate": 2.542950137025072e-05, "loss": 3.9117, "step": 1500672 }, { "epoch": 0.02, "learning_rate": 2.54211154227402e-05, "loss": 3.9268, "step": 1501184 }, { "epoch": 0.02, "learning_rate": 2.5412762232837144e-05, "loss": 3.9221, "step": 1501696 }, { "epoch": 0.02, "learning_rate": 2.5404376285326624e-05, "loss": 3.911, "step": 1502208 }, { "epoch": 0.02, "learning_rate": 2.5395990337816107e-05, "loss": 3.9046, "step": 1502720 }, { "epoch": 0.02, "learning_rate": 2.5387604390305587e-05, "loss": 3.9216, "step": 1503232 }, { "epoch": 0.02, "learning_rate": 2.5379218442795067e-05, "loss": 3.9016, "step": 1503744 }, { "epoch": 0.02, "learning_rate": 2.537083249528454e-05, "loss": 3.9141, "step": 1504256 }, { "epoch": 0.02, "learning_rate": 2.5362462926577756e-05, "loss": 3.9099, "step": 1504768 }, { "epoch": 0.02, "learning_rate": 2.5354076979067236e-05, "loss": 3.9161, "step": 1505280 }, { "epoch": 0.02, "learning_rate": 2.5345691031556716e-05, "loss": 3.9001, "step": 1505792 }, { "epoch": 0.02, "learning_rate": 2.5337305084046193e-05, "loss": 3.9194, "step": 1506304 }, { "epoch": 0.02, "learning_rate": 2.5328919136535673e-05, "loss": 3.9074, "step": 1506816 }, { "epoch": 0.02, "learning_rate": 2.5320533189025153e-05, "loss": 3.9086, "step": 1507328 }, { "epoch": 0.02, "learning_rate": 2.5312163620318362e-05, "loss": 3.9175, "step": 1507840 }, { "epoch": 0.02, "learning_rate": 2.5303777672807845e-05, "loss": 3.9078, "step": 1508352 }, { "epoch": 0.02, "learning_rate": 2.5295391725297325e-05, "loss": 3.9304, "step": 1508864 }, { "epoch": 0.02, "learning_rate": 2.5287005777786805e-05, "loss": 3.9241, "step": 1509376 }, { "epoch": 0.02, "learning_rate": 2.5278619830276285e-05, "loss": 3.9176, "step": 1509888 }, { "epoch": 0.02, "learning_rate": 2.5270233882765765e-05, "loss": 3.9089, "step": 1510400 }, { "epoch": 0.02, "learning_rate": 2.5261847935255245e-05, "loss": 3.9151, "step": 1510912 }, { "epoch": 0.02, "learning_rate": 2.5253461987744725e-05, "loss": 3.9146, "step": 1511424 }, { "epoch": 0.02, "learning_rate": 2.5245092419037934e-05, "loss": 3.9071, "step": 1511936 }, { "epoch": 0.02, "learning_rate": 2.5236722850331146e-05, "loss": 3.9219, "step": 1512448 }, { "epoch": 0.02, "learning_rate": 2.5228336902820626e-05, "loss": 3.9153, "step": 1512960 }, { "epoch": 0.02, "learning_rate": 2.5219950955310106e-05, "loss": 3.9122, "step": 1513472 }, { "epoch": 0.02, "learning_rate": 2.5211565007799586e-05, "loss": 3.9116, "step": 1513984 }, { "epoch": 0.02, "learning_rate": 2.5203179060289066e-05, "loss": 3.9148, "step": 1514496 }, { "epoch": 0.02, "learning_rate": 2.5194793112778546e-05, "loss": 3.9072, "step": 1515008 }, { "epoch": 0.02, "learning_rate": 2.5186407165268026e-05, "loss": 3.9193, "step": 1515520 }, { "epoch": 0.02, "learning_rate": 2.517802121775751e-05, "loss": 3.9029, "step": 1516032 }, { "epoch": 0.02, "learning_rate": 2.516965164905072e-05, "loss": 3.9223, "step": 1516544 }, { "epoch": 0.02, "learning_rate": 2.5161282080343928e-05, "loss": 3.9198, "step": 1517056 }, { "epoch": 0.02, "learning_rate": 2.515291251163714e-05, "loss": 3.9182, "step": 1517568 }, { "epoch": 0.02, "learning_rate": 2.514452656412662e-05, "loss": 3.9105, "step": 1518080 }, { "epoch": 0.02, "learning_rate": 2.51361406166161e-05, "loss": 3.9115, "step": 1518592 }, { "epoch": 0.02, "learning_rate": 2.512775466910558e-05, "loss": 3.9205, "step": 1519104 }, { "epoch": 0.02, "learning_rate": 2.511936872159506e-05, "loss": 3.9196, "step": 1519616 }, { "epoch": 0.02, "learning_rate": 2.511098277408454e-05, "loss": 3.9095, "step": 1520128 }, { "epoch": 0.02, "learning_rate": 2.510259682657402e-05, "loss": 3.9218, "step": 1520640 }, { "epoch": 0.02, "learning_rate": 2.50942108790635e-05, "loss": 3.9182, "step": 1521152 }, { "epoch": 0.02, "learning_rate": 2.508582493155298e-05, "loss": 3.9233, "step": 1521664 }, { "epoch": 0.02, "learning_rate": 2.5077438984042463e-05, "loss": 3.914, "step": 1522176 }, { "epoch": 0.02, "learning_rate": 2.5069053036531943e-05, "loss": 3.9273, "step": 1522688 }, { "epoch": 0.02, "learning_rate": 2.5060667089021423e-05, "loss": 3.9197, "step": 1523200 }, { "epoch": 0.02, "learning_rate": 2.5052281141510903e-05, "loss": 3.9118, "step": 1523712 }, { "epoch": 0.02, "learning_rate": 2.5043911572804112e-05, "loss": 3.9165, "step": 1524224 }, { "epoch": 0.02, "learning_rate": 2.5035542004097325e-05, "loss": 3.9218, "step": 1524736 }, { "epoch": 0.02, "learning_rate": 2.5027156056586805e-05, "loss": 3.9135, "step": 1525248 }, { "epoch": 0.02, "learning_rate": 2.5018770109076285e-05, "loss": 3.9044, "step": 1525760 }, { "epoch": 0.02, "learning_rate": 2.5010384161565765e-05, "loss": 3.9157, "step": 1526272 }, { "epoch": 0.03, "eval_loss": 4.002975940704346, "eval_runtime": 293.1724, "eval_samples_per_second": 1301.592, "eval_steps_per_second": 40.676, "step": 1526400 }, { "epoch": 1.0, "learning_rate": 2.5001998214055244e-05, "loss": 3.9098, "step": 1526784 }, { "epoch": 1.0, "learning_rate": 2.4993628645348454e-05, "loss": 3.9049, "step": 1527296 }, { "epoch": 1.0, "learning_rate": 2.4985242697837934e-05, "loss": 3.9245, "step": 1527808 }, { "epoch": 1.0, "learning_rate": 2.4976856750327414e-05, "loss": 3.9245, "step": 1528320 }, { "epoch": 1.0, "learning_rate": 2.4968470802816893e-05, "loss": 3.9217, "step": 1528832 }, { "epoch": 1.0, "learning_rate": 2.4960084855306373e-05, "loss": 3.9134, "step": 1529344 }, { "epoch": 1.0, "learning_rate": 2.4951715286599583e-05, "loss": 3.9191, "step": 1529856 }, { "epoch": 1.0, "learning_rate": 2.4943329339089062e-05, "loss": 3.9002, "step": 1530368 }, { "epoch": 1.0, "learning_rate": 2.4934943391578542e-05, "loss": 3.924, "step": 1530880 }, { "epoch": 1.0, "learning_rate": 2.4926557444068026e-05, "loss": 3.9219, "step": 1531392 }, { "epoch": 1.0, "learning_rate": 2.4918171496557506e-05, "loss": 3.9163, "step": 1531904 }, { "epoch": 1.0, "learning_rate": 2.4909818306654447e-05, "loss": 3.9238, "step": 1532416 }, { "epoch": 1.0, "learning_rate": 2.4901448737947656e-05, "loss": 3.91, "step": 1532928 }, { "epoch": 1.0, "learning_rate": 2.489306279043714e-05, "loss": 3.915, "step": 1533440 }, { "epoch": 1.0, "learning_rate": 2.488467684292662e-05, "loss": 3.9056, "step": 1533952 }, { "epoch": 1.0, "learning_rate": 2.48762908954161e-05, "loss": 3.9084, "step": 1534464 }, { "epoch": 1.0, "learning_rate": 2.486790494790558e-05, "loss": 3.9071, "step": 1534976 }, { "epoch": 1.0, "learning_rate": 2.4859519000395056e-05, "loss": 3.9079, "step": 1535488 }, { "epoch": 1.0, "learning_rate": 2.4851133052884536e-05, "loss": 3.9109, "step": 1536000 }, { "epoch": 1.0, "learning_rate": 2.4842747105374016e-05, "loss": 3.933, "step": 1536512 }, { "epoch": 1.0, "learning_rate": 2.4834361157863496e-05, "loss": 3.9178, "step": 1537024 }, { "epoch": 1.0, "learning_rate": 2.482597521035298e-05, "loss": 3.9232, "step": 1537536 }, { "epoch": 1.0, "learning_rate": 2.481760564164619e-05, "loss": 3.9162, "step": 1538048 }, { "epoch": 1.0, "learning_rate": 2.480921969413567e-05, "loss": 3.9226, "step": 1538560 }, { "epoch": 1.0, "learning_rate": 2.480083374662515e-05, "loss": 3.9106, "step": 1539072 }, { "epoch": 1.0, "learning_rate": 2.479244779911463e-05, "loss": 3.9163, "step": 1539584 }, { "epoch": 1.0, "learning_rate": 2.478406185160411e-05, "loss": 3.9114, "step": 1540096 }, { "epoch": 1.0, "learning_rate": 2.477567590409359e-05, "loss": 3.9049, "step": 1540608 }, { "epoch": 1.0, "learning_rate": 2.4767289956583068e-05, "loss": 3.9045, "step": 1541120 }, { "epoch": 1.0, "learning_rate": 2.4758904009072548e-05, "loss": 3.9133, "step": 1541632 }, { "epoch": 1.01, "learning_rate": 2.475053444036576e-05, "loss": 3.9113, "step": 1542144 }, { "epoch": 1.01, "learning_rate": 2.4742148492855237e-05, "loss": 3.9206, "step": 1542656 }, { "epoch": 1.01, "learning_rate": 2.4733762545344717e-05, "loss": 3.9166, "step": 1543168 }, { "epoch": 1.01, "learning_rate": 2.47253765978342e-05, "loss": 3.9189, "step": 1543680 }, { "epoch": 1.01, "learning_rate": 2.4717007029127413e-05, "loss": 3.9097, "step": 1544192 }, { "epoch": 1.01, "learning_rate": 2.470862108161689e-05, "loss": 3.9244, "step": 1544704 }, { "epoch": 1.01, "learning_rate": 2.470023513410637e-05, "loss": 3.9056, "step": 1545216 }, { "epoch": 1.01, "learning_rate": 2.469184918659585e-05, "loss": 3.9147, "step": 1545728 }, { "epoch": 1.01, "learning_rate": 2.468346323908533e-05, "loss": 3.8982, "step": 1546240 }, { "epoch": 1.01, "learning_rate": 2.467507729157481e-05, "loss": 3.9135, "step": 1546752 }, { "epoch": 1.01, "learning_rate": 2.466669134406429e-05, "loss": 3.9103, "step": 1547264 }, { "epoch": 1.01, "learning_rate": 2.465830539655377e-05, "loss": 3.9232, "step": 1547776 }, { "epoch": 1.01, "learning_rate": 2.464991944904325e-05, "loss": 3.9087, "step": 1548288 }, { "epoch": 1.01, "learning_rate": 2.464153350153273e-05, "loss": 3.9151, "step": 1548800 }, { "epoch": 1.01, "learning_rate": 2.4633163932825942e-05, "loss": 3.9185, "step": 1549312 }, { "epoch": 1.01, "learning_rate": 2.462477798531542e-05, "loss": 3.919, "step": 1549824 }, { "epoch": 1.01, "learning_rate": 2.46163920378049e-05, "loss": 3.9161, "step": 1550336 }, { "epoch": 1.01, "learning_rate": 2.4608022469098114e-05, "loss": 3.9042, "step": 1550848 }, { "epoch": 1.01, "learning_rate": 2.459963652158759e-05, "loss": 3.8958, "step": 1551360 }, { "epoch": 1.01, "learning_rate": 2.4591266952880803e-05, "loss": 3.9229, "step": 1551872 }, { "epoch": 1.01, "learning_rate": 2.4582881005370283e-05, "loss": 3.9167, "step": 1552384 }, { "epoch": 1.01, "learning_rate": 2.4574495057859763e-05, "loss": 3.911, "step": 1552896 }, { "epoch": 1.01, "learning_rate": 2.4566109110349243e-05, "loss": 3.9093, "step": 1553408 }, { "epoch": 1.01, "learning_rate": 2.4557723162838723e-05, "loss": 3.9092, "step": 1553920 }, { "epoch": 1.01, "learning_rate": 2.4549337215328203e-05, "loss": 3.8941, "step": 1554432 }, { "epoch": 1.01, "learning_rate": 2.4540951267817683e-05, "loss": 3.9092, "step": 1554944 }, { "epoch": 1.01, "learning_rate": 2.4532565320307163e-05, "loss": 3.901, "step": 1555456 }, { "epoch": 1.01, "learning_rate": 2.4524179372796643e-05, "loss": 3.9083, "step": 1555968 }, { "epoch": 1.01, "learning_rate": 2.4515793425286123e-05, "loss": 3.9199, "step": 1556480 }, { "epoch": 1.01, "learning_rate": 2.4507407477775603e-05, "loss": 3.9054, "step": 1556992 }, { "epoch": 1.01, "learning_rate": 2.4499037909068815e-05, "loss": 3.8971, "step": 1557504 }, { "epoch": 1.01, "learning_rate": 2.4490651961558295e-05, "loss": 3.9152, "step": 1558016 }, { "epoch": 1.01, "learning_rate": 2.4482266014047772e-05, "loss": 3.8931, "step": 1558528 }, { "epoch": 1.01, "learning_rate": 2.4473880066537252e-05, "loss": 3.904, "step": 1559040 }, { "epoch": 1.01, "learning_rate": 2.446549411902673e-05, "loss": 3.9122, "step": 1559552 }, { "epoch": 1.01, "learning_rate": 2.445710817151621e-05, "loss": 3.9129, "step": 1560064 }, { "epoch": 1.01, "learning_rate": 2.4448738602809424e-05, "loss": 3.9018, "step": 1560576 }, { "epoch": 1.01, "learning_rate": 2.4440369034102637e-05, "loss": 3.8992, "step": 1561088 }, { "epoch": 1.01, "learning_rate": 2.4431983086592117e-05, "loss": 3.9029, "step": 1561600 }, { "epoch": 1.01, "learning_rate": 2.4423597139081597e-05, "loss": 3.9112, "step": 1562112 }, { "epoch": 1.01, "learning_rate": 2.4415211191571073e-05, "loss": 3.9113, "step": 1562624 }, { "epoch": 1.01, "learning_rate": 2.4406825244060556e-05, "loss": 3.9081, "step": 1563136 }, { "epoch": 1.01, "learning_rate": 2.4398439296550036e-05, "loss": 3.9149, "step": 1563648 }, { "epoch": 1.01, "learning_rate": 2.4390053349039516e-05, "loss": 3.9206, "step": 1564160 }, { "epoch": 1.01, "learning_rate": 2.4381667401528996e-05, "loss": 3.9078, "step": 1564672 }, { "epoch": 1.01, "learning_rate": 2.4373281454018476e-05, "loss": 3.9005, "step": 1565184 }, { "epoch": 1.01, "learning_rate": 2.4364911885311685e-05, "loss": 3.9175, "step": 1565696 }, { "epoch": 1.01, "learning_rate": 2.4356525937801165e-05, "loss": 3.9099, "step": 1566208 }, { "epoch": 1.01, "learning_rate": 2.434813999029065e-05, "loss": 3.903, "step": 1566720 }, { "epoch": 1.01, "learning_rate": 2.433975404278013e-05, "loss": 3.9067, "step": 1567232 }, { "epoch": 1.01, "learning_rate": 2.4331368095269605e-05, "loss": 3.9135, "step": 1567744 }, { "epoch": 1.01, "learning_rate": 2.4322998526562818e-05, "loss": 3.9222, "step": 1568256 }, { "epoch": 1.01, "learning_rate": 2.4314612579052298e-05, "loss": 3.9068, "step": 1568768 }, { "epoch": 1.01, "learning_rate": 2.4306226631541778e-05, "loss": 3.8925, "step": 1569280 }, { "epoch": 1.01, "learning_rate": 2.429785706283499e-05, "loss": 3.904, "step": 1569792 }, { "epoch": 1.01, "learning_rate": 2.428947111532447e-05, "loss": 3.8988, "step": 1570304 }, { "epoch": 1.01, "learning_rate": 2.428108516781395e-05, "loss": 3.9123, "step": 1570816 }, { "epoch": 1.01, "learning_rate": 2.4272699220303427e-05, "loss": 3.9093, "step": 1571328 }, { "epoch": 1.01, "learning_rate": 2.426432965159664e-05, "loss": 3.9002, "step": 1571840 }, { "epoch": 1.02, "learning_rate": 2.425594370408612e-05, "loss": 3.9154, "step": 1572352 }, { "epoch": 1.02, "learning_rate": 2.424757413537933e-05, "loss": 3.9029, "step": 1572864 }, { "epoch": 1.02, "learning_rate": 2.423918818786881e-05, "loss": 3.9057, "step": 1573376 }, { "epoch": 1.02, "learning_rate": 2.423080224035829e-05, "loss": 3.903, "step": 1573888 }, { "epoch": 1.02, "learning_rate": 2.422241629284777e-05, "loss": 3.9104, "step": 1574400 }, { "epoch": 1.02, "learning_rate": 2.421403034533725e-05, "loss": 3.9209, "step": 1574912 }, { "epoch": 1.02, "learning_rate": 2.4205644397826728e-05, "loss": 3.9099, "step": 1575424 }, { "epoch": 1.02, "learning_rate": 2.419725845031621e-05, "loss": 3.8898, "step": 1575936 }, { "epoch": 1.02, "learning_rate": 2.418887250280569e-05, "loss": 3.9087, "step": 1576448 }, { "epoch": 1.02, "learning_rate": 2.418048655529517e-05, "loss": 3.9062, "step": 1576960 }, { "epoch": 1.02, "learning_rate": 2.417211698658838e-05, "loss": 3.9127, "step": 1577472 }, { "epoch": 1.02, "learning_rate": 2.416373103907786e-05, "loss": 3.9192, "step": 1577984 }, { "epoch": 1.02, "learning_rate": 2.415534509156734e-05, "loss": 3.9059, "step": 1578496 }, { "epoch": 1.02, "learning_rate": 2.414695914405682e-05, "loss": 3.8987, "step": 1579008 }, { "epoch": 1.02, "learning_rate": 2.4138573196546303e-05, "loss": 3.9137, "step": 1579520 }, { "epoch": 1.02, "learning_rate": 2.4130187249035783e-05, "loss": 3.8897, "step": 1580032 }, { "epoch": 1.02, "learning_rate": 2.412180130152526e-05, "loss": 3.9082, "step": 1580544 }, { "epoch": 1.02, "learning_rate": 2.4113431732818472e-05, "loss": 3.9014, "step": 1581056 }, { "epoch": 1.02, "learning_rate": 2.4105045785307952e-05, "loss": 3.9113, "step": 1581568 }, { "epoch": 1.02, "learning_rate": 2.4096659837797432e-05, "loss": 3.8956, "step": 1582080 }, { "epoch": 1.02, "learning_rate": 2.4088273890286912e-05, "loss": 3.9127, "step": 1582592 }, { "epoch": 1.02, "learning_rate": 2.4079887942776392e-05, "loss": 3.8979, "step": 1583104 }, { "epoch": 1.02, "learning_rate": 2.4071501995265872e-05, "loss": 3.9015, "step": 1583616 }, { "epoch": 1.02, "learning_rate": 2.406313242655908e-05, "loss": 3.911, "step": 1584128 }, { "epoch": 1.02, "learning_rate": 2.405474647904856e-05, "loss": 3.9048, "step": 1584640 }, { "epoch": 1.02, "learning_rate": 2.404636053153804e-05, "loss": 3.92, "step": 1585152 }, { "epoch": 1.02, "learning_rate": 2.403797458402752e-05, "loss": 3.9141, "step": 1585664 }, { "epoch": 1.02, "learning_rate": 2.4029588636517004e-05, "loss": 3.906, "step": 1586176 }, { "epoch": 1.02, "learning_rate": 2.4021202689006484e-05, "loss": 3.9086, "step": 1586688 }, { "epoch": 1.02, "learning_rate": 2.4012816741495964e-05, "loss": 3.9014, "step": 1587200 }, { "epoch": 1.02, "learning_rate": 2.400443079398544e-05, "loss": 3.9113, "step": 1587712 }, { "epoch": 1.02, "learning_rate": 2.3996061225278653e-05, "loss": 3.8995, "step": 1588224 }, { "epoch": 1.02, "learning_rate": 2.3987691656571866e-05, "loss": 3.9169, "step": 1588736 }, { "epoch": 1.02, "learning_rate": 2.3979305709061346e-05, "loss": 3.9032, "step": 1589248 }, { "epoch": 1.02, "learning_rate": 2.3970919761550826e-05, "loss": 3.9019, "step": 1589760 }, { "epoch": 1.02, "learning_rate": 2.3962533814040306e-05, "loss": 3.9035, "step": 1590272 }, { "epoch": 1.02, "learning_rate": 2.3954164245333515e-05, "loss": 3.9107, "step": 1590784 }, { "epoch": 1.02, "learning_rate": 2.3945778297822995e-05, "loss": 3.9004, "step": 1591296 }, { "epoch": 1.02, "learning_rate": 2.3937392350312475e-05, "loss": 3.9109, "step": 1591808 }, { "epoch": 1.02, "learning_rate": 2.3929006402801958e-05, "loss": 3.8982, "step": 1592320 }, { "epoch": 1.02, "learning_rate": 2.3920620455291438e-05, "loss": 3.914, "step": 1592832 }, { "epoch": 1.02, "learning_rate": 2.3912234507780915e-05, "loss": 3.9111, "step": 1593344 }, { "epoch": 1.02, "learning_rate": 2.3903864939074127e-05, "loss": 3.9115, "step": 1593856 }, { "epoch": 1.02, "learning_rate": 2.3895478991563607e-05, "loss": 3.9033, "step": 1594368 }, { "epoch": 1.02, "learning_rate": 2.3887093044053087e-05, "loss": 3.9022, "step": 1594880 }, { "epoch": 1.02, "learning_rate": 2.3878707096542567e-05, "loss": 3.9174, "step": 1595392 }, { "epoch": 1.02, "learning_rate": 2.3870321149032047e-05, "loss": 3.9088, "step": 1595904 }, { "epoch": 1.02, "learning_rate": 2.386195158032526e-05, "loss": 3.9031, "step": 1596416 }, { "epoch": 1.02, "learning_rate": 2.3853565632814736e-05, "loss": 3.9159, "step": 1596928 }, { "epoch": 1.02, "learning_rate": 2.3845179685304216e-05, "loss": 3.9103, "step": 1597440 }, { "epoch": 1.02, "learning_rate": 2.3836793737793696e-05, "loss": 3.9187, "step": 1597952 }, { "epoch": 1.02, "learning_rate": 2.3828407790283176e-05, "loss": 3.9085, "step": 1598464 }, { "epoch": 1.02, "learning_rate": 2.382003822157639e-05, "loss": 3.9147, "step": 1598976 }, { "epoch": 1.02, "learning_rate": 2.381165227406587e-05, "loss": 3.9121, "step": 1599488 }, { "epoch": 1.02, "learning_rate": 2.380326632655535e-05, "loss": 3.9061, "step": 1600000 }, { "epoch": 1.02, "learning_rate": 2.3794880379044828e-05, "loss": 3.9101, "step": 1600512 }, { "epoch": 1.02, "learning_rate": 2.3786494431534308e-05, "loss": 3.9115, "step": 1601024 }, { "epoch": 1.02, "learning_rate": 2.3778108484023788e-05, "loss": 3.909, "step": 1601536 }, { "epoch": 1.02, "learning_rate": 2.3769722536513268e-05, "loss": 3.8964, "step": 1602048 }, { "epoch": 1.02, "learning_rate": 2.3761336589002748e-05, "loss": 3.91, "step": 1602560 }, { "epoch": 1.03, "eval_loss": 3.9997189044952393, "eval_runtime": 297.2732, "eval_samples_per_second": 1283.638, "eval_steps_per_second": 40.115, "step": 1602720 }, { "epoch": 0.0, "learning_rate": 2.375296702029596e-05, "loss": 3.8999, "step": 1603072 }, { "epoch": 0.0, "learning_rate": 2.374458107278544e-05, "loss": 3.8975, "step": 1603584 }, { "epoch": 0.0, "learning_rate": 2.3736195125274917e-05, "loss": 3.917, "step": 1604096 }, { "epoch": 0.0, "learning_rate": 2.3727809177764397e-05, "loss": 3.9165, "step": 1604608 }, { "epoch": 0.0, "learning_rate": 2.371942323025388e-05, "loss": 3.9128, "step": 1605120 }, { "epoch": 0.0, "learning_rate": 2.371103728274336e-05, "loss": 3.9077, "step": 1605632 }, { "epoch": 0.0, "learning_rate": 2.370265133523284e-05, "loss": 3.9076, "step": 1606144 }, { "epoch": 0.0, "learning_rate": 2.369426538772232e-05, "loss": 3.8954, "step": 1606656 }, { "epoch": 0.0, "learning_rate": 2.36858794402118e-05, "loss": 3.9119, "step": 1607168 }, { "epoch": 0.0, "learning_rate": 2.3677493492701277e-05, "loss": 3.9164, "step": 1607680 }, { "epoch": 0.0, "learning_rate": 2.3669107545190757e-05, "loss": 3.9078, "step": 1608192 }, { "epoch": 0.0, "learning_rate": 2.3660721597680237e-05, "loss": 3.9147, "step": 1608704 }, { "epoch": 0.0, "learning_rate": 2.365235202897345e-05, "loss": 3.9042, "step": 1609216 }, { "epoch": 0.0, "learning_rate": 2.364396608146293e-05, "loss": 3.9081, "step": 1609728 }, { "epoch": 0.0, "learning_rate": 2.363558013395241e-05, "loss": 3.8993, "step": 1610240 }, { "epoch": 0.0, "learning_rate": 2.362719418644189e-05, "loss": 3.9012, "step": 1610752 }, { "epoch": 0.0, "learning_rate": 2.361880823893137e-05, "loss": 3.9003, "step": 1611264 }, { "epoch": 0.0, "learning_rate": 2.361042229142085e-05, "loss": 3.8998, "step": 1611776 }, { "epoch": 0.0, "learning_rate": 2.360203634391033e-05, "loss": 3.9058, "step": 1612288 }, { "epoch": 0.0, "learning_rate": 2.359365039639981e-05, "loss": 3.9192, "step": 1612800 }, { "epoch": 0.0, "learning_rate": 2.358526444888929e-05, "loss": 3.9149, "step": 1613312 }, { "epoch": 0.0, "learning_rate": 2.357687850137877e-05, "loss": 3.9148, "step": 1613824 }, { "epoch": 0.0, "learning_rate": 2.356849255386825e-05, "loss": 3.906, "step": 1614336 }, { "epoch": 0.0, "learning_rate": 2.3560122985161458e-05, "loss": 3.9169, "step": 1614848 }, { "epoch": 0.0, "learning_rate": 2.3551737037650938e-05, "loss": 3.9008, "step": 1615360 }, { "epoch": 0.0, "learning_rate": 2.354335109014042e-05, "loss": 3.9125, "step": 1615872 }, { "epoch": 0.0, "learning_rate": 2.35349651426299e-05, "loss": 3.9027, "step": 1616384 }, { "epoch": 0.0, "learning_rate": 2.352657919511938e-05, "loss": 3.8963, "step": 1616896 }, { "epoch": 0.0, "learning_rate": 2.351820962641259e-05, "loss": 3.9, "step": 1617408 }, { "epoch": 0.0, "learning_rate": 2.350982367890207e-05, "loss": 3.9027, "step": 1617920 }, { "epoch": 0.01, "learning_rate": 2.350143773139155e-05, "loss": 3.9071, "step": 1618432 }, { "epoch": 0.01, "learning_rate": 2.349305178388103e-05, "loss": 3.9099, "step": 1618944 }, { "epoch": 0.01, "learning_rate": 2.3484665836370513e-05, "loss": 3.914, "step": 1619456 }, { "epoch": 0.01, "learning_rate": 2.347627988885999e-05, "loss": 3.9114, "step": 1619968 }, { "epoch": 0.01, "learning_rate": 2.3467910320153202e-05, "loss": 3.9022, "step": 1620480 }, { "epoch": 0.01, "learning_rate": 2.3459524372642682e-05, "loss": 3.9134, "step": 1620992 }, { "epoch": 0.01, "learning_rate": 2.345113842513216e-05, "loss": 3.9033, "step": 1621504 }, { "epoch": 0.01, "learning_rate": 2.3442752477621642e-05, "loss": 3.9003, "step": 1622016 }, { "epoch": 0.01, "learning_rate": 2.3434366530111122e-05, "loss": 3.8963, "step": 1622528 }, { "epoch": 0.01, "learning_rate": 2.3425980582600602e-05, "loss": 3.902, "step": 1623040 }, { "epoch": 0.01, "learning_rate": 2.3417594635090082e-05, "loss": 3.9074, "step": 1623552 }, { "epoch": 0.01, "learning_rate": 2.3409208687579562e-05, "loss": 3.9127, "step": 1624064 }, { "epoch": 0.01, "learning_rate": 2.3400822740069042e-05, "loss": 3.9028, "step": 1624576 }, { "epoch": 0.01, "learning_rate": 2.339243679255852e-05, "loss": 3.9064, "step": 1625088 }, { "epoch": 0.01, "learning_rate": 2.338406722385173e-05, "loss": 3.9125, "step": 1625600 }, { "epoch": 0.01, "learning_rate": 2.3375681276341214e-05, "loss": 3.911, "step": 1626112 }, { "epoch": 0.01, "learning_rate": 2.3367295328830694e-05, "loss": 3.9106, "step": 1626624 }, { "epoch": 0.01, "learning_rate": 2.335890938132017e-05, "loss": 3.8975, "step": 1627136 }, { "epoch": 0.01, "learning_rate": 2.335052343380965e-05, "loss": 3.8848, "step": 1627648 }, { "epoch": 0.01, "learning_rate": 2.3342153865102863e-05, "loss": 3.9175, "step": 1628160 }, { "epoch": 0.01, "learning_rate": 2.3333767917592343e-05, "loss": 3.9099, "step": 1628672 }, { "epoch": 0.01, "learning_rate": 2.3325381970081823e-05, "loss": 3.9052, "step": 1629184 }, { "epoch": 0.01, "learning_rate": 2.3316996022571303e-05, "loss": 3.9028, "step": 1629696 }, { "epoch": 0.01, "learning_rate": 2.3308626453864516e-05, "loss": 3.8967, "step": 1630208 }, { "epoch": 0.01, "learning_rate": 2.3300240506353992e-05, "loss": 3.8898, "step": 1630720 }, { "epoch": 0.01, "learning_rate": 2.3291854558843472e-05, "loss": 3.8998, "step": 1631232 }, { "epoch": 0.01, "learning_rate": 2.3283468611332952e-05, "loss": 3.8917, "step": 1631744 }, { "epoch": 0.01, "learning_rate": 2.3275099042626168e-05, "loss": 3.9023, "step": 1632256 }, { "epoch": 0.01, "learning_rate": 2.3266713095115645e-05, "loss": 3.9118, "step": 1632768 }, { "epoch": 0.01, "learning_rate": 2.3258327147605125e-05, "loss": 3.8972, "step": 1633280 }, { "epoch": 0.01, "learning_rate": 2.3249941200094605e-05, "loss": 3.8906, "step": 1633792 }, { "epoch": 0.01, "learning_rate": 2.3241571631387814e-05, "loss": 3.9091, "step": 1634304 }, { "epoch": 0.01, "learning_rate": 2.3233185683877297e-05, "loss": 3.8888, "step": 1634816 }, { "epoch": 0.01, "learning_rate": 2.322481611517051e-05, "loss": 3.8938, "step": 1635328 }, { "epoch": 0.01, "learning_rate": 2.321643016765999e-05, "loss": 3.9065, "step": 1635840 }, { "epoch": 0.01, "learning_rate": 2.3208044220149466e-05, "loss": 3.9049, "step": 1636352 }, { "epoch": 0.01, "learning_rate": 2.3199658272638946e-05, "loss": 3.895, "step": 1636864 }, { "epoch": 0.01, "learning_rate": 2.3191272325128426e-05, "loss": 3.8908, "step": 1637376 }, { "epoch": 0.01, "learning_rate": 2.3182886377617906e-05, "loss": 3.8941, "step": 1637888 }, { "epoch": 0.01, "learning_rate": 2.317450043010739e-05, "loss": 3.9018, "step": 1638400 }, { "epoch": 0.01, "learning_rate": 2.316611448259687e-05, "loss": 3.9082, "step": 1638912 }, { "epoch": 0.01, "learning_rate": 2.315772853508635e-05, "loss": 3.8995, "step": 1639424 }, { "epoch": 0.01, "learning_rate": 2.3149342587575826e-05, "loss": 3.9063, "step": 1639936 }, { "epoch": 0.01, "learning_rate": 2.3140956640065306e-05, "loss": 3.9121, "step": 1640448 }, { "epoch": 0.01, "learning_rate": 2.3132570692554786e-05, "loss": 3.908, "step": 1640960 }, { "epoch": 0.01, "learning_rate": 2.3124201123847998e-05, "loss": 3.8903, "step": 1641472 }, { "epoch": 0.01, "learning_rate": 2.3115815176337478e-05, "loss": 3.9076, "step": 1641984 }, { "epoch": 0.01, "learning_rate": 2.3107429228826958e-05, "loss": 3.907, "step": 1642496 }, { "epoch": 0.01, "learning_rate": 2.3099043281316438e-05, "loss": 3.8945, "step": 1643008 }, { "epoch": 0.01, "learning_rate": 2.3090673712609647e-05, "loss": 3.9056, "step": 1643520 }, { "epoch": 0.01, "learning_rate": 2.3082287765099127e-05, "loss": 3.9025, "step": 1644032 }, { "epoch": 0.01, "learning_rate": 2.3073901817588607e-05, "loss": 3.9147, "step": 1644544 }, { "epoch": 0.01, "learning_rate": 2.306551587007809e-05, "loss": 3.9029, "step": 1645056 }, { "epoch": 0.01, "learning_rate": 2.3057162680175032e-05, "loss": 3.8822, "step": 1645568 }, { "epoch": 0.01, "learning_rate": 2.3048776732664512e-05, "loss": 3.8982, "step": 1646080 }, { "epoch": 0.01, "learning_rate": 2.304040716395772e-05, "loss": 3.8943, "step": 1646592 }, { "epoch": 0.01, "learning_rate": 2.3032021216447204e-05, "loss": 3.9024, "step": 1647104 }, { "epoch": 0.01, "learning_rate": 2.3023635268936684e-05, "loss": 3.9029, "step": 1647616 }, { "epoch": 0.01, "learning_rate": 2.3015265700229893e-05, "loss": 3.8958, "step": 1648128 }, { "epoch": 0.02, "learning_rate": 2.3006879752719373e-05, "loss": 3.9063, "step": 1648640 }, { "epoch": 0.02, "learning_rate": 2.2998493805208853e-05, "loss": 3.8995, "step": 1649152 }, { "epoch": 0.02, "learning_rate": 2.2990107857698333e-05, "loss": 3.8932, "step": 1649664 }, { "epoch": 0.02, "learning_rate": 2.2981721910187813e-05, "loss": 3.901, "step": 1650176 }, { "epoch": 0.02, "learning_rate": 2.2973335962677293e-05, "loss": 3.9065, "step": 1650688 }, { "epoch": 0.02, "learning_rate": 2.2964950015166773e-05, "loss": 3.9126, "step": 1651200 }, { "epoch": 0.02, "learning_rate": 2.2956564067656253e-05, "loss": 3.9004, "step": 1651712 }, { "epoch": 0.02, "learning_rate": 2.2948178120145733e-05, "loss": 3.8859, "step": 1652224 }, { "epoch": 0.02, "learning_rate": 2.2939792172635213e-05, "loss": 3.9007, "step": 1652736 }, { "epoch": 0.02, "learning_rate": 2.2931406225124693e-05, "loss": 3.8995, "step": 1653248 }, { "epoch": 0.02, "learning_rate": 2.2923036656417905e-05, "loss": 3.9069, "step": 1653760 }, { "epoch": 0.02, "learning_rate": 2.2914650708907385e-05, "loss": 3.9113, "step": 1654272 }, { "epoch": 0.02, "learning_rate": 2.2906264761396865e-05, "loss": 3.8927, "step": 1654784 }, { "epoch": 0.02, "learning_rate": 2.2897878813886345e-05, "loss": 3.894, "step": 1655296 }, { "epoch": 0.02, "learning_rate": 2.2889492866375825e-05, "loss": 3.9075, "step": 1655808 }, { "epoch": 0.02, "learning_rate": 2.2881106918865302e-05, "loss": 3.8861, "step": 1656320 }, { "epoch": 0.02, "learning_rate": 2.2872720971354782e-05, "loss": 3.9031, "step": 1656832 }, { "epoch": 0.02, "learning_rate": 2.2864335023844262e-05, "loss": 3.8895, "step": 1657344 }, { "epoch": 0.02, "learning_rate": 2.2855949076333745e-05, "loss": 3.9051, "step": 1657856 }, { "epoch": 0.02, "learning_rate": 2.2847563128823225e-05, "loss": 3.8883, "step": 1658368 }, { "epoch": 0.02, "learning_rate": 2.2839193560116434e-05, "loss": 3.9027, "step": 1658880 }, { "epoch": 0.02, "learning_rate": 2.2830807612605914e-05, "loss": 3.8977, "step": 1659392 }, { "epoch": 0.02, "learning_rate": 2.2822421665095394e-05, "loss": 3.8919, "step": 1659904 }, { "epoch": 0.02, "learning_rate": 2.2814035717584874e-05, "loss": 3.9037, "step": 1660416 }, { "epoch": 0.02, "learning_rate": 2.2805649770074354e-05, "loss": 3.8956, "step": 1660928 }, { "epoch": 0.02, "learning_rate": 2.2797263822563834e-05, "loss": 3.9149, "step": 1661440 }, { "epoch": 0.02, "learning_rate": 2.2788877875053314e-05, "loss": 3.9124, "step": 1661952 }, { "epoch": 0.02, "learning_rate": 2.2780508306346526e-05, "loss": 3.8976, "step": 1662464 }, { "epoch": 0.02, "learning_rate": 2.2772122358836006e-05, "loss": 3.9053, "step": 1662976 }, { "epoch": 0.02, "learning_rate": 2.2763736411325483e-05, "loss": 3.8949, "step": 1663488 }, { "epoch": 0.02, "learning_rate": 2.2755350463814963e-05, "loss": 3.9028, "step": 1664000 }, { "epoch": 0.02, "learning_rate": 2.2746964516304446e-05, "loss": 3.8975, "step": 1664512 }, { "epoch": 0.02, "learning_rate": 2.2738578568793926e-05, "loss": 3.9065, "step": 1665024 }, { "epoch": 0.02, "learning_rate": 2.2730192621283406e-05, "loss": 3.8987, "step": 1665536 }, { "epoch": 0.02, "learning_rate": 2.2721806673772886e-05, "loss": 3.8946, "step": 1666048 }, { "epoch": 0.02, "learning_rate": 2.2713437105066095e-05, "loss": 3.9018, "step": 1666560 }, { "epoch": 0.02, "learning_rate": 2.2705051157555575e-05, "loss": 3.9015, "step": 1667072 }, { "epoch": 0.02, "learning_rate": 2.2696665210045055e-05, "loss": 3.8904, "step": 1667584 }, { "epoch": 0.02, "learning_rate": 2.2688295641338268e-05, "loss": 3.9045, "step": 1668096 }, { "epoch": 0.02, "learning_rate": 2.2679909693827748e-05, "loss": 3.8899, "step": 1668608 }, { "epoch": 0.02, "learning_rate": 2.2671523746317227e-05, "loss": 3.9149, "step": 1669120 }, { "epoch": 0.02, "learning_rate": 2.2663137798806707e-05, "loss": 3.8977, "step": 1669632 }, { "epoch": 0.02, "learning_rate": 2.2654751851296187e-05, "loss": 3.9091, "step": 1670144 }, { "epoch": 0.02, "learning_rate": 2.26463822825894e-05, "loss": 3.8951, "step": 1670656 }, { "epoch": 0.02, "learning_rate": 2.263799633507888e-05, "loss": 3.8993, "step": 1671168 }, { "epoch": 0.02, "learning_rate": 2.262961038756836e-05, "loss": 3.9083, "step": 1671680 }, { "epoch": 0.02, "learning_rate": 2.2621224440057836e-05, "loss": 3.9003, "step": 1672192 }, { "epoch": 0.02, "learning_rate": 2.2612838492547316e-05, "loss": 3.898, "step": 1672704 }, { "epoch": 0.02, "learning_rate": 2.260446892384053e-05, "loss": 3.9096, "step": 1673216 }, { "epoch": 0.02, "learning_rate": 2.259608297633001e-05, "loss": 3.9053, "step": 1673728 }, { "epoch": 0.02, "learning_rate": 2.258769702881949e-05, "loss": 3.911, "step": 1674240 }, { "epoch": 0.02, "learning_rate": 2.257931108130897e-05, "loss": 3.8975, "step": 1674752 }, { "epoch": 0.02, "learning_rate": 2.257092513379845e-05, "loss": 3.9105, "step": 1675264 }, { "epoch": 0.02, "learning_rate": 2.256255556509166e-05, "loss": 3.902, "step": 1675776 }, { "epoch": 0.02, "learning_rate": 2.2554169617581138e-05, "loss": 3.9002, "step": 1676288 }, { "epoch": 0.02, "learning_rate": 2.254578367007062e-05, "loss": 3.9041, "step": 1676800 }, { "epoch": 0.02, "learning_rate": 2.25373977225601e-05, "loss": 3.9025, "step": 1677312 }, { "epoch": 0.02, "learning_rate": 2.252901177504958e-05, "loss": 3.9086, "step": 1677824 }, { "epoch": 0.02, "learning_rate": 2.252064220634279e-05, "loss": 3.8825, "step": 1678336 }, { "epoch": 0.02, "learning_rate": 2.251225625883227e-05, "loss": 3.9074, "step": 1678848 }, { "epoch": 0.03, "eval_loss": 3.996596097946167, "eval_runtime": 294.2951, "eval_samples_per_second": 1296.627, "eval_steps_per_second": 40.521, "step": 1679040 }, { "epoch": 0.0, "learning_rate": 2.250387031132175e-05, "loss": 3.8963, "step": 1679360 }, { "epoch": 0.0, "learning_rate": 2.249548436381123e-05, "loss": 3.8926, "step": 1679872 }, { "epoch": 0.0, "learning_rate": 2.248709841630071e-05, "loss": 3.9062, "step": 1680384 }, { "epoch": 0.0, "learning_rate": 2.2478712468790193e-05, "loss": 3.914, "step": 1680896 }, { "epoch": 0.0, "learning_rate": 2.247032652127967e-05, "loss": 3.9048, "step": 1681408 }, { "epoch": 0.0, "learning_rate": 2.246194057376915e-05, "loss": 3.8971, "step": 1681920 }, { "epoch": 0.0, "learning_rate": 2.245355462625863e-05, "loss": 3.9022, "step": 1682432 }, { "epoch": 0.0, "learning_rate": 2.244516867874811e-05, "loss": 3.8898, "step": 1682944 }, { "epoch": 0.0, "learning_rate": 2.243678273123759e-05, "loss": 3.9057, "step": 1683456 }, { "epoch": 0.0, "learning_rate": 2.242839678372707e-05, "loss": 3.906, "step": 1683968 }, { "epoch": 0.0, "learning_rate": 2.2420010836216553e-05, "loss": 3.9072, "step": 1684480 }, { "epoch": 0.0, "learning_rate": 2.241162488870603e-05, "loss": 3.905, "step": 1684992 }, { "epoch": 0.0, "learning_rate": 2.2403255319999242e-05, "loss": 3.9014, "step": 1685504 }, { "epoch": 0.0, "learning_rate": 2.2394869372488722e-05, "loss": 3.8981, "step": 1686016 }, { "epoch": 0.0, "learning_rate": 2.23864834249782e-05, "loss": 3.8941, "step": 1686528 }, { "epoch": 0.0, "learning_rate": 2.237809747746768e-05, "loss": 3.8887, "step": 1687040 }, { "epoch": 0.0, "learning_rate": 2.2369711529957162e-05, "loss": 3.8965, "step": 1687552 }, { "epoch": 0.0, "learning_rate": 2.236132558244664e-05, "loss": 3.8938, "step": 1688064 }, { "epoch": 0.0, "learning_rate": 2.235293963493612e-05, "loss": 3.8985, "step": 1688576 }, { "epoch": 0.0, "learning_rate": 2.23445536874256e-05, "loss": 3.9123, "step": 1689088 }, { "epoch": 0.0, "learning_rate": 2.233618411871881e-05, "loss": 3.9134, "step": 1689600 }, { "epoch": 0.0, "learning_rate": 2.232779817120829e-05, "loss": 3.9046, "step": 1690112 }, { "epoch": 0.0, "learning_rate": 2.2319428602501503e-05, "loss": 3.8998, "step": 1690624 }, { "epoch": 0.0, "learning_rate": 2.2311042654990983e-05, "loss": 3.9093, "step": 1691136 }, { "epoch": 0.0, "learning_rate": 2.2302656707480463e-05, "loss": 3.8941, "step": 1691648 }, { "epoch": 0.0, "learning_rate": 2.2294270759969943e-05, "loss": 3.9071, "step": 1692160 }, { "epoch": 0.0, "learning_rate": 2.2285884812459423e-05, "loss": 3.8958, "step": 1692672 }, { "epoch": 0.0, "learning_rate": 2.2277498864948903e-05, "loss": 3.8864, "step": 1693184 }, { "epoch": 0.0, "learning_rate": 2.226911291743838e-05, "loss": 3.8965, "step": 1693696 }, { "epoch": 0.0, "learning_rate": 2.2260726969927863e-05, "loss": 3.8978, "step": 1694208 }, { "epoch": 0.01, "learning_rate": 2.2252341022417343e-05, "loss": 3.8979, "step": 1694720 }, { "epoch": 0.01, "learning_rate": 2.2243955074906823e-05, "loss": 3.9061, "step": 1695232 }, { "epoch": 0.01, "learning_rate": 2.2235569127396303e-05, "loss": 3.9064, "step": 1695744 }, { "epoch": 0.01, "learning_rate": 2.2227199558689512e-05, "loss": 3.9042, "step": 1696256 }, { "epoch": 0.01, "learning_rate": 2.2218846368786457e-05, "loss": 3.8934, "step": 1696768 }, { "epoch": 0.01, "learning_rate": 2.2210460421275937e-05, "loss": 3.9136, "step": 1697280 }, { "epoch": 0.01, "learning_rate": 2.2202074473765417e-05, "loss": 3.8962, "step": 1697792 }, { "epoch": 0.01, "learning_rate": 2.2193688526254897e-05, "loss": 3.8901, "step": 1698304 }, { "epoch": 0.01, "learning_rate": 2.2185302578744377e-05, "loss": 3.8946, "step": 1698816 }, { "epoch": 0.01, "learning_rate": 2.2176916631233853e-05, "loss": 3.8908, "step": 1699328 }, { "epoch": 0.01, "learning_rate": 2.2168530683723333e-05, "loss": 3.9001, "step": 1699840 }, { "epoch": 0.01, "learning_rate": 2.2160144736212816e-05, "loss": 3.9083, "step": 1700352 }, { "epoch": 0.01, "learning_rate": 2.2151758788702296e-05, "loss": 3.8935, "step": 1700864 }, { "epoch": 0.01, "learning_rate": 2.2143372841191776e-05, "loss": 3.8983, "step": 1701376 }, { "epoch": 0.01, "learning_rate": 2.2134986893681256e-05, "loss": 3.9074, "step": 1701888 }, { "epoch": 0.01, "learning_rate": 2.2126600946170736e-05, "loss": 3.907, "step": 1702400 }, { "epoch": 0.01, "learning_rate": 2.2118214998660213e-05, "loss": 3.9056, "step": 1702912 }, { "epoch": 0.01, "learning_rate": 2.2109845429953425e-05, "loss": 3.8931, "step": 1703424 }, { "epoch": 0.01, "learning_rate": 2.210145948244291e-05, "loss": 3.8695, "step": 1703936 }, { "epoch": 0.01, "learning_rate": 2.2093089913736118e-05, "loss": 3.9144, "step": 1704448 }, { "epoch": 0.01, "learning_rate": 2.2084703966225598e-05, "loss": 3.9032, "step": 1704960 }, { "epoch": 0.01, "learning_rate": 2.2076318018715078e-05, "loss": 3.9001, "step": 1705472 }, { "epoch": 0.01, "learning_rate": 2.2067932071204558e-05, "loss": 3.8948, "step": 1705984 }, { "epoch": 0.01, "learning_rate": 2.2059546123694038e-05, "loss": 3.8891, "step": 1706496 }, { "epoch": 0.01, "learning_rate": 2.2051160176183518e-05, "loss": 3.8868, "step": 1707008 }, { "epoch": 0.01, "learning_rate": 2.2042774228672998e-05, "loss": 3.8917, "step": 1707520 }, { "epoch": 0.01, "learning_rate": 2.2034388281162477e-05, "loss": 3.8904, "step": 1708032 }, { "epoch": 0.01, "learning_rate": 2.2026018712455687e-05, "loss": 3.8939, "step": 1708544 }, { "epoch": 0.01, "learning_rate": 2.2017632764945167e-05, "loss": 3.9064, "step": 1709056 }, { "epoch": 0.01, "learning_rate": 2.2009246817434646e-05, "loss": 3.8875, "step": 1709568 }, { "epoch": 0.01, "learning_rate": 2.2000860869924126e-05, "loss": 3.8841, "step": 1710080 }, { "epoch": 0.01, "learning_rate": 2.199249130121734e-05, "loss": 3.9021, "step": 1710592 }, { "epoch": 0.01, "learning_rate": 2.198410535370682e-05, "loss": 3.8861, "step": 1711104 }, { "epoch": 0.01, "learning_rate": 2.19757194061963e-05, "loss": 3.8906, "step": 1711616 }, { "epoch": 0.01, "learning_rate": 2.196733345868578e-05, "loss": 3.8964, "step": 1712128 }, { "epoch": 0.01, "learning_rate": 2.1958963889978988e-05, "loss": 3.8968, "step": 1712640 }, { "epoch": 0.01, "learning_rate": 2.1950594321272204e-05, "loss": 3.8886, "step": 1713152 }, { "epoch": 0.01, "learning_rate": 2.1942208373761684e-05, "loss": 3.8842, "step": 1713664 }, { "epoch": 0.01, "learning_rate": 2.193382242625116e-05, "loss": 3.8832, "step": 1714176 }, { "epoch": 0.01, "learning_rate": 2.192543647874064e-05, "loss": 3.9013, "step": 1714688 }, { "epoch": 0.01, "learning_rate": 2.191705053123012e-05, "loss": 3.8979, "step": 1715200 }, { "epoch": 0.01, "learning_rate": 2.1908680962523333e-05, "loss": 3.8968, "step": 1715712 }, { "epoch": 0.01, "learning_rate": 2.1900295015012813e-05, "loss": 3.8958, "step": 1716224 }, { "epoch": 0.01, "learning_rate": 2.1891909067502293e-05, "loss": 3.906, "step": 1716736 }, { "epoch": 0.01, "learning_rate": 2.1883523119991773e-05, "loss": 3.9018, "step": 1717248 }, { "epoch": 0.01, "learning_rate": 2.1875137172481253e-05, "loss": 3.8874, "step": 1717760 }, { "epoch": 0.01, "learning_rate": 2.1866751224970732e-05, "loss": 3.8975, "step": 1718272 }, { "epoch": 0.01, "learning_rate": 2.1858365277460212e-05, "loss": 3.9023, "step": 1718784 }, { "epoch": 0.01, "learning_rate": 2.1849979329949692e-05, "loss": 3.8839, "step": 1719296 }, { "epoch": 0.01, "learning_rate": 2.1841593382439172e-05, "loss": 3.8983, "step": 1719808 }, { "epoch": 0.01, "learning_rate": 2.1833207434928652e-05, "loss": 3.8984, "step": 1720320 }, { "epoch": 0.01, "learning_rate": 2.1824821487418132e-05, "loss": 3.9044, "step": 1720832 }, { "epoch": 0.01, "learning_rate": 2.1816435539907612e-05, "loss": 3.8964, "step": 1721344 }, { "epoch": 0.01, "learning_rate": 2.180806597120082e-05, "loss": 3.8776, "step": 1721856 }, { "epoch": 0.01, "learning_rate": 2.1799696402494034e-05, "loss": 3.8916, "step": 1722368 }, { "epoch": 0.01, "learning_rate": 2.1791310454983514e-05, "loss": 3.8885, "step": 1722880 }, { "epoch": 0.01, "learning_rate": 2.1782924507472994e-05, "loss": 3.8995, "step": 1723392 }, { "epoch": 0.01, "learning_rate": 2.1774538559962474e-05, "loss": 3.8939, "step": 1723904 }, { "epoch": 0.01, "learning_rate": 2.1766168991255686e-05, "loss": 3.8882, "step": 1724416 }, { "epoch": 0.02, "learning_rate": 2.1757783043745163e-05, "loss": 3.8968, "step": 1724928 }, { "epoch": 0.02, "learning_rate": 2.1749397096234646e-05, "loss": 3.8985, "step": 1725440 }, { "epoch": 0.02, "learning_rate": 2.1741011148724126e-05, "loss": 3.8831, "step": 1725952 }, { "epoch": 0.02, "learning_rate": 2.1732625201213606e-05, "loss": 3.8925, "step": 1726464 }, { "epoch": 0.02, "learning_rate": 2.1724239253703086e-05, "loss": 3.9028, "step": 1726976 }, { "epoch": 0.02, "learning_rate": 2.1715853306192566e-05, "loss": 3.9042, "step": 1727488 }, { "epoch": 0.02, "learning_rate": 2.1707467358682046e-05, "loss": 3.8957, "step": 1728000 }, { "epoch": 0.02, "learning_rate": 2.1699081411171522e-05, "loss": 3.8816, "step": 1728512 }, { "epoch": 0.02, "learning_rate": 2.1690695463661002e-05, "loss": 3.8931, "step": 1729024 }, { "epoch": 0.02, "learning_rate": 2.1682325894954218e-05, "loss": 3.8902, "step": 1729536 }, { "epoch": 0.02, "learning_rate": 2.1673939947443695e-05, "loss": 3.9025, "step": 1730048 }, { "epoch": 0.02, "learning_rate": 2.1665553999933175e-05, "loss": 3.9049, "step": 1730560 }, { "epoch": 0.02, "learning_rate": 2.1657168052422655e-05, "loss": 3.8906, "step": 1731072 }, { "epoch": 0.02, "learning_rate": 2.1648782104912135e-05, "loss": 3.889, "step": 1731584 }, { "epoch": 0.02, "learning_rate": 2.1640412536205347e-05, "loss": 3.8963, "step": 1732096 }, { "epoch": 0.02, "learning_rate": 2.1632026588694827e-05, "loss": 3.88, "step": 1732608 }, { "epoch": 0.02, "learning_rate": 2.1623640641184307e-05, "loss": 3.8974, "step": 1733120 }, { "epoch": 0.02, "learning_rate": 2.1615254693673787e-05, "loss": 3.8786, "step": 1733632 }, { "epoch": 0.02, "learning_rate": 2.1606885124966996e-05, "loss": 3.8993, "step": 1734144 }, { "epoch": 0.02, "learning_rate": 2.1598499177456476e-05, "loss": 3.8851, "step": 1734656 }, { "epoch": 0.02, "learning_rate": 2.1590113229945956e-05, "loss": 3.8937, "step": 1735168 }, { "epoch": 0.02, "learning_rate": 2.158172728243544e-05, "loss": 3.8907, "step": 1735680 }, { "epoch": 0.02, "learning_rate": 2.157334133492492e-05, "loss": 3.8889, "step": 1736192 }, { "epoch": 0.02, "learning_rate": 2.15649553874144e-05, "loss": 3.8945, "step": 1736704 }, { "epoch": 0.02, "learning_rate": 2.1556569439903876e-05, "loss": 3.8864, "step": 1737216 }, { "epoch": 0.02, "learning_rate": 2.1548183492393356e-05, "loss": 3.9086, "step": 1737728 }, { "epoch": 0.02, "learning_rate": 2.1539797544882836e-05, "loss": 3.9025, "step": 1738240 }, { "epoch": 0.02, "learning_rate": 2.1531427976176048e-05, "loss": 3.8935, "step": 1738752 }, { "epoch": 0.02, "learning_rate": 2.152305840746926e-05, "loss": 3.8975, "step": 1739264 }, { "epoch": 0.02, "learning_rate": 2.151467245995874e-05, "loss": 3.8876, "step": 1739776 }, { "epoch": 0.02, "learning_rate": 2.150628651244822e-05, "loss": 3.8964, "step": 1740288 }, { "epoch": 0.02, "learning_rate": 2.1497900564937697e-05, "loss": 3.8925, "step": 1740800 }, { "epoch": 0.02, "learning_rate": 2.1489547375034642e-05, "loss": 3.8942, "step": 1741312 }, { "epoch": 0.02, "learning_rate": 2.1481161427524122e-05, "loss": 3.8934, "step": 1741824 }, { "epoch": 0.02, "learning_rate": 2.1472775480013602e-05, "loss": 3.8905, "step": 1742336 }, { "epoch": 0.02, "learning_rate": 2.1464389532503082e-05, "loss": 3.8958, "step": 1742848 }, { "epoch": 0.02, "learning_rate": 2.1456003584992562e-05, "loss": 3.894, "step": 1743360 }, { "epoch": 0.02, "learning_rate": 2.1447617637482042e-05, "loss": 3.8895, "step": 1743872 }, { "epoch": 0.02, "learning_rate": 2.1439231689971522e-05, "loss": 3.8974, "step": 1744384 }, { "epoch": 0.02, "learning_rate": 2.1430862121264734e-05, "loss": 3.8807, "step": 1744896 }, { "epoch": 0.02, "learning_rate": 2.1422476173754214e-05, "loss": 3.9063, "step": 1745408 }, { "epoch": 0.02, "learning_rate": 2.1414090226243694e-05, "loss": 3.895, "step": 1745920 }, { "epoch": 0.02, "learning_rate": 2.140570427873317e-05, "loss": 3.9013, "step": 1746432 }, { "epoch": 0.02, "learning_rate": 2.139731833122265e-05, "loss": 3.884, "step": 1746944 }, { "epoch": 0.02, "learning_rate": 2.138893238371213e-05, "loss": 3.8968, "step": 1747456 }, { "epoch": 0.02, "learning_rate": 2.138054643620161e-05, "loss": 3.9008, "step": 1747968 }, { "epoch": 0.02, "learning_rate": 2.1372160488691094e-05, "loss": 3.898, "step": 1748480 }, { "epoch": 0.02, "learning_rate": 2.1363790919984303e-05, "loss": 3.8886, "step": 1748992 }, { "epoch": 0.02, "learning_rate": 2.1355404972473783e-05, "loss": 3.9037, "step": 1749504 }, { "epoch": 0.02, "learning_rate": 2.1347019024963263e-05, "loss": 3.8961, "step": 1750016 }, { "epoch": 0.02, "learning_rate": 2.1338633077452743e-05, "loss": 3.908, "step": 1750528 }, { "epoch": 0.02, "learning_rate": 2.1330247129942223e-05, "loss": 3.8893, "step": 1751040 }, { "epoch": 0.02, "learning_rate": 2.1321877561235436e-05, "loss": 3.9041, "step": 1751552 }, { "epoch": 0.02, "learning_rate": 2.1313491613724915e-05, "loss": 3.8973, "step": 1752064 }, { "epoch": 0.02, "learning_rate": 2.1305105666214395e-05, "loss": 3.8936, "step": 1752576 }, { "epoch": 0.02, "learning_rate": 2.1296719718703875e-05, "loss": 3.8968, "step": 1753088 }, { "epoch": 0.02, "learning_rate": 2.1288333771193352e-05, "loss": 3.8973, "step": 1753600 }, { "epoch": 0.02, "learning_rate": 2.1279947823682832e-05, "loss": 3.8995, "step": 1754112 }, { "epoch": 0.02, "learning_rate": 2.1271561876172312e-05, "loss": 3.8808, "step": 1754624 }, { "epoch": 0.02, "learning_rate": 2.1263175928661795e-05, "loss": 3.9004, "step": 1755136 }, { "epoch": 0.03, "eval_loss": 3.993619680404663, "eval_runtime": 289.3218, "eval_samples_per_second": 1318.916, "eval_steps_per_second": 41.217, "step": 1755360 }, { "epoch": 1.0, "learning_rate": 2.1254806359955004e-05, "loss": 3.8902, "step": 1755648 }, { "epoch": 1.0, "learning_rate": 2.1246436791248217e-05, "loss": 3.8867, "step": 1756160 }, { "epoch": 1.0, "learning_rate": 2.1238050843737697e-05, "loss": 3.8991, "step": 1756672 }, { "epoch": 1.0, "learning_rate": 2.1229664896227177e-05, "loss": 3.9045, "step": 1757184 }, { "epoch": 1.0, "learning_rate": 2.1221278948716657e-05, "loss": 3.8986, "step": 1757696 }, { "epoch": 1.0, "learning_rate": 2.121290938000987e-05, "loss": 3.8951, "step": 1758208 }, { "epoch": 1.0, "learning_rate": 2.1204539811303078e-05, "loss": 3.899, "step": 1758720 }, { "epoch": 1.0, "learning_rate": 2.1196153863792558e-05, "loss": 3.8848, "step": 1759232 }, { "epoch": 1.0, "learning_rate": 2.1187767916282038e-05, "loss": 3.8995, "step": 1759744 }, { "epoch": 1.0, "learning_rate": 2.1179381968771518e-05, "loss": 3.8984, "step": 1760256 }, { "epoch": 1.0, "learning_rate": 2.1170996021261e-05, "loss": 3.8987, "step": 1760768 }, { "epoch": 1.0, "learning_rate": 2.1162610073750478e-05, "loss": 3.9006, "step": 1761280 }, { "epoch": 1.0, "learning_rate": 2.115424050504369e-05, "loss": 3.8915, "step": 1761792 }, { "epoch": 1.0, "learning_rate": 2.114585455753317e-05, "loss": 3.8922, "step": 1762304 }, { "epoch": 1.0, "learning_rate": 2.113746861002265e-05, "loss": 3.8907, "step": 1762816 }, { "epoch": 1.0, "learning_rate": 2.1129082662512127e-05, "loss": 3.8825, "step": 1763328 }, { "epoch": 1.0, "learning_rate": 2.112069671500161e-05, "loss": 3.8915, "step": 1763840 }, { "epoch": 1.0, "learning_rate": 2.111231076749109e-05, "loss": 3.8874, "step": 1764352 }, { "epoch": 1.0, "learning_rate": 2.110392481998057e-05, "loss": 3.8918, "step": 1764864 }, { "epoch": 1.0, "learning_rate": 2.109553887247005e-05, "loss": 3.9021, "step": 1765376 }, { "epoch": 1.0, "learning_rate": 2.108715292495953e-05, "loss": 3.9089, "step": 1765888 }, { "epoch": 1.0, "learning_rate": 2.1078766977449007e-05, "loss": 3.9039, "step": 1766400 }, { "epoch": 1.0, "learning_rate": 2.1070381029938487e-05, "loss": 3.8917, "step": 1766912 }, { "epoch": 1.0, "learning_rate": 2.1062011461231703e-05, "loss": 3.8998, "step": 1767424 }, { "epoch": 1.0, "learning_rate": 2.1053625513721183e-05, "loss": 3.8912, "step": 1767936 }, { "epoch": 1.0, "learning_rate": 2.104525594501439e-05, "loss": 3.9009, "step": 1768448 }, { "epoch": 1.0, "learning_rate": 2.103686999750387e-05, "loss": 3.8935, "step": 1768960 }, { "epoch": 1.0, "learning_rate": 2.102848404999335e-05, "loss": 3.88, "step": 1769472 }, { "epoch": 1.0, "learning_rate": 2.1020098102482828e-05, "loss": 3.8934, "step": 1769984 }, { "epoch": 1.0, "learning_rate": 2.101171215497231e-05, "loss": 3.885, "step": 1770496 }, { "epoch": 1.01, "learning_rate": 2.100332620746179e-05, "loss": 3.8912, "step": 1771008 }, { "epoch": 1.01, "learning_rate": 2.099494025995127e-05, "loss": 3.901, "step": 1771520 }, { "epoch": 1.01, "learning_rate": 2.098655431244075e-05, "loss": 3.8976, "step": 1772032 }, { "epoch": 1.01, "learning_rate": 2.097816836493023e-05, "loss": 3.8972, "step": 1772544 }, { "epoch": 1.01, "learning_rate": 2.096979879622344e-05, "loss": 3.8875, "step": 1773056 }, { "epoch": 1.01, "learning_rate": 2.0961429227516656e-05, "loss": 3.9093, "step": 1773568 }, { "epoch": 1.01, "learning_rate": 2.0953043280006133e-05, "loss": 3.8941, "step": 1774080 }, { "epoch": 1.01, "learning_rate": 2.0944657332495613e-05, "loss": 3.8833, "step": 1774592 }, { "epoch": 1.01, "learning_rate": 2.0936271384985093e-05, "loss": 3.8926, "step": 1775104 }, { "epoch": 1.01, "learning_rate": 2.0927885437474573e-05, "loss": 3.8847, "step": 1775616 }, { "epoch": 1.01, "learning_rate": 2.0919499489964053e-05, "loss": 3.8916, "step": 1776128 }, { "epoch": 1.01, "learning_rate": 2.0911113542453533e-05, "loss": 3.898, "step": 1776640 }, { "epoch": 1.01, "learning_rate": 2.0902727594943013e-05, "loss": 3.895, "step": 1777152 }, { "epoch": 1.01, "learning_rate": 2.0894341647432492e-05, "loss": 3.8908, "step": 1777664 }, { "epoch": 1.01, "learning_rate": 2.0885972078725705e-05, "loss": 3.9021, "step": 1778176 }, { "epoch": 1.01, "learning_rate": 2.0877586131215185e-05, "loss": 3.8995, "step": 1778688 }, { "epoch": 1.01, "learning_rate": 2.086920018370466e-05, "loss": 3.9029, "step": 1779200 }, { "epoch": 1.01, "learning_rate": 2.086081423619414e-05, "loss": 3.8854, "step": 1779712 }, { "epoch": 1.01, "learning_rate": 2.085242828868362e-05, "loss": 3.8622, "step": 1780224 }, { "epoch": 1.01, "learning_rate": 2.0844058719976837e-05, "loss": 3.9123, "step": 1780736 }, { "epoch": 1.01, "learning_rate": 2.0835672772466314e-05, "loss": 3.8945, "step": 1781248 }, { "epoch": 1.01, "learning_rate": 2.0827286824955794e-05, "loss": 3.8976, "step": 1781760 }, { "epoch": 1.01, "learning_rate": 2.0818900877445274e-05, "loss": 3.8906, "step": 1782272 }, { "epoch": 1.01, "learning_rate": 2.0810531308738486e-05, "loss": 3.8803, "step": 1782784 }, { "epoch": 1.01, "learning_rate": 2.0802145361227966e-05, "loss": 3.882, "step": 1783296 }, { "epoch": 1.01, "learning_rate": 2.0793759413717446e-05, "loss": 3.8852, "step": 1783808 }, { "epoch": 1.01, "learning_rate": 2.0785373466206926e-05, "loss": 3.8831, "step": 1784320 }, { "epoch": 1.01, "learning_rate": 2.0776987518696406e-05, "loss": 3.8864, "step": 1784832 }, { "epoch": 1.01, "learning_rate": 2.0768601571185886e-05, "loss": 3.9055, "step": 1785344 }, { "epoch": 1.01, "learning_rate": 2.0760215623675366e-05, "loss": 3.8814, "step": 1785856 }, { "epoch": 1.01, "learning_rate": 2.0751829676164843e-05, "loss": 3.8782, "step": 1786368 }, { "epoch": 1.01, "learning_rate": 2.074346010745806e-05, "loss": 3.8996, "step": 1786880 }, { "epoch": 1.01, "learning_rate": 2.0735090538751267e-05, "loss": 3.8768, "step": 1787392 }, { "epoch": 1.01, "learning_rate": 2.0726704591240747e-05, "loss": 3.8826, "step": 1787904 }, { "epoch": 1.01, "learning_rate": 2.0718318643730227e-05, "loss": 3.8916, "step": 1788416 }, { "epoch": 1.01, "learning_rate": 2.0709932696219707e-05, "loss": 3.893, "step": 1788928 }, { "epoch": 1.01, "learning_rate": 2.0701546748709187e-05, "loss": 3.8821, "step": 1789440 }, { "epoch": 1.01, "learning_rate": 2.0693160801198667e-05, "loss": 3.8864, "step": 1789952 }, { "epoch": 1.01, "learning_rate": 2.0684774853688147e-05, "loss": 3.8751, "step": 1790464 }, { "epoch": 1.01, "learning_rate": 2.0676388906177627e-05, "loss": 3.8946, "step": 1790976 }, { "epoch": 1.01, "learning_rate": 2.066801933747084e-05, "loss": 3.8912, "step": 1791488 }, { "epoch": 1.01, "learning_rate": 2.065964976876405e-05, "loss": 3.889, "step": 1792000 }, { "epoch": 1.01, "learning_rate": 2.065126382125353e-05, "loss": 3.893, "step": 1792512 }, { "epoch": 1.01, "learning_rate": 2.0642877873743012e-05, "loss": 3.8963, "step": 1793024 }, { "epoch": 1.01, "learning_rate": 2.0634491926232492e-05, "loss": 3.9019, "step": 1793536 }, { "epoch": 1.01, "learning_rate": 2.062610597872197e-05, "loss": 3.8809, "step": 1794048 }, { "epoch": 1.01, "learning_rate": 2.061772003121145e-05, "loss": 3.8919, "step": 1794560 }, { "epoch": 1.01, "learning_rate": 2.060935046250466e-05, "loss": 3.8969, "step": 1795072 }, { "epoch": 1.01, "learning_rate": 2.0600980893797874e-05, "loss": 3.8744, "step": 1795584 }, { "epoch": 1.01, "learning_rate": 2.0592594946287353e-05, "loss": 3.8951, "step": 1796096 }, { "epoch": 1.01, "learning_rate": 2.0584208998776833e-05, "loss": 3.8914, "step": 1796608 }, { "epoch": 1.01, "learning_rate": 2.0575823051266313e-05, "loss": 3.9006, "step": 1797120 }, { "epoch": 1.01, "learning_rate": 2.056743710375579e-05, "loss": 3.8934, "step": 1797632 }, { "epoch": 1.01, "learning_rate": 2.055905115624527e-05, "loss": 3.8742, "step": 1798144 }, { "epoch": 1.01, "learning_rate": 2.055066520873475e-05, "loss": 3.878, "step": 1798656 }, { "epoch": 1.01, "learning_rate": 2.0542295640027966e-05, "loss": 3.886, "step": 1799168 }, { "epoch": 1.01, "learning_rate": 2.0533909692517442e-05, "loss": 3.8948, "step": 1799680 }, { "epoch": 1.01, "learning_rate": 2.0525523745006922e-05, "loss": 3.8855, "step": 1800192 }, { "epoch": 1.01, "learning_rate": 2.0517154176300135e-05, "loss": 3.8857, "step": 1800704 }, { "epoch": 1.02, "learning_rate": 2.050876822878961e-05, "loss": 3.8921, "step": 1801216 }, { "epoch": 1.02, "learning_rate": 2.0500382281279095e-05, "loss": 3.8923, "step": 1801728 }, { "epoch": 1.02, "learning_rate": 2.0491996333768575e-05, "loss": 3.8816, "step": 1802240 }, { "epoch": 1.02, "learning_rate": 2.0483610386258055e-05, "loss": 3.8855, "step": 1802752 }, { "epoch": 1.02, "learning_rate": 2.0475224438747535e-05, "loss": 3.8965, "step": 1803264 }, { "epoch": 1.02, "learning_rate": 2.0466838491237014e-05, "loss": 3.8963, "step": 1803776 }, { "epoch": 1.02, "learning_rate": 2.0458452543726494e-05, "loss": 3.8914, "step": 1804288 }, { "epoch": 1.02, "learning_rate": 2.045006659621597e-05, "loss": 3.8779, "step": 1804800 }, { "epoch": 1.02, "learning_rate": 2.044168064870545e-05, "loss": 3.8896, "step": 1805312 }, { "epoch": 1.02, "learning_rate": 2.0433294701194934e-05, "loss": 3.883, "step": 1805824 }, { "epoch": 1.02, "learning_rate": 2.0424908753684414e-05, "loss": 3.8993, "step": 1806336 }, { "epoch": 1.02, "learning_rate": 2.0416522806173894e-05, "loss": 3.8956, "step": 1806848 }, { "epoch": 1.02, "learning_rate": 2.0408136858663374e-05, "loss": 3.889, "step": 1807360 }, { "epoch": 1.02, "learning_rate": 2.039975091115285e-05, "loss": 3.8868, "step": 1807872 }, { "epoch": 1.02, "learning_rate": 2.039136496364233e-05, "loss": 3.8851, "step": 1808384 }, { "epoch": 1.02, "learning_rate": 2.0382995394935543e-05, "loss": 3.8796, "step": 1808896 }, { "epoch": 1.02, "learning_rate": 2.0374609447425027e-05, "loss": 3.8882, "step": 1809408 }, { "epoch": 1.02, "learning_rate": 2.0366239878718236e-05, "loss": 3.8767, "step": 1809920 }, { "epoch": 1.02, "learning_rate": 2.0357853931207716e-05, "loss": 3.8948, "step": 1810432 }, { "epoch": 1.02, "learning_rate": 2.0349467983697196e-05, "loss": 3.8803, "step": 1810944 }, { "epoch": 1.02, "learning_rate": 2.0341082036186675e-05, "loss": 3.8844, "step": 1811456 }, { "epoch": 1.02, "learning_rate": 2.0332696088676152e-05, "loss": 3.884, "step": 1811968 }, { "epoch": 1.02, "learning_rate": 2.0324310141165635e-05, "loss": 3.881, "step": 1812480 }, { "epoch": 1.02, "learning_rate": 2.0315924193655115e-05, "loss": 3.8917, "step": 1812992 }, { "epoch": 1.02, "learning_rate": 2.0307538246144595e-05, "loss": 3.8848, "step": 1813504 }, { "epoch": 1.02, "learning_rate": 2.0299168677437804e-05, "loss": 3.9045, "step": 1814016 }, { "epoch": 1.02, "learning_rate": 2.0290782729927284e-05, "loss": 3.897, "step": 1814528 }, { "epoch": 1.02, "learning_rate": 2.0282396782416764e-05, "loss": 3.8872, "step": 1815040 }, { "epoch": 1.02, "learning_rate": 2.0274027213709977e-05, "loss": 3.8909, "step": 1815552 }, { "epoch": 1.02, "learning_rate": 2.0265641266199457e-05, "loss": 3.8823, "step": 1816064 }, { "epoch": 1.02, "learning_rate": 2.0257255318688937e-05, "loss": 3.8881, "step": 1816576 }, { "epoch": 1.02, "learning_rate": 2.0248869371178417e-05, "loss": 3.8924, "step": 1817088 }, { "epoch": 1.02, "learning_rate": 2.0240483423667897e-05, "loss": 3.8866, "step": 1817600 }, { "epoch": 1.02, "learning_rate": 2.0232097476157377e-05, "loss": 3.8891, "step": 1818112 }, { "epoch": 1.02, "learning_rate": 2.0223711528646857e-05, "loss": 3.8864, "step": 1818624 }, { "epoch": 1.02, "learning_rate": 2.021534195994007e-05, "loss": 3.8897, "step": 1819136 }, { "epoch": 1.02, "learning_rate": 2.020695601242955e-05, "loss": 3.8894, "step": 1819648 }, { "epoch": 1.02, "learning_rate": 2.019857006491903e-05, "loss": 3.8805, "step": 1820160 }, { "epoch": 1.02, "learning_rate": 2.0190184117408505e-05, "loss": 3.8908, "step": 1820672 }, { "epoch": 1.02, "learning_rate": 2.0181814548701718e-05, "loss": 3.8798, "step": 1821184 }, { "epoch": 1.02, "learning_rate": 2.0173428601191198e-05, "loss": 3.9018, "step": 1821696 }, { "epoch": 1.02, "learning_rate": 2.016504265368068e-05, "loss": 3.8873, "step": 1822208 }, { "epoch": 1.02, "learning_rate": 2.0156656706170158e-05, "loss": 3.8941, "step": 1822720 }, { "epoch": 1.02, "learning_rate": 2.0148270758659638e-05, "loss": 3.8805, "step": 1823232 }, { "epoch": 1.02, "learning_rate": 2.0139884811149118e-05, "loss": 3.8916, "step": 1823744 }, { "epoch": 1.02, "learning_rate": 2.0131498863638598e-05, "loss": 3.8941, "step": 1824256 }, { "epoch": 1.02, "learning_rate": 2.0123112916128078e-05, "loss": 3.8925, "step": 1824768 }, { "epoch": 1.02, "learning_rate": 2.011474334742129e-05, "loss": 3.8852, "step": 1825280 }, { "epoch": 1.02, "learning_rate": 2.010635739991077e-05, "loss": 3.8962, "step": 1825792 }, { "epoch": 1.02, "learning_rate": 2.009797145240025e-05, "loss": 3.891, "step": 1826304 }, { "epoch": 1.02, "learning_rate": 2.008958550488973e-05, "loss": 3.9061, "step": 1826816 }, { "epoch": 1.02, "learning_rate": 2.008121593618294e-05, "loss": 3.8843, "step": 1827328 }, { "epoch": 1.02, "learning_rate": 2.007282998867242e-05, "loss": 3.9006, "step": 1827840 }, { "epoch": 1.02, "learning_rate": 2.00644440411619e-05, "loss": 3.8914, "step": 1828352 }, { "epoch": 1.02, "learning_rate": 2.0056058093651382e-05, "loss": 3.889, "step": 1828864 }, { "epoch": 1.02, "learning_rate": 2.004768852494459e-05, "loss": 3.8897, "step": 1829376 }, { "epoch": 1.02, "learning_rate": 2.003930257743407e-05, "loss": 3.8927, "step": 1829888 }, { "epoch": 1.02, "learning_rate": 2.003091662992355e-05, "loss": 3.8953, "step": 1830400 }, { "epoch": 1.02, "learning_rate": 2.002253068241303e-05, "loss": 3.8748, "step": 1830912 }, { "epoch": 1.02, "learning_rate": 2.001414473490251e-05, "loss": 3.895, "step": 1831424 }, { "epoch": 1.03, "eval_loss": 3.9921257495880127, "eval_runtime": 287.134, "eval_samples_per_second": 1328.965, "eval_steps_per_second": 41.531, "step": 1831680 }, { "epoch": 0.0, "learning_rate": 2.0005775166195724e-05, "loss": 3.8801, "step": 1831936 }, { "epoch": 0.0, "learning_rate": 1.9997389218685204e-05, "loss": 3.8816, "step": 1832448 }, { "epoch": 0.0, "learning_rate": 1.9989003271174684e-05, "loss": 3.8922, "step": 1832960 }, { "epoch": 0.0, "learning_rate": 1.998061732366416e-05, "loss": 3.9036, "step": 1833472 }, { "epoch": 0.0, "learning_rate": 1.997223137615364e-05, "loss": 3.8934, "step": 1833984 }, { "epoch": 0.0, "learning_rate": 1.996384542864312e-05, "loss": 3.8862, "step": 1834496 }, { "epoch": 0.0, "learning_rate": 1.99554594811326e-05, "loss": 3.8993, "step": 1835008 }, { "epoch": 0.0, "learning_rate": 1.9947073533622083e-05, "loss": 3.879, "step": 1835520 }, { "epoch": 0.0, "learning_rate": 1.9938687586111563e-05, "loss": 3.8919, "step": 1836032 }, { "epoch": 0.0, "learning_rate": 1.9930301638601043e-05, "loss": 3.897, "step": 1836544 }, { "epoch": 0.0, "learning_rate": 1.992191569109052e-05, "loss": 3.8914, "step": 1837056 }, { "epoch": 0.0, "learning_rate": 1.9913546122383732e-05, "loss": 3.8942, "step": 1837568 }, { "epoch": 0.0, "learning_rate": 1.9905176553676945e-05, "loss": 3.8961, "step": 1838080 }, { "epoch": 0.0, "learning_rate": 1.9896790606166425e-05, "loss": 3.8811, "step": 1838592 }, { "epoch": 0.0, "learning_rate": 1.9888404658655905e-05, "loss": 3.8809, "step": 1839104 }, { "epoch": 0.0, "learning_rate": 1.9880018711145385e-05, "loss": 3.8785, "step": 1839616 }, { "epoch": 0.0, "learning_rate": 1.9871632763634865e-05, "loss": 3.8834, "step": 1840128 }, { "epoch": 0.0, "learning_rate": 1.986324681612434e-05, "loss": 3.8869, "step": 1840640 }, { "epoch": 0.0, "learning_rate": 1.985486086861382e-05, "loss": 3.8841, "step": 1841152 }, { "epoch": 0.0, "learning_rate": 1.9846474921103305e-05, "loss": 3.8959, "step": 1841664 }, { "epoch": 0.0, "learning_rate": 1.9838088973592785e-05, "loss": 3.9044, "step": 1842176 }, { "epoch": 0.0, "learning_rate": 1.9829703026082265e-05, "loss": 3.8986, "step": 1842688 }, { "epoch": 0.0, "learning_rate": 1.9821317078571744e-05, "loss": 3.8886, "step": 1843200 }, { "epoch": 0.0, "learning_rate": 1.9812931131061224e-05, "loss": 3.8928, "step": 1843712 }, { "epoch": 0.0, "learning_rate": 1.98045451835507e-05, "loss": 3.8915, "step": 1844224 }, { "epoch": 0.0, "learning_rate": 1.979615923604018e-05, "loss": 3.8902, "step": 1844736 }, { "epoch": 0.0, "learning_rate": 1.978777328852966e-05, "loss": 3.8892, "step": 1845248 }, { "epoch": 0.0, "learning_rate": 1.9779403719822873e-05, "loss": 3.8796, "step": 1845760 }, { "epoch": 0.0, "learning_rate": 1.9771017772312353e-05, "loss": 3.8854, "step": 1846272 }, { "epoch": 0.0, "learning_rate": 1.9762631824801833e-05, "loss": 3.882, "step": 1846784 }, { "epoch": 0.01, "learning_rate": 1.9754245877291313e-05, "loss": 3.883, "step": 1847296 }, { "epoch": 0.01, "learning_rate": 1.9745859929780793e-05, "loss": 3.8958, "step": 1847808 }, { "epoch": 0.01, "learning_rate": 1.9737473982270273e-05, "loss": 3.895, "step": 1848320 }, { "epoch": 0.01, "learning_rate": 1.9729088034759753e-05, "loss": 3.8916, "step": 1848832 }, { "epoch": 0.01, "learning_rate": 1.9720702087249233e-05, "loss": 3.887, "step": 1849344 }, { "epoch": 0.01, "learning_rate": 1.9712332518542446e-05, "loss": 3.8952, "step": 1849856 }, { "epoch": 0.01, "learning_rate": 1.9703946571031926e-05, "loss": 3.8889, "step": 1850368 }, { "epoch": 0.01, "learning_rate": 1.9695560623521405e-05, "loss": 3.8822, "step": 1850880 }, { "epoch": 0.01, "learning_rate": 1.9687174676010882e-05, "loss": 3.8869, "step": 1851392 }, { "epoch": 0.01, "learning_rate": 1.9678788728500362e-05, "loss": 3.8781, "step": 1851904 }, { "epoch": 0.01, "learning_rate": 1.9670402780989845e-05, "loss": 3.8843, "step": 1852416 }, { "epoch": 0.01, "learning_rate": 1.9662016833479325e-05, "loss": 3.8953, "step": 1852928 }, { "epoch": 0.01, "learning_rate": 1.9653630885968805e-05, "loss": 3.8854, "step": 1853440 }, { "epoch": 0.01, "learning_rate": 1.9645244938458285e-05, "loss": 3.8881, "step": 1853952 }, { "epoch": 0.01, "learning_rate": 1.9636858990947762e-05, "loss": 3.8993, "step": 1854464 }, { "epoch": 0.01, "learning_rate": 1.9628473043437242e-05, "loss": 3.8917, "step": 1854976 }, { "epoch": 0.01, "learning_rate": 1.9620103474730454e-05, "loss": 3.8937, "step": 1855488 }, { "epoch": 0.01, "learning_rate": 1.9611717527219938e-05, "loss": 3.8868, "step": 1856000 }, { "epoch": 0.01, "learning_rate": 1.9603331579709414e-05, "loss": 3.8602, "step": 1856512 }, { "epoch": 0.01, "learning_rate": 1.9594945632198894e-05, "loss": 3.903, "step": 1857024 }, { "epoch": 0.01, "learning_rate": 1.9586576063492107e-05, "loss": 3.8882, "step": 1857536 }, { "epoch": 0.01, "learning_rate": 1.9578190115981587e-05, "loss": 3.8921, "step": 1858048 }, { "epoch": 0.01, "learning_rate": 1.9569804168471066e-05, "loss": 3.8879, "step": 1858560 }, { "epoch": 0.01, "learning_rate": 1.956143459976428e-05, "loss": 3.876, "step": 1859072 }, { "epoch": 0.01, "learning_rate": 1.955304865225376e-05, "loss": 3.8751, "step": 1859584 }, { "epoch": 0.01, "learning_rate": 1.9544662704743235e-05, "loss": 3.8817, "step": 1860096 }, { "epoch": 0.01, "learning_rate": 1.9536276757232715e-05, "loss": 3.879, "step": 1860608 }, { "epoch": 0.01, "learning_rate": 1.9527890809722195e-05, "loss": 3.8781, "step": 1861120 }, { "epoch": 0.01, "learning_rate": 1.9519504862211675e-05, "loss": 3.8999, "step": 1861632 }, { "epoch": 0.01, "learning_rate": 1.9511118914701155e-05, "loss": 3.8781, "step": 1862144 }, { "epoch": 0.01, "learning_rate": 1.9502749345994368e-05, "loss": 3.8729, "step": 1862656 }, { "epoch": 0.01, "learning_rate": 1.9494363398483848e-05, "loss": 3.8958, "step": 1863168 }, { "epoch": 0.01, "learning_rate": 1.9485977450973328e-05, "loss": 3.8685, "step": 1863680 }, { "epoch": 0.01, "learning_rate": 1.9477591503462808e-05, "loss": 3.8755, "step": 1864192 }, { "epoch": 0.01, "learning_rate": 1.9469205555952288e-05, "loss": 3.8897, "step": 1864704 }, { "epoch": 0.01, "learning_rate": 1.9460819608441768e-05, "loss": 3.8893, "step": 1865216 }, { "epoch": 0.01, "learning_rate": 1.9452433660931248e-05, "loss": 3.8762, "step": 1865728 }, { "epoch": 0.01, "learning_rate": 1.944406409222446e-05, "loss": 3.8773, "step": 1866240 }, { "epoch": 0.01, "learning_rate": 1.943567814471394e-05, "loss": 3.8733, "step": 1866752 }, { "epoch": 0.01, "learning_rate": 1.9427292197203417e-05, "loss": 3.8881, "step": 1867264 }, { "epoch": 0.01, "learning_rate": 1.941892262849663e-05, "loss": 3.8839, "step": 1867776 }, { "epoch": 0.01, "learning_rate": 1.941053668098611e-05, "loss": 3.8842, "step": 1868288 }, { "epoch": 0.01, "learning_rate": 1.9402150733475592e-05, "loss": 3.8879, "step": 1868800 }, { "epoch": 0.01, "learning_rate": 1.939376478596507e-05, "loss": 3.8903, "step": 1869312 }, { "epoch": 0.01, "learning_rate": 1.938537883845455e-05, "loss": 3.8951, "step": 1869824 }, { "epoch": 0.01, "learning_rate": 1.937699289094403e-05, "loss": 3.8751, "step": 1870336 }, { "epoch": 0.01, "learning_rate": 1.936860694343351e-05, "loss": 3.8896, "step": 1870848 }, { "epoch": 0.01, "learning_rate": 1.936023737472672e-05, "loss": 3.8916, "step": 1871360 }, { "epoch": 0.01, "learning_rate": 1.93518514272162e-05, "loss": 3.8674, "step": 1871872 }, { "epoch": 0.01, "learning_rate": 1.934346547970568e-05, "loss": 3.8892, "step": 1872384 }, { "epoch": 0.01, "learning_rate": 1.933507953219516e-05, "loss": 3.8896, "step": 1872896 }, { "epoch": 0.01, "learning_rate": 1.932669358468464e-05, "loss": 3.8966, "step": 1873408 }, { "epoch": 0.01, "learning_rate": 1.931832401597785e-05, "loss": 3.8888, "step": 1873920 }, { "epoch": 0.01, "learning_rate": 1.930993806846733e-05, "loss": 3.8739, "step": 1874432 }, { "epoch": 0.01, "learning_rate": 1.9301552120956813e-05, "loss": 3.868, "step": 1874944 }, { "epoch": 0.01, "learning_rate": 1.9293166173446293e-05, "loss": 3.883, "step": 1875456 }, { "epoch": 0.01, "learning_rate": 1.9284796604739502e-05, "loss": 3.889, "step": 1875968 }, { "epoch": 0.01, "learning_rate": 1.9276410657228982e-05, "loss": 3.8806, "step": 1876480 }, { "epoch": 0.01, "learning_rate": 1.926804108852219e-05, "loss": 3.8773, "step": 1876992 }, { "epoch": 0.02, "learning_rate": 1.9259655141011675e-05, "loss": 3.8845, "step": 1877504 }, { "epoch": 0.02, "learning_rate": 1.9251269193501155e-05, "loss": 3.8889, "step": 1878016 }, { "epoch": 0.02, "learning_rate": 1.9242883245990635e-05, "loss": 3.8766, "step": 1878528 }, { "epoch": 0.02, "learning_rate": 1.9234497298480115e-05, "loss": 3.8812, "step": 1879040 }, { "epoch": 0.02, "learning_rate": 1.9226111350969595e-05, "loss": 3.8884, "step": 1879552 }, { "epoch": 0.02, "learning_rate": 1.921772540345907e-05, "loss": 3.8929, "step": 1880064 }, { "epoch": 0.02, "learning_rate": 1.920933945594855e-05, "loss": 3.8858, "step": 1880576 }, { "epoch": 0.02, "learning_rate": 1.920095350843803e-05, "loss": 3.8766, "step": 1881088 }, { "epoch": 0.02, "learning_rate": 1.9192583939731247e-05, "loss": 3.8805, "step": 1881600 }, { "epoch": 0.02, "learning_rate": 1.9184197992220724e-05, "loss": 3.88, "step": 1882112 }, { "epoch": 0.02, "learning_rate": 1.9175812044710204e-05, "loss": 3.8911, "step": 1882624 }, { "epoch": 0.02, "learning_rate": 1.9167426097199684e-05, "loss": 3.8906, "step": 1883136 }, { "epoch": 0.02, "learning_rate": 1.9159040149689164e-05, "loss": 3.8833, "step": 1883648 }, { "epoch": 0.02, "learning_rate": 1.9150670580982376e-05, "loss": 3.8814, "step": 1884160 }, { "epoch": 0.02, "learning_rate": 1.9142284633471856e-05, "loss": 3.8748, "step": 1884672 }, { "epoch": 0.02, "learning_rate": 1.9133898685961336e-05, "loss": 3.8792, "step": 1885184 }, { "epoch": 0.02, "learning_rate": 1.9125512738450816e-05, "loss": 3.8806, "step": 1885696 }, { "epoch": 0.02, "learning_rate": 1.9117143169744025e-05, "loss": 3.8709, "step": 1886208 }, { "epoch": 0.02, "learning_rate": 1.9108757222233505e-05, "loss": 3.8925, "step": 1886720 }, { "epoch": 0.02, "learning_rate": 1.9100371274722985e-05, "loss": 3.8782, "step": 1887232 }, { "epoch": 0.02, "learning_rate": 1.9091985327212468e-05, "loss": 3.8763, "step": 1887744 }, { "epoch": 0.02, "learning_rate": 1.9083599379701948e-05, "loss": 3.8769, "step": 1888256 }, { "epoch": 0.02, "learning_rate": 1.9075229810995157e-05, "loss": 3.8744, "step": 1888768 }, { "epoch": 0.02, "learning_rate": 1.9066843863484637e-05, "loss": 3.8908, "step": 1889280 }, { "epoch": 0.02, "learning_rate": 1.9058457915974117e-05, "loss": 3.8762, "step": 1889792 }, { "epoch": 0.02, "learning_rate": 1.9050071968463597e-05, "loss": 3.9012, "step": 1890304 }, { "epoch": 0.02, "learning_rate": 1.9041686020953077e-05, "loss": 3.8927, "step": 1890816 }, { "epoch": 0.02, "learning_rate": 1.903331645224629e-05, "loss": 3.8838, "step": 1891328 }, { "epoch": 0.02, "learning_rate": 1.902493050473577e-05, "loss": 3.883, "step": 1891840 }, { "epoch": 0.02, "learning_rate": 1.901654455722525e-05, "loss": 3.8803, "step": 1892352 }, { "epoch": 0.02, "learning_rate": 1.9008158609714726e-05, "loss": 3.8815, "step": 1892864 }, { "epoch": 0.02, "learning_rate": 1.8999772662204206e-05, "loss": 3.8893, "step": 1893376 }, { "epoch": 0.02, "learning_rate": 1.8991403093497422e-05, "loss": 3.879, "step": 1893888 }, { "epoch": 0.02, "learning_rate": 1.8983017145986902e-05, "loss": 3.8869, "step": 1894400 }, { "epoch": 0.02, "learning_rate": 1.897463119847638e-05, "loss": 3.8792, "step": 1894912 }, { "epoch": 0.02, "learning_rate": 1.896624525096586e-05, "loss": 3.8836, "step": 1895424 }, { "epoch": 0.02, "learning_rate": 1.895787568225907e-05, "loss": 3.8847, "step": 1895936 }, { "epoch": 0.02, "learning_rate": 1.8949489734748547e-05, "loss": 3.8737, "step": 1896448 }, { "epoch": 0.02, "learning_rate": 1.894110378723803e-05, "loss": 3.8867, "step": 1896960 }, { "epoch": 0.02, "learning_rate": 1.893271783972751e-05, "loss": 3.8749, "step": 1897472 }, { "epoch": 0.02, "learning_rate": 1.892433189221699e-05, "loss": 3.8944, "step": 1897984 }, { "epoch": 0.02, "learning_rate": 1.891594594470647e-05, "loss": 3.8828, "step": 1898496 }, { "epoch": 0.02, "learning_rate": 1.890757637599968e-05, "loss": 3.8881, "step": 1899008 }, { "epoch": 0.02, "learning_rate": 1.889919042848916e-05, "loss": 3.8736, "step": 1899520 }, { "epoch": 0.02, "learning_rate": 1.889080448097864e-05, "loss": 3.8916, "step": 1900032 }, { "epoch": 0.02, "learning_rate": 1.8882418533468123e-05, "loss": 3.8824, "step": 1900544 }, { "epoch": 0.02, "learning_rate": 1.8874032585957603e-05, "loss": 3.8878, "step": 1901056 }, { "epoch": 0.02, "learning_rate": 1.8865646638447083e-05, "loss": 3.8819, "step": 1901568 }, { "epoch": 0.02, "learning_rate": 1.885729344854402e-05, "loss": 3.8895, "step": 1902080 }, { "epoch": 0.02, "learning_rate": 1.88489075010335e-05, "loss": 3.8855, "step": 1902592 }, { "epoch": 0.02, "learning_rate": 1.8840521553522984e-05, "loss": 3.9025, "step": 1903104 }, { "epoch": 0.02, "learning_rate": 1.8832135606012464e-05, "loss": 3.8767, "step": 1903616 }, { "epoch": 0.02, "learning_rate": 1.8823749658501944e-05, "loss": 3.8949, "step": 1904128 }, { "epoch": 0.02, "learning_rate": 1.8815363710991424e-05, "loss": 3.8876, "step": 1904640 }, { "epoch": 0.02, "learning_rate": 1.8806977763480904e-05, "loss": 3.8891, "step": 1905152 }, { "epoch": 0.02, "learning_rate": 1.879859181597038e-05, "loss": 3.8797, "step": 1905664 }, { "epoch": 0.02, "learning_rate": 1.879020586845986e-05, "loss": 3.8887, "step": 1906176 }, { "epoch": 0.02, "learning_rate": 1.878181992094934e-05, "loss": 3.8879, "step": 1906688 }, { "epoch": 0.02, "learning_rate": 1.8773433973438824e-05, "loss": 3.8804, "step": 1907200 }, { "epoch": 0.02, "learning_rate": 1.8765064404732033e-05, "loss": 3.8859, "step": 1907712 }, { "epoch": 0.03, "eval_loss": 3.9900238513946533, "eval_runtime": 294.0646, "eval_samples_per_second": 1297.643, "eval_steps_per_second": 40.552, "step": 1908000 }, { "epoch": 1.0, "learning_rate": 1.8756678457221513e-05, "loss": 3.8771, "step": 1908224 }, { "epoch": 1.0, "learning_rate": 1.8748292509710993e-05, "loss": 3.8752, "step": 1908736 }, { "epoch": 1.0, "learning_rate": 1.8739906562200473e-05, "loss": 3.8845, "step": 1909248 }, { "epoch": 1.0, "learning_rate": 1.8731520614689953e-05, "loss": 3.8984, "step": 1909760 }, { "epoch": 1.0, "learning_rate": 1.8723134667179433e-05, "loss": 3.8919, "step": 1910272 }, { "epoch": 1.0, "learning_rate": 1.8714748719668913e-05, "loss": 3.8782, "step": 1910784 }, { "epoch": 1.0, "learning_rate": 1.8706362772158393e-05, "loss": 3.8954, "step": 1911296 }, { "epoch": 1.0, "learning_rate": 1.8697976824647873e-05, "loss": 3.8733, "step": 1911808 }, { "epoch": 1.0, "learning_rate": 1.8689607255941085e-05, "loss": 3.8862, "step": 1912320 }, { "epoch": 1.0, "learning_rate": 1.8681237687234294e-05, "loss": 3.8945, "step": 1912832 }, { "epoch": 1.0, "learning_rate": 1.8672851739723778e-05, "loss": 3.884, "step": 1913344 }, { "epoch": 1.0, "learning_rate": 1.8664465792213258e-05, "loss": 3.888, "step": 1913856 }, { "epoch": 1.0, "learning_rate": 1.8656096223506467e-05, "loss": 3.8907, "step": 1914368 }, { "epoch": 1.0, "learning_rate": 1.8647710275995947e-05, "loss": 3.8769, "step": 1914880 }, { "epoch": 1.0, "learning_rate": 1.8639324328485427e-05, "loss": 3.876, "step": 1915392 }, { "epoch": 1.0, "learning_rate": 1.8630938380974907e-05, "loss": 3.8738, "step": 1915904 }, { "epoch": 1.0, "learning_rate": 1.8622552433464387e-05, "loss": 3.8778, "step": 1916416 }, { "epoch": 1.0, "learning_rate": 1.8614166485953867e-05, "loss": 3.8807, "step": 1916928 }, { "epoch": 1.0, "learning_rate": 1.8605780538443347e-05, "loss": 3.8778, "step": 1917440 }, { "epoch": 1.0, "learning_rate": 1.859741096973656e-05, "loss": 3.8914, "step": 1917952 }, { "epoch": 1.0, "learning_rate": 1.8589025022226036e-05, "loss": 3.8982, "step": 1918464 }, { "epoch": 1.0, "learning_rate": 1.8580639074715516e-05, "loss": 3.8946, "step": 1918976 }, { "epoch": 1.0, "learning_rate": 1.8572253127204995e-05, "loss": 3.887, "step": 1919488 }, { "epoch": 1.0, "learning_rate": 1.856386717969448e-05, "loss": 3.883, "step": 1920000 }, { "epoch": 1.0, "learning_rate": 1.855548123218396e-05, "loss": 3.8894, "step": 1920512 }, { "epoch": 1.0, "learning_rate": 1.854709528467344e-05, "loss": 3.8846, "step": 1921024 }, { "epoch": 1.0, "learning_rate": 1.8538709337162915e-05, "loss": 3.8808, "step": 1921536 }, { "epoch": 1.0, "learning_rate": 1.8530323389652395e-05, "loss": 3.8776, "step": 1922048 }, { "epoch": 1.0, "learning_rate": 1.8521937442141875e-05, "loss": 3.8789, "step": 1922560 }, { "epoch": 1.0, "learning_rate": 1.8513551494631355e-05, "loss": 3.8788, "step": 1923072 }, { "epoch": 1.01, "learning_rate": 1.850516554712084e-05, "loss": 3.8785, "step": 1923584 }, { "epoch": 1.01, "learning_rate": 1.8496795978414048e-05, "loss": 3.887, "step": 1924096 }, { "epoch": 1.01, "learning_rate": 1.8488410030903528e-05, "loss": 3.8948, "step": 1924608 }, { "epoch": 1.01, "learning_rate": 1.8480024083393008e-05, "loss": 3.8844, "step": 1925120 }, { "epoch": 1.01, "learning_rate": 1.8471654514686217e-05, "loss": 3.885, "step": 1925632 }, { "epoch": 1.01, "learning_rate": 1.8463284945979432e-05, "loss": 3.8832, "step": 1926144 }, { "epoch": 1.01, "learning_rate": 1.8454898998468912e-05, "loss": 3.8916, "step": 1926656 }, { "epoch": 1.01, "learning_rate": 1.844651305095839e-05, "loss": 3.8747, "step": 1927168 }, { "epoch": 1.01, "learning_rate": 1.843812710344787e-05, "loss": 3.8817, "step": 1927680 }, { "epoch": 1.01, "learning_rate": 1.842974115593735e-05, "loss": 3.8715, "step": 1928192 }, { "epoch": 1.01, "learning_rate": 1.842135520842683e-05, "loss": 3.8829, "step": 1928704 }, { "epoch": 1.01, "learning_rate": 1.841296926091631e-05, "loss": 3.8827, "step": 1929216 }, { "epoch": 1.01, "learning_rate": 1.840458331340579e-05, "loss": 3.8826, "step": 1929728 }, { "epoch": 1.01, "learning_rate": 1.8396197365895272e-05, "loss": 3.8858, "step": 1930240 }, { "epoch": 1.01, "learning_rate": 1.838782779718848e-05, "loss": 3.8908, "step": 1930752 }, { "epoch": 1.01, "learning_rate": 1.837944184967796e-05, "loss": 3.8875, "step": 1931264 }, { "epoch": 1.01, "learning_rate": 1.837105590216744e-05, "loss": 3.8897, "step": 1931776 }, { "epoch": 1.01, "learning_rate": 1.836266995465692e-05, "loss": 3.8834, "step": 1932288 }, { "epoch": 1.01, "learning_rate": 1.83542840071464e-05, "loss": 3.8538, "step": 1932800 }, { "epoch": 1.01, "learning_rate": 1.834589805963588e-05, "loss": 3.8934, "step": 1933312 }, { "epoch": 1.01, "learning_rate": 1.833751211212536e-05, "loss": 3.8818, "step": 1933824 }, { "epoch": 1.01, "learning_rate": 1.832912616461484e-05, "loss": 3.8879, "step": 1934336 }, { "epoch": 1.01, "learning_rate": 1.832074021710432e-05, "loss": 3.8821, "step": 1934848 }, { "epoch": 1.01, "learning_rate": 1.83123542695938e-05, "loss": 3.8708, "step": 1935360 }, { "epoch": 1.01, "learning_rate": 1.830398470088701e-05, "loss": 3.8696, "step": 1935872 }, { "epoch": 1.01, "learning_rate": 1.8295598753376493e-05, "loss": 3.8749, "step": 1936384 }, { "epoch": 1.01, "learning_rate": 1.8287212805865973e-05, "loss": 3.8759, "step": 1936896 }, { "epoch": 1.01, "learning_rate": 1.8278826858355453e-05, "loss": 3.8696, "step": 1937408 }, { "epoch": 1.01, "learning_rate": 1.827044091084493e-05, "loss": 3.8951, "step": 1937920 }, { "epoch": 1.01, "learning_rate": 1.826205496333441e-05, "loss": 3.8771, "step": 1938432 }, { "epoch": 1.01, "learning_rate": 1.825366901582389e-05, "loss": 3.8621, "step": 1938944 }, { "epoch": 1.01, "learning_rate": 1.824528306831337e-05, "loss": 3.8937, "step": 1939456 }, { "epoch": 1.01, "learning_rate": 1.8236913499606582e-05, "loss": 3.8672, "step": 1939968 }, { "epoch": 1.01, "learning_rate": 1.8228527552096062e-05, "loss": 3.8684, "step": 1940480 }, { "epoch": 1.01, "learning_rate": 1.8220157983389275e-05, "loss": 3.8857, "step": 1940992 }, { "epoch": 1.01, "learning_rate": 1.821177203587875e-05, "loss": 3.878, "step": 1941504 }, { "epoch": 1.01, "learning_rate": 1.820338608836823e-05, "loss": 3.8764, "step": 1942016 }, { "epoch": 1.01, "learning_rate": 1.819500014085771e-05, "loss": 3.874, "step": 1942528 }, { "epoch": 1.01, "learning_rate": 1.8186630572150927e-05, "loss": 3.87, "step": 1943040 }, { "epoch": 1.01, "learning_rate": 1.8178244624640403e-05, "loss": 3.8827, "step": 1943552 }, { "epoch": 1.01, "learning_rate": 1.8169858677129883e-05, "loss": 3.8799, "step": 1944064 }, { "epoch": 1.01, "learning_rate": 1.8161472729619363e-05, "loss": 3.8806, "step": 1944576 }, { "epoch": 1.01, "learning_rate": 1.8153086782108843e-05, "loss": 3.8807, "step": 1945088 }, { "epoch": 1.01, "learning_rate": 1.8144700834598323e-05, "loss": 3.8842, "step": 1945600 }, { "epoch": 1.01, "learning_rate": 1.8136314887087803e-05, "loss": 3.8939, "step": 1946112 }, { "epoch": 1.01, "learning_rate": 1.8127928939577283e-05, "loss": 3.8676, "step": 1946624 }, { "epoch": 1.01, "learning_rate": 1.8119542992066763e-05, "loss": 3.8802, "step": 1947136 }, { "epoch": 1.01, "learning_rate": 1.8111157044556243e-05, "loss": 3.8883, "step": 1947648 }, { "epoch": 1.01, "learning_rate": 1.8102771097045723e-05, "loss": 3.8641, "step": 1948160 }, { "epoch": 1.01, "learning_rate": 1.8094401528338932e-05, "loss": 3.8792, "step": 1948672 }, { "epoch": 1.01, "learning_rate": 1.8086015580828412e-05, "loss": 3.8852, "step": 1949184 }, { "epoch": 1.01, "learning_rate": 1.8077629633317895e-05, "loss": 3.8894, "step": 1949696 }, { "epoch": 1.01, "learning_rate": 1.8069243685807375e-05, "loss": 3.89, "step": 1950208 }, { "epoch": 1.01, "learning_rate": 1.8060857738296855e-05, "loss": 3.8648, "step": 1950720 }, { "epoch": 1.01, "learning_rate": 1.8052488169590064e-05, "loss": 3.8617, "step": 1951232 }, { "epoch": 1.01, "learning_rate": 1.8044102222079544e-05, "loss": 3.8798, "step": 1951744 }, { "epoch": 1.01, "learning_rate": 1.8035716274569024e-05, "loss": 3.8812, "step": 1952256 }, { "epoch": 1.01, "learning_rate": 1.8027346705862237e-05, "loss": 3.875, "step": 1952768 }, { "epoch": 1.01, "learning_rate": 1.8018960758351717e-05, "loss": 3.8761, "step": 1953280 }, { "epoch": 1.02, "learning_rate": 1.8010574810841197e-05, "loss": 3.8759, "step": 1953792 }, { "epoch": 1.02, "learning_rate": 1.8002188863330677e-05, "loss": 3.8829, "step": 1954304 }, { "epoch": 1.02, "learning_rate": 1.7993802915820157e-05, "loss": 3.8787, "step": 1954816 }, { "epoch": 1.02, "learning_rate": 1.7985416968309637e-05, "loss": 3.8771, "step": 1955328 }, { "epoch": 1.02, "learning_rate": 1.7977031020799117e-05, "loss": 3.8799, "step": 1955840 }, { "epoch": 1.02, "learning_rate": 1.7968645073288597e-05, "loss": 3.8893, "step": 1956352 }, { "epoch": 1.02, "learning_rate": 1.7960259125778076e-05, "loss": 3.8828, "step": 1956864 }, { "epoch": 1.02, "learning_rate": 1.7951873178267556e-05, "loss": 3.8726, "step": 1957376 }, { "epoch": 1.02, "learning_rate": 1.7943487230757036e-05, "loss": 3.8739, "step": 1957888 }, { "epoch": 1.02, "learning_rate": 1.7935117662050246e-05, "loss": 3.8759, "step": 1958400 }, { "epoch": 1.02, "learning_rate": 1.7926731714539725e-05, "loss": 3.8862, "step": 1958912 }, { "epoch": 1.02, "learning_rate": 1.7918345767029205e-05, "loss": 3.8839, "step": 1959424 }, { "epoch": 1.02, "learning_rate": 1.790995981951869e-05, "loss": 3.8792, "step": 1959936 }, { "epoch": 1.02, "learning_rate": 1.790157387200817e-05, "loss": 3.8785, "step": 1960448 }, { "epoch": 1.02, "learning_rate": 1.7893187924497645e-05, "loss": 3.8717, "step": 1960960 }, { "epoch": 1.02, "learning_rate": 1.7884801976987125e-05, "loss": 3.8782, "step": 1961472 }, { "epoch": 1.02, "learning_rate": 1.7876416029476605e-05, "loss": 3.8725, "step": 1961984 }, { "epoch": 1.02, "learning_rate": 1.7868046460769818e-05, "loss": 3.8692, "step": 1962496 }, { "epoch": 1.02, "learning_rate": 1.7859660513259298e-05, "loss": 3.8858, "step": 1963008 }, { "epoch": 1.02, "learning_rate": 1.785129094455251e-05, "loss": 3.8706, "step": 1963520 }, { "epoch": 1.02, "learning_rate": 1.784290499704199e-05, "loss": 3.8749, "step": 1964032 }, { "epoch": 1.02, "learning_rate": 1.783451904953147e-05, "loss": 3.8725, "step": 1964544 }, { "epoch": 1.02, "learning_rate": 1.7826133102020947e-05, "loss": 3.8704, "step": 1965056 }, { "epoch": 1.02, "learning_rate": 1.7817747154510427e-05, "loss": 3.8842, "step": 1965568 }, { "epoch": 1.02, "learning_rate": 1.780936120699991e-05, "loss": 3.8732, "step": 1966080 }, { "epoch": 1.02, "learning_rate": 1.780097525948939e-05, "loss": 3.893, "step": 1966592 }, { "epoch": 1.02, "learning_rate": 1.779258931197887e-05, "loss": 3.8873, "step": 1967104 }, { "epoch": 1.02, "learning_rate": 1.778421974327208e-05, "loss": 3.8821, "step": 1967616 }, { "epoch": 1.02, "learning_rate": 1.777583379576156e-05, "loss": 3.8793, "step": 1968128 }, { "epoch": 1.02, "learning_rate": 1.776744784825104e-05, "loss": 3.8776, "step": 1968640 }, { "epoch": 1.02, "learning_rate": 1.775907827954425e-05, "loss": 3.875, "step": 1969152 }, { "epoch": 1.02, "learning_rate": 1.775069233203373e-05, "loss": 3.887, "step": 1969664 }, { "epoch": 1.02, "learning_rate": 1.774230638452321e-05, "loss": 3.8803, "step": 1970176 }, { "epoch": 1.02, "learning_rate": 1.773392043701269e-05, "loss": 3.8807, "step": 1970688 }, { "epoch": 1.02, "learning_rate": 1.772553448950217e-05, "loss": 3.8713, "step": 1971200 }, { "epoch": 1.02, "learning_rate": 1.771714854199165e-05, "loss": 3.8799, "step": 1971712 }, { "epoch": 1.02, "learning_rate": 1.7708778973284864e-05, "loss": 3.8795, "step": 1972224 }, { "epoch": 1.02, "learning_rate": 1.7700393025774344e-05, "loss": 3.8691, "step": 1972736 }, { "epoch": 1.02, "learning_rate": 1.7692007078263823e-05, "loss": 3.8833, "step": 1973248 }, { "epoch": 1.02, "learning_rate": 1.76836211307533e-05, "loss": 3.8641, "step": 1973760 }, { "epoch": 1.02, "learning_rate": 1.767523518324278e-05, "loss": 3.8956, "step": 1974272 }, { "epoch": 1.02, "learning_rate": 1.766684923573226e-05, "loss": 3.8762, "step": 1974784 }, { "epoch": 1.02, "learning_rate": 1.7658479667025472e-05, "loss": 3.8843, "step": 1975296 }, { "epoch": 1.02, "learning_rate": 1.7650093719514952e-05, "loss": 3.8695, "step": 1975808 }, { "epoch": 1.02, "learning_rate": 1.7641707772004432e-05, "loss": 3.8875, "step": 1976320 }, { "epoch": 1.02, "learning_rate": 1.7633321824493912e-05, "loss": 3.8779, "step": 1976832 }, { "epoch": 1.02, "learning_rate": 1.7624935876983392e-05, "loss": 3.8825, "step": 1977344 }, { "epoch": 1.02, "learning_rate": 1.7616549929472872e-05, "loss": 3.8781, "step": 1977856 }, { "epoch": 1.02, "learning_rate": 1.7608163981962352e-05, "loss": 3.8813, "step": 1978368 }, { "epoch": 1.02, "learning_rate": 1.759977803445183e-05, "loss": 3.8816, "step": 1978880 }, { "epoch": 1.02, "learning_rate": 1.7591408465745045e-05, "loss": 3.8994, "step": 1979392 }, { "epoch": 1.02, "learning_rate": 1.7583022518234525e-05, "loss": 3.8716, "step": 1979904 }, { "epoch": 1.02, "learning_rate": 1.7574652949527734e-05, "loss": 3.8875, "step": 1980416 }, { "epoch": 1.02, "learning_rate": 1.7566267002017214e-05, "loss": 3.8858, "step": 1980928 }, { "epoch": 1.02, "learning_rate": 1.7557881054506694e-05, "loss": 3.884, "step": 1981440 }, { "epoch": 1.02, "learning_rate": 1.7549495106996174e-05, "loss": 3.8729, "step": 1981952 }, { "epoch": 1.02, "learning_rate": 1.7541109159485657e-05, "loss": 3.884, "step": 1982464 }, { "epoch": 1.02, "learning_rate": 1.7532723211975133e-05, "loss": 3.8813, "step": 1982976 }, { "epoch": 1.02, "learning_rate": 1.7524337264464613e-05, "loss": 3.8762, "step": 1983488 }, { "epoch": 1.02, "learning_rate": 1.7515951316954093e-05, "loss": 3.8817, "step": 1984000 }, { "epoch": 1.03, "eval_loss": 3.9888546466827393, "eval_runtime": 295.3965, "eval_samples_per_second": 1291.793, "eval_steps_per_second": 40.369, "step": 1984320 }, { "epoch": 0.0, "learning_rate": 1.7507565369443573e-05, "loss": 3.8724, "step": 1984512 }, { "epoch": 0.0, "learning_rate": 1.7499179421933053e-05, "loss": 3.8684, "step": 1985024 }, { "epoch": 0.0, "learning_rate": 1.7490793474422533e-05, "loss": 3.8812, "step": 1985536 }, { "epoch": 0.0, "learning_rate": 1.7482407526912013e-05, "loss": 3.8918, "step": 1986048 }, { "epoch": 0.0, "learning_rate": 1.7474021579401493e-05, "loss": 3.8894, "step": 1986560 }, { "epoch": 0.0, "learning_rate": 1.7465635631890973e-05, "loss": 3.8778, "step": 1987072 }, { "epoch": 0.0, "learning_rate": 1.7457249684380453e-05, "loss": 3.8837, "step": 1987584 }, { "epoch": 0.0, "learning_rate": 1.7448863736869933e-05, "loss": 3.8725, "step": 1988096 }, { "epoch": 0.0, "learning_rate": 1.7440477789359413e-05, "loss": 3.8768, "step": 1988608 }, { "epoch": 0.0, "learning_rate": 1.7432091841848893e-05, "loss": 3.8893, "step": 1989120 }, { "epoch": 0.0, "learning_rate": 1.7423705894338373e-05, "loss": 3.8806, "step": 1989632 }, { "epoch": 0.0, "learning_rate": 1.7415319946827853e-05, "loss": 3.8881, "step": 1990144 }, { "epoch": 0.0, "learning_rate": 1.7406950378121065e-05, "loss": 3.8877, "step": 1990656 }, { "epoch": 0.0, "learning_rate": 1.7398564430610545e-05, "loss": 3.8716, "step": 1991168 }, { "epoch": 0.0, "learning_rate": 1.7390178483100022e-05, "loss": 3.8716, "step": 1991680 }, { "epoch": 0.0, "learning_rate": 1.7381792535589502e-05, "loss": 3.8656, "step": 1992192 }, { "epoch": 0.0, "learning_rate": 1.7373406588078982e-05, "loss": 3.8769, "step": 1992704 }, { "epoch": 0.0, "learning_rate": 1.7365020640568465e-05, "loss": 3.8782, "step": 1993216 }, { "epoch": 0.0, "learning_rate": 1.7356634693057945e-05, "loss": 3.8688, "step": 1993728 }, { "epoch": 0.0, "learning_rate": 1.7348248745547425e-05, "loss": 3.885, "step": 1994240 }, { "epoch": 0.0, "learning_rate": 1.73398627980369e-05, "loss": 3.8927, "step": 1994752 }, { "epoch": 0.0, "learning_rate": 1.7331493229330114e-05, "loss": 3.887, "step": 1995264 }, { "epoch": 0.0, "learning_rate": 1.7323107281819594e-05, "loss": 3.8847, "step": 1995776 }, { "epoch": 0.0, "learning_rate": 1.7314721334309074e-05, "loss": 3.8795, "step": 1996288 }, { "epoch": 0.0, "learning_rate": 1.7306335386798554e-05, "loss": 3.8847, "step": 1996800 }, { "epoch": 0.0, "learning_rate": 1.7297949439288034e-05, "loss": 3.882, "step": 1997312 }, { "epoch": 0.0, "learning_rate": 1.7289563491777514e-05, "loss": 3.8736, "step": 1997824 }, { "epoch": 0.0, "learning_rate": 1.7281193923070726e-05, "loss": 3.8705, "step": 1998336 }, { "epoch": 0.0, "learning_rate": 1.7272807975560203e-05, "loss": 3.8768, "step": 1998848 }, { "epoch": 0.0, "learning_rate": 1.7264422028049683e-05, "loss": 3.8732, "step": 1999360 }, { "epoch": 0.01, "learning_rate": 1.7256036080539166e-05, "loss": 3.8762, "step": 1999872 }, { "epoch": 0.01, "learning_rate": 1.7247650133028646e-05, "loss": 3.8822, "step": 2000384 }, { "epoch": 0.01, "learning_rate": 1.7239264185518126e-05, "loss": 3.8858, "step": 2000896 }, { "epoch": 0.01, "learning_rate": 1.7230878238007606e-05, "loss": 3.8838, "step": 2001408 }, { "epoch": 0.01, "learning_rate": 1.7222508669300815e-05, "loss": 3.8742, "step": 2001920 }, { "epoch": 0.01, "learning_rate": 1.7214139100594028e-05, "loss": 3.8836, "step": 2002432 }, { "epoch": 0.01, "learning_rate": 1.7205753153083508e-05, "loss": 3.8869, "step": 2002944 }, { "epoch": 0.01, "learning_rate": 1.7197367205572988e-05, "loss": 3.8653, "step": 2003456 }, { "epoch": 0.01, "learning_rate": 1.7188981258062467e-05, "loss": 3.8785, "step": 2003968 }, { "epoch": 0.01, "learning_rate": 1.7180595310551947e-05, "loss": 3.867, "step": 2004480 }, { "epoch": 0.01, "learning_rate": 1.7172209363041427e-05, "loss": 3.8767, "step": 2004992 }, { "epoch": 0.01, "learning_rate": 1.7163823415530907e-05, "loss": 3.874, "step": 2005504 }, { "epoch": 0.01, "learning_rate": 1.7155437468020384e-05, "loss": 3.8768, "step": 2006016 }, { "epoch": 0.01, "learning_rate": 1.7147051520509867e-05, "loss": 3.8798, "step": 2006528 }, { "epoch": 0.01, "learning_rate": 1.7138665572999347e-05, "loss": 3.8871, "step": 2007040 }, { "epoch": 0.01, "learning_rate": 1.7130296004292556e-05, "loss": 3.8849, "step": 2007552 }, { "epoch": 0.01, "learning_rate": 1.7121910056782036e-05, "loss": 3.8871, "step": 2008064 }, { "epoch": 0.01, "learning_rate": 1.7113524109271516e-05, "loss": 3.8765, "step": 2008576 }, { "epoch": 0.01, "learning_rate": 1.710515454056473e-05, "loss": 3.8514, "step": 2009088 }, { "epoch": 0.01, "learning_rate": 1.709676859305421e-05, "loss": 3.8888, "step": 2009600 }, { "epoch": 0.01, "learning_rate": 1.708838264554369e-05, "loss": 3.8792, "step": 2010112 }, { "epoch": 0.01, "learning_rate": 1.707999669803317e-05, "loss": 3.8838, "step": 2010624 }, { "epoch": 0.01, "learning_rate": 1.707161075052265e-05, "loss": 3.8763, "step": 2011136 }, { "epoch": 0.01, "learning_rate": 1.706322480301213e-05, "loss": 3.8692, "step": 2011648 }, { "epoch": 0.01, "learning_rate": 1.705483885550161e-05, "loss": 3.864, "step": 2012160 }, { "epoch": 0.01, "learning_rate": 1.704646928679482e-05, "loss": 3.8691, "step": 2012672 }, { "epoch": 0.01, "learning_rate": 1.70380833392843e-05, "loss": 3.8768, "step": 2013184 }, { "epoch": 0.01, "learning_rate": 1.702969739177378e-05, "loss": 3.8618, "step": 2013696 }, { "epoch": 0.01, "learning_rate": 1.702131144426326e-05, "loss": 3.891, "step": 2014208 }, { "epoch": 0.01, "learning_rate": 1.7012925496752737e-05, "loss": 3.8737, "step": 2014720 }, { "epoch": 0.01, "learning_rate": 1.7004539549242217e-05, "loss": 3.8593, "step": 2015232 }, { "epoch": 0.01, "learning_rate": 1.6996153601731697e-05, "loss": 3.8844, "step": 2015744 }, { "epoch": 0.01, "learning_rate": 1.6987767654221177e-05, "loss": 3.8625, "step": 2016256 }, { "epoch": 0.01, "learning_rate": 1.697938170671066e-05, "loss": 3.8639, "step": 2016768 }, { "epoch": 0.01, "learning_rate": 1.697099575920014e-05, "loss": 3.88, "step": 2017280 }, { "epoch": 0.01, "learning_rate": 1.696260981168962e-05, "loss": 3.8759, "step": 2017792 }, { "epoch": 0.01, "learning_rate": 1.6954223864179097e-05, "loss": 3.8687, "step": 2018304 }, { "epoch": 0.01, "learning_rate": 1.694585429547231e-05, "loss": 3.8681, "step": 2018816 }, { "epoch": 0.01, "learning_rate": 1.693746834796179e-05, "loss": 3.8661, "step": 2019328 }, { "epoch": 0.01, "learning_rate": 1.692908240045127e-05, "loss": 3.8739, "step": 2019840 }, { "epoch": 0.01, "learning_rate": 1.692069645294075e-05, "loss": 3.8819, "step": 2020352 }, { "epoch": 0.01, "learning_rate": 1.6912326884233962e-05, "loss": 3.8743, "step": 2020864 }, { "epoch": 0.01, "learning_rate": 1.6903940936723442e-05, "loss": 3.8755, "step": 2021376 }, { "epoch": 0.01, "learning_rate": 1.689555498921292e-05, "loss": 3.8752, "step": 2021888 }, { "epoch": 0.01, "learning_rate": 1.68871690417024e-05, "loss": 3.8894, "step": 2022400 }, { "epoch": 0.01, "learning_rate": 1.6878783094191882e-05, "loss": 3.8664, "step": 2022912 }, { "epoch": 0.01, "learning_rate": 1.687039714668136e-05, "loss": 3.8799, "step": 2023424 }, { "epoch": 0.01, "learning_rate": 1.686202757797457e-05, "loss": 3.8793, "step": 2023936 }, { "epoch": 0.01, "learning_rate": 1.685364163046405e-05, "loss": 3.864, "step": 2024448 }, { "epoch": 0.01, "learning_rate": 1.6845272061757263e-05, "loss": 3.8744, "step": 2024960 }, { "epoch": 0.01, "learning_rate": 1.6836886114246743e-05, "loss": 3.8803, "step": 2025472 }, { "epoch": 0.01, "learning_rate": 1.6828500166736223e-05, "loss": 3.8836, "step": 2025984 }, { "epoch": 0.01, "learning_rate": 1.6820114219225703e-05, "loss": 3.8868, "step": 2026496 }, { "epoch": 0.01, "learning_rate": 1.6811744650518916e-05, "loss": 3.8571, "step": 2027008 }, { "epoch": 0.01, "learning_rate": 1.6803358703008392e-05, "loss": 3.8602, "step": 2027520 }, { "epoch": 0.01, "learning_rate": 1.6794972755497872e-05, "loss": 3.874, "step": 2028032 }, { "epoch": 0.01, "learning_rate": 1.6786586807987352e-05, "loss": 3.8773, "step": 2028544 }, { "epoch": 0.01, "learning_rate": 1.6778200860476835e-05, "loss": 3.868, "step": 2029056 }, { "epoch": 0.01, "learning_rate": 1.6769831291770044e-05, "loss": 3.8725, "step": 2029568 }, { "epoch": 0.01, "learning_rate": 1.6761445344259524e-05, "loss": 3.8717, "step": 2030080 }, { "epoch": 0.02, "learning_rate": 1.6753059396749004e-05, "loss": 3.8782, "step": 2030592 }, { "epoch": 0.02, "learning_rate": 1.6744689828042213e-05, "loss": 3.8701, "step": 2031104 }, { "epoch": 0.02, "learning_rate": 1.6736303880531697e-05, "loss": 3.8702, "step": 2031616 }, { "epoch": 0.02, "learning_rate": 1.6727917933021177e-05, "loss": 3.879, "step": 2032128 }, { "epoch": 0.02, "learning_rate": 1.6719531985510657e-05, "loss": 3.8834, "step": 2032640 }, { "epoch": 0.02, "learning_rate": 1.6711146038000137e-05, "loss": 3.8791, "step": 2033152 }, { "epoch": 0.02, "learning_rate": 1.6702760090489617e-05, "loss": 3.864, "step": 2033664 }, { "epoch": 0.02, "learning_rate": 1.6694374142979097e-05, "loss": 3.8669, "step": 2034176 }, { "epoch": 0.02, "learning_rate": 1.6685988195468573e-05, "loss": 3.8747, "step": 2034688 }, { "epoch": 0.02, "learning_rate": 1.6677602247958053e-05, "loss": 3.879, "step": 2035200 }, { "epoch": 0.02, "learning_rate": 1.6669216300447536e-05, "loss": 3.8805, "step": 2035712 }, { "epoch": 0.02, "learning_rate": 1.666084673174075e-05, "loss": 3.8733, "step": 2036224 }, { "epoch": 0.02, "learning_rate": 1.6652460784230226e-05, "loss": 3.8738, "step": 2036736 }, { "epoch": 0.02, "learning_rate": 1.6644074836719705e-05, "loss": 3.8655, "step": 2037248 }, { "epoch": 0.02, "learning_rate": 1.6635688889209185e-05, "loss": 3.8723, "step": 2037760 }, { "epoch": 0.02, "learning_rate": 1.6627302941698665e-05, "loss": 3.8681, "step": 2038272 }, { "epoch": 0.02, "learning_rate": 1.661894975179561e-05, "loss": 3.8663, "step": 2038784 }, { "epoch": 0.02, "learning_rate": 1.661056380428509e-05, "loss": 3.8793, "step": 2039296 }, { "epoch": 0.02, "learning_rate": 1.660217785677457e-05, "loss": 3.8694, "step": 2039808 }, { "epoch": 0.02, "learning_rate": 1.6593791909264047e-05, "loss": 3.8665, "step": 2040320 }, { "epoch": 0.02, "learning_rate": 1.6585405961753527e-05, "loss": 3.8668, "step": 2040832 }, { "epoch": 0.02, "learning_rate": 1.6577020014243007e-05, "loss": 3.8658, "step": 2041344 }, { "epoch": 0.02, "learning_rate": 1.656863406673249e-05, "loss": 3.8788, "step": 2041856 }, { "epoch": 0.02, "learning_rate": 1.656024811922197e-05, "loss": 3.873, "step": 2042368 }, { "epoch": 0.02, "learning_rate": 1.655187855051518e-05, "loss": 3.8824, "step": 2042880 }, { "epoch": 0.02, "learning_rate": 1.654349260300466e-05, "loss": 3.8811, "step": 2043392 }, { "epoch": 0.02, "learning_rate": 1.653510665549414e-05, "loss": 3.8784, "step": 2043904 }, { "epoch": 0.02, "learning_rate": 1.652672070798362e-05, "loss": 3.875, "step": 2044416 }, { "epoch": 0.02, "learning_rate": 1.65183347604731e-05, "loss": 3.8719, "step": 2044928 }, { "epoch": 0.02, "learning_rate": 1.650994881296258e-05, "loss": 3.8717, "step": 2045440 }, { "epoch": 0.02, "learning_rate": 1.650156286545206e-05, "loss": 3.8784, "step": 2045952 }, { "epoch": 0.02, "learning_rate": 1.649317691794154e-05, "loss": 3.8716, "step": 2046464 }, { "epoch": 0.02, "learning_rate": 1.648479097043102e-05, "loss": 3.8798, "step": 2046976 }, { "epoch": 0.02, "learning_rate": 1.6476421401724228e-05, "loss": 3.8643, "step": 2047488 }, { "epoch": 0.02, "learning_rate": 1.6468051833017444e-05, "loss": 3.8779, "step": 2048000 }, { "epoch": 0.02, "learning_rate": 1.6459665885506924e-05, "loss": 3.8706, "step": 2048512 }, { "epoch": 0.02, "learning_rate": 1.6451279937996404e-05, "loss": 3.8679, "step": 2049024 }, { "epoch": 0.02, "learning_rate": 1.644289399048588e-05, "loss": 3.8748, "step": 2049536 }, { "epoch": 0.02, "learning_rate": 1.643450804297536e-05, "loss": 3.8569, "step": 2050048 }, { "epoch": 0.02, "learning_rate": 1.642612209546484e-05, "loss": 3.8938, "step": 2050560 }, { "epoch": 0.02, "learning_rate": 1.641773614795432e-05, "loss": 3.8705, "step": 2051072 }, { "epoch": 0.02, "learning_rate": 1.64093502004438e-05, "loss": 3.8805, "step": 2051584 }, { "epoch": 0.02, "learning_rate": 1.6400980631737013e-05, "loss": 3.8656, "step": 2052096 }, { "epoch": 0.02, "learning_rate": 1.6392594684226493e-05, "loss": 3.8794, "step": 2052608 }, { "epoch": 0.02, "learning_rate": 1.6384208736715973e-05, "loss": 3.8746, "step": 2053120 }, { "epoch": 0.02, "learning_rate": 1.6375822789205452e-05, "loss": 3.88, "step": 2053632 }, { "epoch": 0.02, "learning_rate": 1.636745322049866e-05, "loss": 3.8736, "step": 2054144 }, { "epoch": 0.02, "learning_rate": 1.6359067272988145e-05, "loss": 3.8749, "step": 2054656 }, { "epoch": 0.02, "learning_rate": 1.6350681325477625e-05, "loss": 3.8778, "step": 2055168 }, { "epoch": 0.02, "learning_rate": 1.6342295377967105e-05, "loss": 3.8964, "step": 2055680 }, { "epoch": 0.02, "learning_rate": 1.6333925809260314e-05, "loss": 3.8635, "step": 2056192 }, { "epoch": 0.02, "learning_rate": 1.6325539861749794e-05, "loss": 3.8871, "step": 2056704 }, { "epoch": 0.02, "learning_rate": 1.6317153914239274e-05, "loss": 3.8822, "step": 2057216 }, { "epoch": 0.02, "learning_rate": 1.6308767966728754e-05, "loss": 3.8775, "step": 2057728 }, { "epoch": 0.02, "learning_rate": 1.6300382019218234e-05, "loss": 3.87, "step": 2058240 }, { "epoch": 0.02, "learning_rate": 1.6291996071707714e-05, "loss": 3.879, "step": 2058752 }, { "epoch": 0.02, "learning_rate": 1.6283610124197194e-05, "loss": 3.8759, "step": 2059264 }, { "epoch": 0.02, "learning_rate": 1.6275224176686674e-05, "loss": 3.8753, "step": 2059776 }, { "epoch": 0.02, "learning_rate": 1.6266838229176154e-05, "loss": 3.8741, "step": 2060288 }, { "epoch": 0.03, "eval_loss": 3.986988067626953, "eval_runtime": 295.4886, "eval_samples_per_second": 1291.39, "eval_steps_per_second": 40.357, "step": 2060640 }, { "epoch": 1.0, "learning_rate": 1.6258468660469363e-05, "loss": 3.8694, "step": 2060800 }, { "epoch": 1.0, "learning_rate": 1.6250082712958846e-05, "loss": 3.8641, "step": 2061312 }, { "epoch": 1.0, "learning_rate": 1.6241713144252055e-05, "loss": 3.8736, "step": 2061824 }, { "epoch": 1.0, "learning_rate": 1.6233327196741535e-05, "loss": 3.8865, "step": 2062336 }, { "epoch": 1.0, "learning_rate": 1.6224941249231015e-05, "loss": 3.8845, "step": 2062848 }, { "epoch": 1.0, "learning_rate": 1.6216555301720495e-05, "loss": 3.8724, "step": 2063360 }, { "epoch": 1.0, "learning_rate": 1.6208169354209975e-05, "loss": 3.8824, "step": 2063872 }, { "epoch": 1.0, "learning_rate": 1.6199783406699455e-05, "loss": 3.8705, "step": 2064384 }, { "epoch": 1.0, "learning_rate": 1.6191397459188938e-05, "loss": 3.8709, "step": 2064896 }, { "epoch": 1.0, "learning_rate": 1.6183011511678415e-05, "loss": 3.8808, "step": 2065408 }, { "epoch": 1.0, "learning_rate": 1.6174641942971627e-05, "loss": 3.8849, "step": 2065920 }, { "epoch": 1.0, "learning_rate": 1.6166272374264836e-05, "loss": 3.8815, "step": 2066432 }, { "epoch": 1.0, "learning_rate": 1.6157902805558052e-05, "loss": 3.8782, "step": 2066944 }, { "epoch": 1.0, "learning_rate": 1.614951685804753e-05, "loss": 3.8672, "step": 2067456 }, { "epoch": 1.0, "learning_rate": 1.614113091053701e-05, "loss": 3.8704, "step": 2067968 }, { "epoch": 1.0, "learning_rate": 1.613274496302649e-05, "loss": 3.8576, "step": 2068480 }, { "epoch": 1.0, "learning_rate": 1.612435901551597e-05, "loss": 3.8746, "step": 2068992 }, { "epoch": 1.0, "learning_rate": 1.611597306800545e-05, "loss": 3.8731, "step": 2069504 }, { "epoch": 1.0, "learning_rate": 1.610758712049493e-05, "loss": 3.8645, "step": 2070016 }, { "epoch": 1.0, "learning_rate": 1.609920117298441e-05, "loss": 3.8783, "step": 2070528 }, { "epoch": 1.0, "learning_rate": 1.609081522547389e-05, "loss": 3.8884, "step": 2071040 }, { "epoch": 1.0, "learning_rate": 1.608242927796337e-05, "loss": 3.8821, "step": 2071552 }, { "epoch": 1.0, "learning_rate": 1.607404333045285e-05, "loss": 3.8818, "step": 2072064 }, { "epoch": 1.0, "learning_rate": 1.606565738294233e-05, "loss": 3.8746, "step": 2072576 }, { "epoch": 1.0, "learning_rate": 1.6057287814235537e-05, "loss": 3.8788, "step": 2073088 }, { "epoch": 1.0, "learning_rate": 1.6048901866725017e-05, "loss": 3.8763, "step": 2073600 }, { "epoch": 1.0, "learning_rate": 1.60405159192145e-05, "loss": 3.868, "step": 2074112 }, { "epoch": 1.0, "learning_rate": 1.603212997170398e-05, "loss": 3.8638, "step": 2074624 }, { "epoch": 1.0, "learning_rate": 1.602376040299719e-05, "loss": 3.8736, "step": 2075136 }, { "epoch": 1.0, "learning_rate": 1.601537445548667e-05, "loss": 3.8687, "step": 2075648 }, { "epoch": 1.01, "learning_rate": 1.6007004886779882e-05, "loss": 3.8758, "step": 2076160 }, { "epoch": 1.01, "learning_rate": 1.5998618939269362e-05, "loss": 3.8733, "step": 2076672 }, { "epoch": 1.01, "learning_rate": 1.5990232991758842e-05, "loss": 3.8755, "step": 2077184 }, { "epoch": 1.01, "learning_rate": 1.5981847044248322e-05, "loss": 3.8849, "step": 2077696 }, { "epoch": 1.01, "learning_rate": 1.5973461096737802e-05, "loss": 3.8684, "step": 2078208 }, { "epoch": 1.01, "learning_rate": 1.596509152803101e-05, "loss": 3.8812, "step": 2078720 }, { "epoch": 1.01, "learning_rate": 1.595670558052049e-05, "loss": 3.8826, "step": 2079232 }, { "epoch": 1.01, "learning_rate": 1.594831963300997e-05, "loss": 3.8593, "step": 2079744 }, { "epoch": 1.01, "learning_rate": 1.5939933685499454e-05, "loss": 3.8761, "step": 2080256 }, { "epoch": 1.01, "learning_rate": 1.5931564116792664e-05, "loss": 3.8641, "step": 2080768 }, { "epoch": 1.01, "learning_rate": 1.5923178169282143e-05, "loss": 3.867, "step": 2081280 }, { "epoch": 1.01, "learning_rate": 1.5914792221771623e-05, "loss": 3.8717, "step": 2081792 }, { "epoch": 1.01, "learning_rate": 1.5906406274261103e-05, "loss": 3.8735, "step": 2082304 }, { "epoch": 1.01, "learning_rate": 1.5898020326750583e-05, "loss": 3.8765, "step": 2082816 }, { "epoch": 1.01, "learning_rate": 1.5889634379240063e-05, "loss": 3.8813, "step": 2083328 }, { "epoch": 1.01, "learning_rate": 1.5881248431729543e-05, "loss": 3.8805, "step": 2083840 }, { "epoch": 1.01, "learning_rate": 1.5872862484219023e-05, "loss": 3.8807, "step": 2084352 }, { "epoch": 1.01, "learning_rate": 1.5864492915512236e-05, "loss": 3.8735, "step": 2084864 }, { "epoch": 1.01, "learning_rate": 1.5856106968001716e-05, "loss": 3.8468, "step": 2085376 }, { "epoch": 1.01, "learning_rate": 1.5847721020491192e-05, "loss": 3.8822, "step": 2085888 }, { "epoch": 1.01, "learning_rate": 1.5839335072980676e-05, "loss": 3.8741, "step": 2086400 }, { "epoch": 1.01, "learning_rate": 1.5830965504273888e-05, "loss": 3.8824, "step": 2086912 }, { "epoch": 1.01, "learning_rate": 1.582261231437083e-05, "loss": 3.8705, "step": 2087424 }, { "epoch": 1.01, "learning_rate": 1.5814226366860306e-05, "loss": 3.8613, "step": 2087936 }, { "epoch": 1.01, "learning_rate": 1.5805840419349786e-05, "loss": 3.8678, "step": 2088448 }, { "epoch": 1.01, "learning_rate": 1.5797470850643002e-05, "loss": 3.8585, "step": 2088960 }, { "epoch": 1.01, "learning_rate": 1.578908490313248e-05, "loss": 3.8735, "step": 2089472 }, { "epoch": 1.01, "learning_rate": 1.578069895562196e-05, "loss": 3.8534, "step": 2089984 }, { "epoch": 1.01, "learning_rate": 1.577231300811144e-05, "loss": 3.8898, "step": 2090496 }, { "epoch": 1.01, "learning_rate": 1.576392706060092e-05, "loss": 3.8709, "step": 2091008 }, { "epoch": 1.01, "learning_rate": 1.57555411130904e-05, "loss": 3.8522, "step": 2091520 }, { "epoch": 1.01, "learning_rate": 1.574715516557988e-05, "loss": 3.8794, "step": 2092032 }, { "epoch": 1.01, "learning_rate": 1.5738769218069362e-05, "loss": 3.8607, "step": 2092544 }, { "epoch": 1.01, "learning_rate": 1.573038327055884e-05, "loss": 3.8614, "step": 2093056 }, { "epoch": 1.01, "learning_rate": 1.5721997323048318e-05, "loss": 3.8709, "step": 2093568 }, { "epoch": 1.01, "learning_rate": 1.571362775434153e-05, "loss": 3.8683, "step": 2094080 }, { "epoch": 1.01, "learning_rate": 1.570524180683101e-05, "loss": 3.8655, "step": 2094592 }, { "epoch": 1.01, "learning_rate": 1.5696855859320487e-05, "loss": 3.8689, "step": 2095104 }, { "epoch": 1.01, "learning_rate": 1.568846991180997e-05, "loss": 3.8574, "step": 2095616 }, { "epoch": 1.01, "learning_rate": 1.568008396429945e-05, "loss": 3.8698, "step": 2096128 }, { "epoch": 1.01, "learning_rate": 1.567169801678893e-05, "loss": 3.8752, "step": 2096640 }, { "epoch": 1.01, "learning_rate": 1.566331206927841e-05, "loss": 3.8694, "step": 2097152 }, { "epoch": 1.01, "learning_rate": 1.565492612176789e-05, "loss": 3.8742, "step": 2097664 }, { "epoch": 1.01, "learning_rate": 1.5646540174257367e-05, "loss": 3.8657, "step": 2098176 }, { "epoch": 1.01, "learning_rate": 1.5638154226746847e-05, "loss": 3.8898, "step": 2098688 }, { "epoch": 1.01, "learning_rate": 1.562976827923633e-05, "loss": 3.8592, "step": 2099200 }, { "epoch": 1.01, "learning_rate": 1.562138233172581e-05, "loss": 3.8759, "step": 2099712 }, { "epoch": 1.01, "learning_rate": 1.561301276301902e-05, "loss": 3.8656, "step": 2100224 }, { "epoch": 1.01, "learning_rate": 1.56046268155085e-05, "loss": 3.866, "step": 2100736 }, { "epoch": 1.01, "learning_rate": 1.5596257246801712e-05, "loss": 3.8689, "step": 2101248 }, { "epoch": 1.01, "learning_rate": 1.5587871299291192e-05, "loss": 3.8772, "step": 2101760 }, { "epoch": 1.01, "learning_rate": 1.5579485351780672e-05, "loss": 3.88, "step": 2102272 }, { "epoch": 1.01, "learning_rate": 1.557109940427015e-05, "loss": 3.8797, "step": 2102784 }, { "epoch": 1.01, "learning_rate": 1.556271345675963e-05, "loss": 3.8545, "step": 2103296 }, { "epoch": 1.01, "learning_rate": 1.555434388805284e-05, "loss": 3.8568, "step": 2103808 }, { "epoch": 1.01, "learning_rate": 1.554595794054232e-05, "loss": 3.869, "step": 2104320 }, { "epoch": 1.01, "learning_rate": 1.55375719930318e-05, "loss": 3.8749, "step": 2104832 }, { "epoch": 1.01, "learning_rate": 1.5529186045521284e-05, "loss": 3.8637, "step": 2105344 }, { "epoch": 1.01, "learning_rate": 1.5520816476814493e-05, "loss": 3.8677, "step": 2105856 }, { "epoch": 1.01, "learning_rate": 1.5512430529303973e-05, "loss": 3.8706, "step": 2106368 }, { "epoch": 1.02, "learning_rate": 1.5504044581793453e-05, "loss": 3.8696, "step": 2106880 }, { "epoch": 1.02, "learning_rate": 1.5495675013086665e-05, "loss": 3.8682, "step": 2107392 }, { "epoch": 1.02, "learning_rate": 1.5487289065576145e-05, "loss": 3.867, "step": 2107904 }, { "epoch": 1.02, "learning_rate": 1.5478903118065625e-05, "loss": 3.8727, "step": 2108416 }, { "epoch": 1.02, "learning_rate": 1.5470517170555105e-05, "loss": 3.877, "step": 2108928 }, { "epoch": 1.02, "learning_rate": 1.5462131223044585e-05, "loss": 3.8795, "step": 2109440 }, { "epoch": 1.02, "learning_rate": 1.5453745275534065e-05, "loss": 3.8581, "step": 2109952 }, { "epoch": 1.02, "learning_rate": 1.5445359328023545e-05, "loss": 3.8606, "step": 2110464 }, { "epoch": 1.02, "learning_rate": 1.5436973380513022e-05, "loss": 3.8699, "step": 2110976 }, { "epoch": 1.02, "learning_rate": 1.5428587433002502e-05, "loss": 3.8721, "step": 2111488 }, { "epoch": 1.02, "learning_rate": 1.5420217864295718e-05, "loss": 3.8775, "step": 2112000 }, { "epoch": 1.02, "learning_rate": 1.5411831916785198e-05, "loss": 3.8686, "step": 2112512 }, { "epoch": 1.02, "learning_rate": 1.5403445969274674e-05, "loss": 3.8707, "step": 2113024 }, { "epoch": 1.02, "learning_rate": 1.5395060021764154e-05, "loss": 3.862, "step": 2113536 }, { "epoch": 1.02, "learning_rate": 1.5386674074253634e-05, "loss": 3.8653, "step": 2114048 }, { "epoch": 1.02, "learning_rate": 1.5378304505546847e-05, "loss": 3.8654, "step": 2114560 }, { "epoch": 1.02, "learning_rate": 1.5369918558036326e-05, "loss": 3.8624, "step": 2115072 }, { "epoch": 1.02, "learning_rate": 1.5361532610525806e-05, "loss": 3.8708, "step": 2115584 }, { "epoch": 1.02, "learning_rate": 1.5353146663015286e-05, "loss": 3.8658, "step": 2116096 }, { "epoch": 1.02, "learning_rate": 1.5344777094308495e-05, "loss": 3.8621, "step": 2116608 }, { "epoch": 1.02, "learning_rate": 1.5336391146797975e-05, "loss": 3.864, "step": 2117120 }, { "epoch": 1.02, "learning_rate": 1.5328005199287455e-05, "loss": 3.8594, "step": 2117632 }, { "epoch": 1.02, "learning_rate": 1.531961925177694e-05, "loss": 3.874, "step": 2118144 }, { "epoch": 1.02, "learning_rate": 1.531123330426642e-05, "loss": 3.8682, "step": 2118656 }, { "epoch": 1.02, "learning_rate": 1.5302863735559628e-05, "loss": 3.8775, "step": 2119168 }, { "epoch": 1.02, "learning_rate": 1.5294477788049108e-05, "loss": 3.8729, "step": 2119680 }, { "epoch": 1.02, "learning_rate": 1.5286091840538588e-05, "loss": 3.876, "step": 2120192 }, { "epoch": 1.02, "learning_rate": 1.5277705893028068e-05, "loss": 3.8717, "step": 2120704 }, { "epoch": 1.02, "learning_rate": 1.5269319945517548e-05, "loss": 3.8618, "step": 2121216 }, { "epoch": 1.02, "learning_rate": 1.526093399800703e-05, "loss": 3.8751, "step": 2121728 }, { "epoch": 1.02, "learning_rate": 1.5252548050496508e-05, "loss": 3.8691, "step": 2122240 }, { "epoch": 1.02, "learning_rate": 1.5244162102985987e-05, "loss": 3.8655, "step": 2122752 }, { "epoch": 1.02, "learning_rate": 1.5235776155475467e-05, "loss": 3.8763, "step": 2123264 }, { "epoch": 1.02, "learning_rate": 1.5227406586768678e-05, "loss": 3.8651, "step": 2123776 }, { "epoch": 1.02, "learning_rate": 1.521903701806189e-05, "loss": 3.8687, "step": 2124288 }, { "epoch": 1.02, "learning_rate": 1.521065107055137e-05, "loss": 3.8644, "step": 2124800 }, { "epoch": 1.02, "learning_rate": 1.520226512304085e-05, "loss": 3.8639, "step": 2125312 }, { "epoch": 1.02, "learning_rate": 1.5193879175530329e-05, "loss": 3.8695, "step": 2125824 }, { "epoch": 1.02, "learning_rate": 1.5185509606823541e-05, "loss": 3.8593, "step": 2126336 }, { "epoch": 1.02, "learning_rate": 1.5177123659313023e-05, "loss": 3.885, "step": 2126848 }, { "epoch": 1.02, "learning_rate": 1.51687377118025e-05, "loss": 3.8676, "step": 2127360 }, { "epoch": 1.02, "learning_rate": 1.516035176429198e-05, "loss": 3.8748, "step": 2127872 }, { "epoch": 1.02, "learning_rate": 1.5151965816781461e-05, "loss": 3.8608, "step": 2128384 }, { "epoch": 1.02, "learning_rate": 1.5143596248074674e-05, "loss": 3.8737, "step": 2128896 }, { "epoch": 1.02, "learning_rate": 1.513521030056415e-05, "loss": 3.871, "step": 2129408 }, { "epoch": 1.02, "learning_rate": 1.5126824353053632e-05, "loss": 3.8743, "step": 2129920 }, { "epoch": 1.02, "learning_rate": 1.5118438405543112e-05, "loss": 3.8696, "step": 2130432 }, { "epoch": 1.02, "learning_rate": 1.5110052458032592e-05, "loss": 3.8689, "step": 2130944 }, { "epoch": 1.02, "learning_rate": 1.5101682889325803e-05, "loss": 3.8705, "step": 2131456 }, { "epoch": 1.02, "learning_rate": 1.5093296941815283e-05, "loss": 3.8911, "step": 2131968 }, { "epoch": 1.02, "learning_rate": 1.5084910994304763e-05, "loss": 3.8635, "step": 2132480 }, { "epoch": 1.02, "learning_rate": 1.5076525046794242e-05, "loss": 3.8812, "step": 2132992 }, { "epoch": 1.02, "learning_rate": 1.5068155478087453e-05, "loss": 3.88, "step": 2133504 }, { "epoch": 1.02, "learning_rate": 1.5059769530576933e-05, "loss": 3.8683, "step": 2134016 }, { "epoch": 1.02, "learning_rate": 1.5051383583066415e-05, "loss": 3.8721, "step": 2134528 }, { "epoch": 1.02, "learning_rate": 1.5042997635555895e-05, "loss": 3.869, "step": 2135040 }, { "epoch": 1.02, "learning_rate": 1.5034611688045375e-05, "loss": 3.8699, "step": 2135552 }, { "epoch": 1.02, "learning_rate": 1.5026225740534855e-05, "loss": 3.8719, "step": 2136064 }, { "epoch": 1.02, "learning_rate": 1.5017856171828066e-05, "loss": 3.8677, "step": 2136576 }, { "epoch": 1.03, "eval_loss": 3.9853992462158203, "eval_runtime": 294.6169, "eval_samples_per_second": 1295.211, "eval_steps_per_second": 40.476, "step": 2136960 }, { "epoch": 0.0, "learning_rate": 1.5009470224317545e-05, "loss": 3.8766, "step": 2137088 }, { "epoch": 0.0, "learning_rate": 1.5001084276807025e-05, "loss": 3.8547, "step": 2137600 }, { "epoch": 0.0, "learning_rate": 1.4992698329296505e-05, "loss": 3.8672, "step": 2138112 }, { "epoch": 0.0, "learning_rate": 1.4984312381785984e-05, "loss": 3.8837, "step": 2138624 }, { "epoch": 0.0, "learning_rate": 1.4975926434275464e-05, "loss": 3.8782, "step": 2139136 }, { "epoch": 0.0, "learning_rate": 1.4967540486764944e-05, "loss": 3.871, "step": 2139648 }, { "epoch": 0.0, "learning_rate": 1.4959154539254425e-05, "loss": 3.8827, "step": 2140160 }, { "epoch": 0.0, "learning_rate": 1.4950768591743905e-05, "loss": 3.864, "step": 2140672 }, { "epoch": 0.0, "learning_rate": 1.4942382644233385e-05, "loss": 3.8621, "step": 2141184 }, { "epoch": 0.0, "learning_rate": 1.4933996696722863e-05, "loss": 3.8782, "step": 2141696 }, { "epoch": 0.0, "learning_rate": 1.4925610749212343e-05, "loss": 3.8776, "step": 2142208 }, { "epoch": 0.0, "learning_rate": 1.4917224801701823e-05, "loss": 3.873, "step": 2142720 }, { "epoch": 0.0, "learning_rate": 1.4908855232995036e-05, "loss": 3.8824, "step": 2143232 }, { "epoch": 0.0, "learning_rate": 1.4900469285484514e-05, "loss": 3.8588, "step": 2143744 }, { "epoch": 0.0, "learning_rate": 1.4892083337973994e-05, "loss": 3.8631, "step": 2144256 }, { "epoch": 0.0, "learning_rate": 1.4883697390463474e-05, "loss": 3.8552, "step": 2144768 }, { "epoch": 0.0, "learning_rate": 1.4875311442952956e-05, "loss": 3.8691, "step": 2145280 }, { "epoch": 0.0, "learning_rate": 1.4866925495442436e-05, "loss": 3.8687, "step": 2145792 }, { "epoch": 0.0, "learning_rate": 1.4858539547931916e-05, "loss": 3.8604, "step": 2146304 }, { "epoch": 0.0, "learning_rate": 1.4850153600421395e-05, "loss": 3.8656, "step": 2146816 }, { "epoch": 0.0, "learning_rate": 1.4841784031714606e-05, "loss": 3.8907, "step": 2147328 }, { "epoch": 0.0, "learning_rate": 1.4833398084204086e-05, "loss": 3.8712, "step": 2147840 }, { "epoch": 0.0, "learning_rate": 1.4825012136693566e-05, "loss": 3.8772, "step": 2148352 }, { "epoch": 0.0, "learning_rate": 1.4816626189183044e-05, "loss": 3.8712, "step": 2148864 }, { "epoch": 0.0, "learning_rate": 1.4808240241672524e-05, "loss": 3.8764, "step": 2149376 }, { "epoch": 0.0, "learning_rate": 1.4799870672965737e-05, "loss": 3.8691, "step": 2149888 }, { "epoch": 0.0, "learning_rate": 1.4791484725455219e-05, "loss": 3.8661, "step": 2150400 }, { "epoch": 0.0, "learning_rate": 1.4783098777944695e-05, "loss": 3.8576, "step": 2150912 }, { "epoch": 0.0, "learning_rate": 1.4774712830434175e-05, "loss": 3.8691, "step": 2151424 }, { "epoch": 0.0, "learning_rate": 1.4766326882923657e-05, "loss": 3.8604, "step": 2151936 }, { "epoch": 0.01, "learning_rate": 1.475795731421687e-05, "loss": 3.8712, "step": 2152448 }, { "epoch": 0.01, "learning_rate": 1.4749571366706347e-05, "loss": 3.868, "step": 2152960 }, { "epoch": 0.01, "learning_rate": 1.4741185419195827e-05, "loss": 3.8766, "step": 2153472 }, { "epoch": 0.01, "learning_rate": 1.4732799471685307e-05, "loss": 3.8774, "step": 2153984 }, { "epoch": 0.01, "learning_rate": 1.4724429902978518e-05, "loss": 3.8667, "step": 2154496 }, { "epoch": 0.01, "learning_rate": 1.471606033427173e-05, "loss": 3.8751, "step": 2155008 }, { "epoch": 0.01, "learning_rate": 1.470767438676121e-05, "loss": 3.8788, "step": 2155520 }, { "epoch": 0.01, "learning_rate": 1.469928843925069e-05, "loss": 3.8526, "step": 2156032 }, { "epoch": 0.01, "learning_rate": 1.4690902491740169e-05, "loss": 3.8707, "step": 2156544 }, { "epoch": 0.01, "learning_rate": 1.4682516544229649e-05, "loss": 3.8631, "step": 2157056 }, { "epoch": 0.01, "learning_rate": 1.4674130596719129e-05, "loss": 3.8622, "step": 2157568 }, { "epoch": 0.01, "learning_rate": 1.466574464920861e-05, "loss": 3.8734, "step": 2158080 }, { "epoch": 0.01, "learning_rate": 1.465735870169809e-05, "loss": 3.8699, "step": 2158592 }, { "epoch": 0.01, "learning_rate": 1.4648989132991301e-05, "loss": 3.8719, "step": 2159104 }, { "epoch": 0.01, "learning_rate": 1.4640603185480781e-05, "loss": 3.8744, "step": 2159616 }, { "epoch": 0.01, "learning_rate": 1.4632217237970261e-05, "loss": 3.8761, "step": 2160128 }, { "epoch": 0.01, "learning_rate": 1.4623831290459741e-05, "loss": 3.8765, "step": 2160640 }, { "epoch": 0.01, "learning_rate": 1.4615445342949221e-05, "loss": 3.8707, "step": 2161152 }, { "epoch": 0.01, "learning_rate": 1.46070593954387e-05, "loss": 3.8421, "step": 2161664 }, { "epoch": 0.01, "learning_rate": 1.4598689826731912e-05, "loss": 3.8754, "step": 2162176 }, { "epoch": 0.01, "learning_rate": 1.4590320258025122e-05, "loss": 3.8712, "step": 2162688 }, { "epoch": 0.01, "learning_rate": 1.4581934310514602e-05, "loss": 3.8771, "step": 2163200 }, { "epoch": 0.01, "learning_rate": 1.4573548363004082e-05, "loss": 3.867, "step": 2163712 }, { "epoch": 0.01, "learning_rate": 1.4565162415493564e-05, "loss": 3.8595, "step": 2164224 }, { "epoch": 0.01, "learning_rate": 1.4556792846786773e-05, "loss": 3.8552, "step": 2164736 }, { "epoch": 0.01, "learning_rate": 1.4548406899276255e-05, "loss": 3.8574, "step": 2165248 }, { "epoch": 0.01, "learning_rate": 1.4540020951765735e-05, "loss": 3.8675, "step": 2165760 }, { "epoch": 0.01, "learning_rate": 1.4531635004255215e-05, "loss": 3.8473, "step": 2166272 }, { "epoch": 0.01, "learning_rate": 1.4523249056744695e-05, "loss": 3.8859, "step": 2166784 }, { "epoch": 0.01, "learning_rate": 1.4514863109234173e-05, "loss": 3.867, "step": 2167296 }, { "epoch": 0.01, "learning_rate": 1.4506477161723653e-05, "loss": 3.8487, "step": 2167808 }, { "epoch": 0.01, "learning_rate": 1.4498091214213133e-05, "loss": 3.8737, "step": 2168320 }, { "epoch": 0.01, "learning_rate": 1.4489705266702613e-05, "loss": 3.8562, "step": 2168832 }, { "epoch": 0.01, "learning_rate": 1.4481319319192094e-05, "loss": 3.8579, "step": 2169344 }, { "epoch": 0.01, "learning_rate": 1.4472933371681574e-05, "loss": 3.866, "step": 2169856 }, { "epoch": 0.01, "learning_rate": 1.4464547424171054e-05, "loss": 3.8685, "step": 2170368 }, { "epoch": 0.01, "learning_rate": 1.4456161476660533e-05, "loss": 3.8548, "step": 2170880 }, { "epoch": 0.01, "learning_rate": 1.4447775529150013e-05, "loss": 3.8688, "step": 2171392 }, { "epoch": 0.01, "learning_rate": 1.4439405960443225e-05, "loss": 3.8517, "step": 2171904 }, { "epoch": 0.01, "learning_rate": 1.4431020012932703e-05, "loss": 3.8645, "step": 2172416 }, { "epoch": 0.01, "learning_rate": 1.4422634065422183e-05, "loss": 3.8729, "step": 2172928 }, { "epoch": 0.01, "learning_rate": 1.4414248117911663e-05, "loss": 3.8665, "step": 2173440 }, { "epoch": 0.01, "learning_rate": 1.4405878549204876e-05, "loss": 3.8671, "step": 2173952 }, { "epoch": 0.01, "learning_rate": 1.4397492601694354e-05, "loss": 3.8632, "step": 2174464 }, { "epoch": 0.01, "learning_rate": 1.4389106654183834e-05, "loss": 3.888, "step": 2174976 }, { "epoch": 0.01, "learning_rate": 1.4380720706673314e-05, "loss": 3.8525, "step": 2175488 }, { "epoch": 0.01, "learning_rate": 1.4372334759162796e-05, "loss": 3.8732, "step": 2176000 }, { "epoch": 0.01, "learning_rate": 1.4363948811652275e-05, "loss": 3.8621, "step": 2176512 }, { "epoch": 0.01, "learning_rate": 1.4355562864141755e-05, "loss": 3.8612, "step": 2177024 }, { "epoch": 0.01, "learning_rate": 1.4347176916631235e-05, "loss": 3.8658, "step": 2177536 }, { "epoch": 0.01, "learning_rate": 1.4338790969120714e-05, "loss": 3.8672, "step": 2178048 }, { "epoch": 0.01, "learning_rate": 1.4330405021610194e-05, "loss": 3.8812, "step": 2178560 }, { "epoch": 0.01, "learning_rate": 1.4322035452903406e-05, "loss": 3.877, "step": 2179072 }, { "epoch": 0.01, "learning_rate": 1.4313649505392884e-05, "loss": 3.8511, "step": 2179584 }, { "epoch": 0.01, "learning_rate": 1.4305263557882364e-05, "loss": 3.8518, "step": 2180096 }, { "epoch": 0.01, "learning_rate": 1.4296877610371844e-05, "loss": 3.8589, "step": 2180608 }, { "epoch": 0.01, "learning_rate": 1.4288491662861326e-05, "loss": 3.8724, "step": 2181120 }, { "epoch": 0.01, "learning_rate": 1.4280105715350806e-05, "loss": 3.8631, "step": 2181632 }, { "epoch": 0.01, "learning_rate": 1.4271736146644017e-05, "loss": 3.8599, "step": 2182144 }, { "epoch": 0.01, "learning_rate": 1.4263366577937229e-05, "loss": 3.8718, "step": 2182656 }, { "epoch": 0.02, "learning_rate": 1.4254980630426709e-05, "loss": 3.8629, "step": 2183168 }, { "epoch": 0.02, "learning_rate": 1.4246594682916187e-05, "loss": 3.8677, "step": 2183680 }, { "epoch": 0.02, "learning_rate": 1.4238208735405667e-05, "loss": 3.8599, "step": 2184192 }, { "epoch": 0.02, "learning_rate": 1.4229822787895147e-05, "loss": 3.869, "step": 2184704 }, { "epoch": 0.02, "learning_rate": 1.4221436840384627e-05, "loss": 3.8703, "step": 2185216 }, { "epoch": 0.02, "learning_rate": 1.4213067271677838e-05, "loss": 3.8755, "step": 2185728 }, { "epoch": 0.02, "learning_rate": 1.4204681324167318e-05, "loss": 3.8546, "step": 2186240 }, { "epoch": 0.02, "learning_rate": 1.4196295376656798e-05, "loss": 3.8583, "step": 2186752 }, { "epoch": 0.02, "learning_rate": 1.418790942914628e-05, "loss": 3.8659, "step": 2187264 }, { "epoch": 0.02, "learning_rate": 1.417952348163576e-05, "loss": 3.8653, "step": 2187776 }, { "epoch": 0.02, "learning_rate": 1.417113753412524e-05, "loss": 3.8774, "step": 2188288 }, { "epoch": 0.02, "learning_rate": 1.4162751586614718e-05, "loss": 3.8633, "step": 2188800 }, { "epoch": 0.02, "learning_rate": 1.4154365639104198e-05, "loss": 3.8657, "step": 2189312 }, { "epoch": 0.02, "learning_rate": 1.4145979691593678e-05, "loss": 3.8616, "step": 2189824 }, { "epoch": 0.02, "learning_rate": 1.4137593744083158e-05, "loss": 3.8581, "step": 2190336 }, { "epoch": 0.02, "learning_rate": 1.4129224175376368e-05, "loss": 3.8632, "step": 2190848 }, { "epoch": 0.02, "learning_rate": 1.4120838227865848e-05, "loss": 3.8605, "step": 2191360 }, { "epoch": 0.02, "learning_rate": 1.4112452280355328e-05, "loss": 3.8658, "step": 2191872 }, { "epoch": 0.02, "learning_rate": 1.410406633284481e-05, "loss": 3.8611, "step": 2192384 }, { "epoch": 0.02, "learning_rate": 1.409568038533429e-05, "loss": 3.8556, "step": 2192896 }, { "epoch": 0.02, "learning_rate": 1.408729443782377e-05, "loss": 3.8602, "step": 2193408 }, { "epoch": 0.02, "learning_rate": 1.4078908490313248e-05, "loss": 3.8514, "step": 2193920 }, { "epoch": 0.02, "learning_rate": 1.407053892160646e-05, "loss": 3.8683, "step": 2194432 }, { "epoch": 0.02, "learning_rate": 1.406215297409594e-05, "loss": 3.8686, "step": 2194944 }, { "epoch": 0.02, "learning_rate": 1.405376702658542e-05, "loss": 3.8685, "step": 2195456 }, { "epoch": 0.02, "learning_rate": 1.4045381079074899e-05, "loss": 3.873, "step": 2195968 }, { "epoch": 0.02, "learning_rate": 1.4036995131564379e-05, "loss": 3.8714, "step": 2196480 }, { "epoch": 0.02, "learning_rate": 1.4028625562857591e-05, "loss": 3.8671, "step": 2196992 }, { "epoch": 0.02, "learning_rate": 1.402023961534707e-05, "loss": 3.8589, "step": 2197504 }, { "epoch": 0.02, "learning_rate": 1.401185366783655e-05, "loss": 3.8718, "step": 2198016 }, { "epoch": 0.02, "learning_rate": 1.4003484099129764e-05, "loss": 3.8636, "step": 2198528 }, { "epoch": 0.02, "learning_rate": 1.3995098151619244e-05, "loss": 3.8621, "step": 2199040 }, { "epoch": 0.02, "learning_rate": 1.398671220410872e-05, "loss": 3.8721, "step": 2199552 }, { "epoch": 0.02, "learning_rate": 1.39783262565982e-05, "loss": 3.857, "step": 2200064 }, { "epoch": 0.02, "learning_rate": 1.3969940309087682e-05, "loss": 3.866, "step": 2200576 }, { "epoch": 0.02, "learning_rate": 1.3961554361577162e-05, "loss": 3.8576, "step": 2201088 }, { "epoch": 0.02, "learning_rate": 1.3953168414066642e-05, "loss": 3.8626, "step": 2201600 }, { "epoch": 0.02, "learning_rate": 1.3944782466556122e-05, "loss": 3.8665, "step": 2202112 }, { "epoch": 0.02, "learning_rate": 1.3936412897849332e-05, "loss": 3.8574, "step": 2202624 }, { "epoch": 0.02, "learning_rate": 1.3928026950338812e-05, "loss": 3.8762, "step": 2203136 }, { "epoch": 0.02, "learning_rate": 1.3919641002828292e-05, "loss": 3.8665, "step": 2203648 }, { "epoch": 0.02, "learning_rate": 1.3911255055317774e-05, "loss": 3.8687, "step": 2204160 }, { "epoch": 0.02, "learning_rate": 1.390286910780725e-05, "loss": 3.8593, "step": 2204672 }, { "epoch": 0.02, "learning_rate": 1.3894499539100465e-05, "loss": 3.8669, "step": 2205184 }, { "epoch": 0.02, "learning_rate": 1.3886113591589945e-05, "loss": 3.8685, "step": 2205696 }, { "epoch": 0.02, "learning_rate": 1.3877727644079425e-05, "loss": 3.8701, "step": 2206208 }, { "epoch": 0.02, "learning_rate": 1.3869341696568903e-05, "loss": 3.8662, "step": 2206720 }, { "epoch": 0.02, "learning_rate": 1.3860955749058383e-05, "loss": 3.8611, "step": 2207232 }, { "epoch": 0.02, "learning_rate": 1.3852569801547863e-05, "loss": 3.8686, "step": 2207744 }, { "epoch": 0.02, "learning_rate": 1.3844200232841075e-05, "loss": 3.8844, "step": 2208256 }, { "epoch": 0.02, "learning_rate": 1.3835814285330554e-05, "loss": 3.863, "step": 2208768 }, { "epoch": 0.02, "learning_rate": 1.3827428337820033e-05, "loss": 3.8727, "step": 2209280 }, { "epoch": 0.02, "learning_rate": 1.3819042390309513e-05, "loss": 3.876, "step": 2209792 }, { "epoch": 0.02, "learning_rate": 1.3810656442798995e-05, "loss": 3.8658, "step": 2210304 }, { "epoch": 0.02, "learning_rate": 1.3802270495288475e-05, "loss": 3.8674, "step": 2210816 }, { "epoch": 0.02, "learning_rate": 1.3793884547777955e-05, "loss": 3.8658, "step": 2211328 }, { "epoch": 0.02, "learning_rate": 1.3785514979071166e-05, "loss": 3.8678, "step": 2211840 }, { "epoch": 0.02, "learning_rate": 1.3777129031560646e-05, "loss": 3.8722, "step": 2212352 }, { "epoch": 0.02, "learning_rate": 1.3768743084050126e-05, "loss": 3.8609, "step": 2212864 }, { "epoch": 0.03, "eval_loss": 3.983924388885498, "eval_runtime": 294.6134, "eval_samples_per_second": 1295.226, "eval_steps_per_second": 40.477, "step": 2213280 }, { "epoch": 1.0, "learning_rate": 1.3760357136539606e-05, "loss": 3.8638, "step": 2213376 }, { "epoch": 1.0, "learning_rate": 1.3751971189029084e-05, "loss": 3.8501, "step": 2213888 }, { "epoch": 1.0, "learning_rate": 1.3743585241518564e-05, "loss": 3.8651, "step": 2214400 }, { "epoch": 1.0, "learning_rate": 1.3735199294008044e-05, "loss": 3.8823, "step": 2214912 }, { "epoch": 1.0, "learning_rate": 1.3726813346497524e-05, "loss": 3.8721, "step": 2215424 }, { "epoch": 1.0, "learning_rate": 1.3718427398987005e-05, "loss": 3.8663, "step": 2215936 }, { "epoch": 1.0, "learning_rate": 1.3710057830280215e-05, "loss": 3.8722, "step": 2216448 }, { "epoch": 1.0, "learning_rate": 1.3701688261573429e-05, "loss": 3.8665, "step": 2216960 }, { "epoch": 1.0, "learning_rate": 1.3693302314062905e-05, "loss": 3.8579, "step": 2217472 }, { "epoch": 1.0, "learning_rate": 1.3684916366552385e-05, "loss": 3.8777, "step": 2217984 }, { "epoch": 1.0, "learning_rate": 1.3676530419041867e-05, "loss": 3.8689, "step": 2218496 }, { "epoch": 1.0, "learning_rate": 1.3668144471531347e-05, "loss": 3.8728, "step": 2219008 }, { "epoch": 1.0, "learning_rate": 1.365979128162829e-05, "loss": 3.8768, "step": 2219520 }, { "epoch": 1.0, "learning_rate": 1.365140533411777e-05, "loss": 3.8551, "step": 2220032 }, { "epoch": 1.0, "learning_rate": 1.364301938660725e-05, "loss": 3.8595, "step": 2220544 }, { "epoch": 1.0, "learning_rate": 1.363463343909673e-05, "loss": 3.8503, "step": 2221056 }, { "epoch": 1.0, "learning_rate": 1.3626247491586208e-05, "loss": 3.867, "step": 2221568 }, { "epoch": 1.0, "learning_rate": 1.3617861544075688e-05, "loss": 3.8622, "step": 2222080 }, { "epoch": 1.0, "learning_rate": 1.3609475596565168e-05, "loss": 3.8595, "step": 2222592 }, { "epoch": 1.0, "learning_rate": 1.360108964905465e-05, "loss": 3.8599, "step": 2223104 }, { "epoch": 1.0, "learning_rate": 1.359270370154413e-05, "loss": 3.8869, "step": 2223616 }, { "epoch": 1.0, "learning_rate": 1.3584334132837339e-05, "loss": 3.8669, "step": 2224128 }, { "epoch": 1.0, "learning_rate": 1.357594818532682e-05, "loss": 3.8718, "step": 2224640 }, { "epoch": 1.0, "learning_rate": 1.35675622378163e-05, "loss": 3.8705, "step": 2225152 }, { "epoch": 1.0, "learning_rate": 1.355917629030578e-05, "loss": 3.8743, "step": 2225664 }, { "epoch": 1.0, "learning_rate": 1.355079034279526e-05, "loss": 3.864, "step": 2226176 }, { "epoch": 1.0, "learning_rate": 1.3542404395284739e-05, "loss": 3.8614, "step": 2226688 }, { "epoch": 1.0, "learning_rate": 1.3534051205381682e-05, "loss": 3.8612, "step": 2227200 }, { "epoch": 1.0, "learning_rate": 1.3525665257871162e-05, "loss": 3.8597, "step": 2227712 }, { "epoch": 1.0, "learning_rate": 1.3517279310360642e-05, "loss": 3.8598, "step": 2228224 }, { "epoch": 1.01, "learning_rate": 1.3508893362850122e-05, "loss": 3.8666, "step": 2228736 }, { "epoch": 1.01, "learning_rate": 1.3500507415339604e-05, "loss": 3.8598, "step": 2229248 }, { "epoch": 1.01, "learning_rate": 1.3492121467829083e-05, "loss": 3.8759, "step": 2229760 }, { "epoch": 1.01, "learning_rate": 1.348373552031856e-05, "loss": 3.8689, "step": 2230272 }, { "epoch": 1.01, "learning_rate": 1.3475349572808042e-05, "loss": 3.8652, "step": 2230784 }, { "epoch": 1.01, "learning_rate": 1.3466980004101254e-05, "loss": 3.8747, "step": 2231296 }, { "epoch": 1.01, "learning_rate": 1.3458594056590734e-05, "loss": 3.8716, "step": 2231808 }, { "epoch": 1.01, "learning_rate": 1.3450208109080212e-05, "loss": 3.8483, "step": 2232320 }, { "epoch": 1.01, "learning_rate": 1.3441822161569692e-05, "loss": 3.8667, "step": 2232832 }, { "epoch": 1.01, "learning_rate": 1.3433436214059172e-05, "loss": 3.8576, "step": 2233344 }, { "epoch": 1.01, "learning_rate": 1.3425050266548652e-05, "loss": 3.859, "step": 2233856 }, { "epoch": 1.01, "learning_rate": 1.3416664319038132e-05, "loss": 3.868, "step": 2234368 }, { "epoch": 1.01, "learning_rate": 1.3408278371527614e-05, "loss": 3.8691, "step": 2234880 }, { "epoch": 1.01, "learning_rate": 1.339989242401709e-05, "loss": 3.8628, "step": 2235392 }, { "epoch": 1.01, "learning_rate": 1.339150647650657e-05, "loss": 3.8728, "step": 2235904 }, { "epoch": 1.01, "learning_rate": 1.3383120528996052e-05, "loss": 3.8697, "step": 2236416 }, { "epoch": 1.01, "learning_rate": 1.3374734581485532e-05, "loss": 3.8691, "step": 2236928 }, { "epoch": 1.01, "learning_rate": 1.3366365012778743e-05, "loss": 3.8705, "step": 2237440 }, { "epoch": 1.01, "learning_rate": 1.3357979065268223e-05, "loss": 3.8404, "step": 2237952 }, { "epoch": 1.01, "learning_rate": 1.3349609496561435e-05, "loss": 3.8671, "step": 2238464 }, { "epoch": 1.01, "learning_rate": 1.3341223549050915e-05, "loss": 3.8729, "step": 2238976 }, { "epoch": 1.01, "learning_rate": 1.3332837601540393e-05, "loss": 3.8686, "step": 2239488 }, { "epoch": 1.01, "learning_rate": 1.3324451654029873e-05, "loss": 3.8605, "step": 2240000 }, { "epoch": 1.01, "learning_rate": 1.3316065706519353e-05, "loss": 3.8575, "step": 2240512 }, { "epoch": 1.01, "learning_rate": 1.3307696137812564e-05, "loss": 3.8544, "step": 2241024 }, { "epoch": 1.01, "learning_rate": 1.3299326569105777e-05, "loss": 3.8505, "step": 2241536 }, { "epoch": 1.01, "learning_rate": 1.3290940621595258e-05, "loss": 3.867, "step": 2242048 }, { "epoch": 1.01, "learning_rate": 1.3282554674084738e-05, "loss": 3.846, "step": 2242560 }, { "epoch": 1.01, "learning_rate": 1.3274168726574215e-05, "loss": 3.8737, "step": 2243072 }, { "epoch": 1.01, "learning_rate": 1.3265799157867429e-05, "loss": 3.8658, "step": 2243584 }, { "epoch": 1.01, "learning_rate": 1.3257413210356909e-05, "loss": 3.8503, "step": 2244096 }, { "epoch": 1.01, "learning_rate": 1.3249027262846389e-05, "loss": 3.8675, "step": 2244608 }, { "epoch": 1.01, "learning_rate": 1.3240641315335867e-05, "loss": 3.8506, "step": 2245120 }, { "epoch": 1.01, "learning_rate": 1.3232255367825347e-05, "loss": 3.8537, "step": 2245632 }, { "epoch": 1.01, "learning_rate": 1.3223869420314827e-05, "loss": 3.8577, "step": 2246144 }, { "epoch": 1.01, "learning_rate": 1.3215483472804307e-05, "loss": 3.868, "step": 2246656 }, { "epoch": 1.01, "learning_rate": 1.3207097525293789e-05, "loss": 3.8511, "step": 2247168 }, { "epoch": 1.01, "learning_rate": 1.3198711577783269e-05, "loss": 3.8628, "step": 2247680 }, { "epoch": 1.01, "learning_rate": 1.3190325630272745e-05, "loss": 3.8479, "step": 2248192 }, { "epoch": 1.01, "learning_rate": 1.3181939682762227e-05, "loss": 3.8599, "step": 2248704 }, { "epoch": 1.01, "learning_rate": 1.3173553735251707e-05, "loss": 3.8648, "step": 2249216 }, { "epoch": 1.01, "learning_rate": 1.3165167787741187e-05, "loss": 3.8649, "step": 2249728 }, { "epoch": 1.01, "learning_rate": 1.3156781840230667e-05, "loss": 3.8597, "step": 2250240 }, { "epoch": 1.01, "learning_rate": 1.3148412271523878e-05, "loss": 3.8636, "step": 2250752 }, { "epoch": 1.01, "learning_rate": 1.3140026324013357e-05, "loss": 3.8801, "step": 2251264 }, { "epoch": 1.01, "learning_rate": 1.313165675530657e-05, "loss": 3.8484, "step": 2251776 }, { "epoch": 1.01, "learning_rate": 1.3123270807796048e-05, "loss": 3.8706, "step": 2252288 }, { "epoch": 1.01, "learning_rate": 1.3114884860285528e-05, "loss": 3.8592, "step": 2252800 }, { "epoch": 1.01, "learning_rate": 1.310651529157874e-05, "loss": 3.8567, "step": 2253312 }, { "epoch": 1.01, "learning_rate": 1.3098129344068219e-05, "loss": 3.8597, "step": 2253824 }, { "epoch": 1.01, "learning_rate": 1.3089743396557699e-05, "loss": 3.8652, "step": 2254336 }, { "epoch": 1.01, "learning_rate": 1.3081357449047179e-05, "loss": 3.8728, "step": 2254848 }, { "epoch": 1.01, "learning_rate": 1.307297150153666e-05, "loss": 3.8745, "step": 2255360 }, { "epoch": 1.01, "learning_rate": 1.306460193282987e-05, "loss": 3.8514, "step": 2255872 }, { "epoch": 1.01, "learning_rate": 1.3056215985319351e-05, "loss": 3.8468, "step": 2256384 }, { "epoch": 1.01, "learning_rate": 1.3047830037808831e-05, "loss": 3.8543, "step": 2256896 }, { "epoch": 1.01, "learning_rate": 1.3039444090298311e-05, "loss": 3.8665, "step": 2257408 }, { "epoch": 1.01, "learning_rate": 1.3031058142787791e-05, "loss": 3.8565, "step": 2257920 }, { "epoch": 1.01, "learning_rate": 1.3022688574081002e-05, "loss": 3.8557, "step": 2258432 }, { "epoch": 1.01, "learning_rate": 1.3014302626570482e-05, "loss": 3.868, "step": 2258944 }, { "epoch": 1.02, "learning_rate": 1.3005916679059962e-05, "loss": 3.8563, "step": 2259456 }, { "epoch": 1.02, "learning_rate": 1.2997530731549443e-05, "loss": 3.8656, "step": 2259968 }, { "epoch": 1.02, "learning_rate": 1.2989144784038923e-05, "loss": 3.8538, "step": 2260480 }, { "epoch": 1.02, "learning_rate": 1.29807588365284e-05, "loss": 3.8667, "step": 2260992 }, { "epoch": 1.02, "learning_rate": 1.2972372889017882e-05, "loss": 3.8615, "step": 2261504 }, { "epoch": 1.02, "learning_rate": 1.2963986941507362e-05, "loss": 3.8751, "step": 2262016 }, { "epoch": 1.02, "learning_rate": 1.2955617372800574e-05, "loss": 3.8499, "step": 2262528 }, { "epoch": 1.02, "learning_rate": 1.2947231425290052e-05, "loss": 3.8542, "step": 2263040 }, { "epoch": 1.02, "learning_rate": 1.2938845477779532e-05, "loss": 3.8676, "step": 2263552 }, { "epoch": 1.02, "learning_rate": 1.2930475909072745e-05, "loss": 3.8604, "step": 2264064 }, { "epoch": 1.02, "learning_rate": 1.2922089961562225e-05, "loss": 3.8707, "step": 2264576 }, { "epoch": 1.02, "learning_rate": 1.2913704014051703e-05, "loss": 3.8597, "step": 2265088 }, { "epoch": 1.02, "learning_rate": 1.2905318066541183e-05, "loss": 3.8591, "step": 2265600 }, { "epoch": 1.02, "learning_rate": 1.2896932119030663e-05, "loss": 3.8568, "step": 2266112 }, { "epoch": 1.02, "learning_rate": 1.2888546171520145e-05, "loss": 3.8587, "step": 2266624 }, { "epoch": 1.02, "learning_rate": 1.2880176602813354e-05, "loss": 3.8579, "step": 2267136 }, { "epoch": 1.02, "learning_rate": 1.2871790655302835e-05, "loss": 3.8567, "step": 2267648 }, { "epoch": 1.02, "learning_rate": 1.2863404707792315e-05, "loss": 3.8623, "step": 2268160 }, { "epoch": 1.02, "learning_rate": 1.2855018760281795e-05, "loss": 3.856, "step": 2268672 }, { "epoch": 1.02, "learning_rate": 1.2846632812771275e-05, "loss": 3.8551, "step": 2269184 }, { "epoch": 1.02, "learning_rate": 1.2838246865260755e-05, "loss": 3.8579, "step": 2269696 }, { "epoch": 1.02, "learning_rate": 1.2829860917750233e-05, "loss": 3.8466, "step": 2270208 }, { "epoch": 1.02, "learning_rate": 1.2821474970239713e-05, "loss": 3.8687, "step": 2270720 }, { "epoch": 1.02, "learning_rate": 1.2813105401532926e-05, "loss": 3.8597, "step": 2271232 }, { "epoch": 1.02, "learning_rate": 1.2804719454022404e-05, "loss": 3.8652, "step": 2271744 }, { "epoch": 1.02, "learning_rate": 1.2796333506511884e-05, "loss": 3.8715, "step": 2272256 }, { "epoch": 1.02, "learning_rate": 1.2787947559001364e-05, "loss": 3.8683, "step": 2272768 }, { "epoch": 1.02, "learning_rate": 1.2779561611490846e-05, "loss": 3.8605, "step": 2273280 }, { "epoch": 1.02, "learning_rate": 1.2771175663980326e-05, "loss": 3.8543, "step": 2273792 }, { "epoch": 1.02, "learning_rate": 1.2762806095273536e-05, "loss": 3.8672, "step": 2274304 }, { "epoch": 1.02, "learning_rate": 1.2754420147763016e-05, "loss": 3.861, "step": 2274816 }, { "epoch": 1.02, "learning_rate": 1.2746034200252496e-05, "loss": 3.8553, "step": 2275328 }, { "epoch": 1.02, "learning_rate": 1.2737648252741976e-05, "loss": 3.8691, "step": 2275840 }, { "epoch": 1.02, "learning_rate": 1.2729262305231456e-05, "loss": 3.8575, "step": 2276352 }, { "epoch": 1.02, "learning_rate": 1.2720876357720938e-05, "loss": 3.8611, "step": 2276864 }, { "epoch": 1.02, "learning_rate": 1.2712490410210414e-05, "loss": 3.8553, "step": 2277376 }, { "epoch": 1.02, "learning_rate": 1.2704120841503629e-05, "loss": 3.8564, "step": 2277888 }, { "epoch": 1.02, "learning_rate": 1.2695751272796838e-05, "loss": 3.8654, "step": 2278400 }, { "epoch": 1.02, "learning_rate": 1.2687365325286318e-05, "loss": 3.8544, "step": 2278912 }, { "epoch": 1.02, "learning_rate": 1.26789793777758e-05, "loss": 3.8668, "step": 2279424 }, { "epoch": 1.02, "learning_rate": 1.267059343026528e-05, "loss": 3.8687, "step": 2279936 }, { "epoch": 1.02, "learning_rate": 1.266220748275476e-05, "loss": 3.863, "step": 2280448 }, { "epoch": 1.02, "learning_rate": 1.2653821535244237e-05, "loss": 3.8537, "step": 2280960 }, { "epoch": 1.02, "learning_rate": 1.264545196653745e-05, "loss": 3.8686, "step": 2281472 }, { "epoch": 1.02, "learning_rate": 1.263706601902693e-05, "loss": 3.8629, "step": 2281984 }, { "epoch": 1.02, "learning_rate": 1.262868007151641e-05, "loss": 3.8661, "step": 2282496 }, { "epoch": 1.02, "learning_rate": 1.2620294124005888e-05, "loss": 3.8595, "step": 2283008 }, { "epoch": 1.02, "learning_rate": 1.2611908176495368e-05, "loss": 3.8585, "step": 2283520 }, { "epoch": 1.02, "learning_rate": 1.2603522228984848e-05, "loss": 3.8697, "step": 2284032 }, { "epoch": 1.02, "learning_rate": 1.259513628147433e-05, "loss": 3.8799, "step": 2284544 }, { "epoch": 1.02, "learning_rate": 1.258675033396381e-05, "loss": 3.8562, "step": 2285056 }, { "epoch": 1.02, "learning_rate": 1.257836438645329e-05, "loss": 3.8712, "step": 2285568 }, { "epoch": 1.02, "learning_rate": 1.2569978438942768e-05, "loss": 3.872, "step": 2286080 }, { "epoch": 1.02, "learning_rate": 1.2561592491432248e-05, "loss": 3.8617, "step": 2286592 }, { "epoch": 1.02, "learning_rate": 1.2553206543921728e-05, "loss": 3.8654, "step": 2287104 }, { "epoch": 1.02, "learning_rate": 1.254483697521494e-05, "loss": 3.8595, "step": 2287616 }, { "epoch": 1.02, "learning_rate": 1.2536467406508151e-05, "loss": 3.8595, "step": 2288128 }, { "epoch": 1.02, "learning_rate": 1.2528081458997631e-05, "loss": 3.8715, "step": 2288640 }, { "epoch": 1.02, "learning_rate": 1.2519695511487111e-05, "loss": 3.8528, "step": 2289152 }, { "epoch": 1.03, "eval_loss": 3.9826714992523193, "eval_runtime": 294.418, "eval_samples_per_second": 1296.086, "eval_steps_per_second": 40.504, "step": 2289600 }, { "epoch": 0.0, "learning_rate": 1.2511309563976593e-05, "loss": 3.8718, "step": 2289664 }, { "epoch": 0.0, "learning_rate": 1.250292361646607e-05, "loss": 3.8505, "step": 2290176 }, { "epoch": 0.0, "learning_rate": 1.2494537668955549e-05, "loss": 3.8603, "step": 2290688 }, { "epoch": 0.0, "learning_rate": 1.248615172144503e-05, "loss": 3.8768, "step": 2291200 }, { "epoch": 0.0, "learning_rate": 1.247776577393451e-05, "loss": 3.8727, "step": 2291712 }, { "epoch": 0.0, "learning_rate": 1.246937982642399e-05, "loss": 3.8612, "step": 2292224 }, { "epoch": 0.0, "learning_rate": 1.2460993878913469e-05, "loss": 3.8687, "step": 2292736 }, { "epoch": 0.0, "learning_rate": 1.245260793140295e-05, "loss": 3.8585, "step": 2293248 }, { "epoch": 0.0, "learning_rate": 1.244422198389243e-05, "loss": 3.8548, "step": 2293760 }, { "epoch": 0.0, "learning_rate": 1.2435836036381909e-05, "loss": 3.8715, "step": 2294272 }, { "epoch": 0.0, "learning_rate": 1.242745008887139e-05, "loss": 3.8672, "step": 2294784 }, { "epoch": 0.0, "learning_rate": 1.241906414136087e-05, "loss": 3.8682, "step": 2295296 }, { "epoch": 0.0, "learning_rate": 1.2410694572654081e-05, "loss": 3.8733, "step": 2295808 }, { "epoch": 0.0, "learning_rate": 1.2402308625143561e-05, "loss": 3.8511, "step": 2296320 }, { "epoch": 0.0, "learning_rate": 1.2393922677633041e-05, "loss": 3.8548, "step": 2296832 }, { "epoch": 0.0, "learning_rate": 1.2385536730122521e-05, "loss": 3.8479, "step": 2297344 }, { "epoch": 0.0, "learning_rate": 1.2377150782612e-05, "loss": 3.8654, "step": 2297856 }, { "epoch": 0.0, "learning_rate": 1.2368764835101481e-05, "loss": 3.8594, "step": 2298368 }, { "epoch": 0.0, "learning_rate": 1.2360378887590961e-05, "loss": 3.8569, "step": 2298880 }, { "epoch": 0.0, "learning_rate": 1.235199294008044e-05, "loss": 3.8613, "step": 2299392 }, { "epoch": 0.0, "learning_rate": 1.234360699256992e-05, "loss": 3.8799, "step": 2299904 }, { "epoch": 0.0, "learning_rate": 1.23352210450594e-05, "loss": 3.8694, "step": 2300416 }, { "epoch": 0.0, "learning_rate": 1.2326835097548879e-05, "loss": 3.8631, "step": 2300928 }, { "epoch": 0.0, "learning_rate": 1.2318465528842092e-05, "loss": 3.8669, "step": 2301440 }, { "epoch": 0.0, "learning_rate": 1.2310079581331572e-05, "loss": 3.8701, "step": 2301952 }, { "epoch": 0.0, "learning_rate": 1.2301693633821051e-05, "loss": 3.8633, "step": 2302464 }, { "epoch": 0.0, "learning_rate": 1.229330768631053e-05, "loss": 3.8561, "step": 2302976 }, { "epoch": 0.0, "learning_rate": 1.2284921738800011e-05, "loss": 3.8581, "step": 2303488 }, { "epoch": 0.0, "learning_rate": 1.2276535791289491e-05, "loss": 3.8533, "step": 2304000 }, { "epoch": 0.0, "learning_rate": 1.226814984377897e-05, "loss": 3.8586, "step": 2304512 }, { "epoch": 0.01, "learning_rate": 1.225976389626845e-05, "loss": 3.8629, "step": 2305024 }, { "epoch": 0.01, "learning_rate": 1.2251394327561662e-05, "loss": 3.8603, "step": 2305536 }, { "epoch": 0.01, "learning_rate": 1.2243024758854873e-05, "loss": 3.8661, "step": 2306048 }, { "epoch": 0.01, "learning_rate": 1.2234638811344353e-05, "loss": 3.8676, "step": 2306560 }, { "epoch": 0.01, "learning_rate": 1.2226252863833833e-05, "loss": 3.8619, "step": 2307072 }, { "epoch": 0.01, "learning_rate": 1.2217883295127045e-05, "loss": 3.869, "step": 2307584 }, { "epoch": 0.01, "learning_rate": 1.2209497347616525e-05, "loss": 3.8683, "step": 2308096 }, { "epoch": 0.01, "learning_rate": 1.2201111400106003e-05, "loss": 3.8454, "step": 2308608 }, { "epoch": 0.01, "learning_rate": 1.2192725452595483e-05, "loss": 3.8686, "step": 2309120 }, { "epoch": 0.01, "learning_rate": 1.2184339505084965e-05, "loss": 3.8456, "step": 2309632 }, { "epoch": 0.01, "learning_rate": 1.2175953557574443e-05, "loss": 3.8572, "step": 2310144 }, { "epoch": 0.01, "learning_rate": 1.2167567610063923e-05, "loss": 3.8598, "step": 2310656 }, { "epoch": 0.01, "learning_rate": 1.2159181662553403e-05, "loss": 3.8704, "step": 2311168 }, { "epoch": 0.01, "learning_rate": 1.2150795715042885e-05, "loss": 3.8582, "step": 2311680 }, { "epoch": 0.01, "learning_rate": 1.2142409767532363e-05, "loss": 3.8657, "step": 2312192 }, { "epoch": 0.01, "learning_rate": 1.2134023820021843e-05, "loss": 3.8698, "step": 2312704 }, { "epoch": 0.01, "learning_rate": 1.2125637872511323e-05, "loss": 3.8634, "step": 2313216 }, { "epoch": 0.01, "learning_rate": 1.2117268303804534e-05, "loss": 3.8681, "step": 2313728 }, { "epoch": 0.01, "learning_rate": 1.2108882356294014e-05, "loss": 3.8367, "step": 2314240 }, { "epoch": 0.01, "learning_rate": 1.2100496408783495e-05, "loss": 3.8608, "step": 2314752 }, { "epoch": 0.01, "learning_rate": 1.2092110461272975e-05, "loss": 3.8684, "step": 2315264 }, { "epoch": 0.01, "learning_rate": 1.2083740892566184e-05, "loss": 3.8672, "step": 2315776 }, { "epoch": 0.01, "learning_rate": 1.2075354945055666e-05, "loss": 3.8604, "step": 2316288 }, { "epoch": 0.01, "learning_rate": 1.2066968997545146e-05, "loss": 3.8512, "step": 2316800 }, { "epoch": 0.01, "learning_rate": 1.2058583050034624e-05, "loss": 3.8556, "step": 2317312 }, { "epoch": 0.01, "learning_rate": 1.2050213481327837e-05, "loss": 3.8411, "step": 2317824 }, { "epoch": 0.01, "learning_rate": 1.2041827533817317e-05, "loss": 3.8694, "step": 2318336 }, { "epoch": 0.01, "learning_rate": 1.2033441586306797e-05, "loss": 3.8411, "step": 2318848 }, { "epoch": 0.01, "learning_rate": 1.2025055638796277e-05, "loss": 3.868, "step": 2319360 }, { "epoch": 0.01, "learning_rate": 1.2016686070089487e-05, "loss": 3.8622, "step": 2319872 }, { "epoch": 0.01, "learning_rate": 1.2008300122578967e-05, "loss": 3.8486, "step": 2320384 }, { "epoch": 0.01, "learning_rate": 1.1999914175068447e-05, "loss": 3.862, "step": 2320896 }, { "epoch": 0.01, "learning_rate": 1.1991528227557927e-05, "loss": 3.8466, "step": 2321408 }, { "epoch": 0.01, "learning_rate": 1.1983142280047407e-05, "loss": 3.8513, "step": 2321920 }, { "epoch": 0.01, "learning_rate": 1.1974756332536887e-05, "loss": 3.8527, "step": 2322432 }, { "epoch": 0.01, "learning_rate": 1.1966370385026367e-05, "loss": 3.8639, "step": 2322944 }, { "epoch": 0.01, "learning_rate": 1.1957984437515847e-05, "loss": 3.8473, "step": 2323456 }, { "epoch": 0.01, "learning_rate": 1.1949614868809058e-05, "loss": 3.8597, "step": 2323968 }, { "epoch": 0.01, "learning_rate": 1.194122892129854e-05, "loss": 3.8449, "step": 2324480 }, { "epoch": 0.01, "learning_rate": 1.1932842973788018e-05, "loss": 3.8531, "step": 2324992 }, { "epoch": 0.01, "learning_rate": 1.192447340508123e-05, "loss": 3.8667, "step": 2325504 }, { "epoch": 0.01, "learning_rate": 1.191608745757071e-05, "loss": 3.8632, "step": 2326016 }, { "epoch": 0.01, "learning_rate": 1.1907701510060189e-05, "loss": 3.8555, "step": 2326528 }, { "epoch": 0.01, "learning_rate": 1.1899315562549669e-05, "loss": 3.8613, "step": 2327040 }, { "epoch": 0.01, "learning_rate": 1.1890945993842881e-05, "loss": 3.8708, "step": 2327552 }, { "epoch": 0.01, "learning_rate": 1.1882560046332361e-05, "loss": 3.8485, "step": 2328064 }, { "epoch": 0.01, "learning_rate": 1.187417409882184e-05, "loss": 3.8651, "step": 2328576 }, { "epoch": 0.01, "learning_rate": 1.1865788151311321e-05, "loss": 3.8533, "step": 2329088 }, { "epoch": 0.01, "learning_rate": 1.1857402203800801e-05, "loss": 3.8576, "step": 2329600 }, { "epoch": 0.01, "learning_rate": 1.1849016256290279e-05, "loss": 3.8548, "step": 2330112 }, { "epoch": 0.01, "learning_rate": 1.1840630308779759e-05, "loss": 3.8581, "step": 2330624 }, { "epoch": 0.01, "learning_rate": 1.183224436126924e-05, "loss": 3.8714, "step": 2331136 }, { "epoch": 0.01, "learning_rate": 1.1823874792562452e-05, "loss": 3.8687, "step": 2331648 }, { "epoch": 0.01, "learning_rate": 1.1815488845051931e-05, "loss": 3.8545, "step": 2332160 }, { "epoch": 0.01, "learning_rate": 1.1807102897541411e-05, "loss": 3.8376, "step": 2332672 }, { "epoch": 0.01, "learning_rate": 1.1798733328834622e-05, "loss": 3.8492, "step": 2333184 }, { "epoch": 0.01, "learning_rate": 1.1790347381324104e-05, "loss": 3.8608, "step": 2333696 }, { "epoch": 0.01, "learning_rate": 1.1781961433813582e-05, "loss": 3.8538, "step": 2334208 }, { "epoch": 0.01, "learning_rate": 1.1773591865106793e-05, "loss": 3.8526, "step": 2334720 }, { "epoch": 0.01, "learning_rate": 1.1765205917596275e-05, "loss": 3.8652, "step": 2335232 }, { "epoch": 0.02, "learning_rate": 1.1756819970085753e-05, "loss": 3.8555, "step": 2335744 }, { "epoch": 0.02, "learning_rate": 1.1748434022575233e-05, "loss": 3.8586, "step": 2336256 }, { "epoch": 0.02, "learning_rate": 1.1740048075064713e-05, "loss": 3.8527, "step": 2336768 }, { "epoch": 0.02, "learning_rate": 1.1731662127554193e-05, "loss": 3.8657, "step": 2337280 }, { "epoch": 0.02, "learning_rate": 1.1723276180043673e-05, "loss": 3.8535, "step": 2337792 }, { "epoch": 0.02, "learning_rate": 1.1714890232533153e-05, "loss": 3.8721, "step": 2338304 }, { "epoch": 0.02, "learning_rate": 1.1706520663826365e-05, "loss": 3.8483, "step": 2338816 }, { "epoch": 0.02, "learning_rate": 1.1698134716315843e-05, "loss": 3.8501, "step": 2339328 }, { "epoch": 0.02, "learning_rate": 1.1689748768805323e-05, "loss": 3.862, "step": 2339840 }, { "epoch": 0.02, "learning_rate": 1.1681362821294805e-05, "loss": 3.8561, "step": 2340352 }, { "epoch": 0.02, "learning_rate": 1.1672976873784283e-05, "loss": 3.8663, "step": 2340864 }, { "epoch": 0.02, "learning_rate": 1.1664590926273763e-05, "loss": 3.8581, "step": 2341376 }, { "epoch": 0.02, "learning_rate": 1.1656204978763243e-05, "loss": 3.8561, "step": 2341888 }, { "epoch": 0.02, "learning_rate": 1.1647819031252725e-05, "loss": 3.8523, "step": 2342400 }, { "epoch": 0.02, "learning_rate": 1.1639449462545934e-05, "loss": 3.8582, "step": 2342912 }, { "epoch": 0.02, "learning_rate": 1.1631063515035416e-05, "loss": 3.848, "step": 2343424 }, { "epoch": 0.02, "learning_rate": 1.1622677567524895e-05, "loss": 3.8541, "step": 2343936 }, { "epoch": 0.02, "learning_rate": 1.1614291620014374e-05, "loss": 3.8576, "step": 2344448 }, { "epoch": 0.02, "learning_rate": 1.1605922051307586e-05, "loss": 3.8534, "step": 2344960 }, { "epoch": 0.02, "learning_rate": 1.1597536103797066e-05, "loss": 3.8493, "step": 2345472 }, { "epoch": 0.02, "learning_rate": 1.1589150156286546e-05, "loss": 3.8581, "step": 2345984 }, { "epoch": 0.02, "learning_rate": 1.1580764208776024e-05, "loss": 3.8419, "step": 2346496 }, { "epoch": 0.02, "learning_rate": 1.1572378261265506e-05, "loss": 3.8644, "step": 2347008 }, { "epoch": 0.02, "learning_rate": 1.1563992313754986e-05, "loss": 3.8566, "step": 2347520 }, { "epoch": 0.02, "learning_rate": 1.1555606366244464e-05, "loss": 3.8634, "step": 2348032 }, { "epoch": 0.02, "learning_rate": 1.1547220418733944e-05, "loss": 3.8649, "step": 2348544 }, { "epoch": 0.02, "learning_rate": 1.1538834471223426e-05, "loss": 3.8668, "step": 2349056 }, { "epoch": 0.02, "learning_rate": 1.1530464902516637e-05, "loss": 3.857, "step": 2349568 }, { "epoch": 0.02, "learning_rate": 1.1522078955006117e-05, "loss": 3.8541, "step": 2350080 }, { "epoch": 0.02, "learning_rate": 1.1513709386299327e-05, "loss": 3.8602, "step": 2350592 }, { "epoch": 0.02, "learning_rate": 1.1505323438788807e-05, "loss": 3.8593, "step": 2351104 }, { "epoch": 0.02, "learning_rate": 1.1496937491278289e-05, "loss": 3.8481, "step": 2351616 }, { "epoch": 0.02, "learning_rate": 1.1488551543767767e-05, "loss": 3.8694, "step": 2352128 }, { "epoch": 0.02, "learning_rate": 1.1480165596257247e-05, "loss": 3.8523, "step": 2352640 }, { "epoch": 0.02, "learning_rate": 1.1471779648746727e-05, "loss": 3.8607, "step": 2353152 }, { "epoch": 0.02, "learning_rate": 1.1463393701236207e-05, "loss": 3.8516, "step": 2353664 }, { "epoch": 0.02, "learning_rate": 1.1455007753725687e-05, "loss": 3.8487, "step": 2354176 }, { "epoch": 0.02, "learning_rate": 1.1446621806215167e-05, "loss": 3.8624, "step": 2354688 }, { "epoch": 0.02, "learning_rate": 1.143826861631211e-05, "loss": 3.8508, "step": 2355200 }, { "epoch": 0.02, "learning_rate": 1.1429882668801589e-05, "loss": 3.8552, "step": 2355712 }, { "epoch": 0.02, "learning_rate": 1.142149672129107e-05, "loss": 3.8692, "step": 2356224 }, { "epoch": 0.02, "learning_rate": 1.141311077378055e-05, "loss": 3.8575, "step": 2356736 }, { "epoch": 0.02, "learning_rate": 1.1404724826270028e-05, "loss": 3.8526, "step": 2357248 }, { "epoch": 0.02, "learning_rate": 1.1396355257563241e-05, "loss": 3.8632, "step": 2357760 }, { "epoch": 0.02, "learning_rate": 1.1387969310052721e-05, "loss": 3.862, "step": 2358272 }, { "epoch": 0.02, "learning_rate": 1.1379583362542201e-05, "loss": 3.8629, "step": 2358784 }, { "epoch": 0.02, "learning_rate": 1.1371197415031679e-05, "loss": 3.8504, "step": 2359296 }, { "epoch": 0.02, "learning_rate": 1.136281146752116e-05, "loss": 3.8577, "step": 2359808 }, { "epoch": 0.02, "learning_rate": 1.1354441898814372e-05, "loss": 3.8703, "step": 2360320 }, { "epoch": 0.02, "learning_rate": 1.1346055951303852e-05, "loss": 3.8718, "step": 2360832 }, { "epoch": 0.02, "learning_rate": 1.1337670003793332e-05, "loss": 3.8574, "step": 2361344 }, { "epoch": 0.02, "learning_rate": 1.1329284056282811e-05, "loss": 3.8594, "step": 2361856 }, { "epoch": 0.02, "learning_rate": 1.1320898108772291e-05, "loss": 3.8693, "step": 2362368 }, { "epoch": 0.02, "learning_rate": 1.1312528540065502e-05, "loss": 3.8606, "step": 2362880 }, { "epoch": 0.02, "learning_rate": 1.1304142592554982e-05, "loss": 3.8604, "step": 2363392 }, { "epoch": 0.02, "learning_rate": 1.1295756645044462e-05, "loss": 3.8573, "step": 2363904 }, { "epoch": 0.02, "learning_rate": 1.1287370697533944e-05, "loss": 3.8556, "step": 2364416 }, { "epoch": 0.02, "learning_rate": 1.1279001128827153e-05, "loss": 3.8698, "step": 2364928 }, { "epoch": 0.02, "learning_rate": 1.1270615181316633e-05, "loss": 3.8486, "step": 2365440 }, { "epoch": 0.03, "eval_loss": 3.9814891815185547, "eval_runtime": 288.2002, "eval_samples_per_second": 1324.049, "eval_steps_per_second": 41.377, "step": 2365920 }, { "epoch": 1.0, "learning_rate": 1.1262229233806114e-05, "loss": 3.8557, "step": 2365952 }, { "epoch": 1.0, "learning_rate": 1.1253843286295593e-05, "loss": 3.8499, "step": 2366464 }, { "epoch": 1.0, "learning_rate": 1.1245473717588805e-05, "loss": 3.8531, "step": 2366976 }, { "epoch": 1.0, "learning_rate": 1.1237104148882016e-05, "loss": 3.873, "step": 2367488 }, { "epoch": 1.0, "learning_rate": 1.1228718201371496e-05, "loss": 3.8721, "step": 2368000 }, { "epoch": 1.0, "learning_rate": 1.1220332253860976e-05, "loss": 3.8566, "step": 2368512 }, { "epoch": 1.0, "learning_rate": 1.1211946306350456e-05, "loss": 3.8621, "step": 2369024 }, { "epoch": 1.0, "learning_rate": 1.1203560358839936e-05, "loss": 3.8578, "step": 2369536 }, { "epoch": 1.0, "learning_rate": 1.1195174411329416e-05, "loss": 3.8538, "step": 2370048 }, { "epoch": 1.0, "learning_rate": 1.1186788463818896e-05, "loss": 3.866, "step": 2370560 }, { "epoch": 1.0, "learning_rate": 1.1178402516308376e-05, "loss": 3.8603, "step": 2371072 }, { "epoch": 1.0, "learning_rate": 1.1170016568797856e-05, "loss": 3.866, "step": 2371584 }, { "epoch": 1.0, "learning_rate": 1.1161663378894799e-05, "loss": 3.8704, "step": 2372096 }, { "epoch": 1.0, "learning_rate": 1.1153277431384277e-05, "loss": 3.8508, "step": 2372608 }, { "epoch": 1.0, "learning_rate": 1.1144891483873759e-05, "loss": 3.8491, "step": 2373120 }, { "epoch": 1.0, "learning_rate": 1.1136505536363239e-05, "loss": 3.8443, "step": 2373632 }, { "epoch": 1.0, "learning_rate": 1.1128119588852717e-05, "loss": 3.8579, "step": 2374144 }, { "epoch": 1.0, "learning_rate": 1.1119733641342197e-05, "loss": 3.8592, "step": 2374656 }, { "epoch": 1.0, "learning_rate": 1.1111347693831679e-05, "loss": 3.8519, "step": 2375168 }, { "epoch": 1.0, "learning_rate": 1.1102961746321157e-05, "loss": 3.8556, "step": 2375680 }, { "epoch": 1.0, "learning_rate": 1.1094575798810637e-05, "loss": 3.8728, "step": 2376192 }, { "epoch": 1.0, "learning_rate": 1.1086189851300117e-05, "loss": 3.8628, "step": 2376704 }, { "epoch": 1.0, "learning_rate": 1.107782028259333e-05, "loss": 3.8649, "step": 2377216 }, { "epoch": 1.0, "learning_rate": 1.1069434335082808e-05, "loss": 3.8577, "step": 2377728 }, { "epoch": 1.0, "learning_rate": 1.1061048387572288e-05, "loss": 3.8697, "step": 2378240 }, { "epoch": 1.0, "learning_rate": 1.105266244006177e-05, "loss": 3.8567, "step": 2378752 }, { "epoch": 1.0, "learning_rate": 1.1044276492551247e-05, "loss": 3.8583, "step": 2379264 }, { "epoch": 1.0, "learning_rate": 1.103590692384446e-05, "loss": 3.8515, "step": 2379776 }, { "epoch": 1.0, "learning_rate": 1.102752097633394e-05, "loss": 3.8497, "step": 2380288 }, { "epoch": 1.0, "learning_rate": 1.101913502882342e-05, "loss": 3.8552, "step": 2380800 }, { "epoch": 1.01, "learning_rate": 1.1010749081312898e-05, "loss": 3.8556, "step": 2381312 }, { "epoch": 1.01, "learning_rate": 1.100236313380238e-05, "loss": 3.8579, "step": 2381824 }, { "epoch": 1.01, "learning_rate": 1.099397718629186e-05, "loss": 3.8617, "step": 2382336 }, { "epoch": 1.01, "learning_rate": 1.0985591238781338e-05, "loss": 3.8624, "step": 2382848 }, { "epoch": 1.01, "learning_rate": 1.097722167007455e-05, "loss": 3.8647, "step": 2383360 }, { "epoch": 1.01, "learning_rate": 1.0968852101367761e-05, "loss": 3.863, "step": 2383872 }, { "epoch": 1.01, "learning_rate": 1.0960466153857241e-05, "loss": 3.864, "step": 2384384 }, { "epoch": 1.01, "learning_rate": 1.0952080206346721e-05, "loss": 3.8432, "step": 2384896 }, { "epoch": 1.01, "learning_rate": 1.0943694258836201e-05, "loss": 3.8666, "step": 2385408 }, { "epoch": 1.01, "learning_rate": 1.0935308311325681e-05, "loss": 3.8393, "step": 2385920 }, { "epoch": 1.01, "learning_rate": 1.0926922363815161e-05, "loss": 3.8555, "step": 2386432 }, { "epoch": 1.01, "learning_rate": 1.0918536416304641e-05, "loss": 3.8569, "step": 2386944 }, { "epoch": 1.01, "learning_rate": 1.0910150468794121e-05, "loss": 3.8668, "step": 2387456 }, { "epoch": 1.01, "learning_rate": 1.0901764521283601e-05, "loss": 3.8533, "step": 2387968 }, { "epoch": 1.01, "learning_rate": 1.0893378573773081e-05, "loss": 3.8646, "step": 2388480 }, { "epoch": 1.01, "learning_rate": 1.088499262626256e-05, "loss": 3.8643, "step": 2388992 }, { "epoch": 1.01, "learning_rate": 1.0876623057555772e-05, "loss": 3.8628, "step": 2389504 }, { "epoch": 1.01, "learning_rate": 1.0868237110045252e-05, "loss": 3.8608, "step": 2390016 }, { "epoch": 1.01, "learning_rate": 1.0859867541338462e-05, "loss": 3.8358, "step": 2390528 }, { "epoch": 1.01, "learning_rate": 1.0851481593827944e-05, "loss": 3.8554, "step": 2391040 }, { "epoch": 1.01, "learning_rate": 1.0843095646317424e-05, "loss": 3.8655, "step": 2391552 }, { "epoch": 1.01, "learning_rate": 1.0834709698806902e-05, "loss": 3.8613, "step": 2392064 }, { "epoch": 1.01, "learning_rate": 1.0826323751296382e-05, "loss": 3.8554, "step": 2392576 }, { "epoch": 1.01, "learning_rate": 1.0817937803785864e-05, "loss": 3.8481, "step": 2393088 }, { "epoch": 1.01, "learning_rate": 1.0809551856275342e-05, "loss": 3.8514, "step": 2393600 }, { "epoch": 1.01, "learning_rate": 1.0801165908764822e-05, "loss": 3.8363, "step": 2394112 }, { "epoch": 1.01, "learning_rate": 1.0792779961254302e-05, "loss": 3.8683, "step": 2394624 }, { "epoch": 1.01, "learning_rate": 1.0784410392547515e-05, "loss": 3.8388, "step": 2395136 }, { "epoch": 1.01, "learning_rate": 1.0776024445036993e-05, "loss": 3.8609, "step": 2395648 }, { "epoch": 1.01, "learning_rate": 1.0767638497526473e-05, "loss": 3.8583, "step": 2396160 }, { "epoch": 1.01, "learning_rate": 1.0759252550015954e-05, "loss": 3.8478, "step": 2396672 }, { "epoch": 1.01, "learning_rate": 1.0750866602505433e-05, "loss": 3.8536, "step": 2397184 }, { "epoch": 1.01, "learning_rate": 1.0742480654994913e-05, "loss": 3.8466, "step": 2397696 }, { "epoch": 1.01, "learning_rate": 1.0734094707484393e-05, "loss": 3.8474, "step": 2398208 }, { "epoch": 1.01, "learning_rate": 1.0725708759973874e-05, "loss": 3.8429, "step": 2398720 }, { "epoch": 1.01, "learning_rate": 1.0717339191267083e-05, "loss": 3.8646, "step": 2399232 }, { "epoch": 1.01, "learning_rate": 1.0708953243756565e-05, "loss": 3.8487, "step": 2399744 }, { "epoch": 1.01, "learning_rate": 1.0700583675049776e-05, "loss": 3.8488, "step": 2400256 }, { "epoch": 1.01, "learning_rate": 1.0692197727539256e-05, "loss": 3.8435, "step": 2400768 }, { "epoch": 1.01, "learning_rate": 1.0683811780028736e-05, "loss": 3.8519, "step": 2401280 }, { "epoch": 1.01, "learning_rate": 1.0675425832518216e-05, "loss": 3.8639, "step": 2401792 }, { "epoch": 1.01, "learning_rate": 1.0667039885007696e-05, "loss": 3.8568, "step": 2402304 }, { "epoch": 1.01, "learning_rate": 1.0658653937497176e-05, "loss": 3.8494, "step": 2402816 }, { "epoch": 1.01, "learning_rate": 1.0650267989986655e-05, "loss": 3.8608, "step": 2403328 }, { "epoch": 1.01, "learning_rate": 1.0641882042476135e-05, "loss": 3.8677, "step": 2403840 }, { "epoch": 1.01, "learning_rate": 1.0633512473769346e-05, "loss": 3.8432, "step": 2404352 }, { "epoch": 1.01, "learning_rate": 1.0625126526258826e-05, "loss": 3.8628, "step": 2404864 }, { "epoch": 1.01, "learning_rate": 1.0616740578748306e-05, "loss": 3.8521, "step": 2405376 }, { "epoch": 1.01, "learning_rate": 1.0608354631237786e-05, "loss": 3.8528, "step": 2405888 }, { "epoch": 1.01, "learning_rate": 1.0599968683727266e-05, "loss": 3.8486, "step": 2406400 }, { "epoch": 1.01, "learning_rate": 1.0591582736216746e-05, "loss": 3.8586, "step": 2406912 }, { "epoch": 1.01, "learning_rate": 1.0583196788706226e-05, "loss": 3.8676, "step": 2407424 }, { "epoch": 1.01, "learning_rate": 1.0574810841195704e-05, "loss": 3.8664, "step": 2407936 }, { "epoch": 1.01, "learning_rate": 1.0566424893685186e-05, "loss": 3.8528, "step": 2408448 }, { "epoch": 1.01, "learning_rate": 1.0558055324978397e-05, "loss": 3.8305, "step": 2408960 }, { "epoch": 1.01, "learning_rate": 1.0549685756271609e-05, "loss": 3.8536, "step": 2409472 }, { "epoch": 1.01, "learning_rate": 1.0541299808761087e-05, "loss": 3.8539, "step": 2409984 }, { "epoch": 1.01, "learning_rate": 1.0532913861250567e-05, "loss": 3.8568, "step": 2410496 }, { "epoch": 1.01, "learning_rate": 1.0524527913740049e-05, "loss": 3.8447, "step": 2411008 }, { "epoch": 1.01, "learning_rate": 1.051615834503326e-05, "loss": 3.861, "step": 2411520 }, { "epoch": 1.02, "learning_rate": 1.0507772397522738e-05, "loss": 3.8542, "step": 2412032 }, { "epoch": 1.02, "learning_rate": 1.049938645001222e-05, "loss": 3.8567, "step": 2412544 }, { "epoch": 1.02, "learning_rate": 1.04910005025017e-05, "loss": 3.8461, "step": 2413056 }, { "epoch": 1.02, "learning_rate": 1.0482614554991178e-05, "loss": 3.8613, "step": 2413568 }, { "epoch": 1.02, "learning_rate": 1.0474228607480658e-05, "loss": 3.8473, "step": 2414080 }, { "epoch": 1.02, "learning_rate": 1.046584265997014e-05, "loss": 3.8672, "step": 2414592 }, { "epoch": 1.02, "learning_rate": 1.0457456712459618e-05, "loss": 3.851, "step": 2415104 }, { "epoch": 1.02, "learning_rate": 1.0449070764949098e-05, "loss": 3.8448, "step": 2415616 }, { "epoch": 1.02, "learning_rate": 1.0440684817438578e-05, "loss": 3.857, "step": 2416128 }, { "epoch": 1.02, "learning_rate": 1.043229886992806e-05, "loss": 3.8557, "step": 2416640 }, { "epoch": 1.02, "learning_rate": 1.0423912922417538e-05, "loss": 3.8606, "step": 2417152 }, { "epoch": 1.02, "learning_rate": 1.041554335371075e-05, "loss": 3.8551, "step": 2417664 }, { "epoch": 1.02, "learning_rate": 1.0407173785003961e-05, "loss": 3.8519, "step": 2418176 }, { "epoch": 1.02, "learning_rate": 1.039878783749344e-05, "loss": 3.8486, "step": 2418688 }, { "epoch": 1.02, "learning_rate": 1.039040188998292e-05, "loss": 3.8551, "step": 2419200 }, { "epoch": 1.02, "learning_rate": 1.03820159424724e-05, "loss": 3.841, "step": 2419712 }, { "epoch": 1.02, "learning_rate": 1.0373646373765612e-05, "loss": 3.8527, "step": 2420224 }, { "epoch": 1.02, "learning_rate": 1.0365260426255092e-05, "loss": 3.853, "step": 2420736 }, { "epoch": 1.02, "learning_rate": 1.0356874478744571e-05, "loss": 3.8541, "step": 2421248 }, { "epoch": 1.02, "learning_rate": 1.0348488531234051e-05, "loss": 3.8429, "step": 2421760 }, { "epoch": 1.02, "learning_rate": 1.0340118962527264e-05, "loss": 3.8552, "step": 2422272 }, { "epoch": 1.02, "learning_rate": 1.0331733015016742e-05, "loss": 3.8445, "step": 2422784 }, { "epoch": 1.02, "learning_rate": 1.0323347067506222e-05, "loss": 3.8591, "step": 2423296 }, { "epoch": 1.02, "learning_rate": 1.0314961119995704e-05, "loss": 3.8523, "step": 2423808 }, { "epoch": 1.02, "learning_rate": 1.0306575172485182e-05, "loss": 3.8551, "step": 2424320 }, { "epoch": 1.02, "learning_rate": 1.0298189224974662e-05, "loss": 3.8618, "step": 2424832 }, { "epoch": 1.02, "learning_rate": 1.0289803277464142e-05, "loss": 3.8619, "step": 2425344 }, { "epoch": 1.02, "learning_rate": 1.0281417329953624e-05, "loss": 3.8562, "step": 2425856 }, { "epoch": 1.02, "learning_rate": 1.0273031382443102e-05, "loss": 3.8472, "step": 2426368 }, { "epoch": 1.02, "learning_rate": 1.0264661813736313e-05, "loss": 3.8571, "step": 2426880 }, { "epoch": 1.02, "learning_rate": 1.0256275866225794e-05, "loss": 3.8545, "step": 2427392 }, { "epoch": 1.02, "learning_rate": 1.0247889918715273e-05, "loss": 3.8453, "step": 2427904 }, { "epoch": 1.02, "learning_rate": 1.0239503971204753e-05, "loss": 3.8608, "step": 2428416 }, { "epoch": 1.02, "learning_rate": 1.0231134402497965e-05, "loss": 3.8514, "step": 2428928 }, { "epoch": 1.02, "learning_rate": 1.0222748454987445e-05, "loss": 3.8591, "step": 2429440 }, { "epoch": 1.02, "learning_rate": 1.0214362507476923e-05, "loss": 3.8471, "step": 2429952 }, { "epoch": 1.02, "learning_rate": 1.0205976559966405e-05, "loss": 3.8485, "step": 2430464 }, { "epoch": 1.02, "learning_rate": 1.0197606991259616e-05, "loss": 3.8549, "step": 2430976 }, { "epoch": 1.02, "learning_rate": 1.0189237422552828e-05, "loss": 3.8494, "step": 2431488 }, { "epoch": 1.02, "learning_rate": 1.0180851475042306e-05, "loss": 3.8464, "step": 2432000 }, { "epoch": 1.02, "learning_rate": 1.0172465527531786e-05, "loss": 3.867, "step": 2432512 }, { "epoch": 1.02, "learning_rate": 1.0164079580021266e-05, "loss": 3.8568, "step": 2433024 }, { "epoch": 1.02, "learning_rate": 1.0155693632510746e-05, "loss": 3.8491, "step": 2433536 }, { "epoch": 1.02, "learning_rate": 1.0147324063803957e-05, "loss": 3.8588, "step": 2434048 }, { "epoch": 1.02, "learning_rate": 1.0138938116293439e-05, "loss": 3.8563, "step": 2434560 }, { "epoch": 1.02, "learning_rate": 1.0130552168782919e-05, "loss": 3.8592, "step": 2435072 }, { "epoch": 1.02, "learning_rate": 1.0122166221272397e-05, "loss": 3.8544, "step": 2435584 }, { "epoch": 1.02, "learning_rate": 1.011379665256561e-05, "loss": 3.8522, "step": 2436096 }, { "epoch": 1.02, "learning_rate": 1.010542708385882e-05, "loss": 3.8659, "step": 2436608 }, { "epoch": 1.02, "learning_rate": 1.00970411363483e-05, "loss": 3.8662, "step": 2437120 }, { "epoch": 1.02, "learning_rate": 1.008865518883778e-05, "loss": 3.8552, "step": 2437632 }, { "epoch": 1.02, "learning_rate": 1.008026924132726e-05, "loss": 3.8558, "step": 2438144 }, { "epoch": 1.02, "learning_rate": 1.007188329381674e-05, "loss": 3.8678, "step": 2438656 }, { "epoch": 1.02, "learning_rate": 1.006349734630622e-05, "loss": 3.8529, "step": 2439168 }, { "epoch": 1.02, "learning_rate": 1.00551113987957e-05, "loss": 3.8581, "step": 2439680 }, { "epoch": 1.02, "learning_rate": 1.004672545128518e-05, "loss": 3.8539, "step": 2440192 }, { "epoch": 1.02, "learning_rate": 1.003833950377466e-05, "loss": 3.853, "step": 2440704 }, { "epoch": 1.02, "learning_rate": 1.002995355626414e-05, "loss": 3.8661, "step": 2441216 }, { "epoch": 1.02, "learning_rate": 1.002156760875362e-05, "loss": 3.8478, "step": 2441728 }, { "epoch": 1.03, "learning_rate": 1.00131816612431e-05, "loss": 3.8523, "step": 2442240 }, { "epoch": 1.03, "eval_loss": 3.9803507328033447, "eval_runtime": 287.7259, "eval_samples_per_second": 1326.231, "eval_steps_per_second": 41.446, "step": 2442240 }, { "epoch": 0.0, "learning_rate": 1.0004795713732578e-05, "loss": 3.8449, "step": 2442752 }, { "epoch": 0.0, "learning_rate": 9.99640976622206e-06, "loss": 3.8479, "step": 2443264 }, { "epoch": 0.0, "learning_rate": 9.98802381871154e-06, "loss": 3.8698, "step": 2443776 }, { "epoch": 0.0, "learning_rate": 9.979637871201018e-06, "loss": 3.8684, "step": 2444288 }, { "epoch": 0.0, "learning_rate": 9.971251923690498e-06, "loss": 3.854, "step": 2444800 }, { "epoch": 0.0, "learning_rate": 9.96286597617998e-06, "loss": 3.8589, "step": 2445312 }, { "epoch": 0.0, "learning_rate": 9.954480028669458e-06, "loss": 3.8538, "step": 2445824 }, { "epoch": 0.0, "learning_rate": 9.946094081158938e-06, "loss": 3.8475, "step": 2446336 }, { "epoch": 0.0, "learning_rate": 9.93770813364842e-06, "loss": 3.8648, "step": 2446848 }, { "epoch": 0.0, "learning_rate": 9.9293221861379e-06, "loss": 3.8551, "step": 2447360 }, { "epoch": 0.0, "learning_rate": 9.920936238627378e-06, "loss": 3.8638, "step": 2447872 }, { "epoch": 0.0, "learning_rate": 9.912550291116857e-06, "loss": 3.8617, "step": 2448384 }, { "epoch": 0.0, "learning_rate": 9.90418072241007e-06, "loss": 3.8541, "step": 2448896 }, { "epoch": 0.0, "learning_rate": 9.895794774899548e-06, "loss": 3.8472, "step": 2449408 }, { "epoch": 0.0, "learning_rate": 9.887408827389028e-06, "loss": 3.8407, "step": 2449920 }, { "epoch": 0.0, "learning_rate": 9.87902287987851e-06, "loss": 3.8523, "step": 2450432 }, { "epoch": 0.0, "learning_rate": 9.87063693236799e-06, "loss": 3.8549, "step": 2450944 }, { "epoch": 0.0, "learning_rate": 9.862250984857468e-06, "loss": 3.8494, "step": 2451456 }, { "epoch": 0.0, "learning_rate": 9.853865037346948e-06, "loss": 3.8504, "step": 2451968 }, { "epoch": 0.0, "learning_rate": 9.84547908983643e-06, "loss": 3.8737, "step": 2452480 }, { "epoch": 0.0, "learning_rate": 9.837093142325908e-06, "loss": 3.8571, "step": 2452992 }, { "epoch": 0.0, "learning_rate": 9.828707194815388e-06, "loss": 3.8608, "step": 2453504 }, { "epoch": 0.0, "learning_rate": 9.8203376261086e-06, "loss": 3.8554, "step": 2454016 }, { "epoch": 0.0, "learning_rate": 9.81195167859808e-06, "loss": 3.8694, "step": 2454528 }, { "epoch": 0.0, "learning_rate": 9.803565731087559e-06, "loss": 3.8478, "step": 2455040 }, { "epoch": 0.0, "learning_rate": 9.79517978357704e-06, "loss": 3.8555, "step": 2455552 }, { "epoch": 0.0, "learning_rate": 9.786810214870251e-06, "loss": 3.8482, "step": 2456064 }, { "epoch": 0.0, "learning_rate": 9.77842426735973e-06, "loss": 3.8499, "step": 2456576 }, { "epoch": 0.0, "learning_rate": 9.770038319849211e-06, "loss": 3.8517, "step": 2457088 }, { "epoch": 0.01, "learning_rate": 9.761652372338691e-06, "loss": 3.8518, "step": 2457600 }, { "epoch": 0.01, "learning_rate": 9.75326642482817e-06, "loss": 3.8539, "step": 2458112 }, { "epoch": 0.01, "learning_rate": 9.744896856121382e-06, "loss": 3.8614, "step": 2458624 }, { "epoch": 0.01, "learning_rate": 9.736510908610862e-06, "loss": 3.8555, "step": 2459136 }, { "epoch": 0.01, "learning_rate": 9.728124961100342e-06, "loss": 3.8649, "step": 2459648 }, { "epoch": 0.01, "learning_rate": 9.719755392393554e-06, "loss": 3.8574, "step": 2460160 }, { "epoch": 0.01, "learning_rate": 9.711369444883032e-06, "loss": 3.8632, "step": 2460672 }, { "epoch": 0.01, "learning_rate": 9.702983497372512e-06, "loss": 3.8415, "step": 2461184 }, { "epoch": 0.01, "learning_rate": 9.694597549861994e-06, "loss": 3.8637, "step": 2461696 }, { "epoch": 0.01, "learning_rate": 9.686211602351472e-06, "loss": 3.8373, "step": 2462208 }, { "epoch": 0.01, "learning_rate": 9.677825654840952e-06, "loss": 3.8547, "step": 2462720 }, { "epoch": 0.01, "learning_rate": 9.669439707330432e-06, "loss": 3.8507, "step": 2463232 }, { "epoch": 0.01, "learning_rate": 9.661053759819912e-06, "loss": 3.8608, "step": 2463744 }, { "epoch": 0.01, "learning_rate": 9.652667812309392e-06, "loss": 3.8476, "step": 2464256 }, { "epoch": 0.01, "learning_rate": 9.644298243602603e-06, "loss": 3.8643, "step": 2464768 }, { "epoch": 0.01, "learning_rate": 9.635912296092084e-06, "loss": 3.8587, "step": 2465280 }, { "epoch": 0.01, "learning_rate": 9.627526348581563e-06, "loss": 3.8586, "step": 2465792 }, { "epoch": 0.01, "learning_rate": 9.619140401071043e-06, "loss": 3.8597, "step": 2466304 }, { "epoch": 0.01, "learning_rate": 9.610754453560524e-06, "loss": 3.8317, "step": 2466816 }, { "epoch": 0.01, "learning_rate": 9.602368506050003e-06, "loss": 3.8549, "step": 2467328 }, { "epoch": 0.01, "learning_rate": 9.593998937343213e-06, "loss": 3.86, "step": 2467840 }, { "epoch": 0.01, "learning_rate": 9.585612989832695e-06, "loss": 3.8559, "step": 2468352 }, { "epoch": 0.01, "learning_rate": 9.577227042322175e-06, "loss": 3.8541, "step": 2468864 }, { "epoch": 0.01, "learning_rate": 9.568841094811653e-06, "loss": 3.8427, "step": 2469376 }, { "epoch": 0.01, "learning_rate": 9.560455147301133e-06, "loss": 3.8513, "step": 2469888 }, { "epoch": 0.01, "learning_rate": 9.552069199790615e-06, "loss": 3.8341, "step": 2470400 }, { "epoch": 0.01, "learning_rate": 9.543699631083826e-06, "loss": 3.8632, "step": 2470912 }, { "epoch": 0.01, "learning_rate": 9.535313683573306e-06, "loss": 3.833, "step": 2471424 }, { "epoch": 0.01, "learning_rate": 9.526927736062786e-06, "loss": 3.8608, "step": 2471936 }, { "epoch": 0.01, "learning_rate": 9.518541788552265e-06, "loss": 3.8546, "step": 2472448 }, { "epoch": 0.01, "learning_rate": 9.510155841041744e-06, "loss": 3.8432, "step": 2472960 }, { "epoch": 0.01, "learning_rate": 9.501769893531225e-06, "loss": 3.8476, "step": 2473472 }, { "epoch": 0.01, "learning_rate": 9.493383946020705e-06, "loss": 3.8449, "step": 2473984 }, { "epoch": 0.01, "learning_rate": 9.484997998510184e-06, "loss": 3.8446, "step": 2474496 }, { "epoch": 0.01, "learning_rate": 9.476628429803396e-06, "loss": 3.8387, "step": 2475008 }, { "epoch": 0.01, "learning_rate": 9.468242482292876e-06, "loss": 3.8599, "step": 2475520 }, { "epoch": 0.01, "learning_rate": 9.459856534782356e-06, "loss": 3.8473, "step": 2476032 }, { "epoch": 0.01, "learning_rate": 9.451470587271836e-06, "loss": 3.8443, "step": 2476544 }, { "epoch": 0.01, "learning_rate": 9.443117397368778e-06, "loss": 3.8404, "step": 2477056 }, { "epoch": 0.01, "learning_rate": 9.43473144985826e-06, "loss": 3.8454, "step": 2477568 }, { "epoch": 0.01, "learning_rate": 9.42634550234774e-06, "loss": 3.8603, "step": 2478080 }, { "epoch": 0.01, "learning_rate": 9.417959554837217e-06, "loss": 3.8578, "step": 2478592 }, { "epoch": 0.01, "learning_rate": 9.409573607326697e-06, "loss": 3.8454, "step": 2479104 }, { "epoch": 0.01, "learning_rate": 9.401187659816179e-06, "loss": 3.8592, "step": 2479616 }, { "epoch": 0.01, "learning_rate": 9.392801712305657e-06, "loss": 3.8636, "step": 2480128 }, { "epoch": 0.01, "learning_rate": 9.384432143598868e-06, "loss": 3.8426, "step": 2480640 }, { "epoch": 0.01, "learning_rate": 9.37604619608835e-06, "loss": 3.8573, "step": 2481152 }, { "epoch": 0.01, "learning_rate": 9.36766024857783e-06, "loss": 3.8506, "step": 2481664 }, { "epoch": 0.01, "learning_rate": 9.35929067987104e-06, "loss": 3.8508, "step": 2482176 }, { "epoch": 0.01, "learning_rate": 9.35090473236052e-06, "loss": 3.8455, "step": 2482688 }, { "epoch": 0.01, "learning_rate": 9.34251878485e-06, "loss": 3.8521, "step": 2483200 }, { "epoch": 0.01, "learning_rate": 9.334132837339479e-06, "loss": 3.861, "step": 2483712 }, { "epoch": 0.01, "learning_rate": 9.32574688982896e-06, "loss": 3.8676, "step": 2484224 }, { "epoch": 0.01, "learning_rate": 9.31736094231844e-06, "loss": 3.8461, "step": 2484736 }, { "epoch": 0.01, "learning_rate": 9.30897499480792e-06, "loss": 3.8268, "step": 2485248 }, { "epoch": 0.01, "learning_rate": 9.300589047297398e-06, "loss": 3.8494, "step": 2485760 }, { "epoch": 0.01, "learning_rate": 9.292219478590611e-06, "loss": 3.8494, "step": 2486272 }, { "epoch": 0.01, "learning_rate": 9.283833531080091e-06, "loss": 3.8528, "step": 2486784 }, { "epoch": 0.01, "learning_rate": 9.275447583569571e-06, "loss": 3.8475, "step": 2487296 }, { "epoch": 0.01, "learning_rate": 9.267078014862782e-06, "loss": 3.8563, "step": 2487808 }, { "epoch": 0.02, "learning_rate": 9.258692067352262e-06, "loss": 3.8504, "step": 2488320 }, { "epoch": 0.02, "learning_rate": 9.250306119841742e-06, "loss": 3.8486, "step": 2488832 }, { "epoch": 0.02, "learning_rate": 9.241920172331222e-06, "loss": 3.8425, "step": 2489344 }, { "epoch": 0.02, "learning_rate": 9.233534224820701e-06, "loss": 3.8576, "step": 2489856 }, { "epoch": 0.02, "learning_rate": 9.225148277310181e-06, "loss": 3.8447, "step": 2490368 }, { "epoch": 0.02, "learning_rate": 9.216762329799661e-06, "loss": 3.8621, "step": 2490880 }, { "epoch": 0.02, "learning_rate": 9.208376382289141e-06, "loss": 3.852, "step": 2491392 }, { "epoch": 0.02, "learning_rate": 9.199990434778621e-06, "loss": 3.8385, "step": 2491904 }, { "epoch": 0.02, "learning_rate": 9.191604487268101e-06, "loss": 3.8526, "step": 2492416 }, { "epoch": 0.02, "learning_rate": 9.183218539757581e-06, "loss": 3.855, "step": 2492928 }, { "epoch": 0.02, "learning_rate": 9.174848971050792e-06, "loss": 3.859, "step": 2493440 }, { "epoch": 0.02, "learning_rate": 9.166463023540272e-06, "loss": 3.8517, "step": 2493952 }, { "epoch": 0.02, "learning_rate": 9.158077076029752e-06, "loss": 3.8499, "step": 2494464 }, { "epoch": 0.02, "learning_rate": 9.149691128519232e-06, "loss": 3.8448, "step": 2494976 }, { "epoch": 0.02, "learning_rate": 9.141305181008712e-06, "loss": 3.8541, "step": 2495488 }, { "epoch": 0.02, "learning_rate": 9.132935612301924e-06, "loss": 3.8367, "step": 2496000 }, { "epoch": 0.02, "learning_rate": 9.124549664791403e-06, "loss": 3.8476, "step": 2496512 }, { "epoch": 0.02, "learning_rate": 9.116163717280883e-06, "loss": 3.8506, "step": 2497024 }, { "epoch": 0.02, "learning_rate": 9.107794148574095e-06, "loss": 3.8515, "step": 2497536 }, { "epoch": 0.02, "learning_rate": 9.099408201063575e-06, "loss": 3.8395, "step": 2498048 }, { "epoch": 0.02, "learning_rate": 9.091022253553053e-06, "loss": 3.85, "step": 2498560 }, { "epoch": 0.02, "learning_rate": 9.082636306042535e-06, "loss": 3.8459, "step": 2499072 }, { "epoch": 0.02, "learning_rate": 9.074250358532015e-06, "loss": 3.8535, "step": 2499584 }, { "epoch": 0.02, "learning_rate": 9.065864411021493e-06, "loss": 3.8455, "step": 2500096 }, { "epoch": 0.02, "learning_rate": 9.057478463510973e-06, "loss": 3.8476, "step": 2500608 }, { "epoch": 0.02, "learning_rate": 9.049092516000455e-06, "loss": 3.8631, "step": 2501120 }, { "epoch": 0.02, "learning_rate": 9.040722947293665e-06, "loss": 3.8596, "step": 2501632 }, { "epoch": 0.02, "learning_rate": 9.032353378586876e-06, "loss": 3.8525, "step": 2502144 }, { "epoch": 0.02, "learning_rate": 9.023967431076356e-06, "loss": 3.8449, "step": 2502656 }, { "epoch": 0.02, "learning_rate": 9.015581483565836e-06, "loss": 3.8544, "step": 2503168 }, { "epoch": 0.02, "learning_rate": 9.007195536055316e-06, "loss": 3.8494, "step": 2503680 }, { "epoch": 0.02, "learning_rate": 8.998809588544796e-06, "loss": 3.8473, "step": 2504192 }, { "epoch": 0.02, "learning_rate": 8.990423641034276e-06, "loss": 3.8633, "step": 2504704 }, { "epoch": 0.02, "learning_rate": 8.982037693523756e-06, "loss": 3.8453, "step": 2505216 }, { "epoch": 0.02, "learning_rate": 8.973668124816967e-06, "loss": 3.8551, "step": 2505728 }, { "epoch": 0.02, "learning_rate": 8.965282177306447e-06, "loss": 3.8421, "step": 2506240 }, { "epoch": 0.02, "learning_rate": 8.956896229795927e-06, "loss": 3.8454, "step": 2506752 }, { "epoch": 0.02, "learning_rate": 8.948510282285407e-06, "loss": 3.8532, "step": 2507264 }, { "epoch": 0.02, "learning_rate": 8.940124334774887e-06, "loss": 3.847, "step": 2507776 }, { "epoch": 0.02, "learning_rate": 8.931738387264367e-06, "loss": 3.8411, "step": 2508288 }, { "epoch": 0.02, "learning_rate": 8.923352439753847e-06, "loss": 3.8676, "step": 2508800 }, { "epoch": 0.02, "learning_rate": 8.914966492243327e-06, "loss": 3.8549, "step": 2509312 }, { "epoch": 0.02, "learning_rate": 8.906580544732806e-06, "loss": 3.8512, "step": 2509824 }, { "epoch": 0.02, "learning_rate": 8.89822735482975e-06, "loss": 3.85, "step": 2510336 }, { "epoch": 0.02, "learning_rate": 8.88984140731923e-06, "loss": 3.8501, "step": 2510848 }, { "epoch": 0.02, "learning_rate": 8.881455459808708e-06, "loss": 3.857, "step": 2511360 }, { "epoch": 0.02, "learning_rate": 8.87306951229819e-06, "loss": 3.8538, "step": 2511872 }, { "epoch": 0.02, "learning_rate": 8.8646999435914e-06, "loss": 3.8501, "step": 2512384 }, { "epoch": 0.02, "learning_rate": 8.85631399608088e-06, "loss": 3.8653, "step": 2512896 }, { "epoch": 0.02, "learning_rate": 8.84792804857036e-06, "loss": 3.8584, "step": 2513408 }, { "epoch": 0.02, "learning_rate": 8.83954210105984e-06, "loss": 3.8562, "step": 2513920 }, { "epoch": 0.02, "learning_rate": 8.83115615354932e-06, "loss": 3.8528, "step": 2514432 }, { "epoch": 0.02, "learning_rate": 8.822786584842531e-06, "loss": 3.8579, "step": 2514944 }, { "epoch": 0.02, "learning_rate": 8.814400637332011e-06, "loss": 3.8537, "step": 2515456 }, { "epoch": 0.02, "learning_rate": 8.806014689821491e-06, "loss": 3.8535, "step": 2515968 }, { "epoch": 0.02, "learning_rate": 8.797628742310971e-06, "loss": 3.8531, "step": 2516480 }, { "epoch": 0.02, "learning_rate": 8.789259173604182e-06, "loss": 3.8541, "step": 2516992 }, { "epoch": 0.02, "learning_rate": 8.780873226093662e-06, "loss": 3.8623, "step": 2517504 }, { "epoch": 0.02, "learning_rate": 8.772487278583143e-06, "loss": 3.8457, "step": 2518016 }, { "epoch": 0.02, "learning_rate": 8.764101331072622e-06, "loss": 3.8484, "step": 2518528 }, { "epoch": 0.03, "eval_loss": 3.9793899059295654, "eval_runtime": 292.8217, "eval_samples_per_second": 1303.151, "eval_steps_per_second": 40.724, "step": 2518560 }, { "epoch": 1.0, "learning_rate": 8.755715383562102e-06, "loss": 3.8425, "step": 2519040 }, { "epoch": 1.0, "learning_rate": 8.747345814855314e-06, "loss": 3.8472, "step": 2519552 }, { "epoch": 1.0, "learning_rate": 8.738959867344792e-06, "loss": 3.8681, "step": 2520064 }, { "epoch": 1.0, "learning_rate": 8.730573919834272e-06, "loss": 3.8616, "step": 2520576 }, { "epoch": 1.0, "learning_rate": 8.722187972323754e-06, "loss": 3.8539, "step": 2521088 }, { "epoch": 1.0, "learning_rate": 8.713802024813234e-06, "loss": 3.8545, "step": 2521600 }, { "epoch": 1.0, "learning_rate": 8.705416077302712e-06, "loss": 3.8525, "step": 2522112 }, { "epoch": 1.0, "learning_rate": 8.697030129792192e-06, "loss": 3.8445, "step": 2522624 }, { "epoch": 1.0, "learning_rate": 8.688660561085405e-06, "loss": 3.859, "step": 2523136 }, { "epoch": 1.0, "learning_rate": 8.680274613574883e-06, "loss": 3.8549, "step": 2523648 }, { "epoch": 1.0, "learning_rate": 8.671888666064364e-06, "loss": 3.8587, "step": 2524160 }, { "epoch": 1.0, "learning_rate": 8.663502718553844e-06, "loss": 3.861, "step": 2524672 }, { "epoch": 1.0, "learning_rate": 8.655149528650788e-06, "loss": 3.8492, "step": 2525184 }, { "epoch": 1.0, "learning_rate": 8.646763581140266e-06, "loss": 3.8467, "step": 2525696 }, { "epoch": 1.0, "learning_rate": 8.638377633629746e-06, "loss": 3.8405, "step": 2526208 }, { "epoch": 1.0, "learning_rate": 8.629991686119226e-06, "loss": 3.8427, "step": 2526720 }, { "epoch": 1.0, "learning_rate": 8.621605738608708e-06, "loss": 3.8522, "step": 2527232 }, { "epoch": 1.0, "learning_rate": 8.613219791098186e-06, "loss": 3.8437, "step": 2527744 }, { "epoch": 1.0, "learning_rate": 8.604833843587666e-06, "loss": 3.8518, "step": 2528256 }, { "epoch": 1.0, "learning_rate": 8.596464274880878e-06, "loss": 3.8722, "step": 2528768 }, { "epoch": 1.0, "learning_rate": 8.588078327370357e-06, "loss": 3.8541, "step": 2529280 }, { "epoch": 1.0, "learning_rate": 8.579692379859836e-06, "loss": 3.8593, "step": 2529792 }, { "epoch": 1.0, "learning_rate": 8.571306432349316e-06, "loss": 3.8508, "step": 2530304 }, { "epoch": 1.0, "learning_rate": 8.562920484838798e-06, "loss": 3.8647, "step": 2530816 }, { "epoch": 1.0, "learning_rate": 8.554534537328276e-06, "loss": 3.8465, "step": 2531328 }, { "epoch": 1.0, "learning_rate": 8.546148589817756e-06, "loss": 3.8513, "step": 2531840 }, { "epoch": 1.0, "learning_rate": 8.537762642307238e-06, "loss": 3.8446, "step": 2532352 }, { "epoch": 1.0, "learning_rate": 8.529376694796716e-06, "loss": 3.8503, "step": 2532864 }, { "epoch": 1.0, "learning_rate": 8.520990747286196e-06, "loss": 3.8456, "step": 2533376 }, { "epoch": 1.01, "learning_rate": 8.512621178579409e-06, "loss": 3.8485, "step": 2533888 }, { "epoch": 1.01, "learning_rate": 8.504235231068889e-06, "loss": 3.8493, "step": 2534400 }, { "epoch": 1.01, "learning_rate": 8.495849283558367e-06, "loss": 3.8599, "step": 2534912 }, { "epoch": 1.01, "learning_rate": 8.487463336047847e-06, "loss": 3.8511, "step": 2535424 }, { "epoch": 1.01, "learning_rate": 8.479077388537328e-06, "loss": 3.859, "step": 2535936 }, { "epoch": 1.01, "learning_rate": 8.470707819830538e-06, "loss": 3.8501, "step": 2536448 }, { "epoch": 1.01, "learning_rate": 8.46232187232002e-06, "loss": 3.8618, "step": 2536960 }, { "epoch": 1.01, "learning_rate": 8.4539359248095e-06, "loss": 3.8407, "step": 2537472 }, { "epoch": 1.01, "learning_rate": 8.445549977298979e-06, "loss": 3.8572, "step": 2537984 }, { "epoch": 1.01, "learning_rate": 8.43718040859219e-06, "loss": 3.8355, "step": 2538496 }, { "epoch": 1.01, "learning_rate": 8.42879446108167e-06, "loss": 3.855, "step": 2539008 }, { "epoch": 1.01, "learning_rate": 8.42040851357115e-06, "loss": 3.8448, "step": 2539520 }, { "epoch": 1.01, "learning_rate": 8.412022566060628e-06, "loss": 3.8603, "step": 2540032 }, { "epoch": 1.01, "learning_rate": 8.40363661855011e-06, "loss": 3.8435, "step": 2540544 }, { "epoch": 1.01, "learning_rate": 8.39525067103959e-06, "loss": 3.8593, "step": 2541056 }, { "epoch": 1.01, "learning_rate": 8.38686472352907e-06, "loss": 3.8581, "step": 2541568 }, { "epoch": 1.01, "learning_rate": 8.378478776018548e-06, "loss": 3.8567, "step": 2542080 }, { "epoch": 1.01, "learning_rate": 8.37009282850803e-06, "loss": 3.86, "step": 2542592 }, { "epoch": 1.01, "learning_rate": 8.36170688099751e-06, "loss": 3.8333, "step": 2543104 }, { "epoch": 1.01, "learning_rate": 8.35333731229072e-06, "loss": 3.8456, "step": 2543616 }, { "epoch": 1.01, "learning_rate": 8.3449513647802e-06, "loss": 3.8571, "step": 2544128 }, { "epoch": 1.01, "learning_rate": 8.33656541726968e-06, "loss": 3.8563, "step": 2544640 }, { "epoch": 1.01, "learning_rate": 8.32817946975916e-06, "loss": 3.8487, "step": 2545152 }, { "epoch": 1.01, "learning_rate": 8.31979352224864e-06, "loss": 3.845, "step": 2545664 }, { "epoch": 1.01, "learning_rate": 8.31140757473812e-06, "loss": 3.8455, "step": 2546176 }, { "epoch": 1.01, "learning_rate": 8.3030216272276e-06, "loss": 3.8366, "step": 2546688 }, { "epoch": 1.01, "learning_rate": 8.29465205852081e-06, "loss": 3.852, "step": 2547200 }, { "epoch": 1.01, "learning_rate": 8.28626611101029e-06, "loss": 3.8368, "step": 2547712 }, { "epoch": 1.01, "learning_rate": 8.27788016349977e-06, "loss": 3.8477, "step": 2548224 }, { "epoch": 1.01, "learning_rate": 8.26949421598925e-06, "loss": 3.8567, "step": 2548736 }, { "epoch": 1.01, "learning_rate": 8.26110826847873e-06, "loss": 3.8405, "step": 2549248 }, { "epoch": 1.01, "learning_rate": 8.25272232096821e-06, "loss": 3.8419, "step": 2549760 }, { "epoch": 1.01, "learning_rate": 8.24433637345769e-06, "loss": 3.8457, "step": 2550272 }, { "epoch": 1.01, "learning_rate": 8.235966804750901e-06, "loss": 3.8373, "step": 2550784 }, { "epoch": 1.01, "learning_rate": 8.227580857240381e-06, "loss": 3.8387, "step": 2551296 }, { "epoch": 1.01, "learning_rate": 8.219194909729861e-06, "loss": 3.8583, "step": 2551808 }, { "epoch": 1.01, "learning_rate": 8.210808962219343e-06, "loss": 3.8464, "step": 2552320 }, { "epoch": 1.01, "learning_rate": 8.202439393512552e-06, "loss": 3.8421, "step": 2552832 }, { "epoch": 1.01, "learning_rate": 8.194053446002032e-06, "loss": 3.8374, "step": 2553344 }, { "epoch": 1.01, "learning_rate": 8.185667498491514e-06, "loss": 3.842, "step": 2553856 }, { "epoch": 1.01, "learning_rate": 8.177281550980992e-06, "loss": 3.8551, "step": 2554368 }, { "epoch": 1.01, "learning_rate": 8.168895603470472e-06, "loss": 3.8497, "step": 2554880 }, { "epoch": 1.01, "learning_rate": 8.160509655959952e-06, "loss": 3.8448, "step": 2555392 }, { "epoch": 1.01, "learning_rate": 8.152123708449432e-06, "loss": 3.8564, "step": 2555904 }, { "epoch": 1.01, "learning_rate": 8.143737760938912e-06, "loss": 3.8577, "step": 2556416 }, { "epoch": 1.01, "learning_rate": 8.135368192232124e-06, "loss": 3.8429, "step": 2556928 }, { "epoch": 1.01, "learning_rate": 8.126982244721604e-06, "loss": 3.8514, "step": 2557440 }, { "epoch": 1.01, "learning_rate": 8.118612676014813e-06, "loss": 3.8486, "step": 2557952 }, { "epoch": 1.01, "learning_rate": 8.110226728504295e-06, "loss": 3.8498, "step": 2558464 }, { "epoch": 1.01, "learning_rate": 8.101840780993775e-06, "loss": 3.8435, "step": 2558976 }, { "epoch": 1.01, "learning_rate": 8.093454833483255e-06, "loss": 3.8472, "step": 2559488 }, { "epoch": 1.01, "learning_rate": 8.085068885972733e-06, "loss": 3.858, "step": 2560000 }, { "epoch": 1.01, "learning_rate": 8.076682938462215e-06, "loss": 3.8568, "step": 2560512 }, { "epoch": 1.01, "learning_rate": 8.068296990951695e-06, "loss": 3.8485, "step": 2561024 }, { "epoch": 1.01, "learning_rate": 8.059911043441173e-06, "loss": 3.8244, "step": 2561536 }, { "epoch": 1.01, "learning_rate": 8.051541474734385e-06, "loss": 3.8453, "step": 2562048 }, { "epoch": 1.01, "learning_rate": 8.043171906027596e-06, "loss": 3.8502, "step": 2562560 }, { "epoch": 1.01, "learning_rate": 8.034785958517078e-06, "loss": 3.8496, "step": 2563072 }, { "epoch": 1.01, "learning_rate": 8.026400011006556e-06, "loss": 3.8491, "step": 2563584 }, { "epoch": 1.01, "learning_rate": 8.018030442299767e-06, "loss": 3.8472, "step": 2564096 }, { "epoch": 1.02, "learning_rate": 8.009644494789249e-06, "loss": 3.8496, "step": 2564608 }, { "epoch": 1.02, "learning_rate": 8.001258547278729e-06, "loss": 3.8428, "step": 2565120 }, { "epoch": 1.02, "learning_rate": 7.992872599768207e-06, "loss": 3.8385, "step": 2565632 }, { "epoch": 1.02, "learning_rate": 7.984486652257687e-06, "loss": 3.8582, "step": 2566144 }, { "epoch": 1.02, "learning_rate": 7.976100704747168e-06, "loss": 3.8389, "step": 2566656 }, { "epoch": 1.02, "learning_rate": 7.967714757236647e-06, "loss": 3.8605, "step": 2567168 }, { "epoch": 1.02, "learning_rate": 7.959328809726127e-06, "loss": 3.8529, "step": 2567680 }, { "epoch": 1.02, "learning_rate": 7.950942862215607e-06, "loss": 3.8341, "step": 2568192 }, { "epoch": 1.02, "learning_rate": 7.942573293508819e-06, "loss": 3.8485, "step": 2568704 }, { "epoch": 1.02, "learning_rate": 7.93420372480203e-06, "loss": 3.8477, "step": 2569216 }, { "epoch": 1.02, "learning_rate": 7.92581777729151e-06, "loss": 3.8565, "step": 2569728 }, { "epoch": 1.02, "learning_rate": 7.91743182978099e-06, "loss": 3.8491, "step": 2570240 }, { "epoch": 1.02, "learning_rate": 7.909045882270468e-06, "loss": 3.8484, "step": 2570752 }, { "epoch": 1.02, "learning_rate": 7.90065993475995e-06, "loss": 3.8393, "step": 2571264 }, { "epoch": 1.02, "learning_rate": 7.89227398724943e-06, "loss": 3.853, "step": 2571776 }, { "epoch": 1.02, "learning_rate": 7.88388803973891e-06, "loss": 3.8341, "step": 2572288 }, { "epoch": 1.02, "learning_rate": 7.87550209222839e-06, "loss": 3.8444, "step": 2572800 }, { "epoch": 1.02, "learning_rate": 7.86711614471787e-06, "loss": 3.8489, "step": 2573312 }, { "epoch": 1.02, "learning_rate": 7.85873019720735e-06, "loss": 3.8467, "step": 2573824 }, { "epoch": 1.02, "learning_rate": 7.850344249696828e-06, "loss": 3.835, "step": 2574336 }, { "epoch": 1.02, "learning_rate": 7.84197468099004e-06, "loss": 3.848, "step": 2574848 }, { "epoch": 1.02, "learning_rate": 7.83358873347952e-06, "loss": 3.842, "step": 2575360 }, { "epoch": 1.02, "learning_rate": 7.825202785969e-06, "loss": 3.8483, "step": 2575872 }, { "epoch": 1.02, "learning_rate": 7.81681683845848e-06, "loss": 3.845, "step": 2576384 }, { "epoch": 1.02, "learning_rate": 7.80843089094796e-06, "loss": 3.8422, "step": 2576896 }, { "epoch": 1.02, "learning_rate": 7.80004494343744e-06, "loss": 3.8666, "step": 2577408 }, { "epoch": 1.02, "learning_rate": 7.791658995926918e-06, "loss": 3.8576, "step": 2577920 }, { "epoch": 1.02, "learning_rate": 7.78328942722013e-06, "loss": 3.8518, "step": 2578432 }, { "epoch": 1.02, "learning_rate": 7.77490347970961e-06, "loss": 3.8404, "step": 2578944 }, { "epoch": 1.02, "learning_rate": 7.76651753219909e-06, "loss": 3.8501, "step": 2579456 }, { "epoch": 1.02, "learning_rate": 7.75813158468857e-06, "loss": 3.8482, "step": 2579968 }, { "epoch": 1.02, "learning_rate": 7.74974563717805e-06, "loss": 3.8407, "step": 2580480 }, { "epoch": 1.02, "learning_rate": 7.74135968966753e-06, "loss": 3.8588, "step": 2580992 }, { "epoch": 1.02, "learning_rate": 7.73297374215701e-06, "loss": 3.8472, "step": 2581504 }, { "epoch": 1.02, "learning_rate": 7.72458779464649e-06, "loss": 3.8473, "step": 2582016 }, { "epoch": 1.02, "learning_rate": 7.716218225939701e-06, "loss": 3.8431, "step": 2582528 }, { "epoch": 1.02, "learning_rate": 7.707848657232914e-06, "loss": 3.8444, "step": 2583040 }, { "epoch": 1.02, "learning_rate": 7.699462709722392e-06, "loss": 3.8473, "step": 2583552 }, { "epoch": 1.02, "learning_rate": 7.691076762211872e-06, "loss": 3.8468, "step": 2584064 }, { "epoch": 1.02, "learning_rate": 7.682690814701354e-06, "loss": 3.8332, "step": 2584576 }, { "epoch": 1.02, "learning_rate": 7.674304867190832e-06, "loss": 3.8654, "step": 2585088 }, { "epoch": 1.02, "learning_rate": 7.665918919680312e-06, "loss": 3.8593, "step": 2585600 }, { "epoch": 1.02, "learning_rate": 7.657549350973524e-06, "loss": 3.8483, "step": 2586112 }, { "epoch": 1.02, "learning_rate": 7.649163403463004e-06, "loss": 3.8466, "step": 2586624 }, { "epoch": 1.02, "learning_rate": 7.640777455952482e-06, "loss": 3.8427, "step": 2587136 }, { "epoch": 1.02, "learning_rate": 7.632391508441964e-06, "loss": 3.856, "step": 2587648 }, { "epoch": 1.02, "learning_rate": 7.624021939735175e-06, "loss": 3.8516, "step": 2588160 }, { "epoch": 1.02, "learning_rate": 7.615635992224656e-06, "loss": 3.845, "step": 2588672 }, { "epoch": 1.02, "learning_rate": 7.607250044714134e-06, "loss": 3.8625, "step": 2589184 }, { "epoch": 1.02, "learning_rate": 7.598864097203615e-06, "loss": 3.8526, "step": 2589696 }, { "epoch": 1.02, "learning_rate": 7.590478149693095e-06, "loss": 3.8543, "step": 2590208 }, { "epoch": 1.02, "learning_rate": 7.582092202182574e-06, "loss": 3.8497, "step": 2590720 }, { "epoch": 1.02, "learning_rate": 7.573706254672054e-06, "loss": 3.8579, "step": 2591232 }, { "epoch": 1.02, "learning_rate": 7.5653203071615346e-06, "loss": 3.8515, "step": 2591744 }, { "epoch": 1.02, "learning_rate": 7.5569507384547445e-06, "loss": 3.8502, "step": 2592256 }, { "epoch": 1.02, "learning_rate": 7.548564790944225e-06, "loss": 3.8492, "step": 2592768 }, { "epoch": 1.02, "learning_rate": 7.540178843433705e-06, "loss": 3.8511, "step": 2593280 }, { "epoch": 1.02, "learning_rate": 7.531809274726917e-06, "loss": 3.8556, "step": 2593792 }, { "epoch": 1.02, "learning_rate": 7.523423327216396e-06, "loss": 3.843, "step": 2594304 }, { "epoch": 1.02, "learning_rate": 7.515037379705876e-06, "loss": 3.8468, "step": 2594816 }, { "epoch": 1.03, "eval_loss": 3.978384256362915, "eval_runtime": 291.6916, "eval_samples_per_second": 1308.2, "eval_steps_per_second": 40.882, "step": 2594880 }, { "epoch": 0.0, "learning_rate": 7.506651432195357e-06, "loss": 3.8372, "step": 2595328 }, { "epoch": 0.0, "learning_rate": 7.498265484684836e-06, "loss": 3.8422, "step": 2595840 }, { "epoch": 0.0, "learning_rate": 7.489879537174316e-06, "loss": 3.8624, "step": 2596352 }, { "epoch": 0.0, "learning_rate": 7.481493589663796e-06, "loss": 3.8613, "step": 2596864 }, { "epoch": 0.0, "learning_rate": 7.473107642153277e-06, "loss": 3.8512, "step": 2597376 }, { "epoch": 0.0, "learning_rate": 7.464721694642756e-06, "loss": 3.8499, "step": 2597888 }, { "epoch": 0.0, "learning_rate": 7.456335747132236e-06, "loss": 3.8499, "step": 2598400 }, { "epoch": 0.0, "learning_rate": 7.447949799621716e-06, "loss": 3.8407, "step": 2598912 }, { "epoch": 0.0, "learning_rate": 7.439563852111195e-06, "loss": 3.8595, "step": 2599424 }, { "epoch": 0.0, "learning_rate": 7.4311779046006755e-06, "loss": 3.8525, "step": 2599936 }, { "epoch": 0.0, "learning_rate": 7.4227919570901555e-06, "loss": 3.8534, "step": 2600448 }, { "epoch": 0.0, "learning_rate": 7.414406009579635e-06, "loss": 3.8559, "step": 2600960 }, { "epoch": 0.0, "learning_rate": 7.406036440872846e-06, "loss": 3.8447, "step": 2601472 }, { "epoch": 0.0, "learning_rate": 7.397650493362326e-06, "loss": 3.8446, "step": 2601984 }, { "epoch": 0.0, "learning_rate": 7.389264545851807e-06, "loss": 3.8417, "step": 2602496 }, { "epoch": 0.0, "learning_rate": 7.380878598341285e-06, "loss": 3.8431, "step": 2603008 }, { "epoch": 0.0, "learning_rate": 7.372492650830766e-06, "loss": 3.8468, "step": 2603520 }, { "epoch": 0.0, "learning_rate": 7.364106703320246e-06, "loss": 3.8414, "step": 2604032 }, { "epoch": 0.0, "learning_rate": 7.355720755809725e-06, "loss": 3.848, "step": 2604544 }, { "epoch": 0.0, "learning_rate": 7.347334808299206e-06, "loss": 3.8733, "step": 2605056 }, { "epoch": 0.0, "learning_rate": 7.3389652395924176e-06, "loss": 3.8501, "step": 2605568 }, { "epoch": 0.0, "learning_rate": 7.3305792920818975e-06, "loss": 3.8535, "step": 2606080 }, { "epoch": 0.0, "learning_rate": 7.3222097233751075e-06, "loss": 3.8519, "step": 2606592 }, { "epoch": 0.0, "learning_rate": 7.313823775864588e-06, "loss": 3.8589, "step": 2607104 }, { "epoch": 0.0, "learning_rate": 7.305437828354068e-06, "loss": 3.8427, "step": 2607616 }, { "epoch": 0.0, "learning_rate": 7.297051880843549e-06, "loss": 3.8523, "step": 2608128 }, { "epoch": 0.0, "learning_rate": 7.288665933333027e-06, "loss": 3.8403, "step": 2608640 }, { "epoch": 0.0, "learning_rate": 7.280279985822508e-06, "loss": 3.8443, "step": 2609152 }, { "epoch": 0.0, "learning_rate": 7.271894038311988e-06, "loss": 3.8429, "step": 2609664 }, { "epoch": 0.01, "learning_rate": 7.263508090801467e-06, "loss": 3.8433, "step": 2610176 }, { "epoch": 0.01, "learning_rate": 7.255122143290947e-06, "loss": 3.8464, "step": 2610688 }, { "epoch": 0.01, "learning_rate": 7.24676895338789e-06, "loss": 3.8578, "step": 2611200 }, { "epoch": 0.01, "learning_rate": 7.23838300587737e-06, "loss": 3.8487, "step": 2611712 }, { "epoch": 0.01, "learning_rate": 7.2299970583668495e-06, "loss": 3.8579, "step": 2612224 }, { "epoch": 0.01, "learning_rate": 7.221627489660061e-06, "loss": 3.8438, "step": 2612736 }, { "epoch": 0.01, "learning_rate": 7.213241542149542e-06, "loss": 3.8618, "step": 2613248 }, { "epoch": 0.01, "learning_rate": 7.204855594639022e-06, "loss": 3.8341, "step": 2613760 }, { "epoch": 0.01, "learning_rate": 7.196469647128501e-06, "loss": 3.8554, "step": 2614272 }, { "epoch": 0.01, "learning_rate": 7.188083699617981e-06, "loss": 3.8312, "step": 2614784 }, { "epoch": 0.01, "learning_rate": 7.179697752107462e-06, "loss": 3.8508, "step": 2615296 }, { "epoch": 0.01, "learning_rate": 7.171311804596941e-06, "loss": 3.8404, "step": 2615808 }, { "epoch": 0.01, "learning_rate": 7.162925857086421e-06, "loss": 3.8584, "step": 2616320 }, { "epoch": 0.01, "learning_rate": 7.154539909575901e-06, "loss": 3.8416, "step": 2616832 }, { "epoch": 0.01, "learning_rate": 7.14615396206538e-06, "loss": 3.8522, "step": 2617344 }, { "epoch": 0.01, "learning_rate": 7.137768014554861e-06, "loss": 3.8537, "step": 2617856 }, { "epoch": 0.01, "learning_rate": 7.129382067044341e-06, "loss": 3.8561, "step": 2618368 }, { "epoch": 0.01, "learning_rate": 7.120996119533821e-06, "loss": 3.8541, "step": 2618880 }, { "epoch": 0.01, "learning_rate": 7.112626550827031e-06, "loss": 3.834, "step": 2619392 }, { "epoch": 0.01, "learning_rate": 7.104240603316511e-06, "loss": 3.8378, "step": 2619904 }, { "epoch": 0.01, "learning_rate": 7.095854655805992e-06, "loss": 3.8561, "step": 2620416 }, { "epoch": 0.01, "learning_rate": 7.08746870829547e-06, "loss": 3.8536, "step": 2620928 }, { "epoch": 0.01, "learning_rate": 7.079082760784951e-06, "loss": 3.8441, "step": 2621440 }, { "epoch": 0.01, "learning_rate": 7.070696813274431e-06, "loss": 3.8438, "step": 2621952 }, { "epoch": 0.01, "learning_rate": 7.062327244567643e-06, "loss": 3.8427, "step": 2622464 }, { "epoch": 0.01, "learning_rate": 7.053941297057122e-06, "loss": 3.8309, "step": 2622976 }, { "epoch": 0.01, "learning_rate": 7.045555349546603e-06, "loss": 3.8478, "step": 2623488 }, { "epoch": 0.01, "learning_rate": 7.037169402036083e-06, "loss": 3.8338, "step": 2624000 }, { "epoch": 0.01, "learning_rate": 7.028783454525562e-06, "loss": 3.8481, "step": 2624512 }, { "epoch": 0.01, "learning_rate": 7.020397507015042e-06, "loss": 3.8543, "step": 2625024 }, { "epoch": 0.01, "learning_rate": 7.0120115595045225e-06, "loss": 3.8387, "step": 2625536 }, { "epoch": 0.01, "learning_rate": 7.003625611994001e-06, "loss": 3.8395, "step": 2626048 }, { "epoch": 0.01, "learning_rate": 6.9952560432872124e-06, "loss": 3.8446, "step": 2626560 }, { "epoch": 0.01, "learning_rate": 6.986870095776693e-06, "loss": 3.832, "step": 2627072 }, { "epoch": 0.01, "learning_rate": 6.978484148266173e-06, "loss": 3.8327, "step": 2627584 }, { "epoch": 0.01, "learning_rate": 6.970098200755652e-06, "loss": 3.8555, "step": 2628096 }, { "epoch": 0.01, "learning_rate": 6.961728632048864e-06, "loss": 3.8452, "step": 2628608 }, { "epoch": 0.01, "learning_rate": 6.9533590633420756e-06, "loss": 3.8388, "step": 2629120 }, { "epoch": 0.01, "learning_rate": 6.9449731158315555e-06, "loss": 3.8344, "step": 2629632 }, { "epoch": 0.01, "learning_rate": 6.936587168321035e-06, "loss": 3.842, "step": 2630144 }, { "epoch": 0.01, "learning_rate": 6.9282012208105154e-06, "loss": 3.8533, "step": 2630656 }, { "epoch": 0.01, "learning_rate": 6.919815273299995e-06, "loss": 3.8494, "step": 2631168 }, { "epoch": 0.01, "learning_rate": 6.9114293257894745e-06, "loss": 3.841, "step": 2631680 }, { "epoch": 0.01, "learning_rate": 6.9030433782789545e-06, "loss": 3.8533, "step": 2632192 }, { "epoch": 0.01, "learning_rate": 6.894657430768435e-06, "loss": 3.8512, "step": 2632704 }, { "epoch": 0.01, "learning_rate": 6.886287862061647e-06, "loss": 3.8392, "step": 2633216 }, { "epoch": 0.01, "learning_rate": 6.877901914551126e-06, "loss": 3.8469, "step": 2633728 }, { "epoch": 0.01, "learning_rate": 6.869515967040606e-06, "loss": 3.8489, "step": 2634240 }, { "epoch": 0.01, "learning_rate": 6.861146398333818e-06, "loss": 3.8444, "step": 2634752 }, { "epoch": 0.01, "learning_rate": 6.8527604508232976e-06, "loss": 3.8441, "step": 2635264 }, { "epoch": 0.01, "learning_rate": 6.844374503312777e-06, "loss": 3.843, "step": 2635776 }, { "epoch": 0.01, "learning_rate": 6.8359885558022575e-06, "loss": 3.8546, "step": 2636288 }, { "epoch": 0.01, "learning_rate": 6.827618987095469e-06, "loss": 3.8566, "step": 2636800 }, { "epoch": 0.01, "learning_rate": 6.819233039584947e-06, "loss": 3.8435, "step": 2637312 }, { "epoch": 0.01, "learning_rate": 6.810847092074428e-06, "loss": 3.8297, "step": 2637824 }, { "epoch": 0.01, "learning_rate": 6.802461144563908e-06, "loss": 3.8398, "step": 2638336 }, { "epoch": 0.01, "learning_rate": 6.79409157585712e-06, "loss": 3.8458, "step": 2638848 }, { "epoch": 0.01, "learning_rate": 6.785705628346599e-06, "loss": 3.8486, "step": 2639360 }, { "epoch": 0.01, "learning_rate": 6.777319680836079e-06, "loss": 3.8446, "step": 2639872 }, { "epoch": 0.01, "learning_rate": 6.76893373332556e-06, "loss": 3.8446, "step": 2640384 }, { "epoch": 0.02, "learning_rate": 6.760547785815039e-06, "loss": 3.8521, "step": 2640896 }, { "epoch": 0.02, "learning_rate": 6.752161838304519e-06, "loss": 3.8369, "step": 2641408 }, { "epoch": 0.02, "learning_rate": 6.7437758907939995e-06, "loss": 3.8401, "step": 2641920 }, { "epoch": 0.02, "learning_rate": 6.7353899432834794e-06, "loss": 3.8509, "step": 2642432 }, { "epoch": 0.02, "learning_rate": 6.727020374576689e-06, "loss": 3.8414, "step": 2642944 }, { "epoch": 0.02, "learning_rate": 6.71863442706617e-06, "loss": 3.8576, "step": 2643456 }, { "epoch": 0.02, "learning_rate": 6.71024847955565e-06, "loss": 3.8478, "step": 2643968 }, { "epoch": 0.02, "learning_rate": 6.701862532045129e-06, "loss": 3.8337, "step": 2644480 }, { "epoch": 0.02, "learning_rate": 6.693476584534609e-06, "loss": 3.8474, "step": 2644992 }, { "epoch": 0.02, "learning_rate": 6.68509063702409e-06, "loss": 3.8424, "step": 2645504 }, { "epoch": 0.02, "learning_rate": 6.67670468951357e-06, "loss": 3.8581, "step": 2646016 }, { "epoch": 0.02, "learning_rate": 6.668318742003049e-06, "loss": 3.8509, "step": 2646528 }, { "epoch": 0.02, "learning_rate": 6.659949173296261e-06, "loss": 3.8403, "step": 2647040 }, { "epoch": 0.02, "learning_rate": 6.651563225785741e-06, "loss": 3.8352, "step": 2647552 }, { "epoch": 0.02, "learning_rate": 6.64317727827522e-06, "loss": 3.8513, "step": 2648064 }, { "epoch": 0.02, "learning_rate": 6.634791330764701e-06, "loss": 3.8325, "step": 2648576 }, { "epoch": 0.02, "learning_rate": 6.626421762057912e-06, "loss": 3.8415, "step": 2649088 }, { "epoch": 0.02, "learning_rate": 6.618035814547392e-06, "loss": 3.8428, "step": 2649600 }, { "epoch": 0.02, "learning_rate": 6.609649867036871e-06, "loss": 3.8443, "step": 2650112 }, { "epoch": 0.02, "learning_rate": 6.601263919526351e-06, "loss": 3.8309, "step": 2650624 }, { "epoch": 0.02, "learning_rate": 6.592894350819563e-06, "loss": 3.8516, "step": 2651136 }, { "epoch": 0.02, "learning_rate": 6.5845247821127745e-06, "loss": 3.8397, "step": 2651648 }, { "epoch": 0.02, "learning_rate": 6.576138834602254e-06, "loss": 3.8416, "step": 2652160 }, { "epoch": 0.02, "learning_rate": 6.5677528870917344e-06, "loss": 3.8462, "step": 2652672 }, { "epoch": 0.02, "learning_rate": 6.559366939581214e-06, "loss": 3.8383, "step": 2653184 }, { "epoch": 0.02, "learning_rate": 6.5509809920706935e-06, "loss": 3.8625, "step": 2653696 }, { "epoch": 0.02, "learning_rate": 6.5425950445601735e-06, "loss": 3.8537, "step": 2654208 }, { "epoch": 0.02, "learning_rate": 6.534209097049654e-06, "loss": 3.8504, "step": 2654720 }, { "epoch": 0.02, "learning_rate": 6.525823149539134e-06, "loss": 3.837, "step": 2655232 }, { "epoch": 0.02, "learning_rate": 6.517453580832344e-06, "loss": 3.8488, "step": 2655744 }, { "epoch": 0.02, "learning_rate": 6.509084012125556e-06, "loss": 3.8486, "step": 2656256 }, { "epoch": 0.02, "learning_rate": 6.500698064615037e-06, "loss": 3.8354, "step": 2656768 }, { "epoch": 0.02, "learning_rate": 6.4923121171045165e-06, "loss": 3.8542, "step": 2657280 }, { "epoch": 0.02, "learning_rate": 6.483926169593996e-06, "loss": 3.8461, "step": 2657792 }, { "epoch": 0.02, "learning_rate": 6.475540222083476e-06, "loss": 3.8431, "step": 2658304 }, { "epoch": 0.02, "learning_rate": 6.467154274572956e-06, "loss": 3.8446, "step": 2658816 }, { "epoch": 0.02, "learning_rate": 6.4587683270624355e-06, "loss": 3.8433, "step": 2659328 }, { "epoch": 0.02, "learning_rate": 6.450398758355647e-06, "loss": 3.8372, "step": 2659840 }, { "epoch": 0.02, "learning_rate": 6.442029189648859e-06, "loss": 3.8492, "step": 2660352 }, { "epoch": 0.02, "learning_rate": 6.433643242138339e-06, "loss": 3.8343, "step": 2660864 }, { "epoch": 0.02, "learning_rate": 6.425257294627818e-06, "loss": 3.8586, "step": 2661376 }, { "epoch": 0.02, "learning_rate": 6.416871347117298e-06, "loss": 3.8573, "step": 2661888 }, { "epoch": 0.02, "learning_rate": 6.408485399606779e-06, "loss": 3.8431, "step": 2662400 }, { "epoch": 0.02, "learning_rate": 6.400099452096258e-06, "loss": 3.8427, "step": 2662912 }, { "epoch": 0.02, "learning_rate": 6.391713504585738e-06, "loss": 3.8418, "step": 2663424 }, { "epoch": 0.02, "learning_rate": 6.383327557075218e-06, "loss": 3.8509, "step": 2663936 }, { "epoch": 0.02, "learning_rate": 6.374957988368429e-06, "loss": 3.8494, "step": 2664448 }, { "epoch": 0.02, "learning_rate": 6.366572040857908e-06, "loss": 3.8449, "step": 2664960 }, { "epoch": 0.02, "learning_rate": 6.358186093347389e-06, "loss": 3.8549, "step": 2665472 }, { "epoch": 0.02, "learning_rate": 6.349800145836869e-06, "loss": 3.8507, "step": 2665984 }, { "epoch": 0.02, "learning_rate": 6.341414198326348e-06, "loss": 3.8534, "step": 2666496 }, { "epoch": 0.02, "learning_rate": 6.333028250815828e-06, "loss": 3.8448, "step": 2667008 }, { "epoch": 0.02, "learning_rate": 6.324642303305309e-06, "loss": 3.8592, "step": 2667520 }, { "epoch": 0.02, "learning_rate": 6.316256355794787e-06, "loss": 3.85, "step": 2668032 }, { "epoch": 0.02, "learning_rate": 6.307886787087999e-06, "loss": 3.8422, "step": 2668544 }, { "epoch": 0.02, "learning_rate": 6.29950083957748e-06, "loss": 3.8488, "step": 2669056 }, { "epoch": 0.02, "learning_rate": 6.29111489206696e-06, "loss": 3.8512, "step": 2669568 }, { "epoch": 0.02, "learning_rate": 6.282728944556439e-06, "loss": 3.8486, "step": 2670080 }, { "epoch": 0.02, "learning_rate": 6.27435937584965e-06, "loss": 3.8384, "step": 2670592 }, { "epoch": 0.02, "learning_rate": 6.265973428339131e-06, "loss": 3.8399, "step": 2671104 }, { "epoch": 0.03, "eval_loss": 3.9779341220855713, "eval_runtime": 299.9978, "eval_samples_per_second": 1271.979, "eval_steps_per_second": 39.75, "step": 2671200 }, { "epoch": 0.0, "learning_rate": 6.257587480828611e-06, "loss": 3.8372, "step": 2671616 }, { "epoch": 0.0, "learning_rate": 6.249201533318091e-06, "loss": 3.8389, "step": 2672128 }, { "epoch": 0.0, "learning_rate": 6.24081558580757e-06, "loss": 3.859, "step": 2672640 }, { "epoch": 0.0, "learning_rate": 6.23242963829705e-06, "loss": 3.8583, "step": 2673152 }, { "epoch": 0.0, "learning_rate": 6.22404369078653e-06, "loss": 3.8562, "step": 2673664 }, { "epoch": 0.0, "learning_rate": 6.21565774327601e-06, "loss": 3.8401, "step": 2674176 }, { "epoch": 0.0, "learning_rate": 6.20727179576549e-06, "loss": 3.85, "step": 2674688 }, { "epoch": 0.0, "learning_rate": 6.19888584825497e-06, "loss": 3.8341, "step": 2675200 }, { "epoch": 0.0, "learning_rate": 6.190499900744449e-06, "loss": 3.8581, "step": 2675712 }, { "epoch": 0.0, "learning_rate": 6.18211395323393e-06, "loss": 3.8514, "step": 2676224 }, { "epoch": 0.0, "learning_rate": 6.173728005723409e-06, "loss": 3.8465, "step": 2676736 }, { "epoch": 0.0, "learning_rate": 6.16534205821289e-06, "loss": 3.8559, "step": 2677248 }, { "epoch": 0.0, "learning_rate": 6.156972489506101e-06, "loss": 3.8414, "step": 2677760 }, { "epoch": 0.0, "learning_rate": 6.148586541995581e-06, "loss": 3.8455, "step": 2678272 }, { "epoch": 0.0, "learning_rate": 6.1402005944850605e-06, "loss": 3.8362, "step": 2678784 }, { "epoch": 0.0, "learning_rate": 6.1318146469745405e-06, "loss": 3.8451, "step": 2679296 }, { "epoch": 0.0, "learning_rate": 6.1234286994640205e-06, "loss": 3.8402, "step": 2679808 }, { "epoch": 0.0, "learning_rate": 6.1150427519535e-06, "loss": 3.8399, "step": 2680320 }, { "epoch": 0.0, "learning_rate": 6.1066568044429795e-06, "loss": 3.8443, "step": 2680832 }, { "epoch": 0.0, "learning_rate": 6.09827085693246e-06, "loss": 3.8676, "step": 2681344 }, { "epoch": 0.0, "learning_rate": 6.089901288225671e-06, "loss": 3.848, "step": 2681856 }, { "epoch": 0.0, "learning_rate": 6.081515340715151e-06, "loss": 3.852, "step": 2682368 }, { "epoch": 0.0, "learning_rate": 6.073129393204631e-06, "loss": 3.8491, "step": 2682880 }, { "epoch": 0.0, "learning_rate": 6.064743445694111e-06, "loss": 3.8577, "step": 2683392 }, { "epoch": 0.0, "learning_rate": 6.056357498183591e-06, "loss": 3.8413, "step": 2683904 }, { "epoch": 0.0, "learning_rate": 6.0479879294768026e-06, "loss": 3.8487, "step": 2684416 }, { "epoch": 0.0, "learning_rate": 6.0396019819662825e-06, "loss": 3.8385, "step": 2684928 }, { "epoch": 0.0, "learning_rate": 6.031216034455762e-06, "loss": 3.84, "step": 2685440 }, { "epoch": 0.0, "learning_rate": 6.022846465748973e-06, "loss": 3.8382, "step": 2685952 }, { "epoch": 0.01, "learning_rate": 6.014460518238453e-06, "loss": 3.8466, "step": 2686464 }, { "epoch": 0.01, "learning_rate": 6.006074570727933e-06, "loss": 3.8424, "step": 2686976 }, { "epoch": 0.01, "learning_rate": 5.997688623217413e-06, "loss": 3.8547, "step": 2687488 }, { "epoch": 0.01, "learning_rate": 5.989302675706893e-06, "loss": 3.8482, "step": 2688000 }, { "epoch": 0.01, "learning_rate": 5.980916728196373e-06, "loss": 3.852, "step": 2688512 }, { "epoch": 0.01, "learning_rate": 5.972547159489585e-06, "loss": 3.8443, "step": 2689024 }, { "epoch": 0.01, "learning_rate": 5.964161211979064e-06, "loss": 3.8544, "step": 2689536 }, { "epoch": 0.01, "learning_rate": 5.955775264468544e-06, "loss": 3.8376, "step": 2690048 }, { "epoch": 0.01, "learning_rate": 5.9473893169580246e-06, "loss": 3.8491, "step": 2690560 }, { "epoch": 0.01, "learning_rate": 5.939003369447504e-06, "loss": 3.8307, "step": 2691072 }, { "epoch": 0.01, "learning_rate": 5.9306174219369845e-06, "loss": 3.8465, "step": 2691584 }, { "epoch": 0.01, "learning_rate": 5.9222314744264636e-06, "loss": 3.841, "step": 2692096 }, { "epoch": 0.01, "learning_rate": 5.9138455269159435e-06, "loss": 3.8564, "step": 2692608 }, { "epoch": 0.01, "learning_rate": 5.9054595794054235e-06, "loss": 3.8412, "step": 2693120 }, { "epoch": 0.01, "learning_rate": 5.897090010698634e-06, "loss": 3.8481, "step": 2693632 }, { "epoch": 0.01, "learning_rate": 5.888704063188115e-06, "loss": 3.8506, "step": 2694144 }, { "epoch": 0.01, "learning_rate": 5.880318115677594e-06, "loss": 3.8557, "step": 2694656 }, { "epoch": 0.01, "learning_rate": 5.871932168167075e-06, "loss": 3.8483, "step": 2695168 }, { "epoch": 0.01, "learning_rate": 5.863546220656554e-06, "loss": 3.8374, "step": 2695680 }, { "epoch": 0.01, "learning_rate": 5.855160273146034e-06, "loss": 3.8298, "step": 2696192 }, { "epoch": 0.01, "learning_rate": 5.846774325635514e-06, "loss": 3.8536, "step": 2696704 }, { "epoch": 0.01, "learning_rate": 5.838388378124994e-06, "loss": 3.8507, "step": 2697216 }, { "epoch": 0.01, "learning_rate": 5.830018809418206e-06, "loss": 3.8447, "step": 2697728 }, { "epoch": 0.01, "learning_rate": 5.8216328619076856e-06, "loss": 3.8377, "step": 2698240 }, { "epoch": 0.01, "learning_rate": 5.813263293200897e-06, "loss": 3.8448, "step": 2698752 }, { "epoch": 0.01, "learning_rate": 5.804877345690376e-06, "loss": 3.8276, "step": 2699264 }, { "epoch": 0.01, "learning_rate": 5.796491398179857e-06, "loss": 3.8473, "step": 2699776 }, { "epoch": 0.01, "learning_rate": 5.788105450669336e-06, "loss": 3.8299, "step": 2700288 }, { "epoch": 0.01, "learning_rate": 5.779719503158816e-06, "loss": 3.8455, "step": 2700800 }, { "epoch": 0.01, "learning_rate": 5.771333555648296e-06, "loss": 3.8512, "step": 2701312 }, { "epoch": 0.01, "learning_rate": 5.762963986941508e-06, "loss": 3.8402, "step": 2701824 }, { "epoch": 0.01, "learning_rate": 5.754578039430988e-06, "loss": 3.8329, "step": 2702336 }, { "epoch": 0.01, "learning_rate": 5.746192091920468e-06, "loss": 3.8429, "step": 2702848 }, { "epoch": 0.01, "learning_rate": 5.737806144409948e-06, "loss": 3.8293, "step": 2703360 }, { "epoch": 0.01, "learning_rate": 5.729420196899428e-06, "loss": 3.8348, "step": 2703872 }, { "epoch": 0.01, "learning_rate": 5.721034249388907e-06, "loss": 3.8486, "step": 2704384 }, { "epoch": 0.01, "learning_rate": 5.712664680682118e-06, "loss": 3.8449, "step": 2704896 }, { "epoch": 0.01, "learning_rate": 5.704278733171598e-06, "loss": 3.8349, "step": 2705408 }, { "epoch": 0.01, "learning_rate": 5.695892785661078e-06, "loss": 3.8293, "step": 2705920 }, { "epoch": 0.01, "learning_rate": 5.687506838150558e-06, "loss": 3.8426, "step": 2706432 }, { "epoch": 0.01, "learning_rate": 5.679120890640038e-06, "loss": 3.8453, "step": 2706944 }, { "epoch": 0.01, "learning_rate": 5.670734943129518e-06, "loss": 3.8468, "step": 2707456 }, { "epoch": 0.01, "learning_rate": 5.662348995618997e-06, "loss": 3.8417, "step": 2707968 }, { "epoch": 0.01, "learning_rate": 5.653963048108478e-06, "loss": 3.8504, "step": 2708480 }, { "epoch": 0.01, "learning_rate": 5.645577100597958e-06, "loss": 3.8514, "step": 2708992 }, { "epoch": 0.01, "learning_rate": 5.6372239106949004e-06, "loss": 3.8399, "step": 2709504 }, { "epoch": 0.01, "learning_rate": 5.62883796318438e-06, "loss": 3.8396, "step": 2710016 }, { "epoch": 0.01, "learning_rate": 5.62045201567386e-06, "loss": 3.8463, "step": 2710528 }, { "epoch": 0.01, "learning_rate": 5.61206606816334e-06, "loss": 3.8465, "step": 2711040 }, { "epoch": 0.01, "learning_rate": 5.603696499456552e-06, "loss": 3.8408, "step": 2711552 }, { "epoch": 0.01, "learning_rate": 5.595310551946031e-06, "loss": 3.8401, "step": 2712064 }, { "epoch": 0.01, "learning_rate": 5.586924604435512e-06, "loss": 3.8483, "step": 2712576 }, { "epoch": 0.01, "learning_rate": 5.578538656924991e-06, "loss": 3.8523, "step": 2713088 }, { "epoch": 0.01, "learning_rate": 5.570152709414471e-06, "loss": 3.845, "step": 2713600 }, { "epoch": 0.01, "learning_rate": 5.561766761903951e-06, "loss": 3.8292, "step": 2714112 }, { "epoch": 0.01, "learning_rate": 5.553380814393431e-06, "loss": 3.8305, "step": 2714624 }, { "epoch": 0.01, "learning_rate": 5.544994866882911e-06, "loss": 3.8401, "step": 2715136 }, { "epoch": 0.01, "learning_rate": 5.536608919372391e-06, "loss": 3.8474, "step": 2715648 }, { "epoch": 0.01, "learning_rate": 5.528222971861871e-06, "loss": 3.8445, "step": 2716160 }, { "epoch": 0.01, "learning_rate": 5.519837024351351e-06, "loss": 3.8365, "step": 2716672 }, { "epoch": 0.02, "learning_rate": 5.5114674556445615e-06, "loss": 3.8498, "step": 2717184 }, { "epoch": 0.02, "learning_rate": 5.503081508134042e-06, "loss": 3.839, "step": 2717696 }, { "epoch": 0.02, "learning_rate": 5.494695560623521e-06, "loss": 3.8371, "step": 2718208 }, { "epoch": 0.02, "learning_rate": 5.486309613113001e-06, "loss": 3.8432, "step": 2718720 }, { "epoch": 0.02, "learning_rate": 5.477940044406213e-06, "loss": 3.8466, "step": 2719232 }, { "epoch": 0.02, "learning_rate": 5.469570475699425e-06, "loss": 3.8548, "step": 2719744 }, { "epoch": 0.02, "learning_rate": 5.4611845281889046e-06, "loss": 3.8391, "step": 2720256 }, { "epoch": 0.02, "learning_rate": 5.452798580678384e-06, "loss": 3.8282, "step": 2720768 }, { "epoch": 0.02, "learning_rate": 5.4444126331678645e-06, "loss": 3.846, "step": 2721280 }, { "epoch": 0.02, "learning_rate": 5.4360266856573436e-06, "loss": 3.8408, "step": 2721792 }, { "epoch": 0.02, "learning_rate": 5.427640738146824e-06, "loss": 3.8531, "step": 2722304 }, { "epoch": 0.02, "learning_rate": 5.4192547906363035e-06, "loss": 3.8511, "step": 2722816 }, { "epoch": 0.02, "learning_rate": 5.4108688431257834e-06, "loss": 3.8387, "step": 2723328 }, { "epoch": 0.02, "learning_rate": 5.402482895615263e-06, "loss": 3.8321, "step": 2723840 }, { "epoch": 0.02, "learning_rate": 5.394096948104743e-06, "loss": 3.8502, "step": 2724352 }, { "epoch": 0.02, "learning_rate": 5.385711000594223e-06, "loss": 3.8292, "step": 2724864 }, { "epoch": 0.02, "learning_rate": 5.377325053083703e-06, "loss": 3.8411, "step": 2725376 }, { "epoch": 0.02, "learning_rate": 5.368955484376915e-06, "loss": 3.8364, "step": 2725888 }, { "epoch": 0.02, "learning_rate": 5.360585915670126e-06, "loss": 3.8449, "step": 2726400 }, { "epoch": 0.02, "learning_rate": 5.352199968159606e-06, "loss": 3.8271, "step": 2726912 }, { "epoch": 0.02, "learning_rate": 5.343814020649086e-06, "loss": 3.8474, "step": 2727424 }, { "epoch": 0.02, "learning_rate": 5.3354280731385656e-06, "loss": 3.8353, "step": 2727936 }, { "epoch": 0.02, "learning_rate": 5.327058504431777e-06, "loss": 3.8379, "step": 2728448 }, { "epoch": 0.02, "learning_rate": 5.318672556921256e-06, "loss": 3.8447, "step": 2728960 }, { "epoch": 0.02, "learning_rate": 5.310286609410737e-06, "loss": 3.8364, "step": 2729472 }, { "epoch": 0.02, "learning_rate": 5.301900661900216e-06, "loss": 3.8597, "step": 2729984 }, { "epoch": 0.02, "learning_rate": 5.293514714389697e-06, "loss": 3.8528, "step": 2730496 }, { "epoch": 0.02, "learning_rate": 5.285128766879176e-06, "loss": 3.845, "step": 2731008 }, { "epoch": 0.02, "learning_rate": 5.276742819368656e-06, "loss": 3.8355, "step": 2731520 }, { "epoch": 0.02, "learning_rate": 5.268356871858136e-06, "loss": 3.8451, "step": 2732032 }, { "epoch": 0.02, "learning_rate": 5.259987303151348e-06, "loss": 3.8443, "step": 2732544 }, { "epoch": 0.02, "learning_rate": 5.251601355640828e-06, "loss": 3.8357, "step": 2733056 }, { "epoch": 0.02, "learning_rate": 5.243215408130308e-06, "loss": 3.849, "step": 2733568 }, { "epoch": 0.02, "learning_rate": 5.2348294606197875e-06, "loss": 3.844, "step": 2734080 }, { "epoch": 0.02, "learning_rate": 5.22647627071673e-06, "loss": 3.8405, "step": 2734592 }, { "epoch": 0.02, "learning_rate": 5.21809032320621e-06, "loss": 3.8397, "step": 2735104 }, { "epoch": 0.02, "learning_rate": 5.20970437569569e-06, "loss": 3.8425, "step": 2735616 }, { "epoch": 0.02, "learning_rate": 5.20131842818517e-06, "loss": 3.8366, "step": 2736128 }, { "epoch": 0.02, "learning_rate": 5.192948859478381e-06, "loss": 3.8485, "step": 2736640 }, { "epoch": 0.02, "learning_rate": 5.184579290771593e-06, "loss": 3.832, "step": 2737152 }, { "epoch": 0.02, "learning_rate": 5.176193343261072e-06, "loss": 3.8517, "step": 2737664 }, { "epoch": 0.02, "learning_rate": 5.167807395750553e-06, "loss": 3.8475, "step": 2738176 }, { "epoch": 0.02, "learning_rate": 5.159421448240032e-06, "loss": 3.8457, "step": 2738688 }, { "epoch": 0.02, "learning_rate": 5.151035500729512e-06, "loss": 3.8395, "step": 2739200 }, { "epoch": 0.02, "learning_rate": 5.142649553218992e-06, "loss": 3.8399, "step": 2739712 }, { "epoch": 0.02, "learning_rate": 5.134263605708472e-06, "loss": 3.8503, "step": 2740224 }, { "epoch": 0.02, "learning_rate": 5.125877658197952e-06, "loss": 3.8477, "step": 2740736 }, { "epoch": 0.02, "learning_rate": 5.117508089491163e-06, "loss": 3.8398, "step": 2741248 }, { "epoch": 0.02, "learning_rate": 5.109122141980644e-06, "loss": 3.8505, "step": 2741760 }, { "epoch": 0.02, "learning_rate": 5.100736194470123e-06, "loss": 3.8468, "step": 2742272 }, { "epoch": 0.02, "learning_rate": 5.092350246959603e-06, "loss": 3.8537, "step": 2742784 }, { "epoch": 0.02, "learning_rate": 5.083964299449083e-06, "loss": 3.8431, "step": 2743296 }, { "epoch": 0.02, "learning_rate": 5.0755783519385626e-06, "loss": 3.8554, "step": 2743808 }, { "epoch": 0.02, "learning_rate": 5.0671924044280425e-06, "loss": 3.8489, "step": 2744320 }, { "epoch": 0.02, "learning_rate": 5.058822835721254e-06, "loss": 3.8409, "step": 2744832 }, { "epoch": 0.02, "learning_rate": 5.050436888210734e-06, "loss": 3.8453, "step": 2745344 }, { "epoch": 0.02, "learning_rate": 5.042050940700214e-06, "loss": 3.8526, "step": 2745856 }, { "epoch": 0.02, "learning_rate": 5.033664993189693e-06, "loss": 3.8448, "step": 2746368 }, { "epoch": 0.02, "learning_rate": 5.025295424482905e-06, "loss": 3.834, "step": 2746880 }, { "epoch": 0.02, "learning_rate": 5.016909476972385e-06, "loss": 3.8457, "step": 2747392 }, { "epoch": 0.03, "eval_loss": 3.977097749710083, "eval_runtime": 291.9653, "eval_samples_per_second": 1306.974, "eval_steps_per_second": 40.844, "step": 2747520 }, { "epoch": 1.0, "learning_rate": 5.008523529461865e-06, "loss": 3.8386, "step": 2747904 }, { "epoch": 1.0, "learning_rate": 5.000137581951345e-06, "loss": 3.8364, "step": 2748416 }, { "epoch": 1.0, "learning_rate": 4.991751634440825e-06, "loss": 3.8564, "step": 2748928 }, { "epoch": 1.0, "learning_rate": 4.983365686930305e-06, "loss": 3.8556, "step": 2749440 }, { "epoch": 1.0, "learning_rate": 4.9749797394197845e-06, "loss": 3.852, "step": 2749952 }, { "epoch": 1.0, "learning_rate": 4.9665937919092645e-06, "loss": 3.8442, "step": 2750464 }, { "epoch": 1.0, "learning_rate": 4.9582078443987445e-06, "loss": 3.8459, "step": 2750976 }, { "epoch": 1.0, "learning_rate": 4.949838275691956e-06, "loss": 3.8298, "step": 2751488 }, { "epoch": 1.0, "learning_rate": 4.941452328181435e-06, "loss": 3.854, "step": 2752000 }, { "epoch": 1.0, "learning_rate": 4.933082759474647e-06, "loss": 3.8508, "step": 2752512 }, { "epoch": 1.0, "learning_rate": 4.924696811964127e-06, "loss": 3.8436, "step": 2753024 }, { "epoch": 1.0, "learning_rate": 4.916310864453606e-06, "loss": 3.8531, "step": 2753536 }, { "epoch": 1.0, "learning_rate": 4.9079412957468175e-06, "loss": 3.8402, "step": 2754048 }, { "epoch": 1.0, "learning_rate": 4.8995553482362975e-06, "loss": 3.8422, "step": 2754560 }, { "epoch": 1.0, "learning_rate": 4.8911694007257775e-06, "loss": 3.8378, "step": 2755072 }, { "epoch": 1.0, "learning_rate": 4.882783453215257e-06, "loss": 3.8385, "step": 2755584 }, { "epoch": 1.0, "learning_rate": 4.874397505704738e-06, "loss": 3.8383, "step": 2756096 }, { "epoch": 1.0, "learning_rate": 4.866011558194217e-06, "loss": 3.8382, "step": 2756608 }, { "epoch": 1.0, "learning_rate": 4.857625610683697e-06, "loss": 3.8419, "step": 2757120 }, { "epoch": 1.0, "learning_rate": 4.849239663173177e-06, "loss": 3.8635, "step": 2757632 }, { "epoch": 1.0, "learning_rate": 4.840870094466388e-06, "loss": 3.8468, "step": 2758144 }, { "epoch": 1.0, "learning_rate": 4.832484146955869e-06, "loss": 3.8531, "step": 2758656 }, { "epoch": 1.0, "learning_rate": 4.824098199445348e-06, "loss": 3.8456, "step": 2759168 }, { "epoch": 1.0, "learning_rate": 4.815712251934829e-06, "loss": 3.8522, "step": 2759680 }, { "epoch": 1.0, "learning_rate": 4.807326304424308e-06, "loss": 3.8402, "step": 2760192 }, { "epoch": 1.0, "learning_rate": 4.798940356913788e-06, "loss": 3.8455, "step": 2760704 }, { "epoch": 1.0, "learning_rate": 4.790554409403268e-06, "loss": 3.8404, "step": 2761216 }, { "epoch": 1.0, "learning_rate": 4.782168461892748e-06, "loss": 3.8351, "step": 2761728 }, { "epoch": 1.0, "learning_rate": 4.773798893185959e-06, "loss": 3.8337, "step": 2762240 }, { "epoch": 1.0, "learning_rate": 4.765412945675439e-06, "loss": 3.8448, "step": 2762752 }, { "epoch": 1.01, "learning_rate": 4.757026998164919e-06, "loss": 3.8418, "step": 2763264 }, { "epoch": 1.01, "learning_rate": 4.748641050654399e-06, "loss": 3.8515, "step": 2763776 }, { "epoch": 1.01, "learning_rate": 4.740255103143878e-06, "loss": 3.847, "step": 2764288 }, { "epoch": 1.01, "learning_rate": 4.731869155633359e-06, "loss": 3.8503, "step": 2764800 }, { "epoch": 1.01, "learning_rate": 4.72349958692657e-06, "loss": 3.8411, "step": 2765312 }, { "epoch": 1.01, "learning_rate": 4.71511363941605e-06, "loss": 3.8541, "step": 2765824 }, { "epoch": 1.01, "learning_rate": 4.70672769190553e-06, "loss": 3.837, "step": 2766336 }, { "epoch": 1.01, "learning_rate": 4.69834174439501e-06, "loss": 3.8437, "step": 2766848 }, { "epoch": 1.01, "learning_rate": 4.68995579688449e-06, "loss": 3.8283, "step": 2767360 }, { "epoch": 1.01, "learning_rate": 4.68156984937397e-06, "loss": 3.8439, "step": 2767872 }, { "epoch": 1.01, "learning_rate": 4.673200280667181e-06, "loss": 3.8418, "step": 2768384 }, { "epoch": 1.01, "learning_rate": 4.664830711960393e-06, "loss": 3.8542, "step": 2768896 }, { "epoch": 1.01, "learning_rate": 4.656444764449872e-06, "loss": 3.8401, "step": 2769408 }, { "epoch": 1.01, "learning_rate": 4.648058816939352e-06, "loss": 3.8458, "step": 2769920 }, { "epoch": 1.01, "learning_rate": 4.639672869428832e-06, "loss": 3.8491, "step": 2770432 }, { "epoch": 1.01, "learning_rate": 4.631286921918312e-06, "loss": 3.8506, "step": 2770944 }, { "epoch": 1.01, "learning_rate": 4.622900974407792e-06, "loss": 3.8459, "step": 2771456 }, { "epoch": 1.01, "learning_rate": 4.614515026897272e-06, "loss": 3.834, "step": 2771968 }, { "epoch": 1.01, "learning_rate": 4.606129079386751e-06, "loss": 3.8271, "step": 2772480 }, { "epoch": 1.01, "learning_rate": 4.597759510679963e-06, "loss": 3.8547, "step": 2772992 }, { "epoch": 1.01, "learning_rate": 4.589389941973174e-06, "loss": 3.8478, "step": 2773504 }, { "epoch": 1.01, "learning_rate": 4.581003994462654e-06, "loss": 3.8401, "step": 2774016 }, { "epoch": 1.01, "learning_rate": 4.572618046952134e-06, "loss": 3.841, "step": 2774528 }, { "epoch": 1.01, "learning_rate": 4.564232099441614e-06, "loss": 3.8409, "step": 2775040 }, { "epoch": 1.01, "learning_rate": 4.555846151931094e-06, "loss": 3.8245, "step": 2775552 }, { "epoch": 1.01, "learning_rate": 4.547460204420574e-06, "loss": 3.8404, "step": 2776064 }, { "epoch": 1.01, "learning_rate": 4.539074256910054e-06, "loss": 3.8316, "step": 2776576 }, { "epoch": 1.01, "learning_rate": 4.530688309399533e-06, "loss": 3.8407, "step": 2777088 }, { "epoch": 1.01, "learning_rate": 4.522302361889014e-06, "loss": 3.851, "step": 2777600 }, { "epoch": 1.01, "learning_rate": 4.513916414378493e-06, "loss": 3.8374, "step": 2778112 }, { "epoch": 1.01, "learning_rate": 4.505546845671705e-06, "loss": 3.8293, "step": 2778624 }, { "epoch": 1.01, "learning_rate": 4.497160898161185e-06, "loss": 3.8476, "step": 2779136 }, { "epoch": 1.01, "learning_rate": 4.4887749506506645e-06, "loss": 3.8235, "step": 2779648 }, { "epoch": 1.01, "learning_rate": 4.4803890031401445e-06, "loss": 3.8368, "step": 2780160 }, { "epoch": 1.01, "learning_rate": 4.472019434433356e-06, "loss": 3.8437, "step": 2780672 }, { "epoch": 1.01, "learning_rate": 4.463633486922836e-06, "loss": 3.8438, "step": 2781184 }, { "epoch": 1.01, "learning_rate": 4.455247539412315e-06, "loss": 3.8329, "step": 2781696 }, { "epoch": 1.01, "learning_rate": 4.446861591901796e-06, "loss": 3.8298, "step": 2782208 }, { "epoch": 1.01, "learning_rate": 4.438475644391275e-06, "loss": 3.8342, "step": 2782720 }, { "epoch": 1.01, "learning_rate": 4.430089696880756e-06, "loss": 3.8438, "step": 2783232 }, { "epoch": 1.01, "learning_rate": 4.421703749370235e-06, "loss": 3.8421, "step": 2783744 }, { "epoch": 1.01, "learning_rate": 4.413317801859715e-06, "loss": 3.8382, "step": 2784256 }, { "epoch": 1.01, "learning_rate": 4.404931854349195e-06, "loss": 3.8473, "step": 2784768 }, { "epoch": 1.01, "learning_rate": 4.396545906838675e-06, "loss": 3.8498, "step": 2785280 }, { "epoch": 1.01, "learning_rate": 4.388159959328155e-06, "loss": 3.8394, "step": 2785792 }, { "epoch": 1.01, "learning_rate": 4.3797903906213665e-06, "loss": 3.832, "step": 2786304 }, { "epoch": 1.01, "learning_rate": 4.3714044431108464e-06, "loss": 3.8495, "step": 2786816 }, { "epoch": 1.01, "learning_rate": 4.363034874404057e-06, "loss": 3.8443, "step": 2787328 }, { "epoch": 1.01, "learning_rate": 4.354648926893537e-06, "loss": 3.8363, "step": 2787840 }, { "epoch": 1.01, "learning_rate": 4.346262979383017e-06, "loss": 3.839, "step": 2788352 }, { "epoch": 1.01, "learning_rate": 4.337877031872497e-06, "loss": 3.8466, "step": 2788864 }, { "epoch": 1.01, "learning_rate": 4.329491084361977e-06, "loss": 3.8536, "step": 2789376 }, { "epoch": 1.01, "learning_rate": 4.321105136851457e-06, "loss": 3.8393, "step": 2789888 }, { "epoch": 1.01, "learning_rate": 4.312719189340936e-06, "loss": 3.8265, "step": 2790400 }, { "epoch": 1.01, "learning_rate": 4.304333241830417e-06, "loss": 3.8376, "step": 2790912 }, { "epoch": 1.01, "learning_rate": 4.295947294319896e-06, "loss": 3.8323, "step": 2791424 }, { "epoch": 1.01, "learning_rate": 4.287561346809377e-06, "loss": 3.8444, "step": 2791936 }, { "epoch": 1.01, "learning_rate": 4.279175399298856e-06, "loss": 3.8429, "step": 2792448 }, { "epoch": 1.01, "learning_rate": 4.270805830592068e-06, "loss": 3.8318, "step": 2792960 }, { "epoch": 1.02, "learning_rate": 4.2624198830815475e-06, "loss": 3.8472, "step": 2793472 }, { "epoch": 1.02, "learning_rate": 4.2540339355710275e-06, "loss": 3.8357, "step": 2793984 }, { "epoch": 1.02, "learning_rate": 4.2456479880605074e-06, "loss": 3.8394, "step": 2794496 }, { "epoch": 1.02, "learning_rate": 4.237262040549987e-06, "loss": 3.8358, "step": 2795008 }, { "epoch": 1.02, "learning_rate": 4.228876093039467e-06, "loss": 3.8428, "step": 2795520 }, { "epoch": 1.02, "learning_rate": 4.220506524332678e-06, "loss": 3.8544, "step": 2796032 }, { "epoch": 1.02, "learning_rate": 4.212120576822159e-06, "loss": 3.8422, "step": 2796544 }, { "epoch": 1.02, "learning_rate": 4.203734629311638e-06, "loss": 3.8213, "step": 2797056 }, { "epoch": 1.02, "learning_rate": 4.195348681801118e-06, "loss": 3.8412, "step": 2797568 }, { "epoch": 1.02, "learning_rate": 4.18697911309433e-06, "loss": 3.8395, "step": 2798080 }, { "epoch": 1.02, "learning_rate": 4.17859316558381e-06, "loss": 3.8459, "step": 2798592 }, { "epoch": 1.02, "learning_rate": 4.1702072180732896e-06, "loss": 3.8508, "step": 2799104 }, { "epoch": 1.02, "learning_rate": 4.1618212705627695e-06, "loss": 3.8392, "step": 2799616 }, { "epoch": 1.02, "learning_rate": 4.1534353230522495e-06, "loss": 3.8341, "step": 2800128 }, { "epoch": 1.02, "learning_rate": 4.1450493755417294e-06, "loss": 3.8448, "step": 2800640 }, { "epoch": 1.02, "learning_rate": 4.1366634280312085e-06, "loss": 3.8236, "step": 2801152 }, { "epoch": 1.02, "learning_rate": 4.128277480520689e-06, "loss": 3.8411, "step": 2801664 }, { "epoch": 1.02, "learning_rate": 4.1199079118139e-06, "loss": 3.8344, "step": 2802176 }, { "epoch": 1.02, "learning_rate": 4.111538343107112e-06, "loss": 3.8447, "step": 2802688 }, { "epoch": 1.02, "learning_rate": 4.103152395596591e-06, "loss": 3.8276, "step": 2803200 }, { "epoch": 1.02, "learning_rate": 4.094782826889803e-06, "loss": 3.8452, "step": 2803712 }, { "epoch": 1.02, "learning_rate": 4.0863968793792825e-06, "loss": 3.8314, "step": 2804224 }, { "epoch": 1.02, "learning_rate": 4.078010931868763e-06, "loss": 3.8353, "step": 2804736 }, { "epoch": 1.02, "learning_rate": 4.069624984358242e-06, "loss": 3.8447, "step": 2805248 }, { "epoch": 1.02, "learning_rate": 4.061239036847723e-06, "loss": 3.8384, "step": 2805760 }, { "epoch": 1.02, "learning_rate": 4.052869468140934e-06, "loss": 3.8538, "step": 2806272 }, { "epoch": 1.02, "learning_rate": 4.044483520630414e-06, "loss": 3.8492, "step": 2806784 }, { "epoch": 1.02, "learning_rate": 4.036097573119894e-06, "loss": 3.8393, "step": 2807296 }, { "epoch": 1.02, "learning_rate": 4.027711625609373e-06, "loss": 3.8407, "step": 2807808 }, { "epoch": 1.02, "learning_rate": 4.019325678098854e-06, "loss": 3.8359, "step": 2808320 }, { "epoch": 1.02, "learning_rate": 4.010939730588333e-06, "loss": 3.8439, "step": 2808832 }, { "epoch": 1.02, "learning_rate": 4.002553783077814e-06, "loss": 3.8332, "step": 2809344 }, { "epoch": 1.02, "learning_rate": 3.994167835567293e-06, "loss": 3.8493, "step": 2809856 }, { "epoch": 1.02, "learning_rate": 3.985781888056773e-06, "loss": 3.8353, "step": 2810368 }, { "epoch": 1.02, "learning_rate": 3.977395940546253e-06, "loss": 3.8363, "step": 2810880 }, { "epoch": 1.02, "learning_rate": 3.969026371839464e-06, "loss": 3.8375, "step": 2811392 }, { "epoch": 1.02, "learning_rate": 3.960640424328944e-06, "loss": 3.8444, "step": 2811904 }, { "epoch": 1.02, "learning_rate": 3.952254476818424e-06, "loss": 3.8341, "step": 2812416 }, { "epoch": 1.02, "learning_rate": 3.943868529307904e-06, "loss": 3.8441, "step": 2812928 }, { "epoch": 1.02, "learning_rate": 3.935482581797384e-06, "loss": 3.8307, "step": 2813440 }, { "epoch": 1.02, "learning_rate": 3.927096634286863e-06, "loss": 3.8487, "step": 2813952 }, { "epoch": 1.02, "learning_rate": 3.918710686776344e-06, "loss": 3.846, "step": 2814464 }, { "epoch": 1.02, "learning_rate": 3.910324739265823e-06, "loss": 3.8448, "step": 2814976 }, { "epoch": 1.02, "learning_rate": 3.901955170559035e-06, "loss": 3.8379, "step": 2815488 }, { "epoch": 1.02, "learning_rate": 3.8935856018522465e-06, "loss": 3.8359, "step": 2816000 }, { "epoch": 1.02, "learning_rate": 3.8851996543417264e-06, "loss": 3.8505, "step": 2816512 }, { "epoch": 1.02, "learning_rate": 3.876813706831206e-06, "loss": 3.8423, "step": 2817024 }, { "epoch": 1.02, "learning_rate": 3.868427759320686e-06, "loss": 3.8375, "step": 2817536 }, { "epoch": 1.02, "learning_rate": 3.860041811810166e-06, "loss": 3.8506, "step": 2818048 }, { "epoch": 1.02, "learning_rate": 3.851655864299645e-06, "loss": 3.8444, "step": 2818560 }, { "epoch": 1.02, "learning_rate": 3.843269916789126e-06, "loss": 3.8524, "step": 2819072 }, { "epoch": 1.02, "learning_rate": 3.834883969278605e-06, "loss": 3.8423, "step": 2819584 }, { "epoch": 1.02, "learning_rate": 3.826514400571817e-06, "loss": 3.8514, "step": 2820096 }, { "epoch": 1.02, "learning_rate": 3.818128453061297e-06, "loss": 3.8481, "step": 2820608 }, { "epoch": 1.02, "learning_rate": 3.8097425055507773e-06, "loss": 3.8376, "step": 2821120 }, { "epoch": 1.02, "learning_rate": 3.801356558040257e-06, "loss": 3.8438, "step": 2821632 }, { "epoch": 1.02, "learning_rate": 3.7929869893334685e-06, "loss": 3.8463, "step": 2822144 }, { "epoch": 1.02, "learning_rate": 3.784601041822948e-06, "loss": 3.8446, "step": 2822656 }, { "epoch": 1.02, "learning_rate": 3.7762150943124275e-06, "loss": 3.8293, "step": 2823168 }, { "epoch": 1.02, "learning_rate": 3.767829146801908e-06, "loss": 3.8448, "step": 2823680 }, { "epoch": 1.03, "eval_loss": 3.976405143737793, "eval_runtime": 291.0399, "eval_samples_per_second": 1311.129, "eval_steps_per_second": 40.974, "step": 2823840 }, { "epoch": 0.0, "learning_rate": 3.7594431992913874e-06, "loss": 3.8329, "step": 2824192 }, { "epoch": 0.0, "learning_rate": 3.751057251780867e-06, "loss": 3.8336, "step": 2824704 }, { "epoch": 0.0, "learning_rate": 3.7426713042703474e-06, "loss": 3.8521, "step": 2825216 }, { "epoch": 0.0, "learning_rate": 3.7342853567598273e-06, "loss": 3.853, "step": 2825728 }, { "epoch": 0.0, "learning_rate": 3.7258994092493073e-06, "loss": 3.8479, "step": 2826240 }, { "epoch": 0.0, "learning_rate": 3.7175134617387872e-06, "loss": 3.8422, "step": 2826752 }, { "epoch": 0.0, "learning_rate": 3.7091275142282668e-06, "loss": 3.8433, "step": 2827264 }, { "epoch": 0.0, "learning_rate": 3.700741566717747e-06, "loss": 3.8317, "step": 2827776 }, { "epoch": 0.0, "learning_rate": 3.6923556192072267e-06, "loss": 3.8472, "step": 2828288 }, { "epoch": 0.0, "learning_rate": 3.683969671696707e-06, "loss": 3.8506, "step": 2828800 }, { "epoch": 0.0, "learning_rate": 3.6755837241861866e-06, "loss": 3.841, "step": 2829312 }, { "epoch": 0.0, "learning_rate": 3.667197776675666e-06, "loss": 3.8486, "step": 2829824 }, { "epoch": 0.0, "learning_rate": 3.6588282079688777e-06, "loss": 3.8393, "step": 2830336 }, { "epoch": 0.0, "learning_rate": 3.6504422604583573e-06, "loss": 3.8422, "step": 2830848 }, { "epoch": 0.0, "learning_rate": 3.6420563129478377e-06, "loss": 3.8331, "step": 2831360 }, { "epoch": 0.0, "learning_rate": 3.633670365437317e-06, "loss": 3.837, "step": 2831872 }, { "epoch": 0.0, "learning_rate": 3.6252844179267976e-06, "loss": 3.8355, "step": 2832384 }, { "epoch": 0.0, "learning_rate": 3.616898470416277e-06, "loss": 3.8361, "step": 2832896 }, { "epoch": 0.0, "learning_rate": 3.608512522905757e-06, "loss": 3.8412, "step": 2833408 }, { "epoch": 0.0, "learning_rate": 3.600126575395237e-06, "loss": 3.855, "step": 2833920 }, { "epoch": 0.0, "learning_rate": 3.5917570066884482e-06, "loss": 3.8496, "step": 2834432 }, { "epoch": 0.0, "learning_rate": 3.5833710591779286e-06, "loss": 3.8499, "step": 2834944 }, { "epoch": 0.0, "learning_rate": 3.574985111667408e-06, "loss": 3.8422, "step": 2835456 }, { "epoch": 0.0, "learning_rate": 3.5665991641568885e-06, "loss": 3.8515, "step": 2835968 }, { "epoch": 0.0, "learning_rate": 3.558213216646368e-06, "loss": 3.8352, "step": 2836480 }, { "epoch": 0.0, "learning_rate": 3.5498436479395797e-06, "loss": 3.8492, "step": 2836992 }, { "epoch": 0.0, "learning_rate": 3.5414740792327905e-06, "loss": 3.8368, "step": 2837504 }, { "epoch": 0.0, "learning_rate": 3.533088131722271e-06, "loss": 3.8311, "step": 2838016 }, { "epoch": 0.0, "learning_rate": 3.5247021842117504e-06, "loss": 3.8368, "step": 2838528 }, { "epoch": 0.0, "learning_rate": 3.5163162367012303e-06, "loss": 3.8375, "step": 2839040 }, { "epoch": 0.01, "learning_rate": 3.5079302891907107e-06, "loss": 3.8409, "step": 2839552 }, { "epoch": 0.01, "learning_rate": 3.4995443416801903e-06, "loss": 3.844, "step": 2840064 }, { "epoch": 0.01, "learning_rate": 3.4911583941696706e-06, "loss": 3.8489, "step": 2840576 }, { "epoch": 0.01, "learning_rate": 3.48277244665915e-06, "loss": 3.8482, "step": 2841088 }, { "epoch": 0.01, "learning_rate": 3.474402877952362e-06, "loss": 3.8382, "step": 2841600 }, { "epoch": 0.01, "learning_rate": 3.4660169304418413e-06, "loss": 3.849, "step": 2842112 }, { "epoch": 0.01, "learning_rate": 3.457630982931321e-06, "loss": 3.8404, "step": 2842624 }, { "epoch": 0.01, "learning_rate": 3.4492450354208012e-06, "loss": 3.8364, "step": 2843136 }, { "epoch": 0.01, "learning_rate": 3.4408590879102808e-06, "loss": 3.8322, "step": 2843648 }, { "epoch": 0.01, "learning_rate": 3.432473140399761e-06, "loss": 3.8369, "step": 2844160 }, { "epoch": 0.01, "learning_rate": 3.4241035716929724e-06, "loss": 3.8424, "step": 2844672 }, { "epoch": 0.01, "learning_rate": 3.4157176241824523e-06, "loss": 3.8478, "step": 2845184 }, { "epoch": 0.01, "learning_rate": 3.4073316766719323e-06, "loss": 3.8387, "step": 2845696 }, { "epoch": 0.01, "learning_rate": 3.398945729161412e-06, "loss": 3.8413, "step": 2846208 }, { "epoch": 0.01, "learning_rate": 3.390559781650892e-06, "loss": 3.8478, "step": 2846720 }, { "epoch": 0.01, "learning_rate": 3.3821738341403717e-06, "loss": 3.8467, "step": 2847232 }, { "epoch": 0.01, "learning_rate": 3.373787886629852e-06, "loss": 3.8468, "step": 2847744 }, { "epoch": 0.01, "learning_rate": 3.365418317923063e-06, "loss": 3.8334, "step": 2848256 }, { "epoch": 0.01, "learning_rate": 3.3570323704125433e-06, "loss": 3.821, "step": 2848768 }, { "epoch": 0.01, "learning_rate": 3.348646422902023e-06, "loss": 3.8537, "step": 2849280 }, { "epoch": 0.01, "learning_rate": 3.3402768541952344e-06, "loss": 3.8446, "step": 2849792 }, { "epoch": 0.01, "learning_rate": 3.331890906684714e-06, "loss": 3.8409, "step": 2850304 }, { "epoch": 0.01, "learning_rate": 3.323504959174194e-06, "loss": 3.8378, "step": 2850816 }, { "epoch": 0.01, "learning_rate": 3.315119011663674e-06, "loss": 3.8332, "step": 2851328 }, { "epoch": 0.01, "learning_rate": 3.306733064153154e-06, "loss": 3.8261, "step": 2851840 }, { "epoch": 0.01, "learning_rate": 3.298347116642634e-06, "loss": 3.8356, "step": 2852352 }, { "epoch": 0.01, "learning_rate": 3.289977547935845e-06, "loss": 3.8307, "step": 2852864 }, { "epoch": 0.01, "learning_rate": 3.2815916004253254e-06, "loss": 3.837, "step": 2853376 }, { "epoch": 0.01, "learning_rate": 3.273205652914805e-06, "loss": 3.8483, "step": 2853888 }, { "epoch": 0.01, "learning_rate": 3.2648197054042845e-06, "loss": 3.8359, "step": 2854400 }, { "epoch": 0.01, "learning_rate": 3.256433757893765e-06, "loss": 3.828, "step": 2854912 }, { "epoch": 0.01, "learning_rate": 3.2480478103832444e-06, "loss": 3.8447, "step": 2855424 }, { "epoch": 0.01, "learning_rate": 3.2396618628727247e-06, "loss": 3.824, "step": 2855936 }, { "epoch": 0.01, "learning_rate": 3.2312759153622043e-06, "loss": 3.831, "step": 2856448 }, { "epoch": 0.01, "learning_rate": 3.222889967851684e-06, "loss": 3.8432, "step": 2856960 }, { "epoch": 0.01, "learning_rate": 3.2145203991448954e-06, "loss": 3.8429, "step": 2857472 }, { "epoch": 0.01, "learning_rate": 3.2061344516343754e-06, "loss": 3.8315, "step": 2857984 }, { "epoch": 0.01, "learning_rate": 3.1977485041238558e-06, "loss": 3.8296, "step": 2858496 }, { "epoch": 0.01, "learning_rate": 3.1893625566133353e-06, "loss": 3.8309, "step": 2859008 }, { "epoch": 0.01, "learning_rate": 3.180976609102815e-06, "loss": 3.8369, "step": 2859520 }, { "epoch": 0.01, "learning_rate": 3.1725906615922952e-06, "loss": 3.8438, "step": 2860032 }, { "epoch": 0.01, "learning_rate": 3.1642047140817748e-06, "loss": 3.8361, "step": 2860544 }, { "epoch": 0.01, "learning_rate": 3.155818766571255e-06, "loss": 3.8423, "step": 2861056 }, { "epoch": 0.01, "learning_rate": 3.147449197864466e-06, "loss": 3.8464, "step": 2861568 }, { "epoch": 0.01, "learning_rate": 3.1390632503539463e-06, "loss": 3.8455, "step": 2862080 }, { "epoch": 0.01, "learning_rate": 3.130677302843426e-06, "loss": 3.8268, "step": 2862592 }, { "epoch": 0.01, "learning_rate": 3.122291355332906e-06, "loss": 3.8445, "step": 2863104 }, { "epoch": 0.01, "learning_rate": 3.1139545442335804e-06, "loss": 3.8453, "step": 2863616 }, { "epoch": 0.01, "learning_rate": 3.1055685967230603e-06, "loss": 3.8301, "step": 2864128 }, { "epoch": 0.01, "learning_rate": 3.0971826492125403e-06, "loss": 3.8413, "step": 2864640 }, { "epoch": 0.01, "learning_rate": 3.08879670170202e-06, "loss": 3.8412, "step": 2865152 }, { "epoch": 0.01, "learning_rate": 3.0804107541914998e-06, "loss": 3.8522, "step": 2865664 }, { "epoch": 0.01, "learning_rate": 3.0720248066809797e-06, "loss": 3.8389, "step": 2866176 }, { "epoch": 0.01, "learning_rate": 3.0636388591704597e-06, "loss": 3.82, "step": 2866688 }, { "epoch": 0.01, "learning_rate": 3.0552529116599392e-06, "loss": 3.8363, "step": 2867200 }, { "epoch": 0.01, "learning_rate": 3.046866964149419e-06, "loss": 3.8324, "step": 2867712 }, { "epoch": 0.01, "learning_rate": 3.038481016638899e-06, "loss": 3.8411, "step": 2868224 }, { "epoch": 0.01, "learning_rate": 3.0301114479321108e-06, "loss": 3.8387, "step": 2868736 }, { "epoch": 0.01, "learning_rate": 3.0217255004215907e-06, "loss": 3.8335, "step": 2869248 }, { "epoch": 0.02, "learning_rate": 3.0133395529110707e-06, "loss": 3.843, "step": 2869760 }, { "epoch": 0.02, "learning_rate": 3.0049536054005506e-06, "loss": 3.8365, "step": 2870272 }, { "epoch": 0.02, "learning_rate": 2.99656765789003e-06, "loss": 3.8315, "step": 2870784 }, { "epoch": 0.02, "learning_rate": 2.988198089183242e-06, "loss": 3.8392, "step": 2871296 }, { "epoch": 0.02, "learning_rate": 2.9798121416727213e-06, "loss": 3.8448, "step": 2871808 }, { "epoch": 0.02, "learning_rate": 2.9714261941622013e-06, "loss": 3.8499, "step": 2872320 }, { "epoch": 0.02, "learning_rate": 2.9630402466516812e-06, "loss": 3.8387, "step": 2872832 }, { "epoch": 0.02, "learning_rate": 2.9546706779448925e-06, "loss": 3.8243, "step": 2873344 }, { "epoch": 0.02, "learning_rate": 2.9462847304343724e-06, "loss": 3.8396, "step": 2873856 }, { "epoch": 0.02, "learning_rate": 2.9378987829238524e-06, "loss": 3.8382, "step": 2874368 }, { "epoch": 0.02, "learning_rate": 2.929529214217064e-06, "loss": 3.8446, "step": 2874880 }, { "epoch": 0.02, "learning_rate": 2.921143266706544e-06, "loss": 3.8484, "step": 2875392 }, { "epoch": 0.02, "learning_rate": 2.912757319196024e-06, "loss": 3.8311, "step": 2875904 }, { "epoch": 0.02, "learning_rate": 2.9043713716855035e-06, "loss": 3.833, "step": 2876416 }, { "epoch": 0.02, "learning_rate": 2.8959854241749834e-06, "loss": 3.8442, "step": 2876928 }, { "epoch": 0.02, "learning_rate": 2.8875994766644634e-06, "loss": 3.8223, "step": 2877440 }, { "epoch": 0.02, "learning_rate": 2.8792135291539433e-06, "loss": 3.8398, "step": 2877952 }, { "epoch": 0.02, "learning_rate": 2.8708275816434233e-06, "loss": 3.8257, "step": 2878464 }, { "epoch": 0.02, "learning_rate": 2.862441634132903e-06, "loss": 3.8445, "step": 2878976 }, { "epoch": 0.02, "learning_rate": 2.8540556866223828e-06, "loss": 3.8267, "step": 2879488 }, { "epoch": 0.02, "learning_rate": 2.8456697391118627e-06, "loss": 3.8419, "step": 2880000 }, { "epoch": 0.02, "learning_rate": 2.8372837916013427e-06, "loss": 3.8344, "step": 2880512 }, { "epoch": 0.02, "learning_rate": 2.828914222894554e-06, "loss": 3.828, "step": 2881024 }, { "epoch": 0.02, "learning_rate": 2.8205446541877655e-06, "loss": 3.8427, "step": 2881536 }, { "epoch": 0.02, "learning_rate": 2.8121587066772455e-06, "loss": 3.8329, "step": 2882048 }, { "epoch": 0.02, "learning_rate": 2.8037727591667254e-06, "loss": 3.8535, "step": 2882560 }, { "epoch": 0.02, "learning_rate": 2.7953868116562054e-06, "loss": 3.8504, "step": 2883072 }, { "epoch": 0.02, "learning_rate": 2.787000864145685e-06, "loss": 3.836, "step": 2883584 }, { "epoch": 0.02, "learning_rate": 2.778614916635165e-06, "loss": 3.8427, "step": 2884096 }, { "epoch": 0.02, "learning_rate": 2.770228969124645e-06, "loss": 3.8322, "step": 2884608 }, { "epoch": 0.02, "learning_rate": 2.7618430216141248e-06, "loss": 3.8396, "step": 2885120 }, { "epoch": 0.02, "learning_rate": 2.753473452907336e-06, "loss": 3.835, "step": 2885632 }, { "epoch": 0.02, "learning_rate": 2.745087505396816e-06, "loss": 3.8436, "step": 2886144 }, { "epoch": 0.02, "learning_rate": 2.7367015578862955e-06, "loss": 3.8377, "step": 2886656 }, { "epoch": 0.02, "learning_rate": 2.7283156103757754e-06, "loss": 3.8329, "step": 2887168 }, { "epoch": 0.02, "learning_rate": 2.719946041668987e-06, "loss": 3.839, "step": 2887680 }, { "epoch": 0.02, "learning_rate": 2.711560094158467e-06, "loss": 3.8385, "step": 2888192 }, { "epoch": 0.02, "learning_rate": 2.703174146647947e-06, "loss": 3.832, "step": 2888704 }, { "epoch": 0.02, "learning_rate": 2.694788199137427e-06, "loss": 3.8418, "step": 2889216 }, { "epoch": 0.02, "learning_rate": 2.686418630430638e-06, "loss": 3.8264, "step": 2889728 }, { "epoch": 0.02, "learning_rate": 2.678032682920118e-06, "loss": 3.8529, "step": 2890240 }, { "epoch": 0.02, "learning_rate": 2.669646735409598e-06, "loss": 3.837, "step": 2890752 }, { "epoch": 0.02, "learning_rate": 2.6612607878990776e-06, "loss": 3.8463, "step": 2891264 }, { "epoch": 0.02, "learning_rate": 2.6528912191922892e-06, "loss": 3.8326, "step": 2891776 }, { "epoch": 0.02, "learning_rate": 2.644505271681769e-06, "loss": 3.8374, "step": 2892288 }, { "epoch": 0.02, "learning_rate": 2.636119324171249e-06, "loss": 3.8481, "step": 2892800 }, { "epoch": 0.02, "learning_rate": 2.627733376660729e-06, "loss": 3.8384, "step": 2893312 }, { "epoch": 0.02, "learning_rate": 2.619347429150209e-06, "loss": 3.8371, "step": 2893824 }, { "epoch": 0.02, "learning_rate": 2.610961481639689e-06, "loss": 3.8478, "step": 2894336 }, { "epoch": 0.02, "learning_rate": 2.6025755341291686e-06, "loss": 3.8426, "step": 2894848 }, { "epoch": 0.02, "learning_rate": 2.5941895866186485e-06, "loss": 3.8504, "step": 2895360 }, { "epoch": 0.02, "learning_rate": 2.5858363967155914e-06, "loss": 3.8359, "step": 2895872 }, { "epoch": 0.02, "learning_rate": 2.5774504492050714e-06, "loss": 3.8479, "step": 2896384 }, { "epoch": 0.02, "learning_rate": 2.569064501694551e-06, "loss": 3.8438, "step": 2896896 }, { "epoch": 0.02, "learning_rate": 2.560678554184031e-06, "loss": 3.8391, "step": 2897408 }, { "epoch": 0.02, "learning_rate": 2.552292606673511e-06, "loss": 3.8423, "step": 2897920 }, { "epoch": 0.02, "learning_rate": 2.5439066591629908e-06, "loss": 3.8422, "step": 2898432 }, { "epoch": 0.02, "learning_rate": 2.5355370904562024e-06, "loss": 3.8487, "step": 2898944 }, { "epoch": 0.02, "learning_rate": 2.5271511429456824e-06, "loss": 3.8237, "step": 2899456 }, { "epoch": 0.02, "learning_rate": 2.5187651954351623e-06, "loss": 3.8464, "step": 2899968 }, { "epoch": 0.03, "eval_loss": 3.976100444793701, "eval_runtime": 294.6061, "eval_samples_per_second": 1295.258, "eval_steps_per_second": 40.478, "step": 2900160 }, { "epoch": 1.0, "learning_rate": 2.510379247924642e-06, "loss": 3.8369, "step": 2900480 }, { "epoch": 1.0, "learning_rate": 2.501993300414122e-06, "loss": 3.8335, "step": 2900992 }, { "epoch": 1.0, "learning_rate": 2.4936073529036018e-06, "loss": 3.8463, "step": 2901504 }, { "epoch": 1.0, "learning_rate": 2.4852214053930817e-06, "loss": 3.8533, "step": 2902016 }, { "epoch": 1.0, "learning_rate": 2.476851836686293e-06, "loss": 3.8452, "step": 2902528 }, { "epoch": 1.0, "learning_rate": 2.468465889175773e-06, "loss": 3.8378, "step": 2903040 }, { "epoch": 1.0, "learning_rate": 2.4600799416652524e-06, "loss": 3.8422, "step": 2903552 }, { "epoch": 1.0, "learning_rate": 2.4516939941547324e-06, "loss": 3.8296, "step": 2904064 }, { "epoch": 1.0, "learning_rate": 2.4433080466442123e-06, "loss": 3.8451, "step": 2904576 }, { "epoch": 1.0, "learning_rate": 2.434938477937424e-06, "loss": 3.8463, "step": 2905088 }, { "epoch": 1.0, "learning_rate": 2.426552530426904e-06, "loss": 3.8453, "step": 2905600 }, { "epoch": 1.0, "learning_rate": 2.418166582916384e-06, "loss": 3.8439, "step": 2906112 }, { "epoch": 1.0, "learning_rate": 2.409797014209595e-06, "loss": 3.841, "step": 2906624 }, { "epoch": 1.0, "learning_rate": 2.401411066699075e-06, "loss": 3.838, "step": 2907136 }, { "epoch": 1.0, "learning_rate": 2.393025119188555e-06, "loss": 3.8339, "step": 2907648 }, { "epoch": 1.0, "learning_rate": 2.3846391716780345e-06, "loss": 3.8279, "step": 2908160 }, { "epoch": 1.0, "learning_rate": 2.3762532241675145e-06, "loss": 3.8347, "step": 2908672 }, { "epoch": 1.0, "learning_rate": 2.3678672766569944e-06, "loss": 3.8323, "step": 2909184 }, { "epoch": 1.0, "learning_rate": 2.3594977079502057e-06, "loss": 3.8406, "step": 2909696 }, { "epoch": 1.0, "learning_rate": 2.3511117604396856e-06, "loss": 3.851, "step": 2910208 }, { "epoch": 1.0, "learning_rate": 2.342725812929166e-06, "loss": 3.8521, "step": 2910720 }, { "epoch": 1.0, "learning_rate": 2.334339865418646e-06, "loss": 3.8453, "step": 2911232 }, { "epoch": 1.0, "learning_rate": 2.3259539179081255e-06, "loss": 3.8402, "step": 2911744 }, { "epoch": 1.0, "learning_rate": 2.3175679703976054e-06, "loss": 3.849, "step": 2912256 }, { "epoch": 1.0, "learning_rate": 2.3091820228870854e-06, "loss": 3.8344, "step": 2912768 }, { "epoch": 1.0, "learning_rate": 2.3007960753765653e-06, "loss": 3.8477, "step": 2913280 }, { "epoch": 1.0, "learning_rate": 2.2924101278660453e-06, "loss": 3.8365, "step": 2913792 }, { "epoch": 1.0, "learning_rate": 2.284024180355525e-06, "loss": 3.8254, "step": 2914304 }, { "epoch": 1.0, "learning_rate": 2.2756546116487365e-06, "loss": 3.8373, "step": 2914816 }, { "epoch": 1.0, "learning_rate": 2.267268664138216e-06, "loss": 3.8361, "step": 2915328 }, { "epoch": 1.01, "learning_rate": 2.258882716627696e-06, "loss": 3.8401, "step": 2915840 }, { "epoch": 1.01, "learning_rate": 2.250496769117176e-06, "loss": 3.847, "step": 2916352 }, { "epoch": 1.01, "learning_rate": 2.2421272004103876e-06, "loss": 3.8442, "step": 2916864 }, { "epoch": 1.01, "learning_rate": 2.2337412528998675e-06, "loss": 3.8436, "step": 2917376 }, { "epoch": 1.01, "learning_rate": 2.2253716841930787e-06, "loss": 3.8353, "step": 2917888 }, { "epoch": 1.01, "learning_rate": 2.2169857366825587e-06, "loss": 3.8537, "step": 2918400 }, { "epoch": 1.01, "learning_rate": 2.2085997891720386e-06, "loss": 3.8341, "step": 2918912 }, { "epoch": 1.01, "learning_rate": 2.2002138416615186e-06, "loss": 3.8322, "step": 2919424 }, { "epoch": 1.01, "learning_rate": 2.191827894150998e-06, "loss": 3.8365, "step": 2919936 }, { "epoch": 1.01, "learning_rate": 2.183441946640478e-06, "loss": 3.8302, "step": 2920448 }, { "epoch": 1.01, "learning_rate": 2.175055999129958e-06, "loss": 3.841, "step": 2920960 }, { "epoch": 1.01, "learning_rate": 2.166670051619438e-06, "loss": 3.8496, "step": 2921472 }, { "epoch": 1.01, "learning_rate": 2.1582841041089175e-06, "loss": 3.8346, "step": 2921984 }, { "epoch": 1.01, "learning_rate": 2.1498981565983975e-06, "loss": 3.8394, "step": 2922496 }, { "epoch": 1.01, "learning_rate": 2.141528587891609e-06, "loss": 3.8464, "step": 2923008 }, { "epoch": 1.01, "learning_rate": 2.133142640381089e-06, "loss": 3.8485, "step": 2923520 }, { "epoch": 1.01, "learning_rate": 2.124756692870569e-06, "loss": 3.8476, "step": 2924032 }, { "epoch": 1.01, "learning_rate": 2.116370745360049e-06, "loss": 3.8348, "step": 2924544 }, { "epoch": 1.01, "learning_rate": 2.107984797849529e-06, "loss": 3.8099, "step": 2925056 }, { "epoch": 1.01, "learning_rate": 2.09961522914274e-06, "loss": 3.8548, "step": 2925568 }, { "epoch": 1.01, "learning_rate": 2.09122928163222e-06, "loss": 3.8434, "step": 2926080 }, { "epoch": 1.01, "learning_rate": 2.0828433341216996e-06, "loss": 3.8419, "step": 2926592 }, { "epoch": 1.01, "learning_rate": 2.0744573866111796e-06, "loss": 3.8341, "step": 2927104 }, { "epoch": 1.01, "learning_rate": 2.0660714391006595e-06, "loss": 3.8319, "step": 2927616 }, { "epoch": 1.01, "learning_rate": 2.0576854915901395e-06, "loss": 3.8254, "step": 2928128 }, { "epoch": 1.01, "learning_rate": 2.0492995440796195e-06, "loss": 3.8307, "step": 2928640 }, { "epoch": 1.01, "learning_rate": 2.040913596569099e-06, "loss": 3.8317, "step": 2929152 }, { "epoch": 1.01, "learning_rate": 2.0325440278623106e-06, "loss": 3.8349, "step": 2929664 }, { "epoch": 1.01, "learning_rate": 2.0241580803517906e-06, "loss": 3.8469, "step": 2930176 }, { "epoch": 1.01, "learning_rate": 2.0157721328412705e-06, "loss": 3.8291, "step": 2930688 }, { "epoch": 1.01, "learning_rate": 2.0074025641344818e-06, "loss": 3.826, "step": 2931200 }, { "epoch": 1.01, "learning_rate": 1.9990166166239617e-06, "loss": 3.8434, "step": 2931712 }, { "epoch": 1.01, "learning_rate": 1.9906306691134417e-06, "loss": 3.826, "step": 2932224 }, { "epoch": 1.01, "learning_rate": 1.9822447216029216e-06, "loss": 3.8298, "step": 2932736 }, { "epoch": 1.01, "learning_rate": 1.9738587740924016e-06, "loss": 3.8389, "step": 2933248 }, { "epoch": 1.01, "learning_rate": 1.965472826581881e-06, "loss": 3.8397, "step": 2933760 }, { "epoch": 1.01, "learning_rate": 1.957086879071361e-06, "loss": 3.8299, "step": 2934272 }, { "epoch": 1.01, "learning_rate": 1.948700931560841e-06, "loss": 3.8263, "step": 2934784 }, { "epoch": 1.01, "learning_rate": 1.9403313628540527e-06, "loss": 3.8268, "step": 2935296 }, { "epoch": 1.01, "learning_rate": 1.9319454153435326e-06, "loss": 3.8418, "step": 2935808 }, { "epoch": 1.01, "learning_rate": 1.9235594678330126e-06, "loss": 3.8387, "step": 2936320 }, { "epoch": 1.01, "learning_rate": 1.9151898991262238e-06, "loss": 3.8385, "step": 2936832 }, { "epoch": 1.01, "learning_rate": 1.9068039516157037e-06, "loss": 3.8366, "step": 2937344 }, { "epoch": 1.01, "learning_rate": 1.898434382908915e-06, "loss": 3.8477, "step": 2937856 }, { "epoch": 1.01, "learning_rate": 1.890048435398395e-06, "loss": 3.843, "step": 2938368 }, { "epoch": 1.01, "learning_rate": 1.8816624878878749e-06, "loss": 3.8294, "step": 2938880 }, { "epoch": 1.01, "learning_rate": 1.8732765403773546e-06, "loss": 3.8401, "step": 2939392 }, { "epoch": 1.01, "learning_rate": 1.8648905928668346e-06, "loss": 3.8451, "step": 2939904 }, { "epoch": 1.01, "learning_rate": 1.8565046453563145e-06, "loss": 3.8265, "step": 2940416 }, { "epoch": 1.01, "learning_rate": 1.8481186978457945e-06, "loss": 3.8409, "step": 2940928 }, { "epoch": 1.01, "learning_rate": 1.839732750335274e-06, "loss": 3.8414, "step": 2941440 }, { "epoch": 1.01, "learning_rate": 1.8313631816284856e-06, "loss": 3.847, "step": 2941952 }, { "epoch": 1.01, "learning_rate": 1.8229772341179654e-06, "loss": 3.8399, "step": 2942464 }, { "epoch": 1.01, "learning_rate": 1.8145912866074453e-06, "loss": 3.8188, "step": 2942976 }, { "epoch": 1.01, "learning_rate": 1.8062053390969253e-06, "loss": 3.8341, "step": 2943488 }, { "epoch": 1.01, "learning_rate": 1.7978193915864053e-06, "loss": 3.832, "step": 2944000 }, { "epoch": 1.01, "learning_rate": 1.7894498228796165e-06, "loss": 3.8412, "step": 2944512 }, { "epoch": 1.01, "learning_rate": 1.7810638753690964e-06, "loss": 3.8355, "step": 2945024 }, { "epoch": 1.01, "learning_rate": 1.7726943066623078e-06, "loss": 3.8315, "step": 2945536 }, { "epoch": 1.02, "learning_rate": 1.7643083591517878e-06, "loss": 3.8387, "step": 2946048 }, { "epoch": 1.02, "learning_rate": 1.7559224116412678e-06, "loss": 3.8395, "step": 2946560 }, { "epoch": 1.02, "learning_rate": 1.7475364641307473e-06, "loss": 3.8272, "step": 2947072 }, { "epoch": 1.02, "learning_rate": 1.7391505166202272e-06, "loss": 3.8355, "step": 2947584 }, { "epoch": 1.02, "learning_rate": 1.7307645691097072e-06, "loss": 3.8454, "step": 2948096 }, { "epoch": 1.02, "learning_rate": 1.7223786215991872e-06, "loss": 3.8464, "step": 2948608 }, { "epoch": 1.02, "learning_rate": 1.7139926740886671e-06, "loss": 3.8382, "step": 2949120 }, { "epoch": 1.02, "learning_rate": 1.7056067265781469e-06, "loss": 3.8237, "step": 2949632 }, { "epoch": 1.02, "learning_rate": 1.6972207790676268e-06, "loss": 3.8366, "step": 2950144 }, { "epoch": 1.02, "learning_rate": 1.6888348315571068e-06, "loss": 3.8331, "step": 2950656 }, { "epoch": 1.02, "learning_rate": 1.6804488840465867e-06, "loss": 3.8443, "step": 2951168 }, { "epoch": 1.02, "learning_rate": 1.672079315339798e-06, "loss": 3.8495, "step": 2951680 }, { "epoch": 1.02, "learning_rate": 1.6637097466330094e-06, "loss": 3.8333, "step": 2952192 }, { "epoch": 1.02, "learning_rate": 1.6553237991224893e-06, "loss": 3.8314, "step": 2952704 }, { "epoch": 1.02, "learning_rate": 1.6469378516119693e-06, "loss": 3.8396, "step": 2953216 }, { "epoch": 1.02, "learning_rate": 1.6385519041014492e-06, "loss": 3.8213, "step": 2953728 }, { "epoch": 1.02, "learning_rate": 1.6301659565909288e-06, "loss": 3.8392, "step": 2954240 }, { "epoch": 1.02, "learning_rate": 1.6217800090804087e-06, "loss": 3.821, "step": 2954752 }, { "epoch": 1.02, "learning_rate": 1.6134104403736201e-06, "loss": 3.8437, "step": 2955264 }, { "epoch": 1.02, "learning_rate": 1.6050244928631e-06, "loss": 3.8283, "step": 2955776 }, { "epoch": 1.02, "learning_rate": 1.59663854535258e-06, "loss": 3.8354, "step": 2956288 }, { "epoch": 1.02, "learning_rate": 1.58825259784206e-06, "loss": 3.834, "step": 2956800 }, { "epoch": 1.02, "learning_rate": 1.57986665033154e-06, "loss": 3.8326, "step": 2957312 }, { "epoch": 1.02, "learning_rate": 1.5714807028210197e-06, "loss": 3.8382, "step": 2957824 }, { "epoch": 1.02, "learning_rate": 1.563111134114231e-06, "loss": 3.8298, "step": 2958336 }, { "epoch": 1.02, "learning_rate": 1.554725186603711e-06, "loss": 3.8526, "step": 2958848 }, { "epoch": 1.02, "learning_rate": 1.5463392390931908e-06, "loss": 3.8454, "step": 2959360 }, { "epoch": 1.02, "learning_rate": 1.5379532915826708e-06, "loss": 3.8353, "step": 2959872 }, { "epoch": 1.02, "learning_rate": 1.5295673440721505e-06, "loss": 3.8392, "step": 2960384 }, { "epoch": 1.02, "learning_rate": 1.5211813965616305e-06, "loss": 3.8279, "step": 2960896 }, { "epoch": 1.02, "learning_rate": 1.512811827854842e-06, "loss": 3.8385, "step": 2961408 }, { "epoch": 1.02, "learning_rate": 1.5044258803443219e-06, "loss": 3.8368, "step": 2961920 }, { "epoch": 1.02, "learning_rate": 1.4960399328338016e-06, "loss": 3.8367, "step": 2962432 }, { "epoch": 1.02, "learning_rate": 1.4876539853232816e-06, "loss": 3.8365, "step": 2962944 }, { "epoch": 1.02, "learning_rate": 1.479284416616493e-06, "loss": 3.834, "step": 2963456 }, { "epoch": 1.02, "learning_rate": 1.470898469105973e-06, "loss": 3.8379, "step": 2963968 }, { "epoch": 1.02, "learning_rate": 1.462512521595453e-06, "loss": 3.8375, "step": 2964480 }, { "epoch": 1.02, "learning_rate": 1.4541265740849327e-06, "loss": 3.8332, "step": 2964992 }, { "epoch": 1.02, "learning_rate": 1.445757005378144e-06, "loss": 3.8398, "step": 2965504 }, { "epoch": 1.02, "learning_rate": 1.4373710578676238e-06, "loss": 3.8222, "step": 2966016 }, { "epoch": 1.02, "learning_rate": 1.4289851103571038e-06, "loss": 3.8482, "step": 2966528 }, { "epoch": 1.02, "learning_rate": 1.4205991628465837e-06, "loss": 3.8393, "step": 2967040 }, { "epoch": 1.02, "learning_rate": 1.4122132153360637e-06, "loss": 3.8445, "step": 2967552 }, { "epoch": 1.02, "learning_rate": 1.403843646629275e-06, "loss": 3.8258, "step": 2968064 }, { "epoch": 1.02, "learning_rate": 1.3954576991187549e-06, "loss": 3.8396, "step": 2968576 }, { "epoch": 1.02, "learning_rate": 1.3870717516082348e-06, "loss": 3.8437, "step": 2969088 }, { "epoch": 1.02, "learning_rate": 1.3786858040977148e-06, "loss": 3.8407, "step": 2969600 }, { "epoch": 1.02, "learning_rate": 1.3702998565871947e-06, "loss": 3.8318, "step": 2970112 }, { "epoch": 1.02, "learning_rate": 1.361930287880406e-06, "loss": 3.8483, "step": 2970624 }, { "epoch": 1.02, "learning_rate": 1.353544340369886e-06, "loss": 3.8408, "step": 2971136 }, { "epoch": 1.02, "learning_rate": 1.3451583928593656e-06, "loss": 3.8502, "step": 2971648 }, { "epoch": 1.02, "learning_rate": 1.3367724453488456e-06, "loss": 3.8319, "step": 2972160 }, { "epoch": 1.02, "learning_rate": 1.328402876642057e-06, "loss": 3.849, "step": 2972672 }, { "epoch": 1.02, "learning_rate": 1.320016929131537e-06, "loss": 3.8415, "step": 2973184 }, { "epoch": 1.02, "learning_rate": 1.3116309816210167e-06, "loss": 3.8375, "step": 2973696 }, { "epoch": 1.02, "learning_rate": 1.3032450341104967e-06, "loss": 3.84, "step": 2974208 }, { "epoch": 1.02, "learning_rate": 1.2948590865999766e-06, "loss": 3.8398, "step": 2974720 }, { "epoch": 1.02, "learning_rate": 1.2864731390894564e-06, "loss": 3.8442, "step": 2975232 }, { "epoch": 1.02, "learning_rate": 1.2780871915789363e-06, "loss": 3.8245, "step": 2975744 }, { "epoch": 1.02, "learning_rate": 1.2697012440684163e-06, "loss": 3.8464, "step": 2976256 }, { "epoch": 1.03, "eval_loss": 3.9754867553710938, "eval_runtime": 294.7845, "eval_samples_per_second": 1294.474, "eval_steps_per_second": 40.453, "step": 2976480 }, { "epoch": 0.0, "learning_rate": 1.2613152965578962e-06, "loss": 3.8345, "step": 2976768 }, { "epoch": 0.0, "learning_rate": 1.2529293490473762e-06, "loss": 3.8314, "step": 2977280 }, { "epoch": 0.0, "learning_rate": 1.244543401536856e-06, "loss": 3.8439, "step": 2977792 }, { "epoch": 0.0, "learning_rate": 1.236157454026336e-06, "loss": 3.8488, "step": 2978304 }, { "epoch": 0.0, "learning_rate": 1.2277715065158156e-06, "loss": 3.8432, "step": 2978816 }, { "epoch": 0.0, "learning_rate": 1.2193855590052956e-06, "loss": 3.8381, "step": 2979328 }, { "epoch": 0.0, "learning_rate": 1.2109996114947756e-06, "loss": 3.8434, "step": 2979840 }, { "epoch": 0.0, "learning_rate": 1.2026136639842555e-06, "loss": 3.8296, "step": 2980352 }, { "epoch": 0.0, "learning_rate": 1.1942277164737355e-06, "loss": 3.8451, "step": 2980864 }, { "epoch": 0.0, "learning_rate": 1.1858417689632152e-06, "loss": 3.8439, "step": 2981376 }, { "epoch": 0.0, "learning_rate": 1.1774558214526952e-06, "loss": 3.8426, "step": 2981888 }, { "epoch": 0.0, "learning_rate": 1.169069873942175e-06, "loss": 3.8443, "step": 2982400 }, { "epoch": 0.0, "learning_rate": 1.1607003052353863e-06, "loss": 3.8359, "step": 2982912 }, { "epoch": 0.0, "learning_rate": 1.1523143577248663e-06, "loss": 3.8344, "step": 2983424 }, { "epoch": 0.0, "learning_rate": 1.1439284102143462e-06, "loss": 3.8341, "step": 2983936 }, { "epoch": 0.0, "learning_rate": 1.1355424627038262e-06, "loss": 3.8273, "step": 2984448 }, { "epoch": 0.0, "learning_rate": 1.127156515193306e-06, "loss": 3.8348, "step": 2984960 }, { "epoch": 0.0, "learning_rate": 1.118770567682786e-06, "loss": 3.8321, "step": 2985472 }, { "epoch": 0.0, "learning_rate": 1.1103846201722656e-06, "loss": 3.8365, "step": 2985984 }, { "epoch": 0.0, "learning_rate": 1.1019986726617456e-06, "loss": 3.847, "step": 2986496 }, { "epoch": 0.0, "learning_rate": 1.0936127251512256e-06, "loss": 3.8524, "step": 2987008 }, { "epoch": 0.0, "learning_rate": 1.0852267776407055e-06, "loss": 3.8489, "step": 2987520 }, { "epoch": 0.0, "learning_rate": 1.0768408301301855e-06, "loss": 3.835, "step": 2988032 }, { "epoch": 0.0, "learning_rate": 1.0684712614233967e-06, "loss": 3.8471, "step": 2988544 }, { "epoch": 0.0, "learning_rate": 1.0600853139128766e-06, "loss": 3.8336, "step": 2989056 }, { "epoch": 0.0, "learning_rate": 1.0516993664023564e-06, "loss": 3.8436, "step": 2989568 }, { "epoch": 0.0, "learning_rate": 1.0433134188918363e-06, "loss": 3.8375, "step": 2990080 }, { "epoch": 0.0, "learning_rate": 1.0349274713813163e-06, "loss": 3.8237, "step": 2990592 }, { "epoch": 0.0, "learning_rate": 1.0265415238707962e-06, "loss": 3.8367, "step": 2991104 }, { "epoch": 0.0, "learning_rate": 1.0181555763602762e-06, "loss": 3.8293, "step": 2991616 }, { "epoch": 0.01, "learning_rate": 1.009769628849756e-06, "loss": 3.8364, "step": 2992128 }, { "epoch": 0.01, "learning_rate": 1.001383681339236e-06, "loss": 3.8451, "step": 2992640 }, { "epoch": 0.01, "learning_rate": 9.930141126324471e-07, "loss": 3.8405, "step": 2993152 }, { "epoch": 0.01, "learning_rate": 9.846281651219273e-07, "loss": 3.8423, "step": 2993664 }, { "epoch": 0.01, "learning_rate": 9.762585964151385e-07, "loss": 3.8333, "step": 2994176 }, { "epoch": 0.01, "learning_rate": 9.6788902770835e-07, "loss": 3.8543, "step": 2994688 }, { "epoch": 0.01, "learning_rate": 9.595030801978297e-07, "loss": 3.8384, "step": 2995200 }, { "epoch": 0.01, "learning_rate": 9.511171326873097e-07, "loss": 3.8278, "step": 2995712 }, { "epoch": 0.01, "learning_rate": 9.427311851767896e-07, "loss": 3.8368, "step": 2996224 }, { "epoch": 0.01, "learning_rate": 9.343452376662695e-07, "loss": 3.8274, "step": 2996736 }, { "epoch": 0.01, "learning_rate": 9.259592901557493e-07, "loss": 3.8343, "step": 2997248 }, { "epoch": 0.01, "learning_rate": 9.175733426452292e-07, "loss": 3.842, "step": 2997760 }, { "epoch": 0.01, "learning_rate": 9.091873951347092e-07, "loss": 3.8371, "step": 2998272 }, { "epoch": 0.01, "learning_rate": 9.00801447624189e-07, "loss": 3.8334, "step": 2998784 }, { "epoch": 0.01, "learning_rate": 8.924318789174005e-07, "loss": 3.8462, "step": 2999296 }, { "epoch": 0.01, "learning_rate": 8.840459314068803e-07, "loss": 3.844, "step": 2999808 }, { "epoch": 0.01, "learning_rate": 8.756599838963603e-07, "loss": 3.8464, "step": 3000320 }, { "epoch": 0.01, "learning_rate": 8.6727403638584e-07, "loss": 3.8304, "step": 3000832 }, { "epoch": 0.01, "learning_rate": 8.5888808887532e-07, "loss": 3.8075, "step": 3001344 }, { "epoch": 0.01, "learning_rate": 8.505185201685313e-07, "loss": 3.8588, "step": 3001856 }, { "epoch": 0.01, "learning_rate": 8.421325726580112e-07, "loss": 3.8362, "step": 3002368 }, { "epoch": 0.01, "learning_rate": 8.337466251474912e-07, "loss": 3.8415, "step": 3002880 }, { "epoch": 0.01, "learning_rate": 8.25360677636971e-07, "loss": 3.8352, "step": 3003392 }, { "epoch": 0.01, "learning_rate": 8.16974730126451e-07, "loss": 3.8262, "step": 3003904 }, { "epoch": 0.01, "learning_rate": 8.085887826159307e-07, "loss": 3.8266, "step": 3004416 }, { "epoch": 0.01, "learning_rate": 8.002028351054108e-07, "loss": 3.8294, "step": 3004928 }, { "epoch": 0.01, "learning_rate": 7.918168875948906e-07, "loss": 3.8302, "step": 3005440 }, { "epoch": 0.01, "learning_rate": 7.834473188881021e-07, "loss": 3.8294, "step": 3005952 }, { "epoch": 0.01, "learning_rate": 7.750613713775819e-07, "loss": 3.8493, "step": 3006464 }, { "epoch": 0.01, "learning_rate": 7.666918026707934e-07, "loss": 3.8273, "step": 3006976 }, { "epoch": 0.01, "learning_rate": 7.583058551602732e-07, "loss": 3.8232, "step": 3007488 }, { "epoch": 0.01, "learning_rate": 7.499199076497531e-07, "loss": 3.8452, "step": 3008000 }, { "epoch": 0.01, "learning_rate": 7.415339601392329e-07, "loss": 3.822, "step": 3008512 }, { "epoch": 0.01, "learning_rate": 7.331480126287129e-07, "loss": 3.8265, "step": 3009024 }, { "epoch": 0.01, "learning_rate": 7.247620651181928e-07, "loss": 3.8386, "step": 3009536 }, { "epoch": 0.01, "learning_rate": 7.163761176076727e-07, "loss": 3.8372, "step": 3010048 }, { "epoch": 0.01, "learning_rate": 7.080229277046155e-07, "loss": 3.828, "step": 3010560 }, { "epoch": 0.01, "learning_rate": 6.996369801940954e-07, "loss": 3.83, "step": 3011072 }, { "epoch": 0.01, "learning_rate": 6.912510326835754e-07, "loss": 3.821, "step": 3011584 }, { "epoch": 0.01, "learning_rate": 6.828650851730552e-07, "loss": 3.8394, "step": 3012096 }, { "epoch": 0.01, "learning_rate": 6.744791376625351e-07, "loss": 3.8371, "step": 3012608 }, { "epoch": 0.01, "learning_rate": 6.66093190152015e-07, "loss": 3.8348, "step": 3013120 }, { "epoch": 0.01, "learning_rate": 6.577072426414949e-07, "loss": 3.8362, "step": 3013632 }, { "epoch": 0.01, "learning_rate": 6.493212951309747e-07, "loss": 3.8412, "step": 3014144 }, { "epoch": 0.01, "learning_rate": 6.409353476204547e-07, "loss": 3.8463, "step": 3014656 }, { "epoch": 0.01, "learning_rate": 6.325494001099345e-07, "loss": 3.8264, "step": 3015168 }, { "epoch": 0.01, "learning_rate": 6.241634525994145e-07, "loss": 3.8375, "step": 3015680 }, { "epoch": 0.01, "learning_rate": 6.157775050888943e-07, "loss": 3.8426, "step": 3016192 }, { "epoch": 0.01, "learning_rate": 6.074079363821058e-07, "loss": 3.8206, "step": 3016704 }, { "epoch": 0.01, "learning_rate": 5.990383676753171e-07, "loss": 3.8412, "step": 3017216 }, { "epoch": 0.01, "learning_rate": 5.90652420164797e-07, "loss": 3.8371, "step": 3017728 }, { "epoch": 0.01, "learning_rate": 5.822664726542769e-07, "loss": 3.8454, "step": 3018240 }, { "epoch": 0.01, "learning_rate": 5.738805251437567e-07, "loss": 3.8404, "step": 3018752 }, { "epoch": 0.01, "learning_rate": 5.654945776332367e-07, "loss": 3.8218, "step": 3019264 }, { "epoch": 0.01, "learning_rate": 5.57125008926448e-07, "loss": 3.8242, "step": 3019776 }, { "epoch": 0.01, "learning_rate": 5.48739061415928e-07, "loss": 3.8301, "step": 3020288 }, { "epoch": 0.01, "learning_rate": 5.403531139054079e-07, "loss": 3.841, "step": 3020800 }, { "epoch": 0.01, "learning_rate": 5.319671663948878e-07, "loss": 3.8311, "step": 3021312 }, { "epoch": 0.01, "learning_rate": 5.235975976880992e-07, "loss": 3.8308, "step": 3021824 }, { "epoch": 0.02, "learning_rate": 5.15211650177579e-07, "loss": 3.837, "step": 3022336 }, { "epoch": 0.02, "learning_rate": 5.068257026670589e-07, "loss": 3.8359, "step": 3022848 }, { "epoch": 0.02, "learning_rate": 4.984397551565387e-07, "loss": 3.8271, "step": 3023360 }, { "epoch": 0.02, "learning_rate": 4.900538076460187e-07, "loss": 3.8312, "step": 3023872 }, { "epoch": 0.02, "learning_rate": 4.816678601354986e-07, "loss": 3.843, "step": 3024384 }, { "epoch": 0.02, "learning_rate": 4.732819126249785e-07, "loss": 3.8432, "step": 3024896 }, { "epoch": 0.02, "learning_rate": 4.648959651144584e-07, "loss": 3.8376, "step": 3025408 }, { "epoch": 0.02, "learning_rate": 4.5651001760393826e-07, "loss": 3.823, "step": 3025920 }, { "epoch": 0.02, "learning_rate": 4.4812407009341816e-07, "loss": 3.8356, "step": 3026432 }, { "epoch": 0.02, "learning_rate": 4.3973812258289807e-07, "loss": 3.8284, "step": 3026944 }, { "epoch": 0.02, "learning_rate": 4.313521750723779e-07, "loss": 3.8414, "step": 3027456 }, { "epoch": 0.02, "learning_rate": 4.229826063655893e-07, "loss": 3.8416, "step": 3027968 }, { "epoch": 0.02, "learning_rate": 4.145966588550692e-07, "loss": 3.8367, "step": 3028480 }, { "epoch": 0.02, "learning_rate": 4.0621071134454915e-07, "loss": 3.8316, "step": 3028992 }, { "epoch": 0.02, "learning_rate": 3.9782476383402905e-07, "loss": 3.8318, "step": 3029504 }, { "epoch": 0.02, "learning_rate": 3.894388163235089e-07, "loss": 3.8238, "step": 3030016 }, { "epoch": 0.02, "learning_rate": 3.810856264204518e-07, "loss": 3.8352, "step": 3030528 }, { "epoch": 0.02, "learning_rate": 3.7269967890993165e-07, "loss": 3.8224, "step": 3031040 }, { "epoch": 0.02, "learning_rate": 3.643301102031431e-07, "loss": 3.8419, "step": 3031552 }, { "epoch": 0.02, "learning_rate": 3.559441626926229e-07, "loss": 3.8281, "step": 3032064 }, { "epoch": 0.02, "learning_rate": 3.475582151821028e-07, "loss": 3.8311, "step": 3032576 }, { "epoch": 0.02, "learning_rate": 3.3917226767158273e-07, "loss": 3.8293, "step": 3033088 }, { "epoch": 0.02, "learning_rate": 3.3078632016106263e-07, "loss": 3.8288, "step": 3033600 }, { "epoch": 0.02, "learning_rate": 3.224003726505425e-07, "loss": 3.8401, "step": 3034112 }, { "epoch": 0.02, "learning_rate": 3.1401442514002244e-07, "loss": 3.8303, "step": 3034624 }, { "epoch": 0.02, "learning_rate": 3.056284776295023e-07, "loss": 3.8522, "step": 3035136 }, { "epoch": 0.02, "learning_rate": 2.972589089227137e-07, "loss": 3.8453, "step": 3035648 }, { "epoch": 0.02, "learning_rate": 2.8887296141219356e-07, "loss": 3.8345, "step": 3036160 }, { "epoch": 0.02, "learning_rate": 2.8048701390167346e-07, "loss": 3.8356, "step": 3036672 }, { "epoch": 0.02, "learning_rate": 2.7210106639115337e-07, "loss": 3.8273, "step": 3037184 }, { "epoch": 0.02, "learning_rate": 2.6371511888063327e-07, "loss": 3.8338, "step": 3037696 }, { "epoch": 0.02, "learning_rate": 2.553291713701131e-07, "loss": 3.8395, "step": 3038208 }, { "epoch": 0.02, "learning_rate": 2.469432238595931e-07, "loss": 3.8327, "step": 3038720 }, { "epoch": 0.02, "learning_rate": 2.385572763490729e-07, "loss": 3.8349, "step": 3039232 }, { "epoch": 0.02, "learning_rate": 2.302040864460158e-07, "loss": 3.8335, "step": 3039744 }, { "epoch": 0.02, "learning_rate": 2.218181389354957e-07, "loss": 3.8359, "step": 3040256 }, { "epoch": 0.02, "learning_rate": 2.134321914249756e-07, "loss": 3.8369, "step": 3040768 }, { "epoch": 0.02, "learning_rate": 2.0504624391445548e-07, "loss": 3.8273, "step": 3041280 }, { "epoch": 0.02, "learning_rate": 1.9666029640393538e-07, "loss": 3.8372, "step": 3041792 }, { "epoch": 0.02, "learning_rate": 1.8829072769714675e-07, "loss": 3.8262, "step": 3042304 }, { "epoch": 0.02, "learning_rate": 1.7990478018662663e-07, "loss": 3.8478, "step": 3042816 }, { "epoch": 0.02, "learning_rate": 1.7153521147983803e-07, "loss": 3.8351, "step": 3043328 }, { "epoch": 0.02, "learning_rate": 1.631492639693179e-07, "loss": 3.8404, "step": 3043840 }, { "epoch": 0.02, "learning_rate": 1.547633164587978e-07, "loss": 3.827, "step": 3044352 }, { "epoch": 0.02, "learning_rate": 1.463773689482777e-07, "loss": 3.8393, "step": 3044864 }, { "epoch": 0.02, "learning_rate": 1.3799142143775759e-07, "loss": 3.8417, "step": 3045376 }, { "epoch": 0.02, "learning_rate": 1.296054739272375e-07, "loss": 3.8391, "step": 3045888 }, { "epoch": 0.02, "learning_rate": 1.212195264167174e-07, "loss": 3.8329, "step": 3046400 }, { "epoch": 0.02, "learning_rate": 1.1283357890619728e-07, "loss": 3.8428, "step": 3046912 }, { "epoch": 0.02, "learning_rate": 1.0444763139567718e-07, "loss": 3.837, "step": 3047424 }, { "epoch": 0.02, "learning_rate": 9.607806268888857e-08, "loss": 3.8525, "step": 3047936 }, { "epoch": 0.02, "learning_rate": 8.769211517836846e-08, "loss": 3.8308, "step": 3048448 }, { "epoch": 0.02, "learning_rate": 7.930616766784835e-08, "loss": 3.847, "step": 3048960 }, { "epoch": 0.02, "learning_rate": 7.092022015732825e-08, "loss": 3.8381, "step": 3049472 }, { "epoch": 0.02, "learning_rate": 6.255065145053962e-08, "loss": 3.837, "step": 3049984 }, { "epoch": 0.02, "learning_rate": 5.416470394001952e-08, "loss": 3.8369, "step": 3050496 }, { "epoch": 0.02, "learning_rate": 4.577875642949941e-08, "loss": 3.8391, "step": 3051008 }, { "epoch": 0.02, "learning_rate": 3.7392808918979305e-08, "loss": 3.8427, "step": 3051520 }, { "epoch": 0.02, "learning_rate": 2.9006861408459194e-08, "loss": 3.8241, "step": 3052032 }, { "epoch": 0.02, "learning_rate": 2.063729270167057e-08, "loss": 3.8418, "step": 3052544 }, { "epoch": 0.02, "eval_loss": 3.9751081466674805, "eval_runtime": 292.8427, "eval_samples_per_second": 1303.058, "eval_steps_per_second": 40.722, "step": 3052726 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.261394059617431e+18, "trial_name": null, "trial_params": null }