{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 12.269938650306749, "eval_steps": 500, "global_step": 2000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03067484662576687, "grad_norm": 2.5978403091430664, "learning_rate": 1.6326530612244901e-07, "loss": 1.1372, "step": 5 }, { "epoch": 0.06134969325153374, "grad_norm": 2.5917587280273438, "learning_rate": 3.6734693877551025e-07, "loss": 1.1384, "step": 10 }, { "epoch": 0.09202453987730061, "grad_norm": 2.413616895675659, "learning_rate": 5.714285714285715e-07, "loss": 1.1299, "step": 15 }, { "epoch": 0.12269938650306748, "grad_norm": 2.1455910205841064, "learning_rate": 7.755102040816327e-07, "loss": 1.1148, "step": 20 }, { "epoch": 0.15337423312883436, "grad_norm": 1.4798907041549683, "learning_rate": 9.795918367346939e-07, "loss": 1.0779, "step": 25 }, { "epoch": 0.18404907975460122, "grad_norm": 1.122052550315857, "learning_rate": 1.1836734693877552e-06, "loss": 1.0483, "step": 30 }, { "epoch": 0.2147239263803681, "grad_norm": 0.9710678458213806, "learning_rate": 1.3877551020408165e-06, "loss": 1.0004, "step": 35 }, { "epoch": 0.24539877300613497, "grad_norm": 1.1292918920516968, "learning_rate": 1.5918367346938775e-06, "loss": 0.9636, "step": 40 }, { "epoch": 0.27607361963190186, "grad_norm": 0.7304956912994385, "learning_rate": 1.7959183673469388e-06, "loss": 0.914, "step": 45 }, { "epoch": 0.3067484662576687, "grad_norm": 0.5761268734931946, "learning_rate": 2.0000000000000003e-06, "loss": 0.8871, "step": 50 }, { "epoch": 0.3374233128834356, "grad_norm": 0.5395930409431458, "learning_rate": 2.2040816326530616e-06, "loss": 0.8649, "step": 55 }, { "epoch": 0.36809815950920244, "grad_norm": 0.4449169635772705, "learning_rate": 2.4081632653061225e-06, "loss": 0.8375, "step": 60 }, { "epoch": 0.3987730061349693, "grad_norm": 0.3775625228881836, "learning_rate": 2.6122448979591842e-06, "loss": 0.8179, "step": 65 }, { "epoch": 0.4294478527607362, "grad_norm": 0.33234792947769165, "learning_rate": 2.816326530612245e-06, "loss": 0.8027, "step": 70 }, { "epoch": 0.4601226993865031, "grad_norm": 0.3218803405761719, "learning_rate": 3.0204081632653064e-06, "loss": 0.7834, "step": 75 }, { "epoch": 0.49079754601226994, "grad_norm": 0.30811169743537903, "learning_rate": 3.2244897959183672e-06, "loss": 0.7754, "step": 80 }, { "epoch": 0.5214723926380368, "grad_norm": 0.3008837401866913, "learning_rate": 3.428571428571429e-06, "loss": 0.77, "step": 85 }, { "epoch": 0.5521472392638037, "grad_norm": 0.30381834506988525, "learning_rate": 3.6326530612244903e-06, "loss": 0.7576, "step": 90 }, { "epoch": 0.5828220858895705, "grad_norm": 0.29334792494773865, "learning_rate": 3.836734693877551e-06, "loss": 0.7528, "step": 95 }, { "epoch": 0.6134969325153374, "grad_norm": 0.3081793785095215, "learning_rate": 4.040816326530612e-06, "loss": 0.743, "step": 100 }, { "epoch": 0.6441717791411042, "grad_norm": 0.2884787917137146, "learning_rate": 4.244897959183674e-06, "loss": 0.7357, "step": 105 }, { "epoch": 0.6748466257668712, "grad_norm": 0.31221410632133484, "learning_rate": 4.448979591836735e-06, "loss": 0.736, "step": 110 }, { "epoch": 0.7055214723926381, "grad_norm": 0.29866281151771545, "learning_rate": 4.653061224489796e-06, "loss": 0.7242, "step": 115 }, { "epoch": 0.7361963190184049, "grad_norm": 0.3165671229362488, "learning_rate": 4.857142857142858e-06, "loss": 0.7137, "step": 120 }, { "epoch": 0.7668711656441718, "grad_norm": 0.30676907300949097, "learning_rate": 5.061224489795918e-06, "loss": 0.7153, "step": 125 }, { "epoch": 0.7975460122699386, "grad_norm": 0.3097768723964691, "learning_rate": 5.26530612244898e-06, "loss": 0.7099, "step": 130 }, { "epoch": 0.8282208588957055, "grad_norm": 0.3433418869972229, "learning_rate": 5.4693877551020415e-06, "loss": 0.7029, "step": 135 }, { "epoch": 0.8588957055214724, "grad_norm": 0.3297426104545593, "learning_rate": 5.673469387755103e-06, "loss": 0.7023, "step": 140 }, { "epoch": 0.8895705521472392, "grad_norm": 0.32176053524017334, "learning_rate": 5.877551020408164e-06, "loss": 0.6954, "step": 145 }, { "epoch": 0.9202453987730062, "grad_norm": 0.35964256525039673, "learning_rate": 6.0816326530612245e-06, "loss": 0.6938, "step": 150 }, { "epoch": 0.950920245398773, "grad_norm": 0.34248167276382446, "learning_rate": 6.285714285714286e-06, "loss": 0.6882, "step": 155 }, { "epoch": 0.9815950920245399, "grad_norm": 0.34893444180488586, "learning_rate": 6.489795918367348e-06, "loss": 0.6905, "step": 160 }, { "epoch": 1.0122699386503067, "grad_norm": 0.3583211302757263, "learning_rate": 6.693877551020409e-06, "loss": 0.679, "step": 165 }, { "epoch": 1.0429447852760736, "grad_norm": 0.33445632457733154, "learning_rate": 6.8979591836734705e-06, "loss": 0.6711, "step": 170 }, { "epoch": 1.0736196319018405, "grad_norm": 0.3518800437450409, "learning_rate": 7.102040816326531e-06, "loss": 0.6684, "step": 175 }, { "epoch": 1.1042944785276074, "grad_norm": 0.37601813673973083, "learning_rate": 7.306122448979592e-06, "loss": 0.67, "step": 180 }, { "epoch": 1.1349693251533743, "grad_norm": 0.35547634959220886, "learning_rate": 7.5102040816326536e-06, "loss": 0.6614, "step": 185 }, { "epoch": 1.165644171779141, "grad_norm": 0.3293817937374115, "learning_rate": 7.714285714285716e-06, "loss": 0.6615, "step": 190 }, { "epoch": 1.196319018404908, "grad_norm": 0.39242789149284363, "learning_rate": 7.918367346938776e-06, "loss": 0.6563, "step": 195 }, { "epoch": 1.2269938650306749, "grad_norm": 0.3492467701435089, "learning_rate": 8.122448979591837e-06, "loss": 0.6559, "step": 200 }, { "epoch": 1.2576687116564418, "grad_norm": 0.38162752985954285, "learning_rate": 8.326530612244899e-06, "loss": 0.6534, "step": 205 }, { "epoch": 1.2883435582822087, "grad_norm": 0.41921180486679077, "learning_rate": 8.530612244897961e-06, "loss": 0.6537, "step": 210 }, { "epoch": 1.3190184049079754, "grad_norm": 0.35677486658096313, "learning_rate": 8.734693877551021e-06, "loss": 0.6468, "step": 215 }, { "epoch": 1.3496932515337423, "grad_norm": 0.4290676414966583, "learning_rate": 8.938775510204082e-06, "loss": 0.6457, "step": 220 }, { "epoch": 1.3803680981595092, "grad_norm": 0.33468857407569885, "learning_rate": 9.142857142857144e-06, "loss": 0.646, "step": 225 }, { "epoch": 1.4110429447852761, "grad_norm": 0.37300559878349304, "learning_rate": 9.346938775510204e-06, "loss": 0.6436, "step": 230 }, { "epoch": 1.441717791411043, "grad_norm": 0.37263476848602295, "learning_rate": 9.551020408163266e-06, "loss": 0.6364, "step": 235 }, { "epoch": 1.4723926380368098, "grad_norm": 0.4007490873336792, "learning_rate": 9.755102040816327e-06, "loss": 0.6394, "step": 240 }, { "epoch": 1.5030674846625767, "grad_norm": 0.3758663833141327, "learning_rate": 9.959183673469387e-06, "loss": 0.6392, "step": 245 }, { "epoch": 1.5337423312883436, "grad_norm": 0.39793241024017334, "learning_rate": 9.999918433243253e-06, "loss": 0.6389, "step": 250 }, { "epoch": 1.5644171779141103, "grad_norm": 0.4773501455783844, "learning_rate": 9.999587072854989e-06, "loss": 0.6364, "step": 255 }, { "epoch": 1.5950920245398774, "grad_norm": 0.43220365047454834, "learning_rate": 9.99900083779239e-06, "loss": 0.6321, "step": 260 }, { "epoch": 1.6257668711656441, "grad_norm": 0.4072875678539276, "learning_rate": 9.998159757941219e-06, "loss": 0.6328, "step": 265 }, { "epoch": 1.656441717791411, "grad_norm": 0.3672327995300293, "learning_rate": 9.997063876179007e-06, "loss": 0.6314, "step": 270 }, { "epoch": 1.687116564417178, "grad_norm": 0.44787004590034485, "learning_rate": 9.99571324837287e-06, "loss": 0.6265, "step": 275 }, { "epoch": 1.7177914110429446, "grad_norm": 0.4095243513584137, "learning_rate": 9.994107943376654e-06, "loss": 0.6241, "step": 280 }, { "epoch": 1.7484662576687118, "grad_norm": 0.48604634404182434, "learning_rate": 9.992248043027441e-06, "loss": 0.6219, "step": 285 }, { "epoch": 1.7791411042944785, "grad_norm": 0.46355390548706055, "learning_rate": 9.990133642141359e-06, "loss": 0.6224, "step": 290 }, { "epoch": 1.8098159509202454, "grad_norm": 0.36252495646476746, "learning_rate": 9.987764848508756e-06, "loss": 0.6295, "step": 295 }, { "epoch": 1.8404907975460123, "grad_norm": 0.39227545261383057, "learning_rate": 9.985141782888705e-06, "loss": 0.6188, "step": 300 }, { "epoch": 1.871165644171779, "grad_norm": 0.4363463222980499, "learning_rate": 9.982264579002853e-06, "loss": 0.6156, "step": 305 }, { "epoch": 1.9018404907975461, "grad_norm": 0.36619096994400024, "learning_rate": 9.979133383528591e-06, "loss": 0.6186, "step": 310 }, { "epoch": 1.9325153374233128, "grad_norm": 0.38282138109207153, "learning_rate": 9.975748356091589e-06, "loss": 0.6179, "step": 315 }, { "epoch": 1.9631901840490797, "grad_norm": 0.377532958984375, "learning_rate": 9.972109669257645e-06, "loss": 0.6103, "step": 320 }, { "epoch": 1.9938650306748467, "grad_norm": 0.3768117129802704, "learning_rate": 9.968217508523913e-06, "loss": 0.6126, "step": 325 }, { "epoch": 2.0245398773006134, "grad_norm": 0.3956761360168457, "learning_rate": 9.964072072309412e-06, "loss": 0.598, "step": 330 }, { "epoch": 2.0552147239263805, "grad_norm": 0.4610372483730316, "learning_rate": 9.959673571944939e-06, "loss": 0.5874, "step": 335 }, { "epoch": 2.085889570552147, "grad_norm": 0.4218359589576721, "learning_rate": 9.955022231662282e-06, "loss": 0.5883, "step": 340 }, { "epoch": 2.116564417177914, "grad_norm": 0.3745018243789673, "learning_rate": 9.95011828858279e-06, "loss": 0.5911, "step": 345 }, { "epoch": 2.147239263803681, "grad_norm": 0.3876558840274811, "learning_rate": 9.944961992705288e-06, "loss": 0.5871, "step": 350 }, { "epoch": 2.1779141104294477, "grad_norm": 0.43544134497642517, "learning_rate": 9.939553606893334e-06, "loss": 0.5923, "step": 355 }, { "epoch": 2.208588957055215, "grad_norm": 0.42091232538223267, "learning_rate": 9.933893406861808e-06, "loss": 0.5869, "step": 360 }, { "epoch": 2.2392638036809815, "grad_norm": 0.4135364890098572, "learning_rate": 9.927981681162873e-06, "loss": 0.5893, "step": 365 }, { "epoch": 2.2699386503067487, "grad_norm": 0.36126476526260376, "learning_rate": 9.921818731171249e-06, "loss": 0.5884, "step": 370 }, { "epoch": 2.3006134969325154, "grad_norm": 0.36540037393569946, "learning_rate": 9.915404871068855e-06, "loss": 0.5851, "step": 375 }, { "epoch": 2.331288343558282, "grad_norm": 0.40658003091812134, "learning_rate": 9.9087404278288e-06, "loss": 0.5864, "step": 380 }, { "epoch": 2.361963190184049, "grad_norm": 0.3715730607509613, "learning_rate": 9.901825741198697e-06, "loss": 0.5869, "step": 385 }, { "epoch": 2.392638036809816, "grad_norm": 0.414098858833313, "learning_rate": 9.894661163683361e-06, "loss": 0.5865, "step": 390 }, { "epoch": 2.4233128834355826, "grad_norm": 0.40678825974464417, "learning_rate": 9.887247060526827e-06, "loss": 0.5866, "step": 395 }, { "epoch": 2.4539877300613497, "grad_norm": 0.37045034766197205, "learning_rate": 9.879583809693737e-06, "loss": 0.5765, "step": 400 }, { "epoch": 2.4846625766871164, "grad_norm": 0.36025142669677734, "learning_rate": 9.871671801850065e-06, "loss": 0.5828, "step": 405 }, { "epoch": 2.5153374233128836, "grad_norm": 0.36954501271247864, "learning_rate": 9.863511440343206e-06, "loss": 0.5799, "step": 410 }, { "epoch": 2.5460122699386503, "grad_norm": 0.3953179121017456, "learning_rate": 9.855103141181412e-06, "loss": 0.5814, "step": 415 }, { "epoch": 2.5766871165644174, "grad_norm": 0.39428064227104187, "learning_rate": 9.846447333012587e-06, "loss": 0.5797, "step": 420 }, { "epoch": 2.607361963190184, "grad_norm": 0.3589676022529602, "learning_rate": 9.837544457102428e-06, "loss": 0.5843, "step": 425 }, { "epoch": 2.638036809815951, "grad_norm": 0.3701938986778259, "learning_rate": 9.82839496731194e-06, "loss": 0.5775, "step": 430 }, { "epoch": 2.668711656441718, "grad_norm": 0.4202510118484497, "learning_rate": 9.818999330074288e-06, "loss": 0.5833, "step": 435 }, { "epoch": 2.6993865030674846, "grad_norm": 0.39413678646087646, "learning_rate": 9.809358024371025e-06, "loss": 0.5748, "step": 440 }, { "epoch": 2.7300613496932513, "grad_norm": 0.3659398555755615, "learning_rate": 9.799471541707672e-06, "loss": 0.5769, "step": 445 }, { "epoch": 2.7607361963190185, "grad_norm": 0.3878413140773773, "learning_rate": 9.789340386088663e-06, "loss": 0.5786, "step": 450 }, { "epoch": 2.791411042944785, "grad_norm": 0.38252297043800354, "learning_rate": 9.778965073991652e-06, "loss": 0.5767, "step": 455 }, { "epoch": 2.8220858895705523, "grad_norm": 0.36087849736213684, "learning_rate": 9.768346134341174e-06, "loss": 0.578, "step": 460 }, { "epoch": 2.852760736196319, "grad_norm": 0.376136839389801, "learning_rate": 9.757484108481695e-06, "loss": 0.574, "step": 465 }, { "epoch": 2.883435582822086, "grad_norm": 0.4361047148704529, "learning_rate": 9.74637955015001e-06, "loss": 0.5728, "step": 470 }, { "epoch": 2.914110429447853, "grad_norm": 0.39456483721733093, "learning_rate": 9.735033025447e-06, "loss": 0.5757, "step": 475 }, { "epoch": 2.9447852760736195, "grad_norm": 0.4185245633125305, "learning_rate": 9.723445112808802e-06, "loss": 0.5727, "step": 480 }, { "epoch": 2.9754601226993866, "grad_norm": 0.39723867177963257, "learning_rate": 9.71161640297729e-06, "loss": 0.5687, "step": 485 }, { "epoch": 3.0061349693251533, "grad_norm": 0.416050523519516, "learning_rate": 9.699547498969978e-06, "loss": 0.5705, "step": 490 }, { "epoch": 3.03680981595092, "grad_norm": 0.423635333776474, "learning_rate": 9.687239016049275e-06, "loss": 0.5491, "step": 495 }, { "epoch": 3.067484662576687, "grad_norm": 0.3904474675655365, "learning_rate": 9.674691581691114e-06, "loss": 0.5454, "step": 500 }, { "epoch": 3.098159509202454, "grad_norm": 0.4019912779331207, "learning_rate": 9.661905835552974e-06, "loss": 0.5467, "step": 505 }, { "epoch": 3.128834355828221, "grad_norm": 0.41804239153862, "learning_rate": 9.648882429441258e-06, "loss": 0.5475, "step": 510 }, { "epoch": 3.1595092024539877, "grad_norm": 0.4303177297115326, "learning_rate": 9.635622027278076e-06, "loss": 0.5455, "step": 515 }, { "epoch": 3.190184049079755, "grad_norm": 0.4063819348812103, "learning_rate": 9.622125305067394e-06, "loss": 0.5473, "step": 520 }, { "epoch": 3.2208588957055215, "grad_norm": 0.43505850434303284, "learning_rate": 9.608392950860568e-06, "loss": 0.5436, "step": 525 }, { "epoch": 3.2515337423312882, "grad_norm": 0.3967374563217163, "learning_rate": 9.594425664721275e-06, "loss": 0.5445, "step": 530 }, { "epoch": 3.2822085889570554, "grad_norm": 0.47021791338920593, "learning_rate": 9.580224158689821e-06, "loss": 0.5504, "step": 535 }, { "epoch": 3.312883435582822, "grad_norm": 0.3992370069026947, "learning_rate": 9.565789156746843e-06, "loss": 0.547, "step": 540 }, { "epoch": 3.3435582822085887, "grad_norm": 0.39715853333473206, "learning_rate": 9.551121394776395e-06, "loss": 0.5412, "step": 545 }, { "epoch": 3.374233128834356, "grad_norm": 0.42063596844673157, "learning_rate": 9.536221620528442e-06, "loss": 0.5488, "step": 550 }, { "epoch": 3.4049079754601226, "grad_norm": 0.42583799362182617, "learning_rate": 9.521090593580737e-06, "loss": 0.5445, "step": 555 }, { "epoch": 3.4355828220858897, "grad_norm": 0.43498581647872925, "learning_rate": 9.505729085300098e-06, "loss": 0.5463, "step": 560 }, { "epoch": 3.4662576687116564, "grad_norm": 0.4072875380516052, "learning_rate": 9.490137878803078e-06, "loss": 0.55, "step": 565 }, { "epoch": 3.4969325153374236, "grad_norm": 0.3940719664096832, "learning_rate": 9.47431776891606e-06, "loss": 0.5473, "step": 570 }, { "epoch": 3.5276073619631902, "grad_norm": 0.4124390184879303, "learning_rate": 9.458269562134717e-06, "loss": 0.5386, "step": 575 }, { "epoch": 3.558282208588957, "grad_norm": 0.3916858732700348, "learning_rate": 9.441994076582907e-06, "loss": 0.5448, "step": 580 }, { "epoch": 3.588957055214724, "grad_norm": 0.3731173276901245, "learning_rate": 9.425492141970973e-06, "loss": 0.5464, "step": 585 }, { "epoch": 3.6196319018404908, "grad_norm": 0.3597932457923889, "learning_rate": 9.408764599553429e-06, "loss": 0.5479, "step": 590 }, { "epoch": 3.6503067484662575, "grad_norm": 0.3645245432853699, "learning_rate": 9.391812302086088e-06, "loss": 0.5439, "step": 595 }, { "epoch": 3.6809815950920246, "grad_norm": 0.3898046016693115, "learning_rate": 9.374636113782576e-06, "loss": 0.5476, "step": 600 }, { "epoch": 3.7116564417177913, "grad_norm": 0.43808862566947937, "learning_rate": 9.357236910270292e-06, "loss": 0.5449, "step": 605 }, { "epoch": 3.7423312883435584, "grad_norm": 0.4190289378166199, "learning_rate": 9.339615578545753e-06, "loss": 0.5437, "step": 610 }, { "epoch": 3.773006134969325, "grad_norm": 0.4174676239490509, "learning_rate": 9.321773016929382e-06, "loss": 0.5397, "step": 615 }, { "epoch": 3.8036809815950923, "grad_norm": 0.43420159816741943, "learning_rate": 9.30371013501972e-06, "loss": 0.5424, "step": 620 }, { "epoch": 3.834355828220859, "grad_norm": 0.3853442668914795, "learning_rate": 9.285427853647038e-06, "loss": 0.5445, "step": 625 }, { "epoch": 3.8650306748466257, "grad_norm": 0.3969941735267639, "learning_rate": 9.26692710482641e-06, "loss": 0.5443, "step": 630 }, { "epoch": 3.895705521472393, "grad_norm": 0.3643360137939453, "learning_rate": 9.248208831710195e-06, "loss": 0.5439, "step": 635 }, { "epoch": 3.9263803680981595, "grad_norm": 0.4028114676475525, "learning_rate": 9.229273988539951e-06, "loss": 0.5413, "step": 640 }, { "epoch": 3.957055214723926, "grad_norm": 0.37028396129608154, "learning_rate": 9.210123540597792e-06, "loss": 0.5454, "step": 645 }, { "epoch": 3.9877300613496933, "grad_norm": 0.37116727232933044, "learning_rate": 9.190758464157184e-06, "loss": 0.5383, "step": 650 }, { "epoch": 4.0184049079754605, "grad_norm": 0.5018491744995117, "learning_rate": 9.171179746433164e-06, "loss": 0.5207, "step": 655 }, { "epoch": 4.049079754601227, "grad_norm": 0.4621087610721588, "learning_rate": 9.151388385532022e-06, "loss": 0.5123, "step": 660 }, { "epoch": 4.079754601226994, "grad_norm": 0.42231205105781555, "learning_rate": 9.131385390400417e-06, "loss": 0.5174, "step": 665 }, { "epoch": 4.110429447852761, "grad_norm": 0.3881925046443939, "learning_rate": 9.111171780773938e-06, "loss": 0.5137, "step": 670 }, { "epoch": 4.141104294478527, "grad_norm": 0.4086911380290985, "learning_rate": 9.090748587125118e-06, "loss": 0.516, "step": 675 }, { "epoch": 4.171779141104294, "grad_norm": 0.39884117245674133, "learning_rate": 9.070116850610911e-06, "loss": 0.5126, "step": 680 }, { "epoch": 4.2024539877300615, "grad_norm": 0.44755688309669495, "learning_rate": 9.049277623019603e-06, "loss": 0.5165, "step": 685 }, { "epoch": 4.233128834355828, "grad_norm": 0.39085808396339417, "learning_rate": 9.0282319667172e-06, "loss": 0.5149, "step": 690 }, { "epoch": 4.263803680981595, "grad_norm": 0.43618932366371155, "learning_rate": 9.006980954593262e-06, "loss": 0.5121, "step": 695 }, { "epoch": 4.294478527607362, "grad_norm": 0.3801281452178955, "learning_rate": 8.985525670006225e-06, "loss": 0.5152, "step": 700 }, { "epoch": 4.325153374233129, "grad_norm": 0.4198702871799469, "learning_rate": 8.963867206728147e-06, "loss": 0.5182, "step": 705 }, { "epoch": 4.355828220858895, "grad_norm": 0.39775219559669495, "learning_rate": 8.942006668888972e-06, "loss": 0.5196, "step": 710 }, { "epoch": 4.386503067484663, "grad_norm": 0.39523759484291077, "learning_rate": 8.919945170920224e-06, "loss": 0.5174, "step": 715 }, { "epoch": 4.41717791411043, "grad_norm": 0.39512258768081665, "learning_rate": 8.89768383749821e-06, "loss": 0.5165, "step": 720 }, { "epoch": 4.447852760736196, "grad_norm": 0.4098737835884094, "learning_rate": 8.875223803486674e-06, "loss": 0.5181, "step": 725 }, { "epoch": 4.478527607361963, "grad_norm": 0.39851200580596924, "learning_rate": 8.852566213878947e-06, "loss": 0.5145, "step": 730 }, { "epoch": 4.50920245398773, "grad_norm": 0.41544604301452637, "learning_rate": 8.829712223739574e-06, "loss": 0.5121, "step": 735 }, { "epoch": 4.539877300613497, "grad_norm": 0.42748644948005676, "learning_rate": 8.80666299814543e-06, "loss": 0.5148, "step": 740 }, { "epoch": 4.570552147239264, "grad_norm": 0.42468902468681335, "learning_rate": 8.783419712126335e-06, "loss": 0.5164, "step": 745 }, { "epoch": 4.601226993865031, "grad_norm": 0.41848933696746826, "learning_rate": 8.759983550605132e-06, "loss": 0.511, "step": 750 }, { "epoch": 4.631901840490798, "grad_norm": 0.3945312201976776, "learning_rate": 8.736355708337298e-06, "loss": 0.5143, "step": 755 }, { "epoch": 4.662576687116564, "grad_norm": 0.3941504657268524, "learning_rate": 8.71253738985003e-06, "loss": 0.5131, "step": 760 }, { "epoch": 4.693251533742331, "grad_norm": 0.4362662732601166, "learning_rate": 8.688529809380843e-06, "loss": 0.517, "step": 765 }, { "epoch": 4.723926380368098, "grad_norm": 0.4152030646800995, "learning_rate": 8.66433419081566e-06, "loss": 0.5199, "step": 770 }, { "epoch": 4.754601226993865, "grad_norm": 0.40423014760017395, "learning_rate": 8.639951767626429e-06, "loss": 0.5178, "step": 775 }, { "epoch": 4.785276073619632, "grad_norm": 0.393555223941803, "learning_rate": 8.615383782808238e-06, "loss": 0.5141, "step": 780 }, { "epoch": 4.815950920245399, "grad_norm": 0.3810482323169708, "learning_rate": 8.590631488815945e-06, "loss": 0.5155, "step": 785 }, { "epoch": 4.846625766871165, "grad_norm": 0.3922368884086609, "learning_rate": 8.565696147500338e-06, "loss": 0.5115, "step": 790 }, { "epoch": 4.877300613496932, "grad_norm": 0.36917635798454285, "learning_rate": 8.540579030043795e-06, "loss": 0.5185, "step": 795 }, { "epoch": 4.9079754601226995, "grad_norm": 0.37421196699142456, "learning_rate": 8.515281416895489e-06, "loss": 0.5143, "step": 800 }, { "epoch": 4.938650306748467, "grad_norm": 0.37189459800720215, "learning_rate": 8.48980459770611e-06, "loss": 0.5145, "step": 805 }, { "epoch": 4.969325153374233, "grad_norm": 0.3715671896934509, "learning_rate": 8.464149871262118e-06, "loss": 0.5116, "step": 810 }, { "epoch": 5.0, "grad_norm": 0.4017976224422455, "learning_rate": 8.43831854541953e-06, "loss": 0.5113, "step": 815 }, { "epoch": 5.030674846625767, "grad_norm": 0.43677598237991333, "learning_rate": 8.412311937037255e-06, "loss": 0.484, "step": 820 }, { "epoch": 5.061349693251533, "grad_norm": 0.4145989418029785, "learning_rate": 8.386131371909948e-06, "loss": 0.4879, "step": 825 }, { "epoch": 5.0920245398773005, "grad_norm": 0.4305966794490814, "learning_rate": 8.35977818470044e-06, "loss": 0.4855, "step": 830 }, { "epoch": 5.122699386503068, "grad_norm": 0.40984871983528137, "learning_rate": 8.33325371887168e-06, "loss": 0.4853, "step": 835 }, { "epoch": 5.153374233128835, "grad_norm": 0.4154280722141266, "learning_rate": 8.30655932661826e-06, "loss": 0.4889, "step": 840 }, { "epoch": 5.184049079754601, "grad_norm": 0.403626948595047, "learning_rate": 8.279696368797471e-06, "loss": 0.4946, "step": 845 }, { "epoch": 5.214723926380368, "grad_norm": 0.45823124051094055, "learning_rate": 8.252666214859936e-06, "loss": 0.4855, "step": 850 }, { "epoch": 5.245398773006135, "grad_norm": 0.4164683520793915, "learning_rate": 8.225470242779791e-06, "loss": 0.4873, "step": 855 }, { "epoch": 5.276073619631902, "grad_norm": 0.42235732078552246, "learning_rate": 8.19810983898444e-06, "loss": 0.492, "step": 860 }, { "epoch": 5.306748466257669, "grad_norm": 0.39570316672325134, "learning_rate": 8.170586398283878e-06, "loss": 0.4879, "step": 865 }, { "epoch": 5.337423312883436, "grad_norm": 0.4298191964626312, "learning_rate": 8.142901323799578e-06, "loss": 0.4877, "step": 870 }, { "epoch": 5.368098159509202, "grad_norm": 0.4283137321472168, "learning_rate": 8.115056026892965e-06, "loss": 0.4877, "step": 875 }, { "epoch": 5.398773006134969, "grad_norm": 0.4249846935272217, "learning_rate": 8.08705192709347e-06, "loss": 0.4899, "step": 880 }, { "epoch": 5.429447852760736, "grad_norm": 0.40995773673057556, "learning_rate": 8.058890452026155e-06, "loss": 0.488, "step": 885 }, { "epoch": 5.460122699386503, "grad_norm": 0.40157032012939453, "learning_rate": 8.030573037338942e-06, "loss": 0.4924, "step": 890 }, { "epoch": 5.49079754601227, "grad_norm": 0.40010377764701843, "learning_rate": 8.002101126629422e-06, "loss": 0.4884, "step": 895 }, { "epoch": 5.521472392638037, "grad_norm": 0.40110117197036743, "learning_rate": 7.973476171371255e-06, "loss": 0.4868, "step": 900 }, { "epoch": 5.552147239263804, "grad_norm": 0.43940532207489014, "learning_rate": 7.94469963084019e-06, "loss": 0.486, "step": 905 }, { "epoch": 5.58282208588957, "grad_norm": 0.389099657535553, "learning_rate": 7.91577297203966e-06, "loss": 0.4873, "step": 910 }, { "epoch": 5.613496932515337, "grad_norm": 0.45393890142440796, "learning_rate": 7.886697669625995e-06, "loss": 0.4935, "step": 915 }, { "epoch": 5.644171779141105, "grad_norm": 0.44767045974731445, "learning_rate": 7.857475205833255e-06, "loss": 0.4939, "step": 920 }, { "epoch": 5.674846625766871, "grad_norm": 0.37822064757347107, "learning_rate": 7.828107070397657e-06, "loss": 0.4833, "step": 925 }, { "epoch": 5.705521472392638, "grad_norm": 0.47380632162094116, "learning_rate": 7.798594760481639e-06, "loss": 0.4883, "step": 930 }, { "epoch": 5.736196319018405, "grad_norm": 0.41387900710105896, "learning_rate": 7.768939780597523e-06, "loss": 0.491, "step": 935 }, { "epoch": 5.766871165644172, "grad_norm": 0.44347015023231506, "learning_rate": 7.739143642530833e-06, "loss": 0.4913, "step": 940 }, { "epoch": 5.7975460122699385, "grad_norm": 0.43487074971199036, "learning_rate": 7.70920786526321e-06, "loss": 0.4937, "step": 945 }, { "epoch": 5.828220858895706, "grad_norm": 0.39147791266441345, "learning_rate": 7.679133974894984e-06, "loss": 0.4887, "step": 950 }, { "epoch": 5.858895705521473, "grad_norm": 0.4729338586330414, "learning_rate": 7.648923504567374e-06, "loss": 0.4871, "step": 955 }, { "epoch": 5.889570552147239, "grad_norm": 0.38986459374427795, "learning_rate": 7.618577994384324e-06, "loss": 0.4881, "step": 960 }, { "epoch": 5.920245398773006, "grad_norm": 0.421047180891037, "learning_rate": 7.588098991334001e-06, "loss": 0.4875, "step": 965 }, { "epoch": 5.950920245398773, "grad_norm": 0.4043465852737427, "learning_rate": 7.557488049209921e-06, "loss": 0.4878, "step": 970 }, { "epoch": 5.9815950920245395, "grad_norm": 0.39679425954818726, "learning_rate": 7.52674672853174e-06, "loss": 0.4873, "step": 975 }, { "epoch": 6.012269938650307, "grad_norm": 0.4268780052661896, "learning_rate": 7.495876596465703e-06, "loss": 0.4755, "step": 980 }, { "epoch": 6.042944785276074, "grad_norm": 0.49131566286087036, "learning_rate": 7.464879226744748e-06, "loss": 0.46, "step": 985 }, { "epoch": 6.07361963190184, "grad_norm": 0.422818660736084, "learning_rate": 7.433756199588282e-06, "loss": 0.4606, "step": 990 }, { "epoch": 6.104294478527607, "grad_norm": 0.4517934322357178, "learning_rate": 7.402509101621618e-06, "loss": 0.4616, "step": 995 }, { "epoch": 6.134969325153374, "grad_norm": 0.42230966687202454, "learning_rate": 7.371139525795094e-06, "loss": 0.4625, "step": 1000 }, { "epoch": 6.1656441717791415, "grad_norm": 0.4756508767604828, "learning_rate": 7.3396490713028674e-06, "loss": 0.4631, "step": 1005 }, { "epoch": 6.196319018404908, "grad_norm": 0.4194376468658447, "learning_rate": 7.308039343501381e-06, "loss": 0.4636, "step": 1010 }, { "epoch": 6.226993865030675, "grad_norm": 0.4464778006076813, "learning_rate": 7.276311953827533e-06, "loss": 0.4634, "step": 1015 }, { "epoch": 6.257668711656442, "grad_norm": 0.42353737354278564, "learning_rate": 7.244468519716521e-06, "loss": 0.4618, "step": 1020 }, { "epoch": 6.288343558282208, "grad_norm": 0.4474755525588989, "learning_rate": 7.212510664519391e-06, "loss": 0.4638, "step": 1025 }, { "epoch": 6.319018404907975, "grad_norm": 0.41456103324890137, "learning_rate": 7.180440017420277e-06, "loss": 0.4603, "step": 1030 }, { "epoch": 6.3496932515337425, "grad_norm": 0.41820865869522095, "learning_rate": 7.148258213353347e-06, "loss": 0.4625, "step": 1035 }, { "epoch": 6.38036809815951, "grad_norm": 0.42110052704811096, "learning_rate": 7.115966892919459e-06, "loss": 0.4629, "step": 1040 }, { "epoch": 6.411042944785276, "grad_norm": 0.4150598645210266, "learning_rate": 7.083567702302517e-06, "loss": 0.4604, "step": 1045 }, { "epoch": 6.441717791411043, "grad_norm": 0.40612462162971497, "learning_rate": 7.05106229318556e-06, "loss": 0.4642, "step": 1050 }, { "epoch": 6.47239263803681, "grad_norm": 0.4007202386856079, "learning_rate": 7.018452322666549e-06, "loss": 0.4692, "step": 1055 }, { "epoch": 6.5030674846625764, "grad_norm": 0.4103841483592987, "learning_rate": 6.985739453173903e-06, "loss": 0.4606, "step": 1060 }, { "epoch": 6.533742331288344, "grad_norm": 0.41603884100914, "learning_rate": 6.9529253523817396e-06, "loss": 0.4646, "step": 1065 }, { "epoch": 6.564417177914111, "grad_norm": 0.40389156341552734, "learning_rate": 6.9200116931248575e-06, "loss": 0.4662, "step": 1070 }, { "epoch": 6.595092024539877, "grad_norm": 0.4311538338661194, "learning_rate": 6.887000153313468e-06, "loss": 0.467, "step": 1075 }, { "epoch": 6.625766871165644, "grad_norm": 0.4369893968105316, "learning_rate": 6.853892415847645e-06, "loss": 0.4656, "step": 1080 }, { "epoch": 6.656441717791411, "grad_norm": 0.4239542484283447, "learning_rate": 6.8206901685315366e-06, "loss": 0.4635, "step": 1085 }, { "epoch": 6.6871165644171775, "grad_norm": 0.4784742593765259, "learning_rate": 6.787395103987323e-06, "loss": 0.4647, "step": 1090 }, { "epoch": 6.717791411042945, "grad_norm": 0.4250466227531433, "learning_rate": 6.754008919568927e-06, "loss": 0.4642, "step": 1095 }, { "epoch": 6.748466257668712, "grad_norm": 0.40565210580825806, "learning_rate": 6.72053331727549e-06, "loss": 0.4647, "step": 1100 }, { "epoch": 6.779141104294479, "grad_norm": 0.41947269439697266, "learning_rate": 6.686970003664588e-06, "loss": 0.4678, "step": 1105 }, { "epoch": 6.809815950920245, "grad_norm": 0.43468502163887024, "learning_rate": 6.653320689765257e-06, "loss": 0.466, "step": 1110 }, { "epoch": 6.840490797546012, "grad_norm": 0.4085966944694519, "learning_rate": 6.619587090990748e-06, "loss": 0.4642, "step": 1115 }, { "epoch": 6.871165644171779, "grad_norm": 0.40702173113822937, "learning_rate": 6.585770927051085e-06, "loss": 0.4645, "step": 1120 }, { "epoch": 6.901840490797546, "grad_norm": 0.4169243276119232, "learning_rate": 6.551873921865393e-06, "loss": 0.4661, "step": 1125 }, { "epoch": 6.932515337423313, "grad_norm": 0.4328126013278961, "learning_rate": 6.517897803474011e-06, "loss": 0.4679, "step": 1130 }, { "epoch": 6.96319018404908, "grad_norm": 0.40873920917510986, "learning_rate": 6.483844303950411e-06, "loss": 0.4635, "step": 1135 }, { "epoch": 6.993865030674847, "grad_norm": 0.44031643867492676, "learning_rate": 6.4497151593128795e-06, "loss": 0.4651, "step": 1140 }, { "epoch": 7.024539877300613, "grad_norm": 0.6135973334312439, "learning_rate": 6.415512109436031e-06, "loss": 0.4404, "step": 1145 }, { "epoch": 7.0552147239263805, "grad_norm": 0.5111101269721985, "learning_rate": 6.381236897962102e-06, "loss": 0.4372, "step": 1150 }, { "epoch": 7.085889570552148, "grad_norm": 0.4504176080226898, "learning_rate": 6.3468912722120715e-06, "loss": 0.4397, "step": 1155 }, { "epoch": 7.116564417177914, "grad_norm": 0.42820578813552856, "learning_rate": 6.312476983096573e-06, "loss": 0.44, "step": 1160 }, { "epoch": 7.147239263803681, "grad_norm": 0.44418537616729736, "learning_rate": 6.277995785026642e-06, "loss": 0.4374, "step": 1165 }, { "epoch": 7.177914110429448, "grad_norm": 0.43857964873313904, "learning_rate": 6.243449435824276e-06, "loss": 0.4394, "step": 1170 }, { "epoch": 7.208588957055214, "grad_norm": 0.4350876808166504, "learning_rate": 6.2088396966328155e-06, "loss": 0.4346, "step": 1175 }, { "epoch": 7.2392638036809815, "grad_norm": 0.4213852286338806, "learning_rate": 6.174168331827179e-06, "loss": 0.4381, "step": 1180 }, { "epoch": 7.269938650306749, "grad_norm": 0.4279233515262604, "learning_rate": 6.139437108923898e-06, "loss": 0.4405, "step": 1185 }, { "epoch": 7.300613496932515, "grad_norm": 0.4222026467323303, "learning_rate": 6.1046477984910215e-06, "loss": 0.4383, "step": 1190 }, { "epoch": 7.331288343558282, "grad_norm": 0.4608646631240845, "learning_rate": 6.069802174057849e-06, "loss": 0.4399, "step": 1195 }, { "epoch": 7.361963190184049, "grad_norm": 0.43802234530448914, "learning_rate": 6.034902012024521e-06, "loss": 0.4418, "step": 1200 }, { "epoch": 7.392638036809816, "grad_norm": 0.45217955112457275, "learning_rate": 5.999949091571462e-06, "loss": 0.4432, "step": 1205 }, { "epoch": 7.423312883435583, "grad_norm": 0.4765477478504181, "learning_rate": 5.964945194568669e-06, "loss": 0.4341, "step": 1210 }, { "epoch": 7.45398773006135, "grad_norm": 0.4318167269229889, "learning_rate": 5.9298921054848826e-06, "loss": 0.4355, "step": 1215 }, { "epoch": 7.484662576687117, "grad_norm": 0.4203420877456665, "learning_rate": 5.894791611296614e-06, "loss": 0.4417, "step": 1220 }, { "epoch": 7.515337423312883, "grad_norm": 0.4351012408733368, "learning_rate": 5.859645501397048e-06, "loss": 0.4461, "step": 1225 }, { "epoch": 7.54601226993865, "grad_norm": 0.4254397749900818, "learning_rate": 5.824455567504817e-06, "loss": 0.4399, "step": 1230 }, { "epoch": 7.576687116564417, "grad_norm": 0.40902575850486755, "learning_rate": 5.789223603572663e-06, "loss": 0.4407, "step": 1235 }, { "epoch": 7.6073619631901845, "grad_norm": 0.4211549162864685, "learning_rate": 5.753951405695981e-06, "loss": 0.4388, "step": 1240 }, { "epoch": 7.638036809815951, "grad_norm": 0.43186110258102417, "learning_rate": 5.7186407720212655e-06, "loss": 0.4431, "step": 1245 }, { "epoch": 7.668711656441718, "grad_norm": 0.4310693144798279, "learning_rate": 5.683293502654429e-06, "loss": 0.4419, "step": 1250 }, { "epoch": 7.699386503067485, "grad_norm": 0.4637373089790344, "learning_rate": 5.647911399569043e-06, "loss": 0.4415, "step": 1255 }, { "epoch": 7.730061349693251, "grad_norm": 0.4452053904533386, "learning_rate": 5.612496266514468e-06, "loss": 0.4443, "step": 1260 }, { "epoch": 7.7607361963190185, "grad_norm": 0.44300079345703125, "learning_rate": 5.577049908923912e-06, "loss": 0.4424, "step": 1265 }, { "epoch": 7.791411042944786, "grad_norm": 0.4136279225349426, "learning_rate": 5.541574133822374e-06, "loss": 0.4381, "step": 1270 }, { "epoch": 7.822085889570552, "grad_norm": 0.39727237820625305, "learning_rate": 5.506070749734539e-06, "loss": 0.4449, "step": 1275 }, { "epoch": 7.852760736196319, "grad_norm": 0.4188498258590698, "learning_rate": 5.470541566592573e-06, "loss": 0.4438, "step": 1280 }, { "epoch": 7.883435582822086, "grad_norm": 0.43856287002563477, "learning_rate": 5.434988395643852e-06, "loss": 0.4433, "step": 1285 }, { "epoch": 7.914110429447852, "grad_norm": 0.4030952453613281, "learning_rate": 5.3994130493586385e-06, "loss": 0.4419, "step": 1290 }, { "epoch": 7.9447852760736195, "grad_norm": 0.425555557012558, "learning_rate": 5.363817341337665e-06, "loss": 0.4424, "step": 1295 }, { "epoch": 7.975460122699387, "grad_norm": 0.4450756013393402, "learning_rate": 5.328203086219693e-06, "loss": 0.4433, "step": 1300 }, { "epoch": 8.006134969325153, "grad_norm": 0.5804970860481262, "learning_rate": 5.292572099588998e-06, "loss": 0.4375, "step": 1305 }, { "epoch": 8.036809815950921, "grad_norm": 0.5236377716064453, "learning_rate": 5.2569261978828155e-06, "loss": 0.4167, "step": 1310 }, { "epoch": 8.067484662576687, "grad_norm": 0.467786580324173, "learning_rate": 5.221267198298738e-06, "loss": 0.4159, "step": 1315 }, { "epoch": 8.098159509202453, "grad_norm": 0.4583148956298828, "learning_rate": 5.185596918702072e-06, "loss": 0.4125, "step": 1320 }, { "epoch": 8.128834355828221, "grad_norm": 0.443567156791687, "learning_rate": 5.1499171775331754e-06, "loss": 0.4165, "step": 1325 }, { "epoch": 8.159509202453988, "grad_norm": 0.47137385606765747, "learning_rate": 5.114229793714749e-06, "loss": 0.4157, "step": 1330 }, { "epoch": 8.190184049079754, "grad_norm": 0.4504995048046112, "learning_rate": 5.078536586559104e-06, "loss": 0.4155, "step": 1335 }, { "epoch": 8.220858895705522, "grad_norm": 0.4822964668273926, "learning_rate": 5.042839375675425e-06, "loss": 0.4189, "step": 1340 }, { "epoch": 8.251533742331288, "grad_norm": 0.441819429397583, "learning_rate": 5.0071399808770015e-06, "loss": 0.4165, "step": 1345 }, { "epoch": 8.282208588957054, "grad_norm": 0.46287593245506287, "learning_rate": 4.971440222088459e-06, "loss": 0.4158, "step": 1350 }, { "epoch": 8.312883435582823, "grad_norm": 0.46531328558921814, "learning_rate": 4.935741919252973e-06, "loss": 0.4213, "step": 1355 }, { "epoch": 8.343558282208589, "grad_norm": 0.45542043447494507, "learning_rate": 4.900046892239507e-06, "loss": 0.4122, "step": 1360 }, { "epoch": 8.374233128834355, "grad_norm": 0.4518256187438965, "learning_rate": 4.864356960750011e-06, "loss": 0.4179, "step": 1365 }, { "epoch": 8.404907975460123, "grad_norm": 0.4747672975063324, "learning_rate": 4.828673944226684e-06, "loss": 0.4187, "step": 1370 }, { "epoch": 8.43558282208589, "grad_norm": 0.4235823452472687, "learning_rate": 4.792999661759196e-06, "loss": 0.421, "step": 1375 }, { "epoch": 8.466257668711656, "grad_norm": 0.41661733388900757, "learning_rate": 4.757335931991965e-06, "loss": 0.4189, "step": 1380 }, { "epoch": 8.496932515337424, "grad_norm": 0.4476306140422821, "learning_rate": 4.721684573031447e-06, "loss": 0.4189, "step": 1385 }, { "epoch": 8.52760736196319, "grad_norm": 0.45303910970687866, "learning_rate": 4.686047402353433e-06, "loss": 0.4181, "step": 1390 }, { "epoch": 8.558282208588958, "grad_norm": 0.44240671396255493, "learning_rate": 4.650426236710421e-06, "loss": 0.418, "step": 1395 }, { "epoch": 8.588957055214724, "grad_norm": 0.45954430103302, "learning_rate": 4.614822892038974e-06, "loss": 0.419, "step": 1400 }, { "epoch": 8.61963190184049, "grad_norm": 0.4528447985649109, "learning_rate": 4.579239183367166e-06, "loss": 0.418, "step": 1405 }, { "epoch": 8.650306748466258, "grad_norm": 0.4467931389808655, "learning_rate": 4.543676924722042e-06, "loss": 0.4177, "step": 1410 }, { "epoch": 8.680981595092025, "grad_norm": 0.4380550682544708, "learning_rate": 4.508137929037138e-06, "loss": 0.4206, "step": 1415 }, { "epoch": 8.71165644171779, "grad_norm": 0.4435415267944336, "learning_rate": 4.472624008060071e-06, "loss": 0.42, "step": 1420 }, { "epoch": 8.742331288343559, "grad_norm": 0.4348682761192322, "learning_rate": 4.437136972260168e-06, "loss": 0.4205, "step": 1425 }, { "epoch": 8.773006134969325, "grad_norm": 0.42294904589653015, "learning_rate": 4.401678630736172e-06, "loss": 0.4211, "step": 1430 }, { "epoch": 8.803680981595091, "grad_norm": 0.42331093549728394, "learning_rate": 4.366250791124017e-06, "loss": 0.4185, "step": 1435 }, { "epoch": 8.83435582822086, "grad_norm": 0.41695448756217957, "learning_rate": 4.330855259504676e-06, "loss": 0.4215, "step": 1440 }, { "epoch": 8.865030674846626, "grad_norm": 0.4440816342830658, "learning_rate": 4.295493840312087e-06, "loss": 0.4217, "step": 1445 }, { "epoch": 8.895705521472392, "grad_norm": 0.42288738489151, "learning_rate": 4.260168336241169e-06, "loss": 0.4225, "step": 1450 }, { "epoch": 8.92638036809816, "grad_norm": 0.43750008940696716, "learning_rate": 4.224880548155913e-06, "loss": 0.4209, "step": 1455 }, { "epoch": 8.957055214723926, "grad_norm": 0.4323638081550598, "learning_rate": 4.1896322749975885e-06, "loss": 0.4284, "step": 1460 }, { "epoch": 8.987730061349692, "grad_norm": 0.42216283082962036, "learning_rate": 4.154425313693018e-06, "loss": 0.4209, "step": 1465 }, { "epoch": 9.01840490797546, "grad_norm": 0.5621673464775085, "learning_rate": 4.119261459062992e-06, "loss": 0.4052, "step": 1470 }, { "epoch": 9.049079754601227, "grad_norm": 0.48066237568855286, "learning_rate": 4.084142503730754e-06, "loss": 0.3959, "step": 1475 }, { "epoch": 9.079754601226995, "grad_norm": 0.4512442648410797, "learning_rate": 4.049070238030618e-06, "loss": 0.3949, "step": 1480 }, { "epoch": 9.110429447852761, "grad_norm": 0.4584384560585022, "learning_rate": 4.014046449916703e-06, "loss": 0.394, "step": 1485 }, { "epoch": 9.141104294478527, "grad_norm": 0.4640498161315918, "learning_rate": 3.979072924871784e-06, "loss": 0.3932, "step": 1490 }, { "epoch": 9.171779141104295, "grad_norm": 0.44619888067245483, "learning_rate": 3.944151445816265e-06, "loss": 0.3989, "step": 1495 }, { "epoch": 9.202453987730062, "grad_norm": 0.4594890773296356, "learning_rate": 3.909283793017289e-06, "loss": 0.3939, "step": 1500 }, { "epoch": 9.233128834355828, "grad_norm": 0.47108158469200134, "learning_rate": 3.874471743997983e-06, "loss": 0.3981, "step": 1505 }, { "epoch": 9.263803680981596, "grad_norm": 0.4786073565483093, "learning_rate": 3.839717073446842e-06, "loss": 0.3977, "step": 1510 }, { "epoch": 9.294478527607362, "grad_norm": 0.47187334299087524, "learning_rate": 3.80502155312726e-06, "loss": 0.395, "step": 1515 }, { "epoch": 9.325153374233128, "grad_norm": 0.46660172939300537, "learning_rate": 3.770386951787193e-06, "loss": 0.3971, "step": 1520 }, { "epoch": 9.355828220858896, "grad_norm": 0.4632403552532196, "learning_rate": 3.735815035069007e-06, "loss": 0.3947, "step": 1525 }, { "epoch": 9.386503067484663, "grad_norm": 0.47112977504730225, "learning_rate": 3.7013075654194586e-06, "loss": 0.3999, "step": 1530 }, { "epoch": 9.417177914110429, "grad_norm": 0.48859986662864685, "learning_rate": 3.666866301999843e-06, "loss": 0.3983, "step": 1535 }, { "epoch": 9.447852760736197, "grad_norm": 0.44551530480384827, "learning_rate": 3.6324930005963256e-06, "loss": 0.4012, "step": 1540 }, { "epoch": 9.478527607361963, "grad_norm": 0.4551395773887634, "learning_rate": 3.5981894135304207e-06, "loss": 0.4018, "step": 1545 }, { "epoch": 9.50920245398773, "grad_norm": 0.4616907835006714, "learning_rate": 3.563957289569669e-06, "loss": 0.3995, "step": 1550 }, { "epoch": 9.539877300613497, "grad_norm": 0.4593202769756317, "learning_rate": 3.5297983738384813e-06, "loss": 0.3998, "step": 1555 }, { "epoch": 9.570552147239264, "grad_norm": 0.44857659935951233, "learning_rate": 3.495714407729174e-06, "loss": 0.4041, "step": 1560 }, { "epoch": 9.60122699386503, "grad_norm": 0.4826293885707855, "learning_rate": 3.461707128813201e-06, "loss": 0.3994, "step": 1565 }, { "epoch": 9.631901840490798, "grad_norm": 0.4611422121524811, "learning_rate": 3.427778270752561e-06, "loss": 0.4035, "step": 1570 }, { "epoch": 9.662576687116564, "grad_norm": 0.4648556411266327, "learning_rate": 3.3939295632114313e-06, "loss": 0.4021, "step": 1575 }, { "epoch": 9.69325153374233, "grad_norm": 0.4454943835735321, "learning_rate": 3.3601627317679832e-06, "loss": 0.3982, "step": 1580 }, { "epoch": 9.723926380368098, "grad_norm": 0.45751452445983887, "learning_rate": 3.326479497826409e-06, "loss": 0.4007, "step": 1585 }, { "epoch": 9.754601226993865, "grad_norm": 0.4437613785266876, "learning_rate": 3.292881578529179e-06, "loss": 0.4038, "step": 1590 }, { "epoch": 9.785276073619633, "grad_norm": 0.44608426094055176, "learning_rate": 3.2593706866694934e-06, "loss": 0.399, "step": 1595 }, { "epoch": 9.815950920245399, "grad_norm": 0.44054606556892395, "learning_rate": 3.225948530603965e-06, "loss": 0.4004, "step": 1600 }, { "epoch": 9.846625766871165, "grad_norm": 0.44678565859794617, "learning_rate": 3.192616814165537e-06, "loss": 0.3987, "step": 1605 }, { "epoch": 9.877300613496933, "grad_norm": 0.4583883285522461, "learning_rate": 3.1593772365766107e-06, "loss": 0.4016, "step": 1610 }, { "epoch": 9.9079754601227, "grad_norm": 0.44818422198295593, "learning_rate": 3.126231492362435e-06, "loss": 0.4031, "step": 1615 }, { "epoch": 9.938650306748466, "grad_norm": 0.4891637861728668, "learning_rate": 3.0931812712647107e-06, "loss": 0.4017, "step": 1620 }, { "epoch": 9.969325153374234, "grad_norm": 0.47009608149528503, "learning_rate": 3.0602282581554498e-06, "loss": 0.3981, "step": 1625 }, { "epoch": 10.0, "grad_norm": 0.476095050573349, "learning_rate": 3.0273741329510852e-06, "loss": 0.3981, "step": 1630 }, { "epoch": 10.030674846625766, "grad_norm": 0.5378819108009338, "learning_rate": 2.9946205705268337e-06, "loss": 0.3802, "step": 1635 }, { "epoch": 10.061349693251534, "grad_norm": 0.5001988410949707, "learning_rate": 2.9619692406312983e-06, "loss": 0.3811, "step": 1640 }, { "epoch": 10.0920245398773, "grad_norm": 0.49986687302589417, "learning_rate": 2.929421807801364e-06, "loss": 0.3819, "step": 1645 }, { "epoch": 10.122699386503067, "grad_norm": 0.47913286089897156, "learning_rate": 2.8969799312773263e-06, "loss": 0.3786, "step": 1650 }, { "epoch": 10.153374233128835, "grad_norm": 0.46896302700042725, "learning_rate": 2.8646452649183132e-06, "loss": 0.3775, "step": 1655 }, { "epoch": 10.184049079754601, "grad_norm": 0.4729619324207306, "learning_rate": 2.8324194571179696e-06, "loss": 0.3781, "step": 1660 }, { "epoch": 10.214723926380367, "grad_norm": 0.49238312244415283, "learning_rate": 2.800304150720424e-06, "loss": 0.3841, "step": 1665 }, { "epoch": 10.245398773006135, "grad_norm": 0.5394685864448547, "learning_rate": 2.7683009829365417e-06, "loss": 0.3834, "step": 1670 }, { "epoch": 10.276073619631902, "grad_norm": 0.47765809297561646, "learning_rate": 2.736411585260445e-06, "loss": 0.382, "step": 1675 }, { "epoch": 10.30674846625767, "grad_norm": 0.4734129309654236, "learning_rate": 2.704637583386369e-06, "loss": 0.3828, "step": 1680 }, { "epoch": 10.337423312883436, "grad_norm": 0.48051029443740845, "learning_rate": 2.672980597125764e-06, "loss": 0.3784, "step": 1685 }, { "epoch": 10.368098159509202, "grad_norm": 0.4490968585014343, "learning_rate": 2.6414422403247174e-06, "loss": 0.3786, "step": 1690 }, { "epoch": 10.39877300613497, "grad_norm": 0.44560185074806213, "learning_rate": 2.610024120781694e-06, "loss": 0.3839, "step": 1695 }, { "epoch": 10.429447852760736, "grad_norm": 0.4588739573955536, "learning_rate": 2.5787278401655714e-06, "loss": 0.381, "step": 1700 }, { "epoch": 10.460122699386503, "grad_norm": 0.4592171311378479, "learning_rate": 2.5475549939339716e-06, "loss": 0.3828, "step": 1705 }, { "epoch": 10.49079754601227, "grad_norm": 0.47413405776023865, "learning_rate": 2.5165071712519447e-06, "loss": 0.3812, "step": 1710 }, { "epoch": 10.521472392638037, "grad_norm": 0.4702529013156891, "learning_rate": 2.4855859549109446e-06, "loss": 0.378, "step": 1715 }, { "epoch": 10.552147239263803, "grad_norm": 0.44477346539497375, "learning_rate": 2.4547929212481436e-06, "loss": 0.3841, "step": 1720 }, { "epoch": 10.582822085889571, "grad_norm": 0.4779837131500244, "learning_rate": 2.4241296400660696e-06, "loss": 0.383, "step": 1725 }, { "epoch": 10.613496932515337, "grad_norm": 0.46424034237861633, "learning_rate": 2.39359767455258e-06, "loss": 0.3832, "step": 1730 }, { "epoch": 10.644171779141104, "grad_norm": 0.4713508188724518, "learning_rate": 2.3631985812011736e-06, "loss": 0.3843, "step": 1735 }, { "epoch": 10.674846625766872, "grad_norm": 0.4567889869213104, "learning_rate": 2.332933909731635e-06, "loss": 0.3798, "step": 1740 }, { "epoch": 10.705521472392638, "grad_norm": 0.44534802436828613, "learning_rate": 2.302805203011039e-06, "loss": 0.38, "step": 1745 }, { "epoch": 10.736196319018404, "grad_norm": 0.4395006000995636, "learning_rate": 2.2728139969751005e-06, "loss": 0.384, "step": 1750 }, { "epoch": 10.766871165644172, "grad_norm": 0.4457756280899048, "learning_rate": 2.2429618205498543e-06, "loss": 0.3833, "step": 1755 }, { "epoch": 10.797546012269938, "grad_norm": 0.46420347690582275, "learning_rate": 2.213250195573734e-06, "loss": 0.3822, "step": 1760 }, { "epoch": 10.828220858895705, "grad_norm": 0.4520081877708435, "learning_rate": 2.1836806367199763e-06, "loss": 0.3836, "step": 1765 }, { "epoch": 10.858895705521473, "grad_norm": 0.4488300681114197, "learning_rate": 2.1542546514194103e-06, "loss": 0.3824, "step": 1770 }, { "epoch": 10.889570552147239, "grad_norm": 0.4576306939125061, "learning_rate": 2.124973739783609e-06, "loss": 0.385, "step": 1775 }, { "epoch": 10.920245398773005, "grad_norm": 0.46807441115379333, "learning_rate": 2.0958393945284074e-06, "loss": 0.3865, "step": 1780 }, { "epoch": 10.950920245398773, "grad_norm": 0.4553256332874298, "learning_rate": 2.066853100897822e-06, "loss": 0.3845, "step": 1785 }, { "epoch": 10.98159509202454, "grad_norm": 0.43590047955513, "learning_rate": 2.0380163365883188e-06, "loss": 0.3853, "step": 1790 }, { "epoch": 11.012269938650308, "grad_norm": 0.4983638525009155, "learning_rate": 2.0093305716734814e-06, "loss": 0.3732, "step": 1795 }, { "epoch": 11.042944785276074, "grad_norm": 0.4627988934516907, "learning_rate": 1.9807972685290843e-06, "loss": 0.3674, "step": 1800 }, { "epoch": 11.07361963190184, "grad_norm": 0.4763619303703308, "learning_rate": 1.952417881758526e-06, "loss": 0.3691, "step": 1805 }, { "epoch": 11.104294478527608, "grad_norm": 0.49472418427467346, "learning_rate": 1.9241938581186766e-06, "loss": 0.3666, "step": 1810 }, { "epoch": 11.134969325153374, "grad_norm": 0.45994389057159424, "learning_rate": 1.8961266364461306e-06, "loss": 0.3685, "step": 1815 }, { "epoch": 11.16564417177914, "grad_norm": 0.4785662889480591, "learning_rate": 1.868217647583852e-06, "loss": 0.3652, "step": 1820 }, { "epoch": 11.196319018404909, "grad_norm": 0.4587504267692566, "learning_rate": 1.8404683143082309e-06, "loss": 0.3667, "step": 1825 }, { "epoch": 11.226993865030675, "grad_norm": 0.45679721236228943, "learning_rate": 1.8128800512565514e-06, "loss": 0.3665, "step": 1830 }, { "epoch": 11.257668711656441, "grad_norm": 0.4806920289993286, "learning_rate": 1.7854542648548773e-06, "loss": 0.3663, "step": 1835 }, { "epoch": 11.28834355828221, "grad_norm": 0.45936256647109985, "learning_rate": 1.7581923532463507e-06, "loss": 0.3665, "step": 1840 }, { "epoch": 11.319018404907975, "grad_norm": 0.4692569673061371, "learning_rate": 1.731095706219914e-06, "loss": 0.3655, "step": 1845 }, { "epoch": 11.349693251533742, "grad_norm": 0.48757705092430115, "learning_rate": 1.7041657051394645e-06, "loss": 0.3696, "step": 1850 }, { "epoch": 11.38036809815951, "grad_norm": 0.4615464508533478, "learning_rate": 1.6774037228734375e-06, "loss": 0.3689, "step": 1855 }, { "epoch": 11.411042944785276, "grad_norm": 0.4684435725212097, "learning_rate": 1.650811123724802e-06, "loss": 0.3677, "step": 1860 }, { "epoch": 11.441717791411042, "grad_norm": 0.46784135699272156, "learning_rate": 1.6243892633615272e-06, "loss": 0.37, "step": 1865 }, { "epoch": 11.47239263803681, "grad_norm": 0.44636908173561096, "learning_rate": 1.598139488747467e-06, "loss": 0.3653, "step": 1870 }, { "epoch": 11.503067484662576, "grad_norm": 0.45427629351615906, "learning_rate": 1.5720631380736839e-06, "loss": 0.3678, "step": 1875 }, { "epoch": 11.533742331288344, "grad_norm": 0.44010183215141296, "learning_rate": 1.5461615406902414e-06, "loss": 0.3698, "step": 1880 }, { "epoch": 11.56441717791411, "grad_norm": 0.4783858358860016, "learning_rate": 1.5204360170384286e-06, "loss": 0.372, "step": 1885 }, { "epoch": 11.595092024539877, "grad_norm": 0.4582843780517578, "learning_rate": 1.4948878785834453e-06, "loss": 0.3719, "step": 1890 }, { "epoch": 11.625766871165645, "grad_norm": 0.44995734095573425, "learning_rate": 1.4695184277475482e-06, "loss": 0.3704, "step": 1895 }, { "epoch": 11.656441717791411, "grad_norm": 0.46788886189460754, "learning_rate": 1.4443289578436459e-06, "loss": 0.3687, "step": 1900 }, { "epoch": 11.687116564417177, "grad_norm": 0.4666103720664978, "learning_rate": 1.4193207530093806e-06, "loss": 0.3675, "step": 1905 }, { "epoch": 11.717791411042946, "grad_norm": 0.4628080427646637, "learning_rate": 1.3944950881416541e-06, "loss": 0.3707, "step": 1910 }, { "epoch": 11.748466257668712, "grad_norm": 0.44799864292144775, "learning_rate": 1.369853228831632e-06, "loss": 0.3708, "step": 1915 }, { "epoch": 11.779141104294478, "grad_norm": 0.47202908992767334, "learning_rate": 1.3453964313002337e-06, "loss": 0.3701, "step": 1920 }, { "epoch": 11.809815950920246, "grad_norm": 0.4674662947654724, "learning_rate": 1.3211259423340882e-06, "loss": 0.3689, "step": 1925 }, { "epoch": 11.840490797546012, "grad_norm": 0.4523491859436035, "learning_rate": 1.2970429992219714e-06, "loss": 0.3665, "step": 1930 }, { "epoch": 11.871165644171779, "grad_norm": 0.4463663101196289, "learning_rate": 1.2731488296917315e-06, "loss": 0.3732, "step": 1935 }, { "epoch": 11.901840490797547, "grad_norm": 0.4559671878814697, "learning_rate": 1.2494446518477022e-06, "loss": 0.3683, "step": 1940 }, { "epoch": 11.932515337423313, "grad_norm": 0.4432070851325989, "learning_rate": 1.2259316741086052e-06, "loss": 0.3703, "step": 1945 }, { "epoch": 11.963190184049079, "grad_norm": 0.4581555128097534, "learning_rate": 1.2026110951459364e-06, "loss": 0.3686, "step": 1950 }, { "epoch": 11.993865030674847, "grad_norm": 0.4442911744117737, "learning_rate": 1.1794841038228772e-06, "loss": 0.3686, "step": 1955 }, { "epoch": 12.024539877300613, "grad_norm": 0.4809685945510864, "learning_rate": 1.156551879133672e-06, "loss": 0.3568, "step": 1960 }, { "epoch": 12.05521472392638, "grad_norm": 0.4492509067058563, "learning_rate": 1.133815590143525e-06, "loss": 0.3586, "step": 1965 }, { "epoch": 12.085889570552148, "grad_norm": 0.46284252405166626, "learning_rate": 1.1112763959290102e-06, "loss": 0.3601, "step": 1970 }, { "epoch": 12.116564417177914, "grad_norm": 0.45158612728118896, "learning_rate": 1.088935445518981e-06, "loss": 0.3574, "step": 1975 }, { "epoch": 12.14723926380368, "grad_norm": 0.4570388197898865, "learning_rate": 1.0667938778359838e-06, "loss": 0.3584, "step": 1980 }, { "epoch": 12.177914110429448, "grad_norm": 0.4470795691013336, "learning_rate": 1.0448528216382103e-06, "loss": 0.3582, "step": 1985 }, { "epoch": 12.208588957055214, "grad_norm": 0.4757451117038727, "learning_rate": 1.0231133954619449e-06, "loss": 0.3595, "step": 1990 }, { "epoch": 12.239263803680982, "grad_norm": 0.44901788234710693, "learning_rate": 1.0015767075645472e-06, "loss": 0.3573, "step": 1995 }, { "epoch": 12.269938650306749, "grad_norm": 0.457893431186676, "learning_rate": 9.802438558679529e-07, "loss": 0.3602, "step": 2000 } ], "logging_steps": 5, "max_steps": 2445, "num_input_tokens_seen": 0, "num_train_epochs": 15, "save_steps": 400, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.747402775285413e+19, "train_batch_size": 2, "trial_name": null, "trial_params": null }