| [ |
| { |
| "loss": 4.6142, |
| "grad_norm": 33.659332275390625, |
| "learning_rate": 1.8e-05, |
| "epoch": 0.006297229219143577, |
| "step": 10 |
| }, |
| { |
| "loss": 2.6482, |
| "grad_norm": 14.412582397460938, |
| "learning_rate": 3.8e-05, |
| "epoch": 0.012594458438287154, |
| "step": 20 |
| }, |
| { |
| "loss": 2.2011, |
| "grad_norm": 9.777717590332031, |
| "learning_rate": 5.8e-05, |
| "epoch": 0.018891687657430732, |
| "step": 30 |
| }, |
| { |
| "loss": 1.9662, |
| "grad_norm": 17.46149253845215, |
| "learning_rate": 7.800000000000001e-05, |
| "epoch": 0.02518891687657431, |
| "step": 40 |
| }, |
| { |
| "loss": 1.8247, |
| "grad_norm": 9.683545112609863, |
| "learning_rate": 9.8e-05, |
| "epoch": 0.031486146095717885, |
| "step": 50 |
| }, |
| { |
| "loss": 1.8919, |
| "grad_norm": 10.557292938232422, |
| "learning_rate": 0.000118, |
| "epoch": 0.037783375314861464, |
| "step": 60 |
| }, |
| { |
| "loss": 1.9162, |
| "grad_norm": 11.902077674865723, |
| "learning_rate": 0.000138, |
| "epoch": 0.04408060453400504, |
| "step": 70 |
| }, |
| { |
| "eval_loss": 1.7838011980056763, |
| "eval_runtime": 33.8157, |
| "eval_samples_per_second": 15.348, |
| "eval_steps_per_second": 3.844, |
| "epoch": 0.04974811083123426, |
| "step": 79 |
| }, |
| { |
| "loss": 1.8701, |
| "grad_norm": 8.326041221618652, |
| "learning_rate": 0.00015800000000000002, |
| "epoch": 0.05037783375314862, |
| "step": 80 |
| }, |
| { |
| "loss": 1.7494, |
| "grad_norm": 8.273054122924805, |
| "learning_rate": 0.00017800000000000002, |
| "epoch": 0.05667506297229219, |
| "step": 90 |
| }, |
| { |
| "loss": 1.7557, |
| "grad_norm": 10.647675514221191, |
| "learning_rate": 0.00019800000000000002, |
| "epoch": 0.06297229219143577, |
| "step": 100 |
| }, |
| { |
| "loss": 1.7535, |
| "grad_norm": 6.604005813598633, |
| "learning_rate": 0.0001999819475629623, |
| "epoch": 0.06926952141057935, |
| "step": 110 |
| }, |
| { |
| "loss": 1.7317, |
| "grad_norm": 6.132753372192383, |
| "learning_rate": 0.00019991955244474347, |
| "epoch": 0.07556675062972293, |
| "step": 120 |
| }, |
| { |
| "loss": 1.6196, |
| "grad_norm": 5.765186786651611, |
| "learning_rate": 0.0001998126195808803, |
| "epoch": 0.0818639798488665, |
| "step": 130 |
| }, |
| { |
| "loss": 1.5384, |
| "grad_norm": 5.294787883758545, |
| "learning_rate": 0.00019966119663520412, |
| "epoch": 0.08816120906801007, |
| "step": 140 |
| }, |
| { |
| "loss": 1.7253, |
| "grad_norm": 8.26528549194336, |
| "learning_rate": 0.00019946535110237904, |
| "epoch": 0.09445843828715365, |
| "step": 150 |
| }, |
| { |
| "eval_loss": 1.7441585063934326, |
| "eval_runtime": 14.4715, |
| "eval_samples_per_second": 35.864, |
| "eval_steps_per_second": 8.983, |
| "epoch": 0.09949622166246852, |
| "step": 158 |
| }, |
| { |
| "loss": 1.7126, |
| "grad_norm": 5.565060138702393, |
| "learning_rate": 0.00019922517027781746, |
| "epoch": 0.10075566750629723, |
| "step": 160 |
| }, |
| { |
| "loss": 1.8884, |
| "grad_norm": 6.4396867752075195, |
| "learning_rate": 0.000198940761218769, |
| "epoch": 0.1070528967254408, |
| "step": 170 |
| }, |
| { |
| "loss": 1.7091, |
| "grad_norm": 5.561753273010254, |
| "learning_rate": 0.0001986122506966014, |
| "epoch": 0.11335012594458438, |
| "step": 180 |
| }, |
| { |
| "loss": 1.7571, |
| "grad_norm": 4.833555221557617, |
| "learning_rate": 0.000198239785140294, |
| "epoch": 0.11964735516372796, |
| "step": 190 |
| }, |
| { |
| "loss": 1.6005, |
| "grad_norm": 5.930907249450684, |
| "learning_rate": 0.000197823530571169, |
| "epoch": 0.12594458438287154, |
| "step": 200 |
| }, |
| { |
| "loss": 1.7721, |
| "grad_norm": 5.551156520843506, |
| "learning_rate": 0.00019736367252888974, |
| "epoch": 0.13224181360201512, |
| "step": 210 |
| }, |
| { |
| "loss": 1.6479, |
| "grad_norm": 5.802966117858887, |
| "learning_rate": 0.000196860415988759, |
| "epoch": 0.1385390428211587, |
| "step": 220 |
| }, |
| { |
| "loss": 1.6939, |
| "grad_norm": 5.381985664367676, |
| "learning_rate": 0.00019631398527035422, |
| "epoch": 0.14483627204030228, |
| "step": 230 |
| }, |
| { |
| "eval_loss": 1.6404942274093628, |
| "eval_runtime": 14.4847, |
| "eval_samples_per_second": 35.831, |
| "eval_steps_per_second": 8.975, |
| "epoch": 0.14924433249370278, |
| "step": 237 |
| }, |
| { |
| "loss": 1.6613, |
| "grad_norm": 5.851009368896484, |
| "learning_rate": 0.00019572462393754005, |
| "epoch": 0.15113350125944586, |
| "step": 240 |
| }, |
| { |
| "loss": 1.6204, |
| "grad_norm": 5.324190139770508, |
| "learning_rate": 0.00019509259468990323, |
| "epoch": 0.1574307304785894, |
| "step": 250 |
| }, |
| { |
| "loss": 1.5024, |
| "grad_norm": 6.643704891204834, |
| "learning_rate": 0.00019441817924565786, |
| "epoch": 0.163727959697733, |
| "step": 260 |
| }, |
| { |
| "loss": 1.7425, |
| "grad_norm": 5.175152778625488, |
| "learning_rate": 0.00019370167821607353, |
| "epoch": 0.17002518891687657, |
| "step": 270 |
| }, |
| { |
| "loss": 1.6053, |
| "grad_norm": 5.162317276000977, |
| "learning_rate": 0.00019294341097148194, |
| "epoch": 0.17632241813602015, |
| "step": 280 |
| }, |
| { |
| "loss": 1.6262, |
| "grad_norm": 4.8840179443359375, |
| "learning_rate": 0.0001921437154989221, |
| "epoch": 0.18261964735516373, |
| "step": 290 |
| }, |
| { |
| "loss": 1.6046, |
| "grad_norm": 5.020822048187256, |
| "learning_rate": 0.0001913029482514873, |
| "epoch": 0.1889168765743073, |
| "step": 300 |
| }, |
| { |
| "loss": 1.6283, |
| "grad_norm": 4.799527645111084, |
| "learning_rate": 0.00019042148398944116, |
| "epoch": 0.1952141057934509, |
| "step": 310 |
| }, |
| { |
| "eval_loss": 1.6082123517990112, |
| "eval_runtime": 14.6548, |
| "eval_samples_per_second": 35.415, |
| "eval_steps_per_second": 8.871, |
| "epoch": 0.19899244332493704, |
| "step": 316 |
| }, |
| { |
| "loss": 1.6391, |
| "grad_norm": 5.666315078735352, |
| "learning_rate": 0.0001894997156131734, |
| "epoch": 0.20151133501259447, |
| "step": 320 |
| }, |
| { |
| "loss": 1.6637, |
| "grad_norm": 5.880155086517334, |
| "learning_rate": 0.00018853805398807004, |
| "epoch": 0.20780856423173805, |
| "step": 330 |
| }, |
| { |
| "loss": 1.444, |
| "grad_norm": 5.846175193786621, |
| "learning_rate": 0.00018753692776137584, |
| "epoch": 0.2141057934508816, |
| "step": 340 |
| }, |
| { |
| "loss": 1.625, |
| "grad_norm": 5.362205982208252, |
| "learning_rate": 0.00018649678317113084, |
| "epoch": 0.22040302267002518, |
| "step": 350 |
| }, |
| { |
| "loss": 1.6577, |
| "grad_norm": 4.623821258544922, |
| "learning_rate": 0.0001854180838472659, |
| "epoch": 0.22670025188916876, |
| "step": 360 |
| }, |
| { |
| "loss": 1.5298, |
| "grad_norm": 4.931164741516113, |
| "learning_rate": 0.00018430131060494616, |
| "epoch": 0.23299748110831234, |
| "step": 370 |
| }, |
| { |
| "loss": 1.5142, |
| "grad_norm": 5.050358295440674, |
| "learning_rate": 0.00018314696123025454, |
| "epoch": 0.23929471032745592, |
| "step": 380 |
| }, |
| { |
| "loss": 1.5357, |
| "grad_norm": 4.571812629699707, |
| "learning_rate": 0.00018195555025831022, |
| "epoch": 0.2455919395465995, |
| "step": 390 |
| }, |
| { |
| "eval_loss": 1.5576220750808716, |
| "eval_runtime": 14.7082, |
| "eval_samples_per_second": 35.286, |
| "eval_steps_per_second": 8.839, |
| "epoch": 0.24874055415617127, |
| "step": 395 |
| }, |
| { |
| "loss": 1.5179, |
| "grad_norm": 4.708597183227539, |
| "learning_rate": 0.00018072760874392215, |
| "epoch": 0.2518891687657431, |
| "step": 400 |
| }, |
| { |
| "loss": 1.5781, |
| "grad_norm": 4.262819766998291, |
| "learning_rate": 0.00017946368402487845, |
| "epoch": 0.25818639798488663, |
| "step": 410 |
| }, |
| { |
| "loss": 1.4886, |
| "grad_norm": 5.044946193695068, |
| "learning_rate": 0.00017816433947797858, |
| "epoch": 0.26448362720403024, |
| "step": 420 |
| }, |
| { |
| "loss": 1.4781, |
| "grad_norm": 5.743882656097412, |
| "learning_rate": 0.00017683015426791566, |
| "epoch": 0.2707808564231738, |
| "step": 430 |
| }, |
| { |
| "loss": 1.5219, |
| "grad_norm": 5.393696308135986, |
| "learning_rate": 0.00017546172308912213, |
| "epoch": 0.2770780856423174, |
| "step": 440 |
| }, |
| { |
| "loss": 1.5132, |
| "grad_norm": 7.644551753997803, |
| "learning_rate": 0.0001740596559006929, |
| "epoch": 0.28337531486146095, |
| "step": 450 |
| }, |
| { |
| "loss": 1.4883, |
| "grad_norm": 5.462601661682129, |
| "learning_rate": 0.00017262457765450457, |
| "epoch": 0.28967254408060455, |
| "step": 460 |
| }, |
| { |
| "loss": 1.5252, |
| "grad_norm": 4.247793197631836, |
| "learning_rate": 0.000171157128016652, |
| "epoch": 0.2959697732997481, |
| "step": 470 |
| }, |
| { |
| "eval_loss": 1.5793730020523071, |
| "eval_runtime": 14.5182, |
| "eval_samples_per_second": 35.748, |
| "eval_steps_per_second": 8.954, |
| "epoch": 0.29848866498740556, |
| "step": 474 |
| }, |
| { |
| "loss": 1.6033, |
| "grad_norm": 6.310419082641602, |
| "learning_rate": 0.00016965796108232598, |
| "epoch": 0.3022670025188917, |
| "step": 480 |
| }, |
| { |
| "loss": 1.6718, |
| "grad_norm": 5.100507736206055, |
| "learning_rate": 0.00016812774508425933, |
| "epoch": 0.30856423173803527, |
| "step": 490 |
| }, |
| { |
| "loss": 1.5078, |
| "grad_norm": 4.1262946128845215, |
| "learning_rate": 0.00016656716209487174, |
| "epoch": 0.3148614609571788, |
| "step": 500 |
| }, |
| { |
| "loss": 1.4854, |
| "grad_norm": 5.230551719665527, |
| "learning_rate": 0.00016497690772224522, |
| "epoch": 0.3211586901763224, |
| "step": 510 |
| }, |
| { |
| "loss": 1.5091, |
| "grad_norm": 5.111631393432617, |
| "learning_rate": 0.00016335769080006674, |
| "epoch": 0.327455919395466, |
| "step": 520 |
| }, |
| { |
| "loss": 1.5427, |
| "grad_norm": 4.551891803741455, |
| "learning_rate": 0.00016171023307167545, |
| "epoch": 0.3337531486146096, |
| "step": 530 |
| }, |
| { |
| "loss": 1.5839, |
| "grad_norm": 4.708298683166504, |
| "learning_rate": 0.00016003526886835553, |
| "epoch": 0.34005037783375314, |
| "step": 540 |
| }, |
| { |
| "loss": 1.4655, |
| "grad_norm": 4.417643070220947, |
| "learning_rate": 0.00015833354478201844, |
| "epoch": 0.34634760705289674, |
| "step": 550 |
| }, |
| { |
| "eval_loss": 1.5285385847091675, |
| "eval_runtime": 14.6291, |
| "eval_samples_per_second": 35.477, |
| "eval_steps_per_second": 8.886, |
| "epoch": 0.3482367758186398, |
| "step": 553 |
| }, |
| { |
| "loss": 1.5909, |
| "grad_norm": 5.512932300567627, |
| "learning_rate": 0.00015660581933241993, |
| "epoch": 0.3526448362720403, |
| "step": 560 |
| }, |
| { |
| "loss": 1.5667, |
| "grad_norm": 5.218059539794922, |
| "learning_rate": 0.00015485286262906044, |
| "epoch": 0.3589420654911839, |
| "step": 570 |
| }, |
| { |
| "loss": 1.584, |
| "grad_norm": 5.250601291656494, |
| "learning_rate": 0.00015307545602791955, |
| "epoch": 0.36523929471032746, |
| "step": 580 |
| }, |
| { |
| "loss": 1.5065, |
| "grad_norm": 5.601760387420654, |
| "learning_rate": 0.00015127439178317745, |
| "epoch": 0.371536523929471, |
| "step": 590 |
| }, |
| { |
| "loss": 1.4472, |
| "grad_norm": 4.8602986335754395, |
| "learning_rate": 0.00014945047269407876, |
| "epoch": 0.3778337531486146, |
| "step": 600 |
| }, |
| { |
| "loss": 1.5242, |
| "grad_norm": 3.2672348022460938, |
| "learning_rate": 0.0001476045117470958, |
| "epoch": 0.38413098236775817, |
| "step": 610 |
| }, |
| { |
| "loss": 1.4048, |
| "grad_norm": 4.925168037414551, |
| "learning_rate": 0.0001457373317535515, |
| "epoch": 0.3904282115869018, |
| "step": 620 |
| }, |
| { |
| "loss": 1.4479, |
| "grad_norm": 5.590626239776611, |
| "learning_rate": 0.00014384976498286252, |
| "epoch": 0.3967254408060453, |
| "step": 630 |
| }, |
| { |
| "eval_loss": 1.489644169807434, |
| "eval_runtime": 14.4216, |
| "eval_samples_per_second": 35.988, |
| "eval_steps_per_second": 9.014, |
| "epoch": 0.3979848866498741, |
| "step": 632 |
| }, |
| { |
| "loss": 1.4313, |
| "grad_norm": 5.052401065826416, |
| "learning_rate": 0.00014194265279156675, |
| "epoch": 0.40302267002518893, |
| "step": 640 |
| }, |
| { |
| "loss": 1.5194, |
| "grad_norm": 3.9724292755126953, |
| "learning_rate": 0.00014001684524830057, |
| "epoch": 0.4093198992443325, |
| "step": 650 |
| }, |
| { |
| "loss": 1.4166, |
| "grad_norm": 4.177152156829834, |
| "learning_rate": 0.0001380732007548925, |
| "epoch": 0.4156171284634761, |
| "step": 660 |
| }, |
| { |
| "loss": 1.5784, |
| "grad_norm": 4.706490516662598, |
| "learning_rate": 0.00013611258566374257, |
| "epoch": 0.42191435768261965, |
| "step": 670 |
| }, |
| { |
| "loss": 1.3634, |
| "grad_norm": 4.3738017082214355, |
| "learning_rate": 0.00013413587389165784, |
| "epoch": 0.4282115869017632, |
| "step": 680 |
| }, |
| { |
| "loss": 1.5313, |
| "grad_norm": 3.9545352458953857, |
| "learning_rate": 0.00013214394653031616, |
| "epoch": 0.4345088161209068, |
| "step": 690 |
| }, |
| { |
| "loss": 1.3985, |
| "grad_norm": 4.201825141906738, |
| "learning_rate": 0.000130137691453532, |
| "epoch": 0.44080604534005036, |
| "step": 700 |
| }, |
| { |
| "loss": 1.5721, |
| "grad_norm": 5.4546966552734375, |
| "learning_rate": 0.0001281180029214988, |
| "epoch": 0.44710327455919396, |
| "step": 710 |
| }, |
| { |
| "eval_loss": 1.4889687299728394, |
| "eval_runtime": 14.577, |
| "eval_samples_per_second": 35.604, |
| "eval_steps_per_second": 8.918, |
| "epoch": 0.4477329974811083, |
| "step": 711 |
| }, |
| { |
| "loss": 1.4477, |
| "grad_norm": 5.406968116760254, |
| "learning_rate": 0.00012608578118218535, |
| "epoch": 0.4534005037783375, |
| "step": 720 |
| }, |
| { |
| "loss": 1.4616, |
| "grad_norm": 4.538527965545654, |
| "learning_rate": 0.00012404193207006246, |
| "epoch": 0.4596977329974811, |
| "step": 730 |
| }, |
| { |
| "loss": 1.5133, |
| "grad_norm": 4.29402494430542, |
| "learning_rate": 0.00012198736660234009, |
| "epoch": 0.4659949622166247, |
| "step": 740 |
| }, |
| { |
| "loss": 1.4501, |
| "grad_norm": 3.8199307918548584, |
| "learning_rate": 0.0001199230005728942, |
| "epoch": 0.4722921914357683, |
| "step": 750 |
| }, |
| { |
| "loss": 1.5288, |
| "grad_norm": 6.067654132843018, |
| "learning_rate": 0.00011784975414406426, |
| "epoch": 0.47858942065491183, |
| "step": 760 |
| }, |
| { |
| "loss": 1.3803, |
| "grad_norm": 5.480033874511719, |
| "learning_rate": 0.00011576855143650371, |
| "epoch": 0.48488664987405544, |
| "step": 770 |
| }, |
| { |
| "loss": 1.5517, |
| "grad_norm": 4.182514190673828, |
| "learning_rate": 0.00011368032011726635, |
| "epoch": 0.491183879093199, |
| "step": 780 |
| }, |
| { |
| "loss": 1.5284, |
| "grad_norm": 4.433547496795654, |
| "learning_rate": 0.00011158599098631137, |
| "epoch": 0.49748110831234255, |
| "step": 790 |
| }, |
| { |
| "eval_loss": 1.4723758697509766, |
| "eval_runtime": 14.538, |
| "eval_samples_per_second": 35.7, |
| "eval_steps_per_second": 8.942, |
| "epoch": 0.49748110831234255, |
| "step": 790 |
| }, |
| { |
| "loss": 1.5369, |
| "grad_norm": 4.8588433265686035, |
| "learning_rate": 0.00010948649756161246, |
| "epoch": 0.5037783375314862, |
| "step": 800 |
| }, |
| { |
| "loss": 1.4349, |
| "grad_norm": 4.88569450378418, |
| "learning_rate": 0.00010738277566305514, |
| "epoch": 0.5100755667506297, |
| "step": 810 |
| }, |
| { |
| "loss": 1.6126, |
| "grad_norm": 5.098734378814697, |
| "learning_rate": 0.0001052757629953082, |
| "epoch": 0.5163727959697733, |
| "step": 820 |
| }, |
| { |
| "loss": 1.5043, |
| "grad_norm": 4.012162208557129, |
| "learning_rate": 0.00010316639872985472, |
| "epoch": 0.5226700251889169, |
| "step": 830 |
| }, |
| { |
| "loss": 1.4438, |
| "grad_norm": 4.813101768493652, |
| "learning_rate": 0.00010105562308636973, |
| "epoch": 0.5289672544080605, |
| "step": 840 |
| }, |
| { |
| "loss": 1.434, |
| "grad_norm": 3.8592841625213623, |
| "learning_rate": 9.894437691363028e-05, |
| "epoch": 0.535264483627204, |
| "step": 850 |
| }, |
| { |
| "loss": 1.4978, |
| "grad_norm": 5.364985942840576, |
| "learning_rate": 9.683360127014529e-05, |
| "epoch": 0.5415617128463476, |
| "step": 860 |
| }, |
| { |
| "eval_loss": 1.4382336139678955, |
| "eval_runtime": 14.714, |
| "eval_samples_per_second": 35.272, |
| "eval_steps_per_second": 8.835, |
| "epoch": 0.5472292191435768, |
| "step": 869 |
| }, |
| { |
| "loss": 1.4885, |
| "grad_norm": 5.363029479980469, |
| "learning_rate": 9.47242370046918e-05, |
| "epoch": 0.5478589420654912, |
| "step": 870 |
| }, |
| { |
| "loss": 1.5044, |
| "grad_norm": 4.980364799499512, |
| "learning_rate": 9.261722433694485e-05, |
| "epoch": 0.5541561712846348, |
| "step": 880 |
| }, |
| { |
| "loss": 1.353, |
| "grad_norm": 4.4146952629089355, |
| "learning_rate": 9.051350243838756e-05, |
| "epoch": 0.5604534005037783, |
| "step": 890 |
| }, |
| { |
| "loss": 1.3262, |
| "grad_norm": 5.358567237854004, |
| "learning_rate": 8.841400901368864e-05, |
| "epoch": 0.5667506297229219, |
| "step": 900 |
| }, |
| { |
| "loss": 1.5514, |
| "grad_norm": 4.715535640716553, |
| "learning_rate": 8.631967988273366e-05, |
| "epoch": 0.5730478589420654, |
| "step": 910 |
| }, |
| { |
| "loss": 1.4533, |
| "grad_norm": 4.502087116241455, |
| "learning_rate": 8.423144856349631e-05, |
| "epoch": 0.5793450881612091, |
| "step": 920 |
| }, |
| { |
| "loss": 1.4378, |
| "grad_norm": 4.85370397567749, |
| "learning_rate": 8.215024585593577e-05, |
| "epoch": 0.5856423173803527, |
| "step": 930 |
| }, |
| { |
| "loss": 1.4769, |
| "grad_norm": 4.3678297996521, |
| "learning_rate": 8.007699942710581e-05, |
| "epoch": 0.5919395465994962, |
| "step": 940 |
| }, |
| { |
| "eval_loss": 1.4315046072006226, |
| "eval_runtime": 14.4016, |
| "eval_samples_per_second": 36.038, |
| "eval_steps_per_second": 9.027, |
| "epoch": 0.5969773299748111, |
| "step": 948 |
| }, |
| { |
| "loss": 1.3736, |
| "grad_norm": 4.551608085632324, |
| "learning_rate": 7.801263339765994e-05, |
| "epoch": 0.5982367758186398, |
| "step": 950 |
| }, |
| { |
| "loss": 1.4156, |
| "grad_norm": 3.7702224254608154, |
| "learning_rate": 7.595806792993759e-05, |
| "epoch": 0.6045340050377834, |
| "step": 960 |
| }, |
| { |
| "loss": 1.3623, |
| "grad_norm": 4.440454483032227, |
| "learning_rate": 7.391421881781468e-05, |
| "epoch": 0.610831234256927, |
| "step": 970 |
| }, |
| { |
| "loss": 1.38, |
| "grad_norm": 4.850752830505371, |
| "learning_rate": 7.188199707850122e-05, |
| "epoch": 0.6171284634760705, |
| "step": 980 |
| }, |
| { |
| "loss": 1.3101, |
| "grad_norm": 3.9209938049316406, |
| "learning_rate": 6.986230854646804e-05, |
| "epoch": 0.6234256926952141, |
| "step": 990 |
| }, |
| { |
| "loss": 1.3677, |
| "grad_norm": 4.586505889892578, |
| "learning_rate": 6.785605346968386e-05, |
| "epoch": 0.6297229219143576, |
| "step": 1000 |
| }, |
| { |
| "loss": 1.4159, |
| "grad_norm": 4.723811149597168, |
| "learning_rate": 6.586412610834221e-05, |
| "epoch": 0.6360201511335013, |
| "step": 1010 |
| }, |
| { |
| "loss": 1.3878, |
| "grad_norm": 4.9766154289245605, |
| "learning_rate": 6.388741433625746e-05, |
| "epoch": 0.6423173803526449, |
| "step": 1020 |
| }, |
| { |
| "eval_loss": 1.4128155708312988, |
| "eval_runtime": 14.5331, |
| "eval_samples_per_second": 35.712, |
| "eval_steps_per_second": 8.945, |
| "epoch": 0.6467254408060453, |
| "step": 1027 |
| }, |
| { |
| "loss": 1.3711, |
| "grad_norm": 4.173240661621094, |
| "learning_rate": 6.192679924510752e-05, |
| "epoch": 0.6486146095717884, |
| "step": 1030 |
| }, |
| { |
| "loss": 1.408, |
| "grad_norm": 5.662805557250977, |
| "learning_rate": 5.998315475169942e-05, |
| "epoch": 0.654911838790932, |
| "step": 1040 |
| }, |
| { |
| "loss": 1.4101, |
| "grad_norm": 4.8551716804504395, |
| "learning_rate": 5.8057347208433266e-05, |
| "epoch": 0.6612090680100756, |
| "step": 1050 |
| }, |
| { |
| "loss": 1.2795, |
| "grad_norm": 4.329833030700684, |
| "learning_rate": 5.615023501713752e-05, |
| "epoch": 0.6675062972292192, |
| "step": 1060 |
| }, |
| { |
| "loss": 1.4149, |
| "grad_norm": 3.759012460708618, |
| "learning_rate": 5.4262668246448475e-05, |
| "epoch": 0.6738035264483627, |
| "step": 1070 |
| }, |
| { |
| "loss": 1.3728, |
| "grad_norm": 4.901814937591553, |
| "learning_rate": 5.239548825290419e-05, |
| "epoch": 0.6801007556675063, |
| "step": 1080 |
| }, |
| { |
| "loss": 1.4085, |
| "grad_norm": 4.735474109649658, |
| "learning_rate": 5.0549527305921265e-05, |
| "epoch": 0.6863979848866498, |
| "step": 1090 |
| }, |
| { |
| "loss": 1.3691, |
| "grad_norm": 3.6761767864227295, |
| "learning_rate": 4.872560821682256e-05, |
| "epoch": 0.6926952141057935, |
| "step": 1100 |
| }, |
| { |
| "eval_loss": 1.4010512828826904, |
| "eval_runtime": 14.5256, |
| "eval_samples_per_second": 35.73, |
| "eval_steps_per_second": 8.95, |
| "epoch": 0.6964735516372796, |
| "step": 1106 |
| }, |
| { |
| "loss": 1.3057, |
| "grad_norm": 4.493793964385986, |
| "learning_rate": 4.692454397208048e-05, |
| "epoch": 0.698992443324937, |
| "step": 1110 |
| }, |
| { |
| "loss": 1.3721, |
| "grad_norm": 5.266867160797119, |
| "learning_rate": 4.5147137370939595e-05, |
| "epoch": 0.7052896725440806, |
| "step": 1120 |
| }, |
| { |
| "loss": 1.4906, |
| "grad_norm": 4.867866039276123, |
| "learning_rate": 4.339418066758008e-05, |
| "epoch": 0.7115869017632241, |
| "step": 1130 |
| }, |
| { |
| "loss": 1.4071, |
| "grad_norm": 4.608040809631348, |
| "learning_rate": 4.166645521798157e-05, |
| "epoch": 0.7178841309823678, |
| "step": 1140 |
| }, |
| { |
| "loss": 1.3585, |
| "grad_norm": 7.612720012664795, |
| "learning_rate": 3.99647311316445e-05, |
| "epoch": 0.7241813602015114, |
| "step": 1150 |
| }, |
| { |
| "loss": 1.4131, |
| "grad_norm": 5.223732948303223, |
| "learning_rate": 3.828976692832458e-05, |
| "epoch": 0.7304785894206549, |
| "step": 1160 |
| }, |
| { |
| "loss": 1.3566, |
| "grad_norm": 4.113969802856445, |
| "learning_rate": 3.6642309199933275e-05, |
| "epoch": 0.7367758186397985, |
| "step": 1170 |
| }, |
| { |
| "loss": 1.2864, |
| "grad_norm": 3.8852932453155518, |
| "learning_rate": 3.502309227775482e-05, |
| "epoch": 0.743073047858942, |
| "step": 1180 |
| }, |
| { |
| "eval_loss": 1.391667366027832, |
| "eval_runtime": 14.5167, |
| "eval_samples_per_second": 35.752, |
| "eval_steps_per_second": 8.955, |
| "epoch": 0.7462216624685138, |
| "step": 1185 |
| }, |
| { |
| "loss": 1.416, |
| "grad_norm": 4.738650798797607, |
| "learning_rate": 3.343283790512829e-05, |
| "epoch": 0.7493702770780857, |
| "step": 1190 |
| }, |
| { |
| "loss": 1.4496, |
| "grad_norm": 4.808592319488525, |
| "learning_rate": 3.1872254915740686e-05, |
| "epoch": 0.7556675062972292, |
| "step": 1200 |
| }, |
| { |
| "loss": 1.3199, |
| "grad_norm": 5.310007095336914, |
| "learning_rate": 3.0342038917674064e-05, |
| "epoch": 0.7619647355163728, |
| "step": 1210 |
| }, |
| { |
| "loss": 1.4116, |
| "grad_norm": 3.6367766857147217, |
| "learning_rate": 2.8842871983347998e-05, |
| "epoch": 0.7682619647355163, |
| "step": 1220 |
| }, |
| { |
| "loss": 1.4192, |
| "grad_norm": 4.783074378967285, |
| "learning_rate": 2.7375422345495448e-05, |
| "epoch": 0.77455919395466, |
| "step": 1230 |
| }, |
| { |
| "loss": 1.294, |
| "grad_norm": 5.352371692657471, |
| "learning_rate": 2.5940344099307146e-05, |
| "epoch": 0.7808564231738035, |
| "step": 1240 |
| }, |
| { |
| "loss": 1.493, |
| "grad_norm": 4.887784957885742, |
| "learning_rate": 2.45382769108779e-05, |
| "epoch": 0.7871536523929471, |
| "step": 1250 |
| }, |
| { |
| "loss": 1.4063, |
| "grad_norm": 5.015107154846191, |
| "learning_rate": 2.3169845732084338e-05, |
| "epoch": 0.7934508816120907, |
| "step": 1260 |
| }, |
| { |
| "eval_loss": 1.3790984153747559, |
| "eval_runtime": 14.5192, |
| "eval_samples_per_second": 35.746, |
| "eval_steps_per_second": 8.954, |
| "epoch": 0.7959697732997482, |
| "step": 1264 |
| }, |
| { |
| "loss": 1.4125, |
| "grad_norm": 4.3769917488098145, |
| "learning_rate": 2.1835660522021417e-05, |
| "epoch": 0.7997481108312342, |
| "step": 1270 |
| }, |
| { |
| "loss": 1.3623, |
| "grad_norm": 4.965677261352539, |
| "learning_rate": 2.0536315975121544e-05, |
| "epoch": 0.8060453400503779, |
| "step": 1280 |
| }, |
| { |
| "loss": 1.3702, |
| "grad_norm": 5.39815616607666, |
| "learning_rate": 1.927239125607788e-05, |
| "epoch": 0.8123425692695214, |
| "step": 1290 |
| }, |
| { |
| "loss": 1.3878, |
| "grad_norm": 4.974949836730957, |
| "learning_rate": 1.8044449741689794e-05, |
| "epoch": 0.818639798488665, |
| "step": 1300 |
| }, |
| { |
| "loss": 1.4957, |
| "grad_norm": 4.583181381225586, |
| "learning_rate": 1.6853038769745467e-05, |
| "epoch": 0.8249370277078085, |
| "step": 1310 |
| }, |
| { |
| "loss": 1.4018, |
| "grad_norm": 5.503086566925049, |
| "learning_rate": 1.5698689395053835e-05, |
| "epoch": 0.8312342569269522, |
| "step": 1320 |
| }, |
| { |
| "loss": 1.2619, |
| "grad_norm": 4.569085121154785, |
| "learning_rate": 1.4581916152734132e-05, |
| "epoch": 0.8375314861460957, |
| "step": 1330 |
| }, |
| { |
| "loss": 1.4125, |
| "grad_norm": 5.070247173309326, |
| "learning_rate": 1.3503216828869192e-05, |
| "epoch": 0.8438287153652393, |
| "step": 1340 |
| }, |
| { |
| "eval_loss": 1.3746401071548462, |
| "eval_runtime": 14.702, |
| "eval_samples_per_second": 35.301, |
| "eval_steps_per_second": 8.842, |
| "epoch": 0.8457178841309824, |
| "step": 1343 |
| }, |
| { |
| "loss": 1.405, |
| "grad_norm": 4.505115032196045, |
| "learning_rate": 1.2463072238624185e-05, |
| "epoch": 0.8501259445843828, |
| "step": 1350 |
| }, |
| { |
| "loss": 1.2935, |
| "grad_norm": 3.9875564575195312, |
| "learning_rate": 1.146194601192998e-05, |
| "epoch": 0.8564231738035264, |
| "step": 1360 |
| }, |
| { |
| "loss": 1.3752, |
| "grad_norm": 4.175727844238281, |
| "learning_rate": 1.0500284386826597e-05, |
| "epoch": 0.8627204030226701, |
| "step": 1370 |
| }, |
| { |
| "loss": 1.4002, |
| "grad_norm": 3.8710429668426514, |
| "learning_rate": 9.578516010558847e-06, |
| "epoch": 0.8690176322418136, |
| "step": 1380 |
| }, |
| { |
| "loss": 1.2572, |
| "grad_norm": 39.77766418457031, |
| "learning_rate": 8.697051748512708e-06, |
| "epoch": 0.8753148614609572, |
| "step": 1390 |
| }, |
| { |
| "loss": 1.3341, |
| "grad_norm": 5.350057601928711, |
| "learning_rate": 7.856284501077926e-06, |
| "epoch": 0.8816120906801007, |
| "step": 1400 |
| }, |
| { |
| "loss": 1.3181, |
| "grad_norm": 4.475919246673584, |
| "learning_rate": 7.056589028518068e-06, |
| "epoch": 0.8879093198992444, |
| "step": 1410 |
| }, |
| { |
| "loss": 1.3217, |
| "grad_norm": 4.369590759277344, |
| "learning_rate": 6.2983217839264756e-06, |
| "epoch": 0.8942065491183879, |
| "step": 1420 |
| }, |
| { |
| "eval_loss": 1.37122642993927, |
| "eval_runtime": 14.501, |
| "eval_samples_per_second": 35.791, |
| "eval_steps_per_second": 8.965, |
| "epoch": 0.8954659949622166, |
| "step": 1422 |
| }, |
| { |
| "loss": 1.3551, |
| "grad_norm": 4.054989337921143, |
| "learning_rate": 5.581820754342137e-06, |
| "epoch": 0.9005037783375315, |
| "step": 1430 |
| }, |
| { |
| "loss": 1.2635, |
| "grad_norm": 4.094259738922119, |
| "learning_rate": 4.907405310096769e-06, |
| "epoch": 0.906801007556675, |
| "step": 1440 |
| }, |
| { |
| "loss": 1.3872, |
| "grad_norm": 4.884560585021973, |
| "learning_rate": 4.275376062459946e-06, |
| "epoch": 0.9130982367758187, |
| "step": 1450 |
| }, |
| { |
| "loss": 1.2567, |
| "grad_norm": 4.7786641120910645, |
| "learning_rate": 3.6860147296457816e-06, |
| "epoch": 0.9193954659949622, |
| "step": 1460 |
| }, |
| { |
| "loss": 1.4019, |
| "grad_norm": 4.289524078369141, |
| "learning_rate": 3.1395840112410034e-06, |
| "epoch": 0.9256926952141058, |
| "step": 1470 |
| }, |
| { |
| "loss": 1.3127, |
| "grad_norm": 4.1973490715026855, |
| "learning_rate": 2.636327471110289e-06, |
| "epoch": 0.9319899244332494, |
| "step": 1480 |
| }, |
| { |
| "loss": 1.2502, |
| "grad_norm": 4.9555206298828125, |
| "learning_rate": 2.1764694288310184e-06, |
| "epoch": 0.9382871536523929, |
| "step": 1490 |
| }, |
| { |
| "loss": 1.3839, |
| "grad_norm": 5.079888343811035, |
| "learning_rate": 1.7602148597060108e-06, |
| "epoch": 0.9445843828715366, |
| "step": 1500 |
| }, |
| { |
| "eval_loss": 1.3689830303192139, |
| "eval_runtime": 14.5025, |
| "eval_samples_per_second": 35.787, |
| "eval_steps_per_second": 8.964, |
| "epoch": 0.9452141057934509, |
| "step": 1501 |
| }, |
| { |
| "loss": 1.4754, |
| "grad_norm": 4.302427768707275, |
| "learning_rate": 1.3877493033986223e-06, |
| "epoch": 0.9508816120906801, |
| "step": 1510 |
| }, |
| { |
| "loss": 1.3091, |
| "grad_norm": 4.7720866203308105, |
| "learning_rate": 1.0592387812310311e-06, |
| "epoch": 0.9571788413098237, |
| "step": 1520 |
| }, |
| { |
| "loss": 1.2316, |
| "grad_norm": 4.849659442901611, |
| "learning_rate": 7.748297221825573e-07, |
| "epoch": 0.9634760705289672, |
| "step": 1530 |
| }, |
| { |
| "loss": 1.2809, |
| "grad_norm": 4.5142621994018555, |
| "learning_rate": 5.346488976209596e-07, |
| "epoch": 0.9697732997481109, |
| "step": 1540 |
| }, |
| { |
| "loss": 1.2613, |
| "grad_norm": 4.6826019287109375, |
| "learning_rate": 3.3880336479590325e-07, |
| "epoch": 0.9760705289672544, |
| "step": 1550 |
| }, |
| { |
| "loss": 1.3195, |
| "grad_norm": 4.848607540130615, |
| "learning_rate": 1.8738041911969818e-07, |
| "epoch": 0.982367758186398, |
| "step": 1560 |
| }, |
| { |
| "loss": 1.3067, |
| "grad_norm": 4.836756706237793, |
| "learning_rate": 8.044755525652425e-08, |
| "epoch": 0.9886649874055415, |
| "step": 1570 |
| }, |
| { |
| "loss": 1.3373, |
| "grad_norm": 4.4072771072387695, |
| "learning_rate": 1.8052437037707758e-08, |
| "epoch": 0.9949622166246851, |
| "step": 1580 |
| }, |
| { |
| "eval_loss": 1.3691413402557373, |
| "eval_runtime": 14.5693, |
| "eval_samples_per_second": 35.623, |
| "eval_steps_per_second": 8.923, |
| "epoch": 0.9949622166246851, |
| "step": 1580 |
| }, |
| { |
| "train_runtime": 1573.3242, |
| "train_samples_per_second": 16.149, |
| "train_steps_per_second": 1.009, |
| "total_flos": 1.159913454336e+16, |
| "train_loss": 1.5156250816748784, |
| "epoch": 1.0, |
| "step": 1588 |
| } |
| ] |
