|
{ |
|
"best_metric": 2.7728683948516846, |
|
"best_model_checkpoint": "no_dp/200g/pq48/model/checkpoint-15400", |
|
"epoch": 4.928, |
|
"global_step": 15400, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 4.2553191489361704e-05, |
|
"loss": 5.1012, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 8.510638297872341e-05, |
|
"loss": 2.7514, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00012765957446808513, |
|
"loss": 2.6598, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00017021276595744682, |
|
"loss": 2.5369, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0001999614841443061, |
|
"loss": 2.5098, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00019983309795865967, |
|
"loss": 2.5152, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00019970471177301323, |
|
"loss": 2.5338, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0001995763255873668, |
|
"loss": 2.5428, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00019944793940172037, |
|
"loss": 2.4986, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00019931955321607396, |
|
"loss": 2.558, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00019919116703042753, |
|
"loss": 2.5121, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00019906278084478113, |
|
"loss": 2.5065, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0001989343946591347, |
|
"loss": 2.5236, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00019880600847348826, |
|
"loss": 2.5117, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00019867762228784183, |
|
"loss": 2.491, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00019854923610219542, |
|
"loss": 2.5113, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.000198420849916549, |
|
"loss": 2.566, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00019829246373090256, |
|
"loss": 2.5459, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00019816407754525615, |
|
"loss": 2.5136, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00019803569135960972, |
|
"loss": 2.5249, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"eval_loss": 3.242783784866333, |
|
"eval_runtime": 18.1543, |
|
"eval_samples_per_second": 13.495, |
|
"eval_steps_per_second": 3.415, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0001979073051739633, |
|
"loss": 2.5607, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00019777891898831686, |
|
"loss": 2.4883, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00019765053280267045, |
|
"loss": 2.4921, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00019752214661702402, |
|
"loss": 2.5086, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0001973937604313776, |
|
"loss": 2.5164, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00019726537424573118, |
|
"loss": 2.5436, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00019713698806008475, |
|
"loss": 2.509, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00019700860187443832, |
|
"loss": 2.5178, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00019688021568879189, |
|
"loss": 2.495, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00019675182950314548, |
|
"loss": 2.5538, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00019662344331749905, |
|
"loss": 2.5125, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00019649505713185262, |
|
"loss": 2.5139, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0001963666709462062, |
|
"loss": 2.5327, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00019623828476055978, |
|
"loss": 2.5429, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00019610989857491335, |
|
"loss": 2.5356, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0001959815123892669, |
|
"loss": 2.524, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0001958531262036205, |
|
"loss": 2.5331, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019572474001797408, |
|
"loss": 2.5054, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019559635383232767, |
|
"loss": 2.5175, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00019546796764668124, |
|
"loss": 2.545, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 3.2383222579956055, |
|
"eval_runtime": 18.3453, |
|
"eval_samples_per_second": 13.355, |
|
"eval_steps_per_second": 3.38, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0001953395814610348, |
|
"loss": 2.4682, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00019521119527538837, |
|
"loss": 2.5215, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00019508280908974194, |
|
"loss": 2.5322, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00019495442290409554, |
|
"loss": 2.5012, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0001948260367184491, |
|
"loss": 2.5186, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0001946976505328027, |
|
"loss": 2.5382, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00019456926434715627, |
|
"loss": 2.5583, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00019444087816150983, |
|
"loss": 2.5141, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0001943124919758634, |
|
"loss": 2.513, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00019418410579021697, |
|
"loss": 2.5377, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00019405571960457056, |
|
"loss": 2.5084, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00019392733341892413, |
|
"loss": 2.4841, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00019379894723327773, |
|
"loss": 2.5388, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0001936705610476313, |
|
"loss": 2.4809, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00019354217486198486, |
|
"loss": 2.501, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00019341378867633843, |
|
"loss": 2.4665, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.000193285402490692, |
|
"loss": 2.5074, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.0001931570163050456, |
|
"loss": 2.5129, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00019302863011939916, |
|
"loss": 2.5306, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00019290024393375275, |
|
"loss": 2.4846, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"eval_loss": 3.239039897918701, |
|
"eval_runtime": 18.7589, |
|
"eval_samples_per_second": 13.06, |
|
"eval_steps_per_second": 3.305, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019277185774810632, |
|
"loss": 2.5436, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0001926434715624599, |
|
"loss": 2.5501, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019251508537681346, |
|
"loss": 2.5268, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019238669919116702, |
|
"loss": 2.4928, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00019225831300552062, |
|
"loss": 2.5337, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.0001921299268198742, |
|
"loss": 2.5305, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00019200154063422778, |
|
"loss": 2.5259, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00019187315444858135, |
|
"loss": 2.5631, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00019174476826293492, |
|
"loss": 2.4957, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00019161638207728848, |
|
"loss": 2.5006, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00019148799589164205, |
|
"loss": 2.5372, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00019135960970599565, |
|
"loss": 2.5347, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00019123122352034921, |
|
"loss": 2.475, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0001911028373347028, |
|
"loss": 2.5021, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00019097445114905638, |
|
"loss": 2.4774, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00019084606496340995, |
|
"loss": 2.5018, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0001907176787777635, |
|
"loss": 2.5184, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0001905892925921171, |
|
"loss": 2.5351, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00019046090640647068, |
|
"loss": 2.5199, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00019033252022082424, |
|
"loss": 2.5677, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"eval_loss": 3.238361358642578, |
|
"eval_runtime": 19.151, |
|
"eval_samples_per_second": 12.793, |
|
"eval_steps_per_second": 3.237, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00019020413403517784, |
|
"loss": 2.5148, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.0001900757478495314, |
|
"loss": 2.4906, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00018994736166388497, |
|
"loss": 2.507, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00018981897547823854, |
|
"loss": 2.5294, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00018969058929259214, |
|
"loss": 2.5556, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0001895622031069457, |
|
"loss": 2.5672, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00018943381692129927, |
|
"loss": 2.503, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00018930543073565287, |
|
"loss": 2.4767, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00018917704455000643, |
|
"loss": 2.5208, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00018904865836436, |
|
"loss": 2.494, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00018892027217871357, |
|
"loss": 2.5109, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00018879188599306716, |
|
"loss": 2.4998, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00018866349980742073, |
|
"loss": 2.5035, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0001885351136217743, |
|
"loss": 2.5393, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0001884067274361279, |
|
"loss": 2.5166, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00018827834125048146, |
|
"loss": 2.5766, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00018814995506483503, |
|
"loss": 2.5017, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0001880215688791886, |
|
"loss": 2.4852, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0001878931826935422, |
|
"loss": 2.4849, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00018776479650789576, |
|
"loss": 2.5115, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"eval_loss": 3.2380220890045166, |
|
"eval_runtime": 19.5958, |
|
"eval_samples_per_second": 12.503, |
|
"eval_steps_per_second": 3.164, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00018763641032224935, |
|
"loss": 2.498, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00018750802413660292, |
|
"loss": 2.504, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0001873796379509565, |
|
"loss": 2.498, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00018725125176531006, |
|
"loss": 2.497, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00018712286557966362, |
|
"loss": 2.4932, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00018699447939401722, |
|
"loss": 2.4998, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0001868660932083708, |
|
"loss": 2.5412, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00018673770702272438, |
|
"loss": 2.5564, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00018660932083707795, |
|
"loss": 2.4806, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00018648093465143152, |
|
"loss": 2.5238, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00018635254846578508, |
|
"loss": 2.5122, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00018622416228013865, |
|
"loss": 2.5157, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00018609577609449225, |
|
"loss": 2.5518, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00018596738990884581, |
|
"loss": 2.5311, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.0001858390037231994, |
|
"loss": 2.5248, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.00018571061753755298, |
|
"loss": 2.5314, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.00018558223135190654, |
|
"loss": 2.4989, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.0001854538451662601, |
|
"loss": 2.5067, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.00018532545898061368, |
|
"loss": 2.5281, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.00018519707279496727, |
|
"loss": 2.5048, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"eval_loss": 3.2373909950256348, |
|
"eval_runtime": 19.3406, |
|
"eval_samples_per_second": 12.668, |
|
"eval_steps_per_second": 3.206, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.00018506868660932084, |
|
"loss": 2.5105, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.00018494030042367444, |
|
"loss": 2.5044, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.000184811914238028, |
|
"loss": 2.5047, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.00018468352805238157, |
|
"loss": 2.5247, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.00018455514186673514, |
|
"loss": 2.5052, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0001844267556810887, |
|
"loss": 2.5128, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.0001842983694954423, |
|
"loss": 2.5106, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.00018416998330979587, |
|
"loss": 2.5227, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.00018404159712414946, |
|
"loss": 2.5085, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.00018391321093850303, |
|
"loss": 2.5624, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.0001837848247528566, |
|
"loss": 2.4828, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.00018365643856721017, |
|
"loss": 2.5308, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.00018352805238156374, |
|
"loss": 2.4968, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.00018339966619591733, |
|
"loss": 2.5342, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.0001832712800102709, |
|
"loss": 2.5219, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0001831428938246245, |
|
"loss": 2.5061, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.00018301450763897806, |
|
"loss": 2.5174, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.00018288612145333163, |
|
"loss": 2.5119, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0001827577352676852, |
|
"loss": 2.5252, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.0001826293490820388, |
|
"loss": 2.5221, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"eval_loss": 3.2366342544555664, |
|
"eval_runtime": 19.7443, |
|
"eval_samples_per_second": 12.409, |
|
"eval_steps_per_second": 3.14, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.00018250096289639236, |
|
"loss": 2.5447, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.00018237257671074593, |
|
"loss": 2.5341, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.00018224419052509952, |
|
"loss": 2.5363, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.0001821158043394531, |
|
"loss": 2.4924, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.00018198741815380666, |
|
"loss": 2.5046, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.00018185903196816022, |
|
"loss": 2.5324, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.00018173064578251382, |
|
"loss": 2.531, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.00018160225959686739, |
|
"loss": 2.5211, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.00018147387341122095, |
|
"loss": 2.4991, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.00018134548722557455, |
|
"loss": 2.5311, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.00018121710103992812, |
|
"loss": 2.4974, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.00018108871485428168, |
|
"loss": 2.5151, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.00018096032866863525, |
|
"loss": 2.5389, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.00018083194248298885, |
|
"loss": 2.5229, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00018070355629734241, |
|
"loss": 2.521, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00018057517011169598, |
|
"loss": 2.5176, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00018044678392604958, |
|
"loss": 2.5102, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.00018031839774040314, |
|
"loss": 2.548, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.0001801900115547567, |
|
"loss": 2.4808, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.00018006162536911028, |
|
"loss": 2.5139, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"eval_loss": 3.2361488342285156, |
|
"eval_runtime": 19.7846, |
|
"eval_samples_per_second": 12.383, |
|
"eval_steps_per_second": 3.134, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.00017993323918346387, |
|
"loss": 2.4948, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.00017980485299781744, |
|
"loss": 2.5186, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.00017967646681217104, |
|
"loss": 2.5022, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.0001795480806265246, |
|
"loss": 2.5247, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.00017941969444087817, |
|
"loss": 2.5225, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.00017929130825523174, |
|
"loss": 2.5411, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0001791629220695853, |
|
"loss": 2.5414, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.0001790345358839389, |
|
"loss": 2.5605, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.00017890614969829247, |
|
"loss": 2.4825, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.00017877776351264606, |
|
"loss": 2.5361, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.00017864937732699963, |
|
"loss": 2.5516, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.0001785209911413532, |
|
"loss": 2.5325, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.00017839260495570677, |
|
"loss": 2.5388, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.00017826421877006034, |
|
"loss": 2.5086, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.00017813583258441393, |
|
"loss": 2.4966, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.0001780074463987675, |
|
"loss": 2.5409, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.0001778790602131211, |
|
"loss": 2.5362, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.00017775067402747466, |
|
"loss": 2.5335, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.00017762228784182823, |
|
"loss": 2.4791, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.0001774939016561818, |
|
"loss": 2.5195, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"eval_loss": 3.236736297607422, |
|
"eval_runtime": 21.0844, |
|
"eval_samples_per_second": 11.62, |
|
"eval_steps_per_second": 2.941, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.00017736551547053536, |
|
"loss": 2.5242, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.00017723712928488896, |
|
"loss": 2.4817, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.00017710874309924253, |
|
"loss": 2.4905, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.00017698035691359612, |
|
"loss": 2.547, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.0001768519707279497, |
|
"loss": 2.5064, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.00017672358454230326, |
|
"loss": 2.4788, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.00017659519835665682, |
|
"loss": 2.5302, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.0001764668121710104, |
|
"loss": 2.5457, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.00017633842598536399, |
|
"loss": 2.5214, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.00017621003979971755, |
|
"loss": 2.542, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.00017608165361407115, |
|
"loss": 2.5656, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.00017595326742842472, |
|
"loss": 2.4981, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.00017582488124277828, |
|
"loss": 2.4853, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.00017569649505713185, |
|
"loss": 2.5358, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.00017556810887148542, |
|
"loss": 2.4726, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.000175439722685839, |
|
"loss": 2.5438, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.00017531133650019258, |
|
"loss": 2.4908, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.00017518295031454618, |
|
"loss": 2.4917, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.00017505456412889974, |
|
"loss": 2.5277, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.0001749261779432533, |
|
"loss": 2.4852, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"eval_loss": 3.237051010131836, |
|
"eval_runtime": 20.1654, |
|
"eval_samples_per_second": 12.15, |
|
"eval_steps_per_second": 3.075, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.00017479779175760688, |
|
"loss": 2.4729, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.00017466940557196047, |
|
"loss": 2.5233, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.00017454101938631404, |
|
"loss": 2.5075, |
|
"step": 2030 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.0001744126332006676, |
|
"loss": 2.4588, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.0001742842470150212, |
|
"loss": 2.4816, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.00017415586082937477, |
|
"loss": 2.5267, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.00017402747464372834, |
|
"loss": 2.5311, |
|
"step": 2070 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0001738990884580819, |
|
"loss": 2.5033, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0001737707022724355, |
|
"loss": 2.5374, |
|
"step": 2090 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.00017364231608678907, |
|
"loss": 2.5268, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.00017351392990114264, |
|
"loss": 2.4735, |
|
"step": 2110 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.00017338554371549623, |
|
"loss": 2.5047, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.0001732571575298498, |
|
"loss": 2.4888, |
|
"step": 2130 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.00017312877134420337, |
|
"loss": 2.5098, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.00017300038515855693, |
|
"loss": 2.5174, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.00017287199897291053, |
|
"loss": 2.46, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.0001727436127872641, |
|
"loss": 2.5271, |
|
"step": 2170 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.00017261522660161766, |
|
"loss": 2.5379, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.00017248684041597126, |
|
"loss": 2.5238, |
|
"step": 2190 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.00017235845423032483, |
|
"loss": 2.4717, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"eval_loss": 3.2369184494018555, |
|
"eval_runtime": 20.2418, |
|
"eval_samples_per_second": 12.104, |
|
"eval_steps_per_second": 3.063, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.0001722300680446784, |
|
"loss": 2.51, |
|
"step": 2210 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.00017210168185903196, |
|
"loss": 2.4942, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.00017197329567338556, |
|
"loss": 2.5224, |
|
"step": 2230 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.00017184490948773912, |
|
"loss": 2.4574, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.00017171652330209272, |
|
"loss": 2.4818, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.0001715881371164463, |
|
"loss": 2.5107, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.00017145975093079985, |
|
"loss": 2.4903, |
|
"step": 2270 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.00017133136474515342, |
|
"loss": 2.4643, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.000171202978559507, |
|
"loss": 2.487, |
|
"step": 2290 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.00017107459237386059, |
|
"loss": 2.441, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.00017094620618821415, |
|
"loss": 2.4879, |
|
"step": 2310 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.00017081782000256775, |
|
"loss": 2.4722, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.00017068943381692132, |
|
"loss": 2.4536, |
|
"step": 2330 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.00017056104763127488, |
|
"loss": 2.4906, |
|
"step": 2340 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.00017043266144562845, |
|
"loss": 2.4774, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.00017030427525998202, |
|
"loss": 2.4841, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.0001701758890743356, |
|
"loss": 2.4553, |
|
"step": 2370 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.00017004750288868918, |
|
"loss": 2.4753, |
|
"step": 2380 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.00016991911670304278, |
|
"loss": 2.4639, |
|
"step": 2390 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.00016979073051739634, |
|
"loss": 2.478, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"eval_loss": 3.230825662612915, |
|
"eval_runtime": 20.2385, |
|
"eval_samples_per_second": 12.106, |
|
"eval_steps_per_second": 3.063, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.0001696623443317499, |
|
"loss": 2.4865, |
|
"step": 2410 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.00016953395814610348, |
|
"loss": 2.4674, |
|
"step": 2420 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 0.00016940557196045705, |
|
"loss": 2.4918, |
|
"step": 2430 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 0.00016927718577481064, |
|
"loss": 2.4475, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 0.0001691487995891642, |
|
"loss": 2.4412, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.0001690204134035178, |
|
"loss": 2.4191, |
|
"step": 2460 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.00016889202721787137, |
|
"loss": 2.4417, |
|
"step": 2470 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.00016876364103222494, |
|
"loss": 2.4551, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.0001686352548465785, |
|
"loss": 2.4121, |
|
"step": 2490 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.00016850686866093207, |
|
"loss": 2.404, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.00016837848247528567, |
|
"loss": 2.4255, |
|
"step": 2510 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.00016825009628963924, |
|
"loss": 2.4331, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.00016812171010399283, |
|
"loss": 2.3895, |
|
"step": 2530 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.0001679933239183464, |
|
"loss": 2.4009, |
|
"step": 2540 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.00016786493773269997, |
|
"loss": 2.3949, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.00016773655154705353, |
|
"loss": 2.365, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.0001676081653614071, |
|
"loss": 2.3417, |
|
"step": 2570 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.0001674797791757607, |
|
"loss": 2.337, |
|
"step": 2580 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.00016735139299011426, |
|
"loss": 2.3209, |
|
"step": 2590 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.00016722300680446786, |
|
"loss": 2.2669, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"eval_loss": 3.255279302597046, |
|
"eval_runtime": 20.5641, |
|
"eval_samples_per_second": 11.914, |
|
"eval_steps_per_second": 3.015, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.00016709462061882143, |
|
"loss": 2.3116, |
|
"step": 2610 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.000166966234433175, |
|
"loss": 2.2675, |
|
"step": 2620 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.00016683784824752856, |
|
"loss": 2.2535, |
|
"step": 2630 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.00016670946206188216, |
|
"loss": 2.2727, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.00016658107587623572, |
|
"loss": 2.2375, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.0001664526896905893, |
|
"loss": 2.219, |
|
"step": 2660 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.0001663243035049429, |
|
"loss": 2.2154, |
|
"step": 2670 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.00016619591731929645, |
|
"loss": 2.1943, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.00016606753113365002, |
|
"loss": 2.1903, |
|
"step": 2690 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.0001659391449480036, |
|
"loss": 2.1549, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.00016581075876235718, |
|
"loss": 2.1586, |
|
"step": 2710 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.00016568237257671075, |
|
"loss": 2.1177, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.00016555398639106432, |
|
"loss": 2.1021, |
|
"step": 2730 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.00016542560020541791, |
|
"loss": 2.1095, |
|
"step": 2740 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.00016529721401977148, |
|
"loss": 2.0926, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.00016516882783412505, |
|
"loss": 2.113, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.00016504044164847862, |
|
"loss": 2.068, |
|
"step": 2770 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.0001649120554628322, |
|
"loss": 2.0883, |
|
"step": 2780 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.00016478366927718578, |
|
"loss": 2.0081, |
|
"step": 2790 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.00016465528309153935, |
|
"loss": 2.032, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"eval_loss": 3.217292547225952, |
|
"eval_runtime": 21.0218, |
|
"eval_samples_per_second": 11.655, |
|
"eval_steps_per_second": 2.949, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.00016452689690589294, |
|
"loss": 2.0047, |
|
"step": 2810 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.0001643985107202465, |
|
"loss": 1.9981, |
|
"step": 2820 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.00016427012453460008, |
|
"loss": 2.0106, |
|
"step": 2830 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.00016414173834895365, |
|
"loss": 1.9899, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.00016401335216330724, |
|
"loss": 1.9797, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.0001638849659776608, |
|
"loss": 1.9515, |
|
"step": 2860 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.0001637565797920144, |
|
"loss": 1.9447, |
|
"step": 2870 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.00016362819360636797, |
|
"loss": 1.9104, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.00016349980742072154, |
|
"loss": 1.9492, |
|
"step": 2890 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.0001633714212350751, |
|
"loss": 1.8934, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.00016324303504942867, |
|
"loss": 1.9037, |
|
"step": 2910 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.00016311464886378227, |
|
"loss": 1.8648, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.00016298626267813584, |
|
"loss": 1.8924, |
|
"step": 2930 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.00016285787649248943, |
|
"loss": 1.8973, |
|
"step": 2940 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.000162729490306843, |
|
"loss": 1.8486, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.00016260110412119657, |
|
"loss": 1.8513, |
|
"step": 2960 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.00016247271793555013, |
|
"loss": 1.7895, |
|
"step": 2970 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.0001623443317499037, |
|
"loss": 1.8191, |
|
"step": 2980 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.0001622159455642573, |
|
"loss": 1.8043, |
|
"step": 2990 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.00016208755937861086, |
|
"loss": 1.7903, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"eval_loss": 3.213151693344116, |
|
"eval_runtime": 22.55, |
|
"eval_samples_per_second": 10.865, |
|
"eval_steps_per_second": 2.749, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.00016195917319296446, |
|
"loss": 1.7643, |
|
"step": 3010 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 0.00016183078700731803, |
|
"loss": 1.7993, |
|
"step": 3020 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 0.0001617024008216716, |
|
"loss": 1.7724, |
|
"step": 3030 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 0.00016157401463602516, |
|
"loss": 1.7695, |
|
"step": 3040 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.00016144562845037873, |
|
"loss": 1.7523, |
|
"step": 3050 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.00016131724226473232, |
|
"loss": 1.7377, |
|
"step": 3060 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.0001611888560790859, |
|
"loss": 1.7342, |
|
"step": 3070 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.00016106046989343949, |
|
"loss": 1.7138, |
|
"step": 3080 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.00016093208370779305, |
|
"loss": 1.7086, |
|
"step": 3090 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.00016080369752214662, |
|
"loss": 1.6836, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0001606753113365002, |
|
"loss": 1.6674, |
|
"step": 3110 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.00016054692515085376, |
|
"loss": 1.6596, |
|
"step": 3120 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.00016041853896520735, |
|
"loss": 1.696, |
|
"step": 3130 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.00016029015277956092, |
|
"loss": 1.6819, |
|
"step": 3140 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.00016016176659391451, |
|
"loss": 1.6334, |
|
"step": 3150 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.00016003338040826808, |
|
"loss": 1.6732, |
|
"step": 3160 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.00015990499422262165, |
|
"loss": 1.6274, |
|
"step": 3170 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 0.00015977660803697522, |
|
"loss": 1.6208, |
|
"step": 3180 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 0.00015964822185132878, |
|
"loss": 1.6326, |
|
"step": 3190 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 0.00015951983566568238, |
|
"loss": 1.6452, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"eval_loss": 3.215333938598633, |
|
"eval_runtime": 22.1374, |
|
"eval_samples_per_second": 11.067, |
|
"eval_steps_per_second": 2.801, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.00015939144948003595, |
|
"loss": 1.5803, |
|
"step": 3210 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.00015926306329438954, |
|
"loss": 1.5709, |
|
"step": 3220 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.0001591346771087431, |
|
"loss": 1.5314, |
|
"step": 3230 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.00015900629092309668, |
|
"loss": 1.575, |
|
"step": 3240 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.00015887790473745024, |
|
"loss": 1.5771, |
|
"step": 3250 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.00015874951855180384, |
|
"loss": 1.5262, |
|
"step": 3260 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 0.0001586211323661574, |
|
"loss": 1.5487, |
|
"step": 3270 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 0.00015849274618051097, |
|
"loss": 1.6042, |
|
"step": 3280 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 0.00015836435999486457, |
|
"loss": 1.5461, |
|
"step": 3290 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.00015823597380921814, |
|
"loss": 1.5276, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.0001581075876235717, |
|
"loss": 1.5156, |
|
"step": 3310 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.00015797920143792527, |
|
"loss": 1.5216, |
|
"step": 3320 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.00015785081525227887, |
|
"loss": 1.5222, |
|
"step": 3330 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.00015772242906663244, |
|
"loss": 1.5387, |
|
"step": 3340 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.000157594042880986, |
|
"loss": 1.5132, |
|
"step": 3350 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.0001574656566953396, |
|
"loss": 1.5071, |
|
"step": 3360 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.00015733727050969317, |
|
"loss": 1.511, |
|
"step": 3370 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.00015720888432404673, |
|
"loss": 1.4431, |
|
"step": 3380 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.0001570804981384003, |
|
"loss": 1.5396, |
|
"step": 3390 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.0001569521119527539, |
|
"loss": 1.4582, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"eval_loss": 3.210672378540039, |
|
"eval_runtime": 21.4378, |
|
"eval_samples_per_second": 11.428, |
|
"eval_steps_per_second": 2.892, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.00015682372576710746, |
|
"loss": 1.4895, |
|
"step": 3410 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.00015669533958146103, |
|
"loss": 1.5125, |
|
"step": 3420 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 0.00015656695339581463, |
|
"loss": 1.4513, |
|
"step": 3430 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 0.0001564385672101682, |
|
"loss": 1.4618, |
|
"step": 3440 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 0.00015631018102452176, |
|
"loss": 1.4753, |
|
"step": 3450 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.00015618179483887533, |
|
"loss": 1.4461, |
|
"step": 3460 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.00015605340865322892, |
|
"loss": 1.4776, |
|
"step": 3470 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.0001559250224675825, |
|
"loss": 1.4803, |
|
"step": 3480 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.00015579663628193609, |
|
"loss": 1.4715, |
|
"step": 3490 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.00015566825009628965, |
|
"loss": 1.4895, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.00015553986391064322, |
|
"loss": 1.4508, |
|
"step": 3510 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.0001554114777249968, |
|
"loss": 1.4798, |
|
"step": 3520 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.00015528309153935036, |
|
"loss": 1.464, |
|
"step": 3530 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.00015515470535370395, |
|
"loss": 1.4962, |
|
"step": 3540 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 0.00015502631916805752, |
|
"loss": 1.4928, |
|
"step": 3550 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 0.0001548979329824111, |
|
"loss": 1.4514, |
|
"step": 3560 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 0.00015476954679676468, |
|
"loss": 1.4411, |
|
"step": 3570 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.00015464116061111825, |
|
"loss": 1.4615, |
|
"step": 3580 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.00015451277442547182, |
|
"loss": 1.4316, |
|
"step": 3590 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.00015438438823982538, |
|
"loss": 1.4307, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"eval_loss": 3.2117092609405518, |
|
"eval_runtime": 21.4948, |
|
"eval_samples_per_second": 11.398, |
|
"eval_steps_per_second": 2.884, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.00015425600205417898, |
|
"loss": 1.4404, |
|
"step": 3610 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.00015412761586853255, |
|
"loss": 1.4268, |
|
"step": 3620 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.00015399922968288614, |
|
"loss": 1.532, |
|
"step": 3630 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.0001538708434972397, |
|
"loss": 1.4648, |
|
"step": 3640 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.0001537424573115933, |
|
"loss": 1.4205, |
|
"step": 3650 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.00015361407112594684, |
|
"loss": 1.4521, |
|
"step": 3660 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.0001534856849403004, |
|
"loss": 1.4168, |
|
"step": 3670 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.000153357298754654, |
|
"loss": 1.4106, |
|
"step": 3680 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.00015322891256900757, |
|
"loss": 1.3974, |
|
"step": 3690 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.00015310052638336117, |
|
"loss": 1.4781, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 0.00015297214019771474, |
|
"loss": 1.4205, |
|
"step": 3710 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 0.00015284375401206833, |
|
"loss": 1.4014, |
|
"step": 3720 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 0.00015271536782642187, |
|
"loss": 1.4117, |
|
"step": 3730 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.00015258698164077544, |
|
"loss": 1.451, |
|
"step": 3740 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.00015245859545512903, |
|
"loss": 1.4373, |
|
"step": 3750 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0001523302092694826, |
|
"loss": 1.4163, |
|
"step": 3760 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.0001522018230838362, |
|
"loss": 1.4008, |
|
"step": 3770 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.00015207343689818976, |
|
"loss": 1.429, |
|
"step": 3780 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.00015194505071254336, |
|
"loss": 1.3728, |
|
"step": 3790 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 0.0001518166645268969, |
|
"loss": 1.4415, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"eval_loss": 3.2094931602478027, |
|
"eval_runtime": 21.4153, |
|
"eval_samples_per_second": 11.44, |
|
"eval_steps_per_second": 2.895, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 0.00015168827834125047, |
|
"loss": 1.3961, |
|
"step": 3810 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 0.00015155989215560406, |
|
"loss": 1.436, |
|
"step": 3820 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.00015143150596995763, |
|
"loss": 1.3948, |
|
"step": 3830 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.00015130311978431122, |
|
"loss": 1.4421, |
|
"step": 3840 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.0001511747335986648, |
|
"loss": 1.4253, |
|
"step": 3850 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.0001510463474130184, |
|
"loss": 1.3843, |
|
"step": 3860 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.00015091796122737193, |
|
"loss": 1.4081, |
|
"step": 3870 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.00015078957504172552, |
|
"loss": 1.42, |
|
"step": 3880 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.0001506611888560791, |
|
"loss": 1.4154, |
|
"step": 3890 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.00015053280267043266, |
|
"loss": 1.3841, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.00015040441648478625, |
|
"loss": 1.4444, |
|
"step": 3910 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.00015027603029913982, |
|
"loss": 1.4293, |
|
"step": 3920 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.00015014764411349342, |
|
"loss": 1.3899, |
|
"step": 3930 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.00015001925792784696, |
|
"loss": 1.3872, |
|
"step": 3940 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.00014989087174220055, |
|
"loss": 1.3453, |
|
"step": 3950 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.00014976248555655412, |
|
"loss": 1.4377, |
|
"step": 3960 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.00014963409937090769, |
|
"loss": 1.4414, |
|
"step": 3970 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.00014950571318526128, |
|
"loss": 1.4276, |
|
"step": 3980 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.00014937732699961485, |
|
"loss": 1.3869, |
|
"step": 3990 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.00014924894081396844, |
|
"loss": 1.3769, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"eval_loss": 3.210235118865967, |
|
"eval_runtime": 22.4765, |
|
"eval_samples_per_second": 10.9, |
|
"eval_steps_per_second": 2.758, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.00014912055462832198, |
|
"loss": 1.3984, |
|
"step": 4010 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.00014899216844267558, |
|
"loss": 1.3901, |
|
"step": 4020 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.00014886378225702915, |
|
"loss": 1.3554, |
|
"step": 4030 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.00014873539607138271, |
|
"loss": 1.3686, |
|
"step": 4040 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.0001486070098857363, |
|
"loss": 1.4238, |
|
"step": 4050 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.00014847862370008988, |
|
"loss": 1.3989, |
|
"step": 4060 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.00014835023751444347, |
|
"loss": 1.3669, |
|
"step": 4070 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 0.000148221851328797, |
|
"loss": 1.3657, |
|
"step": 4080 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 0.0001480934651431506, |
|
"loss": 1.4461, |
|
"step": 4090 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 0.00014796507895750417, |
|
"loss": 1.4083, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.00014783669277185777, |
|
"loss": 1.4099, |
|
"step": 4110 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.00014770830658621134, |
|
"loss": 1.3649, |
|
"step": 4120 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.0001475799204005649, |
|
"loss": 1.3779, |
|
"step": 4130 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.0001474515342149185, |
|
"loss": 1.3748, |
|
"step": 4140 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 0.00014732314802927204, |
|
"loss": 1.3675, |
|
"step": 4150 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 0.00014719476184362563, |
|
"loss": 1.3694, |
|
"step": 4160 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 0.0001470663756579792, |
|
"loss": 1.3872, |
|
"step": 4170 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 0.0001469379894723328, |
|
"loss": 1.3932, |
|
"step": 4180 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 0.00014680960328668636, |
|
"loss": 1.3731, |
|
"step": 4190 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 0.00014668121710103993, |
|
"loss": 1.3818, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"eval_loss": 3.2028753757476807, |
|
"eval_runtime": 23.6251, |
|
"eval_samples_per_second": 10.37, |
|
"eval_steps_per_second": 2.624, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 0.0001465528309153935, |
|
"loss": 1.4166, |
|
"step": 4210 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 0.00014642444472974707, |
|
"loss": 1.399, |
|
"step": 4220 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 0.00014629605854410066, |
|
"loss": 1.3926, |
|
"step": 4230 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.00014616767235845423, |
|
"loss": 1.38, |
|
"step": 4240 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.00014603928617280782, |
|
"loss": 1.369, |
|
"step": 4250 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.0001459108999871614, |
|
"loss": 1.399, |
|
"step": 4260 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 0.000145782513801515, |
|
"loss": 1.3719, |
|
"step": 4270 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 0.00014565412761586853, |
|
"loss": 1.4045, |
|
"step": 4280 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 0.0001455257414302221, |
|
"loss": 1.3649, |
|
"step": 4290 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 0.0001453973552445757, |
|
"loss": 1.3546, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 0.00014526896905892926, |
|
"loss": 1.3254, |
|
"step": 4310 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 0.00014514058287328285, |
|
"loss": 1.386, |
|
"step": 4320 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 0.00014501219668763642, |
|
"loss": 1.4197, |
|
"step": 4330 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 0.00014488381050199001, |
|
"loss": 1.3766, |
|
"step": 4340 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 0.00014475542431634356, |
|
"loss": 1.4138, |
|
"step": 4350 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 0.00014462703813069712, |
|
"loss": 1.3573, |
|
"step": 4360 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 0.00014449865194505072, |
|
"loss": 1.408, |
|
"step": 4370 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 0.00014437026575940429, |
|
"loss": 1.3904, |
|
"step": 4380 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 0.00014424187957375788, |
|
"loss": 1.3784, |
|
"step": 4390 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 0.00014411349338811145, |
|
"loss": 1.3305, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"eval_loss": 3.20974063873291, |
|
"eval_runtime": 21.2964, |
|
"eval_samples_per_second": 11.504, |
|
"eval_steps_per_second": 2.911, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 0.00014398510720246504, |
|
"loss": 1.3753, |
|
"step": 4410 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 0.00014385672101681858, |
|
"loss": 1.3904, |
|
"step": 4420 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.00014372833483117215, |
|
"loss": 1.3385, |
|
"step": 4430 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.00014359994864552575, |
|
"loss": 1.4045, |
|
"step": 4440 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.0001434715624598793, |
|
"loss": 1.3598, |
|
"step": 4450 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 0.0001433431762742329, |
|
"loss": 1.4395, |
|
"step": 4460 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 0.00014321479008858648, |
|
"loss": 1.3675, |
|
"step": 4470 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 0.00014308640390294007, |
|
"loss": 1.3726, |
|
"step": 4480 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.0001429580177172936, |
|
"loss": 1.3672, |
|
"step": 4490 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.0001428296315316472, |
|
"loss": 1.369, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.00014270124534600077, |
|
"loss": 1.3693, |
|
"step": 4510 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 0.00014257285916035434, |
|
"loss": 1.3451, |
|
"step": 4520 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 0.00014244447297470794, |
|
"loss": 1.3428, |
|
"step": 4530 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 0.0001423160867890615, |
|
"loss": 1.3624, |
|
"step": 4540 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 0.0001421877006034151, |
|
"loss": 1.3698, |
|
"step": 4550 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 0.00014205931441776864, |
|
"loss": 1.3757, |
|
"step": 4560 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 0.00014193092823212223, |
|
"loss": 1.4012, |
|
"step": 4570 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.0001418025420464758, |
|
"loss": 1.3687, |
|
"step": 4580 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.00014167415586082937, |
|
"loss": 1.3346, |
|
"step": 4590 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.00014154576967518296, |
|
"loss": 1.3435, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"eval_loss": 3.2012200355529785, |
|
"eval_runtime": 21.2116, |
|
"eval_samples_per_second": 11.55, |
|
"eval_steps_per_second": 2.923, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 0.00014141738348953653, |
|
"loss": 1.3611, |
|
"step": 4610 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 0.00014128899730389013, |
|
"loss": 1.3314, |
|
"step": 4620 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 0.00014116061111824367, |
|
"loss": 1.3513, |
|
"step": 4630 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 0.00014103222493259726, |
|
"loss": 1.3328, |
|
"step": 4640 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 0.00014090383874695083, |
|
"loss": 1.3097, |
|
"step": 4650 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 0.0001407754525613044, |
|
"loss": 1.3986, |
|
"step": 4660 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 0.000140647066375658, |
|
"loss": 1.3753, |
|
"step": 4670 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 0.00014051868019001156, |
|
"loss": 1.3896, |
|
"step": 4680 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 0.00014039029400436515, |
|
"loss": 1.4122, |
|
"step": 4690 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 0.0001402619078187187, |
|
"loss": 1.3947, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 0.0001401335216330723, |
|
"loss": 1.3524, |
|
"step": 4710 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 0.00014000513544742586, |
|
"loss": 1.377, |
|
"step": 4720 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 0.00013987674926177945, |
|
"loss": 1.3707, |
|
"step": 4730 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 0.00013974836307613302, |
|
"loss": 1.3984, |
|
"step": 4740 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 0.0001396199768904866, |
|
"loss": 1.3621, |
|
"step": 4750 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 0.00013949159070484018, |
|
"loss": 1.3331, |
|
"step": 4760 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 0.00013936320451919372, |
|
"loss": 1.3458, |
|
"step": 4770 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 0.00013923481833354732, |
|
"loss": 1.3915, |
|
"step": 4780 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 0.00013910643214790088, |
|
"loss": 1.3844, |
|
"step": 4790 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 0.00013897804596225448, |
|
"loss": 1.3452, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"eval_loss": 3.208151340484619, |
|
"eval_runtime": 21.4265, |
|
"eval_samples_per_second": 11.434, |
|
"eval_steps_per_second": 2.894, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 0.00013884965977660805, |
|
"loss": 1.366, |
|
"step": 4810 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 0.00013872127359096161, |
|
"loss": 1.3231, |
|
"step": 4820 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 0.0001385928874053152, |
|
"loss": 1.343, |
|
"step": 4830 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 0.00013846450121966875, |
|
"loss": 1.369, |
|
"step": 4840 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 0.00013833611503402235, |
|
"loss": 1.3541, |
|
"step": 4850 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 0.0001382077288483759, |
|
"loss": 1.3872, |
|
"step": 4860 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 0.0001380793426627295, |
|
"loss": 1.3562, |
|
"step": 4870 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 0.00013795095647708308, |
|
"loss": 1.4112, |
|
"step": 4880 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 0.00013782257029143667, |
|
"loss": 1.3391, |
|
"step": 4890 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 0.00013769418410579024, |
|
"loss": 1.3979, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 0.00013756579792014378, |
|
"loss": 1.3862, |
|
"step": 4910 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 0.00013743741173449737, |
|
"loss": 1.3407, |
|
"step": 4920 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 0.00013730902554885094, |
|
"loss": 1.3499, |
|
"step": 4930 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 0.00013718063936320454, |
|
"loss": 1.3607, |
|
"step": 4940 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 0.0001370522531775581, |
|
"loss": 1.4431, |
|
"step": 4950 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 0.0001369238669919117, |
|
"loss": 1.3812, |
|
"step": 4960 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 0.00013679548080626527, |
|
"loss": 1.3765, |
|
"step": 4970 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 0.0001366670946206188, |
|
"loss": 1.3872, |
|
"step": 4980 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.0001365387084349724, |
|
"loss": 1.3645, |
|
"step": 4990 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.00013641032224932597, |
|
"loss": 1.3862, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"eval_loss": 3.209571361541748, |
|
"eval_runtime": 21.1757, |
|
"eval_samples_per_second": 11.57, |
|
"eval_steps_per_second": 2.928, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.00013628193606367956, |
|
"loss": 1.3032, |
|
"step": 5010 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 0.00013615354987803313, |
|
"loss": 1.3614, |
|
"step": 5020 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 0.00013602516369238673, |
|
"loss": 1.328, |
|
"step": 5030 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 0.0001358967775067403, |
|
"loss": 1.3637, |
|
"step": 5040 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 0.00013576839132109383, |
|
"loss": 1.338, |
|
"step": 5050 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 0.00013564000513544743, |
|
"loss": 1.3134, |
|
"step": 5060 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 0.000135511618949801, |
|
"loss": 1.3708, |
|
"step": 5070 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 0.0001353832327641546, |
|
"loss": 1.3789, |
|
"step": 5080 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 0.00013525484657850816, |
|
"loss": 1.3866, |
|
"step": 5090 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 0.00013512646039286175, |
|
"loss": 1.3795, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.00013499807420721532, |
|
"loss": 1.3935, |
|
"step": 5110 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.0001348696880215689, |
|
"loss": 1.3888, |
|
"step": 5120 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.00013474130183592246, |
|
"loss": 1.3898, |
|
"step": 5130 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.00013461291565027602, |
|
"loss": 1.3766, |
|
"step": 5140 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 0.00013448452946462962, |
|
"loss": 1.3804, |
|
"step": 5150 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 0.0001343561432789832, |
|
"loss": 1.3439, |
|
"step": 5160 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 0.00013422775709333678, |
|
"loss": 1.3499, |
|
"step": 5170 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 0.00013409937090769035, |
|
"loss": 1.3845, |
|
"step": 5180 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 0.00013397098472204392, |
|
"loss": 1.3515, |
|
"step": 5190 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 0.00013384259853639748, |
|
"loss": 1.3254, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"eval_loss": 3.1990888118743896, |
|
"eval_runtime": 20.9965, |
|
"eval_samples_per_second": 11.669, |
|
"eval_steps_per_second": 2.953, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 0.00013371421235075105, |
|
"loss": 1.3745, |
|
"step": 5210 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 0.00013358582616510465, |
|
"loss": 1.3104, |
|
"step": 5220 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 0.00013345743997945821, |
|
"loss": 1.3143, |
|
"step": 5230 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.0001333290537938118, |
|
"loss": 1.3493, |
|
"step": 5240 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.00013320066760816538, |
|
"loss": 1.3828, |
|
"step": 5250 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.00013307228142251894, |
|
"loss": 1.3474, |
|
"step": 5260 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 0.0001329438952368725, |
|
"loss": 1.3623, |
|
"step": 5270 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 0.00013281550905122608, |
|
"loss": 1.4258, |
|
"step": 5280 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 0.00013268712286557967, |
|
"loss": 1.3752, |
|
"step": 5290 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 0.00013255873667993324, |
|
"loss": 1.3817, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 0.00013243035049428684, |
|
"loss": 1.3128, |
|
"step": 5310 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 0.0001323019643086404, |
|
"loss": 1.3706, |
|
"step": 5320 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 0.00013217357812299397, |
|
"loss": 1.4055, |
|
"step": 5330 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 0.00013204519193734754, |
|
"loss": 1.3704, |
|
"step": 5340 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 0.00013191680575170113, |
|
"loss": 1.3531, |
|
"step": 5350 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.0001317884195660547, |
|
"loss": 1.3543, |
|
"step": 5360 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.00013166003338040827, |
|
"loss": 1.3645, |
|
"step": 5370 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.00013153164719476186, |
|
"loss": 1.2981, |
|
"step": 5380 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.00013140326100911543, |
|
"loss": 1.3721, |
|
"step": 5390 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 0.000131274874823469, |
|
"loss": 1.4074, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"eval_loss": 3.1983258724212646, |
|
"eval_runtime": 21.1414, |
|
"eval_samples_per_second": 11.589, |
|
"eval_steps_per_second": 2.933, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 0.00013114648863782257, |
|
"loss": 1.3606, |
|
"step": 5410 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 0.00013101810245217616, |
|
"loss": 1.3904, |
|
"step": 5420 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 0.00013088971626652973, |
|
"loss": 1.3862, |
|
"step": 5430 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 0.0001307613300808833, |
|
"loss": 1.3039, |
|
"step": 5440 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 0.0001306329438952369, |
|
"loss": 1.3717, |
|
"step": 5450 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 0.00013050455770959046, |
|
"loss": 1.3603, |
|
"step": 5460 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 0.00013037617152394403, |
|
"loss": 1.3798, |
|
"step": 5470 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 0.0001302477853382976, |
|
"loss": 1.4127, |
|
"step": 5480 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.0001301193991526512, |
|
"loss": 1.3446, |
|
"step": 5490 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.00012999101296700476, |
|
"loss": 1.3701, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.00012986262678135835, |
|
"loss": 1.3847, |
|
"step": 5510 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 0.00012973424059571192, |
|
"loss": 1.3619, |
|
"step": 5520 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 0.0001296058544100655, |
|
"loss": 1.3273, |
|
"step": 5530 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 0.00012947746822441906, |
|
"loss": 1.293, |
|
"step": 5540 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 0.00012934908203877262, |
|
"loss": 1.3071, |
|
"step": 5550 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 0.00012922069585312622, |
|
"loss": 1.3257, |
|
"step": 5560 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 0.00012909230966747979, |
|
"loss": 1.2834, |
|
"step": 5570 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 0.00012896392348183338, |
|
"loss": 1.3343, |
|
"step": 5580 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 0.00012883553729618695, |
|
"loss": 1.3695, |
|
"step": 5590 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 0.00012870715111054052, |
|
"loss": 1.3344, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"eval_loss": 3.2032129764556885, |
|
"eval_runtime": 21.827, |
|
"eval_samples_per_second": 11.225, |
|
"eval_steps_per_second": 2.841, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 0.00012857876492489408, |
|
"loss": 1.3378, |
|
"step": 5610 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 0.00012845037873924765, |
|
"loss": 1.3026, |
|
"step": 5620 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 0.00012832199255360125, |
|
"loss": 1.3513, |
|
"step": 5630 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 0.00012819360636795481, |
|
"loss": 1.3281, |
|
"step": 5640 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 0.0001280652201823084, |
|
"loss": 1.326, |
|
"step": 5650 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 0.00012793683399666198, |
|
"loss": 1.379, |
|
"step": 5660 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 0.00012780844781101552, |
|
"loss": 1.3591, |
|
"step": 5670 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 0.0001276800616253691, |
|
"loss": 1.3602, |
|
"step": 5680 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 0.00012755167543972268, |
|
"loss": 1.3466, |
|
"step": 5690 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 0.00012742328925407627, |
|
"loss": 1.3572, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 0.00012729490306842984, |
|
"loss": 1.3291, |
|
"step": 5710 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 0.00012716651688278344, |
|
"loss": 1.3421, |
|
"step": 5720 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 0.000127038130697137, |
|
"loss": 1.3793, |
|
"step": 5730 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 0.00012690974451149057, |
|
"loss": 1.3981, |
|
"step": 5740 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 0.00012678135832584414, |
|
"loss": 1.3172, |
|
"step": 5750 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 0.0001266529721401977, |
|
"loss": 1.3635, |
|
"step": 5760 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 0.0001265245859545513, |
|
"loss": 1.3431, |
|
"step": 5770 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 0.00012639619976890487, |
|
"loss": 1.3612, |
|
"step": 5780 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 0.00012626781358325846, |
|
"loss": 1.3389, |
|
"step": 5790 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 0.00012613942739761203, |
|
"loss": 1.3045, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"eval_loss": 3.1942386627197266, |
|
"eval_runtime": 21.0367, |
|
"eval_samples_per_second": 11.646, |
|
"eval_steps_per_second": 2.947, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 0.0001260110412119656, |
|
"loss": 1.3249, |
|
"step": 5810 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 0.00012588265502631917, |
|
"loss": 1.348, |
|
"step": 5820 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 0.00012575426884067273, |
|
"loss": 1.345, |
|
"step": 5830 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 0.00012562588265502633, |
|
"loss": 1.3046, |
|
"step": 5840 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 0.0001254974964693799, |
|
"loss": 1.3945, |
|
"step": 5850 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.0001253691102837335, |
|
"loss": 1.358, |
|
"step": 5860 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.00012524072409808706, |
|
"loss": 1.3153, |
|
"step": 5870 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.00012511233791244063, |
|
"loss": 1.3501, |
|
"step": 5880 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.0001249839517267942, |
|
"loss": 1.3676, |
|
"step": 5890 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 0.00012485556554114776, |
|
"loss": 1.3276, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 0.00012472717935550136, |
|
"loss": 1.3583, |
|
"step": 5910 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 0.00012459879316985493, |
|
"loss": 1.3802, |
|
"step": 5920 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.00012447040698420852, |
|
"loss": 1.302, |
|
"step": 5930 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.0001243420207985621, |
|
"loss": 1.3062, |
|
"step": 5940 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.00012421363461291566, |
|
"loss": 1.2754, |
|
"step": 5950 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"learning_rate": 0.00012408524842726922, |
|
"loss": 1.3343, |
|
"step": 5960 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"learning_rate": 0.00012395686224162282, |
|
"loss": 1.3755, |
|
"step": 5970 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"learning_rate": 0.00012382847605597639, |
|
"loss": 1.3378, |
|
"step": 5980 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.00012370008987032995, |
|
"loss": 1.3095, |
|
"step": 5990 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.00012357170368468355, |
|
"loss": 1.3413, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"eval_loss": 3.1875319480895996, |
|
"eval_runtime": 20.9846, |
|
"eval_samples_per_second": 11.675, |
|
"eval_steps_per_second": 2.955, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.00012344331749903712, |
|
"loss": 1.3291, |
|
"step": 6010 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 0.00012331493131339068, |
|
"loss": 1.3553, |
|
"step": 6020 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 0.00012318654512774425, |
|
"loss": 1.3918, |
|
"step": 6030 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 0.00012305815894209785, |
|
"loss": 1.3198, |
|
"step": 6040 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 0.0001229297727564514, |
|
"loss": 1.3337, |
|
"step": 6050 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 0.00012280138657080498, |
|
"loss": 1.3334, |
|
"step": 6060 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 0.00012267300038515858, |
|
"loss": 1.325, |
|
"step": 6070 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 0.00012254461419951214, |
|
"loss": 1.3105, |
|
"step": 6080 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 0.0001224162280138657, |
|
"loss": 1.3541, |
|
"step": 6090 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 0.00012228784182821928, |
|
"loss": 1.3766, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 0.00012215945564257287, |
|
"loss": 1.3555, |
|
"step": 6110 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 0.00012203106945692644, |
|
"loss": 1.3298, |
|
"step": 6120 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 0.00012190268327128002, |
|
"loss": 1.3839, |
|
"step": 6130 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 0.00012177429708563359, |
|
"loss": 1.3546, |
|
"step": 6140 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 0.00012164591089998716, |
|
"loss": 1.3295, |
|
"step": 6150 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 0.00012151752471434075, |
|
"loss": 1.3959, |
|
"step": 6160 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 0.0001213891385286943, |
|
"loss": 1.3529, |
|
"step": 6170 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 0.0001212607523430479, |
|
"loss": 1.2984, |
|
"step": 6180 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 0.00012113236615740147, |
|
"loss": 1.3385, |
|
"step": 6190 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 0.00012100397997175505, |
|
"loss": 1.3483, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"eval_loss": 3.187854290008545, |
|
"eval_runtime": 20.97, |
|
"eval_samples_per_second": 11.683, |
|
"eval_steps_per_second": 2.957, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.00012087559378610862, |
|
"loss": 1.3532, |
|
"step": 6210 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.00012074720760046219, |
|
"loss": 1.3083, |
|
"step": 6220 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.00012061882141481578, |
|
"loss": 1.3277, |
|
"step": 6230 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.00012049043522916933, |
|
"loss": 1.3015, |
|
"step": 6240 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.00012036204904352293, |
|
"loss": 1.3581, |
|
"step": 6250 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.0001202336628578765, |
|
"loss": 1.334, |
|
"step": 6260 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 0.00012010527667223008, |
|
"loss": 1.2963, |
|
"step": 6270 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 0.00011997689048658365, |
|
"loss": 1.2901, |
|
"step": 6280 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 0.00011984850430093721, |
|
"loss": 1.3133, |
|
"step": 6290 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 0.00011972011811529081, |
|
"loss": 1.3234, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 0.00011959173192964436, |
|
"loss": 1.334, |
|
"step": 6310 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 0.00011946334574399796, |
|
"loss": 1.3247, |
|
"step": 6320 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 0.00011933495955835152, |
|
"loss": 1.3786, |
|
"step": 6330 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 0.0001192065733727051, |
|
"loss": 1.3241, |
|
"step": 6340 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 0.00011907818718705867, |
|
"loss": 1.344, |
|
"step": 6350 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 0.00011894980100141227, |
|
"loss": 1.354, |
|
"step": 6360 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 0.00011882141481576584, |
|
"loss": 1.3745, |
|
"step": 6370 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 0.00011869302863011939, |
|
"loss": 1.3263, |
|
"step": 6380 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 0.00011856464244447298, |
|
"loss": 1.3413, |
|
"step": 6390 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 0.00011843625625882655, |
|
"loss": 1.3387, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"eval_loss": 3.170781373977661, |
|
"eval_runtime": 21.1856, |
|
"eval_samples_per_second": 11.564, |
|
"eval_steps_per_second": 2.927, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 0.00011830787007318013, |
|
"loss": 1.3112, |
|
"step": 6410 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 0.0001181794838875337, |
|
"loss": 1.2843, |
|
"step": 6420 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 0.0001180510977018873, |
|
"loss": 1.3479, |
|
"step": 6430 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 0.00011792271151624086, |
|
"loss": 1.2897, |
|
"step": 6440 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 0.00011779432533059442, |
|
"loss": 1.3337, |
|
"step": 6450 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 0.00011766593914494801, |
|
"loss": 1.3058, |
|
"step": 6460 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 0.00011753755295930158, |
|
"loss": 1.3257, |
|
"step": 6470 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 0.00011740916677365516, |
|
"loss": 1.3423, |
|
"step": 6480 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 0.00011728078058800873, |
|
"loss": 1.3402, |
|
"step": 6490 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 0.00011715239440236232, |
|
"loss": 1.3348, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 0.00011702400821671589, |
|
"loss": 1.2905, |
|
"step": 6510 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 0.00011689562203106945, |
|
"loss": 1.3138, |
|
"step": 6520 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 0.00011676723584542304, |
|
"loss": 1.3687, |
|
"step": 6530 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 0.00011663884965977661, |
|
"loss": 1.3398, |
|
"step": 6540 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 0.00011651046347413019, |
|
"loss": 1.3528, |
|
"step": 6550 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 0.00011638207728848376, |
|
"loss": 1.3367, |
|
"step": 6560 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 0.00011625369110283735, |
|
"loss": 1.3325, |
|
"step": 6570 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 0.00011612530491719092, |
|
"loss": 1.3588, |
|
"step": 6580 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 0.0001159969187315445, |
|
"loss": 1.3162, |
|
"step": 6590 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 0.00011586853254589807, |
|
"loss": 1.3332, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"eval_loss": 3.1261515617370605, |
|
"eval_runtime": 20.8712, |
|
"eval_samples_per_second": 11.739, |
|
"eval_steps_per_second": 2.971, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 0.00011574014636025164, |
|
"loss": 1.2807, |
|
"step": 6610 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 0.00011561176017460522, |
|
"loss": 1.3397, |
|
"step": 6620 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 0.00011548337398895879, |
|
"loss": 1.2873, |
|
"step": 6630 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 0.00011535498780331238, |
|
"loss": 1.2933, |
|
"step": 6640 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 0.00011522660161766595, |
|
"loss": 1.3099, |
|
"step": 6650 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 0.00011509821543201953, |
|
"loss": 1.3117, |
|
"step": 6660 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 0.0001149698292463731, |
|
"loss": 1.3321, |
|
"step": 6670 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 0.00011484144306072666, |
|
"loss": 1.3497, |
|
"step": 6680 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 0.00011471305687508025, |
|
"loss": 1.3022, |
|
"step": 6690 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 0.00011458467068943381, |
|
"loss": 1.368, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 2.15, |
|
"learning_rate": 0.00011445628450378741, |
|
"loss": 1.3394, |
|
"step": 6710 |
|
}, |
|
{ |
|
"epoch": 2.15, |
|
"learning_rate": 0.00011432789831814098, |
|
"loss": 1.3592, |
|
"step": 6720 |
|
}, |
|
{ |
|
"epoch": 2.15, |
|
"learning_rate": 0.00011419951213249456, |
|
"loss": 1.3023, |
|
"step": 6730 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 0.00011407112594684812, |
|
"loss": 1.3225, |
|
"step": 6740 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 0.0001139427397612017, |
|
"loss": 1.3464, |
|
"step": 6750 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 0.00011381435357555527, |
|
"loss": 1.3179, |
|
"step": 6760 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 0.00011368596738990884, |
|
"loss": 1.3485, |
|
"step": 6770 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 0.00011355758120426244, |
|
"loss": 1.3569, |
|
"step": 6780 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 0.000113429195018616, |
|
"loss": 1.3076, |
|
"step": 6790 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 0.00011330080883296958, |
|
"loss": 1.3492, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"eval_loss": 3.0547232627868652, |
|
"eval_runtime": 20.5571, |
|
"eval_samples_per_second": 11.918, |
|
"eval_steps_per_second": 3.016, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 0.00011317242264732315, |
|
"loss": 1.2886, |
|
"step": 6810 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 0.00011304403646167673, |
|
"loss": 1.3107, |
|
"step": 6820 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 0.0001129156502760303, |
|
"loss": 1.3639, |
|
"step": 6830 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 0.00011278726409038387, |
|
"loss": 1.3256, |
|
"step": 6840 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 0.00011265887790473746, |
|
"loss": 1.3228, |
|
"step": 6850 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 0.00011253049171909103, |
|
"loss": 1.3511, |
|
"step": 6860 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 0.00011240210553344461, |
|
"loss": 1.3226, |
|
"step": 6870 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 0.00011227371934779818, |
|
"loss": 1.3623, |
|
"step": 6880 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 0.00011214533316215176, |
|
"loss": 1.3489, |
|
"step": 6890 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 0.00011201694697650533, |
|
"loss": 1.2869, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 0.0001118885607908589, |
|
"loss": 1.3938, |
|
"step": 6910 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 0.00011176017460521249, |
|
"loss": 1.3458, |
|
"step": 6920 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 0.00011163178841956606, |
|
"loss": 1.2612, |
|
"step": 6930 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 0.00011150340223391964, |
|
"loss": 1.3065, |
|
"step": 6940 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 0.00011137501604827321, |
|
"loss": 1.3339, |
|
"step": 6950 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 0.00011124662986262679, |
|
"loss": 1.299, |
|
"step": 6960 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 0.00011111824367698036, |
|
"loss": 1.3493, |
|
"step": 6970 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 0.00011098985749133395, |
|
"loss": 1.3342, |
|
"step": 6980 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 0.00011086147130568752, |
|
"loss": 1.3922, |
|
"step": 6990 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 0.00011073308512004109, |
|
"loss": 1.3206, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"eval_loss": 3.0793209075927734, |
|
"eval_runtime": 20.1171, |
|
"eval_samples_per_second": 12.179, |
|
"eval_steps_per_second": 3.082, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 0.00011060469893439467, |
|
"loss": 1.3175, |
|
"step": 7010 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 0.00011047631274874824, |
|
"loss": 1.3209, |
|
"step": 7020 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 0.00011034792656310182, |
|
"loss": 1.3383, |
|
"step": 7030 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 0.00011021954037745538, |
|
"loss": 1.3293, |
|
"step": 7040 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 0.00011009115419180898, |
|
"loss": 1.2861, |
|
"step": 7050 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 0.00010996276800616255, |
|
"loss": 1.3326, |
|
"step": 7060 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 0.00010983438182051611, |
|
"loss": 1.3398, |
|
"step": 7070 |
|
}, |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 0.0001097059956348697, |
|
"loss": 1.3578, |
|
"step": 7080 |
|
}, |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 0.00010957760944922326, |
|
"loss": 1.3683, |
|
"step": 7090 |
|
}, |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 0.00010944922326357684, |
|
"loss": 1.304, |
|
"step": 7100 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 0.00010932083707793041, |
|
"loss": 1.3196, |
|
"step": 7110 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 0.00010919245089228401, |
|
"loss": 1.3587, |
|
"step": 7120 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 0.00010906406470663757, |
|
"loss": 1.3147, |
|
"step": 7130 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 0.00010893567852099114, |
|
"loss": 1.307, |
|
"step": 7140 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 0.00010880729233534472, |
|
"loss": 1.3609, |
|
"step": 7150 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 0.00010867890614969829, |
|
"loss": 1.3336, |
|
"step": 7160 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 0.00010855051996405187, |
|
"loss": 1.3514, |
|
"step": 7170 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 0.00010842213377840544, |
|
"loss": 1.3203, |
|
"step": 7180 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 0.00010829374759275903, |
|
"loss": 1.3451, |
|
"step": 7190 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 0.0001081653614071126, |
|
"loss": 1.3545, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"eval_loss": 3.0495612621307373, |
|
"eval_runtime": 22.2315, |
|
"eval_samples_per_second": 11.02, |
|
"eval_steps_per_second": 2.789, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 2.31, |
|
"learning_rate": 0.00010803697522146618, |
|
"loss": 1.3852, |
|
"step": 7210 |
|
}, |
|
{ |
|
"epoch": 2.31, |
|
"learning_rate": 0.00010790858903581975, |
|
"loss": 1.2726, |
|
"step": 7220 |
|
}, |
|
{ |
|
"epoch": 2.31, |
|
"learning_rate": 0.00010778020285017332, |
|
"loss": 1.3145, |
|
"step": 7230 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 0.0001076518166645269, |
|
"loss": 1.3485, |
|
"step": 7240 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 0.00010752343047888047, |
|
"loss": 1.3202, |
|
"step": 7250 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 0.00010739504429323406, |
|
"loss": 1.3129, |
|
"step": 7260 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 0.00010726665810758763, |
|
"loss": 1.3076, |
|
"step": 7270 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 0.00010713827192194121, |
|
"loss": 1.2815, |
|
"step": 7280 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 0.00010700988573629478, |
|
"loss": 1.3511, |
|
"step": 7290 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 0.00010688149955064835, |
|
"loss": 1.2882, |
|
"step": 7300 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 0.00010675311336500193, |
|
"loss": 1.3341, |
|
"step": 7310 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 0.0001066247271793555, |
|
"loss": 1.2887, |
|
"step": 7320 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 0.00010649634099370909, |
|
"loss": 1.3705, |
|
"step": 7330 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 0.00010636795480806266, |
|
"loss": 1.3462, |
|
"step": 7340 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 0.00010623956862241624, |
|
"loss": 1.3383, |
|
"step": 7350 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 0.00010611118243676981, |
|
"loss": 1.3337, |
|
"step": 7360 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 0.00010598279625112339, |
|
"loss": 1.3041, |
|
"step": 7370 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 0.00010585441006547696, |
|
"loss": 1.3707, |
|
"step": 7380 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 0.00010572602387983052, |
|
"loss": 1.3023, |
|
"step": 7390 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 0.00010559763769418412, |
|
"loss": 1.2776, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"eval_loss": 3.0625219345092773, |
|
"eval_runtime": 19.937, |
|
"eval_samples_per_second": 12.289, |
|
"eval_steps_per_second": 3.11, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 0.00010546925150853769, |
|
"loss": 1.304, |
|
"step": 7410 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 0.00010534086532289127, |
|
"loss": 1.3461, |
|
"step": 7420 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 0.00010521247913724484, |
|
"loss": 1.3576, |
|
"step": 7430 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 0.00010508409295159842, |
|
"loss": 1.3421, |
|
"step": 7440 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 0.00010495570676595198, |
|
"loss": 1.3644, |
|
"step": 7450 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 0.00010482732058030555, |
|
"loss": 1.3315, |
|
"step": 7460 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 0.00010469893439465915, |
|
"loss": 1.3011, |
|
"step": 7470 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 0.00010457054820901271, |
|
"loss": 1.256, |
|
"step": 7480 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 0.0001044421620233663, |
|
"loss": 1.3173, |
|
"step": 7490 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 0.00010431377583771986, |
|
"loss": 1.3781, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 0.00010418538965207344, |
|
"loss": 1.2921, |
|
"step": 7510 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 0.00010405700346642701, |
|
"loss": 1.2946, |
|
"step": 7520 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 0.00010392861728078058, |
|
"loss": 1.3369, |
|
"step": 7530 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 0.00010380023109513417, |
|
"loss": 1.366, |
|
"step": 7540 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 0.00010367184490948774, |
|
"loss": 1.3326, |
|
"step": 7550 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 0.00010354345872384132, |
|
"loss": 1.3287, |
|
"step": 7560 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 0.00010341507253819489, |
|
"loss": 1.2873, |
|
"step": 7570 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 0.00010328668635254847, |
|
"loss": 1.3481, |
|
"step": 7580 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 0.00010315830016690204, |
|
"loss": 1.3212, |
|
"step": 7590 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 0.00010302991398125563, |
|
"loss": 1.3645, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"eval_loss": 3.0130844116210938, |
|
"eval_runtime": 20.5364, |
|
"eval_samples_per_second": 11.93, |
|
"eval_steps_per_second": 3.019, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 0.0001029015277956092, |
|
"loss": 1.3224, |
|
"step": 7610 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 0.00010277314160996277, |
|
"loss": 1.3072, |
|
"step": 7620 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 0.00010264475542431635, |
|
"loss": 1.2947, |
|
"step": 7630 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 0.00010251636923866992, |
|
"loss": 1.3951, |
|
"step": 7640 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 0.0001023879830530235, |
|
"loss": 1.3322, |
|
"step": 7650 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 0.00010225959686737707, |
|
"loss": 1.3588, |
|
"step": 7660 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 0.00010213121068173066, |
|
"loss": 1.367, |
|
"step": 7670 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 0.00010200282449608423, |
|
"loss": 1.3491, |
|
"step": 7680 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 0.0001018744383104378, |
|
"loss": 1.3388, |
|
"step": 7690 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 0.00010174605212479138, |
|
"loss": 1.3045, |
|
"step": 7700 |
|
}, |
|
{ |
|
"epoch": 2.47, |
|
"learning_rate": 0.00010161766593914495, |
|
"loss": 1.3669, |
|
"step": 7710 |
|
}, |
|
{ |
|
"epoch": 2.47, |
|
"learning_rate": 0.00010148927975349853, |
|
"loss": 1.3145, |
|
"step": 7720 |
|
}, |
|
{ |
|
"epoch": 2.47, |
|
"learning_rate": 0.0001013608935678521, |
|
"loss": 1.3466, |
|
"step": 7730 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 0.00010123250738220569, |
|
"loss": 1.3257, |
|
"step": 7740 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 0.00010110412119655926, |
|
"loss": 1.3222, |
|
"step": 7750 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 0.00010097573501091283, |
|
"loss": 1.4099, |
|
"step": 7760 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 0.0001008473488252664, |
|
"loss": 1.3349, |
|
"step": 7770 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 0.00010071896263961997, |
|
"loss": 1.3444, |
|
"step": 7780 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 0.00010059057645397356, |
|
"loss": 1.3368, |
|
"step": 7790 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 0.00010046219026832712, |
|
"loss": 1.3673, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"eval_loss": 3.070995569229126, |
|
"eval_runtime": 22.3209, |
|
"eval_samples_per_second": 10.976, |
|
"eval_steps_per_second": 2.778, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 0.00010033380408268072, |
|
"loss": 1.305, |
|
"step": 7810 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 0.00010020541789703429, |
|
"loss": 1.3473, |
|
"step": 7820 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 0.00010007703171138787, |
|
"loss": 1.3259, |
|
"step": 7830 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 9.994864552574143e-05, |
|
"loss": 1.314, |
|
"step": 7840 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 9.982025934009502e-05, |
|
"loss": 1.3634, |
|
"step": 7850 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 9.969187315444858e-05, |
|
"loss": 1.377, |
|
"step": 7860 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 9.956348696880216e-05, |
|
"loss": 1.3121, |
|
"step": 7870 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 9.943510078315573e-05, |
|
"loss": 1.3613, |
|
"step": 7880 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 9.930671459750931e-05, |
|
"loss": 1.3213, |
|
"step": 7890 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 9.917832841186288e-05, |
|
"loss": 1.2616, |
|
"step": 7900 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 9.904994222621646e-05, |
|
"loss": 1.3149, |
|
"step": 7910 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 9.892155604057004e-05, |
|
"loss": 1.3147, |
|
"step": 7920 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 9.879316985492361e-05, |
|
"loss": 1.3505, |
|
"step": 7930 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 9.866478366927719e-05, |
|
"loss": 1.4176, |
|
"step": 7940 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 9.853639748363077e-05, |
|
"loss": 1.3489, |
|
"step": 7950 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 9.840801129798434e-05, |
|
"loss": 1.3728, |
|
"step": 7960 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 9.827962511233791e-05, |
|
"loss": 1.31, |
|
"step": 7970 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 9.815123892669149e-05, |
|
"loss": 1.3491, |
|
"step": 7980 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 9.802285274104507e-05, |
|
"loss": 1.3423, |
|
"step": 7990 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 9.789446655539864e-05, |
|
"loss": 1.329, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"eval_loss": 2.9742517471313477, |
|
"eval_runtime": 20.1551, |
|
"eval_samples_per_second": 12.156, |
|
"eval_steps_per_second": 3.076, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 9.776608036975222e-05, |
|
"loss": 1.3596, |
|
"step": 8010 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 9.76376941841058e-05, |
|
"loss": 1.3228, |
|
"step": 8020 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 9.750930799845937e-05, |
|
"loss": 1.2961, |
|
"step": 8030 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 9.738092181281294e-05, |
|
"loss": 1.2992, |
|
"step": 8040 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 9.725253562716652e-05, |
|
"loss": 1.3207, |
|
"step": 8050 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 9.71241494415201e-05, |
|
"loss": 1.3096, |
|
"step": 8060 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 9.699576325587367e-05, |
|
"loss": 1.3638, |
|
"step": 8070 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"learning_rate": 9.686737707022725e-05, |
|
"loss": 1.3179, |
|
"step": 8080 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"learning_rate": 9.673899088458083e-05, |
|
"loss": 1.3479, |
|
"step": 8090 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"learning_rate": 9.66106046989344e-05, |
|
"loss": 1.2827, |
|
"step": 8100 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 9.648221851328796e-05, |
|
"loss": 1.3087, |
|
"step": 8110 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 9.635383232764155e-05, |
|
"loss": 1.3363, |
|
"step": 8120 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 9.622544614199513e-05, |
|
"loss": 1.2648, |
|
"step": 8130 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 9.60970599563487e-05, |
|
"loss": 1.3517, |
|
"step": 8140 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 9.596867377070228e-05, |
|
"loss": 1.3494, |
|
"step": 8150 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 9.584028758505586e-05, |
|
"loss": 1.2962, |
|
"step": 8160 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 9.571190139940942e-05, |
|
"loss": 1.3348, |
|
"step": 8170 |
|
}, |
|
{ |
|
"epoch": 2.62, |
|
"learning_rate": 9.5583515213763e-05, |
|
"loss": 1.3275, |
|
"step": 8180 |
|
}, |
|
{ |
|
"epoch": 2.62, |
|
"learning_rate": 9.545512902811657e-05, |
|
"loss": 1.2885, |
|
"step": 8190 |
|
}, |
|
{ |
|
"epoch": 2.62, |
|
"learning_rate": 9.532674284247016e-05, |
|
"loss": 1.3703, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 2.62, |
|
"eval_loss": 3.0707430839538574, |
|
"eval_runtime": 19.7129, |
|
"eval_samples_per_second": 12.428, |
|
"eval_steps_per_second": 3.145, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 9.519835665682372e-05, |
|
"loss": 1.3315, |
|
"step": 8210 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 9.50699704711773e-05, |
|
"loss": 1.331, |
|
"step": 8220 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 9.494158428553089e-05, |
|
"loss": 1.3438, |
|
"step": 8230 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 9.481319809988445e-05, |
|
"loss": 1.3512, |
|
"step": 8240 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 9.468481191423803e-05, |
|
"loss": 1.3345, |
|
"step": 8250 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 9.455642572859162e-05, |
|
"loss": 1.2768, |
|
"step": 8260 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 9.442803954294518e-05, |
|
"loss": 1.314, |
|
"step": 8270 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 9.429965335729875e-05, |
|
"loss": 1.3449, |
|
"step": 8280 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 9.417126717165233e-05, |
|
"loss": 1.2917, |
|
"step": 8290 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 9.404288098600591e-05, |
|
"loss": 1.2936, |
|
"step": 8300 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 9.391449480035948e-05, |
|
"loss": 1.3231, |
|
"step": 8310 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 9.378610861471306e-05, |
|
"loss": 1.284, |
|
"step": 8320 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 9.365772242906664e-05, |
|
"loss": 1.3236, |
|
"step": 8330 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 9.352933624342021e-05, |
|
"loss": 1.2997, |
|
"step": 8340 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 9.340095005777378e-05, |
|
"loss": 1.3507, |
|
"step": 8350 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 9.327256387212736e-05, |
|
"loss": 1.3251, |
|
"step": 8360 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 9.314417768648094e-05, |
|
"loss": 1.333, |
|
"step": 8370 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 9.301579150083451e-05, |
|
"loss": 1.3207, |
|
"step": 8380 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 9.288740531518809e-05, |
|
"loss": 1.3081, |
|
"step": 8390 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 9.275901912954167e-05, |
|
"loss": 1.3929, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"eval_loss": 2.9242935180664062, |
|
"eval_runtime": 21.5088, |
|
"eval_samples_per_second": 11.391, |
|
"eval_steps_per_second": 2.883, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 9.263063294389525e-05, |
|
"loss": 1.3581, |
|
"step": 8410 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 9.25022467582488e-05, |
|
"loss": 1.3558, |
|
"step": 8420 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 9.237386057260239e-05, |
|
"loss": 1.2677, |
|
"step": 8430 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 9.224547438695597e-05, |
|
"loss": 1.3475, |
|
"step": 8440 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 9.211708820130954e-05, |
|
"loss": 1.3642, |
|
"step": 8450 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 9.198870201566312e-05, |
|
"loss": 1.3315, |
|
"step": 8460 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 9.18603158300167e-05, |
|
"loss": 1.2664, |
|
"step": 8470 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 9.173192964437028e-05, |
|
"loss": 1.3002, |
|
"step": 8480 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 9.160354345872385e-05, |
|
"loss": 1.3049, |
|
"step": 8490 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 9.147515727307742e-05, |
|
"loss": 1.3071, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 9.1346771087431e-05, |
|
"loss": 1.296, |
|
"step": 8510 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 9.121838490178456e-05, |
|
"loss": 1.3209, |
|
"step": 8520 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 9.108999871613815e-05, |
|
"loss": 1.3194, |
|
"step": 8530 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 9.096161253049173e-05, |
|
"loss": 1.3408, |
|
"step": 8540 |
|
}, |
|
{ |
|
"epoch": 2.74, |
|
"learning_rate": 9.083322634484531e-05, |
|
"loss": 1.3393, |
|
"step": 8550 |
|
}, |
|
{ |
|
"epoch": 2.74, |
|
"learning_rate": 9.070484015919888e-05, |
|
"loss": 1.3184, |
|
"step": 8560 |
|
}, |
|
{ |
|
"epoch": 2.74, |
|
"learning_rate": 9.057645397355246e-05, |
|
"loss": 1.3467, |
|
"step": 8570 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 9.044806778790602e-05, |
|
"loss": 1.3147, |
|
"step": 8580 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 9.031968160225959e-05, |
|
"loss": 1.3321, |
|
"step": 8590 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 9.019129541661317e-05, |
|
"loss": 1.3214, |
|
"step": 8600 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"eval_loss": 2.9662914276123047, |
|
"eval_runtime": 19.942, |
|
"eval_samples_per_second": 12.286, |
|
"eval_steps_per_second": 3.109, |
|
"step": 8600 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 9.006290923096675e-05, |
|
"loss": 1.3744, |
|
"step": 8610 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 8.993452304532034e-05, |
|
"loss": 1.335, |
|
"step": 8620 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 8.98061368596739e-05, |
|
"loss": 1.3666, |
|
"step": 8630 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 8.967775067402748e-05, |
|
"loss": 1.2971, |
|
"step": 8640 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 8.954936448838105e-05, |
|
"loss": 1.3281, |
|
"step": 8650 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 8.942097830273462e-05, |
|
"loss": 1.2946, |
|
"step": 8660 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 8.92925921170882e-05, |
|
"loss": 1.2826, |
|
"step": 8670 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 8.916420593144178e-05, |
|
"loss": 1.3137, |
|
"step": 8680 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 8.903581974579536e-05, |
|
"loss": 1.3198, |
|
"step": 8690 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 8.890743356014893e-05, |
|
"loss": 1.3907, |
|
"step": 8700 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 8.877904737450251e-05, |
|
"loss": 1.3613, |
|
"step": 8710 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 8.86506611888561e-05, |
|
"loss": 1.3362, |
|
"step": 8720 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 8.852227500320965e-05, |
|
"loss": 1.3087, |
|
"step": 8730 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 8.839388881756323e-05, |
|
"loss": 1.3282, |
|
"step": 8740 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 8.826550263191681e-05, |
|
"loss": 1.3035, |
|
"step": 8750 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 8.813711644627038e-05, |
|
"loss": 1.3509, |
|
"step": 8760 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 8.800873026062396e-05, |
|
"loss": 1.3177, |
|
"step": 8770 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 8.788034407497754e-05, |
|
"loss": 1.2968, |
|
"step": 8780 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 8.775195788933112e-05, |
|
"loss": 1.3317, |
|
"step": 8790 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 8.762357170368469e-05, |
|
"loss": 1.3184, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"eval_loss": 2.977778434753418, |
|
"eval_runtime": 21.3075, |
|
"eval_samples_per_second": 11.498, |
|
"eval_steps_per_second": 2.91, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 8.749518551803826e-05, |
|
"loss": 1.3189, |
|
"step": 8810 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 8.736679933239184e-05, |
|
"loss": 1.3593, |
|
"step": 8820 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 8.72384131467454e-05, |
|
"loss": 1.2973, |
|
"step": 8830 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 8.711002696109899e-05, |
|
"loss": 1.3356, |
|
"step": 8840 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 8.698164077545257e-05, |
|
"loss": 1.2957, |
|
"step": 8850 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 8.685325458980615e-05, |
|
"loss": 1.2868, |
|
"step": 8860 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 8.672486840415972e-05, |
|
"loss": 1.3393, |
|
"step": 8870 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 8.65964822185133e-05, |
|
"loss": 1.2805, |
|
"step": 8880 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 8.646809603286687e-05, |
|
"loss": 1.3268, |
|
"step": 8890 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 8.633970984722043e-05, |
|
"loss": 1.3004, |
|
"step": 8900 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 8.621132366157401e-05, |
|
"loss": 1.3551, |
|
"step": 8910 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 8.60829374759276e-05, |
|
"loss": 1.2792, |
|
"step": 8920 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 8.595455129028118e-05, |
|
"loss": 1.2719, |
|
"step": 8930 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 8.582616510463474e-05, |
|
"loss": 1.3509, |
|
"step": 8940 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 8.569777891898833e-05, |
|
"loss": 1.27, |
|
"step": 8950 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 8.55693927333419e-05, |
|
"loss": 1.2834, |
|
"step": 8960 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 8.544100654769546e-05, |
|
"loss": 1.3124, |
|
"step": 8970 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 8.531262036204904e-05, |
|
"loss": 1.3382, |
|
"step": 8980 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 8.518423417640262e-05, |
|
"loss": 1.3541, |
|
"step": 8990 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 8.50558479907562e-05, |
|
"loss": 1.3432, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"eval_loss": 2.9086410999298096, |
|
"eval_runtime": 19.3634, |
|
"eval_samples_per_second": 12.653, |
|
"eval_steps_per_second": 3.202, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 8.492746180510977e-05, |
|
"loss": 1.2825, |
|
"step": 9010 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 8.479907561946335e-05, |
|
"loss": 1.3358, |
|
"step": 9020 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 8.467068943381694e-05, |
|
"loss": 1.2916, |
|
"step": 9030 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 8.454230324817049e-05, |
|
"loss": 1.3391, |
|
"step": 9040 |
|
}, |
|
{ |
|
"epoch": 2.9, |
|
"learning_rate": 8.441391706252407e-05, |
|
"loss": 1.2946, |
|
"step": 9050 |
|
}, |
|
{ |
|
"epoch": 2.9, |
|
"learning_rate": 8.428553087687765e-05, |
|
"loss": 1.3257, |
|
"step": 9060 |
|
}, |
|
{ |
|
"epoch": 2.9, |
|
"learning_rate": 8.415714469123123e-05, |
|
"loss": 1.321, |
|
"step": 9070 |
|
}, |
|
{ |
|
"epoch": 2.91, |
|
"learning_rate": 8.40287585055848e-05, |
|
"loss": 1.3226, |
|
"step": 9080 |
|
}, |
|
{ |
|
"epoch": 2.91, |
|
"learning_rate": 8.390037231993838e-05, |
|
"loss": 1.3706, |
|
"step": 9090 |
|
}, |
|
{ |
|
"epoch": 2.91, |
|
"learning_rate": 8.377198613429196e-05, |
|
"loss": 1.361, |
|
"step": 9100 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 8.364359994864553e-05, |
|
"loss": 1.333, |
|
"step": 9110 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 8.35152137629991e-05, |
|
"loss": 1.3091, |
|
"step": 9120 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 8.338682757735268e-05, |
|
"loss": 1.2521, |
|
"step": 9130 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 8.325844139170626e-05, |
|
"loss": 1.2842, |
|
"step": 9140 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 8.313005520605983e-05, |
|
"loss": 1.3595, |
|
"step": 9150 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 8.300166902041341e-05, |
|
"loss": 1.3506, |
|
"step": 9160 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 8.287328283476699e-05, |
|
"loss": 1.3885, |
|
"step": 9170 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 8.274489664912056e-05, |
|
"loss": 1.3072, |
|
"step": 9180 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 8.261651046347414e-05, |
|
"loss": 1.3088, |
|
"step": 9190 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 8.248812427782771e-05, |
|
"loss": 1.3689, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"eval_loss": 2.906977891921997, |
|
"eval_runtime": 19.3088, |
|
"eval_samples_per_second": 12.689, |
|
"eval_steps_per_second": 3.211, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 8.235973809218129e-05, |
|
"loss": 1.3285, |
|
"step": 9210 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 8.223135190653486e-05, |
|
"loss": 1.3557, |
|
"step": 9220 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 8.210296572088844e-05, |
|
"loss": 1.29, |
|
"step": 9230 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 8.197457953524202e-05, |
|
"loss": 1.3173, |
|
"step": 9240 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 8.184619334959559e-05, |
|
"loss": 1.3229, |
|
"step": 9250 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 8.171780716394917e-05, |
|
"loss": 1.3679, |
|
"step": 9260 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 8.158942097830274e-05, |
|
"loss": 1.2966, |
|
"step": 9270 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 8.146103479265632e-05, |
|
"loss": 1.3165, |
|
"step": 9280 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 8.133264860700988e-05, |
|
"loss": 1.2764, |
|
"step": 9290 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 8.120426242136347e-05, |
|
"loss": 1.3668, |
|
"step": 9300 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 8.107587623571705e-05, |
|
"loss": 1.3319, |
|
"step": 9310 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 8.094749005007061e-05, |
|
"loss": 1.3229, |
|
"step": 9320 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 8.08191038644242e-05, |
|
"loss": 1.3364, |
|
"step": 9330 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 8.069071767877778e-05, |
|
"loss": 1.312, |
|
"step": 9340 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 8.056233149313134e-05, |
|
"loss": 1.3258, |
|
"step": 9350 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 8.043394530748491e-05, |
|
"loss": 1.2949, |
|
"step": 9360 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 8.03055591218385e-05, |
|
"loss": 1.3362, |
|
"step": 9370 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 8.017717293619207e-05, |
|
"loss": 1.3359, |
|
"step": 9380 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 8.004878675054564e-05, |
|
"loss": 1.3524, |
|
"step": 9390 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 7.992040056489922e-05, |
|
"loss": 1.3049, |
|
"step": 9400 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"eval_loss": 2.963099956512451, |
|
"eval_runtime": 21.1133, |
|
"eval_samples_per_second": 11.604, |
|
"eval_steps_per_second": 2.937, |
|
"step": 9400 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 7.97920143792528e-05, |
|
"loss": 1.3289, |
|
"step": 9410 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 7.966362819360637e-05, |
|
"loss": 1.3135, |
|
"step": 9420 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 7.953524200795994e-05, |
|
"loss": 1.3374, |
|
"step": 9430 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 7.940685582231352e-05, |
|
"loss": 1.3279, |
|
"step": 9440 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 7.92784696366671e-05, |
|
"loss": 1.3405, |
|
"step": 9450 |
|
}, |
|
{ |
|
"epoch": 3.03, |
|
"learning_rate": 7.915008345102067e-05, |
|
"loss": 1.3124, |
|
"step": 9460 |
|
}, |
|
{ |
|
"epoch": 3.03, |
|
"learning_rate": 7.902169726537425e-05, |
|
"loss": 1.32, |
|
"step": 9470 |
|
}, |
|
{ |
|
"epoch": 3.03, |
|
"learning_rate": 7.889331107972783e-05, |
|
"loss": 1.3316, |
|
"step": 9480 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 7.87649248940814e-05, |
|
"loss": 1.3025, |
|
"step": 9490 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 7.863653870843498e-05, |
|
"loss": 1.3009, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 7.850815252278855e-05, |
|
"loss": 1.3364, |
|
"step": 9510 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"learning_rate": 7.837976633714213e-05, |
|
"loss": 1.3452, |
|
"step": 9520 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"learning_rate": 7.82513801514957e-05, |
|
"loss": 1.3202, |
|
"step": 9530 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"learning_rate": 7.812299396584928e-05, |
|
"loss": 1.3349, |
|
"step": 9540 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"learning_rate": 7.799460778020286e-05, |
|
"loss": 1.3456, |
|
"step": 9550 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"learning_rate": 7.786622159455643e-05, |
|
"loss": 1.2725, |
|
"step": 9560 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"learning_rate": 7.773783540891001e-05, |
|
"loss": 1.2822, |
|
"step": 9570 |
|
}, |
|
{ |
|
"epoch": 3.07, |
|
"learning_rate": 7.760944922326358e-05, |
|
"loss": 1.3512, |
|
"step": 9580 |
|
}, |
|
{ |
|
"epoch": 3.07, |
|
"learning_rate": 7.748106303761716e-05, |
|
"loss": 1.3526, |
|
"step": 9590 |
|
}, |
|
{ |
|
"epoch": 3.07, |
|
"learning_rate": 7.735267685197073e-05, |
|
"loss": 1.3758, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 3.07, |
|
"eval_loss": 2.8628766536712646, |
|
"eval_runtime": 20.5324, |
|
"eval_samples_per_second": 11.932, |
|
"eval_steps_per_second": 3.02, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 7.722429066632431e-05, |
|
"loss": 1.3041, |
|
"step": 9610 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 7.709590448067789e-05, |
|
"loss": 1.3036, |
|
"step": 9620 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 7.696751829503146e-05, |
|
"loss": 1.3425, |
|
"step": 9630 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 7.683913210938504e-05, |
|
"loss": 1.3164, |
|
"step": 9640 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 7.671074592373862e-05, |
|
"loss": 1.2856, |
|
"step": 9650 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 7.658235973809219e-05, |
|
"loss": 1.3245, |
|
"step": 9660 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 7.645397355244575e-05, |
|
"loss": 1.3103, |
|
"step": 9670 |
|
}, |
|
{ |
|
"epoch": 3.1, |
|
"learning_rate": 7.632558736679933e-05, |
|
"loss": 1.3374, |
|
"step": 9680 |
|
}, |
|
{ |
|
"epoch": 3.1, |
|
"learning_rate": 7.619720118115292e-05, |
|
"loss": 1.2918, |
|
"step": 9690 |
|
}, |
|
{ |
|
"epoch": 3.1, |
|
"learning_rate": 7.606881499550648e-05, |
|
"loss": 1.3163, |
|
"step": 9700 |
|
}, |
|
{ |
|
"epoch": 3.11, |
|
"learning_rate": 7.594042880986006e-05, |
|
"loss": 1.3001, |
|
"step": 9710 |
|
}, |
|
{ |
|
"epoch": 3.11, |
|
"learning_rate": 7.581204262421365e-05, |
|
"loss": 1.3561, |
|
"step": 9720 |
|
}, |
|
{ |
|
"epoch": 3.11, |
|
"learning_rate": 7.568365643856721e-05, |
|
"loss": 1.3027, |
|
"step": 9730 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 7.555527025292078e-05, |
|
"loss": 1.3124, |
|
"step": 9740 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 7.542688406727436e-05, |
|
"loss": 1.2735, |
|
"step": 9750 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 7.529849788162794e-05, |
|
"loss": 1.3199, |
|
"step": 9760 |
|
}, |
|
{ |
|
"epoch": 3.13, |
|
"learning_rate": 7.517011169598151e-05, |
|
"loss": 1.3475, |
|
"step": 9770 |
|
}, |
|
{ |
|
"epoch": 3.13, |
|
"learning_rate": 7.504172551033509e-05, |
|
"loss": 1.3021, |
|
"step": 9780 |
|
}, |
|
{ |
|
"epoch": 3.13, |
|
"learning_rate": 7.491333932468867e-05, |
|
"loss": 1.2966, |
|
"step": 9790 |
|
}, |
|
{ |
|
"epoch": 3.14, |
|
"learning_rate": 7.478495313904224e-05, |
|
"loss": 1.2945, |
|
"step": 9800 |
|
}, |
|
{ |
|
"epoch": 3.14, |
|
"eval_loss": 2.908586263656616, |
|
"eval_runtime": 21.6554, |
|
"eval_samples_per_second": 11.314, |
|
"eval_steps_per_second": 2.863, |
|
"step": 9800 |
|
}, |
|
{ |
|
"epoch": 3.14, |
|
"learning_rate": 7.465656695339582e-05, |
|
"loss": 1.3383, |
|
"step": 9810 |
|
}, |
|
{ |
|
"epoch": 3.14, |
|
"learning_rate": 7.452818076774939e-05, |
|
"loss": 1.3487, |
|
"step": 9820 |
|
}, |
|
{ |
|
"epoch": 3.15, |
|
"learning_rate": 7.439979458210297e-05, |
|
"loss": 1.3326, |
|
"step": 9830 |
|
}, |
|
{ |
|
"epoch": 3.15, |
|
"learning_rate": 7.427140839645654e-05, |
|
"loss": 1.3064, |
|
"step": 9840 |
|
}, |
|
{ |
|
"epoch": 3.15, |
|
"learning_rate": 7.414302221081012e-05, |
|
"loss": 1.3458, |
|
"step": 9850 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 7.40146360251637e-05, |
|
"loss": 1.2609, |
|
"step": 9860 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 7.388624983951727e-05, |
|
"loss": 1.2891, |
|
"step": 9870 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 7.375786365387085e-05, |
|
"loss": 1.2677, |
|
"step": 9880 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 7.362947746822442e-05, |
|
"loss": 1.3163, |
|
"step": 9890 |
|
}, |
|
{ |
|
"epoch": 3.17, |
|
"learning_rate": 7.3501091282578e-05, |
|
"loss": 1.3273, |
|
"step": 9900 |
|
}, |
|
{ |
|
"epoch": 3.17, |
|
"learning_rate": 7.337270509693157e-05, |
|
"loss": 1.295, |
|
"step": 9910 |
|
}, |
|
{ |
|
"epoch": 3.17, |
|
"learning_rate": 7.324431891128515e-05, |
|
"loss": 1.3314, |
|
"step": 9920 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 7.311593272563873e-05, |
|
"loss": 1.3027, |
|
"step": 9930 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 7.29875465399923e-05, |
|
"loss": 1.3501, |
|
"step": 9940 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 7.285916035434588e-05, |
|
"loss": 1.3191, |
|
"step": 9950 |
|
}, |
|
{ |
|
"epoch": 3.19, |
|
"learning_rate": 7.273077416869946e-05, |
|
"loss": 1.3304, |
|
"step": 9960 |
|
}, |
|
{ |
|
"epoch": 3.19, |
|
"learning_rate": 7.260238798305303e-05, |
|
"loss": 1.3301, |
|
"step": 9970 |
|
}, |
|
{ |
|
"epoch": 3.19, |
|
"learning_rate": 7.24740017974066e-05, |
|
"loss": 1.2849, |
|
"step": 9980 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 7.234561561176018e-05, |
|
"loss": 1.3446, |
|
"step": 9990 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 7.221722942611376e-05, |
|
"loss": 1.2784, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"eval_loss": 2.9091832637786865, |
|
"eval_runtime": 19.1329, |
|
"eval_samples_per_second": 12.805, |
|
"eval_steps_per_second": 3.24, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 7.208884324046733e-05, |
|
"loss": 1.3146, |
|
"step": 10010 |
|
}, |
|
{ |
|
"epoch": 3.21, |
|
"learning_rate": 7.19604570548209e-05, |
|
"loss": 1.3419, |
|
"step": 10020 |
|
}, |
|
{ |
|
"epoch": 3.21, |
|
"learning_rate": 7.183207086917449e-05, |
|
"loss": 1.2744, |
|
"step": 10030 |
|
}, |
|
{ |
|
"epoch": 3.21, |
|
"learning_rate": 7.170368468352806e-05, |
|
"loss": 1.2712, |
|
"step": 10040 |
|
}, |
|
{ |
|
"epoch": 3.22, |
|
"learning_rate": 7.157529849788162e-05, |
|
"loss": 1.329, |
|
"step": 10050 |
|
}, |
|
{ |
|
"epoch": 3.22, |
|
"learning_rate": 7.14469123122352e-05, |
|
"loss": 1.3274, |
|
"step": 10060 |
|
}, |
|
{ |
|
"epoch": 3.22, |
|
"learning_rate": 7.131852612658879e-05, |
|
"loss": 1.2891, |
|
"step": 10070 |
|
}, |
|
{ |
|
"epoch": 3.23, |
|
"learning_rate": 7.119013994094235e-05, |
|
"loss": 1.3204, |
|
"step": 10080 |
|
}, |
|
{ |
|
"epoch": 3.23, |
|
"learning_rate": 7.106175375529593e-05, |
|
"loss": 1.3069, |
|
"step": 10090 |
|
}, |
|
{ |
|
"epoch": 3.23, |
|
"learning_rate": 7.093336756964952e-05, |
|
"loss": 1.2687, |
|
"step": 10100 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 7.080498138400308e-05, |
|
"loss": 1.3616, |
|
"step": 10110 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 7.067659519835666e-05, |
|
"loss": 1.3083, |
|
"step": 10120 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 7.054820901271023e-05, |
|
"loss": 1.2789, |
|
"step": 10130 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 7.041982282706381e-05, |
|
"loss": 1.2915, |
|
"step": 10140 |
|
}, |
|
{ |
|
"epoch": 3.25, |
|
"learning_rate": 7.029143664141738e-05, |
|
"loss": 1.3557, |
|
"step": 10150 |
|
}, |
|
{ |
|
"epoch": 3.25, |
|
"learning_rate": 7.016305045577096e-05, |
|
"loss": 1.3067, |
|
"step": 10160 |
|
}, |
|
{ |
|
"epoch": 3.25, |
|
"learning_rate": 7.003466427012454e-05, |
|
"loss": 1.3458, |
|
"step": 10170 |
|
}, |
|
{ |
|
"epoch": 3.26, |
|
"learning_rate": 6.990627808447811e-05, |
|
"loss": 1.35, |
|
"step": 10180 |
|
}, |
|
{ |
|
"epoch": 3.26, |
|
"learning_rate": 6.977789189883169e-05, |
|
"loss": 1.249, |
|
"step": 10190 |
|
}, |
|
{ |
|
"epoch": 3.26, |
|
"learning_rate": 6.964950571318526e-05, |
|
"loss": 1.3281, |
|
"step": 10200 |
|
}, |
|
{ |
|
"epoch": 3.26, |
|
"eval_loss": 2.900317430496216, |
|
"eval_runtime": 18.7618, |
|
"eval_samples_per_second": 13.058, |
|
"eval_steps_per_second": 3.305, |
|
"step": 10200 |
|
}, |
|
{ |
|
"epoch": 3.27, |
|
"learning_rate": 6.952111952753884e-05, |
|
"loss": 1.3082, |
|
"step": 10210 |
|
}, |
|
{ |
|
"epoch": 3.27, |
|
"learning_rate": 6.939273334189241e-05, |
|
"loss": 1.3152, |
|
"step": 10220 |
|
}, |
|
{ |
|
"epoch": 3.27, |
|
"learning_rate": 6.926434715624599e-05, |
|
"loss": 1.2966, |
|
"step": 10230 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 6.913596097059957e-05, |
|
"loss": 1.2834, |
|
"step": 10240 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 6.900757478495314e-05, |
|
"loss": 1.252, |
|
"step": 10250 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 6.887918859930672e-05, |
|
"loss": 1.3031, |
|
"step": 10260 |
|
}, |
|
{ |
|
"epoch": 3.29, |
|
"learning_rate": 6.87508024136603e-05, |
|
"loss": 1.3502, |
|
"step": 10270 |
|
}, |
|
{ |
|
"epoch": 3.29, |
|
"learning_rate": 6.862241622801387e-05, |
|
"loss": 1.2864, |
|
"step": 10280 |
|
}, |
|
{ |
|
"epoch": 3.29, |
|
"learning_rate": 6.849403004236744e-05, |
|
"loss": 1.2712, |
|
"step": 10290 |
|
}, |
|
{ |
|
"epoch": 3.3, |
|
"learning_rate": 6.836564385672102e-05, |
|
"loss": 1.3088, |
|
"step": 10300 |
|
}, |
|
{ |
|
"epoch": 3.3, |
|
"learning_rate": 6.82372576710746e-05, |
|
"loss": 1.3473, |
|
"step": 10310 |
|
}, |
|
{ |
|
"epoch": 3.3, |
|
"learning_rate": 6.810887148542817e-05, |
|
"loss": 1.2813, |
|
"step": 10320 |
|
}, |
|
{ |
|
"epoch": 3.31, |
|
"learning_rate": 6.798048529978175e-05, |
|
"loss": 1.2786, |
|
"step": 10330 |
|
}, |
|
{ |
|
"epoch": 3.31, |
|
"learning_rate": 6.785209911413533e-05, |
|
"loss": 1.2843, |
|
"step": 10340 |
|
}, |
|
{ |
|
"epoch": 3.31, |
|
"learning_rate": 6.77237129284889e-05, |
|
"loss": 1.3054, |
|
"step": 10350 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 6.759532674284246e-05, |
|
"loss": 1.3189, |
|
"step": 10360 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 6.746694055719605e-05, |
|
"loss": 1.3086, |
|
"step": 10370 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 6.733855437154963e-05, |
|
"loss": 1.3594, |
|
"step": 10380 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 6.72101681859032e-05, |
|
"loss": 1.293, |
|
"step": 10390 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"learning_rate": 6.708178200025678e-05, |
|
"loss": 1.37, |
|
"step": 10400 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"eval_loss": 2.882394313812256, |
|
"eval_runtime": 21.2636, |
|
"eval_samples_per_second": 11.522, |
|
"eval_steps_per_second": 2.916, |
|
"step": 10400 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"learning_rate": 6.695339581461036e-05, |
|
"loss": 1.3138, |
|
"step": 10410 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"learning_rate": 6.682500962896392e-05, |
|
"loss": 1.2954, |
|
"step": 10420 |
|
}, |
|
{ |
|
"epoch": 3.34, |
|
"learning_rate": 6.66966234433175e-05, |
|
"loss": 1.2855, |
|
"step": 10430 |
|
}, |
|
{ |
|
"epoch": 3.34, |
|
"learning_rate": 6.656823725767107e-05, |
|
"loss": 1.2926, |
|
"step": 10440 |
|
}, |
|
{ |
|
"epoch": 3.34, |
|
"learning_rate": 6.643985107202465e-05, |
|
"loss": 1.3426, |
|
"step": 10450 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"learning_rate": 6.631146488637822e-05, |
|
"loss": 1.3332, |
|
"step": 10460 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"learning_rate": 6.61830787007318e-05, |
|
"loss": 1.3252, |
|
"step": 10470 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"learning_rate": 6.605469251508538e-05, |
|
"loss": 1.3774, |
|
"step": 10480 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 6.592630632943895e-05, |
|
"loss": 1.2875, |
|
"step": 10490 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 6.579792014379253e-05, |
|
"loss": 1.3397, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 6.56695339581461e-05, |
|
"loss": 1.2861, |
|
"step": 10510 |
|
}, |
|
{ |
|
"epoch": 3.37, |
|
"learning_rate": 6.554114777249968e-05, |
|
"loss": 1.3011, |
|
"step": 10520 |
|
}, |
|
{ |
|
"epoch": 3.37, |
|
"learning_rate": 6.541276158685325e-05, |
|
"loss": 1.3151, |
|
"step": 10530 |
|
}, |
|
{ |
|
"epoch": 3.37, |
|
"learning_rate": 6.528437540120683e-05, |
|
"loss": 1.2988, |
|
"step": 10540 |
|
}, |
|
{ |
|
"epoch": 3.38, |
|
"learning_rate": 6.515598921556041e-05, |
|
"loss": 1.3183, |
|
"step": 10550 |
|
}, |
|
{ |
|
"epoch": 3.38, |
|
"learning_rate": 6.502760302991398e-05, |
|
"loss": 1.2912, |
|
"step": 10560 |
|
}, |
|
{ |
|
"epoch": 3.38, |
|
"learning_rate": 6.489921684426756e-05, |
|
"loss": 1.3569, |
|
"step": 10570 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"learning_rate": 6.477083065862114e-05, |
|
"loss": 1.3309, |
|
"step": 10580 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"learning_rate": 6.464244447297471e-05, |
|
"loss": 1.31, |
|
"step": 10590 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"learning_rate": 6.451405828732828e-05, |
|
"loss": 1.3624, |
|
"step": 10600 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"eval_loss": 2.867548704147339, |
|
"eval_runtime": 18.5659, |
|
"eval_samples_per_second": 13.196, |
|
"eval_steps_per_second": 3.339, |
|
"step": 10600 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 6.438567210168186e-05, |
|
"loss": 1.2427, |
|
"step": 10610 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 6.425728591603544e-05, |
|
"loss": 1.3263, |
|
"step": 10620 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 6.412889973038901e-05, |
|
"loss": 1.3423, |
|
"step": 10630 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 6.400051354474259e-05, |
|
"loss": 1.2818, |
|
"step": 10640 |
|
}, |
|
{ |
|
"epoch": 3.41, |
|
"learning_rate": 6.387212735909617e-05, |
|
"loss": 1.3123, |
|
"step": 10650 |
|
}, |
|
{ |
|
"epoch": 3.41, |
|
"learning_rate": 6.374374117344974e-05, |
|
"loss": 1.3706, |
|
"step": 10660 |
|
}, |
|
{ |
|
"epoch": 3.41, |
|
"learning_rate": 6.36153549878033e-05, |
|
"loss": 1.3805, |
|
"step": 10670 |
|
}, |
|
{ |
|
"epoch": 3.42, |
|
"learning_rate": 6.348696880215689e-05, |
|
"loss": 1.3253, |
|
"step": 10680 |
|
}, |
|
{ |
|
"epoch": 3.42, |
|
"learning_rate": 6.335858261651047e-05, |
|
"loss": 1.3191, |
|
"step": 10690 |
|
}, |
|
{ |
|
"epoch": 3.42, |
|
"learning_rate": 6.323019643086404e-05, |
|
"loss": 1.3424, |
|
"step": 10700 |
|
}, |
|
{ |
|
"epoch": 3.43, |
|
"learning_rate": 6.310181024521762e-05, |
|
"loss": 1.2761, |
|
"step": 10710 |
|
}, |
|
{ |
|
"epoch": 3.43, |
|
"learning_rate": 6.29734240595712e-05, |
|
"loss": 1.3341, |
|
"step": 10720 |
|
}, |
|
{ |
|
"epoch": 3.43, |
|
"learning_rate": 6.284503787392477e-05, |
|
"loss": 1.3413, |
|
"step": 10730 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 6.271665168827835e-05, |
|
"loss": 1.3187, |
|
"step": 10740 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 6.258826550263192e-05, |
|
"loss": 1.2959, |
|
"step": 10750 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 6.24598793169855e-05, |
|
"loss": 1.3233, |
|
"step": 10760 |
|
}, |
|
{ |
|
"epoch": 3.45, |
|
"learning_rate": 6.233149313133906e-05, |
|
"loss": 1.2996, |
|
"step": 10770 |
|
}, |
|
{ |
|
"epoch": 3.45, |
|
"learning_rate": 6.220310694569265e-05, |
|
"loss": 1.2983, |
|
"step": 10780 |
|
}, |
|
{ |
|
"epoch": 3.45, |
|
"learning_rate": 6.207472076004623e-05, |
|
"loss": 1.3227, |
|
"step": 10790 |
|
}, |
|
{ |
|
"epoch": 3.46, |
|
"learning_rate": 6.19463345743998e-05, |
|
"loss": 1.3342, |
|
"step": 10800 |
|
}, |
|
{ |
|
"epoch": 3.46, |
|
"eval_loss": 2.8953816890716553, |
|
"eval_runtime": 19.649, |
|
"eval_samples_per_second": 12.469, |
|
"eval_steps_per_second": 3.155, |
|
"step": 10800 |
|
}, |
|
{ |
|
"epoch": 3.46, |
|
"learning_rate": 6.181794838875338e-05, |
|
"loss": 1.3401, |
|
"step": 10810 |
|
}, |
|
{ |
|
"epoch": 3.46, |
|
"learning_rate": 6.168956220310694e-05, |
|
"loss": 1.2826, |
|
"step": 10820 |
|
}, |
|
{ |
|
"epoch": 3.47, |
|
"learning_rate": 6.156117601746052e-05, |
|
"loss": 1.3054, |
|
"step": 10830 |
|
}, |
|
{ |
|
"epoch": 3.47, |
|
"learning_rate": 6.143278983181409e-05, |
|
"loss": 1.2962, |
|
"step": 10840 |
|
}, |
|
{ |
|
"epoch": 3.47, |
|
"learning_rate": 6.130440364616767e-05, |
|
"loss": 1.3537, |
|
"step": 10850 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 6.117601746052125e-05, |
|
"loss": 1.3499, |
|
"step": 10860 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 6.104763127487482e-05, |
|
"loss": 1.3098, |
|
"step": 10870 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 6.09192450892284e-05, |
|
"loss": 1.317, |
|
"step": 10880 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 6.0790858903581984e-05, |
|
"loss": 1.3156, |
|
"step": 10890 |
|
}, |
|
{ |
|
"epoch": 3.49, |
|
"learning_rate": 6.0662472717935545e-05, |
|
"loss": 1.3326, |
|
"step": 10900 |
|
}, |
|
{ |
|
"epoch": 3.49, |
|
"learning_rate": 6.0534086532289126e-05, |
|
"loss": 1.3396, |
|
"step": 10910 |
|
}, |
|
{ |
|
"epoch": 3.49, |
|
"learning_rate": 6.04057003466427e-05, |
|
"loss": 1.3063, |
|
"step": 10920 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 6.027731416099628e-05, |
|
"loss": 1.3104, |
|
"step": 10930 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 6.0148927975349857e-05, |
|
"loss": 1.2979, |
|
"step": 10940 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 6.002054178970343e-05, |
|
"loss": 1.2832, |
|
"step": 10950 |
|
}, |
|
{ |
|
"epoch": 3.51, |
|
"learning_rate": 5.989215560405701e-05, |
|
"loss": 1.3144, |
|
"step": 10960 |
|
}, |
|
{ |
|
"epoch": 3.51, |
|
"learning_rate": 5.976376941841059e-05, |
|
"loss": 1.3328, |
|
"step": 10970 |
|
}, |
|
{ |
|
"epoch": 3.51, |
|
"learning_rate": 5.9635383232764154e-05, |
|
"loss": 1.3197, |
|
"step": 10980 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 5.950699704711773e-05, |
|
"loss": 1.2936, |
|
"step": 10990 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 5.937861086147131e-05, |
|
"loss": 1.3141, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"eval_loss": 2.8439722061157227, |
|
"eval_runtime": 18.9629, |
|
"eval_samples_per_second": 12.92, |
|
"eval_steps_per_second": 3.27, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 5.9250224675824884e-05, |
|
"loss": 1.3305, |
|
"step": 11010 |
|
}, |
|
{ |
|
"epoch": 3.53, |
|
"learning_rate": 5.912183849017846e-05, |
|
"loss": 1.3028, |
|
"step": 11020 |
|
}, |
|
{ |
|
"epoch": 3.53, |
|
"learning_rate": 5.899345230453204e-05, |
|
"loss": 1.2801, |
|
"step": 11030 |
|
}, |
|
{ |
|
"epoch": 3.53, |
|
"learning_rate": 5.8865066118885614e-05, |
|
"loss": 1.3237, |
|
"step": 11040 |
|
}, |
|
{ |
|
"epoch": 3.54, |
|
"learning_rate": 5.873667993323919e-05, |
|
"loss": 1.2736, |
|
"step": 11050 |
|
}, |
|
{ |
|
"epoch": 3.54, |
|
"learning_rate": 5.8608293747592757e-05, |
|
"loss": 1.3252, |
|
"step": 11060 |
|
}, |
|
{ |
|
"epoch": 3.54, |
|
"learning_rate": 5.847990756194633e-05, |
|
"loss": 1.3889, |
|
"step": 11070 |
|
}, |
|
{ |
|
"epoch": 3.55, |
|
"learning_rate": 5.835152137629991e-05, |
|
"loss": 1.3591, |
|
"step": 11080 |
|
}, |
|
{ |
|
"epoch": 3.55, |
|
"learning_rate": 5.822313519065349e-05, |
|
"loss": 1.3319, |
|
"step": 11090 |
|
}, |
|
{ |
|
"epoch": 3.55, |
|
"learning_rate": 5.809474900500707e-05, |
|
"loss": 1.3349, |
|
"step": 11100 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 5.796636281936064e-05, |
|
"loss": 1.2943, |
|
"step": 11110 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 5.783797663371422e-05, |
|
"loss": 1.2849, |
|
"step": 11120 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 5.7709590448067784e-05, |
|
"loss": 1.2418, |
|
"step": 11130 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 5.758120426242136e-05, |
|
"loss": 1.3197, |
|
"step": 11140 |
|
}, |
|
{ |
|
"epoch": 3.57, |
|
"learning_rate": 5.745281807677494e-05, |
|
"loss": 1.3252, |
|
"step": 11150 |
|
}, |
|
{ |
|
"epoch": 3.57, |
|
"learning_rate": 5.7324431891128515e-05, |
|
"loss": 1.3162, |
|
"step": 11160 |
|
}, |
|
{ |
|
"epoch": 3.57, |
|
"learning_rate": 5.7196045705482096e-05, |
|
"loss": 1.3396, |
|
"step": 11170 |
|
}, |
|
{ |
|
"epoch": 3.58, |
|
"learning_rate": 5.706765951983567e-05, |
|
"loss": 1.3389, |
|
"step": 11180 |
|
}, |
|
{ |
|
"epoch": 3.58, |
|
"learning_rate": 5.6939273334189245e-05, |
|
"loss": 1.2966, |
|
"step": 11190 |
|
}, |
|
{ |
|
"epoch": 3.58, |
|
"learning_rate": 5.6810887148542826e-05, |
|
"loss": 1.2682, |
|
"step": 11200 |
|
}, |
|
{ |
|
"epoch": 3.58, |
|
"eval_loss": 2.8363993167877197, |
|
"eval_runtime": 18.8266, |
|
"eval_samples_per_second": 13.014, |
|
"eval_steps_per_second": 3.293, |
|
"step": 11200 |
|
}, |
|
{ |
|
"epoch": 3.59, |
|
"learning_rate": 5.668250096289639e-05, |
|
"loss": 1.3595, |
|
"step": 11210 |
|
}, |
|
{ |
|
"epoch": 3.59, |
|
"learning_rate": 5.655411477724997e-05, |
|
"loss": 1.3125, |
|
"step": 11220 |
|
}, |
|
{ |
|
"epoch": 3.59, |
|
"learning_rate": 5.642572859160354e-05, |
|
"loss": 1.3331, |
|
"step": 11230 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 5.6297342405957124e-05, |
|
"loss": 1.3395, |
|
"step": 11240 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 5.61689562203107e-05, |
|
"loss": 1.3325, |
|
"step": 11250 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 5.604057003466427e-05, |
|
"loss": 1.2867, |
|
"step": 11260 |
|
}, |
|
{ |
|
"epoch": 3.61, |
|
"learning_rate": 5.5912183849017854e-05, |
|
"loss": 1.3693, |
|
"step": 11270 |
|
}, |
|
{ |
|
"epoch": 3.61, |
|
"learning_rate": 5.578379766337143e-05, |
|
"loss": 1.3203, |
|
"step": 11280 |
|
}, |
|
{ |
|
"epoch": 3.61, |
|
"learning_rate": 5.5655411477724996e-05, |
|
"loss": 1.2907, |
|
"step": 11290 |
|
}, |
|
{ |
|
"epoch": 3.62, |
|
"learning_rate": 5.552702529207857e-05, |
|
"loss": 1.3367, |
|
"step": 11300 |
|
}, |
|
{ |
|
"epoch": 3.62, |
|
"learning_rate": 5.539863910643215e-05, |
|
"loss": 1.3119, |
|
"step": 11310 |
|
}, |
|
{ |
|
"epoch": 3.62, |
|
"learning_rate": 5.5270252920785726e-05, |
|
"loss": 1.3461, |
|
"step": 11320 |
|
}, |
|
{ |
|
"epoch": 3.63, |
|
"learning_rate": 5.51418667351393e-05, |
|
"loss": 1.357, |
|
"step": 11330 |
|
}, |
|
{ |
|
"epoch": 3.63, |
|
"learning_rate": 5.501348054949288e-05, |
|
"loss": 1.2975, |
|
"step": 11340 |
|
}, |
|
{ |
|
"epoch": 3.63, |
|
"learning_rate": 5.4885094363846456e-05, |
|
"loss": 1.3471, |
|
"step": 11350 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 5.475670817820003e-05, |
|
"loss": 1.3502, |
|
"step": 11360 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 5.46283219925536e-05, |
|
"loss": 1.3625, |
|
"step": 11370 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 5.449993580690718e-05, |
|
"loss": 1.3376, |
|
"step": 11380 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 5.4371549621260754e-05, |
|
"loss": 1.2861, |
|
"step": 11390 |
|
}, |
|
{ |
|
"epoch": 3.65, |
|
"learning_rate": 5.424316343561433e-05, |
|
"loss": 1.3429, |
|
"step": 11400 |
|
}, |
|
{ |
|
"epoch": 3.65, |
|
"eval_loss": 2.8389124870300293, |
|
"eval_runtime": 18.7908, |
|
"eval_samples_per_second": 13.038, |
|
"eval_steps_per_second": 3.299, |
|
"step": 11400 |
|
}, |
|
{ |
|
"epoch": 3.65, |
|
"learning_rate": 5.411477724996791e-05, |
|
"loss": 1.3179, |
|
"step": 11410 |
|
}, |
|
{ |
|
"epoch": 3.65, |
|
"learning_rate": 5.3986391064321484e-05, |
|
"loss": 1.2985, |
|
"step": 11420 |
|
}, |
|
{ |
|
"epoch": 3.66, |
|
"learning_rate": 5.385800487867506e-05, |
|
"loss": 1.3498, |
|
"step": 11430 |
|
}, |
|
{ |
|
"epoch": 3.66, |
|
"learning_rate": 5.3729618693028626e-05, |
|
"loss": 1.3392, |
|
"step": 11440 |
|
}, |
|
{ |
|
"epoch": 3.66, |
|
"learning_rate": 5.360123250738221e-05, |
|
"loss": 1.3173, |
|
"step": 11450 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"learning_rate": 5.347284632173578e-05, |
|
"loss": 1.3435, |
|
"step": 11460 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"learning_rate": 5.3344460136089356e-05, |
|
"loss": 1.3364, |
|
"step": 11470 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"learning_rate": 5.321607395044294e-05, |
|
"loss": 1.3126, |
|
"step": 11480 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 5.308768776479651e-05, |
|
"loss": 1.3108, |
|
"step": 11490 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 5.2959301579150086e-05, |
|
"loss": 1.3552, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 5.283091539350367e-05, |
|
"loss": 1.3506, |
|
"step": 11510 |
|
}, |
|
{ |
|
"epoch": 3.69, |
|
"learning_rate": 5.2702529207857235e-05, |
|
"loss": 1.2901, |
|
"step": 11520 |
|
}, |
|
{ |
|
"epoch": 3.69, |
|
"learning_rate": 5.257414302221081e-05, |
|
"loss": 1.3161, |
|
"step": 11530 |
|
}, |
|
{ |
|
"epoch": 3.69, |
|
"learning_rate": 5.2445756836564384e-05, |
|
"loss": 1.3214, |
|
"step": 11540 |
|
}, |
|
{ |
|
"epoch": 3.7, |
|
"learning_rate": 5.2317370650917965e-05, |
|
"loss": 1.2752, |
|
"step": 11550 |
|
}, |
|
{ |
|
"epoch": 3.7, |
|
"learning_rate": 5.218898446527154e-05, |
|
"loss": 1.283, |
|
"step": 11560 |
|
}, |
|
{ |
|
"epoch": 3.7, |
|
"learning_rate": 5.2060598279625114e-05, |
|
"loss": 1.2814, |
|
"step": 11570 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 5.1932212093978695e-05, |
|
"loss": 1.3424, |
|
"step": 11580 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 5.180382590833227e-05, |
|
"loss": 1.3574, |
|
"step": 11590 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 5.167543972268584e-05, |
|
"loss": 1.3321, |
|
"step": 11600 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"eval_loss": 2.87870454788208, |
|
"eval_runtime": 18.5317, |
|
"eval_samples_per_second": 13.221, |
|
"eval_steps_per_second": 3.346, |
|
"step": 11600 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"learning_rate": 5.154705353703941e-05, |
|
"loss": 1.285, |
|
"step": 11610 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"learning_rate": 5.141866735139299e-05, |
|
"loss": 1.2646, |
|
"step": 11620 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"learning_rate": 5.129028116574657e-05, |
|
"loss": 1.2828, |
|
"step": 11630 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"learning_rate": 5.116189498010014e-05, |
|
"loss": 1.2474, |
|
"step": 11640 |
|
}, |
|
{ |
|
"epoch": 3.73, |
|
"learning_rate": 5.103350879445372e-05, |
|
"loss": 1.2835, |
|
"step": 11650 |
|
}, |
|
{ |
|
"epoch": 3.73, |
|
"learning_rate": 5.09051226088073e-05, |
|
"loss": 1.3228, |
|
"step": 11660 |
|
}, |
|
{ |
|
"epoch": 3.73, |
|
"learning_rate": 5.077673642316088e-05, |
|
"loss": 1.2964, |
|
"step": 11670 |
|
}, |
|
{ |
|
"epoch": 3.74, |
|
"learning_rate": 5.064835023751444e-05, |
|
"loss": 1.2865, |
|
"step": 11680 |
|
}, |
|
{ |
|
"epoch": 3.74, |
|
"learning_rate": 5.051996405186802e-05, |
|
"loss": 1.3758, |
|
"step": 11690 |
|
}, |
|
{ |
|
"epoch": 3.74, |
|
"learning_rate": 5.0391577866221595e-05, |
|
"loss": 1.2731, |
|
"step": 11700 |
|
}, |
|
{ |
|
"epoch": 3.75, |
|
"learning_rate": 5.026319168057517e-05, |
|
"loss": 1.2935, |
|
"step": 11710 |
|
}, |
|
{ |
|
"epoch": 3.75, |
|
"learning_rate": 5.013480549492875e-05, |
|
"loss": 1.2774, |
|
"step": 11720 |
|
}, |
|
{ |
|
"epoch": 3.75, |
|
"learning_rate": 5.0006419309282325e-05, |
|
"loss": 1.3293, |
|
"step": 11730 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 4.98780331236359e-05, |
|
"loss": 1.3058, |
|
"step": 11740 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 4.9749646937989474e-05, |
|
"loss": 1.3071, |
|
"step": 11750 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 4.962126075234305e-05, |
|
"loss": 1.3527, |
|
"step": 11760 |
|
}, |
|
{ |
|
"epoch": 3.77, |
|
"learning_rate": 4.949287456669662e-05, |
|
"loss": 1.2699, |
|
"step": 11770 |
|
}, |
|
{ |
|
"epoch": 3.77, |
|
"learning_rate": 4.93644883810502e-05, |
|
"loss": 1.3338, |
|
"step": 11780 |
|
}, |
|
{ |
|
"epoch": 3.77, |
|
"learning_rate": 4.923610219540378e-05, |
|
"loss": 1.2862, |
|
"step": 11790 |
|
}, |
|
{ |
|
"epoch": 3.78, |
|
"learning_rate": 4.910771600975735e-05, |
|
"loss": 1.3376, |
|
"step": 11800 |
|
}, |
|
{ |
|
"epoch": 3.78, |
|
"eval_loss": 2.83416748046875, |
|
"eval_runtime": 18.9268, |
|
"eval_samples_per_second": 12.945, |
|
"eval_steps_per_second": 3.276, |
|
"step": 11800 |
|
}, |
|
{ |
|
"epoch": 3.78, |
|
"learning_rate": 4.897932982411093e-05, |
|
"loss": 1.2812, |
|
"step": 11810 |
|
}, |
|
{ |
|
"epoch": 3.78, |
|
"learning_rate": 4.88509436384645e-05, |
|
"loss": 1.2754, |
|
"step": 11820 |
|
}, |
|
{ |
|
"epoch": 3.79, |
|
"learning_rate": 4.8722557452818077e-05, |
|
"loss": 1.3151, |
|
"step": 11830 |
|
}, |
|
{ |
|
"epoch": 3.79, |
|
"learning_rate": 4.859417126717166e-05, |
|
"loss": 1.3505, |
|
"step": 11840 |
|
}, |
|
{ |
|
"epoch": 3.79, |
|
"learning_rate": 4.8465785081525225e-05, |
|
"loss": 1.3378, |
|
"step": 11850 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 4.833739889587881e-05, |
|
"loss": 1.3392, |
|
"step": 11860 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 4.820901271023238e-05, |
|
"loss": 1.3284, |
|
"step": 11870 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 4.8080626524585956e-05, |
|
"loss": 1.2991, |
|
"step": 11880 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 4.795224033893953e-05, |
|
"loss": 1.2661, |
|
"step": 11890 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 4.7823854153293104e-05, |
|
"loss": 1.3254, |
|
"step": 11900 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 4.7695467967646686e-05, |
|
"loss": 1.3288, |
|
"step": 11910 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 4.756708178200026e-05, |
|
"loss": 1.3429, |
|
"step": 11920 |
|
}, |
|
{ |
|
"epoch": 3.82, |
|
"learning_rate": 4.7438695596353834e-05, |
|
"loss": 1.2864, |
|
"step": 11930 |
|
}, |
|
{ |
|
"epoch": 3.82, |
|
"learning_rate": 4.731030941070741e-05, |
|
"loss": 1.344, |
|
"step": 11940 |
|
}, |
|
{ |
|
"epoch": 3.82, |
|
"learning_rate": 4.718192322506098e-05, |
|
"loss": 1.3097, |
|
"step": 11950 |
|
}, |
|
{ |
|
"epoch": 3.83, |
|
"learning_rate": 4.7053537039414565e-05, |
|
"loss": 1.2976, |
|
"step": 11960 |
|
}, |
|
{ |
|
"epoch": 3.83, |
|
"learning_rate": 4.692515085376813e-05, |
|
"loss": 1.3466, |
|
"step": 11970 |
|
}, |
|
{ |
|
"epoch": 3.83, |
|
"learning_rate": 4.6796764668121713e-05, |
|
"loss": 1.3243, |
|
"step": 11980 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"learning_rate": 4.666837848247529e-05, |
|
"loss": 1.3558, |
|
"step": 11990 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"learning_rate": 4.653999229682887e-05, |
|
"loss": 1.323, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"eval_loss": 2.860560417175293, |
|
"eval_runtime": 20.552, |
|
"eval_samples_per_second": 11.921, |
|
"eval_steps_per_second": 3.017, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"learning_rate": 4.641160611118244e-05, |
|
"loss": 1.3103, |
|
"step": 12010 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 4.628321992553601e-05, |
|
"loss": 1.3065, |
|
"step": 12020 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 4.615483373988959e-05, |
|
"loss": 1.3307, |
|
"step": 12030 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 4.602644755424317e-05, |
|
"loss": 1.2767, |
|
"step": 12040 |
|
}, |
|
{ |
|
"epoch": 3.86, |
|
"learning_rate": 4.589806136859674e-05, |
|
"loss": 1.302, |
|
"step": 12050 |
|
}, |
|
{ |
|
"epoch": 3.86, |
|
"learning_rate": 4.5769675182950316e-05, |
|
"loss": 1.2922, |
|
"step": 12060 |
|
}, |
|
{ |
|
"epoch": 3.86, |
|
"learning_rate": 4.56412889973039e-05, |
|
"loss": 1.2721, |
|
"step": 12070 |
|
}, |
|
{ |
|
"epoch": 3.87, |
|
"learning_rate": 4.5512902811657465e-05, |
|
"loss": 1.2948, |
|
"step": 12080 |
|
}, |
|
{ |
|
"epoch": 3.87, |
|
"learning_rate": 4.538451662601104e-05, |
|
"loss": 1.3105, |
|
"step": 12090 |
|
}, |
|
{ |
|
"epoch": 3.87, |
|
"learning_rate": 4.525613044036462e-05, |
|
"loss": 1.3264, |
|
"step": 12100 |
|
}, |
|
{ |
|
"epoch": 3.88, |
|
"learning_rate": 4.5127744254718195e-05, |
|
"loss": 1.3475, |
|
"step": 12110 |
|
}, |
|
{ |
|
"epoch": 3.88, |
|
"learning_rate": 4.499935806907177e-05, |
|
"loss": 1.263, |
|
"step": 12120 |
|
}, |
|
{ |
|
"epoch": 3.88, |
|
"learning_rate": 4.4870971883425344e-05, |
|
"loss": 1.223, |
|
"step": 12130 |
|
}, |
|
{ |
|
"epoch": 3.88, |
|
"learning_rate": 4.4742585697778925e-05, |
|
"loss": 1.3058, |
|
"step": 12140 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 4.46141995121325e-05, |
|
"loss": 1.2798, |
|
"step": 12150 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 4.448581332648607e-05, |
|
"loss": 1.3021, |
|
"step": 12160 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 4.435742714083965e-05, |
|
"loss": 1.3255, |
|
"step": 12170 |
|
}, |
|
{ |
|
"epoch": 3.9, |
|
"learning_rate": 4.422904095519322e-05, |
|
"loss": 1.298, |
|
"step": 12180 |
|
}, |
|
{ |
|
"epoch": 3.9, |
|
"learning_rate": 4.4100654769546804e-05, |
|
"loss": 1.3036, |
|
"step": 12190 |
|
}, |
|
{ |
|
"epoch": 3.9, |
|
"learning_rate": 4.397226858390037e-05, |
|
"loss": 1.313, |
|
"step": 12200 |
|
}, |
|
{ |
|
"epoch": 3.9, |
|
"eval_loss": 2.8852741718292236, |
|
"eval_runtime": 18.9773, |
|
"eval_samples_per_second": 12.91, |
|
"eval_steps_per_second": 3.267, |
|
"step": 12200 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 4.3843882398253946e-05, |
|
"loss": 1.2639, |
|
"step": 12210 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 4.371549621260753e-05, |
|
"loss": 1.3247, |
|
"step": 12220 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 4.35871100269611e-05, |
|
"loss": 1.2936, |
|
"step": 12230 |
|
}, |
|
{ |
|
"epoch": 3.92, |
|
"learning_rate": 4.3458723841314676e-05, |
|
"loss": 1.3149, |
|
"step": 12240 |
|
}, |
|
{ |
|
"epoch": 3.92, |
|
"learning_rate": 4.333033765566825e-05, |
|
"loss": 1.2739, |
|
"step": 12250 |
|
}, |
|
{ |
|
"epoch": 3.92, |
|
"learning_rate": 4.320195147002183e-05, |
|
"loss": 1.3176, |
|
"step": 12260 |
|
}, |
|
{ |
|
"epoch": 3.93, |
|
"learning_rate": 4.3073565284375406e-05, |
|
"loss": 1.3224, |
|
"step": 12270 |
|
}, |
|
{ |
|
"epoch": 3.93, |
|
"learning_rate": 4.2945179098728974e-05, |
|
"loss": 1.2981, |
|
"step": 12280 |
|
}, |
|
{ |
|
"epoch": 3.93, |
|
"learning_rate": 4.2816792913082555e-05, |
|
"loss": 1.2808, |
|
"step": 12290 |
|
}, |
|
{ |
|
"epoch": 3.94, |
|
"learning_rate": 4.268840672743613e-05, |
|
"loss": 1.365, |
|
"step": 12300 |
|
}, |
|
{ |
|
"epoch": 3.94, |
|
"learning_rate": 4.256002054178971e-05, |
|
"loss": 1.2944, |
|
"step": 12310 |
|
}, |
|
{ |
|
"epoch": 3.94, |
|
"learning_rate": 4.243163435614328e-05, |
|
"loss": 1.2929, |
|
"step": 12320 |
|
}, |
|
{ |
|
"epoch": 3.95, |
|
"learning_rate": 4.230324817049686e-05, |
|
"loss": 1.2694, |
|
"step": 12330 |
|
}, |
|
{ |
|
"epoch": 3.95, |
|
"learning_rate": 4.2174861984850434e-05, |
|
"loss": 1.2925, |
|
"step": 12340 |
|
}, |
|
{ |
|
"epoch": 3.95, |
|
"learning_rate": 4.204647579920401e-05, |
|
"loss": 1.3186, |
|
"step": 12350 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 4.191808961355758e-05, |
|
"loss": 1.3315, |
|
"step": 12360 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 4.178970342791116e-05, |
|
"loss": 1.2653, |
|
"step": 12370 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 4.166131724226474e-05, |
|
"loss": 1.2869, |
|
"step": 12380 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 4.1532931056618306e-05, |
|
"loss": 1.3109, |
|
"step": 12390 |
|
}, |
|
{ |
|
"epoch": 3.97, |
|
"learning_rate": 4.140454487097189e-05, |
|
"loss": 1.3118, |
|
"step": 12400 |
|
}, |
|
{ |
|
"epoch": 3.97, |
|
"eval_loss": 2.8200929164886475, |
|
"eval_runtime": 20.3527, |
|
"eval_samples_per_second": 12.038, |
|
"eval_steps_per_second": 3.046, |
|
"step": 12400 |
|
}, |
|
{ |
|
"epoch": 3.97, |
|
"learning_rate": 4.127615868532546e-05, |
|
"loss": 1.3498, |
|
"step": 12410 |
|
}, |
|
{ |
|
"epoch": 3.97, |
|
"learning_rate": 4.1147772499679036e-05, |
|
"loss": 1.3476, |
|
"step": 12420 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 4.101938631403261e-05, |
|
"loss": 1.3672, |
|
"step": 12430 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 4.0891000128386185e-05, |
|
"loss": 1.2693, |
|
"step": 12440 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 4.0762613942739766e-05, |
|
"loss": 1.3115, |
|
"step": 12450 |
|
}, |
|
{ |
|
"epoch": 3.99, |
|
"learning_rate": 4.063422775709334e-05, |
|
"loss": 1.2866, |
|
"step": 12460 |
|
}, |
|
{ |
|
"epoch": 3.99, |
|
"learning_rate": 4.0505841571446915e-05, |
|
"loss": 1.2638, |
|
"step": 12470 |
|
}, |
|
{ |
|
"epoch": 3.99, |
|
"learning_rate": 4.037745538580049e-05, |
|
"loss": 1.3217, |
|
"step": 12480 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 4.0249069200154064e-05, |
|
"loss": 1.3078, |
|
"step": 12490 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 4.0120683014507645e-05, |
|
"loss": 1.2922, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 3.999229682886121e-05, |
|
"loss": 1.3052, |
|
"step": 12510 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 3.9863910643214794e-05, |
|
"loss": 1.2415, |
|
"step": 12520 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 3.973552445756837e-05, |
|
"loss": 1.3334, |
|
"step": 12530 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 3.960713827192194e-05, |
|
"loss": 1.2991, |
|
"step": 12540 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"learning_rate": 3.947875208627552e-05, |
|
"loss": 1.2874, |
|
"step": 12550 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"learning_rate": 3.935036590062909e-05, |
|
"loss": 1.2998, |
|
"step": 12560 |
|
}, |
|
{ |
|
"epoch": 4.02, |
|
"learning_rate": 3.922197971498267e-05, |
|
"loss": 1.2986, |
|
"step": 12570 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 3.909359352933625e-05, |
|
"loss": 1.2701, |
|
"step": 12580 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 3.896520734368982e-05, |
|
"loss": 1.3572, |
|
"step": 12590 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 3.8836821158043397e-05, |
|
"loss": 1.3413, |
|
"step": 12600 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"eval_loss": 2.804445743560791, |
|
"eval_runtime": 18.2216, |
|
"eval_samples_per_second": 13.446, |
|
"eval_steps_per_second": 3.403, |
|
"step": 12600 |
|
}, |
|
{ |
|
"epoch": 4.04, |
|
"learning_rate": 3.870843497239697e-05, |
|
"loss": 1.2774, |
|
"step": 12610 |
|
}, |
|
{ |
|
"epoch": 4.04, |
|
"learning_rate": 3.858004878675055e-05, |
|
"loss": 1.3689, |
|
"step": 12620 |
|
}, |
|
{ |
|
"epoch": 4.04, |
|
"learning_rate": 3.845166260110412e-05, |
|
"loss": 1.2887, |
|
"step": 12630 |
|
}, |
|
{ |
|
"epoch": 4.04, |
|
"learning_rate": 3.83232764154577e-05, |
|
"loss": 1.3541, |
|
"step": 12640 |
|
}, |
|
{ |
|
"epoch": 4.05, |
|
"learning_rate": 3.8194890229811275e-05, |
|
"loss": 1.3393, |
|
"step": 12650 |
|
}, |
|
{ |
|
"epoch": 4.05, |
|
"learning_rate": 3.806650404416485e-05, |
|
"loss": 1.2939, |
|
"step": 12660 |
|
}, |
|
{ |
|
"epoch": 4.05, |
|
"learning_rate": 3.7938117858518424e-05, |
|
"loss": 1.3126, |
|
"step": 12670 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 3.7809731672872e-05, |
|
"loss": 1.3473, |
|
"step": 12680 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 3.768134548722558e-05, |
|
"loss": 1.263, |
|
"step": 12690 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 3.755295930157915e-05, |
|
"loss": 1.2946, |
|
"step": 12700 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 3.742457311593273e-05, |
|
"loss": 1.3479, |
|
"step": 12710 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 3.72961869302863e-05, |
|
"loss": 1.2681, |
|
"step": 12720 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 3.716780074463988e-05, |
|
"loss": 1.3546, |
|
"step": 12730 |
|
}, |
|
{ |
|
"epoch": 4.08, |
|
"learning_rate": 3.703941455899345e-05, |
|
"loss": 1.2858, |
|
"step": 12740 |
|
}, |
|
{ |
|
"epoch": 4.08, |
|
"learning_rate": 3.691102837334703e-05, |
|
"loss": 1.2936, |
|
"step": 12750 |
|
}, |
|
{ |
|
"epoch": 4.08, |
|
"learning_rate": 3.678264218770061e-05, |
|
"loss": 1.2651, |
|
"step": 12760 |
|
}, |
|
{ |
|
"epoch": 4.09, |
|
"learning_rate": 3.665425600205418e-05, |
|
"loss": 1.2997, |
|
"step": 12770 |
|
}, |
|
{ |
|
"epoch": 4.09, |
|
"learning_rate": 3.652586981640776e-05, |
|
"loss": 1.3142, |
|
"step": 12780 |
|
}, |
|
{ |
|
"epoch": 4.09, |
|
"learning_rate": 3.639748363076133e-05, |
|
"loss": 1.3195, |
|
"step": 12790 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 3.6269097445114906e-05, |
|
"loss": 1.326, |
|
"step": 12800 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"eval_loss": 2.809899091720581, |
|
"eval_runtime": 18.2967, |
|
"eval_samples_per_second": 13.39, |
|
"eval_steps_per_second": 3.389, |
|
"step": 12800 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 3.614071125946849e-05, |
|
"loss": 1.2853, |
|
"step": 12810 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 3.6012325073822055e-05, |
|
"loss": 1.3272, |
|
"step": 12820 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 3.5883938888175636e-05, |
|
"loss": 1.322, |
|
"step": 12830 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 3.575555270252921e-05, |
|
"loss": 1.3367, |
|
"step": 12840 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 3.5627166516882785e-05, |
|
"loss": 1.3345, |
|
"step": 12850 |
|
}, |
|
{ |
|
"epoch": 4.12, |
|
"learning_rate": 3.549878033123636e-05, |
|
"loss": 1.2767, |
|
"step": 12860 |
|
}, |
|
{ |
|
"epoch": 4.12, |
|
"learning_rate": 3.5370394145589933e-05, |
|
"loss": 1.3082, |
|
"step": 12870 |
|
}, |
|
{ |
|
"epoch": 4.12, |
|
"learning_rate": 3.5242007959943515e-05, |
|
"loss": 1.2771, |
|
"step": 12880 |
|
}, |
|
{ |
|
"epoch": 4.12, |
|
"learning_rate": 3.511362177429709e-05, |
|
"loss": 1.3112, |
|
"step": 12890 |
|
}, |
|
{ |
|
"epoch": 4.13, |
|
"learning_rate": 3.4985235588650664e-05, |
|
"loss": 1.2905, |
|
"step": 12900 |
|
}, |
|
{ |
|
"epoch": 4.13, |
|
"learning_rate": 3.485684940300424e-05, |
|
"loss": 1.3086, |
|
"step": 12910 |
|
}, |
|
{ |
|
"epoch": 4.13, |
|
"learning_rate": 3.472846321735781e-05, |
|
"loss": 1.3241, |
|
"step": 12920 |
|
}, |
|
{ |
|
"epoch": 4.14, |
|
"learning_rate": 3.4600077031711394e-05, |
|
"loss": 1.2797, |
|
"step": 12930 |
|
}, |
|
{ |
|
"epoch": 4.14, |
|
"learning_rate": 3.447169084606496e-05, |
|
"loss": 1.314, |
|
"step": 12940 |
|
}, |
|
{ |
|
"epoch": 4.14, |
|
"learning_rate": 3.434330466041854e-05, |
|
"loss": 1.288, |
|
"step": 12950 |
|
}, |
|
{ |
|
"epoch": 4.15, |
|
"learning_rate": 3.421491847477212e-05, |
|
"loss": 1.3242, |
|
"step": 12960 |
|
}, |
|
{ |
|
"epoch": 4.15, |
|
"learning_rate": 3.408653228912569e-05, |
|
"loss": 1.3337, |
|
"step": 12970 |
|
}, |
|
{ |
|
"epoch": 4.15, |
|
"learning_rate": 3.3958146103479266e-05, |
|
"loss": 1.301, |
|
"step": 12980 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 3.382975991783284e-05, |
|
"loss": 1.3097, |
|
"step": 12990 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 3.370137373218642e-05, |
|
"loss": 1.3231, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"eval_loss": 2.8279800415039062, |
|
"eval_runtime": 18.618, |
|
"eval_samples_per_second": 13.159, |
|
"eval_steps_per_second": 3.33, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 3.357298754653999e-05, |
|
"loss": 1.3095, |
|
"step": 13010 |
|
}, |
|
{ |
|
"epoch": 4.17, |
|
"learning_rate": 3.344460136089357e-05, |
|
"loss": 1.2812, |
|
"step": 13020 |
|
}, |
|
{ |
|
"epoch": 4.17, |
|
"learning_rate": 3.3316215175247145e-05, |
|
"loss": 1.3446, |
|
"step": 13030 |
|
}, |
|
{ |
|
"epoch": 4.17, |
|
"learning_rate": 3.318782898960072e-05, |
|
"loss": 1.3248, |
|
"step": 13040 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"learning_rate": 3.3059442803954294e-05, |
|
"loss": 1.2818, |
|
"step": 13050 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"learning_rate": 3.293105661830787e-05, |
|
"loss": 1.3438, |
|
"step": 13060 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"learning_rate": 3.280267043266145e-05, |
|
"loss": 1.2774, |
|
"step": 13070 |
|
}, |
|
{ |
|
"epoch": 4.19, |
|
"learning_rate": 3.2674284247015024e-05, |
|
"loss": 1.3032, |
|
"step": 13080 |
|
}, |
|
{ |
|
"epoch": 4.19, |
|
"learning_rate": 3.25458980613686e-05, |
|
"loss": 1.3166, |
|
"step": 13090 |
|
}, |
|
{ |
|
"epoch": 4.19, |
|
"learning_rate": 3.241751187572217e-05, |
|
"loss": 1.283, |
|
"step": 13100 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 3.228912569007575e-05, |
|
"loss": 1.2912, |
|
"step": 13110 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 3.216073950442933e-05, |
|
"loss": 1.3202, |
|
"step": 13120 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 3.2032353318782896e-05, |
|
"loss": 1.2662, |
|
"step": 13130 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 3.190396713313648e-05, |
|
"loss": 1.3472, |
|
"step": 13140 |
|
}, |
|
{ |
|
"epoch": 4.21, |
|
"learning_rate": 3.177558094749005e-05, |
|
"loss": 1.2994, |
|
"step": 13150 |
|
}, |
|
{ |
|
"epoch": 4.21, |
|
"learning_rate": 3.1647194761843626e-05, |
|
"loss": 1.3269, |
|
"step": 13160 |
|
}, |
|
{ |
|
"epoch": 4.21, |
|
"learning_rate": 3.15188085761972e-05, |
|
"loss": 1.3077, |
|
"step": 13170 |
|
}, |
|
{ |
|
"epoch": 4.22, |
|
"learning_rate": 3.1390422390550775e-05, |
|
"loss": 1.3272, |
|
"step": 13180 |
|
}, |
|
{ |
|
"epoch": 4.22, |
|
"learning_rate": 3.1262036204904356e-05, |
|
"loss": 1.2886, |
|
"step": 13190 |
|
}, |
|
{ |
|
"epoch": 4.22, |
|
"learning_rate": 3.113365001925793e-05, |
|
"loss": 1.3483, |
|
"step": 13200 |
|
}, |
|
{ |
|
"epoch": 4.22, |
|
"eval_loss": 2.8313188552856445, |
|
"eval_runtime": 19.0512, |
|
"eval_samples_per_second": 12.86, |
|
"eval_steps_per_second": 3.254, |
|
"step": 13200 |
|
}, |
|
{ |
|
"epoch": 4.23, |
|
"learning_rate": 3.1005263833611505e-05, |
|
"loss": 1.2993, |
|
"step": 13210 |
|
}, |
|
{ |
|
"epoch": 4.23, |
|
"learning_rate": 3.087687764796508e-05, |
|
"loss": 1.3328, |
|
"step": 13220 |
|
}, |
|
{ |
|
"epoch": 4.23, |
|
"learning_rate": 3.0748491462318654e-05, |
|
"loss": 1.287, |
|
"step": 13230 |
|
}, |
|
{ |
|
"epoch": 4.24, |
|
"learning_rate": 3.0620105276672235e-05, |
|
"loss": 1.3159, |
|
"step": 13240 |
|
}, |
|
{ |
|
"epoch": 4.24, |
|
"learning_rate": 3.0491719091025806e-05, |
|
"loss": 1.2865, |
|
"step": 13250 |
|
}, |
|
{ |
|
"epoch": 4.24, |
|
"learning_rate": 3.0363332905379384e-05, |
|
"loss": 1.315, |
|
"step": 13260 |
|
}, |
|
{ |
|
"epoch": 4.25, |
|
"learning_rate": 3.023494671973296e-05, |
|
"loss": 1.3756, |
|
"step": 13270 |
|
}, |
|
{ |
|
"epoch": 4.25, |
|
"learning_rate": 3.0106560534086536e-05, |
|
"loss": 1.2587, |
|
"step": 13280 |
|
}, |
|
{ |
|
"epoch": 4.25, |
|
"learning_rate": 2.9978174348440107e-05, |
|
"loss": 1.3396, |
|
"step": 13290 |
|
}, |
|
{ |
|
"epoch": 4.26, |
|
"learning_rate": 2.9849788162793685e-05, |
|
"loss": 1.2969, |
|
"step": 13300 |
|
}, |
|
{ |
|
"epoch": 4.26, |
|
"learning_rate": 2.9721401977147263e-05, |
|
"loss": 1.2825, |
|
"step": 13310 |
|
}, |
|
{ |
|
"epoch": 4.26, |
|
"learning_rate": 2.9593015791500834e-05, |
|
"loss": 1.2873, |
|
"step": 13320 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 2.946462960585441e-05, |
|
"loss": 1.3161, |
|
"step": 13330 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 2.9336243420207986e-05, |
|
"loss": 1.3063, |
|
"step": 13340 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 2.9207857234561564e-05, |
|
"loss": 1.2876, |
|
"step": 13350 |
|
}, |
|
{ |
|
"epoch": 4.28, |
|
"learning_rate": 2.9079471048915135e-05, |
|
"loss": 1.2855, |
|
"step": 13360 |
|
}, |
|
{ |
|
"epoch": 4.28, |
|
"learning_rate": 2.8951084863268713e-05, |
|
"loss": 1.2826, |
|
"step": 13370 |
|
}, |
|
{ |
|
"epoch": 4.28, |
|
"learning_rate": 2.882269867762229e-05, |
|
"loss": 1.3686, |
|
"step": 13380 |
|
}, |
|
{ |
|
"epoch": 4.28, |
|
"learning_rate": 2.8694312491975865e-05, |
|
"loss": 1.3276, |
|
"step": 13390 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"learning_rate": 2.8565926306329436e-05, |
|
"loss": 1.3024, |
|
"step": 13400 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"eval_loss": 2.886902332305908, |
|
"eval_runtime": 19.1942, |
|
"eval_samples_per_second": 12.764, |
|
"eval_steps_per_second": 3.23, |
|
"step": 13400 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"learning_rate": 2.8437540120683014e-05, |
|
"loss": 1.3332, |
|
"step": 13410 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"learning_rate": 2.8309153935036592e-05, |
|
"loss": 1.2835, |
|
"step": 13420 |
|
}, |
|
{ |
|
"epoch": 4.3, |
|
"learning_rate": 2.818076774939017e-05, |
|
"loss": 1.3267, |
|
"step": 13430 |
|
}, |
|
{ |
|
"epoch": 4.3, |
|
"learning_rate": 2.805238156374374e-05, |
|
"loss": 1.2836, |
|
"step": 13440 |
|
}, |
|
{ |
|
"epoch": 4.3, |
|
"learning_rate": 2.792399537809732e-05, |
|
"loss": 1.3308, |
|
"step": 13450 |
|
}, |
|
{ |
|
"epoch": 4.31, |
|
"learning_rate": 2.7795609192450893e-05, |
|
"loss": 1.3019, |
|
"step": 13460 |
|
}, |
|
{ |
|
"epoch": 4.31, |
|
"learning_rate": 2.766722300680447e-05, |
|
"loss": 1.3229, |
|
"step": 13470 |
|
}, |
|
{ |
|
"epoch": 4.31, |
|
"learning_rate": 2.7538836821158042e-05, |
|
"loss": 1.2779, |
|
"step": 13480 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"learning_rate": 2.741045063551162e-05, |
|
"loss": 1.2808, |
|
"step": 13490 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"learning_rate": 2.7282064449865198e-05, |
|
"loss": 1.338, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"learning_rate": 2.7153678264218772e-05, |
|
"loss": 1.2423, |
|
"step": 13510 |
|
}, |
|
{ |
|
"epoch": 4.33, |
|
"learning_rate": 2.7025292078572347e-05, |
|
"loss": 1.2724, |
|
"step": 13520 |
|
}, |
|
{ |
|
"epoch": 4.33, |
|
"learning_rate": 2.689690589292592e-05, |
|
"loss": 1.2834, |
|
"step": 13530 |
|
}, |
|
{ |
|
"epoch": 4.33, |
|
"learning_rate": 2.67685197072795e-05, |
|
"loss": 1.2745, |
|
"step": 13540 |
|
}, |
|
{ |
|
"epoch": 4.34, |
|
"learning_rate": 2.6640133521633077e-05, |
|
"loss": 1.3837, |
|
"step": 13550 |
|
}, |
|
{ |
|
"epoch": 4.34, |
|
"learning_rate": 2.6511747335986648e-05, |
|
"loss": 1.3006, |
|
"step": 13560 |
|
}, |
|
{ |
|
"epoch": 4.34, |
|
"learning_rate": 2.6383361150340226e-05, |
|
"loss": 1.3066, |
|
"step": 13570 |
|
}, |
|
{ |
|
"epoch": 4.35, |
|
"learning_rate": 2.62549749646938e-05, |
|
"loss": 1.3148, |
|
"step": 13580 |
|
}, |
|
{ |
|
"epoch": 4.35, |
|
"learning_rate": 2.6126588779047378e-05, |
|
"loss": 1.3003, |
|
"step": 13590 |
|
}, |
|
{ |
|
"epoch": 4.35, |
|
"learning_rate": 2.599820259340095e-05, |
|
"loss": 1.3606, |
|
"step": 13600 |
|
}, |
|
{ |
|
"epoch": 4.35, |
|
"eval_loss": 2.804246664047241, |
|
"eval_runtime": 18.3649, |
|
"eval_samples_per_second": 13.341, |
|
"eval_steps_per_second": 3.376, |
|
"step": 13600 |
|
}, |
|
{ |
|
"epoch": 4.36, |
|
"learning_rate": 2.5869816407754527e-05, |
|
"loss": 1.2876, |
|
"step": 13610 |
|
}, |
|
{ |
|
"epoch": 4.36, |
|
"learning_rate": 2.5741430222108105e-05, |
|
"loss": 1.2714, |
|
"step": 13620 |
|
}, |
|
{ |
|
"epoch": 4.36, |
|
"learning_rate": 2.5613044036461676e-05, |
|
"loss": 1.305, |
|
"step": 13630 |
|
}, |
|
{ |
|
"epoch": 4.36, |
|
"learning_rate": 2.5484657850815253e-05, |
|
"loss": 1.3137, |
|
"step": 13640 |
|
}, |
|
{ |
|
"epoch": 4.37, |
|
"learning_rate": 2.5356271665168828e-05, |
|
"loss": 1.303, |
|
"step": 13650 |
|
}, |
|
{ |
|
"epoch": 4.37, |
|
"learning_rate": 2.5227885479522406e-05, |
|
"loss": 1.3187, |
|
"step": 13660 |
|
}, |
|
{ |
|
"epoch": 4.37, |
|
"learning_rate": 2.5099499293875977e-05, |
|
"loss": 1.308, |
|
"step": 13670 |
|
}, |
|
{ |
|
"epoch": 4.38, |
|
"learning_rate": 2.4971113108229555e-05, |
|
"loss": 1.3194, |
|
"step": 13680 |
|
}, |
|
{ |
|
"epoch": 4.38, |
|
"learning_rate": 2.4842726922583132e-05, |
|
"loss": 1.3043, |
|
"step": 13690 |
|
}, |
|
{ |
|
"epoch": 4.38, |
|
"learning_rate": 2.4714340736936707e-05, |
|
"loss": 1.2563, |
|
"step": 13700 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 2.458595455129028e-05, |
|
"loss": 1.2401, |
|
"step": 13710 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 2.4457568365643856e-05, |
|
"loss": 1.3077, |
|
"step": 13720 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 2.4329182179997434e-05, |
|
"loss": 1.3053, |
|
"step": 13730 |
|
}, |
|
{ |
|
"epoch": 4.4, |
|
"learning_rate": 2.4200795994351008e-05, |
|
"loss": 1.355, |
|
"step": 13740 |
|
}, |
|
{ |
|
"epoch": 4.4, |
|
"learning_rate": 2.4072409808704586e-05, |
|
"loss": 1.3303, |
|
"step": 13750 |
|
}, |
|
{ |
|
"epoch": 4.4, |
|
"learning_rate": 2.394402362305816e-05, |
|
"loss": 1.2951, |
|
"step": 13760 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"learning_rate": 2.3815637437411735e-05, |
|
"loss": 1.2951, |
|
"step": 13770 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"learning_rate": 2.368725125176531e-05, |
|
"loss": 1.3561, |
|
"step": 13780 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"learning_rate": 2.3558865066118887e-05, |
|
"loss": 1.2898, |
|
"step": 13790 |
|
}, |
|
{ |
|
"epoch": 4.42, |
|
"learning_rate": 2.343047888047246e-05, |
|
"loss": 1.2504, |
|
"step": 13800 |
|
}, |
|
{ |
|
"epoch": 4.42, |
|
"eval_loss": 2.8036038875579834, |
|
"eval_runtime": 18.6905, |
|
"eval_samples_per_second": 13.108, |
|
"eval_steps_per_second": 3.317, |
|
"step": 13800 |
|
}, |
|
{ |
|
"epoch": 4.42, |
|
"learning_rate": 2.330209269482604e-05, |
|
"loss": 1.2722, |
|
"step": 13810 |
|
}, |
|
{ |
|
"epoch": 4.42, |
|
"learning_rate": 2.3173706509179614e-05, |
|
"loss": 1.3503, |
|
"step": 13820 |
|
}, |
|
{ |
|
"epoch": 4.43, |
|
"learning_rate": 2.304532032353319e-05, |
|
"loss": 1.3205, |
|
"step": 13830 |
|
}, |
|
{ |
|
"epoch": 4.43, |
|
"learning_rate": 2.2916934137886763e-05, |
|
"loss": 1.3247, |
|
"step": 13840 |
|
}, |
|
{ |
|
"epoch": 4.43, |
|
"learning_rate": 2.278854795224034e-05, |
|
"loss": 1.2586, |
|
"step": 13850 |
|
}, |
|
{ |
|
"epoch": 4.44, |
|
"learning_rate": 2.2660161766593915e-05, |
|
"loss": 1.3464, |
|
"step": 13860 |
|
}, |
|
{ |
|
"epoch": 4.44, |
|
"learning_rate": 2.2531775580947493e-05, |
|
"loss": 1.2934, |
|
"step": 13870 |
|
}, |
|
{ |
|
"epoch": 4.44, |
|
"learning_rate": 2.2403389395301067e-05, |
|
"loss": 1.2662, |
|
"step": 13880 |
|
}, |
|
{ |
|
"epoch": 4.44, |
|
"learning_rate": 2.2275003209654645e-05, |
|
"loss": 1.3408, |
|
"step": 13890 |
|
}, |
|
{ |
|
"epoch": 4.45, |
|
"learning_rate": 2.214661702400822e-05, |
|
"loss": 1.312, |
|
"step": 13900 |
|
}, |
|
{ |
|
"epoch": 4.45, |
|
"learning_rate": 2.2018230838361794e-05, |
|
"loss": 1.3107, |
|
"step": 13910 |
|
}, |
|
{ |
|
"epoch": 4.45, |
|
"learning_rate": 2.1889844652715368e-05, |
|
"loss": 1.3335, |
|
"step": 13920 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 2.1761458467068943e-05, |
|
"loss": 1.3201, |
|
"step": 13930 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 2.163307228142252e-05, |
|
"loss": 1.2635, |
|
"step": 13940 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 2.1504686095776095e-05, |
|
"loss": 1.3334, |
|
"step": 13950 |
|
}, |
|
{ |
|
"epoch": 4.47, |
|
"learning_rate": 2.1376299910129673e-05, |
|
"loss": 1.3262, |
|
"step": 13960 |
|
}, |
|
{ |
|
"epoch": 4.47, |
|
"learning_rate": 2.1247913724483244e-05, |
|
"loss": 1.2668, |
|
"step": 13970 |
|
}, |
|
{ |
|
"epoch": 4.47, |
|
"learning_rate": 2.111952753883682e-05, |
|
"loss": 1.3086, |
|
"step": 13980 |
|
}, |
|
{ |
|
"epoch": 4.48, |
|
"learning_rate": 2.0991141353190396e-05, |
|
"loss": 1.3484, |
|
"step": 13990 |
|
}, |
|
{ |
|
"epoch": 4.48, |
|
"learning_rate": 2.0862755167543974e-05, |
|
"loss": 1.3429, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 4.48, |
|
"eval_loss": 2.7863011360168457, |
|
"eval_runtime": 18.6179, |
|
"eval_samples_per_second": 13.159, |
|
"eval_steps_per_second": 3.33, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 4.48, |
|
"learning_rate": 2.073436898189755e-05, |
|
"loss": 1.3074, |
|
"step": 14010 |
|
}, |
|
{ |
|
"epoch": 4.49, |
|
"learning_rate": 2.0605982796251126e-05, |
|
"loss": 1.298, |
|
"step": 14020 |
|
}, |
|
{ |
|
"epoch": 4.49, |
|
"learning_rate": 2.04775966106047e-05, |
|
"loss": 1.3444, |
|
"step": 14030 |
|
}, |
|
{ |
|
"epoch": 4.49, |
|
"learning_rate": 2.0349210424958275e-05, |
|
"loss": 1.315, |
|
"step": 14040 |
|
}, |
|
{ |
|
"epoch": 4.5, |
|
"learning_rate": 2.022082423931185e-05, |
|
"loss": 1.3381, |
|
"step": 14050 |
|
}, |
|
{ |
|
"epoch": 4.5, |
|
"learning_rate": 2.0092438053665427e-05, |
|
"loss": 1.3194, |
|
"step": 14060 |
|
}, |
|
{ |
|
"epoch": 4.5, |
|
"learning_rate": 1.9964051868019002e-05, |
|
"loss": 1.2764, |
|
"step": 14070 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 1.983566568237258e-05, |
|
"loss": 1.3662, |
|
"step": 14080 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 1.9707279496726154e-05, |
|
"loss": 1.2613, |
|
"step": 14090 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 1.957889331107973e-05, |
|
"loss": 1.3026, |
|
"step": 14100 |
|
}, |
|
{ |
|
"epoch": 4.52, |
|
"learning_rate": 1.9450507125433303e-05, |
|
"loss": 1.2899, |
|
"step": 14110 |
|
}, |
|
{ |
|
"epoch": 4.52, |
|
"learning_rate": 1.932212093978688e-05, |
|
"loss": 1.2312, |
|
"step": 14120 |
|
}, |
|
{ |
|
"epoch": 4.52, |
|
"learning_rate": 1.9193734754140455e-05, |
|
"loss": 1.3309, |
|
"step": 14130 |
|
}, |
|
{ |
|
"epoch": 4.52, |
|
"learning_rate": 1.9065348568494033e-05, |
|
"loss": 1.2901, |
|
"step": 14140 |
|
}, |
|
{ |
|
"epoch": 4.53, |
|
"learning_rate": 1.8936962382847607e-05, |
|
"loss": 1.2901, |
|
"step": 14150 |
|
}, |
|
{ |
|
"epoch": 4.53, |
|
"learning_rate": 1.8808576197201182e-05, |
|
"loss": 1.3078, |
|
"step": 14160 |
|
}, |
|
{ |
|
"epoch": 4.53, |
|
"learning_rate": 1.8680190011554756e-05, |
|
"loss": 1.3452, |
|
"step": 14170 |
|
}, |
|
{ |
|
"epoch": 4.54, |
|
"learning_rate": 1.8551803825908334e-05, |
|
"loss": 1.3169, |
|
"step": 14180 |
|
}, |
|
{ |
|
"epoch": 4.54, |
|
"learning_rate": 1.842341764026191e-05, |
|
"loss": 1.2868, |
|
"step": 14190 |
|
}, |
|
{ |
|
"epoch": 4.54, |
|
"learning_rate": 1.8295031454615486e-05, |
|
"loss": 1.2972, |
|
"step": 14200 |
|
}, |
|
{ |
|
"epoch": 4.54, |
|
"eval_loss": 2.785550594329834, |
|
"eval_runtime": 18.4442, |
|
"eval_samples_per_second": 13.283, |
|
"eval_steps_per_second": 3.361, |
|
"step": 14200 |
|
}, |
|
{ |
|
"epoch": 4.55, |
|
"learning_rate": 1.816664526896906e-05, |
|
"loss": 1.264, |
|
"step": 14210 |
|
}, |
|
{ |
|
"epoch": 4.55, |
|
"learning_rate": 1.8038259083322635e-05, |
|
"loss": 1.2973, |
|
"step": 14220 |
|
}, |
|
{ |
|
"epoch": 4.55, |
|
"learning_rate": 1.790987289767621e-05, |
|
"loss": 1.2801, |
|
"step": 14230 |
|
}, |
|
{ |
|
"epoch": 4.56, |
|
"learning_rate": 1.7781486712029784e-05, |
|
"loss": 1.2748, |
|
"step": 14240 |
|
}, |
|
{ |
|
"epoch": 4.56, |
|
"learning_rate": 1.7653100526383362e-05, |
|
"loss": 1.293, |
|
"step": 14250 |
|
}, |
|
{ |
|
"epoch": 4.56, |
|
"learning_rate": 1.7524714340736936e-05, |
|
"loss": 1.3245, |
|
"step": 14260 |
|
}, |
|
{ |
|
"epoch": 4.57, |
|
"learning_rate": 1.7396328155090514e-05, |
|
"loss": 1.2806, |
|
"step": 14270 |
|
}, |
|
{ |
|
"epoch": 4.57, |
|
"learning_rate": 1.726794196944409e-05, |
|
"loss": 1.3297, |
|
"step": 14280 |
|
}, |
|
{ |
|
"epoch": 4.57, |
|
"learning_rate": 1.7139555783797663e-05, |
|
"loss": 1.3335, |
|
"step": 14290 |
|
}, |
|
{ |
|
"epoch": 4.58, |
|
"learning_rate": 1.7011169598151238e-05, |
|
"loss": 1.3061, |
|
"step": 14300 |
|
}, |
|
{ |
|
"epoch": 4.58, |
|
"learning_rate": 1.6882783412504815e-05, |
|
"loss": 1.37, |
|
"step": 14310 |
|
}, |
|
{ |
|
"epoch": 4.58, |
|
"learning_rate": 1.675439722685839e-05, |
|
"loss": 1.3159, |
|
"step": 14320 |
|
}, |
|
{ |
|
"epoch": 4.59, |
|
"learning_rate": 1.6626011041211968e-05, |
|
"loss": 1.2974, |
|
"step": 14330 |
|
}, |
|
{ |
|
"epoch": 4.59, |
|
"learning_rate": 1.6497624855565542e-05, |
|
"loss": 1.3199, |
|
"step": 14340 |
|
}, |
|
{ |
|
"epoch": 4.59, |
|
"learning_rate": 1.6369238669919117e-05, |
|
"loss": 1.3074, |
|
"step": 14350 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 1.624085248427269e-05, |
|
"loss": 1.3178, |
|
"step": 14360 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 1.611246629862627e-05, |
|
"loss": 1.3229, |
|
"step": 14370 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 1.5984080112979843e-05, |
|
"loss": 1.2973, |
|
"step": 14380 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 1.585569392733342e-05, |
|
"loss": 1.3566, |
|
"step": 14390 |
|
}, |
|
{ |
|
"epoch": 4.61, |
|
"learning_rate": 1.5727307741686996e-05, |
|
"loss": 1.3059, |
|
"step": 14400 |
|
}, |
|
{ |
|
"epoch": 4.61, |
|
"eval_loss": 2.794135332107544, |
|
"eval_runtime": 18.8681, |
|
"eval_samples_per_second": 12.985, |
|
"eval_steps_per_second": 3.286, |
|
"step": 14400 |
|
}, |
|
{ |
|
"epoch": 4.61, |
|
"learning_rate": 1.559892155604057e-05, |
|
"loss": 1.291, |
|
"step": 14410 |
|
}, |
|
{ |
|
"epoch": 4.61, |
|
"learning_rate": 1.5470535370394144e-05, |
|
"loss": 1.3669, |
|
"step": 14420 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 1.5342149184747722e-05, |
|
"loss": 1.262, |
|
"step": 14430 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 1.5213762999101297e-05, |
|
"loss": 1.317, |
|
"step": 14440 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 1.5085376813454875e-05, |
|
"loss": 1.3441, |
|
"step": 14450 |
|
}, |
|
{ |
|
"epoch": 4.63, |
|
"learning_rate": 1.4956990627808449e-05, |
|
"loss": 1.3354, |
|
"step": 14460 |
|
}, |
|
{ |
|
"epoch": 4.63, |
|
"learning_rate": 1.4828604442162025e-05, |
|
"loss": 1.336, |
|
"step": 14470 |
|
}, |
|
{ |
|
"epoch": 4.63, |
|
"learning_rate": 1.47002182565156e-05, |
|
"loss": 1.2977, |
|
"step": 14480 |
|
}, |
|
{ |
|
"epoch": 4.64, |
|
"learning_rate": 1.4571832070869176e-05, |
|
"loss": 1.3086, |
|
"step": 14490 |
|
}, |
|
{ |
|
"epoch": 4.64, |
|
"learning_rate": 1.444344588522275e-05, |
|
"loss": 1.317, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 4.64, |
|
"learning_rate": 1.4315059699576328e-05, |
|
"loss": 1.2984, |
|
"step": 14510 |
|
}, |
|
{ |
|
"epoch": 4.65, |
|
"learning_rate": 1.4186673513929902e-05, |
|
"loss": 1.2949, |
|
"step": 14520 |
|
}, |
|
{ |
|
"epoch": 4.65, |
|
"learning_rate": 1.4058287328283479e-05, |
|
"loss": 1.2557, |
|
"step": 14530 |
|
}, |
|
{ |
|
"epoch": 4.65, |
|
"learning_rate": 1.3929901142637053e-05, |
|
"loss": 1.3669, |
|
"step": 14540 |
|
}, |
|
{ |
|
"epoch": 4.66, |
|
"learning_rate": 1.3801514956990627e-05, |
|
"loss": 1.3359, |
|
"step": 14550 |
|
}, |
|
{ |
|
"epoch": 4.66, |
|
"learning_rate": 1.3673128771344204e-05, |
|
"loss": 1.3185, |
|
"step": 14560 |
|
}, |
|
{ |
|
"epoch": 4.66, |
|
"learning_rate": 1.3544742585697778e-05, |
|
"loss": 1.3216, |
|
"step": 14570 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"learning_rate": 1.3416356400051356e-05, |
|
"loss": 1.3084, |
|
"step": 14580 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"learning_rate": 1.328797021440493e-05, |
|
"loss": 1.2814, |
|
"step": 14590 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"learning_rate": 1.3159584028758506e-05, |
|
"loss": 1.32, |
|
"step": 14600 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"eval_loss": 2.784442186355591, |
|
"eval_runtime": 18.4288, |
|
"eval_samples_per_second": 13.294, |
|
"eval_steps_per_second": 3.364, |
|
"step": 14600 |
|
}, |
|
{ |
|
"epoch": 4.68, |
|
"learning_rate": 1.3031197843112081e-05, |
|
"loss": 1.2484, |
|
"step": 14610 |
|
}, |
|
{ |
|
"epoch": 4.68, |
|
"learning_rate": 1.2902811657465657e-05, |
|
"loss": 1.3358, |
|
"step": 14620 |
|
}, |
|
{ |
|
"epoch": 4.68, |
|
"learning_rate": 1.2774425471819231e-05, |
|
"loss": 1.2901, |
|
"step": 14630 |
|
}, |
|
{ |
|
"epoch": 4.68, |
|
"learning_rate": 1.264603928617281e-05, |
|
"loss": 1.2854, |
|
"step": 14640 |
|
}, |
|
{ |
|
"epoch": 4.69, |
|
"learning_rate": 1.2517653100526384e-05, |
|
"loss": 1.3051, |
|
"step": 14650 |
|
}, |
|
{ |
|
"epoch": 4.69, |
|
"learning_rate": 1.238926691487996e-05, |
|
"loss": 1.3336, |
|
"step": 14660 |
|
}, |
|
{ |
|
"epoch": 4.69, |
|
"learning_rate": 1.2260880729233536e-05, |
|
"loss": 1.3198, |
|
"step": 14670 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"learning_rate": 1.213249454358711e-05, |
|
"loss": 1.2949, |
|
"step": 14680 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"learning_rate": 1.2004108357940687e-05, |
|
"loss": 1.2741, |
|
"step": 14690 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"learning_rate": 1.1875722172294261e-05, |
|
"loss": 1.2738, |
|
"step": 14700 |
|
}, |
|
{ |
|
"epoch": 4.71, |
|
"learning_rate": 1.1747335986647837e-05, |
|
"loss": 1.2862, |
|
"step": 14710 |
|
}, |
|
{ |
|
"epoch": 4.71, |
|
"learning_rate": 1.1618949801001412e-05, |
|
"loss": 1.2932, |
|
"step": 14720 |
|
}, |
|
{ |
|
"epoch": 4.71, |
|
"learning_rate": 1.1490563615354988e-05, |
|
"loss": 1.3267, |
|
"step": 14730 |
|
}, |
|
{ |
|
"epoch": 4.72, |
|
"learning_rate": 1.1362177429708564e-05, |
|
"loss": 1.2263, |
|
"step": 14740 |
|
}, |
|
{ |
|
"epoch": 4.72, |
|
"learning_rate": 1.1233791244062138e-05, |
|
"loss": 1.3034, |
|
"step": 14750 |
|
}, |
|
{ |
|
"epoch": 4.72, |
|
"learning_rate": 1.1105405058415714e-05, |
|
"loss": 1.3151, |
|
"step": 14760 |
|
}, |
|
{ |
|
"epoch": 4.73, |
|
"learning_rate": 1.097701887276929e-05, |
|
"loss": 1.2675, |
|
"step": 14770 |
|
}, |
|
{ |
|
"epoch": 4.73, |
|
"learning_rate": 1.0848632687122865e-05, |
|
"loss": 1.231, |
|
"step": 14780 |
|
}, |
|
{ |
|
"epoch": 4.73, |
|
"learning_rate": 1.0720246501476441e-05, |
|
"loss": 1.3287, |
|
"step": 14790 |
|
}, |
|
{ |
|
"epoch": 4.74, |
|
"learning_rate": 1.0591860315830017e-05, |
|
"loss": 1.3045, |
|
"step": 14800 |
|
}, |
|
{ |
|
"epoch": 4.74, |
|
"eval_loss": 2.802720308303833, |
|
"eval_runtime": 18.3533, |
|
"eval_samples_per_second": 13.349, |
|
"eval_steps_per_second": 3.378, |
|
"step": 14800 |
|
}, |
|
{ |
|
"epoch": 4.74, |
|
"learning_rate": 1.0463474130183593e-05, |
|
"loss": 1.2984, |
|
"step": 14810 |
|
}, |
|
{ |
|
"epoch": 4.74, |
|
"learning_rate": 1.0335087944537168e-05, |
|
"loss": 1.2968, |
|
"step": 14820 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 1.0206701758890744e-05, |
|
"loss": 1.3277, |
|
"step": 14830 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 1.007831557324432e-05, |
|
"loss": 1.2606, |
|
"step": 14840 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 9.949929387597895e-06, |
|
"loss": 1.3264, |
|
"step": 14850 |
|
}, |
|
{ |
|
"epoch": 4.76, |
|
"learning_rate": 9.82154320195147e-06, |
|
"loss": 1.3067, |
|
"step": 14860 |
|
}, |
|
{ |
|
"epoch": 4.76, |
|
"learning_rate": 9.693157016305047e-06, |
|
"loss": 1.2843, |
|
"step": 14870 |
|
}, |
|
{ |
|
"epoch": 4.76, |
|
"learning_rate": 9.564770830658621e-06, |
|
"loss": 1.3023, |
|
"step": 14880 |
|
}, |
|
{ |
|
"epoch": 4.76, |
|
"learning_rate": 9.436384645012197e-06, |
|
"loss": 1.2994, |
|
"step": 14890 |
|
}, |
|
{ |
|
"epoch": 4.77, |
|
"learning_rate": 9.307998459365773e-06, |
|
"loss": 1.291, |
|
"step": 14900 |
|
}, |
|
{ |
|
"epoch": 4.77, |
|
"learning_rate": 9.179612273719348e-06, |
|
"loss": 1.2788, |
|
"step": 14910 |
|
}, |
|
{ |
|
"epoch": 4.77, |
|
"learning_rate": 9.051226088072924e-06, |
|
"loss": 1.2862, |
|
"step": 14920 |
|
}, |
|
{ |
|
"epoch": 4.78, |
|
"learning_rate": 8.9228399024265e-06, |
|
"loss": 1.3124, |
|
"step": 14930 |
|
}, |
|
{ |
|
"epoch": 4.78, |
|
"learning_rate": 8.794453716780075e-06, |
|
"loss": 1.2976, |
|
"step": 14940 |
|
}, |
|
{ |
|
"epoch": 4.78, |
|
"learning_rate": 8.66606753113365e-06, |
|
"loss": 1.3183, |
|
"step": 14950 |
|
}, |
|
{ |
|
"epoch": 4.79, |
|
"learning_rate": 8.537681345487227e-06, |
|
"loss": 1.33, |
|
"step": 14960 |
|
}, |
|
{ |
|
"epoch": 4.79, |
|
"learning_rate": 8.409295159840801e-06, |
|
"loss": 1.274, |
|
"step": 14970 |
|
}, |
|
{ |
|
"epoch": 4.79, |
|
"learning_rate": 8.280908974194377e-06, |
|
"loss": 1.3306, |
|
"step": 14980 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 8.152522788547954e-06, |
|
"loss": 1.2901, |
|
"step": 14990 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 8.024136602901528e-06, |
|
"loss": 1.3151, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"eval_loss": 2.7771408557891846, |
|
"eval_runtime": 20.4202, |
|
"eval_samples_per_second": 11.998, |
|
"eval_steps_per_second": 3.036, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 7.895750417255102e-06, |
|
"loss": 1.3311, |
|
"step": 15010 |
|
}, |
|
{ |
|
"epoch": 4.81, |
|
"learning_rate": 7.767364231608679e-06, |
|
"loss": 1.3577, |
|
"step": 15020 |
|
}, |
|
{ |
|
"epoch": 4.81, |
|
"learning_rate": 7.638978045962255e-06, |
|
"loss": 1.3439, |
|
"step": 15030 |
|
}, |
|
{ |
|
"epoch": 4.81, |
|
"learning_rate": 7.51059186031583e-06, |
|
"loss": 1.3173, |
|
"step": 15040 |
|
}, |
|
{ |
|
"epoch": 4.82, |
|
"learning_rate": 7.382205674669405e-06, |
|
"loss": 1.3243, |
|
"step": 15050 |
|
}, |
|
{ |
|
"epoch": 4.82, |
|
"learning_rate": 7.253819489022981e-06, |
|
"loss": 1.3513, |
|
"step": 15060 |
|
}, |
|
{ |
|
"epoch": 4.82, |
|
"learning_rate": 7.125433303376557e-06, |
|
"loss": 1.3579, |
|
"step": 15070 |
|
}, |
|
{ |
|
"epoch": 4.83, |
|
"learning_rate": 6.997047117730132e-06, |
|
"loss": 1.3134, |
|
"step": 15080 |
|
}, |
|
{ |
|
"epoch": 4.83, |
|
"learning_rate": 6.868660932083708e-06, |
|
"loss": 1.2951, |
|
"step": 15090 |
|
}, |
|
{ |
|
"epoch": 4.83, |
|
"learning_rate": 6.7402747464372835e-06, |
|
"loss": 1.3347, |
|
"step": 15100 |
|
}, |
|
{ |
|
"epoch": 4.84, |
|
"learning_rate": 6.611888560790859e-06, |
|
"loss": 1.334, |
|
"step": 15110 |
|
}, |
|
{ |
|
"epoch": 4.84, |
|
"learning_rate": 6.483502375144435e-06, |
|
"loss": 1.276, |
|
"step": 15120 |
|
}, |
|
{ |
|
"epoch": 4.84, |
|
"learning_rate": 6.35511618949801e-06, |
|
"loss": 1.3366, |
|
"step": 15130 |
|
}, |
|
{ |
|
"epoch": 4.84, |
|
"learning_rate": 6.2267300038515855e-06, |
|
"loss": 1.2627, |
|
"step": 15140 |
|
}, |
|
{ |
|
"epoch": 4.85, |
|
"learning_rate": 6.098343818205162e-06, |
|
"loss": 1.3141, |
|
"step": 15150 |
|
}, |
|
{ |
|
"epoch": 4.85, |
|
"learning_rate": 5.969957632558737e-06, |
|
"loss": 1.3147, |
|
"step": 15160 |
|
}, |
|
{ |
|
"epoch": 4.85, |
|
"learning_rate": 5.841571446912312e-06, |
|
"loss": 1.2916, |
|
"step": 15170 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"learning_rate": 5.713185261265888e-06, |
|
"loss": 1.3098, |
|
"step": 15180 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"learning_rate": 5.584799075619464e-06, |
|
"loss": 1.327, |
|
"step": 15190 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"learning_rate": 5.45641288997304e-06, |
|
"loss": 1.3464, |
|
"step": 15200 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"eval_loss": 2.7908942699432373, |
|
"eval_runtime": 18.6093, |
|
"eval_samples_per_second": 13.165, |
|
"eval_steps_per_second": 3.332, |
|
"step": 15200 |
|
}, |
|
{ |
|
"epoch": 4.87, |
|
"learning_rate": 5.328026704326615e-06, |
|
"loss": 1.282, |
|
"step": 15210 |
|
}, |
|
{ |
|
"epoch": 4.87, |
|
"learning_rate": 5.19964051868019e-06, |
|
"loss": 1.2989, |
|
"step": 15220 |
|
}, |
|
{ |
|
"epoch": 4.87, |
|
"learning_rate": 5.0712543330337664e-06, |
|
"loss": 1.2585, |
|
"step": 15230 |
|
}, |
|
{ |
|
"epoch": 4.88, |
|
"learning_rate": 4.942868147387341e-06, |
|
"loss": 1.3185, |
|
"step": 15240 |
|
}, |
|
{ |
|
"epoch": 4.88, |
|
"learning_rate": 4.814481961740917e-06, |
|
"loss": 1.284, |
|
"step": 15250 |
|
}, |
|
{ |
|
"epoch": 4.88, |
|
"learning_rate": 4.686095776094492e-06, |
|
"loss": 1.3084, |
|
"step": 15260 |
|
}, |
|
{ |
|
"epoch": 4.89, |
|
"learning_rate": 4.5577095904480676e-06, |
|
"loss": 1.3058, |
|
"step": 15270 |
|
}, |
|
{ |
|
"epoch": 4.89, |
|
"learning_rate": 4.429323404801644e-06, |
|
"loss": 1.3166, |
|
"step": 15280 |
|
}, |
|
{ |
|
"epoch": 4.89, |
|
"learning_rate": 4.300937219155219e-06, |
|
"loss": 1.3149, |
|
"step": 15290 |
|
}, |
|
{ |
|
"epoch": 4.9, |
|
"learning_rate": 4.172551033508794e-06, |
|
"loss": 1.2988, |
|
"step": 15300 |
|
}, |
|
{ |
|
"epoch": 4.9, |
|
"learning_rate": 4.04416484786237e-06, |
|
"loss": 1.3295, |
|
"step": 15310 |
|
}, |
|
{ |
|
"epoch": 4.9, |
|
"learning_rate": 3.915778662215946e-06, |
|
"loss": 1.3293, |
|
"step": 15320 |
|
}, |
|
{ |
|
"epoch": 4.91, |
|
"learning_rate": 3.7873924765695214e-06, |
|
"loss": 1.3101, |
|
"step": 15330 |
|
}, |
|
{ |
|
"epoch": 4.91, |
|
"learning_rate": 3.659006290923097e-06, |
|
"loss": 1.2937, |
|
"step": 15340 |
|
}, |
|
{ |
|
"epoch": 4.91, |
|
"learning_rate": 3.5306201052766724e-06, |
|
"loss": 1.291, |
|
"step": 15350 |
|
}, |
|
{ |
|
"epoch": 4.92, |
|
"learning_rate": 3.402233919630248e-06, |
|
"loss": 1.2611, |
|
"step": 15360 |
|
}, |
|
{ |
|
"epoch": 4.92, |
|
"learning_rate": 3.273847733983824e-06, |
|
"loss": 1.2765, |
|
"step": 15370 |
|
}, |
|
{ |
|
"epoch": 4.92, |
|
"learning_rate": 3.1454615483373995e-06, |
|
"loss": 1.2504, |
|
"step": 15380 |
|
}, |
|
{ |
|
"epoch": 4.92, |
|
"learning_rate": 3.0170753626909744e-06, |
|
"loss": 1.3436, |
|
"step": 15390 |
|
}, |
|
{ |
|
"epoch": 4.93, |
|
"learning_rate": 2.88868917704455e-06, |
|
"loss": 1.342, |
|
"step": 15400 |
|
}, |
|
{ |
|
"epoch": 4.93, |
|
"eval_loss": 2.7728683948516846, |
|
"eval_runtime": 19.2093, |
|
"eval_samples_per_second": 12.754, |
|
"eval_steps_per_second": 3.228, |
|
"step": 15400 |
|
} |
|
], |
|
"max_steps": 15625, |
|
"num_train_epochs": 5, |
|
"total_flos": 2.6865388290048e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|