| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 5128, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0078003120124804995, | |
| "grad_norm": 2.144841432571411, | |
| "learning_rate": 0.0009989971027412525, | |
| "loss": 1.1174, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015600624024960999, | |
| "grad_norm": 1.0625462532043457, | |
| "learning_rate": 0.0009978827724537553, | |
| "loss": 0.5035, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0234009360374415, | |
| "grad_norm": 1.619573950767517, | |
| "learning_rate": 0.0009967684421662581, | |
| "loss": 0.3841, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.031201248049921998, | |
| "grad_norm": 3.2681403160095215, | |
| "learning_rate": 0.000995654111878761, | |
| "loss": 0.4974, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0390015600624025, | |
| "grad_norm": 1.5944786071777344, | |
| "learning_rate": 0.0009945397815912637, | |
| "loss": 0.4797, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.046801872074883, | |
| "grad_norm": 1.8234444856643677, | |
| "learning_rate": 0.0009934254513037665, | |
| "loss": 0.637, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.054602184087363496, | |
| "grad_norm": 3.790844440460205, | |
| "learning_rate": 0.0009923111210162691, | |
| "loss": 0.4479, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.062402496099843996, | |
| "grad_norm": 2.9351046085357666, | |
| "learning_rate": 0.000991196790728772, | |
| "loss": 0.4332, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07020280811232449, | |
| "grad_norm": 2.2770025730133057, | |
| "learning_rate": 0.0009900824604412747, | |
| "loss": 0.4399, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.078003120124805, | |
| "grad_norm": 1.86591637134552, | |
| "learning_rate": 0.0009889681301537775, | |
| "loss": 0.407, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08580343213728549, | |
| "grad_norm": 1.6851640939712524, | |
| "learning_rate": 0.0009878537998662805, | |
| "loss": 0.3862, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.093603744149766, | |
| "grad_norm": 2.5469818115234375, | |
| "learning_rate": 0.0009867394695787831, | |
| "loss": 0.4166, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10140405616224649, | |
| "grad_norm": 1.8210259675979614, | |
| "learning_rate": 0.000985625139291286, | |
| "loss": 0.3785, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.10920436817472699, | |
| "grad_norm": 2.031057119369507, | |
| "learning_rate": 0.0009845108090037887, | |
| "loss": 0.4177, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11700468018720749, | |
| "grad_norm": 1.6646612882614136, | |
| "learning_rate": 0.0009833964787162915, | |
| "loss": 0.402, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12480499219968799, | |
| "grad_norm": 1.8680285215377808, | |
| "learning_rate": 0.0009822821484287943, | |
| "loss": 0.3282, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13260530421216848, | |
| "grad_norm": 1.8039604425430298, | |
| "learning_rate": 0.0009811678181412971, | |
| "loss": 0.3536, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.14040561622464898, | |
| "grad_norm": 3.3018901348114014, | |
| "learning_rate": 0.0009800534878538, | |
| "loss": 0.4595, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1482059282371295, | |
| "grad_norm": 3.684013843536377, | |
| "learning_rate": 0.0009789391575663027, | |
| "loss": 0.4288, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.15600624024961, | |
| "grad_norm": 1.4512592554092407, | |
| "learning_rate": 0.0009778248272788055, | |
| "loss": 0.5086, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16380655226209048, | |
| "grad_norm": 2.3981761932373047, | |
| "learning_rate": 0.0009767104969913081, | |
| "loss": 0.4084, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.17160686427457097, | |
| "grad_norm": 3.7943010330200195, | |
| "learning_rate": 0.000975596166703811, | |
| "loss": 0.4524, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.1794071762870515, | |
| "grad_norm": 2.657606840133667, | |
| "learning_rate": 0.0009744818364163138, | |
| "loss": 0.3592, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.187207488299532, | |
| "grad_norm": 2.7629363536834717, | |
| "learning_rate": 0.0009733675061288166, | |
| "loss": 0.4263, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.19500780031201248, | |
| "grad_norm": 1.3749983310699463, | |
| "learning_rate": 0.0009722531758413193, | |
| "loss": 0.48, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.20280811232449297, | |
| "grad_norm": 2.648716449737549, | |
| "learning_rate": 0.0009711388455538221, | |
| "loss": 0.416, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.21060842433697347, | |
| "grad_norm": 1.5672308206558228, | |
| "learning_rate": 0.0009700245152663249, | |
| "loss": 0.4223, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.21840873634945399, | |
| "grad_norm": 2.618163585662842, | |
| "learning_rate": 0.0009689101849788277, | |
| "loss": 0.4172, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.22620904836193448, | |
| "grad_norm": 3.6365268230438232, | |
| "learning_rate": 0.0009677958546913305, | |
| "loss": 0.5501, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.23400936037441497, | |
| "grad_norm": 2.740039825439453, | |
| "learning_rate": 0.0009666815244038332, | |
| "loss": 0.3553, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24180967238689546, | |
| "grad_norm": 3.406210422515869, | |
| "learning_rate": 0.000965567194116336, | |
| "loss": 0.3518, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.24960998439937598, | |
| "grad_norm": 1.4707075357437134, | |
| "learning_rate": 0.000964452863828839, | |
| "loss": 0.3452, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.2574102964118565, | |
| "grad_norm": 1.608324408531189, | |
| "learning_rate": 0.0009633385335413417, | |
| "loss": 0.4908, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.26521060842433697, | |
| "grad_norm": 4.090480327606201, | |
| "learning_rate": 0.0009622242032538444, | |
| "loss": 0.4597, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.27301092043681746, | |
| "grad_norm": 2.2214395999908447, | |
| "learning_rate": 0.0009611098729663472, | |
| "loss": 0.4552, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28081123244929795, | |
| "grad_norm": 1.9134166240692139, | |
| "learning_rate": 0.00095999554267885, | |
| "loss": 0.3571, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.28861154446177845, | |
| "grad_norm": 1.8127851486206055, | |
| "learning_rate": 0.0009588812123913528, | |
| "loss": 0.3808, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.296411856474259, | |
| "grad_norm": 2.2262885570526123, | |
| "learning_rate": 0.0009577668821038556, | |
| "loss": 0.4099, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3042121684867395, | |
| "grad_norm": 2.8041303157806396, | |
| "learning_rate": 0.0009566525518163583, | |
| "loss": 0.3988, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.31201248049922, | |
| "grad_norm": 6.797432899475098, | |
| "learning_rate": 0.0009555382215288611, | |
| "loss": 0.4728, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.31981279251170047, | |
| "grad_norm": 3.1861369609832764, | |
| "learning_rate": 0.000954423891241364, | |
| "loss": 0.3502, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.32761310452418096, | |
| "grad_norm": 2.9223642349243164, | |
| "learning_rate": 0.0009533095609538667, | |
| "loss": 0.4215, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.33541341653666146, | |
| "grad_norm": 6.848895072937012, | |
| "learning_rate": 0.0009521952306663694, | |
| "loss": 0.415, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.34321372854914195, | |
| "grad_norm": 9.054282188415527, | |
| "learning_rate": 0.0009510809003788722, | |
| "loss": 0.4667, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.35101404056162244, | |
| "grad_norm": 2.3005900382995605, | |
| "learning_rate": 0.0009499665700913752, | |
| "loss": 0.6565, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.358814352574103, | |
| "grad_norm": 2.9467573165893555, | |
| "learning_rate": 0.000948852239803878, | |
| "loss": 0.3837, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.3666146645865835, | |
| "grad_norm": 1.5977652072906494, | |
| "learning_rate": 0.0009477379095163808, | |
| "loss": 0.407, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.374414976599064, | |
| "grad_norm": 2.8274600505828857, | |
| "learning_rate": 0.0009466235792288835, | |
| "loss": 0.4501, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.38221528861154447, | |
| "grad_norm": 1.8566502332687378, | |
| "learning_rate": 0.0009455092489413863, | |
| "loss": 0.3146, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.39001560062402496, | |
| "grad_norm": 2.5871951580047607, | |
| "learning_rate": 0.0009443949186538891, | |
| "loss": 0.3335, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39781591263650545, | |
| "grad_norm": 2.0552711486816406, | |
| "learning_rate": 0.0009432805883663919, | |
| "loss": 0.3698, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.40561622464898595, | |
| "grad_norm": 1.5244548320770264, | |
| "learning_rate": 0.0009421662580788946, | |
| "loss": 0.581, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.41341653666146644, | |
| "grad_norm": 1.5146633386611938, | |
| "learning_rate": 0.0009410519277913974, | |
| "loss": 0.3634, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.42121684867394693, | |
| "grad_norm": 2.394819736480713, | |
| "learning_rate": 0.0009399375975039002, | |
| "loss": 0.338, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.4290171606864275, | |
| "grad_norm": 2.3500325679779053, | |
| "learning_rate": 0.000938823267216403, | |
| "loss": 0.4025, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.43681747269890797, | |
| "grad_norm": 2.4186370372772217, | |
| "learning_rate": 0.0009377089369289058, | |
| "loss": 0.4095, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.44461778471138846, | |
| "grad_norm": 1.9770065546035767, | |
| "learning_rate": 0.0009365946066414085, | |
| "loss": 0.4275, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.45241809672386896, | |
| "grad_norm": 1.7679632902145386, | |
| "learning_rate": 0.0009354802763539114, | |
| "loss": 0.3949, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.46021840873634945, | |
| "grad_norm": 2.0794620513916016, | |
| "learning_rate": 0.0009343659460664142, | |
| "loss": 0.4208, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.46801872074882994, | |
| "grad_norm": 2.677424192428589, | |
| "learning_rate": 0.000933251615778917, | |
| "loss": 0.4089, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.47581903276131043, | |
| "grad_norm": 1.526112675666809, | |
| "learning_rate": 0.0009321372854914197, | |
| "loss": 0.4196, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.4836193447737909, | |
| "grad_norm": 1.8656370639801025, | |
| "learning_rate": 0.0009310229552039225, | |
| "loss": 0.3732, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.4914196567862715, | |
| "grad_norm": 3.3338847160339355, | |
| "learning_rate": 0.0009299086249164253, | |
| "loss": 0.4231, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.49921996879875197, | |
| "grad_norm": 2.1057350635528564, | |
| "learning_rate": 0.0009287942946289281, | |
| "loss": 0.3921, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.5070202808112324, | |
| "grad_norm": 1.544977068901062, | |
| "learning_rate": 0.0009276799643414309, | |
| "loss": 0.3748, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.514820592823713, | |
| "grad_norm": 3.4070258140563965, | |
| "learning_rate": 0.0009265656340539336, | |
| "loss": 0.4027, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.5226209048361935, | |
| "grad_norm": 5.5486931800842285, | |
| "learning_rate": 0.0009254513037664364, | |
| "loss": 0.4326, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.5304212168486739, | |
| "grad_norm": 3.6824769973754883, | |
| "learning_rate": 0.0009243369734789392, | |
| "loss": 0.4809, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.5382215288611545, | |
| "grad_norm": 6.3154778480529785, | |
| "learning_rate": 0.000923222643191442, | |
| "loss": 0.3588, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.5460218408736349, | |
| "grad_norm": 3.133465528488159, | |
| "learning_rate": 0.0009221083129039447, | |
| "loss": 0.4712, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5538221528861155, | |
| "grad_norm": 4.222598552703857, | |
| "learning_rate": 0.0009209939826164475, | |
| "loss": 0.4135, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.5616224648985959, | |
| "grad_norm": 4.6125078201293945, | |
| "learning_rate": 0.0009198796523289504, | |
| "loss": 0.393, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.5694227769110765, | |
| "grad_norm": 6.543318748474121, | |
| "learning_rate": 0.0009187653220414532, | |
| "loss": 0.6138, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.5772230889235569, | |
| "grad_norm": 2.596463680267334, | |
| "learning_rate": 0.000917650991753956, | |
| "loss": 0.3694, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.5850234009360374, | |
| "grad_norm": 2.428490161895752, | |
| "learning_rate": 0.0009165366614664587, | |
| "loss": 0.4535, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.592823712948518, | |
| "grad_norm": 1.8790688514709473, | |
| "learning_rate": 0.0009154223311789615, | |
| "loss": 0.3986, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.6006240249609984, | |
| "grad_norm": 3.141587734222412, | |
| "learning_rate": 0.0009143080008914643, | |
| "loss": 0.3881, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.608424336973479, | |
| "grad_norm": 2.125810146331787, | |
| "learning_rate": 0.0009131936706039671, | |
| "loss": 0.4225, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.6162246489859594, | |
| "grad_norm": 2.532404661178589, | |
| "learning_rate": 0.0009120793403164698, | |
| "loss": 0.3423, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.62402496099844, | |
| "grad_norm": 3.6324350833892822, | |
| "learning_rate": 0.0009109650100289726, | |
| "loss": 0.4205, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6318252730109204, | |
| "grad_norm": 1.4804415702819824, | |
| "learning_rate": 0.0009098506797414754, | |
| "loss": 0.4042, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.6396255850234009, | |
| "grad_norm": 1.5140562057495117, | |
| "learning_rate": 0.0009087363494539782, | |
| "loss": 0.3056, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.6474258970358814, | |
| "grad_norm": 2.470576047897339, | |
| "learning_rate": 0.000907622019166481, | |
| "loss": 0.391, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.6552262090483619, | |
| "grad_norm": 3.4496209621429443, | |
| "learning_rate": 0.0009065076888789837, | |
| "loss": 0.4163, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.6630265210608425, | |
| "grad_norm": 1.8823250532150269, | |
| "learning_rate": 0.0009053933585914866, | |
| "loss": 0.3877, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.6708268330733229, | |
| "grad_norm": 2.492297410964966, | |
| "learning_rate": 0.0009042790283039894, | |
| "loss": 0.3542, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.6786271450858035, | |
| "grad_norm": 3.977569341659546, | |
| "learning_rate": 0.0009031646980164922, | |
| "loss": 0.4168, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.6864274570982839, | |
| "grad_norm": 3.938462495803833, | |
| "learning_rate": 0.0009020503677289949, | |
| "loss": 0.4894, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.6942277691107644, | |
| "grad_norm": 1.3457701206207275, | |
| "learning_rate": 0.0009009360374414977, | |
| "loss": 0.4903, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.7020280811232449, | |
| "grad_norm": 6.3473124504089355, | |
| "learning_rate": 0.0008998217071540005, | |
| "loss": 0.4766, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.7098283931357254, | |
| "grad_norm": 3.145792245864868, | |
| "learning_rate": 0.0008987073768665033, | |
| "loss": 0.4119, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.717628705148206, | |
| "grad_norm": 1.809446930885315, | |
| "learning_rate": 0.0008975930465790061, | |
| "loss": 0.3991, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.7254290171606864, | |
| "grad_norm": 1.7960044145584106, | |
| "learning_rate": 0.0008964787162915088, | |
| "loss": 0.3095, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.733229329173167, | |
| "grad_norm": 2.9710285663604736, | |
| "learning_rate": 0.0008953643860040116, | |
| "loss": 0.5104, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.7410296411856474, | |
| "grad_norm": 2.460524797439575, | |
| "learning_rate": 0.0008942500557165144, | |
| "loss": 0.4332, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.748829953198128, | |
| "grad_norm": 1.6166704893112183, | |
| "learning_rate": 0.0008931357254290172, | |
| "loss": 0.3856, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.7566302652106084, | |
| "grad_norm": 1.747750163078308, | |
| "learning_rate": 0.0008920213951415199, | |
| "loss": 0.3973, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.7644305772230889, | |
| "grad_norm": 1.4469414949417114, | |
| "learning_rate": 0.0008909070648540227, | |
| "loss": 0.3344, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.7722308892355694, | |
| "grad_norm": 4.661273956298828, | |
| "learning_rate": 0.0008897927345665256, | |
| "loss": 0.6003, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.7800312012480499, | |
| "grad_norm": 3.6588950157165527, | |
| "learning_rate": 0.0008886784042790284, | |
| "loss": 0.473, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7878315132605305, | |
| "grad_norm": 2.208383798599243, | |
| "learning_rate": 0.0008876755070202809, | |
| "loss": 0.3899, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.7956318252730109, | |
| "grad_norm": 2.3569576740264893, | |
| "learning_rate": 0.0008865611767327836, | |
| "loss": 0.3871, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.8034321372854915, | |
| "grad_norm": 2.7071454524993896, | |
| "learning_rate": 0.0008854468464452864, | |
| "loss": 0.3149, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.8112324492979719, | |
| "grad_norm": 2.8024532794952393, | |
| "learning_rate": 0.0008843325161577892, | |
| "loss": 0.3328, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.8190327613104524, | |
| "grad_norm": 3.0969290733337402, | |
| "learning_rate": 0.000883218185870292, | |
| "loss": 0.3948, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.8268330733229329, | |
| "grad_norm": 2.982484817504883, | |
| "learning_rate": 0.0008821038555827947, | |
| "loss": 0.4323, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.8346333853354134, | |
| "grad_norm": 3.133814573287964, | |
| "learning_rate": 0.0008809895252952975, | |
| "loss": 0.4393, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.8424336973478939, | |
| "grad_norm": 3.3123364448547363, | |
| "learning_rate": 0.0008798751950078003, | |
| "loss": 0.3244, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.8502340093603744, | |
| "grad_norm": 2.308555841445923, | |
| "learning_rate": 0.0008787608647203032, | |
| "loss": 0.424, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.858034321372855, | |
| "grad_norm": 3.654137134552002, | |
| "learning_rate": 0.000877646534432806, | |
| "loss": 0.3445, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8658346333853354, | |
| "grad_norm": 2.149843692779541, | |
| "learning_rate": 0.0008765322041453087, | |
| "loss": 0.3398, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.8736349453978159, | |
| "grad_norm": 3.1334431171417236, | |
| "learning_rate": 0.0008754178738578115, | |
| "loss": 0.3333, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.8814352574102964, | |
| "grad_norm": 2.2942090034484863, | |
| "learning_rate": 0.0008743035435703143, | |
| "loss": 0.4188, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.8892355694227769, | |
| "grad_norm": 2.0195343494415283, | |
| "learning_rate": 0.0008731892132828171, | |
| "loss": 0.4047, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.8970358814352574, | |
| "grad_norm": 2.3850839138031006, | |
| "learning_rate": 0.0008720748829953198, | |
| "loss": 0.3931, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.9048361934477379, | |
| "grad_norm": 1.6200228929519653, | |
| "learning_rate": 0.0008709605527078226, | |
| "loss": 0.409, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.9126365054602185, | |
| "grad_norm": 2.9001989364624023, | |
| "learning_rate": 0.0008698462224203254, | |
| "loss": 0.4289, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.9204368174726989, | |
| "grad_norm": 1.52889883518219, | |
| "learning_rate": 0.0008687318921328282, | |
| "loss": 0.3575, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.9282371294851794, | |
| "grad_norm": 2.359733819961548, | |
| "learning_rate": 0.000867617561845331, | |
| "loss": 0.3837, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.9360374414976599, | |
| "grad_norm": 2.3807597160339355, | |
| "learning_rate": 0.0008665032315578337, | |
| "loss": 0.4206, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.9438377535101404, | |
| "grad_norm": 1.8366179466247559, | |
| "learning_rate": 0.0008653889012703365, | |
| "loss": 0.3101, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.9516380655226209, | |
| "grad_norm": 3.1048014163970947, | |
| "learning_rate": 0.0008642745709828393, | |
| "loss": 0.4104, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.9594383775351014, | |
| "grad_norm": 1.5314342975616455, | |
| "learning_rate": 0.0008631602406953422, | |
| "loss": 0.3539, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.9672386895475819, | |
| "grad_norm": 2.8501791954040527, | |
| "learning_rate": 0.0008620459104078449, | |
| "loss": 0.4104, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.9750390015600624, | |
| "grad_norm": 5.708191394805908, | |
| "learning_rate": 0.0008609315801203477, | |
| "loss": 0.4038, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.982839313572543, | |
| "grad_norm": 2.173867702484131, | |
| "learning_rate": 0.0008598172498328505, | |
| "loss": 0.338, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.9906396255850234, | |
| "grad_norm": 2.7057418823242188, | |
| "learning_rate": 0.0008587029195453533, | |
| "loss": 0.3941, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.9984399375975039, | |
| "grad_norm": 1.3492989540100098, | |
| "learning_rate": 0.0008575885892578561, | |
| "loss": 0.3696, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4044143855571747, | |
| "eval_runtime": 635.8286, | |
| "eval_samples_per_second": 0.865, | |
| "eval_steps_per_second": 0.865, | |
| "eval_wer": 26.665379416875844, | |
| "step": 1282 | |
| }, | |
| { | |
| "epoch": 1.0062402496099845, | |
| "grad_norm": 2.5727291107177734, | |
| "learning_rate": 0.0008564742589703588, | |
| "loss": 0.3369, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.0140405616224648, | |
| "grad_norm": 2.681490182876587, | |
| "learning_rate": 0.0008553599286828616, | |
| "loss": 0.2434, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.0218408736349454, | |
| "grad_norm": 2.0296504497528076, | |
| "learning_rate": 0.0008542455983953644, | |
| "loss": 0.2122, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.029641185647426, | |
| "grad_norm": 2.277512311935425, | |
| "learning_rate": 0.0008531312681078672, | |
| "loss": 0.3932, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.0374414976599065, | |
| "grad_norm": 4.77215576171875, | |
| "learning_rate": 0.0008520169378203699, | |
| "loss": 0.2658, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.045241809672387, | |
| "grad_norm": 1.4027091264724731, | |
| "learning_rate": 0.0008509026075328727, | |
| "loss": 0.3524, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.0530421216848673, | |
| "grad_norm": 2.2849514484405518, | |
| "learning_rate": 0.0008497882772453755, | |
| "loss": 0.2705, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.0608424336973479, | |
| "grad_norm": 1.2896777391433716, | |
| "learning_rate": 0.0008486739469578784, | |
| "loss": 0.264, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.0686427457098284, | |
| "grad_norm": 2.4552128314971924, | |
| "learning_rate": 0.0008475596166703812, | |
| "loss": 0.2833, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.076443057722309, | |
| "grad_norm": 2.044693946838379, | |
| "learning_rate": 0.0008464452863828839, | |
| "loss": 0.2116, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.0842433697347893, | |
| "grad_norm": 1.3727463483810425, | |
| "learning_rate": 0.0008453309560953867, | |
| "loss": 0.2533, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.0920436817472698, | |
| "grad_norm": 1.6917822360992432, | |
| "learning_rate": 0.0008442166258078895, | |
| "loss": 0.4259, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.0998439937597504, | |
| "grad_norm": 2.198549747467041, | |
| "learning_rate": 0.0008431022955203923, | |
| "loss": 0.3161, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.107644305772231, | |
| "grad_norm": 1.7467869520187378, | |
| "learning_rate": 0.000841987965232895, | |
| "loss": 0.2377, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.1154446177847115, | |
| "grad_norm": 2.5347695350646973, | |
| "learning_rate": 0.0008408736349453978, | |
| "loss": 0.3258, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.1232449297971918, | |
| "grad_norm": 1.9081774950027466, | |
| "learning_rate": 0.0008397593046579006, | |
| "loss": 0.2462, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.1310452418096724, | |
| "grad_norm": 1.5889848470687866, | |
| "learning_rate": 0.0008386449743704034, | |
| "loss": 0.2404, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.138845553822153, | |
| "grad_norm": 1.8944768905639648, | |
| "learning_rate": 0.0008375306440829062, | |
| "loss": 0.2707, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.1466458658346335, | |
| "grad_norm": 2.5448453426361084, | |
| "learning_rate": 0.0008364163137954089, | |
| "loss": 0.3342, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.154446177847114, | |
| "grad_norm": 2.0936005115509033, | |
| "learning_rate": 0.0008353019835079117, | |
| "loss": 0.385, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.1622464898595943, | |
| "grad_norm": 2.614129066467285, | |
| "learning_rate": 0.0008341876532204145, | |
| "loss": 0.2817, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.1700468018720749, | |
| "grad_norm": 1.6156001091003418, | |
| "learning_rate": 0.0008330733229329174, | |
| "loss": 0.3527, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.1778471138845554, | |
| "grad_norm": 1.4294220209121704, | |
| "learning_rate": 0.0008319589926454201, | |
| "loss": 0.2469, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.185647425897036, | |
| "grad_norm": 3.197176456451416, | |
| "learning_rate": 0.0008308446623579229, | |
| "loss": 0.2753, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.1934477379095163, | |
| "grad_norm": 2.1629223823547363, | |
| "learning_rate": 0.0008297303320704257, | |
| "loss": 0.3951, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.2012480499219969, | |
| "grad_norm": 2.9824419021606445, | |
| "learning_rate": 0.0008286160017829285, | |
| "loss": 0.3278, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.2090483619344774, | |
| "grad_norm": 2.866138219833374, | |
| "learning_rate": 0.0008275016714954313, | |
| "loss": 0.4267, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.216848673946958, | |
| "grad_norm": 2.36781644821167, | |
| "learning_rate": 0.000826387341207934, | |
| "loss": 0.3414, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.2246489859594383, | |
| "grad_norm": 1.8305447101593018, | |
| "learning_rate": 0.0008252730109204368, | |
| "loss": 0.2925, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.2324492979719188, | |
| "grad_norm": 1.9879776239395142, | |
| "learning_rate": 0.0008241586806329396, | |
| "loss": 0.357, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.2402496099843994, | |
| "grad_norm": 2.183350086212158, | |
| "learning_rate": 0.0008230443503454424, | |
| "loss": 0.3409, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.24804992199688, | |
| "grad_norm": 2.197072744369507, | |
| "learning_rate": 0.0008219300200579451, | |
| "loss": 0.33, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.2558502340093605, | |
| "grad_norm": 3.2065696716308594, | |
| "learning_rate": 0.0008208156897704479, | |
| "loss": 0.2853, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.2636505460218408, | |
| "grad_norm": 2.0581350326538086, | |
| "learning_rate": 0.0008197013594829507, | |
| "loss": 0.3647, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.2714508580343213, | |
| "grad_norm": 3.149153232574463, | |
| "learning_rate": 0.0008185870291954536, | |
| "loss": 0.3921, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.2792511700468019, | |
| "grad_norm": 2.5097105503082275, | |
| "learning_rate": 0.0008174726989079563, | |
| "loss": 0.3302, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.2870514820592824, | |
| "grad_norm": 2.7537474632263184, | |
| "learning_rate": 0.0008163583686204591, | |
| "loss": 0.3286, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.294851794071763, | |
| "grad_norm": 1.966965675354004, | |
| "learning_rate": 0.0008152440383329619, | |
| "loss": 0.2785, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.3026521060842433, | |
| "grad_norm": 1.9159988164901733, | |
| "learning_rate": 0.0008141297080454647, | |
| "loss": 0.3299, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.3104524180967239, | |
| "grad_norm": 2.2212252616882324, | |
| "learning_rate": 0.0008130153777579675, | |
| "loss": 0.2807, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.3182527301092044, | |
| "grad_norm": 4.194318771362305, | |
| "learning_rate": 0.0008119010474704702, | |
| "loss": 0.3161, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.3260530421216847, | |
| "grad_norm": 1.7189604043960571, | |
| "learning_rate": 0.000810786717182973, | |
| "loss": 0.3356, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.3338533541341655, | |
| "grad_norm": 1.5196418762207031, | |
| "learning_rate": 0.0008096723868954758, | |
| "loss": 0.2616, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.3416536661466458, | |
| "grad_norm": 1.497450351715088, | |
| "learning_rate": 0.0008085580566079786, | |
| "loss": 0.2946, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.3494539781591264, | |
| "grad_norm": 1.74885892868042, | |
| "learning_rate": 0.0008074437263204813, | |
| "loss": 0.2801, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.357254290171607, | |
| "grad_norm": 2.040701389312744, | |
| "learning_rate": 0.0008063293960329841, | |
| "loss": 0.3203, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.3650546021840873, | |
| "grad_norm": 3.760457754135132, | |
| "learning_rate": 0.0008052150657454869, | |
| "loss": 0.4569, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.3728549141965678, | |
| "grad_norm": 2.92971134185791, | |
| "learning_rate": 0.0008041007354579897, | |
| "loss": 0.3321, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.3806552262090483, | |
| "grad_norm": 1.9461047649383545, | |
| "learning_rate": 0.0008029864051704926, | |
| "loss": 0.2696, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.388455538221529, | |
| "grad_norm": 3.2626147270202637, | |
| "learning_rate": 0.0008018720748829953, | |
| "loss": 0.3322, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.3962558502340094, | |
| "grad_norm": 2.1270642280578613, | |
| "learning_rate": 0.0008007577445954981, | |
| "loss": 0.2965, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.4040561622464898, | |
| "grad_norm": 2.3174221515655518, | |
| "learning_rate": 0.0007996434143080009, | |
| "loss": 0.3425, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.4118564742589703, | |
| "grad_norm": 2.5749576091766357, | |
| "learning_rate": 0.0007985290840205037, | |
| "loss": 0.3622, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.4196567862714509, | |
| "grad_norm": 1.873813509941101, | |
| "learning_rate": 0.0007974147537330064, | |
| "loss": 0.2497, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.4274570982839314, | |
| "grad_norm": 3.633928060531616, | |
| "learning_rate": 0.0007963004234455092, | |
| "loss": 0.4058, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.435257410296412, | |
| "grad_norm": 2.356269598007202, | |
| "learning_rate": 0.000795186093158012, | |
| "loss": 0.2635, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.4430577223088923, | |
| "grad_norm": 1.9108752012252808, | |
| "learning_rate": 0.0007940717628705148, | |
| "loss": 0.336, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.4508580343213728, | |
| "grad_norm": 1.5505330562591553, | |
| "learning_rate": 0.0007929574325830176, | |
| "loss": 0.3493, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.4586583463338534, | |
| "grad_norm": 1.9970422983169556, | |
| "learning_rate": 0.0007918431022955203, | |
| "loss": 0.273, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.466458658346334, | |
| "grad_norm": 2.753758192062378, | |
| "learning_rate": 0.0007907287720080231, | |
| "loss": 0.2845, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.4742589703588145, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0007897258747492757, | |
| "loss": 0.2544, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.4820592823712948, | |
| "grad_norm": 3.0995099544525146, | |
| "learning_rate": 0.0007886115444617785, | |
| "loss": 0.2884, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.4898595943837754, | |
| "grad_norm": 5.728559970855713, | |
| "learning_rate": 0.0007874972141742812, | |
| "loss": 0.2681, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.497659906396256, | |
| "grad_norm": 1.492622971534729, | |
| "learning_rate": 0.000786382883886784, | |
| "loss": 0.2891, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.5054602184087362, | |
| "grad_norm": 1.7419252395629883, | |
| "learning_rate": 0.0007852685535992868, | |
| "loss": 0.4089, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.513260530421217, | |
| "grad_norm": 6.814690589904785, | |
| "learning_rate": 0.0007841542233117896, | |
| "loss": 0.3372, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.5210608424336973, | |
| "grad_norm": 2.380725860595703, | |
| "learning_rate": 0.0007830398930242924, | |
| "loss": 0.3189, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.5288611544461779, | |
| "grad_norm": 5.004116058349609, | |
| "learning_rate": 0.0007819255627367951, | |
| "loss": 0.3018, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.5366614664586584, | |
| "grad_norm": 2.604365825653076, | |
| "learning_rate": 0.0007808112324492979, | |
| "loss": 0.3054, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.5444617784711387, | |
| "grad_norm": 1.585584044456482, | |
| "learning_rate": 0.0007796969021618007, | |
| "loss": 0.3477, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.5522620904836193, | |
| "grad_norm": 1.8678693771362305, | |
| "learning_rate": 0.0007785825718743035, | |
| "loss": 0.3577, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.5600624024960998, | |
| "grad_norm": 1.654689073562622, | |
| "learning_rate": 0.0007774682415868062, | |
| "loss": 0.2625, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.5678627145085804, | |
| "grad_norm": 2.108919858932495, | |
| "learning_rate": 0.0007763539112993092, | |
| "loss": 0.2497, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.575663026521061, | |
| "grad_norm": 7.198604106903076, | |
| "learning_rate": 0.000775239581011812, | |
| "loss": 0.3382, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.5834633385335413, | |
| "grad_norm": 2.2285892963409424, | |
| "learning_rate": 0.0007741252507243148, | |
| "loss": 0.2598, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.5912636505460218, | |
| "grad_norm": 1.7743014097213745, | |
| "learning_rate": 0.0007730109204368176, | |
| "loss": 0.2757, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.5990639625585024, | |
| "grad_norm": 1.7763789892196655, | |
| "learning_rate": 0.0007718965901493203, | |
| "loss": 0.2703, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.6068642745709827, | |
| "grad_norm": 2.159956693649292, | |
| "learning_rate": 0.000770782259861823, | |
| "loss": 0.2824, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.6146645865834635, | |
| "grad_norm": 1.4845560789108276, | |
| "learning_rate": 0.0007696679295743259, | |
| "loss": 0.2528, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.6224648985959438, | |
| "grad_norm": 3.627887010574341, | |
| "learning_rate": 0.0007685535992868287, | |
| "loss": 0.3197, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.6302652106084243, | |
| "grad_norm": 2.2174973487854004, | |
| "learning_rate": 0.0007674392689993314, | |
| "loss": 0.2994, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.6380655226209049, | |
| "grad_norm": 2.5977325439453125, | |
| "learning_rate": 0.0007663249387118342, | |
| "loss": 0.2991, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.6458658346333852, | |
| "grad_norm": 1.9066824913024902, | |
| "learning_rate": 0.000765210608424337, | |
| "loss": 0.2166, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.653666146645866, | |
| "grad_norm": 1.7197297811508179, | |
| "learning_rate": 0.0007640962781368398, | |
| "loss": 0.2948, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.6614664586583463, | |
| "grad_norm": 2.054304361343384, | |
| "learning_rate": 0.0007629819478493426, | |
| "loss": 0.3073, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.6692667706708268, | |
| "grad_norm": 1.7934963703155518, | |
| "learning_rate": 0.0007618676175618453, | |
| "loss": 0.2667, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.6770670826833074, | |
| "grad_norm": 2.5259838104248047, | |
| "learning_rate": 0.0007607532872743482, | |
| "loss": 0.3322, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.6848673946957877, | |
| "grad_norm": 3.6354122161865234, | |
| "learning_rate": 0.000759638956986851, | |
| "loss": 0.3909, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.6926677067082685, | |
| "grad_norm": 1.6722809076309204, | |
| "learning_rate": 0.0007585246266993538, | |
| "loss": 0.2987, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.7004680187207488, | |
| "grad_norm": 4.3235015869140625, | |
| "learning_rate": 0.0007574102964118565, | |
| "loss": 0.3112, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.7082683307332294, | |
| "grad_norm": 2.236316442489624, | |
| "learning_rate": 0.0007562959661243593, | |
| "loss": 0.3174, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.71606864274571, | |
| "grad_norm": 21.32891273498535, | |
| "learning_rate": 0.0007551816358368621, | |
| "loss": 0.3696, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.7238689547581902, | |
| "grad_norm": 2.4251410961151123, | |
| "learning_rate": 0.0007540673055493649, | |
| "loss": 0.3171, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 1.7316692667706708, | |
| "grad_norm": 2.4152424335479736, | |
| "learning_rate": 0.0007529529752618677, | |
| "loss": 0.328, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.7394695787831513, | |
| "grad_norm": 2.0988574028015137, | |
| "learning_rate": 0.0007518386449743704, | |
| "loss": 0.3061, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 1.7472698907956317, | |
| "grad_norm": 4.469291687011719, | |
| "learning_rate": 0.0007507243146868732, | |
| "loss": 0.3315, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.7550702028081124, | |
| "grad_norm": 2.4917778968811035, | |
| "learning_rate": 0.000749609984399376, | |
| "loss": 0.4296, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.7628705148205928, | |
| "grad_norm": 3.073840379714966, | |
| "learning_rate": 0.0007484956541118788, | |
| "loss": 0.3685, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.7706708268330733, | |
| "grad_norm": 2.205733299255371, | |
| "learning_rate": 0.0007473813238243815, | |
| "loss": 0.2691, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 1.7784711388455539, | |
| "grad_norm": 2.3948941230773926, | |
| "learning_rate": 0.0007462669935368844, | |
| "loss": 0.3065, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.7862714508580342, | |
| "grad_norm": 2.6060824394226074, | |
| "learning_rate": 0.0007451526632493872, | |
| "loss": 0.3354, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 1.794071762870515, | |
| "grad_norm": 3.2586774826049805, | |
| "learning_rate": 0.00074403833296189, | |
| "loss": 0.261, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.8018720748829953, | |
| "grad_norm": 1.6417285203933716, | |
| "learning_rate": 0.0007429240026743928, | |
| "loss": 0.3828, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.8096723868954758, | |
| "grad_norm": 4.006927967071533, | |
| "learning_rate": 0.0007418096723868955, | |
| "loss": 0.4228, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.8174726989079564, | |
| "grad_norm": 2.5880374908447266, | |
| "learning_rate": 0.0007406953420993983, | |
| "loss": 0.2766, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 1.8252730109204367, | |
| "grad_norm": 1.602337121963501, | |
| "learning_rate": 0.0007395810118119011, | |
| "loss": 0.2794, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.8330733229329175, | |
| "grad_norm": 5.932153224945068, | |
| "learning_rate": 0.0007384666815244039, | |
| "loss": 0.3471, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.8408736349453978, | |
| "grad_norm": 4.076808452606201, | |
| "learning_rate": 0.0007373523512369066, | |
| "loss": 0.2649, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.8486739469578783, | |
| "grad_norm": 4.666397571563721, | |
| "learning_rate": 0.0007362380209494094, | |
| "loss": 0.2751, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.856474258970359, | |
| "grad_norm": 3.792745590209961, | |
| "learning_rate": 0.0007351236906619122, | |
| "loss": 0.2606, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.8642745709828392, | |
| "grad_norm": 2.5275423526763916, | |
| "learning_rate": 0.000734009360374415, | |
| "loss": 0.3469, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 1.8720748829953198, | |
| "grad_norm": 1.59649658203125, | |
| "learning_rate": 0.0007328950300869178, | |
| "loss": 0.2724, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.8798751950078003, | |
| "grad_norm": 3.7428267002105713, | |
| "learning_rate": 0.0007317806997994206, | |
| "loss": 0.4426, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 1.8876755070202809, | |
| "grad_norm": 3.7439956665039062, | |
| "learning_rate": 0.0007306663695119234, | |
| "loss": 0.2901, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.8954758190327614, | |
| "grad_norm": 2.3777198791503906, | |
| "learning_rate": 0.0007295520392244262, | |
| "loss": 0.2837, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.9032761310452417, | |
| "grad_norm": 2.7654988765716553, | |
| "learning_rate": 0.000728437708936929, | |
| "loss": 0.277, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.9110764430577223, | |
| "grad_norm": 1.8758680820465088, | |
| "learning_rate": 0.0007273233786494317, | |
| "loss": 0.2706, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.9188767550702028, | |
| "grad_norm": 2.8725340366363525, | |
| "learning_rate": 0.0007262090483619345, | |
| "loss": 0.2566, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.9266770670826832, | |
| "grad_norm": 2.4021458625793457, | |
| "learning_rate": 0.0007250947180744373, | |
| "loss": 0.2645, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 1.934477379095164, | |
| "grad_norm": 2.8407838344573975, | |
| "learning_rate": 0.0007239803877869401, | |
| "loss": 0.3152, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.9422776911076443, | |
| "grad_norm": 3.606403112411499, | |
| "learning_rate": 0.0007228660574994429, | |
| "loss": 0.373, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.9500780031201248, | |
| "grad_norm": 2.362473487854004, | |
| "learning_rate": 0.0007217517272119456, | |
| "loss": 0.4332, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.9578783151326054, | |
| "grad_norm": 1.9711815118789673, | |
| "learning_rate": 0.0007206373969244484, | |
| "loss": 0.2606, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 1.9656786271450857, | |
| "grad_norm": 2.683908224105835, | |
| "learning_rate": 0.0007195230666369512, | |
| "loss": 0.3582, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.9734789391575664, | |
| "grad_norm": 2.5902493000030518, | |
| "learning_rate": 0.000718408736349454, | |
| "loss": 0.2694, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 1.9812792511700468, | |
| "grad_norm": 3.92708420753479, | |
| "learning_rate": 0.0007172944060619567, | |
| "loss": 0.3083, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.9890795631825273, | |
| "grad_norm": 2.6788370609283447, | |
| "learning_rate": 0.0007161800757744596, | |
| "loss": 0.2587, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.9968798751950079, | |
| "grad_norm": 2.413313627243042, | |
| "learning_rate": 0.0007150657454869624, | |
| "loss": 0.2732, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.3617618680000305, | |
| "eval_runtime": 36952.264, | |
| "eval_samples_per_second": 0.015, | |
| "eval_steps_per_second": 0.015, | |
| "eval_wer": 22.793975670978952, | |
| "step": 2564 | |
| }, | |
| { | |
| "epoch": 2.004680187207488, | |
| "grad_norm": 1.572451114654541, | |
| "learning_rate": 0.0007139514151994652, | |
| "loss": 0.2147, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 2.012480499219969, | |
| "grad_norm": 2.4759023189544678, | |
| "learning_rate": 0.000712837084911968, | |
| "loss": 0.2015, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 2.0202808112324493, | |
| "grad_norm": 1.6903563737869263, | |
| "learning_rate": 0.0007117227546244707, | |
| "loss": 0.1703, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 2.0280811232449296, | |
| "grad_norm": 3.494985580444336, | |
| "learning_rate": 0.0007106084243369735, | |
| "loss": 0.2063, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.0358814352574104, | |
| "grad_norm": 1.5024439096450806, | |
| "learning_rate": 0.0007094940940494763, | |
| "loss": 0.1807, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 2.0436817472698907, | |
| "grad_norm": 1.9423105716705322, | |
| "learning_rate": 0.0007083797637619791, | |
| "loss": 0.1953, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 2.0514820592823715, | |
| "grad_norm": 0.8572360277175903, | |
| "learning_rate": 0.0007072654334744818, | |
| "loss": 0.3423, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 2.059282371294852, | |
| "grad_norm": 2.574855327606201, | |
| "learning_rate": 0.0007061511031869846, | |
| "loss": 0.1916, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 2.067082683307332, | |
| "grad_norm": 2.2941219806671143, | |
| "learning_rate": 0.0007050367728994874, | |
| "loss": 0.2168, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.074882995319813, | |
| "grad_norm": 2.0448150634765625, | |
| "learning_rate": 0.0007039224426119902, | |
| "loss": 0.2412, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 2.0826833073322932, | |
| "grad_norm": 1.8044381141662598, | |
| "learning_rate": 0.000702808112324493, | |
| "loss": 0.3261, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 2.090483619344774, | |
| "grad_norm": 2.752220630645752, | |
| "learning_rate": 0.0007016937820369958, | |
| "loss": 0.2007, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 2.0982839313572543, | |
| "grad_norm": 1.4598050117492676, | |
| "learning_rate": 0.0007005794517494986, | |
| "loss": 0.1856, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 2.1060842433697347, | |
| "grad_norm": 3.578192710876465, | |
| "learning_rate": 0.0006994651214620014, | |
| "loss": 0.1991, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.1138845553822154, | |
| "grad_norm": 2.6971054077148438, | |
| "learning_rate": 0.0006983507911745042, | |
| "loss": 0.2134, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 2.1216848673946958, | |
| "grad_norm": 2.437596559524536, | |
| "learning_rate": 0.0006972364608870069, | |
| "loss": 0.228, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 2.129485179407176, | |
| "grad_norm": 2.6254658699035645, | |
| "learning_rate": 0.0006961221305995097, | |
| "loss": 0.1671, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 2.137285491419657, | |
| "grad_norm": 1.3765720129013062, | |
| "learning_rate": 0.0006950078003120125, | |
| "loss": 0.2391, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 2.145085803432137, | |
| "grad_norm": 2.192396879196167, | |
| "learning_rate": 0.0006938934700245153, | |
| "loss": 0.2331, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.152886115444618, | |
| "grad_norm": 1.4418809413909912, | |
| "learning_rate": 0.0006927791397370181, | |
| "loss": 0.2041, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 2.1606864274570983, | |
| "grad_norm": 2.553459882736206, | |
| "learning_rate": 0.0006916648094495208, | |
| "loss": 0.2342, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 2.1684867394695786, | |
| "grad_norm": 1.7199114561080933, | |
| "learning_rate": 0.0006905504791620236, | |
| "loss": 0.1841, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 2.1762870514820594, | |
| "grad_norm": 2.2145979404449463, | |
| "learning_rate": 0.0006894361488745264, | |
| "loss": 0.1821, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 2.1840873634945397, | |
| "grad_norm": 2.434779405593872, | |
| "learning_rate": 0.0006883218185870292, | |
| "loss": 0.2115, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.1918876755070205, | |
| "grad_norm": 1.0518474578857422, | |
| "learning_rate": 0.0006872074882995319, | |
| "loss": 0.2186, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 2.199687987519501, | |
| "grad_norm": 1.9856785535812378, | |
| "learning_rate": 0.0006860931580120348, | |
| "loss": 0.2448, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 2.207488299531981, | |
| "grad_norm": 17.3148136138916, | |
| "learning_rate": 0.0006849788277245376, | |
| "loss": 0.2372, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 2.215288611544462, | |
| "grad_norm": 3.4590959548950195, | |
| "learning_rate": 0.0006838644974370404, | |
| "loss": 0.3179, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 2.223088923556942, | |
| "grad_norm": 2.127650260925293, | |
| "learning_rate": 0.0006827501671495432, | |
| "loss": 0.2445, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.230889235569423, | |
| "grad_norm": 1.895729660987854, | |
| "learning_rate": 0.0006816358368620459, | |
| "loss": 0.1966, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 2.2386895475819033, | |
| "grad_norm": 1.4693467617034912, | |
| "learning_rate": 0.0006805215065745487, | |
| "loss": 0.2351, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 2.2464898595943836, | |
| "grad_norm": 1.500453233718872, | |
| "learning_rate": 0.0006794071762870515, | |
| "loss": 0.1946, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 2.2542901716068644, | |
| "grad_norm": 2.8631374835968018, | |
| "learning_rate": 0.0006782928459995543, | |
| "loss": 0.2367, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 2.2620904836193447, | |
| "grad_norm": 1.5281766653060913, | |
| "learning_rate": 0.000677178515712057, | |
| "loss": 0.1855, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.2698907956318255, | |
| "grad_norm": 2.3027195930480957, | |
| "learning_rate": 0.0006760641854245598, | |
| "loss": 0.2117, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 2.277691107644306, | |
| "grad_norm": 2.9962668418884277, | |
| "learning_rate": 0.0006749498551370626, | |
| "loss": 0.2441, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 2.285491419656786, | |
| "grad_norm": 2.489192008972168, | |
| "learning_rate": 0.0006738355248495654, | |
| "loss": 0.2212, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 2.293291731669267, | |
| "grad_norm": 1.366945743560791, | |
| "learning_rate": 0.0006727211945620682, | |
| "loss": 0.2003, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 2.3010920436817472, | |
| "grad_norm": 1.4768056869506836, | |
| "learning_rate": 0.000671606864274571, | |
| "loss": 0.3107, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.308892355694228, | |
| "grad_norm": 1.797979474067688, | |
| "learning_rate": 0.0006704925339870738, | |
| "loss": 0.1978, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 2.3166926677067083, | |
| "grad_norm": 1.9439573287963867, | |
| "learning_rate": 0.0006693782036995766, | |
| "loss": 0.2306, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 2.3244929797191887, | |
| "grad_norm": 1.582478642463684, | |
| "learning_rate": 0.0006682638734120794, | |
| "loss": 0.2079, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 2.3322932917316694, | |
| "grad_norm": 2.1245157718658447, | |
| "learning_rate": 0.0006671495431245821, | |
| "loss": 0.2258, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 2.3400936037441498, | |
| "grad_norm": 2.427675724029541, | |
| "learning_rate": 0.0006660352128370849, | |
| "loss": 0.2846, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.34789391575663, | |
| "grad_norm": 0.9095527529716492, | |
| "learning_rate": 0.0006649208825495877, | |
| "loss": 0.1746, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 2.355694227769111, | |
| "grad_norm": 2.0468294620513916, | |
| "learning_rate": 0.0006638065522620905, | |
| "loss": 0.2645, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 2.363494539781591, | |
| "grad_norm": 1.5703836679458618, | |
| "learning_rate": 0.0006626922219745933, | |
| "loss": 0.1896, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 2.371294851794072, | |
| "grad_norm": 2.37263822555542, | |
| "learning_rate": 0.000661577891687096, | |
| "loss": 0.232, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 2.3790951638065523, | |
| "grad_norm": 1.6041433811187744, | |
| "learning_rate": 0.0006604635613995988, | |
| "loss": 0.2135, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.3868954758190326, | |
| "grad_norm": 1.87883722782135, | |
| "learning_rate": 0.0006593492311121016, | |
| "loss": 0.1993, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 2.3946957878315134, | |
| "grad_norm": 2.5502099990844727, | |
| "learning_rate": 0.0006582349008246044, | |
| "loss": 0.2468, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 2.4024960998439937, | |
| "grad_norm": 2.681384801864624, | |
| "learning_rate": 0.0006571205705371071, | |
| "loss": 0.2364, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 2.410296411856474, | |
| "grad_norm": 1.2032707929611206, | |
| "learning_rate": 0.00065600624024961, | |
| "loss": 0.2732, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 2.418096723868955, | |
| "grad_norm": 1.553661584854126, | |
| "learning_rate": 0.0006548919099621128, | |
| "loss": 0.2214, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.425897035881435, | |
| "grad_norm": 0.9736389517784119, | |
| "learning_rate": 0.0006537775796746156, | |
| "loss": 0.1778, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 2.433697347893916, | |
| "grad_norm": 1.911352276802063, | |
| "learning_rate": 0.0006526632493871184, | |
| "loss": 0.2062, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 2.4414976599063962, | |
| "grad_norm": 1.4338595867156982, | |
| "learning_rate": 0.0006515489190996211, | |
| "loss": 0.193, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 2.4492979719188765, | |
| "grad_norm": 1.3027153015136719, | |
| "learning_rate": 0.0006504345888121239, | |
| "loss": 0.3175, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 2.4570982839313573, | |
| "grad_norm": 2.262709140777588, | |
| "learning_rate": 0.0006493202585246267, | |
| "loss": 0.2874, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.4648985959438376, | |
| "grad_norm": 1.36016845703125, | |
| "learning_rate": 0.0006482059282371295, | |
| "loss": 0.1603, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 2.4726989079563184, | |
| "grad_norm": 3.441779613494873, | |
| "learning_rate": 0.0006470915979496322, | |
| "loss": 0.4564, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 2.4804992199687987, | |
| "grad_norm": 1.8022549152374268, | |
| "learning_rate": 0.000645977267662135, | |
| "loss": 0.1928, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 2.488299531981279, | |
| "grad_norm": 2.104497194290161, | |
| "learning_rate": 0.0006448629373746378, | |
| "loss": 0.2047, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 2.49609984399376, | |
| "grad_norm": 2.5888454914093018, | |
| "learning_rate": 0.0006437486070871406, | |
| "loss": 0.2591, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.50390015600624, | |
| "grad_norm": 1.3476183414459229, | |
| "learning_rate": 0.0006426342767996434, | |
| "loss": 0.2636, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 2.511700468018721, | |
| "grad_norm": 2.888965606689453, | |
| "learning_rate": 0.0006415199465121462, | |
| "loss": 0.216, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 2.5195007800312013, | |
| "grad_norm": 1.8190357685089111, | |
| "learning_rate": 0.000640405616224649, | |
| "loss": 0.3498, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 2.5273010920436816, | |
| "grad_norm": 1.5132287740707397, | |
| "learning_rate": 0.0006392912859371518, | |
| "loss": 0.227, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 2.5351014040561624, | |
| "grad_norm": 2.8061325550079346, | |
| "learning_rate": 0.0006381769556496546, | |
| "loss": 0.2089, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.5429017160686427, | |
| "grad_norm": 2.2521767616271973, | |
| "learning_rate": 0.0006370626253621573, | |
| "loss": 0.2362, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 2.5507020280811235, | |
| "grad_norm": 1.4635623693466187, | |
| "learning_rate": 0.0006359482950746601, | |
| "loss": 0.1901, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 2.5585023400936038, | |
| "grad_norm": 1.9882755279541016, | |
| "learning_rate": 0.0006348339647871629, | |
| "loss": 0.2387, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 2.566302652106084, | |
| "grad_norm": 6.737502098083496, | |
| "learning_rate": 0.0006337196344996657, | |
| "loss": 0.2278, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 2.574102964118565, | |
| "grad_norm": 1.686926245689392, | |
| "learning_rate": 0.0006326053042121685, | |
| "loss": 0.3118, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.581903276131045, | |
| "grad_norm": 1.436584234237671, | |
| "learning_rate": 0.0006314909739246712, | |
| "loss": 0.1787, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 2.589703588143526, | |
| "grad_norm": 3.646476984024048, | |
| "learning_rate": 0.000630376643637174, | |
| "loss": 0.2165, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 2.5975039001560063, | |
| "grad_norm": 1.8787113428115845, | |
| "learning_rate": 0.0006292623133496768, | |
| "loss": 0.1993, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 2.6053042121684866, | |
| "grad_norm": 2.4485440254211426, | |
| "learning_rate": 0.0006281479830621796, | |
| "loss": 0.24, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 2.6131045241809674, | |
| "grad_norm": 2.73197865486145, | |
| "learning_rate": 0.0006270336527746824, | |
| "loss": 0.228, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.6209048361934477, | |
| "grad_norm": 3.2943315505981445, | |
| "learning_rate": 0.0006259193224871852, | |
| "loss": 0.2289, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 2.6287051482059285, | |
| "grad_norm": 2.165308952331543, | |
| "learning_rate": 0.000624804992199688, | |
| "loss": 0.2435, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 2.636505460218409, | |
| "grad_norm": 2.3766629695892334, | |
| "learning_rate": 0.0006236906619121908, | |
| "loss": 0.26, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 2.644305772230889, | |
| "grad_norm": 1.1527057886123657, | |
| "learning_rate": 0.0006225763316246936, | |
| "loss": 0.2486, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 2.6521060842433695, | |
| "grad_norm": 2.6304874420166016, | |
| "learning_rate": 0.0006214620013371963, | |
| "loss": 0.3827, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.6599063962558502, | |
| "grad_norm": 1.5219537019729614, | |
| "learning_rate": 0.0006203476710496991, | |
| "loss": 0.2231, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 2.667706708268331, | |
| "grad_norm": 1.9267528057098389, | |
| "learning_rate": 0.0006192333407622019, | |
| "loss": 0.2468, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 2.6755070202808113, | |
| "grad_norm": 2.247861385345459, | |
| "learning_rate": 0.0006181190104747047, | |
| "loss": 0.2463, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 2.6833073322932917, | |
| "grad_norm": 2.6133053302764893, | |
| "learning_rate": 0.0006170046801872074, | |
| "loss": 0.2636, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 2.691107644305772, | |
| "grad_norm": 1.4675954580307007, | |
| "learning_rate": 0.0006158903498997102, | |
| "loss": 0.2141, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.6989079563182528, | |
| "grad_norm": 3.3972527980804443, | |
| "learning_rate": 0.000614776019612213, | |
| "loss": 0.2102, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 2.706708268330733, | |
| "grad_norm": 2.0020527839660645, | |
| "learning_rate": 0.0006136616893247158, | |
| "loss": 0.2618, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 2.714508580343214, | |
| "grad_norm": 1.4799424409866333, | |
| "learning_rate": 0.0006125473590372186, | |
| "loss": 0.2644, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 2.722308892355694, | |
| "grad_norm": 2.207921028137207, | |
| "learning_rate": 0.0006114330287497214, | |
| "loss": 0.2496, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 2.7301092043681745, | |
| "grad_norm": 2.7361607551574707, | |
| "learning_rate": 0.0006103186984622242, | |
| "loss": 0.1917, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.7379095163806553, | |
| "grad_norm": 2.6031532287597656, | |
| "learning_rate": 0.000609204368174727, | |
| "loss": 0.2358, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 2.7457098283931356, | |
| "grad_norm": 1.442651629447937, | |
| "learning_rate": 0.0006080900378872299, | |
| "loss": 0.2929, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 2.7535101404056164, | |
| "grad_norm": 2.853076457977295, | |
| "learning_rate": 0.0006069757075997325, | |
| "loss": 0.2287, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 2.7613104524180967, | |
| "grad_norm": 1.827863335609436, | |
| "learning_rate": 0.0006058613773122353, | |
| "loss": 0.284, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 2.769110764430577, | |
| "grad_norm": 1.29642915725708, | |
| "learning_rate": 0.0006047470470247382, | |
| "loss": 0.2156, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.776911076443058, | |
| "grad_norm": 2.0758543014526367, | |
| "learning_rate": 0.000603632716737241, | |
| "loss": 0.4312, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 2.784711388455538, | |
| "grad_norm": 2.1832942962646484, | |
| "learning_rate": 0.0006025183864497438, | |
| "loss": 0.22, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 2.792511700468019, | |
| "grad_norm": 1.541040301322937, | |
| "learning_rate": 0.0006014040561622464, | |
| "loss": 0.2452, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 2.800312012480499, | |
| "grad_norm": 1.5947539806365967, | |
| "learning_rate": 0.0006002897258747492, | |
| "loss": 0.2708, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 2.8081123244929795, | |
| "grad_norm": 2.130390167236328, | |
| "learning_rate": 0.000599175395587252, | |
| "loss": 0.2194, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.8159126365054603, | |
| "grad_norm": 2.382166862487793, | |
| "learning_rate": 0.0005980610652997549, | |
| "loss": 0.1931, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 2.8237129485179406, | |
| "grad_norm": 4.421852111816406, | |
| "learning_rate": 0.0005969467350122577, | |
| "loss": 0.3081, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 2.8315132605304214, | |
| "grad_norm": 1.1889768838882446, | |
| "learning_rate": 0.0005958324047247605, | |
| "loss": 0.2134, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 2.8393135725429017, | |
| "grad_norm": 2.6204874515533447, | |
| "learning_rate": 0.0005947180744372633, | |
| "loss": 0.2128, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 2.847113884555382, | |
| "grad_norm": 1.4705913066864014, | |
| "learning_rate": 0.0005936037441497661, | |
| "loss": 0.1894, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.854914196567863, | |
| "grad_norm": 3.110135555267334, | |
| "learning_rate": 0.0005924894138622688, | |
| "loss": 0.2072, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 2.862714508580343, | |
| "grad_norm": 1.3255491256713867, | |
| "learning_rate": 0.0005913750835747716, | |
| "loss": 0.2325, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 2.870514820592824, | |
| "grad_norm": 2.2520713806152344, | |
| "learning_rate": 0.0005902607532872744, | |
| "loss": 0.2121, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 2.8783151326053042, | |
| "grad_norm": 1.4630913734436035, | |
| "learning_rate": 0.0005891464229997772, | |
| "loss": 0.2281, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 2.8861154446177846, | |
| "grad_norm": 2.0491292476654053, | |
| "learning_rate": 0.00058803209271228, | |
| "loss": 0.2227, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.8939157566302653, | |
| "grad_norm": 6.133053302764893, | |
| "learning_rate": 0.0005869177624247827, | |
| "loss": 0.3106, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 2.9017160686427457, | |
| "grad_norm": 2.3226382732391357, | |
| "learning_rate": 0.0005858034321372855, | |
| "loss": 0.2193, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 2.9095163806552264, | |
| "grad_norm": 1.351330041885376, | |
| "learning_rate": 0.0005846891018497883, | |
| "loss": 0.1928, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 2.9173166926677068, | |
| "grad_norm": 0.9889002442359924, | |
| "learning_rate": 0.0005835747715622911, | |
| "loss": 0.2395, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 2.925117004680187, | |
| "grad_norm": 3.9231808185577393, | |
| "learning_rate": 0.0005824604412747938, | |
| "loss": 0.2288, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.932917316692668, | |
| "grad_norm": 1.1299773454666138, | |
| "learning_rate": 0.0005813461109872967, | |
| "loss": 0.1996, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 2.940717628705148, | |
| "grad_norm": 1.894411563873291, | |
| "learning_rate": 0.0005802317806997995, | |
| "loss": 0.2444, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 2.948517940717629, | |
| "grad_norm": 3.100918769836426, | |
| "learning_rate": 0.0005791174504123023, | |
| "loss": 0.2723, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 2.9563182527301093, | |
| "grad_norm": 2.921398639678955, | |
| "learning_rate": 0.0005780031201248051, | |
| "loss": 0.1963, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 2.9641185647425896, | |
| "grad_norm": 2.898193120956421, | |
| "learning_rate": 0.0005768887898373078, | |
| "loss": 0.2262, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.97191887675507, | |
| "grad_norm": 1.8510135412216187, | |
| "learning_rate": 0.0005757744595498106, | |
| "loss": 0.2253, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 2.9797191887675507, | |
| "grad_norm": 2.716972827911377, | |
| "learning_rate": 0.0005746601292623134, | |
| "loss": 0.222, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 2.9875195007800315, | |
| "grad_norm": 2.466111660003662, | |
| "learning_rate": 0.0005735457989748162, | |
| "loss": 0.2903, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 2.995319812792512, | |
| "grad_norm": 2.409747838973999, | |
| "learning_rate": 0.0005724314686873189, | |
| "loss": 0.3088, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.34428906440734863, | |
| "eval_runtime": 557.5413, | |
| "eval_samples_per_second": 0.986, | |
| "eval_steps_per_second": 0.986, | |
| "eval_wer": 24.454527901139215, | |
| "step": 3846 | |
| }, | |
| { | |
| "epoch": 3.003120124804992, | |
| "grad_norm": 1.5137571096420288, | |
| "learning_rate": 0.0005713171383998217, | |
| "loss": 0.197, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 3.010920436817473, | |
| "grad_norm": 0.7653738856315613, | |
| "learning_rate": 0.0005702028081123245, | |
| "loss": 0.1295, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 3.0187207488299532, | |
| "grad_norm": 1.05947744846344, | |
| "learning_rate": 0.0005690884778248273, | |
| "loss": 0.1684, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 3.0265210608424336, | |
| "grad_norm": 1.4757158756256104, | |
| "learning_rate": 0.0005679741475373301, | |
| "loss": 0.1379, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 3.0343213728549143, | |
| "grad_norm": 1.789844274520874, | |
| "learning_rate": 0.0005668598172498329, | |
| "loss": 0.1711, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 3.0421216848673946, | |
| "grad_norm": 1.6123414039611816, | |
| "learning_rate": 0.0005657454869623357, | |
| "loss": 0.1375, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.049921996879875, | |
| "grad_norm": 1.1085964441299438, | |
| "learning_rate": 0.0005646311566748385, | |
| "loss": 0.1552, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 3.0577223088923557, | |
| "grad_norm": 0.5497006773948669, | |
| "learning_rate": 0.0005635168263873413, | |
| "loss": 0.2185, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 3.065522620904836, | |
| "grad_norm": 1.584539532661438, | |
| "learning_rate": 0.000562402496099844, | |
| "loss": 0.1398, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 3.073322932917317, | |
| "grad_norm": 1.2666114568710327, | |
| "learning_rate": 0.0005612881658123468, | |
| "loss": 0.1372, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 3.081123244929797, | |
| "grad_norm": 2.3011374473571777, | |
| "learning_rate": 0.0005601738355248496, | |
| "loss": 0.1354, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 3.0889235569422775, | |
| "grad_norm": 1.05606210231781, | |
| "learning_rate": 0.0005590595052373524, | |
| "loss": 0.1158, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 3.0967238689547583, | |
| "grad_norm": 1.0332001447677612, | |
| "learning_rate": 0.0005579451749498552, | |
| "loss": 0.1333, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 3.1045241809672386, | |
| "grad_norm": 1.020912766456604, | |
| "learning_rate": 0.0005568308446623579, | |
| "loss": 0.1259, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 3.1123244929797194, | |
| "grad_norm": 1.2610992193222046, | |
| "learning_rate": 0.0005557165143748607, | |
| "loss": 0.1391, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 3.1201248049921997, | |
| "grad_norm": 1.1720095872879028, | |
| "learning_rate": 0.0005546021840873635, | |
| "loss": 0.188, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.12792511700468, | |
| "grad_norm": 3.7483229637145996, | |
| "learning_rate": 0.0005534878537998663, | |
| "loss": 0.1198, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 3.135725429017161, | |
| "grad_norm": 0.9843854308128357, | |
| "learning_rate": 0.000552373523512369, | |
| "loss": 0.1405, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 3.143525741029641, | |
| "grad_norm": 2.162191152572632, | |
| "learning_rate": 0.0005512591932248719, | |
| "loss": 0.1268, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 3.151326053042122, | |
| "grad_norm": 1.1201051473617554, | |
| "learning_rate": 0.0005501448629373747, | |
| "loss": 0.1354, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 3.159126365054602, | |
| "grad_norm": 8.070413589477539, | |
| "learning_rate": 0.0005490305326498775, | |
| "loss": 0.1438, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 3.1669266770670825, | |
| "grad_norm": 0.971108078956604, | |
| "learning_rate": 0.0005479162023623803, | |
| "loss": 0.1521, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 3.1747269890795633, | |
| "grad_norm": 0.9375523924827576, | |
| "learning_rate": 0.000546801872074883, | |
| "loss": 0.1313, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 3.1825273010920436, | |
| "grad_norm": 1.3351547718048096, | |
| "learning_rate": 0.0005456875417873858, | |
| "loss": 0.1626, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 3.1903276131045244, | |
| "grad_norm": 2.073784589767456, | |
| "learning_rate": 0.0005445732114998886, | |
| "loss": 0.1435, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 3.1981279251170047, | |
| "grad_norm": 1.691977620124817, | |
| "learning_rate": 0.0005434588812123914, | |
| "loss": 0.1742, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.205928237129485, | |
| "grad_norm": 22.18892478942871, | |
| "learning_rate": 0.0005423445509248941, | |
| "loss": 0.1618, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 3.213728549141966, | |
| "grad_norm": 1.7861751317977905, | |
| "learning_rate": 0.0005412302206373969, | |
| "loss": 0.1351, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 3.221528861154446, | |
| "grad_norm": 1.1942836046218872, | |
| "learning_rate": 0.0005401158903498997, | |
| "loss": 0.1403, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 3.2293291731669265, | |
| "grad_norm": 4.223365306854248, | |
| "learning_rate": 0.0005390015600624025, | |
| "loss": 0.1568, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 3.2371294851794072, | |
| "grad_norm": 1.828805685043335, | |
| "learning_rate": 0.0005378872297749053, | |
| "loss": 0.1732, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 3.2449297971918876, | |
| "grad_norm": 1.3445240259170532, | |
| "learning_rate": 0.0005367728994874081, | |
| "loss": 0.1609, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 3.2527301092043683, | |
| "grad_norm": 1.8210989236831665, | |
| "learning_rate": 0.0005356585691999109, | |
| "loss": 0.1529, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 3.2605304212168487, | |
| "grad_norm": 1.5427830219268799, | |
| "learning_rate": 0.0005345442389124137, | |
| "loss": 0.1245, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 3.268330733229329, | |
| "grad_norm": 2.216970920562744, | |
| "learning_rate": 0.0005334299086249165, | |
| "loss": 0.1321, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 3.2761310452418098, | |
| "grad_norm": 2.470158338546753, | |
| "learning_rate": 0.0005323155783374192, | |
| "loss": 0.1466, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.28393135725429, | |
| "grad_norm": 1.8444827795028687, | |
| "learning_rate": 0.000531201248049922, | |
| "loss": 0.141, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 3.291731669266771, | |
| "grad_norm": 1.771625280380249, | |
| "learning_rate": 0.0005300869177624248, | |
| "loss": 0.1443, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 3.299531981279251, | |
| "grad_norm": 2.486222267150879, | |
| "learning_rate": 0.0005289725874749276, | |
| "loss": 0.1665, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 3.3073322932917315, | |
| "grad_norm": 2.0185546875, | |
| "learning_rate": 0.0005278582571874304, | |
| "loss": 0.2224, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 3.3151326053042123, | |
| "grad_norm": 1.810857892036438, | |
| "learning_rate": 0.0005267439268999331, | |
| "loss": 0.1384, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 3.3229329173166926, | |
| "grad_norm": 0.9884628057479858, | |
| "learning_rate": 0.0005256295966124359, | |
| "loss": 0.1028, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 3.330733229329173, | |
| "grad_norm": 0.9811989068984985, | |
| "learning_rate": 0.0005245152663249387, | |
| "loss": 0.1327, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 3.3385335413416537, | |
| "grad_norm": 0.9268475770950317, | |
| "learning_rate": 0.0005234009360374415, | |
| "loss": 0.2011, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 3.346333853354134, | |
| "grad_norm": 2.9813990592956543, | |
| "learning_rate": 0.0005222866057499443, | |
| "loss": 0.1729, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 3.354134165366615, | |
| "grad_norm": 1.216805338859558, | |
| "learning_rate": 0.0005211722754624471, | |
| "loss": 0.148, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.361934477379095, | |
| "grad_norm": 4.585384845733643, | |
| "learning_rate": 0.0005200579451749499, | |
| "loss": 0.28, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 3.3697347893915754, | |
| "grad_norm": 1.331865906715393, | |
| "learning_rate": 0.0005189436148874527, | |
| "loss": 0.1757, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 3.377535101404056, | |
| "grad_norm": 3.4767305850982666, | |
| "learning_rate": 0.0005178292845999555, | |
| "loss": 0.1955, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 3.3853354134165365, | |
| "grad_norm": 1.2598906755447388, | |
| "learning_rate": 0.0005167149543124582, | |
| "loss": 0.1633, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 3.3931357254290173, | |
| "grad_norm": 1.9768121242523193, | |
| "learning_rate": 0.000515600624024961, | |
| "loss": 0.1314, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 3.4009360374414976, | |
| "grad_norm": 1.916244387626648, | |
| "learning_rate": 0.0005144862937374638, | |
| "loss": 0.1826, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 3.408736349453978, | |
| "grad_norm": 1.159989595413208, | |
| "learning_rate": 0.0005133719634499666, | |
| "loss": 0.1655, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 3.4165366614664587, | |
| "grad_norm": 2.1428520679473877, | |
| "learning_rate": 0.0005122576331624693, | |
| "loss": 0.1868, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 3.424336973478939, | |
| "grad_norm": 1.3343071937561035, | |
| "learning_rate": 0.0005111433028749721, | |
| "loss": 0.1539, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 3.43213728549142, | |
| "grad_norm": 2.33966326713562, | |
| "learning_rate": 0.0005100289725874749, | |
| "loss": 0.1613, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.4399375975039, | |
| "grad_norm": 1.662204384803772, | |
| "learning_rate": 0.0005089146422999777, | |
| "loss": 0.1554, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 3.4477379095163805, | |
| "grad_norm": 0.7760083675384521, | |
| "learning_rate": 0.0005078003120124805, | |
| "loss": 0.0962, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 3.4555382215288613, | |
| "grad_norm": 1.860338807106018, | |
| "learning_rate": 0.0005066859817249833, | |
| "loss": 0.1757, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 3.4633385335413416, | |
| "grad_norm": 0.6259675025939941, | |
| "learning_rate": 0.0005055716514374861, | |
| "loss": 0.176, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 3.4711388455538223, | |
| "grad_norm": 2.819291591644287, | |
| "learning_rate": 0.0005044573211499889, | |
| "loss": 0.2447, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 3.4789391575663027, | |
| "grad_norm": 1.125827431678772, | |
| "learning_rate": 0.0005033429908624917, | |
| "loss": 0.1265, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 3.486739469578783, | |
| "grad_norm": 1.1929935216903687, | |
| "learning_rate": 0.0005022286605749944, | |
| "loss": 0.1428, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 3.4945397815912638, | |
| "grad_norm": 1.2320295572280884, | |
| "learning_rate": 0.0005011143302874972, | |
| "loss": 0.1372, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 3.502340093603744, | |
| "grad_norm": 1.1627320051193237, | |
| "learning_rate": 0.0005, | |
| "loss": 0.1143, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 3.510140405616225, | |
| "grad_norm": 2.7850723266601562, | |
| "learning_rate": 0.0004988856697125028, | |
| "loss": 0.1431, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.517940717628705, | |
| "grad_norm": 1.2920804023742676, | |
| "learning_rate": 0.0004977713394250056, | |
| "loss": 0.17, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 3.5257410296411855, | |
| "grad_norm": 1.2807234525680542, | |
| "learning_rate": 0.0004966570091375084, | |
| "loss": 0.1379, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 3.5335413416536663, | |
| "grad_norm": 1.2454224824905396, | |
| "learning_rate": 0.0004955426788500111, | |
| "loss": 0.1439, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 3.5413416536661466, | |
| "grad_norm": 3.7264480590820312, | |
| "learning_rate": 0.0004944283485625139, | |
| "loss": 0.1691, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 3.5491419656786274, | |
| "grad_norm": 1.653113842010498, | |
| "learning_rate": 0.0004933140182750167, | |
| "loss": 0.157, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 3.5569422776911077, | |
| "grad_norm": 2.0576372146606445, | |
| "learning_rate": 0.0004921996879875195, | |
| "loss": 0.171, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 3.564742589703588, | |
| "grad_norm": 1.499207615852356, | |
| "learning_rate": 0.0004910853577000223, | |
| "loss": 0.1297, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 3.572542901716069, | |
| "grad_norm": 1.2240318059921265, | |
| "learning_rate": 0.0004899710274125251, | |
| "loss": 0.2274, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 3.580343213728549, | |
| "grad_norm": 1.4562804698944092, | |
| "learning_rate": 0.0004888566971250279, | |
| "loss": 0.1884, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 3.58814352574103, | |
| "grad_norm": 2.0862207412719727, | |
| "learning_rate": 0.00048774236683753067, | |
| "loss": 0.1323, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.5959438377535102, | |
| "grad_norm": 1.8791660070419312, | |
| "learning_rate": 0.00048662803655003347, | |
| "loss": 0.1446, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 3.6037441497659906, | |
| "grad_norm": 2.589106798171997, | |
| "learning_rate": 0.0004855137062625362, | |
| "loss": 0.1722, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 3.611544461778471, | |
| "grad_norm": 1.3053058385849, | |
| "learning_rate": 0.000484399375975039, | |
| "loss": 0.1458, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 3.6193447737909517, | |
| "grad_norm": 1.4898595809936523, | |
| "learning_rate": 0.00048328504568754177, | |
| "loss": 0.155, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 3.627145085803432, | |
| "grad_norm": 1.9109569787979126, | |
| "learning_rate": 0.00048217071540004457, | |
| "loss": 0.1526, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 3.6349453978159127, | |
| "grad_norm": 2.045905351638794, | |
| "learning_rate": 0.00048105638511254737, | |
| "loss": 0.1281, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 3.642745709828393, | |
| "grad_norm": 2.0706069469451904, | |
| "learning_rate": 0.0004799420548250502, | |
| "loss": 0.2016, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 3.6505460218408734, | |
| "grad_norm": 1.3242971897125244, | |
| "learning_rate": 0.000478827724537553, | |
| "loss": 0.1715, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 3.658346333853354, | |
| "grad_norm": 1.2207064628601074, | |
| "learning_rate": 0.0004777133942500557, | |
| "loss": 0.1262, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 3.6661466458658345, | |
| "grad_norm": 2.0521817207336426, | |
| "learning_rate": 0.0004765990639625585, | |
| "loss": 0.1929, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.6739469578783153, | |
| "grad_norm": 1.009435772895813, | |
| "learning_rate": 0.00047548473367506127, | |
| "loss": 0.2248, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 3.6817472698907956, | |
| "grad_norm": 1.105904221534729, | |
| "learning_rate": 0.0004743704033875641, | |
| "loss": 0.1554, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 3.689547581903276, | |
| "grad_norm": 1.9131145477294922, | |
| "learning_rate": 0.0004732560731000669, | |
| "loss": 0.1435, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 3.6973478939157567, | |
| "grad_norm": 4.082576751708984, | |
| "learning_rate": 0.0004721417428125697, | |
| "loss": 0.1539, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 3.705148205928237, | |
| "grad_norm": 0.8368641138076782, | |
| "learning_rate": 0.0004710274125250724, | |
| "loss": 0.1296, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 3.712948517940718, | |
| "grad_norm": 2.7137794494628906, | |
| "learning_rate": 0.00046991308223757523, | |
| "loss": 0.1557, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 3.720748829953198, | |
| "grad_norm": 1.2786542177200317, | |
| "learning_rate": 0.00046879875195007803, | |
| "loss": 0.1529, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 3.7285491419656784, | |
| "grad_norm": 2.214386463165283, | |
| "learning_rate": 0.0004676844216625808, | |
| "loss": 0.143, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 3.736349453978159, | |
| "grad_norm": 1.2340818643569946, | |
| "learning_rate": 0.0004665700913750836, | |
| "loss": 0.1481, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 3.7441497659906395, | |
| "grad_norm": 1.804880976676941, | |
| "learning_rate": 0.0004654557610875864, | |
| "loss": 0.1385, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.7519500780031203, | |
| "grad_norm": 1.0058701038360596, | |
| "learning_rate": 0.0004643414308000892, | |
| "loss": 0.2446, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 3.7597503900156006, | |
| "grad_norm": 2.6180830001831055, | |
| "learning_rate": 0.00046322710051259193, | |
| "loss": 0.18, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 3.767550702028081, | |
| "grad_norm": 0.8924421072006226, | |
| "learning_rate": 0.00046211277022509473, | |
| "loss": 0.1533, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 3.7753510140405617, | |
| "grad_norm": 1.5280059576034546, | |
| "learning_rate": 0.0004609984399375975, | |
| "loss": 0.1567, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 3.783151326053042, | |
| "grad_norm": 2.1860077381134033, | |
| "learning_rate": 0.0004598841096501003, | |
| "loss": 0.1502, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 3.790951638065523, | |
| "grad_norm": 1.2397303581237793, | |
| "learning_rate": 0.00045876977936260314, | |
| "loss": 0.163, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 3.798751950078003, | |
| "grad_norm": 1.8644335269927979, | |
| "learning_rate": 0.0004576554490751059, | |
| "loss": 0.1843, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 3.8065522620904835, | |
| "grad_norm": 4.985640525817871, | |
| "learning_rate": 0.0004565411187876087, | |
| "loss": 0.2699, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 3.8143525741029642, | |
| "grad_norm": 1.4370672702789307, | |
| "learning_rate": 0.00045542678850011144, | |
| "loss": 0.1285, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 3.8221528861154446, | |
| "grad_norm": 1.725677728652954, | |
| "learning_rate": 0.00045431245821261424, | |
| "loss": 0.1609, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.8299531981279253, | |
| "grad_norm": 0.9739437699317932, | |
| "learning_rate": 0.000453198127925117, | |
| "loss": 0.1614, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 3.8377535101404057, | |
| "grad_norm": 3.672434091567993, | |
| "learning_rate": 0.0004520837976376198, | |
| "loss": 0.1747, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 3.845553822152886, | |
| "grad_norm": 1.3917264938354492, | |
| "learning_rate": 0.0004509694673501226, | |
| "loss": 0.159, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 3.8533541341653668, | |
| "grad_norm": 2.578519105911255, | |
| "learning_rate": 0.0004498551370626254, | |
| "loss": 0.1394, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 3.861154446177847, | |
| "grad_norm": 1.3072192668914795, | |
| "learning_rate": 0.00044874080677512814, | |
| "loss": 0.1167, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 3.868954758190328, | |
| "grad_norm": 1.1134214401245117, | |
| "learning_rate": 0.00044762647648763094, | |
| "loss": 0.1445, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 3.876755070202808, | |
| "grad_norm": 2.7288825511932373, | |
| "learning_rate": 0.00044651214620013374, | |
| "loss": 0.1693, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 3.8845553822152885, | |
| "grad_norm": 1.1238129138946533, | |
| "learning_rate": 0.0004453978159126365, | |
| "loss": 0.1455, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 3.892355694227769, | |
| "grad_norm": 1.7059211730957031, | |
| "learning_rate": 0.0004442834856251393, | |
| "loss": 0.1069, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 3.9001560062402496, | |
| "grad_norm": 1.0301696062088013, | |
| "learning_rate": 0.0004431691553376421, | |
| "loss": 0.3035, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.9079563182527304, | |
| "grad_norm": 1.744986891746521, | |
| "learning_rate": 0.0004420548250501449, | |
| "loss": 0.1249, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 3.9157566302652107, | |
| "grad_norm": 0.8731406331062317, | |
| "learning_rate": 0.00044094049476264764, | |
| "loss": 0.1714, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 3.923556942277691, | |
| "grad_norm": 1.1749571561813354, | |
| "learning_rate": 0.00043982616447515045, | |
| "loss": 0.264, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 3.9313572542901714, | |
| "grad_norm": 2.552839756011963, | |
| "learning_rate": 0.0004387118341876532, | |
| "loss": 0.2517, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 3.939157566302652, | |
| "grad_norm": 1.9722734689712524, | |
| "learning_rate": 0.000437597503900156, | |
| "loss": 0.1854, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 3.9469578783151325, | |
| "grad_norm": 2.063805341720581, | |
| "learning_rate": 0.0004364831736126588, | |
| "loss": 0.1574, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 3.954758190327613, | |
| "grad_norm": 4.838432312011719, | |
| "learning_rate": 0.0004353688433251616, | |
| "loss": 0.1939, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 3.9625585023400935, | |
| "grad_norm": 1.9519829750061035, | |
| "learning_rate": 0.0004342545130376644, | |
| "loss": 0.1334, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 3.970358814352574, | |
| "grad_norm": 1.3953014612197876, | |
| "learning_rate": 0.00043314018275016715, | |
| "loss": 0.1504, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 3.9781591263650546, | |
| "grad_norm": 1.6272999048233032, | |
| "learning_rate": 0.00043202585246266995, | |
| "loss": 0.153, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.985959438377535, | |
| "grad_norm": 1.610538125038147, | |
| "learning_rate": 0.0004309115221751727, | |
| "loss": 0.1727, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 3.9937597503900157, | |
| "grad_norm": 1.6635684967041016, | |
| "learning_rate": 0.0004297971918876755, | |
| "loss": 0.1316, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.31802308559417725, | |
| "eval_runtime": 526.9062, | |
| "eval_samples_per_second": 1.044, | |
| "eval_steps_per_second": 1.044, | |
| "eval_wer": 21.84784707472485, | |
| "step": 5128 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 8974, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.51799588339712e+18, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |