| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.7096917276557995, |
| "eval_steps": 100, |
| "global_step": 1200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005914097730464996, |
| "grad_norm": 5.2180352210998535, |
| "learning_rate": 1.8e-05, |
| "loss": 5.424943542480468, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.011828195460929992, |
| "grad_norm": 4.250089168548584, |
| "learning_rate": 3.8e-05, |
| "loss": 4.415760040283203, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.01774229319139499, |
| "grad_norm": 1.9420628547668457, |
| "learning_rate": 5.8e-05, |
| "loss": 3.3620418548583983, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.023656390921859984, |
| "grad_norm": 1.2024555206298828, |
| "learning_rate": 7.800000000000001e-05, |
| "loss": 2.703177833557129, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.02957048865232498, |
| "grad_norm": 0.8111334443092346, |
| "learning_rate": 9.8e-05, |
| "loss": 2.4913867950439452, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03548458638278998, |
| "grad_norm": 1.530247688293457, |
| "learning_rate": 0.000118, |
| "loss": 2.1947019577026365, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.04139868411325497, |
| "grad_norm": 1.1452527046203613, |
| "learning_rate": 0.000138, |
| "loss": 2.0160297393798827, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.04731278184371997, |
| "grad_norm": 0.9424326419830322, |
| "learning_rate": 0.00015800000000000002, |
| "loss": 2.019273567199707, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.05322687957418496, |
| "grad_norm": 1.8786909580230713, |
| "learning_rate": 0.00017800000000000002, |
| "loss": 2.1498268127441404, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.05914097730464996, |
| "grad_norm": 1.6165390014648438, |
| "learning_rate": 0.00019800000000000002, |
| "loss": 1.7820545196533204, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.05914097730464996, |
| "eval_loss": 1.9202771186828613, |
| "eval_runtime": 73.1239, |
| "eval_samples_per_second": 20.554, |
| "eval_steps_per_second": 20.554, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.06505507503511496, |
| "grad_norm": 1.7568436861038208, |
| "learning_rate": 0.00019999838371969757, |
| "loss": 1.8914276123046876, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.07096917276557996, |
| "grad_norm": 1.8437843322753906, |
| "learning_rate": 0.00019999279664498885, |
| "loss": 2.0527172088623047, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.07688327049604494, |
| "grad_norm": 1.4281401634216309, |
| "learning_rate": 0.0001999832190447127, |
| "loss": 1.5733016014099122, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.08279736822650995, |
| "grad_norm": 1.5277072191238403, |
| "learning_rate": 0.00019996965130109317, |
| "loss": 1.6824659347534179, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.08871146595697493, |
| "grad_norm": 1.022353172302246, |
| "learning_rate": 0.00019995209395559364, |
| "loss": 1.5354164123535157, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.09462556368743993, |
| "grad_norm": 1.2274901866912842, |
| "learning_rate": 0.0001999305477088949, |
| "loss": 1.6824844360351563, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.10053966141790494, |
| "grad_norm": 0.8041242361068726, |
| "learning_rate": 0.00019990501342086731, |
| "loss": 1.7703128814697267, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.10645375914836992, |
| "grad_norm": 1.3753713369369507, |
| "learning_rate": 0.00019987549211053667, |
| "loss": 1.8396759033203125, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.11236785687883492, |
| "grad_norm": 1.3298134803771973, |
| "learning_rate": 0.00019984198495604324, |
| "loss": 1.9465333938598632, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.11828195460929992, |
| "grad_norm": 1.3702126741409302, |
| "learning_rate": 0.00019980449329459488, |
| "loss": 1.6306316375732421, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.11828195460929992, |
| "eval_loss": 1.798754334449768, |
| "eval_runtime": 72.8882, |
| "eval_samples_per_second": 20.621, |
| "eval_steps_per_second": 20.621, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.12419605233976491, |
| "grad_norm": 1.1323479413986206, |
| "learning_rate": 0.00019976301862241374, |
| "loss": 1.8380266189575196, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.1301101500702299, |
| "grad_norm": 1.1640722751617432, |
| "learning_rate": 0.0001997175625946764, |
| "loss": 1.4453817367553712, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.13602424780069491, |
| "grad_norm": 0.5486578941345215, |
| "learning_rate": 0.00019966812702544803, |
| "loss": 1.6653100967407226, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.14193834553115992, |
| "grad_norm": 0.8607975244522095, |
| "learning_rate": 0.0001996147138876097, |
| "loss": 1.6253957748413086, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.1478524432616249, |
| "grad_norm": 1.1080461740493774, |
| "learning_rate": 0.00019955732531277992, |
| "loss": 1.7128946304321289, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.1537665409920899, |
| "grad_norm": 1.1675671339035034, |
| "learning_rate": 0.00019949596359122938, |
| "loss": 1.4436548233032227, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.1596806387225549, |
| "grad_norm": 0.7477723956108093, |
| "learning_rate": 0.00019943063117178967, |
| "loss": 1.7975515365600585, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.1655947364530199, |
| "grad_norm": 0.6756472587585449, |
| "learning_rate": 0.00019936133066175555, |
| "loss": 1.557283306121826, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.1715088341834849, |
| "grad_norm": 1.1745697259902954, |
| "learning_rate": 0.00019928806482678076, |
| "loss": 1.562563991546631, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.17742293191394987, |
| "grad_norm": 0.8426774144172668, |
| "learning_rate": 0.00019921083659076784, |
| "loss": 1.5517897605895996, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.17742293191394987, |
| "eval_loss": 1.7579774856567383, |
| "eval_runtime": 72.5035, |
| "eval_samples_per_second": 20.73, |
| "eval_steps_per_second": 20.73, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.18333702964441487, |
| "grad_norm": 0.47852444648742676, |
| "learning_rate": 0.00019912964903575123, |
| "loss": 1.516515350341797, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.18925112737487987, |
| "grad_norm": 1.277382731437683, |
| "learning_rate": 0.00019904450540177452, |
| "loss": 1.6330038070678712, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.19516522510534487, |
| "grad_norm": 0.6363489031791687, |
| "learning_rate": 0.000198955409086761, |
| "loss": 1.6154375076293945, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.20107932283580987, |
| "grad_norm": 1.1205073595046997, |
| "learning_rate": 0.0001988623636463779, |
| "loss": 1.6122692108154297, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.20699342056627484, |
| "grad_norm": 1.0732148885726929, |
| "learning_rate": 0.00019876537279389493, |
| "loss": 1.8808629989624024, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.21290751829673984, |
| "grad_norm": 1.1619702577590942, |
| "learning_rate": 0.0001986644404000356, |
| "loss": 1.471642303466797, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.21882161602720485, |
| "grad_norm": 1.0153286457061768, |
| "learning_rate": 0.00019855957049282302, |
| "loss": 1.5440849304199218, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.22473571375766985, |
| "grad_norm": 0.712260901927948, |
| "learning_rate": 0.0001984507672574192, |
| "loss": 1.5636033058166503, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.23064981148813485, |
| "grad_norm": 1.073734998703003, |
| "learning_rate": 0.00019833803503595777, |
| "loss": 1.9609308242797852, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.23656390921859985, |
| "grad_norm": 1.0462348461151123, |
| "learning_rate": 0.00019822137832737098, |
| "loss": 1.4796849250793458, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.23656390921859985, |
| "eval_loss": 1.7245409488677979, |
| "eval_runtime": 73.5942, |
| "eval_samples_per_second": 20.423, |
| "eval_steps_per_second": 20.423, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.24247800694906482, |
| "grad_norm": 0.6932668089866638, |
| "learning_rate": 0.00019810080178720997, |
| "loss": 1.6222585678100585, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.24839210467952982, |
| "grad_norm": 1.1368882656097412, |
| "learning_rate": 0.00019797631022745895, |
| "loss": 1.7100778579711915, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.25430620240999485, |
| "grad_norm": 0.8383238315582275, |
| "learning_rate": 0.00019784790861634342, |
| "loss": 1.4401205062866211, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.2602203001404598, |
| "grad_norm": 0.8375674486160278, |
| "learning_rate": 0.00019771560207813155, |
| "loss": 1.6655614852905274, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.2661343978709248, |
| "grad_norm": 1.1425868272781372, |
| "learning_rate": 0.00019757939589292996, |
| "loss": 1.549529457092285, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.27204849560138983, |
| "grad_norm": 1.4245469570159912, |
| "learning_rate": 0.00019743929549647285, |
| "loss": 1.3803598403930664, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.2779625933318548, |
| "grad_norm": 0.5421410799026489, |
| "learning_rate": 0.00019729530647990507, |
| "loss": 1.4490249633789063, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.28387669106231983, |
| "grad_norm": 1.3041306734085083, |
| "learning_rate": 0.0001971474345895591, |
| "loss": 1.872774887084961, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.2897907887927848, |
| "grad_norm": 0.5212927460670471, |
| "learning_rate": 0.0001969956857267256, |
| "loss": 1.5607462882995606, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.2957048865232498, |
| "grad_norm": 1.2135010957717896, |
| "learning_rate": 0.00019684006594741806, |
| "loss": 1.7492666244506836, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2957048865232498, |
| "eval_loss": 1.6998990774154663, |
| "eval_runtime": 73.5394, |
| "eval_samples_per_second": 20.438, |
| "eval_steps_per_second": 20.438, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3016189842537148, |
| "grad_norm": 0.6691944599151611, |
| "learning_rate": 0.0001966805814621308, |
| "loss": 1.4699878692626953, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.3075330819841798, |
| "grad_norm": 1.1748926639556885, |
| "learning_rate": 0.00019651723863559151, |
| "loss": 1.374594020843506, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.3134471797146448, |
| "grad_norm": 0.6550143361091614, |
| "learning_rate": 0.00019635004398650704, |
| "loss": 1.6440496444702148, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.3193612774451098, |
| "grad_norm": 1.100718379020691, |
| "learning_rate": 0.00019617900418730325, |
| "loss": 1.8898862838745116, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.32527537517557475, |
| "grad_norm": 0.9766672849655151, |
| "learning_rate": 0.00019600412606385868, |
| "loss": 1.3778706550598145, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.3311894729060398, |
| "grad_norm": 1.0393085479736328, |
| "learning_rate": 0.00019582541659523233, |
| "loss": 1.670578956604004, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.33710357063650476, |
| "grad_norm": 1.0927174091339111, |
| "learning_rate": 0.000195642882913385, |
| "loss": 1.419454288482666, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.3430176683669698, |
| "grad_norm": 1.0158544778823853, |
| "learning_rate": 0.0001954565323028946, |
| "loss": 1.5266822814941405, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.34893176609743476, |
| "grad_norm": 0.6772964000701904, |
| "learning_rate": 0.00019526637220066567, |
| "loss": 1.3381025314331054, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.35484586382789973, |
| "grad_norm": 0.7992995381355286, |
| "learning_rate": 0.0001950724101956323, |
| "loss": 1.573591709136963, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.35484586382789973, |
| "eval_loss": 1.678901195526123, |
| "eval_runtime": 73.2508, |
| "eval_samples_per_second": 20.519, |
| "eval_steps_per_second": 20.519, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.36075996155836476, |
| "grad_norm": 0.6109696626663208, |
| "learning_rate": 0.00019487465402845557, |
| "loss": 1.3037412643432618, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.36667405928882973, |
| "grad_norm": 0.9946038126945496, |
| "learning_rate": 0.0001946731115912143, |
| "loss": 1.6696025848388671, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.37258815701929476, |
| "grad_norm": 0.7230735421180725, |
| "learning_rate": 0.00019446779092709035, |
| "loss": 2.071816825866699, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.37850225474975974, |
| "grad_norm": 1.1146931648254395, |
| "learning_rate": 0.00019425870023004763, |
| "loss": 1.8486011505126954, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.3844163524802247, |
| "grad_norm": 1.1962776184082031, |
| "learning_rate": 0.0001940458478445049, |
| "loss": 1.691929244995117, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.39033045021068974, |
| "grad_norm": 1.0420191287994385, |
| "learning_rate": 0.0001938292422650029, |
| "loss": 1.482090950012207, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.3962445479411547, |
| "grad_norm": 1.2826957702636719, |
| "learning_rate": 0.0001936088921358654, |
| "loss": 1.7656858444213868, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.40215864567161974, |
| "grad_norm": 1.3457494974136353, |
| "learning_rate": 0.00019338480625085403, |
| "loss": 1.577683162689209, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.4080727434020847, |
| "grad_norm": 0.6976184248924255, |
| "learning_rate": 0.00019315699355281754, |
| "loss": 1.5872076988220214, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.4139868411325497, |
| "grad_norm": 1.1318235397338867, |
| "learning_rate": 0.00019292546313333478, |
| "loss": 1.3969389915466308, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.4139868411325497, |
| "eval_loss": 1.664991021156311, |
| "eval_runtime": 79.1652, |
| "eval_samples_per_second": 18.986, |
| "eval_steps_per_second": 18.986, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.4199009388630147, |
| "grad_norm": 1.1243572235107422, |
| "learning_rate": 0.0001926902242323519, |
| "loss": 1.6042152404785157, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.4258150365934797, |
| "grad_norm": 1.1055822372436523, |
| "learning_rate": 0.00019245128623781368, |
| "loss": 1.9429645538330078, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.4317291343239447, |
| "grad_norm": 1.0177127122879028, |
| "learning_rate": 0.00019220865868528874, |
| "loss": 1.8175060272216796, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.4376432320544097, |
| "grad_norm": 0.81801837682724, |
| "learning_rate": 0.00019196235125758907, |
| "loss": 1.7039094924926759, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.4435573297848747, |
| "grad_norm": 1.0496128797531128, |
| "learning_rate": 0.00019171237378438365, |
| "loss": 1.6293031692504882, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.4494714275153397, |
| "grad_norm": 1.0377826690673828, |
| "learning_rate": 0.00019145873624180606, |
| "loss": 1.598710060119629, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.45538552524580467, |
| "grad_norm": 0.7196580171585083, |
| "learning_rate": 0.00019120144875205638, |
| "loss": 1.4807973861694337, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.4612996229762697, |
| "grad_norm": 0.8920046091079712, |
| "learning_rate": 0.00019094052158299737, |
| "loss": 1.567158031463623, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.46721372070673467, |
| "grad_norm": 0.6375955939292908, |
| "learning_rate": 0.0001906759651477445, |
| "loss": 1.4658871650695802, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.4731278184371997, |
| "grad_norm": 1.1181913614273071, |
| "learning_rate": 0.00019040779000425046, |
| "loss": 1.5718339920043944, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.4731278184371997, |
| "eval_loss": 1.6554144620895386, |
| "eval_runtime": 72.7518, |
| "eval_samples_per_second": 20.659, |
| "eval_steps_per_second": 20.659, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.47904191616766467, |
| "grad_norm": 1.0074750185012817, |
| "learning_rate": 0.00019013600685488386, |
| "loss": 1.9402446746826172, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.48495601389812965, |
| "grad_norm": 1.205483078956604, |
| "learning_rate": 0.00018986062654600204, |
| "loss": 1.7085580825805664, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.4908701116285947, |
| "grad_norm": 1.1965411901474, |
| "learning_rate": 0.00018958166006751833, |
| "loss": 1.6262685775756835, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.49678420935905965, |
| "grad_norm": 0.49395665526390076, |
| "learning_rate": 0.0001892991185524633, |
| "loss": 0.988164234161377, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.5026983070895247, |
| "grad_norm": 0.5631020069122314, |
| "learning_rate": 0.0001890130132765406, |
| "loss": 1.140714740753174, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.5086124048199897, |
| "grad_norm": 0.9770917892456055, |
| "learning_rate": 0.0001887233556576768, |
| "loss": 1.5494470596313477, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.5145265025504546, |
| "grad_norm": 1.101150393486023, |
| "learning_rate": 0.00018843015725556606, |
| "loss": 1.5402188301086426, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.5204406002809197, |
| "grad_norm": 0.5578099489212036, |
| "learning_rate": 0.00018813342977120834, |
| "loss": 1.4955373764038087, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.5263546980113847, |
| "grad_norm": 0.5652608871459961, |
| "learning_rate": 0.0001878331850464428, |
| "loss": 1.2806446075439453, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.5322687957418496, |
| "grad_norm": 0.895172119140625, |
| "learning_rate": 0.00018752943506347513, |
| "loss": 1.4293109893798828, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5322687957418496, |
| "eval_loss": 1.6352789402008057, |
| "eval_runtime": 80.8942, |
| "eval_samples_per_second": 18.58, |
| "eval_steps_per_second": 18.58, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5381828934723146, |
| "grad_norm": 0.9870158433914185, |
| "learning_rate": 0.0001872221919443992, |
| "loss": 1.7498294830322265, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.5440969912027797, |
| "grad_norm": 0.8602092266082764, |
| "learning_rate": 0.00018691146795071344, |
| "loss": 1.4824910163879395, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.5500110889332446, |
| "grad_norm": 0.8170483112335205, |
| "learning_rate": 0.00018659727548283158, |
| "loss": 1.6763690948486327, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.5559251866637096, |
| "grad_norm": 0.7792373895645142, |
| "learning_rate": 0.00018627962707958755, |
| "loss": 1.7227746963500976, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.5618392843941746, |
| "grad_norm": 0.5349337458610535, |
| "learning_rate": 0.00018595853541773528, |
| "loss": 1.3281389236450196, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.5677533821246397, |
| "grad_norm": 1.0277243852615356, |
| "learning_rate": 0.00018563401331144267, |
| "loss": 1.7380207061767579, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.5736674798551046, |
| "grad_norm": 0.776485800743103, |
| "learning_rate": 0.00018530607371178024, |
| "loss": 1.4630879402160644, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.5795815775855696, |
| "grad_norm": 1.0938167572021484, |
| "learning_rate": 0.0001849747297062043, |
| "loss": 1.4838638305664062, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.5854956753160346, |
| "grad_norm": 0.65599524974823, |
| "learning_rate": 0.00018463999451803466, |
| "loss": 1.3914700508117677, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.5914097730464996, |
| "grad_norm": 0.732549250125885, |
| "learning_rate": 0.00018430188150592682, |
| "loss": 1.5909401893615722, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5914097730464996, |
| "eval_loss": 1.630129337310791, |
| "eval_runtime": 75.4466, |
| "eval_samples_per_second": 19.921, |
| "eval_steps_per_second": 19.921, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5973238707769646, |
| "grad_norm": 0.99312824010849, |
| "learning_rate": 0.000183960404163339, |
| "loss": 1.5250720024108886, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.6032379685074296, |
| "grad_norm": 0.6171141862869263, |
| "learning_rate": 0.00018361557611799344, |
| "loss": 1.434851837158203, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.6091520662378945, |
| "grad_norm": 0.5486176013946533, |
| "learning_rate": 0.00018326741113133284, |
| "loss": 1.3386061668395997, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.6150661639683596, |
| "grad_norm": 1.2491796016693115, |
| "learning_rate": 0.0001829159230979708, |
| "loss": 1.6222826004028321, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.6209802616988246, |
| "grad_norm": 1.112250566482544, |
| "learning_rate": 0.00018256112604513768, |
| "loss": 1.5261116027832031, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.6268943594292896, |
| "grad_norm": 1.1598140001296997, |
| "learning_rate": 0.00018220303413212042, |
| "loss": 1.768622589111328, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.6328084571597545, |
| "grad_norm": 1.1736910343170166, |
| "learning_rate": 0.0001818416616496979, |
| "loss": 1.7666938781738282, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.6387225548902196, |
| "grad_norm": 1.0749396085739136, |
| "learning_rate": 0.00018147702301957015, |
| "loss": 1.5079362869262696, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.6446366526206846, |
| "grad_norm": 1.0853893756866455, |
| "learning_rate": 0.00018110913279378323, |
| "loss": 1.6800750732421874, |
| "step": 1090 |
| }, |
| { |
| "epoch": 0.6505507503511495, |
| "grad_norm": 1.4306273460388184, |
| "learning_rate": 0.00018073800565414824, |
| "loss": 1.597597026824951, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.6505507503511495, |
| "eval_loss": 1.6213648319244385, |
| "eval_runtime": 76.3887, |
| "eval_samples_per_second": 19.676, |
| "eval_steps_per_second": 19.676, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.6564648480816145, |
| "grad_norm": 0.9976714253425598, |
| "learning_rate": 0.00018036365641165548, |
| "loss": 1.5979490280151367, |
| "step": 1110 |
| }, |
| { |
| "epoch": 0.6623789458120796, |
| "grad_norm": 1.050653338432312, |
| "learning_rate": 0.0001799861000058833, |
| "loss": 1.4489970207214355, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.6682930435425446, |
| "grad_norm": 0.7765175700187683, |
| "learning_rate": 0.000179605351504402, |
| "loss": 1.6825380325317383, |
| "step": 1130 |
| }, |
| { |
| "epoch": 0.6742071412730095, |
| "grad_norm": 0.606610119342804, |
| "learning_rate": 0.00017922142610217242, |
| "loss": 1.295132827758789, |
| "step": 1140 |
| }, |
| { |
| "epoch": 0.6801212390034745, |
| "grad_norm": 1.0216376781463623, |
| "learning_rate": 0.00017883433912093958, |
| "loss": 1.6792869567871094, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.6860353367339396, |
| "grad_norm": 1.4456205368041992, |
| "learning_rate": 0.0001784441060086212, |
| "loss": 1.3720205307006836, |
| "step": 1160 |
| }, |
| { |
| "epoch": 0.6919494344644045, |
| "grad_norm": 0.698352038860321, |
| "learning_rate": 0.0001780507423386912, |
| "loss": 1.4192619323730469, |
| "step": 1170 |
| }, |
| { |
| "epoch": 0.6978635321948695, |
| "grad_norm": 0.6584682464599609, |
| "learning_rate": 0.00017765426380955817, |
| "loss": 1.1639105796813964, |
| "step": 1180 |
| }, |
| { |
| "epoch": 0.7037776299253345, |
| "grad_norm": 1.0101826190948486, |
| "learning_rate": 0.0001772546862439391, |
| "loss": 1.6940256118774415, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.7096917276557995, |
| "grad_norm": 1.281262755393982, |
| "learning_rate": 0.0001768520255882274, |
| "loss": 1.7322410583496093, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.7096917276557995, |
| "eval_loss": 1.6151379346847534, |
| "eval_runtime": 76.2088, |
| "eval_samples_per_second": 19.722, |
| "eval_steps_per_second": 19.722, |
| "step": 1200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 5073, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.816491476825088e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
