{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.5712447732389836, "eval_steps": 500, "global_step": 2000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.012865873271148279, "grad_norm": 1.9229779243469238, "learning_rate": 4.5e-06, "loss": 3.131273651123047, "step": 10 }, { "epoch": 0.025731746542296558, "grad_norm": 1.5902587175369263, "learning_rate": 9.5e-06, "loss": 2.9485034942626953, "step": 20 }, { "epoch": 0.03859761981344484, "grad_norm": 1.4832384586334229, "learning_rate": 1.45e-05, "loss": 2.8429616928100585, "step": 30 }, { "epoch": 0.051463493084593116, "grad_norm": 1.5204882621765137, "learning_rate": 1.9500000000000003e-05, "loss": 2.842297172546387, "step": 40 }, { "epoch": 0.0643293663557414, "grad_norm": 1.284334659576416, "learning_rate": 2.45e-05, "loss": 2.686099624633789, "step": 50 }, { "epoch": 0.07719523962688968, "grad_norm": 1.3740590810775757, "learning_rate": 2.95e-05, "loss": 2.704598808288574, "step": 60 }, { "epoch": 0.09006111289803795, "grad_norm": 1.8986170291900635, "learning_rate": 3.45e-05, "loss": 2.7180160522460937, "step": 70 }, { "epoch": 0.10292698616918623, "grad_norm": 1.3583054542541504, "learning_rate": 3.9500000000000005e-05, "loss": 2.6402956008911134, "step": 80 }, { "epoch": 0.11579285944033452, "grad_norm": 1.3155664205551147, "learning_rate": 4.4500000000000004e-05, "loss": 2.5915760040283202, "step": 90 }, { "epoch": 0.1286587327114828, "grad_norm": 1.3320988416671753, "learning_rate": 4.9500000000000004e-05, "loss": 2.708783721923828, "step": 100 }, { "epoch": 0.14152460598263106, "grad_norm": 1.3533453941345215, "learning_rate": 5.45e-05, "loss": 2.63944091796875, "step": 110 }, { "epoch": 0.15439047925377936, "grad_norm": 1.381525993347168, "learning_rate": 5.95e-05, "loss": 2.5701248168945314, "step": 120 }, { "epoch": 0.16725635252492763, "grad_norm": 1.3566951751708984, "learning_rate": 6.450000000000001e-05, "loss": 2.6062128067016603, "step": 130 }, { "epoch": 0.1801222257960759, "grad_norm": 1.487178087234497, "learning_rate": 6.95e-05, "loss": 2.635186767578125, "step": 140 }, { "epoch": 0.1929880990672242, "grad_norm": 1.2946099042892456, "learning_rate": 7.450000000000001e-05, "loss": 2.6566871643066405, "step": 150 }, { "epoch": 0.20585397233837247, "grad_norm": 1.475674033164978, "learning_rate": 7.950000000000001e-05, "loss": 2.572060775756836, "step": 160 }, { "epoch": 0.21871984560952074, "grad_norm": 2.1084113121032715, "learning_rate": 8.450000000000001e-05, "loss": 2.5129844665527346, "step": 170 }, { "epoch": 0.23158571888066903, "grad_norm": 1.3213211297988892, "learning_rate": 8.950000000000001e-05, "loss": 2.5856971740722656, "step": 180 }, { "epoch": 0.2444515921518173, "grad_norm": 1.4585779905319214, "learning_rate": 9.449999999999999e-05, "loss": 2.5216487884521483, "step": 190 }, { "epoch": 0.2573174654229656, "grad_norm": 1.3272548913955688, "learning_rate": 9.95e-05, "loss": 2.6331623077392576, "step": 200 }, { "epoch": 0.2701833386941139, "grad_norm": 1.2405599355697632, "learning_rate": 9.999561136371555e-05, "loss": 2.5547435760498045, "step": 210 }, { "epoch": 0.2830492119652621, "grad_norm": 1.337110161781311, "learning_rate": 9.99804417582332e-05, "loss": 2.5865997314453124, "step": 220 }, { "epoch": 0.2959150852364104, "grad_norm": 1.7058504819869995, "learning_rate": 9.995444028966307e-05, "loss": 2.6484580993652345, "step": 230 }, { "epoch": 0.3087809585075587, "grad_norm": 1.493330717086792, "learning_rate": 9.991761259309634e-05, "loss": 2.592666435241699, "step": 240 }, { "epoch": 0.32164683177870695, "grad_norm": 1.3736194372177124, "learning_rate": 9.986996664990636e-05, "loss": 2.570736312866211, "step": 250 }, { "epoch": 0.33451270504985525, "grad_norm": 1.5846096277236938, "learning_rate": 9.981151278601899e-05, "loss": 2.46077938079834, "step": 260 }, { "epoch": 0.34737857832100355, "grad_norm": 1.4125752449035645, "learning_rate": 9.974226366967458e-05, "loss": 2.60552864074707, "step": 270 }, { "epoch": 0.3602444515921518, "grad_norm": 1.5096468925476074, "learning_rate": 9.96622343086826e-05, "loss": 2.442317771911621, "step": 280 }, { "epoch": 0.3731103248633001, "grad_norm": 1.4419718980789185, "learning_rate": 9.957144204716908e-05, "loss": 2.5379360198974608, "step": 290 }, { "epoch": 0.3859761981344484, "grad_norm": 1.3278104066848755, "learning_rate": 9.946990656181781e-05, "loss": 2.6057674407958986, "step": 300 }, { "epoch": 0.39884207140559663, "grad_norm": 1.232189655303955, "learning_rate": 9.935764985760583e-05, "loss": 2.5440723419189455, "step": 310 }, { "epoch": 0.41170794467674493, "grad_norm": 1.587889552116394, "learning_rate": 9.923469626303466e-05, "loss": 2.4821359634399416, "step": 320 }, { "epoch": 0.42457381794789323, "grad_norm": 1.4969263076782227, "learning_rate": 9.910107242485756e-05, "loss": 2.4613248825073244, "step": 330 }, { "epoch": 0.43743969121904147, "grad_norm": 1.2167006731033325, "learning_rate": 9.895680730230483e-05, "loss": 2.439605712890625, "step": 340 }, { "epoch": 0.45030556449018977, "grad_norm": 1.3582571744918823, "learning_rate": 9.880193216080749e-05, "loss": 2.4103574752807617, "step": 350 }, { "epoch": 0.46317143776133807, "grad_norm": 1.327419400215149, "learning_rate": 9.863648056522152e-05, "loss": 2.479293441772461, "step": 360 }, { "epoch": 0.4760373110324863, "grad_norm": 1.3256139755249023, "learning_rate": 9.846048837255353e-05, "loss": 2.478465270996094, "step": 370 }, { "epoch": 0.4889031843036346, "grad_norm": 1.35889732837677, "learning_rate": 9.827399372418978e-05, "loss": 2.435022735595703, "step": 380 }, { "epoch": 0.5017690575747829, "grad_norm": 1.214181900024414, "learning_rate": 9.807703703763015e-05, "loss": 2.5142974853515625, "step": 390 }, { "epoch": 0.5146349308459311, "grad_norm": 1.553303837776184, "learning_rate": 9.786966099772874e-05, "loss": 2.447306823730469, "step": 400 }, { "epoch": 0.5275008041170794, "grad_norm": 1.3571453094482422, "learning_rate": 9.765191054744305e-05, "loss": 2.484339141845703, "step": 410 }, { "epoch": 0.5403666773882277, "grad_norm": 1.59647798538208, "learning_rate": 9.742383287809399e-05, "loss": 2.365188980102539, "step": 420 }, { "epoch": 0.553232550659376, "grad_norm": 1.3741739988327026, "learning_rate": 9.718547741913833e-05, "loss": 2.4120407104492188, "step": 430 }, { "epoch": 0.5660984239305242, "grad_norm": 1.3817009925842285, "learning_rate": 9.693689582745644e-05, "loss": 2.410173225402832, "step": 440 }, { "epoch": 0.5789642972016725, "grad_norm": 1.3521440029144287, "learning_rate": 9.667814197615692e-05, "loss": 2.4579553604125977, "step": 450 }, { "epoch": 0.5918301704728208, "grad_norm": 1.580779790878296, "learning_rate": 9.640927194290116e-05, "loss": 2.4759321212768555, "step": 460 }, { "epoch": 0.6046960437439691, "grad_norm": 1.3386242389678955, "learning_rate": 9.613034399775016e-05, "loss": 2.4329578399658205, "step": 470 }, { "epoch": 0.6175619170151174, "grad_norm": 1.4756091833114624, "learning_rate": 9.584141859053602e-05, "loss": 2.486847686767578, "step": 480 }, { "epoch": 0.6304277902862657, "grad_norm": 1.225603461265564, "learning_rate": 9.554255833776119e-05, "loss": 2.4275352478027346, "step": 490 }, { "epoch": 0.6432936635574139, "grad_norm": 1.3665364980697632, "learning_rate": 9.523382800902804e-05, "loss": 2.390964889526367, "step": 500 }, { "epoch": 0.6561595368285622, "grad_norm": 1.400194764137268, "learning_rate": 9.4915294513002e-05, "loss": 2.471600341796875, "step": 510 }, { "epoch": 0.6690254100997105, "grad_norm": 1.2987993955612183, "learning_rate": 9.458702688291073e-05, "loss": 2.3756614685058595, "step": 520 }, { "epoch": 0.6818912833708588, "grad_norm": 1.1703332662582397, "learning_rate": 9.424909626158332e-05, "loss": 2.4364620208740235, "step": 530 }, { "epoch": 0.6947571566420071, "grad_norm": 1.3593236207962036, "learning_rate": 9.390157588603201e-05, "loss": 2.3480419158935546, "step": 540 }, { "epoch": 0.7076230299131554, "grad_norm": 1.2493035793304443, "learning_rate": 9.354454107158003e-05, "loss": 2.4248210906982424, "step": 550 }, { "epoch": 0.7204889031843036, "grad_norm": 1.2349282503128052, "learning_rate": 9.317806919553927e-05, "loss": 2.410304832458496, "step": 560 }, { "epoch": 0.7333547764554519, "grad_norm": 1.1844069957733154, "learning_rate": 9.280223968044073e-05, "loss": 2.4124820709228514, "step": 570 }, { "epoch": 0.7462206497266002, "grad_norm": 1.216843843460083, "learning_rate": 9.241713397682202e-05, "loss": 2.3515693664550783, "step": 580 }, { "epoch": 0.7590865229977485, "grad_norm": 1.2797318696975708, "learning_rate": 9.202283554557525e-05, "loss": 2.440851593017578, "step": 590 }, { "epoch": 0.7719523962688968, "grad_norm": 1.2528715133666992, "learning_rate": 9.161942983985916e-05, "loss": 2.4378475189208983, "step": 600 }, { "epoch": 0.7848182695400451, "grad_norm": 1.1354225873947144, "learning_rate": 9.120700428657954e-05, "loss": 2.3769287109375, "step": 610 }, { "epoch": 0.7976841428111933, "grad_norm": 1.293675422668457, "learning_rate": 9.078564826744188e-05, "loss": 2.3717182159423826, "step": 620 }, { "epoch": 0.8105500160823416, "grad_norm": 1.5594234466552734, "learning_rate": 9.035545309958046e-05, "loss": 2.3546916961669924, "step": 630 }, { "epoch": 0.8234158893534899, "grad_norm": 1.315688133239746, "learning_rate": 8.991651201576788e-05, "loss": 2.2907150268554686, "step": 640 }, { "epoch": 0.8362817626246382, "grad_norm": 1.37774658203125, "learning_rate": 8.946892014420935e-05, "loss": 2.3812816619873045, "step": 650 }, { "epoch": 0.8491476358957865, "grad_norm": 1.233496904373169, "learning_rate": 8.901277448792656e-05, "loss": 2.3371837615966795, "step": 660 }, { "epoch": 0.8620135091669348, "grad_norm": 1.1091872453689575, "learning_rate": 8.85481739037347e-05, "loss": 2.313151550292969, "step": 670 }, { "epoch": 0.8748793824380829, "grad_norm": 1.2073731422424316, "learning_rate": 8.807521908081822e-05, "loss": 2.319954681396484, "step": 680 }, { "epoch": 0.8877452557092312, "grad_norm": 1.48874831199646, "learning_rate": 8.759401251890921e-05, "loss": 2.4533824920654297, "step": 690 }, { "epoch": 0.9006111289803795, "grad_norm": 1.5078450441360474, "learning_rate": 8.710465850607337e-05, "loss": 2.3390689849853517, "step": 700 }, { "epoch": 0.9134770022515278, "grad_norm": 1.19990074634552, "learning_rate": 8.66072630961086e-05, "loss": 2.2620731353759767, "step": 710 }, { "epoch": 0.9263428755226761, "grad_norm": 1.1868500709533691, "learning_rate": 8.610193408556073e-05, "loss": 2.309833526611328, "step": 720 }, { "epoch": 0.9392087487938244, "grad_norm": 1.3001115322113037, "learning_rate": 8.558878099036169e-05, "loss": 2.444794845581055, "step": 730 }, { "epoch": 0.9520746220649726, "grad_norm": 1.3591334819793701, "learning_rate": 8.506791502209496e-05, "loss": 2.413535308837891, "step": 740 }, { "epoch": 0.9649404953361209, "grad_norm": 1.4358940124511719, "learning_rate": 8.453944906389353e-05, "loss": 2.3826751708984375, "step": 750 }, { "epoch": 0.9778063686072692, "grad_norm": 1.156792163848877, "learning_rate": 8.400349764597571e-05, "loss": 2.3242250442504884, "step": 760 }, { "epoch": 0.9906722418784175, "grad_norm": 1.2707802057266235, "learning_rate": 8.34601769208239e-05, "loss": 2.2294876098632814, "step": 770 }, { "epoch": 1.0025731746542297, "grad_norm": 1.155531644821167, "learning_rate": 8.290960463801174e-05, "loss": 2.3388866424560546, "step": 780 }, { "epoch": 1.0154390479253779, "grad_norm": 1.2098199129104614, "learning_rate": 8.23519001186852e-05, "loss": 2.022981643676758, "step": 790 }, { "epoch": 1.0283049211965263, "grad_norm": 1.2994295358657837, "learning_rate": 8.17871842297031e-05, "loss": 2.00899658203125, "step": 800 }, { "epoch": 1.0411707944676745, "grad_norm": 1.2398685216903687, "learning_rate": 8.12155793574425e-05, "loss": 1.9260929107666016, "step": 810 }, { "epoch": 1.0540366677388229, "grad_norm": 1.2227600812911987, "learning_rate": 8.063720938127506e-05, "loss": 1.9288578033447266, "step": 820 }, { "epoch": 1.066902541009971, "grad_norm": 2.119344711303711, "learning_rate": 8.00521996467194e-05, "loss": 2.1025238037109375, "step": 830 }, { "epoch": 1.0797684142811192, "grad_norm": 1.2340764999389648, "learning_rate": 7.946067693827617e-05, "loss": 1.9557228088378906, "step": 840 }, { "epoch": 1.0926342875522677, "grad_norm": 1.1174405813217163, "learning_rate": 7.886276945195099e-05, "loss": 1.9837318420410157, "step": 850 }, { "epoch": 1.1055001608234158, "grad_norm": 1.294333815574646, "learning_rate": 7.825860676747145e-05, "loss": 2.018222427368164, "step": 860 }, { "epoch": 1.1183660340945643, "grad_norm": 1.2146308422088623, "learning_rate": 7.764831982020455e-05, "loss": 1.957394790649414, "step": 870 }, { "epoch": 1.1312319073657124, "grad_norm": 1.3394722938537598, "learning_rate": 7.703204087277988e-05, "loss": 1.949086570739746, "step": 880 }, { "epoch": 1.1440977806368609, "grad_norm": 1.20905339717865, "learning_rate": 7.640990348642556e-05, "loss": 1.9966390609741211, "step": 890 }, { "epoch": 1.156963653908009, "grad_norm": 1.2661844491958618, "learning_rate": 7.57820424920225e-05, "loss": 1.9434684753417968, "step": 900 }, { "epoch": 1.1698295271791572, "grad_norm": 1.107378602027893, "learning_rate": 7.51485939608836e-05, "loss": 1.9927230834960938, "step": 910 }, { "epoch": 1.1826954004503056, "grad_norm": 1.355488657951355, "learning_rate": 7.450969517526412e-05, "loss": 2.0167285919189455, "step": 920 }, { "epoch": 1.1955612737214538, "grad_norm": 1.3436405658721924, "learning_rate": 7.386548459860953e-05, "loss": 1.9840282440185546, "step": 930 }, { "epoch": 1.208427146992602, "grad_norm": 1.1386462450027466, "learning_rate": 7.321610184554747e-05, "loss": 1.8912723541259766, "step": 940 }, { "epoch": 1.2212930202637504, "grad_norm": 1.1454792022705078, "learning_rate": 7.25616876516302e-05, "loss": 1.900678825378418, "step": 950 }, { "epoch": 1.2341588935348986, "grad_norm": 1.1625381708145142, "learning_rate": 7.190238384283412e-05, "loss": 1.9375591278076172, "step": 960 }, { "epoch": 1.247024766806047, "grad_norm": 1.3781540393829346, "learning_rate": 7.123833330482284e-05, "loss": 2.066437911987305, "step": 970 }, { "epoch": 1.2598906400771952, "grad_norm": 1.2113057374954224, "learning_rate": 7.056967995198082e-05, "loss": 1.9703704833984375, "step": 980 }, { "epoch": 1.2727565133483436, "grad_norm": 1.3010709285736084, "learning_rate": 6.989656869622397e-05, "loss": 2.0397720336914062, "step": 990 }, { "epoch": 1.2856223866194918, "grad_norm": 1.2311277389526367, "learning_rate": 6.92191454155939e-05, "loss": 1.9269041061401366, "step": 1000 }, { "epoch": 1.29848825989064, "grad_norm": 1.091778039932251, "learning_rate": 6.853755692264313e-05, "loss": 1.996831512451172, "step": 1010 }, { "epoch": 1.3113541331617884, "grad_norm": 1.4477002620697021, "learning_rate": 6.785195093261741e-05, "loss": 1.949301528930664, "step": 1020 }, { "epoch": 1.3242200064329366, "grad_norm": 1.1657599210739136, "learning_rate": 6.716247603144266e-05, "loss": 1.9906345367431642, "step": 1030 }, { "epoch": 1.337085879704085, "grad_norm": 1.0720555782318115, "learning_rate": 6.646928164352308e-05, "loss": 1.9201814651489257, "step": 1040 }, { "epoch": 1.3499517529752332, "grad_norm": 1.379020094871521, "learning_rate": 6.577251799935763e-05, "loss": 1.9012016296386718, "step": 1050 }, { "epoch": 1.3628176262463816, "grad_norm": 1.3552391529083252, "learning_rate": 6.507233610298174e-05, "loss": 1.9635028839111328, "step": 1060 }, { "epoch": 1.3756834995175298, "grad_norm": 1.272336721420288, "learning_rate": 6.436888769924142e-05, "loss": 2.034423828125, "step": 1070 }, { "epoch": 1.388549372788678, "grad_norm": 1.150260329246521, "learning_rate": 6.366232524090681e-05, "loss": 1.8565523147583007, "step": 1080 }, { "epoch": 1.4014152460598264, "grad_norm": 1.3935184478759766, "learning_rate": 6.295280185563226e-05, "loss": 1.940822219848633, "step": 1090 }, { "epoch": 1.4142811193309746, "grad_norm": 1.1125247478485107, "learning_rate": 6.224047131277033e-05, "loss": 1.9374893188476563, "step": 1100 }, { "epoch": 1.4271469926021227, "grad_norm": 1.4775182008743286, "learning_rate": 6.152548799004641e-05, "loss": 1.9341915130615235, "step": 1110 }, { "epoch": 1.4400128658732712, "grad_norm": 1.168436884880066, "learning_rate": 6.080800684010172e-05, "loss": 2.006146240234375, "step": 1120 }, { "epoch": 1.4528787391444196, "grad_norm": 1.2249674797058105, "learning_rate": 6.008818335691178e-05, "loss": 1.9467155456542968, "step": 1130 }, { "epoch": 1.4657446124155677, "grad_norm": 1.2196557521820068, "learning_rate": 5.936617354208722e-05, "loss": 1.9186494827270508, "step": 1140 }, { "epoch": 1.478610485686716, "grad_norm": 1.223923683166504, "learning_rate": 5.864213387106503e-05, "loss": 2.034763717651367, "step": 1150 }, { "epoch": 1.4914763589578643, "grad_norm": 1.2659380435943604, "learning_rate": 5.7916221259196693e-05, "loss": 1.9768272399902345, "step": 1160 }, { "epoch": 1.5043422322290125, "grad_norm": 1.4587719440460205, "learning_rate": 5.718859302774124e-05, "loss": 1.9238140106201171, "step": 1170 }, { "epoch": 1.5172081055001607, "grad_norm": 1.2151159048080444, "learning_rate": 5.645940686977033e-05, "loss": 1.9502479553222656, "step": 1180 }, { "epoch": 1.5300739787713091, "grad_norm": 1.2910637855529785, "learning_rate": 5.5728820815992546e-05, "loss": 1.9518865585327148, "step": 1190 }, { "epoch": 1.5429398520424575, "grad_norm": 1.3418300151824951, "learning_rate": 5.499699320050483e-05, "loss": 1.959632110595703, "step": 1200 }, { "epoch": 1.5558057253136055, "grad_norm": 1.335964322090149, "learning_rate": 5.426408262647784e-05, "loss": 1.8697946548461915, "step": 1210 }, { "epoch": 1.568671598584754, "grad_norm": 1.1634818315505981, "learning_rate": 5.353024793178325e-05, "loss": 2.0493751525878907, "step": 1220 }, { "epoch": 1.5815374718559023, "grad_norm": 1.2977160215377808, "learning_rate": 5.279564815457001e-05, "loss": 2.0341678619384767, "step": 1230 }, { "epoch": 1.5944033451270505, "grad_norm": 1.20073664188385, "learning_rate": 5.2060442498797335e-05, "loss": 1.8752460479736328, "step": 1240 }, { "epoch": 1.6072692183981987, "grad_norm": 1.2579463720321655, "learning_rate": 5.1324790299731695e-05, "loss": 1.8853199005126953, "step": 1250 }, { "epoch": 1.620135091669347, "grad_norm": 1.205967664718628, "learning_rate": 5.058885098941529e-05, "loss": 1.8524391174316406, "step": 1260 }, { "epoch": 1.6330009649404953, "grad_norm": 1.3424036502838135, "learning_rate": 4.9852784062113686e-05, "loss": 1.9468013763427734, "step": 1270 }, { "epoch": 1.6458668382116435, "grad_norm": 1.2947489023208618, "learning_rate": 4.911674903974983e-05, "loss": 2.009492874145508, "step": 1280 }, { "epoch": 1.6587327114827919, "grad_norm": 1.2692880630493164, "learning_rate": 4.838090543733222e-05, "loss": 1.9324432373046876, "step": 1290 }, { "epoch": 1.6715985847539403, "grad_norm": 1.2025070190429688, "learning_rate": 4.7645412728384356e-05, "loss": 1.9288585662841797, "step": 1300 }, { "epoch": 1.6844644580250885, "grad_norm": 1.2608730792999268, "learning_rate": 4.691043031038345e-05, "loss": 1.8749698638916015, "step": 1310 }, { "epoch": 1.6973303312962367, "grad_norm": 1.2710654735565186, "learning_rate": 4.617611747021543e-05, "loss": 1.8965923309326171, "step": 1320 }, { "epoch": 1.710196204567385, "grad_norm": 1.1973843574523926, "learning_rate": 4.544263334965389e-05, "loss": 1.9404924392700196, "step": 1330 }, { "epoch": 1.7230620778385333, "grad_norm": 1.3660880327224731, "learning_rate": 4.471013691087069e-05, "loss": 1.8931024551391602, "step": 1340 }, { "epoch": 1.7359279511096815, "grad_norm": 1.2408908605575562, "learning_rate": 4.397878690198523e-05, "loss": 1.9381546020507812, "step": 1350 }, { "epoch": 1.7487938243808299, "grad_norm": 1.249464511871338, "learning_rate": 4.3248741822660344e-05, "loss": 2.0181365966796876, "step": 1360 }, { "epoch": 1.7616596976519783, "grad_norm": 1.3093994855880737, "learning_rate": 4.252015988975183e-05, "loss": 1.9135875701904297, "step": 1370 }, { "epoch": 1.7745255709231265, "grad_norm": 1.3367854356765747, "learning_rate": 4.179319900301943e-05, "loss": 1.8839527130126954, "step": 1380 }, { "epoch": 1.7873914441942746, "grad_norm": 1.4029282331466675, "learning_rate": 4.1068016710906476e-05, "loss": 1.9376346588134765, "step": 1390 }, { "epoch": 1.800257317465423, "grad_norm": 1.1457457542419434, "learning_rate": 4.0344770176395606e-05, "loss": 1.958260726928711, "step": 1400 }, { "epoch": 1.8131231907365712, "grad_norm": 1.2105348110198975, "learning_rate": 3.962361614294818e-05, "loss": 1.9137763977050781, "step": 1410 }, { "epoch": 1.8259890640077194, "grad_norm": 1.5545076131820679, "learning_rate": 3.890471090053448e-05, "loss": 1.9242362976074219, "step": 1420 }, { "epoch": 1.8388549372788678, "grad_norm": 1.1947731971740723, "learning_rate": 3.818821025176212e-05, "loss": 1.8615493774414062, "step": 1430 }, { "epoch": 1.851720810550016, "grad_norm": 1.0786476135253906, "learning_rate": 3.7474269478110413e-05, "loss": 1.9201824188232421, "step": 1440 }, { "epoch": 1.8645866838211642, "grad_norm": 1.3867851495742798, "learning_rate": 3.676304330627721e-05, "loss": 1.852809524536133, "step": 1450 }, { "epoch": 1.8774525570923126, "grad_norm": 1.1828950643539429, "learning_rate": 3.605468587464641e-05, "loss": 1.9051380157470703, "step": 1460 }, { "epoch": 1.890318430363461, "grad_norm": 1.1371843814849854, "learning_rate": 3.534935069988268e-05, "loss": 1.9557598114013672, "step": 1470 }, { "epoch": 1.9031843036346092, "grad_norm": 1.2321115732192993, "learning_rate": 3.4647190643660976e-05, "loss": 1.9113624572753907, "step": 1480 }, { "epoch": 1.9160501769057574, "grad_norm": 1.3084759712219238, "learning_rate": 3.3948357879538186e-05, "loss": 1.860207748413086, "step": 1490 }, { "epoch": 1.9289160501769058, "grad_norm": 1.1466325521469116, "learning_rate": 3.3253003859973574e-05, "loss": 1.927144432067871, "step": 1500 }, { "epoch": 1.941781923448054, "grad_norm": 1.3287715911865234, "learning_rate": 3.2561279283505883e-05, "loss": 1.866561508178711, "step": 1510 }, { "epoch": 1.9546477967192022, "grad_norm": 1.1149462461471558, "learning_rate": 3.187333406209357e-05, "loss": 1.8511821746826171, "step": 1520 }, { "epoch": 1.9675136699903506, "grad_norm": 1.1395113468170166, "learning_rate": 3.118931728862548e-05, "loss": 1.955026626586914, "step": 1530 }, { "epoch": 1.980379543261499, "grad_norm": 1.2678197622299194, "learning_rate": 3.0509377204609303e-05, "loss": 1.8696395874023437, "step": 1540 }, { "epoch": 1.9932454165326472, "grad_norm": 1.2618764638900757, "learning_rate": 2.9833661168044268e-05, "loss": 1.9680551528930663, "step": 1550 }, { "epoch": 2.0051463493084594, "grad_norm": 1.1506320238113403, "learning_rate": 2.9162315621485425e-05, "loss": 1.7739978790283204, "step": 1560 }, { "epoch": 2.0180122225796078, "grad_norm": 1.1438027620315552, "learning_rate": 2.849548606030638e-05, "loss": 1.584134864807129, "step": 1570 }, { "epoch": 2.0308780958507557, "grad_norm": 1.0453646183013916, "learning_rate": 2.7833317001167113e-05, "loss": 1.5621303558349608, "step": 1580 }, { "epoch": 2.043743969121904, "grad_norm": 1.2313755750656128, "learning_rate": 2.7175951950694213e-05, "loss": 1.5715694427490234, "step": 1590 }, { "epoch": 2.0566098423930526, "grad_norm": 1.1432842016220093, "learning_rate": 2.6523533374379616e-05, "loss": 1.5611574172973632, "step": 1600 }, { "epoch": 2.0694757156642005, "grad_norm": 1.0692554712295532, "learning_rate": 2.587620266570542e-05, "loss": 1.560830020904541, "step": 1610 }, { "epoch": 2.082341588935349, "grad_norm": 1.2590630054473877, "learning_rate": 2.5234100115500643e-05, "loss": 1.5709400177001953, "step": 1620 }, { "epoch": 2.0952074622064973, "grad_norm": 1.2724279165267944, "learning_rate": 2.4597364881537116e-05, "loss": 1.5988688468933105, "step": 1630 }, { "epoch": 2.1080733354776457, "grad_norm": 1.2695716619491577, "learning_rate": 2.3966134958371038e-05, "loss": 1.5167072296142579, "step": 1640 }, { "epoch": 2.1209392087487937, "grad_norm": 1.3567490577697754, "learning_rate": 2.334054714743642e-05, "loss": 1.557693862915039, "step": 1650 }, { "epoch": 2.133805082019942, "grad_norm": 1.1806862354278564, "learning_rate": 2.2720737027397188e-05, "loss": 1.5348047256469726, "step": 1660 }, { "epoch": 2.1466709552910905, "grad_norm": 1.1810389757156372, "learning_rate": 2.2106838924764372e-05, "loss": 1.4987117767333984, "step": 1670 }, { "epoch": 2.1595368285622385, "grad_norm": 1.4680360555648804, "learning_rate": 2.1498985884784556e-05, "loss": 1.5722600936889648, "step": 1680 }, { "epoch": 2.172402701833387, "grad_norm": 1.1552165746688843, "learning_rate": 2.089730964260604e-05, "loss": 1.4727974891662599, "step": 1690 }, { "epoch": 2.1852685751045353, "grad_norm": 1.2037168741226196, "learning_rate": 2.030194059472888e-05, "loss": 1.5671278953552246, "step": 1700 }, { "epoch": 2.1981344483756837, "grad_norm": 1.2964924573898315, "learning_rate": 1.9713007770745208e-05, "loss": 1.5296795845031739, "step": 1710 }, { "epoch": 2.2110003216468317, "grad_norm": 1.1843016147613525, "learning_rate": 1.9130638805375596e-05, "loss": 1.5861730575561523, "step": 1720 }, { "epoch": 2.22386619491798, "grad_norm": 1.1061370372772217, "learning_rate": 1.8554959910807775e-05, "loss": 1.5718308448791505, "step": 1730 }, { "epoch": 2.2367320681891285, "grad_norm": 1.0514782667160034, "learning_rate": 1.7986095849343748e-05, "loss": 1.5716367721557618, "step": 1740 }, { "epoch": 2.2495979414602765, "grad_norm": 1.355810284614563, "learning_rate": 1.7424169906361026e-05, "loss": 1.513425636291504, "step": 1750 }, { "epoch": 2.262463814731425, "grad_norm": 1.258013367652893, "learning_rate": 1.686930386359391e-05, "loss": 1.519799041748047, "step": 1760 }, { "epoch": 2.2753296880025733, "grad_norm": 1.1479936838150024, "learning_rate": 1.6321617972740812e-05, "loss": 1.458241081237793, "step": 1770 }, { "epoch": 2.2881955612737217, "grad_norm": 1.158414363861084, "learning_rate": 1.578123092940294e-05, "loss": 1.485111618041992, "step": 1780 }, { "epoch": 2.3010614345448697, "grad_norm": 0.9942500591278076, "learning_rate": 1.5248259847360463e-05, "loss": 1.5456393241882325, "step": 1790 }, { "epoch": 2.313927307816018, "grad_norm": 1.1772578954696655, "learning_rate": 1.4722820233191315e-05, "loss": 1.5449344635009765, "step": 1800 }, { "epoch": 2.3267931810871665, "grad_norm": 1.1509796380996704, "learning_rate": 1.4205025961238332e-05, "loss": 1.586848258972168, "step": 1810 }, { "epoch": 2.3396590543583144, "grad_norm": 1.1740349531173706, "learning_rate": 1.369498924893029e-05, "loss": 1.5965656280517577, "step": 1820 }, { "epoch": 2.352524927629463, "grad_norm": 1.3412179946899414, "learning_rate": 1.3192820632461783e-05, "loss": 1.5539812088012694, "step": 1830 }, { "epoch": 2.3653908009006113, "grad_norm": 1.2437797784805298, "learning_rate": 1.2698628942837699e-05, "loss": 1.5491289138793944, "step": 1840 }, { "epoch": 2.3782566741717592, "grad_norm": 1.2594537734985352, "learning_rate": 1.2212521282287092e-05, "loss": 1.5462745666503905, "step": 1850 }, { "epoch": 2.3911225474429076, "grad_norm": 1.1844170093536377, "learning_rate": 1.1734603001051753e-05, "loss": 1.4849842071533204, "step": 1860 }, { "epoch": 2.403988420714056, "grad_norm": 1.1546885967254639, "learning_rate": 1.1264977674554556e-05, "loss": 1.524639892578125, "step": 1870 }, { "epoch": 2.416854293985204, "grad_norm": 1.211249589920044, "learning_rate": 1.0803747080952304e-05, "loss": 1.4558378219604493, "step": 1880 }, { "epoch": 2.4297201672563524, "grad_norm": 1.2866480350494385, "learning_rate": 1.0351011179078213e-05, "loss": 1.5683873176574707, "step": 1890 }, { "epoch": 2.442586040527501, "grad_norm": 1.1505744457244873, "learning_rate": 9.906868086778643e-06, "loss": 1.5223015785217284, "step": 1900 }, { "epoch": 2.4554519137986492, "grad_norm": 1.0969706773757935, "learning_rate": 9.471414059648703e-06, "loss": 1.5726696014404298, "step": 1910 }, { "epoch": 2.468317787069797, "grad_norm": 1.3082823753356934, "learning_rate": 9.04474347017168e-06, "loss": 1.5587408065795898, "step": 1920 }, { "epoch": 2.4811836603409456, "grad_norm": 1.2790173292160034, "learning_rate": 8.62694878726631e-06, "loss": 1.4755376815795898, "step": 1930 }, { "epoch": 2.494049533612094, "grad_norm": 1.1735286712646484, "learning_rate": 8.218120556246833e-06, "loss": 1.512919807434082, "step": 1940 }, { "epoch": 2.506915406883242, "grad_norm": 1.1867064237594604, "learning_rate": 7.81834737919978e-06, "loss": 1.542198944091797, "step": 1950 }, { "epoch": 2.5197812801543904, "grad_norm": 1.2459471225738525, "learning_rate": 7.427715895781906e-06, "loss": 1.5312854766845703, "step": 1960 }, { "epoch": 2.532647153425539, "grad_norm": 1.2053990364074707, "learning_rate": 7.046310764443575e-06, "loss": 1.5742183685302735, "step": 1970 }, { "epoch": 2.545513026696687, "grad_norm": 1.2814679145812988, "learning_rate": 6.6742146440812895e-06, "loss": 1.552420425415039, "step": 1980 }, { "epoch": 2.558378899967835, "grad_norm": 1.287398099899292, "learning_rate": 6.311508176123771e-06, "loss": 1.5379514694213867, "step": 1990 }, { "epoch": 2.5712447732389836, "grad_norm": 1.143372893333435, "learning_rate": 5.958269967055163e-06, "loss": 1.5470756530761718, "step": 2000 } ], "logging_steps": 10, "max_steps": 2334, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 400, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 7.828144940017254e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }