| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.1942794016660199, | |
| "eval_steps": 1000, | |
| "global_step": 40000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.9856985041650495e-05, | |
| "grad_norm": 8.064935684204102, | |
| "learning_rate": 0.0, | |
| "loss": 3.4849, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014928492520825246, | |
| "grad_norm": 3.3433420658111572, | |
| "learning_rate": 0.00019998742849959144, | |
| "loss": 1.9038, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0029856985041650493, | |
| "grad_norm": 2.907883405685425, | |
| "learning_rate": 0.0001999731427036726, | |
| "loss": 1.608, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004478547756247574, | |
| "grad_norm": 3.2614288330078125, | |
| "learning_rate": 0.00019995885690775376, | |
| "loss": 1.5505, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.005971397008330099, | |
| "grad_norm": 3.8400654792785645, | |
| "learning_rate": 0.00019994457111183493, | |
| "loss": 1.5737, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.007464246260412624, | |
| "grad_norm": 3.3358442783355713, | |
| "learning_rate": 0.00019993028531591612, | |
| "loss": 1.567, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.008957095512495149, | |
| "grad_norm": 2.131911277770996, | |
| "learning_rate": 0.00019991599951999726, | |
| "loss": 1.5208, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.010449944764577673, | |
| "grad_norm": 3.180992364883423, | |
| "learning_rate": 0.00019990171372407845, | |
| "loss": 1.5586, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.011942794016660197, | |
| "grad_norm": 3.024989128112793, | |
| "learning_rate": 0.0001998874279281596, | |
| "loss": 1.5267, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.013435643268742723, | |
| "grad_norm": 3.4935102462768555, | |
| "learning_rate": 0.00019987314213224078, | |
| "loss": 1.5609, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.014928492520825247, | |
| "grad_norm": 3.565504550933838, | |
| "learning_rate": 0.00019985885633632194, | |
| "loss": 1.5112, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01642134177290777, | |
| "grad_norm": 2.0692882537841797, | |
| "learning_rate": 0.00019984457054040308, | |
| "loss": 1.5087, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.017914191024990297, | |
| "grad_norm": 4.110323905944824, | |
| "learning_rate": 0.00019983028474448427, | |
| "loss": 1.5073, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.01940704027707282, | |
| "grad_norm": 2.8632736206054688, | |
| "learning_rate": 0.0001998159989485654, | |
| "loss": 1.472, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.020899889529155346, | |
| "grad_norm": 2.629347324371338, | |
| "learning_rate": 0.0001998017131526466, | |
| "loss": 1.5236, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.022392738781237872, | |
| "grad_norm": 3.696873188018799, | |
| "learning_rate": 0.00019978742735672774, | |
| "loss": 1.5216, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.023885588033320394, | |
| "grad_norm": 3.253305435180664, | |
| "learning_rate": 0.00019977314156080893, | |
| "loss": 1.5915, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.02537843728540292, | |
| "grad_norm": 2.9587886333465576, | |
| "learning_rate": 0.0001997588557648901, | |
| "loss": 1.4862, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.026871286537485446, | |
| "grad_norm": 3.3311073780059814, | |
| "learning_rate": 0.00019974456996897126, | |
| "loss": 1.4703, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.02836413578956797, | |
| "grad_norm": 2.5960264205932617, | |
| "learning_rate": 0.00019973028417305243, | |
| "loss": 1.4818, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.029856985041650495, | |
| "grad_norm": 3.3142144680023193, | |
| "learning_rate": 0.0001997159983771336, | |
| "loss": 1.4746, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03134983429373302, | |
| "grad_norm": 3.5049827098846436, | |
| "learning_rate": 0.00019970171258121476, | |
| "loss": 1.442, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.03284268354581554, | |
| "grad_norm": 3.0218605995178223, | |
| "learning_rate": 0.00019968742678529592, | |
| "loss": 1.5265, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.03433553279789807, | |
| "grad_norm": 2.936182975769043, | |
| "learning_rate": 0.00019967314098937709, | |
| "loss": 1.5174, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.035828382049980595, | |
| "grad_norm": 2.877253293991089, | |
| "learning_rate": 0.00019965885519345825, | |
| "loss": 1.4499, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.03732123130206312, | |
| "grad_norm": 6.07016658782959, | |
| "learning_rate": 0.00019964456939753941, | |
| "loss": 1.4542, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.03881408055414564, | |
| "grad_norm": 2.1618189811706543, | |
| "learning_rate": 0.0001996302836016206, | |
| "loss": 1.4343, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.040306929806228166, | |
| "grad_norm": 2.8267719745635986, | |
| "learning_rate": 0.00019961599780570174, | |
| "loss": 1.463, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.04179977905831069, | |
| "grad_norm": 2.6036462783813477, | |
| "learning_rate": 0.00019960171200978294, | |
| "loss": 1.4557, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.04329262831039322, | |
| "grad_norm": 3.0187127590179443, | |
| "learning_rate": 0.00019958742621386407, | |
| "loss": 1.4472, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.044785477562475744, | |
| "grad_norm": 3.9822633266448975, | |
| "learning_rate": 0.00019957314041794526, | |
| "loss": 1.4384, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04627832681455826, | |
| "grad_norm": 2.919654607772827, | |
| "learning_rate": 0.0001995588546220264, | |
| "loss": 1.4969, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.04777117606664079, | |
| "grad_norm": 2.922963857650757, | |
| "learning_rate": 0.0001995445688261076, | |
| "loss": 1.4987, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.049264025318723315, | |
| "grad_norm": 2.9638512134552, | |
| "learning_rate": 0.00019953028303018876, | |
| "loss": 1.4722, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.05075687457080584, | |
| "grad_norm": 3.408391237258911, | |
| "learning_rate": 0.00019951599723426992, | |
| "loss": 1.4723, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.052249723822888366, | |
| "grad_norm": 3.023597240447998, | |
| "learning_rate": 0.0001995017114383511, | |
| "loss": 1.4478, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.05374257307497089, | |
| "grad_norm": 2.1655213832855225, | |
| "learning_rate": 0.00019948742564243225, | |
| "loss": 1.4071, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.05523542232705341, | |
| "grad_norm": 3.796663999557495, | |
| "learning_rate": 0.00019947313984651342, | |
| "loss": 1.446, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.05672827157913594, | |
| "grad_norm": 3.0415594577789307, | |
| "learning_rate": 0.00019945885405059458, | |
| "loss": 1.4324, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.05822112083121846, | |
| "grad_norm": 2.524627685546875, | |
| "learning_rate": 0.00019944456825467575, | |
| "loss": 1.3963, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.05971397008330099, | |
| "grad_norm": 3.2881991863250732, | |
| "learning_rate": 0.0001994302824587569, | |
| "loss": 1.4522, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.061206819335383515, | |
| "grad_norm": 3.392430067062378, | |
| "learning_rate": 0.00019941599666283808, | |
| "loss": 1.4329, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.06269966858746603, | |
| "grad_norm": 3.9426393508911133, | |
| "learning_rate": 0.00019940171086691927, | |
| "loss": 1.5203, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.06419251783954856, | |
| "grad_norm": 3.3737235069274902, | |
| "learning_rate": 0.0001993874250710004, | |
| "loss": 1.3674, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.06568536709163109, | |
| "grad_norm": 3.783085346221924, | |
| "learning_rate": 0.0001993731392750816, | |
| "loss": 1.4339, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.06717821634371361, | |
| "grad_norm": 3.4819202423095703, | |
| "learning_rate": 0.00019935885347916273, | |
| "loss": 1.4436, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.06867106559579614, | |
| "grad_norm": 3.141775608062744, | |
| "learning_rate": 0.00019934456768324393, | |
| "loss": 1.4683, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.07016391484787866, | |
| "grad_norm": 3.2881035804748535, | |
| "learning_rate": 0.00019933028188732506, | |
| "loss": 1.4395, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.07165676409996119, | |
| "grad_norm": 3.718122959136963, | |
| "learning_rate": 0.00019931599609140626, | |
| "loss": 1.4396, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.07314961335204372, | |
| "grad_norm": 4.3829474449157715, | |
| "learning_rate": 0.00019930171029548742, | |
| "loss": 1.4477, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.07464246260412624, | |
| "grad_norm": 3.3698525428771973, | |
| "learning_rate": 0.00019928742449956858, | |
| "loss": 1.3529, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.07613531185620875, | |
| "grad_norm": 3.7569565773010254, | |
| "learning_rate": 0.00019927313870364975, | |
| "loss": 1.4246, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.07762816110829128, | |
| "grad_norm": 3.1486406326293945, | |
| "learning_rate": 0.00019925885290773091, | |
| "loss": 1.3813, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.0791210103603738, | |
| "grad_norm": 4.0635480880737305, | |
| "learning_rate": 0.00019924456711181208, | |
| "loss": 1.4259, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.08061385961245633, | |
| "grad_norm": 3.2710611820220947, | |
| "learning_rate": 0.00019923028131589324, | |
| "loss": 1.3747, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.08210670886453886, | |
| "grad_norm": 3.4968345165252686, | |
| "learning_rate": 0.0001992159955199744, | |
| "loss": 1.4721, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.08359955811662138, | |
| "grad_norm": 4.274214267730713, | |
| "learning_rate": 0.00019920170972405557, | |
| "loss": 1.437, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.08509240736870391, | |
| "grad_norm": 2.970602512359619, | |
| "learning_rate": 0.00019918742392813674, | |
| "loss": 1.3336, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.08658525662078644, | |
| "grad_norm": 4.143342971801758, | |
| "learning_rate": 0.00019917313813221793, | |
| "loss": 1.4264, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.08807810587286896, | |
| "grad_norm": 3.7546920776367188, | |
| "learning_rate": 0.00019915885233629907, | |
| "loss": 1.441, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.08957095512495149, | |
| "grad_norm": 3.9160516262054443, | |
| "learning_rate": 0.00019914456654038026, | |
| "loss": 1.4261, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.09106380437703401, | |
| "grad_norm": 3.842073917388916, | |
| "learning_rate": 0.0001991302807444614, | |
| "loss": 1.4076, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.09255665362911653, | |
| "grad_norm": 4.392395496368408, | |
| "learning_rate": 0.0001991159949485426, | |
| "loss": 1.3789, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.09404950288119905, | |
| "grad_norm": 3.822425603866577, | |
| "learning_rate": 0.00019910170915262373, | |
| "loss": 1.3877, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.09554235213328158, | |
| "grad_norm": 3.1348562240600586, | |
| "learning_rate": 0.0001990874233567049, | |
| "loss": 1.4081, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.0970352013853641, | |
| "grad_norm": 3.453887939453125, | |
| "learning_rate": 0.00019907313756078608, | |
| "loss": 1.4143, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.09852805063744663, | |
| "grad_norm": 3.5057384967803955, | |
| "learning_rate": 0.00019905885176486722, | |
| "loss": 1.4264, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.10002089988952916, | |
| "grad_norm": 3.145796060562134, | |
| "learning_rate": 0.0001990445659689484, | |
| "loss": 1.4368, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.10151374914161168, | |
| "grad_norm": 3.4077043533325195, | |
| "learning_rate": 0.00019903028017302955, | |
| "loss": 1.388, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.10300659839369421, | |
| "grad_norm": 3.65567946434021, | |
| "learning_rate": 0.00019901599437711074, | |
| "loss": 1.42, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.10449944764577673, | |
| "grad_norm": 4.460702419281006, | |
| "learning_rate": 0.0001990017085811919, | |
| "loss": 1.3991, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.10599229689785926, | |
| "grad_norm": 4.155653476715088, | |
| "learning_rate": 0.00019898742278527307, | |
| "loss": 1.371, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.10748514614994178, | |
| "grad_norm": 3.8904318809509277, | |
| "learning_rate": 0.00019897313698935423, | |
| "loss": 1.4378, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.1089779954020243, | |
| "grad_norm": 4.0509233474731445, | |
| "learning_rate": 0.0001989588511934354, | |
| "loss": 1.3945, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.11047084465410682, | |
| "grad_norm": 3.785123109817505, | |
| "learning_rate": 0.00019894456539751656, | |
| "loss": 1.436, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.11196369390618935, | |
| "grad_norm": 3.4556167125701904, | |
| "learning_rate": 0.00019893027960159773, | |
| "loss": 1.3794, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.11345654315827187, | |
| "grad_norm": 4.0479559898376465, | |
| "learning_rate": 0.0001989159938056789, | |
| "loss": 1.4734, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.1149493924103544, | |
| "grad_norm": 3.890805721282959, | |
| "learning_rate": 0.00019890170800976006, | |
| "loss": 1.4341, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.11644224166243693, | |
| "grad_norm": 3.8178727626800537, | |
| "learning_rate": 0.00019888742221384122, | |
| "loss": 1.4754, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.11793509091451945, | |
| "grad_norm": 2.456165075302124, | |
| "learning_rate": 0.00019887313641792241, | |
| "loss": 1.3887, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.11942794016660198, | |
| "grad_norm": 3.5763051509857178, | |
| "learning_rate": 0.00019885885062200355, | |
| "loss": 1.3901, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1209207894186845, | |
| "grad_norm": 3.885662317276001, | |
| "learning_rate": 0.00019884456482608474, | |
| "loss": 1.3856, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.12241363867076703, | |
| "grad_norm": 3.6095409393310547, | |
| "learning_rate": 0.00019883027903016588, | |
| "loss": 1.448, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.12390648792284956, | |
| "grad_norm": 3.7112534046173096, | |
| "learning_rate": 0.00019881599323424707, | |
| "loss": 1.3537, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.12539933717493207, | |
| "grad_norm": 3.3566672801971436, | |
| "learning_rate": 0.0001988017074383282, | |
| "loss": 1.4389, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.1268921864270146, | |
| "grad_norm": 4.570401191711426, | |
| "learning_rate": 0.0001987874216424094, | |
| "loss": 1.4191, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.12838503567909712, | |
| "grad_norm": 4.455029010772705, | |
| "learning_rate": 0.00019877313584649057, | |
| "loss": 1.3677, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.12987788493117966, | |
| "grad_norm": 3.0861828327178955, | |
| "learning_rate": 0.00019875885005057173, | |
| "loss": 1.3677, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.13137073418326217, | |
| "grad_norm": 4.419896602630615, | |
| "learning_rate": 0.0001987445642546529, | |
| "loss": 1.4524, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.1328635834353447, | |
| "grad_norm": 5.187576770782471, | |
| "learning_rate": 0.00019873027845873406, | |
| "loss": 1.3868, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.13435643268742722, | |
| "grad_norm": 5.111696243286133, | |
| "learning_rate": 0.00019871599266281523, | |
| "loss": 1.4458, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.13584928193950974, | |
| "grad_norm": 3.2652997970581055, | |
| "learning_rate": 0.0001987017068668964, | |
| "loss": 1.4529, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.13734213119159228, | |
| "grad_norm": 4.190273761749268, | |
| "learning_rate": 0.00019868742107097755, | |
| "loss": 1.3991, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.1388349804436748, | |
| "grad_norm": 4.85620641708374, | |
| "learning_rate": 0.00019867313527505872, | |
| "loss": 1.3916, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.14032782969575733, | |
| "grad_norm": 3.030954360961914, | |
| "learning_rate": 0.00019865884947913988, | |
| "loss": 1.3805, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.14182067894783984, | |
| "grad_norm": 3.264406681060791, | |
| "learning_rate": 0.00019864456368322108, | |
| "loss": 1.4048, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.14331352819992238, | |
| "grad_norm": 3.2138588428497314, | |
| "learning_rate": 0.0001986302778873022, | |
| "loss": 1.4092, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.1448063774520049, | |
| "grad_norm": 3.847222328186035, | |
| "learning_rate": 0.0001986159920913834, | |
| "loss": 1.3871, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.14629922670408743, | |
| "grad_norm": 4.004987716674805, | |
| "learning_rate": 0.00019860170629546454, | |
| "loss": 1.3845, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.14779207595616994, | |
| "grad_norm": 3.5088725090026855, | |
| "learning_rate": 0.00019858742049954573, | |
| "loss": 1.379, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.14928492520825248, | |
| "grad_norm": 3.275099277496338, | |
| "learning_rate": 0.00019857313470362687, | |
| "loss": 1.3628, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.150777774460335, | |
| "grad_norm": 3.7903060913085938, | |
| "learning_rate": 0.00019855884890770806, | |
| "loss": 1.3804, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.1522706237124175, | |
| "grad_norm": 4.294798374176025, | |
| "learning_rate": 0.00019854456311178923, | |
| "loss": 1.3988, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.15376347296450005, | |
| "grad_norm": 3.2719295024871826, | |
| "learning_rate": 0.0001985302773158704, | |
| "loss": 1.387, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.15525632221658256, | |
| "grad_norm": 4.143224239349365, | |
| "learning_rate": 0.00019851599151995156, | |
| "loss": 1.393, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.1567491714686651, | |
| "grad_norm": 3.404754638671875, | |
| "learning_rate": 0.00019850170572403272, | |
| "loss": 1.4205, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.1582420207207476, | |
| "grad_norm": 3.607126474380493, | |
| "learning_rate": 0.0001984874199281139, | |
| "loss": 1.4239, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.15973486997283015, | |
| "grad_norm": 4.140823841094971, | |
| "learning_rate": 0.00019847313413219505, | |
| "loss": 1.4204, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.16122771922491266, | |
| "grad_norm": 3.893251419067383, | |
| "learning_rate": 0.00019845884833627622, | |
| "loss": 1.392, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.1627205684769952, | |
| "grad_norm": 4.304211139678955, | |
| "learning_rate": 0.00019844456254035738, | |
| "loss": 1.44, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.16421341772907772, | |
| "grad_norm": 5.273501873016357, | |
| "learning_rate": 0.00019843027674443855, | |
| "loss": 1.445, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.16570626698116026, | |
| "grad_norm": 4.787700176239014, | |
| "learning_rate": 0.00019841599094851974, | |
| "loss": 1.3668, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.16719911623324277, | |
| "grad_norm": 3.7984108924865723, | |
| "learning_rate": 0.00019840170515260087, | |
| "loss": 1.3523, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.16869196548532528, | |
| "grad_norm": 3.885608673095703, | |
| "learning_rate": 0.00019838741935668207, | |
| "loss": 1.3917, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.17018481473740782, | |
| "grad_norm": 3.459803342819214, | |
| "learning_rate": 0.0001983731335607632, | |
| "loss": 1.3833, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.17167766398949033, | |
| "grad_norm": 3.7103006839752197, | |
| "learning_rate": 0.0001983588477648444, | |
| "loss": 1.4473, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.17317051324157287, | |
| "grad_norm": 6.645928382873535, | |
| "learning_rate": 0.00019834456196892553, | |
| "loss": 1.3706, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.17466336249365538, | |
| "grad_norm": 3.7201037406921387, | |
| "learning_rate": 0.0001983302761730067, | |
| "loss": 1.3733, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.17615621174573792, | |
| "grad_norm": 4.050106048583984, | |
| "learning_rate": 0.0001983159903770879, | |
| "loss": 1.4096, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.17764906099782043, | |
| "grad_norm": 4.190842628479004, | |
| "learning_rate": 0.00019830170458116903, | |
| "loss": 1.4404, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.17914191024990297, | |
| "grad_norm": 4.393162727355957, | |
| "learning_rate": 0.00019828741878525022, | |
| "loss": 1.4443, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.1806347595019855, | |
| "grad_norm": 3.597520351409912, | |
| "learning_rate": 0.00019827313298933136, | |
| "loss": 1.4063, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.18212760875406803, | |
| "grad_norm": 3.608085870742798, | |
| "learning_rate": 0.00019825884719341255, | |
| "loss": 1.3857, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.18362045800615054, | |
| "grad_norm": 3.7055492401123047, | |
| "learning_rate": 0.0001982445613974937, | |
| "loss": 1.3997, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.18511330725823305, | |
| "grad_norm": 3.875457763671875, | |
| "learning_rate": 0.00019823027560157488, | |
| "loss": 1.4296, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.1866061565103156, | |
| "grad_norm": 5.074592590332031, | |
| "learning_rate": 0.00019821598980565604, | |
| "loss": 1.3785, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 0.1880990057623981, | |
| "grad_norm": 6.013392448425293, | |
| "learning_rate": 0.0001982017040097372, | |
| "loss": 1.4391, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.18959185501448064, | |
| "grad_norm": 5.679958820343018, | |
| "learning_rate": 0.00019818741821381837, | |
| "loss": 1.367, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 0.19108470426656315, | |
| "grad_norm": 3.6182546615600586, | |
| "learning_rate": 0.00019817313241789954, | |
| "loss": 1.4508, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.1925775535186457, | |
| "grad_norm": 5.209213733673096, | |
| "learning_rate": 0.0001981588466219807, | |
| "loss": 1.3878, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 0.1940704027707282, | |
| "grad_norm": 3.0043230056762695, | |
| "learning_rate": 0.00019814456082606187, | |
| "loss": 1.4248, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.19556325202281075, | |
| "grad_norm": 3.157851219177246, | |
| "learning_rate": 0.00019813027503014303, | |
| "loss": 1.3725, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 0.19705610127489326, | |
| "grad_norm": 3.5292418003082275, | |
| "learning_rate": 0.0001981159892342242, | |
| "loss": 1.3932, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.1985489505269758, | |
| "grad_norm": 3.2819600105285645, | |
| "learning_rate": 0.00019810170343830536, | |
| "loss": 1.3495, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 0.2000417997790583, | |
| "grad_norm": 3.0243399143218994, | |
| "learning_rate": 0.00019808741764238655, | |
| "loss": 1.3689, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.20153464903114082, | |
| "grad_norm": 3.4495368003845215, | |
| "learning_rate": 0.0001980731318464677, | |
| "loss": 1.3725, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.20302749828322336, | |
| "grad_norm": 3.538259744644165, | |
| "learning_rate": 0.00019805884605054888, | |
| "loss": 1.3905, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.20452034753530587, | |
| "grad_norm": 4.162181377410889, | |
| "learning_rate": 0.00019804456025463002, | |
| "loss": 1.4129, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 0.20601319678738841, | |
| "grad_norm": 4.592432022094727, | |
| "learning_rate": 0.0001980302744587112, | |
| "loss": 1.3634, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.20750604603947093, | |
| "grad_norm": 3.45967960357666, | |
| "learning_rate": 0.00019801598866279237, | |
| "loss": 1.416, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 0.20899889529155347, | |
| "grad_norm": 4.221930503845215, | |
| "learning_rate": 0.00019800170286687354, | |
| "loss": 1.4051, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.21049174454363598, | |
| "grad_norm": 4.144239902496338, | |
| "learning_rate": 0.0001979874170709547, | |
| "loss": 1.4219, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 0.21198459379571852, | |
| "grad_norm": 4.7492570877075195, | |
| "learning_rate": 0.00019797313127503587, | |
| "loss": 1.4028, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.21347744304780103, | |
| "grad_norm": 3.5841355323791504, | |
| "learning_rate": 0.00019795884547911703, | |
| "loss": 1.4361, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 0.21497029229988357, | |
| "grad_norm": 4.662593364715576, | |
| "learning_rate": 0.0001979445596831982, | |
| "loss": 1.3816, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.21646314155196608, | |
| "grad_norm": 4.700701713562012, | |
| "learning_rate": 0.00019793027388727936, | |
| "loss": 1.4226, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 0.2179559908040486, | |
| "grad_norm": 4.025181293487549, | |
| "learning_rate": 0.00019791598809136053, | |
| "loss": 1.4291, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.21944884005613113, | |
| "grad_norm": 3.064573049545288, | |
| "learning_rate": 0.0001979017022954417, | |
| "loss": 1.4293, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 0.22094168930821365, | |
| "grad_norm": 6.342152118682861, | |
| "learning_rate": 0.00019788741649952288, | |
| "loss": 1.4173, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.22243453856029619, | |
| "grad_norm": 5.89996337890625, | |
| "learning_rate": 0.00019787313070360402, | |
| "loss": 1.396, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 0.2239273878123787, | |
| "grad_norm": 4.462945938110352, | |
| "learning_rate": 0.0001978588449076852, | |
| "loss": 1.3868, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.22542023706446124, | |
| "grad_norm": 3.6449055671691895, | |
| "learning_rate": 0.00019784455911176635, | |
| "loss": 1.396, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 0.22691308631654375, | |
| "grad_norm": 4.674243927001953, | |
| "learning_rate": 0.00019783027331584754, | |
| "loss": 1.395, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.2284059355686263, | |
| "grad_norm": 3.6160385608673096, | |
| "learning_rate": 0.00019781598751992868, | |
| "loss": 1.3918, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 0.2298987848207088, | |
| "grad_norm": 4.326193332672119, | |
| "learning_rate": 0.00019780170172400987, | |
| "loss": 1.3947, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.23139163407279134, | |
| "grad_norm": 5.4003777503967285, | |
| "learning_rate": 0.00019778741592809104, | |
| "loss": 1.344, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 0.23288448332487385, | |
| "grad_norm": 4.711580753326416, | |
| "learning_rate": 0.0001977731301321722, | |
| "loss": 1.3959, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.23437733257695637, | |
| "grad_norm": 3.4752814769744873, | |
| "learning_rate": 0.00019775884433625337, | |
| "loss": 1.3722, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 0.2358701818290389, | |
| "grad_norm": 4.028527736663818, | |
| "learning_rate": 0.00019774455854033453, | |
| "loss": 1.3683, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.23736303108112142, | |
| "grad_norm": 4.094334602355957, | |
| "learning_rate": 0.0001977302727444157, | |
| "loss": 1.3607, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 0.23885588033320396, | |
| "grad_norm": 5.232580661773682, | |
| "learning_rate": 0.00019771598694849686, | |
| "loss": 1.4354, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.24034872958528647, | |
| "grad_norm": 4.269852161407471, | |
| "learning_rate": 0.00019770170115257802, | |
| "loss": 1.4372, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 0.241841578837369, | |
| "grad_norm": 3.312541961669922, | |
| "learning_rate": 0.0001976874153566592, | |
| "loss": 1.3826, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.24333442808945152, | |
| "grad_norm": 3.8900692462921143, | |
| "learning_rate": 0.00019767312956074035, | |
| "loss": 1.4189, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 0.24482727734153406, | |
| "grad_norm": 3.894512414932251, | |
| "learning_rate": 0.00019765884376482155, | |
| "loss": 1.3365, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.24632012659361657, | |
| "grad_norm": 4.644411563873291, | |
| "learning_rate": 0.00019764455796890268, | |
| "loss": 1.4311, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 0.2478129758456991, | |
| "grad_norm": 8.174029350280762, | |
| "learning_rate": 0.00019763027217298387, | |
| "loss": 1.361, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.24930582509778162, | |
| "grad_norm": 4.615732192993164, | |
| "learning_rate": 0.000197615986377065, | |
| "loss": 1.4552, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 0.25079867434986414, | |
| "grad_norm": 4.421249866485596, | |
| "learning_rate": 0.0001976017005811462, | |
| "loss": 1.3463, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.2522915236019467, | |
| "grad_norm": 2.8386716842651367, | |
| "learning_rate": 0.00019758741478522734, | |
| "loss": 1.348, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 0.2537843728540292, | |
| "grad_norm": 4.3141703605651855, | |
| "learning_rate": 0.0001975731289893085, | |
| "loss": 1.4306, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.2552772221061117, | |
| "grad_norm": 3.947331428527832, | |
| "learning_rate": 0.0001975588431933897, | |
| "loss": 1.3823, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 0.25677007135819424, | |
| "grad_norm": 3.2268636226654053, | |
| "learning_rate": 0.00019754455739747084, | |
| "loss": 1.4199, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.2582629206102768, | |
| "grad_norm": 4.0353102684021, | |
| "learning_rate": 0.00019753027160155203, | |
| "loss": 1.3927, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 0.2597557698623593, | |
| "grad_norm": 3.490560293197632, | |
| "learning_rate": 0.00019751598580563316, | |
| "loss": 1.401, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.2612486191144418, | |
| "grad_norm": 5.577207088470459, | |
| "learning_rate": 0.00019750170000971436, | |
| "loss": 1.3586, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 0.26274146836652434, | |
| "grad_norm": 4.168467998504639, | |
| "learning_rate": 0.0001974874142137955, | |
| "loss": 1.3303, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.2642343176186069, | |
| "grad_norm": 3.812627077102661, | |
| "learning_rate": 0.00019747312841787669, | |
| "loss": 1.3717, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 0.2657271668706894, | |
| "grad_norm": 4.875237464904785, | |
| "learning_rate": 0.00019745884262195785, | |
| "loss": 1.3873, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.2672200161227719, | |
| "grad_norm": 4.048189163208008, | |
| "learning_rate": 0.00019744455682603902, | |
| "loss": 1.3775, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 0.26871286537485445, | |
| "grad_norm": 3.9090261459350586, | |
| "learning_rate": 0.00019743027103012018, | |
| "loss": 1.4296, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.270205714626937, | |
| "grad_norm": 2.8476953506469727, | |
| "learning_rate": 0.00019741598523420134, | |
| "loss": 1.4175, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 0.2716985638790195, | |
| "grad_norm": 5.782102584838867, | |
| "learning_rate": 0.0001974016994382825, | |
| "loss": 1.3835, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.273191413131102, | |
| "grad_norm": 4.640264987945557, | |
| "learning_rate": 0.00019738741364236367, | |
| "loss": 1.4524, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 0.27468426238318455, | |
| "grad_norm": 4.81790828704834, | |
| "learning_rate": 0.00019737312784644484, | |
| "loss": 1.3183, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.2761771116352671, | |
| "grad_norm": 2.685009717941284, | |
| "learning_rate": 0.000197358842050526, | |
| "loss": 1.3243, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 0.2776699608873496, | |
| "grad_norm": 5.321321487426758, | |
| "learning_rate": 0.00019734455625460717, | |
| "loss": 1.4086, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.2791628101394321, | |
| "grad_norm": 3.065791368484497, | |
| "learning_rate": 0.00019733027045868836, | |
| "loss": 1.337, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 0.28065565939151466, | |
| "grad_norm": 4.3569817543029785, | |
| "learning_rate": 0.0001973159846627695, | |
| "loss": 1.4082, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.2821485086435972, | |
| "grad_norm": 4.67582368850708, | |
| "learning_rate": 0.0001973016988668507, | |
| "loss": 1.3832, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 0.2836413578956797, | |
| "grad_norm": 4.942144870758057, | |
| "learning_rate": 0.00019728741307093183, | |
| "loss": 1.3734, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.2851342071477622, | |
| "grad_norm": 4.853246688842773, | |
| "learning_rate": 0.00019727312727501302, | |
| "loss": 1.4111, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 0.28662705639984476, | |
| "grad_norm": 3.071237325668335, | |
| "learning_rate": 0.00019725884147909418, | |
| "loss": 1.3746, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.28811990565192724, | |
| "grad_norm": 4.844615459442139, | |
| "learning_rate": 0.00019724455568317535, | |
| "loss": 1.3051, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 0.2896127549040098, | |
| "grad_norm": 5.954223155975342, | |
| "learning_rate": 0.0001972302698872565, | |
| "loss": 1.4131, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.2911056041560923, | |
| "grad_norm": 3.6717801094055176, | |
| "learning_rate": 0.00019721598409133768, | |
| "loss": 1.4166, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 0.29259845340817486, | |
| "grad_norm": 3.6257095336914062, | |
| "learning_rate": 0.00019720169829541884, | |
| "loss": 1.3679, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.29409130266025735, | |
| "grad_norm": 4.245635032653809, | |
| "learning_rate": 0.0001971874124995, | |
| "loss": 1.3171, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 0.2955841519123399, | |
| "grad_norm": 5.362602710723877, | |
| "learning_rate": 0.00019717312670358117, | |
| "loss": 1.3932, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.2970770011644224, | |
| "grad_norm": 4.6283721923828125, | |
| "learning_rate": 0.00019715884090766234, | |
| "loss": 1.3757, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 0.29856985041650497, | |
| "grad_norm": 4.299574851989746, | |
| "learning_rate": 0.0001971445551117435, | |
| "loss": 1.4018, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.30006269966858745, | |
| "grad_norm": 4.7913641929626465, | |
| "learning_rate": 0.0001971302693158247, | |
| "loss": 1.4228, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 0.30155554892067, | |
| "grad_norm": 5.312823295593262, | |
| "learning_rate": 0.00019711598351990583, | |
| "loss": 1.3866, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.30304839817275253, | |
| "grad_norm": 4.099662780761719, | |
| "learning_rate": 0.00019710169772398702, | |
| "loss": 1.454, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 0.304541247424835, | |
| "grad_norm": 4.254878520965576, | |
| "learning_rate": 0.00019708741192806816, | |
| "loss": 1.3526, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.30603409667691756, | |
| "grad_norm": 4.056606292724609, | |
| "learning_rate": 0.00019707312613214935, | |
| "loss": 1.4167, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 0.3075269459290001, | |
| "grad_norm": 3.790809154510498, | |
| "learning_rate": 0.0001970588403362305, | |
| "loss": 1.3536, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.30901979518108263, | |
| "grad_norm": 4.46298360824585, | |
| "learning_rate": 0.00019704455454031168, | |
| "loss": 1.3613, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 0.3105126444331651, | |
| "grad_norm": 4.52452278137207, | |
| "learning_rate": 0.00019703026874439284, | |
| "loss": 1.4591, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.31200549368524766, | |
| "grad_norm": 4.735177040100098, | |
| "learning_rate": 0.000197015982948474, | |
| "loss": 1.4617, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 0.3134983429373302, | |
| "grad_norm": 4.48261833190918, | |
| "learning_rate": 0.00019700169715255517, | |
| "loss": 1.4072, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.31499119218941274, | |
| "grad_norm": 3.3441503047943115, | |
| "learning_rate": 0.00019698741135663634, | |
| "loss": 1.4082, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 0.3164840414414952, | |
| "grad_norm": 3.9771218299865723, | |
| "learning_rate": 0.0001969731255607175, | |
| "loss": 1.4184, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.31797689069357776, | |
| "grad_norm": 6.366194725036621, | |
| "learning_rate": 0.00019695883976479867, | |
| "loss": 1.387, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 0.3194697399456603, | |
| "grad_norm": 5.072678089141846, | |
| "learning_rate": 0.00019694455396887983, | |
| "loss": 1.3996, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.3209625891977428, | |
| "grad_norm": 3.7204978466033936, | |
| "learning_rate": 0.000196930268172961, | |
| "loss": 1.3774, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 0.3224554384498253, | |
| "grad_norm": 4.47731351852417, | |
| "learning_rate": 0.00019691598237704216, | |
| "loss": 1.3552, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.32394828770190787, | |
| "grad_norm": 3.4569220542907715, | |
| "learning_rate": 0.00019690169658112335, | |
| "loss": 1.3794, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 0.3254411369539904, | |
| "grad_norm": 4.344145774841309, | |
| "learning_rate": 0.0001968874107852045, | |
| "loss": 1.4419, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.3269339862060729, | |
| "grad_norm": 4.089848041534424, | |
| "learning_rate": 0.00019687312498928568, | |
| "loss": 1.4116, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 0.32842683545815543, | |
| "grad_norm": 3.995945930480957, | |
| "learning_rate": 0.00019685883919336682, | |
| "loss": 1.3532, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.32991968471023797, | |
| "grad_norm": 3.8309378623962402, | |
| "learning_rate": 0.00019684455339744798, | |
| "loss": 1.3957, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 0.3314125339623205, | |
| "grad_norm": 4.386235237121582, | |
| "learning_rate": 0.00019683026760152915, | |
| "loss": 1.3616, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.332905383214403, | |
| "grad_norm": 5.133239269256592, | |
| "learning_rate": 0.00019681598180561031, | |
| "loss": 1.3959, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 0.33439823246648553, | |
| "grad_norm": 4.216183662414551, | |
| "learning_rate": 0.0001968016960096915, | |
| "loss": 1.3446, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.3358910817185681, | |
| "grad_norm": 3.631131172180176, | |
| "learning_rate": 0.00019678741021377264, | |
| "loss": 1.3779, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 0.33738393097065056, | |
| "grad_norm": 4.603448390960693, | |
| "learning_rate": 0.00019677312441785384, | |
| "loss": 1.3962, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.3388767802227331, | |
| "grad_norm": 3.6482913494110107, | |
| "learning_rate": 0.00019675883862193497, | |
| "loss": 1.3931, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 0.34036962947481564, | |
| "grad_norm": 5.040388107299805, | |
| "learning_rate": 0.00019674455282601616, | |
| "loss": 1.3465, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.3418624787268982, | |
| "grad_norm": 5.762825012207031, | |
| "learning_rate": 0.0001967302670300973, | |
| "loss": 1.3577, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 0.34335532797898066, | |
| "grad_norm": 4.941501617431641, | |
| "learning_rate": 0.0001967159812341785, | |
| "loss": 1.3676, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.3448481772310632, | |
| "grad_norm": 5.368370532989502, | |
| "learning_rate": 0.00019670169543825966, | |
| "loss": 1.4265, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 0.34634102648314574, | |
| "grad_norm": 4.931522369384766, | |
| "learning_rate": 0.00019668740964234082, | |
| "loss": 1.3551, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.3478338757352283, | |
| "grad_norm": 3.9685990810394287, | |
| "learning_rate": 0.000196673123846422, | |
| "loss": 1.402, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 0.34932672498731077, | |
| "grad_norm": 5.771200656890869, | |
| "learning_rate": 0.00019665883805050315, | |
| "loss": 1.3596, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.3508195742393933, | |
| "grad_norm": 5.142852306365967, | |
| "learning_rate": 0.00019664455225458432, | |
| "loss": 1.385, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 0.35231242349147585, | |
| "grad_norm": 3.295628786087036, | |
| "learning_rate": 0.00019663026645866548, | |
| "loss": 1.3454, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.35380527274355833, | |
| "grad_norm": 4.34658145904541, | |
| "learning_rate": 0.00019661598066274665, | |
| "loss": 1.3976, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 0.35529812199564087, | |
| "grad_norm": 4.032591819763184, | |
| "learning_rate": 0.0001966016948668278, | |
| "loss": 1.3571, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.3567909712477234, | |
| "grad_norm": 3.9286158084869385, | |
| "learning_rate": 0.00019658740907090898, | |
| "loss": 1.398, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 0.35828382049980595, | |
| "grad_norm": 5.184597492218018, | |
| "learning_rate": 0.00019657312327499017, | |
| "loss": 1.3827, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.35977666975188843, | |
| "grad_norm": 4.4749226570129395, | |
| "learning_rate": 0.0001965588374790713, | |
| "loss": 1.373, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 0.361269519003971, | |
| "grad_norm": 3.5633764266967773, | |
| "learning_rate": 0.0001965445516831525, | |
| "loss": 1.3704, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.3627623682560535, | |
| "grad_norm": 7.570897102355957, | |
| "learning_rate": 0.00019653026588723363, | |
| "loss": 1.3515, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 0.36425521750813605, | |
| "grad_norm": 4.239411354064941, | |
| "learning_rate": 0.00019651598009131483, | |
| "loss": 1.3813, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.36574806676021854, | |
| "grad_norm": 3.8941049575805664, | |
| "learning_rate": 0.00019650169429539596, | |
| "loss": 1.3954, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 0.3672409160123011, | |
| "grad_norm": 4.8694586753845215, | |
| "learning_rate": 0.00019648740849947716, | |
| "loss": 1.3531, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.3687337652643836, | |
| "grad_norm": 3.914964437484741, | |
| "learning_rate": 0.00019647312270355832, | |
| "loss": 1.3954, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 0.3702266145164661, | |
| "grad_norm": 3.4050538539886475, | |
| "learning_rate": 0.00019645883690763948, | |
| "loss": 1.3498, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.37171946376854864, | |
| "grad_norm": 4.436797618865967, | |
| "learning_rate": 0.00019644455111172065, | |
| "loss": 1.3889, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 0.3732123130206312, | |
| "grad_norm": 2.7660670280456543, | |
| "learning_rate": 0.00019643026531580181, | |
| "loss": 1.3392, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.3747051622727137, | |
| "grad_norm": 5.364072799682617, | |
| "learning_rate": 0.00019641597951988298, | |
| "loss": 1.3157, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 0.3761980115247962, | |
| "grad_norm": 5.123339653015137, | |
| "learning_rate": 0.00019640169372396414, | |
| "loss": 1.3523, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.37769086077687875, | |
| "grad_norm": 3.4495439529418945, | |
| "learning_rate": 0.0001963874079280453, | |
| "loss": 1.3331, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 0.3791837100289613, | |
| "grad_norm": 4.613680362701416, | |
| "learning_rate": 0.00019637312213212647, | |
| "loss": 1.3707, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.3806765592810438, | |
| "grad_norm": 3.5819404125213623, | |
| "learning_rate": 0.00019635883633620764, | |
| "loss": 1.4023, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 0.3821694085331263, | |
| "grad_norm": 3.5075576305389404, | |
| "learning_rate": 0.00019634455054028883, | |
| "loss": 1.3815, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.38366225778520885, | |
| "grad_norm": 4.425256729125977, | |
| "learning_rate": 0.00019633026474436997, | |
| "loss": 1.3801, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 0.3851551070372914, | |
| "grad_norm": 3.5711112022399902, | |
| "learning_rate": 0.00019631597894845116, | |
| "loss": 1.3375, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.3866479562893739, | |
| "grad_norm": 5.728016376495361, | |
| "learning_rate": 0.0001963016931525323, | |
| "loss": 1.3914, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 0.3881408055414564, | |
| "grad_norm": 4.294504642486572, | |
| "learning_rate": 0.0001962874073566135, | |
| "loss": 1.4561, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.38963365479353895, | |
| "grad_norm": 5.329941749572754, | |
| "learning_rate": 0.00019627312156069465, | |
| "loss": 1.4018, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 0.3911265040456215, | |
| "grad_norm": 4.166362762451172, | |
| "learning_rate": 0.00019625883576477582, | |
| "loss": 1.4334, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.392619353297704, | |
| "grad_norm": 3.3922691345214844, | |
| "learning_rate": 0.00019624454996885698, | |
| "loss": 1.3956, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 0.3941122025497865, | |
| "grad_norm": 4.340898036956787, | |
| "learning_rate": 0.00019623026417293815, | |
| "loss": 1.3643, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.39560505180186906, | |
| "grad_norm": 6.623823165893555, | |
| "learning_rate": 0.0001962159783770193, | |
| "loss": 1.362, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 0.3970979010539516, | |
| "grad_norm": 4.490639686584473, | |
| "learning_rate": 0.00019620169258110048, | |
| "loss": 1.3742, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.3985907503060341, | |
| "grad_norm": 4.179808139801025, | |
| "learning_rate": 0.00019618740678518164, | |
| "loss": 1.4191, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 0.4000835995581166, | |
| "grad_norm": 5.623187065124512, | |
| "learning_rate": 0.0001961731209892628, | |
| "loss": 1.3793, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.40157644881019916, | |
| "grad_norm": 3.9650678634643555, | |
| "learning_rate": 0.00019615883519334397, | |
| "loss": 1.3917, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 0.40306929806228164, | |
| "grad_norm": 5.047702312469482, | |
| "learning_rate": 0.00019614454939742516, | |
| "loss": 1.4501, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.4045621473143642, | |
| "grad_norm": 3.46647310256958, | |
| "learning_rate": 0.0001961302636015063, | |
| "loss": 1.4091, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 0.4060549965664467, | |
| "grad_norm": 3.2203481197357178, | |
| "learning_rate": 0.0001961159778055875, | |
| "loss": 1.4003, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 0.40754784581852926, | |
| "grad_norm": 3.727679967880249, | |
| "learning_rate": 0.00019610169200966863, | |
| "loss": 1.4004, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 0.40904069507061175, | |
| "grad_norm": 4.469257831573486, | |
| "learning_rate": 0.0001960874062137498, | |
| "loss": 1.4061, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 0.4105335443226943, | |
| "grad_norm": 4.041538715362549, | |
| "learning_rate": 0.00019607312041783096, | |
| "loss": 1.411, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 0.41202639357477683, | |
| "grad_norm": 5.2691779136657715, | |
| "learning_rate": 0.00019605883462191212, | |
| "loss": 1.3396, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.41351924282685937, | |
| "grad_norm": 6.236726760864258, | |
| "learning_rate": 0.00019604454882599331, | |
| "loss": 1.4295, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 0.41501209207894185, | |
| "grad_norm": 6.703745365142822, | |
| "learning_rate": 0.00019603026303007445, | |
| "loss": 1.4105, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 0.4165049413310244, | |
| "grad_norm": 3.997664451599121, | |
| "learning_rate": 0.00019601597723415564, | |
| "loss": 1.347, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 0.41799779058310693, | |
| "grad_norm": 5.311407566070557, | |
| "learning_rate": 0.00019600169143823678, | |
| "loss": 1.4546, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.4194906398351894, | |
| "grad_norm": 4.0283098220825195, | |
| "learning_rate": 0.00019598740564231797, | |
| "loss": 1.4513, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 0.42098348908727196, | |
| "grad_norm": 7.345764636993408, | |
| "learning_rate": 0.0001959731198463991, | |
| "loss": 1.3832, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.4224763383393545, | |
| "grad_norm": 4.324542045593262, | |
| "learning_rate": 0.0001959588340504803, | |
| "loss": 1.3751, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 0.42396918759143704, | |
| "grad_norm": 3.8322675228118896, | |
| "learning_rate": 0.00019594454825456147, | |
| "loss": 1.344, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 0.4254620368435195, | |
| "grad_norm": 4.62548303604126, | |
| "learning_rate": 0.00019593026245864263, | |
| "loss": 1.4346, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 0.42695488609560206, | |
| "grad_norm": 4.585489273071289, | |
| "learning_rate": 0.0001959159766627238, | |
| "loss": 1.4145, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 0.4284477353476846, | |
| "grad_norm": 3.64227557182312, | |
| "learning_rate": 0.00019590169086680496, | |
| "loss": 1.367, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 0.42994058459976714, | |
| "grad_norm": 4.730580806732178, | |
| "learning_rate": 0.00019588740507088613, | |
| "loss": 1.3653, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.4314334338518496, | |
| "grad_norm": 4.4075398445129395, | |
| "learning_rate": 0.0001958731192749673, | |
| "loss": 1.4081, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 0.43292628310393216, | |
| "grad_norm": 3.0498785972595215, | |
| "learning_rate": 0.00019585883347904845, | |
| "loss": 1.343, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.4344191323560147, | |
| "grad_norm": 4.179199695587158, | |
| "learning_rate": 0.00019584454768312962, | |
| "loss": 1.3662, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 0.4359119816080972, | |
| "grad_norm": 4.1148786544799805, | |
| "learning_rate": 0.00019583026188721078, | |
| "loss": 1.3785, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 0.4374048308601797, | |
| "grad_norm": 4.012060165405273, | |
| "learning_rate": 0.00019581597609129198, | |
| "loss": 1.4056, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 0.43889768011226227, | |
| "grad_norm": 7.186342716217041, | |
| "learning_rate": 0.0001958016902953731, | |
| "loss": 1.3943, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.4403905293643448, | |
| "grad_norm": 3.951267957687378, | |
| "learning_rate": 0.0001957874044994543, | |
| "loss": 1.3976, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 0.4418833786164273, | |
| "grad_norm": 5.276801586151123, | |
| "learning_rate": 0.00019577311870353544, | |
| "loss": 1.4137, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 0.44337622786850983, | |
| "grad_norm": 4.107429504394531, | |
| "learning_rate": 0.00019575883290761663, | |
| "loss": 1.388, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 0.44486907712059237, | |
| "grad_norm": 4.274941444396973, | |
| "learning_rate": 0.00019574454711169777, | |
| "loss": 1.3446, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 0.4463619263726749, | |
| "grad_norm": 4.174200534820557, | |
| "learning_rate": 0.00019573026131577896, | |
| "loss": 1.3703, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 0.4478547756247574, | |
| "grad_norm": 3.867125988006592, | |
| "learning_rate": 0.00019571597551986013, | |
| "loss": 1.3745, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.44934762487683994, | |
| "grad_norm": 6.454402923583984, | |
| "learning_rate": 0.0001957016897239413, | |
| "loss": 1.3081, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 0.4508404741289225, | |
| "grad_norm": 3.8726885318756104, | |
| "learning_rate": 0.00019568740392802246, | |
| "loss": 1.3527, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 0.45233332338100496, | |
| "grad_norm": 3.6218361854553223, | |
| "learning_rate": 0.00019567311813210362, | |
| "loss": 1.4549, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 0.4538261726330875, | |
| "grad_norm": 5.2475361824035645, | |
| "learning_rate": 0.0001956588323361848, | |
| "loss": 1.361, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 0.45531902188517004, | |
| "grad_norm": 4.388748645782471, | |
| "learning_rate": 0.00019564454654026595, | |
| "loss": 1.3164, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 0.4568118711372526, | |
| "grad_norm": 4.97973108291626, | |
| "learning_rate": 0.00019563026074434712, | |
| "loss": 1.3755, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.45830472038933506, | |
| "grad_norm": 4.538138389587402, | |
| "learning_rate": 0.00019561597494842828, | |
| "loss": 1.4339, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 0.4597975696414176, | |
| "grad_norm": 4.389719009399414, | |
| "learning_rate": 0.00019560168915250945, | |
| "loss": 1.4163, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 0.46129041889350014, | |
| "grad_norm": 4.347919464111328, | |
| "learning_rate": 0.00019558740335659064, | |
| "loss": 1.3663, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 0.4627832681455827, | |
| "grad_norm": 4.820595741271973, | |
| "learning_rate": 0.00019557311756067177, | |
| "loss": 1.3441, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.46427611739766517, | |
| "grad_norm": 2.6965413093566895, | |
| "learning_rate": 0.00019555883176475297, | |
| "loss": 1.3657, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 0.4657689666497477, | |
| "grad_norm": 4.741116523742676, | |
| "learning_rate": 0.0001955445459688341, | |
| "loss": 1.4414, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.46726181590183025, | |
| "grad_norm": 3.9512829780578613, | |
| "learning_rate": 0.0001955302601729153, | |
| "loss": 1.354, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 0.46875466515391273, | |
| "grad_norm": 7.704863548278809, | |
| "learning_rate": 0.00019551597437699646, | |
| "loss": 1.4107, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 0.47024751440599527, | |
| "grad_norm": 3.502988338470459, | |
| "learning_rate": 0.00019550168858107763, | |
| "loss": 1.415, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 0.4717403636580778, | |
| "grad_norm": 4.246065139770508, | |
| "learning_rate": 0.0001954874027851588, | |
| "loss": 1.3414, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 0.47323321291016035, | |
| "grad_norm": 3.4039735794067383, | |
| "learning_rate": 0.00019547311698923995, | |
| "loss": 1.3303, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 0.47472606216224283, | |
| "grad_norm": 3.279521942138672, | |
| "learning_rate": 0.00019545883119332112, | |
| "loss": 1.3447, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.4762189114143254, | |
| "grad_norm": 2.9335134029388428, | |
| "learning_rate": 0.00019544454539740228, | |
| "loss": 1.3998, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 0.4777117606664079, | |
| "grad_norm": 3.317011833190918, | |
| "learning_rate": 0.00019543025960148345, | |
| "loss": 1.3506, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.47920460991849045, | |
| "grad_norm": 3.5980935096740723, | |
| "learning_rate": 0.0001954159738055646, | |
| "loss": 1.3622, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 0.48069745917057294, | |
| "grad_norm": 4.726743698120117, | |
| "learning_rate": 0.00019540168800964578, | |
| "loss": 1.3414, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 0.4821903084226555, | |
| "grad_norm": 5.129758358001709, | |
| "learning_rate": 0.00019538740221372694, | |
| "loss": 1.3873, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 0.483683157674738, | |
| "grad_norm": 5.122271537780762, | |
| "learning_rate": 0.0001953731164178081, | |
| "loss": 1.428, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.4851760069268205, | |
| "grad_norm": 3.359868049621582, | |
| "learning_rate": 0.0001953588306218893, | |
| "loss": 1.3111, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 0.48666885617890304, | |
| "grad_norm": 5.066514492034912, | |
| "learning_rate": 0.00019534454482597044, | |
| "loss": 1.2961, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 0.4881617054309856, | |
| "grad_norm": 4.902595520019531, | |
| "learning_rate": 0.0001953302590300516, | |
| "loss": 1.3682, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 0.4896545546830681, | |
| "grad_norm": 5.0537028312683105, | |
| "learning_rate": 0.00019531597323413277, | |
| "loss": 1.315, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 0.4911474039351506, | |
| "grad_norm": 3.7002792358398438, | |
| "learning_rate": 0.00019530168743821393, | |
| "loss": 1.3441, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 0.49264025318723315, | |
| "grad_norm": 4.845950603485107, | |
| "learning_rate": 0.00019528740164229512, | |
| "loss": 1.3887, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.4941331024393157, | |
| "grad_norm": 4.933434963226318, | |
| "learning_rate": 0.00019527311584637626, | |
| "loss": 1.3865, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 0.4956259516913982, | |
| "grad_norm": 3.8103625774383545, | |
| "learning_rate": 0.00019525883005045745, | |
| "loss": 1.3757, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 0.4971188009434807, | |
| "grad_norm": 4.501999855041504, | |
| "learning_rate": 0.0001952445442545386, | |
| "loss": 1.4482, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 0.49861165019556325, | |
| "grad_norm": 5.600002765655518, | |
| "learning_rate": 0.00019523025845861978, | |
| "loss": 1.4209, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 0.5001044994476458, | |
| "grad_norm": 5.138682842254639, | |
| "learning_rate": 0.00019521597266270092, | |
| "loss": 1.4287, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 0.5015973486997283, | |
| "grad_norm": 5.575449466705322, | |
| "learning_rate": 0.0001952016868667821, | |
| "loss": 1.3992, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 0.5030901979518109, | |
| "grad_norm": 3.6443893909454346, | |
| "learning_rate": 0.00019518740107086327, | |
| "loss": 1.3661, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 0.5045830472038934, | |
| "grad_norm": 3.904905319213867, | |
| "learning_rate": 0.00019517311527494444, | |
| "loss": 1.4448, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 0.5060758964559758, | |
| "grad_norm": 4.380904197692871, | |
| "learning_rate": 0.0001951588294790256, | |
| "loss": 1.4076, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 0.5075687457080584, | |
| "grad_norm": 3.5924415588378906, | |
| "learning_rate": 0.00019514454368310677, | |
| "loss": 1.3833, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.5090615949601409, | |
| "grad_norm": 3.7007193565368652, | |
| "learning_rate": 0.00019513025788718793, | |
| "loss": 1.391, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 0.5105544442122234, | |
| "grad_norm": 3.9879095554351807, | |
| "learning_rate": 0.0001951159720912691, | |
| "loss": 1.3419, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 0.512047293464306, | |
| "grad_norm": 5.663998126983643, | |
| "learning_rate": 0.00019510168629535026, | |
| "loss": 1.3481, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 0.5135401427163885, | |
| "grad_norm": 3.9803707599639893, | |
| "learning_rate": 0.00019508740049943143, | |
| "loss": 1.4034, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 0.5150329919684711, | |
| "grad_norm": 3.718477725982666, | |
| "learning_rate": 0.0001950731147035126, | |
| "loss": 1.406, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 0.5165258412205536, | |
| "grad_norm": 4.864751815795898, | |
| "learning_rate": 0.00019505882890759378, | |
| "loss": 1.375, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 0.518018690472636, | |
| "grad_norm": 3.697645664215088, | |
| "learning_rate": 0.00019504454311167492, | |
| "loss": 1.4283, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 0.5195115397247186, | |
| "grad_norm": 4.063074111938477, | |
| "learning_rate": 0.0001950302573157561, | |
| "loss": 1.378, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 0.5210043889768011, | |
| "grad_norm": 4.223004341125488, | |
| "learning_rate": 0.00019501597151983725, | |
| "loss": 1.3789, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 0.5224972382288836, | |
| "grad_norm": 3.329366683959961, | |
| "learning_rate": 0.00019500168572391844, | |
| "loss": 1.346, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.5239900874809662, | |
| "grad_norm": 4.774710178375244, | |
| "learning_rate": 0.00019498739992799958, | |
| "loss": 1.3895, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 0.5254829367330487, | |
| "grad_norm": 6.2145490646362305, | |
| "learning_rate": 0.00019497311413208077, | |
| "loss": 1.3715, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 0.5269757859851312, | |
| "grad_norm": 3.9069626331329346, | |
| "learning_rate": 0.00019495882833616194, | |
| "loss": 1.4572, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 0.5284686352372138, | |
| "grad_norm": 3.347576141357422, | |
| "learning_rate": 0.0001949445425402431, | |
| "loss": 1.359, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 0.5299614844892963, | |
| "grad_norm": 5.305202484130859, | |
| "learning_rate": 0.00019493025674432427, | |
| "loss": 1.4038, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 0.5314543337413788, | |
| "grad_norm": 3.865619659423828, | |
| "learning_rate": 0.00019491597094840543, | |
| "loss": 1.3913, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 0.5329471829934613, | |
| "grad_norm": 4.791336536407471, | |
| "learning_rate": 0.0001949016851524866, | |
| "loss": 1.3852, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 0.5344400322455438, | |
| "grad_norm": 3.7827060222625732, | |
| "learning_rate": 0.00019488739935656776, | |
| "loss": 1.3108, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 0.5359328814976264, | |
| "grad_norm": 4.945117473602295, | |
| "learning_rate": 0.00019487311356064892, | |
| "loss": 1.346, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 0.5374257307497089, | |
| "grad_norm": 4.561169147491455, | |
| "learning_rate": 0.0001948588277647301, | |
| "loss": 1.3904, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.5389185800017914, | |
| "grad_norm": 4.608798027038574, | |
| "learning_rate": 0.00019484454196881125, | |
| "loss": 1.4133, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 0.540411429253874, | |
| "grad_norm": 4.303143501281738, | |
| "learning_rate": 0.00019483025617289245, | |
| "loss": 1.3994, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 0.5419042785059565, | |
| "grad_norm": 5.815835952758789, | |
| "learning_rate": 0.00019481597037697358, | |
| "loss": 1.392, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 0.543397127758039, | |
| "grad_norm": 5.349491596221924, | |
| "learning_rate": 0.00019480168458105477, | |
| "loss": 1.418, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 0.5448899770101215, | |
| "grad_norm": 3.7407824993133545, | |
| "learning_rate": 0.0001947873987851359, | |
| "loss": 1.3747, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 0.546382826262204, | |
| "grad_norm": 5.2810163497924805, | |
| "learning_rate": 0.0001947731129892171, | |
| "loss": 1.4023, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 0.5478756755142866, | |
| "grad_norm": 4.417948246002197, | |
| "learning_rate": 0.00019475882719329824, | |
| "loss": 1.4005, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 0.5493685247663691, | |
| "grad_norm": 5.287749290466309, | |
| "learning_rate": 0.00019474454139737943, | |
| "loss": 1.4211, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 0.5508613740184516, | |
| "grad_norm": 4.0996809005737305, | |
| "learning_rate": 0.0001947302556014606, | |
| "loss": 1.3559, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 0.5523542232705342, | |
| "grad_norm": 5.229327201843262, | |
| "learning_rate": 0.00019471596980554176, | |
| "loss": 1.4549, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.5538470725226167, | |
| "grad_norm": 4.409546852111816, | |
| "learning_rate": 0.00019470168400962293, | |
| "loss": 1.3683, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 0.5553399217746992, | |
| "grad_norm": 5.4077229499816895, | |
| "learning_rate": 0.0001946873982137041, | |
| "loss": 1.398, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 0.5568327710267817, | |
| "grad_norm": 5.208966255187988, | |
| "learning_rate": 0.00019467311241778526, | |
| "loss": 1.3276, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 0.5583256202788642, | |
| "grad_norm": 4.8162617683410645, | |
| "learning_rate": 0.00019465882662186642, | |
| "loss": 1.3314, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 0.5598184695309467, | |
| "grad_norm": 5.04697322845459, | |
| "learning_rate": 0.00019464454082594759, | |
| "loss": 1.3883, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 0.5613113187830293, | |
| "grad_norm": 4.038108825683594, | |
| "learning_rate": 0.00019463025503002875, | |
| "loss": 1.4377, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 0.5628041680351118, | |
| "grad_norm": 4.910576820373535, | |
| "learning_rate": 0.00019461596923410992, | |
| "loss": 1.3713, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 0.5642970172871944, | |
| "grad_norm": 5.3433756828308105, | |
| "learning_rate": 0.00019460168343819108, | |
| "loss": 1.4359, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 0.5657898665392769, | |
| "grad_norm": 3.9515552520751953, | |
| "learning_rate": 0.00019458739764227224, | |
| "loss": 1.3608, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 0.5672827157913594, | |
| "grad_norm": 4.515705108642578, | |
| "learning_rate": 0.0001945731118463534, | |
| "loss": 1.3274, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.568775565043442, | |
| "grad_norm": 4.434077262878418, | |
| "learning_rate": 0.00019455882605043457, | |
| "loss": 1.3681, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 0.5702684142955244, | |
| "grad_norm": 4.534008979797363, | |
| "learning_rate": 0.00019454454025451574, | |
| "loss": 1.3863, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 0.5717612635476069, | |
| "grad_norm": 4.200322151184082, | |
| "learning_rate": 0.00019453025445859693, | |
| "loss": 1.3743, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 0.5732541127996895, | |
| "grad_norm": 5.686845779418945, | |
| "learning_rate": 0.00019451596866267807, | |
| "loss": 1.3225, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 0.574746962051772, | |
| "grad_norm": 7.821211814880371, | |
| "learning_rate": 0.00019450168286675926, | |
| "loss": 1.3775, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 0.5762398113038545, | |
| "grad_norm": 5.200834274291992, | |
| "learning_rate": 0.0001944873970708404, | |
| "loss": 1.3423, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 0.5777326605559371, | |
| "grad_norm": 5.26302433013916, | |
| "learning_rate": 0.0001944731112749216, | |
| "loss": 1.3813, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 0.5792255098080196, | |
| "grad_norm": 3.3207719326019287, | |
| "learning_rate": 0.00019445882547900273, | |
| "loss": 1.3922, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 0.5807183590601022, | |
| "grad_norm": 4.619020938873291, | |
| "learning_rate": 0.00019444453968308392, | |
| "loss": 1.3533, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 0.5822112083121846, | |
| "grad_norm": 5.780002593994141, | |
| "learning_rate": 0.00019443025388716508, | |
| "loss": 1.4035, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.5837040575642671, | |
| "grad_norm": 4.961215496063232, | |
| "learning_rate": 0.00019441596809124625, | |
| "loss": 1.3687, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 0.5851969068163497, | |
| "grad_norm": 4.50115442276001, | |
| "learning_rate": 0.0001944016822953274, | |
| "loss": 1.342, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 0.5866897560684322, | |
| "grad_norm": 3.9477944374084473, | |
| "learning_rate": 0.00019438739649940858, | |
| "loss": 1.394, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 0.5881826053205147, | |
| "grad_norm": 3.7466814517974854, | |
| "learning_rate": 0.00019437311070348974, | |
| "loss": 1.3414, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 0.5896754545725973, | |
| "grad_norm": 4.382058143615723, | |
| "learning_rate": 0.0001943588249075709, | |
| "loss": 1.3669, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 0.5911683038246798, | |
| "grad_norm": 3.7016665935516357, | |
| "learning_rate": 0.00019434453911165207, | |
| "loss": 1.4548, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 0.5926611530767623, | |
| "grad_norm": 4.4738030433654785, | |
| "learning_rate": 0.00019433025331573324, | |
| "loss": 1.4273, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 0.5941540023288449, | |
| "grad_norm": 5.2445454597473145, | |
| "learning_rate": 0.0001943159675198144, | |
| "loss": 1.3746, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 0.5956468515809273, | |
| "grad_norm": 3.766219139099121, | |
| "learning_rate": 0.0001943016817238956, | |
| "loss": 1.4391, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 0.5971397008330099, | |
| "grad_norm": 6.310808181762695, | |
| "learning_rate": 0.00019428739592797673, | |
| "loss": 1.3316, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.5986325500850924, | |
| "grad_norm": 4.055521488189697, | |
| "learning_rate": 0.00019427311013205792, | |
| "loss": 1.3784, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 0.6001253993371749, | |
| "grad_norm": 4.933177471160889, | |
| "learning_rate": 0.00019425882433613906, | |
| "loss": 1.3352, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 0.6016182485892575, | |
| "grad_norm": 3.8867061138153076, | |
| "learning_rate": 0.00019424453854022025, | |
| "loss": 1.4169, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 0.60311109784134, | |
| "grad_norm": 3.364475727081299, | |
| "learning_rate": 0.0001942302527443014, | |
| "loss": 1.3767, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 0.6046039470934225, | |
| "grad_norm": 3.48152232170105, | |
| "learning_rate": 0.00019421596694838258, | |
| "loss": 1.3659, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 0.6060967963455051, | |
| "grad_norm": 3.3658649921417236, | |
| "learning_rate": 0.00019420168115246374, | |
| "loss": 1.3745, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 0.6075896455975875, | |
| "grad_norm": 4.441917896270752, | |
| "learning_rate": 0.0001941873953565449, | |
| "loss": 1.3827, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 0.60908249484967, | |
| "grad_norm": 5.014800548553467, | |
| "learning_rate": 0.00019417310956062607, | |
| "loss": 1.3792, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 0.6105753441017526, | |
| "grad_norm": 5.472316265106201, | |
| "learning_rate": 0.00019415882376470724, | |
| "loss": 1.394, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 0.6120681933538351, | |
| "grad_norm": 5.35073184967041, | |
| "learning_rate": 0.0001941445379687884, | |
| "loss": 1.401, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.6135610426059177, | |
| "grad_norm": 4.284445762634277, | |
| "learning_rate": 0.00019413025217286957, | |
| "loss": 1.4354, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 0.6150538918580002, | |
| "grad_norm": 3.561774492263794, | |
| "learning_rate": 0.00019411596637695073, | |
| "loss": 1.3295, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 0.6165467411100827, | |
| "grad_norm": 4.479186534881592, | |
| "learning_rate": 0.0001941016805810319, | |
| "loss": 1.3629, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 0.6180395903621653, | |
| "grad_norm": 4.186618804931641, | |
| "learning_rate": 0.00019408739478511306, | |
| "loss": 1.3399, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 0.6195324396142478, | |
| "grad_norm": 3.589655637741089, | |
| "learning_rate": 0.00019407310898919425, | |
| "loss": 1.3516, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 0.6210252888663302, | |
| "grad_norm": 4.330646514892578, | |
| "learning_rate": 0.0001940588231932754, | |
| "loss": 1.3148, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 0.6225181381184128, | |
| "grad_norm": 6.324933052062988, | |
| "learning_rate": 0.00019404453739735658, | |
| "loss": 1.331, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 0.6240109873704953, | |
| "grad_norm": 4.652800559997559, | |
| "learning_rate": 0.00019403025160143772, | |
| "loss": 1.3604, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 0.6255038366225778, | |
| "grad_norm": 4.831106662750244, | |
| "learning_rate": 0.0001940159658055189, | |
| "loss": 1.3322, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 0.6269966858746604, | |
| "grad_norm": 6.0938920974731445, | |
| "learning_rate": 0.00019400168000960005, | |
| "loss": 1.4106, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.6284895351267429, | |
| "grad_norm": 4.424108028411865, | |
| "learning_rate": 0.00019398739421368124, | |
| "loss": 1.4001, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 0.6299823843788255, | |
| "grad_norm": 4.329803466796875, | |
| "learning_rate": 0.0001939731084177624, | |
| "loss": 1.4048, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 0.631475233630908, | |
| "grad_norm": 3.915818929672241, | |
| "learning_rate": 0.00019395882262184357, | |
| "loss": 1.3619, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 0.6329680828829904, | |
| "grad_norm": 3.9562571048736572, | |
| "learning_rate": 0.00019394453682592474, | |
| "loss": 1.3636, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 0.634460932135073, | |
| "grad_norm": 5.229249954223633, | |
| "learning_rate": 0.0001939302510300059, | |
| "loss": 1.3502, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 0.6359537813871555, | |
| "grad_norm": 4.149145126342773, | |
| "learning_rate": 0.00019391596523408706, | |
| "loss": 1.3603, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 0.637446630639238, | |
| "grad_norm": 4.068868637084961, | |
| "learning_rate": 0.00019390167943816823, | |
| "loss": 1.3945, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 0.6389394798913206, | |
| "grad_norm": 3.6808931827545166, | |
| "learning_rate": 0.0001938873936422494, | |
| "loss": 1.4015, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 0.6404323291434031, | |
| "grad_norm": 4.391795635223389, | |
| "learning_rate": 0.00019387310784633056, | |
| "loss": 1.3428, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 0.6419251783954856, | |
| "grad_norm": 5.109655380249023, | |
| "learning_rate": 0.00019385882205041172, | |
| "loss": 1.3874, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.6434180276475682, | |
| "grad_norm": 4.560513496398926, | |
| "learning_rate": 0.0001938445362544929, | |
| "loss": 1.3833, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 0.6449108768996507, | |
| "grad_norm": 3.6108620166778564, | |
| "learning_rate": 0.00019383025045857405, | |
| "loss": 1.3981, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 0.6464037261517332, | |
| "grad_norm": 4.100367546081543, | |
| "learning_rate": 0.00019381596466265522, | |
| "loss": 1.3139, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 0.6478965754038157, | |
| "grad_norm": 3.1513540744781494, | |
| "learning_rate": 0.00019380167886673638, | |
| "loss": 1.3359, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 0.6493894246558982, | |
| "grad_norm": 4.793807506561279, | |
| "learning_rate": 0.00019378739307081755, | |
| "loss": 1.4025, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 0.6508822739079808, | |
| "grad_norm": 4.403114318847656, | |
| "learning_rate": 0.0001937731072748987, | |
| "loss": 1.349, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 0.6523751231600633, | |
| "grad_norm": 4.445423603057861, | |
| "learning_rate": 0.00019375882147897988, | |
| "loss": 1.4641, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 0.6538679724121458, | |
| "grad_norm": 5.721547603607178, | |
| "learning_rate": 0.00019374453568306107, | |
| "loss": 1.3451, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 0.6553608216642284, | |
| "grad_norm": 4.411465644836426, | |
| "learning_rate": 0.0001937302498871422, | |
| "loss": 1.3893, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 0.6568536709163109, | |
| "grad_norm": 3.181412696838379, | |
| "learning_rate": 0.0001937159640912234, | |
| "loss": 1.385, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.6583465201683933, | |
| "grad_norm": 7.374556541442871, | |
| "learning_rate": 0.00019370167829530453, | |
| "loss": 1.4051, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 0.6598393694204759, | |
| "grad_norm": 4.452084064483643, | |
| "learning_rate": 0.00019368739249938573, | |
| "loss": 1.3389, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 0.6613322186725584, | |
| "grad_norm": 5.60634708404541, | |
| "learning_rate": 0.0001936731067034669, | |
| "loss": 1.3924, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 0.662825067924641, | |
| "grad_norm": 4.35741662979126, | |
| "learning_rate": 0.00019365882090754806, | |
| "loss": 1.3957, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 0.6643179171767235, | |
| "grad_norm": 4.173916816711426, | |
| "learning_rate": 0.00019364453511162922, | |
| "loss": 1.3669, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 0.665810766428806, | |
| "grad_norm": 3.8707377910614014, | |
| "learning_rate": 0.00019363024931571038, | |
| "loss": 1.3478, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 0.6673036156808886, | |
| "grad_norm": 4.765937328338623, | |
| "learning_rate": 0.00019361596351979155, | |
| "loss": 1.4007, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 0.6687964649329711, | |
| "grad_norm": 4.315809726715088, | |
| "learning_rate": 0.00019360167772387271, | |
| "loss": 1.3622, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 0.6702893141850536, | |
| "grad_norm": 5.977219104766846, | |
| "learning_rate": 0.00019358739192795388, | |
| "loss": 1.3836, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 0.6717821634371361, | |
| "grad_norm": 4.420149803161621, | |
| "learning_rate": 0.00019357310613203504, | |
| "loss": 1.3488, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.6732750126892186, | |
| "grad_norm": 3.9537293910980225, | |
| "learning_rate": 0.0001935588203361162, | |
| "loss": 1.3892, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 0.6747678619413011, | |
| "grad_norm": 5.468355655670166, | |
| "learning_rate": 0.0001935445345401974, | |
| "loss": 1.4475, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 0.6762607111933837, | |
| "grad_norm": 4.3148674964904785, | |
| "learning_rate": 0.00019353024874427854, | |
| "loss": 1.3866, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 0.6777535604454662, | |
| "grad_norm": 4.004809379577637, | |
| "learning_rate": 0.00019351596294835973, | |
| "loss": 1.3811, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 0.6792464096975488, | |
| "grad_norm": 4.404988765716553, | |
| "learning_rate": 0.00019350167715244087, | |
| "loss": 1.3648, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 0.6807392589496313, | |
| "grad_norm": 5.115052223205566, | |
| "learning_rate": 0.00019348739135652206, | |
| "loss": 1.3523, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 0.6822321082017138, | |
| "grad_norm": 5.083719730377197, | |
| "learning_rate": 0.0001934731055606032, | |
| "loss": 1.3978, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 0.6837249574537964, | |
| "grad_norm": 4.038282871246338, | |
| "learning_rate": 0.0001934588197646844, | |
| "loss": 1.2788, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 0.6852178067058788, | |
| "grad_norm": 5.438407897949219, | |
| "learning_rate": 0.00019344453396876555, | |
| "loss": 1.4181, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 0.6867106559579613, | |
| "grad_norm": 5.381191730499268, | |
| "learning_rate": 0.00019343024817284672, | |
| "loss": 1.4145, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.6882035052100439, | |
| "grad_norm": 3.183706283569336, | |
| "learning_rate": 0.00019341596237692788, | |
| "loss": 1.3271, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 0.6896963544621264, | |
| "grad_norm": 4.063404083251953, | |
| "learning_rate": 0.00019340167658100905, | |
| "loss": 1.3717, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 0.6911892037142089, | |
| "grad_norm": 5.677481651306152, | |
| "learning_rate": 0.0001933873907850902, | |
| "loss": 1.344, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 0.6926820529662915, | |
| "grad_norm": 5.376470565795898, | |
| "learning_rate": 0.00019337310498917138, | |
| "loss": 1.295, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 0.694174902218374, | |
| "grad_norm": 3.8844990730285645, | |
| "learning_rate": 0.00019335881919325254, | |
| "loss": 1.381, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 0.6956677514704566, | |
| "grad_norm": 5.285017013549805, | |
| "learning_rate": 0.0001933445333973337, | |
| "loss": 1.3505, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 0.697160600722539, | |
| "grad_norm": 4.133642196655273, | |
| "learning_rate": 0.00019333024760141487, | |
| "loss": 1.3604, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 0.6986534499746215, | |
| "grad_norm": 5.037447929382324, | |
| "learning_rate": 0.00019331596180549606, | |
| "loss": 1.3209, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 0.7001462992267041, | |
| "grad_norm": 4.916257858276367, | |
| "learning_rate": 0.0001933016760095772, | |
| "loss": 1.4084, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 0.7016391484787866, | |
| "grad_norm": 3.469505786895752, | |
| "learning_rate": 0.0001932873902136584, | |
| "loss": 1.3705, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.7031319977308691, | |
| "grad_norm": 3.624896287918091, | |
| "learning_rate": 0.00019327310441773953, | |
| "loss": 1.3507, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 0.7046248469829517, | |
| "grad_norm": 4.352174758911133, | |
| "learning_rate": 0.00019325881862182072, | |
| "loss": 1.3184, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 0.7061176962350342, | |
| "grad_norm": 6.4549150466918945, | |
| "learning_rate": 0.00019324453282590186, | |
| "loss": 1.4161, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 0.7076105454871167, | |
| "grad_norm": 6.221735000610352, | |
| "learning_rate": 0.00019323024702998305, | |
| "loss": 1.3425, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 0.7091033947391993, | |
| "grad_norm": 4.285811901092529, | |
| "learning_rate": 0.00019321596123406421, | |
| "loss": 1.3418, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 0.7105962439912817, | |
| "grad_norm": 4.533527374267578, | |
| "learning_rate": 0.00019320167543814538, | |
| "loss": 1.3723, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 0.7120890932433643, | |
| "grad_norm": 3.838109016418457, | |
| "learning_rate": 0.00019318738964222654, | |
| "loss": 1.3624, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 0.7135819424954468, | |
| "grad_norm": 3.8401126861572266, | |
| "learning_rate": 0.0001931731038463077, | |
| "loss": 1.4239, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 0.7150747917475293, | |
| "grad_norm": 5.9049787521362305, | |
| "learning_rate": 0.00019315881805038887, | |
| "loss": 1.3642, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 0.7165676409996119, | |
| "grad_norm": 5.397033214569092, | |
| "learning_rate": 0.00019314453225447004, | |
| "loss": 1.3298, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.7180604902516944, | |
| "grad_norm": 5.649387359619141, | |
| "learning_rate": 0.0001931302464585512, | |
| "loss": 1.4102, | |
| "step": 24050 | |
| }, | |
| { | |
| "epoch": 0.7195533395037769, | |
| "grad_norm": 5.697938919067383, | |
| "learning_rate": 0.00019311596066263237, | |
| "loss": 1.3765, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 0.7210461887558595, | |
| "grad_norm": 4.244998455047607, | |
| "learning_rate": 0.00019310167486671353, | |
| "loss": 1.3471, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 0.722539038007942, | |
| "grad_norm": 4.579226493835449, | |
| "learning_rate": 0.0001930873890707947, | |
| "loss": 1.3897, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 0.7240318872600244, | |
| "grad_norm": 8.80657958984375, | |
| "learning_rate": 0.00019307310327487586, | |
| "loss": 1.3628, | |
| "step": 24250 | |
| }, | |
| { | |
| "epoch": 0.725524736512107, | |
| "grad_norm": 5.42709493637085, | |
| "learning_rate": 0.00019305881747895703, | |
| "loss": 1.3587, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 0.7270175857641895, | |
| "grad_norm": 4.2680840492248535, | |
| "learning_rate": 0.0001930445316830382, | |
| "loss": 1.3414, | |
| "step": 24350 | |
| }, | |
| { | |
| "epoch": 0.7285104350162721, | |
| "grad_norm": 5.641107559204102, | |
| "learning_rate": 0.00019303024588711935, | |
| "loss": 1.4095, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 0.7300032842683546, | |
| "grad_norm": 5.29530143737793, | |
| "learning_rate": 0.00019301596009120052, | |
| "loss": 1.389, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 0.7314961335204371, | |
| "grad_norm": 4.110136032104492, | |
| "learning_rate": 0.00019300167429528168, | |
| "loss": 1.4641, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.7329889827725197, | |
| "grad_norm": 4.390302658081055, | |
| "learning_rate": 0.00019298738849936288, | |
| "loss": 1.4028, | |
| "step": 24550 | |
| }, | |
| { | |
| "epoch": 0.7344818320246022, | |
| "grad_norm": 3.717409372329712, | |
| "learning_rate": 0.000192973102703444, | |
| "loss": 1.436, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 0.7359746812766846, | |
| "grad_norm": 5.399808406829834, | |
| "learning_rate": 0.0001929588169075252, | |
| "loss": 1.2887, | |
| "step": 24650 | |
| }, | |
| { | |
| "epoch": 0.7374675305287672, | |
| "grad_norm": 5.027936935424805, | |
| "learning_rate": 0.00019294453111160634, | |
| "loss": 1.3591, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 0.7389603797808497, | |
| "grad_norm": 5.12235689163208, | |
| "learning_rate": 0.00019293024531568753, | |
| "loss": 1.4305, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 0.7404532290329322, | |
| "grad_norm": 4.445746898651123, | |
| "learning_rate": 0.0001929159595197687, | |
| "loss": 1.3609, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 0.7419460782850148, | |
| "grad_norm": 4.590288162231445, | |
| "learning_rate": 0.00019290167372384986, | |
| "loss": 1.3811, | |
| "step": 24850 | |
| }, | |
| { | |
| "epoch": 0.7434389275370973, | |
| "grad_norm": 3.841573476791382, | |
| "learning_rate": 0.00019288738792793103, | |
| "loss": 1.3632, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 0.7449317767891799, | |
| "grad_norm": 5.2155327796936035, | |
| "learning_rate": 0.0001928731021320122, | |
| "loss": 1.4422, | |
| "step": 24950 | |
| }, | |
| { | |
| "epoch": 0.7464246260412624, | |
| "grad_norm": 4.942720413208008, | |
| "learning_rate": 0.00019285881633609336, | |
| "loss": 1.3916, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.7479174752933448, | |
| "grad_norm": 5.292357921600342, | |
| "learning_rate": 0.00019284453054017452, | |
| "loss": 1.3048, | |
| "step": 25050 | |
| }, | |
| { | |
| "epoch": 0.7494103245454274, | |
| "grad_norm": 6.690375804901123, | |
| "learning_rate": 0.0001928302447442557, | |
| "loss": 1.3967, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 0.7509031737975099, | |
| "grad_norm": 4.590394496917725, | |
| "learning_rate": 0.00019281595894833685, | |
| "loss": 1.3925, | |
| "step": 25150 | |
| }, | |
| { | |
| "epoch": 0.7523960230495924, | |
| "grad_norm": 4.220889091491699, | |
| "learning_rate": 0.00019280167315241802, | |
| "loss": 1.3263, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 0.753888872301675, | |
| "grad_norm": 4.847371578216553, | |
| "learning_rate": 0.00019278738735649918, | |
| "loss": 1.4141, | |
| "step": 25250 | |
| }, | |
| { | |
| "epoch": 0.7553817215537575, | |
| "grad_norm": 5.392793655395508, | |
| "learning_rate": 0.00019277310156058035, | |
| "loss": 1.3147, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 0.75687457080584, | |
| "grad_norm": 4.261468887329102, | |
| "learning_rate": 0.00019275881576466154, | |
| "loss": 1.3102, | |
| "step": 25350 | |
| }, | |
| { | |
| "epoch": 0.7583674200579226, | |
| "grad_norm": 4.498802661895752, | |
| "learning_rate": 0.00019274452996874267, | |
| "loss": 1.3912, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 0.759860269310005, | |
| "grad_norm": 5.2235283851623535, | |
| "learning_rate": 0.00019273024417282387, | |
| "loss": 1.3375, | |
| "step": 25450 | |
| }, | |
| { | |
| "epoch": 0.7613531185620876, | |
| "grad_norm": 6.409016132354736, | |
| "learning_rate": 0.000192715958376905, | |
| "loss": 1.3339, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.7628459678141701, | |
| "grad_norm": 4.4392805099487305, | |
| "learning_rate": 0.0001927016725809862, | |
| "loss": 1.3599, | |
| "step": 25550 | |
| }, | |
| { | |
| "epoch": 0.7643388170662526, | |
| "grad_norm": 5.580776691436768, | |
| "learning_rate": 0.00019268738678506736, | |
| "loss": 1.3812, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 0.7658316663183352, | |
| "grad_norm": 5.473046779632568, | |
| "learning_rate": 0.00019267310098914852, | |
| "loss": 1.3582, | |
| "step": 25650 | |
| }, | |
| { | |
| "epoch": 0.7673245155704177, | |
| "grad_norm": 6.353076934814453, | |
| "learning_rate": 0.0001926588151932297, | |
| "loss": 1.3388, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 0.7688173648225002, | |
| "grad_norm": 4.247453689575195, | |
| "learning_rate": 0.00019264452939731085, | |
| "loss": 1.3745, | |
| "step": 25750 | |
| }, | |
| { | |
| "epoch": 0.7703102140745828, | |
| "grad_norm": 5.048892498016357, | |
| "learning_rate": 0.00019263024360139202, | |
| "loss": 1.405, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 0.7718030633266653, | |
| "grad_norm": 4.883440017700195, | |
| "learning_rate": 0.00019261595780547318, | |
| "loss": 1.4082, | |
| "step": 25850 | |
| }, | |
| { | |
| "epoch": 0.7732959125787477, | |
| "grad_norm": 4.221151828765869, | |
| "learning_rate": 0.00019260167200955435, | |
| "loss": 1.3766, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 0.7747887618308303, | |
| "grad_norm": 8.68738079071045, | |
| "learning_rate": 0.0001925873862136355, | |
| "loss": 1.4046, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 0.7762816110829128, | |
| "grad_norm": 4.479017734527588, | |
| "learning_rate": 0.00019257310041771668, | |
| "loss": 1.3452, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.7777744603349954, | |
| "grad_norm": 4.299473285675049, | |
| "learning_rate": 0.00019255881462179787, | |
| "loss": 1.3702, | |
| "step": 26050 | |
| }, | |
| { | |
| "epoch": 0.7792673095870779, | |
| "grad_norm": 5.272589683532715, | |
| "learning_rate": 0.000192544528825879, | |
| "loss": 1.3725, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 0.7807601588391604, | |
| "grad_norm": 4.644061088562012, | |
| "learning_rate": 0.0001925302430299602, | |
| "loss": 1.4143, | |
| "step": 26150 | |
| }, | |
| { | |
| "epoch": 0.782253008091243, | |
| "grad_norm": 4.7033185958862305, | |
| "learning_rate": 0.00019251595723404134, | |
| "loss": 1.3666, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 0.7837458573433255, | |
| "grad_norm": 3.5262560844421387, | |
| "learning_rate": 0.00019250167143812253, | |
| "loss": 1.4135, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 0.785238706595408, | |
| "grad_norm": 3.8599159717559814, | |
| "learning_rate": 0.00019248738564220367, | |
| "loss": 1.3258, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 0.7867315558474905, | |
| "grad_norm": 5.743364334106445, | |
| "learning_rate": 0.00019247309984628486, | |
| "loss": 1.3946, | |
| "step": 26350 | |
| }, | |
| { | |
| "epoch": 0.788224405099573, | |
| "grad_norm": 5.478078365325928, | |
| "learning_rate": 0.00019245881405036602, | |
| "loss": 1.3881, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 0.7897172543516555, | |
| "grad_norm": 5.912649631500244, | |
| "learning_rate": 0.0001924445282544472, | |
| "loss": 1.4139, | |
| "step": 26450 | |
| }, | |
| { | |
| "epoch": 0.7912101036037381, | |
| "grad_norm": 3.753570079803467, | |
| "learning_rate": 0.00019243024245852835, | |
| "loss": 1.3267, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.7927029528558206, | |
| "grad_norm": 4.155190944671631, | |
| "learning_rate": 0.00019241595666260952, | |
| "loss": 1.3539, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 0.7941958021079032, | |
| "grad_norm": 4.314638614654541, | |
| "learning_rate": 0.00019240167086669068, | |
| "loss": 1.3635, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 0.7956886513599857, | |
| "grad_norm": 4.177329063415527, | |
| "learning_rate": 0.00019238738507077185, | |
| "loss": 1.3642, | |
| "step": 26650 | |
| }, | |
| { | |
| "epoch": 0.7971815006120682, | |
| "grad_norm": 4.3052144050598145, | |
| "learning_rate": 0.000192373099274853, | |
| "loss": 1.3011, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 0.7986743498641508, | |
| "grad_norm": 5.800657272338867, | |
| "learning_rate": 0.00019235881347893417, | |
| "loss": 1.3247, | |
| "step": 26750 | |
| }, | |
| { | |
| "epoch": 0.8001671991162332, | |
| "grad_norm": 4.211179733276367, | |
| "learning_rate": 0.00019234452768301534, | |
| "loss": 1.3399, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 0.8016600483683157, | |
| "grad_norm": 4.8080315589904785, | |
| "learning_rate": 0.0001923302418870965, | |
| "loss": 1.3439, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 0.8031528976203983, | |
| "grad_norm": 5.03045129776001, | |
| "learning_rate": 0.00019231595609117767, | |
| "loss": 1.4009, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 0.8046457468724808, | |
| "grad_norm": 8.932162284851074, | |
| "learning_rate": 0.00019230167029525883, | |
| "loss": 1.3298, | |
| "step": 26950 | |
| }, | |
| { | |
| "epoch": 0.8061385961245633, | |
| "grad_norm": 5.651429176330566, | |
| "learning_rate": 0.00019228738449934, | |
| "loss": 1.4044, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.8076314453766459, | |
| "grad_norm": 4.428074836730957, | |
| "learning_rate": 0.00019227309870342116, | |
| "loss": 1.3988, | |
| "step": 27050 | |
| }, | |
| { | |
| "epoch": 0.8091242946287284, | |
| "grad_norm": 6.512781620025635, | |
| "learning_rate": 0.00019225881290750233, | |
| "loss": 1.3529, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 0.810617143880811, | |
| "grad_norm": 5.393406867980957, | |
| "learning_rate": 0.0001922445271115835, | |
| "loss": 1.3266, | |
| "step": 27150 | |
| }, | |
| { | |
| "epoch": 0.8121099931328934, | |
| "grad_norm": 3.74702525138855, | |
| "learning_rate": 0.00019223024131566468, | |
| "loss": 1.416, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 0.8136028423849759, | |
| "grad_norm": 3.856290817260742, | |
| "learning_rate": 0.00019221595551974582, | |
| "loss": 1.4082, | |
| "step": 27250 | |
| }, | |
| { | |
| "epoch": 0.8150956916370585, | |
| "grad_norm": 4.597848415374756, | |
| "learning_rate": 0.000192201669723827, | |
| "loss": 1.3751, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 0.816588540889141, | |
| "grad_norm": 3.875593662261963, | |
| "learning_rate": 0.00019218738392790815, | |
| "loss": 1.4024, | |
| "step": 27350 | |
| }, | |
| { | |
| "epoch": 0.8180813901412235, | |
| "grad_norm": 5.470495700836182, | |
| "learning_rate": 0.00019217309813198934, | |
| "loss": 1.394, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 0.8195742393933061, | |
| "grad_norm": 4.562834739685059, | |
| "learning_rate": 0.00019215881233607048, | |
| "loss": 1.3161, | |
| "step": 27450 | |
| }, | |
| { | |
| "epoch": 0.8210670886453886, | |
| "grad_norm": 4.183352470397949, | |
| "learning_rate": 0.00019214452654015167, | |
| "loss": 1.3427, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.8225599378974711, | |
| "grad_norm": 5.345236301422119, | |
| "learning_rate": 0.00019213024074423284, | |
| "loss": 1.3551, | |
| "step": 27550 | |
| }, | |
| { | |
| "epoch": 0.8240527871495537, | |
| "grad_norm": 5.217405319213867, | |
| "learning_rate": 0.000192115954948314, | |
| "loss": 1.3174, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 0.8255456364016361, | |
| "grad_norm": 4.486965179443359, | |
| "learning_rate": 0.00019210166915239517, | |
| "loss": 1.3931, | |
| "step": 27650 | |
| }, | |
| { | |
| "epoch": 0.8270384856537187, | |
| "grad_norm": 4.183075904846191, | |
| "learning_rate": 0.00019208738335647633, | |
| "loss": 1.3672, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 0.8285313349058012, | |
| "grad_norm": 4.916398525238037, | |
| "learning_rate": 0.0001920730975605575, | |
| "loss": 1.3993, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 0.8300241841578837, | |
| "grad_norm": 3.99765682220459, | |
| "learning_rate": 0.00019205881176463866, | |
| "loss": 1.362, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 0.8315170334099663, | |
| "grad_norm": 3.948981523513794, | |
| "learning_rate": 0.00019204452596871982, | |
| "loss": 1.3912, | |
| "step": 27850 | |
| }, | |
| { | |
| "epoch": 0.8330098826620488, | |
| "grad_norm": 6.524683475494385, | |
| "learning_rate": 0.000192030240172801, | |
| "loss": 1.3845, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 0.8345027319141313, | |
| "grad_norm": 4.598319053649902, | |
| "learning_rate": 0.00019201595437688215, | |
| "loss": 1.38, | |
| "step": 27950 | |
| }, | |
| { | |
| "epoch": 0.8359955811662139, | |
| "grad_norm": 4.287365436553955, | |
| "learning_rate": 0.00019200166858096335, | |
| "loss": 1.3687, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.8374884304182963, | |
| "grad_norm": 5.497170448303223, | |
| "learning_rate": 0.00019198738278504448, | |
| "loss": 1.4324, | |
| "step": 28050 | |
| }, | |
| { | |
| "epoch": 0.8389812796703788, | |
| "grad_norm": 3.9373042583465576, | |
| "learning_rate": 0.00019197309698912567, | |
| "loss": 1.3892, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 0.8404741289224614, | |
| "grad_norm": 5.157922267913818, | |
| "learning_rate": 0.0001919588111932068, | |
| "loss": 1.3764, | |
| "step": 28150 | |
| }, | |
| { | |
| "epoch": 0.8419669781745439, | |
| "grad_norm": 4.0024895668029785, | |
| "learning_rate": 0.000191944525397288, | |
| "loss": 1.3571, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 0.8434598274266265, | |
| "grad_norm": 4.894957542419434, | |
| "learning_rate": 0.00019193023960136917, | |
| "loss": 1.3997, | |
| "step": 28250 | |
| }, | |
| { | |
| "epoch": 0.844952676678709, | |
| "grad_norm": 4.829247951507568, | |
| "learning_rate": 0.00019191595380545033, | |
| "loss": 1.3751, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 0.8464455259307915, | |
| "grad_norm": 4.123593330383301, | |
| "learning_rate": 0.0001919016680095315, | |
| "loss": 1.4183, | |
| "step": 28350 | |
| }, | |
| { | |
| "epoch": 0.8479383751828741, | |
| "grad_norm": 4.012912273406982, | |
| "learning_rate": 0.00019188738221361266, | |
| "loss": 1.3757, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 0.8494312244349566, | |
| "grad_norm": 5.17979097366333, | |
| "learning_rate": 0.00019187309641769383, | |
| "loss": 1.3975, | |
| "step": 28450 | |
| }, | |
| { | |
| "epoch": 0.850924073687039, | |
| "grad_norm": 4.665642261505127, | |
| "learning_rate": 0.000191858810621775, | |
| "loss": 1.4539, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.8524169229391216, | |
| "grad_norm": 4.333798408508301, | |
| "learning_rate": 0.00019184452482585616, | |
| "loss": 1.3711, | |
| "step": 28550 | |
| }, | |
| { | |
| "epoch": 0.8539097721912041, | |
| "grad_norm": 4.485865116119385, | |
| "learning_rate": 0.00019183023902993732, | |
| "loss": 1.4299, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 0.8554026214432866, | |
| "grad_norm": 6.3318328857421875, | |
| "learning_rate": 0.00019181595323401849, | |
| "loss": 1.3621, | |
| "step": 28650 | |
| }, | |
| { | |
| "epoch": 0.8568954706953692, | |
| "grad_norm": 3.915356159210205, | |
| "learning_rate": 0.00019180166743809965, | |
| "loss": 1.4561, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 0.8583883199474517, | |
| "grad_norm": 4.613978862762451, | |
| "learning_rate": 0.00019178738164218081, | |
| "loss": 1.3267, | |
| "step": 28750 | |
| }, | |
| { | |
| "epoch": 0.8598811691995343, | |
| "grad_norm": 4.935427188873291, | |
| "learning_rate": 0.000191773095846262, | |
| "loss": 1.3962, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 0.8613740184516168, | |
| "grad_norm": 4.204285144805908, | |
| "learning_rate": 0.00019175881005034314, | |
| "loss": 1.3644, | |
| "step": 28850 | |
| }, | |
| { | |
| "epoch": 0.8628668677036992, | |
| "grad_norm": 3.901266098022461, | |
| "learning_rate": 0.00019174452425442434, | |
| "loss": 1.344, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 0.8643597169557818, | |
| "grad_norm": 5.1740922927856445, | |
| "learning_rate": 0.00019173023845850547, | |
| "loss": 1.3852, | |
| "step": 28950 | |
| }, | |
| { | |
| "epoch": 0.8658525662078643, | |
| "grad_norm": 4.984529972076416, | |
| "learning_rate": 0.00019171595266258667, | |
| "loss": 1.3853, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.8673454154599468, | |
| "grad_norm": 4.719232082366943, | |
| "learning_rate": 0.00019170166686666783, | |
| "loss": 1.3962, | |
| "step": 29050 | |
| }, | |
| { | |
| "epoch": 0.8688382647120294, | |
| "grad_norm": 6.084499359130859, | |
| "learning_rate": 0.000191687381070749, | |
| "loss": 1.3377, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 0.8703311139641119, | |
| "grad_norm": 5.261173248291016, | |
| "learning_rate": 0.00019167309527483016, | |
| "loss": 1.3673, | |
| "step": 29150 | |
| }, | |
| { | |
| "epoch": 0.8718239632161944, | |
| "grad_norm": 5.18539571762085, | |
| "learning_rate": 0.00019165880947891132, | |
| "loss": 1.358, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 0.873316812468277, | |
| "grad_norm": 4.789880275726318, | |
| "learning_rate": 0.0001916445236829925, | |
| "loss": 1.3426, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 0.8748096617203595, | |
| "grad_norm": 3.2945287227630615, | |
| "learning_rate": 0.00019163023788707365, | |
| "loss": 1.3308, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 0.876302510972442, | |
| "grad_norm": 5.060371398925781, | |
| "learning_rate": 0.00019161595209115482, | |
| "loss": 1.3497, | |
| "step": 29350 | |
| }, | |
| { | |
| "epoch": 0.8777953602245245, | |
| "grad_norm": 4.771635055541992, | |
| "learning_rate": 0.00019160166629523598, | |
| "loss": 1.3517, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 0.879288209476607, | |
| "grad_norm": 4.408042907714844, | |
| "learning_rate": 0.00019158738049931715, | |
| "loss": 1.3636, | |
| "step": 29450 | |
| }, | |
| { | |
| "epoch": 0.8807810587286896, | |
| "grad_norm": 5.183899879455566, | |
| "learning_rate": 0.0001915730947033983, | |
| "loss": 1.3569, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.8822739079807721, | |
| "grad_norm": 4.176016807556152, | |
| "learning_rate": 0.00019155880890747948, | |
| "loss": 1.3659, | |
| "step": 29550 | |
| }, | |
| { | |
| "epoch": 0.8837667572328546, | |
| "grad_norm": 4.783830165863037, | |
| "learning_rate": 0.00019154452311156064, | |
| "loss": 1.368, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 0.8852596064849372, | |
| "grad_norm": 3.7985739707946777, | |
| "learning_rate": 0.0001915302373156418, | |
| "loss": 1.4091, | |
| "step": 29650 | |
| }, | |
| { | |
| "epoch": 0.8867524557370197, | |
| "grad_norm": 4.401581287384033, | |
| "learning_rate": 0.00019151595151972297, | |
| "loss": 1.3613, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 0.8882453049891021, | |
| "grad_norm": 6.214754581451416, | |
| "learning_rate": 0.00019150166572380414, | |
| "loss": 1.4077, | |
| "step": 29750 | |
| }, | |
| { | |
| "epoch": 0.8897381542411847, | |
| "grad_norm": 4.197826862335205, | |
| "learning_rate": 0.0001914873799278853, | |
| "loss": 1.347, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 0.8912310034932672, | |
| "grad_norm": 3.1535027027130127, | |
| "learning_rate": 0.0001914730941319665, | |
| "loss": 1.3452, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 0.8927238527453498, | |
| "grad_norm": 4.618538856506348, | |
| "learning_rate": 0.00019145880833604763, | |
| "loss": 1.3417, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 0.8942167019974323, | |
| "grad_norm": 3.913506031036377, | |
| "learning_rate": 0.00019144452254012882, | |
| "loss": 1.3503, | |
| "step": 29950 | |
| }, | |
| { | |
| "epoch": 0.8957095512495148, | |
| "grad_norm": 4.013761043548584, | |
| "learning_rate": 0.00019143023674420996, | |
| "loss": 1.4109, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.8972024005015974, | |
| "grad_norm": 4.6257758140563965, | |
| "learning_rate": 0.00019141595094829115, | |
| "loss": 1.3679, | |
| "step": 30050 | |
| }, | |
| { | |
| "epoch": 0.8986952497536799, | |
| "grad_norm": 4.422520637512207, | |
| "learning_rate": 0.0001914016651523723, | |
| "loss": 1.3893, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 0.9001880990057624, | |
| "grad_norm": 4.911538124084473, | |
| "learning_rate": 0.00019138737935645348, | |
| "loss": 1.3346, | |
| "step": 30150 | |
| }, | |
| { | |
| "epoch": 0.901680948257845, | |
| "grad_norm": 6.410045623779297, | |
| "learning_rate": 0.00019137309356053464, | |
| "loss": 1.3651, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 0.9031737975099274, | |
| "grad_norm": 3.8565444946289062, | |
| "learning_rate": 0.0001913588077646158, | |
| "loss": 1.3436, | |
| "step": 30250 | |
| }, | |
| { | |
| "epoch": 0.9046666467620099, | |
| "grad_norm": 4.632288455963135, | |
| "learning_rate": 0.00019134452196869697, | |
| "loss": 1.3858, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 0.9061594960140925, | |
| "grad_norm": 5.382070064544678, | |
| "learning_rate": 0.00019133023617277814, | |
| "loss": 1.3872, | |
| "step": 30350 | |
| }, | |
| { | |
| "epoch": 0.907652345266175, | |
| "grad_norm": 4.425014019012451, | |
| "learning_rate": 0.0001913159503768593, | |
| "loss": 1.4488, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 0.9091451945182576, | |
| "grad_norm": 3.7266223430633545, | |
| "learning_rate": 0.00019130166458094047, | |
| "loss": 1.376, | |
| "step": 30450 | |
| }, | |
| { | |
| "epoch": 0.9106380437703401, | |
| "grad_norm": 7.25547981262207, | |
| "learning_rate": 0.00019128737878502163, | |
| "loss": 1.3488, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.9121308930224226, | |
| "grad_norm": 5.824578285217285, | |
| "learning_rate": 0.0001912730929891028, | |
| "loss": 1.4001, | |
| "step": 30550 | |
| }, | |
| { | |
| "epoch": 0.9136237422745052, | |
| "grad_norm": 5.808544635772705, | |
| "learning_rate": 0.00019125880719318396, | |
| "loss": 1.3132, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 0.9151165915265876, | |
| "grad_norm": 4.343785285949707, | |
| "learning_rate": 0.00019124452139726515, | |
| "loss": 1.3592, | |
| "step": 30650 | |
| }, | |
| { | |
| "epoch": 0.9166094407786701, | |
| "grad_norm": 5.0626325607299805, | |
| "learning_rate": 0.0001912302356013463, | |
| "loss": 1.4418, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 0.9181022900307527, | |
| "grad_norm": 4.336055755615234, | |
| "learning_rate": 0.00019121594980542748, | |
| "loss": 1.3624, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 0.9195951392828352, | |
| "grad_norm": 6.215260982513428, | |
| "learning_rate": 0.00019120166400950862, | |
| "loss": 1.4053, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 0.9210879885349177, | |
| "grad_norm": 4.496364116668701, | |
| "learning_rate": 0.0001911873782135898, | |
| "loss": 1.4117, | |
| "step": 30850 | |
| }, | |
| { | |
| "epoch": 0.9225808377870003, | |
| "grad_norm": 4.023138046264648, | |
| "learning_rate": 0.00019117309241767095, | |
| "loss": 1.3783, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 0.9240736870390828, | |
| "grad_norm": 3.8177783489227295, | |
| "learning_rate": 0.00019115880662175214, | |
| "loss": 1.3127, | |
| "step": 30950 | |
| }, | |
| { | |
| "epoch": 0.9255665362911654, | |
| "grad_norm": 3.893087387084961, | |
| "learning_rate": 0.0001911445208258333, | |
| "loss": 1.3359, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.9270593855432478, | |
| "grad_norm": 3.9967384338378906, | |
| "learning_rate": 0.00019113023502991447, | |
| "loss": 1.3897, | |
| "step": 31050 | |
| }, | |
| { | |
| "epoch": 0.9285522347953303, | |
| "grad_norm": 3.2351789474487305, | |
| "learning_rate": 0.00019111594923399563, | |
| "loss": 1.3406, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 0.9300450840474129, | |
| "grad_norm": 4.571500778198242, | |
| "learning_rate": 0.0001911016634380768, | |
| "loss": 1.3783, | |
| "step": 31150 | |
| }, | |
| { | |
| "epoch": 0.9315379332994954, | |
| "grad_norm": 6.241518020629883, | |
| "learning_rate": 0.00019108737764215796, | |
| "loss": 1.3659, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 0.9330307825515779, | |
| "grad_norm": 3.2547826766967773, | |
| "learning_rate": 0.00019107309184623913, | |
| "loss": 1.3137, | |
| "step": 31250 | |
| }, | |
| { | |
| "epoch": 0.9345236318036605, | |
| "grad_norm": 5.386812686920166, | |
| "learning_rate": 0.0001910588060503203, | |
| "loss": 1.3974, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 0.936016481055743, | |
| "grad_norm": 4.239005088806152, | |
| "learning_rate": 0.00019104452025440146, | |
| "loss": 1.3789, | |
| "step": 31350 | |
| }, | |
| { | |
| "epoch": 0.9375093303078255, | |
| "grad_norm": 3.7252326011657715, | |
| "learning_rate": 0.00019103023445848262, | |
| "loss": 1.3622, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 0.9390021795599081, | |
| "grad_norm": 5.890969276428223, | |
| "learning_rate": 0.00019101594866256381, | |
| "loss": 1.3905, | |
| "step": 31450 | |
| }, | |
| { | |
| "epoch": 0.9404950288119905, | |
| "grad_norm": 5.796853542327881, | |
| "learning_rate": 0.00019100166286664495, | |
| "loss": 1.3797, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.9419878780640731, | |
| "grad_norm": 4.130026817321777, | |
| "learning_rate": 0.00019098737707072614, | |
| "loss": 1.3365, | |
| "step": 31550 | |
| }, | |
| { | |
| "epoch": 0.9434807273161556, | |
| "grad_norm": 3.65081524848938, | |
| "learning_rate": 0.00019097309127480728, | |
| "loss": 1.4347, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 0.9449735765682381, | |
| "grad_norm": 4.91404390335083, | |
| "learning_rate": 0.00019095880547888847, | |
| "loss": 1.4056, | |
| "step": 31650 | |
| }, | |
| { | |
| "epoch": 0.9464664258203207, | |
| "grad_norm": 4.7272114753723145, | |
| "learning_rate": 0.00019094451968296964, | |
| "loss": 1.2828, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 0.9479592750724032, | |
| "grad_norm": 5.111660957336426, | |
| "learning_rate": 0.0001909302338870508, | |
| "loss": 1.3486, | |
| "step": 31750 | |
| }, | |
| { | |
| "epoch": 0.9494521243244857, | |
| "grad_norm": 3.1206741333007812, | |
| "learning_rate": 0.00019091594809113197, | |
| "loss": 1.3416, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 0.9509449735765683, | |
| "grad_norm": 4.359163761138916, | |
| "learning_rate": 0.00019090166229521313, | |
| "loss": 1.3471, | |
| "step": 31850 | |
| }, | |
| { | |
| "epoch": 0.9524378228286507, | |
| "grad_norm": 4.667807102203369, | |
| "learning_rate": 0.0001908873764992943, | |
| "loss": 1.4042, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 0.9539306720807332, | |
| "grad_norm": 4.410369873046875, | |
| "learning_rate": 0.00019087309070337546, | |
| "loss": 1.3909, | |
| "step": 31950 | |
| }, | |
| { | |
| "epoch": 0.9554235213328158, | |
| "grad_norm": 4.987631320953369, | |
| "learning_rate": 0.00019085880490745663, | |
| "loss": 1.3548, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.9569163705848983, | |
| "grad_norm": 4.66121768951416, | |
| "learning_rate": 0.0001908445191115378, | |
| "loss": 1.3753, | |
| "step": 32050 | |
| }, | |
| { | |
| "epoch": 0.9584092198369809, | |
| "grad_norm": 6.010061740875244, | |
| "learning_rate": 0.00019083023331561896, | |
| "loss": 1.4128, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 0.9599020690890634, | |
| "grad_norm": 3.118246078491211, | |
| "learning_rate": 0.00019081594751970012, | |
| "loss": 1.3625, | |
| "step": 32150 | |
| }, | |
| { | |
| "epoch": 0.9613949183411459, | |
| "grad_norm": 3.821732759475708, | |
| "learning_rate": 0.00019080166172378128, | |
| "loss": 1.3691, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 0.9628877675932285, | |
| "grad_norm": 5.321105480194092, | |
| "learning_rate": 0.00019078737592786245, | |
| "loss": 1.3499, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 0.964380616845311, | |
| "grad_norm": 5.963992595672607, | |
| "learning_rate": 0.00019077309013194361, | |
| "loss": 1.3145, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 0.9658734660973934, | |
| "grad_norm": 4.071386337280273, | |
| "learning_rate": 0.00019075880433602478, | |
| "loss": 1.3215, | |
| "step": 32350 | |
| }, | |
| { | |
| "epoch": 0.967366315349476, | |
| "grad_norm": 3.7641048431396484, | |
| "learning_rate": 0.00019074451854010594, | |
| "loss": 1.3846, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 0.9688591646015585, | |
| "grad_norm": 5.985085487365723, | |
| "learning_rate": 0.0001907302327441871, | |
| "loss": 1.3383, | |
| "step": 32450 | |
| }, | |
| { | |
| "epoch": 0.970352013853641, | |
| "grad_norm": 6.602528095245361, | |
| "learning_rate": 0.0001907159469482683, | |
| "loss": 1.4195, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.9718448631057236, | |
| "grad_norm": 5.370469570159912, | |
| "learning_rate": 0.00019070166115234944, | |
| "loss": 1.3485, | |
| "step": 32550 | |
| }, | |
| { | |
| "epoch": 0.9733377123578061, | |
| "grad_norm": 4.588457107543945, | |
| "learning_rate": 0.00019068737535643063, | |
| "loss": 1.3896, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 0.9748305616098887, | |
| "grad_norm": 6.389341354370117, | |
| "learning_rate": 0.00019067308956051177, | |
| "loss": 1.3118, | |
| "step": 32650 | |
| }, | |
| { | |
| "epoch": 0.9763234108619712, | |
| "grad_norm": 4.051975250244141, | |
| "learning_rate": 0.00019065880376459296, | |
| "loss": 1.4065, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 0.9778162601140536, | |
| "grad_norm": 5.474813938140869, | |
| "learning_rate": 0.0001906445179686741, | |
| "loss": 1.3967, | |
| "step": 32750 | |
| }, | |
| { | |
| "epoch": 0.9793091093661362, | |
| "grad_norm": 4.033454895019531, | |
| "learning_rate": 0.0001906302321727553, | |
| "loss": 1.3212, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 0.9808019586182187, | |
| "grad_norm": 4.46946382522583, | |
| "learning_rate": 0.00019061594637683645, | |
| "loss": 1.3917, | |
| "step": 32850 | |
| }, | |
| { | |
| "epoch": 0.9822948078703012, | |
| "grad_norm": 4.98955774307251, | |
| "learning_rate": 0.00019060166058091762, | |
| "loss": 1.3814, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 0.9837876571223838, | |
| "grad_norm": 4.879435062408447, | |
| "learning_rate": 0.00019058737478499878, | |
| "loss": 1.3486, | |
| "step": 32950 | |
| }, | |
| { | |
| "epoch": 0.9852805063744663, | |
| "grad_norm": 4.0941925048828125, | |
| "learning_rate": 0.00019057308898907995, | |
| "loss": 1.3289, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.9867733556265488, | |
| "grad_norm": 5.2992706298828125, | |
| "learning_rate": 0.0001905588031931611, | |
| "loss": 1.3458, | |
| "step": 33050 | |
| }, | |
| { | |
| "epoch": 0.9882662048786314, | |
| "grad_norm": 4.284411430358887, | |
| "learning_rate": 0.00019054451739724228, | |
| "loss": 1.3932, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 0.9897590541307139, | |
| "grad_norm": 4.969634532928467, | |
| "learning_rate": 0.00019053023160132344, | |
| "loss": 1.4044, | |
| "step": 33150 | |
| }, | |
| { | |
| "epoch": 0.9912519033827965, | |
| "grad_norm": 5.532953262329102, | |
| "learning_rate": 0.0001905159458054046, | |
| "loss": 1.3658, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 0.9927447526348789, | |
| "grad_norm": 4.402670383453369, | |
| "learning_rate": 0.00019050166000948577, | |
| "loss": 1.343, | |
| "step": 33250 | |
| }, | |
| { | |
| "epoch": 0.9942376018869614, | |
| "grad_norm": 4.458900451660156, | |
| "learning_rate": 0.00019048737421356696, | |
| "loss": 1.4002, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 0.995730451139044, | |
| "grad_norm": 3.934340238571167, | |
| "learning_rate": 0.0001904730884176481, | |
| "loss": 1.413, | |
| "step": 33350 | |
| }, | |
| { | |
| "epoch": 0.9972233003911265, | |
| "grad_norm": 4.274466514587402, | |
| "learning_rate": 0.0001904588026217293, | |
| "loss": 1.3552, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 0.998716149643209, | |
| "grad_norm": 4.774006366729736, | |
| "learning_rate": 0.00019044451682581043, | |
| "loss": 1.3825, | |
| "step": 33450 | |
| }, | |
| { | |
| "epoch": 1.0002089988952916, | |
| "grad_norm": 3.870762825012207, | |
| "learning_rate": 0.00019043023102989162, | |
| "loss": 1.3715, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.001701848147374, | |
| "grad_norm": 3.595686912536621, | |
| "learning_rate": 0.00019041594523397276, | |
| "loss": 1.3352, | |
| "step": 33550 | |
| }, | |
| { | |
| "epoch": 1.0031946973994565, | |
| "grad_norm": 5.492071151733398, | |
| "learning_rate": 0.00019040165943805395, | |
| "loss": 1.2927, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 1.004687546651539, | |
| "grad_norm": 5.381584167480469, | |
| "learning_rate": 0.00019038737364213511, | |
| "loss": 1.2545, | |
| "step": 33650 | |
| }, | |
| { | |
| "epoch": 1.0061803959036217, | |
| "grad_norm": 5.983656883239746, | |
| "learning_rate": 0.00019037308784621628, | |
| "loss": 1.2393, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 1.0076732451557042, | |
| "grad_norm": 4.956115245819092, | |
| "learning_rate": 0.00019035880205029744, | |
| "loss": 1.2931, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 1.0091660944077867, | |
| "grad_norm": 4.604572296142578, | |
| "learning_rate": 0.0001903445162543786, | |
| "loss": 1.2786, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 1.0106589436598692, | |
| "grad_norm": 5.043067932128906, | |
| "learning_rate": 0.00019033023045845977, | |
| "loss": 1.2933, | |
| "step": 33850 | |
| }, | |
| { | |
| "epoch": 1.0121517929119517, | |
| "grad_norm": 4.53336238861084, | |
| "learning_rate": 0.00019031594466254094, | |
| "loss": 1.3114, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 1.0136446421640344, | |
| "grad_norm": 5.106605052947998, | |
| "learning_rate": 0.0001903016588666221, | |
| "loss": 1.2994, | |
| "step": 33950 | |
| }, | |
| { | |
| "epoch": 1.0151374914161169, | |
| "grad_norm": 5.796351909637451, | |
| "learning_rate": 0.00019028737307070327, | |
| "loss": 1.2555, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.0166303406681994, | |
| "grad_norm": 4.970977306365967, | |
| "learning_rate": 0.00019027308727478443, | |
| "loss": 1.3343, | |
| "step": 34050 | |
| }, | |
| { | |
| "epoch": 1.0181231899202818, | |
| "grad_norm": 4.233397960662842, | |
| "learning_rate": 0.00019025880147886562, | |
| "loss": 1.2485, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 1.0196160391723643, | |
| "grad_norm": 4.012045383453369, | |
| "learning_rate": 0.00019024451568294676, | |
| "loss": 1.2816, | |
| "step": 34150 | |
| }, | |
| { | |
| "epoch": 1.0211088884244468, | |
| "grad_norm": 4.715073585510254, | |
| "learning_rate": 0.00019023022988702795, | |
| "loss": 1.2541, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 1.0226017376765295, | |
| "grad_norm": 3.7285947799682617, | |
| "learning_rate": 0.0001902159440911091, | |
| "loss": 1.3094, | |
| "step": 34250 | |
| }, | |
| { | |
| "epoch": 1.024094586928612, | |
| "grad_norm": 4.012038707733154, | |
| "learning_rate": 0.00019020165829519028, | |
| "loss": 1.2791, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 1.0255874361806945, | |
| "grad_norm": 4.04899263381958, | |
| "learning_rate": 0.00019018737249927142, | |
| "loss": 1.3085, | |
| "step": 34350 | |
| }, | |
| { | |
| "epoch": 1.027080285432777, | |
| "grad_norm": 4.380834102630615, | |
| "learning_rate": 0.0001901730867033526, | |
| "loss": 1.3212, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 1.0285731346848594, | |
| "grad_norm": 5.275148868560791, | |
| "learning_rate": 0.00019015880090743378, | |
| "loss": 1.2749, | |
| "step": 34450 | |
| }, | |
| { | |
| "epoch": 1.0300659839369422, | |
| "grad_norm": 4.162272930145264, | |
| "learning_rate": 0.00019014451511151494, | |
| "loss": 1.296, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.0315588331890246, | |
| "grad_norm": 4.128006935119629, | |
| "learning_rate": 0.0001901302293155961, | |
| "loss": 1.2547, | |
| "step": 34550 | |
| }, | |
| { | |
| "epoch": 1.0330516824411071, | |
| "grad_norm": 3.930121421813965, | |
| "learning_rate": 0.00019011594351967727, | |
| "loss": 1.2831, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 1.0345445316931896, | |
| "grad_norm": 4.515873908996582, | |
| "learning_rate": 0.00019010165772375843, | |
| "loss": 1.2747, | |
| "step": 34650 | |
| }, | |
| { | |
| "epoch": 1.036037380945272, | |
| "grad_norm": 4.484467506408691, | |
| "learning_rate": 0.0001900873719278396, | |
| "loss": 1.289, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 1.0375302301973546, | |
| "grad_norm": 3.8937742710113525, | |
| "learning_rate": 0.00019007308613192076, | |
| "loss": 1.2939, | |
| "step": 34750 | |
| }, | |
| { | |
| "epoch": 1.0390230794494373, | |
| "grad_norm": 4.367059230804443, | |
| "learning_rate": 0.00019005880033600193, | |
| "loss": 1.2522, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 1.0405159287015198, | |
| "grad_norm": 5.143396854400635, | |
| "learning_rate": 0.0001900445145400831, | |
| "loss": 1.2996, | |
| "step": 34850 | |
| }, | |
| { | |
| "epoch": 1.0420087779536022, | |
| "grad_norm": 5.060800552368164, | |
| "learning_rate": 0.00019003022874416426, | |
| "loss": 1.3122, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 1.0435016272056847, | |
| "grad_norm": 4.775914192199707, | |
| "learning_rate": 0.00019001594294824542, | |
| "loss": 1.2595, | |
| "step": 34950 | |
| }, | |
| { | |
| "epoch": 1.0449944764577672, | |
| "grad_norm": 5.256932258605957, | |
| "learning_rate": 0.0001900016571523266, | |
| "loss": 1.3148, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.04648732570985, | |
| "grad_norm": 4.253088474273682, | |
| "learning_rate": 0.00018998737135640775, | |
| "loss": 1.2575, | |
| "step": 35050 | |
| }, | |
| { | |
| "epoch": 1.0479801749619324, | |
| "grad_norm": 4.784812927246094, | |
| "learning_rate": 0.00018997308556048892, | |
| "loss": 1.2911, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 1.049473024214015, | |
| "grad_norm": 3.9015183448791504, | |
| "learning_rate": 0.0001899587997645701, | |
| "loss": 1.2647, | |
| "step": 35150 | |
| }, | |
| { | |
| "epoch": 1.0509658734660974, | |
| "grad_norm": 4.729675769805908, | |
| "learning_rate": 0.00018994451396865125, | |
| "loss": 1.2876, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 1.0524587227181799, | |
| "grad_norm": 4.921074867248535, | |
| "learning_rate": 0.00018993022817273244, | |
| "loss": 1.2956, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 1.0539515719702623, | |
| "grad_norm": 4.466576099395752, | |
| "learning_rate": 0.00018991594237681357, | |
| "loss": 1.2938, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 1.055444421222345, | |
| "grad_norm": 4.142183780670166, | |
| "learning_rate": 0.00018990165658089477, | |
| "loss": 1.282, | |
| "step": 35350 | |
| }, | |
| { | |
| "epoch": 1.0569372704744275, | |
| "grad_norm": 4.372234344482422, | |
| "learning_rate": 0.0001898873707849759, | |
| "loss": 1.2793, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 1.05843011972651, | |
| "grad_norm": 5.349823474884033, | |
| "learning_rate": 0.0001898730849890571, | |
| "loss": 1.3678, | |
| "step": 35450 | |
| }, | |
| { | |
| "epoch": 1.0599229689785925, | |
| "grad_norm": 4.57612419128418, | |
| "learning_rate": 0.00018985879919313826, | |
| "loss": 1.3256, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.061415818230675, | |
| "grad_norm": 5.3342156410217285, | |
| "learning_rate": 0.00018984451339721942, | |
| "loss": 1.2897, | |
| "step": 35550 | |
| }, | |
| { | |
| "epoch": 1.0629086674827577, | |
| "grad_norm": 5.361871242523193, | |
| "learning_rate": 0.0001898302276013006, | |
| "loss": 1.2933, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 1.0644015167348402, | |
| "grad_norm": 3.6657068729400635, | |
| "learning_rate": 0.00018981594180538175, | |
| "loss": 1.3359, | |
| "step": 35650 | |
| }, | |
| { | |
| "epoch": 1.0658943659869227, | |
| "grad_norm": 4.428374290466309, | |
| "learning_rate": 0.00018980165600946292, | |
| "loss": 1.3278, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 1.0673872152390051, | |
| "grad_norm": 5.079537391662598, | |
| "learning_rate": 0.00018978737021354408, | |
| "loss": 1.2699, | |
| "step": 35750 | |
| }, | |
| { | |
| "epoch": 1.0688800644910876, | |
| "grad_norm": 5.303153038024902, | |
| "learning_rate": 0.00018977308441762525, | |
| "loss": 1.2985, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 1.0703729137431701, | |
| "grad_norm": 4.319901943206787, | |
| "learning_rate": 0.0001897587986217064, | |
| "loss": 1.2661, | |
| "step": 35850 | |
| }, | |
| { | |
| "epoch": 1.0718657629952528, | |
| "grad_norm": 6.0582451820373535, | |
| "learning_rate": 0.00018974451282578758, | |
| "loss": 1.2837, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 1.0733586122473353, | |
| "grad_norm": 5.738245964050293, | |
| "learning_rate": 0.00018973022702986877, | |
| "loss": 1.3075, | |
| "step": 35950 | |
| }, | |
| { | |
| "epoch": 1.0748514614994178, | |
| "grad_norm": 4.602933883666992, | |
| "learning_rate": 0.0001897159412339499, | |
| "loss": 1.2585, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.0763443107515003, | |
| "grad_norm": 4.273153305053711, | |
| "learning_rate": 0.0001897016554380311, | |
| "loss": 1.3382, | |
| "step": 36050 | |
| }, | |
| { | |
| "epoch": 1.0778371600035828, | |
| "grad_norm": 4.225873947143555, | |
| "learning_rate": 0.00018968736964211224, | |
| "loss": 1.2964, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 1.0793300092556652, | |
| "grad_norm": 4.828727722167969, | |
| "learning_rate": 0.00018967308384619343, | |
| "loss": 1.3734, | |
| "step": 36150 | |
| }, | |
| { | |
| "epoch": 1.080822858507748, | |
| "grad_norm": 3.7251532077789307, | |
| "learning_rate": 0.00018965879805027457, | |
| "loss": 1.2706, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 1.0823157077598304, | |
| "grad_norm": 4.92055606842041, | |
| "learning_rate": 0.00018964451225435576, | |
| "loss": 1.3187, | |
| "step": 36250 | |
| }, | |
| { | |
| "epoch": 1.083808557011913, | |
| "grad_norm": 4.827970027923584, | |
| "learning_rate": 0.00018963022645843692, | |
| "loss": 1.2574, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 1.0853014062639954, | |
| "grad_norm": 4.742151737213135, | |
| "learning_rate": 0.00018961594066251809, | |
| "loss": 1.3076, | |
| "step": 36350 | |
| }, | |
| { | |
| "epoch": 1.086794255516078, | |
| "grad_norm": 3.70794939994812, | |
| "learning_rate": 0.00018960165486659925, | |
| "loss": 1.3075, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 1.0882871047681606, | |
| "grad_norm": 4.062809944152832, | |
| "learning_rate": 0.00018958736907068042, | |
| "loss": 1.2628, | |
| "step": 36450 | |
| }, | |
| { | |
| "epoch": 1.089779954020243, | |
| "grad_norm": 5.072466850280762, | |
| "learning_rate": 0.00018957308327476158, | |
| "loss": 1.3278, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.0912728032723256, | |
| "grad_norm": 4.530171871185303, | |
| "learning_rate": 0.00018955879747884274, | |
| "loss": 1.3233, | |
| "step": 36550 | |
| }, | |
| { | |
| "epoch": 1.092765652524408, | |
| "grad_norm": 3.9391825199127197, | |
| "learning_rate": 0.0001895445116829239, | |
| "loss": 1.2973, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 1.0942585017764905, | |
| "grad_norm": 6.774008274078369, | |
| "learning_rate": 0.00018953022588700507, | |
| "loss": 1.2801, | |
| "step": 36650 | |
| }, | |
| { | |
| "epoch": 1.0957513510285732, | |
| "grad_norm": 4.565464496612549, | |
| "learning_rate": 0.00018951594009108624, | |
| "loss": 1.3718, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 1.0972442002806557, | |
| "grad_norm": 5.68241548538208, | |
| "learning_rate": 0.00018950165429516743, | |
| "loss": 1.2928, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 1.0987370495327382, | |
| "grad_norm": 4.235448360443115, | |
| "learning_rate": 0.00018948736849924857, | |
| "loss": 1.3097, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 1.1002298987848207, | |
| "grad_norm": 4.672369003295898, | |
| "learning_rate": 0.00018947308270332976, | |
| "loss": 1.2875, | |
| "step": 36850 | |
| }, | |
| { | |
| "epoch": 1.1017227480369032, | |
| "grad_norm": 6.449750900268555, | |
| "learning_rate": 0.0001894587969074109, | |
| "loss": 1.2823, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 1.1032155972889857, | |
| "grad_norm": 5.093149662017822, | |
| "learning_rate": 0.0001894445111114921, | |
| "loss": 1.315, | |
| "step": 36950 | |
| }, | |
| { | |
| "epoch": 1.1047084465410684, | |
| "grad_norm": 5.433828353881836, | |
| "learning_rate": 0.00018943022531557323, | |
| "loss": 1.2781, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.1062012957931509, | |
| "grad_norm": 5.176681995391846, | |
| "learning_rate": 0.00018941593951965442, | |
| "loss": 1.2652, | |
| "step": 37050 | |
| }, | |
| { | |
| "epoch": 1.1076941450452333, | |
| "grad_norm": 4.09026575088501, | |
| "learning_rate": 0.00018940165372373558, | |
| "loss": 1.3045, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 1.1091869942973158, | |
| "grad_norm": 5.223085880279541, | |
| "learning_rate": 0.00018938736792781675, | |
| "loss": 1.3009, | |
| "step": 37150 | |
| }, | |
| { | |
| "epoch": 1.1106798435493983, | |
| "grad_norm": 5.105752944946289, | |
| "learning_rate": 0.0001893730821318979, | |
| "loss": 1.2915, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 1.1121726928014808, | |
| "grad_norm": 3.945962905883789, | |
| "learning_rate": 0.00018935879633597908, | |
| "loss": 1.341, | |
| "step": 37250 | |
| }, | |
| { | |
| "epoch": 1.1136655420535635, | |
| "grad_norm": 4.856802463531494, | |
| "learning_rate": 0.00018934451054006024, | |
| "loss": 1.3318, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 1.115158391305646, | |
| "grad_norm": 4.858597755432129, | |
| "learning_rate": 0.0001893302247441414, | |
| "loss": 1.2756, | |
| "step": 37350 | |
| }, | |
| { | |
| "epoch": 1.1166512405577285, | |
| "grad_norm": 4.594838619232178, | |
| "learning_rate": 0.00018931593894822257, | |
| "loss": 1.2712, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 1.118144089809811, | |
| "grad_norm": 4.745405673980713, | |
| "learning_rate": 0.00018930165315230374, | |
| "loss": 1.2878, | |
| "step": 37450 | |
| }, | |
| { | |
| "epoch": 1.1196369390618934, | |
| "grad_norm": 4.112718105316162, | |
| "learning_rate": 0.0001892873673563849, | |
| "loss": 1.3337, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.1211297883139761, | |
| "grad_norm": 4.297769069671631, | |
| "learning_rate": 0.00018927308156046607, | |
| "loss": 1.3324, | |
| "step": 37550 | |
| }, | |
| { | |
| "epoch": 1.1226226375660586, | |
| "grad_norm": 5.46763801574707, | |
| "learning_rate": 0.00018925879576454723, | |
| "loss": 1.276, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 1.124115486818141, | |
| "grad_norm": 5.648976802825928, | |
| "learning_rate": 0.0001892445099686284, | |
| "loss": 1.3238, | |
| "step": 37650 | |
| }, | |
| { | |
| "epoch": 1.1256083360702236, | |
| "grad_norm": 4.185100078582764, | |
| "learning_rate": 0.00018923022417270956, | |
| "loss": 1.2848, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 1.127101185322306, | |
| "grad_norm": 4.676313877105713, | |
| "learning_rate": 0.00018921593837679072, | |
| "loss": 1.3038, | |
| "step": 37750 | |
| }, | |
| { | |
| "epoch": 1.1285940345743888, | |
| "grad_norm": 4.426568508148193, | |
| "learning_rate": 0.00018920165258087192, | |
| "loss": 1.3343, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 1.1300868838264713, | |
| "grad_norm": 4.887205600738525, | |
| "learning_rate": 0.00018918736678495305, | |
| "loss": 1.3456, | |
| "step": 37850 | |
| }, | |
| { | |
| "epoch": 1.1315797330785538, | |
| "grad_norm": 5.455615043640137, | |
| "learning_rate": 0.00018917308098903424, | |
| "loss": 1.3258, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 1.1330725823306362, | |
| "grad_norm": 5.676678657531738, | |
| "learning_rate": 0.00018915879519311538, | |
| "loss": 1.3702, | |
| "step": 37950 | |
| }, | |
| { | |
| "epoch": 1.1345654315827187, | |
| "grad_norm": 3.9528415203094482, | |
| "learning_rate": 0.00018914450939719657, | |
| "loss": 1.3097, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.1360582808348014, | |
| "grad_norm": 4.538026332855225, | |
| "learning_rate": 0.0001891302236012777, | |
| "loss": 1.316, | |
| "step": 38050 | |
| }, | |
| { | |
| "epoch": 1.137551130086884, | |
| "grad_norm": 4.46422815322876, | |
| "learning_rate": 0.0001891159378053589, | |
| "loss": 1.2479, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 1.1390439793389664, | |
| "grad_norm": 4.823958396911621, | |
| "learning_rate": 0.00018910165200944007, | |
| "loss": 1.2616, | |
| "step": 38150 | |
| }, | |
| { | |
| "epoch": 1.1405368285910489, | |
| "grad_norm": 5.7128167152404785, | |
| "learning_rate": 0.00018908736621352123, | |
| "loss": 1.2853, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 1.1420296778431314, | |
| "grad_norm": 3.5420877933502197, | |
| "learning_rate": 0.0001890730804176024, | |
| "loss": 1.3008, | |
| "step": 38250 | |
| }, | |
| { | |
| "epoch": 1.1435225270952138, | |
| "grad_norm": 4.617981910705566, | |
| "learning_rate": 0.00018905879462168356, | |
| "loss": 1.2888, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 1.1450153763472963, | |
| "grad_norm": 4.542544364929199, | |
| "learning_rate": 0.00018904450882576473, | |
| "loss": 1.3009, | |
| "step": 38350 | |
| }, | |
| { | |
| "epoch": 1.146508225599379, | |
| "grad_norm": 4.301428318023682, | |
| "learning_rate": 0.0001890302230298459, | |
| "loss": 1.2834, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 1.1480010748514615, | |
| "grad_norm": 4.136764049530029, | |
| "learning_rate": 0.00018901593723392706, | |
| "loss": 1.3895, | |
| "step": 38450 | |
| }, | |
| { | |
| "epoch": 1.149493924103544, | |
| "grad_norm": 5.59256649017334, | |
| "learning_rate": 0.00018900165143800822, | |
| "loss": 1.295, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.1509867733556265, | |
| "grad_norm": 3.4925365447998047, | |
| "learning_rate": 0.00018898736564208939, | |
| "loss": 1.3385, | |
| "step": 38550 | |
| }, | |
| { | |
| "epoch": 1.152479622607709, | |
| "grad_norm": 4.884555816650391, | |
| "learning_rate": 0.00018897307984617058, | |
| "loss": 1.2776, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 1.1539724718597917, | |
| "grad_norm": 3.866908550262451, | |
| "learning_rate": 0.00018895879405025171, | |
| "loss": 1.3173, | |
| "step": 38650 | |
| }, | |
| { | |
| "epoch": 1.1554653211118742, | |
| "grad_norm": 4.8104939460754395, | |
| "learning_rate": 0.0001889445082543329, | |
| "loss": 1.2988, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 1.1569581703639567, | |
| "grad_norm": 3.814675807952881, | |
| "learning_rate": 0.00018893022245841404, | |
| "loss": 1.348, | |
| "step": 38750 | |
| }, | |
| { | |
| "epoch": 1.1584510196160391, | |
| "grad_norm": 5.720306873321533, | |
| "learning_rate": 0.00018891593666249524, | |
| "loss": 1.2844, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 1.1599438688681216, | |
| "grad_norm": 4.06850528717041, | |
| "learning_rate": 0.00018890165086657637, | |
| "loss": 1.3514, | |
| "step": 38850 | |
| }, | |
| { | |
| "epoch": 1.1614367181202043, | |
| "grad_norm": 6.193358898162842, | |
| "learning_rate": 0.00018888736507065757, | |
| "loss": 1.3587, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 1.1629295673722868, | |
| "grad_norm": 4.8998212814331055, | |
| "learning_rate": 0.00018887307927473873, | |
| "loss": 1.317, | |
| "step": 38950 | |
| }, | |
| { | |
| "epoch": 1.1644224166243693, | |
| "grad_norm": 4.4293107986450195, | |
| "learning_rate": 0.0001888587934788199, | |
| "loss": 1.3473, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.1659152658764518, | |
| "grad_norm": 6.795536994934082, | |
| "learning_rate": 0.00018884450768290106, | |
| "loss": 1.2793, | |
| "step": 39050 | |
| }, | |
| { | |
| "epoch": 1.1674081151285343, | |
| "grad_norm": 4.158294200897217, | |
| "learning_rate": 0.00018883022188698222, | |
| "loss": 1.3175, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 1.168900964380617, | |
| "grad_norm": 5.839204788208008, | |
| "learning_rate": 0.0001888159360910634, | |
| "loss": 1.2931, | |
| "step": 39150 | |
| }, | |
| { | |
| "epoch": 1.1703938136326995, | |
| "grad_norm": 6.633917331695557, | |
| "learning_rate": 0.00018880165029514455, | |
| "loss": 1.3053, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 1.171886662884782, | |
| "grad_norm": 4.409125328063965, | |
| "learning_rate": 0.00018878736449922572, | |
| "loss": 1.3074, | |
| "step": 39250 | |
| }, | |
| { | |
| "epoch": 1.1733795121368644, | |
| "grad_norm": 4.820318698883057, | |
| "learning_rate": 0.00018877307870330688, | |
| "loss": 1.329, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 1.174872361388947, | |
| "grad_norm": 5.104337215423584, | |
| "learning_rate": 0.00018875879290738805, | |
| "loss": 1.2628, | |
| "step": 39350 | |
| }, | |
| { | |
| "epoch": 1.1763652106410294, | |
| "grad_norm": 5.449405670166016, | |
| "learning_rate": 0.00018874450711146924, | |
| "loss": 1.2672, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 1.1778580598931119, | |
| "grad_norm": 5.3521504402160645, | |
| "learning_rate": 0.00018873022131555038, | |
| "loss": 1.3236, | |
| "step": 39450 | |
| }, | |
| { | |
| "epoch": 1.1793509091451946, | |
| "grad_norm": 5.748175144195557, | |
| "learning_rate": 0.00018871593551963157, | |
| "loss": 1.284, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.180843758397277, | |
| "grad_norm": 4.418118953704834, | |
| "learning_rate": 0.0001887016497237127, | |
| "loss": 1.299, | |
| "step": 39550 | |
| }, | |
| { | |
| "epoch": 1.1823366076493596, | |
| "grad_norm": 4.267107009887695, | |
| "learning_rate": 0.0001886873639277939, | |
| "loss": 1.3287, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 1.183829456901442, | |
| "grad_norm": 4.607259273529053, | |
| "learning_rate": 0.00018867307813187503, | |
| "loss": 1.3087, | |
| "step": 39650 | |
| }, | |
| { | |
| "epoch": 1.1853223061535245, | |
| "grad_norm": 4.254667282104492, | |
| "learning_rate": 0.00018865879233595623, | |
| "loss": 1.3015, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 1.1868151554056072, | |
| "grad_norm": 5.307114124298096, | |
| "learning_rate": 0.0001886445065400374, | |
| "loss": 1.2802, | |
| "step": 39750 | |
| }, | |
| { | |
| "epoch": 1.1883080046576897, | |
| "grad_norm": 3.9305639266967773, | |
| "learning_rate": 0.00018863022074411856, | |
| "loss": 1.2975, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 1.1898008539097722, | |
| "grad_norm": 4.650544166564941, | |
| "learning_rate": 0.00018861593494819972, | |
| "loss": 1.3239, | |
| "step": 39850 | |
| }, | |
| { | |
| "epoch": 1.1912937031618547, | |
| "grad_norm": 4.182717800140381, | |
| "learning_rate": 0.00018860164915228086, | |
| "loss": 1.3948, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 1.1927865524139372, | |
| "grad_norm": 5.322524547576904, | |
| "learning_rate": 0.00018858736335636205, | |
| "loss": 1.3411, | |
| "step": 39950 | |
| }, | |
| { | |
| "epoch": 1.1942794016660199, | |
| "grad_norm": 5.221969127655029, | |
| "learning_rate": 0.0001885730775604432, | |
| "loss": 1.3047, | |
| "step": 40000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 700001, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 21, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.011899217623384e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |