{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9982631930527722,
  "eval_steps": 200,
  "global_step": 467,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021376085504342017,
      "grad_norm": 4.144618309291183,
      "learning_rate": 1.0638297872340425e-08,
      "logits": -2.4370906352996826,
      "logps": -292.5074157714844,
      "loss": -0.9502,
      "step": 1
    },
    {
      "epoch": 0.01068804275217101,
      "grad_norm": 4.443240441390166,
      "learning_rate": 5.3191489361702123e-08,
      "logits": -2.583270788192749,
      "logps": -364.1216125488281,
      "loss": -0.9522,
      "step": 5
    },
    {
      "epoch": 0.02137608550434202,
      "grad_norm": 3.9998839110089173,
      "learning_rate": 1.0638297872340425e-07,
      "logits": -2.557814598083496,
      "logps": -341.51373291015625,
      "loss": -0.9517,
      "step": 10
    },
    {
      "epoch": 0.03206412825651302,
      "grad_norm": 5.028172797811144,
      "learning_rate": 1.5957446808510638e-07,
      "logits": -2.553781032562256,
      "logps": -356.0725402832031,
      "loss": -0.9509,
      "step": 15
    },
    {
      "epoch": 0.04275217100868404,
      "grad_norm": 4.030810565077173,
      "learning_rate": 2.127659574468085e-07,
      "logits": -2.571854591369629,
      "logps": -348.39935302734375,
      "loss": -0.9528,
      "step": 20
    },
    {
      "epoch": 0.053440213760855046,
      "grad_norm": 3.8090269607771132,
      "learning_rate": 2.659574468085106e-07,
      "logits": -2.5878312587738037,
      "logps": -406.37213134765625,
      "loss": -0.9574,
      "step": 25
    },
    {
      "epoch": 0.06412825651302605,
      "grad_norm": 2.8431249266903733,
      "learning_rate": 3.1914893617021275e-07,
      "logits": -2.5716335773468018,
      "logps": -364.21356201171875,
      "loss": -0.9599,
      "step": 30
    },
    {
      "epoch": 0.07481629926519706,
      "grad_norm": 2.0535603789448813,
      "learning_rate": 3.7234042553191484e-07,
      "logits": -2.5569186210632324,
      "logps": -358.84136962890625,
      "loss": -0.9666,
      "step": 35
    },
    {
      "epoch": 0.08550434201736808,
      "grad_norm": 1.8061536976732258,
      "learning_rate": 4.25531914893617e-07,
      "logits": -2.527008533477783,
      "logps": -367.78704833984375,
      "loss": -0.9693,
      "step": 40
    },
    {
      "epoch": 0.09619238476953908,
      "grad_norm": 1.604043129189636,
      "learning_rate": 4.787234042553192e-07,
      "logits": -2.5640478134155273,
      "logps": -358.61578369140625,
      "loss": -0.9721,
      "step": 45
    },
    {
      "epoch": 0.10688042752171009,
      "grad_norm": 1.1777757605957209,
      "learning_rate": 4.999370587356267e-07,
      "logits": -2.5156993865966797,
      "logps": -357.37811279296875,
      "loss": -0.9745,
      "step": 50
    },
    {
      "epoch": 0.11756847027388109,
      "grad_norm": 1.187271000332806,
      "learning_rate": 4.995525324419337e-07,
      "logits": -2.609391689300537,
      "logps": -395.1018371582031,
      "loss": -0.9755,
      "step": 55
    },
    {
      "epoch": 0.1282565130260521,
      "grad_norm": 1.024247106270327,
      "learning_rate": 4.988189843662815e-07,
      "logits": -2.5524516105651855,
      "logps": -318.79522705078125,
      "loss": -0.9749,
      "step": 60
    },
    {
      "epoch": 0.13894455577822312,
      "grad_norm": 0.8915771300354084,
      "learning_rate": 4.977374404419837e-07,
      "logits": -2.5753390789031982,
      "logps": -350.32806396484375,
      "loss": -0.978,
      "step": 65
    },
    {
      "epoch": 0.14963259853039412,
      "grad_norm": 1.2524804928994735,
      "learning_rate": 4.963094133060148e-07,
      "logits": -2.5401415824890137,
      "logps": -379.8075256347656,
      "loss": -0.9757,
      "step": 70
    },
    {
      "epoch": 0.16032064128256512,
      "grad_norm": 0.7694631129436605,
      "learning_rate": 4.945369001834514e-07,
      "logits": -2.5206758975982666,
      "logps": -356.40985107421875,
      "loss": -0.9789,
      "step": 75
    },
    {
      "epoch": 0.17100868403473615,
      "grad_norm": 0.7358727043648916,
      "learning_rate": 4.924223800941717e-07,
      "logits": -2.5486698150634766,
      "logps": -374.1065979003906,
      "loss": -0.9771,
      "step": 80
    },
    {
      "epoch": 0.18169672678690715,
      "grad_norm": 0.6957765026619465,
      "learning_rate": 4.899688103857222e-07,
      "logits": -2.5429470539093018,
      "logps": -364.36236572265625,
      "loss": -0.9792,
      "step": 85
    },
    {
      "epoch": 0.19238476953907815,
      "grad_norm": 0.8280701082216594,
      "learning_rate": 4.871796225971999e-07,
      "logits": -2.532397747039795,
      "logps": -350.89117431640625,
      "loss": -0.9792,
      "step": 90
    },
    {
      "epoch": 0.20307281229124916,
      "grad_norm": 1.0680065630808142,
      "learning_rate": 4.840587176599343e-07,
      "logits": -2.5151004791259766,
      "logps": -327.36285400390625,
      "loss": -0.9785,
      "step": 95
    },
    {
      "epoch": 0.21376085504342018,
      "grad_norm": 0.7506322261698104,
      "learning_rate": 4.806104604416823e-07,
      "logits": -2.4897637367248535,
      "logps": -337.66754150390625,
      "loss": -0.9789,
      "step": 100
    },
    {
      "epoch": 0.22444889779559118,
      "grad_norm": 0.5811696456456295,
      "learning_rate": 4.768396736419662e-07,
      "logits": -2.541165828704834,
      "logps": -368.1877746582031,
      "loss": -0.9805,
      "step": 105
    },
    {
      "epoch": 0.23513694054776219,
      "grad_norm": 0.738032641791767,
      "learning_rate": 4.7275163104709194e-07,
      "logits": -2.5737557411193848,
      "logps": -381.4657287597656,
      "loss": -0.9808,
      "step": 110
    },
    {
      "epoch": 0.2458249832999332,
      "grad_norm": 0.7647725788119588,
      "learning_rate": 4.683520501542824e-07,
      "logits": -2.4939820766448975,
      "logps": -354.36785888671875,
      "loss": -0.9794,
      "step": 115
    },
    {
      "epoch": 0.2565130260521042,
      "grad_norm": 0.7167751151533713,
      "learning_rate": 4.636470841752404e-07,
      "logits": -2.4981443881988525,
      "logps": -360.51641845703125,
      "loss": -0.9803,
      "step": 120
    },
    {
      "epoch": 0.26720106880427524,
      "grad_norm": 0.752459158388082,
      "learning_rate": 4.5864331343032565e-07,
      "logits": -2.5119669437408447,
      "logps": -338.3499755859375,
      "loss": -0.9812,
      "step": 125
    },
    {
      "epoch": 0.27788911155644624,
      "grad_norm": 0.718260065630518,
      "learning_rate": 4.533477361453819e-07,
      "logits": -2.497870445251465,
      "logps": -329.90179443359375,
      "loss": -0.9813,
      "step": 130
    },
    {
      "epoch": 0.28857715430861725,
      "grad_norm": 0.818924100709432,
      "learning_rate": 4.4776775866408533e-07,
      "logits": -2.490985631942749,
      "logps": -322.59564208984375,
      "loss": -0.9809,
      "step": 135
    },
    {
      "epoch": 0.29926519706078825,
      "grad_norm": 0.6824986443058841,
      "learning_rate": 4.4191118508950277e-07,
      "logits": -2.537930727005005,
      "logps": -395.7263488769531,
      "loss": -0.9821,
      "step": 140
    },
    {
      "epoch": 0.30995323981295925,
      "grad_norm": 0.8110074699949732,
      "learning_rate": 4.357862063693485e-07,
      "logits": -2.4960224628448486,
      "logps": -361.6850891113281,
      "loss": -0.9797,
      "step": 145
    },
    {
      "epoch": 0.32064128256513025,
      "grad_norm": 0.8384626324691244,
      "learning_rate": 4.294013888402029e-07,
      "logits": -2.5415549278259277,
      "logps": -374.12567138671875,
      "loss": -0.9812,
      "step": 150
    },
    {
      "epoch": 0.33132932531730125,
      "grad_norm": 0.6248771798111524,
      "learning_rate": 4.227656622467162e-07,
      "logits": -2.582817316055298,
      "logps": -348.4563903808594,
      "loss": -0.9806,
      "step": 155
    },
    {
      "epoch": 0.3420173680694723,
      "grad_norm": 0.7559261109196969,
      "learning_rate": 4.158883072525528e-07,
      "logits": -2.540769338607788,
      "logps": -374.34222412109375,
      "loss": -0.9819,
      "step": 160
    },
    {
      "epoch": 0.3527054108216433,
      "grad_norm": 0.7030619477149825,
      "learning_rate": 4.087789424605447e-07,
      "logits": -2.5171778202056885,
      "logps": -374.92919921875,
      "loss": -0.9814,
      "step": 165
    },
    {
      "epoch": 0.3633934535738143,
      "grad_norm": 0.6410886893374934,
      "learning_rate": 4.0144751096020497e-07,
      "logits": -2.4577980041503906,
      "logps": -350.4930114746094,
      "loss": -0.9803,
      "step": 170
    },
    {
      "epoch": 0.3740814963259853,
      "grad_norm": 0.5449201423049997,
      "learning_rate": 3.939042664214184e-07,
      "logits": -2.4617953300476074,
      "logps": -350.728515625,
      "loss": -0.9819,
      "step": 175
    },
    {
      "epoch": 0.3847695390781563,
      "grad_norm": 0.6597713346208942,
      "learning_rate": 3.8615975875375676e-07,
      "logits": -2.502950668334961,
      "logps": -357.53375244140625,
      "loss": -0.9815,
      "step": 180
    },
    {
      "epoch": 0.3954575818303273,
      "grad_norm": 0.8129100423700869,
      "learning_rate": 3.7822481935147655e-07,
      "logits": -2.4940545558929443,
      "logps": -357.49517822265625,
      "loss": -0.9808,
      "step": 185
    },
    {
      "epoch": 0.4061456245824983,
      "grad_norm": 0.6945949053045897,
      "learning_rate": 3.7011054594483443e-07,
      "logits": -2.457098960876465,
      "logps": -343.8159484863281,
      "loss": -0.9819,
      "step": 190
    },
    {
      "epoch": 0.4168336673346693,
      "grad_norm": 0.5179850886219067,
      "learning_rate": 3.618282870789081e-07,
      "logits": -2.5071024894714355,
      "logps": -362.4822082519531,
      "loss": -0.9833,
      "step": 195
    },
    {
      "epoch": 0.42752171008684037,
      "grad_norm": 0.5483352919981096,
      "learning_rate": 3.5338962624163016e-07,
      "logits": -2.4931092262268066,
      "logps": -354.5975036621094,
      "loss": -0.9822,
      "step": 200
    },
    {
      "epoch": 0.42752171008684037,
      "eval_logits": -2.525296688079834,
      "eval_logps": -365.9304504394531,
      "eval_loss": -0.9821345806121826,
      "eval_runtime": 250.0395,
      "eval_samples_per_second": 7.871,
      "eval_steps_per_second": 1.968,
      "step": 200
    },
    {
      "epoch": 0.43820975283901137,
      "grad_norm": 0.43061055575306856,
      "learning_rate": 3.448063656632321e-07,
      "logits": -2.4786181449890137,
      "logps": -345.92315673828125,
      "loss": -0.9819,
      "step": 205
    },
    {
      "epoch": 0.44889779559118237,
      "grad_norm": 0.6750096952736351,
      "learning_rate": 3.360905098097587e-07,
      "logits": -2.4176249504089355,
      "logps": -325.74383544921875,
      "loss": -0.9813,
      "step": 210
    },
    {
      "epoch": 0.45958583834335337,
      "grad_norm": 0.49631954839027165,
      "learning_rate": 3.272542485937368e-07,
      "logits": -2.429324150085449,
      "logps": -366.7755432128906,
      "loss": -0.9821,
      "step": 215
    },
    {
      "epoch": 0.47027388109552437,
      "grad_norm": 0.5975173365047985,
      "learning_rate": 3.1830994032548e-07,
      "logits": -2.4488985538482666,
      "logps": -332.4563293457031,
      "loss": -0.9811,
      "step": 220
    },
    {
      "epoch": 0.48096192384769537,
      "grad_norm": 0.663048456274181,
      "learning_rate": 3.0927009442887437e-07,
      "logits": -2.53755521774292,
      "logps": -375.02789306640625,
      "loss": -0.983,
      "step": 225
    },
    {
      "epoch": 0.4916499665998664,
      "grad_norm": 0.6572101285581632,
      "learning_rate": 3.001473539458182e-07,
      "logits": -2.5210976600646973,
      "logps": -406.8955993652344,
      "loss": -0.9818,
      "step": 230
    },
    {
      "epoch": 0.5023380093520374,
      "grad_norm": 0.5240738779831536,
      "learning_rate": 2.909544778537844e-07,
      "logits": -2.5041861534118652,
      "logps": -354.63165283203125,
      "loss": -0.9825,
      "step": 235
    },
    {
      "epoch": 0.5130260521042084,
      "grad_norm": 0.6037632112214091,
      "learning_rate": 2.817043232212371e-07,
      "logits": -2.4589896202087402,
      "logps": -375.8338928222656,
      "loss": -0.9826,
      "step": 240
    },
    {
      "epoch": 0.5237140948563794,
      "grad_norm": 0.5398014313679249,
      "learning_rate": 2.7240982722585837e-07,
      "logits": -2.500366687774658,
      "logps": -374.3420715332031,
      "loss": -0.9829,
      "step": 245
    },
    {
      "epoch": 0.5344021376085505,
      "grad_norm": 0.46120553294990174,
      "learning_rate": 2.63083989060736e-07,
      "logits": -2.5605239868164062,
      "logps": -370.4330139160156,
      "loss": -0.9836,
      "step": 250
    },
    {
      "epoch": 0.5450901803607214,
      "grad_norm": 0.6627277011411432,
      "learning_rate": 2.537398517538159e-07,
      "logits": -2.388418436050415,
      "logps": -344.0787353515625,
      "loss": -0.9819,
      "step": 255
    },
    {
      "epoch": 0.5557782231128925,
      "grad_norm": 0.8145694884968578,
      "learning_rate": 2.4439048392604877e-07,
      "logits": -2.468952178955078,
      "logps": -359.54522705078125,
      "loss": -0.9813,
      "step": 260
    },
    {
      "epoch": 0.5664662658650634,
      "grad_norm": 0.7253536336911885,
      "learning_rate": 2.3504896151374144e-07,
      "logits": -2.47514271736145,
      "logps": -374.31329345703125,
      "loss": -0.9808,
      "step": 265
    },
    {
      "epoch": 0.5771543086172345,
      "grad_norm": 0.9417827012511475,
      "learning_rate": 2.2572834948067795e-07,
      "logits": -2.443847179412842,
      "logps": -347.3822021484375,
      "loss": -0.9824,
      "step": 270
    },
    {
      "epoch": 0.5878423513694054,
      "grad_norm": 0.7270613953039524,
      "learning_rate": 2.164416835455862e-07,
      "logits": -2.508747100830078,
      "logps": -344.39581298828125,
      "loss": -0.9821,
      "step": 275
    },
    {
      "epoch": 0.5985303941215765,
      "grad_norm": 0.5204524163509038,
      "learning_rate": 2.072019519505062e-07,
      "logits": -2.4477667808532715,
      "logps": -388.79876708984375,
      "loss": -0.9821,
      "step": 280
    },
    {
      "epoch": 0.6092184368737475,
      "grad_norm": 0.5864054809619796,
      "learning_rate": 1.980220772955602e-07,
      "logits": -2.4833598136901855,
      "logps": -346.50457763671875,
      "loss": -0.9836,
      "step": 285
    },
    {
      "epoch": 0.6199064796259185,
      "grad_norm": 0.46980511942280184,
      "learning_rate": 1.8891489846552644e-07,
      "logits": -2.4780659675598145,
      "logps": -371.79412841796875,
      "loss": -0.9821,
      "step": 290
    },
    {
      "epoch": 0.6305945223780896,
      "grad_norm": 0.8669828661798684,
      "learning_rate": 1.7989315267349933e-07,
      "logits": -2.422987699508667,
      "logps": -377.4803771972656,
      "loss": -0.9823,
      "step": 295
    },
    {
      "epoch": 0.6412825651302605,
      "grad_norm": 0.5112420954158757,
      "learning_rate": 1.7096945764674398e-07,
      "logits": -2.466285228729248,
      "logps": -366.07470703125,
      "loss": -0.9813,
      "step": 300
    },
    {
      "epoch": 0.6519706078824316,
      "grad_norm": 0.48775619642338164,
      "learning_rate": 1.621562939796643e-07,
      "logits": -2.483970880508423,
      "logps": -371.234619140625,
      "loss": -0.9822,
      "step": 305
    },
    {
      "epoch": 0.6626586506346025,
      "grad_norm": 0.5564287633975539,
      "learning_rate": 1.5346598767856345e-07,
      "logits": -2.499943733215332,
      "logps": -369.6706237792969,
      "loss": -0.9831,
      "step": 310
    },
    {
      "epoch": 0.6733466933867736,
      "grad_norm": 0.7231747250697979,
      "learning_rate": 1.4491069292260866e-07,
      "logits": -2.4685072898864746,
      "logps": -376.16961669921875,
      "loss": -0.9824,
      "step": 315
    },
    {
      "epoch": 0.6840347361389446,
      "grad_norm": 0.661176842586643,
      "learning_rate": 1.365023750651133e-07,
      "logits": -2.492729663848877,
      "logps": -346.41900634765625,
      "loss": -0.9832,
      "step": 320
    },
    {
      "epoch": 0.6947227788911156,
      "grad_norm": 0.4909448631410863,
      "learning_rate": 1.2825279389890818e-07,
      "logits": -2.5009281635284424,
      "logps": -374.65557861328125,
      "loss": -0.9836,
      "step": 325
    },
    {
      "epoch": 0.7054108216432866,
      "grad_norm": 0.5185643168907794,
      "learning_rate": 1.201734872092077e-07,
      "logits": -2.467710494995117,
      "logps": -340.84930419921875,
      "loss": -0.9822,
      "step": 330
    },
    {
      "epoch": 0.7160988643954576,
      "grad_norm": 0.6784097865826475,
      "learning_rate": 1.1227575463697439e-07,
      "logits": -2.4435300827026367,
      "logps": -385.37371826171875,
      "loss": -0.9839,
      "step": 335
    },
    {
      "epoch": 0.7267869071476286,
      "grad_norm": 0.5681041639682554,
      "learning_rate": 1.0457064187534861e-07,
      "logits": -2.5163304805755615,
      "logps": -337.10699462890625,
      "loss": -0.9824,
      "step": 340
    },
    {
      "epoch": 0.7374749498997996,
      "grad_norm": 0.6201107786600963,
      "learning_rate": 9.706892522124838e-08,
      "logits": -2.4154000282287598,
      "logps": -362.8922119140625,
      "loss": -0.9827,
      "step": 345
    },
    {
      "epoch": 0.7481629926519706,
      "grad_norm": 0.5187696831915886,
      "learning_rate": 8.978109650374396e-08,
      "logits": -2.5054590702056885,
      "logps": -371.92529296875,
      "loss": -0.9832,
      "step": 350
    },
    {
      "epoch": 0.7588510354041417,
      "grad_norm": 0.5927947372060335,
      "learning_rate": 8.271734841028552e-08,
      "logits": -2.453186273574829,
      "logps": -351.21710205078125,
      "loss": -0.9832,
      "step": 355
    },
    {
      "epoch": 0.7695390781563126,
      "grad_norm": 0.5155549921451843,
      "learning_rate": 7.588756023130833e-08,
      "logits": -2.4131436347961426,
      "logps": -383.7878112792969,
      "loss": -0.9834,
      "step": 360
    },
    {
      "epoch": 0.7802271209084837,
      "grad_norm": 0.5437828894083891,
      "learning_rate": 6.930128404315214e-08,
      "logits": -2.4493746757507324,
      "logps": -346.37139892578125,
      "loss": -0.9827,
      "step": 365
    },
    {
      "epoch": 0.7909151636606546,
      "grad_norm": 0.5188378273885912,
      "learning_rate": 6.296773134861824e-08,
      "logits": -2.4425647258758545,
      "logps": -353.88543701171875,
      "loss": -0.9837,
      "step": 370
    },
    {
      "epoch": 0.8016032064128257,
      "grad_norm": 0.7179382209946391,
      "learning_rate": 5.6895760193850145e-08,
      "logits": -2.4108431339263916,
      "logps": -374.7716979980469,
      "loss": -0.983,
      "step": 375
    },
    {
      "epoch": 0.8122912491649966,
      "grad_norm": 0.602255698324553,
      "learning_rate": 5.109386277955477e-08,
      "logits": -2.4562315940856934,
      "logps": -378.78900146484375,
      "loss": -0.9835,
      "step": 380
    },
    {
      "epoch": 0.8229792919171677,
      "grad_norm": 0.6577211360942027,
      "learning_rate": 4.557015358389216e-08,
      "logits": -2.3970322608947754,
      "logps": -331.5000305175781,
      "loss": -0.9828,
      "step": 385
    },
    {
      "epoch": 0.8336673346693386,
      "grad_norm": 0.8004556085082426,
      "learning_rate": 4.0332358013644015e-08,
      "logits": -2.432544708251953,
      "logps": -357.0811462402344,
      "loss": -0.9826,
      "step": 390
    },
    {
      "epoch": 0.8443553774215097,
      "grad_norm": 0.4634282872060418,
      "learning_rate": 3.538780159953347e-08,
      "logits": -2.445672035217285,
      "logps": -316.62701416015625,
      "loss": -0.9826,
      "step": 395
    },
    {
      "epoch": 0.8550434201736807,
      "grad_norm": 0.4981081952819575,
      "learning_rate": 3.074339975080836e-08,
      "logits": -2.430974006652832,
      "logps": -350.957763671875,
      "loss": -0.9831,
      "step": 400
    },
    {
      "epoch": 0.8550434201736807,
      "eval_logits": -2.498615264892578,
      "eval_logps": -367.2024230957031,
      "eval_loss": -0.9829599261283875,
      "eval_runtime": 248.2317,
      "eval_samples_per_second": 7.928,
      "eval_steps_per_second": 1.982,
      "step": 400
    },
    {
      "epoch": 0.8657314629258517,
      "grad_norm": 0.578411992118365,
      "learning_rate": 2.6405648083415833e-08,
      "logits": -2.495081663131714,
      "logps": -374.2669982910156,
      "loss": -0.9825,
      "step": 405
    },
    {
      "epoch": 0.8764195056780227,
      "grad_norm": 0.5522861384589975,
      "learning_rate": 2.2380613335296033e-08,
      "logits": -2.4359846115112305,
      "logps": -338.86114501953125,
      "loss": -0.9821,
      "step": 410
    },
    {
      "epoch": 0.8871075484301937,
      "grad_norm": 0.7074451698785211,
      "learning_rate": 1.8673924881500823e-08,
      "logits": -2.4411728382110596,
      "logps": -326.24774169921875,
      "loss": -0.9839,
      "step": 415
    },
    {
      "epoch": 0.8977955911823647,
      "grad_norm": 0.7637843131603954,
      "learning_rate": 1.5290766861003475e-08,
      "logits": -2.477762460708618,
      "logps": -369.47308349609375,
      "loss": -0.9814,
      "step": 420
    },
    {
      "epoch": 0.9084836339345357,
      "grad_norm": 0.5779848729334695,
      "learning_rate": 1.2235870926211616e-08,
      "logits": -2.4777328968048096,
      "logps": -377.16595458984375,
      "loss": -0.9828,
      "step": 425
    },
    {
      "epoch": 0.9191716766867067,
      "grad_norm": 0.5081183401454111,
      "learning_rate": 9.513509625323518e-09,
      "logits": -2.468085527420044,
      "logps": -348.59912109375,
      "loss": -0.9824,
      "step": 430
    },
    {
      "epoch": 0.9298597194388778,
      "grad_norm": 0.47547960596320854,
      "learning_rate": 7.127490426783123e-09,
      "logits": -2.472496271133423,
      "logps": -361.31817626953125,
      "loss": -0.9836,
      "step": 435
    },
    {
      "epoch": 0.9405477621910487,
      "grad_norm": 0.7265965690147222,
      "learning_rate": 5.08115039419113e-09,
      "logits": -2.464423418045044,
      "logps": -363.0411682128906,
      "loss": -0.9838,
      "step": 440
    },
    {
      "epoch": 0.9512358049432198,
      "grad_norm": 0.6304061963733877,
      "learning_rate": 3.3773515191196646e-09,
      "logits": -2.4736855030059814,
      "logps": -375.7623291015625,
      "loss": -0.9824,
      "step": 445
    },
    {
      "epoch": 0.9619238476953907,
      "grad_norm": 0.5923376706584298,
      "learning_rate": 2.0184767183584474e-09,
      "logits": -2.3635292053222656,
      "logps": -339.05474853515625,
      "loss": -0.9817,
      "step": 450
    },
    {
      "epoch": 0.9726118904475618,
      "grad_norm": 0.7234317981852313,
      "learning_rate": 1.0064265011902328e-09,
      "logits": -2.437248706817627,
      "logps": -354.68902587890625,
      "loss": -0.9819,
      "step": 455
    },
    {
      "epoch": 0.9832999331997327,
      "grad_norm": 0.7069667245732063,
      "learning_rate": 3.4261631135654167e-10,
      "logits": -2.447913646697998,
      "logps": -356.58453369140625,
      "loss": -0.9827,
      "step": 460
    },
    {
      "epoch": 0.9939879759519038,
      "grad_norm": 0.6543519569575565,
      "learning_rate": 2.797454743164174e-11,
      "logits": -2.452890634536743,
      "logps": -342.41961669921875,
      "loss": -0.9811,
      "step": 465
    },
    {
      "epoch": 0.9982631930527722,
      "step": 467,
      "total_flos": 0.0,
      "train_loss": -0.9793714555478964,
      "train_runtime": 18622.5753,
      "train_samples_per_second": 3.215,
      "train_steps_per_second": 0.025
    }
  ],
  "logging_steps": 5,
  "max_steps": 467,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}