{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.999259807549963,
  "eval_steps": 100,
  "global_step": 675,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007401924500370096,
      "grad_norm": 0.6677651277112562,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 1.0786,
      "step": 5
    },
    {
      "epoch": 0.014803849000740192,
      "grad_norm": 0.5722064349275372,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.0903,
      "step": 10
    },
    {
      "epoch": 0.02220577350111029,
      "grad_norm": 0.35990263606190365,
      "learning_rate": 4.411764705882353e-06,
      "loss": 1.0631,
      "step": 15
    },
    {
      "epoch": 0.029607698001480384,
      "grad_norm": 0.38649057268135256,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.0153,
      "step": 20
    },
    {
      "epoch": 0.037009622501850484,
      "grad_norm": 0.32955202530777505,
      "learning_rate": 7.352941176470589e-06,
      "loss": 0.9792,
      "step": 25
    },
    {
      "epoch": 0.04441154700222058,
      "grad_norm": 0.25684601653269357,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.9341,
      "step": 30
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 0.18647088366865341,
      "learning_rate": 1.0294117647058823e-05,
      "loss": 0.8972,
      "step": 35
    },
    {
      "epoch": 0.05921539600296077,
      "grad_norm": 0.18552772548396557,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.8749,
      "step": 40
    },
    {
      "epoch": 0.06661732050333087,
      "grad_norm": 0.17707650341467074,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.8592,
      "step": 45
    },
    {
      "epoch": 0.07401924500370097,
      "grad_norm": 0.1888814710520619,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 0.8706,
      "step": 50
    },
    {
      "epoch": 0.08142116950407106,
      "grad_norm": 0.16771182697525636,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.8633,
      "step": 55
    },
    {
      "epoch": 0.08882309400444116,
      "grad_norm": 0.17693257965328252,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8375,
      "step": 60
    },
    {
      "epoch": 0.09622501850481126,
      "grad_norm": 0.17368427495644334,
      "learning_rate": 1.911764705882353e-05,
      "loss": 0.833,
      "step": 65
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 0.20747768951612397,
      "learning_rate": 1.9999464266898485e-05,
      "loss": 0.8274,
      "step": 70
    },
    {
      "epoch": 0.11102886750555144,
      "grad_norm": 0.19776111155184978,
      "learning_rate": 1.9993437928712977e-05,
      "loss": 0.8218,
      "step": 75
    },
    {
      "epoch": 0.11843079200592153,
      "grad_norm": 0.18864224844745114,
      "learning_rate": 1.998071963486563e-05,
      "loss": 0.8109,
      "step": 80
    },
    {
      "epoch": 0.12583271650629163,
      "grad_norm": 0.17484784010530582,
      "learning_rate": 1.9961317901970953e-05,
      "loss": 0.7995,
      "step": 85
    },
    {
      "epoch": 0.13323464100666174,
      "grad_norm": 0.18875618975921596,
      "learning_rate": 1.993524572210807e-05,
      "loss": 0.7991,
      "step": 90
    },
    {
      "epoch": 0.14063656550703182,
      "grad_norm": 0.20019313739033587,
      "learning_rate": 1.990252055412077e-05,
      "loss": 0.7947,
      "step": 95
    },
    {
      "epoch": 0.14803849000740193,
      "grad_norm": 0.1977811468739612,
      "learning_rate": 1.9863164311926433e-05,
      "loss": 0.8215,
      "step": 100
    },
    {
      "epoch": 0.14803849000740193,
      "eval_loss": 0.8237107992172241,
      "eval_runtime": 7.4399,
      "eval_samples_per_second": 17.204,
      "eval_steps_per_second": 2.151,
      "step": 100
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 0.1703033428273923,
      "learning_rate": 1.981720334984174e-05,
      "loss": 0.7958,
      "step": 105
    },
    {
      "epoch": 0.16284233900814213,
      "grad_norm": 0.17213094767585055,
      "learning_rate": 1.9764668444934853e-05,
      "loss": 0.7895,
      "step": 110
    },
    {
      "epoch": 0.1702442635085122,
      "grad_norm": 0.19306907524923636,
      "learning_rate": 1.970559477641606e-05,
      "loss": 0.766,
      "step": 115
    },
    {
      "epoch": 0.17764618800888232,
      "grad_norm": 0.1823172169804357,
      "learning_rate": 1.9640021902080523e-05,
      "loss": 0.7963,
      "step": 120
    },
    {
      "epoch": 0.1850481125092524,
      "grad_norm": 0.15225193764112274,
      "learning_rate": 1.9567993731818988e-05,
      "loss": 0.7954,
      "step": 125
    },
    {
      "epoch": 0.19245003700962252,
      "grad_norm": 0.17702912049055494,
      "learning_rate": 1.9489558498214197e-05,
      "loss": 0.7875,
      "step": 130
    },
    {
      "epoch": 0.1998519615099926,
      "grad_norm": 0.16536442759668538,
      "learning_rate": 1.9404768724242667e-05,
      "loss": 0.7732,
      "step": 135
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 0.17695469917627027,
      "learning_rate": 1.931368118810346e-05,
      "loss": 0.798,
      "step": 140
    },
    {
      "epoch": 0.2146558105107328,
      "grad_norm": 0.18668537652959327,
      "learning_rate": 1.92163568851975e-05,
      "loss": 0.7788,
      "step": 145
    },
    {
      "epoch": 0.22205773501110287,
      "grad_norm": 0.19092408401343772,
      "learning_rate": 1.911286098728296e-05,
      "loss": 0.7753,
      "step": 150
    },
    {
      "epoch": 0.22945965951147299,
      "grad_norm": 0.18559715805668162,
      "learning_rate": 1.900326279883392e-05,
      "loss": 0.8045,
      "step": 155
    },
    {
      "epoch": 0.23686158401184307,
      "grad_norm": 0.18303788735937754,
      "learning_rate": 1.8887635710631716e-05,
      "loss": 0.8076,
      "step": 160
    },
    {
      "epoch": 0.24426350851221318,
      "grad_norm": 0.1727421146270662,
      "learning_rate": 1.8766057150619865e-05,
      "loss": 0.7806,
      "step": 165
    },
    {
      "epoch": 0.25166543301258326,
      "grad_norm": 0.16831652909455164,
      "learning_rate": 1.8638608532055635e-05,
      "loss": 0.7975,
      "step": 170
    },
    {
      "epoch": 0.25906735751295334,
      "grad_norm": 0.16233969726713526,
      "learning_rate": 1.8505375198992856e-05,
      "loss": 0.7862,
      "step": 175
    },
    {
      "epoch": 0.2664692820133235,
      "grad_norm": 0.17738766153741692,
      "learning_rate": 1.836644636913258e-05,
      "loss": 0.7573,
      "step": 180
    },
    {
      "epoch": 0.27387120651369357,
      "grad_norm": 0.18574919808380788,
      "learning_rate": 1.8221915074079764e-05,
      "loss": 0.7807,
      "step": 185
    },
    {
      "epoch": 0.28127313101406365,
      "grad_norm": 0.19177650849967526,
      "learning_rate": 1.8071878097046064e-05,
      "loss": 0.7589,
      "step": 190
    },
    {
      "epoch": 0.28867505551443373,
      "grad_norm": 0.16334964744370573,
      "learning_rate": 1.7916435908040413e-05,
      "loss": 0.7753,
      "step": 195
    },
    {
      "epoch": 0.29607698001480387,
      "grad_norm": 0.16244944722916593,
      "learning_rate": 1.7755692596590778e-05,
      "loss": 0.7775,
      "step": 200
    },
    {
      "epoch": 0.29607698001480387,
      "eval_loss": 0.792992353439331,
      "eval_runtime": 7.4106,
      "eval_samples_per_second": 17.273,
      "eval_steps_per_second": 2.159,
      "step": 200
    },
    {
      "epoch": 0.30347890451517395,
      "grad_norm": 0.17715403064277388,
      "learning_rate": 1.7589755802042188e-05,
      "loss": 0.776,
      "step": 205
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 0.17508986500166754,
      "learning_rate": 1.7418736641477636e-05,
      "loss": 0.7591,
      "step": 210
    },
    {
      "epoch": 0.3182827535159141,
      "grad_norm": 0.15999470402359026,
      "learning_rate": 1.7242749635310222e-05,
      "loss": 0.7607,
      "step": 215
    },
    {
      "epoch": 0.32568467801628426,
      "grad_norm": 0.1626819033920982,
      "learning_rate": 1.7061912630596252e-05,
      "loss": 0.7632,
      "step": 220
    },
    {
      "epoch": 0.33308660251665434,
      "grad_norm": 0.18407704372355851,
      "learning_rate": 1.6876346722120747e-05,
      "loss": 0.778,
      "step": 225
    },
    {
      "epoch": 0.3404885270170244,
      "grad_norm": 0.17328606506049593,
      "learning_rate": 1.6686176171308125e-05,
      "loss": 0.8005,
      "step": 230
    },
    {
      "epoch": 0.3478904515173945,
      "grad_norm": 0.16916776680028325,
      "learning_rate": 1.6491528323012412e-05,
      "loss": 0.7623,
      "step": 235
    },
    {
      "epoch": 0.35529237601776464,
      "grad_norm": 0.15837424098002126,
      "learning_rate": 1.6292533520242663e-05,
      "loss": 0.7646,
      "step": 240
    },
    {
      "epoch": 0.3626943005181347,
      "grad_norm": 0.1648529296157822,
      "learning_rate": 1.6089325016880737e-05,
      "loss": 0.7553,
      "step": 245
    },
    {
      "epoch": 0.3700962250185048,
      "grad_norm": 0.1722042996400624,
      "learning_rate": 1.588203888844982e-05,
      "loss": 0.7707,
      "step": 250
    },
    {
      "epoch": 0.3774981495188749,
      "grad_norm": 0.16050551428905252,
      "learning_rate": 1.5670813940993504e-05,
      "loss": 0.7435,
      "step": 255
    },
    {
      "epoch": 0.38490007401924503,
      "grad_norm": 0.1468845556389716,
      "learning_rate": 1.5455791618126407e-05,
      "loss": 0.7357,
      "step": 260
    },
    {
      "epoch": 0.3923019985196151,
      "grad_norm": 0.15657890189823614,
      "learning_rate": 1.5237115906318565e-05,
      "loss": 0.7596,
      "step": 265
    },
    {
      "epoch": 0.3997039230199852,
      "grad_norm": 0.1722407778545654,
      "learning_rate": 1.5014933238477069e-05,
      "loss": 0.7405,
      "step": 270
    },
    {
      "epoch": 0.4071058475203553,
      "grad_norm": 0.1715058049538323,
      "learning_rate": 1.4789392395889468e-05,
      "loss": 0.766,
      "step": 275
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 0.1611503458192985,
      "learning_rate": 1.4560644408594602e-05,
      "loss": 0.7464,
      "step": 280
    },
    {
      "epoch": 0.4219096965210955,
      "grad_norm": 0.1661548200950646,
      "learning_rate": 1.432884245424761e-05,
      "loss": 0.7584,
      "step": 285
    },
    {
      "epoch": 0.4293116210214656,
      "grad_norm": 0.16927831949079214,
      "learning_rate": 1.4094141755546816e-05,
      "loss": 0.7858,
      "step": 290
    },
    {
      "epoch": 0.43671354552183567,
      "grad_norm": 0.1574850762747471,
      "learning_rate": 1.3856699476291176e-05,
      "loss": 0.7455,
      "step": 295
    },
    {
      "epoch": 0.44411547002220575,
      "grad_norm": 0.1744882309738823,
      "learning_rate": 1.3616674616137902e-05,
      "loss": 0.7674,
      "step": 300
    },
    {
      "epoch": 0.44411547002220575,
      "eval_loss": 0.7782045602798462,
      "eval_runtime": 7.4217,
      "eval_samples_per_second": 17.247,
      "eval_steps_per_second": 2.156,
      "step": 300
    },
    {
      "epoch": 0.4515173945225759,
      "grad_norm": 0.1618448599435551,
      "learning_rate": 1.3374227904130724e-05,
      "loss": 0.7574,
      "step": 305
    },
    {
      "epoch": 0.45891931902294597,
      "grad_norm": 0.16272430492033355,
      "learning_rate": 1.3129521691070108e-05,
      "loss": 0.7354,
      "step": 310
    },
    {
      "epoch": 0.46632124352331605,
      "grad_norm": 0.17805107895523076,
      "learning_rate": 1.2882719840797473e-05,
      "loss": 0.7539,
      "step": 315
    },
    {
      "epoch": 0.47372316802368614,
      "grad_norm": 0.17630754983453525,
      "learning_rate": 1.2633987620466229e-05,
      "loss": 0.7379,
      "step": 320
    },
    {
      "epoch": 0.4811250925240563,
      "grad_norm": 0.1617923521402878,
      "learning_rate": 1.2383491589873122e-05,
      "loss": 0.743,
      "step": 325
    },
    {
      "epoch": 0.48852701702442636,
      "grad_norm": 0.15297179161199892,
      "learning_rate": 1.213139948992394e-05,
      "loss": 0.7525,
      "step": 330
    },
    {
      "epoch": 0.49592894152479644,
      "grad_norm": 0.19383034727623744,
      "learning_rate": 1.187788013030837e-05,
      "loss": 0.7498,
      "step": 335
    },
    {
      "epoch": 0.5033308660251665,
      "grad_norm": 0.15637509144236988,
      "learning_rate": 1.1623103276459086e-05,
      "loss": 0.7535,
      "step": 340
    },
    {
      "epoch": 0.5107327905255367,
      "grad_norm": 0.16045862427323498,
      "learning_rate": 1.1367239535870913e-05,
      "loss": 0.7453,
      "step": 345
    },
    {
      "epoch": 0.5181347150259067,
      "grad_norm": 0.17698858161148076,
      "learning_rate": 1.1110460243856051e-05,
      "loss": 0.7329,
      "step": 350
    },
    {
      "epoch": 0.5255366395262768,
      "grad_norm": 0.17040850730538934,
      "learning_rate": 1.085293734881197e-05,
      "loss": 0.7496,
      "step": 355
    },
    {
      "epoch": 0.532938564026647,
      "grad_norm": 0.1516391951391077,
      "learning_rate": 1.0594843297078736e-05,
      "loss": 0.7689,
      "step": 360
    },
    {
      "epoch": 0.540340488527017,
      "grad_norm": 0.17717536543082385,
      "learning_rate": 1.0336350917462925e-05,
      "loss": 0.7586,
      "step": 365
    },
    {
      "epoch": 0.5477424130273871,
      "grad_norm": 0.15016943441369615,
      "learning_rate": 1.0077633305505402e-05,
      "loss": 0.7462,
      "step": 370
    },
    {
      "epoch": 0.5551443375277573,
      "grad_norm": 0.15913796873415315,
      "learning_rate": 9.818863707570476e-06,
      "loss": 0.7635,
      "step": 375
    },
    {
      "epoch": 0.5625462620281273,
      "grad_norm": 0.16666990971754578,
      "learning_rate": 9.560215404834094e-06,
      "loss": 0.7541,
      "step": 380
    },
    {
      "epoch": 0.5699481865284974,
      "grad_norm": 0.16161835204134142,
      "learning_rate": 9.30186159724869e-06,
      "loss": 0.7171,
      "step": 385
    },
    {
      "epoch": 0.5773501110288675,
      "grad_norm": 0.15424373108412043,
      "learning_rate": 9.043975287562443e-06,
      "loss": 0.7496,
      "step": 390
    },
    {
      "epoch": 0.5847520355292376,
      "grad_norm": 0.17121844554933624,
      "learning_rate": 8.786729165470584e-06,
      "loss": 0.7279,
      "step": 395
    },
    {
      "epoch": 0.5921539600296077,
      "grad_norm": 0.17445724777238197,
      "learning_rate": 8.530295491976338e-06,
      "loss": 0.7334,
      "step": 400
    },
    {
      "epoch": 0.5921539600296077,
      "eval_loss": 0.7663605213165283,
      "eval_runtime": 7.4181,
      "eval_samples_per_second": 17.255,
      "eval_steps_per_second": 2.157,
      "step": 400
    },
    {
      "epoch": 0.5995558845299778,
      "grad_norm": 0.15017702386342432,
      "learning_rate": 8.274845984038916e-06,
      "loss": 0.7197,
      "step": 405
    },
    {
      "epoch": 0.6069578090303479,
      "grad_norm": 0.16598073279170417,
      "learning_rate": 8.020551699585843e-06,
      "loss": 0.7495,
      "step": 410
    },
    {
      "epoch": 0.6143597335307179,
      "grad_norm": 0.15212926433085763,
      "learning_rate": 7.76758292296659e-06,
      "loss": 0.7289,
      "step": 415
    },
    {
      "epoch": 0.6217616580310881,
      "grad_norm": 0.16430026960784816,
      "learning_rate": 7.5161090509242005e-06,
      "loss": 0.7447,
      "step": 420
    },
    {
      "epoch": 0.6291635825314582,
      "grad_norm": 0.16670189821433365,
      "learning_rate": 7.2662984791613186e-06,
      "loss": 0.737,
      "step": 425
    },
    {
      "epoch": 0.6365655070318282,
      "grad_norm": 0.166174564668407,
      "learning_rate": 7.01831848957653e-06,
      "loss": 0.7518,
      "step": 430
    },
    {
      "epoch": 0.6439674315321984,
      "grad_norm": 0.15187524190909013,
      "learning_rate": 6.772335138246548e-06,
      "loss": 0.7495,
      "step": 435
    },
    {
      "epoch": 0.6513693560325685,
      "grad_norm": 0.15771310643006878,
      "learning_rate": 6.528513144229256e-06,
      "loss": 0.7454,
      "step": 440
    },
    {
      "epoch": 0.6587712805329385,
      "grad_norm": 0.1545722716082389,
      "learning_rate": 6.287015779262064e-06,
      "loss": 0.7516,
      "step": 445
    },
    {
      "epoch": 0.6661732050333087,
      "grad_norm": 0.16486187790859883,
      "learning_rate": 6.048004758429451e-06,
      "loss": 0.7301,
      "step": 450
    },
    {
      "epoch": 0.6735751295336787,
      "grad_norm": 0.15313953292819255,
      "learning_rate": 5.811640131872867e-06,
      "loss": 0.7525,
      "step": 455
    },
    {
      "epoch": 0.6809770540340488,
      "grad_norm": 0.15174175480942678,
      "learning_rate": 5.578080177615575e-06,
      "loss": 0.723,
      "step": 460
    },
    {
      "epoch": 0.688378978534419,
      "grad_norm": 0.15793530605455464,
      "learning_rate": 5.347481295574141e-06,
      "loss": 0.7199,
      "step": 465
    },
    {
      "epoch": 0.695780903034789,
      "grad_norm": 0.15600126164264752,
      "learning_rate": 5.119997902827584e-06,
      "loss": 0.7315,
      "step": 470
    },
    {
      "epoch": 0.7031828275351591,
      "grad_norm": 0.1537946952676734,
      "learning_rate": 4.8957823302142916e-06,
      "loss": 0.7381,
      "step": 475
    },
    {
      "epoch": 0.7105847520355293,
      "grad_norm": 0.14471078551971742,
      "learning_rate": 4.674984720325961e-06,
      "loss": 0.7235,
      "step": 480
    },
    {
      "epoch": 0.7179866765358993,
      "grad_norm": 0.1485927432710996,
      "learning_rate": 4.457752926966888e-06,
      "loss": 0.7177,
      "step": 485
    },
    {
      "epoch": 0.7253886010362695,
      "grad_norm": 0.14777285394061146,
      "learning_rate": 4.244232416145839e-06,
      "loss": 0.7364,
      "step": 490
    },
    {
      "epoch": 0.7327905255366395,
      "grad_norm": 0.14915923688072272,
      "learning_rate": 4.0345661686669745e-06,
      "loss": 0.7299,
      "step": 495
    },
    {
      "epoch": 0.7401924500370096,
      "grad_norm": 0.1575162299441041,
      "learning_rate": 3.828894584384867e-06,
      "loss": 0.7383,
      "step": 500
    },
    {
      "epoch": 0.7401924500370096,
      "eval_loss": 0.7590785026550293,
      "eval_runtime": 7.4207,
      "eval_samples_per_second": 17.249,
      "eval_steps_per_second": 2.156,
      "step": 500
    },
    {
      "epoch": 0.7475943745373798,
      "grad_norm": 0.14090130126556033,
      "learning_rate": 3.62735538818787e-06,
      "loss": 0.7225,
      "step": 505
    },
    {
      "epoch": 0.7549962990377498,
      "grad_norm": 0.16015231295751484,
      "learning_rate": 3.4300835377726904e-06,
      "loss": 0.7258,
      "step": 510
    },
    {
      "epoch": 0.7623982235381199,
      "grad_norm": 0.15634890673943705,
      "learning_rate": 3.2372111332720045e-06,
      "loss": 0.7615,
      "step": 515
    },
    {
      "epoch": 0.7698001480384901,
      "grad_norm": 0.15492129407975255,
      "learning_rate": 3.048867328795588e-06,
      "loss": 0.7185,
      "step": 520
    },
    {
      "epoch": 0.7772020725388601,
      "grad_norm": 0.1536820552855932,
      "learning_rate": 2.865178245944218e-06,
      "loss": 0.7172,
      "step": 525
    },
    {
      "epoch": 0.7846039970392302,
      "grad_norm": 0.14404942403792287,
      "learning_rate": 2.686266889354211e-06,
      "loss": 0.7402,
      "step": 530
    },
    {
      "epoch": 0.7920059215396003,
      "grad_norm": 0.15061771515240063,
      "learning_rate": 2.5122530643292274e-06,
      "loss": 0.7457,
      "step": 535
    },
    {
      "epoch": 0.7994078460399704,
      "grad_norm": 0.15931765312029125,
      "learning_rate": 2.3432532966144526e-06,
      "loss": 0.735,
      "step": 540
    },
    {
      "epoch": 0.8068097705403405,
      "grad_norm": 0.14880606411370811,
      "learning_rate": 2.1793807543668857e-06,
      "loss": 0.7369,
      "step": 545
    },
    {
      "epoch": 0.8142116950407106,
      "grad_norm": 0.13955804663380328,
      "learning_rate": 2.0207451723739633e-06,
      "loss": 0.7286,
      "step": 550
    },
    {
      "epoch": 0.8216136195410807,
      "grad_norm": 0.14222438381196842,
      "learning_rate": 1.8674527785713247e-06,
      "loss": 0.7352,
      "step": 555
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 0.15493563458184517,
      "learning_rate": 1.7196062229088606e-06,
      "loss": 0.7024,
      "step": 560
    },
    {
      "epoch": 0.8364174685418209,
      "grad_norm": 0.15849673501104045,
      "learning_rate": 1.577304508612717e-06,
      "loss": 0.7327,
      "step": 565
    },
    {
      "epoch": 0.843819393042191,
      "grad_norm": 0.1319970212658075,
      "learning_rate": 1.4406429258892762e-06,
      "loss": 0.7533,
      "step": 570
    },
    {
      "epoch": 0.851221317542561,
      "grad_norm": 0.1537421430544868,
      "learning_rate": 1.3097129881154936e-06,
      "loss": 0.7227,
      "step": 575
    },
    {
      "epoch": 0.8586232420429312,
      "grad_norm": 0.14761812731310603,
      "learning_rate": 1.1846023705583442e-06,
      "loss": 0.7192,
      "step": 580
    },
    {
      "epoch": 0.8660251665433013,
      "grad_norm": 0.1467426757613686,
      "learning_rate": 1.065394851664394e-06,
      "loss": 0.7372,
      "step": 585
    },
    {
      "epoch": 0.8734270910436713,
      "grad_norm": 0.13796190944318665,
      "learning_rate": 9.521702569588199e-07,
      "loss": 0.7567,
      "step": 590
    },
    {
      "epoch": 0.8808290155440415,
      "grad_norm": 0.1465576861864633,
      "learning_rate": 8.450044055914497e-07,
      "loss": 0.7251,
      "step": 595
    },
    {
      "epoch": 0.8882309400444115,
      "grad_norm": 0.1438541063374612,
      "learning_rate": 7.439690595656013e-07,
      "loss": 0.7476,
      "step": 600
    },
    {
      "epoch": 0.8882309400444115,
      "eval_loss": 0.756076455116272,
      "eval_runtime": 7.4191,
      "eval_samples_per_second": 17.253,
      "eval_steps_per_second": 2.157,
      "step": 600
    },
    {
      "epoch": 0.8956328645447816,
      "grad_norm": 0.15935861793163747,
      "learning_rate": 6.491318756837417e-07,
      "loss": 0.7326,
      "step": 605
    },
    {
      "epoch": 0.9030347890451518,
      "grad_norm": 0.13053574456346068,
      "learning_rate": 5.605563602421149e-07,
      "loss": 0.7086,
      "step": 610
    },
    {
      "epoch": 0.9104367135455218,
      "grad_norm": 0.14030080200508646,
      "learning_rate": 4.783018265047179e-07,
      "loss": 0.7587,
      "step": 615
    },
    {
      "epoch": 0.9178386380458919,
      "grad_norm": 0.14930285941092133,
      "learning_rate": 4.024233549850509e-07,
      "loss": 0.7466,
      "step": 620
    },
    {
      "epoch": 0.9252405625462621,
      "grad_norm": 0.138865713951949,
      "learning_rate": 3.329717565622825e-07,
      "loss": 0.7435,
      "step": 625
    },
    {
      "epoch": 0.9326424870466321,
      "grad_norm": 0.13900920647213558,
      "learning_rate": 2.6999353845651113e-07,
      "loss": 0.7269,
      "step": 630
    },
    {
      "epoch": 0.9400444115470022,
      "grad_norm": 0.14964928985956502,
      "learning_rate": 2.1353087308590314e-07,
      "loss": 0.742,
      "step": 635
    },
    {
      "epoch": 0.9474463360473723,
      "grad_norm": 0.14169454043564503,
      "learning_rate": 1.6362156982656085e-07,
      "loss": 0.732,
      "step": 640
    },
    {
      "epoch": 0.9548482605477424,
      "grad_norm": 0.13204403743757542,
      "learning_rate": 1.2029904969404482e-07,
      "loss": 0.7158,
      "step": 645
    },
    {
      "epoch": 0.9622501850481125,
      "grad_norm": 0.15194221565424584,
      "learning_rate": 8.359232296349163e-08,
      "loss": 0.7192,
      "step": 650
    },
    {
      "epoch": 0.9696521095484826,
      "grad_norm": 0.1435144775044456,
      "learning_rate": 5.3525969743324356e-08,
      "loss": 0.7349,
      "step": 655
    },
    {
      "epoch": 0.9770540340488527,
      "grad_norm": 0.13844204120911296,
      "learning_rate": 3.012012351554017e-08,
      "loss": 0.7093,
      "step": 660
    },
    {
      "epoch": 0.9844559585492227,
      "grad_norm": 0.15365673275391972,
      "learning_rate": 1.3390457653639221e-08,
      "loss": 0.7378,
      "step": 665
    },
    {
      "epoch": 0.9918578830495929,
      "grad_norm": 0.16372514723707865,
      "learning_rate": 3.3481749271768726e-09,
      "loss": 0.7492,
      "step": 670
    },
    {
      "epoch": 0.999259807549963,
      "grad_norm": 0.14453971027117873,
      "learning_rate": 0.0,
      "loss": 0.7185,
      "step": 675
    },
    {
      "epoch": 0.999259807549963,
      "step": 675,
      "total_flos": 5.2170668949005926e+17,
      "train_loss": 0.7709741959748445,
      "train_runtime": 4715.7656,
      "train_samples_per_second": 4.583,
      "train_steps_per_second": 0.143
    }
  ],
  "logging_steps": 5,
  "max_steps": 675,
  "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": 5.2170668949005926e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}