{
  "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": 2.674959598727342,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 1.0787,
      "step": 5
    },
    {
      "epoch": 0.014803849000740192,
      "grad_norm": 2.2849930335009767,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.0901,
      "step": 10
    },
    {
      "epoch": 0.02220577350111029,
      "grad_norm": 1.4169102513042604,
      "learning_rate": 4.411764705882353e-06,
      "loss": 1.0619,
      "step": 15
    },
    {
      "epoch": 0.029607698001480384,
      "grad_norm": 1.3754280634869183,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.0087,
      "step": 20
    },
    {
      "epoch": 0.037009622501850484,
      "grad_norm": 1.1141154652271672,
      "learning_rate": 7.352941176470589e-06,
      "loss": 0.9684,
      "step": 25
    },
    {
      "epoch": 0.04441154700222058,
      "grad_norm": 0.9534792105007532,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.9217,
      "step": 30
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 0.7606504248144849,
      "learning_rate": 1.0294117647058823e-05,
      "loss": 0.8859,
      "step": 35
    },
    {
      "epoch": 0.05921539600296077,
      "grad_norm": 0.68529790584477,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.8631,
      "step": 40
    },
    {
      "epoch": 0.06661732050333087,
      "grad_norm": 0.7482947060538522,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.8485,
      "step": 45
    },
    {
      "epoch": 0.07401924500370097,
      "grad_norm": 0.814176151345203,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 0.861,
      "step": 50
    },
    {
      "epoch": 0.08142116950407106,
      "grad_norm": 0.6269959293106316,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.8545,
      "step": 55
    },
    {
      "epoch": 0.08882309400444116,
      "grad_norm": 0.7352759272340602,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8293,
      "step": 60
    },
    {
      "epoch": 0.09622501850481126,
      "grad_norm": 0.6918084490038217,
      "learning_rate": 1.911764705882353e-05,
      "loss": 0.8259,
      "step": 65
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 0.7718482933587625,
      "learning_rate": 1.9999464266898485e-05,
      "loss": 0.8211,
      "step": 70
    },
    {
      "epoch": 0.11102886750555144,
      "grad_norm": 0.9788064725128405,
      "learning_rate": 1.9993437928712977e-05,
      "loss": 0.8164,
      "step": 75
    },
    {
      "epoch": 0.11843079200592153,
      "grad_norm": 0.837998184141708,
      "learning_rate": 1.998071963486563e-05,
      "loss": 0.8062,
      "step": 80
    },
    {
      "epoch": 0.12583271650629163,
      "grad_norm": 0.6629895054599079,
      "learning_rate": 1.9961317901970953e-05,
      "loss": 0.7945,
      "step": 85
    },
    {
      "epoch": 0.13323464100666174,
      "grad_norm": 0.7557912436308644,
      "learning_rate": 1.993524572210807e-05,
      "loss": 0.7947,
      "step": 90
    },
    {
      "epoch": 0.14063656550703182,
      "grad_norm": 0.797960903546945,
      "learning_rate": 1.990252055412077e-05,
      "loss": 0.7906,
      "step": 95
    },
    {
      "epoch": 0.14803849000740193,
      "grad_norm": 0.7886433512486097,
      "learning_rate": 1.9863164311926433e-05,
      "loss": 0.8171,
      "step": 100
    },
    {
      "epoch": 0.14803849000740193,
      "eval_loss": 0.8197493553161621,
      "eval_runtime": 7.2314,
      "eval_samples_per_second": 17.701,
      "eval_steps_per_second": 2.213,
      "step": 100
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 0.7194704926083675,
      "learning_rate": 1.981720334984174e-05,
      "loss": 0.792,
      "step": 105
    },
    {
      "epoch": 0.16284233900814213,
      "grad_norm": 0.7153212599875873,
      "learning_rate": 1.9764668444934853e-05,
      "loss": 0.7859,
      "step": 110
    },
    {
      "epoch": 0.1702442635085122,
      "grad_norm": 0.7209996155683963,
      "learning_rate": 1.970559477641606e-05,
      "loss": 0.7631,
      "step": 115
    },
    {
      "epoch": 0.17764618800888232,
      "grad_norm": 0.7333599419087882,
      "learning_rate": 1.9640021902080523e-05,
      "loss": 0.793,
      "step": 120
    },
    {
      "epoch": 0.1850481125092524,
      "grad_norm": 0.6289153412562695,
      "learning_rate": 1.9567993731818988e-05,
      "loss": 0.7916,
      "step": 125
    },
    {
      "epoch": 0.19245003700962252,
      "grad_norm": 0.7521612039190329,
      "learning_rate": 1.9489558498214197e-05,
      "loss": 0.7843,
      "step": 130
    },
    {
      "epoch": 0.1998519615099926,
      "grad_norm": 0.6568997079081034,
      "learning_rate": 1.9404768724242667e-05,
      "loss": 0.7703,
      "step": 135
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 0.7360339897713676,
      "learning_rate": 1.931368118810346e-05,
      "loss": 0.7947,
      "step": 140
    },
    {
      "epoch": 0.2146558105107328,
      "grad_norm": 0.7557749076828488,
      "learning_rate": 1.92163568851975e-05,
      "loss": 0.7757,
      "step": 145
    },
    {
      "epoch": 0.22205773501110287,
      "grad_norm": 0.8218802431960855,
      "learning_rate": 1.911286098728296e-05,
      "loss": 0.772,
      "step": 150
    },
    {
      "epoch": 0.22945965951147299,
      "grad_norm": 0.7041654789385663,
      "learning_rate": 1.900326279883392e-05,
      "loss": 0.8017,
      "step": 155
    },
    {
      "epoch": 0.23686158401184307,
      "grad_norm": 0.7107270494061172,
      "learning_rate": 1.8887635710631716e-05,
      "loss": 0.8045,
      "step": 160
    },
    {
      "epoch": 0.24426350851221318,
      "grad_norm": 0.7042955521495632,
      "learning_rate": 1.8766057150619865e-05,
      "loss": 0.7775,
      "step": 165
    },
    {
      "epoch": 0.25166543301258326,
      "grad_norm": 0.7141479489682149,
      "learning_rate": 1.8638608532055635e-05,
      "loss": 0.7947,
      "step": 170
    },
    {
      "epoch": 0.25906735751295334,
      "grad_norm": 0.6682818577909502,
      "learning_rate": 1.8505375198992856e-05,
      "loss": 0.7831,
      "step": 175
    },
    {
      "epoch": 0.2664692820133235,
      "grad_norm": 0.7193249750447441,
      "learning_rate": 1.836644636913258e-05,
      "loss": 0.7542,
      "step": 180
    },
    {
      "epoch": 0.27387120651369357,
      "grad_norm": 0.7847188441908851,
      "learning_rate": 1.8221915074079764e-05,
      "loss": 0.7778,
      "step": 185
    },
    {
      "epoch": 0.28127313101406365,
      "grad_norm": 0.8828987676403609,
      "learning_rate": 1.8071878097046064e-05,
      "loss": 0.7564,
      "step": 190
    },
    {
      "epoch": 0.28867505551443373,
      "grad_norm": 0.6213320600286455,
      "learning_rate": 1.7916435908040413e-05,
      "loss": 0.7723,
      "step": 195
    },
    {
      "epoch": 0.29607698001480387,
      "grad_norm": 0.6595102663479724,
      "learning_rate": 1.7755692596590778e-05,
      "loss": 0.7747,
      "step": 200
    },
    {
      "epoch": 0.29607698001480387,
      "eval_loss": 0.7899559736251831,
      "eval_runtime": 7.2104,
      "eval_samples_per_second": 17.752,
      "eval_steps_per_second": 2.219,
      "step": 200
    },
    {
      "epoch": 0.30347890451517395,
      "grad_norm": 0.706296557877635,
      "learning_rate": 1.7589755802042188e-05,
      "loss": 0.773,
      "step": 205
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 0.6937734870068385,
      "learning_rate": 1.7418736641477636e-05,
      "loss": 0.7563,
      "step": 210
    },
    {
      "epoch": 0.3182827535159141,
      "grad_norm": 0.6327617109092492,
      "learning_rate": 1.7242749635310222e-05,
      "loss": 0.758,
      "step": 215
    },
    {
      "epoch": 0.32568467801628426,
      "grad_norm": 0.6635934294750666,
      "learning_rate": 1.7061912630596252e-05,
      "loss": 0.7605,
      "step": 220
    },
    {
      "epoch": 0.33308660251665434,
      "grad_norm": 0.7228160092157478,
      "learning_rate": 1.6876346722120747e-05,
      "loss": 0.7754,
      "step": 225
    },
    {
      "epoch": 0.3404885270170244,
      "grad_norm": 0.6952975644500169,
      "learning_rate": 1.6686176171308125e-05,
      "loss": 0.7977,
      "step": 230
    },
    {
      "epoch": 0.3478904515173945,
      "grad_norm": 0.6717058633626165,
      "learning_rate": 1.6491528323012412e-05,
      "loss": 0.7594,
      "step": 235
    },
    {
      "epoch": 0.35529237601776464,
      "grad_norm": 0.6596693045521963,
      "learning_rate": 1.6292533520242663e-05,
      "loss": 0.7623,
      "step": 240
    },
    {
      "epoch": 0.3626943005181347,
      "grad_norm": 0.6470637566854384,
      "learning_rate": 1.6089325016880737e-05,
      "loss": 0.7526,
      "step": 245
    },
    {
      "epoch": 0.3700962250185048,
      "grad_norm": 0.6877498215548267,
      "learning_rate": 1.588203888844982e-05,
      "loss": 0.7681,
      "step": 250
    },
    {
      "epoch": 0.3774981495188749,
      "grad_norm": 0.6358323626672553,
      "learning_rate": 1.5670813940993504e-05,
      "loss": 0.741,
      "step": 255
    },
    {
      "epoch": 0.38490007401924503,
      "grad_norm": 0.600848318475503,
      "learning_rate": 1.5455791618126407e-05,
      "loss": 0.7334,
      "step": 260
    },
    {
      "epoch": 0.3923019985196151,
      "grad_norm": 0.6314609013122284,
      "learning_rate": 1.5237115906318565e-05,
      "loss": 0.7572,
      "step": 265
    },
    {
      "epoch": 0.3997039230199852,
      "grad_norm": 0.6546980627619242,
      "learning_rate": 1.5014933238477069e-05,
      "loss": 0.7378,
      "step": 270
    },
    {
      "epoch": 0.4071058475203553,
      "grad_norm": 0.6975545683818176,
      "learning_rate": 1.4789392395889468e-05,
      "loss": 0.7632,
      "step": 275
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 0.6503686028697638,
      "learning_rate": 1.4560644408594602e-05,
      "loss": 0.744,
      "step": 280
    },
    {
      "epoch": 0.4219096965210955,
      "grad_norm": 0.6602116319307001,
      "learning_rate": 1.432884245424761e-05,
      "loss": 0.7556,
      "step": 285
    },
    {
      "epoch": 0.4293116210214656,
      "grad_norm": 0.6672698383287922,
      "learning_rate": 1.4094141755546816e-05,
      "loss": 0.7831,
      "step": 290
    },
    {
      "epoch": 0.43671354552183567,
      "grad_norm": 0.6305307497798698,
      "learning_rate": 1.3856699476291176e-05,
      "loss": 0.7426,
      "step": 295
    },
    {
      "epoch": 0.44411547002220575,
      "grad_norm": 0.6859073767100461,
      "learning_rate": 1.3616674616137902e-05,
      "loss": 0.7645,
      "step": 300
    },
    {
      "epoch": 0.44411547002220575,
      "eval_loss": 0.7755689024925232,
      "eval_runtime": 7.2066,
      "eval_samples_per_second": 17.762,
      "eval_steps_per_second": 2.22,
      "step": 300
    },
    {
      "epoch": 0.4515173945225759,
      "grad_norm": 0.6626556377379951,
      "learning_rate": 1.3374227904130724e-05,
      "loss": 0.7549,
      "step": 305
    },
    {
      "epoch": 0.45891931902294597,
      "grad_norm": 0.6499839877597537,
      "learning_rate": 1.3129521691070108e-05,
      "loss": 0.7328,
      "step": 310
    },
    {
      "epoch": 0.46632124352331605,
      "grad_norm": 0.722140222976433,
      "learning_rate": 1.2882719840797473e-05,
      "loss": 0.7514,
      "step": 315
    },
    {
      "epoch": 0.47372316802368614,
      "grad_norm": 0.6900675221213151,
      "learning_rate": 1.2633987620466229e-05,
      "loss": 0.7353,
      "step": 320
    },
    {
      "epoch": 0.4811250925240563,
      "grad_norm": 0.6297341225224966,
      "learning_rate": 1.2383491589873122e-05,
      "loss": 0.7407,
      "step": 325
    },
    {
      "epoch": 0.48852701702442636,
      "grad_norm": 0.6139804357167142,
      "learning_rate": 1.213139948992394e-05,
      "loss": 0.7497,
      "step": 330
    },
    {
      "epoch": 0.49592894152479644,
      "grad_norm": 0.7120439739230976,
      "learning_rate": 1.187788013030837e-05,
      "loss": 0.7468,
      "step": 335
    },
    {
      "epoch": 0.5033308660251665,
      "grad_norm": 0.6179256601206382,
      "learning_rate": 1.1623103276459086e-05,
      "loss": 0.7507,
      "step": 340
    },
    {
      "epoch": 0.5107327905255367,
      "grad_norm": 0.6483835976434715,
      "learning_rate": 1.1367239535870913e-05,
      "loss": 0.7425,
      "step": 345
    },
    {
      "epoch": 0.5181347150259067,
      "grad_norm": 0.6928461738197682,
      "learning_rate": 1.1110460243856051e-05,
      "loss": 0.7302,
      "step": 350
    },
    {
      "epoch": 0.5255366395262768,
      "grad_norm": 0.6706880141545486,
      "learning_rate": 1.085293734881197e-05,
      "loss": 0.7468,
      "step": 355
    },
    {
      "epoch": 0.532938564026647,
      "grad_norm": 0.6042342171269331,
      "learning_rate": 1.0594843297078736e-05,
      "loss": 0.766,
      "step": 360
    },
    {
      "epoch": 0.540340488527017,
      "grad_norm": 0.693508088289296,
      "learning_rate": 1.0336350917462925e-05,
      "loss": 0.7558,
      "step": 365
    },
    {
      "epoch": 0.5477424130273871,
      "grad_norm": 0.6083705213800933,
      "learning_rate": 1.0077633305505402e-05,
      "loss": 0.7433,
      "step": 370
    },
    {
      "epoch": 0.5551443375277573,
      "grad_norm": 0.6396792431151416,
      "learning_rate": 9.818863707570476e-06,
      "loss": 0.7608,
      "step": 375
    },
    {
      "epoch": 0.5625462620281273,
      "grad_norm": 0.6663076065375303,
      "learning_rate": 9.560215404834094e-06,
      "loss": 0.7515,
      "step": 380
    },
    {
      "epoch": 0.5699481865284974,
      "grad_norm": 0.641428537274285,
      "learning_rate": 9.30186159724869e-06,
      "loss": 0.7146,
      "step": 385
    },
    {
      "epoch": 0.5773501110288675,
      "grad_norm": 0.6138036144437788,
      "learning_rate": 9.043975287562443e-06,
      "loss": 0.747,
      "step": 390
    },
    {
      "epoch": 0.5847520355292376,
      "grad_norm": 0.6807331921757377,
      "learning_rate": 8.786729165470584e-06,
      "loss": 0.7253,
      "step": 395
    },
    {
      "epoch": 0.5921539600296077,
      "grad_norm": 0.6952002905984943,
      "learning_rate": 8.530295491976338e-06,
      "loss": 0.7307,
      "step": 400
    },
    {
      "epoch": 0.5921539600296077,
      "eval_loss": 0.7637839317321777,
      "eval_runtime": 7.2078,
      "eval_samples_per_second": 17.759,
      "eval_steps_per_second": 2.22,
      "step": 400
    },
    {
      "epoch": 0.5995558845299778,
      "grad_norm": 0.5939454843322792,
      "learning_rate": 8.274845984038916e-06,
      "loss": 0.7174,
      "step": 405
    },
    {
      "epoch": 0.6069578090303479,
      "grad_norm": 0.6621271866381216,
      "learning_rate": 8.020551699585843e-06,
      "loss": 0.7469,
      "step": 410
    },
    {
      "epoch": 0.6143597335307179,
      "grad_norm": 0.6106430449913639,
      "learning_rate": 7.76758292296659e-06,
      "loss": 0.7264,
      "step": 415
    },
    {
      "epoch": 0.6217616580310881,
      "grad_norm": 0.6584389038177016,
      "learning_rate": 7.5161090509242005e-06,
      "loss": 0.7418,
      "step": 420
    },
    {
      "epoch": 0.6291635825314582,
      "grad_norm": 0.6508063180682058,
      "learning_rate": 7.2662984791613186e-06,
      "loss": 0.7345,
      "step": 425
    },
    {
      "epoch": 0.6365655070318282,
      "grad_norm": 0.654746417724555,
      "learning_rate": 7.01831848957653e-06,
      "loss": 0.7488,
      "step": 430
    },
    {
      "epoch": 0.6439674315321984,
      "grad_norm": 0.6038759794228741,
      "learning_rate": 6.772335138246548e-06,
      "loss": 0.747,
      "step": 435
    },
    {
      "epoch": 0.6513693560325685,
      "grad_norm": 0.6254763438931118,
      "learning_rate": 6.528513144229256e-06,
      "loss": 0.7427,
      "step": 440
    },
    {
      "epoch": 0.6587712805329385,
      "grad_norm": 0.6195437763354315,
      "learning_rate": 6.287015779262064e-06,
      "loss": 0.7489,
      "step": 445
    },
    {
      "epoch": 0.6661732050333087,
      "grad_norm": 0.6629664159964251,
      "learning_rate": 6.048004758429451e-06,
      "loss": 0.7274,
      "step": 450
    },
    {
      "epoch": 0.6735751295336787,
      "grad_norm": 0.6058164232925908,
      "learning_rate": 5.811640131872867e-06,
      "loss": 0.7496,
      "step": 455
    },
    {
      "epoch": 0.6809770540340488,
      "grad_norm": 0.6082658380867586,
      "learning_rate": 5.578080177615575e-06,
      "loss": 0.7201,
      "step": 460
    },
    {
      "epoch": 0.688378978534419,
      "grad_norm": 0.6242205120975641,
      "learning_rate": 5.347481295574141e-06,
      "loss": 0.7172,
      "step": 465
    },
    {
      "epoch": 0.695780903034789,
      "grad_norm": 0.6109755979913201,
      "learning_rate": 5.119997902827584e-06,
      "loss": 0.7286,
      "step": 470
    },
    {
      "epoch": 0.7031828275351591,
      "grad_norm": 0.6087033956225949,
      "learning_rate": 4.8957823302142916e-06,
      "loss": 0.7354,
      "step": 475
    },
    {
      "epoch": 0.7105847520355293,
      "grad_norm": 0.5865522874345606,
      "learning_rate": 4.674984720325961e-06,
      "loss": 0.7212,
      "step": 480
    },
    {
      "epoch": 0.7179866765358993,
      "grad_norm": 0.5900008473027598,
      "learning_rate": 4.457752926966888e-06,
      "loss": 0.715,
      "step": 485
    },
    {
      "epoch": 0.7253886010362695,
      "grad_norm": 0.5840665816418219,
      "learning_rate": 4.244232416145839e-06,
      "loss": 0.7337,
      "step": 490
    },
    {
      "epoch": 0.7327905255366395,
      "grad_norm": 0.5914947024608387,
      "learning_rate": 4.0345661686669745e-06,
      "loss": 0.7271,
      "step": 495
    },
    {
      "epoch": 0.7401924500370096,
      "grad_norm": 0.6196202183056477,
      "learning_rate": 3.828894584384867e-06,
      "loss": 0.7355,
      "step": 500
    },
    {
      "epoch": 0.7401924500370096,
      "eval_loss": 0.7563655972480774,
      "eval_runtime": 7.2181,
      "eval_samples_per_second": 17.733,
      "eval_steps_per_second": 2.217,
      "step": 500
    },
    {
      "epoch": 0.7475943745373798,
      "grad_norm": 0.5586852736192075,
      "learning_rate": 3.62735538818787e-06,
      "loss": 0.7197,
      "step": 505
    },
    {
      "epoch": 0.7549962990377498,
      "grad_norm": 0.6337625854919152,
      "learning_rate": 3.4300835377726904e-06,
      "loss": 0.7233,
      "step": 510
    },
    {
      "epoch": 0.7623982235381199,
      "grad_norm": 0.6205123290247885,
      "learning_rate": 3.2372111332720045e-06,
      "loss": 0.7587,
      "step": 515
    },
    {
      "epoch": 0.7698001480384901,
      "grad_norm": 0.6153129450053498,
      "learning_rate": 3.048867328795588e-06,
      "loss": 0.7156,
      "step": 520
    },
    {
      "epoch": 0.7772020725388601,
      "grad_norm": 0.6026709629344417,
      "learning_rate": 2.865178245944218e-06,
      "loss": 0.7144,
      "step": 525
    },
    {
      "epoch": 0.7846039970392302,
      "grad_norm": 0.5724937932245526,
      "learning_rate": 2.686266889354211e-06,
      "loss": 0.7375,
      "step": 530
    },
    {
      "epoch": 0.7920059215396003,
      "grad_norm": 0.5925644676097567,
      "learning_rate": 2.5122530643292274e-06,
      "loss": 0.7429,
      "step": 535
    },
    {
      "epoch": 0.7994078460399704,
      "grad_norm": 0.6326300634198754,
      "learning_rate": 2.3432532966144526e-06,
      "loss": 0.7323,
      "step": 540
    },
    {
      "epoch": 0.8068097705403405,
      "grad_norm": 0.5849976467168821,
      "learning_rate": 2.1793807543668857e-06,
      "loss": 0.7338,
      "step": 545
    },
    {
      "epoch": 0.8142116950407106,
      "grad_norm": 0.5500210584534766,
      "learning_rate": 2.0207451723739633e-06,
      "loss": 0.7257,
      "step": 550
    },
    {
      "epoch": 0.8216136195410807,
      "grad_norm": 0.5676680461413595,
      "learning_rate": 1.8674527785713247e-06,
      "loss": 0.7325,
      "step": 555
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 0.6239434546631168,
      "learning_rate": 1.7196062229088606e-06,
      "loss": 0.6996,
      "step": 560
    },
    {
      "epoch": 0.8364174685418209,
      "grad_norm": 0.6254391500900318,
      "learning_rate": 1.577304508612717e-06,
      "loss": 0.7298,
      "step": 565
    },
    {
      "epoch": 0.843819393042191,
      "grad_norm": 0.5238189690989516,
      "learning_rate": 1.4406429258892762e-06,
      "loss": 0.7503,
      "step": 570
    },
    {
      "epoch": 0.851221317542561,
      "grad_norm": 0.6133649327761147,
      "learning_rate": 1.3097129881154936e-06,
      "loss": 0.7199,
      "step": 575
    },
    {
      "epoch": 0.8586232420429312,
      "grad_norm": 0.5832243304649319,
      "learning_rate": 1.1846023705583442e-06,
      "loss": 0.7164,
      "step": 580
    },
    {
      "epoch": 0.8660251665433013,
      "grad_norm": 0.581421408776636,
      "learning_rate": 1.065394851664394e-06,
      "loss": 0.7345,
      "step": 585
    },
    {
      "epoch": 0.8734270910436713,
      "grad_norm": 0.5486795664712047,
      "learning_rate": 9.521702569588199e-07,
      "loss": 0.7537,
      "step": 590
    },
    {
      "epoch": 0.8808290155440415,
      "grad_norm": 0.5762089839170463,
      "learning_rate": 8.450044055914497e-07,
      "loss": 0.7221,
      "step": 595
    },
    {
      "epoch": 0.8882309400444115,
      "grad_norm": 0.5637562364478066,
      "learning_rate": 7.439690595656013e-07,
      "loss": 0.7445,
      "step": 600
    },
    {
      "epoch": 0.8882309400444115,
      "eval_loss": 0.7531630992889404,
      "eval_runtime": 6.3295,
      "eval_samples_per_second": 20.223,
      "eval_steps_per_second": 2.528,
      "step": 600
    },
    {
      "epoch": 0.8956328645447816,
      "grad_norm": 0.6333025954598674,
      "learning_rate": 6.491318756837417e-07,
      "loss": 0.7298,
      "step": 605
    },
    {
      "epoch": 0.9030347890451518,
      "grad_norm": 0.5151052584290405,
      "learning_rate": 5.605563602421149e-07,
      "loss": 0.7058,
      "step": 610
    },
    {
      "epoch": 0.9104367135455218,
      "grad_norm": 0.558083301486103,
      "learning_rate": 4.783018265047179e-07,
      "loss": 0.7557,
      "step": 615
    },
    {
      "epoch": 0.9178386380458919,
      "grad_norm": 0.5838054593517799,
      "learning_rate": 4.024233549850509e-07,
      "loss": 0.7436,
      "step": 620
    },
    {
      "epoch": 0.9252405625462621,
      "grad_norm": 0.5532527164872905,
      "learning_rate": 3.329717565622825e-07,
      "loss": 0.7404,
      "step": 625
    },
    {
      "epoch": 0.9326424870466321,
      "grad_norm": 0.5531839239223881,
      "learning_rate": 2.6999353845651113e-07,
      "loss": 0.724,
      "step": 630
    },
    {
      "epoch": 0.9400444115470022,
      "grad_norm": 0.5908996580668381,
      "learning_rate": 2.1353087308590314e-07,
      "loss": 0.7391,
      "step": 635
    },
    {
      "epoch": 0.9474463360473723,
      "grad_norm": 0.5583503930295213,
      "learning_rate": 1.6362156982656085e-07,
      "loss": 0.7292,
      "step": 640
    },
    {
      "epoch": 0.9548482605477424,
      "grad_norm": 0.5273929642155748,
      "learning_rate": 1.2029904969404482e-07,
      "loss": 0.7127,
      "step": 645
    },
    {
      "epoch": 0.9622501850481125,
      "grad_norm": 0.6043817732068986,
      "learning_rate": 8.359232296349163e-08,
      "loss": 0.7163,
      "step": 650
    },
    {
      "epoch": 0.9696521095484826,
      "grad_norm": 0.5680817655810946,
      "learning_rate": 5.3525969743324356e-08,
      "loss": 0.7322,
      "step": 655
    },
    {
      "epoch": 0.9770540340488527,
      "grad_norm": 0.5484921768212552,
      "learning_rate": 3.012012351554017e-08,
      "loss": 0.7064,
      "step": 660
    },
    {
      "epoch": 0.9844559585492227,
      "grad_norm": 0.5841736663763849,
      "learning_rate": 1.3390457653639221e-08,
      "loss": 0.7353,
      "step": 665
    },
    {
      "epoch": 0.9918578830495929,
      "grad_norm": 0.6439690756031937,
      "learning_rate": 3.3481749271768726e-09,
      "loss": 0.7463,
      "step": 670
    },
    {
      "epoch": 0.999259807549963,
      "grad_norm": 0.5777335037865771,
      "learning_rate": 0.0,
      "loss": 0.7158,
      "step": 675
    },
    {
      "epoch": 0.999259807549963,
      "step": 675,
      "total_flos": 76888336760832.0,
      "train_loss": 0.7675936229140671,
      "train_runtime": 4627.4844,
      "train_samples_per_second": 4.67,
      "train_steps_per_second": 0.146
    }
  ],
  "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": 76888336760832.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}