{
  "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": 2.6775108151736338,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 1.0786,
      "step": 5
    },
    {
      "epoch": 0.014803849000740192,
      "grad_norm": 2.2851851588534995,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.0902,
      "step": 10
    },
    {
      "epoch": 0.02220577350111029,
      "grad_norm": 1.417397856010511,
      "learning_rate": 4.411764705882353e-06,
      "loss": 1.0621,
      "step": 15
    },
    {
      "epoch": 0.029607698001480384,
      "grad_norm": 1.3738879264596535,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.0088,
      "step": 20
    },
    {
      "epoch": 0.037009622501850484,
      "grad_norm": 1.1109699834815427,
      "learning_rate": 7.352941176470589e-06,
      "loss": 0.9684,
      "step": 25
    },
    {
      "epoch": 0.04441154700222058,
      "grad_norm": 0.9463420086714082,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.9217,
      "step": 30
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 0.7526598257379206,
      "learning_rate": 1.0294117647058823e-05,
      "loss": 0.8859,
      "step": 35
    },
    {
      "epoch": 0.05921539600296077,
      "grad_norm": 0.6789903099544737,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.8631,
      "step": 40
    },
    {
      "epoch": 0.06661732050333087,
      "grad_norm": 0.7365159287878734,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.8487,
      "step": 45
    },
    {
      "epoch": 0.07401924500370097,
      "grad_norm": 0.8042938213713893,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 0.861,
      "step": 50
    },
    {
      "epoch": 0.08142116950407106,
      "grad_norm": 0.6165613278255507,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.8545,
      "step": 55
    },
    {
      "epoch": 0.08882309400444116,
      "grad_norm": 0.7210736075544439,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8293,
      "step": 60
    },
    {
      "epoch": 0.09622501850481126,
      "grad_norm": 0.6666914117441736,
      "learning_rate": 1.911764705882353e-05,
      "loss": 0.8258,
      "step": 65
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 0.7516529208544338,
      "learning_rate": 1.9999464266898485e-05,
      "loss": 0.8209,
      "step": 70
    },
    {
      "epoch": 0.11102886750555144,
      "grad_norm": 0.9295745950078508,
      "learning_rate": 1.9993437928712977e-05,
      "loss": 0.8163,
      "step": 75
    },
    {
      "epoch": 0.11843079200592153,
      "grad_norm": 0.7963544491349841,
      "learning_rate": 1.998071963486563e-05,
      "loss": 0.806,
      "step": 80
    },
    {
      "epoch": 0.12583271650629163,
      "grad_norm": 0.6518245421854616,
      "learning_rate": 1.9961317901970953e-05,
      "loss": 0.7944,
      "step": 85
    },
    {
      "epoch": 0.13323464100666174,
      "grad_norm": 0.7301619917942446,
      "learning_rate": 1.993524572210807e-05,
      "loss": 0.7945,
      "step": 90
    },
    {
      "epoch": 0.14063656550703182,
      "grad_norm": 0.7939833726588112,
      "learning_rate": 1.990252055412077e-05,
      "loss": 0.7905,
      "step": 95
    },
    {
      "epoch": 0.14803849000740193,
      "grad_norm": 0.7581792486406171,
      "learning_rate": 1.9863164311926433e-05,
      "loss": 0.8172,
      "step": 100
    },
    {
      "epoch": 0.14803849000740193,
      "eval_loss": 0.8196660876274109,
      "eval_runtime": 3.1366,
      "eval_samples_per_second": 40.809,
      "eval_steps_per_second": 5.101,
      "step": 100
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 0.7016968966754382,
      "learning_rate": 1.981720334984174e-05,
      "loss": 0.7921,
      "step": 105
    },
    {
      "epoch": 0.16284233900814213,
      "grad_norm": 0.6900772941844979,
      "learning_rate": 1.9764668444934853e-05,
      "loss": 0.7859,
      "step": 110
    },
    {
      "epoch": 0.1702442635085122,
      "grad_norm": 0.7157070191788967,
      "learning_rate": 1.970559477641606e-05,
      "loss": 0.7632,
      "step": 115
    },
    {
      "epoch": 0.17764618800888232,
      "grad_norm": 0.712102923863696,
      "learning_rate": 1.9640021902080523e-05,
      "loss": 0.7929,
      "step": 120
    },
    {
      "epoch": 0.1850481125092524,
      "grad_norm": 0.6157872973388774,
      "learning_rate": 1.9567993731818988e-05,
      "loss": 0.7917,
      "step": 125
    },
    {
      "epoch": 0.19245003700962252,
      "grad_norm": 0.7204939438541231,
      "learning_rate": 1.9489558498214197e-05,
      "loss": 0.7841,
      "step": 130
    },
    {
      "epoch": 0.1998519615099926,
      "grad_norm": 0.6377400481525809,
      "learning_rate": 1.9404768724242667e-05,
      "loss": 0.7703,
      "step": 135
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 0.7051032220059237,
      "learning_rate": 1.931368118810346e-05,
      "loss": 0.7946,
      "step": 140
    },
    {
      "epoch": 0.2146558105107328,
      "grad_norm": 0.7323582491272024,
      "learning_rate": 1.92163568851975e-05,
      "loss": 0.7758,
      "step": 145
    },
    {
      "epoch": 0.22205773501110287,
      "grad_norm": 0.756759073944075,
      "learning_rate": 1.911286098728296e-05,
      "loss": 0.7719,
      "step": 150
    },
    {
      "epoch": 0.22945965951147299,
      "grad_norm": 0.6865799388160192,
      "learning_rate": 1.900326279883392e-05,
      "loss": 0.8015,
      "step": 155
    },
    {
      "epoch": 0.23686158401184307,
      "grad_norm": 0.6847504220269061,
      "learning_rate": 1.8887635710631716e-05,
      "loss": 0.8043,
      "step": 160
    },
    {
      "epoch": 0.24426350851221318,
      "grad_norm": 0.6700839600945346,
      "learning_rate": 1.8766057150619865e-05,
      "loss": 0.7775,
      "step": 165
    },
    {
      "epoch": 0.25166543301258326,
      "grad_norm": 0.6680950835148527,
      "learning_rate": 1.8638608532055635e-05,
      "loss": 0.7947,
      "step": 170
    },
    {
      "epoch": 0.25906735751295334,
      "grad_norm": 0.6402750693582475,
      "learning_rate": 1.8505375198992856e-05,
      "loss": 0.7829,
      "step": 175
    },
    {
      "epoch": 0.2664692820133235,
      "grad_norm": 0.6939213711416119,
      "learning_rate": 1.836644636913258e-05,
      "loss": 0.754,
      "step": 180
    },
    {
      "epoch": 0.27387120651369357,
      "grad_norm": 0.7356761514310879,
      "learning_rate": 1.8221915074079764e-05,
      "loss": 0.7777,
      "step": 185
    },
    {
      "epoch": 0.28127313101406365,
      "grad_norm": 0.802978821551516,
      "learning_rate": 1.8071878097046064e-05,
      "loss": 0.7563,
      "step": 190
    },
    {
      "epoch": 0.28867505551443373,
      "grad_norm": 0.6184097232596234,
      "learning_rate": 1.7916435908040413e-05,
      "loss": 0.7724,
      "step": 195
    },
    {
      "epoch": 0.29607698001480387,
      "grad_norm": 0.6385164678688181,
      "learning_rate": 1.7755692596590778e-05,
      "loss": 0.7745,
      "step": 200
    },
    {
      "epoch": 0.29607698001480387,
      "eval_loss": 0.789804220199585,
      "eval_runtime": 3.1175,
      "eval_samples_per_second": 41.059,
      "eval_steps_per_second": 5.132,
      "step": 200
    },
    {
      "epoch": 0.30347890451517395,
      "grad_norm": 0.6691522805213952,
      "learning_rate": 1.7589755802042188e-05,
      "loss": 0.7729,
      "step": 205
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 0.6636501965912796,
      "learning_rate": 1.7418736641477636e-05,
      "loss": 0.7561,
      "step": 210
    },
    {
      "epoch": 0.3182827535159141,
      "grad_norm": 0.611145630788428,
      "learning_rate": 1.7242749635310222e-05,
      "loss": 0.758,
      "step": 215
    },
    {
      "epoch": 0.32568467801628426,
      "grad_norm": 0.6305855837605814,
      "learning_rate": 1.7061912630596252e-05,
      "loss": 0.7603,
      "step": 220
    },
    {
      "epoch": 0.33308660251665434,
      "grad_norm": 0.7090046779427459,
      "learning_rate": 1.6876346722120747e-05,
      "loss": 0.7751,
      "step": 225
    },
    {
      "epoch": 0.3404885270170244,
      "grad_norm": 0.6532776336382563,
      "learning_rate": 1.6686176171308125e-05,
      "loss": 0.7977,
      "step": 230
    },
    {
      "epoch": 0.3478904515173945,
      "grad_norm": 0.6472281999169955,
      "learning_rate": 1.6491528323012412e-05,
      "loss": 0.7594,
      "step": 235
    },
    {
      "epoch": 0.35529237601776464,
      "grad_norm": 0.6244474985256501,
      "learning_rate": 1.6292533520242663e-05,
      "loss": 0.7623,
      "step": 240
    },
    {
      "epoch": 0.3626943005181347,
      "grad_norm": 0.617771152272651,
      "learning_rate": 1.6089325016880737e-05,
      "loss": 0.7526,
      "step": 245
    },
    {
      "epoch": 0.3700962250185048,
      "grad_norm": 0.662731194922601,
      "learning_rate": 1.588203888844982e-05,
      "loss": 0.768,
      "step": 250
    },
    {
      "epoch": 0.3774981495188749,
      "grad_norm": 0.6103795212497318,
      "learning_rate": 1.5670813940993504e-05,
      "loss": 0.7409,
      "step": 255
    },
    {
      "epoch": 0.38490007401924503,
      "grad_norm": 0.5749536608079369,
      "learning_rate": 1.5455791618126407e-05,
      "loss": 0.7332,
      "step": 260
    },
    {
      "epoch": 0.3923019985196151,
      "grad_norm": 0.602251187466067,
      "learning_rate": 1.5237115906318565e-05,
      "loss": 0.7571,
      "step": 265
    },
    {
      "epoch": 0.3997039230199852,
      "grad_norm": 0.6415472326761182,
      "learning_rate": 1.5014933238477069e-05,
      "loss": 0.7378,
      "step": 270
    },
    {
      "epoch": 0.4071058475203553,
      "grad_norm": 0.659239039689651,
      "learning_rate": 1.4789392395889468e-05,
      "loss": 0.7631,
      "step": 275
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 0.6281187227003566,
      "learning_rate": 1.4560644408594602e-05,
      "loss": 0.744,
      "step": 280
    },
    {
      "epoch": 0.4219096965210955,
      "grad_norm": 0.6384180417923108,
      "learning_rate": 1.432884245424761e-05,
      "loss": 0.7556,
      "step": 285
    },
    {
      "epoch": 0.4293116210214656,
      "grad_norm": 0.6391130592098728,
      "learning_rate": 1.4094141755546816e-05,
      "loss": 0.7831,
      "step": 290
    },
    {
      "epoch": 0.43671354552183567,
      "grad_norm": 0.6054256423919505,
      "learning_rate": 1.3856699476291176e-05,
      "loss": 0.7426,
      "step": 295
    },
    {
      "epoch": 0.44411547002220575,
      "grad_norm": 0.6630675705036657,
      "learning_rate": 1.3616674616137902e-05,
      "loss": 0.7643,
      "step": 300
    },
    {
      "epoch": 0.44411547002220575,
      "eval_loss": 0.7754666805267334,
      "eval_runtime": 3.1148,
      "eval_samples_per_second": 41.094,
      "eval_steps_per_second": 5.137,
      "step": 300
    },
    {
      "epoch": 0.4515173945225759,
      "grad_norm": 0.6288014510844427,
      "learning_rate": 1.3374227904130724e-05,
      "loss": 0.7547,
      "step": 305
    },
    {
      "epoch": 0.45891931902294597,
      "grad_norm": 0.6217403326546215,
      "learning_rate": 1.3129521691070108e-05,
      "loss": 0.7326,
      "step": 310
    },
    {
      "epoch": 0.46632124352331605,
      "grad_norm": 0.6800329210502148,
      "learning_rate": 1.2882719840797473e-05,
      "loss": 0.7511,
      "step": 315
    },
    {
      "epoch": 0.47372316802368614,
      "grad_norm": 0.6592173647356895,
      "learning_rate": 1.2633987620466229e-05,
      "loss": 0.7353,
      "step": 320
    },
    {
      "epoch": 0.4811250925240563,
      "grad_norm": 0.61539180630925,
      "learning_rate": 1.2383491589873122e-05,
      "loss": 0.7404,
      "step": 325
    },
    {
      "epoch": 0.48852701702442636,
      "grad_norm": 0.5886471962514216,
      "learning_rate": 1.213139948992394e-05,
      "loss": 0.7497,
      "step": 330
    },
    {
      "epoch": 0.49592894152479644,
      "grad_norm": 0.6761058710511431,
      "learning_rate": 1.187788013030837e-05,
      "loss": 0.7466,
      "step": 335
    },
    {
      "epoch": 0.5033308660251665,
      "grad_norm": 0.5915448374095998,
      "learning_rate": 1.1623103276459086e-05,
      "loss": 0.7505,
      "step": 340
    },
    {
      "epoch": 0.5107327905255367,
      "grad_norm": 0.613959957668376,
      "learning_rate": 1.1367239535870913e-05,
      "loss": 0.7424,
      "step": 345
    },
    {
      "epoch": 0.5181347150259067,
      "grad_norm": 0.6605036359255322,
      "learning_rate": 1.1110460243856051e-05,
      "loss": 0.73,
      "step": 350
    },
    {
      "epoch": 0.5255366395262768,
      "grad_norm": 0.6398359412241029,
      "learning_rate": 1.085293734881197e-05,
      "loss": 0.7466,
      "step": 355
    },
    {
      "epoch": 0.532938564026647,
      "grad_norm": 0.5798477551421798,
      "learning_rate": 1.0594843297078736e-05,
      "loss": 0.7658,
      "step": 360
    },
    {
      "epoch": 0.540340488527017,
      "grad_norm": 0.6712170318895565,
      "learning_rate": 1.0336350917462925e-05,
      "loss": 0.7557,
      "step": 365
    },
    {
      "epoch": 0.5477424130273871,
      "grad_norm": 0.5826431750982008,
      "learning_rate": 1.0077633305505402e-05,
      "loss": 0.7431,
      "step": 370
    },
    {
      "epoch": 0.5551443375277573,
      "grad_norm": 0.6066723768251325,
      "learning_rate": 9.818863707570476e-06,
      "loss": 0.7606,
      "step": 375
    },
    {
      "epoch": 0.5625462620281273,
      "grad_norm": 0.6314411822904215,
      "learning_rate": 9.560215404834094e-06,
      "loss": 0.7513,
      "step": 380
    },
    {
      "epoch": 0.5699481865284974,
      "grad_norm": 0.6118960640467581,
      "learning_rate": 9.30186159724869e-06,
      "loss": 0.7143,
      "step": 385
    },
    {
      "epoch": 0.5773501110288675,
      "grad_norm": 0.5791113121477641,
      "learning_rate": 9.043975287562443e-06,
      "loss": 0.7468,
      "step": 390
    },
    {
      "epoch": 0.5847520355292376,
      "grad_norm": 0.6539665929663285,
      "learning_rate": 8.786729165470584e-06,
      "loss": 0.7252,
      "step": 395
    },
    {
      "epoch": 0.5921539600296077,
      "grad_norm": 0.6570821598447145,
      "learning_rate": 8.530295491976338e-06,
      "loss": 0.7306,
      "step": 400
    },
    {
      "epoch": 0.5921539600296077,
      "eval_loss": 0.7634406089782715,
      "eval_runtime": 3.1189,
      "eval_samples_per_second": 41.04,
      "eval_steps_per_second": 5.13,
      "step": 400
    },
    {
      "epoch": 0.5995558845299778,
      "grad_norm": 0.5746384557086938,
      "learning_rate": 8.274845984038916e-06,
      "loss": 0.7172,
      "step": 405
    },
    {
      "epoch": 0.6069578090303479,
      "grad_norm": 0.6320655117299494,
      "learning_rate": 8.020551699585843e-06,
      "loss": 0.7466,
      "step": 410
    },
    {
      "epoch": 0.6143597335307179,
      "grad_norm": 0.5898386214469216,
      "learning_rate": 7.76758292296659e-06,
      "loss": 0.7263,
      "step": 415
    },
    {
      "epoch": 0.6217616580310881,
      "grad_norm": 0.6220035683197175,
      "learning_rate": 7.5161090509242005e-06,
      "loss": 0.7416,
      "step": 420
    },
    {
      "epoch": 0.6291635825314582,
      "grad_norm": 0.6329578494406625,
      "learning_rate": 7.2662984791613186e-06,
      "loss": 0.7342,
      "step": 425
    },
    {
      "epoch": 0.6365655070318282,
      "grad_norm": 0.6311281483111099,
      "learning_rate": 7.01831848957653e-06,
      "loss": 0.7487,
      "step": 430
    },
    {
      "epoch": 0.6439674315321984,
      "grad_norm": 0.5769698545850361,
      "learning_rate": 6.772335138246548e-06,
      "loss": 0.7468,
      "step": 435
    },
    {
      "epoch": 0.6513693560325685,
      "grad_norm": 0.6102214233524648,
      "learning_rate": 6.528513144229256e-06,
      "loss": 0.7426,
      "step": 440
    },
    {
      "epoch": 0.6587712805329385,
      "grad_norm": 0.5989944660076076,
      "learning_rate": 6.287015779262064e-06,
      "loss": 0.7487,
      "step": 445
    },
    {
      "epoch": 0.6661732050333087,
      "grad_norm": 0.6314411792160693,
      "learning_rate": 6.048004758429451e-06,
      "loss": 0.7272,
      "step": 450
    },
    {
      "epoch": 0.6735751295336787,
      "grad_norm": 0.5870201642987204,
      "learning_rate": 5.811640131872867e-06,
      "loss": 0.7496,
      "step": 455
    },
    {
      "epoch": 0.6809770540340488,
      "grad_norm": 0.5903691127260594,
      "learning_rate": 5.578080177615575e-06,
      "loss": 0.72,
      "step": 460
    },
    {
      "epoch": 0.688378978534419,
      "grad_norm": 0.6012396431395267,
      "learning_rate": 5.347481295574141e-06,
      "loss": 0.7169,
      "step": 465
    },
    {
      "epoch": 0.695780903034789,
      "grad_norm": 0.5964212989584798,
      "learning_rate": 5.119997902827584e-06,
      "loss": 0.7285,
      "step": 470
    },
    {
      "epoch": 0.7031828275351591,
      "grad_norm": 0.583131600111171,
      "learning_rate": 4.8957823302142916e-06,
      "loss": 0.7352,
      "step": 475
    },
    {
      "epoch": 0.7105847520355293,
      "grad_norm": 0.6015054612003533,
      "learning_rate": 4.674984720325961e-06,
      "loss": 0.7207,
      "step": 480
    },
    {
      "epoch": 0.7179866765358993,
      "grad_norm": 0.572136571323486,
      "learning_rate": 4.457752926966888e-06,
      "loss": 0.7148,
      "step": 485
    },
    {
      "epoch": 0.7253886010362695,
      "grad_norm": 0.56847509551642,
      "learning_rate": 4.244232416145839e-06,
      "loss": 0.7336,
      "step": 490
    },
    {
      "epoch": 0.7327905255366395,
      "grad_norm": 0.5757906808389407,
      "learning_rate": 4.0345661686669745e-06,
      "loss": 0.7268,
      "step": 495
    },
    {
      "epoch": 0.7401924500370096,
      "grad_norm": 0.5983359707263747,
      "learning_rate": 3.828894584384867e-06,
      "loss": 0.7354,
      "step": 500
    },
    {
      "epoch": 0.7401924500370096,
      "eval_loss": 0.7560299634933472,
      "eval_runtime": 3.1145,
      "eval_samples_per_second": 41.098,
      "eval_steps_per_second": 5.137,
      "step": 500
    },
    {
      "epoch": 0.7475943745373798,
      "grad_norm": 0.5419364484450241,
      "learning_rate": 3.62735538818787e-06,
      "loss": 0.7197,
      "step": 505
    },
    {
      "epoch": 0.7549962990377498,
      "grad_norm": 0.6155819372126309,
      "learning_rate": 3.4300835377726904e-06,
      "loss": 0.7231,
      "step": 510
    },
    {
      "epoch": 0.7623982235381199,
      "grad_norm": 0.5981808223491859,
      "learning_rate": 3.2372111332720045e-06,
      "loss": 0.7586,
      "step": 515
    },
    {
      "epoch": 0.7698001480384901,
      "grad_norm": 0.595017563636788,
      "learning_rate": 3.048867328795588e-06,
      "loss": 0.7155,
      "step": 520
    },
    {
      "epoch": 0.7772020725388601,
      "grad_norm": 0.5884490157915484,
      "learning_rate": 2.865178245944218e-06,
      "loss": 0.7143,
      "step": 525
    },
    {
      "epoch": 0.7846039970392302,
      "grad_norm": 0.5544892806408136,
      "learning_rate": 2.686266889354211e-06,
      "loss": 0.7373,
      "step": 530
    },
    {
      "epoch": 0.7920059215396003,
      "grad_norm": 0.5749123573168023,
      "learning_rate": 2.5122530643292274e-06,
      "loss": 0.7427,
      "step": 535
    },
    {
      "epoch": 0.7994078460399704,
      "grad_norm": 0.6154627187110704,
      "learning_rate": 2.3432532966144526e-06,
      "loss": 0.7322,
      "step": 540
    },
    {
      "epoch": 0.8068097705403405,
      "grad_norm": 0.5733911384614117,
      "learning_rate": 2.1793807543668857e-06,
      "loss": 0.7339,
      "step": 545
    },
    {
      "epoch": 0.8142116950407106,
      "grad_norm": 0.5381154079459709,
      "learning_rate": 2.0207451723739633e-06,
      "loss": 0.7257,
      "step": 550
    },
    {
      "epoch": 0.8216136195410807,
      "grad_norm": 0.5433117693556794,
      "learning_rate": 1.8674527785713247e-06,
      "loss": 0.7322,
      "step": 555
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 0.595956230708808,
      "learning_rate": 1.7196062229088606e-06,
      "loss": 0.6995,
      "step": 560
    },
    {
      "epoch": 0.8364174685418209,
      "grad_norm": 0.6085342637714587,
      "learning_rate": 1.577304508612717e-06,
      "loss": 0.7297,
      "step": 565
    },
    {
      "epoch": 0.843819393042191,
      "grad_norm": 0.5074631477260008,
      "learning_rate": 1.4406429258892762e-06,
      "loss": 0.7501,
      "step": 570
    },
    {
      "epoch": 0.851221317542561,
      "grad_norm": 0.5995398947896622,
      "learning_rate": 1.3097129881154936e-06,
      "loss": 0.7198,
      "step": 575
    },
    {
      "epoch": 0.8586232420429312,
      "grad_norm": 0.5695360882732575,
      "learning_rate": 1.1846023705583442e-06,
      "loss": 0.7162,
      "step": 580
    },
    {
      "epoch": 0.8660251665433013,
      "grad_norm": 0.5623090258953476,
      "learning_rate": 1.065394851664394e-06,
      "loss": 0.7343,
      "step": 585
    },
    {
      "epoch": 0.8734270910436713,
      "grad_norm": 0.5332283600389667,
      "learning_rate": 9.521702569588199e-07,
      "loss": 0.7534,
      "step": 590
    },
    {
      "epoch": 0.8808290155440415,
      "grad_norm": 0.5633894812870882,
      "learning_rate": 8.450044055914497e-07,
      "loss": 0.7219,
      "step": 595
    },
    {
      "epoch": 0.8882309400444115,
      "grad_norm": 0.5436178972328131,
      "learning_rate": 7.439690595656013e-07,
      "loss": 0.7444,
      "step": 600
    },
    {
      "epoch": 0.8882309400444115,
      "eval_loss": 0.753079891204834,
      "eval_runtime": 3.1158,
      "eval_samples_per_second": 41.081,
      "eval_steps_per_second": 5.135,
      "step": 600
    },
    {
      "epoch": 0.8956328645447816,
      "grad_norm": 0.6195975140382083,
      "learning_rate": 6.491318756837417e-07,
      "loss": 0.7298,
      "step": 605
    },
    {
      "epoch": 0.9030347890451518,
      "grad_norm": 0.5006646668310524,
      "learning_rate": 5.605563602421149e-07,
      "loss": 0.7057,
      "step": 610
    },
    {
      "epoch": 0.9104367135455218,
      "grad_norm": 0.5419782192826523,
      "learning_rate": 4.783018265047179e-07,
      "loss": 0.7555,
      "step": 615
    },
    {
      "epoch": 0.9178386380458919,
      "grad_norm": 0.5640257061503108,
      "learning_rate": 4.024233549850509e-07,
      "loss": 0.7435,
      "step": 620
    },
    {
      "epoch": 0.9252405625462621,
      "grad_norm": 0.5379715425608906,
      "learning_rate": 3.329717565622825e-07,
      "loss": 0.7403,
      "step": 625
    },
    {
      "epoch": 0.9326424870466321,
      "grad_norm": 0.5381235622677996,
      "learning_rate": 2.6999353845651113e-07,
      "loss": 0.724,
      "step": 630
    },
    {
      "epoch": 0.9400444115470022,
      "grad_norm": 0.5712874960471778,
      "learning_rate": 2.1353087308590314e-07,
      "loss": 0.7389,
      "step": 635
    },
    {
      "epoch": 0.9474463360473723,
      "grad_norm": 0.5442876768823635,
      "learning_rate": 1.6362156982656085e-07,
      "loss": 0.729,
      "step": 640
    },
    {
      "epoch": 0.9548482605477424,
      "grad_norm": 0.5108903031358344,
      "learning_rate": 1.2029904969404482e-07,
      "loss": 0.7124,
      "step": 645
    },
    {
      "epoch": 0.9622501850481125,
      "grad_norm": 0.5895082578648588,
      "learning_rate": 8.359232296349163e-08,
      "loss": 0.7163,
      "step": 650
    },
    {
      "epoch": 0.9696521095484826,
      "grad_norm": 0.5546776379603184,
      "learning_rate": 5.3525969743324356e-08,
      "loss": 0.732,
      "step": 655
    },
    {
      "epoch": 0.9770540340488527,
      "grad_norm": 0.5289857496809237,
      "learning_rate": 3.012012351554017e-08,
      "loss": 0.7063,
      "step": 660
    },
    {
      "epoch": 0.9844559585492227,
      "grad_norm": 0.5751846330162846,
      "learning_rate": 1.3390457653639221e-08,
      "loss": 0.7351,
      "step": 665
    },
    {
      "epoch": 0.9918578830495929,
      "grad_norm": 0.6323603287547246,
      "learning_rate": 3.3481749271768726e-09,
      "loss": 0.746,
      "step": 670
    },
    {
      "epoch": 0.999259807549963,
      "grad_norm": 0.5546360557881977,
      "learning_rate": 0.0,
      "loss": 0.7157,
      "step": 675
    },
    {
      "epoch": 0.999259807549963,
      "step": 675,
      "total_flos": 76888336760832.0,
      "train_loss": 0.7674887858496772,
      "train_runtime": 1975.5352,
      "train_samples_per_second": 10.939,
      "train_steps_per_second": 0.342
    }
  ],
  "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
}