{
  "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": 2.794903997125339,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 1.1994,
      "step": 5
    },
    {
      "epoch": 0.014803849000740192,
      "grad_norm": 2.2899213548596,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.1698,
      "step": 10
    },
    {
      "epoch": 0.02220577350111029,
      "grad_norm": 1.6638315051215307,
      "learning_rate": 4.411764705882353e-06,
      "loss": 1.1745,
      "step": 15
    },
    {
      "epoch": 0.029607698001480384,
      "grad_norm": 1.3701468978662918,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.0642,
      "step": 20
    },
    {
      "epoch": 0.037009622501850484,
      "grad_norm": 1.2683654885984532,
      "learning_rate": 7.352941176470589e-06,
      "loss": 1.0177,
      "step": 25
    },
    {
      "epoch": 0.04441154700222058,
      "grad_norm": 0.8617431967779211,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.967,
      "step": 30
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 0.7961453971337379,
      "learning_rate": 1.0294117647058823e-05,
      "loss": 0.9571,
      "step": 35
    },
    {
      "epoch": 0.05921539600296077,
      "grad_norm": 0.783030655349695,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.9246,
      "step": 40
    },
    {
      "epoch": 0.06661732050333087,
      "grad_norm": 0.6906045906755041,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.9103,
      "step": 45
    },
    {
      "epoch": 0.07401924500370097,
      "grad_norm": 0.7040438295908158,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 0.9017,
      "step": 50
    },
    {
      "epoch": 0.08142116950407106,
      "grad_norm": 0.7077475845069939,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.872,
      "step": 55
    },
    {
      "epoch": 0.08882309400444116,
      "grad_norm": 0.7211343192963949,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8708,
      "step": 60
    },
    {
      "epoch": 0.09622501850481126,
      "grad_norm": 0.6514457332458641,
      "learning_rate": 1.911764705882353e-05,
      "loss": 0.8929,
      "step": 65
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 0.7270264866162934,
      "learning_rate": 1.9999464266898485e-05,
      "loss": 0.8485,
      "step": 70
    },
    {
      "epoch": 0.11102886750555144,
      "grad_norm": 0.7177646162807655,
      "learning_rate": 1.9993437928712977e-05,
      "loss": 0.8673,
      "step": 75
    },
    {
      "epoch": 0.11843079200592153,
      "grad_norm": 0.864667079189985,
      "learning_rate": 1.998071963486563e-05,
      "loss": 0.875,
      "step": 80
    },
    {
      "epoch": 0.12583271650629163,
      "grad_norm": 0.8425997105878871,
      "learning_rate": 1.9961317901970953e-05,
      "loss": 0.8684,
      "step": 85
    },
    {
      "epoch": 0.13323464100666174,
      "grad_norm": 0.75689462451379,
      "learning_rate": 1.993524572210807e-05,
      "loss": 0.85,
      "step": 90
    },
    {
      "epoch": 0.14063656550703182,
      "grad_norm": 0.7945372383993669,
      "learning_rate": 1.990252055412077e-05,
      "loss": 0.8433,
      "step": 95
    },
    {
      "epoch": 0.14803849000740193,
      "grad_norm": 0.7156329414658931,
      "learning_rate": 1.9863164311926433e-05,
      "loss": 0.8508,
      "step": 100
    },
    {
      "epoch": 0.14803849000740193,
      "eval_loss": 0.8746742606163025,
      "eval_runtime": 3.4514,
      "eval_samples_per_second": 74.173,
      "eval_steps_per_second": 4.636,
      "step": 100
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 0.640639552176462,
      "learning_rate": 1.981720334984174e-05,
      "loss": 0.8298,
      "step": 105
    },
    {
      "epoch": 0.16284233900814213,
      "grad_norm": 0.724211584253385,
      "learning_rate": 1.9764668444934853e-05,
      "loss": 0.8431,
      "step": 110
    },
    {
      "epoch": 0.1702442635085122,
      "grad_norm": 0.6791286598449765,
      "learning_rate": 1.970559477641606e-05,
      "loss": 0.836,
      "step": 115
    },
    {
      "epoch": 0.17764618800888232,
      "grad_norm": 0.743979705476657,
      "learning_rate": 1.9640021902080523e-05,
      "loss": 0.8323,
      "step": 120
    },
    {
      "epoch": 0.1850481125092524,
      "grad_norm": 0.7119935575187614,
      "learning_rate": 1.9567993731818988e-05,
      "loss": 0.8384,
      "step": 125
    },
    {
      "epoch": 0.19245003700962252,
      "grad_norm": 0.7793010780788937,
      "learning_rate": 1.9489558498214197e-05,
      "loss": 0.8296,
      "step": 130
    },
    {
      "epoch": 0.1998519615099926,
      "grad_norm": 0.7142208149833662,
      "learning_rate": 1.9404768724242667e-05,
      "loss": 0.8326,
      "step": 135
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 0.6507055675164792,
      "learning_rate": 1.931368118810346e-05,
      "loss": 0.8511,
      "step": 140
    },
    {
      "epoch": 0.2146558105107328,
      "grad_norm": 0.7743951408818872,
      "learning_rate": 1.92163568851975e-05,
      "loss": 0.8389,
      "step": 145
    },
    {
      "epoch": 0.22205773501110287,
      "grad_norm": 0.7141832452825222,
      "learning_rate": 1.911286098728296e-05,
      "loss": 0.8376,
      "step": 150
    },
    {
      "epoch": 0.22945965951147299,
      "grad_norm": 0.7172125462795979,
      "learning_rate": 1.900326279883392e-05,
      "loss": 0.8477,
      "step": 155
    },
    {
      "epoch": 0.23686158401184307,
      "grad_norm": 0.7117382748092328,
      "learning_rate": 1.8887635710631716e-05,
      "loss": 0.822,
      "step": 160
    },
    {
      "epoch": 0.24426350851221318,
      "grad_norm": 0.6915893219358582,
      "learning_rate": 1.8766057150619865e-05,
      "loss": 0.83,
      "step": 165
    },
    {
      "epoch": 0.25166543301258326,
      "grad_norm": 0.7275088377525234,
      "learning_rate": 1.8638608532055635e-05,
      "loss": 0.8319,
      "step": 170
    },
    {
      "epoch": 0.25906735751295334,
      "grad_norm": 0.6792315451082475,
      "learning_rate": 1.8505375198992856e-05,
      "loss": 0.8096,
      "step": 175
    },
    {
      "epoch": 0.2664692820133235,
      "grad_norm": 0.6603768149658193,
      "learning_rate": 1.836644636913258e-05,
      "loss": 0.8107,
      "step": 180
    },
    {
      "epoch": 0.27387120651369357,
      "grad_norm": 0.7906151827614104,
      "learning_rate": 1.8221915074079764e-05,
      "loss": 0.8327,
      "step": 185
    },
    {
      "epoch": 0.28127313101406365,
      "grad_norm": 0.7214051132119957,
      "learning_rate": 1.8071878097046064e-05,
      "loss": 0.8193,
      "step": 190
    },
    {
      "epoch": 0.28867505551443373,
      "grad_norm": 0.6903003064716787,
      "learning_rate": 1.7916435908040413e-05,
      "loss": 0.8147,
      "step": 195
    },
    {
      "epoch": 0.29607698001480387,
      "grad_norm": 0.7652624704605868,
      "learning_rate": 1.7755692596590778e-05,
      "loss": 0.8062,
      "step": 200
    },
    {
      "epoch": 0.29607698001480387,
      "eval_loss": 0.8443604707717896,
      "eval_runtime": 3.4526,
      "eval_samples_per_second": 74.148,
      "eval_steps_per_second": 4.634,
      "step": 200
    },
    {
      "epoch": 0.30347890451517395,
      "grad_norm": 0.7493476210094535,
      "learning_rate": 1.7589755802042188e-05,
      "loss": 0.8216,
      "step": 205
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 0.6940637251912045,
      "learning_rate": 1.7418736641477636e-05,
      "loss": 0.8431,
      "step": 210
    },
    {
      "epoch": 0.3182827535159141,
      "grad_norm": 0.6773196644452423,
      "learning_rate": 1.7242749635310222e-05,
      "loss": 0.8151,
      "step": 215
    },
    {
      "epoch": 0.32568467801628426,
      "grad_norm": 0.6862706043257215,
      "learning_rate": 1.7061912630596252e-05,
      "loss": 0.8012,
      "step": 220
    },
    {
      "epoch": 0.33308660251665434,
      "grad_norm": 0.7150683038312725,
      "learning_rate": 1.6876346722120747e-05,
      "loss": 0.7966,
      "step": 225
    },
    {
      "epoch": 0.3404885270170244,
      "grad_norm": 0.6726897716030948,
      "learning_rate": 1.6686176171308125e-05,
      "loss": 0.8191,
      "step": 230
    },
    {
      "epoch": 0.3478904515173945,
      "grad_norm": 0.7020523061571385,
      "learning_rate": 1.6491528323012412e-05,
      "loss": 0.8163,
      "step": 235
    },
    {
      "epoch": 0.35529237601776464,
      "grad_norm": 0.798121494860887,
      "learning_rate": 1.6292533520242663e-05,
      "loss": 0.825,
      "step": 240
    },
    {
      "epoch": 0.3626943005181347,
      "grad_norm": 0.6867454070632956,
      "learning_rate": 1.6089325016880737e-05,
      "loss": 0.8119,
      "step": 245
    },
    {
      "epoch": 0.3700962250185048,
      "grad_norm": 0.6968202812261177,
      "learning_rate": 1.588203888844982e-05,
      "loss": 0.827,
      "step": 250
    },
    {
      "epoch": 0.3774981495188749,
      "grad_norm": 0.6958678869528214,
      "learning_rate": 1.5670813940993504e-05,
      "loss": 0.8096,
      "step": 255
    },
    {
      "epoch": 0.38490007401924503,
      "grad_norm": 0.7336646935799767,
      "learning_rate": 1.5455791618126407e-05,
      "loss": 0.8129,
      "step": 260
    },
    {
      "epoch": 0.3923019985196151,
      "grad_norm": 0.7712789154763156,
      "learning_rate": 1.5237115906318565e-05,
      "loss": 0.7941,
      "step": 265
    },
    {
      "epoch": 0.3997039230199852,
      "grad_norm": 0.6617684914457387,
      "learning_rate": 1.5014933238477069e-05,
      "loss": 0.7918,
      "step": 270
    },
    {
      "epoch": 0.4071058475203553,
      "grad_norm": 0.7111113848439705,
      "learning_rate": 1.4789392395889468e-05,
      "loss": 0.8001,
      "step": 275
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 0.6735120909936372,
      "learning_rate": 1.4560644408594602e-05,
      "loss": 0.7947,
      "step": 280
    },
    {
      "epoch": 0.4219096965210955,
      "grad_norm": 0.6598824739980695,
      "learning_rate": 1.432884245424761e-05,
      "loss": 0.7868,
      "step": 285
    },
    {
      "epoch": 0.4293116210214656,
      "grad_norm": 0.7241624466216231,
      "learning_rate": 1.4094141755546816e-05,
      "loss": 0.8076,
      "step": 290
    },
    {
      "epoch": 0.43671354552183567,
      "grad_norm": 0.6814075885350022,
      "learning_rate": 1.3856699476291176e-05,
      "loss": 0.8246,
      "step": 295
    },
    {
      "epoch": 0.44411547002220575,
      "grad_norm": 0.6831399432634763,
      "learning_rate": 1.3616674616137902e-05,
      "loss": 0.8024,
      "step": 300
    },
    {
      "epoch": 0.44411547002220575,
      "eval_loss": 0.82861328125,
      "eval_runtime": 3.4533,
      "eval_samples_per_second": 74.132,
      "eval_steps_per_second": 4.633,
      "step": 300
    },
    {
      "epoch": 0.4515173945225759,
      "grad_norm": 0.7041584873176774,
      "learning_rate": 1.3374227904130724e-05,
      "loss": 0.8068,
      "step": 305
    },
    {
      "epoch": 0.45891931902294597,
      "grad_norm": 0.6583635390083319,
      "learning_rate": 1.3129521691070108e-05,
      "loss": 0.7919,
      "step": 310
    },
    {
      "epoch": 0.46632124352331605,
      "grad_norm": 0.6516072087075866,
      "learning_rate": 1.2882719840797473e-05,
      "loss": 0.7838,
      "step": 315
    },
    {
      "epoch": 0.47372316802368614,
      "grad_norm": 0.672299943937887,
      "learning_rate": 1.2633987620466229e-05,
      "loss": 0.7974,
      "step": 320
    },
    {
      "epoch": 0.4811250925240563,
      "grad_norm": 0.6686495070852051,
      "learning_rate": 1.2383491589873122e-05,
      "loss": 0.7966,
      "step": 325
    },
    {
      "epoch": 0.48852701702442636,
      "grad_norm": 0.6771991281963923,
      "learning_rate": 1.213139948992394e-05,
      "loss": 0.7731,
      "step": 330
    },
    {
      "epoch": 0.49592894152479644,
      "grad_norm": 0.6350329323569988,
      "learning_rate": 1.187788013030837e-05,
      "loss": 0.7967,
      "step": 335
    },
    {
      "epoch": 0.5033308660251665,
      "grad_norm": 0.6692457889055545,
      "learning_rate": 1.1623103276459086e-05,
      "loss": 0.7847,
      "step": 340
    },
    {
      "epoch": 0.5107327905255367,
      "grad_norm": 0.619877213288807,
      "learning_rate": 1.1367239535870913e-05,
      "loss": 0.7854,
      "step": 345
    },
    {
      "epoch": 0.5181347150259067,
      "grad_norm": 0.6274021978965624,
      "learning_rate": 1.1110460243856051e-05,
      "loss": 0.7971,
      "step": 350
    },
    {
      "epoch": 0.5255366395262768,
      "grad_norm": 0.579883215557642,
      "learning_rate": 1.085293734881197e-05,
      "loss": 0.7649,
      "step": 355
    },
    {
      "epoch": 0.532938564026647,
      "grad_norm": 0.580030942735355,
      "learning_rate": 1.0594843297078736e-05,
      "loss": 0.7978,
      "step": 360
    },
    {
      "epoch": 0.540340488527017,
      "grad_norm": 0.642992183348472,
      "learning_rate": 1.0336350917462925e-05,
      "loss": 0.8069,
      "step": 365
    },
    {
      "epoch": 0.5477424130273871,
      "grad_norm": 0.6553773306502982,
      "learning_rate": 1.0077633305505402e-05,
      "loss": 0.805,
      "step": 370
    },
    {
      "epoch": 0.5551443375277573,
      "grad_norm": 0.6988793873905308,
      "learning_rate": 9.818863707570476e-06,
      "loss": 0.7917,
      "step": 375
    },
    {
      "epoch": 0.5625462620281273,
      "grad_norm": 0.6089392924331548,
      "learning_rate": 9.560215404834094e-06,
      "loss": 0.7832,
      "step": 380
    },
    {
      "epoch": 0.5699481865284974,
      "grad_norm": 0.6301128789347067,
      "learning_rate": 9.30186159724869e-06,
      "loss": 0.8165,
      "step": 385
    },
    {
      "epoch": 0.5773501110288675,
      "grad_norm": 0.6131218215489028,
      "learning_rate": 9.043975287562443e-06,
      "loss": 0.7971,
      "step": 390
    },
    {
      "epoch": 0.5847520355292376,
      "grad_norm": 0.7288004589094269,
      "learning_rate": 8.786729165470584e-06,
      "loss": 0.7914,
      "step": 395
    },
    {
      "epoch": 0.5921539600296077,
      "grad_norm": 0.5950433165900502,
      "learning_rate": 8.530295491976338e-06,
      "loss": 0.8017,
      "step": 400
    },
    {
      "epoch": 0.5921539600296077,
      "eval_loss": 0.8175073862075806,
      "eval_runtime": 3.4534,
      "eval_samples_per_second": 74.131,
      "eval_steps_per_second": 4.633,
      "step": 400
    },
    {
      "epoch": 0.5995558845299778,
      "grad_norm": 0.6171980133759358,
      "learning_rate": 8.274845984038916e-06,
      "loss": 0.7773,
      "step": 405
    },
    {
      "epoch": 0.6069578090303479,
      "grad_norm": 0.5961411739983544,
      "learning_rate": 8.020551699585843e-06,
      "loss": 0.7884,
      "step": 410
    },
    {
      "epoch": 0.6143597335307179,
      "grad_norm": 0.6611605547109711,
      "learning_rate": 7.76758292296659e-06,
      "loss": 0.794,
      "step": 415
    },
    {
      "epoch": 0.6217616580310881,
      "grad_norm": 0.7084966828449921,
      "learning_rate": 7.5161090509242005e-06,
      "loss": 0.8082,
      "step": 420
    },
    {
      "epoch": 0.6291635825314582,
      "grad_norm": 0.6332099312221346,
      "learning_rate": 7.2662984791613186e-06,
      "loss": 0.7975,
      "step": 425
    },
    {
      "epoch": 0.6365655070318282,
      "grad_norm": 0.6375020624281856,
      "learning_rate": 7.01831848957653e-06,
      "loss": 0.7978,
      "step": 430
    },
    {
      "epoch": 0.6439674315321984,
      "grad_norm": 0.6809440275226949,
      "learning_rate": 6.772335138246548e-06,
      "loss": 0.8003,
      "step": 435
    },
    {
      "epoch": 0.6513693560325685,
      "grad_norm": 0.6057601832656101,
      "learning_rate": 6.528513144229256e-06,
      "loss": 0.7919,
      "step": 440
    },
    {
      "epoch": 0.6587712805329385,
      "grad_norm": 0.5899616134242256,
      "learning_rate": 6.287015779262064e-06,
      "loss": 0.782,
      "step": 445
    },
    {
      "epoch": 0.6661732050333087,
      "grad_norm": 0.6176873085432919,
      "learning_rate": 6.048004758429451e-06,
      "loss": 0.7918,
      "step": 450
    },
    {
      "epoch": 0.6735751295336787,
      "grad_norm": 0.648525215589336,
      "learning_rate": 5.811640131872867e-06,
      "loss": 0.7753,
      "step": 455
    },
    {
      "epoch": 0.6809770540340488,
      "grad_norm": 0.6086284504684217,
      "learning_rate": 5.578080177615575e-06,
      "loss": 0.7993,
      "step": 460
    },
    {
      "epoch": 0.688378978534419,
      "grad_norm": 0.5680934523620634,
      "learning_rate": 5.347481295574141e-06,
      "loss": 0.78,
      "step": 465
    },
    {
      "epoch": 0.695780903034789,
      "grad_norm": 0.61124283739532,
      "learning_rate": 5.119997902827584e-06,
      "loss": 0.7804,
      "step": 470
    },
    {
      "epoch": 0.7031828275351591,
      "grad_norm": 0.6372644600744317,
      "learning_rate": 4.8957823302142916e-06,
      "loss": 0.8032,
      "step": 475
    },
    {
      "epoch": 0.7105847520355293,
      "grad_norm": 0.6141994534169796,
      "learning_rate": 4.674984720325961e-06,
      "loss": 0.786,
      "step": 480
    },
    {
      "epoch": 0.7179866765358993,
      "grad_norm": 0.6250113156473952,
      "learning_rate": 4.457752926966888e-06,
      "loss": 0.8048,
      "step": 485
    },
    {
      "epoch": 0.7253886010362695,
      "grad_norm": 0.5910253383137196,
      "learning_rate": 4.244232416145839e-06,
      "loss": 0.7737,
      "step": 490
    },
    {
      "epoch": 0.7327905255366395,
      "grad_norm": 0.6242857113765174,
      "learning_rate": 4.0345661686669745e-06,
      "loss": 0.7838,
      "step": 495
    },
    {
      "epoch": 0.7401924500370096,
      "grad_norm": 0.6333883531751213,
      "learning_rate": 3.828894584384867e-06,
      "loss": 0.7925,
      "step": 500
    },
    {
      "epoch": 0.7401924500370096,
      "eval_loss": 0.809844434261322,
      "eval_runtime": 3.4503,
      "eval_samples_per_second": 74.197,
      "eval_steps_per_second": 4.637,
      "step": 500
    },
    {
      "epoch": 0.7475943745373798,
      "grad_norm": 0.658871736973691,
      "learning_rate": 3.62735538818787e-06,
      "loss": 0.7676,
      "step": 505
    },
    {
      "epoch": 0.7549962990377498,
      "grad_norm": 0.6057637427080839,
      "learning_rate": 3.4300835377726904e-06,
      "loss": 0.7765,
      "step": 510
    },
    {
      "epoch": 0.7623982235381199,
      "grad_norm": 0.6304036273657166,
      "learning_rate": 3.2372111332720045e-06,
      "loss": 0.7876,
      "step": 515
    },
    {
      "epoch": 0.7698001480384901,
      "grad_norm": 0.6052780167888957,
      "learning_rate": 3.048867328795588e-06,
      "loss": 0.7814,
      "step": 520
    },
    {
      "epoch": 0.7772020725388601,
      "grad_norm": 0.6334645877396388,
      "learning_rate": 2.865178245944218e-06,
      "loss": 0.7854,
      "step": 525
    },
    {
      "epoch": 0.7846039970392302,
      "grad_norm": 0.5996815983095651,
      "learning_rate": 2.686266889354211e-06,
      "loss": 0.7669,
      "step": 530
    },
    {
      "epoch": 0.7920059215396003,
      "grad_norm": 0.6313090473295673,
      "learning_rate": 2.5122530643292274e-06,
      "loss": 0.7769,
      "step": 535
    },
    {
      "epoch": 0.7994078460399704,
      "grad_norm": 0.597495560189999,
      "learning_rate": 2.3432532966144526e-06,
      "loss": 0.7879,
      "step": 540
    },
    {
      "epoch": 0.8068097705403405,
      "grad_norm": 0.5922406784953627,
      "learning_rate": 2.1793807543668857e-06,
      "loss": 0.7929,
      "step": 545
    },
    {
      "epoch": 0.8142116950407106,
      "grad_norm": 0.5657672868223141,
      "learning_rate": 2.0207451723739633e-06,
      "loss": 0.7591,
      "step": 550
    },
    {
      "epoch": 0.8216136195410807,
      "grad_norm": 0.661732050287292,
      "learning_rate": 1.8674527785713247e-06,
      "loss": 0.7976,
      "step": 555
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 0.5965088983030619,
      "learning_rate": 1.7196062229088606e-06,
      "loss": 0.7949,
      "step": 560
    },
    {
      "epoch": 0.8364174685418209,
      "grad_norm": 0.5672448885306686,
      "learning_rate": 1.577304508612717e-06,
      "loss": 0.7738,
      "step": 565
    },
    {
      "epoch": 0.843819393042191,
      "grad_norm": 0.6054393122315499,
      "learning_rate": 1.4406429258892762e-06,
      "loss": 0.7765,
      "step": 570
    },
    {
      "epoch": 0.851221317542561,
      "grad_norm": 0.5815737907187217,
      "learning_rate": 1.3097129881154936e-06,
      "loss": 0.7814,
      "step": 575
    },
    {
      "epoch": 0.8586232420429312,
      "grad_norm": 0.5959896748304101,
      "learning_rate": 1.1846023705583442e-06,
      "loss": 0.7732,
      "step": 580
    },
    {
      "epoch": 0.8660251665433013,
      "grad_norm": 0.6027211591961824,
      "learning_rate": 1.065394851664394e-06,
      "loss": 0.7608,
      "step": 585
    },
    {
      "epoch": 0.8734270910436713,
      "grad_norm": 0.5709554583327551,
      "learning_rate": 9.521702569588199e-07,
      "loss": 0.7945,
      "step": 590
    },
    {
      "epoch": 0.8808290155440415,
      "grad_norm": 0.5709616814673604,
      "learning_rate": 8.450044055914497e-07,
      "loss": 0.7854,
      "step": 595
    },
    {
      "epoch": 0.8882309400444115,
      "grad_norm": 0.6092547537682526,
      "learning_rate": 7.439690595656013e-07,
      "loss": 0.74,
      "step": 600
    },
    {
      "epoch": 0.8882309400444115,
      "eval_loss": 0.8062630891799927,
      "eval_runtime": 3.4536,
      "eval_samples_per_second": 74.126,
      "eval_steps_per_second": 4.633,
      "step": 600
    },
    {
      "epoch": 0.8956328645447816,
      "grad_norm": 0.5794094511868785,
      "learning_rate": 6.491318756837417e-07,
      "loss": 0.7873,
      "step": 605
    },
    {
      "epoch": 0.9030347890451518,
      "grad_norm": 0.6256876372175488,
      "learning_rate": 5.605563602421149e-07,
      "loss": 0.7872,
      "step": 610
    },
    {
      "epoch": 0.9104367135455218,
      "grad_norm": 0.5718366849892658,
      "learning_rate": 4.783018265047179e-07,
      "loss": 0.7807,
      "step": 615
    },
    {
      "epoch": 0.9178386380458919,
      "grad_norm": 0.5934631080661485,
      "learning_rate": 4.024233549850509e-07,
      "loss": 0.7768,
      "step": 620
    },
    {
      "epoch": 0.9252405625462621,
      "grad_norm": 0.5841161765073699,
      "learning_rate": 3.329717565622825e-07,
      "loss": 0.7592,
      "step": 625
    },
    {
      "epoch": 0.9326424870466321,
      "grad_norm": 0.5709231339768578,
      "learning_rate": 2.6999353845651113e-07,
      "loss": 0.7724,
      "step": 630
    },
    {
      "epoch": 0.9400444115470022,
      "grad_norm": 0.5806844863532445,
      "learning_rate": 2.1353087308590314e-07,
      "loss": 0.7753,
      "step": 635
    },
    {
      "epoch": 0.9474463360473723,
      "grad_norm": 0.5759817692217581,
      "learning_rate": 1.6362156982656085e-07,
      "loss": 0.7781,
      "step": 640
    },
    {
      "epoch": 0.9548482605477424,
      "grad_norm": 0.6259498518130084,
      "learning_rate": 1.2029904969404482e-07,
      "loss": 0.801,
      "step": 645
    },
    {
      "epoch": 0.9622501850481125,
      "grad_norm": 0.557201726085551,
      "learning_rate": 8.359232296349163e-08,
      "loss": 0.7883,
      "step": 650
    },
    {
      "epoch": 0.9696521095484826,
      "grad_norm": 0.5968731879007182,
      "learning_rate": 5.3525969743324356e-08,
      "loss": 0.7696,
      "step": 655
    },
    {
      "epoch": 0.9770540340488527,
      "grad_norm": 0.5631272418941485,
      "learning_rate": 3.012012351554017e-08,
      "loss": 0.7789,
      "step": 660
    },
    {
      "epoch": 0.9844559585492227,
      "grad_norm": 0.586328553632967,
      "learning_rate": 1.3390457653639221e-08,
      "loss": 0.7757,
      "step": 665
    },
    {
      "epoch": 0.9918578830495929,
      "grad_norm": 0.5780808334391859,
      "learning_rate": 3.3481749271768726e-09,
      "loss": 0.7817,
      "step": 670
    },
    {
      "epoch": 0.999259807549963,
      "grad_norm": 0.5885397933955042,
      "learning_rate": 0.0,
      "loss": 0.7951,
      "step": 675
    },
    {
      "epoch": 0.999259807549963,
      "step": 675,
      "total_flos": 76888336760832.0,
      "train_loss": 0.8197506145194725,
      "train_runtime": 2459.9036,
      "train_samples_per_second": 17.569,
      "train_steps_per_second": 0.274
    }
  ],
  "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": 2,
  "trial_name": null,
  "trial_params": null
}