{
  "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": 2.6711983870524056,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 1.0786,
      "step": 5
    },
    {
      "epoch": 0.014803849000740192,
      "grad_norm": 2.2850429898049907,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.0901,
      "step": 10
    },
    {
      "epoch": 0.02220577350111029,
      "grad_norm": 1.4164101597454035,
      "learning_rate": 4.411764705882353e-06,
      "loss": 1.062,
      "step": 15
    },
    {
      "epoch": 0.029607698001480384,
      "grad_norm": 1.3745187579444922,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.0087,
      "step": 20
    },
    {
      "epoch": 0.037009622501850484,
      "grad_norm": 1.1121622604345802,
      "learning_rate": 7.352941176470589e-06,
      "loss": 0.9684,
      "step": 25
    },
    {
      "epoch": 0.04441154700222058,
      "grad_norm": 0.9508871498106621,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.9216,
      "step": 30
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 0.7596309946374104,
      "learning_rate": 1.0294117647058823e-05,
      "loss": 0.8858,
      "step": 35
    },
    {
      "epoch": 0.05921539600296077,
      "grad_norm": 0.6887627241116573,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.8631,
      "step": 40
    },
    {
      "epoch": 0.06661732050333087,
      "grad_norm": 0.7462108328677874,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.8486,
      "step": 45
    },
    {
      "epoch": 0.07401924500370097,
      "grad_norm": 0.8183224452124802,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 0.861,
      "step": 50
    },
    {
      "epoch": 0.08142116950407106,
      "grad_norm": 0.624336375155499,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.8546,
      "step": 55
    },
    {
      "epoch": 0.08882309400444116,
      "grad_norm": 0.7318163733327753,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8293,
      "step": 60
    },
    {
      "epoch": 0.09622501850481126,
      "grad_norm": 0.6829238922108138,
      "learning_rate": 1.911764705882353e-05,
      "loss": 0.8259,
      "step": 65
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 0.7705436640022516,
      "learning_rate": 1.9999464266898485e-05,
      "loss": 0.821,
      "step": 70
    },
    {
      "epoch": 0.11102886750555144,
      "grad_norm": 0.9662677211066796,
      "learning_rate": 1.9993437928712977e-05,
      "loss": 0.8164,
      "step": 75
    },
    {
      "epoch": 0.11843079200592153,
      "grad_norm": 0.8221071092928778,
      "learning_rate": 1.998071963486563e-05,
      "loss": 0.8061,
      "step": 80
    },
    {
      "epoch": 0.12583271650629163,
      "grad_norm": 0.6591697934160696,
      "learning_rate": 1.9961317901970953e-05,
      "loss": 0.7946,
      "step": 85
    },
    {
      "epoch": 0.13323464100666174,
      "grad_norm": 0.754203028620329,
      "learning_rate": 1.993524572210807e-05,
      "loss": 0.7946,
      "step": 90
    },
    {
      "epoch": 0.14063656550703182,
      "grad_norm": 0.8039153662244777,
      "learning_rate": 1.990252055412077e-05,
      "loss": 0.7905,
      "step": 95
    },
    {
      "epoch": 0.14803849000740193,
      "grad_norm": 0.781165214016037,
      "learning_rate": 1.9863164311926433e-05,
      "loss": 0.8172,
      "step": 100
    },
    {
      "epoch": 0.14803849000740193,
      "eval_loss": 0.8197938203811646,
      "eval_runtime": 7.0716,
      "eval_samples_per_second": 18.101,
      "eval_steps_per_second": 2.263,
      "step": 100
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 0.7152532780522096,
      "learning_rate": 1.981720334984174e-05,
      "loss": 0.7922,
      "step": 105
    },
    {
      "epoch": 0.16284233900814213,
      "grad_norm": 0.7112781720919623,
      "learning_rate": 1.9764668444934853e-05,
      "loss": 0.7859,
      "step": 110
    },
    {
      "epoch": 0.1702442635085122,
      "grad_norm": 0.7230408660226788,
      "learning_rate": 1.970559477641606e-05,
      "loss": 0.7631,
      "step": 115
    },
    {
      "epoch": 0.17764618800888232,
      "grad_norm": 0.740098112673674,
      "learning_rate": 1.9640021902080523e-05,
      "loss": 0.793,
      "step": 120
    },
    {
      "epoch": 0.1850481125092524,
      "grad_norm": 0.6292091634572502,
      "learning_rate": 1.9567993731818988e-05,
      "loss": 0.7915,
      "step": 125
    },
    {
      "epoch": 0.19245003700962252,
      "grad_norm": 0.7449842900907743,
      "learning_rate": 1.9489558498214197e-05,
      "loss": 0.7843,
      "step": 130
    },
    {
      "epoch": 0.1998519615099926,
      "grad_norm": 0.6522957401073987,
      "learning_rate": 1.9404768724242667e-05,
      "loss": 0.7703,
      "step": 135
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 0.7270180074164395,
      "learning_rate": 1.931368118810346e-05,
      "loss": 0.7946,
      "step": 140
    },
    {
      "epoch": 0.2146558105107328,
      "grad_norm": 0.7449701767462928,
      "learning_rate": 1.92163568851975e-05,
      "loss": 0.7757,
      "step": 145
    },
    {
      "epoch": 0.22205773501110287,
      "grad_norm": 0.8040526421185312,
      "learning_rate": 1.911286098728296e-05,
      "loss": 0.772,
      "step": 150
    },
    {
      "epoch": 0.22945965951147299,
      "grad_norm": 0.6985006196832154,
      "learning_rate": 1.900326279883392e-05,
      "loss": 0.8015,
      "step": 155
    },
    {
      "epoch": 0.23686158401184307,
      "grad_norm": 0.7076271931589052,
      "learning_rate": 1.8887635710631716e-05,
      "loss": 0.8046,
      "step": 160
    },
    {
      "epoch": 0.24426350851221318,
      "grad_norm": 0.6971259985896139,
      "learning_rate": 1.8766057150619865e-05,
      "loss": 0.7776,
      "step": 165
    },
    {
      "epoch": 0.25166543301258326,
      "grad_norm": 0.7076194420512543,
      "learning_rate": 1.8638608532055635e-05,
      "loss": 0.7948,
      "step": 170
    },
    {
      "epoch": 0.25906735751295334,
      "grad_norm": 0.6632786419003115,
      "learning_rate": 1.8505375198992856e-05,
      "loss": 0.7831,
      "step": 175
    },
    {
      "epoch": 0.2664692820133235,
      "grad_norm": 0.721096344753536,
      "learning_rate": 1.836644636913258e-05,
      "loss": 0.7542,
      "step": 180
    },
    {
      "epoch": 0.27387120651369357,
      "grad_norm": 0.7757218802191107,
      "learning_rate": 1.8221915074079764e-05,
      "loss": 0.7778,
      "step": 185
    },
    {
      "epoch": 0.28127313101406365,
      "grad_norm": 0.8616930044863143,
      "learning_rate": 1.8071878097046064e-05,
      "loss": 0.7563,
      "step": 190
    },
    {
      "epoch": 0.28867505551443373,
      "grad_norm": 0.6334483796106015,
      "learning_rate": 1.7916435908040413e-05,
      "loss": 0.7724,
      "step": 195
    },
    {
      "epoch": 0.29607698001480387,
      "grad_norm": 0.6518461677157017,
      "learning_rate": 1.7755692596590778e-05,
      "loss": 0.7745,
      "step": 200
    },
    {
      "epoch": 0.29607698001480387,
      "eval_loss": 0.7899715900421143,
      "eval_runtime": 7.0684,
      "eval_samples_per_second": 18.109,
      "eval_steps_per_second": 2.264,
      "step": 200
    },
    {
      "epoch": 0.30347890451517395,
      "grad_norm": 0.7017860070843315,
      "learning_rate": 1.7589755802042188e-05,
      "loss": 0.7731,
      "step": 205
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 0.6904991065029692,
      "learning_rate": 1.7418736641477636e-05,
      "loss": 0.7562,
      "step": 210
    },
    {
      "epoch": 0.3182827535159141,
      "grad_norm": 0.6275148924891102,
      "learning_rate": 1.7242749635310222e-05,
      "loss": 0.758,
      "step": 215
    },
    {
      "epoch": 0.32568467801628426,
      "grad_norm": 0.6587580564442483,
      "learning_rate": 1.7061912630596252e-05,
      "loss": 0.7605,
      "step": 220
    },
    {
      "epoch": 0.33308660251665434,
      "grad_norm": 0.7198577935496436,
      "learning_rate": 1.6876346722120747e-05,
      "loss": 0.7752,
      "step": 225
    },
    {
      "epoch": 0.3404885270170244,
      "grad_norm": 0.6958333507702643,
      "learning_rate": 1.6686176171308125e-05,
      "loss": 0.7977,
      "step": 230
    },
    {
      "epoch": 0.3478904515173945,
      "grad_norm": 0.6724152701357283,
      "learning_rate": 1.6491528323012412e-05,
      "loss": 0.7596,
      "step": 235
    },
    {
      "epoch": 0.35529237601776464,
      "grad_norm": 0.638858633828288,
      "learning_rate": 1.6292533520242663e-05,
      "loss": 0.7624,
      "step": 240
    },
    {
      "epoch": 0.3626943005181347,
      "grad_norm": 0.6431148825387747,
      "learning_rate": 1.6089325016880737e-05,
      "loss": 0.7527,
      "step": 245
    },
    {
      "epoch": 0.3700962250185048,
      "grad_norm": 0.6786290253539599,
      "learning_rate": 1.588203888844982e-05,
      "loss": 0.7681,
      "step": 250
    },
    {
      "epoch": 0.3774981495188749,
      "grad_norm": 0.6412436561923461,
      "learning_rate": 1.5670813940993504e-05,
      "loss": 0.7409,
      "step": 255
    },
    {
      "epoch": 0.38490007401924503,
      "grad_norm": 0.5934851423161538,
      "learning_rate": 1.5455791618126407e-05,
      "loss": 0.7332,
      "step": 260
    },
    {
      "epoch": 0.3923019985196151,
      "grad_norm": 0.6287423337684374,
      "learning_rate": 1.5237115906318565e-05,
      "loss": 0.7571,
      "step": 265
    },
    {
      "epoch": 0.3997039230199852,
      "grad_norm": 0.6583649676370655,
      "learning_rate": 1.5014933238477069e-05,
      "loss": 0.7378,
      "step": 270
    },
    {
      "epoch": 0.4071058475203553,
      "grad_norm": 0.6894774111149516,
      "learning_rate": 1.4789392395889468e-05,
      "loss": 0.7631,
      "step": 275
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 0.6464094457090966,
      "learning_rate": 1.4560644408594602e-05,
      "loss": 0.7439,
      "step": 280
    },
    {
      "epoch": 0.4219096965210955,
      "grad_norm": 0.6611425021412513,
      "learning_rate": 1.432884245424761e-05,
      "loss": 0.7556,
      "step": 285
    },
    {
      "epoch": 0.4293116210214656,
      "grad_norm": 0.6630113373342271,
      "learning_rate": 1.4094141755546816e-05,
      "loss": 0.7831,
      "step": 290
    },
    {
      "epoch": 0.43671354552183567,
      "grad_norm": 0.6260601475890385,
      "learning_rate": 1.3856699476291176e-05,
      "loss": 0.7425,
      "step": 295
    },
    {
      "epoch": 0.44411547002220575,
      "grad_norm": 0.6783000504772533,
      "learning_rate": 1.3616674616137902e-05,
      "loss": 0.7644,
      "step": 300
    },
    {
      "epoch": 0.44411547002220575,
      "eval_loss": 0.7755021452903748,
      "eval_runtime": 7.069,
      "eval_samples_per_second": 18.107,
      "eval_steps_per_second": 2.263,
      "step": 300
    },
    {
      "epoch": 0.4515173945225759,
      "grad_norm": 0.6542622892237095,
      "learning_rate": 1.3374227904130724e-05,
      "loss": 0.7549,
      "step": 305
    },
    {
      "epoch": 0.45891931902294597,
      "grad_norm": 0.6469269032098538,
      "learning_rate": 1.3129521691070108e-05,
      "loss": 0.7325,
      "step": 310
    },
    {
      "epoch": 0.46632124352331605,
      "grad_norm": 0.719394700629109,
      "learning_rate": 1.2882719840797473e-05,
      "loss": 0.7513,
      "step": 315
    },
    {
      "epoch": 0.47372316802368614,
      "grad_norm": 0.6863894097467634,
      "learning_rate": 1.2633987620466229e-05,
      "loss": 0.7353,
      "step": 320
    },
    {
      "epoch": 0.4811250925240563,
      "grad_norm": 0.6306280609604339,
      "learning_rate": 1.2383491589873122e-05,
      "loss": 0.7405,
      "step": 325
    },
    {
      "epoch": 0.48852701702442636,
      "grad_norm": 0.6102585875926645,
      "learning_rate": 1.213139948992394e-05,
      "loss": 0.7497,
      "step": 330
    },
    {
      "epoch": 0.49592894152479644,
      "grad_norm": 0.7031905875380544,
      "learning_rate": 1.187788013030837e-05,
      "loss": 0.7467,
      "step": 335
    },
    {
      "epoch": 0.5033308660251665,
      "grad_norm": 0.61376243967075,
      "learning_rate": 1.1623103276459086e-05,
      "loss": 0.7506,
      "step": 340
    },
    {
      "epoch": 0.5107327905255367,
      "grad_norm": 0.6419232469607933,
      "learning_rate": 1.1367239535870913e-05,
      "loss": 0.7425,
      "step": 345
    },
    {
      "epoch": 0.5181347150259067,
      "grad_norm": 0.6882955220689385,
      "learning_rate": 1.1110460243856051e-05,
      "loss": 0.7302,
      "step": 350
    },
    {
      "epoch": 0.5255366395262768,
      "grad_norm": 0.6612307540611313,
      "learning_rate": 1.085293734881197e-05,
      "loss": 0.7468,
      "step": 355
    },
    {
      "epoch": 0.532938564026647,
      "grad_norm": 0.6001245809915299,
      "learning_rate": 1.0594843297078736e-05,
      "loss": 0.7658,
      "step": 360
    },
    {
      "epoch": 0.540340488527017,
      "grad_norm": 0.6909746665266651,
      "learning_rate": 1.0336350917462925e-05,
      "loss": 0.7557,
      "step": 365
    },
    {
      "epoch": 0.5477424130273871,
      "grad_norm": 0.6054573158153876,
      "learning_rate": 1.0077633305505402e-05,
      "loss": 0.7433,
      "step": 370
    },
    {
      "epoch": 0.5551443375277573,
      "grad_norm": 0.6301644127515204,
      "learning_rate": 9.818863707570476e-06,
      "loss": 0.7608,
      "step": 375
    },
    {
      "epoch": 0.5625462620281273,
      "grad_norm": 0.6569705040647524,
      "learning_rate": 9.560215404834094e-06,
      "loss": 0.7514,
      "step": 380
    },
    {
      "epoch": 0.5699481865284974,
      "grad_norm": 0.6362202129337399,
      "learning_rate": 9.30186159724869e-06,
      "loss": 0.7146,
      "step": 385
    },
    {
      "epoch": 0.5773501110288675,
      "grad_norm": 0.6110859517886038,
      "learning_rate": 9.043975287562443e-06,
      "loss": 0.7471,
      "step": 390
    },
    {
      "epoch": 0.5847520355292376,
      "grad_norm": 0.6796848603284529,
      "learning_rate": 8.786729165470584e-06,
      "loss": 0.7253,
      "step": 395
    },
    {
      "epoch": 0.5921539600296077,
      "grad_norm": 0.6868812256194778,
      "learning_rate": 8.530295491976338e-06,
      "loss": 0.7307,
      "step": 400
    },
    {
      "epoch": 0.5921539600296077,
      "eval_loss": 0.7635293006896973,
      "eval_runtime": 7.068,
      "eval_samples_per_second": 18.11,
      "eval_steps_per_second": 2.264,
      "step": 400
    },
    {
      "epoch": 0.5995558845299778,
      "grad_norm": 0.5909043234717403,
      "learning_rate": 8.274845984038916e-06,
      "loss": 0.7173,
      "step": 405
    },
    {
      "epoch": 0.6069578090303479,
      "grad_norm": 0.6535110161863971,
      "learning_rate": 8.020551699585843e-06,
      "loss": 0.7468,
      "step": 410
    },
    {
      "epoch": 0.6143597335307179,
      "grad_norm": 0.6069738166341774,
      "learning_rate": 7.76758292296659e-06,
      "loss": 0.7264,
      "step": 415
    },
    {
      "epoch": 0.6217616580310881,
      "grad_norm": 0.6481589336019623,
      "learning_rate": 7.5161090509242005e-06,
      "loss": 0.7418,
      "step": 420
    },
    {
      "epoch": 0.6291635825314582,
      "grad_norm": 0.6463244762446874,
      "learning_rate": 7.2662984791613186e-06,
      "loss": 0.7345,
      "step": 425
    },
    {
      "epoch": 0.6365655070318282,
      "grad_norm": 0.6541386096546981,
      "learning_rate": 7.01831848957653e-06,
      "loss": 0.7489,
      "step": 430
    },
    {
      "epoch": 0.6439674315321984,
      "grad_norm": 0.5992703121063927,
      "learning_rate": 6.772335138246548e-06,
      "loss": 0.7467,
      "step": 435
    },
    {
      "epoch": 0.6513693560325685,
      "grad_norm": 0.6237688537708815,
      "learning_rate": 6.528513144229256e-06,
      "loss": 0.7427,
      "step": 440
    },
    {
      "epoch": 0.6587712805329385,
      "grad_norm": 0.6109938157457578,
      "learning_rate": 6.287015779262064e-06,
      "loss": 0.7487,
      "step": 445
    },
    {
      "epoch": 0.6661732050333087,
      "grad_norm": 0.6586419654811464,
      "learning_rate": 6.048004758429451e-06,
      "loss": 0.7273,
      "step": 450
    },
    {
      "epoch": 0.6735751295336787,
      "grad_norm": 0.6029040703445087,
      "learning_rate": 5.811640131872867e-06,
      "loss": 0.7497,
      "step": 455
    },
    {
      "epoch": 0.6809770540340488,
      "grad_norm": 0.6047746463189991,
      "learning_rate": 5.578080177615575e-06,
      "loss": 0.72,
      "step": 460
    },
    {
      "epoch": 0.688378978534419,
      "grad_norm": 0.6186061941025227,
      "learning_rate": 5.347481295574141e-06,
      "loss": 0.7171,
      "step": 465
    },
    {
      "epoch": 0.695780903034789,
      "grad_norm": 0.6099372690494231,
      "learning_rate": 5.119997902827584e-06,
      "loss": 0.7285,
      "step": 470
    },
    {
      "epoch": 0.7031828275351591,
      "grad_norm": 0.6075548251479312,
      "learning_rate": 4.8957823302142916e-06,
      "loss": 0.7354,
      "step": 475
    },
    {
      "epoch": 0.7105847520355293,
      "grad_norm": 0.5740031002086223,
      "learning_rate": 4.674984720325961e-06,
      "loss": 0.7208,
      "step": 480
    },
    {
      "epoch": 0.7179866765358993,
      "grad_norm": 0.587440122556811,
      "learning_rate": 4.457752926966888e-06,
      "loss": 0.7149,
      "step": 485
    },
    {
      "epoch": 0.7253886010362695,
      "grad_norm": 0.579300724322737,
      "learning_rate": 4.244232416145839e-06,
      "loss": 0.7336,
      "step": 490
    },
    {
      "epoch": 0.7327905255366395,
      "grad_norm": 0.5893313506909182,
      "learning_rate": 4.0345661686669745e-06,
      "loss": 0.7269,
      "step": 495
    },
    {
      "epoch": 0.7401924500370096,
      "grad_norm": 0.6207840467733526,
      "learning_rate": 3.828894584384867e-06,
      "loss": 0.7354,
      "step": 500
    },
    {
      "epoch": 0.7401924500370096,
      "eval_loss": 0.7562252283096313,
      "eval_runtime": 7.0669,
      "eval_samples_per_second": 18.113,
      "eval_steps_per_second": 2.264,
      "step": 500
    },
    {
      "epoch": 0.7475943745373798,
      "grad_norm": 0.5588930357912468,
      "learning_rate": 3.62735538818787e-06,
      "loss": 0.7195,
      "step": 505
    },
    {
      "epoch": 0.7549962990377498,
      "grad_norm": 0.6311587155804506,
      "learning_rate": 3.4300835377726904e-06,
      "loss": 0.7232,
      "step": 510
    },
    {
      "epoch": 0.7623982235381199,
      "grad_norm": 0.6171722843809619,
      "learning_rate": 3.2372111332720045e-06,
      "loss": 0.7587,
      "step": 515
    },
    {
      "epoch": 0.7698001480384901,
      "grad_norm": 0.6041124442799582,
      "learning_rate": 3.048867328795588e-06,
      "loss": 0.7155,
      "step": 520
    },
    {
      "epoch": 0.7772020725388601,
      "grad_norm": 0.604453809119269,
      "learning_rate": 2.865178245944218e-06,
      "loss": 0.7145,
      "step": 525
    },
    {
      "epoch": 0.7846039970392302,
      "grad_norm": 0.5678261075203981,
      "learning_rate": 2.686266889354211e-06,
      "loss": 0.7373,
      "step": 530
    },
    {
      "epoch": 0.7920059215396003,
      "grad_norm": 0.5878591560004413,
      "learning_rate": 2.5122530643292274e-06,
      "loss": 0.7429,
      "step": 535
    },
    {
      "epoch": 0.7994078460399704,
      "grad_norm": 0.6335605148603548,
      "learning_rate": 2.3432532966144526e-06,
      "loss": 0.7322,
      "step": 540
    },
    {
      "epoch": 0.8068097705403405,
      "grad_norm": 0.5832205633293672,
      "learning_rate": 2.1793807543668857e-06,
      "loss": 0.7339,
      "step": 545
    },
    {
      "epoch": 0.8142116950407106,
      "grad_norm": 0.5484140593938892,
      "learning_rate": 2.0207451723739633e-06,
      "loss": 0.7257,
      "step": 550
    },
    {
      "epoch": 0.8216136195410807,
      "grad_norm": 0.5608949535445834,
      "learning_rate": 1.8674527785713247e-06,
      "loss": 0.7323,
      "step": 555
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 0.614987231897141,
      "learning_rate": 1.7196062229088606e-06,
      "loss": 0.6996,
      "step": 560
    },
    {
      "epoch": 0.8364174685418209,
      "grad_norm": 0.6274220285054067,
      "learning_rate": 1.577304508612717e-06,
      "loss": 0.7297,
      "step": 565
    },
    {
      "epoch": 0.843819393042191,
      "grad_norm": 0.5189133367191697,
      "learning_rate": 1.4406429258892762e-06,
      "loss": 0.7502,
      "step": 570
    },
    {
      "epoch": 0.851221317542561,
      "grad_norm": 0.6163635903896416,
      "learning_rate": 1.3097129881154936e-06,
      "loss": 0.7199,
      "step": 575
    },
    {
      "epoch": 0.8586232420429312,
      "grad_norm": 0.5826045976899757,
      "learning_rate": 1.1846023705583442e-06,
      "loss": 0.7163,
      "step": 580
    },
    {
      "epoch": 0.8660251665433013,
      "grad_norm": 0.5795867643385718,
      "learning_rate": 1.065394851664394e-06,
      "loss": 0.7344,
      "step": 585
    },
    {
      "epoch": 0.8734270910436713,
      "grad_norm": 0.5465940844303231,
      "learning_rate": 9.521702569588199e-07,
      "loss": 0.7536,
      "step": 590
    },
    {
      "epoch": 0.8808290155440415,
      "grad_norm": 0.5733953437784535,
      "learning_rate": 8.450044055914497e-07,
      "loss": 0.722,
      "step": 595
    },
    {
      "epoch": 0.8882309400444115,
      "grad_norm": 0.5600976250568785,
      "learning_rate": 7.439690595656013e-07,
      "loss": 0.7445,
      "step": 600
    },
    {
      "epoch": 0.8882309400444115,
      "eval_loss": 0.7531653642654419,
      "eval_runtime": 7.0744,
      "eval_samples_per_second": 18.093,
      "eval_steps_per_second": 2.262,
      "step": 600
    },
    {
      "epoch": 0.8956328645447816,
      "grad_norm": 0.6305328535331403,
      "learning_rate": 6.491318756837417e-07,
      "loss": 0.7297,
      "step": 605
    },
    {
      "epoch": 0.9030347890451518,
      "grad_norm": 0.5122359209490615,
      "learning_rate": 5.605563602421149e-07,
      "loss": 0.7058,
      "step": 610
    },
    {
      "epoch": 0.9104367135455218,
      "grad_norm": 0.5559611714691143,
      "learning_rate": 4.783018265047179e-07,
      "loss": 0.7557,
      "step": 615
    },
    {
      "epoch": 0.9178386380458919,
      "grad_norm": 0.5817671631266513,
      "learning_rate": 4.024233549850509e-07,
      "loss": 0.7436,
      "step": 620
    },
    {
      "epoch": 0.9252405625462621,
      "grad_norm": 0.551371591210011,
      "learning_rate": 3.329717565622825e-07,
      "loss": 0.7404,
      "step": 625
    },
    {
      "epoch": 0.9326424870466321,
      "grad_norm": 0.5524848990635999,
      "learning_rate": 2.6999353845651113e-07,
      "loss": 0.724,
      "step": 630
    },
    {
      "epoch": 0.9400444115470022,
      "grad_norm": 0.5847475817270994,
      "learning_rate": 2.1353087308590314e-07,
      "loss": 0.739,
      "step": 635
    },
    {
      "epoch": 0.9474463360473723,
      "grad_norm": 0.5576073965990508,
      "learning_rate": 1.6362156982656085e-07,
      "loss": 0.729,
      "step": 640
    },
    {
      "epoch": 0.9548482605477424,
      "grad_norm": 0.5237921834045887,
      "learning_rate": 1.2029904969404482e-07,
      "loss": 0.7126,
      "step": 645
    },
    {
      "epoch": 0.9622501850481125,
      "grad_norm": 0.6022735856021589,
      "learning_rate": 8.359232296349163e-08,
      "loss": 0.7163,
      "step": 650
    },
    {
      "epoch": 0.9696521095484826,
      "grad_norm": 0.5687438455500246,
      "learning_rate": 5.3525969743324356e-08,
      "loss": 0.7321,
      "step": 655
    },
    {
      "epoch": 0.9770540340488527,
      "grad_norm": 0.5475861274240331,
      "learning_rate": 3.012012351554017e-08,
      "loss": 0.7065,
      "step": 660
    },
    {
      "epoch": 0.9844559585492227,
      "grad_norm": 0.5811810010866978,
      "learning_rate": 1.3390457653639221e-08,
      "loss": 0.7351,
      "step": 665
    },
    {
      "epoch": 0.9918578830495929,
      "grad_norm": 0.6427867903548724,
      "learning_rate": 3.3481749271768726e-09,
      "loss": 0.7461,
      "step": 670
    },
    {
      "epoch": 0.999259807549963,
      "grad_norm": 0.5721249942658874,
      "learning_rate": 0.0,
      "loss": 0.7157,
      "step": 675
    },
    {
      "epoch": 0.999259807549963,
      "step": 675,
      "total_flos": 76888336760832.0,
      "train_loss": 0.7675520939297146,
      "train_runtime": 4819.1398,
      "train_samples_per_second": 4.484,
      "train_steps_per_second": 0.14
    }
  ],
  "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": 1,
  "trial_name": null,
  "trial_params": null
}