{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2658788774002954,
  "eval_steps": 500,
  "global_step": 540,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002461841457410143,
      "grad_norm": 4.863656520843506,
      "learning_rate": 4.302e-06,
      "loss": 1.089,
      "mean_token_accuracy": 0.814908242225647,
      "num_tokens": 321007.0,
      "step": 5
    },
    {
      "epoch": 0.004923682914820286,
      "grad_norm": 1.8138774633407593,
      "learning_rate": 9.6795e-06,
      "loss": 0.78,
      "mean_token_accuracy": 0.8449344515800477,
      "num_tokens": 642166.0,
      "step": 10
    },
    {
      "epoch": 0.007385524372230428,
      "grad_norm": 1.0333073139190674,
      "learning_rate": 1.5056999999999998e-05,
      "loss": 0.4551,
      "mean_token_accuracy": 0.892854881286621,
      "num_tokens": 965077.0,
      "step": 15
    },
    {
      "epoch": 0.009847365829640572,
      "grad_norm": 0.7795208096504211,
      "learning_rate": 2.04345e-05,
      "loss": 0.2095,
      "mean_token_accuracy": 0.9469747185707093,
      "num_tokens": 1285948.0,
      "step": 20
    },
    {
      "epoch": 0.012309207287050714,
      "grad_norm": 0.3677549362182617,
      "learning_rate": 2.1509842516210667e-05,
      "loss": 0.054,
      "mean_token_accuracy": 0.9857019901275634,
      "num_tokens": 1607712.0,
      "step": 25
    },
    {
      "epoch": 0.014771048744460856,
      "grad_norm": 0.1727459728717804,
      "learning_rate": 2.1509202748855685e-05,
      "loss": 0.024,
      "mean_token_accuracy": 0.9930675268173218,
      "num_tokens": 1928019.0,
      "step": 30
    },
    {
      "epoch": 0.017232890201871,
      "grad_norm": 0.10718400031328201,
      "learning_rate": 2.1508070894201505e-05,
      "loss": 0.0165,
      "mean_token_accuracy": 0.9949277758598327,
      "num_tokens": 2249242.0,
      "step": 35
    },
    {
      "epoch": 0.019694731659281144,
      "grad_norm": 0.06165456026792526,
      "learning_rate": 2.1506447021304556e-05,
      "loss": 0.0225,
      "mean_token_accuracy": 0.9936946630477905,
      "num_tokens": 2570223.0,
      "step": 40
    },
    {
      "epoch": 0.022156573116691284,
      "grad_norm": 0.05492320656776428,
      "learning_rate": 2.150433122924014e-05,
      "loss": 0.0222,
      "mean_token_accuracy": 0.9935277819633483,
      "num_tokens": 2890223.0,
      "step": 45
    },
    {
      "epoch": 0.024618414574101428,
      "grad_norm": 0.12794291973114014,
      "learning_rate": 2.1501723647096418e-05,
      "loss": 0.0282,
      "mean_token_accuracy": 0.9920882940292358,
      "num_tokens": 3212891.0,
      "step": 50
    },
    {
      "epoch": 0.02708025603151157,
      "grad_norm": 0.058887798339128494,
      "learning_rate": 2.149862443396651e-05,
      "loss": 0.0171,
      "mean_token_accuracy": 0.9939746260643005,
      "num_tokens": 3534669.0,
      "step": 55
    },
    {
      "epoch": 0.029542097488921712,
      "grad_norm": 0.04351770132780075,
      "learning_rate": 2.1495033778938793e-05,
      "loss": 0.0187,
      "mean_token_accuracy": 0.9938419580459594,
      "num_tokens": 3855274.0,
      "step": 60
    },
    {
      "epoch": 0.032003938946331856,
      "grad_norm": 0.07655734568834305,
      "learning_rate": 2.149095190108538e-05,
      "loss": 0.0193,
      "mean_token_accuracy": 0.9937954783439636,
      "num_tokens": 4177238.0,
      "step": 65
    },
    {
      "epoch": 0.034465780403742,
      "grad_norm": 0.11325498670339584,
      "learning_rate": 2.1486379049448737e-05,
      "loss": 0.0201,
      "mean_token_accuracy": 0.9936431646347046,
      "num_tokens": 4499030.0,
      "step": 70
    },
    {
      "epoch": 0.03692762186115214,
      "grad_norm": 0.05018791928887367,
      "learning_rate": 2.1481315503026496e-05,
      "loss": 0.0179,
      "mean_token_accuracy": 0.9939479827880859,
      "num_tokens": 4820095.0,
      "step": 75
    },
    {
      "epoch": 0.03938946331856229,
      "grad_norm": 0.03790418058633804,
      "learning_rate": 2.1475761570754427e-05,
      "loss": 0.0215,
      "mean_token_accuracy": 0.9932880401611328,
      "num_tokens": 5141458.0,
      "step": 80
    },
    {
      "epoch": 0.041851304775972424,
      "grad_norm": 0.0859006866812706,
      "learning_rate": 2.1469717591487602e-05,
      "loss": 0.0186,
      "mean_token_accuracy": 0.9938247919082641,
      "num_tokens": 5463752.0,
      "step": 85
    },
    {
      "epoch": 0.04431314623338257,
      "grad_norm": 0.07740197330713272,
      "learning_rate": 2.1463183933979705e-05,
      "loss": 0.0147,
      "mean_token_accuracy": 0.9945960640907288,
      "num_tokens": 5787431.0,
      "step": 90
    },
    {
      "epoch": 0.04677498769079271,
      "grad_norm": 0.047287341207265854,
      "learning_rate": 2.1456160996860543e-05,
      "loss": 0.023,
      "mean_token_accuracy": 0.9928844809532166,
      "num_tokens": 6109152.0,
      "step": 95
    },
    {
      "epoch": 0.049236829148202856,
      "grad_norm": 0.05829532817006111,
      "learning_rate": 2.144864920861172e-05,
      "loss": 0.0117,
      "mean_token_accuracy": 0.9954191327095032,
      "num_tokens": 6431705.0,
      "step": 100
    },
    {
      "epoch": 0.051698670605613,
      "grad_norm": 0.05723382532596588,
      "learning_rate": 2.144064902754051e-05,
      "loss": 0.0154,
      "mean_token_accuracy": 0.9943364858627319,
      "num_tokens": 6752736.0,
      "step": 105
    },
    {
      "epoch": 0.05416051206302314,
      "grad_norm": 0.044273972511291504,
      "learning_rate": 2.1432160941751866e-05,
      "loss": 0.0143,
      "mean_token_accuracy": 0.99447603225708,
      "num_tokens": 7073483.0,
      "step": 110
    },
    {
      "epoch": 0.05662235352043329,
      "grad_norm": 0.03600989282131195,
      "learning_rate": 2.142318546911867e-05,
      "loss": 0.014,
      "mean_token_accuracy": 0.9947222352027894,
      "num_tokens": 7394385.0,
      "step": 115
    },
    {
      "epoch": 0.059084194977843424,
      "grad_norm": 0.06433593481779099,
      "learning_rate": 2.1413723157250112e-05,
      "loss": 0.013,
      "mean_token_accuracy": 0.9951158881187439,
      "num_tokens": 7714463.0,
      "step": 120
    },
    {
      "epoch": 0.06154603643525357,
      "grad_norm": 0.04521690681576729,
      "learning_rate": 2.1403774583458295e-05,
      "loss": 0.0113,
      "mean_token_accuracy": 0.9955456614494324,
      "num_tokens": 8035037.0,
      "step": 125
    },
    {
      "epoch": 0.06400787789266371,
      "grad_norm": 0.041315168142318726,
      "learning_rate": 2.1393340354723012e-05,
      "loss": 0.0133,
      "mean_token_accuracy": 0.9949990749359131,
      "num_tokens": 8356667.0,
      "step": 130
    },
    {
      "epoch": 0.06646971935007386,
      "grad_norm": 0.05133018270134926,
      "learning_rate": 2.13824211076547e-05,
      "loss": 0.0136,
      "mean_token_accuracy": 0.9947412252426148,
      "num_tokens": 8677204.0,
      "step": 135
    },
    {
      "epoch": 0.068931560807484,
      "grad_norm": 0.11235912144184113,
      "learning_rate": 2.1371017508455625e-05,
      "loss": 0.0134,
      "mean_token_accuracy": 0.9950397968292236,
      "num_tokens": 8998263.0,
      "step": 140
    },
    {
      "epoch": 0.07139340226489414,
      "grad_norm": 0.04020993784070015,
      "learning_rate": 2.1359130252879188e-05,
      "loss": 0.0115,
      "mean_token_accuracy": 0.9955047130584717,
      "num_tokens": 9318743.0,
      "step": 145
    },
    {
      "epoch": 0.07385524372230429,
      "grad_norm": 0.036466777324676514,
      "learning_rate": 2.1346760066187538e-05,
      "loss": 0.0123,
      "mean_token_accuracy": 0.9949952602386475,
      "num_tokens": 9639416.0,
      "step": 150
    },
    {
      "epoch": 0.07631708517971443,
      "grad_norm": 0.048606228083372116,
      "learning_rate": 2.1333907703107276e-05,
      "loss": 0.0124,
      "mean_token_accuracy": 0.9953677892684937,
      "num_tokens": 9960679.0,
      "step": 155
    },
    {
      "epoch": 0.07877892663712457,
      "grad_norm": 0.04641677811741829,
      "learning_rate": 2.1320573947783423e-05,
      "loss": 0.0131,
      "mean_token_accuracy": 0.9949431777000427,
      "num_tokens": 10281860.0,
      "step": 160
    },
    {
      "epoch": 0.08124076809453472,
      "grad_norm": 0.03626161813735962,
      "learning_rate": 2.1306759613731585e-05,
      "loss": 0.0125,
      "mean_token_accuracy": 0.9951719403266907,
      "num_tokens": 10602773.0,
      "step": 165
    },
    {
      "epoch": 0.08370260955194485,
      "grad_norm": 0.05205853655934334,
      "learning_rate": 2.1292465543788306e-05,
      "loss": 0.0155,
      "mean_token_accuracy": 0.9943783760070801,
      "num_tokens": 10924549.0,
      "step": 170
    },
    {
      "epoch": 0.08616445100935499,
      "grad_norm": 0.035130131989717484,
      "learning_rate": 2.127769261005965e-05,
      "loss": 0.0131,
      "mean_token_accuracy": 0.9950395941734314,
      "num_tokens": 11245489.0,
      "step": 175
    },
    {
      "epoch": 0.08862629246676514,
      "grad_norm": 0.033537521958351135,
      "learning_rate": 2.1262441713867998e-05,
      "loss": 0.0105,
      "mean_token_accuracy": 0.9956490755081177,
      "num_tokens": 11566883.0,
      "step": 180
    },
    {
      "epoch": 0.09108813392417528,
      "grad_norm": 0.057261981070041656,
      "learning_rate": 2.1246713785697052e-05,
      "loss": 0.0173,
      "mean_token_accuracy": 0.9939020276069641,
      "num_tokens": 11888530.0,
      "step": 185
    },
    {
      "epoch": 0.09354997538158542,
      "grad_norm": 0.04334254190325737,
      "learning_rate": 2.1230509785135057e-05,
      "loss": 0.0159,
      "mean_token_accuracy": 0.9945520758628845,
      "num_tokens": 12210957.0,
      "step": 190
    },
    {
      "epoch": 0.09601181683899557,
      "grad_norm": 0.04960763081908226,
      "learning_rate": 2.1213830700816276e-05,
      "loss": 0.0175,
      "mean_token_accuracy": 0.9940741300582886,
      "num_tokens": 12533023.0,
      "step": 195
    },
    {
      "epoch": 0.09847365829640571,
      "grad_norm": 0.07423041760921478,
      "learning_rate": 2.1196677550360644e-05,
      "loss": 0.0176,
      "mean_token_accuracy": 0.9938151836395264,
      "num_tokens": 12855021.0,
      "step": 200
    },
    {
      "epoch": 0.10093549975381585,
      "grad_norm": 0.053134091198444366,
      "learning_rate": 2.1179051380311706e-05,
      "loss": 0.0137,
      "mean_token_accuracy": 0.9949296712875366,
      "num_tokens": 13176812.0,
      "step": 205
    },
    {
      "epoch": 0.103397341211226,
      "grad_norm": 0.04765772819519043,
      "learning_rate": 2.116095326607275e-05,
      "loss": 0.014,
      "mean_token_accuracy": 0.9948251724243165,
      "num_tokens": 13497620.0,
      "step": 210
    },
    {
      "epoch": 0.10585918266863614,
      "grad_norm": 0.040181875228881836,
      "learning_rate": 2.11423843118412e-05,
      "loss": 0.0132,
      "mean_token_accuracy": 0.9949268341064453,
      "num_tokens": 13820439.0,
      "step": 215
    },
    {
      "epoch": 0.10832102412604629,
      "grad_norm": 0.027366064488887787,
      "learning_rate": 2.1123345650541254e-05,
      "loss": 0.0136,
      "mean_token_accuracy": 0.9947750210762024,
      "num_tokens": 14141877.0,
      "step": 220
    },
    {
      "epoch": 0.11078286558345643,
      "grad_norm": 0.03280498832464218,
      "learning_rate": 2.110383844375474e-05,
      "loss": 0.014,
      "mean_token_accuracy": 0.9947653651237488,
      "num_tokens": 14463239.0,
      "step": 225
    },
    {
      "epoch": 0.11324470704086657,
      "grad_norm": 0.042962074279785156,
      "learning_rate": 2.1083863881650274e-05,
      "loss": 0.0114,
      "mean_token_accuracy": 0.9954652309417724,
      "num_tokens": 14783936.0,
      "step": 230
    },
    {
      "epoch": 0.11570654849827672,
      "grad_norm": 0.05033653974533081,
      "learning_rate": 2.1063423182910628e-05,
      "loss": 0.0154,
      "mean_token_accuracy": 0.994532835483551,
      "num_tokens": 15104622.0,
      "step": 235
    },
    {
      "epoch": 0.11816838995568685,
      "grad_norm": 0.0309117641299963,
      "learning_rate": 2.1042517594658383e-05,
      "loss": 0.013,
      "mean_token_accuracy": 0.9950152516365052,
      "num_tokens": 15424784.0,
      "step": 240
    },
    {
      "epoch": 0.12063023141309699,
      "grad_norm": 0.06306195259094238,
      "learning_rate": 2.1021148392379833e-05,
      "loss": 0.0203,
      "mean_token_accuracy": 0.9932177662849426,
      "num_tokens": 15746390.0,
      "step": 245
    },
    {
      "epoch": 0.12309207287050714,
      "grad_norm": 0.02742896042764187,
      "learning_rate": 2.0999316879847178e-05,
      "loss": 0.0163,
      "mean_token_accuracy": 0.9943474411964417,
      "num_tokens": 16067945.0,
      "step": 250
    },
    {
      "epoch": 0.1255539143279173,
      "grad_norm": 0.030147450044751167,
      "learning_rate": 2.097702438903896e-05,
      "loss": 0.0132,
      "mean_token_accuracy": 0.995166015625,
      "num_tokens": 16390879.0,
      "step": 255
    },
    {
      "epoch": 0.12801575578532742,
      "grad_norm": 0.03975250944495201,
      "learning_rate": 2.095427228005882e-05,
      "loss": 0.0132,
      "mean_token_accuracy": 0.9950159311294555,
      "num_tokens": 16711084.0,
      "step": 260
    },
    {
      "epoch": 0.13047759724273758,
      "grad_norm": 0.04383750259876251,
      "learning_rate": 2.093106194105249e-05,
      "loss": 0.0119,
      "mean_token_accuracy": 0.9953450441360474,
      "num_tokens": 17033702.0,
      "step": 265
    },
    {
      "epoch": 0.1329394387001477,
      "grad_norm": 0.03241362050175667,
      "learning_rate": 2.090739478812312e-05,
      "loss": 0.0134,
      "mean_token_accuracy": 0.9950896143913269,
      "num_tokens": 17356521.0,
      "step": 270
    },
    {
      "epoch": 0.13540128015755784,
      "grad_norm": 0.026847772300243378,
      "learning_rate": 2.0883272265244868e-05,
      "loss": 0.013,
      "mean_token_accuracy": 0.9950891971588135,
      "num_tokens": 17678363.0,
      "step": 275
    },
    {
      "epoch": 0.137863121614968,
      "grad_norm": 0.03550383076071739,
      "learning_rate": 2.0858695844174815e-05,
      "loss": 0.0137,
      "mean_token_accuracy": 0.994836401939392,
      "num_tokens": 17999515.0,
      "step": 280
    },
    {
      "epoch": 0.14032496307237813,
      "grad_norm": 0.06238512322306633,
      "learning_rate": 2.083366702436315e-05,
      "loss": 0.0158,
      "mean_token_accuracy": 0.9945228219032287,
      "num_tokens": 18320866.0,
      "step": 285
    },
    {
      "epoch": 0.14278680452978829,
      "grad_norm": 0.028855085372924805,
      "learning_rate": 2.080818733286169e-05,
      "loss": 0.0123,
      "mean_token_accuracy": 0.995316994190216,
      "num_tokens": 18643634.0,
      "step": 290
    },
    {
      "epoch": 0.14524864598719842,
      "grad_norm": 0.02972300350666046,
      "learning_rate": 2.078225832423074e-05,
      "loss": 0.0161,
      "mean_token_accuracy": 0.9942253947257995,
      "num_tokens": 18965558.0,
      "step": 295
    },
    {
      "epoch": 0.14771048744460857,
      "grad_norm": 0.03697444871068001,
      "learning_rate": 2.07558815804442e-05,
      "loss": 0.0104,
      "mean_token_accuracy": 0.9958138465881348,
      "num_tokens": 19286951.0,
      "step": 300
    },
    {
      "epoch": 0.1501723289020187,
      "grad_norm": 0.05770840495824814,
      "learning_rate": 2.072905871079309e-05,
      "loss": 0.0131,
      "mean_token_accuracy": 0.9949340224266052,
      "num_tokens": 19607061.0,
      "step": 305
    },
    {
      "epoch": 0.15263417035942886,
      "grad_norm": 0.03469410911202431,
      "learning_rate": 2.0701791351787333e-05,
      "loss": 0.0099,
      "mean_token_accuracy": 0.9958946108818054,
      "num_tokens": 19929274.0,
      "step": 310
    },
    {
      "epoch": 0.155096011816839,
      "grad_norm": 0.05004841461777687,
      "learning_rate": 2.0674081167055918e-05,
      "loss": 0.013,
      "mean_token_accuracy": 0.9950161814689636,
      "num_tokens": 20251062.0,
      "step": 315
    },
    {
      "epoch": 0.15755785327424915,
      "grad_norm": 0.046333201229572296,
      "learning_rate": 2.064592984724541e-05,
      "loss": 0.0144,
      "mean_token_accuracy": 0.9947794795036315,
      "num_tokens": 20572072.0,
      "step": 320
    },
    {
      "epoch": 0.16001969473165928,
      "grad_norm": 0.03235311806201935,
      "learning_rate": 2.0617339109916796e-05,
      "loss": 0.0137,
      "mean_token_accuracy": 0.9948747038841248,
      "num_tokens": 20893294.0,
      "step": 325
    },
    {
      "epoch": 0.16248153618906944,
      "grad_norm": 0.038612525910139084,
      "learning_rate": 2.058831069944068e-05,
      "loss": 0.0152,
      "mean_token_accuracy": 0.9946804523468018,
      "num_tokens": 21214542.0,
      "step": 330
    },
    {
      "epoch": 0.16494337764647957,
      "grad_norm": 0.025016309693455696,
      "learning_rate": 2.0558846386890867e-05,
      "loss": 0.0136,
      "mean_token_accuracy": 0.9951780676841736,
      "num_tokens": 21536734.0,
      "step": 335
    },
    {
      "epoch": 0.1674052191038897,
      "grad_norm": 0.031026452779769897,
      "learning_rate": 2.0528947969936308e-05,
      "loss": 0.012,
      "mean_token_accuracy": 0.9952717900276185,
      "num_tokens": 21857713.0,
      "step": 340
    },
    {
      "epoch": 0.16986706056129985,
      "grad_norm": 0.0282401442527771,
      "learning_rate": 2.0498617272731426e-05,
      "loss": 0.0138,
      "mean_token_accuracy": 0.994832181930542,
      "num_tokens": 22178369.0,
      "step": 345
    },
    {
      "epoch": 0.17232890201870998,
      "grad_norm": 0.03516492620110512,
      "learning_rate": 2.0467856145804803e-05,
      "loss": 0.0126,
      "mean_token_accuracy": 0.9951131939888,
      "num_tokens": 22499186.0,
      "step": 350
    },
    {
      "epoch": 0.17479074347612014,
      "grad_norm": 0.023863811045885086,
      "learning_rate": 2.0436666465946293e-05,
      "loss": 0.012,
      "mean_token_accuracy": 0.9952613711357117,
      "num_tokens": 22818871.0,
      "step": 355
    },
    {
      "epoch": 0.17725258493353027,
      "grad_norm": 0.02898053079843521,
      "learning_rate": 2.0405050136092498e-05,
      "loss": 0.0107,
      "mean_token_accuracy": 0.9957016706466675,
      "num_tokens": 23141414.0,
      "step": 360
    },
    {
      "epoch": 0.17971442639094043,
      "grad_norm": 0.037398334592580795,
      "learning_rate": 2.03730090852107e-05,
      "loss": 0.0132,
      "mean_token_accuracy": 0.9948941230773926,
      "num_tokens": 23461577.0,
      "step": 365
    },
    {
      "epoch": 0.18217626784835056,
      "grad_norm": 0.04012646526098251,
      "learning_rate": 2.034054526818113e-05,
      "loss": 0.0115,
      "mean_token_accuracy": 0.9955559730529785,
      "num_tokens": 23783259.0,
      "step": 370
    },
    {
      "epoch": 0.18463810930576072,
      "grad_norm": 0.04099590331315994,
      "learning_rate": 2.0307660665677727e-05,
      "loss": 0.0137,
      "mean_token_accuracy": 0.9946975588798523,
      "num_tokens": 24103122.0,
      "step": 375
    },
    {
      "epoch": 0.18709995076317085,
      "grad_norm": 0.031648050993680954,
      "learning_rate": 2.027435728404728e-05,
      "loss": 0.0106,
      "mean_token_accuracy": 0.9956473708152771,
      "num_tokens": 24425740.0,
      "step": 380
    },
    {
      "epoch": 0.189561792220581,
      "grad_norm": 0.04404672607779503,
      "learning_rate": 2.0240637155187022e-05,
      "loss": 0.0127,
      "mean_token_accuracy": 0.9950958609580993,
      "num_tokens": 24746163.0,
      "step": 385
    },
    {
      "epoch": 0.19202363367799113,
      "grad_norm": 0.029460404068231583,
      "learning_rate": 2.0206502336420666e-05,
      "loss": 0.0129,
      "mean_token_accuracy": 0.9949822425842285,
      "num_tokens": 25066336.0,
      "step": 390
    },
    {
      "epoch": 0.1944854751354013,
      "grad_norm": 0.04973338544368744,
      "learning_rate": 2.0171954910372855e-05,
      "loss": 0.0125,
      "mean_token_accuracy": 0.9952076077461243,
      "num_tokens": 25387202.0,
      "step": 395
    },
    {
      "epoch": 0.19694731659281142,
      "grad_norm": 0.04149773344397545,
      "learning_rate": 2.0136996984842144e-05,
      "loss": 0.0109,
      "mean_token_accuracy": 0.9957006335258484,
      "num_tokens": 25708881.0,
      "step": 400
    },
    {
      "epoch": 0.19940915805022155,
      "grad_norm": 0.03306461498141289,
      "learning_rate": 2.0101630692672366e-05,
      "loss": 0.0111,
      "mean_token_accuracy": 0.9955379962921143,
      "num_tokens": 26030050.0,
      "step": 405
    },
    {
      "epoch": 0.2018709995076317,
      "grad_norm": 0.030293015763163567,
      "learning_rate": 2.006585819162251e-05,
      "loss": 0.0119,
      "mean_token_accuracy": 0.9954728364944458,
      "num_tokens": 26351231.0,
      "step": 410
    },
    {
      "epoch": 0.20433284096504184,
      "grad_norm": 0.026037540286779404,
      "learning_rate": 2.002968166423509e-05,
      "loss": 0.0112,
      "mean_token_accuracy": 0.9954585909843445,
      "num_tokens": 26674114.0,
      "step": 415
    },
    {
      "epoch": 0.206794682422452,
      "grad_norm": 0.0441579669713974,
      "learning_rate": 1.999310331770294e-05,
      "loss": 0.0121,
      "mean_token_accuracy": 0.9953820586204529,
      "num_tokens": 26994230.0,
      "step": 420
    },
    {
      "epoch": 0.20925652387986213,
      "grad_norm": 0.02964727394282818,
      "learning_rate": 1.9956125383734614e-05,
      "loss": 0.0114,
      "mean_token_accuracy": 0.9954700708389282,
      "num_tokens": 27316428.0,
      "step": 425
    },
    {
      "epoch": 0.21171836533727229,
      "grad_norm": 0.06177075207233429,
      "learning_rate": 1.9918750118418164e-05,
      "loss": 0.0147,
      "mean_token_accuracy": 0.9946566939353942,
      "num_tokens": 27637380.0,
      "step": 430
    },
    {
      "epoch": 0.21418020679468242,
      "grad_norm": 0.027682114392518997,
      "learning_rate": 1.988097980208353e-05,
      "loss": 0.0133,
      "mean_token_accuracy": 0.9948596119880676,
      "num_tokens": 27960067.0,
      "step": 435
    },
    {
      "epoch": 0.21664204825209257,
      "grad_norm": 0.07328087091445923,
      "learning_rate": 1.98428167391634e-05,
      "loss": 0.0118,
      "mean_token_accuracy": 0.9954464673995972,
      "num_tokens": 28282274.0,
      "step": 440
    },
    {
      "epoch": 0.2191038897095027,
      "grad_norm": 0.03303288668394089,
      "learning_rate": 1.980426325805261e-05,
      "loss": 0.012,
      "mean_token_accuracy": 0.9953627109527587,
      "num_tokens": 28602426.0,
      "step": 445
    },
    {
      "epoch": 0.22156573116691286,
      "grad_norm": 0.027796752750873566,
      "learning_rate": 1.97653217109661e-05,
      "loss": 0.0105,
      "mean_token_accuracy": 0.9958163142204285,
      "num_tokens": 28921894.0,
      "step": 450
    },
    {
      "epoch": 0.224027572624323,
      "grad_norm": 0.04791528731584549,
      "learning_rate": 1.9725994473795378e-05,
      "loss": 0.0139,
      "mean_token_accuracy": 0.9947140574455261,
      "num_tokens": 29242623.0,
      "step": 455
    },
    {
      "epoch": 0.22648941408173315,
      "grad_norm": 0.029893744736909866,
      "learning_rate": 1.968628394596358e-05,
      "loss": 0.0115,
      "mean_token_accuracy": 0.9955099821090698,
      "num_tokens": 29564770.0,
      "step": 460
    },
    {
      "epoch": 0.22895125553914328,
      "grad_norm": 0.027840137481689453,
      "learning_rate": 1.9646192550279074e-05,
      "loss": 0.0122,
      "mean_token_accuracy": 0.9954214334487915,
      "num_tokens": 29886114.0,
      "step": 465
    },
    {
      "epoch": 0.23141309699655344,
      "grad_norm": 0.06552904844284058,
      "learning_rate": 1.9605722732787628e-05,
      "loss": 0.0098,
      "mean_token_accuracy": 0.9960446953773499,
      "num_tokens": 30207167.0,
      "step": 470
    },
    {
      "epoch": 0.23387493845396357,
      "grad_norm": 0.03414066135883331,
      "learning_rate": 1.9564876962623197e-05,
      "loss": 0.0134,
      "mean_token_accuracy": 0.9948711514472961,
      "num_tokens": 30528611.0,
      "step": 475
    },
    {
      "epoch": 0.2363367799113737,
      "grad_norm": 0.029639434069395065,
      "learning_rate": 1.952365773185726e-05,
      "loss": 0.0136,
      "mean_token_accuracy": 0.9950312376022339,
      "num_tokens": 30850250.0,
      "step": 480
    },
    {
      "epoch": 0.23879862136878385,
      "grad_norm": 0.03463074937462807,
      "learning_rate": 1.9482067555346758e-05,
      "loss": 0.0132,
      "mean_token_accuracy": 0.9950294494628906,
      "num_tokens": 31172438.0,
      "step": 485
    },
    {
      "epoch": 0.24126046282619398,
      "grad_norm": 0.0427277535200119,
      "learning_rate": 1.94401089705807e-05,
      "loss": 0.0144,
      "mean_token_accuracy": 0.9947101235389709,
      "num_tokens": 31492658.0,
      "step": 490
    },
    {
      "epoch": 0.24372230428360414,
      "grad_norm": 0.026402706280350685,
      "learning_rate": 1.9397784537525315e-05,
      "loss": 0.0115,
      "mean_token_accuracy": 0.9953791737556458,
      "num_tokens": 31814691.0,
      "step": 495
    },
    {
      "epoch": 0.24618414574101427,
      "grad_norm": 0.03977755084633827,
      "learning_rate": 1.935509683846787e-05,
      "loss": 0.0116,
      "mean_token_accuracy": 0.9955008625984192,
      "num_tokens": 32136086.0,
      "step": 500
    },
    {
      "epoch": 0.24864598719842443,
      "grad_norm": 0.03381454944610596,
      "learning_rate": 1.9312048477859128e-05,
      "loss": 0.012,
      "mean_token_accuracy": 0.9952152490615844,
      "num_tokens": 32457275.0,
      "step": 505
    },
    {
      "epoch": 0.2511078286558346,
      "grad_norm": 0.04309482499957085,
      "learning_rate": 1.9268642082154432e-05,
      "loss": 0.0145,
      "mean_token_accuracy": 0.9947703242301941,
      "num_tokens": 32778499.0,
      "step": 510
    },
    {
      "epoch": 0.2535696701132447,
      "grad_norm": 0.026039602234959602,
      "learning_rate": 1.9224880299653475e-05,
      "loss": 0.0106,
      "mean_token_accuracy": 0.9957552552223206,
      "num_tokens": 33100172.0,
      "step": 515
    },
    {
      "epoch": 0.25603151157065485,
      "grad_norm": 0.03149384632706642,
      "learning_rate": 1.918076580033872e-05,
      "loss": 0.0111,
      "mean_token_accuracy": 0.9956293344497681,
      "num_tokens": 33420699.0,
      "step": 520
    },
    {
      "epoch": 0.258493353028065,
      "grad_norm": 0.042891692370176315,
      "learning_rate": 1.9136301275712485e-05,
      "loss": 0.0135,
      "mean_token_accuracy": 0.9950595378875733,
      "num_tokens": 33742306.0,
      "step": 525
    },
    {
      "epoch": 0.26095519448547516,
      "grad_norm": 0.031138205900788307,
      "learning_rate": 1.9091489438632754e-05,
      "loss": 0.0124,
      "mean_token_accuracy": 0.9950516223907471,
      "num_tokens": 34064125.0,
      "step": 530
    },
    {
      "epoch": 0.2634170359428853,
      "grad_norm": 0.03716178983449936,
      "learning_rate": 1.9046333023147636e-05,
      "loss": 0.0116,
      "mean_token_accuracy": 0.9954241394996644,
      "num_tokens": 34385864.0,
      "step": 535
    },
    {
      "epoch": 0.2658788774002954,
      "grad_norm": 0.031479284167289734,
      "learning_rate": 1.9000834784328574e-05,
      "loss": 0.0127,
      "mean_token_accuracy": 0.9949283838272095,
      "num_tokens": 34706971.0,
      "step": 540
    }
  ],
  "logging_steps": 5,
  "max_steps": 2031,
  "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": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.539652714412114e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}