{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9982507288629737,
  "eval_steps": 500,
  "global_step": 428,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011661807580174927,
      "grad_norm": 42.984135524813716,
      "learning_rate": 2.3255813953488376e-06,
      "loss": 0.7996,
      "step": 5
    },
    {
      "epoch": 0.023323615160349854,
      "grad_norm": 34.540550987887656,
      "learning_rate": 4.651162790697675e-06,
      "loss": 0.9118,
      "step": 10
    },
    {
      "epoch": 0.03498542274052478,
      "grad_norm": 13.382857138229893,
      "learning_rate": 6.976744186046513e-06,
      "loss": 0.809,
      "step": 15
    },
    {
      "epoch": 0.04664723032069971,
      "grad_norm": 16.118929797627043,
      "learning_rate": 9.30232558139535e-06,
      "loss": 0.6494,
      "step": 20
    },
    {
      "epoch": 0.05830903790087463,
      "grad_norm": 12.84126148340563,
      "learning_rate": 1.1627906976744187e-05,
      "loss": 0.6804,
      "step": 25
    },
    {
      "epoch": 0.06997084548104957,
      "grad_norm": 11.615382887994867,
      "learning_rate": 1.3953488372093025e-05,
      "loss": 0.742,
      "step": 30
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 9.64223874983612,
      "learning_rate": 1.6279069767441862e-05,
      "loss": 0.7071,
      "step": 35
    },
    {
      "epoch": 0.09329446064139942,
      "grad_norm": 15.158090621941907,
      "learning_rate": 1.86046511627907e-05,
      "loss": 0.7067,
      "step": 40
    },
    {
      "epoch": 0.10495626822157435,
      "grad_norm": 11.684269090645673,
      "learning_rate": 1.9998668323785298e-05,
      "loss": 0.773,
      "step": 45
    },
    {
      "epoch": 0.11661807580174927,
      "grad_norm": 10.880832162601031,
      "learning_rate": 1.9983691039261358e-05,
      "loss": 0.8095,
      "step": 50
    },
    {
      "epoch": 0.1282798833819242,
      "grad_norm": 9.366717268177585,
      "learning_rate": 1.995209688628471e-05,
      "loss": 0.7483,
      "step": 55
    },
    {
      "epoch": 0.13994169096209913,
      "grad_norm": 8.249786072407542,
      "learning_rate": 1.9903938450204972e-05,
      "loss": 0.76,
      "step": 60
    },
    {
      "epoch": 0.15160349854227406,
      "grad_norm": 10.168494788619096,
      "learning_rate": 1.98392958859863e-05,
      "loss": 0.7775,
      "step": 65
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 9.913819683231004,
      "learning_rate": 1.97582767847973e-05,
      "loss": 0.8216,
      "step": 70
    },
    {
      "epoch": 0.1749271137026239,
      "grad_norm": 10.032392176068132,
      "learning_rate": 1.9661015994936204e-05,
      "loss": 0.817,
      "step": 75
    },
    {
      "epoch": 0.18658892128279883,
      "grad_norm": 8.410150731378423,
      "learning_rate": 1.9547675397389144e-05,
      "loss": 0.808,
      "step": 80
    },
    {
      "epoch": 0.19825072886297376,
      "grad_norm": 9.863100877355185,
      "learning_rate": 1.941844363639525e-05,
      "loss": 0.8507,
      "step": 85
    },
    {
      "epoch": 0.2099125364431487,
      "grad_norm": 8.89188615237443,
      "learning_rate": 1.927353580546692e-05,
      "loss": 0.8161,
      "step": 90
    },
    {
      "epoch": 0.22157434402332363,
      "grad_norm": 8.531706916482218,
      "learning_rate": 1.91131930893879e-05,
      "loss": 0.8066,
      "step": 95
    },
    {
      "epoch": 0.23323615160349853,
      "grad_norm": 7.458499940704951,
      "learning_rate": 1.8937682362785025e-05,
      "loss": 0.7976,
      "step": 100
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 9.821230792634003,
      "learning_rate": 1.8747295745941705e-05,
      "loss": 0.745,
      "step": 105
    },
    {
      "epoch": 0.2565597667638484,
      "grad_norm": 7.927784309119138,
      "learning_rate": 1.8542350118592585e-05,
      "loss": 0.7847,
      "step": 110
    },
    {
      "epoch": 0.26822157434402333,
      "grad_norm": 7.469324880697332,
      "learning_rate": 1.8323186592508474e-05,
      "loss": 0.732,
      "step": 115
    },
    {
      "epoch": 0.27988338192419826,
      "grad_norm": 7.78062857430588,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.8037,
      "step": 120
    },
    {
      "epoch": 0.2915451895043732,
      "grad_norm": 7.9449659800223245,
      "learning_rate": 1.7843688005531227e-05,
      "loss": 0.8004,
      "step": 125
    },
    {
      "epoch": 0.3032069970845481,
      "grad_norm": 6.980347848053137,
      "learning_rate": 1.75841510227148e-05,
      "loss": 0.8104,
      "step": 130
    },
    {
      "epoch": 0.31486880466472306,
      "grad_norm": 6.932872697470111,
      "learning_rate": 1.7311990968994598e-05,
      "loss": 0.784,
      "step": 135
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 7.03014955634306,
      "learning_rate": 1.7027660827920798e-05,
      "loss": 0.7162,
      "step": 140
    },
    {
      "epoch": 0.33819241982507287,
      "grad_norm": 9.027538747767453,
      "learning_rate": 1.6731633838952905e-05,
      "loss": 0.8222,
      "step": 145
    },
    {
      "epoch": 0.3498542274052478,
      "grad_norm": 7.2129295786721555,
      "learning_rate": 1.6424402709799404e-05,
      "loss": 0.7633,
      "step": 150
    },
    {
      "epoch": 0.36151603498542273,
      "grad_norm": 9.545693558216767,
      "learning_rate": 1.6106478796354382e-05,
      "loss": 0.8089,
      "step": 155
    },
    {
      "epoch": 0.37317784256559766,
      "grad_norm": 6.988871661431575,
      "learning_rate": 1.577839125159613e-05,
      "loss": 0.7499,
      "step": 160
    },
    {
      "epoch": 0.3848396501457726,
      "grad_norm": 6.859494877590503,
      "learning_rate": 1.5440686144864207e-05,
      "loss": 0.7838,
      "step": 165
    },
    {
      "epoch": 0.3965014577259475,
      "grad_norm": 10.280934791815703,
      "learning_rate": 1.5093925552980934e-05,
      "loss": 0.7613,
      "step": 170
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 6.569790871142721,
      "learning_rate": 1.4738686624729987e-05,
      "loss": 0.7123,
      "step": 175
    },
    {
      "epoch": 0.4198250728862974,
      "grad_norm": 6.872979375161206,
      "learning_rate": 1.4375560620249209e-05,
      "loss": 0.7469,
      "step": 180
    },
    {
      "epoch": 0.4314868804664723,
      "grad_norm": 7.636079144384279,
      "learning_rate": 1.400515192693645e-05,
      "loss": 0.7756,
      "step": 185
    },
    {
      "epoch": 0.44314868804664725,
      "grad_norm": 6.7063579238681115,
      "learning_rate": 1.362807705350641e-05,
      "loss": 0.761,
      "step": 190
    },
    {
      "epoch": 0.45481049562682213,
      "grad_norm": 10.606488159624234,
      "learning_rate": 1.3244963603872707e-05,
      "loss": 0.7783,
      "step": 195
    },
    {
      "epoch": 0.46647230320699706,
      "grad_norm": 10.490595832658897,
      "learning_rate": 1.285644923256311e-05,
      "loss": 0.752,
      "step": 200
    },
    {
      "epoch": 0.478134110787172,
      "grad_norm": 6.474060545032819,
      "learning_rate": 1.24631805834065e-05,
      "loss": 0.7329,
      "step": 205
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 6.195922083451403,
      "learning_rate": 1.2065812213258051e-05,
      "loss": 0.736,
      "step": 210
    },
    {
      "epoch": 0.5014577259475219,
      "grad_norm": 6.590048221376104,
      "learning_rate": 1.1665005502553912e-05,
      "loss": 0.7913,
      "step": 215
    },
    {
      "epoch": 0.5131195335276968,
      "grad_norm": 8.125319637789433,
      "learning_rate": 1.126142755450878e-05,
      "loss": 0.706,
      "step": 220
    },
    {
      "epoch": 0.5247813411078717,
      "grad_norm": 5.990671270414111,
      "learning_rate": 1.08557500847884e-05,
      "loss": 0.6663,
      "step": 225
    },
    {
      "epoch": 0.5364431486880467,
      "grad_norm": 5.457424439670184,
      "learning_rate": 1.044864830350515e-05,
      "loss": 0.6863,
      "step": 230
    },
    {
      "epoch": 0.5481049562682215,
      "grad_norm": 5.029069081649806,
      "learning_rate": 1.0040799791397444e-05,
      "loss": 0.7419,
      "step": 235
    },
    {
      "epoch": 0.5597667638483965,
      "grad_norm": 5.97976812053812,
      "learning_rate": 9.632883372063458e-06,
      "loss": 0.7409,
      "step": 240
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 5.73404097091946,
      "learning_rate": 9.225577982126234e-06,
      "loss": 0.721,
      "step": 245
    },
    {
      "epoch": 0.5830903790087464,
      "grad_norm": 7.281992128147145,
      "learning_rate": 8.819561541210698e-06,
      "loss": 0.7259,
      "step": 250
    },
    {
      "epoch": 0.5947521865889213,
      "grad_norm": 6.711399802745363,
      "learning_rate": 8.415509823613332e-06,
      "loss": 0.7184,
      "step": 255
    },
    {
      "epoch": 0.6064139941690962,
      "grad_norm": 5.973201176677851,
      "learning_rate": 8.014095333542548e-06,
      "loss": 0.6783,
      "step": 260
    },
    {
      "epoch": 0.6180758017492711,
      "grad_norm": 5.883172455604572,
      "learning_rate": 7.615986185801807e-06,
      "loss": 0.6978,
      "step": 265
    },
    {
      "epoch": 0.6297376093294461,
      "grad_norm": 7.527367196282041,
      "learning_rate": 7.221844993778464e-06,
      "loss": 0.7021,
      "step": 270
    },
    {
      "epoch": 0.641399416909621,
      "grad_norm": 6.248190397413816,
      "learning_rate": 6.832327766589177e-06,
      "loss": 0.645,
      "step": 275
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 8.28544581437624,
      "learning_rate": 6.4480828172174714e-06,
      "loss": 0.7004,
      "step": 280
    },
    {
      "epoch": 0.6647230320699709,
      "grad_norm": 6.406350729534571,
      "learning_rate": 6.069749683460765e-06,
      "loss": 0.6751,
      "step": 285
    },
    {
      "epoch": 0.6763848396501457,
      "grad_norm": 5.604361979041009,
      "learning_rate": 5.6979580634828125e-06,
      "loss": 0.6728,
      "step": 290
    },
    {
      "epoch": 0.6880466472303207,
      "grad_norm": 6.500294469087635,
      "learning_rate": 5.333326767743263e-06,
      "loss": 0.7096,
      "step": 295
    },
    {
      "epoch": 0.6997084548104956,
      "grad_norm": 6.173069337697736,
      "learning_rate": 4.976462689048718e-06,
      "loss": 0.6718,
      "step": 300
    },
    {
      "epoch": 0.7113702623906706,
      "grad_norm": 5.7326380834003094,
      "learning_rate": 4.6279597924395434e-06,
      "loss": 0.6785,
      "step": 305
    },
    {
      "epoch": 0.7230320699708455,
      "grad_norm": 6.5217701514071935,
      "learning_rate": 4.2883981265936884e-06,
      "loss": 0.661,
      "step": 310
    },
    {
      "epoch": 0.7346938775510204,
      "grad_norm": 5.886240007868726,
      "learning_rate": 3.958342858392893e-06,
      "loss": 0.6106,
      "step": 315
    },
    {
      "epoch": 0.7463556851311953,
      "grad_norm": 5.8543609692801315,
      "learning_rate": 3.6383433322582028e-06,
      "loss": 0.6282,
      "step": 320
    },
    {
      "epoch": 0.7580174927113703,
      "grad_norm": 5.540207550170581,
      "learning_rate": 3.3289321558203767e-06,
      "loss": 0.6551,
      "step": 325
    },
    {
      "epoch": 0.7696793002915452,
      "grad_norm": 6.364763436662215,
      "learning_rate": 3.0306243134470668e-06,
      "loss": 0.6425,
      "step": 330
    },
    {
      "epoch": 0.7813411078717201,
      "grad_norm": 6.546697364781114,
      "learning_rate": 2.7439163091021525e-06,
      "loss": 0.6829,
      "step": 335
    },
    {
      "epoch": 0.793002915451895,
      "grad_norm": 5.54305433545965,
      "learning_rate": 2.469285339963892e-06,
      "loss": 0.608,
      "step": 340
    },
    {
      "epoch": 0.8046647230320699,
      "grad_norm": 5.2130427650497335,
      "learning_rate": 2.207188502177313e-06,
      "loss": 0.6752,
      "step": 345
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 5.966791369980658,
      "learning_rate": 1.958062030062795e-06,
      "loss": 0.6451,
      "step": 350
    },
    {
      "epoch": 0.8279883381924198,
      "grad_norm": 5.8319616356981685,
      "learning_rate": 1.722320570047089e-06,
      "loss": 0.6544,
      "step": 355
    },
    {
      "epoch": 0.8396501457725948,
      "grad_norm": 5.587246353476323,
      "learning_rate": 1.500356490525261e-06,
      "loss": 0.6203,
      "step": 360
    },
    {
      "epoch": 0.8513119533527697,
      "grad_norm": 4.792540178325021,
      "learning_rate": 1.2925392288022299e-06,
      "loss": 0.613,
      "step": 365
    },
    {
      "epoch": 0.8629737609329446,
      "grad_norm": 5.761492562329574,
      "learning_rate": 1.099214676200816e-06,
      "loss": 0.5613,
      "step": 370
    },
    {
      "epoch": 0.8746355685131195,
      "grad_norm": 6.12518244267695,
      "learning_rate": 9.207046023597866e-07,
      "loss": 0.644,
      "step": 375
    },
    {
      "epoch": 0.8862973760932945,
      "grad_norm": 6.335150291563363,
      "learning_rate": 7.573061196800414e-07,
      "loss": 0.6359,
      "step": 380
    },
    {
      "epoch": 0.8979591836734694,
      "grad_norm": 5.644774834626501,
      "learning_rate": 6.092911888103404e-07,
      "loss": 0.6445,
      "step": 385
    },
    {
      "epoch": 0.9096209912536443,
      "grad_norm": 6.208859110734176,
      "learning_rate": 4.769061659956464e-07,
      "loss": 0.6238,
      "step": 390
    },
    {
      "epoch": 0.9212827988338192,
      "grad_norm": 6.180815291205464,
      "learning_rate": 3.603713930414676e-07,
      "loss": 0.6209,
      "step": 395
    },
    {
      "epoch": 0.9329446064139941,
      "grad_norm": 5.580445503476568,
      "learning_rate": 2.5988083057666534e-07,
      "loss": 0.6283,
      "step": 400
    },
    {
      "epoch": 0.9446064139941691,
      "grad_norm": 6.358276656532779,
      "learning_rate": 1.7560173522513268e-07,
      "loss": 0.6104,
      "step": 405
    },
    {
      "epoch": 0.956268221574344,
      "grad_norm": 5.486425722613415,
      "learning_rate": 1.0767438122364914e-07,
      "loss": 0.6326,
      "step": 410
    },
    {
      "epoch": 0.967930029154519,
      "grad_norm": 6.212119018151375,
      "learning_rate": 5.621182694925731e-08,
      "loss": 0.5795,
      "step": 415
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 5.964963969186111,
      "learning_rate": 2.1299726744747896e-08,
      "loss": 0.6607,
      "step": 420
    },
    {
      "epoch": 0.9912536443148688,
      "grad_norm": 6.566929080347384,
      "learning_rate": 2.9961883554674443e-09,
      "loss": 0.6411,
      "step": 425
    },
    {
      "epoch": 0.9982507288629737,
      "eval_loss": 0.5953396558761597,
      "eval_runtime": 106.3241,
      "eval_samples_per_second": 2.633,
      "eval_steps_per_second": 0.329,
      "step": 428
    },
    {
      "epoch": 0.9982507288629737,
      "step": 428,
      "total_flos": 11492314030080.0,
      "train_loss": 0.7172290003188303,
      "train_runtime": 14976.0603,
      "train_samples_per_second": 0.916,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 5,
  "max_steps": 428,
  "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": 11492314030080.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}