{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 516,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05813953488372093,
      "grad_norm": 2.372250556945801,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 0.5653,
      "step": 10
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 1.589673399925232,
      "learning_rate": 3.846153846153847e-06,
      "loss": 0.4892,
      "step": 20
    },
    {
      "epoch": 0.1744186046511628,
      "grad_norm": 0.6917356848716736,
      "learning_rate": 5.769230769230769e-06,
      "loss": 0.4254,
      "step": 30
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.5806995630264282,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3983,
      "step": 40
    },
    {
      "epoch": 0.29069767441860467,
      "grad_norm": 0.48242250084877014,
      "learning_rate": 9.615384615384616e-06,
      "loss": 0.3774,
      "step": 50
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 0.4931712746620178,
      "learning_rate": 9.99266706925562e-06,
      "loss": 0.3831,
      "step": 60
    },
    {
      "epoch": 0.4069767441860465,
      "grad_norm": 0.4491875469684601,
      "learning_rate": 9.962913897416029e-06,
      "loss": 0.3735,
      "step": 70
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.492576003074646,
      "learning_rate": 9.91041841371078e-06,
      "loss": 0.3734,
      "step": 80
    },
    {
      "epoch": 0.5232558139534884,
      "grad_norm": 0.4783257246017456,
      "learning_rate": 9.835421176144035e-06,
      "loss": 0.3691,
      "step": 90
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 0.502691388130188,
      "learning_rate": 9.738265855914014e-06,
      "loss": 0.3665,
      "step": 100
    },
    {
      "epoch": 0.6395348837209303,
      "grad_norm": 0.4875294268131256,
      "learning_rate": 9.619397662556434e-06,
      "loss": 0.3634,
      "step": 110
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.49050816893577576,
      "learning_rate": 9.479361303793441e-06,
      "loss": 0.3606,
      "step": 120
    },
    {
      "epoch": 0.7558139534883721,
      "grad_norm": 0.5096519589424133,
      "learning_rate": 9.318798489436917e-06,
      "loss": 0.3625,
      "step": 130
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 0.49713432788848877,
      "learning_rate": 9.138444990784455e-06,
      "loss": 0.3565,
      "step": 140
    },
    {
      "epoch": 0.872093023255814,
      "grad_norm": 0.5656277537345886,
      "learning_rate": 8.93912726898311e-06,
      "loss": 0.3537,
      "step": 150
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.46856340765953064,
      "learning_rate": 8.721758687811353e-06,
      "loss": 0.357,
      "step": 160
    },
    {
      "epoch": 0.9883720930232558,
      "grad_norm": 0.478761225938797,
      "learning_rate": 8.487335328233912e-06,
      "loss": 0.3524,
      "step": 170
    },
    {
      "epoch": 1.0465116279069768,
      "grad_norm": 0.5402882695198059,
      "learning_rate": 8.23693142390914e-06,
      "loss": 0.3196,
      "step": 180
    },
    {
      "epoch": 1.1046511627906976,
      "grad_norm": 0.5450319647789001,
      "learning_rate": 7.97169443856545e-06,
      "loss": 0.3046,
      "step": 190
    },
    {
      "epoch": 1.1627906976744187,
      "grad_norm": 0.5245667099952698,
      "learning_rate": 7.692839807804522e-06,
      "loss": 0.3052,
      "step": 200
    },
    {
      "epoch": 1.2209302325581395,
      "grad_norm": 0.5302076935768127,
      "learning_rate": 7.401645369426697e-06,
      "loss": 0.3057,
      "step": 210
    },
    {
      "epoch": 1.2790697674418605,
      "grad_norm": 0.4999724328517914,
      "learning_rate": 7.099445507801324e-06,
      "loss": 0.3073,
      "step": 220
    },
    {
      "epoch": 1.3372093023255813,
      "grad_norm": 0.5193457007408142,
      "learning_rate": 6.7876250391152e-06,
      "loss": 0.308,
      "step": 230
    },
    {
      "epoch": 1.3953488372093024,
      "grad_norm": 0.5382803678512573,
      "learning_rate": 6.467612865519674e-06,
      "loss": 0.3071,
      "step": 240
    },
    {
      "epoch": 1.4534883720930232,
      "grad_norm": 0.510870635509491,
      "learning_rate": 6.14087542725593e-06,
      "loss": 0.3063,
      "step": 250
    },
    {
      "epoch": 1.5116279069767442,
      "grad_norm": 0.5443557500839233,
      "learning_rate": 5.808909982763825e-06,
      "loss": 0.3017,
      "step": 260
    },
    {
      "epoch": 1.5697674418604652,
      "grad_norm": 0.4984321594238281,
      "learning_rate": 5.473237747567805e-06,
      "loss": 0.3047,
      "step": 270
    },
    {
      "epoch": 1.627906976744186,
      "grad_norm": 0.538632869720459,
      "learning_rate": 5.1353969233806735e-06,
      "loss": 0.3055,
      "step": 280
    },
    {
      "epoch": 1.6860465116279069,
      "grad_norm": 0.514262855052948,
      "learning_rate": 4.796935649368936e-06,
      "loss": 0.2999,
      "step": 290
    },
    {
      "epoch": 1.744186046511628,
      "grad_norm": 0.4963250458240509,
      "learning_rate": 4.459404907880293e-06,
      "loss": 0.3064,
      "step": 300
    },
    {
      "epoch": 1.802325581395349,
      "grad_norm": 0.5119029879570007,
      "learning_rate": 4.1243514171423465e-06,
      "loss": 0.3,
      "step": 310
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": 0.5278229713439941,
      "learning_rate": 3.7933105435014727e-06,
      "loss": 0.3026,
      "step": 320
    },
    {
      "epoch": 1.9186046511627906,
      "grad_norm": 0.5023918151855469,
      "learning_rate": 3.4677992656811054e-06,
      "loss": 0.2955,
      "step": 330
    },
    {
      "epoch": 1.9767441860465116,
      "grad_norm": 0.5270472168922424,
      "learning_rate": 3.149309223300428e-06,
      "loss": 0.3035,
      "step": 340
    },
    {
      "epoch": 2.0348837209302326,
      "grad_norm": 0.540235698223114,
      "learning_rate": 2.839299881508272e-06,
      "loss": 0.2671,
      "step": 350
    },
    {
      "epoch": 2.0930232558139537,
      "grad_norm": 0.5879262685775757,
      "learning_rate": 2.5391918430549635e-06,
      "loss": 0.2546,
      "step": 360
    },
    {
      "epoch": 2.1511627906976742,
      "grad_norm": 0.5497400164604187,
      "learning_rate": 2.250360338449226e-06,
      "loss": 0.2551,
      "step": 370
    },
    {
      "epoch": 2.2093023255813953,
      "grad_norm": 0.555575966835022,
      "learning_rate": 1.9741289240311757e-06,
      "loss": 0.2614,
      "step": 380
    },
    {
      "epoch": 2.2674418604651163,
      "grad_norm": 0.5114222764968872,
      "learning_rate": 1.7117634168396774e-06,
      "loss": 0.2602,
      "step": 390
    },
    {
      "epoch": 2.3255813953488373,
      "grad_norm": 0.5456900000572205,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.2524,
      "step": 400
    },
    {
      "epoch": 2.383720930232558,
      "grad_norm": 0.5279563665390015,
      "learning_rate": 1.2333701836832812e-06,
      "loss": 0.2566,
      "step": 410
    },
    {
      "epoch": 2.441860465116279,
      "grad_norm": 0.531123697757721,
      "learning_rate": 1.0195346714717813e-06,
      "loss": 0.2554,
      "step": 420
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.5793979167938232,
      "learning_rate": 8.239394482805996e-07,
      "loss": 0.2538,
      "step": 430
    },
    {
      "epoch": 2.558139534883721,
      "grad_norm": 0.5081056356430054,
      "learning_rate": 6.474808197191401e-07,
      "loss": 0.2613,
      "step": 440
    },
    {
      "epoch": 2.616279069767442,
      "grad_norm": 0.5300784111022949,
      "learning_rate": 4.9096739888146e-07,
      "loss": 0.252,
      "step": 450
    },
    {
      "epoch": 2.6744186046511627,
      "grad_norm": 0.5155430436134338,
      "learning_rate": 3.5511640091604293e-07,
      "loss": 0.2584,
      "step": 460
    },
    {
      "epoch": 2.7325581395348837,
      "grad_norm": 0.5395690202713013,
      "learning_rate": 2.4055035642222225e-07,
      "loss": 0.2587,
      "step": 470
    },
    {
      "epoch": 2.7906976744186047,
      "grad_norm": 0.5123968720436096,
      "learning_rate": 1.477942587339426e-07,
      "loss": 0.2539,
      "step": 480
    },
    {
      "epoch": 2.8488372093023253,
      "grad_norm": 0.5551957488059998,
      "learning_rate": 7.727315816331515e-08,
      "loss": 0.2587,
      "step": 490
    },
    {
      "epoch": 2.9069767441860463,
      "grad_norm": 0.5201088190078735,
      "learning_rate": 2.9310214228202016e-08,
      "loss": 0.2567,
      "step": 500
    },
    {
      "epoch": 2.9651162790697674,
      "grad_norm": 0.5173829197883606,
      "learning_rate": 4.125214789427734e-09,
      "loss": 0.2572,
      "step": 510
    },
    {
      "epoch": 3.0,
      "step": 516,
      "total_flos": 1.4133392230328566e+18,
      "train_loss": 0.3167468981687413,
      "train_runtime": 15514.5251,
      "train_samples_per_second": 4.236,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 516,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4133392230328566e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}