{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 41.758705139160156,
      "learning_rate": 4.9986614686909146e-05,
      "loss": 39.5171,
      "num_input_tokens_seen": 47056,
      "step": 5
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 35.72260665893555,
      "learning_rate": 4.994647308096509e-05,
      "loss": 3.2466,
      "num_input_tokens_seen": 93544,
      "step": 10
    },
    {
      "epoch": 0.25,
      "grad_norm": 40.3800163269043,
      "learning_rate": 4.987961816680492e-05,
      "loss": 3.3122,
      "num_input_tokens_seen": 141120,
      "step": 15
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 22.71551513671875,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 3.0265,
      "num_input_tokens_seen": 188544,
      "step": 20
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 16.711044311523438,
      "learning_rate": 4.966608330212198e-05,
      "loss": 2.6989,
      "num_input_tokens_seen": 235128,
      "step": 25
    },
    {
      "epoch": 0.5,
      "grad_norm": 10.093056678771973,
      "learning_rate": 4.951963201008076e-05,
      "loss": 2.2284,
      "num_input_tokens_seen": 281904,
      "step": 30
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 12.554229736328125,
      "learning_rate": 4.934692448193334e-05,
      "loss": 2.2164,
      "num_input_tokens_seen": 330096,
      "step": 35
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 20.774412155151367,
      "learning_rate": 4.914814565722671e-05,
      "loss": 2.6854,
      "num_input_tokens_seen": 376824,
      "step": 40
    },
    {
      "epoch": 0.75,
      "grad_norm": 12.924601554870605,
      "learning_rate": 4.892350839330522e-05,
      "loss": 2.4108,
      "num_input_tokens_seen": 424048,
      "step": 45
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 23.568218231201172,
      "learning_rate": 4.867325323737765e-05,
      "loss": 2.419,
      "num_input_tokens_seen": 470432,
      "step": 50
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 29.64082908630371,
      "learning_rate": 4.839764816893315e-05,
      "loss": 2.3183,
      "num_input_tokens_seen": 517624,
      "step": 55
    },
    {
      "epoch": 1.0,
      "grad_norm": 17.5496883392334,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 1.9734,
      "num_input_tokens_seen": 564920,
      "step": 60
    },
    {
      "epoch": 1.0833333333333333,
      "grad_norm": 14.56460189819336,
      "learning_rate": 4.7771595623029394e-05,
      "loss": 1.8086,
      "num_input_tokens_seen": 611240,
      "step": 65
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 11.394974708557129,
      "learning_rate": 4.742181853831721e-05,
      "loss": 2.4591,
      "num_input_tokens_seen": 658904,
      "step": 70
    },
    {
      "epoch": 1.25,
      "grad_norm": 5.737662315368652,
      "learning_rate": 4.7048031608708876e-05,
      "loss": 1.7169,
      "num_input_tokens_seen": 706480,
      "step": 75
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 18.580102920532227,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.809,
      "num_input_tokens_seen": 752904,
      "step": 80
    },
    {
      "epoch": 1.4166666666666667,
      "grad_norm": 18.77831268310547,
      "learning_rate": 4.6230054538164474e-05,
      "loss": 2.3907,
      "num_input_tokens_seen": 800304,
      "step": 85
    },
    {
      "epoch": 1.5,
      "grad_norm": 7.019700527191162,
      "learning_rate": 4.5786740307563636e-05,
      "loss": 2.0662,
      "num_input_tokens_seen": 846792,
      "step": 90
    },
    {
      "epoch": 1.5833333333333335,
      "grad_norm": 12.335309028625488,
      "learning_rate": 4.5321167114790385e-05,
      "loss": 2.0185,
      "num_input_tokens_seen": 894552,
      "step": 95
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 8.229971885681152,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 1.9831,
      "num_input_tokens_seen": 941040,
      "step": 100
    },
    {
      "epoch": 1.75,
      "grad_norm": 13.02308177947998,
      "learning_rate": 4.4325261334068426e-05,
      "loss": 2.0873,
      "num_input_tokens_seen": 987776,
      "step": 105
    },
    {
      "epoch": 1.8333333333333335,
      "grad_norm": 6.7481513023376465,
      "learning_rate": 4.379599518697444e-05,
      "loss": 1.9163,
      "num_input_tokens_seen": 1036072,
      "step": 110
    },
    {
      "epoch": 1.9166666666666665,
      "grad_norm": 8.03829288482666,
      "learning_rate": 4.324660181744589e-05,
      "loss": 1.4848,
      "num_input_tokens_seen": 1083328,
      "step": 115
    },
    {
      "epoch": 2.0,
      "grad_norm": 9.837620735168457,
      "learning_rate": 4.267766952966369e-05,
      "loss": 1.7719,
      "num_input_tokens_seen": 1129840,
      "step": 120
    },
    {
      "epoch": 2.0833333333333335,
      "grad_norm": 14.701643943786621,
      "learning_rate": 4.208980755057178e-05,
      "loss": 1.4241,
      "num_input_tokens_seen": 1177616,
      "step": 125
    },
    {
      "epoch": 2.1666666666666665,
      "grad_norm": 30.390798568725586,
      "learning_rate": 4.148364537750172e-05,
      "loss": 1.6277,
      "num_input_tokens_seen": 1225296,
      "step": 130
    },
    {
      "epoch": 2.25,
      "grad_norm": 9.536770820617676,
      "learning_rate": 4.085983210409114e-05,
      "loss": 0.9761,
      "num_input_tokens_seen": 1272160,
      "step": 135
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 11.45682430267334,
      "learning_rate": 4.021903572521802e-05,
      "loss": 1.0144,
      "num_input_tokens_seen": 1319432,
      "step": 140
    },
    {
      "epoch": 2.4166666666666665,
      "grad_norm": 11.267831802368164,
      "learning_rate": 3.956194242169506e-05,
      "loss": 1.3858,
      "num_input_tokens_seen": 1365992,
      "step": 145
    },
    {
      "epoch": 2.5,
      "grad_norm": 11.92896556854248,
      "learning_rate": 3.888925582549006e-05,
      "loss": 0.9969,
      "num_input_tokens_seen": 1412712,
      "step": 150
    },
    {
      "epoch": 2.5833333333333335,
      "grad_norm": 15.724352836608887,
      "learning_rate": 3.82016962662592e-05,
      "loss": 1.0721,
      "num_input_tokens_seen": 1459448,
      "step": 155
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 12.68454360961914,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.6622,
      "num_input_tokens_seen": 1506944,
      "step": 160
    },
    {
      "epoch": 2.75,
      "grad_norm": 6.482985496520996,
      "learning_rate": 3.678491842064995e-05,
      "loss": 1.059,
      "num_input_tokens_seen": 1554216,
      "step": 165
    },
    {
      "epoch": 2.8333333333333335,
      "grad_norm": 15.581390380859375,
      "learning_rate": 3.6057217255475034e-05,
      "loss": 0.774,
      "num_input_tokens_seen": 1600608,
      "step": 170
    },
    {
      "epoch": 2.9166666666666665,
      "grad_norm": 3.8697454929351807,
      "learning_rate": 3.5317675745109866e-05,
      "loss": 1.0403,
      "num_input_tokens_seen": 1647272,
      "step": 175
    },
    {
      "epoch": 3.0,
      "grad_norm": 54.316123962402344,
      "learning_rate": 3.456708580912725e-05,
      "loss": 2.173,
      "num_input_tokens_seen": 1694760,
      "step": 180
    },
    {
      "epoch": 3.0833333333333335,
      "grad_norm": 57.840152740478516,
      "learning_rate": 3.380625119803084e-05,
      "loss": 1.9583,
      "num_input_tokens_seen": 1741936,
      "step": 185
    },
    {
      "epoch": 3.1666666666666665,
      "grad_norm": 26.283540725708008,
      "learning_rate": 3.303598663257904e-05,
      "loss": 1.8407,
      "num_input_tokens_seen": 1788624,
      "step": 190
    },
    {
      "epoch": 3.25,
      "grad_norm": 15.37193489074707,
      "learning_rate": 3.225711693136156e-05,
      "loss": 1.1398,
      "num_input_tokens_seen": 1835336,
      "step": 195
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 53.772212982177734,
      "learning_rate": 3.147047612756302e-05,
      "loss": 0.8378,
      "num_input_tokens_seen": 1882584,
      "step": 200
    },
    {
      "epoch": 3.4166666666666665,
      "grad_norm": 11.857513427734375,
      "learning_rate": 3.0676906575859334e-05,
      "loss": 1.4633,
      "num_input_tokens_seen": 1929344,
      "step": 205
    },
    {
      "epoch": 3.5,
      "grad_norm": 5.734513282775879,
      "learning_rate": 2.9877258050403212e-05,
      "loss": 0.7289,
      "num_input_tokens_seen": 1976064,
      "step": 210
    },
    {
      "epoch": 3.5833333333333335,
      "grad_norm": 7.579070091247559,
      "learning_rate": 2.9072386834864724e-05,
      "loss": 0.9374,
      "num_input_tokens_seen": 2023392,
      "step": 215
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 15.9894437789917,
      "learning_rate": 2.8263154805501297e-05,
      "loss": 0.8814,
      "num_input_tokens_seen": 2070752,
      "step": 220
    },
    {
      "epoch": 3.75,
      "grad_norm": 17.481538772583008,
      "learning_rate": 2.7450428508239024e-05,
      "loss": 0.8873,
      "num_input_tokens_seen": 2118464,
      "step": 225
    },
    {
      "epoch": 3.8333333333333335,
      "grad_norm": 9.79324722290039,
      "learning_rate": 2.663507823075358e-05,
      "loss": 0.5864,
      "num_input_tokens_seen": 2165488,
      "step": 230
    },
    {
      "epoch": 3.9166666666666665,
      "grad_norm": 29.084766387939453,
      "learning_rate": 2.5817977070544407e-05,
      "loss": 0.7186,
      "num_input_tokens_seen": 2212104,
      "step": 235
    },
    {
      "epoch": 4.0,
      "grad_norm": 31.556673049926758,
      "learning_rate": 2.5e-05,
      "loss": 0.8153,
      "num_input_tokens_seen": 2259680,
      "step": 240
    },
    {
      "epoch": 4.083333333333333,
      "grad_norm": 13.266711235046387,
      "learning_rate": 2.41820229294556e-05,
      "loss": 0.5078,
      "num_input_tokens_seen": 2307200,
      "step": 245
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 9.629940032958984,
      "learning_rate": 2.3364921769246423e-05,
      "loss": 0.5766,
      "num_input_tokens_seen": 2354416,
      "step": 250
    },
    {
      "epoch": 4.25,
      "grad_norm": 3.589583396911621,
      "learning_rate": 2.2549571491760986e-05,
      "loss": 0.2176,
      "num_input_tokens_seen": 2400880,
      "step": 255
    },
    {
      "epoch": 4.333333333333333,
      "grad_norm": 7.237700939178467,
      "learning_rate": 2.173684519449872e-05,
      "loss": 0.6257,
      "num_input_tokens_seen": 2448016,
      "step": 260
    },
    {
      "epoch": 4.416666666666667,
      "grad_norm": 34.4775505065918,
      "learning_rate": 2.0927613165135285e-05,
      "loss": 0.4594,
      "num_input_tokens_seen": 2495032,
      "step": 265
    },
    {
      "epoch": 4.5,
      "grad_norm": 1.8570725917816162,
      "learning_rate": 2.0122741949596797e-05,
      "loss": 0.1073,
      "num_input_tokens_seen": 2542264,
      "step": 270
    },
    {
      "epoch": 4.583333333333333,
      "grad_norm": 26.749910354614258,
      "learning_rate": 1.932309342414067e-05,
      "loss": 0.7155,
      "num_input_tokens_seen": 2589368,
      "step": 275
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 11.495745658874512,
      "learning_rate": 1.852952387243698e-05,
      "loss": 1.0752,
      "num_input_tokens_seen": 2636712,
      "step": 280
    },
    {
      "epoch": 4.75,
      "grad_norm": 79.2107925415039,
      "learning_rate": 1.7742883068638447e-05,
      "loss": 0.7887,
      "num_input_tokens_seen": 2682328,
      "step": 285
    },
    {
      "epoch": 4.833333333333333,
      "grad_norm": 6.504589080810547,
      "learning_rate": 1.6964013367420966e-05,
      "loss": 0.1958,
      "num_input_tokens_seen": 2729264,
      "step": 290
    },
    {
      "epoch": 4.916666666666667,
      "grad_norm": 17.09076499938965,
      "learning_rate": 1.6193748801969163e-05,
      "loss": 0.1749,
      "num_input_tokens_seen": 2777032,
      "step": 295
    },
    {
      "epoch": 5.0,
      "grad_norm": 33.851985931396484,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.6815,
      "num_input_tokens_seen": 2824600,
      "step": 300
    }
  ],
  "logging_steps": 5,
  "max_steps": 480,
  "num_input_tokens_seen": 2824600,
  "num_train_epochs": 8,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.486389689735616e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}