{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6713286713286712,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 1.1463329792022705,
      "learning_rate": 0.0,
      "loss": 1.4132,
      "step": 1
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 0.8597254753112793,
      "learning_rate": 4e-05,
      "loss": 0.5978,
      "step": 2
    },
    {
      "epoch": 0.08391608391608392,
      "grad_norm": 1.196772575378418,
      "learning_rate": 8e-05,
      "loss": 1.3866,
      "step": 3
    },
    {
      "epoch": 0.11188811188811189,
      "grad_norm": 1.092492699623108,
      "learning_rate": 0.00012,
      "loss": 1.5973,
      "step": 4
    },
    {
      "epoch": 0.13986013986013987,
      "grad_norm": 1.1433535814285278,
      "learning_rate": 0.00016,
      "loss": 1.3213,
      "step": 5
    },
    {
      "epoch": 0.16783216783216784,
      "grad_norm": 1.0283416509628296,
      "learning_rate": 0.0002,
      "loss": 1.0864,
      "step": 6
    },
    {
      "epoch": 0.1958041958041958,
      "grad_norm": 1.0165659189224243,
      "learning_rate": 0.00019636363636363636,
      "loss": 0.7085,
      "step": 7
    },
    {
      "epoch": 0.22377622377622378,
      "grad_norm": 1.665509581565857,
      "learning_rate": 0.00019272727272727274,
      "loss": 0.9285,
      "step": 8
    },
    {
      "epoch": 0.2517482517482518,
      "grad_norm": 1.216216802597046,
      "learning_rate": 0.0001890909090909091,
      "loss": 1.1977,
      "step": 9
    },
    {
      "epoch": 0.27972027972027974,
      "grad_norm": 1.0458927154541016,
      "learning_rate": 0.00018545454545454545,
      "loss": 0.6523,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.8290866613388062,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.5238,
      "step": 11
    },
    {
      "epoch": 0.3356643356643357,
      "grad_norm": 1.3056946992874146,
      "learning_rate": 0.0001781818181818182,
      "loss": 0.9392,
      "step": 12
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.89715576171875,
      "learning_rate": 0.00017454545454545454,
      "loss": 0.6422,
      "step": 13
    },
    {
      "epoch": 0.3916083916083916,
      "grad_norm": 0.9536185264587402,
      "learning_rate": 0.0001709090909090909,
      "loss": 0.5259,
      "step": 14
    },
    {
      "epoch": 0.4195804195804196,
      "grad_norm": 2.0107877254486084,
      "learning_rate": 0.00016727272727272728,
      "loss": 1.6038,
      "step": 15
    },
    {
      "epoch": 0.44755244755244755,
      "grad_norm": 1.396262288093567,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9653,
      "step": 16
    },
    {
      "epoch": 0.4755244755244755,
      "grad_norm": 1.4076898097991943,
      "learning_rate": 0.00016,
      "loss": 1.2386,
      "step": 17
    },
    {
      "epoch": 0.5034965034965035,
      "grad_norm": 1.2920570373535156,
      "learning_rate": 0.00015636363636363637,
      "loss": 1.3082,
      "step": 18
    },
    {
      "epoch": 0.5314685314685315,
      "grad_norm": 0.8619877696037292,
      "learning_rate": 0.00015272727272727275,
      "loss": 0.4883,
      "step": 19
    },
    {
      "epoch": 0.5594405594405595,
      "grad_norm": 1.2779756784439087,
      "learning_rate": 0.0001490909090909091,
      "loss": 0.6035,
      "step": 20
    },
    {
      "epoch": 0.5874125874125874,
      "grad_norm": 1.474133014678955,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.8825,
      "step": 21
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.3216720819473267,
      "learning_rate": 0.00014181818181818184,
      "loss": 0.8638,
      "step": 22
    },
    {
      "epoch": 0.6433566433566433,
      "grad_norm": 1.0999218225479126,
      "learning_rate": 0.0001381818181818182,
      "loss": 0.6484,
      "step": 23
    },
    {
      "epoch": 0.6713286713286714,
      "grad_norm": 1.1263219118118286,
      "learning_rate": 0.00013454545454545455,
      "loss": 0.5965,
      "step": 24
    },
    {
      "epoch": 0.6993006993006993,
      "grad_norm": 1.020799994468689,
      "learning_rate": 0.00013090909090909093,
      "loss": 0.5809,
      "step": 25
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.032562494277954,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.6899,
      "step": 26
    },
    {
      "epoch": 0.7552447552447552,
      "grad_norm": 1.8015700578689575,
      "learning_rate": 0.00012363636363636364,
      "loss": 1.351,
      "step": 27
    },
    {
      "epoch": 0.7832167832167832,
      "grad_norm": 1.6515522003173828,
      "learning_rate": 0.00012,
      "loss": 1.3753,
      "step": 28
    },
    {
      "epoch": 0.8111888111888111,
      "grad_norm": 1.4862653017044067,
      "learning_rate": 0.00011636363636363636,
      "loss": 1.045,
      "step": 29
    },
    {
      "epoch": 0.8391608391608392,
      "grad_norm": 1.2828856706619263,
      "learning_rate": 0.00011272727272727272,
      "loss": 1.1004,
      "step": 30
    },
    {
      "epoch": 0.8671328671328671,
      "grad_norm": 0.9894140362739563,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.5355,
      "step": 31
    },
    {
      "epoch": 0.8951048951048951,
      "grad_norm": 1.5945513248443604,
      "learning_rate": 0.00010545454545454545,
      "loss": 1.1733,
      "step": 32
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 1.453596830368042,
      "learning_rate": 0.00010181818181818181,
      "loss": 1.1949,
      "step": 33
    },
    {
      "epoch": 0.951048951048951,
      "grad_norm": 1.5049810409545898,
      "learning_rate": 9.818181818181818e-05,
      "loss": 1.0341,
      "step": 34
    },
    {
      "epoch": 0.9790209790209791,
      "grad_norm": 1.3859373331069946,
      "learning_rate": 9.454545454545455e-05,
      "loss": 0.9874,
      "step": 35
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.5079317092895508,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.9925,
      "step": 36
    },
    {
      "epoch": 1.027972027972028,
      "grad_norm": 1.2381432056427002,
      "learning_rate": 8.727272727272727e-05,
      "loss": 0.9168,
      "step": 37
    },
    {
      "epoch": 1.055944055944056,
      "grad_norm": 1.0585517883300781,
      "learning_rate": 8.363636363636364e-05,
      "loss": 0.9168,
      "step": 38
    },
    {
      "epoch": 1.083916083916084,
      "grad_norm": 1.246953010559082,
      "learning_rate": 8e-05,
      "loss": 0.9327,
      "step": 39
    },
    {
      "epoch": 1.1118881118881119,
      "grad_norm": 1.295661211013794,
      "learning_rate": 7.636363636363637e-05,
      "loss": 0.8212,
      "step": 40
    },
    {
      "epoch": 1.1398601398601398,
      "grad_norm": 1.1516053676605225,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.5509,
      "step": 41
    },
    {
      "epoch": 1.167832167832168,
      "grad_norm": 0.874414324760437,
      "learning_rate": 6.90909090909091e-05,
      "loss": 0.3707,
      "step": 42
    },
    {
      "epoch": 1.1958041958041958,
      "grad_norm": 1.9163153171539307,
      "learning_rate": 6.545454545454546e-05,
      "loss": 1.2245,
      "step": 43
    },
    {
      "epoch": 1.2237762237762237,
      "grad_norm": 1.3832831382751465,
      "learning_rate": 6.181818181818182e-05,
      "loss": 0.8484,
      "step": 44
    },
    {
      "epoch": 1.2517482517482517,
      "grad_norm": 1.5212609767913818,
      "learning_rate": 5.818181818181818e-05,
      "loss": 0.563,
      "step": 45
    },
    {
      "epoch": 1.2797202797202798,
      "grad_norm": 1.087664008140564,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.399,
      "step": 46
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 1.8231722116470337,
      "learning_rate": 5.090909090909091e-05,
      "loss": 0.9092,
      "step": 47
    },
    {
      "epoch": 1.3356643356643356,
      "grad_norm": 1.591951608657837,
      "learning_rate": 4.7272727272727275e-05,
      "loss": 0.9348,
      "step": 48
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 1.0458203554153442,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 0.3926,
      "step": 49
    },
    {
      "epoch": 1.3916083916083917,
      "grad_norm": 1.0491923093795776,
      "learning_rate": 4e-05,
      "loss": 0.3799,
      "step": 50
    },
    {
      "epoch": 1.4195804195804196,
      "grad_norm": 1.5752729177474976,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.6908,
      "step": 51
    },
    {
      "epoch": 1.4475524475524475,
      "grad_norm": 1.6831164360046387,
      "learning_rate": 3.272727272727273e-05,
      "loss": 0.7934,
      "step": 52
    },
    {
      "epoch": 1.4755244755244754,
      "grad_norm": 1.3585453033447266,
      "learning_rate": 2.909090909090909e-05,
      "loss": 0.3979,
      "step": 53
    },
    {
      "epoch": 1.5034965034965035,
      "grad_norm": 1.3879740238189697,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 0.962,
      "step": 54
    },
    {
      "epoch": 1.5314685314685315,
      "grad_norm": 1.542452096939087,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 0.6852,
      "step": 55
    },
    {
      "epoch": 1.5594405594405596,
      "grad_norm": 1.3172391653060913,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.1097,
      "step": 56
    },
    {
      "epoch": 1.5874125874125875,
      "grad_norm": 1.2537016868591309,
      "learning_rate": 1.4545454545454545e-05,
      "loss": 0.6174,
      "step": 57
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 1.3360239267349243,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 0.8211,
      "step": 58
    },
    {
      "epoch": 1.6433566433566433,
      "grad_norm": 1.0257346630096436,
      "learning_rate": 7.272727272727272e-06,
      "loss": 0.374,
      "step": 59
    },
    {
      "epoch": 1.6713286713286712,
      "grad_norm": 1.2555755376815796,
      "learning_rate": 3.636363636363636e-06,
      "loss": 1.0604,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 4818101472165888.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}