{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02718129926610492,
  "eval_steps": 1000,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 3.5193,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 3.3989,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 3.5806,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016,
      "loss": 3.5366,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 3.465,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 3.2803,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019789473684210526,
      "loss": 3.7859,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019578947368421054,
      "loss": 2.3265,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019578947368421054,
      "loss": 2.5382,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001936842105263158,
      "loss": 2.3886,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019157894736842104,
      "loss": 3.1107,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018947368421052632,
      "loss": 2.2642,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001873684210526316,
      "loss": 2.7191,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018526315789473685,
      "loss": 2.9972,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001831578947368421,
      "loss": 2.3003,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018105263157894739,
      "loss": 2.0452,
      "step": 16
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017894736842105264,
      "loss": 2.3579,
      "step": 17
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001768421052631579,
      "loss": 2.1803,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017473684210526317,
      "loss": 2.1071,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017263157894736842,
      "loss": 2.3485,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001705263157894737,
      "loss": 2.0367,
      "step": 21
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016842105263157895,
      "loss": 2.186,
      "step": 22
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016631578947368423,
      "loss": 2.2801,
      "step": 23
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016421052631578948,
      "loss": 2.192,
      "step": 24
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016210526315789473,
      "loss": 2.2347,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016,
      "loss": 2.0847,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015789473684210527,
      "loss": 1.8679,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015578947368421052,
      "loss": 1.9996,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001536842105263158,
      "loss": 1.8533,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015157894736842108,
      "loss": 2.424,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014947368421052633,
      "loss": 1.902,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014736842105263158,
      "loss": 2.0139,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014526315789473686,
      "loss": 2.383,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001431578947368421,
      "loss": 1.8211,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014105263157894736,
      "loss": 2.6536,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00013894736842105264,
      "loss": 2.1471,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001368421052631579,
      "loss": 2.2323,
      "step": 37
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00013473684210526317,
      "loss": 1.9407,
      "step": 38
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00013263157894736842,
      "loss": 1.8675,
      "step": 39
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001305263157894737,
      "loss": 2.7075,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012842105263157895,
      "loss": 2.306,
      "step": 41
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001263157894736842,
      "loss": 2.2472,
      "step": 42
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012421052631578949,
      "loss": 2.241,
      "step": 43
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012210526315789474,
      "loss": 2.3056,
      "step": 44
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012,
      "loss": 2.0625,
      "step": 45
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00011789473684210525,
      "loss": 1.5984,
      "step": 46
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00011578947368421053,
      "loss": 1.709,
      "step": 47
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001136842105263158,
      "loss": 2.2164,
      "step": 48
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00011157894736842105,
      "loss": 1.7211,
      "step": 49
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010947368421052633,
      "loss": 1.6704,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010736842105263158,
      "loss": 2.0444,
      "step": 51
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010526315789473685,
      "loss": 1.8508,
      "step": 52
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010315789473684211,
      "loss": 1.7723,
      "step": 53
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010105263157894738,
      "loss": 2.063,
      "step": 54
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.894736842105263e-05,
      "loss": 1.8545,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.68421052631579e-05,
      "loss": 2.3184,
      "step": 56
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.473684210526316e-05,
      "loss": 1.4654,
      "step": 57
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.263157894736843e-05,
      "loss": 1.8831,
      "step": 58
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.052631578947369e-05,
      "loss": 1.8371,
      "step": 59
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.842105263157894e-05,
      "loss": 2.2984,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.631578947368421e-05,
      "loss": 1.6057,
      "step": 61
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.421052631578948e-05,
      "loss": 1.8887,
      "step": 62
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.210526315789474e-05,
      "loss": 1.8164,
      "step": 63
    },
    {
      "epoch": 0.02,
      "learning_rate": 8e-05,
      "loss": 1.7534,
      "step": 64
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.789473684210526e-05,
      "loss": 1.457,
      "step": 65
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.578947368421054e-05,
      "loss": 1.8279,
      "step": 66
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.368421052631579e-05,
      "loss": 2.0363,
      "step": 67
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.157894736842105e-05,
      "loss": 1.8754,
      "step": 68
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.947368421052632e-05,
      "loss": 1.9673,
      "step": 69
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.736842105263159e-05,
      "loss": 1.8458,
      "step": 70
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.526315789473685e-05,
      "loss": 1.6558,
      "step": 71
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.31578947368421e-05,
      "loss": 1.6778,
      "step": 72
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.105263157894737e-05,
      "loss": 2.5774,
      "step": 73
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.894736842105263e-05,
      "loss": 2.1418,
      "step": 74
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.68421052631579e-05,
      "loss": 1.8428,
      "step": 75
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.4736842105263165e-05,
      "loss": 2.1565,
      "step": 76
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 2.0893,
      "step": 77
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.052631578947369e-05,
      "loss": 1.7193,
      "step": 78
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.842105263157895e-05,
      "loss": 2.0253,
      "step": 79
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.6315789473684214e-05,
      "loss": 1.8999,
      "step": 80
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.421052631578947e-05,
      "loss": 1.9748,
      "step": 81
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.210526315789474e-05,
      "loss": 2.0023,
      "step": 82
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 1.9539,
      "step": 83
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.789473684210527e-05,
      "loss": 1.6427,
      "step": 84
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.578947368421053e-05,
      "loss": 1.8795,
      "step": 85
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.368421052631579e-05,
      "loss": 1.9835,
      "step": 86
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.157894736842105e-05,
      "loss": 2.0199,
      "step": 87
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.9473684210526314e-05,
      "loss": 2.1671,
      "step": 88
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.7368421052631583e-05,
      "loss": 1.6357,
      "step": 89
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.5263157894736845e-05,
      "loss": 1.8582,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.3157894736842107e-05,
      "loss": 2.0198,
      "step": 91
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.105263157894737e-05,
      "loss": 1.5241,
      "step": 92
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.8947368421052634e-05,
      "loss": 2.3354,
      "step": 93
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6842105263157896e-05,
      "loss": 1.8607,
      "step": 94
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.4736842105263157e-05,
      "loss": 2.3244,
      "step": 95
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.2631578947368422e-05,
      "loss": 1.811,
      "step": 96
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 1.7307,
      "step": 97
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.421052631578948e-06,
      "loss": 1.7182,
      "step": 98
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.315789473684211e-06,
      "loss": 1.9487,
      "step": 99
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.210526315789474e-06,
      "loss": 1.9158,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 855403008294912.0,
  "trial_name": null,
  "trial_params": null
}