{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03644314868804665,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00048590864917395527,
      "grad_norm": 0.0,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00048590864917395527,
      "eval_loss": NaN,
      "eval_runtime": 26.7373,
      "eval_samples_per_second": 32.427,
      "eval_steps_per_second": 16.232,
      "step": 1
    },
    {
      "epoch": 0.0009718172983479105,
      "grad_norm": 0.0,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0014577259475218659,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.001943634596695821,
      "grad_norm": 0.0,
      "learning_rate": 4.997620553954645e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0024295432458697765,
      "grad_norm": 0.0,
      "learning_rate": 4.990486745229364e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0029154518950437317,
      "grad_norm": 0.0,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.003401360544217687,
      "grad_norm": 0.0,
      "learning_rate": 4.962019382530521e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.003887269193391642,
      "grad_norm": 0.0,
      "learning_rate": 4.940740017799833e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.004373177842565598,
      "grad_norm": 0.0,
      "learning_rate": 4.914814565722671e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.004859086491739553,
      "grad_norm": 0.0,
      "learning_rate": 4.884292376870567e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.005344995140913508,
      "grad_norm": 0.0,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0058309037900874635,
      "grad_norm": 0.0,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.006316812439261419,
      "grad_norm": 0.0,
      "learning_rate": 4.765769467591625e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.006802721088435374,
      "grad_norm": 0.0,
      "learning_rate": 4.717527082945554e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.007288629737609329,
      "grad_norm": 0.0,
      "learning_rate": 4.665063509461097e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.007774538386783284,
      "grad_norm": 0.0,
      "learning_rate": 4.608478614532215e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.00826044703595724,
      "grad_norm": 0.0,
      "learning_rate": 4.54788011072248e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.008746355685131196,
      "grad_norm": 0.0,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.00923226433430515,
      "grad_norm": 0.0,
      "learning_rate": 4.415111107797445e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.009718172983479106,
      "grad_norm": 0.0,
      "learning_rate": 4.34319334202531e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.01020408163265306,
      "grad_norm": 0.0,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.010689990281827016,
      "grad_norm": 0.0,
      "learning_rate": 4.188975519039151e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.011175898931000973,
      "grad_norm": 0.0,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.011661807580174927,
      "grad_norm": 0.0,
      "learning_rate": 4.021903572521802e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.012147716229348883,
      "grad_norm": 0.0,
      "learning_rate": 3.933941090877615e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.012147716229348883,
      "eval_loss": NaN,
      "eval_runtime": 27.8605,
      "eval_samples_per_second": 31.119,
      "eval_steps_per_second": 15.578,
      "step": 25
    },
    {
      "epoch": 0.012633624878522837,
      "grad_norm": 0.0,
      "learning_rate": 3.84324902086706e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.013119533527696793,
      "grad_norm": 0.0,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.013605442176870748,
      "grad_norm": 0.0,
      "learning_rate": 3.654371533087586e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.014091350826044704,
      "grad_norm": 0.0,
      "learning_rate": 3.556545654351749e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.014577259475218658,
      "grad_norm": 0.0,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.015063168124392614,
      "grad_norm": 0.0,
      "learning_rate": 3.355050358314172e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.015549076773566569,
      "grad_norm": 0.0,
      "learning_rate": 3.251764498760683e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.016034985422740525,
      "grad_norm": 0.0,
      "learning_rate": 3.147047612756302e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.01652089407191448,
      "grad_norm": 0.0,
      "learning_rate": 3.0410990348452573e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.017006802721088437,
      "grad_norm": 0.0,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.01749271137026239,
      "grad_norm": 0.0,
      "learning_rate": 2.8263154805501297e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.017978620019436346,
      "grad_norm": 0.0,
      "learning_rate": 2.717889356869146e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.0184645286686103,
      "grad_norm": 0.0,
      "learning_rate": 2.6090484684133404e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.018950437317784258,
      "grad_norm": 0.0,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.019436345966958212,
      "grad_norm": 0.0,
      "learning_rate": 2.3909515315866605e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.019922254616132166,
      "grad_norm": 0.0,
      "learning_rate": 2.2821106431308544e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 0.0,
      "learning_rate": 2.173684519449872e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.02089407191448008,
      "grad_norm": 0.0,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.021379980563654033,
      "grad_norm": 0.0,
      "learning_rate": 1.958900965154743e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.021865889212827987,
      "grad_norm": 0.0,
      "learning_rate": 1.852952387243698e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.022351797862001945,
      "grad_norm": 0.0,
      "learning_rate": 1.7482355012393177e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.0228377065111759,
      "grad_norm": 0.0,
      "learning_rate": 1.6449496416858284e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.023323615160349854,
      "grad_norm": 0.0,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 0.0,
      "learning_rate": 1.443454345648252e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.024295432458697766,
      "grad_norm": 0.0,
      "learning_rate": 1.3456284669124158e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.024295432458697766,
      "eval_loss": NaN,
      "eval_runtime": 26.0571,
      "eval_samples_per_second": 33.273,
      "eval_steps_per_second": 16.656,
      "step": 50
    },
    {
      "epoch": 0.02478134110787172,
      "grad_norm": 0.0,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.025267249757045675,
      "grad_norm": 0.0,
      "learning_rate": 1.1567509791329401e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.02575315840621963,
      "grad_norm": 0.0,
      "learning_rate": 1.0660589091223855e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.026239067055393587,
      "grad_norm": 0.0,
      "learning_rate": 9.780964274781984e-06,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.02672497570456754,
      "grad_norm": 0.0,
      "learning_rate": 8.930309757836517e-06,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.027210884353741496,
      "grad_norm": 0.0,
      "learning_rate": 8.110244809608495e-06,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.027696793002915453,
      "grad_norm": 0.0,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.028182701652089408,
      "grad_norm": 0.0,
      "learning_rate": 6.568066579746901e-06,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.028668610301263362,
      "grad_norm": 0.0,
      "learning_rate": 5.848888922025553e-06,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.029154518950437316,
      "grad_norm": 0.0,
      "learning_rate": 5.166166492719124e-06,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.029640427599611274,
      "grad_norm": 0.0,
      "learning_rate": 4.521198892775203e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.03012633624878523,
      "grad_norm": 0.0,
      "learning_rate": 3.9152138546778625e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 0.0,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.031098153547133137,
      "grad_norm": 0.0,
      "learning_rate": 2.8247291705444575e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.03158406219630709,
      "grad_norm": 0.0,
      "learning_rate": 2.3423053240837515e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.03206997084548105,
      "grad_norm": 0.0,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.03255587949465501,
      "grad_norm": 0.0,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.03304178814382896,
      "grad_norm": 0.0,
      "learning_rate": 1.1570762312943295e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.033527696793002916,
      "grad_norm": 0.0,
      "learning_rate": 8.51854342773295e-07,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.034013605442176874,
      "grad_norm": 0.0,
      "learning_rate": 5.925998220016659e-07,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.034499514091350825,
      "grad_norm": 0.0,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.03498542274052478,
      "grad_norm": 0.0,
      "learning_rate": 2.1387846565474045e-07,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.03547133138969873,
      "grad_norm": 0.0,
      "learning_rate": 9.513254770636137e-08,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.03595724003887269,
      "grad_norm": 0.0,
      "learning_rate": 2.3794460453555047e-08,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.03644314868804665,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.03644314868804665,
      "eval_loss": NaN,
      "eval_runtime": 26.1872,
      "eval_samples_per_second": 33.108,
      "eval_steps_per_second": 16.573,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2768446056038400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}