{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 66,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 2.1806390285491943,
      "learning_rate": 1e-05,
      "loss": 2.259,
      "step": 1
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.0509750843048096,
      "learning_rate": 9.84848484848485e-06,
      "loss": 2.1749,
      "step": 2
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 1.945802092552185,
      "learning_rate": 9.696969696969698e-06,
      "loss": 2.1865,
      "step": 3
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.7818379402160645,
      "learning_rate": 9.545454545454547e-06,
      "loss": 2.1723,
      "step": 4
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 1.5140708684921265,
      "learning_rate": 9.393939393939396e-06,
      "loss": 2.0943,
      "step": 5
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.168502688407898,
      "learning_rate": 9.242424242424244e-06,
      "loss": 1.9775,
      "step": 6
    },
    {
      "epoch": 0.10606060606060606,
      "grad_norm": 0.9731884002685547,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.9921,
      "step": 7
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.8054101467132568,
      "learning_rate": 8.93939393939394e-06,
      "loss": 1.9888,
      "step": 8
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.6741383075714111,
      "learning_rate": 8.787878787878788e-06,
      "loss": 1.8612,
      "step": 9
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 0.6076740026473999,
      "learning_rate": 8.636363636363637e-06,
      "loss": 1.7527,
      "step": 10
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.6412762403488159,
      "learning_rate": 8.484848484848486e-06,
      "loss": 1.8131,
      "step": 11
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.6954469680786133,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.8204,
      "step": 12
    },
    {
      "epoch": 0.19696969696969696,
      "grad_norm": 0.7794247269630432,
      "learning_rate": 8.181818181818183e-06,
      "loss": 1.86,
      "step": 13
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 0.811967134475708,
      "learning_rate": 8.03030303030303e-06,
      "loss": 1.8567,
      "step": 14
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.7707127928733826,
      "learning_rate": 7.87878787878788e-06,
      "loss": 1.7976,
      "step": 15
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.7628827691078186,
      "learning_rate": 7.727272727272727e-06,
      "loss": 1.7364,
      "step": 16
    },
    {
      "epoch": 0.25757575757575757,
      "grad_norm": 0.7113344073295593,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 1.7219,
      "step": 17
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.6681413054466248,
      "learning_rate": 7.424242424242425e-06,
      "loss": 1.7664,
      "step": 18
    },
    {
      "epoch": 0.2878787878787879,
      "grad_norm": 0.6175987720489502,
      "learning_rate": 7.272727272727273e-06,
      "loss": 1.6869,
      "step": 19
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.5634602904319763,
      "learning_rate": 7.121212121212122e-06,
      "loss": 1.7165,
      "step": 20
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.4820578694343567,
      "learning_rate": 6.969696969696971e-06,
      "loss": 1.6105,
      "step": 21
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.5000921487808228,
      "learning_rate": 6.818181818181818e-06,
      "loss": 1.6858,
      "step": 22
    },
    {
      "epoch": 0.3484848484848485,
      "grad_norm": 0.4802851676940918,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.6478,
      "step": 23
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.45336592197418213,
      "learning_rate": 6.515151515151516e-06,
      "loss": 1.5984,
      "step": 24
    },
    {
      "epoch": 0.3787878787878788,
      "grad_norm": 0.4636070132255554,
      "learning_rate": 6.363636363636364e-06,
      "loss": 1.613,
      "step": 25
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 0.4598033130168915,
      "learning_rate": 6.212121212121213e-06,
      "loss": 1.6106,
      "step": 26
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.46231794357299805,
      "learning_rate": 6.060606060606061e-06,
      "loss": 1.581,
      "step": 27
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.4495490789413452,
      "learning_rate": 5.90909090909091e-06,
      "loss": 1.571,
      "step": 28
    },
    {
      "epoch": 0.4393939393939394,
      "grad_norm": 0.43504828214645386,
      "learning_rate": 5.7575757575757586e-06,
      "loss": 1.4945,
      "step": 29
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.4237779974937439,
      "learning_rate": 5.606060606060606e-06,
      "loss": 1.5492,
      "step": 30
    },
    {
      "epoch": 0.4696969696969697,
      "grad_norm": 0.40998709201812744,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 1.5383,
      "step": 31
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.3991314470767975,
      "learning_rate": 5.303030303030303e-06,
      "loss": 1.5579,
      "step": 32
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.3889806866645813,
      "learning_rate": 5.151515151515152e-06,
      "loss": 1.5391,
      "step": 33
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 0.382036030292511,
      "learning_rate": 5e-06,
      "loss": 1.5403,
      "step": 34
    },
    {
      "epoch": 0.5303030303030303,
      "grad_norm": 0.3747563064098358,
      "learning_rate": 4.848484848484849e-06,
      "loss": 1.5569,
      "step": 35
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.3503689765930176,
      "learning_rate": 4.696969696969698e-06,
      "loss": 1.4986,
      "step": 36
    },
    {
      "epoch": 0.5606060606060606,
      "grad_norm": 0.34654778242111206,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 1.4863,
      "step": 37
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 0.3559574782848358,
      "learning_rate": 4.393939393939394e-06,
      "loss": 1.5173,
      "step": 38
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.32772454619407654,
      "learning_rate": 4.242424242424243e-06,
      "loss": 1.4364,
      "step": 39
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.3556043207645416,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 1.4833,
      "step": 40
    },
    {
      "epoch": 0.6212121212121212,
      "grad_norm": 0.3289327323436737,
      "learning_rate": 3.93939393939394e-06,
      "loss": 1.4412,
      "step": 41
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.38381296396255493,
      "learning_rate": 3.7878787878787882e-06,
      "loss": 1.5059,
      "step": 42
    },
    {
      "epoch": 0.6515151515151515,
      "grad_norm": 0.33431607484817505,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 1.4532,
      "step": 43
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.34528639912605286,
      "learning_rate": 3.4848484848484854e-06,
      "loss": 1.4567,
      "step": 44
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.3294561803340912,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.4228,
      "step": 45
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 0.32518258690834045,
      "learning_rate": 3.181818181818182e-06,
      "loss": 1.4301,
      "step": 46
    },
    {
      "epoch": 0.7121212121212122,
      "grad_norm": 0.3199913203716278,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 1.4139,
      "step": 47
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.3203113377094269,
      "learning_rate": 2.8787878787878793e-06,
      "loss": 1.4344,
      "step": 48
    },
    {
      "epoch": 0.7424242424242424,
      "grad_norm": 0.3189423680305481,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 1.407,
      "step": 49
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.3475227653980255,
      "learning_rate": 2.575757575757576e-06,
      "loss": 1.4637,
      "step": 50
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.3078831136226654,
      "learning_rate": 2.4242424242424244e-06,
      "loss": 1.395,
      "step": 51
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 0.3077380061149597,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 1.3932,
      "step": 52
    },
    {
      "epoch": 0.803030303030303,
      "grad_norm": 0.33048221468925476,
      "learning_rate": 2.1212121212121216e-06,
      "loss": 1.4297,
      "step": 53
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.3076639175415039,
      "learning_rate": 1.96969696969697e-06,
      "loss": 1.3972,
      "step": 54
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.31399327516555786,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 1.4242,
      "step": 55
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.29711833596229553,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.3937,
      "step": 56
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.30907464027404785,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 1.4002,
      "step": 57
    },
    {
      "epoch": 0.8787878787878788,
      "grad_norm": 0.3013785481452942,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 1.3923,
      "step": 58
    },
    {
      "epoch": 0.8939393939393939,
      "grad_norm": 0.31994277238845825,
      "learning_rate": 1.2121212121212122e-06,
      "loss": 1.4338,
      "step": 59
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.3298662006855011,
      "learning_rate": 1.0606060606060608e-06,
      "loss": 1.4199,
      "step": 60
    },
    {
      "epoch": 0.9242424242424242,
      "grad_norm": 0.317755788564682,
      "learning_rate": 9.090909090909091e-07,
      "loss": 1.4137,
      "step": 61
    },
    {
      "epoch": 0.9393939393939394,
      "grad_norm": 0.29229098558425903,
      "learning_rate": 7.575757575757576e-07,
      "loss": 1.3405,
      "step": 62
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.3137110471725464,
      "learning_rate": 6.060606060606061e-07,
      "loss": 1.4083,
      "step": 63
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.30957749485969543,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 1.4063,
      "step": 64
    },
    {
      "epoch": 0.9848484848484849,
      "grad_norm": 0.3310662806034088,
      "learning_rate": 3.0303030303030305e-07,
      "loss": 1.4201,
      "step": 65
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.297313928604126,
      "learning_rate": 1.5151515151515152e-07,
      "loss": 1.3758,
      "step": 66
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4051569700241089,
      "eval_runtime": 4.459,
      "eval_samples_per_second": 1.57,
      "eval_steps_per_second": 0.224,
      "step": 66
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3786133191275315e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}