{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0172413793103448,
  "eval_steps": 500,
  "global_step": 59,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2.5e-05,
      "loss": 1.8823,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 1.8925,
      "step": 2
    },
    {
      "epoch": 0.05,
      "learning_rate": 7.5e-05,
      "loss": 1.8355,
      "step": 3
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 1.8682,
      "step": 4
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000125,
      "loss": 1.6578,
      "step": 5
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00015,
      "loss": 1.7746,
      "step": 6
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000175,
      "loss": 1.7078,
      "step": 7
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.3556,
      "step": 8
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00022500000000000002,
      "loss": 1.785,
      "step": 9
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00025,
      "loss": 1.7491,
      "step": 10
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002499874839708436,
      "loss": 1.7576,
      "step": 11
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002499499383897902,
      "loss": 1.7944,
      "step": 12
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002498873707755852,
      "loss": 1.8368,
      "step": 13
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002497997936577979,
      "loss": 1.7509,
      "step": 14
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002496872245743125,
      "loss": 1.9833,
      "step": 15
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002495496860678158,
      "loss": 1.7853,
      "step": 16
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00024938720568128326,
      "loss": 1.7627,
      "step": 17
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002491998159524629,
      "loss": 1.7721,
      "step": 18
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002489875544073596,
      "loss": 1.6278,
      "step": 19
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00024875046355272046,
      "loss": 1.6963,
      "step": 20
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002484885908675223,
      "loss": 1.7123,
      "step": 21
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002482019887934636,
      "loss": 1.7719,
      "step": 22
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00024789071472446306,
      "loss": 1.8138,
      "step": 23
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00024755483099516584,
      "loss": 1.8235,
      "step": 24
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002471944048684608,
      "loss": 1.7845,
      "step": 25
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002468095085220104,
      "loss": 1.6665,
      "step": 26
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00024640021903379704,
      "loss": 1.6388,
      "step": 27
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00024596661836668736,
      "loss": 1.6817,
      "step": 28
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002455087933520188,
      "loss": 1.7617,
      "step": 29
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002450268356722112,
      "loss": 1.6921,
      "step": 30
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00024452084184240636,
      "loss": 1.6591,
      "step": 31
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00024399091319114082,
      "loss": 1.8172,
      "step": 32
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00024343715584005372,
      "loss": 1.7321,
      "step": 33
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00024285968068263553,
      "loss": 1.7617,
      "step": 34
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00024225860336202074,
      "loss": 1.7899,
      "step": 35
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00024163404424782967,
      "loss": 1.7486,
      "step": 36
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002409861284120637,
      "loss": 1.7422,
      "step": 37
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002403149856040586,
      "loss": 1.6344,
      "step": 38
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002396207502245017,
      "loss": 1.7174,
      "step": 39
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00023890356129851697,
      "loss": 1.7665,
      "step": 40
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00023816356244782462,
      "loss": 1.7379,
      "step": 41
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002374009018619796,
      "loss": 1.7206,
      "step": 42
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00023661573226869606,
      "loss": 1.6732,
      "step": 43
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00023580821090326233,
      "loss": 1.7475,
      "step": 44
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00023497849947705368,
      "loss": 1.7546,
      "step": 45
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00023412676414514853,
      "loss": 1.6588,
      "step": 46
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00023325317547305487,
      "loss": 1.7417,
      "step": 47
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00023235790840255328,
      "loss": 1.7224,
      "step": 48
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002314411422166639,
      "loss": 1.6476,
      "step": 49
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00023050306050374382,
      "loss": 1.73,
      "step": 50
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00022954385112072202,
      "loss": 1.6658,
      "step": 51
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00022856370615548027,
      "loss": 1.7046,
      "step": 52
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00022756282188838596,
      "loss": 1.7037,
      "step": 53
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00022654139875298573,
      "loss": 1.7166,
      "step": 54
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00022549964129586758,
      "loss": 1.7816,
      "step": 55
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00022443775813569874,
      "loss": 1.7556,
      "step": 56
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00022335596192144875,
      "loss": 1.7044,
      "step": 57
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00022225446928980495,
      "loss": 1.7183,
      "step": 58
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002211335008217896,
      "loss": 1.738,
      "step": 59
    }
  ],
  "logging_steps": 1,
  "max_steps": 232,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 5.264395754633429e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}