{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.28368794326241137,
  "eval_steps": 500,
  "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": 0.00019981060606060605,
      "loss": 2.9206,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019962121212121212,
      "loss": 2.7609,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001994318181818182,
      "loss": 2.6878,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019924242424242426,
      "loss": 2.6697,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001990530303030303,
      "loss": 2.5818,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019886363636363637,
      "loss": 2.5396,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019867424242424244,
      "loss": 2.5265,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001984848484848485,
      "loss": 2.5475,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019829545454545455,
      "loss": 2.4835,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001981060606060606,
      "loss": 2.4559,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001979166666666667,
      "loss": 2.4511,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019772727272727273,
      "loss": 2.4592,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001975378787878788,
      "loss": 2.4495,
      "step": 13
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019734848484848484,
      "loss": 2.4714,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019715909090909094,
      "loss": 2.4302,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019696969696969698,
      "loss": 2.4097,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019678030303030305,
      "loss": 2.4523,
      "step": 17
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001965909090909091,
      "loss": 2.4325,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019640151515151516,
      "loss": 2.4125,
      "step": 19
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019621212121212123,
      "loss": 2.4329,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019602272727272727,
      "loss": 2.3471,
      "step": 21
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019583333333333334,
      "loss": 2.3012,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001956439393939394,
      "loss": 2.3869,
      "step": 23
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019545454545454548,
      "loss": 2.3822,
      "step": 24
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019526515151515152,
      "loss": 2.3427,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001950757575757576,
      "loss": 2.3659,
      "step": 26
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019488636363636366,
      "loss": 2.3826,
      "step": 27
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001946969696969697,
      "loss": 2.3532,
      "step": 28
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019450757575757577,
      "loss": 2.3828,
      "step": 29
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001943181818181818,
      "loss": 2.3133,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001941287878787879,
      "loss": 2.3613,
      "step": 31
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019393939393939395,
      "loss": 2.3867,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019375000000000002,
      "loss": 2.2966,
      "step": 33
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019356060606060606,
      "loss": 2.3436,
      "step": 34
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019337121212121213,
      "loss": 2.3425,
      "step": 35
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001931818181818182,
      "loss": 2.307,
      "step": 36
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019299242424242424,
      "loss": 2.3521,
      "step": 37
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001928030303030303,
      "loss": 2.3302,
      "step": 38
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019261363636363635,
      "loss": 2.312,
      "step": 39
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019242424242424245,
      "loss": 2.3655,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001922348484848485,
      "loss": 2.344,
      "step": 41
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019204545454545456,
      "loss": 2.3373,
      "step": 42
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001918560606060606,
      "loss": 2.3331,
      "step": 43
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019166666666666667,
      "loss": 2.3376,
      "step": 44
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019147727272727274,
      "loss": 2.3369,
      "step": 45
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019128787878787878,
      "loss": 2.3413,
      "step": 46
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019109848484848485,
      "loss": 2.3212,
      "step": 47
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019090909090909092,
      "loss": 2.307,
      "step": 48
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000190719696969697,
      "loss": 2.2929,
      "step": 49
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019053030303030303,
      "loss": 2.2873,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001903409090909091,
      "loss": 2.3098,
      "step": 51
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019015151515151517,
      "loss": 2.3129,
      "step": 52
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001899621212121212,
      "loss": 2.3038,
      "step": 53
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00018977272727272728,
      "loss": 2.286,
      "step": 54
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018958333333333332,
      "loss": 2.3388,
      "step": 55
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018939393939393942,
      "loss": 2.3193,
      "step": 56
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018920454545454546,
      "loss": 2.3136,
      "step": 57
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018901515151515153,
      "loss": 2.3141,
      "step": 58
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018882575757575757,
      "loss": 2.3646,
      "step": 59
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018863636363636364,
      "loss": 2.3318,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001884469696969697,
      "loss": 2.2977,
      "step": 61
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018825757575757575,
      "loss": 2.2764,
      "step": 62
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018806818181818182,
      "loss": 2.3095,
      "step": 63
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001878787878787879,
      "loss": 2.252,
      "step": 64
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018768939393939396,
      "loss": 2.2786,
      "step": 65
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001875,
      "loss": 2.2789,
      "step": 66
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018731060606060607,
      "loss": 2.2841,
      "step": 67
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018712121212121212,
      "loss": 2.3436,
      "step": 68
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018693181818181818,
      "loss": 2.2956,
      "step": 69
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018674242424242425,
      "loss": 2.2353,
      "step": 70
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001865530303030303,
      "loss": 2.2772,
      "step": 71
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018636363636363636,
      "loss": 2.2496,
      "step": 72
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018617424242424243,
      "loss": 2.2477,
      "step": 73
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001859848484848485,
      "loss": 2.2791,
      "step": 74
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018579545454545454,
      "loss": 2.2799,
      "step": 75
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018560606060606061,
      "loss": 2.3132,
      "step": 76
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018541666666666668,
      "loss": 2.2542,
      "step": 77
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018522727272727273,
      "loss": 2.2609,
      "step": 78
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001850378787878788,
      "loss": 2.2819,
      "step": 79
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018484848484848484,
      "loss": 2.2844,
      "step": 80
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018465909090909093,
      "loss": 2.2542,
      "step": 81
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018446969696969697,
      "loss": 2.2603,
      "step": 82
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018428030303030304,
      "loss": 2.2832,
      "step": 83
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018409090909090909,
      "loss": 2.2869,
      "step": 84
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018390151515151518,
      "loss": 2.2646,
      "step": 85
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018371212121212122,
      "loss": 2.2698,
      "step": 86
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018352272727272727,
      "loss": 2.2757,
      "step": 87
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018333333333333334,
      "loss": 2.2544,
      "step": 88
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001831439393939394,
      "loss": 2.2678,
      "step": 89
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018295454545454547,
      "loss": 2.2778,
      "step": 90
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018276515151515152,
      "loss": 2.2027,
      "step": 91
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018257575757575758,
      "loss": 2.2167,
      "step": 92
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018238636363636365,
      "loss": 2.2602,
      "step": 93
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018219696969696972,
      "loss": 2.2736,
      "step": 94
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018200757575757577,
      "loss": 2.2443,
      "step": 95
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018181818181818183,
      "loss": 2.2299,
      "step": 96
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001816287878787879,
      "loss": 2.2644,
      "step": 97
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018143939393939395,
      "loss": 2.259,
      "step": 98
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018125000000000001,
      "loss": 2.2567,
      "step": 99
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018106060606060606,
      "loss": 2.2599,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 1056,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.5310590559514624e+17,
  "trial_name": null,
  "trial_params": null
}