{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 10,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 9.4375,
      "learning_rate": 0.0,
      "loss": 2.1559,
      "step": 1
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 9.875,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.3059,
      "step": 2
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 11.75,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.3407,
      "step": 3
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 10.375,
      "learning_rate": 6e-06,
      "loss": 2.3596,
      "step": 4
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 9.75,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.1863,
      "step": 5
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 8.25,
      "learning_rate": 1e-05,
      "loss": 2.1556,
      "step": 6
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 9.8125,
      "learning_rate": 9.893617021276596e-06,
      "loss": 2.1315,
      "step": 7
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 7.0,
      "learning_rate": 9.787234042553192e-06,
      "loss": 1.7968,
      "step": 8
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 4.1875,
      "learning_rate": 9.680851063829787e-06,
      "loss": 1.7795,
      "step": 9
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 2.953125,
      "learning_rate": 9.574468085106385e-06,
      "loss": 1.69,
      "step": 10
    },
    {
      "epoch": 0.10101010101010101,
      "eval_loss": 1.81484854221344,
      "eval_model_preparation_time": 0.0169,
      "eval_runtime": 3.1829,
      "eval_samples_per_second": 45.242,
      "eval_steps_per_second": 22.621,
      "step": 10
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 2.8125,
      "learning_rate": 9.46808510638298e-06,
      "loss": 1.6374,
      "step": 11
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.84375,
      "learning_rate": 9.361702127659576e-06,
      "loss": 1.8449,
      "step": 12
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 2.515625,
      "learning_rate": 9.255319148936171e-06,
      "loss": 1.6733,
      "step": 13
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 2.453125,
      "learning_rate": 9.148936170212767e-06,
      "loss": 1.5624,
      "step": 14
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 2.28125,
      "learning_rate": 9.042553191489362e-06,
      "loss": 1.4991,
      "step": 15
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 2.328125,
      "learning_rate": 8.936170212765958e-06,
      "loss": 1.7474,
      "step": 16
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 2.109375,
      "learning_rate": 8.829787234042555e-06,
      "loss": 1.6492,
      "step": 17
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 2.15625,
      "learning_rate": 8.72340425531915e-06,
      "loss": 1.59,
      "step": 18
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 1.828125,
      "learning_rate": 8.617021276595746e-06,
      "loss": 1.5473,
      "step": 19
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 2.078125,
      "learning_rate": 8.510638297872341e-06,
      "loss": 1.6566,
      "step": 20
    },
    {
      "epoch": 0.20202020202020202,
      "eval_loss": 1.6047254800796509,
      "eval_model_preparation_time": 0.0169,
      "eval_runtime": 3.1634,
      "eval_samples_per_second": 45.521,
      "eval_steps_per_second": 22.761,
      "step": 20
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 1.9296875,
      "learning_rate": 8.404255319148937e-06,
      "loss": 1.3761,
      "step": 21
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.7890625,
      "learning_rate": 8.297872340425532e-06,
      "loss": 1.5307,
      "step": 22
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 2.015625,
      "learning_rate": 8.191489361702128e-06,
      "loss": 1.6108,
      "step": 23
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 1.9296875,
      "learning_rate": 8.085106382978723e-06,
      "loss": 1.5662,
      "step": 24
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 1.9609375,
      "learning_rate": 7.97872340425532e-06,
      "loss": 1.6447,
      "step": 25
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 1.84375,
      "learning_rate": 7.872340425531916e-06,
      "loss": 1.5652,
      "step": 26
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 1.78125,
      "learning_rate": 7.765957446808511e-06,
      "loss": 1.5465,
      "step": 27
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 1.7265625,
      "learning_rate": 7.659574468085107e-06,
      "loss": 1.4737,
      "step": 28
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 1.765625,
      "learning_rate": 7.553191489361703e-06,
      "loss": 1.4285,
      "step": 29
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.7578125,
      "learning_rate": 7.446808510638298e-06,
      "loss": 1.5278,
      "step": 30
    },
    {
      "epoch": 0.30303030303030304,
      "eval_loss": 1.4933972358703613,
      "eval_model_preparation_time": 0.0169,
      "eval_runtime": 3.1671,
      "eval_samples_per_second": 45.467,
      "eval_steps_per_second": 22.733,
      "step": 30
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 1.6171875,
      "learning_rate": 7.340425531914894e-06,
      "loss": 1.317,
      "step": 31
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 1.796875,
      "learning_rate": 7.234042553191491e-06,
      "loss": 1.5716,
      "step": 32
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.640625,
      "learning_rate": 7.127659574468085e-06,
      "loss": 1.3389,
      "step": 33
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 1.6875,
      "learning_rate": 7.021276595744682e-06,
      "loss": 1.4052,
      "step": 34
    },
    {
      "epoch": 0.35353535353535354,
      "grad_norm": 1.703125,
      "learning_rate": 6.914893617021278e-06,
      "loss": 1.4422,
      "step": 35
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.6640625,
      "learning_rate": 6.808510638297873e-06,
      "loss": 1.3351,
      "step": 36
    },
    {
      "epoch": 0.37373737373737376,
      "grad_norm": 1.7265625,
      "learning_rate": 6.702127659574469e-06,
      "loss": 1.4089,
      "step": 37
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 1.734375,
      "learning_rate": 6.595744680851064e-06,
      "loss": 1.3695,
      "step": 38
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 1.7265625,
      "learning_rate": 6.48936170212766e-06,
      "loss": 1.4133,
      "step": 39
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 1.7109375,
      "learning_rate": 6.382978723404256e-06,
      "loss": 1.4619,
      "step": 40
    },
    {
      "epoch": 0.40404040404040403,
      "eval_loss": 1.4300950765609741,
      "eval_model_preparation_time": 0.0169,
      "eval_runtime": 3.1719,
      "eval_samples_per_second": 45.398,
      "eval_steps_per_second": 22.699,
      "step": 40
    },
    {
      "epoch": 0.41414141414141414,
      "grad_norm": 1.59375,
      "learning_rate": 6.276595744680851e-06,
      "loss": 1.3818,
      "step": 41
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 1.6875,
      "learning_rate": 6.170212765957447e-06,
      "loss": 1.3216,
      "step": 42
    },
    {
      "epoch": 0.43434343434343436,
      "grad_norm": 1.8671875,
      "learning_rate": 6.063829787234044e-06,
      "loss": 1.5044,
      "step": 43
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.7578125,
      "learning_rate": 5.957446808510638e-06,
      "loss": 1.4391,
      "step": 44
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.8828125,
      "learning_rate": 5.851063829787235e-06,
      "loss": 1.3796,
      "step": 45
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 1.984375,
      "learning_rate": 5.744680851063831e-06,
      "loss": 1.46,
      "step": 46
    },
    {
      "epoch": 0.47474747474747475,
      "grad_norm": 1.890625,
      "learning_rate": 5.638297872340426e-06,
      "loss": 1.3988,
      "step": 47
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 1.96875,
      "learning_rate": 5.531914893617022e-06,
      "loss": 1.3069,
      "step": 48
    },
    {
      "epoch": 0.494949494949495,
      "grad_norm": 1.890625,
      "learning_rate": 5.425531914893617e-06,
      "loss": 1.3012,
      "step": 49
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 1.8515625,
      "learning_rate": 5.319148936170213e-06,
      "loss": 1.3429,
      "step": 50
    },
    {
      "epoch": 0.5050505050505051,
      "eval_loss": 1.3854832649230957,
      "eval_model_preparation_time": 0.0169,
      "eval_runtime": 3.1645,
      "eval_samples_per_second": 45.504,
      "eval_steps_per_second": 22.752,
      "step": 50
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 1.890625,
      "learning_rate": 5.212765957446809e-06,
      "loss": 1.3141,
      "step": 51
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 1.78125,
      "learning_rate": 5.106382978723404e-06,
      "loss": 1.2483,
      "step": 52
    },
    {
      "epoch": 0.5353535353535354,
      "grad_norm": 1.8046875,
      "learning_rate": 5e-06,
      "loss": 1.3407,
      "step": 53
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.671875,
      "learning_rate": 4.893617021276596e-06,
      "loss": 1.2189,
      "step": 54
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.8359375,
      "learning_rate": 4.787234042553192e-06,
      "loss": 1.3621,
      "step": 55
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 1.765625,
      "learning_rate": 4.680851063829788e-06,
      "loss": 1.3592,
      "step": 56
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 1.8125,
      "learning_rate": 4.574468085106383e-06,
      "loss": 1.3573,
      "step": 57
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 1.7265625,
      "learning_rate": 4.468085106382979e-06,
      "loss": 1.3224,
      "step": 58
    },
    {
      "epoch": 0.5959595959595959,
      "grad_norm": 1.96875,
      "learning_rate": 4.361702127659575e-06,
      "loss": 1.3177,
      "step": 59
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.78125,
      "learning_rate": 4.255319148936171e-06,
      "loss": 1.3227,
      "step": 60
    },
    {
      "epoch": 0.6060606060606061,
      "eval_loss": 1.356658697128296,
      "eval_model_preparation_time": 0.0169,
      "eval_runtime": 3.1698,
      "eval_samples_per_second": 45.429,
      "eval_steps_per_second": 22.714,
      "step": 60
    },
    {
      "epoch": 0.6161616161616161,
      "grad_norm": 1.8203125,
      "learning_rate": 4.148936170212766e-06,
      "loss": 1.3576,
      "step": 61
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 1.7421875,
      "learning_rate": 4.042553191489362e-06,
      "loss": 1.2874,
      "step": 62
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.7890625,
      "learning_rate": 3.936170212765958e-06,
      "loss": 1.2097,
      "step": 63
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 1.765625,
      "learning_rate": 3.8297872340425535e-06,
      "loss": 1.2487,
      "step": 64
    },
    {
      "epoch": 0.6565656565656566,
      "grad_norm": 1.9765625,
      "learning_rate": 3.723404255319149e-06,
      "loss": 1.3143,
      "step": 65
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.9296875,
      "learning_rate": 3.6170212765957453e-06,
      "loss": 1.3207,
      "step": 66
    },
    {
      "epoch": 0.6767676767676768,
      "grad_norm": 1.796875,
      "learning_rate": 3.510638297872341e-06,
      "loss": 1.4014,
      "step": 67
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 1.8671875,
      "learning_rate": 3.4042553191489363e-06,
      "loss": 1.2789,
      "step": 68
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 1.7734375,
      "learning_rate": 3.297872340425532e-06,
      "loss": 1.3333,
      "step": 69
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 2.015625,
      "learning_rate": 3.191489361702128e-06,
      "loss": 1.4142,
      "step": 70
    },
    {
      "epoch": 0.7070707070707071,
      "eval_loss": 1.336801528930664,
      "eval_model_preparation_time": 0.0169,
      "eval_runtime": 3.1642,
      "eval_samples_per_second": 45.51,
      "eval_steps_per_second": 22.755,
      "step": 70
    },
    {
      "epoch": 0.7171717171717171,
      "grad_norm": 1.859375,
      "learning_rate": 3.0851063829787237e-06,
      "loss": 1.3983,
      "step": 71
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.875,
      "learning_rate": 2.978723404255319e-06,
      "loss": 1.3606,
      "step": 72
    },
    {
      "epoch": 0.7373737373737373,
      "grad_norm": 1.9140625,
      "learning_rate": 2.8723404255319155e-06,
      "loss": 1.4158,
      "step": 73
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 2.015625,
      "learning_rate": 2.765957446808511e-06,
      "loss": 1.273,
      "step": 74
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 1.8203125,
      "learning_rate": 2.6595744680851065e-06,
      "loss": 1.2416,
      "step": 75
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 1.8203125,
      "learning_rate": 2.553191489361702e-06,
      "loss": 1.3183,
      "step": 76
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 1.75,
      "learning_rate": 2.446808510638298e-06,
      "loss": 1.2538,
      "step": 77
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 1.9375,
      "learning_rate": 2.340425531914894e-06,
      "loss": 1.2425,
      "step": 78
    },
    {
      "epoch": 0.797979797979798,
      "grad_norm": 1.7890625,
      "learning_rate": 2.2340425531914894e-06,
      "loss": 1.2664,
      "step": 79
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 1.8515625,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 1.3056,
      "step": 80
    },
    {
      "epoch": 0.8080808080808081,
      "eval_loss": 1.3236327171325684,
      "eval_model_preparation_time": 0.0169,
      "eval_runtime": 3.1591,
      "eval_samples_per_second": 45.583,
      "eval_steps_per_second": 22.792,
      "step": 80
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 1.6875,
      "learning_rate": 2.021276595744681e-06,
      "loss": 1.2309,
      "step": 81
    },
    {
      "epoch": 0.8282828282828283,
      "grad_norm": 2.125,
      "learning_rate": 1.9148936170212767e-06,
      "loss": 1.3102,
      "step": 82
    },
    {
      "epoch": 0.8383838383838383,
      "grad_norm": 2.03125,
      "learning_rate": 1.8085106382978727e-06,
      "loss": 1.2998,
      "step": 83
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 1.90625,
      "learning_rate": 1.7021276595744682e-06,
      "loss": 1.3077,
      "step": 84
    },
    {
      "epoch": 0.8585858585858586,
      "grad_norm": 1.9140625,
      "learning_rate": 1.595744680851064e-06,
      "loss": 1.3,
      "step": 85
    },
    {
      "epoch": 0.8686868686868687,
      "grad_norm": 1.6953125,
      "learning_rate": 1.4893617021276596e-06,
      "loss": 1.2836,
      "step": 86
    },
    {
      "epoch": 0.8787878787878788,
      "grad_norm": 2.015625,
      "learning_rate": 1.3829787234042555e-06,
      "loss": 1.2684,
      "step": 87
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.0,
      "learning_rate": 1.276595744680851e-06,
      "loss": 1.2866,
      "step": 88
    },
    {
      "epoch": 0.898989898989899,
      "grad_norm": 1.875,
      "learning_rate": 1.170212765957447e-06,
      "loss": 1.4256,
      "step": 89
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.875,
      "learning_rate": 1.0638297872340427e-06,
      "loss": 1.2093,
      "step": 90
    },
    {
      "epoch": 0.9090909090909091,
      "eval_loss": 1.31633722782135,
      "eval_model_preparation_time": 0.0169,
      "eval_runtime": 3.1542,
      "eval_samples_per_second": 45.653,
      "eval_steps_per_second": 22.827,
      "step": 90
    },
    {
      "epoch": 0.9191919191919192,
      "grad_norm": 1.8359375,
      "learning_rate": 9.574468085106384e-07,
      "loss": 1.3478,
      "step": 91
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 2.1875,
      "learning_rate": 8.510638297872341e-07,
      "loss": 1.2843,
      "step": 92
    },
    {
      "epoch": 0.9393939393939394,
      "grad_norm": 1.8125,
      "learning_rate": 7.446808510638298e-07,
      "loss": 1.2619,
      "step": 93
    },
    {
      "epoch": 0.9494949494949495,
      "grad_norm": 1.6875,
      "learning_rate": 6.382978723404255e-07,
      "loss": 1.3074,
      "step": 94
    },
    {
      "epoch": 0.9595959595959596,
      "grad_norm": 1.921875,
      "learning_rate": 5.319148936170213e-07,
      "loss": 1.3186,
      "step": 95
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 2.03125,
      "learning_rate": 4.2553191489361704e-07,
      "loss": 1.3499,
      "step": 96
    },
    {
      "epoch": 0.9797979797979798,
      "grad_norm": 2.0,
      "learning_rate": 3.1914893617021275e-07,
      "loss": 1.2827,
      "step": 97
    },
    {
      "epoch": 0.98989898989899,
      "grad_norm": 1.859375,
      "learning_rate": 2.1276595744680852e-07,
      "loss": 1.1419,
      "step": 98
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.8828125,
      "learning_rate": 1.0638297872340426e-07,
      "loss": 1.2356,
      "step": 99
    }
  ],
  "logging_steps": 1,
  "max_steps": 99,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5524656076046336e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}