{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5050505050505051,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005050505050505051,
      "grad_norm": 0.00640869140625,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.2756,
      "step": 50
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 0.0008697509765625,
      "learning_rate": 0.000196,
      "loss": 0.9178,
      "step": 100
    },
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 0.0002803802490234375,
      "learning_rate": 0.000194,
      "loss": 1.2995,
      "step": 150
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 63.75,
      "learning_rate": 0.000192,
      "loss": 1.0395,
      "step": 200
    },
    {
      "epoch": 0.025252525252525252,
      "grad_norm": 0.00970458984375,
      "learning_rate": 0.00019,
      "loss": 0.9509,
      "step": 250
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 0.00909423828125,
      "learning_rate": 0.000188,
      "loss": 0.7246,
      "step": 300
    },
    {
      "epoch": 0.03535353535353535,
      "grad_norm": 3.8125,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.9811,
      "step": 350
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 0.00823974609375,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.734,
      "step": 400
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.0203857421875,
      "learning_rate": 0.000182,
      "loss": 0.9583,
      "step": 450
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 84.0,
      "learning_rate": 0.00018,
      "loss": 0.7122,
      "step": 500
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.005859375,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.6662,
      "step": 550
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 7.963180541992188e-05,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.7423,
      "step": 600
    },
    {
      "epoch": 0.06565656565656566,
      "grad_norm": 4.5625,
      "learning_rate": 0.000174,
      "loss": 1.175,
      "step": 650
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 0.0014801025390625,
      "learning_rate": 0.000172,
      "loss": 0.6812,
      "step": 700
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 0.0634765625,
      "learning_rate": 0.00017,
      "loss": 0.5917,
      "step": 750
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 7.375,
      "learning_rate": 0.000168,
      "loss": 0.725,
      "step": 800
    },
    {
      "epoch": 0.08585858585858586,
      "grad_norm": 35.0,
      "learning_rate": 0.000166,
      "loss": 0.7658,
      "step": 850
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 6.625,
      "learning_rate": 0.000164,
      "loss": 0.7727,
      "step": 900
    },
    {
      "epoch": 0.09595959595959595,
      "grad_norm": 0.03759765625,
      "learning_rate": 0.000162,
      "loss": 0.5597,
      "step": 950
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 0.005096435546875,
      "learning_rate": 0.00016,
      "loss": 0.5977,
      "step": 1000
    },
    {
      "epoch": 0.10606060606060606,
      "grad_norm": 0.0037078857421875,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.0553,
      "step": 1050
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 11.875,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.7937,
      "step": 1100
    },
    {
      "epoch": 0.11616161616161616,
      "grad_norm": 0.00087738037109375,
      "learning_rate": 0.000154,
      "loss": 0.5609,
      "step": 1150
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.0003604888916015625,
      "learning_rate": 0.000152,
      "loss": 0.43,
      "step": 1200
    },
    {
      "epoch": 0.12626262626262627,
      "grad_norm": 0.00592041015625,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.5442,
      "step": 1250
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 4.875,
      "learning_rate": 0.000148,
      "loss": 0.7502,
      "step": 1300
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 5.0,
      "learning_rate": 0.000146,
      "loss": 0.9968,
      "step": 1350
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 0.016357421875,
      "learning_rate": 0.000144,
      "loss": 0.5973,
      "step": 1400
    },
    {
      "epoch": 0.14646464646464646,
      "grad_norm": 0.92578125,
      "learning_rate": 0.000142,
      "loss": 1.0503,
      "step": 1450
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 0.003082275390625,
      "learning_rate": 0.00014,
      "loss": 0.526,
      "step": 1500
    },
    {
      "epoch": 0.15656565656565657,
      "grad_norm": 0.017333984375,
      "learning_rate": 0.000138,
      "loss": 0.6893,
      "step": 1550
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 5.125,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.6892,
      "step": 1600
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.00186920166015625,
      "learning_rate": 0.000134,
      "loss": 0.5635,
      "step": 1650
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 4.125,
      "learning_rate": 0.000132,
      "loss": 0.7575,
      "step": 1700
    },
    {
      "epoch": 0.17676767676767677,
      "grad_norm": 27.375,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.6113,
      "step": 1750
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.0019989013671875,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.5127,
      "step": 1800
    },
    {
      "epoch": 0.18686868686868688,
      "grad_norm": 0.000514984130859375,
      "learning_rate": 0.000126,
      "loss": 0.6001,
      "step": 1850
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 0.00531005859375,
      "learning_rate": 0.000124,
      "loss": 0.6199,
      "step": 1900
    },
    {
      "epoch": 0.19696969696969696,
      "grad_norm": 0.486328125,
      "learning_rate": 0.000122,
      "loss": 0.8243,
      "step": 1950
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 0.00141143798828125,
      "learning_rate": 0.00012,
      "loss": 0.5386,
      "step": 2000
    },
    {
      "epoch": 0.20707070707070707,
      "grad_norm": 7.65625,
      "learning_rate": 0.000118,
      "loss": 0.4405,
      "step": 2050
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 9.625,
      "learning_rate": 0.000116,
      "loss": 0.7058,
      "step": 2100
    },
    {
      "epoch": 0.21717171717171718,
      "grad_norm": 11.9375,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.6288,
      "step": 2150
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.4375,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.5395,
      "step": 2200
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 2.671875,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.8054,
      "step": 2250
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 0.0034332275390625,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.5827,
      "step": 2300
    },
    {
      "epoch": 0.23737373737373738,
      "grad_norm": 0.0113525390625,
      "learning_rate": 0.00010600000000000002,
      "loss": 0.512,
      "step": 2350
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 2.6875,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.6449,
      "step": 2400
    },
    {
      "epoch": 0.2474747474747475,
      "grad_norm": 8.875,
      "learning_rate": 0.00010200000000000001,
      "loss": 0.5955,
      "step": 2450
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 0.0003261566162109375,
      "learning_rate": 0.0001,
      "loss": 0.4586,
      "step": 2500
    },
    {
      "epoch": 0.25757575757575757,
      "grad_norm": 0.003814697265625,
      "learning_rate": 9.8e-05,
      "loss": 0.6287,
      "step": 2550
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 0.000823974609375,
      "learning_rate": 9.6e-05,
      "loss": 0.8459,
      "step": 2600
    },
    {
      "epoch": 0.2676767676767677,
      "grad_norm": 0.0208740234375,
      "learning_rate": 9.4e-05,
      "loss": 0.4845,
      "step": 2650
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.0003643035888671875,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.8213,
      "step": 2700
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.006927490234375,
      "learning_rate": 9e-05,
      "loss": 0.5009,
      "step": 2750
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 0.0078125,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.5776,
      "step": 2800
    },
    {
      "epoch": 0.2878787878787879,
      "grad_norm": 7.4375,
      "learning_rate": 8.6e-05,
      "loss": 0.5102,
      "step": 2850
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 10.1875,
      "learning_rate": 8.4e-05,
      "loss": 0.5194,
      "step": 2900
    },
    {
      "epoch": 0.29797979797979796,
      "grad_norm": 0.00469970703125,
      "learning_rate": 8.2e-05,
      "loss": 0.9075,
      "step": 2950
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 7.4375,
      "learning_rate": 8e-05,
      "loss": 0.6495,
      "step": 3000
    },
    {
      "epoch": 0.30808080808080807,
      "grad_norm": 33.25,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.3913,
      "step": 3050
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 0.00080108642578125,
      "learning_rate": 7.6e-05,
      "loss": 0.4946,
      "step": 3100
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 4.0625,
      "learning_rate": 7.4e-05,
      "loss": 0.5223,
      "step": 3150
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.0032806396484375,
      "learning_rate": 7.2e-05,
      "loss": 0.5745,
      "step": 3200
    },
    {
      "epoch": 0.3282828282828283,
      "grad_norm": 0.0004863739013671875,
      "learning_rate": 7e-05,
      "loss": 0.5042,
      "step": 3250
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.15625,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.5351,
      "step": 3300
    },
    {
      "epoch": 0.3383838383838384,
      "grad_norm": 12.125,
      "learning_rate": 6.6e-05,
      "loss": 0.3649,
      "step": 3350
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 0.02880859375,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.5516,
      "step": 3400
    },
    {
      "epoch": 0.3484848484848485,
      "grad_norm": 0.005828857421875,
      "learning_rate": 6.2e-05,
      "loss": 0.5899,
      "step": 3450
    },
    {
      "epoch": 0.35353535353535354,
      "grad_norm": 6.59375,
      "learning_rate": 6e-05,
      "loss": 0.4999,
      "step": 3500
    },
    {
      "epoch": 0.35858585858585856,
      "grad_norm": 0.0026397705078125,
      "learning_rate": 5.8e-05,
      "loss": 0.6304,
      "step": 3550
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.0013427734375,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.7675,
      "step": 3600
    },
    {
      "epoch": 0.3686868686868687,
      "grad_norm": 14.375,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.4504,
      "step": 3650
    },
    {
      "epoch": 0.37373737373737376,
      "grad_norm": 0.0235595703125,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.4757,
      "step": 3700
    },
    {
      "epoch": 0.3787878787878788,
      "grad_norm": 0.0018157958984375,
      "learning_rate": 5e-05,
      "loss": 0.4315,
      "step": 3750
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 0.00012302398681640625,
      "learning_rate": 4.8e-05,
      "loss": 0.5263,
      "step": 3800
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.88671875,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.3134,
      "step": 3850
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 0.0245361328125,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.3785,
      "step": 3900
    },
    {
      "epoch": 0.398989898989899,
      "grad_norm": 5.78125,
      "learning_rate": 4.2e-05,
      "loss": 0.4354,
      "step": 3950
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.000598907470703125,
      "learning_rate": 4e-05,
      "loss": 0.7522,
      "step": 4000
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 6.65625,
      "learning_rate": 3.8e-05,
      "loss": 0.5139,
      "step": 4050
    },
    {
      "epoch": 0.41414141414141414,
      "grad_norm": 4.9375,
      "learning_rate": 3.6e-05,
      "loss": 0.3349,
      "step": 4100
    },
    {
      "epoch": 0.41919191919191917,
      "grad_norm": 34.75,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.85,
      "step": 4150
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.01953125,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.4747,
      "step": 4200
    },
    {
      "epoch": 0.4292929292929293,
      "grad_norm": 0.000492095947265625,
      "learning_rate": 3e-05,
      "loss": 0.4613,
      "step": 4250
    },
    {
      "epoch": 0.43434343434343436,
      "grad_norm": 0.0079345703125,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.66,
      "step": 4300
    },
    {
      "epoch": 0.4393939393939394,
      "grad_norm": 0.0013885498046875,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.7939,
      "step": 4350
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 14.75,
      "learning_rate": 2.4e-05,
      "loss": 0.7121,
      "step": 4400
    },
    {
      "epoch": 0.4494949494949495,
      "grad_norm": 6.03125,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.37,
      "step": 4450
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.6015625,
      "learning_rate": 2e-05,
      "loss": 0.5789,
      "step": 4500
    },
    {
      "epoch": 0.4595959595959596,
      "grad_norm": 0.0054931640625,
      "learning_rate": 1.8e-05,
      "loss": 0.3011,
      "step": 4550
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 0.00122833251953125,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.4864,
      "step": 4600
    },
    {
      "epoch": 0.4696969696969697,
      "grad_norm": 9.9375,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.9442,
      "step": 4650
    },
    {
      "epoch": 0.47474747474747475,
      "grad_norm": 0.040283203125,
      "learning_rate": 1.2e-05,
      "loss": 0.5764,
      "step": 4700
    },
    {
      "epoch": 0.4797979797979798,
      "grad_norm": 17.125,
      "learning_rate": 1e-05,
      "loss": 0.9053,
      "step": 4750
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 5.40625,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.455,
      "step": 4800
    },
    {
      "epoch": 0.4898989898989899,
      "grad_norm": 0.000843048095703125,
      "learning_rate": 6e-06,
      "loss": 0.4908,
      "step": 4850
    },
    {
      "epoch": 0.494949494949495,
      "grad_norm": 0.00081634521484375,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.4581,
      "step": 4900
    },
    {
      "epoch": 0.5,
      "grad_norm": 17.125,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.5418,
      "step": 4950
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 9.625,
      "learning_rate": 0.0,
      "loss": 0.7143,
      "step": 5000
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.084143267725312e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}