{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08347245409015025,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008347245409015025,
      "grad_norm": 5.03125,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.2979,
      "step": 50
    },
    {
      "epoch": 0.001669449081803005,
      "grad_norm": 3.734375,
      "learning_rate": 0.000196,
      "loss": 0.8508,
      "step": 100
    },
    {
      "epoch": 0.0025041736227045075,
      "grad_norm": 0.58984375,
      "learning_rate": 0.000194,
      "loss": 0.7959,
      "step": 150
    },
    {
      "epoch": 0.00333889816360601,
      "grad_norm": 0.578125,
      "learning_rate": 0.000192,
      "loss": 0.726,
      "step": 200
    },
    {
      "epoch": 0.004173622704507512,
      "grad_norm": 0.328125,
      "learning_rate": 0.00019,
      "loss": 0.9015,
      "step": 250
    },
    {
      "epoch": 0.005008347245409015,
      "grad_norm": 69.5,
      "learning_rate": 0.000188,
      "loss": 0.4003,
      "step": 300
    },
    {
      "epoch": 0.005843071786310518,
      "grad_norm": 3.015625,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.5518,
      "step": 350
    },
    {
      "epoch": 0.00667779632721202,
      "grad_norm": 0.034912109375,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.4198,
      "step": 400
    },
    {
      "epoch": 0.007512520868113523,
      "grad_norm": 5.90625,
      "learning_rate": 0.000182,
      "loss": 0.8151,
      "step": 450
    },
    {
      "epoch": 0.008347245409015025,
      "grad_norm": 17.125,
      "learning_rate": 0.00018,
      "loss": 0.5379,
      "step": 500
    },
    {
      "epoch": 0.009181969949916527,
      "grad_norm": 0.0654296875,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.5603,
      "step": 550
    },
    {
      "epoch": 0.01001669449081803,
      "grad_norm": 0.10400390625,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.7589,
      "step": 600
    },
    {
      "epoch": 0.010851419031719533,
      "grad_norm": 0.265625,
      "learning_rate": 0.000174,
      "loss": 0.3531,
      "step": 650
    },
    {
      "epoch": 0.011686143572621035,
      "grad_norm": 4.59375,
      "learning_rate": 0.000172,
      "loss": 0.2717,
      "step": 700
    },
    {
      "epoch": 0.012520868113522538,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00017,
      "loss": 0.3344,
      "step": 750
    },
    {
      "epoch": 0.01335559265442404,
      "grad_norm": 4.6875,
      "learning_rate": 0.000168,
      "loss": 0.3585,
      "step": 800
    },
    {
      "epoch": 0.014190317195325543,
      "grad_norm": 0.04736328125,
      "learning_rate": 0.000166,
      "loss": 0.3218,
      "step": 850
    },
    {
      "epoch": 0.015025041736227046,
      "grad_norm": 0.046875,
      "learning_rate": 0.000164,
      "loss": 0.3344,
      "step": 900
    },
    {
      "epoch": 0.015859766277128547,
      "grad_norm": 0.015625,
      "learning_rate": 0.000162,
      "loss": 0.4233,
      "step": 950
    },
    {
      "epoch": 0.01669449081803005,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.00016,
      "loss": 0.6014,
      "step": 1000
    },
    {
      "epoch": 0.017529215358931552,
      "grad_norm": 3.390625,
      "learning_rate": 0.00015800000000000002,
      "loss": 0.4044,
      "step": 1050
    },
    {
      "epoch": 0.018363939899833055,
      "grad_norm": 0.31640625,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.9183,
      "step": 1100
    },
    {
      "epoch": 0.019198664440734557,
      "grad_norm": 0.076171875,
      "learning_rate": 0.000154,
      "loss": 0.2508,
      "step": 1150
    },
    {
      "epoch": 0.02003338898163606,
      "grad_norm": 0.01055908203125,
      "learning_rate": 0.000152,
      "loss": 0.3563,
      "step": 1200
    },
    {
      "epoch": 0.020868113522537562,
      "grad_norm": 54.0,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.4328,
      "step": 1250
    },
    {
      "epoch": 0.021702838063439065,
      "grad_norm": 19.5,
      "learning_rate": 0.000148,
      "loss": 0.312,
      "step": 1300
    },
    {
      "epoch": 0.022537562604340568,
      "grad_norm": 0.0380859375,
      "learning_rate": 0.000146,
      "loss": 0.3068,
      "step": 1350
    },
    {
      "epoch": 0.02337228714524207,
      "grad_norm": 0.006622314453125,
      "learning_rate": 0.000144,
      "loss": 0.3987,
      "step": 1400
    },
    {
      "epoch": 0.024207011686143573,
      "grad_norm": 8.0625,
      "learning_rate": 0.000142,
      "loss": 0.4942,
      "step": 1450
    },
    {
      "epoch": 0.025041736227045076,
      "grad_norm": 26.125,
      "learning_rate": 0.00014,
      "loss": 0.4011,
      "step": 1500
    },
    {
      "epoch": 0.02587646076794658,
      "grad_norm": 0.58203125,
      "learning_rate": 0.000138,
      "loss": 0.5129,
      "step": 1550
    },
    {
      "epoch": 0.02671118530884808,
      "grad_norm": 0.0267333984375,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.1984,
      "step": 1600
    },
    {
      "epoch": 0.027545909849749584,
      "grad_norm": 0.0157470703125,
      "learning_rate": 0.000134,
      "loss": 0.4052,
      "step": 1650
    },
    {
      "epoch": 0.028380634390651086,
      "grad_norm": 4.5625,
      "learning_rate": 0.000132,
      "loss": 0.4439,
      "step": 1700
    },
    {
      "epoch": 0.02921535893155259,
      "grad_norm": 21.125,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.5354,
      "step": 1750
    },
    {
      "epoch": 0.03005008347245409,
      "grad_norm": 15.375,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.5931,
      "step": 1800
    },
    {
      "epoch": 0.030884808013355594,
      "grad_norm": 1.3515625,
      "learning_rate": 0.000126,
      "loss": 0.1363,
      "step": 1850
    },
    {
      "epoch": 0.03171953255425709,
      "grad_norm": 0.53125,
      "learning_rate": 0.000124,
      "loss": 0.4885,
      "step": 1900
    },
    {
      "epoch": 0.0325542570951586,
      "grad_norm": 0.0908203125,
      "learning_rate": 0.000122,
      "loss": 0.265,
      "step": 1950
    },
    {
      "epoch": 0.0333889816360601,
      "grad_norm": 0.0142822265625,
      "learning_rate": 0.00012,
      "loss": 0.265,
      "step": 2000
    },
    {
      "epoch": 0.034223706176961605,
      "grad_norm": 3.25,
      "learning_rate": 0.000118,
      "loss": 0.5515,
      "step": 2050
    },
    {
      "epoch": 0.035058430717863104,
      "grad_norm": 3.5,
      "learning_rate": 0.000116,
      "loss": 0.3973,
      "step": 2100
    },
    {
      "epoch": 0.03589315525876461,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.4916,
      "step": 2150
    },
    {
      "epoch": 0.03672787979966611,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.4639,
      "step": 2200
    },
    {
      "epoch": 0.037562604340567615,
      "grad_norm": 0.10693359375,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.4581,
      "step": 2250
    },
    {
      "epoch": 0.038397328881469114,
      "grad_norm": 5.75,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.3952,
      "step": 2300
    },
    {
      "epoch": 0.03923205342237062,
      "grad_norm": 0.058837890625,
      "learning_rate": 0.00010600000000000002,
      "loss": 0.5916,
      "step": 2350
    },
    {
      "epoch": 0.04006677796327212,
      "grad_norm": 69.5,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.394,
      "step": 2400
    },
    {
      "epoch": 0.040901502504173626,
      "grad_norm": 0.04833984375,
      "learning_rate": 0.00010200000000000001,
      "loss": 0.2667,
      "step": 2450
    },
    {
      "epoch": 0.041736227045075125,
      "grad_norm": 0.005615234375,
      "learning_rate": 0.0001,
      "loss": 0.4901,
      "step": 2500
    },
    {
      "epoch": 0.04257095158597663,
      "grad_norm": 0.004180908203125,
      "learning_rate": 9.8e-05,
      "loss": 0.3322,
      "step": 2550
    },
    {
      "epoch": 0.04340567612687813,
      "grad_norm": 0.048095703125,
      "learning_rate": 9.6e-05,
      "loss": 0.3777,
      "step": 2600
    },
    {
      "epoch": 0.04424040066777963,
      "grad_norm": 0.08447265625,
      "learning_rate": 9.4e-05,
      "loss": 0.4049,
      "step": 2650
    },
    {
      "epoch": 0.045075125208681135,
      "grad_norm": 0.0712890625,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.5967,
      "step": 2700
    },
    {
      "epoch": 0.045909849749582635,
      "grad_norm": 5.78125,
      "learning_rate": 9e-05,
      "loss": 0.2451,
      "step": 2750
    },
    {
      "epoch": 0.04674457429048414,
      "grad_norm": 0.0081787109375,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.4497,
      "step": 2800
    },
    {
      "epoch": 0.04757929883138564,
      "grad_norm": 0.0260009765625,
      "learning_rate": 8.6e-05,
      "loss": 0.4576,
      "step": 2850
    },
    {
      "epoch": 0.048414023372287146,
      "grad_norm": 0.01025390625,
      "learning_rate": 8.4e-05,
      "loss": 0.4427,
      "step": 2900
    },
    {
      "epoch": 0.049248747913188645,
      "grad_norm": 0.04296875,
      "learning_rate": 8.2e-05,
      "loss": 0.4576,
      "step": 2950
    },
    {
      "epoch": 0.05008347245409015,
      "grad_norm": 0.0634765625,
      "learning_rate": 8e-05,
      "loss": 0.3468,
      "step": 3000
    },
    {
      "epoch": 0.05091819699499165,
      "grad_norm": 14.0625,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.491,
      "step": 3050
    },
    {
      "epoch": 0.05175292153589316,
      "grad_norm": 0.0277099609375,
      "learning_rate": 7.6e-05,
      "loss": 0.3008,
      "step": 3100
    },
    {
      "epoch": 0.052587646076794656,
      "grad_norm": 0.03466796875,
      "learning_rate": 7.4e-05,
      "loss": 0.3269,
      "step": 3150
    },
    {
      "epoch": 0.05342237061769616,
      "grad_norm": 0.024169921875,
      "learning_rate": 7.2e-05,
      "loss": 0.4641,
      "step": 3200
    },
    {
      "epoch": 0.05425709515859766,
      "grad_norm": 0.02099609375,
      "learning_rate": 7e-05,
      "loss": 0.2215,
      "step": 3250
    },
    {
      "epoch": 0.05509181969949917,
      "grad_norm": 0.04833984375,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.3736,
      "step": 3300
    },
    {
      "epoch": 0.055926544240400666,
      "grad_norm": 0.040283203125,
      "learning_rate": 6.6e-05,
      "loss": 0.114,
      "step": 3350
    },
    {
      "epoch": 0.05676126878130217,
      "grad_norm": 0.45703125,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.2316,
      "step": 3400
    },
    {
      "epoch": 0.05759599332220367,
      "grad_norm": 0.06982421875,
      "learning_rate": 6.2e-05,
      "loss": 0.6308,
      "step": 3450
    },
    {
      "epoch": 0.05843071786310518,
      "grad_norm": 2.765625,
      "learning_rate": 6e-05,
      "loss": 0.2929,
      "step": 3500
    },
    {
      "epoch": 0.05926544240400668,
      "grad_norm": 0.06396484375,
      "learning_rate": 5.8e-05,
      "loss": 0.5138,
      "step": 3550
    },
    {
      "epoch": 0.06010016694490818,
      "grad_norm": 0.07861328125,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.5067,
      "step": 3600
    },
    {
      "epoch": 0.06093489148580968,
      "grad_norm": 3.875,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.6174,
      "step": 3650
    },
    {
      "epoch": 0.06176961602671119,
      "grad_norm": 0.17578125,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.3295,
      "step": 3700
    },
    {
      "epoch": 0.06260434056761269,
      "grad_norm": 0.08251953125,
      "learning_rate": 5e-05,
      "loss": 0.3084,
      "step": 3750
    },
    {
      "epoch": 0.06343906510851419,
      "grad_norm": 0.33203125,
      "learning_rate": 4.8e-05,
      "loss": 0.3046,
      "step": 3800
    },
    {
      "epoch": 0.0642737896494157,
      "grad_norm": 0.126953125,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.1521,
      "step": 3850
    },
    {
      "epoch": 0.0651085141903172,
      "grad_norm": 0.08447265625,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.4219,
      "step": 3900
    },
    {
      "epoch": 0.0659432387312187,
      "grad_norm": 105.5,
      "learning_rate": 4.2e-05,
      "loss": 0.2136,
      "step": 3950
    },
    {
      "epoch": 0.0667779632721202,
      "grad_norm": 0.0830078125,
      "learning_rate": 4e-05,
      "loss": 0.1255,
      "step": 4000
    },
    {
      "epoch": 0.0676126878130217,
      "grad_norm": 3.84375,
      "learning_rate": 3.8e-05,
      "loss": 0.3222,
      "step": 4050
    },
    {
      "epoch": 0.06844741235392321,
      "grad_norm": 0.04833984375,
      "learning_rate": 3.6e-05,
      "loss": 0.4844,
      "step": 4100
    },
    {
      "epoch": 0.06928213689482471,
      "grad_norm": 3.65625,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.2207,
      "step": 4150
    },
    {
      "epoch": 0.07011686143572621,
      "grad_norm": 0.0478515625,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.2303,
      "step": 4200
    },
    {
      "epoch": 0.0709515859766277,
      "grad_norm": 0.10595703125,
      "learning_rate": 3e-05,
      "loss": 0.3358,
      "step": 4250
    },
    {
      "epoch": 0.07178631051752922,
      "grad_norm": 0.08349609375,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.6106,
      "step": 4300
    },
    {
      "epoch": 0.07262103505843072,
      "grad_norm": 0.09130859375,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.4787,
      "step": 4350
    },
    {
      "epoch": 0.07345575959933222,
      "grad_norm": 0.042236328125,
      "learning_rate": 2.4e-05,
      "loss": 0.145,
      "step": 4400
    },
    {
      "epoch": 0.07429048414023372,
      "grad_norm": 0.020263671875,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.3278,
      "step": 4450
    },
    {
      "epoch": 0.07512520868113523,
      "grad_norm": 0.00701904296875,
      "learning_rate": 2e-05,
      "loss": 0.3238,
      "step": 4500
    },
    {
      "epoch": 0.07595993322203673,
      "grad_norm": 0.01080322265625,
      "learning_rate": 1.8e-05,
      "loss": 0.3776,
      "step": 4550
    },
    {
      "epoch": 0.07679465776293823,
      "grad_norm": 0.049072265625,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.3402,
      "step": 4600
    },
    {
      "epoch": 0.07762938230383973,
      "grad_norm": 0.0712890625,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.429,
      "step": 4650
    },
    {
      "epoch": 0.07846410684474124,
      "grad_norm": 0.53125,
      "learning_rate": 1.2e-05,
      "loss": 0.5878,
      "step": 4700
    },
    {
      "epoch": 0.07929883138564274,
      "grad_norm": 3.828125,
      "learning_rate": 1e-05,
      "loss": 0.4823,
      "step": 4750
    },
    {
      "epoch": 0.08013355592654424,
      "grad_norm": 0.059326171875,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1802,
      "step": 4800
    },
    {
      "epoch": 0.08096828046744574,
      "grad_norm": 0.00628662109375,
      "learning_rate": 6e-06,
      "loss": 0.4154,
      "step": 4850
    },
    {
      "epoch": 0.08180300500834725,
      "grad_norm": 0.06005859375,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.295,
      "step": 4900
    },
    {
      "epoch": 0.08263772954924875,
      "grad_norm": 0.01287841796875,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.3699,
      "step": 4950
    },
    {
      "epoch": 0.08347245409015025,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0,
      "loss": 0.3094,
      "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": 2.145082707738624e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}