{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.091703056768559,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010917030567685589,
      "grad_norm": 0.0361328125,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.2963,
      "step": 50
    },
    {
      "epoch": 0.021834061135371178,
      "grad_norm": 4.6875,
      "learning_rate": 0.000196,
      "loss": 0.9099,
      "step": 100
    },
    {
      "epoch": 0.03275109170305677,
      "grad_norm": 0.4140625,
      "learning_rate": 0.000194,
      "loss": 0.6184,
      "step": 150
    },
    {
      "epoch": 0.043668122270742356,
      "grad_norm": 0.94140625,
      "learning_rate": 0.000192,
      "loss": 0.6445,
      "step": 200
    },
    {
      "epoch": 0.05458515283842795,
      "grad_norm": 0.02490234375,
      "learning_rate": 0.00019,
      "loss": 0.5761,
      "step": 250
    },
    {
      "epoch": 0.06550218340611354,
      "grad_norm": 1.8359375,
      "learning_rate": 0.000188,
      "loss": 0.8202,
      "step": 300
    },
    {
      "epoch": 0.07641921397379912,
      "grad_norm": 25.0,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.6368,
      "step": 350
    },
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 0.006439208984375,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.3766,
      "step": 400
    },
    {
      "epoch": 0.0982532751091703,
      "grad_norm": 176.0,
      "learning_rate": 0.000182,
      "loss": 0.5329,
      "step": 450
    },
    {
      "epoch": 0.1091703056768559,
      "grad_norm": 0.019287109375,
      "learning_rate": 0.00018,
      "loss": 0.6169,
      "step": 500
    },
    {
      "epoch": 0.12008733624454149,
      "grad_norm": 7.03125,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.6633,
      "step": 550
    },
    {
      "epoch": 0.13100436681222707,
      "grad_norm": 0.01361083984375,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.5915,
      "step": 600
    },
    {
      "epoch": 0.14192139737991266,
      "grad_norm": 0.1484375,
      "learning_rate": 0.000174,
      "loss": 0.513,
      "step": 650
    },
    {
      "epoch": 0.15283842794759825,
      "grad_norm": 0.00958251953125,
      "learning_rate": 0.000172,
      "loss": 0.4981,
      "step": 700
    },
    {
      "epoch": 0.16375545851528384,
      "grad_norm": 0.00677490234375,
      "learning_rate": 0.00017,
      "loss": 0.3848,
      "step": 750
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 0.07666015625,
      "learning_rate": 0.000168,
      "loss": 0.452,
      "step": 800
    },
    {
      "epoch": 0.185589519650655,
      "grad_norm": 0.0145263671875,
      "learning_rate": 0.000166,
      "loss": 0.7262,
      "step": 850
    },
    {
      "epoch": 0.1965065502183406,
      "grad_norm": 0.0172119140625,
      "learning_rate": 0.000164,
      "loss": 0.4341,
      "step": 900
    },
    {
      "epoch": 0.2074235807860262,
      "grad_norm": 1.796875,
      "learning_rate": 0.000162,
      "loss": 0.5116,
      "step": 950
    },
    {
      "epoch": 0.2183406113537118,
      "grad_norm": 0.01123046875,
      "learning_rate": 0.00016,
      "loss": 0.5325,
      "step": 1000
    },
    {
      "epoch": 0.2292576419213974,
      "grad_norm": 28.625,
      "learning_rate": 0.00015800000000000002,
      "loss": 0.4908,
      "step": 1050
    },
    {
      "epoch": 0.24017467248908297,
      "grad_norm": 0.0517578125,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.5384,
      "step": 1100
    },
    {
      "epoch": 0.25109170305676853,
      "grad_norm": 0.055419921875,
      "learning_rate": 0.000154,
      "loss": 0.5571,
      "step": 1150
    },
    {
      "epoch": 0.26200873362445415,
      "grad_norm": 0.392578125,
      "learning_rate": 0.000152,
      "loss": 0.5969,
      "step": 1200
    },
    {
      "epoch": 0.27292576419213976,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.3076,
      "step": 1250
    },
    {
      "epoch": 0.2838427947598253,
      "grad_norm": 47.25,
      "learning_rate": 0.000148,
      "loss": 0.3439,
      "step": 1300
    },
    {
      "epoch": 0.29475982532751094,
      "grad_norm": 0.00799560546875,
      "learning_rate": 0.000146,
      "loss": 0.3013,
      "step": 1350
    },
    {
      "epoch": 0.3056768558951965,
      "grad_norm": 0.06396484375,
      "learning_rate": 0.000144,
      "loss": 0.5307,
      "step": 1400
    },
    {
      "epoch": 0.3165938864628821,
      "grad_norm": 20.75,
      "learning_rate": 0.000142,
      "loss": 0.3934,
      "step": 1450
    },
    {
      "epoch": 0.32751091703056767,
      "grad_norm": 0.0703125,
      "learning_rate": 0.00014,
      "loss": 0.2161,
      "step": 1500
    },
    {
      "epoch": 0.3384279475982533,
      "grad_norm": 40.75,
      "learning_rate": 0.000138,
      "loss": 0.4879,
      "step": 1550
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 3.3125,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.4656,
      "step": 1600
    },
    {
      "epoch": 0.36026200873362446,
      "grad_norm": 0.020751953125,
      "learning_rate": 0.000134,
      "loss": 0.2679,
      "step": 1650
    },
    {
      "epoch": 0.37117903930131,
      "grad_norm": 68.5,
      "learning_rate": 0.000132,
      "loss": 0.5902,
      "step": 1700
    },
    {
      "epoch": 0.38209606986899564,
      "grad_norm": 0.091796875,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.2799,
      "step": 1750
    },
    {
      "epoch": 0.3930131004366812,
      "grad_norm": 0.0247802734375,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.4931,
      "step": 1800
    },
    {
      "epoch": 0.4039301310043668,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.000126,
      "loss": 0.3611,
      "step": 1850
    },
    {
      "epoch": 0.4148471615720524,
      "grad_norm": 0.007354736328125,
      "learning_rate": 0.000124,
      "loss": 0.3994,
      "step": 1900
    },
    {
      "epoch": 0.425764192139738,
      "grad_norm": 0.06884765625,
      "learning_rate": 0.000122,
      "loss": 0.3919,
      "step": 1950
    },
    {
      "epoch": 0.4366812227074236,
      "grad_norm": 86.5,
      "learning_rate": 0.00012,
      "loss": 0.2731,
      "step": 2000
    },
    {
      "epoch": 0.44759825327510916,
      "grad_norm": 0.0067138671875,
      "learning_rate": 0.000118,
      "loss": 0.3157,
      "step": 2050
    },
    {
      "epoch": 0.4585152838427948,
      "grad_norm": 0.027099609375,
      "learning_rate": 0.000116,
      "loss": 0.3493,
      "step": 2100
    },
    {
      "epoch": 0.46943231441048033,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.3887,
      "step": 2150
    },
    {
      "epoch": 0.48034934497816595,
      "grad_norm": 0.0086669921875,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.2559,
      "step": 2200
    },
    {
      "epoch": 0.4912663755458515,
      "grad_norm": 0.1044921875,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.4685,
      "step": 2250
    },
    {
      "epoch": 0.5021834061135371,
      "grad_norm": 0.00445556640625,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.3723,
      "step": 2300
    },
    {
      "epoch": 0.5131004366812227,
      "grad_norm": 0.00201416015625,
      "learning_rate": 0.00010600000000000002,
      "loss": 0.3303,
      "step": 2350
    },
    {
      "epoch": 0.5240174672489083,
      "grad_norm": 0.0361328125,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.3119,
      "step": 2400
    },
    {
      "epoch": 0.5349344978165939,
      "grad_norm": 18.25,
      "learning_rate": 0.00010200000000000001,
      "loss": 0.4043,
      "step": 2450
    },
    {
      "epoch": 0.5458515283842795,
      "grad_norm": 0.0026702880859375,
      "learning_rate": 0.0001,
      "loss": 0.114,
      "step": 2500
    },
    {
      "epoch": 0.5567685589519651,
      "grad_norm": 0.06982421875,
      "learning_rate": 9.8e-05,
      "loss": 0.2757,
      "step": 2550
    },
    {
      "epoch": 0.5676855895196506,
      "grad_norm": 0.0146484375,
      "learning_rate": 9.6e-05,
      "loss": 0.3825,
      "step": 2600
    },
    {
      "epoch": 0.5786026200873362,
      "grad_norm": 0.265625,
      "learning_rate": 9.4e-05,
      "loss": 0.4058,
      "step": 2650
    },
    {
      "epoch": 0.5895196506550219,
      "grad_norm": 2.71875,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.2844,
      "step": 2700
    },
    {
      "epoch": 0.6004366812227074,
      "grad_norm": 0.01806640625,
      "learning_rate": 9e-05,
      "loss": 0.317,
      "step": 2750
    },
    {
      "epoch": 0.611353711790393,
      "grad_norm": 1.078125,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.3611,
      "step": 2800
    },
    {
      "epoch": 0.6222707423580786,
      "grad_norm": 0.0830078125,
      "learning_rate": 8.6e-05,
      "loss": 0.2253,
      "step": 2850
    },
    {
      "epoch": 0.6331877729257642,
      "grad_norm": 0.017822265625,
      "learning_rate": 8.4e-05,
      "loss": 0.2998,
      "step": 2900
    },
    {
      "epoch": 0.6441048034934498,
      "grad_norm": 50.0,
      "learning_rate": 8.2e-05,
      "loss": 0.3148,
      "step": 2950
    },
    {
      "epoch": 0.6550218340611353,
      "grad_norm": 0.00156402587890625,
      "learning_rate": 8e-05,
      "loss": 0.3505,
      "step": 3000
    },
    {
      "epoch": 0.665938864628821,
      "grad_norm": 0.0107421875,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.1272,
      "step": 3050
    },
    {
      "epoch": 0.6768558951965066,
      "grad_norm": 0.00897216796875,
      "learning_rate": 7.6e-05,
      "loss": 0.2141,
      "step": 3100
    },
    {
      "epoch": 0.6877729257641921,
      "grad_norm": 0.0042724609375,
      "learning_rate": 7.4e-05,
      "loss": 0.3637,
      "step": 3150
    },
    {
      "epoch": 0.6986899563318777,
      "grad_norm": 0.0189208984375,
      "learning_rate": 7.2e-05,
      "loss": 0.2633,
      "step": 3200
    },
    {
      "epoch": 0.7096069868995634,
      "grad_norm": 0.0101318359375,
      "learning_rate": 7e-05,
      "loss": 0.1656,
      "step": 3250
    },
    {
      "epoch": 0.7205240174672489,
      "grad_norm": 0.06982421875,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.1287,
      "step": 3300
    },
    {
      "epoch": 0.7314410480349345,
      "grad_norm": 16.0,
      "learning_rate": 6.6e-05,
      "loss": 0.1781,
      "step": 3350
    },
    {
      "epoch": 0.74235807860262,
      "grad_norm": 0.1083984375,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.2521,
      "step": 3400
    },
    {
      "epoch": 0.7532751091703057,
      "grad_norm": 0.00106048583984375,
      "learning_rate": 6.2e-05,
      "loss": 0.1658,
      "step": 3450
    },
    {
      "epoch": 0.7641921397379913,
      "grad_norm": 0.0020599365234375,
      "learning_rate": 6e-05,
      "loss": 0.232,
      "step": 3500
    },
    {
      "epoch": 0.7751091703056768,
      "grad_norm": 0.04052734375,
      "learning_rate": 5.8e-05,
      "loss": 0.0531,
      "step": 3550
    },
    {
      "epoch": 0.7860262008733624,
      "grad_norm": 208.0,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.152,
      "step": 3600
    },
    {
      "epoch": 0.7969432314410481,
      "grad_norm": 0.00262451171875,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.3011,
      "step": 3650
    },
    {
      "epoch": 0.8078602620087336,
      "grad_norm": 0.0267333984375,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.3626,
      "step": 3700
    },
    {
      "epoch": 0.8187772925764192,
      "grad_norm": 0.017578125,
      "learning_rate": 5e-05,
      "loss": 0.1233,
      "step": 3750
    },
    {
      "epoch": 0.8296943231441049,
      "grad_norm": 2.453125,
      "learning_rate": 4.8e-05,
      "loss": 0.3622,
      "step": 3800
    },
    {
      "epoch": 0.8406113537117904,
      "grad_norm": 57.25,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.3681,
      "step": 3850
    },
    {
      "epoch": 0.851528384279476,
      "grad_norm": 0.006195068359375,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.4212,
      "step": 3900
    },
    {
      "epoch": 0.8624454148471615,
      "grad_norm": 0.0205078125,
      "learning_rate": 4.2e-05,
      "loss": 0.2464,
      "step": 3950
    },
    {
      "epoch": 0.8733624454148472,
      "grad_norm": 30.125,
      "learning_rate": 4e-05,
      "loss": 0.3118,
      "step": 4000
    },
    {
      "epoch": 0.8842794759825328,
      "grad_norm": 0.01165771484375,
      "learning_rate": 3.8e-05,
      "loss": 0.2954,
      "step": 4050
    },
    {
      "epoch": 0.8951965065502183,
      "grad_norm": 0.003509521484375,
      "learning_rate": 3.6e-05,
      "loss": 0.1704,
      "step": 4100
    },
    {
      "epoch": 0.9061135371179039,
      "grad_norm": 0.005859375,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.3955,
      "step": 4150
    },
    {
      "epoch": 0.9170305676855895,
      "grad_norm": 0.00323486328125,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.3858,
      "step": 4200
    },
    {
      "epoch": 0.9279475982532751,
      "grad_norm": 0.0021209716796875,
      "learning_rate": 3e-05,
      "loss": 0.0347,
      "step": 4250
    },
    {
      "epoch": 0.9388646288209607,
      "grad_norm": 0.07666015625,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.2532,
      "step": 4300
    },
    {
      "epoch": 0.9497816593886463,
      "grad_norm": 0.003997802734375,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.224,
      "step": 4350
    },
    {
      "epoch": 0.9606986899563319,
      "grad_norm": 0.0152587890625,
      "learning_rate": 2.4e-05,
      "loss": 0.0007,
      "step": 4400
    },
    {
      "epoch": 0.9716157205240175,
      "grad_norm": 0.00799560546875,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.1745,
      "step": 4450
    },
    {
      "epoch": 0.982532751091703,
      "grad_norm": 0.00482177734375,
      "learning_rate": 2e-05,
      "loss": 0.2485,
      "step": 4500
    },
    {
      "epoch": 0.9934497816593887,
      "grad_norm": 0.009521484375,
      "learning_rate": 1.8e-05,
      "loss": 0.177,
      "step": 4550
    },
    {
      "epoch": 1.0043668122270741,
      "grad_norm": 0.006622314453125,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.177,
      "step": 4600
    },
    {
      "epoch": 1.01528384279476,
      "grad_norm": 0.0023956298828125,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.1522,
      "step": 4650
    },
    {
      "epoch": 1.0262008733624455,
      "grad_norm": 0.033203125,
      "learning_rate": 1.2e-05,
      "loss": 0.2442,
      "step": 4700
    },
    {
      "epoch": 1.037117903930131,
      "grad_norm": 0.0037841796875,
      "learning_rate": 1e-05,
      "loss": 0.2411,
      "step": 4750
    },
    {
      "epoch": 1.0480349344978166,
      "grad_norm": 0.0019683837890625,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1355,
      "step": 4800
    },
    {
      "epoch": 1.0589519650655022,
      "grad_norm": 2.984375,
      "learning_rate": 6e-06,
      "loss": 0.365,
      "step": 4850
    },
    {
      "epoch": 1.0698689956331877,
      "grad_norm": 0.004119873046875,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.2094,
      "step": 4900
    },
    {
      "epoch": 1.0807860262008733,
      "grad_norm": 0.0024566650390625,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.1219,
      "step": 4950
    },
    {
      "epoch": 1.091703056768559,
      "grad_norm": 0.0034332275390625,
      "learning_rate": 0.0,
      "loss": 0.2887,
      "step": 5000
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.981914056646656e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}