{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4432624113475177,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004432624113475178,
      "grad_norm": 2.75,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.1253,
      "step": 50
    },
    {
      "epoch": 0.008865248226950355,
      "grad_norm": 3.359375,
      "learning_rate": 0.000196,
      "loss": 0.9369,
      "step": 100
    },
    {
      "epoch": 0.013297872340425532,
      "grad_norm": 1.859375,
      "learning_rate": 0.000194,
      "loss": 0.811,
      "step": 150
    },
    {
      "epoch": 0.01773049645390071,
      "grad_norm": 0.478515625,
      "learning_rate": 0.000192,
      "loss": 0.739,
      "step": 200
    },
    {
      "epoch": 0.022163120567375887,
      "grad_norm": 5.46875,
      "learning_rate": 0.00019,
      "loss": 0.8697,
      "step": 250
    },
    {
      "epoch": 0.026595744680851064,
      "grad_norm": 0.2734375,
      "learning_rate": 0.000188,
      "loss": 0.7062,
      "step": 300
    },
    {
      "epoch": 0.03102836879432624,
      "grad_norm": 6.6875,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.8534,
      "step": 350
    },
    {
      "epoch": 0.03546099290780142,
      "grad_norm": 20.25,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.7787,
      "step": 400
    },
    {
      "epoch": 0.0398936170212766,
      "grad_norm": 2.796875,
      "learning_rate": 0.000182,
      "loss": 0.6886,
      "step": 450
    },
    {
      "epoch": 0.044326241134751775,
      "grad_norm": 5.15625,
      "learning_rate": 0.00018,
      "loss": 0.7839,
      "step": 500
    },
    {
      "epoch": 0.04875886524822695,
      "grad_norm": 5.59375,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.956,
      "step": 550
    },
    {
      "epoch": 0.05319148936170213,
      "grad_norm": 4.34375,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.7948,
      "step": 600
    },
    {
      "epoch": 0.057624113475177305,
      "grad_norm": 4.5,
      "learning_rate": 0.000174,
      "loss": 0.5882,
      "step": 650
    },
    {
      "epoch": 0.06205673758865248,
      "grad_norm": 0.388671875,
      "learning_rate": 0.000172,
      "loss": 0.6561,
      "step": 700
    },
    {
      "epoch": 0.06648936170212766,
      "grad_norm": 16.375,
      "learning_rate": 0.00017,
      "loss": 0.6377,
      "step": 750
    },
    {
      "epoch": 0.07092198581560284,
      "grad_norm": 1.78125,
      "learning_rate": 0.000168,
      "loss": 0.8455,
      "step": 800
    },
    {
      "epoch": 0.07535460992907801,
      "grad_norm": 1.3203125,
      "learning_rate": 0.000166,
      "loss": 0.8923,
      "step": 850
    },
    {
      "epoch": 0.0797872340425532,
      "grad_norm": 28.625,
      "learning_rate": 0.000164,
      "loss": 0.8399,
      "step": 900
    },
    {
      "epoch": 0.08421985815602837,
      "grad_norm": 2.265625,
      "learning_rate": 0.000162,
      "loss": 0.7785,
      "step": 950
    },
    {
      "epoch": 0.08865248226950355,
      "grad_norm": 0.47265625,
      "learning_rate": 0.00016,
      "loss": 0.8271,
      "step": 1000
    },
    {
      "epoch": 0.09308510638297872,
      "grad_norm": 2.5625,
      "learning_rate": 0.00015800000000000002,
      "loss": 0.7935,
      "step": 1050
    },
    {
      "epoch": 0.0975177304964539,
      "grad_norm": 9.6875,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.7888,
      "step": 1100
    },
    {
      "epoch": 0.10195035460992907,
      "grad_norm": 10.5,
      "learning_rate": 0.000154,
      "loss": 0.7048,
      "step": 1150
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 0.7109375,
      "learning_rate": 0.000152,
      "loss": 0.9688,
      "step": 1200
    },
    {
      "epoch": 0.11081560283687943,
      "grad_norm": 1.546875,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.6062,
      "step": 1250
    },
    {
      "epoch": 0.11524822695035461,
      "grad_norm": 4.21875,
      "learning_rate": 0.000148,
      "loss": 0.6777,
      "step": 1300
    },
    {
      "epoch": 0.1196808510638298,
      "grad_norm": 6.84375,
      "learning_rate": 0.000146,
      "loss": 0.845,
      "step": 1350
    },
    {
      "epoch": 0.12411347517730496,
      "grad_norm": 3.328125,
      "learning_rate": 0.000144,
      "loss": 0.4355,
      "step": 1400
    },
    {
      "epoch": 0.12854609929078015,
      "grad_norm": 5.96875,
      "learning_rate": 0.000142,
      "loss": 0.7743,
      "step": 1450
    },
    {
      "epoch": 0.13297872340425532,
      "grad_norm": 8.4375,
      "learning_rate": 0.00014,
      "loss": 0.7038,
      "step": 1500
    },
    {
      "epoch": 0.1374113475177305,
      "grad_norm": 4.625,
      "learning_rate": 0.000138,
      "loss": 0.7454,
      "step": 1550
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 4.15625,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.7579,
      "step": 1600
    },
    {
      "epoch": 0.14627659574468085,
      "grad_norm": 4.5,
      "learning_rate": 0.000134,
      "loss": 0.6768,
      "step": 1650
    },
    {
      "epoch": 0.15070921985815602,
      "grad_norm": 2.359375,
      "learning_rate": 0.000132,
      "loss": 0.6181,
      "step": 1700
    },
    {
      "epoch": 0.1551418439716312,
      "grad_norm": 6.3125,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.6848,
      "step": 1750
    },
    {
      "epoch": 0.1595744680851064,
      "grad_norm": 5.71875,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.653,
      "step": 1800
    },
    {
      "epoch": 0.16400709219858156,
      "grad_norm": 0.1298828125,
      "learning_rate": 0.000126,
      "loss": 0.6359,
      "step": 1850
    },
    {
      "epoch": 0.16843971631205673,
      "grad_norm": 11.875,
      "learning_rate": 0.000124,
      "loss": 0.6708,
      "step": 1900
    },
    {
      "epoch": 0.17287234042553193,
      "grad_norm": 9.375,
      "learning_rate": 0.000122,
      "loss": 0.5846,
      "step": 1950
    },
    {
      "epoch": 0.1773049645390071,
      "grad_norm": 10.6875,
      "learning_rate": 0.00012,
      "loss": 0.7585,
      "step": 2000
    },
    {
      "epoch": 0.18173758865248227,
      "grad_norm": 12.375,
      "learning_rate": 0.000118,
      "loss": 0.8175,
      "step": 2050
    },
    {
      "epoch": 0.18617021276595744,
      "grad_norm": 8.75,
      "learning_rate": 0.000116,
      "loss": 0.5447,
      "step": 2100
    },
    {
      "epoch": 0.19060283687943264,
      "grad_norm": 22.125,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.7702,
      "step": 2150
    },
    {
      "epoch": 0.1950354609929078,
      "grad_norm": 0.73046875,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.8125,
      "step": 2200
    },
    {
      "epoch": 0.19946808510638298,
      "grad_norm": 6.46875,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.6041,
      "step": 2250
    },
    {
      "epoch": 0.20390070921985815,
      "grad_norm": 17.625,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.5993,
      "step": 2300
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 9.9375,
      "learning_rate": 0.00010600000000000002,
      "loss": 0.6323,
      "step": 2350
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 19.625,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.5647,
      "step": 2400
    },
    {
      "epoch": 0.21719858156028368,
      "grad_norm": 0.392578125,
      "learning_rate": 0.00010200000000000001,
      "loss": 0.6763,
      "step": 2450
    },
    {
      "epoch": 0.22163120567375885,
      "grad_norm": 12.5,
      "learning_rate": 0.0001,
      "loss": 0.6527,
      "step": 2500
    },
    {
      "epoch": 0.22606382978723405,
      "grad_norm": 5.1875,
      "learning_rate": 9.8e-05,
      "loss": 0.6438,
      "step": 2550
    },
    {
      "epoch": 0.23049645390070922,
      "grad_norm": 4.875,
      "learning_rate": 9.6e-05,
      "loss": 0.7929,
      "step": 2600
    },
    {
      "epoch": 0.2349290780141844,
      "grad_norm": 3.984375,
      "learning_rate": 9.4e-05,
      "loss": 0.6112,
      "step": 2650
    },
    {
      "epoch": 0.2393617021276596,
      "grad_norm": 0.451171875,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.5602,
      "step": 2700
    },
    {
      "epoch": 0.24379432624113476,
      "grad_norm": 18.25,
      "learning_rate": 9e-05,
      "loss": 0.5802,
      "step": 2750
    },
    {
      "epoch": 0.24822695035460993,
      "grad_norm": 0.166015625,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.7554,
      "step": 2800
    },
    {
      "epoch": 0.2526595744680851,
      "grad_norm": 8.625,
      "learning_rate": 8.6e-05,
      "loss": 0.9453,
      "step": 2850
    },
    {
      "epoch": 0.2570921985815603,
      "grad_norm": 6.46875,
      "learning_rate": 8.4e-05,
      "loss": 0.517,
      "step": 2900
    },
    {
      "epoch": 0.26152482269503546,
      "grad_norm": 7.21875,
      "learning_rate": 8.2e-05,
      "loss": 0.5296,
      "step": 2950
    },
    {
      "epoch": 0.26595744680851063,
      "grad_norm": 4.6875,
      "learning_rate": 8e-05,
      "loss": 0.6247,
      "step": 3000
    },
    {
      "epoch": 0.2703900709219858,
      "grad_norm": 3.71875,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.5144,
      "step": 3050
    },
    {
      "epoch": 0.274822695035461,
      "grad_norm": 2.484375,
      "learning_rate": 7.6e-05,
      "loss": 0.548,
      "step": 3100
    },
    {
      "epoch": 0.27925531914893614,
      "grad_norm": 5.1875,
      "learning_rate": 7.4e-05,
      "loss": 0.526,
      "step": 3150
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 1.0078125,
      "learning_rate": 7.2e-05,
      "loss": 0.4873,
      "step": 3200
    },
    {
      "epoch": 0.28812056737588654,
      "grad_norm": 0.53125,
      "learning_rate": 7e-05,
      "loss": 0.6683,
      "step": 3250
    },
    {
      "epoch": 0.2925531914893617,
      "grad_norm": 4.09375,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.5688,
      "step": 3300
    },
    {
      "epoch": 0.2969858156028369,
      "grad_norm": 7.125,
      "learning_rate": 6.6e-05,
      "loss": 0.5528,
      "step": 3350
    },
    {
      "epoch": 0.30141843971631205,
      "grad_norm": 0.375,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.5698,
      "step": 3400
    },
    {
      "epoch": 0.3058510638297872,
      "grad_norm": 0.7421875,
      "learning_rate": 6.2e-05,
      "loss": 0.4358,
      "step": 3450
    },
    {
      "epoch": 0.3102836879432624,
      "grad_norm": 36.75,
      "learning_rate": 6e-05,
      "loss": 0.4974,
      "step": 3500
    },
    {
      "epoch": 0.3147163120567376,
      "grad_norm": 6.28125,
      "learning_rate": 5.8e-05,
      "loss": 0.5822,
      "step": 3550
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 0.140625,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.5152,
      "step": 3600
    },
    {
      "epoch": 0.32358156028368795,
      "grad_norm": 5.375,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.5257,
      "step": 3650
    },
    {
      "epoch": 0.3280141843971631,
      "grad_norm": 8.6875,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.6385,
      "step": 3700
    },
    {
      "epoch": 0.3324468085106383,
      "grad_norm": 0.5859375,
      "learning_rate": 5e-05,
      "loss": 0.6153,
      "step": 3750
    },
    {
      "epoch": 0.33687943262411346,
      "grad_norm": 2.046875,
      "learning_rate": 4.8e-05,
      "loss": 0.5267,
      "step": 3800
    },
    {
      "epoch": 0.34131205673758863,
      "grad_norm": 2.59375,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.7071,
      "step": 3850
    },
    {
      "epoch": 0.34574468085106386,
      "grad_norm": 0.9609375,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.4819,
      "step": 3900
    },
    {
      "epoch": 0.350177304964539,
      "grad_norm": 0.3046875,
      "learning_rate": 4.2e-05,
      "loss": 0.565,
      "step": 3950
    },
    {
      "epoch": 0.3546099290780142,
      "grad_norm": 3.171875,
      "learning_rate": 4e-05,
      "loss": 0.4512,
      "step": 4000
    },
    {
      "epoch": 0.35904255319148937,
      "grad_norm": 2.0625,
      "learning_rate": 3.8e-05,
      "loss": 0.5518,
      "step": 4050
    },
    {
      "epoch": 0.36347517730496454,
      "grad_norm": 23.625,
      "learning_rate": 3.6e-05,
      "loss": 0.7784,
      "step": 4100
    },
    {
      "epoch": 0.3679078014184397,
      "grad_norm": 27.25,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.7082,
      "step": 4150
    },
    {
      "epoch": 0.3723404255319149,
      "grad_norm": 8.375,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.473,
      "step": 4200
    },
    {
      "epoch": 0.37677304964539005,
      "grad_norm": 0.2353515625,
      "learning_rate": 3e-05,
      "loss": 0.5962,
      "step": 4250
    },
    {
      "epoch": 0.38120567375886527,
      "grad_norm": 10.5,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.6379,
      "step": 4300
    },
    {
      "epoch": 0.38563829787234044,
      "grad_norm": 3.15625,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.6172,
      "step": 4350
    },
    {
      "epoch": 0.3900709219858156,
      "grad_norm": 3.09375,
      "learning_rate": 2.4e-05,
      "loss": 0.5332,
      "step": 4400
    },
    {
      "epoch": 0.3945035460992908,
      "grad_norm": 5.59375,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.5809,
      "step": 4450
    },
    {
      "epoch": 0.39893617021276595,
      "grad_norm": 0.2314453125,
      "learning_rate": 2e-05,
      "loss": 0.4821,
      "step": 4500
    },
    {
      "epoch": 0.4033687943262411,
      "grad_norm": 6.15625,
      "learning_rate": 1.8e-05,
      "loss": 0.623,
      "step": 4550
    },
    {
      "epoch": 0.4078014184397163,
      "grad_norm": 32.25,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.6819,
      "step": 4600
    },
    {
      "epoch": 0.4122340425531915,
      "grad_norm": 10.0625,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.8649,
      "step": 4650
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 15.625,
      "learning_rate": 1.2e-05,
      "loss": 0.6015,
      "step": 4700
    },
    {
      "epoch": 0.42109929078014185,
      "grad_norm": 4.5625,
      "learning_rate": 1e-05,
      "loss": 0.7317,
      "step": 4750
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 4.625,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6881,
      "step": 4800
    },
    {
      "epoch": 0.4299645390070922,
      "grad_norm": 22.875,
      "learning_rate": 6e-06,
      "loss": 0.5076,
      "step": 4850
    },
    {
      "epoch": 0.43439716312056736,
      "grad_norm": 10.125,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.7898,
      "step": 4900
    },
    {
      "epoch": 0.43882978723404253,
      "grad_norm": 6.90625,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.426,
      "step": 4950
    },
    {
      "epoch": 0.4432624113475177,
      "grad_norm": 2.96875,
      "learning_rate": 0.0,
      "loss": 0.5788,
      "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": 2.88342593624064e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}