{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 20.95467426130391,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3432,
      "step": 1
    },
    {
      "epoch": 0.08,
      "grad_norm": 20.95146113076943,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.3104,
      "step": 2
    },
    {
      "epoch": 0.12,
      "grad_norm": 18.695715904625004,
      "learning_rate": 1.2e-05,
      "loss": 1.1957,
      "step": 3
    },
    {
      "epoch": 0.16,
      "grad_norm": 6.196711441343313,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.0011,
      "step": 4
    },
    {
      "epoch": 0.2,
      "grad_norm": 26.693832109825298,
      "learning_rate": 2e-05,
      "loss": 0.9089,
      "step": 5
    },
    {
      "epoch": 0.24,
      "grad_norm": 34.60487648182799,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 0.8574,
      "step": 6
    },
    {
      "epoch": 0.28,
      "grad_norm": 7.637162579299049,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 0.7505,
      "step": 7
    },
    {
      "epoch": 0.32,
      "grad_norm": 7.703193584529458,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.6477,
      "step": 8
    },
    {
      "epoch": 0.36,
      "grad_norm": 4.037711068658207,
      "learning_rate": 1.961261695938319e-05,
      "loss": 0.583,
      "step": 9
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.456376319745342,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.5563,
      "step": 10
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.8894485667436451,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.5288,
      "step": 11
    },
    {
      "epoch": 0.48,
      "grad_norm": 3.7707647532983777,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 0.4868,
      "step": 12
    },
    {
      "epoch": 0.52,
      "grad_norm": 2.2345570731954787,
      "learning_rate": 1.848048096156426e-05,
      "loss": 0.4362,
      "step": 13
    },
    {
      "epoch": 0.56,
      "grad_norm": 12.127623139784363,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.5204,
      "step": 14
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.8005689925596364,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.4713,
      "step": 15
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.3208189016174614,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 0.4494,
      "step": 16
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.4294782311814547,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 0.3701,
      "step": 17
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.1861085398275806,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 0.3279,
      "step": 18
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.7972668891366532,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 0.3538,
      "step": 19
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.1118991226768649,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.3527,
      "step": 20
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.2672213064164632,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 0.3516,
      "step": 21
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.1065774033539162,
      "learning_rate": 1.3746065934159123e-05,
      "loss": 0.278,
      "step": 22
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.1584787722909975,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.3224,
      "step": 23
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.0397469207200751,
      "learning_rate": 1.2419218955996677e-05,
      "loss": 0.2877,
      "step": 24
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9846681303683493,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.2563,
      "step": 25
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.965671625038492,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 0.2096,
      "step": 26
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.9423173631619357,
      "learning_rate": 1.0348994967025012e-05,
      "loss": 0.2249,
      "step": 27
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.1630883322890204,
      "learning_rate": 9.651005032974994e-06,
      "loss": 0.2317,
      "step": 28
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.9885726358684307,
      "learning_rate": 8.954715367323468e-06,
      "loss": 0.2162,
      "step": 29
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.8917523276274567,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.2,
      "step": 30
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.8776875901995292,
      "learning_rate": 7.580781044003324e-06,
      "loss": 0.225,
      "step": 31
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.9338614157832891,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.2812,
      "step": 32
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.9462741195866129,
      "learning_rate": 6.25393406584088e-06,
      "loss": 0.2099,
      "step": 33
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 1.067551955524862,
      "learning_rate": 5.616288532109225e-06,
      "loss": 0.2207,
      "step": 34
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.8183862844029435,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.1642,
      "step": 35
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.8753190703243595,
      "learning_rate": 4.408070965292534e-06,
      "loss": 0.175,
      "step": 36
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.8752471430746271,
      "learning_rate": 3.8433852467434175e-06,
      "loss": 0.1647,
      "step": 37
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.8705110834716833,
      "learning_rate": 3.308693936411421e-06,
      "loss": 0.1927,
      "step": 38
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.76304514341136,
      "learning_rate": 2.8066019966134907e-06,
      "loss": 0.1347,
      "step": 39
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.8283768694620569,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.185,
      "step": 40
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.707137631170887,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.1495,
      "step": 41
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.6567669502350291,
      "learning_rate": 1.5195190384357405e-06,
      "loss": 0.134,
      "step": 42
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.7578843790061478,
      "learning_rate": 1.1705240714107301e-06,
      "loss": 0.1868,
      "step": 43
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.8551499434223829,
      "learning_rate": 8.645454235739903e-07,
      "loss": 0.1588,
      "step": 44
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.702284901302281,
      "learning_rate": 6.030737921409169e-07,
      "loss": 0.1302,
      "step": 45
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.7734648176320588,
      "learning_rate": 3.8738304061681107e-07,
      "loss": 0.1503,
      "step": 46
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.8183784862153622,
      "learning_rate": 2.1852399266194312e-07,
      "loss": 0.1744,
      "step": 47
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.8445432365011236,
      "learning_rate": 9.731931258429638e-08,
      "loss": 0.1883,
      "step": 48
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.7786477864917907,
      "learning_rate": 2.4359497401758026e-08,
      "loss": 0.1551,
      "step": 49
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8575569192424809,
      "learning_rate": 0.0,
      "loss": 0.1932,
      "step": 50
    },
    {
      "epoch": 2.0,
      "step": 50,
      "total_flos": 4886773432320.0,
      "train_loss": 0.39206851929426195,
      "train_runtime": 235.2746,
      "train_samples_per_second": 6.784,
      "train_steps_per_second": 0.213
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4886773432320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}