{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 200.0,
  "eval_steps": 500,
  "global_step": 17800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.617977528089888,
      "grad_norm": 0.8927184343338013,
      "learning_rate": 0.0009719101123595506,
      "loss": 2.0717,
      "step": 500
    },
    {
      "epoch": 11.235955056179776,
      "grad_norm": 0.45675593614578247,
      "learning_rate": 0.0009438202247191011,
      "loss": 0.366,
      "step": 1000
    },
    {
      "epoch": 16.853932584269664,
      "grad_norm": 0.4163215160369873,
      "learning_rate": 0.0009157303370786517,
      "loss": 0.1032,
      "step": 1500
    },
    {
      "epoch": 22.471910112359552,
      "grad_norm": 0.3441922962665558,
      "learning_rate": 0.0008876404494382022,
      "loss": 0.0713,
      "step": 2000
    },
    {
      "epoch": 28.089887640449437,
      "grad_norm": 0.39710932970046997,
      "learning_rate": 0.0008595505617977528,
      "loss": 0.0363,
      "step": 2500
    },
    {
      "epoch": 33.70786516853933,
      "grad_norm": 0.16218255460262299,
      "learning_rate": 0.0008314606741573035,
      "loss": 0.0359,
      "step": 3000
    },
    {
      "epoch": 39.325842696629216,
      "grad_norm": 0.17998535931110382,
      "learning_rate": 0.0008033707865168539,
      "loss": 0.0227,
      "step": 3500
    },
    {
      "epoch": 44.943820224719104,
      "grad_norm": 0.16715578734874725,
      "learning_rate": 0.0007752808988764046,
      "loss": 0.0226,
      "step": 4000
    },
    {
      "epoch": 50.561797752808985,
      "grad_norm": 0.43755656480789185,
      "learning_rate": 0.0007471910112359551,
      "loss": 0.0166,
      "step": 4500
    },
    {
      "epoch": 56.17977528089887,
      "grad_norm": 0.10883288085460663,
      "learning_rate": 0.0007191011235955056,
      "loss": 0.0206,
      "step": 5000
    },
    {
      "epoch": 61.79775280898876,
      "grad_norm": 0.06982209533452988,
      "learning_rate": 0.0006910112359550562,
      "loss": 0.0111,
      "step": 5500
    },
    {
      "epoch": 67.41573033707866,
      "grad_norm": 0.18309864401817322,
      "learning_rate": 0.0006629213483146067,
      "loss": 0.0112,
      "step": 6000
    },
    {
      "epoch": 73.03370786516854,
      "grad_norm": 0.2448071986436844,
      "learning_rate": 0.0006348314606741573,
      "loss": 0.0127,
      "step": 6500
    },
    {
      "epoch": 78.65168539325843,
      "grad_norm": 0.4600788652896881,
      "learning_rate": 0.0006067415730337079,
      "loss": 0.0156,
      "step": 7000
    },
    {
      "epoch": 84.26966292134831,
      "grad_norm": 0.039180297404527664,
      "learning_rate": 0.0005786516853932584,
      "loss": 0.01,
      "step": 7500
    },
    {
      "epoch": 89.88764044943821,
      "grad_norm": 0.05856933817267418,
      "learning_rate": 0.000550561797752809,
      "loss": 0.0073,
      "step": 8000
    },
    {
      "epoch": 95.50561797752809,
      "grad_norm": 0.07000260800123215,
      "learning_rate": 0.0005224719101123597,
      "loss": 0.0096,
      "step": 8500
    },
    {
      "epoch": 101.12359550561797,
      "grad_norm": 0.21435591578483582,
      "learning_rate": 0.0004943820224719101,
      "loss": 0.0055,
      "step": 9000
    },
    {
      "epoch": 106.74157303370787,
      "grad_norm": 0.09459387511014938,
      "learning_rate": 0.00046629213483146065,
      "loss": 0.0064,
      "step": 9500
    },
    {
      "epoch": 112.35955056179775,
      "grad_norm": 0.07463132590055466,
      "learning_rate": 0.00043820224719101126,
      "loss": 0.0066,
      "step": 10000
    },
    {
      "epoch": 117.97752808988764,
      "grad_norm": 0.14109277725219727,
      "learning_rate": 0.0004101123595505618,
      "loss": 0.0068,
      "step": 10500
    },
    {
      "epoch": 123.59550561797752,
      "grad_norm": 0.3136846721172333,
      "learning_rate": 0.00038202247191011237,
      "loss": 0.0049,
      "step": 11000
    },
    {
      "epoch": 129.2134831460674,
      "grad_norm": 0.08402496576309204,
      "learning_rate": 0.0003539325842696629,
      "loss": 0.0041,
      "step": 11500
    },
    {
      "epoch": 134.8314606741573,
      "grad_norm": 0.010163770988583565,
      "learning_rate": 0.00032584269662921353,
      "loss": 0.0037,
      "step": 12000
    },
    {
      "epoch": 140.4494382022472,
      "grad_norm": 0.1579727977514267,
      "learning_rate": 0.00029775280898876403,
      "loss": 0.0041,
      "step": 12500
    },
    {
      "epoch": 146.06741573033707,
      "grad_norm": 0.013693171553313732,
      "learning_rate": 0.0002696629213483146,
      "loss": 0.009,
      "step": 13000
    },
    {
      "epoch": 151.68539325842696,
      "grad_norm": 0.04315110668540001,
      "learning_rate": 0.0002415730337078652,
      "loss": 0.0035,
      "step": 13500
    },
    {
      "epoch": 157.30337078651687,
      "grad_norm": 0.022593241184949875,
      "learning_rate": 0.00021348314606741572,
      "loss": 0.003,
      "step": 14000
    },
    {
      "epoch": 162.92134831460675,
      "grad_norm": 0.03392694145441055,
      "learning_rate": 0.0001853932584269663,
      "loss": 0.0028,
      "step": 14500
    },
    {
      "epoch": 168.53932584269663,
      "grad_norm": 0.009065886959433556,
      "learning_rate": 0.00015730337078651685,
      "loss": 0.0025,
      "step": 15000
    },
    {
      "epoch": 174.1573033707865,
      "grad_norm": 0.017768818885087967,
      "learning_rate": 0.00012921348314606744,
      "loss": 0.0024,
      "step": 15500
    },
    {
      "epoch": 179.77528089887642,
      "grad_norm": 0.00971462856978178,
      "learning_rate": 0.00010112359550561798,
      "loss": 0.0024,
      "step": 16000
    },
    {
      "epoch": 185.3932584269663,
      "grad_norm": 0.010951046831905842,
      "learning_rate": 7.303370786516854e-05,
      "loss": 0.0023,
      "step": 16500
    },
    {
      "epoch": 191.01123595505618,
      "grad_norm": 0.011012041941285133,
      "learning_rate": 4.49438202247191e-05,
      "loss": 0.0023,
      "step": 17000
    },
    {
      "epoch": 196.62921348314606,
      "grad_norm": 0.0066545517183840275,
      "learning_rate": 1.685393258426966e-05,
      "loss": 0.0021,
      "step": 17500
    },
    {
      "epoch": 200.0,
      "step": 17800,
      "total_flos": 3.0988736397312e+17,
      "train_loss": 0.08202355481265636,
      "train_runtime": 28705.9446,
      "train_samples_per_second": 2.48,
      "train_steps_per_second": 0.62
    }
  ],
  "logging_steps": 500,
  "max_steps": 17800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 200,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0988736397312e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}