{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 4.184950351715088,
      "learning_rate": 0.00013333333333333334,
      "loss": 3.352059555053711,
      "step": 5
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 13.914199829101562,
      "learning_rate": 0.00019961946980917456,
      "loss": 1.2419548034667969,
      "step": 10
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 1.7003947496414185,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.38210115432739256,
      "step": 15
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.8145407438278198,
      "learning_rate": 0.00019293475242268223,
      "loss": 0.25728816986083985,
      "step": 20
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 0.325599730014801,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.2286611557006836,
      "step": 25
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.35414496064186096,
      "learning_rate": 0.00017844156649195759,
      "loss": 0.21931443214416504,
      "step": 30
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 0.25363680720329285,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.20419161319732665,
      "step": 35
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.16995428502559662,
      "learning_rate": 0.0001573576436351046,
      "loss": 0.18711493015289307,
      "step": 40
    },
    {
      "epoch": 1.1842105263157894,
      "grad_norm": 0.5772308707237244,
      "learning_rate": 0.00014487991802004623,
      "loss": 0.16793118715286254,
      "step": 45
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 0.2523488700389862,
      "learning_rate": 0.00013145447561516138,
      "loss": 0.15176668167114257,
      "step": 50
    },
    {
      "epoch": 1.3157894736842106,
      "eval_loss": 0.15131250023841858,
      "eval_runtime": 0.4149,
      "eval_samples_per_second": 602.57,
      "eval_steps_per_second": 19.282,
      "step": 50
    },
    {
      "epoch": 1.4473684210526316,
      "grad_norm": 0.010118631646037102,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.15125420093536376,
      "step": 55
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 0.02765880525112152,
      "learning_rate": 0.00010290847187431113,
      "loss": 0.15109244585037232,
      "step": 60
    },
    {
      "epoch": 1.7105263157894737,
      "grad_norm": 0.005034108646214008,
      "learning_rate": 8.839070858747697e-05,
      "loss": 0.15083110332489014,
      "step": 65
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 0.00388790899887681,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.15069222450256348,
      "step": 70
    },
    {
      "epoch": 1.973684210526316,
      "grad_norm": 0.0032404710073024035,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.1506070613861084,
      "step": 75
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.0034807652700692415,
      "learning_rate": 4.7502341966544e-05,
      "loss": 0.15054476261138916,
      "step": 80
    },
    {
      "epoch": 2.236842105263158,
      "grad_norm": 0.0030651933047920465,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.1505044221878052,
      "step": 85
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 0.003038919297978282,
      "learning_rate": 2.529749287590042e-05,
      "loss": 0.1504807472229004,
      "step": 90
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.003026943188160658,
      "learning_rate": 1.6451218858706374e-05,
      "loss": 0.1504598617553711,
      "step": 95
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 0.002823486225679517,
      "learning_rate": 9.369221296335006e-06,
      "loss": 0.15044400691986085,
      "step": 100
    },
    {
      "epoch": 2.6315789473684212,
      "eval_loss": 0.15043434500694275,
      "eval_runtime": 0.4215,
      "eval_samples_per_second": 593.179,
      "eval_steps_per_second": 18.982,
      "step": 100
    },
    {
      "epoch": 2.763157894736842,
      "grad_norm": 0.0027727079577744007,
      "learning_rate": 4.20104876845111e-06,
      "loss": 0.15043517351150512,
      "step": 105
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 0.0027681535575538874,
      "learning_rate": 1.055836141905553e-06,
      "loss": 0.1504277229309082,
      "step": 110
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.15042713284492493,
      "eval_runtime": 0.3385,
      "eval_samples_per_second": 738.621,
      "eval_steps_per_second": 23.636,
      "step": 114
    },
    {
      "epoch": 3.0,
      "step": 114,
      "total_flos": 1.842079609965773e+16,
      "train_loss": 0.3649343314923738,
      "train_runtime": 63.8114,
      "train_samples_per_second": 223.314,
      "train_steps_per_second": 1.787
    }
  ],
  "logging_steps": 5,
  "max_steps": 114,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.842079609965773e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}