{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 255,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.03323917090892792,
      "learning_rate": 0.0001999919114627769,
      "loss": 2.763583183288574,
      "step": 10
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.05506502836942673,
      "learning_rate": 0.0001990228692687429,
      "loss": 2.593435287475586,
      "step": 20
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 0.05839679390192032,
      "learning_rate": 0.00019645406355025565,
      "loss": 2.345814323425293,
      "step": 30
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.054268915206193924,
      "learning_rate": 0.00019232699463668542,
      "loss": 2.245083808898926,
      "step": 40
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.04734891280531883,
      "learning_rate": 0.0001867083373715264,
      "loss": 2.1789533615112306,
      "step": 50
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.04950524866580963,
      "learning_rate": 0.00017968886394725874,
      "loss": 2.146891975402832,
      "step": 60
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.048059429973363876,
      "learning_rate": 0.00017138197743559654,
      "loss": 2.1342124938964844,
      "step": 70
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.048672087490558624,
      "learning_rate": 0.00016192187970466644,
      "loss": 2.08856086730957,
      "step": 80
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.053143732249736786,
      "learning_rate": 0.00015146140332132358,
      "loss": 2.0824731826782226,
      "step": 90
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.05677838623523712,
      "learning_rate": 0.00014016954246529696,
      "loss": 2.0192502975463866,
      "step": 100
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.054012443870306015,
      "learning_rate": 0.00012822872274446958,
      "loss": 2.039341926574707,
      "step": 110
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.06396123766899109,
      "learning_rate": 0.00011583185401878101,
      "loss": 2.0363845825195312,
      "step": 120
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.05511175096035004,
      "learning_rate": 0.00010317921384584244,
      "loss": 2.039676856994629,
      "step": 130
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.052731700241565704,
      "learning_rate": 9.047521189774455e-05,
      "loss": 2.0343761444091797,
      "step": 140
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.05958898738026619,
      "learning_rate": 7.792508762150833e-05,
      "loss": 2.042786979675293,
      "step": 150
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.05990149825811386,
      "learning_rate": 6.57315944941107e-05,
      "loss": 2.0720109939575195,
      "step": 160
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.05766311287879944,
      "learning_rate": 5.409172443958843e-05,
      "loss": 2.0328493118286133,
      "step": 170
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.059346605092287064,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 2.0109920501708984,
      "step": 180
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.06073939800262451,
      "learning_rate": 3.321306296333673e-05,
      "loss": 1.9789583206176757,
      "step": 190
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.05661051720380783,
      "learning_rate": 2.431157666431052e-05,
      "loss": 2.008417320251465,
      "step": 200
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.06170394644141197,
      "learning_rate": 1.663287435215498e-05,
      "loss": 2.0092374801635744,
      "step": 210
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.060639169067144394,
      "learning_rate": 1.0301009267953143e-05,
      "loss": 2.00238094329834,
      "step": 220
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.06061309948563576,
      "learning_rate": 5.418275829936537e-06,
      "loss": 2.024155616760254,
      "step": 230
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.06357177346944809,
      "learning_rate": 2.063557016466111e-06,
      "loss": 1.9843828201293945,
      "step": 240
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.06014658138155937,
      "learning_rate": 2.9104997242590527e-07,
      "loss": 1.9744945526123048,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 255,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.324634988544e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}