{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 48,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06477732793522267,
      "grad_norm": 2.660320281982422,
      "learning_rate": 3.333333333333333e-07,
      "loss": 0.7866842746734619,
      "step": 1,
      "token_acc": 0.7847913330765957
    },
    {
      "epoch": 0.32388663967611336,
      "grad_norm": 2.5969700813293457,
      "learning_rate": 9.95134034370785e-07,
      "loss": 0.7780985832214355,
      "step": 5,
      "token_acc": 0.7864214660577772
    },
    {
      "epoch": 0.6477732793522267,
      "grad_norm": 2.2304747104644775,
      "learning_rate": 9.414737964294634e-07,
      "loss": 0.7687731742858886,
      "step": 10,
      "token_acc": 0.7876792671984955
    },
    {
      "epoch": 0.97165991902834,
      "grad_norm": 1.7630908489227295,
      "learning_rate": 8.34565303179429e-07,
      "loss": 0.7465362548828125,
      "step": 15,
      "token_acc": 0.790032398606277
    },
    {
      "epoch": 1.2591093117408907,
      "grad_norm": 1.3999474048614502,
      "learning_rate": 6.87303296707956e-07,
      "loss": 0.7201728820800781,
      "step": 20,
      "token_acc": 0.7961506670887986
    },
    {
      "epoch": 1.582995951417004,
      "grad_norm": 1.2843416929244995,
      "learning_rate": 5.174497483512505e-07,
      "loss": 0.6808279037475586,
      "step": 25,
      "token_acc": 0.8018116122297437
    },
    {
      "epoch": 1.9068825910931175,
      "grad_norm": 1.1600399017333984,
      "learning_rate": 3.454915028125263e-07,
      "loss": 0.680144214630127,
      "step": 30,
      "token_acc": 0.8012318325271961
    },
    {
      "epoch": 2.194331983805668,
      "grad_norm": 0.9812030792236328,
      "learning_rate": 1.9216926233717084e-07,
      "loss": 0.6616860389709472,
      "step": 35,
      "token_acc": 0.8084696413530629
    },
    {
      "epoch": 2.5182186234817814,
      "grad_norm": 0.9344884157180786,
      "learning_rate": 7.597595192178702e-08,
      "loss": 0.6628401756286622,
      "step": 40,
      "token_acc": 0.8051930365682306
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 0.9489951729774475,
      "learning_rate": 1.0926199633097154e-08,
      "loss": 0.6646383762359619,
      "step": 45,
      "token_acc": 0.8049387170931265
    }
  ],
  "logging_steps": 5,
  "max_steps": 48,
  "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": 5.667590557631775e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}