{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 776.0098266601562,
      "learning_rate": 6.666666666666665e-08,
      "loss": 6.788,
      "step": 1
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 776.1124877929688,
      "learning_rate": 1.333333333333333e-07,
      "loss": 6.7875,
      "step": 2
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 776.81640625,
      "learning_rate": 2e-07,
      "loss": 6.7982,
      "step": 3
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 771.4744262695312,
      "learning_rate": 1.9906859460363306e-07,
      "loss": 6.8066,
      "step": 4
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 775.675048828125,
      "learning_rate": 1.9629172873477992e-07,
      "loss": 6.8131,
      "step": 5
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 774.6471557617188,
      "learning_rate": 1.917211301505453e-07,
      "loss": 6.772,
      "step": 6
    },
    {
      "epoch": 0.2692307692307692,
      "grad_norm": 776.7907104492188,
      "learning_rate": 1.8544194045464885e-07,
      "loss": 6.788,
      "step": 7
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 767.07275390625,
      "learning_rate": 1.7757112907044197e-07,
      "loss": 6.7249,
      "step": 8
    },
    {
      "epoch": 0.34615384615384615,
      "grad_norm": 766.0026245117188,
      "learning_rate": 1.6825531432186542e-07,
      "loss": 6.6868,
      "step": 9
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 765.2178955078125,
      "learning_rate": 1.5766803221148673e-07,
      "loss": 6.6827,
      "step": 10
    },
    {
      "epoch": 0.4230769230769231,
      "grad_norm": 766.74755859375,
      "learning_rate": 1.460065037731152e-07,
      "loss": 6.6962,
      "step": 11
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 766.689453125,
      "learning_rate": 1.334879612170986e-07,
      "loss": 6.6907,
      "step": 12
    },
    {
      "epoch": 0.5,
      "grad_norm": 765.7440185546875,
      "learning_rate": 1.203456013052634e-07,
      "loss": 6.6838,
      "step": 13
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 747.0338134765625,
      "learning_rate": 1.068242413364671e-07,
      "loss": 6.3877,
      "step": 14
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 737.4042358398438,
      "learning_rate": 9.317575866353292e-08,
      "loss": 6.5178,
      "step": 15
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 746.3089599609375,
      "learning_rate": 7.965439869473663e-08,
      "loss": 6.3961,
      "step": 16
    },
    {
      "epoch": 0.6538461538461539,
      "grad_norm": 738.47802734375,
      "learning_rate": 6.651203878290138e-08,
      "loss": 6.5289,
      "step": 17
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 748.2200317382812,
      "learning_rate": 5.399349622688478e-08,
      "loss": 6.4789,
      "step": 18
    },
    {
      "epoch": 0.7307692307692307,
      "grad_norm": 743.057861328125,
      "learning_rate": 4.233196778851329e-08,
      "loss": 6.3982,
      "step": 19
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 735.56494140625,
      "learning_rate": 3.174468567813461e-08,
      "loss": 6.4218,
      "step": 20
    },
    {
      "epoch": 0.8076923076923077,
      "grad_norm": 749.7279663085938,
      "learning_rate": 2.2428870929558008e-08,
      "loss": 6.4902,
      "step": 21
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 740.5699462890625,
      "learning_rate": 1.4558059545351143e-08,
      "loss": 6.4878,
      "step": 22
    },
    {
      "epoch": 0.8846153846153846,
      "grad_norm": 743.7008056640625,
      "learning_rate": 8.278869849454717e-09,
      "loss": 6.4387,
      "step": 23
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 748.1434936523438,
      "learning_rate": 3.7082712652200865e-09,
      "loss": 6.466,
      "step": 24
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 744.7090454101562,
      "learning_rate": 9.314053963669243e-10,
      "loss": 6.4702,
      "step": 25
    },
    {
      "epoch": 1.0,
      "grad_norm": 735.6946411132812,
      "learning_rate": 0.0,
      "loss": 6.3073,
      "step": 26
    },
    {
      "epoch": 1.0,
      "step": 26,
      "total_flos": 6.212373250362573e+16,
      "train_loss": 6.596468045161321,
      "train_runtime": 584.4608,
      "train_samples_per_second": 2.842,
      "train_steps_per_second": 0.044
    }
  ],
  "logging_steps": 1,
  "max_steps": 26,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.212373250362573e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}