{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 104,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009615384615384616,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 3.4921,
      "step": 1
    },
    {
      "epoch": 0.04807692307692308,
      "grad_norm": Infinity,
      "learning_rate": 7.272727272727273e-06,
      "loss": 3.4372,
      "step": 5
    },
    {
      "epoch": 0.09615384615384616,
      "grad_norm": 1.3386897115800666e+19,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 3.4356,
      "step": 10
    },
    {
      "epoch": 0.14423076923076922,
      "grad_norm": 49.75270462036133,
      "learning_rate": 1.994869323391895e-05,
      "loss": 3.1194,
      "step": 15
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 81.14952087402344,
      "learning_rate": 1.963705643889941e-05,
      "loss": 2.6138,
      "step": 20
    },
    {
      "epoch": 0.2403846153846154,
      "grad_norm": 11.374646186828613,
      "learning_rate": 1.9051145072503216e-05,
      "loss": 2.3041,
      "step": 25
    },
    {
      "epoch": 0.28846153846153844,
      "grad_norm": 7.008129119873047,
      "learning_rate": 1.8207634412072765e-05,
      "loss": 2.0668,
      "step": 30
    },
    {
      "epoch": 0.33653846153846156,
      "grad_norm": 16.298776626586914,
      "learning_rate": 1.7130531116312202e-05,
      "loss": 1.8889,
      "step": 35
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 5.356802940368652,
      "learning_rate": 1.5850489985953076e-05,
      "loss": 1.83,
      "step": 40
    },
    {
      "epoch": 0.4326923076923077,
      "grad_norm": 7.75869607925415,
      "learning_rate": 1.4403941515576344e-05,
      "loss": 1.7812,
      "step": 45
    },
    {
      "epoch": 0.4807692307692308,
      "grad_norm": 4.185631275177002,
      "learning_rate": 1.283205506682304e-05,
      "loss": 1.75,
      "step": 50
    },
    {
      "epoch": 0.5288461538461539,
      "grad_norm": 2.844418525695801,
      "learning_rate": 1.1179567171508463e-05,
      "loss": 1.6893,
      "step": 55
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 2.267258405685425,
      "learning_rate": 9.493508311612874e-06,
      "loss": 1.6535,
      "step": 60
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.7939544916152954,
      "learning_rate": 7.821864412511485e-06,
      "loss": 1.6214,
      "step": 65
    },
    {
      "epoch": 0.6730769230769231,
      "grad_norm": 1.9716706275939941,
      "learning_rate": 6.21221114389424e-06,
      "loss": 1.6081,
      "step": 70
    },
    {
      "epoch": 0.7211538461538461,
      "grad_norm": 1.7848585844039917,
      "learning_rate": 4.710359896730379e-06,
      "loss": 1.5761,
      "step": 75
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 1.6977120637893677,
      "learning_rate": 3.3590539723276083e-06,
      "loss": 1.5688,
      "step": 80
    },
    {
      "epoch": 0.8173076923076923,
      "grad_norm": 1.863008737564087,
      "learning_rate": 2.196752090479083e-06,
      "loss": 1.5659,
      "step": 85
    },
    {
      "epoch": 0.8653846153846154,
      "grad_norm": 1.4840096235275269,
      "learning_rate": 1.2565338385541792e-06,
      "loss": 1.5474,
      "step": 90
    },
    {
      "epoch": 0.9134615384615384,
      "grad_norm": 1.3736684322357178,
      "learning_rate": 5.651582129001987e-07,
      "loss": 1.5542,
      "step": 95
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 1.390762448310852,
      "learning_rate": 1.4230204685196202e-07,
      "loss": 1.5418,
      "step": 100
    },
    {
      "epoch": 0.9615384615384616,
      "eval_loss": 1.5660021305084229,
      "eval_runtime": 1.8376,
      "eval_samples_per_second": 405.967,
      "eval_steps_per_second": 3.265,
      "step": 100
    },
    {
      "epoch": 1.0,
      "step": 104,
      "total_flos": 3.836373525279539e+16,
      "train_loss": 1.9909558915174925,
      "train_runtime": 382.237,
      "train_samples_per_second": 34.549,
      "train_steps_per_second": 0.272
    }
  ],
  "logging_steps": 5,
  "max_steps": 104,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.836373525279539e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}