{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 210.80020141601562,
      "learning_rate": 4.997e-05,
      "loss": 4.6794,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 19.776996612548828,
      "learning_rate": 4.987e-05,
      "loss": 1.9613,
      "step": 20
    },
    {
      "epoch": 0.03,
      "grad_norm": 2.950834274291992,
      "learning_rate": 4.977e-05,
      "loss": 0.1608,
      "step": 30
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.22875149548053741,
      "learning_rate": 4.967e-05,
      "loss": 0.5829,
      "step": 40
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0006156641175039113,
      "learning_rate": 4.957e-05,
      "loss": 0.1294,
      "step": 50
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.17372851073741913,
      "learning_rate": 4.947e-05,
      "loss": 0.6598,
      "step": 60
    },
    {
      "epoch": 0.07,
      "grad_norm": 4.253387331232261e-08,
      "learning_rate": 4.937e-05,
      "loss": 0.002,
      "step": 70
    },
    {
      "epoch": 0.08,
      "grad_norm": 6.705884629809589e-07,
      "learning_rate": 4.927000000000001e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.09,
      "grad_norm": 2.6538114980212413e-05,
      "learning_rate": 4.9170000000000005e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.1,
      "grad_norm": 3.863420715788379e-06,
      "learning_rate": 4.907e-05,
      "loss": 0.0059,
      "step": 100
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.0,
      "learning_rate": 4.897000000000001e-05,
      "loss": 0.0159,
      "step": 110
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.0,
      "learning_rate": 4.8870000000000005e-05,
      "loss": 0.0049,
      "step": 120
    },
    {
      "epoch": 0.13,
      "grad_norm": 2.1159605694265338e-06,
      "learning_rate": 4.877e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.03220589831471443,
      "learning_rate": 4.867000000000001e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.0,
      "learning_rate": 4.8570000000000004e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.16,
      "grad_norm": 8.797255368619972e-09,
      "learning_rate": 4.847e-05,
      "loss": 0.0011,
      "step": 160
    },
    {
      "epoch": 0.17,
      "grad_norm": 2.5324195007669914e-07,
      "learning_rate": 4.8370000000000006e-05,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.0,
      "learning_rate": 4.8270000000000004e-05,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.2117304777348181e-06,
      "learning_rate": 4.817e-05,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.0,
      "learning_rate": 4.8070000000000006e-05,
      "loss": 0.0,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.91976437710848e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}