{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6169031462060457,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030845157310302282,
      "grad_norm": 2.8206074237823486,
      "learning_rate": 1.0277492291880782e-05,
      "loss": 1.8082,
      "step": 50
    },
    {
      "epoch": 0.061690314620604564,
      "grad_norm": 3.4183013439178467,
      "learning_rate": 2.0554984583761563e-05,
      "loss": 0.6538,
      "step": 100
    },
    {
      "epoch": 0.09253547193090685,
      "grad_norm": 2.170591354370117,
      "learning_rate": 3.083247687564235e-05,
      "loss": 0.4563,
      "step": 150
    },
    {
      "epoch": 0.12338062924120913,
      "grad_norm": 1.4687080383300781,
      "learning_rate": 4.110996916752313e-05,
      "loss": 0.4263,
      "step": 200
    },
    {
      "epoch": 0.15422578655151142,
      "grad_norm": 1.836676836013794,
      "learning_rate": 5.1387461459403907e-05,
      "loss": 0.3994,
      "step": 250
    },
    {
      "epoch": 0.1850709438618137,
      "grad_norm": 1.2718663215637207,
      "learning_rate": 6.16649537512847e-05,
      "loss": 0.3665,
      "step": 300
    },
    {
      "epoch": 0.215916101172116,
      "grad_norm": 1.6945191621780396,
      "learning_rate": 7.194244604316547e-05,
      "loss": 0.3577,
      "step": 350
    },
    {
      "epoch": 0.24676125848241826,
      "grad_norm": 1.2829898595809937,
      "learning_rate": 8.221993833504625e-05,
      "loss": 0.347,
      "step": 400
    },
    {
      "epoch": 0.27760641579272055,
      "grad_norm": 1.01521635055542,
      "learning_rate": 9.249743062692704e-05,
      "loss": 0.3288,
      "step": 450
    },
    {
      "epoch": 0.30845157310302285,
      "grad_norm": 1.522111415863037,
      "learning_rate": 0.00010277492291880781,
      "loss": 0.3267,
      "step": 500
    },
    {
      "epoch": 0.3392967304133251,
      "grad_norm": 0.9678927659988403,
      "learning_rate": 0.00011305241521068859,
      "loss": 0.3198,
      "step": 550
    },
    {
      "epoch": 0.3701418877236274,
      "grad_norm": 1.2144405841827393,
      "learning_rate": 0.0001233299075025694,
      "loss": 0.3099,
      "step": 600
    },
    {
      "epoch": 0.4009870450339297,
      "grad_norm": 1.3122639656066895,
      "learning_rate": 0.00013360739979445017,
      "loss": 0.2929,
      "step": 650
    },
    {
      "epoch": 0.431832202344232,
      "grad_norm": 1.0934101343154907,
      "learning_rate": 0.00014388489208633093,
      "loss": 0.3003,
      "step": 700
    },
    {
      "epoch": 0.4626773596545342,
      "grad_norm": 0.7938969731330872,
      "learning_rate": 0.00015416238437821172,
      "loss": 0.2956,
      "step": 750
    },
    {
      "epoch": 0.4935225169648365,
      "grad_norm": 0.6571168303489685,
      "learning_rate": 0.0001644398766700925,
      "loss": 0.2736,
      "step": 800
    },
    {
      "epoch": 0.5243676742751388,
      "grad_norm": 1.0073938369750977,
      "learning_rate": 0.0001747173689619733,
      "loss": 0.2892,
      "step": 850
    },
    {
      "epoch": 0.5552128315854411,
      "grad_norm": 0.9874083399772644,
      "learning_rate": 0.00018499486125385408,
      "loss": 0.2723,
      "step": 900
    },
    {
      "epoch": 0.5860579888957433,
      "grad_norm": 1.1770968437194824,
      "learning_rate": 0.00019527235354573487,
      "loss": 0.2855,
      "step": 950
    },
    {
      "epoch": 0.6169031462060457,
      "grad_norm": 1.00326669216156,
      "learning_rate": 0.00019997622717095418,
      "loss": 0.2587,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 4863,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7124677004623872.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}