{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 222,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 10.886295318603516,
      "learning_rate": 2.9985590229902075e-05,
      "loss": 1.0015,
      "step": 10
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 5.358567714691162,
      "learning_rate": 2.9730185992421254e-05,
      "loss": 1.018,
      "step": 20
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 4.956131458282471,
      "learning_rate": 2.9160833414327637e-05,
      "loss": 0.9968,
      "step": 30
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 4.287660598754883,
      "learning_rate": 2.828966725734167e-05,
      "loss": 0.9578,
      "step": 40
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 4.38076639175415,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.9616,
      "step": 50
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 3.4410629272460938,
      "learning_rate": 2.5722200684005718e-05,
      "loss": 1.0157,
      "step": 60
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 3.597104549407959,
      "learning_rate": 2.408062136015872e-05,
      "loss": 0.8358,
      "step": 70
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 3.7283811569213867,
      "learning_rate": 2.224550435734272e-05,
      "loss": 0.7411,
      "step": 80
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 3.7816851139068604,
      "learning_rate": 2.025596200843394e-05,
      "loss": 0.601,
      "step": 90
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 2.7771706581115723,
      "learning_rate": 1.8154397954454996e-05,
      "loss": 0.5566,
      "step": 100
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 4.035545349121094,
      "learning_rate": 1.5985603384585545e-05,
      "loss": 0.5708,
      "step": 110
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 3.930940628051758,
      "learning_rate": 1.3795802389729185e-05,
      "loss": 0.542,
      "step": 120
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 3.956760883331299,
      "learning_rate": 1.1631666776267804e-05,
      "loss": 0.6192,
      "step": 130
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 4.3746867179870605,
      "learning_rate": 9.5393213375378e-06,
      "loss": 0.5264,
      "step": 140
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 2.729212999343872,
      "learning_rate": 7.563360783939724e-06,
      "loss": 0.5518,
      "step": 150
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 2.8583178520202637,
      "learning_rate": 5.7458992841091544e-06,
      "loss": 0.3178,
      "step": 160
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 3.17622709274292,
      "learning_rate": 4.125672874528797e-06,
      "loss": 0.321,
      "step": 170
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 3.736758232116699,
      "learning_rate": 2.7372138681624246e-06,
      "loss": 0.2907,
      "step": 180
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 4.735370635986328,
      "learning_rate": 1.6101148581573276e-06,
      "loss": 0.3099,
      "step": 190
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 3.179217576980591,
      "learning_rate": 7.683980030985655e-07,
      "loss": 0.2835,
      "step": 200
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 3.2560248374938965,
      "learning_rate": 2.300030364048139e-07,
      "loss": 0.3437,
      "step": 210
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 2.855491876602173,
      "learning_rate": 6.404912056610091e-09,
      "loss": 0.3025,
      "step": 220
    },
    {
      "epoch": 3.0,
      "step": 222,
      "total_flos": 7668873302114304.0,
      "train_loss": 0.6191561619440714,
      "train_runtime": 439.5999,
      "train_samples_per_second": 8.025,
      "train_steps_per_second": 0.505
    }
  ],
  "logging_steps": 10,
  "max_steps": 222,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7668873302114304.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}