{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 3175,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15748031496062992,
      "grad_norm": 5.84375,
      "learning_rate": 0.00031446540880503143,
      "loss": 1.6016,
      "step": 100
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 2.90625,
      "learning_rate": 0.0004997720451762572,
      "loss": 2.0478,
      "step": 200
    },
    {
      "epoch": 0.47244094488188976,
      "grad_norm": 3.0,
      "learning_rate": 0.0004973084374349976,
      "loss": 2.0072,
      "step": 300
    },
    {
      "epoch": 0.6299212598425197,
      "grad_norm": 2.578125,
      "learning_rate": 0.0004921639131931859,
      "loss": 1.8507,
      "step": 400
    },
    {
      "epoch": 0.7874015748031497,
      "grad_norm": 1.6953125,
      "learning_rate": 0.00048439424102900066,
      "loss": 1.7019,
      "step": 500
    },
    {
      "epoch": 0.9448818897637795,
      "grad_norm": 2.6875,
      "learning_rate": 0.00047408364711169396,
      "loss": 1.5988,
      "step": 600
    },
    {
      "epoch": 1.1023622047244095,
      "grad_norm": 1.8203125,
      "learning_rate": 0.00046134390215823,
      "loss": 1.3103,
      "step": 700
    },
    {
      "epoch": 1.2598425196850394,
      "grad_norm": 1.671875,
      "learning_rate": 0.00044631310979666443,
      "loss": 1.237,
      "step": 800
    },
    {
      "epoch": 1.4173228346456692,
      "grad_norm": 1.7421875,
      "learning_rate": 0.0004291542094708612,
      "loss": 1.2112,
      "step": 900
    },
    {
      "epoch": 1.574803149606299,
      "grad_norm": 2.28125,
      "learning_rate": 0.000410053210115622,
      "loss": 1.1948,
      "step": 1000
    },
    {
      "epoch": 1.7322834645669292,
      "grad_norm": 1.5859375,
      "learning_rate": 0.00038921717374985584,
      "loss": 1.1666,
      "step": 1100
    },
    {
      "epoch": 1.889763779527559,
      "grad_norm": 1.59375,
      "learning_rate": 0.0003668719708463959,
      "loss": 1.1001,
      "step": 1200
    },
    {
      "epoch": 2.047244094488189,
      "grad_norm": 1.6171875,
      "learning_rate": 0.00034325983181110047,
      "loss": 0.9377,
      "step": 1300
    },
    {
      "epoch": 2.204724409448819,
      "grad_norm": 1.640625,
      "learning_rate": 0.00031863672111412524,
      "loss": 0.6561,
      "step": 1400
    },
    {
      "epoch": 2.362204724409449,
      "grad_norm": 1.9296875,
      "learning_rate": 0.00029326956253877123,
      "loss": 0.6872,
      "step": 1500
    },
    {
      "epoch": 2.5196850393700787,
      "grad_norm": 1.5859375,
      "learning_rate": 0.00026743334562725617,
      "loss": 0.6448,
      "step": 1600
    },
    {
      "epoch": 2.677165354330709,
      "grad_norm": 1.6484375,
      "learning_rate": 0.00024140814469062377,
      "loss": 0.643,
      "step": 1700
    },
    {
      "epoch": 2.8346456692913384,
      "grad_norm": 1.28125,
      "learning_rate": 0.0002154760826978469,
      "loss": 0.6216,
      "step": 1800
    },
    {
      "epoch": 2.9921259842519685,
      "grad_norm": 1.625,
      "learning_rate": 0.00018991827295670777,
      "loss": 0.5788,
      "step": 1900
    },
    {
      "epoch": 3.1496062992125986,
      "grad_norm": 1.2890625,
      "learning_rate": 0.00016501177173978493,
      "loss": 0.2589,
      "step": 2000
    },
    {
      "epoch": 3.3070866141732282,
      "grad_norm": 1.7734375,
      "learning_rate": 0.00014102657489022886,
      "loss": 0.2383,
      "step": 2100
    },
    {
      "epoch": 3.4645669291338583,
      "grad_norm": 1.1875,
      "learning_rate": 0.00011822269096524812,
      "loss": 0.2227,
      "step": 2200
    },
    {
      "epoch": 3.622047244094488,
      "grad_norm": 1.46875,
      "learning_rate": 9.684732264553247e-05,
      "loss": 0.2168,
      "step": 2300
    },
    {
      "epoch": 3.779527559055118,
      "grad_norm": 1.0390625,
      "learning_rate": 7.713218696519558e-05,
      "loss": 0.2162,
      "step": 2400
    },
    {
      "epoch": 3.937007874015748,
      "grad_norm": 1.609375,
      "learning_rate": 5.929100341195187e-05,
      "loss": 0.1944,
      "step": 2500
    },
    {
      "epoch": 4.094488188976378,
      "grad_norm": 0.45703125,
      "learning_rate": 4.351717712746703e-05,
      "loss": 0.123,
      "step": 2600
    },
    {
      "epoch": 4.251968503937007,
      "grad_norm": 0.4609375,
      "learning_rate": 2.9981702322862735e-05,
      "loss": 0.0768,
      "step": 2700
    },
    {
      "epoch": 4.409448818897638,
      "grad_norm": 0.59375,
      "learning_rate": 1.8831308637139e-05,
      "loss": 0.0761,
      "step": 2800
    },
    {
      "epoch": 4.566929133858268,
      "grad_norm": 0.53515625,
      "learning_rate": 1.0186870532686742e-05,
      "loss": 0.0786,
      "step": 2900
    },
    {
      "epoch": 4.724409448818898,
      "grad_norm": 0.640625,
      "learning_rate": 4.1420969706420505e-06,
      "loss": 0.0758,
      "step": 3000
    },
    {
      "epoch": 4.881889763779528,
      "grad_norm": 0.515625,
      "learning_rate": 7.625155704936715e-07,
      "loss": 0.0792,
      "step": 3100
    },
    {
      "epoch": 5.0,
      "step": 3175,
      "total_flos": 2.254602634660147e+16,
      "train_loss": 0.7783217168792965,
      "train_runtime": 2040.3082,
      "train_samples_per_second": 12.444,
      "train_steps_per_second": 1.556
    }
  ],
  "logging_steps": 100,
  "max_steps": 3175,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.254602634660147e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}