{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 224,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.848931074142456,
      "learning_rate": 9.53153893518325e-05,
      "loss": 6.0403,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.975097894668579,
      "learning_rate": 6.294095225512603e-05,
      "loss": 5.4718,
      "step": 20
    },
    {
      "epoch": 1.5128205128205128,
      "grad_norm": 2.3797974586486816,
      "learning_rate": 2.132117818244771e-05,
      "loss": 4.8283,
      "step": 30
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.789046287536621,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 4.6286,
      "step": 40
    },
    {
      "epoch": 1.1355932203389831,
      "grad_norm": 1.8822929859161377,
      "learning_rate": 9.596765194911181e-05,
      "loss": 5.0217,
      "step": 50
    },
    {
      "epoch": 1.3615819209039548,
      "grad_norm": 1.4929884672164917,
      "learning_rate": 9.236573524788887e-05,
      "loss": 3.9458,
      "step": 60
    },
    {
      "epoch": 1.5875706214689265,
      "grad_norm": 0.9337669014930725,
      "learning_rate": 8.774114695766286e-05,
      "loss": 3.6254,
      "step": 70
    },
    {
      "epoch": 1.8135593220338984,
      "grad_norm": 0.8921490907669067,
      "learning_rate": 8.22055205725199e-05,
      "loss": 3.4809,
      "step": 80
    },
    {
      "epoch": 2.022598870056497,
      "grad_norm": 0.9192579984664917,
      "learning_rate": 7.589248124491627e-05,
      "loss": 3.4035,
      "step": 90
    },
    {
      "epoch": 2.248587570621469,
      "grad_norm": 1.1187790632247925,
      "learning_rate": 6.895442019201897e-05,
      "loss": 3.3861,
      "step": 100
    },
    {
      "epoch": 2.4745762711864407,
      "grad_norm": 1.2873858213424683,
      "learning_rate": 6.15588161057485e-05,
      "loss": 3.3066,
      "step": 110
    },
    {
      "epoch": 2.7005649717514126,
      "grad_norm": 1.34447181224823,
      "learning_rate": 5.3884192364450325e-05,
      "loss": 3.2884,
      "step": 120
    },
    {
      "epoch": 2.926553672316384,
      "grad_norm": 0.7228454947471619,
      "learning_rate": 4.611580763554969e-05,
      "loss": 3.2397,
      "step": 130
    },
    {
      "epoch": 3.135593220338983,
      "grad_norm": 1.1347743272781372,
      "learning_rate": 3.844118389425153e-05,
      "loss": 3.1814,
      "step": 140
    },
    {
      "epoch": 3.361581920903955,
      "grad_norm": 1.3022897243499756,
      "learning_rate": 3.104557980798104e-05,
      "loss": 3.1947,
      "step": 150
    },
    {
      "epoch": 3.5875706214689265,
      "grad_norm": 1.1423296928405762,
      "learning_rate": 2.410751875508373e-05,
      "loss": 3.2494,
      "step": 160
    },
    {
      "epoch": 3.8135593220338984,
      "grad_norm": 0.9820030927658081,
      "learning_rate": 1.7794479427480117e-05,
      "loss": 3.199,
      "step": 170
    },
    {
      "epoch": 4.022598870056497,
      "grad_norm": 1.5156248807907104,
      "learning_rate": 1.225885304233716e-05,
      "loss": 3.1656,
      "step": 180
    },
    {
      "epoch": 4.248587570621469,
      "grad_norm": 0.8429480195045471,
      "learning_rate": 7.63426475211113e-06,
      "loss": 3.2354,
      "step": 190
    },
    {
      "epoch": 4.47457627118644,
      "grad_norm": 1.0040243864059448,
      "learning_rate": 4.032348050888179e-06,
      "loss": 3.216,
      "step": 200
    },
    {
      "epoch": 4.700564971751413,
      "grad_norm": 1.4402868747711182,
      "learning_rate": 1.5400500400166939e-06,
      "loss": 3.1459,
      "step": 210
    },
    {
      "epoch": 4.926553672316384,
      "grad_norm": 1.0170223712921143,
      "learning_rate": 2.1753260154906973e-07,
      "loss": 3.2043,
      "step": 220
    },
    {
      "epoch": 5.0,
      "step": 224,
      "total_flos": 2.2662781232726016e+17,
      "train_loss": 2.800803001437868,
      "train_runtime": 303.5624,
      "train_samples_per_second": 23.29,
      "train_steps_per_second": 0.741
    }
  ],
  "logging_steps": 10,
  "max_steps": 225,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2662781232726016e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}