{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.985806451612904,
  "eval_steps": 500,
  "global_step": 965,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 60.0,
      "learning_rate": 1.5e-05,
      "loss": 6.9241,
      "step": 50
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 28.375,
      "learning_rate": 3e-05,
      "loss": 6.2276,
      "step": 100
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 20.125,
      "learning_rate": 2.8265895953757228e-05,
      "loss": 4.8431,
      "step": 150
    },
    {
      "epoch": 1.033548387096774,
      "grad_norm": 18.0,
      "learning_rate": 2.653179190751445e-05,
      "loss": 4.1853,
      "step": 200
    },
    {
      "epoch": 1.2916129032258064,
      "grad_norm": 15.4375,
      "learning_rate": 2.4797687861271675e-05,
      "loss": 3.9644,
      "step": 250
    },
    {
      "epoch": 1.5496774193548388,
      "grad_norm": 24.0,
      "learning_rate": 2.3063583815028902e-05,
      "loss": 3.838,
      "step": 300
    },
    {
      "epoch": 1.8077419354838709,
      "grad_norm": 18.125,
      "learning_rate": 2.132947976878613e-05,
      "loss": 3.7908,
      "step": 350
    },
    {
      "epoch": 2.067096774193548,
      "grad_norm": 13.8125,
      "learning_rate": 1.9595375722543353e-05,
      "loss": 3.7595,
      "step": 400
    },
    {
      "epoch": 2.3251612903225807,
      "grad_norm": 19.625,
      "learning_rate": 1.7861271676300577e-05,
      "loss": 3.7634,
      "step": 450
    },
    {
      "epoch": 2.5832258064516127,
      "grad_norm": 12.4375,
      "learning_rate": 1.6127167630057804e-05,
      "loss": 3.7074,
      "step": 500
    },
    {
      "epoch": 2.5832258064516127,
      "eval_loss": 3.7095940113067627,
      "eval_perplexity": 40.784299067771805,
      "eval_runtime": 216.8944,
      "eval_samples_per_second": 1.591,
      "eval_steps_per_second": 0.798,
      "step": 500
    },
    {
      "epoch": 2.841290322580645,
      "grad_norm": 14.875,
      "learning_rate": 1.439306358381503e-05,
      "loss": 3.6857,
      "step": 550
    },
    {
      "epoch": 3.1006451612903225,
      "grad_norm": 14.4375,
      "learning_rate": 1.2658959537572255e-05,
      "loss": 3.6973,
      "step": 600
    },
    {
      "epoch": 3.358709677419355,
      "grad_norm": 23.25,
      "learning_rate": 1.092485549132948e-05,
      "loss": 3.7022,
      "step": 650
    },
    {
      "epoch": 3.616774193548387,
      "grad_norm": 14.5,
      "learning_rate": 9.190751445086706e-06,
      "loss": 3.6774,
      "step": 700
    },
    {
      "epoch": 3.8748387096774195,
      "grad_norm": 14.75,
      "learning_rate": 7.45664739884393e-06,
      "loss": 3.6879,
      "step": 750
    },
    {
      "epoch": 4.134193548387096,
      "grad_norm": 15.625,
      "learning_rate": 5.722543352601156e-06,
      "loss": 3.6654,
      "step": 800
    },
    {
      "epoch": 4.392258064516129,
      "grad_norm": 13.8125,
      "learning_rate": 3.988439306358381e-06,
      "loss": 3.6742,
      "step": 850
    },
    {
      "epoch": 4.650322580645161,
      "grad_norm": 16.75,
      "learning_rate": 2.254335260115607e-06,
      "loss": 3.6861,
      "step": 900
    },
    {
      "epoch": 4.908387096774193,
      "grad_norm": 17.5,
      "learning_rate": 5.202312138728324e-07,
      "loss": 3.6569,
      "step": 950
    }
  ],
  "logging_steps": 50,
  "max_steps": 965,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.867827744702464e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}