{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.6,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.4186272621154785,
      "learning_rate": 1e-05,
      "loss": 18.593,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4134901762008667,
      "learning_rate": 1e-05,
      "loss": 18.5907,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4151455163955688,
      "learning_rate": 1e-05,
      "loss": 18.5914,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4076709747314453,
      "learning_rate": 1e-05,
      "loss": 18.4726,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4128385782241821,
      "learning_rate": 1e-05,
      "loss": 18.4861,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4012584686279297,
      "learning_rate": 1e-05,
      "loss": 18.5662,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4086817502975464,
      "learning_rate": 1e-05,
      "loss": 18.4797,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.4248992204666138,
      "learning_rate": 1e-05,
      "loss": 18.3804,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4157073497772217,
      "learning_rate": 1e-05,
      "loss": 18.5378,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4206557273864746,
      "learning_rate": 1e-05,
      "loss": 18.5848,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.3981428146362305,
      "learning_rate": 1e-05,
      "loss": 18.504,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.413487434387207,
      "learning_rate": 1e-05,
      "loss": 18.4089,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.3889946937561035,
      "learning_rate": 1e-05,
      "loss": 18.5393,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.3847557306289673,
      "learning_rate": 1e-05,
      "loss": 18.5265,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.3759769201278687,
      "learning_rate": 1e-05,
      "loss": 18.472,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.3832721710205078,
      "learning_rate": 1e-05,
      "loss": 18.5209,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.3482437133789062,
      "learning_rate": 1e-05,
      "loss": 18.6949,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.2689204216003418,
      "learning_rate": 1e-05,
      "loss": 18.7909,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.3280190229415894,
      "learning_rate": 1e-05,
      "loss": 19.0463,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.35628342628479,
      "learning_rate": 1e-05,
      "loss": 18.6226,
      "step": 1000
    },
    {
      "epoch": 8.4,
      "grad_norm": 1.3431962728500366,
      "learning_rate": 1e-05,
      "loss": 18.9441,
      "step": 1050
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.0514743328094482,
      "learning_rate": 1e-05,
      "loss": 18.7675,
      "step": 1100
    },
    {
      "epoch": 9.2,
      "grad_norm": 1.1831846237182617,
      "learning_rate": 1e-05,
      "loss": 19.1445,
      "step": 1150
    },
    {
      "epoch": 9.6,
      "grad_norm": 0.977008044719696,
      "learning_rate": 1e-05,
      "loss": 19.4159,
      "step": 1200
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}