{
  "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": 1.4155313968658447,
      "learning_rate": 1e-05,
      "loss": 18.6146,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4067548513412476,
      "learning_rate": 1e-05,
      "loss": 19.1109,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4229923486709595,
      "learning_rate": 1e-05,
      "loss": 18.7667,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4003844261169434,
      "learning_rate": 1e-05,
      "loss": 18.9235,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4214838743209839,
      "learning_rate": 1e-05,
      "loss": 18.8078,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4247723817825317,
      "learning_rate": 1e-05,
      "loss": 18.6608,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4037907123565674,
      "learning_rate": 1e-05,
      "loss": 18.7764,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.4066390991210938,
      "learning_rate": 1e-05,
      "loss": 18.8033,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.406646490097046,
      "learning_rate": 1e-05,
      "loss": 18.5561,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4158658981323242,
      "learning_rate": 1e-05,
      "loss": 18.8981,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.420823335647583,
      "learning_rate": 1e-05,
      "loss": 18.6345,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.4009493589401245,
      "learning_rate": 1e-05,
      "loss": 18.74,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.4026215076446533,
      "learning_rate": 1e-05,
      "loss": 18.9037,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.4201240539550781,
      "learning_rate": 1e-05,
      "loss": 18.6937,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.413161277770996,
      "learning_rate": 1e-05,
      "loss": 18.9671,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.3994218111038208,
      "learning_rate": 1e-05,
      "loss": 19.1391,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.4058501720428467,
      "learning_rate": 1e-05,
      "loss": 18.9155,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.369057297706604,
      "learning_rate": 1e-05,
      "loss": 18.529,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.3677970170974731,
      "learning_rate": 1e-05,
      "loss": 18.8005,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.36356520652771,
      "learning_rate": 1e-05,
      "loss": 19.0127,
      "step": 1000
    },
    {
      "epoch": 8.4,
      "grad_norm": 1.3650695085525513,
      "learning_rate": 1e-05,
      "loss": 18.8836,
      "step": 1050
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.2938820123672485,
      "learning_rate": 1e-05,
      "loss": 18.8773,
      "step": 1100
    },
    {
      "epoch": 9.2,
      "grad_norm": 1.2566759586334229,
      "learning_rate": 1e-05,
      "loss": 18.9608,
      "step": 1150
    },
    {
      "epoch": 9.6,
      "grad_norm": 1.1568825244903564,
      "learning_rate": 1e-05,
      "loss": 19.0219,
      "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
}