{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10131712259371833,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006754474839581223,
      "eval_loss": 10.84744930267334,
      "eval_runtime": 2.4743,
      "eval_samples_per_second": 252.196,
      "eval_steps_per_second": 126.098,
      "step": 1
    },
    {
      "epoch": 0.006754474839581222,
      "grad_norm": 0.431049108505249,
      "learning_rate": 0.0002,
      "loss": 10.8368,
      "step": 10
    },
    {
      "epoch": 0.013508949679162444,
      "grad_norm": 0.5706029534339905,
      "learning_rate": 0.0002,
      "loss": 10.7993,
      "step": 20
    },
    {
      "epoch": 0.020263424518743668,
      "grad_norm": 0.6140374541282654,
      "learning_rate": 0.0002,
      "loss": 10.7465,
      "step": 30
    },
    {
      "epoch": 0.02701789935832489,
      "grad_norm": 0.48200711607933044,
      "learning_rate": 0.0002,
      "loss": 10.685,
      "step": 40
    },
    {
      "epoch": 0.033772374197906116,
      "grad_norm": 0.31821873784065247,
      "learning_rate": 0.0002,
      "loss": 10.6493,
      "step": 50
    },
    {
      "epoch": 0.033772374197906116,
      "eval_loss": 10.633384704589844,
      "eval_runtime": 2.0649,
      "eval_samples_per_second": 302.192,
      "eval_steps_per_second": 151.096,
      "step": 50
    },
    {
      "epoch": 0.040526849037487336,
      "grad_norm": 0.19227109849452972,
      "learning_rate": 0.0002,
      "loss": 10.6272,
      "step": 60
    },
    {
      "epoch": 0.04728132387706856,
      "grad_norm": 0.16618256270885468,
      "learning_rate": 0.0002,
      "loss": 10.617,
      "step": 70
    },
    {
      "epoch": 0.05403579871664978,
      "grad_norm": 0.10431524366140366,
      "learning_rate": 0.0002,
      "loss": 10.617,
      "step": 80
    },
    {
      "epoch": 0.060790273556231005,
      "grad_norm": 0.1364213526248932,
      "learning_rate": 0.0002,
      "loss": 10.6092,
      "step": 90
    },
    {
      "epoch": 0.06754474839581223,
      "grad_norm": 0.1899089217185974,
      "learning_rate": 0.0002,
      "loss": 10.6079,
      "step": 100
    },
    {
      "epoch": 0.06754474839581223,
      "eval_loss": 10.599853515625,
      "eval_runtime": 2.1189,
      "eval_samples_per_second": 294.492,
      "eval_steps_per_second": 147.246,
      "step": 100
    },
    {
      "epoch": 0.07429922323539345,
      "grad_norm": 0.2296675145626068,
      "learning_rate": 0.0002,
      "loss": 10.5936,
      "step": 110
    },
    {
      "epoch": 0.08105369807497467,
      "grad_norm": 0.1406475007534027,
      "learning_rate": 0.0002,
      "loss": 10.5804,
      "step": 120
    },
    {
      "epoch": 0.0878081729145559,
      "grad_norm": 0.14728939533233643,
      "learning_rate": 0.0002,
      "loss": 10.5703,
      "step": 130
    },
    {
      "epoch": 0.09456264775413711,
      "grad_norm": 0.15510405600070953,
      "learning_rate": 0.0002,
      "loss": 10.5586,
      "step": 140
    },
    {
      "epoch": 0.10131712259371833,
      "grad_norm": 0.14784684777259827,
      "learning_rate": 0.0002,
      "loss": 10.5492,
      "step": 150
    },
    {
      "epoch": 0.10131712259371833,
      "eval_loss": 10.54542064666748,
      "eval_runtime": 2.0847,
      "eval_samples_per_second": 299.317,
      "eval_steps_per_second": 149.658,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 24608872857600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}