{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07593735168485999,
  "eval_steps": 5,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018984337921214998,
      "eval_loss": NaN,
      "eval_runtime": 54.2542,
      "eval_samples_per_second": 4.092,
      "eval_steps_per_second": 2.046,
      "step": 1
    },
    {
      "epoch": 0.005695301376364499,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.009492168960607499,
      "eval_loss": NaN,
      "eval_runtime": 54.2284,
      "eval_samples_per_second": 4.094,
      "eval_steps_per_second": 2.047,
      "step": 5
    },
    {
      "epoch": 0.011390602752728999,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0170859041290935,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.018984337921214997,
      "eval_loss": NaN,
      "eval_runtime": 54.2359,
      "eval_samples_per_second": 4.093,
      "eval_steps_per_second": 2.047,
      "step": 10
    },
    {
      "epoch": 0.022781205505457997,
      "grad_norm": NaN,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.028476506881822496,
      "grad_norm": NaN,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.028476506881822496,
      "eval_loss": NaN,
      "eval_runtime": 54.2719,
      "eval_samples_per_second": 4.091,
      "eval_steps_per_second": 2.045,
      "step": 15
    },
    {
      "epoch": 0.034171808258187,
      "grad_norm": NaN,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.037968675842429994,
      "eval_loss": NaN,
      "eval_runtime": 54.2429,
      "eval_samples_per_second": 4.093,
      "eval_steps_per_second": 2.046,
      "step": 20
    },
    {
      "epoch": 0.03986710963455149,
      "grad_norm": NaN,
      "learning_rate": 0.00014067366430758004,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.045562411010915994,
      "grad_norm": NaN,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.04746084480303749,
      "eval_loss": NaN,
      "eval_runtime": 54.2597,
      "eval_samples_per_second": 4.091,
      "eval_steps_per_second": 2.046,
      "step": 25
    },
    {
      "epoch": 0.051257712387280496,
      "grad_norm": NaN,
      "learning_rate": 7.920883091822408e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.05695301376364499,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.05695301376364499,
      "eval_loss": NaN,
      "eval_runtime": 54.2539,
      "eval_samples_per_second": 4.092,
      "eval_steps_per_second": 2.046,
      "step": 30
    },
    {
      "epoch": 0.06264831514000949,
      "grad_norm": NaN,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.0664451827242525,
      "eval_loss": NaN,
      "eval_runtime": 54.2476,
      "eval_samples_per_second": 4.092,
      "eval_steps_per_second": 2.046,
      "step": 35
    },
    {
      "epoch": 0.068343616516374,
      "grad_norm": NaN,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.07403891789273849,
      "grad_norm": NaN,
      "learning_rate": 5.478104631726711e-07,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.07593735168485999,
      "eval_loss": NaN,
      "eval_runtime": 54.2318,
      "eval_samples_per_second": 4.094,
      "eval_steps_per_second": 2.047,
      "step": 40
    }
  ],
  "logging_steps": 3,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.096503191502848e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}