{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004590314436538903,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004590314436538903,
      "grad_norm": 1.536804437637329,
      "learning_rate": 2e-05,
      "loss": 44.313,
      "step": 1
    },
    {
      "epoch": 0.0004590314436538903,
      "eval_loss": 11.08893871307373,
      "eval_runtime": 2.2282,
      "eval_samples_per_second": 412.0,
      "eval_steps_per_second": 206.0,
      "step": 1
    },
    {
      "epoch": 0.0009180628873077806,
      "grad_norm": 1.2373898029327393,
      "learning_rate": 4e-05,
      "loss": 44.3196,
      "step": 2
    },
    {
      "epoch": 0.001377094330961671,
      "grad_norm": 1.148323893547058,
      "learning_rate": 6e-05,
      "loss": 44.422,
      "step": 3
    },
    {
      "epoch": 0.001377094330961671,
      "eval_loss": 11.088759422302246,
      "eval_runtime": 1.808,
      "eval_samples_per_second": 507.75,
      "eval_steps_per_second": 253.875,
      "step": 3
    },
    {
      "epoch": 0.0018361257746155612,
      "grad_norm": 1.2407788038253784,
      "learning_rate": 8e-05,
      "loss": 44.3549,
      "step": 4
    },
    {
      "epoch": 0.0022951572182694515,
      "grad_norm": 1.2076925039291382,
      "learning_rate": 0.0001,
      "loss": 44.3308,
      "step": 5
    },
    {
      "epoch": 0.002754188661923342,
      "grad_norm": 1.3431932926177979,
      "learning_rate": 0.00012,
      "loss": 44.3678,
      "step": 6
    },
    {
      "epoch": 0.002754188661923342,
      "eval_loss": 11.087722778320312,
      "eval_runtime": 1.8553,
      "eval_samples_per_second": 494.802,
      "eval_steps_per_second": 247.401,
      "step": 6
    },
    {
      "epoch": 0.003213220105577232,
      "grad_norm": 1.247185468673706,
      "learning_rate": 0.00014,
      "loss": 44.3369,
      "step": 7
    },
    {
      "epoch": 0.0036722515492311225,
      "grad_norm": 0.9406626224517822,
      "learning_rate": 0.00016,
      "loss": 44.3885,
      "step": 8
    },
    {
      "epoch": 0.004131282992885013,
      "grad_norm": 1.4056161642074585,
      "learning_rate": 0.00018,
      "loss": 44.3898,
      "step": 9
    },
    {
      "epoch": 0.004131282992885013,
      "eval_loss": 11.08541202545166,
      "eval_runtime": 1.8801,
      "eval_samples_per_second": 488.271,
      "eval_steps_per_second": 244.136,
      "step": 9
    },
    {
      "epoch": 0.004590314436538903,
      "grad_norm": 1.5108733177185059,
      "learning_rate": 0.0002,
      "loss": 44.3346,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7471104000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}