{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002866150759529951,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028661507595299513,
      "grad_norm": 0.05394924804568291,
      "learning_rate": 2e-05,
      "loss": 10.3759,
      "step": 1
    },
    {
      "epoch": 0.00028661507595299513,
      "eval_loss": 10.372183799743652,
      "eval_runtime": 8.4729,
      "eval_samples_per_second": 173.495,
      "eval_steps_per_second": 86.748,
      "step": 1
    },
    {
      "epoch": 0.0005732301519059903,
      "grad_norm": 0.04519639536738396,
      "learning_rate": 4e-05,
      "loss": 10.3705,
      "step": 2
    },
    {
      "epoch": 0.0008598452278589854,
      "grad_norm": 0.059499386698007584,
      "learning_rate": 6e-05,
      "loss": 10.3834,
      "step": 3
    },
    {
      "epoch": 0.0008598452278589854,
      "eval_loss": 10.37211799621582,
      "eval_runtime": 8.2943,
      "eval_samples_per_second": 177.231,
      "eval_steps_per_second": 88.615,
      "step": 3
    },
    {
      "epoch": 0.0011464603038119805,
      "grad_norm": 0.053107716143131256,
      "learning_rate": 8e-05,
      "loss": 10.3755,
      "step": 4
    },
    {
      "epoch": 0.0014330753797649756,
      "grad_norm": 0.057291179895401,
      "learning_rate": 0.0001,
      "loss": 10.3722,
      "step": 5
    },
    {
      "epoch": 0.0017196904557179708,
      "grad_norm": 0.0635877400636673,
      "learning_rate": 0.00012,
      "loss": 10.3663,
      "step": 6
    },
    {
      "epoch": 0.0017196904557179708,
      "eval_loss": 10.371790885925293,
      "eval_runtime": 8.618,
      "eval_samples_per_second": 170.573,
      "eval_steps_per_second": 85.286,
      "step": 6
    },
    {
      "epoch": 0.002006305531670966,
      "grad_norm": 0.04109181463718414,
      "learning_rate": 0.00014,
      "loss": 10.3665,
      "step": 7
    },
    {
      "epoch": 0.002292920607623961,
      "grad_norm": 0.040859851986169815,
      "learning_rate": 0.00016,
      "loss": 10.3717,
      "step": 8
    },
    {
      "epoch": 0.0025795356835769563,
      "grad_norm": 0.05362185463309288,
      "learning_rate": 0.00018,
      "loss": 10.3672,
      "step": 9
    },
    {
      "epoch": 0.0025795356835769563,
      "eval_loss": 10.371278762817383,
      "eval_runtime": 8.574,
      "eval_samples_per_second": 171.448,
      "eval_steps_per_second": 85.724,
      "step": 9
    },
    {
      "epoch": 0.002866150759529951,
      "grad_norm": 0.052429113537073135,
      "learning_rate": 0.0002,
      "loss": 10.3656,
      "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": 129309081600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}