{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.444275234513159e-05,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.444275234513159e-06,
      "grad_norm": 0.13059046864509583,
      "learning_rate": 2e-05,
      "loss": 10.8347,
      "step": 1
    },
    {
      "epoch": 9.444275234513159e-06,
      "eval_loss": 10.834060668945312,
      "eval_runtime": 143.1612,
      "eval_samples_per_second": 311.418,
      "eval_steps_per_second": 155.713,
      "step": 1
    },
    {
      "epoch": 1.8888550469026318e-05,
      "grad_norm": 0.13683012127876282,
      "learning_rate": 4e-05,
      "loss": 10.8284,
      "step": 2
    },
    {
      "epoch": 2.8332825703539477e-05,
      "grad_norm": 0.10735035687685013,
      "learning_rate": 6e-05,
      "loss": 10.8353,
      "step": 3
    },
    {
      "epoch": 2.8332825703539477e-05,
      "eval_loss": 10.833964347839355,
      "eval_runtime": 142.0935,
      "eval_samples_per_second": 313.758,
      "eval_steps_per_second": 156.883,
      "step": 3
    },
    {
      "epoch": 3.7777100938052636e-05,
      "grad_norm": 0.13603197038173676,
      "learning_rate": 8e-05,
      "loss": 10.8475,
      "step": 4
    },
    {
      "epoch": 4.7221376172565795e-05,
      "grad_norm": 0.1254109889268875,
      "learning_rate": 0.0001,
      "loss": 10.8279,
      "step": 5
    },
    {
      "epoch": 5.6665651407078953e-05,
      "grad_norm": 0.13037869334220886,
      "learning_rate": 0.00012,
      "loss": 10.8403,
      "step": 6
    },
    {
      "epoch": 5.6665651407078953e-05,
      "eval_loss": 10.8331298828125,
      "eval_runtime": 141.3773,
      "eval_samples_per_second": 315.348,
      "eval_steps_per_second": 157.677,
      "step": 6
    },
    {
      "epoch": 6.610992664159211e-05,
      "grad_norm": 0.17597252130508423,
      "learning_rate": 0.00014,
      "loss": 10.8405,
      "step": 7
    },
    {
      "epoch": 7.555420187610527e-05,
      "grad_norm": 0.18065564334392548,
      "learning_rate": 0.00016,
      "loss": 10.8292,
      "step": 8
    },
    {
      "epoch": 8.499847711061843e-05,
      "grad_norm": 0.1311742663383484,
      "learning_rate": 0.00018,
      "loss": 10.8247,
      "step": 9
    },
    {
      "epoch": 8.499847711061843e-05,
      "eval_loss": 10.83173656463623,
      "eval_runtime": 139.6685,
      "eval_samples_per_second": 319.206,
      "eval_steps_per_second": 159.607,
      "step": 9
    },
    {
      "epoch": 9.444275234513159e-05,
      "grad_norm": 0.15824280679225922,
      "learning_rate": 0.0002,
      "loss": 10.8336,
      "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": 1086891884544.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}