{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005450259568611955,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.450259568611955e-05,
      "grad_norm": 6.631884574890137,
      "learning_rate": 2e-05,
      "loss": 8.6977,
      "step": 1
    },
    {
      "epoch": 5.450259568611955e-05,
      "eval_loss": 9.220256805419922,
      "eval_runtime": 264.2729,
      "eval_samples_per_second": 29.235,
      "eval_steps_per_second": 14.617,
      "step": 1
    },
    {
      "epoch": 0.0001090051913722391,
      "grad_norm": 9.809612274169922,
      "learning_rate": 4e-05,
      "loss": 10.3189,
      "step": 2
    },
    {
      "epoch": 0.00016350778705835866,
      "grad_norm": 6.289460182189941,
      "learning_rate": 6e-05,
      "loss": 8.3409,
      "step": 3
    },
    {
      "epoch": 0.00016350778705835866,
      "eval_loss": 9.174851417541504,
      "eval_runtime": 262.7915,
      "eval_samples_per_second": 29.4,
      "eval_steps_per_second": 14.7,
      "step": 3
    },
    {
      "epoch": 0.0002180103827444782,
      "grad_norm": 8.075634002685547,
      "learning_rate": 8e-05,
      "loss": 8.9204,
      "step": 4
    },
    {
      "epoch": 0.00027251297843059775,
      "grad_norm": 12.626084327697754,
      "learning_rate": 0.0001,
      "loss": 9.0358,
      "step": 5
    },
    {
      "epoch": 0.00032701557411671733,
      "grad_norm": 8.298057556152344,
      "learning_rate": 0.00012,
      "loss": 8.5622,
      "step": 6
    },
    {
      "epoch": 0.00032701557411671733,
      "eval_loss": 8.34109878540039,
      "eval_runtime": 263.0604,
      "eval_samples_per_second": 29.37,
      "eval_steps_per_second": 14.685,
      "step": 6
    },
    {
      "epoch": 0.00038151816980283685,
      "grad_norm": 8.480585098266602,
      "learning_rate": 0.00014,
      "loss": 8.1062,
      "step": 7
    },
    {
      "epoch": 0.0004360207654889564,
      "grad_norm": 10.241305351257324,
      "learning_rate": 0.00016,
      "loss": 7.8909,
      "step": 8
    },
    {
      "epoch": 0.0004905233611750759,
      "grad_norm": 10.4238920211792,
      "learning_rate": 0.00018,
      "loss": 5.9676,
      "step": 9
    },
    {
      "epoch": 0.0004905233611750759,
      "eval_loss": 5.5707926750183105,
      "eval_runtime": 263.0159,
      "eval_samples_per_second": 29.375,
      "eval_steps_per_second": 14.687,
      "step": 9
    },
    {
      "epoch": 0.0005450259568611955,
      "grad_norm": 11.574395179748535,
      "learning_rate": 0.0002,
      "loss": 5.4292,
      "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": 2126998885367808.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}