{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008523332623055614,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.523332623055615e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 5.1899,
      "step": 1
    },
    {
      "epoch": 8.523332623055615e-05,
      "eval_loss": 6.202018737792969,
      "eval_runtime": 358.7946,
      "eval_samples_per_second": 6.884,
      "eval_steps_per_second": 6.884,
      "step": 1
    },
    {
      "epoch": 0.0001704666524611123,
      "grad_norm": 7.228806972503662,
      "learning_rate": 2e-05,
      "loss": 5.8168,
      "step": 2
    },
    {
      "epoch": 0.0002556999786916684,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 6.5219,
      "step": 3
    },
    {
      "epoch": 0.0002556999786916684,
      "eval_loss": 6.202018737792969,
      "eval_runtime": 357.7206,
      "eval_samples_per_second": 6.905,
      "eval_steps_per_second": 6.905,
      "step": 3
    },
    {
      "epoch": 0.0003409333049222246,
      "grad_norm": 4.800383567810059,
      "learning_rate": 4e-05,
      "loss": 5.3551,
      "step": 4
    },
    {
      "epoch": 0.0004261666311527807,
      "grad_norm": 6.785002708435059,
      "learning_rate": 6e-05,
      "loss": 5.7906,
      "step": 5
    },
    {
      "epoch": 0.0005113999573833368,
      "grad_norm": 7.747794151306152,
      "learning_rate": 8e-05,
      "loss": 6.6234,
      "step": 6
    },
    {
      "epoch": 0.0005113999573833368,
      "eval_loss": 6.144652366638184,
      "eval_runtime": 357.6402,
      "eval_samples_per_second": 6.906,
      "eval_steps_per_second": 6.906,
      "step": 6
    },
    {
      "epoch": 0.0005966332836138931,
      "grad_norm": 4.837190628051758,
      "learning_rate": 0.0001,
      "loss": 5.7171,
      "step": 7
    },
    {
      "epoch": 0.0006818666098444492,
      "grad_norm": 5.710320472717285,
      "learning_rate": 0.00012,
      "loss": 6.1524,
      "step": 8
    },
    {
      "epoch": 0.0007670999360750053,
      "grad_norm": 7.983758926391602,
      "learning_rate": 0.00014,
      "loss": 5.4347,
      "step": 9
    },
    {
      "epoch": 0.0007670999360750053,
      "eval_loss": 5.960554599761963,
      "eval_runtime": 357.4345,
      "eval_samples_per_second": 6.91,
      "eval_steps_per_second": 6.91,
      "step": 9
    },
    {
      "epoch": 0.0008523332623055614,
      "grad_norm": 5.738803863525391,
      "learning_rate": 0.00016,
      "loss": 5.8223,
      "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": 2757139491717120.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}