{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007136485280999108,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007136485280999108,
      "grad_norm": 1.854089379310608,
      "learning_rate": 2e-05,
      "loss": 7.3707,
      "step": 1
    },
    {
      "epoch": 0.0007136485280999108,
      "eval_loss": 1.9733723402023315,
      "eval_runtime": 40.7941,
      "eval_samples_per_second": 14.463,
      "eval_steps_per_second": 7.231,
      "step": 1
    },
    {
      "epoch": 0.0014272970561998216,
      "grad_norm": 2.264069080352783,
      "learning_rate": 4e-05,
      "loss": 6.7833,
      "step": 2
    },
    {
      "epoch": 0.0021409455842997323,
      "grad_norm": 1.336599349975586,
      "learning_rate": 6e-05,
      "loss": 7.022,
      "step": 3
    },
    {
      "epoch": 0.0021409455842997323,
      "eval_loss": 1.9719511270523071,
      "eval_runtime": 40.844,
      "eval_samples_per_second": 14.445,
      "eval_steps_per_second": 7.223,
      "step": 3
    },
    {
      "epoch": 0.002854594112399643,
      "grad_norm": 1.47821044921875,
      "learning_rate": 8e-05,
      "loss": 7.9792,
      "step": 4
    },
    {
      "epoch": 0.003568242640499554,
      "grad_norm": 2.16683030128479,
      "learning_rate": 0.0001,
      "loss": 6.8448,
      "step": 5
    },
    {
      "epoch": 0.004281891168599465,
      "grad_norm": 1.805727481842041,
      "learning_rate": 0.00012,
      "loss": 8.0343,
      "step": 6
    },
    {
      "epoch": 0.004281891168599465,
      "eval_loss": 1.9525084495544434,
      "eval_runtime": 40.8154,
      "eval_samples_per_second": 14.455,
      "eval_steps_per_second": 7.228,
      "step": 6
    },
    {
      "epoch": 0.0049955396966993755,
      "grad_norm": 1.9774658679962158,
      "learning_rate": 0.00014,
      "loss": 8.3579,
      "step": 7
    },
    {
      "epoch": 0.005709188224799286,
      "grad_norm": 1.7990143299102783,
      "learning_rate": 0.00016,
      "loss": 7.3282,
      "step": 8
    },
    {
      "epoch": 0.006422836752899197,
      "grad_norm": 2.510244846343994,
      "learning_rate": 0.00018,
      "loss": 7.4668,
      "step": 9
    },
    {
      "epoch": 0.006422836752899197,
      "eval_loss": 1.858172059059143,
      "eval_runtime": 40.8786,
      "eval_samples_per_second": 14.433,
      "eval_steps_per_second": 7.216,
      "step": 9
    },
    {
      "epoch": 0.007136485280999108,
      "grad_norm": 2.346768379211426,
      "learning_rate": 0.0002,
      "loss": 6.903,
      "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": 3176061021978624.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}