{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013802622498274672,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013802622498274672,
      "grad_norm": 2.6702075004577637,
      "learning_rate": 2e-05,
      "loss": 13.3664,
      "step": 1
    },
    {
      "epoch": 0.0013802622498274672,
      "eval_loss": 3.5190110206604004,
      "eval_runtime": 5.875,
      "eval_samples_per_second": 51.915,
      "eval_steps_per_second": 26.043,
      "step": 1
    },
    {
      "epoch": 0.0027605244996549345,
      "grad_norm": 2.1893129348754883,
      "learning_rate": 4e-05,
      "loss": 13.9199,
      "step": 2
    },
    {
      "epoch": 0.004140786749482402,
      "grad_norm": 2.364284038543701,
      "learning_rate": 6e-05,
      "loss": 14.2796,
      "step": 3
    },
    {
      "epoch": 0.004140786749482402,
      "eval_loss": 3.5189876556396484,
      "eval_runtime": 5.8289,
      "eval_samples_per_second": 52.326,
      "eval_steps_per_second": 26.249,
      "step": 3
    },
    {
      "epoch": 0.005521048999309869,
      "grad_norm": 2.0866777896881104,
      "learning_rate": 8e-05,
      "loss": 13.8692,
      "step": 4
    },
    {
      "epoch": 0.006901311249137336,
      "grad_norm": 2.7461817264556885,
      "learning_rate": 0.0001,
      "loss": 13.9277,
      "step": 5
    },
    {
      "epoch": 0.008281573498964804,
      "grad_norm": 2.6720032691955566,
      "learning_rate": 0.00012,
      "loss": 14.387,
      "step": 6
    },
    {
      "epoch": 0.008281573498964804,
      "eval_loss": 3.499831199645996,
      "eval_runtime": 5.9066,
      "eval_samples_per_second": 51.637,
      "eval_steps_per_second": 25.903,
      "step": 6
    },
    {
      "epoch": 0.00966183574879227,
      "grad_norm": 2.4419193267822266,
      "learning_rate": 0.00014,
      "loss": 12.8454,
      "step": 7
    },
    {
      "epoch": 0.011042097998619738,
      "grad_norm": 2.9339168071746826,
      "learning_rate": 0.00016,
      "loss": 15.1389,
      "step": 8
    },
    {
      "epoch": 0.012422360248447204,
      "grad_norm": 3.0656933784484863,
      "learning_rate": 0.00018,
      "loss": 13.6434,
      "step": 9
    },
    {
      "epoch": 0.012422360248447204,
      "eval_loss": 3.362497568130493,
      "eval_runtime": 5.9959,
      "eval_samples_per_second": 50.868,
      "eval_steps_per_second": 25.517,
      "step": 9
    },
    {
      "epoch": 0.013802622498274672,
      "grad_norm": 3.3168411254882812,
      "learning_rate": 0.0002,
      "loss": 12.79,
      "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": 298729403842560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}