{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018303843807199512,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006101281269066504,
      "eval_loss": 6.149837493896484,
      "eval_runtime": 13.1757,
      "eval_samples_per_second": 52.445,
      "eval_steps_per_second": 26.261,
      "step": 1
    },
    {
      "epoch": 0.0018303843807199512,
      "grad_norm": 2.8964645862579346,
      "learning_rate": 3e-05,
      "loss": 5.932,
      "step": 3
    },
    {
      "epoch": 0.0036607687614399025,
      "grad_norm": 2.998232364654541,
      "learning_rate": 6e-05,
      "loss": 6.0007,
      "step": 6
    },
    {
      "epoch": 0.004881025015253203,
      "eval_loss": 5.871977806091309,
      "eval_runtime": 12.2074,
      "eval_samples_per_second": 56.605,
      "eval_steps_per_second": 28.343,
      "step": 8
    },
    {
      "epoch": 0.005491153142159854,
      "grad_norm": 2.0585145950317383,
      "learning_rate": 9e-05,
      "loss": 5.5782,
      "step": 9
    },
    {
      "epoch": 0.007321537522879805,
      "grad_norm": 3.959272623062134,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.8618,
      "step": 12
    },
    {
      "epoch": 0.009151921903599756,
      "grad_norm": 1.9303548336029053,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.3369,
      "step": 15
    },
    {
      "epoch": 0.009762050030506406,
      "eval_loss": 5.450654983520508,
      "eval_runtime": 12.3075,
      "eval_samples_per_second": 56.145,
      "eval_steps_per_second": 28.113,
      "step": 16
    },
    {
      "epoch": 0.010982306284319707,
      "grad_norm": 2.4457473754882812,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.3219,
      "step": 18
    },
    {
      "epoch": 0.012812690665039659,
      "grad_norm": 1.6282868385314941,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 5.0499,
      "step": 21
    },
    {
      "epoch": 0.01464307504575961,
      "grad_norm": 1.859714388847351,
      "learning_rate": 2.061073738537635e-05,
      "loss": 5.0796,
      "step": 24
    },
    {
      "epoch": 0.01464307504575961,
      "eval_loss": 5.20974063873291,
      "eval_runtime": 12.3822,
      "eval_samples_per_second": 55.806,
      "eval_steps_per_second": 27.943,
      "step": 24
    },
    {
      "epoch": 0.01647345942647956,
      "grad_norm": 1.4957493543624878,
      "learning_rate": 5.449673790581611e-06,
      "loss": 4.874,
      "step": 27
    },
    {
      "epoch": 0.018303843807199512,
      "grad_norm": 1.566078543663025,
      "learning_rate": 0.0,
      "loss": 4.8825,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 465923588751360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}