{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009377564177704841,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.377564177704842e-05,
      "grad_norm": 2.2670376300811768,
      "learning_rate": 2e-05,
      "loss": 8.6356,
      "step": 1
    },
    {
      "epoch": 9.377564177704842e-05,
      "eval_loss": 2.014927387237549,
      "eval_runtime": 53.0494,
      "eval_samples_per_second": 84.638,
      "eval_steps_per_second": 42.319,
      "step": 1
    },
    {
      "epoch": 0.00018755128355409684,
      "grad_norm": 2.2460289001464844,
      "learning_rate": 4e-05,
      "loss": 8.1867,
      "step": 2
    },
    {
      "epoch": 0.00028132692533114524,
      "grad_norm": 1.994537115097046,
      "learning_rate": 6e-05,
      "loss": 7.7021,
      "step": 3
    },
    {
      "epoch": 0.00028132692533114524,
      "eval_loss": 2.011679172515869,
      "eval_runtime": 53.005,
      "eval_samples_per_second": 84.709,
      "eval_steps_per_second": 42.354,
      "step": 3
    },
    {
      "epoch": 0.00037510256710819367,
      "grad_norm": 2.632202625274658,
      "learning_rate": 8e-05,
      "loss": 8.0644,
      "step": 4
    },
    {
      "epoch": 0.00046887820888524205,
      "grad_norm": 2.2198660373687744,
      "learning_rate": 0.0001,
      "loss": 7.7364,
      "step": 5
    },
    {
      "epoch": 0.0005626538506622905,
      "grad_norm": 2.4189653396606445,
      "learning_rate": 0.00012,
      "loss": 7.028,
      "step": 6
    },
    {
      "epoch": 0.0005626538506622905,
      "eval_loss": 1.9719938039779663,
      "eval_runtime": 53.0028,
      "eval_samples_per_second": 84.713,
      "eval_steps_per_second": 42.356,
      "step": 6
    },
    {
      "epoch": 0.0006564294924393389,
      "grad_norm": 2.582825183868408,
      "learning_rate": 0.00014,
      "loss": 8.0114,
      "step": 7
    },
    {
      "epoch": 0.0007502051342163873,
      "grad_norm": 2.24534010887146,
      "learning_rate": 0.00016,
      "loss": 7.446,
      "step": 8
    },
    {
      "epoch": 0.0008439807759934357,
      "grad_norm": 2.4724223613739014,
      "learning_rate": 0.00018,
      "loss": 7.2315,
      "step": 9
    },
    {
      "epoch": 0.0008439807759934357,
      "eval_loss": 1.8554983139038086,
      "eval_runtime": 53.0145,
      "eval_samples_per_second": 84.694,
      "eval_steps_per_second": 42.347,
      "step": 9
    },
    {
      "epoch": 0.0009377564177704841,
      "grad_norm": 2.9032371044158936,
      "learning_rate": 0.0002,
      "loss": 6.6547,
      "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": 443125642297344.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}