{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0026518164942985947,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00026518164942985947,
      "grad_norm": 1.952933430671692,
      "learning_rate": 2e-05,
      "loss": 1.5287,
      "step": 1
    },
    {
      "epoch": 0.00026518164942985947,
      "eval_loss": 2.152217149734497,
      "eval_runtime": 165.4111,
      "eval_samples_per_second": 4.8,
      "eval_steps_per_second": 4.8,
      "step": 1
    },
    {
      "epoch": 0.0005303632988597189,
      "grad_norm": 2.4794368743896484,
      "learning_rate": 4e-05,
      "loss": 1.7323,
      "step": 2
    },
    {
      "epoch": 0.0007955449482895784,
      "grad_norm": 2.8174667358398438,
      "learning_rate": 6e-05,
      "loss": 1.92,
      "step": 3
    },
    {
      "epoch": 0.0007955449482895784,
      "eval_loss": 2.0877532958984375,
      "eval_runtime": 165.3717,
      "eval_samples_per_second": 4.801,
      "eval_steps_per_second": 4.801,
      "step": 3
    },
    {
      "epoch": 0.0010607265977194379,
      "grad_norm": 2.571035623550415,
      "learning_rate": 8e-05,
      "loss": 1.5655,
      "step": 4
    },
    {
      "epoch": 0.0013259082471492973,
      "grad_norm": 3.4592769145965576,
      "learning_rate": 0.0001,
      "loss": 2.1417,
      "step": 5
    },
    {
      "epoch": 0.0015910898965791568,
      "grad_norm": 4.04508113861084,
      "learning_rate": 0.00012,
      "loss": 1.9687,
      "step": 6
    },
    {
      "epoch": 0.0015910898965791568,
      "eval_loss": 1.6252325773239136,
      "eval_runtime": 165.4536,
      "eval_samples_per_second": 4.799,
      "eval_steps_per_second": 4.799,
      "step": 6
    },
    {
      "epoch": 0.0018562715460090163,
      "grad_norm": 3.091332197189331,
      "learning_rate": 0.00014,
      "loss": 1.2139,
      "step": 7
    },
    {
      "epoch": 0.0021214531954388757,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 1.2876,
      "step": 8
    },
    {
      "epoch": 0.002386634844868735,
      "grad_norm": 3.9201200008392334,
      "learning_rate": 0.00016,
      "loss": 1.8116,
      "step": 9
    },
    {
      "epoch": 0.002386634844868735,
      "eval_loss": 1.135432243347168,
      "eval_runtime": 165.4874,
      "eval_samples_per_second": 4.798,
      "eval_steps_per_second": 4.798,
      "step": 9
    },
    {
      "epoch": 0.0026518164942985947,
      "grad_norm": 2.1837689876556396,
      "learning_rate": 0.00018,
      "loss": 0.9805,
      "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": 7418872835604480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}