{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0001485729567504123,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4857295675041229e-05,
      "grad_norm": 10.114182472229004,
      "learning_rate": 2e-05,
      "loss": 9.6058,
      "step": 1
    },
    {
      "epoch": 1.4857295675041229e-05,
      "eval_loss": 2.7660813331604004,
      "eval_runtime": 1131.1536,
      "eval_samples_per_second": 25.054,
      "eval_steps_per_second": 12.527,
      "step": 1
    },
    {
      "epoch": 2.9714591350082458e-05,
      "grad_norm": 10.107675552368164,
      "learning_rate": 4e-05,
      "loss": 10.7889,
      "step": 2
    },
    {
      "epoch": 4.4571887025123685e-05,
      "grad_norm": 9.10487174987793,
      "learning_rate": 6e-05,
      "loss": 10.1978,
      "step": 3
    },
    {
      "epoch": 4.4571887025123685e-05,
      "eval_loss": 2.7372186183929443,
      "eval_runtime": 1128.4718,
      "eval_samples_per_second": 25.114,
      "eval_steps_per_second": 12.557,
      "step": 3
    },
    {
      "epoch": 5.9429182700164916e-05,
      "grad_norm": 9.060395240783691,
      "learning_rate": 8e-05,
      "loss": 10.6533,
      "step": 4
    },
    {
      "epoch": 7.428647837520615e-05,
      "grad_norm": 9.928213119506836,
      "learning_rate": 0.0001,
      "loss": 10.2667,
      "step": 5
    },
    {
      "epoch": 8.914377405024737e-05,
      "grad_norm": 10.289470672607422,
      "learning_rate": 0.00012,
      "loss": 9.715,
      "step": 6
    },
    {
      "epoch": 8.914377405024737e-05,
      "eval_loss": 2.4323079586029053,
      "eval_runtime": 1127.6729,
      "eval_samples_per_second": 25.131,
      "eval_steps_per_second": 12.566,
      "step": 6
    },
    {
      "epoch": 0.00010400106972528861,
      "grad_norm": 8.097797393798828,
      "learning_rate": 0.00014,
      "loss": 9.8669,
      "step": 7
    },
    {
      "epoch": 0.00011885836540032983,
      "grad_norm": 7.445133686065674,
      "learning_rate": 0.00016,
      "loss": 8.7606,
      "step": 8
    },
    {
      "epoch": 0.00013371566107537106,
      "grad_norm": 6.71532678604126,
      "learning_rate": 0.00018,
      "loss": 7.8511,
      "step": 9
    },
    {
      "epoch": 0.00013371566107537106,
      "eval_loss": 2.059540271759033,
      "eval_runtime": 1124.6565,
      "eval_samples_per_second": 25.199,
      "eval_steps_per_second": 12.599,
      "step": 9
    },
    {
      "epoch": 0.0001485729567504123,
      "grad_norm": 6.443278789520264,
      "learning_rate": 0.0002,
      "loss": 7.6649,
      "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": 1873043106299904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}