{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02851033499643621,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002851033499643621,
      "grad_norm": 20.248884201049805,
      "learning_rate": 2e-05,
      "loss": 8.2018,
      "step": 1
    },
    {
      "epoch": 0.005702066999287242,
      "grad_norm": 14.870790481567383,
      "learning_rate": 4e-05,
      "loss": 7.0745,
      "step": 2
    },
    {
      "epoch": 0.008553100498930863,
      "grad_norm": 22.119091033935547,
      "learning_rate": 6e-05,
      "loss": 7.3363,
      "step": 3
    },
    {
      "epoch": 0.008553100498930863,
      "eval_loss": 2.084343194961548,
      "eval_runtime": 10.3956,
      "eval_samples_per_second": 14.237,
      "eval_steps_per_second": 7.118,
      "step": 3
    },
    {
      "epoch": 0.011404133998574484,
      "grad_norm": 15.740070343017578,
      "learning_rate": 8e-05,
      "loss": 6.6133,
      "step": 4
    },
    {
      "epoch": 0.014255167498218105,
      "grad_norm": 16.646244049072266,
      "learning_rate": 0.0001,
      "loss": 8.8023,
      "step": 5
    },
    {
      "epoch": 0.017106200997861726,
      "grad_norm": 21.24431800842285,
      "learning_rate": 0.00012,
      "loss": 6.8908,
      "step": 6
    },
    {
      "epoch": 0.017106200997861726,
      "eval_loss": 1.7117934226989746,
      "eval_runtime": 7.4479,
      "eval_samples_per_second": 19.871,
      "eval_steps_per_second": 9.936,
      "step": 6
    },
    {
      "epoch": 0.019957234497505347,
      "grad_norm": 22.27408218383789,
      "learning_rate": 0.00014,
      "loss": 6.9597,
      "step": 7
    },
    {
      "epoch": 0.022808267997148968,
      "grad_norm": 22.20521354675293,
      "learning_rate": 0.00016,
      "loss": 6.843,
      "step": 8
    },
    {
      "epoch": 0.02565930149679259,
      "grad_norm": 18.542362213134766,
      "learning_rate": 0.00018,
      "loss": 5.9452,
      "step": 9
    },
    {
      "epoch": 0.02565930149679259,
      "eval_loss": 1.6345882415771484,
      "eval_runtime": 10.109,
      "eval_samples_per_second": 14.64,
      "eval_steps_per_second": 7.32,
      "step": 9
    },
    {
      "epoch": 0.02851033499643621,
      "grad_norm": 22.020774841308594,
      "learning_rate": 0.0002,
      "loss": 7.0079,
      "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": 1753442880061440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}