{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0019638648860958365,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019638648860958367,
      "grad_norm": 22.271787643432617,
      "learning_rate": 2e-05,
      "loss": 17.4012,
      "step": 1
    },
    {
      "epoch": 0.00019638648860958367,
      "eval_loss": 4.327007293701172,
      "eval_runtime": 33.9795,
      "eval_samples_per_second": 63.097,
      "eval_steps_per_second": 31.548,
      "step": 1
    },
    {
      "epoch": 0.00039277297721916735,
      "grad_norm": 23.483922958374023,
      "learning_rate": 4e-05,
      "loss": 19.7027,
      "step": 2
    },
    {
      "epoch": 0.000589159465828751,
      "grad_norm": 20.356332778930664,
      "learning_rate": 6e-05,
      "loss": 18.6672,
      "step": 3
    },
    {
      "epoch": 0.000589159465828751,
      "eval_loss": 4.278309345245361,
      "eval_runtime": 32.1475,
      "eval_samples_per_second": 66.693,
      "eval_steps_per_second": 33.346,
      "step": 3
    },
    {
      "epoch": 0.0007855459544383347,
      "grad_norm": 23.6341609954834,
      "learning_rate": 8e-05,
      "loss": 15.8312,
      "step": 4
    },
    {
      "epoch": 0.0009819324430479183,
      "grad_norm": 20.734163284301758,
      "learning_rate": 0.0001,
      "loss": 16.0768,
      "step": 5
    },
    {
      "epoch": 0.001178318931657502,
      "grad_norm": 24.285808563232422,
      "learning_rate": 0.00012,
      "loss": 17.108,
      "step": 6
    },
    {
      "epoch": 0.001178318931657502,
      "eval_loss": 3.975220203399658,
      "eval_runtime": 31.5838,
      "eval_samples_per_second": 67.883,
      "eval_steps_per_second": 33.941,
      "step": 6
    },
    {
      "epoch": 0.0013747054202670856,
      "grad_norm": 39.34907531738281,
      "learning_rate": 0.00014,
      "loss": 18.0902,
      "step": 7
    },
    {
      "epoch": 0.0015710919088766694,
      "grad_norm": 22.724729537963867,
      "learning_rate": 0.00016,
      "loss": 14.4645,
      "step": 8
    },
    {
      "epoch": 0.001767478397486253,
      "grad_norm": 21.727907180786133,
      "learning_rate": 0.00018,
      "loss": 13.8723,
      "step": 9
    },
    {
      "epoch": 0.001767478397486253,
      "eval_loss": 3.4033701419830322,
      "eval_runtime": 31.488,
      "eval_samples_per_second": 68.09,
      "eval_steps_per_second": 34.045,
      "step": 9
    },
    {
      "epoch": 0.0019638648860958365,
      "grad_norm": 22.12179183959961,
      "learning_rate": 0.0002,
      "loss": 13.3458,
      "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": 298765642629120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}