{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0756302521008403,
  "eval_steps": 2,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13445378151260504,
      "grad_norm": 64.90283203125,
      "learning_rate": 1e-05,
      "loss": 12.7852,
      "step": 1
    },
    {
      "epoch": 0.13445378151260504,
      "eval_loss": 0.8299278616905212,
      "eval_runtime": 58.6614,
      "eval_samples_per_second": 0.222,
      "eval_steps_per_second": 0.119,
      "step": 1
    },
    {
      "epoch": 0.2689075630252101,
      "grad_norm": 63.91877746582031,
      "learning_rate": 2e-05,
      "loss": 12.5859,
      "step": 2
    },
    {
      "epoch": 0.2689075630252101,
      "eval_loss": 0.7797476053237915,
      "eval_runtime": 0.0898,
      "eval_samples_per_second": 144.765,
      "eval_steps_per_second": 77.95,
      "step": 2
    },
    {
      "epoch": 0.40336134453781514,
      "grad_norm": 57.11682891845703,
      "learning_rate": 3e-05,
      "loss": 11.8086,
      "step": 3
    },
    {
      "epoch": 0.5378151260504201,
      "grad_norm": 64.54560089111328,
      "learning_rate": 4e-05,
      "loss": 11.4844,
      "step": 4
    },
    {
      "epoch": 0.5378151260504201,
      "eval_loss": 0.735276460647583,
      "eval_runtime": 0.0891,
      "eval_samples_per_second": 145.871,
      "eval_steps_per_second": 78.546,
      "step": 4
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 58.462608337402344,
      "learning_rate": 5e-05,
      "loss": 11.8164,
      "step": 5
    },
    {
      "epoch": 0.8067226890756303,
      "grad_norm": 55.280094146728516,
      "learning_rate": 6e-05,
      "loss": 11.2344,
      "step": 6
    },
    {
      "epoch": 0.8067226890756303,
      "eval_loss": 0.6878004670143127,
      "eval_runtime": 0.0892,
      "eval_samples_per_second": 145.68,
      "eval_steps_per_second": 78.443,
      "step": 6
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 44.79998779296875,
      "learning_rate": 7e-05,
      "loss": 10.6719,
      "step": 7
    },
    {
      "epoch": 1.0756302521008403,
      "grad_norm": 50.22980880737305,
      "learning_rate": 8e-05,
      "loss": 10.1758,
      "step": 8
    },
    {
      "epoch": 1.0756302521008403,
      "eval_loss": 0.6066706776618958,
      "eval_runtime": 0.0922,
      "eval_samples_per_second": 140.947,
      "eval_steps_per_second": 75.894,
      "step": 8
    }
  ],
  "logging_steps": 1,
  "max_steps": 8,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 280731410497536.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}