{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005407743889249405,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010815487778498811,
      "grad_norm": 0.2873697578907013,
      "learning_rate": 1e-05,
      "loss": 0.7475,
      "step": 1
    },
    {
      "epoch": 0.00010815487778498811,
      "eval_loss": 0.9235302209854126,
      "eval_runtime": 5629.4503,
      "eval_samples_per_second": 2.766,
      "eval_steps_per_second": 1.383,
      "step": 1
    },
    {
      "epoch": 0.00021630975556997622,
      "grad_norm": 0.30236607789993286,
      "learning_rate": 2e-05,
      "loss": 0.7685,
      "step": 2
    },
    {
      "epoch": 0.00021630975556997622,
      "eval_loss": 0.913867712020874,
      "eval_runtime": 3921.2858,
      "eval_samples_per_second": 3.971,
      "eval_steps_per_second": 1.986,
      "step": 2
    },
    {
      "epoch": 0.0003244646333549643,
      "grad_norm": 0.30508556962013245,
      "learning_rate": 3e-05,
      "loss": 0.6934,
      "step": 3
    },
    {
      "epoch": 0.00043261951113995244,
      "grad_norm": 0.3480895459651947,
      "learning_rate": 4e-05,
      "loss": 0.8097,
      "step": 4
    },
    {
      "epoch": 0.00043261951113995244,
      "eval_loss": 0.9014723896980286,
      "eval_runtime": 5058.3783,
      "eval_samples_per_second": 3.079,
      "eval_steps_per_second": 1.539,
      "step": 4
    },
    {
      "epoch": 0.0005407743889249405,
      "grad_norm": 0.30765968561172485,
      "learning_rate": 5e-05,
      "loss": 0.853,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 6658431293325312.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}