{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0480295566502463,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012315270935960591,
      "eval_loss": 10.3784761428833,
      "eval_runtime": 8.6523,
      "eval_samples_per_second": 632.319,
      "eval_steps_per_second": 79.054,
      "step": 1
    },
    {
      "epoch": 0.012315270935960592,
      "grad_norm": 0.33271121978759766,
      "learning_rate": 9.330127018922194e-05,
      "loss": 166.0521,
      "step": 10
    },
    {
      "epoch": 0.012315270935960592,
      "eval_loss": 10.37819766998291,
      "eval_runtime": 8.8426,
      "eval_samples_per_second": 618.711,
      "eval_steps_per_second": 77.353,
      "step": 10
    },
    {
      "epoch": 0.024630541871921183,
      "grad_norm": 0.390516996383667,
      "learning_rate": 6.91341716182545e-05,
      "loss": 166.0548,
      "step": 20
    },
    {
      "epoch": 0.024630541871921183,
      "eval_loss": 10.377897262573242,
      "eval_runtime": 8.643,
      "eval_samples_per_second": 632.997,
      "eval_steps_per_second": 79.139,
      "step": 20
    },
    {
      "epoch": 0.03694581280788178,
      "grad_norm": 0.3818082809448242,
      "learning_rate": 3.705904774487396e-05,
      "loss": 166.0408,
      "step": 30
    },
    {
      "epoch": 0.03694581280788178,
      "eval_loss": 10.377680778503418,
      "eval_runtime": 8.8119,
      "eval_samples_per_second": 620.864,
      "eval_steps_per_second": 77.622,
      "step": 30
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 16168833515520.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}