{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13855213023900242,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027710426047800486,
      "eval_loss": 4.355137825012207,
      "eval_runtime": 58.9712,
      "eval_samples_per_second": 41.223,
      "eval_steps_per_second": 5.155,
      "step": 1
    },
    {
      "epoch": 0.027710426047800486,
      "grad_norm": 1.860477089881897,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.6053,
      "step": 10
    },
    {
      "epoch": 0.027710426047800486,
      "eval_loss": 3.0410964488983154,
      "eval_runtime": 59.162,
      "eval_samples_per_second": 41.091,
      "eval_steps_per_second": 5.138,
      "step": 10
    },
    {
      "epoch": 0.05542085209560097,
      "grad_norm": 1.2649078369140625,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.8277,
      "step": 20
    },
    {
      "epoch": 0.05542085209560097,
      "eval_loss": 2.6205527782440186,
      "eval_runtime": 59.2126,
      "eval_samples_per_second": 41.055,
      "eval_steps_per_second": 5.134,
      "step": 20
    },
    {
      "epoch": 0.08313127814340146,
      "grad_norm": 1.0012503862380981,
      "learning_rate": 3.705904774487396e-05,
      "loss": 2.4681,
      "step": 30
    },
    {
      "epoch": 0.08313127814340146,
      "eval_loss": 2.379477024078369,
      "eval_runtime": 59.1704,
      "eval_samples_per_second": 41.085,
      "eval_steps_per_second": 5.138,
      "step": 30
    },
    {
      "epoch": 0.11084170419120194,
      "grad_norm": 0.7959256768226624,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 2.3263,
      "step": 40
    },
    {
      "epoch": 0.11084170419120194,
      "eval_loss": 2.277695655822754,
      "eval_runtime": 59.3343,
      "eval_samples_per_second": 40.971,
      "eval_steps_per_second": 5.124,
      "step": 40
    },
    {
      "epoch": 0.13855213023900242,
      "grad_norm": 0.8115575909614563,
      "learning_rate": 0.0,
      "loss": 2.2721,
      "step": 50
    },
    {
      "epoch": 0.13855213023900242,
      "eval_loss": 2.2608070373535156,
      "eval_runtime": 58.9517,
      "eval_samples_per_second": 41.237,
      "eval_steps_per_second": 5.157,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.880364310056141e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}