{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21052631578947367,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.055040013045072556,
      "learning_rate": 1e-05,
      "loss": 11.9298,
      "step": 1
    },
    {
      "epoch": 0.042105263157894736,
      "eval_loss": 11.933928489685059,
      "eval_runtime": 10.6383,
      "eval_samples_per_second": 3.76,
      "eval_steps_per_second": 1.88,
      "step": 1
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.05641110613942146,
      "learning_rate": 2e-05,
      "loss": 11.9309,
      "step": 2
    },
    {
      "epoch": 0.08421052631578947,
      "eval_loss": 11.933919906616211,
      "eval_runtime": 0.0875,
      "eval_samples_per_second": 457.243,
      "eval_steps_per_second": 228.622,
      "step": 2
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 0.051996760070323944,
      "learning_rate": 3e-05,
      "loss": 11.9329,
      "step": 3
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.04837435483932495,
      "learning_rate": 4e-05,
      "loss": 11.9329,
      "step": 4
    },
    {
      "epoch": 0.16842105263157894,
      "eval_loss": 11.933886528015137,
      "eval_runtime": 0.114,
      "eval_samples_per_second": 350.889,
      "eval_steps_per_second": 175.444,
      "step": 4
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.05346900597214699,
      "learning_rate": 5e-05,
      "loss": 11.933,
      "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": 2894954496.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}