{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08998875140607424,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01799775028121485,
      "grad_norm": 0.06505728513002396,
      "learning_rate": 1e-05,
      "loss": 11.929,
      "step": 1
    },
    {
      "epoch": 0.01799775028121485,
      "eval_loss": 11.92982006072998,
      "eval_runtime": 7.724,
      "eval_samples_per_second": 12.17,
      "eval_steps_per_second": 6.085,
      "step": 1
    },
    {
      "epoch": 0.0359955005624297,
      "grad_norm": 0.0667647272348404,
      "learning_rate": 2e-05,
      "loss": 11.9318,
      "step": 2
    },
    {
      "epoch": 0.0359955005624297,
      "eval_loss": 11.929813385009766,
      "eval_runtime": 0.2234,
      "eval_samples_per_second": 420.679,
      "eval_steps_per_second": 210.339,
      "step": 2
    },
    {
      "epoch": 0.05399325084364454,
      "grad_norm": 0.0617186576128006,
      "learning_rate": 3e-05,
      "loss": 11.9305,
      "step": 3
    },
    {
      "epoch": 0.0719910011248594,
      "grad_norm": 0.06441216915845871,
      "learning_rate": 4e-05,
      "loss": 11.931,
      "step": 4
    },
    {
      "epoch": 0.0719910011248594,
      "eval_loss": 11.929778099060059,
      "eval_runtime": 0.2482,
      "eval_samples_per_second": 378.742,
      "eval_steps_per_second": 189.371,
      "step": 4
    },
    {
      "epoch": 0.08998875140607424,
      "grad_norm": 0.063088558614254,
      "learning_rate": 5e-05,
      "loss": 11.9319,
      "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": 4696915968.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}