{
  "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": 0.6876264810562134,
      "learning_rate": 1e-05,
      "loss": 0.7786,
      "step": 1
    },
    {
      "epoch": 0.01799775028121485,
      "eval_loss": 0.8097326159477234,
      "eval_runtime": 55.5448,
      "eval_samples_per_second": 1.692,
      "eval_steps_per_second": 0.846,
      "step": 1
    },
    {
      "epoch": 0.0359955005624297,
      "grad_norm": 0.7143476009368896,
      "learning_rate": 2e-05,
      "loss": 0.8816,
      "step": 2
    },
    {
      "epoch": 0.0359955005624297,
      "eval_loss": 0.7892681956291199,
      "eval_runtime": 5.7119,
      "eval_samples_per_second": 16.457,
      "eval_steps_per_second": 8.228,
      "step": 2
    },
    {
      "epoch": 0.05399325084364454,
      "grad_norm": 0.6934676170349121,
      "learning_rate": 3e-05,
      "loss": 0.7429,
      "step": 3
    },
    {
      "epoch": 0.0719910011248594,
      "grad_norm": 0.6450128555297852,
      "learning_rate": 4e-05,
      "loss": 0.7345,
      "step": 4
    },
    {
      "epoch": 0.0719910011248594,
      "eval_loss": 0.7625122666358948,
      "eval_runtime": 4.3298,
      "eval_samples_per_second": 21.71,
      "eval_steps_per_second": 10.855,
      "step": 4
    },
    {
      "epoch": 0.08998875140607424,
      "grad_norm": 0.6543402671813965,
      "learning_rate": 5e-05,
      "loss": 0.7687,
      "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": 7352017886380032.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}