{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9982174688057041,
  "eval_steps": 70,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07130124777183601,
      "grad_norm": 1.4087971448898315,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 2.5781,
      "step": 5
    },
    {
      "epoch": 0.14260249554367202,
      "grad_norm": 1.1262208223342896,
      "learning_rate": 2.380952380952381e-05,
      "loss": 2.5765,
      "step": 10
    },
    {
      "epoch": 0.21390374331550802,
      "grad_norm": 1.2945618629455566,
      "learning_rate": 3.571428571428572e-05,
      "loss": 2.342,
      "step": 15
    },
    {
      "epoch": 0.28520499108734404,
      "grad_norm": 0.7618772387504578,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.9415,
      "step": 20
    },
    {
      "epoch": 0.35650623885918004,
      "grad_norm": 0.7050806879997253,
      "learning_rate": 5.9523809523809524e-05,
      "loss": 1.6927,
      "step": 25
    },
    {
      "epoch": 0.42780748663101603,
      "grad_norm": 0.9037391543388367,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.6323,
      "step": 30
    },
    {
      "epoch": 0.49910873440285203,
      "grad_norm": 0.8459873795509338,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.556,
      "step": 35
    },
    {
      "epoch": 0.5704099821746881,
      "grad_norm": 0.7082933783531189,
      "learning_rate": 9.523809523809524e-05,
      "loss": 1.4586,
      "step": 40
    },
    {
      "epoch": 0.6417112299465241,
      "grad_norm": 0.625400722026825,
      "learning_rate": 9.998445910004082e-05,
      "loss": 1.4528,
      "step": 45
    },
    {
      "epoch": 0.7130124777183601,
      "grad_norm": 2.810605764389038,
      "learning_rate": 9.988952191691925e-05,
      "loss": 1.4471,
      "step": 50
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 2.9866161346435547,
      "learning_rate": 9.97084451044556e-05,
      "loss": 1.4675,
      "step": 55
    },
    {
      "epoch": 0.8556149732620321,
      "grad_norm": 3.7440223693847656,
      "learning_rate": 9.944154131125642e-05,
      "loss": 1.4057,
      "step": 60
    },
    {
      "epoch": 0.9269162210338681,
      "grad_norm": 0.6605167984962463,
      "learning_rate": 9.90892713754483e-05,
      "loss": 1.4725,
      "step": 65
    },
    {
      "epoch": 0.9982174688057041,
      "grad_norm": 0.5990611910820007,
      "learning_rate": 9.865224352899119e-05,
      "loss": 1.4367,
      "step": 70
    },
    {
      "epoch": 0.9982174688057041,
      "eval_loss": 1.3730539083480835,
      "eval_runtime": 7.9538,
      "eval_samples_per_second": 5.783,
      "eval_steps_per_second": 1.509,
      "step": 70
    }
  ],
  "logging_steps": 5,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.022306552766792e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}