{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 23.076923076923077,
  "eval_steps": 100,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 47.11796188354492,
      "learning_rate": 9.990900000000001e-06,
      "loss": 3.6644,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_loss": 2.4919605255126953,
      "eval_runtime": 12.5517,
      "eval_samples_per_second": 10.437,
      "eval_steps_per_second": 1.354,
      "step": 100
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 31.28130531311035,
      "learning_rate": 9.980900000000001e-06,
      "loss": 2.2347,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_loss": 2.156316041946411,
      "eval_runtime": 11.1792,
      "eval_samples_per_second": 11.718,
      "eval_steps_per_second": 1.521,
      "step": 200
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 39.616390228271484,
      "learning_rate": 9.970900000000001e-06,
      "loss": 2.0254,
      "step": 300
    },
    {
      "epoch": 4.615384615384615,
      "eval_loss": 2.024153709411621,
      "eval_runtime": 11.1934,
      "eval_samples_per_second": 11.703,
      "eval_steps_per_second": 1.519,
      "step": 300
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 28.285825729370117,
      "learning_rate": 9.960900000000001e-06,
      "loss": 1.9361,
      "step": 400
    },
    {
      "epoch": 6.153846153846154,
      "eval_loss": 1.9094743728637695,
      "eval_runtime": 11.3855,
      "eval_samples_per_second": 11.506,
      "eval_steps_per_second": 1.493,
      "step": 400
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 34.14302062988281,
      "learning_rate": 9.950900000000002e-06,
      "loss": 1.8531,
      "step": 500
    },
    {
      "epoch": 7.6923076923076925,
      "eval_loss": 1.8729331493377686,
      "eval_runtime": 11.2935,
      "eval_samples_per_second": 11.6,
      "eval_steps_per_second": 1.505,
      "step": 500
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 39.09531784057617,
      "learning_rate": 9.940900000000002e-06,
      "loss": 1.7669,
      "step": 600
    },
    {
      "epoch": 9.23076923076923,
      "eval_loss": 1.831756830215454,
      "eval_runtime": 11.0535,
      "eval_samples_per_second": 11.851,
      "eval_steps_per_second": 1.538,
      "step": 600
    },
    {
      "epoch": 10.76923076923077,
      "grad_norm": 93.24444580078125,
      "learning_rate": 9.930900000000002e-06,
      "loss": 1.7518,
      "step": 700
    },
    {
      "epoch": 10.76923076923077,
      "eval_loss": 1.7832175493240356,
      "eval_runtime": 11.1684,
      "eval_samples_per_second": 11.729,
      "eval_steps_per_second": 1.522,
      "step": 700
    },
    {
      "epoch": 12.307692307692308,
      "grad_norm": 32.21013641357422,
      "learning_rate": 9.920900000000002e-06,
      "loss": 1.7149,
      "step": 800
    },
    {
      "epoch": 12.307692307692308,
      "eval_loss": 1.7581098079681396,
      "eval_runtime": 11.101,
      "eval_samples_per_second": 11.801,
      "eval_steps_per_second": 1.531,
      "step": 800
    },
    {
      "epoch": 13.846153846153847,
      "grad_norm": 59.90657043457031,
      "learning_rate": 9.9109e-06,
      "loss": 1.6734,
      "step": 900
    },
    {
      "epoch": 13.846153846153847,
      "eval_loss": 1.7163844108581543,
      "eval_runtime": 11.1167,
      "eval_samples_per_second": 11.784,
      "eval_steps_per_second": 1.529,
      "step": 900
    },
    {
      "epoch": 15.384615384615385,
      "grad_norm": 20.61592674255371,
      "learning_rate": 9.9009e-06,
      "loss": 1.6612,
      "step": 1000
    },
    {
      "epoch": 15.384615384615385,
      "eval_loss": 1.6949567794799805,
      "eval_runtime": 11.0663,
      "eval_samples_per_second": 11.838,
      "eval_steps_per_second": 1.536,
      "step": 1000
    },
    {
      "epoch": 16.923076923076923,
      "grad_norm": 17.60099220275879,
      "learning_rate": 9.8909e-06,
      "loss": 1.6199,
      "step": 1100
    },
    {
      "epoch": 16.923076923076923,
      "eval_loss": 1.6769332885742188,
      "eval_runtime": 11.0531,
      "eval_samples_per_second": 11.852,
      "eval_steps_per_second": 1.538,
      "step": 1100
    },
    {
      "epoch": 18.46153846153846,
      "grad_norm": 20.802692413330078,
      "learning_rate": 9.8809e-06,
      "loss": 1.6008,
      "step": 1200
    },
    {
      "epoch": 18.46153846153846,
      "eval_loss": 1.6524990797042847,
      "eval_runtime": 11.0831,
      "eval_samples_per_second": 11.82,
      "eval_steps_per_second": 1.534,
      "step": 1200
    },
    {
      "epoch": 20.0,
      "grad_norm": 21.809823989868164,
      "learning_rate": 9.8709e-06,
      "loss": 1.5812,
      "step": 1300
    },
    {
      "epoch": 20.0,
      "eval_loss": 1.6428295373916626,
      "eval_runtime": 11.1093,
      "eval_samples_per_second": 11.792,
      "eval_steps_per_second": 1.53,
      "step": 1300
    },
    {
      "epoch": 21.53846153846154,
      "grad_norm": 46.8908576965332,
      "learning_rate": 9.8609e-06,
      "loss": 1.5419,
      "step": 1400
    },
    {
      "epoch": 21.53846153846154,
      "eval_loss": 1.6006404161453247,
      "eval_runtime": 11.2393,
      "eval_samples_per_second": 11.655,
      "eval_steps_per_second": 1.513,
      "step": 1400
    },
    {
      "epoch": 23.076923076923077,
      "grad_norm": 27.15238380432129,
      "learning_rate": 9.8509e-06,
      "loss": 1.5374,
      "step": 1500
    },
    {
      "epoch": 23.076923076923077,
      "eval_loss": 1.5862094163894653,
      "eval_runtime": 11.1815,
      "eval_samples_per_second": 11.716,
      "eval_steps_per_second": 1.52,
      "step": 1500
    }
  ],
  "logging_steps": 100,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1539,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.73364749312e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}