{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 13791,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10876658690450294,
      "grad_norm": 7.74190092086792,
      "learning_rate": 4.818722355159162e-05,
      "loss": 1.3121,
      "step": 500
    },
    {
      "epoch": 0.2175331738090059,
      "grad_norm": 21.71584129333496,
      "learning_rate": 4.637444710318324e-05,
      "loss": 1.1551,
      "step": 1000
    },
    {
      "epoch": 0.3262997607135088,
      "grad_norm": 14.698501586914062,
      "learning_rate": 4.4561670654774854e-05,
      "loss": 1.0899,
      "step": 1500
    },
    {
      "epoch": 0.4350663476180118,
      "grad_norm": 12.033799171447754,
      "learning_rate": 4.2748894206366476e-05,
      "loss": 1.054,
      "step": 2000
    },
    {
      "epoch": 0.5438329345225147,
      "grad_norm": 8.601971626281738,
      "learning_rate": 4.093611775795809e-05,
      "loss": 1.015,
      "step": 2500
    },
    {
      "epoch": 0.6525995214270176,
      "grad_norm": 12.497455596923828,
      "learning_rate": 3.912334130954971e-05,
      "loss": 0.9868,
      "step": 3000
    },
    {
      "epoch": 0.7613661083315205,
      "grad_norm": 17.868608474731445,
      "learning_rate": 3.731056486114133e-05,
      "loss": 0.9785,
      "step": 3500
    },
    {
      "epoch": 0.8701326952360235,
      "grad_norm": 9.991225242614746,
      "learning_rate": 3.549778841273294e-05,
      "loss": 0.9544,
      "step": 4000
    },
    {
      "epoch": 0.9788992821405265,
      "grad_norm": 30.770978927612305,
      "learning_rate": 3.368501196432456e-05,
      "loss": 0.9245,
      "step": 4500
    },
    {
      "epoch": 1.0876658690450294,
      "grad_norm": 23.796464920043945,
      "learning_rate": 3.187223551591618e-05,
      "loss": 0.7713,
      "step": 5000
    },
    {
      "epoch": 1.1964324559495323,
      "grad_norm": 24.789031982421875,
      "learning_rate": 3.0059459067507794e-05,
      "loss": 0.7294,
      "step": 5500
    },
    {
      "epoch": 1.3051990428540352,
      "grad_norm": 18.538000106811523,
      "learning_rate": 2.8246682619099413e-05,
      "loss": 0.7132,
      "step": 6000
    },
    {
      "epoch": 1.4139656297585381,
      "grad_norm": 15.591426849365234,
      "learning_rate": 2.643390617069103e-05,
      "loss": 0.7076,
      "step": 6500
    },
    {
      "epoch": 1.5227322166630413,
      "grad_norm": 22.807159423828125,
      "learning_rate": 2.462112972228265e-05,
      "loss": 0.7153,
      "step": 7000
    },
    {
      "epoch": 1.6314988035675442,
      "grad_norm": 11.409658432006836,
      "learning_rate": 2.2808353273874268e-05,
      "loss": 0.6954,
      "step": 7500
    },
    {
      "epoch": 1.740265390472047,
      "grad_norm": 20.154701232910156,
      "learning_rate": 2.0995576825465886e-05,
      "loss": 0.707,
      "step": 8000
    },
    {
      "epoch": 1.84903197737655,
      "grad_norm": 17.02855110168457,
      "learning_rate": 1.91828003770575e-05,
      "loss": 0.6715,
      "step": 8500
    },
    {
      "epoch": 1.957798564281053,
      "grad_norm": 19.347368240356445,
      "learning_rate": 1.737002392864912e-05,
      "loss": 0.6609,
      "step": 9000
    },
    {
      "epoch": 2.066565151185556,
      "grad_norm": 18.68759536743164,
      "learning_rate": 1.5557247480240738e-05,
      "loss": 0.5354,
      "step": 9500
    },
    {
      "epoch": 2.1753317380900588,
      "grad_norm": 15.24686050415039,
      "learning_rate": 1.3744471031832355e-05,
      "loss": 0.4594,
      "step": 10000
    },
    {
      "epoch": 2.2840983249945617,
      "grad_norm": 32.36734390258789,
      "learning_rate": 1.1931694583423973e-05,
      "loss": 0.453,
      "step": 10500
    },
    {
      "epoch": 2.3928649118990646,
      "grad_norm": 19.55815315246582,
      "learning_rate": 1.011891813501559e-05,
      "loss": 0.4465,
      "step": 11000
    },
    {
      "epoch": 2.5016314988035675,
      "grad_norm": 16.438173294067383,
      "learning_rate": 8.306141686607208e-06,
      "loss": 0.4226,
      "step": 11500
    },
    {
      "epoch": 2.6103980857080704,
      "grad_norm": 21.047183990478516,
      "learning_rate": 6.493365238198826e-06,
      "loss": 0.4324,
      "step": 12000
    },
    {
      "epoch": 2.7191646726125733,
      "grad_norm": 29.30052947998047,
      "learning_rate": 4.680588789790443e-06,
      "loss": 0.4306,
      "step": 12500
    },
    {
      "epoch": 2.8279312595170762,
      "grad_norm": 7.3705010414123535,
      "learning_rate": 2.8678123413820606e-06,
      "loss": 0.4371,
      "step": 13000
    },
    {
      "epoch": 2.936697846421579,
      "grad_norm": 24.24944305419922,
      "learning_rate": 1.0550358929736786e-06,
      "loss": 0.4305,
      "step": 13500
    },
    {
      "epoch": 3.0,
      "step": 13791,
      "total_flos": 2.508085260375571e+16,
      "train_loss": 0.7300247143699852,
      "train_runtime": 1073.0221,
      "train_samples_per_second": 205.623,
      "train_steps_per_second": 12.852
    }
  ],
  "logging_steps": 500,
  "max_steps": 13791,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.508085260375571e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}