{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.892857142857143,
  "eval_steps": 500,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 6.38134225738387,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.8639,
      "step": 1
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 6.427662887763939,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.8681,
      "step": 2
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 5.789679210219034,
      "learning_rate": 1e-05,
      "loss": 0.8274,
      "step": 3
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 2.715427948155473,
      "learning_rate": 9.957224306869053e-06,
      "loss": 0.7307,
      "step": 4
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 4.590973911185041,
      "learning_rate": 9.829629131445342e-06,
      "loss": 0.7966,
      "step": 5
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 4.432507923465467,
      "learning_rate": 9.619397662556434e-06,
      "loss": 0.7316,
      "step": 6
    },
    {
      "epoch": 0.75,
      "grad_norm": 5.306261563213631,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.7056,
      "step": 7
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 4.169018233306645,
      "learning_rate": 8.966766701456177e-06,
      "loss": 0.6871,
      "step": 8
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 2.604291092600148,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.6827,
      "step": 9
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 1.6640185227412452,
      "learning_rate": 8.043807145043604e-06,
      "loss": 0.6352,
      "step": 10
    },
    {
      "epoch": 1.1785714285714286,
      "grad_norm": 1.8223282776265066,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.6048,
      "step": 11
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 1.7690767247619352,
      "learning_rate": 6.913417161825449e-06,
      "loss": 0.6075,
      "step": 12
    },
    {
      "epoch": 1.3928571428571428,
      "grad_norm": 1.2297684666814992,
      "learning_rate": 6.294095225512604e-06,
      "loss": 0.5608,
      "step": 13
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.070630517465832,
      "learning_rate": 5.65263096110026e-06,
      "loss": 0.6357,
      "step": 14
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 1.007789087281265,
      "learning_rate": 5e-06,
      "loss": 0.5734,
      "step": 15
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.9958655806019134,
      "learning_rate": 4.347369038899744e-06,
      "loss": 0.5387,
      "step": 16
    },
    {
      "epoch": 1.8214285714285714,
      "grad_norm": 0.9382716443564832,
      "learning_rate": 3.705904774487396e-06,
      "loss": 0.5875,
      "step": 17
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.6927647016669346,
      "learning_rate": 3.0865828381745515e-06,
      "loss": 0.5431,
      "step": 18
    },
    {
      "epoch": 2.0357142857142856,
      "grad_norm": 0.7217038911956491,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.5459,
      "step": 19
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.6908510203254233,
      "learning_rate": 1.956192854956397e-06,
      "loss": 0.5234,
      "step": 20
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.7471539664195086,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.5342,
      "step": 21
    },
    {
      "epoch": 2.357142857142857,
      "grad_norm": 0.6734174560619429,
      "learning_rate": 1.0332332985438248e-06,
      "loss": 0.5331,
      "step": 22
    },
    {
      "epoch": 2.4642857142857144,
      "grad_norm": 0.6359505084389541,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.5339,
      "step": 23
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.48694859883342007,
      "learning_rate": 3.8060233744356634e-07,
      "loss": 0.4833,
      "step": 24
    },
    {
      "epoch": 2.678571428571429,
      "grad_norm": 0.5111742609060286,
      "learning_rate": 1.7037086855465902e-07,
      "loss": 0.5057,
      "step": 25
    },
    {
      "epoch": 2.7857142857142856,
      "grad_norm": 0.48315315504784084,
      "learning_rate": 4.2775693130948094e-08,
      "loss": 0.5156,
      "step": 26
    },
    {
      "epoch": 2.892857142857143,
      "grad_norm": 0.47858711201269805,
      "learning_rate": 0.0,
      "loss": 0.5448,
      "step": 27
    },
    {
      "epoch": 2.892857142857143,
      "step": 27,
      "total_flos": 2.895182914859827e+16,
      "train_loss": 0.625937306218677,
      "train_runtime": 2995.925,
      "train_samples_per_second": 0.888,
      "train_steps_per_second": 0.009
    }
  ],
  "logging_steps": 1,
  "max_steps": 27,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.895182914859827e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}