{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 0.7374217510223389,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.828,
      "step": 1
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.7326979041099548,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.8692,
      "step": 2
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.5996476411819458,
      "learning_rate": 0.0002,
      "loss": 0.7978,
      "step": 3
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.4960692524909973,
      "learning_rate": 0.00019977668786231534,
      "loss": 0.7581,
      "step": 4
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.38662832975387573,
      "learning_rate": 0.000199107748815478,
      "loss": 0.7099,
      "step": 5
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.47017937898635864,
      "learning_rate": 0.0001979961705036587,
      "loss": 0.6783,
      "step": 6
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.39107415080070496,
      "learning_rate": 0.00019644691750543767,
      "loss": 0.6699,
      "step": 7
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.31766048073768616,
      "learning_rate": 0.0001944669091607919,
      "loss": 0.6986,
      "step": 8
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.28557154536247253,
      "learning_rate": 0.00019206498866764288,
      "loss": 0.6539,
      "step": 9
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2970712184906006,
      "learning_rate": 0.00018925188358598813,
      "loss": 0.6672,
      "step": 10
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.33635565638542175,
      "learning_rate": 0.00018604015792601396,
      "loss": 0.5643,
      "step": 11
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.34821704030036926,
      "learning_rate": 0.00018244415603417603,
      "loss": 0.5525,
      "step": 12
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.3633900582790375,
      "learning_rate": 0.0001784799385278661,
      "loss": 0.5256,
      "step": 13
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.3432920575141907,
      "learning_rate": 0.00017416521056479577,
      "loss": 0.5193,
      "step": 14
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.3452214002609253,
      "learning_rate": 0.00016951924276746425,
      "loss": 0.5046,
      "step": 15
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.29285934567451477,
      "learning_rate": 0.00016456278515588024,
      "loss": 0.4897,
      "step": 16
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.30729544162750244,
      "learning_rate": 0.00015931797447293552,
      "loss": 0.501,
      "step": 17
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.2720145583152771,
      "learning_rate": 0.00015380823531633729,
      "loss": 0.4759,
      "step": 18
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.2651268541812897,
      "learning_rate": 0.00014805817551866838,
      "loss": 0.4527,
      "step": 19
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2597902715206146,
      "learning_rate": 0.0001420934762428335,
      "loss": 0.4479,
      "step": 20
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.2531144917011261,
      "learning_rate": 0.00013594077728375128,
      "loss": 0.4056,
      "step": 21
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.2363481968641281,
      "learning_rate": 0.00012962755808856342,
      "loss": 0.3951,
      "step": 22
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.23172461986541748,
      "learning_rate": 0.00012318201502675285,
      "loss": 0.3863,
      "step": 23
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.24559740722179413,
      "learning_rate": 0.00011663293545831302,
      "loss": 0.3809,
      "step": 24
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.24797773361206055,
      "learning_rate": 0.00011000956916240985,
      "loss": 0.3768,
      "step": 25
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.25474536418914795,
      "learning_rate": 0.00010334149770076747,
      "loss": 0.3628,
      "step": 26
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.25486743450164795,
      "learning_rate": 9.665850229923258e-05,
      "loss": 0.3603,
      "step": 27
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.26718005537986755,
      "learning_rate": 8.999043083759017e-05,
      "loss": 0.3584,
      "step": 28
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.2610970139503479,
      "learning_rate": 8.336706454168701e-05,
      "loss": 0.3546,
      "step": 29
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2513510584831238,
      "learning_rate": 7.681798497324716e-05,
      "loss": 0.3507,
      "step": 30
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.23601773381233215,
      "learning_rate": 7.037244191143661e-05,
      "loss": 0.3212,
      "step": 31
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.2521430253982544,
      "learning_rate": 6.405922271624874e-05,
      "loss": 0.3399,
      "step": 32
    },
    {
      "epoch": 3.3,
      "grad_norm": 0.24177978932857513,
      "learning_rate": 5.790652375716652e-05,
      "loss": 0.2891,
      "step": 33
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.25264158844947815,
      "learning_rate": 5.1941824481331626e-05,
      "loss": 0.3047,
      "step": 34
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.23934145271778107,
      "learning_rate": 4.6191764683662744e-05,
      "loss": 0.2896,
      "step": 35
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.25319987535476685,
      "learning_rate": 4.0682025527064486e-05,
      "loss": 0.2977,
      "step": 36
    },
    {
      "epoch": 3.7,
      "grad_norm": 0.23155006766319275,
      "learning_rate": 3.543721484411976e-05,
      "loss": 0.2793,
      "step": 37
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.2498036026954651,
      "learning_rate": 3.0480757232535772e-05,
      "loss": 0.3165,
      "step": 38
    },
    {
      "epoch": 3.9,
      "grad_norm": 0.23940016329288483,
      "learning_rate": 2.5834789435204243e-05,
      "loss": 0.2938,
      "step": 39
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.23618489503860474,
      "learning_rate": 2.1520061472133902e-05,
      "loss": 0.2713,
      "step": 40
    },
    {
      "epoch": 4.1,
      "grad_norm": 0.22089381515979767,
      "learning_rate": 1.7555843965823992e-05,
      "loss": 0.2618,
      "step": 41
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.2343159019947052,
      "learning_rate": 1.3959842073986085e-05,
      "loss": 0.2668,
      "step": 42
    },
    {
      "epoch": 4.3,
      "grad_norm": 0.2323874831199646,
      "learning_rate": 1.0748116414011888e-05,
      "loss": 0.2645,
      "step": 43
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.24557726085186005,
      "learning_rate": 7.935011332357112e-06,
      "loss": 0.2728,
      "step": 44
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.24076133966445923,
      "learning_rate": 5.533090839208133e-06,
      "loss": 0.2729,
      "step": 45
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.22625155746936798,
      "learning_rate": 3.5530824945623542e-06,
      "loss": 0.2929,
      "step": 46
    },
    {
      "epoch": 4.7,
      "grad_norm": 0.23357822000980377,
      "learning_rate": 2.003829496341325e-06,
      "loss": 0.2691,
      "step": 47
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.22757555544376373,
      "learning_rate": 8.922511845219971e-07,
      "loss": 0.2713,
      "step": 48
    },
    {
      "epoch": 4.9,
      "grad_norm": 0.23513054847717285,
      "learning_rate": 2.2331213768468363e-07,
      "loss": 0.2777,
      "step": 49
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.23401321470737457,
      "learning_rate": 0.0,
      "loss": 0.2611,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 7.430306788466688e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}