{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9001113723549066,
  "eval_steps": 4041,
  "global_step": 36369,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.97525058779854e-05,
      "loss": 0.9165,
      "step": 500
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9505011755970797e-05,
      "loss": 0.6643,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9257517633956195e-05,
      "loss": 0.6254,
      "step": 1500
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9010023511941593e-05,
      "loss": 0.604,
      "step": 2000
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.876252938992699e-05,
      "loss": 0.5783,
      "step": 2500
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.8515035267912388e-05,
      "loss": 0.5609,
      "step": 3000
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.8267541145897786e-05,
      "loss": 0.5579,
      "step": 3500
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.8020047023883184e-05,
      "loss": 0.5479,
      "step": 4000
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.5143907070159912,
      "eval_rmse": 0.7172102332115173,
      "eval_runtime": 2327.418,
      "eval_samples_per_second": 123.451,
      "eval_steps_per_second": 1.929,
      "step": 4041
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.777255290186858e-05,
      "loss": 0.5383,
      "step": 4500
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.752505877985398e-05,
      "loss": 0.522,
      "step": 5000
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.7277564657839377e-05,
      "loss": 0.5221,
      "step": 5500
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.7030070535824775e-05,
      "loss": 0.5068,
      "step": 6000
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.6782576413810176e-05,
      "loss": 0.5098,
      "step": 6500
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.6535082291795574e-05,
      "loss": 0.5023,
      "step": 7000
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.628758816978097e-05,
      "loss": 0.4958,
      "step": 7500
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.6040094047766366e-05,
      "loss": 0.4928,
      "step": 8000
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.4747944176197052,
      "eval_rmse": 0.689052939414978,
      "eval_runtime": 2343.1879,
      "eval_samples_per_second": 122.62,
      "eval_steps_per_second": 1.916,
      "step": 8082
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.5792599925751764e-05,
      "loss": 0.4896,
      "step": 8500
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.554510580373716e-05,
      "loss": 0.4816,
      "step": 9000
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.529761168172256e-05,
      "loss": 0.483,
      "step": 9500
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.5050117559707957e-05,
      "loss": 0.4786,
      "step": 10000
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.4802623437693355e-05,
      "loss": 0.4742,
      "step": 10500
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.4555129315678752e-05,
      "loss": 0.4721,
      "step": 11000
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.4307635193664152e-05,
      "loss": 0.4665,
      "step": 11500
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.406014107164955e-05,
      "loss": 0.4632,
      "step": 12000
    },
    {
      "epoch": 0.3,
      "eval_loss": 0.44039463996887207,
      "eval_rmse": 0.6636217832565308,
      "eval_runtime": 2341.3935,
      "eval_samples_per_second": 122.714,
      "eval_steps_per_second": 1.918,
      "step": 12123
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.3812646949634947e-05,
      "loss": 0.4624,
      "step": 12500
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.3565152827620345e-05,
      "loss": 0.4565,
      "step": 13000
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.3317658705605743e-05,
      "loss": 0.4579,
      "step": 13500
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.307016458359114e-05,
      "loss": 0.4612,
      "step": 14000
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.2822670461576538e-05,
      "loss": 0.4484,
      "step": 14500
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.2575176339561936e-05,
      "loss": 0.4502,
      "step": 15000
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.2327682217547334e-05,
      "loss": 0.4391,
      "step": 15500
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.2080188095532732e-05,
      "loss": 0.4475,
      "step": 16000
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.4300330877304077,
      "eval_rmse": 0.6557684540748596,
      "eval_runtime": 2336.2101,
      "eval_samples_per_second": 122.986,
      "eval_steps_per_second": 1.922,
      "step": 16164
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.183269397351813e-05,
      "loss": 0.4388,
      "step": 16500
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.1585199851503527e-05,
      "loss": 0.44,
      "step": 17000
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.1337705729488927e-05,
      "loss": 0.4372,
      "step": 17500
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.1090211607474324e-05,
      "loss": 0.4362,
      "step": 18000
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.0842717485459722e-05,
      "loss": 0.4385,
      "step": 18500
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.059522336344512e-05,
      "loss": 0.4263,
      "step": 19000
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.0347729241430518e-05,
      "loss": 0.4353,
      "step": 19500
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.0100235119415916e-05,
      "loss": 0.4295,
      "step": 20000
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.40923774242401123,
      "eval_rmse": 0.6397165060043335,
      "eval_runtime": 2338.1242,
      "eval_samples_per_second": 122.885,
      "eval_steps_per_second": 1.92,
      "step": 20205
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.852740997401312e-06,
      "loss": 0.4219,
      "step": 20500
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.60524687538671e-06,
      "loss": 0.4215,
      "step": 21000
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.357752753372109e-06,
      "loss": 0.422,
      "step": 21500
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.110258631357507e-06,
      "loss": 0.4221,
      "step": 22000
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.862764509342904e-06,
      "loss": 0.4191,
      "step": 22500
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.615270387328302e-06,
      "loss": 0.4178,
      "step": 23000
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.3677762653137e-06,
      "loss": 0.4154,
      "step": 23500
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.120282143299098e-06,
      "loss": 0.4087,
      "step": 24000
    },
    {
      "epoch": 0.6,
      "eval_loss": 0.39208775758743286,
      "eval_rmse": 0.6261686086654663,
      "eval_runtime": 2337.6873,
      "eval_samples_per_second": 122.908,
      "eval_steps_per_second": 1.921,
      "step": 24246
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.872788021284495e-06,
      "loss": 0.4101,
      "step": 24500
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.625293899269893e-06,
      "loss": 0.417,
      "step": 25000
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.377799777255291e-06,
      "loss": 0.4122,
      "step": 25500
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.130305655240689e-06,
      "loss": 0.4069,
      "step": 26000
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.882811533226087e-06,
      "loss": 0.4046,
      "step": 26500
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.635317411211483e-06,
      "loss": 0.4121,
      "step": 27000
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.387823289196882e-06,
      "loss": 0.402,
      "step": 27500
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.14032916718228e-06,
      "loss": 0.4029,
      "step": 28000
    },
    {
      "epoch": 0.7,
      "eval_loss": 0.39122310280799866,
      "eval_rmse": 0.6254780888557434,
      "eval_runtime": 2318.1699,
      "eval_samples_per_second": 123.943,
      "eval_steps_per_second": 1.937,
      "step": 28287
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.8928350451676775e-06,
      "loss": 0.3937,
      "step": 28500
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.645340923153075e-06,
      "loss": 0.3978,
      "step": 29000
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.397846801138473e-06,
      "loss": 0.3929,
      "step": 29500
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.150352679123871e-06,
      "loss": 0.3855,
      "step": 30000
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.902858557109269e-06,
      "loss": 0.3977,
      "step": 30500
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.655364435094667e-06,
      "loss": 0.387,
      "step": 31000
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.407870313080065e-06,
      "loss": 0.3907,
      "step": 31500
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.160376191065463e-06,
      "loss": 0.392,
      "step": 32000
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.3795255720615387,
      "eval_rmse": 0.6160560250282288,
      "eval_runtime": 2318.679,
      "eval_samples_per_second": 123.916,
      "eval_steps_per_second": 1.936,
      "step": 32328
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.9128820690508604e-06,
      "loss": 0.387,
      "step": 32500
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.665387947036258e-06,
      "loss": 0.389,
      "step": 33000
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.417893825021656e-06,
      "loss": 0.3844,
      "step": 33500
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.1703997030070537e-06,
      "loss": 0.3882,
      "step": 34000
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.922905580992452e-06,
      "loss": 0.3833,
      "step": 34500
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.6754114589778497e-06,
      "loss": 0.3818,
      "step": 35000
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.4279173369632474e-06,
      "loss": 0.3792,
      "step": 35500
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.180423214948645e-06,
      "loss": 0.3818,
      "step": 36000
    },
    {
      "epoch": 0.9,
      "eval_loss": 0.37015318870544434,
      "eval_rmse": 0.6084016561508179,
      "eval_runtime": 2328.1676,
      "eval_samples_per_second": 123.411,
      "eval_steps_per_second": 1.929,
      "step": 36369
    }
  ],
  "logging_steps": 500,
  "max_steps": 40405,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 4041,
  "total_flos": 1.1989753896587223e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}