{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 46.15384615384615,
  "eval_steps": 50,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07692307692307693,
      "eval_loss": 10.376392364501953,
      "eval_runtime": 5.3202,
      "eval_samples_per_second": 282.131,
      "eval_steps_per_second": 4.511,
      "step": 1
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.09619140625,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.378,
      "step": 10
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.00013333333333333334,
      "loss": 10.3754,
      "step": 20
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.0002,
      "loss": 10.3683,
      "step": 30
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.201171875,
      "learning_rate": 0.00019984815164333163,
      "loss": 10.3522,
      "step": 40
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.3203125,
      "learning_rate": 0.00019939306773179497,
      "loss": 10.3159,
      "step": 50
    },
    {
      "epoch": 3.8461538461538463,
      "eval_loss": 10.285228729248047,
      "eval_runtime": 5.2726,
      "eval_samples_per_second": 284.681,
      "eval_steps_per_second": 4.552,
      "step": 50
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 0.32421875,
      "learning_rate": 0.00019863613034027224,
      "loss": 10.2518,
      "step": 60
    },
    {
      "epoch": 5.384615384615385,
      "grad_norm": 0.326171875,
      "learning_rate": 0.00019757963826274357,
      "loss": 10.1828,
      "step": 70
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 0.330078125,
      "learning_rate": 0.00019622680003092503,
      "loss": 10.1177,
      "step": 80
    },
    {
      "epoch": 6.923076923076923,
      "grad_norm": 0.33203125,
      "learning_rate": 0.00019458172417006347,
      "loss": 10.0565,
      "step": 90
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 0.341796875,
      "learning_rate": 0.00019264940672148018,
      "loss": 9.998,
      "step": 100
    },
    {
      "epoch": 7.6923076923076925,
      "eval_loss": 9.973793029785156,
      "eval_runtime": 5.2822,
      "eval_samples_per_second": 284.164,
      "eval_steps_per_second": 4.544,
      "step": 100
    },
    {
      "epoch": 8.461538461538462,
      "grad_norm": 0.345703125,
      "learning_rate": 0.00019043571606975777,
      "loss": 9.942,
      "step": 110
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 0.34765625,
      "learning_rate": 0.0001879473751206489,
      "loss": 9.8887,
      "step": 120
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.349609375,
      "learning_rate": 0.00018519194088383273,
      "loss": 9.836,
      "step": 130
    },
    {
      "epoch": 10.76923076923077,
      "grad_norm": 0.357421875,
      "learning_rate": 0.0001821777815225245,
      "loss": 9.7845,
      "step": 140
    },
    {
      "epoch": 11.538461538461538,
      "grad_norm": 0.361328125,
      "learning_rate": 0.00017891405093963938,
      "loss": 9.7359,
      "step": 150
    },
    {
      "epoch": 11.538461538461538,
      "eval_loss": 9.719038963317871,
      "eval_runtime": 5.2736,
      "eval_samples_per_second": 284.626,
      "eval_steps_per_second": 4.551,
      "step": 150
    },
    {
      "epoch": 12.307692307692308,
      "grad_norm": 0.369140625,
      "learning_rate": 0.00017541066097768963,
      "loss": 9.688,
      "step": 160
    },
    {
      "epoch": 13.076923076923077,
      "grad_norm": 0.3671875,
      "learning_rate": 0.00017167825131684513,
      "loss": 9.6416,
      "step": 170
    },
    {
      "epoch": 13.846153846153847,
      "grad_norm": 0.375,
      "learning_rate": 0.00016772815716257412,
      "loss": 9.597,
      "step": 180
    },
    {
      "epoch": 14.615384615384615,
      "grad_norm": 0.380859375,
      "learning_rate": 0.00016357237482099684,
      "loss": 9.5534,
      "step": 190
    },
    {
      "epoch": 15.384615384615385,
      "grad_norm": 0.37890625,
      "learning_rate": 0.00015922352526649803,
      "loss": 9.5151,
      "step": 200
    },
    {
      "epoch": 15.384615384615385,
      "eval_loss": 9.504176139831543,
      "eval_runtime": 5.2799,
      "eval_samples_per_second": 284.283,
      "eval_steps_per_second": 4.545,
      "step": 200
    },
    {
      "epoch": 16.153846153846153,
      "grad_norm": 0.3828125,
      "learning_rate": 0.00015469481581224272,
      "loss": 9.4734,
      "step": 210
    },
    {
      "epoch": 16.923076923076923,
      "grad_norm": 0.388671875,
      "learning_rate": 0.00015000000000000001,
      "loss": 9.4381,
      "step": 220
    },
    {
      "epoch": 17.692307692307693,
      "grad_norm": 0.39453125,
      "learning_rate": 0.00014515333583108896,
      "loss": 9.4021,
      "step": 230
    },
    {
      "epoch": 18.46153846153846,
      "grad_norm": 0.396484375,
      "learning_rate": 0.00014016954246529696,
      "loss": 9.3725,
      "step": 240
    },
    {
      "epoch": 19.23076923076923,
      "grad_norm": 0.396484375,
      "learning_rate": 0.00013506375551927547,
      "loss": 9.3407,
      "step": 250
    },
    {
      "epoch": 19.23076923076923,
      "eval_loss": 9.341134071350098,
      "eval_runtime": 5.9586,
      "eval_samples_per_second": 251.904,
      "eval_steps_per_second": 4.028,
      "step": 250
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.400390625,
      "learning_rate": 0.00012985148110016947,
      "loss": 9.3153,
      "step": 260
    },
    {
      "epoch": 20.76923076923077,
      "grad_norm": 0.40234375,
      "learning_rate": 0.00012454854871407994,
      "loss": 9.2905,
      "step": 270
    },
    {
      "epoch": 21.53846153846154,
      "grad_norm": 0.408203125,
      "learning_rate": 0.00011917106319237386,
      "loss": 9.2678,
      "step": 280
    },
    {
      "epoch": 22.307692307692307,
      "grad_norm": 0.404296875,
      "learning_rate": 0.00011373535578184082,
      "loss": 9.2496,
      "step": 290
    },
    {
      "epoch": 23.076923076923077,
      "grad_norm": 0.40625,
      "learning_rate": 0.00010825793454723325,
      "loss": 9.2338,
      "step": 300
    },
    {
      "epoch": 23.076923076923077,
      "eval_loss": 9.241479873657227,
      "eval_runtime": 5.2815,
      "eval_samples_per_second": 284.199,
      "eval_steps_per_second": 4.544,
      "step": 300
    },
    {
      "epoch": 23.846153846153847,
      "grad_norm": 0.412109375,
      "learning_rate": 0.00010275543423681621,
      "loss": 9.2185,
      "step": 310
    },
    {
      "epoch": 24.615384615384617,
      "grad_norm": 0.4140625,
      "learning_rate": 9.724456576318381e-05,
      "loss": 9.2101,
      "step": 320
    },
    {
      "epoch": 25.384615384615383,
      "grad_norm": 0.412109375,
      "learning_rate": 9.174206545276677e-05,
      "loss": 9.2002,
      "step": 330
    },
    {
      "epoch": 26.153846153846153,
      "grad_norm": 0.416015625,
      "learning_rate": 8.626464421815919e-05,
      "loss": 9.193,
      "step": 340
    },
    {
      "epoch": 26.923076923076923,
      "grad_norm": 0.41015625,
      "learning_rate": 8.082893680762619e-05,
      "loss": 9.1896,
      "step": 350
    },
    {
      "epoch": 26.923076923076923,
      "eval_loss": 9.20389461517334,
      "eval_runtime": 5.2643,
      "eval_samples_per_second": 285.129,
      "eval_steps_per_second": 4.559,
      "step": 350
    },
    {
      "epoch": 27.692307692307693,
      "grad_norm": 0.416015625,
      "learning_rate": 7.54514512859201e-05,
      "loss": 9.186,
      "step": 360
    },
    {
      "epoch": 28.46153846153846,
      "grad_norm": 0.412109375,
      "learning_rate": 7.014851889983057e-05,
      "loss": 9.182,
      "step": 370
    },
    {
      "epoch": 29.23076923076923,
      "grad_norm": 0.416015625,
      "learning_rate": 6.493624448072457e-05,
      "loss": 9.1823,
      "step": 380
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.4140625,
      "learning_rate": 5.983045753470308e-05,
      "loss": 9.1806,
      "step": 390
    },
    {
      "epoch": 30.76923076923077,
      "grad_norm": 0.419921875,
      "learning_rate": 5.484666416891109e-05,
      "loss": 9.18,
      "step": 400
    },
    {
      "epoch": 30.76923076923077,
      "eval_loss": 9.195965766906738,
      "eval_runtime": 5.2708,
      "eval_samples_per_second": 284.775,
      "eval_steps_per_second": 4.553,
      "step": 400
    },
    {
      "epoch": 31.53846153846154,
      "grad_norm": 0.4140625,
      "learning_rate": 5.000000000000002e-05,
      "loss": 9.1787,
      "step": 410
    },
    {
      "epoch": 32.30769230769231,
      "grad_norm": 0.419921875,
      "learning_rate": 4.530518418775733e-05,
      "loss": 9.1782,
      "step": 420
    },
    {
      "epoch": 33.07692307692308,
      "grad_norm": 0.41796875,
      "learning_rate": 4.077647473350201e-05,
      "loss": 9.1776,
      "step": 430
    },
    {
      "epoch": 33.84615384615385,
      "grad_norm": 0.416015625,
      "learning_rate": 3.642762517900322e-05,
      "loss": 9.1787,
      "step": 440
    },
    {
      "epoch": 34.61538461538461,
      "grad_norm": 0.416015625,
      "learning_rate": 3.227184283742591e-05,
      "loss": 9.1777,
      "step": 450
    },
    {
      "epoch": 34.61538461538461,
      "eval_loss": 9.195714950561523,
      "eval_runtime": 5.2816,
      "eval_samples_per_second": 284.194,
      "eval_steps_per_second": 4.544,
      "step": 450
    },
    {
      "epoch": 35.38461538461539,
      "grad_norm": 0.4140625,
      "learning_rate": 2.8321748683154893e-05,
      "loss": 9.1782,
      "step": 460
    },
    {
      "epoch": 36.15384615384615,
      "grad_norm": 0.419921875,
      "learning_rate": 2.4589339022310386e-05,
      "loss": 9.1783,
      "step": 470
    },
    {
      "epoch": 36.92307692307692,
      "grad_norm": 0.416015625,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 9.1769,
      "step": 480
    },
    {
      "epoch": 37.69230769230769,
      "grad_norm": 0.4140625,
      "learning_rate": 1.7822218477475494e-05,
      "loss": 9.1779,
      "step": 490
    },
    {
      "epoch": 38.46153846153846,
      "grad_norm": 0.419921875,
      "learning_rate": 1.4808059116167305e-05,
      "loss": 9.1781,
      "step": 500
    },
    {
      "epoch": 38.46153846153846,
      "eval_loss": 9.193068504333496,
      "eval_runtime": 5.6598,
      "eval_samples_per_second": 265.206,
      "eval_steps_per_second": 4.24,
      "step": 500
    },
    {
      "epoch": 39.23076923076923,
      "grad_norm": 0.419921875,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 9.1771,
      "step": 510
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.41796875,
      "learning_rate": 9.564283930242257e-06,
      "loss": 9.1775,
      "step": 520
    },
    {
      "epoch": 40.76923076923077,
      "grad_norm": 0.416015625,
      "learning_rate": 7.350593278519824e-06,
      "loss": 9.1773,
      "step": 530
    },
    {
      "epoch": 41.53846153846154,
      "grad_norm": 0.41796875,
      "learning_rate": 5.418275829936537e-06,
      "loss": 9.1787,
      "step": 540
    },
    {
      "epoch": 42.30769230769231,
      "grad_norm": 0.41796875,
      "learning_rate": 3.7731999690749585e-06,
      "loss": 9.1761,
      "step": 550
    },
    {
      "epoch": 42.30769230769231,
      "eval_loss": 9.19363784790039,
      "eval_runtime": 5.2646,
      "eval_samples_per_second": 285.113,
      "eval_steps_per_second": 4.559,
      "step": 550
    },
    {
      "epoch": 43.07692307692308,
      "grad_norm": 0.4140625,
      "learning_rate": 2.420361737256438e-06,
      "loss": 9.1784,
      "step": 560
    },
    {
      "epoch": 43.84615384615385,
      "grad_norm": 0.41796875,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 9.1777,
      "step": 570
    },
    {
      "epoch": 44.61538461538461,
      "grad_norm": 0.419921875,
      "learning_rate": 6.069322682050516e-07,
      "loss": 9.1766,
      "step": 580
    },
    {
      "epoch": 45.38461538461539,
      "grad_norm": 0.412109375,
      "learning_rate": 1.518483566683826e-07,
      "loss": 9.1785,
      "step": 590
    },
    {
      "epoch": 46.15384615384615,
      "grad_norm": 0.419921875,
      "learning_rate": 0.0,
      "loss": 9.1762,
      "step": 600
    },
    {
      "epoch": 46.15384615384615,
      "eval_loss": 9.194318771362305,
      "eval_runtime": 5.2604,
      "eval_samples_per_second": 285.34,
      "eval_steps_per_second": 4.562,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 47,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 245495129702400.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}