{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 1,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 23.256885528564453,
      "learning_rate": 2.5e-05,
      "loss": 0.9107,
      "step": 1
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.57,
      "eval_loss": 0.8262696862220764,
      "eval_runtime": 0.8414,
      "eval_samples_per_second": 118.852,
      "eval_steps_per_second": 3.566,
      "step": 1
    },
    {
      "epoch": 0.4,
      "grad_norm": 23.631181716918945,
      "learning_rate": 5e-05,
      "loss": 0.9117,
      "step": 2
    },
    {
      "epoch": 0.4,
      "eval_accuracy": 0.57,
      "eval_loss": 0.8167089819908142,
      "eval_runtime": 0.8385,
      "eval_samples_per_second": 119.261,
      "eval_steps_per_second": 3.578,
      "step": 2
    },
    {
      "epoch": 0.6,
      "grad_norm": 28.508174896240234,
      "learning_rate": 4.8958333333333335e-05,
      "loss": 0.9991,
      "step": 3
    },
    {
      "epoch": 0.6,
      "eval_accuracy": 0.57,
      "eval_loss": 0.7878709435462952,
      "eval_runtime": 0.8413,
      "eval_samples_per_second": 118.87,
      "eval_steps_per_second": 3.566,
      "step": 3
    },
    {
      "epoch": 0.8,
      "grad_norm": 19.008262634277344,
      "learning_rate": 4.791666666666667e-05,
      "loss": 0.8288,
      "step": 4
    },
    {
      "epoch": 0.8,
      "eval_accuracy": 0.56,
      "eval_loss": 0.7578710913658142,
      "eval_runtime": 0.8391,
      "eval_samples_per_second": 119.176,
      "eval_steps_per_second": 3.575,
      "step": 4
    },
    {
      "epoch": 1.0,
      "grad_norm": 23.889429092407227,
      "learning_rate": 4.6875e-05,
      "loss": 0.8763,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.53,
      "eval_loss": 0.7321679592132568,
      "eval_runtime": 0.8386,
      "eval_samples_per_second": 119.253,
      "eval_steps_per_second": 3.578,
      "step": 5
    },
    {
      "epoch": 1.2,
      "grad_norm": 9.946539878845215,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 0.7244,
      "step": 6
    },
    {
      "epoch": 1.2,
      "eval_accuracy": 0.55,
      "eval_loss": 0.7117968797683716,
      "eval_runtime": 0.8351,
      "eval_samples_per_second": 119.747,
      "eval_steps_per_second": 3.592,
      "step": 6
    },
    {
      "epoch": 1.4,
      "grad_norm": 9.386951446533203,
      "learning_rate": 4.4791666666666673e-05,
      "loss": 0.7601,
      "step": 7
    },
    {
      "epoch": 1.4,
      "eval_accuracy": 0.54,
      "eval_loss": 0.6952930688858032,
      "eval_runtime": 0.8393,
      "eval_samples_per_second": 119.145,
      "eval_steps_per_second": 3.574,
      "step": 7
    },
    {
      "epoch": 1.6,
      "grad_norm": 20.157466888427734,
      "learning_rate": 4.375e-05,
      "loss": 0.8343,
      "step": 8
    },
    {
      "epoch": 1.6,
      "eval_accuracy": 0.54,
      "eval_loss": 0.6882422566413879,
      "eval_runtime": 0.8343,
      "eval_samples_per_second": 119.865,
      "eval_steps_per_second": 3.596,
      "step": 8
    },
    {
      "epoch": 1.8,
      "grad_norm": 6.170377731323242,
      "learning_rate": 4.270833333333333e-05,
      "loss": 0.6825,
      "step": 9
    },
    {
      "epoch": 1.8,
      "eval_accuracy": 0.53,
      "eval_loss": 0.6919335126876831,
      "eval_runtime": 0.8402,
      "eval_samples_per_second": 119.014,
      "eval_steps_per_second": 3.57,
      "step": 9
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.945521831512451,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.7545,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.45,
      "eval_loss": 0.6997266411781311,
      "eval_runtime": 0.8398,
      "eval_samples_per_second": 119.072,
      "eval_steps_per_second": 3.572,
      "step": 10
    },
    {
      "epoch": 2.2,
      "grad_norm": 8.659540176391602,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 0.709,
      "step": 11
    },
    {
      "epoch": 2.2,
      "eval_accuracy": 0.45,
      "eval_loss": 0.7026562690734863,
      "eval_runtime": 0.8388,
      "eval_samples_per_second": 119.217,
      "eval_steps_per_second": 3.577,
      "step": 11
    },
    {
      "epoch": 2.4,
      "grad_norm": 3.4722447395324707,
      "learning_rate": 3.958333333333333e-05,
      "loss": 0.6914,
      "step": 12
    },
    {
      "epoch": 2.4,
      "eval_accuracy": 0.46,
      "eval_loss": 0.704160213470459,
      "eval_runtime": 0.839,
      "eval_samples_per_second": 119.192,
      "eval_steps_per_second": 3.576,
      "step": 12
    },
    {
      "epoch": 2.6,
      "grad_norm": 4.033767223358154,
      "learning_rate": 3.854166666666667e-05,
      "loss": 0.6999,
      "step": 13
    },
    {
      "epoch": 2.6,
      "eval_accuracy": 0.48,
      "eval_loss": 0.7015135884284973,
      "eval_runtime": 0.8381,
      "eval_samples_per_second": 119.324,
      "eval_steps_per_second": 3.58,
      "step": 13
    },
    {
      "epoch": 2.8,
      "grad_norm": 2.7851364612579346,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.6829,
      "step": 14
    },
    {
      "epoch": 2.8,
      "eval_accuracy": 0.49,
      "eval_loss": 0.7031835913658142,
      "eval_runtime": 0.839,
      "eval_samples_per_second": 119.197,
      "eval_steps_per_second": 3.576,
      "step": 14
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.5898079872131348,
      "learning_rate": 3.6458333333333336e-05,
      "loss": 0.6776,
      "step": 15
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.47,
      "eval_loss": 0.7040430307388306,
      "eval_runtime": 0.8373,
      "eval_samples_per_second": 119.43,
      "eval_steps_per_second": 3.583,
      "step": 15
    },
    {
      "epoch": 3.2,
      "grad_norm": 7.040603160858154,
      "learning_rate": 3.541666666666667e-05,
      "loss": 0.7151,
      "step": 16
    },
    {
      "epoch": 3.2,
      "eval_accuracy": 0.46,
      "eval_loss": 0.7056737542152405,
      "eval_runtime": 0.8384,
      "eval_samples_per_second": 119.274,
      "eval_steps_per_second": 3.578,
      "step": 16
    },
    {
      "epoch": 3.4,
      "grad_norm": 6.8378705978393555,
      "learning_rate": 3.4375e-05,
      "loss": 0.7186,
      "step": 17
    },
    {
      "epoch": 3.4,
      "eval_accuracy": 0.46,
      "eval_loss": 0.7082374095916748,
      "eval_runtime": 0.8394,
      "eval_samples_per_second": 119.131,
      "eval_steps_per_second": 3.574,
      "step": 17
    },
    {
      "epoch": 3.6,
      "grad_norm": 4.7442545890808105,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7058,
      "step": 18
    },
    {
      "epoch": 3.6,
      "eval_accuracy": 0.46,
      "eval_loss": 0.7107178568840027,
      "eval_runtime": 0.7888,
      "eval_samples_per_second": 126.768,
      "eval_steps_per_second": 3.803,
      "step": 18
    },
    {
      "epoch": 3.8,
      "grad_norm": 5.4023237228393555,
      "learning_rate": 3.229166666666667e-05,
      "loss": 0.7207,
      "step": 19
    },
    {
      "epoch": 3.8,
      "eval_accuracy": 0.46,
      "eval_loss": 0.7103956341743469,
      "eval_runtime": 0.8395,
      "eval_samples_per_second": 119.117,
      "eval_steps_per_second": 3.573,
      "step": 19
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.683109283447266,
      "learning_rate": 3.125e-05,
      "loss": 0.6839,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.47,
      "eval_loss": 0.7080614566802979,
      "eval_runtime": 0.8405,
      "eval_samples_per_second": 118.971,
      "eval_steps_per_second": 3.569,
      "step": 20
    },
    {
      "epoch": 4.2,
      "grad_norm": 4.991653919219971,
      "learning_rate": 3.0208333333333334e-05,
      "loss": 0.6378,
      "step": 21
    },
    {
      "epoch": 4.2,
      "eval_accuracy": 0.49,
      "eval_loss": 0.7062841653823853,
      "eval_runtime": 0.839,
      "eval_samples_per_second": 119.188,
      "eval_steps_per_second": 3.576,
      "step": 21
    },
    {
      "epoch": 4.4,
      "grad_norm": 4.332605361938477,
      "learning_rate": 2.916666666666667e-05,
      "loss": 0.7266,
      "step": 22
    },
    {
      "epoch": 4.4,
      "eval_accuracy": 0.47,
      "eval_loss": 0.7057519555091858,
      "eval_runtime": 0.8392,
      "eval_samples_per_second": 119.161,
      "eval_steps_per_second": 3.575,
      "step": 22
    },
    {
      "epoch": 4.6,
      "grad_norm": 3.1174395084381104,
      "learning_rate": 2.8125000000000003e-05,
      "loss": 0.6729,
      "step": 23
    },
    {
      "epoch": 4.6,
      "eval_accuracy": 0.46,
      "eval_loss": 0.7046825885772705,
      "eval_runtime": 0.8377,
      "eval_samples_per_second": 119.373,
      "eval_steps_per_second": 3.581,
      "step": 23
    },
    {
      "epoch": 4.8,
      "grad_norm": 3.505262613296509,
      "learning_rate": 2.7083333333333332e-05,
      "loss": 0.7189,
      "step": 24
    },
    {
      "epoch": 4.8,
      "eval_accuracy": 0.46,
      "eval_loss": 0.702241063117981,
      "eval_runtime": 0.8383,
      "eval_samples_per_second": 119.288,
      "eval_steps_per_second": 3.579,
      "step": 24
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.249929904937744,
      "learning_rate": 2.604166666666667e-05,
      "loss": 0.7092,
      "step": 25
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.46,
      "eval_loss": 0.7012988328933716,
      "eval_runtime": 0.8369,
      "eval_samples_per_second": 119.494,
      "eval_steps_per_second": 3.585,
      "step": 25
    },
    {
      "epoch": 5.2,
      "grad_norm": 2.5304999351501465,
      "learning_rate": 2.5e-05,
      "loss": 0.7145,
      "step": 26
    },
    {
      "epoch": 5.2,
      "eval_accuracy": 0.47,
      "eval_loss": 0.7005956768989563,
      "eval_runtime": 0.836,
      "eval_samples_per_second": 119.623,
      "eval_steps_per_second": 3.589,
      "step": 26
    },
    {
      "epoch": 5.4,
      "grad_norm": 2.5304205417633057,
      "learning_rate": 2.3958333333333334e-05,
      "loss": 0.6946,
      "step": 27
    },
    {
      "epoch": 5.4,
      "eval_accuracy": 0.48,
      "eval_loss": 0.7012646198272705,
      "eval_runtime": 0.8366,
      "eval_samples_per_second": 119.526,
      "eval_steps_per_second": 3.586,
      "step": 27
    },
    {
      "epoch": 5.6,
      "grad_norm": 7.720176696777344,
      "learning_rate": 2.2916666666666667e-05,
      "loss": 0.7456,
      "step": 28
    },
    {
      "epoch": 5.6,
      "eval_accuracy": 0.46,
      "eval_loss": 0.7020359635353088,
      "eval_runtime": 0.8393,
      "eval_samples_per_second": 119.141,
      "eval_steps_per_second": 3.574,
      "step": 28
    },
    {
      "epoch": 5.8,
      "grad_norm": 4.178812026977539,
      "learning_rate": 2.1875e-05,
      "loss": 0.7231,
      "step": 29
    },
    {
      "epoch": 5.8,
      "eval_accuracy": 0.47,
      "eval_loss": 0.7020019292831421,
      "eval_runtime": 0.8397,
      "eval_samples_per_second": 119.086,
      "eval_steps_per_second": 3.573,
      "step": 29
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.495377063751221,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 0.6874,
      "step": 30
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.46,
      "eval_loss": 0.7010400295257568,
      "eval_runtime": 0.7916,
      "eval_samples_per_second": 126.329,
      "eval_steps_per_second": 3.79,
      "step": 30
    },
    {
      "epoch": 6.2,
      "grad_norm": 1.7229987382888794,
      "learning_rate": 1.9791666666666665e-05,
      "loss": 0.7039,
      "step": 31
    },
    {
      "epoch": 6.2,
      "eval_accuracy": 0.45,
      "eval_loss": 0.7006199359893799,
      "eval_runtime": 0.8371,
      "eval_samples_per_second": 119.466,
      "eval_steps_per_second": 3.584,
      "step": 31
    },
    {
      "epoch": 6.4,
      "grad_norm": 4.806630611419678,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.6858,
      "step": 32
    },
    {
      "epoch": 6.4,
      "eval_accuracy": 0.45,
      "eval_loss": 0.6990869045257568,
      "eval_runtime": 0.836,
      "eval_samples_per_second": 119.617,
      "eval_steps_per_second": 3.589,
      "step": 32
    },
    {
      "epoch": 6.6,
      "grad_norm": 2.4336676597595215,
      "learning_rate": 1.7708333333333335e-05,
      "loss": 0.6571,
      "step": 33
    },
    {
      "epoch": 6.6,
      "eval_accuracy": 0.46,
      "eval_loss": 0.6985548138618469,
      "eval_runtime": 0.8383,
      "eval_samples_per_second": 119.293,
      "eval_steps_per_second": 3.579,
      "step": 33
    },
    {
      "epoch": 6.8,
      "grad_norm": 2.346224784851074,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.7069,
      "step": 34
    },
    {
      "epoch": 6.8,
      "eval_accuracy": 0.46,
      "eval_loss": 0.6970605254173279,
      "eval_runtime": 0.8399,
      "eval_samples_per_second": 119.069,
      "eval_steps_per_second": 3.572,
      "step": 34
    },
    {
      "epoch": 7.0,
      "grad_norm": 6.023119926452637,
      "learning_rate": 1.5625e-05,
      "loss": 0.6878,
      "step": 35
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.46,
      "eval_loss": 0.6974707245826721,
      "eval_runtime": 0.8356,
      "eval_samples_per_second": 119.671,
      "eval_steps_per_second": 3.59,
      "step": 35
    },
    {
      "epoch": 7.2,
      "grad_norm": 2.5812861919403076,
      "learning_rate": 1.4583333333333335e-05,
      "loss": 0.7148,
      "step": 36
    },
    {
      "epoch": 7.2,
      "eval_accuracy": 0.46,
      "eval_loss": 0.6966310143470764,
      "eval_runtime": 0.8396,
      "eval_samples_per_second": 119.101,
      "eval_steps_per_second": 3.573,
      "step": 36
    },
    {
      "epoch": 7.4,
      "grad_norm": 6.9987263679504395,
      "learning_rate": 1.3541666666666666e-05,
      "loss": 0.6821,
      "step": 37
    },
    {
      "epoch": 7.4,
      "eval_accuracy": 0.46,
      "eval_loss": 0.6957228183746338,
      "eval_runtime": 0.838,
      "eval_samples_per_second": 119.326,
      "eval_steps_per_second": 3.58,
      "step": 37
    },
    {
      "epoch": 7.6,
      "grad_norm": 4.426673889160156,
      "learning_rate": 1.25e-05,
      "loss": 0.6866,
      "step": 38
    },
    {
      "epoch": 7.6,
      "eval_accuracy": 0.46,
      "eval_loss": 0.6958692073822021,
      "eval_runtime": 0.8381,
      "eval_samples_per_second": 119.321,
      "eval_steps_per_second": 3.58,
      "step": 38
    },
    {
      "epoch": 7.8,
      "grad_norm": 1.72467839717865,
      "learning_rate": 1.1458333333333333e-05,
      "loss": 0.6441,
      "step": 39
    },
    {
      "epoch": 7.8,
      "eval_accuracy": 0.46,
      "eval_loss": 0.6971582174301147,
      "eval_runtime": 0.8397,
      "eval_samples_per_second": 119.085,
      "eval_steps_per_second": 3.573,
      "step": 39
    },
    {
      "epoch": 8.0,
      "grad_norm": 10.352705001831055,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 0.7264,
      "step": 40
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.46,
      "eval_loss": 0.6962793469429016,
      "eval_runtime": 0.8388,
      "eval_samples_per_second": 119.219,
      "eval_steps_per_second": 3.577,
      "step": 40
    },
    {
      "epoch": 8.2,
      "grad_norm": 4.645693778991699,
      "learning_rate": 9.375000000000001e-06,
      "loss": 0.7164,
      "step": 41
    },
    {
      "epoch": 8.2,
      "eval_accuracy": 0.46,
      "eval_loss": 0.695371150970459,
      "eval_runtime": 0.839,
      "eval_samples_per_second": 119.183,
      "eval_steps_per_second": 3.575,
      "step": 41
    },
    {
      "epoch": 8.4,
      "grad_norm": 7.059908390045166,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.737,
      "step": 42
    },
    {
      "epoch": 8.4,
      "eval_accuracy": 0.46,
      "eval_loss": 0.6947849988937378,
      "eval_runtime": 0.8369,
      "eval_samples_per_second": 119.483,
      "eval_steps_per_second": 3.585,
      "step": 42
    },
    {
      "epoch": 8.6,
      "grad_norm": 1.3762595653533936,
      "learning_rate": 7.2916666666666674e-06,
      "loss": 0.7173,
      "step": 43
    },
    {
      "epoch": 8.6,
      "eval_accuracy": 0.47,
      "eval_loss": 0.6942089796066284,
      "eval_runtime": 0.8392,
      "eval_samples_per_second": 119.159,
      "eval_steps_per_second": 3.575,
      "step": 43
    },
    {
      "epoch": 8.8,
      "grad_norm": 4.145285129547119,
      "learning_rate": 6.25e-06,
      "loss": 0.6933,
      "step": 44
    },
    {
      "epoch": 8.8,
      "eval_accuracy": 0.47,
      "eval_loss": 0.6938575506210327,
      "eval_runtime": 0.8362,
      "eval_samples_per_second": 119.582,
      "eval_steps_per_second": 3.587,
      "step": 44
    },
    {
      "epoch": 9.0,
      "grad_norm": 3.7309446334838867,
      "learning_rate": 5.208333333333334e-06,
      "loss": 0.7204,
      "step": 45
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.47,
      "eval_loss": 0.6939452886581421,
      "eval_runtime": 0.7873,
      "eval_samples_per_second": 127.008,
      "eval_steps_per_second": 3.81,
      "step": 45
    },
    {
      "epoch": 9.2,
      "grad_norm": 2.0658915042877197,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.707,
      "step": 46
    },
    {
      "epoch": 9.2,
      "eval_accuracy": 0.47,
      "eval_loss": 0.6938378810882568,
      "eval_runtime": 0.8363,
      "eval_samples_per_second": 119.577,
      "eval_steps_per_second": 3.587,
      "step": 46
    },
    {
      "epoch": 9.4,
      "grad_norm": 2.766176223754883,
      "learning_rate": 3.125e-06,
      "loss": 0.7343,
      "step": 47
    },
    {
      "epoch": 9.4,
      "eval_accuracy": 0.47,
      "eval_loss": 0.6941795945167542,
      "eval_runtime": 0.8392,
      "eval_samples_per_second": 119.163,
      "eval_steps_per_second": 3.575,
      "step": 47
    },
    {
      "epoch": 9.6,
      "grad_norm": 3.535402774810791,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 0.7072,
      "step": 48
    },
    {
      "epoch": 9.6,
      "eval_accuracy": 0.48,
      "eval_loss": 0.6940819621086121,
      "eval_runtime": 0.79,
      "eval_samples_per_second": 126.575,
      "eval_steps_per_second": 3.797,
      "step": 48
    },
    {
      "epoch": 9.8,
      "grad_norm": 4.9612932205200195,
      "learning_rate": 1.0416666666666667e-06,
      "loss": 0.6949,
      "step": 49
    },
    {
      "epoch": 9.8,
      "eval_accuracy": 0.47,
      "eval_loss": 0.6937304139137268,
      "eval_runtime": 0.8383,
      "eval_samples_per_second": 119.288,
      "eval_steps_per_second": 3.579,
      "step": 49
    },
    {
      "epoch": 10.0,
      "grad_norm": 3.1242637634277344,
      "learning_rate": 0.0,
      "loss": 0.6862,
      "step": 50
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.46,
      "eval_loss": 0.6938574910163879,
      "eval_runtime": 0.7902,
      "eval_samples_per_second": 126.558,
      "eval_steps_per_second": 3.797,
      "step": 50
    },
    {
      "epoch": 10.0,
      "step": 50,
      "total_flos": 24115496386560.0,
      "train_loss": 0.7265405237674714,
      "train_runtime": 165.0104,
      "train_samples_per_second": 24.241,
      "train_steps_per_second": 0.303
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 24115496386560.0,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}