{
  "best_metric": 0.7272727272727273,
  "best_model_checkpoint": "deit-base-distilled-patch16-224-hasta-85-fold3/checkpoint-2",
  "epoch": 100.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6363636363636364,
      "eval_loss": 0.8685859441757202,
      "eval_runtime": 0.1744,
      "eval_samples_per_second": 63.086,
      "eval_steps_per_second": 5.735,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 0.7871351838111877,
      "eval_runtime": 0.1717,
      "eval_samples_per_second": 64.058,
      "eval_steps_per_second": 5.823,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 0.711575448513031,
      "eval_runtime": 0.1715,
      "eval_samples_per_second": 64.153,
      "eval_steps_per_second": 5.832,
      "step": 3
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 0.7584884762763977,
      "eval_runtime": 0.1763,
      "eval_samples_per_second": 62.411,
      "eval_steps_per_second": 5.674,
      "step": 4
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 0.9216406345367432,
      "eval_runtime": 0.1744,
      "eval_samples_per_second": 63.075,
      "eval_steps_per_second": 5.734,
      "step": 5
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.0847609043121338,
      "eval_runtime": 0.1734,
      "eval_samples_per_second": 63.424,
      "eval_steps_per_second": 5.766,
      "step": 6
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.1930793523788452,
      "eval_runtime": 0.173,
      "eval_samples_per_second": 63.588,
      "eval_steps_per_second": 5.781,
      "step": 7
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.2542675733566284,
      "eval_runtime": 0.1705,
      "eval_samples_per_second": 64.521,
      "eval_steps_per_second": 5.866,
      "step": 8
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.309824824333191,
      "eval_runtime": 0.1695,
      "eval_samples_per_second": 64.889,
      "eval_steps_per_second": 5.899,
      "step": 9
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.2201060056686401,
      "learning_rate": 5e-05,
      "loss": 0.2667,
      "step": 10
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.397866129875183,
      "eval_runtime": 0.176,
      "eval_samples_per_second": 62.498,
      "eval_steps_per_second": 5.682,
      "step": 10
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.4209190607070923,
      "eval_runtime": 0.172,
      "eval_samples_per_second": 63.943,
      "eval_steps_per_second": 5.813,
      "step": 11
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.4301692247390747,
      "eval_runtime": 0.168,
      "eval_samples_per_second": 65.465,
      "eval_steps_per_second": 5.951,
      "step": 12
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.4201545715332031,
      "eval_runtime": 0.1703,
      "eval_samples_per_second": 64.584,
      "eval_steps_per_second": 5.871,
      "step": 13
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.356933355331421,
      "eval_runtime": 0.1667,
      "eval_samples_per_second": 65.987,
      "eval_steps_per_second": 5.999,
      "step": 14
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.3033267259597778,
      "eval_runtime": 0.1614,
      "eval_samples_per_second": 68.144,
      "eval_steps_per_second": 6.195,
      "step": 15
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.341384768486023,
      "eval_runtime": 0.1643,
      "eval_samples_per_second": 66.943,
      "eval_steps_per_second": 6.086,
      "step": 16
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.4311915636062622,
      "eval_runtime": 0.1661,
      "eval_samples_per_second": 66.244,
      "eval_steps_per_second": 6.022,
      "step": 17
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.6062500476837158,
      "eval_runtime": 0.1683,
      "eval_samples_per_second": 65.364,
      "eval_steps_per_second": 5.942,
      "step": 18
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.730796456336975,
      "eval_runtime": 0.1681,
      "eval_samples_per_second": 65.451,
      "eval_steps_per_second": 5.95,
      "step": 19
    },
    {
      "epoch": 20.0,
      "grad_norm": 1.3869937658309937,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.1296,
      "step": 20
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.754102349281311,
      "eval_runtime": 0.1611,
      "eval_samples_per_second": 68.287,
      "eval_steps_per_second": 6.208,
      "step": 20
    },
    {
      "epoch": 21.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.7182806730270386,
      "eval_runtime": 0.1716,
      "eval_samples_per_second": 64.091,
      "eval_steps_per_second": 5.826,
      "step": 21
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.6395237445831299,
      "eval_runtime": 0.1702,
      "eval_samples_per_second": 64.637,
      "eval_steps_per_second": 5.876,
      "step": 22
    },
    {
      "epoch": 23.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.6196506023406982,
      "eval_runtime": 0.1683,
      "eval_samples_per_second": 65.351,
      "eval_steps_per_second": 5.941,
      "step": 23
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.6524826288223267,
      "eval_runtime": 0.1675,
      "eval_samples_per_second": 65.686,
      "eval_steps_per_second": 5.971,
      "step": 24
    },
    {
      "epoch": 25.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.7182972431182861,
      "eval_runtime": 0.1737,
      "eval_samples_per_second": 63.314,
      "eval_steps_per_second": 5.756,
      "step": 25
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.7120441198349,
      "eval_runtime": 0.1687,
      "eval_samples_per_second": 65.187,
      "eval_steps_per_second": 5.926,
      "step": 26
    },
    {
      "epoch": 27.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.6747630834579468,
      "eval_runtime": 0.1698,
      "eval_samples_per_second": 64.768,
      "eval_steps_per_second": 5.888,
      "step": 27
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.5840404033660889,
      "eval_runtime": 0.1739,
      "eval_samples_per_second": 63.271,
      "eval_steps_per_second": 5.752,
      "step": 28
    },
    {
      "epoch": 29.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.5963157415390015,
      "eval_runtime": 0.1734,
      "eval_samples_per_second": 63.425,
      "eval_steps_per_second": 5.766,
      "step": 29
    },
    {
      "epoch": 30.0,
      "grad_norm": 1.0287742614746094,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.0834,
      "step": 30
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.7015838623046875,
      "eval_runtime": 0.1656,
      "eval_samples_per_second": 66.43,
      "eval_steps_per_second": 6.039,
      "step": 30
    },
    {
      "epoch": 31.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.7779998779296875,
      "eval_runtime": 0.1747,
      "eval_samples_per_second": 62.971,
      "eval_steps_per_second": 5.725,
      "step": 31
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.7943252325057983,
      "eval_runtime": 0.1693,
      "eval_samples_per_second": 64.974,
      "eval_steps_per_second": 5.907,
      "step": 32
    },
    {
      "epoch": 33.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.7993260622024536,
      "eval_runtime": 0.1669,
      "eval_samples_per_second": 65.912,
      "eval_steps_per_second": 5.992,
      "step": 33
    },
    {
      "epoch": 34.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.78725004196167,
      "eval_runtime": 0.1675,
      "eval_samples_per_second": 65.661,
      "eval_steps_per_second": 5.969,
      "step": 34
    },
    {
      "epoch": 35.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.8196253776550293,
      "eval_runtime": 0.1767,
      "eval_samples_per_second": 62.262,
      "eval_steps_per_second": 5.66,
      "step": 35
    },
    {
      "epoch": 36.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.9189971685409546,
      "eval_runtime": 0.1726,
      "eval_samples_per_second": 63.737,
      "eval_steps_per_second": 5.794,
      "step": 36
    },
    {
      "epoch": 37.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.0467422008514404,
      "eval_runtime": 0.1715,
      "eval_samples_per_second": 64.128,
      "eval_steps_per_second": 5.83,
      "step": 37
    },
    {
      "epoch": 38.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.164682626724243,
      "eval_runtime": 0.1698,
      "eval_samples_per_second": 64.765,
      "eval_steps_per_second": 5.888,
      "step": 38
    },
    {
      "epoch": 39.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2633535861968994,
      "eval_runtime": 0.1738,
      "eval_samples_per_second": 63.276,
      "eval_steps_per_second": 5.752,
      "step": 39
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.9293741583824158,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0441,
      "step": 40
    },
    {
      "epoch": 40.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.317039966583252,
      "eval_runtime": 0.1666,
      "eval_samples_per_second": 66.02,
      "eval_steps_per_second": 6.002,
      "step": 40
    },
    {
      "epoch": 41.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.3262672424316406,
      "eval_runtime": 0.1689,
      "eval_samples_per_second": 65.138,
      "eval_steps_per_second": 5.922,
      "step": 41
    },
    {
      "epoch": 42.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.299123525619507,
      "eval_runtime": 0.1744,
      "eval_samples_per_second": 63.057,
      "eval_steps_per_second": 5.732,
      "step": 42
    },
    {
      "epoch": 43.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2792396545410156,
      "eval_runtime": 0.1711,
      "eval_samples_per_second": 64.3,
      "eval_steps_per_second": 5.845,
      "step": 43
    },
    {
      "epoch": 44.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.257204532623291,
      "eval_runtime": 0.1767,
      "eval_samples_per_second": 62.267,
      "eval_steps_per_second": 5.661,
      "step": 44
    },
    {
      "epoch": 45.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.275134563446045,
      "eval_runtime": 0.1749,
      "eval_samples_per_second": 62.906,
      "eval_steps_per_second": 5.719,
      "step": 45
    },
    {
      "epoch": 46.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.3103349208831787,
      "eval_runtime": 0.1707,
      "eval_samples_per_second": 64.43,
      "eval_steps_per_second": 5.857,
      "step": 46
    },
    {
      "epoch": 47.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.33245849609375,
      "eval_runtime": 0.1696,
      "eval_samples_per_second": 64.853,
      "eval_steps_per_second": 5.896,
      "step": 47
    },
    {
      "epoch": 48.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.325917959213257,
      "eval_runtime": 0.1718,
      "eval_samples_per_second": 64.015,
      "eval_steps_per_second": 5.82,
      "step": 48
    },
    {
      "epoch": 49.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2974021434783936,
      "eval_runtime": 0.168,
      "eval_samples_per_second": 65.458,
      "eval_steps_per_second": 5.951,
      "step": 49
    },
    {
      "epoch": 50.0,
      "grad_norm": 1.730732798576355,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.0437,
      "step": 50
    },
    {
      "epoch": 50.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.231199026107788,
      "eval_runtime": 0.1697,
      "eval_samples_per_second": 64.818,
      "eval_steps_per_second": 5.893,
      "step": 50
    },
    {
      "epoch": 51.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.163764238357544,
      "eval_runtime": 0.1799,
      "eval_samples_per_second": 61.142,
      "eval_steps_per_second": 5.558,
      "step": 51
    },
    {
      "epoch": 52.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.096306562423706,
      "eval_runtime": 0.1688,
      "eval_samples_per_second": 65.16,
      "eval_steps_per_second": 5.924,
      "step": 52
    },
    {
      "epoch": 53.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.0073812007904053,
      "eval_runtime": 0.174,
      "eval_samples_per_second": 63.211,
      "eval_steps_per_second": 5.746,
      "step": 53
    },
    {
      "epoch": 54.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.9069023132324219,
      "eval_runtime": 0.1683,
      "eval_samples_per_second": 65.373,
      "eval_steps_per_second": 5.943,
      "step": 54
    },
    {
      "epoch": 55.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.8899292945861816,
      "eval_runtime": 0.1719,
      "eval_samples_per_second": 63.994,
      "eval_steps_per_second": 5.818,
      "step": 55
    },
    {
      "epoch": 56.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 1.9431856870651245,
      "eval_runtime": 0.1777,
      "eval_samples_per_second": 61.913,
      "eval_steps_per_second": 5.628,
      "step": 56
    },
    {
      "epoch": 57.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.030669927597046,
      "eval_runtime": 0.178,
      "eval_samples_per_second": 61.806,
      "eval_steps_per_second": 5.619,
      "step": 57
    },
    {
      "epoch": 58.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.1621267795562744,
      "eval_runtime": 0.1698,
      "eval_samples_per_second": 64.789,
      "eval_steps_per_second": 5.89,
      "step": 58
    },
    {
      "epoch": 59.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2469773292541504,
      "eval_runtime": 0.1711,
      "eval_samples_per_second": 64.28,
      "eval_steps_per_second": 5.844,
      "step": 59
    },
    {
      "epoch": 60.0,
      "grad_norm": 1.0086231231689453,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.04,
      "step": 60
    },
    {
      "epoch": 60.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.328124761581421,
      "eval_runtime": 0.1721,
      "eval_samples_per_second": 63.924,
      "eval_steps_per_second": 5.811,
      "step": 60
    },
    {
      "epoch": 61.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.3529090881347656,
      "eval_runtime": 0.1854,
      "eval_samples_per_second": 59.333,
      "eval_steps_per_second": 5.394,
      "step": 61
    },
    {
      "epoch": 62.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.349138021469116,
      "eval_runtime": 0.1698,
      "eval_samples_per_second": 64.782,
      "eval_steps_per_second": 5.889,
      "step": 62
    },
    {
      "epoch": 63.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.3534414768218994,
      "eval_runtime": 0.1708,
      "eval_samples_per_second": 64.397,
      "eval_steps_per_second": 5.854,
      "step": 63
    },
    {
      "epoch": 64.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.3541152477264404,
      "eval_runtime": 0.1758,
      "eval_samples_per_second": 62.568,
      "eval_steps_per_second": 5.688,
      "step": 64
    },
    {
      "epoch": 65.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.3474278450012207,
      "eval_runtime": 0.1716,
      "eval_samples_per_second": 64.121,
      "eval_steps_per_second": 5.829,
      "step": 65
    },
    {
      "epoch": 66.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.3363146781921387,
      "eval_runtime": 0.1734,
      "eval_samples_per_second": 63.453,
      "eval_steps_per_second": 5.768,
      "step": 66
    },
    {
      "epoch": 67.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.319326639175415,
      "eval_runtime": 0.1761,
      "eval_samples_per_second": 62.447,
      "eval_steps_per_second": 5.677,
      "step": 67
    },
    {
      "epoch": 68.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.314405679702759,
      "eval_runtime": 0.1299,
      "eval_samples_per_second": 84.658,
      "eval_steps_per_second": 7.696,
      "step": 68
    },
    {
      "epoch": 69.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.28474497795105,
      "eval_runtime": 0.1827,
      "eval_samples_per_second": 60.222,
      "eval_steps_per_second": 5.475,
      "step": 69
    },
    {
      "epoch": 70.0,
      "grad_norm": 0.6942837834358215,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0232,
      "step": 70
    },
    {
      "epoch": 70.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2487778663635254,
      "eval_runtime": 0.1659,
      "eval_samples_per_second": 66.314,
      "eval_steps_per_second": 6.029,
      "step": 70
    },
    {
      "epoch": 71.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.217459201812744,
      "eval_runtime": 0.1727,
      "eval_samples_per_second": 63.711,
      "eval_steps_per_second": 5.792,
      "step": 71
    },
    {
      "epoch": 72.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.189833879470825,
      "eval_runtime": 0.169,
      "eval_samples_per_second": 65.086,
      "eval_steps_per_second": 5.917,
      "step": 72
    },
    {
      "epoch": 73.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.179706335067749,
      "eval_runtime": 0.1712,
      "eval_samples_per_second": 64.246,
      "eval_steps_per_second": 5.841,
      "step": 73
    },
    {
      "epoch": 74.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.182884931564331,
      "eval_runtime": 0.173,
      "eval_samples_per_second": 63.579,
      "eval_steps_per_second": 5.78,
      "step": 74
    },
    {
      "epoch": 75.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.1805882453918457,
      "eval_runtime": 0.1767,
      "eval_samples_per_second": 62.266,
      "eval_steps_per_second": 5.661,
      "step": 75
    },
    {
      "epoch": 76.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.168536901473999,
      "eval_runtime": 0.1753,
      "eval_samples_per_second": 62.753,
      "eval_steps_per_second": 5.705,
      "step": 76
    },
    {
      "epoch": 77.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.1505448818206787,
      "eval_runtime": 0.1686,
      "eval_samples_per_second": 65.229,
      "eval_steps_per_second": 5.93,
      "step": 77
    },
    {
      "epoch": 78.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.1548378467559814,
      "eval_runtime": 0.1739,
      "eval_samples_per_second": 63.25,
      "eval_steps_per_second": 5.75,
      "step": 78
    },
    {
      "epoch": 79.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.1650230884552,
      "eval_runtime": 0.1691,
      "eval_samples_per_second": 65.031,
      "eval_steps_per_second": 5.912,
      "step": 79
    },
    {
      "epoch": 80.0,
      "grad_norm": 0.7628238797187805,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0243,
      "step": 80
    },
    {
      "epoch": 80.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.1960508823394775,
      "eval_runtime": 0.164,
      "eval_samples_per_second": 67.059,
      "eval_steps_per_second": 6.096,
      "step": 80
    },
    {
      "epoch": 81.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2283194065093994,
      "eval_runtime": 0.1744,
      "eval_samples_per_second": 63.06,
      "eval_steps_per_second": 5.733,
      "step": 81
    },
    {
      "epoch": 82.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2619211673736572,
      "eval_runtime": 0.1712,
      "eval_samples_per_second": 64.243,
      "eval_steps_per_second": 5.84,
      "step": 82
    },
    {
      "epoch": 83.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.278263807296753,
      "eval_runtime": 0.179,
      "eval_samples_per_second": 61.466,
      "eval_steps_per_second": 5.588,
      "step": 83
    },
    {
      "epoch": 84.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2795732021331787,
      "eval_runtime": 0.1715,
      "eval_samples_per_second": 64.133,
      "eval_steps_per_second": 5.83,
      "step": 84
    },
    {
      "epoch": 85.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2779977321624756,
      "eval_runtime": 0.1742,
      "eval_samples_per_second": 63.138,
      "eval_steps_per_second": 5.74,
      "step": 85
    },
    {
      "epoch": 86.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2768728733062744,
      "eval_runtime": 0.1701,
      "eval_samples_per_second": 64.658,
      "eval_steps_per_second": 5.878,
      "step": 86
    },
    {
      "epoch": 87.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.265484571456909,
      "eval_runtime": 0.1708,
      "eval_samples_per_second": 64.411,
      "eval_steps_per_second": 5.856,
      "step": 87
    },
    {
      "epoch": 88.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2583999633789062,
      "eval_runtime": 0.1707,
      "eval_samples_per_second": 64.441,
      "eval_steps_per_second": 5.858,
      "step": 88
    },
    {
      "epoch": 89.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2418525218963623,
      "eval_runtime": 0.1703,
      "eval_samples_per_second": 64.61,
      "eval_steps_per_second": 5.874,
      "step": 89
    },
    {
      "epoch": 90.0,
      "grad_norm": 0.20316258072853088,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.0301,
      "step": 90
    },
    {
      "epoch": 90.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2298619747161865,
      "eval_runtime": 0.1646,
      "eval_samples_per_second": 66.827,
      "eval_steps_per_second": 6.075,
      "step": 90
    },
    {
      "epoch": 91.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2151129245758057,
      "eval_runtime": 0.1786,
      "eval_samples_per_second": 61.585,
      "eval_steps_per_second": 5.599,
      "step": 91
    },
    {
      "epoch": 92.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2037928104400635,
      "eval_runtime": 0.1703,
      "eval_samples_per_second": 64.593,
      "eval_steps_per_second": 5.872,
      "step": 92
    },
    {
      "epoch": 93.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.1956067085266113,
      "eval_runtime": 0.1647,
      "eval_samples_per_second": 66.792,
      "eval_steps_per_second": 6.072,
      "step": 93
    },
    {
      "epoch": 94.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.1945688724517822,
      "eval_runtime": 0.1729,
      "eval_samples_per_second": 63.636,
      "eval_steps_per_second": 5.785,
      "step": 94
    },
    {
      "epoch": 95.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2012369632720947,
      "eval_runtime": 0.1761,
      "eval_samples_per_second": 62.468,
      "eval_steps_per_second": 5.679,
      "step": 95
    },
    {
      "epoch": 96.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2079222202301025,
      "eval_runtime": 0.1796,
      "eval_samples_per_second": 61.263,
      "eval_steps_per_second": 5.569,
      "step": 96
    },
    {
      "epoch": 97.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2151033878326416,
      "eval_runtime": 0.1758,
      "eval_samples_per_second": 62.582,
      "eval_steps_per_second": 5.689,
      "step": 97
    },
    {
      "epoch": 98.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2219274044036865,
      "eval_runtime": 0.1727,
      "eval_samples_per_second": 63.677,
      "eval_steps_per_second": 5.789,
      "step": 98
    },
    {
      "epoch": 99.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.226100206375122,
      "eval_runtime": 0.1736,
      "eval_samples_per_second": 63.349,
      "eval_steps_per_second": 5.759,
      "step": 99
    },
    {
      "epoch": 100.0,
      "grad_norm": 0.9465022683143616,
      "learning_rate": 0.0,
      "loss": 0.0154,
      "step": 100
    },
    {
      "epoch": 100.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 2.2285940647125244,
      "eval_runtime": 0.1765,
      "eval_samples_per_second": 62.326,
      "eval_steps_per_second": 5.666,
      "step": 100
    },
    {
      "epoch": 100.0,
      "step": 100,
      "total_flos": 4.572150213593088e+17,
      "train_loss": 0.07004501149058343,
      "train_runtime": 414.0788,
      "train_samples_per_second": 14.248,
      "train_steps_per_second": 0.241
    },
    {
      "epoch": 100.0,
      "eval_accuracy": 0.7272727272727273,
      "eval_loss": 0.7871351838111877,
      "eval_runtime": 0.2028,
      "eval_samples_per_second": 54.253,
      "eval_steps_per_second": 4.932,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "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": 4.572150213593088e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}