{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.5087719298245617,
  "eval_steps": 2,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03508771929824561,
      "eval_accuracy": 0.6470588235294118,
      "eval_loss": 0.689453125,
      "eval_runtime": 5.7018,
      "eval_samples_per_second": 35.077,
      "eval_steps_per_second": 1.228,
      "step": 2
    },
    {
      "epoch": 0.07017543859649122,
      "eval_accuracy": 0.4461538461538462,
      "eval_loss": 0.6943359375,
      "eval_runtime": 5.7313,
      "eval_samples_per_second": 34.896,
      "eval_steps_per_second": 1.221,
      "step": 4
    },
    {
      "epoch": 0.10526315789473684,
      "eval_accuracy": 0.5855263157894737,
      "eval_loss": 0.6904296875,
      "eval_runtime": 5.6884,
      "eval_samples_per_second": 35.16,
      "eval_steps_per_second": 1.231,
      "step": 6
    },
    {
      "epoch": 0.14035087719298245,
      "eval_accuracy": 0.618421052631579,
      "eval_loss": 0.6884765625,
      "eval_runtime": 5.6745,
      "eval_samples_per_second": 35.245,
      "eval_steps_per_second": 1.234,
      "step": 8
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 1.0490341186523438,
      "learning_rate": 4.956140350877193e-06,
      "loss": 0.6847,
      "step": 10
    },
    {
      "epoch": 0.17543859649122806,
      "eval_accuracy": 0.5592105263157895,
      "eval_loss": 0.68603515625,
      "eval_runtime": 5.6946,
      "eval_samples_per_second": 35.121,
      "eval_steps_per_second": 1.229,
      "step": 10
    },
    {
      "epoch": 0.21052631578947367,
      "eval_accuracy": 0.5125,
      "eval_loss": 0.68994140625,
      "eval_runtime": 5.6918,
      "eval_samples_per_second": 35.138,
      "eval_steps_per_second": 1.23,
      "step": 12
    },
    {
      "epoch": 0.24561403508771928,
      "eval_accuracy": 0.56875,
      "eval_loss": 0.689453125,
      "eval_runtime": 5.6969,
      "eval_samples_per_second": 35.107,
      "eval_steps_per_second": 1.229,
      "step": 14
    },
    {
      "epoch": 0.2807017543859649,
      "eval_accuracy": 0.5492957746478874,
      "eval_loss": 0.6884765625,
      "eval_runtime": 5.695,
      "eval_samples_per_second": 35.119,
      "eval_steps_per_second": 1.229,
      "step": 16
    },
    {
      "epoch": 0.3157894736842105,
      "eval_accuracy": 0.50625,
      "eval_loss": 0.68798828125,
      "eval_runtime": 5.6936,
      "eval_samples_per_second": 35.127,
      "eval_steps_per_second": 1.229,
      "step": 18
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 2.6275153160095215,
      "learning_rate": 4.912280701754386e-06,
      "loss": 0.6859,
      "step": 20
    },
    {
      "epoch": 0.3508771929824561,
      "eval_accuracy": 0.32075471698113206,
      "eval_loss": 0.70068359375,
      "eval_runtime": 5.6962,
      "eval_samples_per_second": 35.111,
      "eval_steps_per_second": 1.229,
      "step": 20
    },
    {
      "epoch": 0.38596491228070173,
      "eval_accuracy": 0.551948051948052,
      "eval_loss": 0.68115234375,
      "eval_runtime": 5.6862,
      "eval_samples_per_second": 35.173,
      "eval_steps_per_second": 1.231,
      "step": 22
    },
    {
      "epoch": 0.42105263157894735,
      "eval_accuracy": 0.70625,
      "eval_loss": 0.67333984375,
      "eval_runtime": 5.6808,
      "eval_samples_per_second": 35.206,
      "eval_steps_per_second": 1.232,
      "step": 24
    },
    {
      "epoch": 0.45614035087719296,
      "eval_accuracy": 0.48125,
      "eval_loss": 0.6962890625,
      "eval_runtime": 5.6965,
      "eval_samples_per_second": 35.109,
      "eval_steps_per_second": 1.229,
      "step": 26
    },
    {
      "epoch": 0.49122807017543857,
      "eval_accuracy": 0.6794871794871795,
      "eval_loss": 0.6826171875,
      "eval_runtime": 5.6976,
      "eval_samples_per_second": 35.103,
      "eval_steps_per_second": 1.229,
      "step": 28
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 3.3578999042510986,
      "learning_rate": 4.8684210526315795e-06,
      "loss": 0.6887,
      "step": 30
    },
    {
      "epoch": 0.5263157894736842,
      "eval_accuracy": 0.60625,
      "eval_loss": 0.68408203125,
      "eval_runtime": 5.6932,
      "eval_samples_per_second": 35.13,
      "eval_steps_per_second": 1.23,
      "step": 30
    },
    {
      "epoch": 0.5614035087719298,
      "eval_accuracy": 0.46153846153846156,
      "eval_loss": 0.69873046875,
      "eval_runtime": 5.6972,
      "eval_samples_per_second": 35.105,
      "eval_steps_per_second": 1.229,
      "step": 32
    },
    {
      "epoch": 0.5964912280701754,
      "eval_accuracy": 0.5328947368421053,
      "eval_loss": 0.689453125,
      "eval_runtime": 5.6896,
      "eval_samples_per_second": 35.152,
      "eval_steps_per_second": 1.23,
      "step": 34
    },
    {
      "epoch": 0.631578947368421,
      "eval_accuracy": 0.6153846153846154,
      "eval_loss": 0.68115234375,
      "eval_runtime": 5.6939,
      "eval_samples_per_second": 35.125,
      "eval_steps_per_second": 1.229,
      "step": 36
    },
    {
      "epoch": 0.6666666666666666,
      "eval_accuracy": 0.61875,
      "eval_loss": 0.67236328125,
      "eval_runtime": 5.6947,
      "eval_samples_per_second": 35.12,
      "eval_steps_per_second": 1.229,
      "step": 38
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 6.319952487945557,
      "learning_rate": 4.824561403508772e-06,
      "loss": 0.6718,
      "step": 40
    },
    {
      "epoch": 0.7017543859649122,
      "eval_accuracy": 0.5641025641025641,
      "eval_loss": 0.66650390625,
      "eval_runtime": 5.6887,
      "eval_samples_per_second": 35.158,
      "eval_steps_per_second": 1.231,
      "step": 40
    },
    {
      "epoch": 0.7368421052631579,
      "eval_accuracy": 0.5986842105263158,
      "eval_loss": 0.681640625,
      "eval_runtime": 5.6953,
      "eval_samples_per_second": 35.117,
      "eval_steps_per_second": 1.229,
      "step": 42
    },
    {
      "epoch": 0.7719298245614035,
      "eval_accuracy": 0.5733333333333334,
      "eval_loss": 0.66455078125,
      "eval_runtime": 5.7338,
      "eval_samples_per_second": 34.881,
      "eval_steps_per_second": 1.221,
      "step": 44
    },
    {
      "epoch": 0.8070175438596491,
      "eval_accuracy": 0.5897435897435898,
      "eval_loss": 0.67724609375,
      "eval_runtime": 5.6996,
      "eval_samples_per_second": 35.09,
      "eval_steps_per_second": 1.228,
      "step": 46
    },
    {
      "epoch": 0.8421052631578947,
      "eval_accuracy": 0.475,
      "eval_loss": 0.6943359375,
      "eval_runtime": 5.6949,
      "eval_samples_per_second": 35.119,
      "eval_steps_per_second": 1.229,
      "step": 48
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 4.040582656860352,
      "learning_rate": 4.780701754385965e-06,
      "loss": 0.6911,
      "step": 50
    },
    {
      "epoch": 0.8771929824561403,
      "eval_accuracy": 0.5923566878980892,
      "eval_loss": 0.67138671875,
      "eval_runtime": 5.6787,
      "eval_samples_per_second": 35.219,
      "eval_steps_per_second": 1.233,
      "step": 50
    },
    {
      "epoch": 0.9122807017543859,
      "eval_accuracy": 0.61875,
      "eval_loss": 0.67822265625,
      "eval_runtime": 5.6958,
      "eval_samples_per_second": 35.114,
      "eval_steps_per_second": 1.229,
      "step": 52
    },
    {
      "epoch": 0.9473684210526315,
      "eval_accuracy": 0.54375,
      "eval_loss": 0.6826171875,
      "eval_runtime": 5.6934,
      "eval_samples_per_second": 35.128,
      "eval_steps_per_second": 1.229,
      "step": 54
    },
    {
      "epoch": 0.9824561403508771,
      "eval_accuracy": 0.65,
      "eval_loss": 0.66552734375,
      "eval_runtime": 5.6981,
      "eval_samples_per_second": 35.1,
      "eval_steps_per_second": 1.228,
      "step": 56
    },
    {
      "epoch": 1.0175438596491229,
      "eval_accuracy": 0.5133333333333333,
      "eval_loss": 0.681640625,
      "eval_runtime": 5.6991,
      "eval_samples_per_second": 35.093,
      "eval_steps_per_second": 1.228,
      "step": 58
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 5.511025905609131,
      "learning_rate": 4.736842105263158e-06,
      "loss": 0.6804,
      "step": 60
    },
    {
      "epoch": 1.0526315789473684,
      "eval_accuracy": 0.6025641025641025,
      "eval_loss": 0.66796875,
      "eval_runtime": 5.6894,
      "eval_samples_per_second": 35.153,
      "eval_steps_per_second": 1.23,
      "step": 60
    },
    {
      "epoch": 1.087719298245614,
      "eval_accuracy": 0.56875,
      "eval_loss": 0.68701171875,
      "eval_runtime": 5.695,
      "eval_samples_per_second": 35.118,
      "eval_steps_per_second": 1.229,
      "step": 62
    },
    {
      "epoch": 1.1228070175438596,
      "eval_accuracy": 0.5844155844155844,
      "eval_loss": 0.67626953125,
      "eval_runtime": 5.6958,
      "eval_samples_per_second": 35.114,
      "eval_steps_per_second": 1.229,
      "step": 64
    },
    {
      "epoch": 1.1578947368421053,
      "eval_accuracy": 0.7,
      "eval_loss": 0.6513671875,
      "eval_runtime": 5.6769,
      "eval_samples_per_second": 35.23,
      "eval_steps_per_second": 1.233,
      "step": 66
    },
    {
      "epoch": 1.1929824561403508,
      "eval_accuracy": 0.625,
      "eval_loss": 0.671875,
      "eval_runtime": 5.7249,
      "eval_samples_per_second": 34.935,
      "eval_steps_per_second": 1.223,
      "step": 68
    },
    {
      "epoch": 1.2280701754385965,
      "grad_norm": 12.084439277648926,
      "learning_rate": 4.692982456140351e-06,
      "loss": 0.6244,
      "step": 70
    },
    {
      "epoch": 1.2280701754385965,
      "eval_accuracy": 0.6375,
      "eval_loss": 0.642578125,
      "eval_runtime": 5.6755,
      "eval_samples_per_second": 35.239,
      "eval_steps_per_second": 1.233,
      "step": 70
    },
    {
      "epoch": 1.263157894736842,
      "eval_accuracy": 0.6907894736842105,
      "eval_loss": 0.6689453125,
      "eval_runtime": 5.6934,
      "eval_samples_per_second": 35.129,
      "eval_steps_per_second": 1.229,
      "step": 72
    },
    {
      "epoch": 1.2982456140350878,
      "eval_accuracy": 0.5192307692307693,
      "eval_loss": 0.6923828125,
      "eval_runtime": 5.7374,
      "eval_samples_per_second": 34.859,
      "eval_steps_per_second": 1.22,
      "step": 74
    },
    {
      "epoch": 1.3333333333333333,
      "eval_accuracy": 0.6014492753623188,
      "eval_loss": 0.6572265625,
      "eval_runtime": 5.6864,
      "eval_samples_per_second": 35.172,
      "eval_steps_per_second": 1.231,
      "step": 76
    },
    {
      "epoch": 1.368421052631579,
      "eval_accuracy": 0.54375,
      "eval_loss": 0.66650390625,
      "eval_runtime": 5.6958,
      "eval_samples_per_second": 35.114,
      "eval_steps_per_second": 1.229,
      "step": 78
    },
    {
      "epoch": 1.4035087719298245,
      "grad_norm": 20.080934524536133,
      "learning_rate": 4.649122807017544e-06,
      "loss": 0.646,
      "step": 80
    },
    {
      "epoch": 1.4035087719298245,
      "eval_accuracy": 0.6410256410256411,
      "eval_loss": 0.6552734375,
      "eval_runtime": 5.6943,
      "eval_samples_per_second": 35.123,
      "eval_steps_per_second": 1.229,
      "step": 80
    },
    {
      "epoch": 1.4385964912280702,
      "eval_accuracy": 0.73125,
      "eval_loss": 0.666015625,
      "eval_runtime": 5.6823,
      "eval_samples_per_second": 35.197,
      "eval_steps_per_second": 1.232,
      "step": 82
    },
    {
      "epoch": 1.4736842105263157,
      "eval_accuracy": 0.68125,
      "eval_loss": 0.642578125,
      "eval_runtime": 5.6942,
      "eval_samples_per_second": 35.123,
      "eval_steps_per_second": 1.229,
      "step": 84
    },
    {
      "epoch": 1.5087719298245614,
      "eval_accuracy": 0.61875,
      "eval_loss": 0.67041015625,
      "eval_runtime": 5.7308,
      "eval_samples_per_second": 34.899,
      "eval_steps_per_second": 1.221,
      "step": 86
    },
    {
      "epoch": 1.543859649122807,
      "eval_accuracy": 0.6217948717948718,
      "eval_loss": 0.6748046875,
      "eval_runtime": 5.6929,
      "eval_samples_per_second": 35.132,
      "eval_steps_per_second": 1.23,
      "step": 88
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 5.714459419250488,
      "learning_rate": 4.605263157894737e-06,
      "loss": 0.6822,
      "step": 90
    },
    {
      "epoch": 1.5789473684210527,
      "eval_accuracy": 0.54375,
      "eval_loss": 0.68408203125,
      "eval_runtime": 5.7252,
      "eval_samples_per_second": 34.933,
      "eval_steps_per_second": 1.223,
      "step": 90
    },
    {
      "epoch": 1.6140350877192984,
      "eval_accuracy": 0.625,
      "eval_loss": 0.68359375,
      "eval_runtime": 5.6946,
      "eval_samples_per_second": 35.121,
      "eval_steps_per_second": 1.229,
      "step": 92
    },
    {
      "epoch": 1.6491228070175439,
      "eval_accuracy": 0.4605263157894737,
      "eval_loss": 0.6953125,
      "eval_runtime": 5.7294,
      "eval_samples_per_second": 34.908,
      "eval_steps_per_second": 1.222,
      "step": 94
    },
    {
      "epoch": 1.6842105263157894,
      "eval_accuracy": 0.625,
      "eval_loss": 0.673828125,
      "eval_runtime": 5.7109,
      "eval_samples_per_second": 35.021,
      "eval_steps_per_second": 1.226,
      "step": 96
    },
    {
      "epoch": 1.719298245614035,
      "eval_accuracy": 0.66875,
      "eval_loss": 0.65869140625,
      "eval_runtime": 5.681,
      "eval_samples_per_second": 35.205,
      "eval_steps_per_second": 1.232,
      "step": 98
    },
    {
      "epoch": 1.7543859649122808,
      "grad_norm": 6.861231803894043,
      "learning_rate": 4.56140350877193e-06,
      "loss": 0.6773,
      "step": 100
    },
    {
      "epoch": 1.7543859649122808,
      "eval_accuracy": 0.60625,
      "eval_loss": 0.67529296875,
      "eval_runtime": 5.7386,
      "eval_samples_per_second": 34.852,
      "eval_steps_per_second": 1.22,
      "step": 100
    },
    {
      "epoch": 1.7894736842105263,
      "eval_accuracy": 0.5,
      "eval_loss": 0.6982421875,
      "eval_runtime": 5.7482,
      "eval_samples_per_second": 34.793,
      "eval_steps_per_second": 1.218,
      "step": 102
    },
    {
      "epoch": 1.8245614035087718,
      "eval_accuracy": 0.7066666666666667,
      "eval_loss": 0.65380859375,
      "eval_runtime": 5.6964,
      "eval_samples_per_second": 35.11,
      "eval_steps_per_second": 1.229,
      "step": 104
    },
    {
      "epoch": 1.8596491228070176,
      "eval_accuracy": 0.625,
      "eval_loss": 0.66943359375,
      "eval_runtime": 5.7164,
      "eval_samples_per_second": 34.987,
      "eval_steps_per_second": 1.225,
      "step": 106
    },
    {
      "epoch": 1.8947368421052633,
      "eval_accuracy": 0.675,
      "eval_loss": 0.66259765625,
      "eval_runtime": 5.7343,
      "eval_samples_per_second": 34.878,
      "eval_steps_per_second": 1.221,
      "step": 108
    },
    {
      "epoch": 1.9298245614035088,
      "grad_norm": 13.946830749511719,
      "learning_rate": 4.517543859649123e-06,
      "loss": 0.6682,
      "step": 110
    },
    {
      "epoch": 1.9298245614035088,
      "eval_accuracy": 0.6089743589743589,
      "eval_loss": 0.67919921875,
      "eval_runtime": 5.712,
      "eval_samples_per_second": 35.014,
      "eval_steps_per_second": 1.225,
      "step": 110
    },
    {
      "epoch": 1.9649122807017543,
      "eval_accuracy": 0.64375,
      "eval_loss": 0.67578125,
      "eval_runtime": 5.7252,
      "eval_samples_per_second": 34.933,
      "eval_steps_per_second": 1.223,
      "step": 112
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.475,
      "eval_loss": 0.6728515625,
      "eval_runtime": 5.7278,
      "eval_samples_per_second": 34.918,
      "eval_steps_per_second": 1.222,
      "step": 114
    },
    {
      "epoch": 2.0350877192982457,
      "eval_accuracy": 0.68125,
      "eval_loss": 0.65966796875,
      "eval_runtime": 5.7284,
      "eval_samples_per_second": 34.914,
      "eval_steps_per_second": 1.222,
      "step": 116
    },
    {
      "epoch": 2.0701754385964914,
      "eval_accuracy": 0.5375,
      "eval_loss": 0.6787109375,
      "eval_runtime": 5.7155,
      "eval_samples_per_second": 34.993,
      "eval_steps_per_second": 1.225,
      "step": 118
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 13.269120216369629,
      "learning_rate": 4.473684210526316e-06,
      "loss": 0.6196,
      "step": 120
    },
    {
      "epoch": 2.1052631578947367,
      "eval_accuracy": 0.6153846153846154,
      "eval_loss": 0.66455078125,
      "eval_runtime": 5.7379,
      "eval_samples_per_second": 34.856,
      "eval_steps_per_second": 1.22,
      "step": 120
    },
    {
      "epoch": 2.1403508771929824,
      "eval_accuracy": 0.5,
      "eval_loss": 0.68701171875,
      "eval_runtime": 5.7384,
      "eval_samples_per_second": 34.853,
      "eval_steps_per_second": 1.22,
      "step": 122
    },
    {
      "epoch": 2.175438596491228,
      "eval_accuracy": 0.675,
      "eval_loss": 0.65283203125,
      "eval_runtime": 5.7229,
      "eval_samples_per_second": 34.947,
      "eval_steps_per_second": 1.223,
      "step": 124
    },
    {
      "epoch": 2.2105263157894735,
      "eval_accuracy": 0.60625,
      "eval_loss": 0.6611328125,
      "eval_runtime": 5.7246,
      "eval_samples_per_second": 34.937,
      "eval_steps_per_second": 1.223,
      "step": 126
    },
    {
      "epoch": 2.245614035087719,
      "eval_accuracy": 0.525,
      "eval_loss": 0.6962890625,
      "eval_runtime": 5.7012,
      "eval_samples_per_second": 35.08,
      "eval_steps_per_second": 1.228,
      "step": 128
    },
    {
      "epoch": 2.280701754385965,
      "grad_norm": 23.41419792175293,
      "learning_rate": 4.429824561403509e-06,
      "loss": 0.6718,
      "step": 130
    },
    {
      "epoch": 2.280701754385965,
      "eval_accuracy": 0.6666666666666666,
      "eval_loss": 0.66748046875,
      "eval_runtime": 5.7123,
      "eval_samples_per_second": 35.012,
      "eval_steps_per_second": 1.225,
      "step": 130
    },
    {
      "epoch": 2.3157894736842106,
      "eval_accuracy": 0.46875,
      "eval_loss": 0.68017578125,
      "eval_runtime": 5.7172,
      "eval_samples_per_second": 34.982,
      "eval_steps_per_second": 1.224,
      "step": 132
    },
    {
      "epoch": 2.3508771929824563,
      "eval_accuracy": 0.6625,
      "eval_loss": 0.63232421875,
      "eval_runtime": 5.6968,
      "eval_samples_per_second": 35.107,
      "eval_steps_per_second": 1.229,
      "step": 134
    },
    {
      "epoch": 2.3859649122807016,
      "eval_accuracy": 0.625,
      "eval_loss": 0.65478515625,
      "eval_runtime": 5.7269,
      "eval_samples_per_second": 34.923,
      "eval_steps_per_second": 1.222,
      "step": 136
    },
    {
      "epoch": 2.4210526315789473,
      "eval_accuracy": 0.4875,
      "eval_loss": 0.6884765625,
      "eval_runtime": 5.6949,
      "eval_samples_per_second": 35.119,
      "eval_steps_per_second": 1.229,
      "step": 138
    },
    {
      "epoch": 2.456140350877193,
      "grad_norm": 16.154586791992188,
      "learning_rate": 4.385964912280702e-06,
      "loss": 0.5888,
      "step": 140
    },
    {
      "epoch": 2.456140350877193,
      "eval_accuracy": 0.5,
      "eval_loss": 0.68798828125,
      "eval_runtime": 5.7221,
      "eval_samples_per_second": 34.952,
      "eval_steps_per_second": 1.223,
      "step": 140
    },
    {
      "epoch": 2.4912280701754383,
      "eval_accuracy": 0.6666666666666666,
      "eval_loss": 0.669921875,
      "eval_runtime": 5.6953,
      "eval_samples_per_second": 35.117,
      "eval_steps_per_second": 1.229,
      "step": 142
    },
    {
      "epoch": 2.526315789473684,
      "eval_accuracy": 0.63125,
      "eval_loss": 0.66455078125,
      "eval_runtime": 5.7068,
      "eval_samples_per_second": 35.046,
      "eval_steps_per_second": 1.227,
      "step": 144
    },
    {
      "epoch": 2.56140350877193,
      "eval_accuracy": 0.725,
      "eval_loss": 0.6474609375,
      "eval_runtime": 5.7194,
      "eval_samples_per_second": 34.969,
      "eval_steps_per_second": 1.224,
      "step": 146
    },
    {
      "epoch": 2.5964912280701755,
      "eval_accuracy": 0.5128205128205128,
      "eval_loss": 0.6962890625,
      "eval_runtime": 5.6966,
      "eval_samples_per_second": 35.108,
      "eval_steps_per_second": 1.229,
      "step": 148
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 16.364059448242188,
      "learning_rate": 4.342105263157895e-06,
      "loss": 0.68,
      "step": 150
    },
    {
      "epoch": 2.6315789473684212,
      "eval_accuracy": 0.6666666666666666,
      "eval_loss": 0.6435546875,
      "eval_runtime": 5.6953,
      "eval_samples_per_second": 35.117,
      "eval_steps_per_second": 1.229,
      "step": 150
    },
    {
      "epoch": 2.6666666666666665,
      "eval_accuracy": 0.6875,
      "eval_loss": 0.63671875,
      "eval_runtime": 5.7156,
      "eval_samples_per_second": 34.992,
      "eval_steps_per_second": 1.225,
      "step": 152
    },
    {
      "epoch": 2.7017543859649122,
      "eval_accuracy": 0.6490066225165563,
      "eval_loss": 0.67041015625,
      "eval_runtime": 5.7168,
      "eval_samples_per_second": 34.985,
      "eval_steps_per_second": 1.224,
      "step": 154
    },
    {
      "epoch": 2.736842105263158,
      "eval_accuracy": 0.6125,
      "eval_loss": 0.662109375,
      "eval_runtime": 5.7331,
      "eval_samples_per_second": 34.885,
      "eval_steps_per_second": 1.221,
      "step": 156
    },
    {
      "epoch": 2.7719298245614032,
      "eval_accuracy": 0.55,
      "eval_loss": 0.68017578125,
      "eval_runtime": 5.6954,
      "eval_samples_per_second": 35.116,
      "eval_steps_per_second": 1.229,
      "step": 158
    },
    {
      "epoch": 2.807017543859649,
      "grad_norm": 13.744967460632324,
      "learning_rate": 4.298245614035088e-06,
      "loss": 0.6943,
      "step": 160
    },
    {
      "epoch": 2.807017543859649,
      "eval_accuracy": 0.7243589743589743,
      "eval_loss": 0.6650390625,
      "eval_runtime": 5.7272,
      "eval_samples_per_second": 34.921,
      "eval_steps_per_second": 1.222,
      "step": 160
    },
    {
      "epoch": 2.8421052631578947,
      "eval_accuracy": 0.63125,
      "eval_loss": 0.65380859375,
      "eval_runtime": 5.6971,
      "eval_samples_per_second": 35.106,
      "eval_steps_per_second": 1.229,
      "step": 162
    },
    {
      "epoch": 2.8771929824561404,
      "eval_accuracy": 0.525,
      "eval_loss": 0.677734375,
      "eval_runtime": 5.7301,
      "eval_samples_per_second": 34.903,
      "eval_steps_per_second": 1.222,
      "step": 164
    },
    {
      "epoch": 2.912280701754386,
      "eval_accuracy": 0.55,
      "eval_loss": 0.67333984375,
      "eval_runtime": 5.731,
      "eval_samples_per_second": 34.898,
      "eval_steps_per_second": 1.221,
      "step": 166
    },
    {
      "epoch": 2.9473684210526314,
      "eval_accuracy": 0.6153846153846154,
      "eval_loss": 0.662109375,
      "eval_runtime": 5.7213,
      "eval_samples_per_second": 34.957,
      "eval_steps_per_second": 1.224,
      "step": 168
    },
    {
      "epoch": 2.982456140350877,
      "grad_norm": 15.55439567565918,
      "learning_rate": 4.254385964912281e-06,
      "loss": 0.6839,
      "step": 170
    },
    {
      "epoch": 2.982456140350877,
      "eval_accuracy": 0.46153846153846156,
      "eval_loss": 0.6640625,
      "eval_runtime": 5.7301,
      "eval_samples_per_second": 34.904,
      "eval_steps_per_second": 1.222,
      "step": 170
    },
    {
      "epoch": 3.017543859649123,
      "eval_accuracy": 0.6858974358974359,
      "eval_loss": 0.65087890625,
      "eval_runtime": 5.7281,
      "eval_samples_per_second": 34.915,
      "eval_steps_per_second": 1.222,
      "step": 172
    },
    {
      "epoch": 3.0526315789473686,
      "eval_accuracy": 0.5897435897435898,
      "eval_loss": 0.67626953125,
      "eval_runtime": 5.6768,
      "eval_samples_per_second": 35.231,
      "eval_steps_per_second": 1.233,
      "step": 174
    },
    {
      "epoch": 3.087719298245614,
      "eval_accuracy": 0.6125,
      "eval_loss": 0.66357421875,
      "eval_runtime": 5.7366,
      "eval_samples_per_second": 34.864,
      "eval_steps_per_second": 1.22,
      "step": 176
    },
    {
      "epoch": 3.1228070175438596,
      "eval_accuracy": 0.66875,
      "eval_loss": 0.6591796875,
      "eval_runtime": 5.6951,
      "eval_samples_per_second": 35.118,
      "eval_steps_per_second": 1.229,
      "step": 178
    },
    {
      "epoch": 3.1578947368421053,
      "grad_norm": 6.636610507965088,
      "learning_rate": 4.210526315789474e-06,
      "loss": 0.637,
      "step": 180
    },
    {
      "epoch": 3.1578947368421053,
      "eval_accuracy": 0.45,
      "eval_loss": 0.69140625,
      "eval_runtime": 5.6948,
      "eval_samples_per_second": 35.12,
      "eval_steps_per_second": 1.229,
      "step": 180
    },
    {
      "epoch": 3.192982456140351,
      "eval_accuracy": 0.5192307692307693,
      "eval_loss": 0.68115234375,
      "eval_runtime": 5.7135,
      "eval_samples_per_second": 35.005,
      "eval_steps_per_second": 1.225,
      "step": 182
    },
    {
      "epoch": 3.2280701754385963,
      "eval_accuracy": 0.5,
      "eval_loss": 0.6591796875,
      "eval_runtime": 5.6984,
      "eval_samples_per_second": 35.098,
      "eval_steps_per_second": 1.228,
      "step": 184
    },
    {
      "epoch": 3.263157894736842,
      "eval_accuracy": 0.61875,
      "eval_loss": 0.66552734375,
      "eval_runtime": 5.6963,
      "eval_samples_per_second": 35.11,
      "eval_steps_per_second": 1.229,
      "step": 186
    },
    {
      "epoch": 3.2982456140350878,
      "eval_accuracy": 0.55625,
      "eval_loss": 0.6650390625,
      "eval_runtime": 5.7329,
      "eval_samples_per_second": 34.886,
      "eval_steps_per_second": 1.221,
      "step": 188
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 19.221059799194336,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.702,
      "step": 190
    },
    {
      "epoch": 3.3333333333333335,
      "eval_accuracy": 0.55,
      "eval_loss": 0.6904296875,
      "eval_runtime": 5.6985,
      "eval_samples_per_second": 35.097,
      "eval_steps_per_second": 1.228,
      "step": 190
    },
    {
      "epoch": 3.3684210526315788,
      "eval_accuracy": 0.575,
      "eval_loss": 0.6484375,
      "eval_runtime": 5.7142,
      "eval_samples_per_second": 35.001,
      "eval_steps_per_second": 1.225,
      "step": 192
    },
    {
      "epoch": 3.4035087719298245,
      "eval_accuracy": 0.55,
      "eval_loss": 0.6650390625,
      "eval_runtime": 5.697,
      "eval_samples_per_second": 35.106,
      "eval_steps_per_second": 1.229,
      "step": 194
    },
    {
      "epoch": 3.43859649122807,
      "eval_accuracy": 0.5576923076923077,
      "eval_loss": 0.64892578125,
      "eval_runtime": 5.6929,
      "eval_samples_per_second": 35.131,
      "eval_steps_per_second": 1.23,
      "step": 196
    },
    {
      "epoch": 3.473684210526316,
      "eval_accuracy": 0.5769230769230769,
      "eval_loss": 0.6611328125,
      "eval_runtime": 5.7185,
      "eval_samples_per_second": 34.974,
      "eval_steps_per_second": 1.224,
      "step": 198
    },
    {
      "epoch": 3.5087719298245617,
      "grad_norm": 2.2680198526359163e-05,
      "learning_rate": 4.12280701754386e-06,
      "loss": 0.6014,
      "step": 200
    },
    {
      "epoch": 3.5087719298245617,
      "eval_accuracy": 0.54375,
      "eval_loss": 0.67919921875,
      "eval_runtime": 5.6948,
      "eval_samples_per_second": 35.12,
      "eval_steps_per_second": 1.229,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 1140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}