diff --git "a/checkpoint-1002/trainer_state.json" "b/checkpoint-1002/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-1002/trainer_state.json"
@@ -0,0 +1,6431 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 20,
+  "global_step": 1002,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 2.8321,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 3.0972,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.6421,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 2.3812,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.6574,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.407,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 3.2132,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 2.2604,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.2e-05,
+      "loss": 1.905,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.8917,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.4666666666666668e-05,
+      "loss": 1.7831,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.372,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 1.7615,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 1.2265,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2e-05,
+      "loss": 0.7593,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.1333333333333335e-05,
+      "loss": 0.8485,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.2666666666666668e-05,
+      "loss": 0.7462,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.4e-05,
+      "loss": 0.7687,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.5333333333333337e-05,
+      "loss": 0.66,
+      "step": 19
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.8335,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.6428894400596619,
+      "eval_runtime": 19.6908,
+      "eval_samples_per_second": 82.729,
+      "eval_steps_per_second": 41.39,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.8233,
+      "step": 21
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.9333333333333336e-05,
+      "loss": 0.7742,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.066666666666667e-05,
+      "loss": 0.8104,
+      "step": 23
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6492,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.698,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.466666666666667e-05,
+      "loss": 0.8286,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9258,
+      "step": 27
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.6863,
+      "step": 28
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.866666666666667e-05,
+      "loss": 0.6822,
+      "step": 29
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4e-05,
+      "loss": 0.7762,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.133333333333333e-05,
+      "loss": 0.7259,
+      "step": 31
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.266666666666667e-05,
+      "loss": 0.6832,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.7542,
+      "step": 33
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.5333333333333335e-05,
+      "loss": 0.742,
+      "step": 34
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.7404,
+      "step": 35
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7476,
+      "step": 36
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.933333333333334e-05,
+      "loss": 0.728,
+      "step": 37
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 5.0666666666666674e-05,
+      "loss": 0.7258,
+      "step": 38
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.5863,
+      "step": 39
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.6725,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.5888345837593079,
+      "eval_runtime": 19.6842,
+      "eval_samples_per_second": 82.757,
+      "eval_steps_per_second": 41.404,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.466666666666666e-05,
+      "loss": 0.672,
+      "step": 41
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.656,
+      "step": 42
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5.7333333333333336e-05,
+      "loss": 0.7206,
+      "step": 43
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5.866666666666667e-05,
+      "loss": 0.7592,
+      "step": 44
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 6e-05,
+      "loss": 0.7326,
+      "step": 45
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.133333333333334e-05,
+      "loss": 0.7992,
+      "step": 46
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.266666666666667e-05,
+      "loss": 0.5875,
+      "step": 47
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6702,
+      "step": 48
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.533333333333334e-05,
+      "loss": 0.7486,
+      "step": 49
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.5083,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.7208,
+      "step": 51
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 6.933333333333334e-05,
+      "loss": 0.8246,
+      "step": 52
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.066666666666667e-05,
+      "loss": 0.7291,
+      "step": 53
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.2e-05,
+      "loss": 0.6183,
+      "step": 54
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.7643,
+      "step": 55
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.466666666666667e-05,
+      "loss": 0.6758,
+      "step": 56
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.6e-05,
+      "loss": 0.5394,
+      "step": 57
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.733333333333333e-05,
+      "loss": 0.7475,
+      "step": 58
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 7.866666666666666e-05,
+      "loss": 0.5581,
+      "step": 59
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8e-05,
+      "loss": 0.5927,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 0.5602975487709045,
+      "eval_runtime": 19.6961,
+      "eval_samples_per_second": 82.707,
+      "eval_steps_per_second": 41.379,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8.133333333333334e-05,
+      "loss": 0.6323,
+      "step": 61
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.266666666666667e-05,
+      "loss": 0.7222,
+      "step": 62
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.4e-05,
+      "loss": 0.6957,
+      "step": 63
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.533333333333334e-05,
+      "loss": 0.4861,
+      "step": 64
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 0.635,
+      "step": 65
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.6229,
+      "step": 66
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 8.933333333333334e-05,
+      "loss": 0.5476,
+      "step": 67
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.066666666666667e-05,
+      "loss": 0.544,
+      "step": 68
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6609,
+      "step": 69
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.803,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.466666666666667e-05,
+      "loss": 0.6424,
+      "step": 71
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.6e-05,
+      "loss": 0.5638,
+      "step": 72
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.733333333333335e-05,
+      "loss": 0.6053,
+      "step": 73
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.866666666666668e-05,
+      "loss": 0.4952,
+      "step": 74
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001,
+      "loss": 0.7466,
+      "step": 75
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00010133333333333335,
+      "loss": 0.5158,
+      "step": 76
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00010266666666666666,
+      "loss": 0.7381,
+      "step": 77
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.5236,
+      "step": 78
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00010533333333333332,
+      "loss": 0.5489,
+      "step": 79
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.5847,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.5362095832824707,
+      "eval_runtime": 19.6974,
+      "eval_samples_per_second": 82.701,
+      "eval_steps_per_second": 41.376,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.5874,
+      "step": 81
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00010933333333333333,
+      "loss": 0.5987,
+      "step": 82
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011066666666666667,
+      "loss": 0.8255,
+      "step": 83
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.6952,
+      "step": 84
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 0.5358,
+      "step": 85
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011466666666666667,
+      "loss": 0.5875,
+      "step": 86
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.000116,
+      "loss": 0.5211,
+      "step": 87
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011733333333333334,
+      "loss": 0.604,
+      "step": 88
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011866666666666669,
+      "loss": 0.7087,
+      "step": 89
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00012,
+      "loss": 0.627,
+      "step": 90
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00012133333333333335,
+      "loss": 0.8013,
+      "step": 91
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00012266666666666668,
+      "loss": 0.7636,
+      "step": 92
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.000124,
+      "loss": 0.5857,
+      "step": 93
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00012533333333333334,
+      "loss": 0.5942,
+      "step": 94
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 0.6063,
+      "step": 95
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.6896,
+      "step": 96
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00012933333333333332,
+      "loss": 0.47,
+      "step": 97
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00013066666666666668,
+      "loss": 0.6455,
+      "step": 98
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.000132,
+      "loss": 0.5724,
+      "step": 99
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.5552,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.525646984577179,
+      "eval_runtime": 19.6963,
+      "eval_samples_per_second": 82.706,
+      "eval_steps_per_second": 41.378,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00013466666666666667,
+      "loss": 0.6286,
+      "step": 101
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.5828,
+      "step": 102
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013733333333333333,
+      "loss": 0.6024,
+      "step": 103
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013866666666666669,
+      "loss": 0.6578,
+      "step": 104
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00014,
+      "loss": 0.5617,
+      "step": 105
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00014133333333333334,
+      "loss": 0.6382,
+      "step": 106
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00014266666666666667,
+      "loss": 0.6114,
+      "step": 107
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000144,
+      "loss": 0.6915,
+      "step": 108
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00014533333333333333,
+      "loss": 0.5593,
+      "step": 109
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.6069,
+      "step": 110
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000148,
+      "loss": 0.4814,
+      "step": 111
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00014933333333333335,
+      "loss": 0.349,
+      "step": 112
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015066666666666668,
+      "loss": 0.4876,
+      "step": 113
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000152,
+      "loss": 0.7599,
+      "step": 114
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015333333333333334,
+      "loss": 0.5611,
+      "step": 115
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015466666666666667,
+      "loss": 0.4964,
+      "step": 116
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6322,
+      "step": 117
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015733333333333333,
+      "loss": 0.6048,
+      "step": 118
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00015866666666666668,
+      "loss": 0.4281,
+      "step": 119
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00016,
+      "loss": 0.5511,
+      "step": 120
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.5242847800254822,
+      "eval_runtime": 19.6845,
+      "eval_samples_per_second": 82.756,
+      "eval_steps_per_second": 41.403,
+      "step": 120
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00016133333333333334,
+      "loss": 0.3825,
+      "step": 121
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00016266666666666667,
+      "loss": 0.5735,
+      "step": 122
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.000164,
+      "loss": 0.5507,
+      "step": 123
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00016533333333333333,
+      "loss": 0.6579,
+      "step": 124
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6705,
+      "step": 125
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.000168,
+      "loss": 0.647,
+      "step": 126
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00016933333333333335,
+      "loss": 0.5078,
+      "step": 127
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00017066666666666668,
+      "loss": 0.6334,
+      "step": 128
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.000172,
+      "loss": 0.5245,
+      "step": 129
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.6218,
+      "step": 130
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00017466666666666667,
+      "loss": 0.5513,
+      "step": 131
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6845,
+      "step": 132
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00017733333333333335,
+      "loss": 0.6162,
+      "step": 133
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00017866666666666668,
+      "loss": 0.4964,
+      "step": 134
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00018,
+      "loss": 0.753,
+      "step": 135
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018133333333333334,
+      "loss": 0.4971,
+      "step": 136
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018266666666666667,
+      "loss": 0.4545,
+      "step": 137
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.455,
+      "step": 138
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00018533333333333333,
+      "loss": 0.5624,
+      "step": 139
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.5466,
+      "step": 140
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 0.5101627707481384,
+      "eval_runtime": 19.7076,
+      "eval_samples_per_second": 82.658,
+      "eval_steps_per_second": 41.355,
+      "step": 140
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.000188,
+      "loss": 0.5263,
+      "step": 141
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00018933333333333335,
+      "loss": 0.6072,
+      "step": 142
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019066666666666668,
+      "loss": 0.6378,
+      "step": 143
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.000192,
+      "loss": 0.5414,
+      "step": 144
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.6037,
+      "step": 145
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001946666666666667,
+      "loss": 0.4801,
+      "step": 146
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000196,
+      "loss": 0.6265,
+      "step": 147
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019733333333333335,
+      "loss": 0.6518,
+      "step": 148
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00019866666666666668,
+      "loss": 0.5443,
+      "step": 149
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002,
+      "loss": 0.5715,
+      "step": 150
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00020133333333333334,
+      "loss": 0.6174,
+      "step": 151
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002026666666666667,
+      "loss": 0.5013,
+      "step": 152
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.5018,
+      "step": 153
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00020533333333333333,
+      "loss": 0.4345,
+      "step": 154
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00020666666666666668,
+      "loss": 0.5074,
+      "step": 155
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.5118,
+      "step": 156
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00020933333333333334,
+      "loss": 0.6067,
+      "step": 157
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00021066666666666665,
+      "loss": 0.7615,
+      "step": 158
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.4524,
+      "step": 159
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.4395,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.5064823627471924,
+      "eval_runtime": 19.6784,
+      "eval_samples_per_second": 82.781,
+      "eval_steps_per_second": 41.416,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00021466666666666666,
+      "loss": 0.3767,
+      "step": 161
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.4539,
+      "step": 162
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00021733333333333335,
+      "loss": 0.553,
+      "step": 163
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00021866666666666665,
+      "loss": 0.5605,
+      "step": 164
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.5756,
+      "step": 165
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022133333333333334,
+      "loss": 0.5019,
+      "step": 166
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022266666666666667,
+      "loss": 0.6492,
+      "step": 167
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.4588,
+      "step": 168
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022533333333333335,
+      "loss": 0.465,
+      "step": 169
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.6886,
+      "step": 170
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6053,
+      "step": 171
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022933333333333334,
+      "loss": 0.5904,
+      "step": 172
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00023066666666666667,
+      "loss": 0.566,
+      "step": 173
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.000232,
+      "loss": 0.6075,
+      "step": 174
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00023333333333333336,
+      "loss": 0.5057,
+      "step": 175
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002346666666666667,
+      "loss": 0.463,
+      "step": 176
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000236,
+      "loss": 0.6253,
+      "step": 177
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00023733333333333337,
+      "loss": 0.4351,
+      "step": 178
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00023866666666666668,
+      "loss": 0.4774,
+      "step": 179
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00024,
+      "loss": 0.6854,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.49708327651023865,
+      "eval_runtime": 19.695,
+      "eval_samples_per_second": 82.711,
+      "eval_steps_per_second": 41.381,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00024133333333333336,
+      "loss": 0.6335,
+      "step": 181
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002426666666666667,
+      "loss": 0.4519,
+      "step": 182
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.000244,
+      "loss": 0.5676,
+      "step": 183
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00024533333333333335,
+      "loss": 0.5759,
+      "step": 184
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002466666666666667,
+      "loss": 0.4579,
+      "step": 185
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.000248,
+      "loss": 0.8357,
+      "step": 186
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00024933333333333334,
+      "loss": 0.5032,
+      "step": 187
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00025066666666666667,
+      "loss": 0.4588,
+      "step": 188
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.000252,
+      "loss": 0.8308,
+      "step": 189
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.4694,
+      "step": 190
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002546666666666667,
+      "loss": 0.4331,
+      "step": 191
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.4927,
+      "step": 192
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002573333333333333,
+      "loss": 0.5314,
+      "step": 193
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00025866666666666665,
+      "loss": 0.7151,
+      "step": 194
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5414,
+      "step": 195
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00026133333333333336,
+      "loss": 0.5041,
+      "step": 196
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00026266666666666664,
+      "loss": 0.7378,
+      "step": 197
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000264,
+      "loss": 0.4902,
+      "step": 198
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026533333333333335,
+      "loss": 0.5758,
+      "step": 199
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.7326,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.5149964690208435,
+      "eval_runtime": 19.7002,
+      "eval_samples_per_second": 82.69,
+      "eval_steps_per_second": 41.37,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.000268,
+      "loss": 0.7322,
+      "step": 201
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026933333333333334,
+      "loss": 0.5464,
+      "step": 202
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00027066666666666667,
+      "loss": 0.6081,
+      "step": 203
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.5572,
+      "step": 204
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00027333333333333333,
+      "loss": 0.4734,
+      "step": 205
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00027466666666666666,
+      "loss": 0.3858,
+      "step": 206
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.000276,
+      "loss": 0.5716,
+      "step": 207
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00027733333333333337,
+      "loss": 0.6245,
+      "step": 208
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002786666666666667,
+      "loss": 0.6528,
+      "step": 209
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028,
+      "loss": 0.6356,
+      "step": 210
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028133333333333336,
+      "loss": 0.5439,
+      "step": 211
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002826666666666667,
+      "loss": 0.7304,
+      "step": 212
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.000284,
+      "loss": 0.4229,
+      "step": 213
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028533333333333335,
+      "loss": 0.6272,
+      "step": 214
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002866666666666667,
+      "loss": 0.6347,
+      "step": 215
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.000288,
+      "loss": 0.5148,
+      "step": 216
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002893333333333334,
+      "loss": 0.5562,
+      "step": 217
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00029066666666666667,
+      "loss": 0.5406,
+      "step": 218
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000292,
+      "loss": 0.5403,
+      "step": 219
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8204,
+      "step": 220
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 0.5008006691932678,
+      "eval_runtime": 19.7142,
+      "eval_samples_per_second": 82.631,
+      "eval_steps_per_second": 41.341,
+      "step": 220
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002946666666666667,
+      "loss": 0.5589,
+      "step": 221
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000296,
+      "loss": 0.5268,
+      "step": 222
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002973333333333333,
+      "loss": 0.4463,
+      "step": 223
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002986666666666667,
+      "loss": 0.4867,
+      "step": 224
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.4553,
+      "step": 225
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00030133333333333336,
+      "loss": 0.673,
+      "step": 226
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003026666666666667,
+      "loss": 0.6834,
+      "step": 227
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.000304,
+      "loss": 0.6557,
+      "step": 228
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00030533333333333335,
+      "loss": 0.5877,
+      "step": 229
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.6514,
+      "step": 230
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000308,
+      "loss": 0.6256,
+      "step": 231
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00030933333333333334,
+      "loss": 0.3928,
+      "step": 232
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00031066666666666666,
+      "loss": 0.5906,
+      "step": 233
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.5967,
+      "step": 234
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003133333333333333,
+      "loss": 0.5324,
+      "step": 235
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00031466666666666665,
+      "loss": 0.4432,
+      "step": 236
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.4914,
+      "step": 237
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00031733333333333337,
+      "loss": 0.7376,
+      "step": 238
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00031866666666666664,
+      "loss": 0.5002,
+      "step": 239
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00032,
+      "loss": 0.6009,
+      "step": 240
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.4971613585948944,
+      "eval_runtime": 19.7057,
+      "eval_samples_per_second": 82.666,
+      "eval_steps_per_second": 41.359,
+      "step": 240
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00032133333333333336,
+      "loss": 0.3989,
+      "step": 241
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003226666666666667,
+      "loss": 0.5301,
+      "step": 242
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.000324,
+      "loss": 0.5951,
+      "step": 243
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00032533333333333334,
+      "loss": 0.55,
+      "step": 244
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003266666666666667,
+      "loss": 0.5858,
+      "step": 245
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000328,
+      "loss": 0.452,
+      "step": 246
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00032933333333333333,
+      "loss": 0.4798,
+      "step": 247
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00033066666666666666,
+      "loss": 0.5152,
+      "step": 248
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000332,
+      "loss": 0.4678,
+      "step": 249
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8398,
+      "step": 250
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003346666666666667,
+      "loss": 0.4644,
+      "step": 251
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000336,
+      "loss": 0.6338,
+      "step": 252
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00033733333333333337,
+      "loss": 0.6207,
+      "step": 253
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003386666666666667,
+      "loss": 0.6672,
+      "step": 254
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00034,
+      "loss": 0.6411,
+      "step": 255
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00034133333333333335,
+      "loss": 0.37,
+      "step": 256
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003426666666666667,
+      "loss": 0.3361,
+      "step": 257
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000344,
+      "loss": 0.4482,
+      "step": 258
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00034533333333333334,
+      "loss": 0.7842,
+      "step": 259
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.4471,
+      "step": 260
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 0.4944275915622711,
+      "eval_runtime": 19.6961,
+      "eval_samples_per_second": 82.707,
+      "eval_steps_per_second": 41.379,
+      "step": 260
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.000348,
+      "loss": 0.5071,
+      "step": 261
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00034933333333333333,
+      "loss": 0.5048,
+      "step": 262
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003506666666666667,
+      "loss": 0.5687,
+      "step": 263
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.5559,
+      "step": 264
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003533333333333333,
+      "loss": 0.4472,
+      "step": 265
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003546666666666667,
+      "loss": 0.4627,
+      "step": 266
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.5967,
+      "step": 267
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035733333333333336,
+      "loss": 0.5931,
+      "step": 268
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035866666666666664,
+      "loss": 0.6736,
+      "step": 269
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00036,
+      "loss": 0.5897,
+      "step": 270
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00036133333333333335,
+      "loss": 0.573,
+      "step": 271
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003626666666666667,
+      "loss": 0.4944,
+      "step": 272
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000364,
+      "loss": 0.5639,
+      "step": 273
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00036533333333333334,
+      "loss": 0.5228,
+      "step": 274
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.4963,
+      "step": 275
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.4877,
+      "step": 276
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00036933333333333333,
+      "loss": 0.5022,
+      "step": 277
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00037066666666666666,
+      "loss": 0.4956,
+      "step": 278
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.4455,
+      "step": 279
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.5934,
+      "step": 280
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.5145900249481201,
+      "eval_runtime": 19.7148,
+      "eval_samples_per_second": 82.628,
+      "eval_steps_per_second": 41.34,
+      "step": 280
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003746666666666667,
+      "loss": 0.5771,
+      "step": 281
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000376,
+      "loss": 0.7037,
+      "step": 282
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00037733333333333336,
+      "loss": 0.586,
+      "step": 283
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003786666666666667,
+      "loss": 0.6398,
+      "step": 284
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00038,
+      "loss": 0.4984,
+      "step": 285
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00038133333333333335,
+      "loss": 0.5042,
+      "step": 286
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003826666666666667,
+      "loss": 0.5879,
+      "step": 287
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.000384,
+      "loss": 0.5108,
+      "step": 288
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003853333333333334,
+      "loss": 0.4034,
+      "step": 289
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.5854,
+      "step": 290
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.000388,
+      "loss": 0.6138,
+      "step": 291
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003893333333333334,
+      "loss": 0.5932,
+      "step": 292
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003906666666666667,
+      "loss": 0.4475,
+      "step": 293
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.000392,
+      "loss": 0.615,
+      "step": 294
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003933333333333333,
+      "loss": 0.7312,
+      "step": 295
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003946666666666667,
+      "loss": 0.5778,
+      "step": 296
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.5074,
+      "step": 297
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00039733333333333336,
+      "loss": 0.5557,
+      "step": 298
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003986666666666667,
+      "loss": 0.5038,
+      "step": 299
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0004,
+      "loss": 0.6574,
+      "step": 300
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.5057099461555481,
+      "eval_runtime": 19.7067,
+      "eval_samples_per_second": 82.662,
+      "eval_steps_per_second": 41.356,
+      "step": 300
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003999979972589652,
+      "loss": 0.6309,
+      "step": 301
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00039999198907597047,
+      "loss": 0.65,
+      "step": 302
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00039998197557134424,
+      "loss": 0.4086,
+      "step": 303
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00039996795694563096,
+      "loss": 0.4373,
+      "step": 304
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003999499334795875,
+      "loss": 0.5783,
+      "step": 305
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003999279055341771,
+      "loss": 0.4066,
+      "step": 306
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003999018735505626,
+      "loss": 0.4617,
+      "step": 307
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003998718380500971,
+      "loss": 0.5894,
+      "step": 308
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00039983779963431395,
+      "loss": 0.5726,
+      "step": 309
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00039979975898491447,
+      "loss": 0.4642,
+      "step": 310
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003997577168637543,
+      "loss": 0.5851,
+      "step": 311
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00039971167411282835,
+      "loss": 0.4258,
+      "step": 312
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003996616316542537,
+      "loss": 0.3955,
+      "step": 313
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00039960759049025105,
+      "loss": 0.5344,
+      "step": 314
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00039954955170312504,
+      "loss": 0.6945,
+      "step": 315
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00039948751645524236,
+      "loss": 0.6328,
+      "step": 316
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003994214859890082,
+      "loss": 0.5978,
+      "step": 317
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00039935146162684205,
+      "loss": 0.5626,
+      "step": 318
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003992774447711503,
+      "loss": 0.4901,
+      "step": 319
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.000399199436904299,
+      "loss": 0.4566,
+      "step": 320
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.487981915473938,
+      "eval_runtime": 19.7019,
+      "eval_samples_per_second": 82.682,
+      "eval_steps_per_second": 41.366,
+      "step": 320
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003991174395885838,
+      "loss": 0.5215,
+      "step": 321
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003990314544661984,
+      "loss": 0.4068,
+      "step": 322
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00039894148325920223,
+      "loss": 0.4953,
+      "step": 323
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003988475277694856,
+      "loss": 0.5265,
+      "step": 324
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00039874958987873364,
+      "loss": 0.4939,
+      "step": 325
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00039864767154838864,
+      "loss": 0.6296,
+      "step": 326
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003985417748196108,
+      "loss": 0.7122,
+      "step": 327
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00039843190181323746,
+      "loss": 0.4771,
+      "step": 328
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00039831805472974037,
+      "loss": 0.3858,
+      "step": 329
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00039820023584918174,
+      "loss": 0.7111,
+      "step": 330
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003980784475311686,
+      "loss": 0.5284,
+      "step": 331
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00039795269221480574,
+      "loss": 0.5413,
+      "step": 332
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00039782297241864635,
+      "loss": 0.6097,
+      "step": 333
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.000397689290740642,
+      "loss": 0.4085,
+      "step": 334
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00039755164985809063,
+      "loss": 0.4514,
+      "step": 335
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00039741005252758255,
+      "loss": 0.6322,
+      "step": 336
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003972645015849457,
+      "loss": 0.3739,
+      "step": 337
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00039711499994518856,
+      "loss": 0.6645,
+      "step": 338
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00039696155060244166,
+      "loss": 0.4806,
+      "step": 339
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.000396804156629898,
+      "loss": 0.6119,
+      "step": 340
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.544212818145752,
+      "eval_runtime": 19.6967,
+      "eval_samples_per_second": 82.704,
+      "eval_steps_per_second": 41.377,
+      "step": 340
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003966428211797514,
+      "loss": 0.4978,
+      "step": 341
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00039647754748313294,
+      "loss": 0.4017,
+      "step": 342
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003963083388500469,
+      "loss": 0.5658,
+      "step": 343
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.000396135198669304,
+      "loss": 0.4991,
+      "step": 344
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00039595813040845353,
+      "loss": 0.6417,
+      "step": 345
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003957771376137144,
+      "loss": 0.3614,
+      "step": 346
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00039559222390990353,
+      "loss": 0.5736,
+      "step": 347
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00039540339300036344,
+      "loss": 0.3924,
+      "step": 348
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003952106486668884,
+      "loss": 0.5228,
+      "step": 349
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00039501399476964805,
+      "loss": 0.3474,
+      "step": 350
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00039481343524711097,
+      "loss": 0.5203,
+      "step": 351
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00039460897411596477,
+      "loss": 0.4705,
+      "step": 352
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003944006154710366,
+      "loss": 0.4839,
+      "step": 353
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003941883634852104,
+      "loss": 0.4044,
+      "step": 354
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003939722224093439,
+      "loss": 0.452,
+      "step": 355
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003937521965721831,
+      "loss": 0.3755,
+      "step": 356
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00039352829038027563,
+      "loss": 0.4767,
+      "step": 357
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003933005083178828,
+      "loss": 0.3707,
+      "step": 358
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003930688549468894,
+      "loss": 0.4981,
+      "step": 359
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003928333349067125,
+      "loss": 0.3779,
+      "step": 360
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.5540307760238647,
+      "eval_runtime": 19.6904,
+      "eval_samples_per_second": 82.731,
+      "eval_steps_per_second": 41.391,
+      "step": 360
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00039259395291420864,
+      "loss": 0.4336,
+      "step": 361
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003923507137635792,
+      "loss": 0.5584,
+      "step": 362
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003921036223262745,
+      "loss": 0.3806,
+      "step": 363
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003918526835508961,
+      "loss": 0.3281,
+      "step": 364
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003915979024630978,
+      "loss": 0.5519,
+      "step": 365
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003913392841654851,
+      "loss": 0.5945,
+      "step": 366
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003910768338375126,
+      "loss": 0.5542,
+      "step": 367
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00039081055673538095,
+      "loss": 0.5227,
+      "step": 368
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003905404581919307,
+      "loss": 0.5136,
+      "step": 369
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003902665436165364,
+      "loss": 0.5915,
+      "step": 370
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00038998881849499755,
+      "loss": 0.4481,
+      "step": 371
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003897072883894291,
+      "loss": 0.3885,
+      "step": 372
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003894219589381501,
+      "loss": 0.5203,
+      "step": 373
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003891328358555705,
+      "loss": 0.3433,
+      "step": 374
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00038883992493207693,
+      "loss": 0.5007,
+      "step": 375
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00038854323203391664,
+      "loss": 0.5168,
+      "step": 376
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00038824276310308003,
+      "loss": 0.4943,
+      "step": 377
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0003879385241571817,
+      "loss": 0.4103,
+      "step": 378
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00038763052128933985,
+      "loss": 0.4409,
+      "step": 379
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0003873187606680543,
+      "loss": 0.4431,
+      "step": 380
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 0.5375325679779053,
+      "eval_runtime": 19.6953,
+      "eval_samples_per_second": 82.71,
+      "eval_steps_per_second": 41.38,
+      "step": 380
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.000387003248537083,
+      "loss": 0.5886,
+      "step": 381
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0003866839912153168,
+      "loss": 0.3477,
+      "step": 382
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00038636099509665306,
+      "loss": 0.3956,
+      "step": 383
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0003860342666498677,
+      "loss": 0.4101,
+      "step": 384
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0003857038124184853,
+      "loss": 0.497,
+      "step": 385
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00038536963902064834,
+      "loss": 0.4663,
+      "step": 386
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0003850317531489847,
+      "loss": 0.3703,
+      "step": 387
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00038469016157047334,
+      "loss": 0.3561,
+      "step": 388
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0003843448711263089,
+      "loss": 0.5081,
+      "step": 389
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00038399588873176487,
+      "loss": 0.5834,
+      "step": 390
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00038364322137605483,
+      "loss": 0.3454,
+      "step": 391
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00038328687612219263,
+      "loss": 0.5714,
+      "step": 392
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00038292686010685093,
+      "loss": 0.4238,
+      "step": 393
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0003825631805402182,
+      "loss": 0.3918,
+      "step": 394
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0003821958447058543,
+      "loss": 0.4761,
+      "step": 395
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0003818248599605448,
+      "loss": 0.4039,
+      "step": 396
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00038145023373415326,
+      "loss": 0.4255,
+      "step": 397
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0003810719735294731,
+      "loss": 0.3922,
+      "step": 398
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00038069008692207646,
+      "loss": 0.3467,
+      "step": 399
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0003803045815601633,
+      "loss": 0.38,
+      "step": 400
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.5541014075279236,
+      "eval_runtime": 19.701,
+      "eval_samples_per_second": 82.686,
+      "eval_steps_per_second": 41.368,
+      "step": 400
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00037991546516440746,
+      "loss": 0.3734,
+      "step": 401
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0003795227455278028,
+      "loss": 0.4125,
+      "step": 402
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00037912643051550674,
+      "loss": 0.5494,
+      "step": 403
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0003787265280646825,
+      "loss": 0.4811,
+      "step": 404
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0003783230461843406,
+      "loss": 0.3422,
+      "step": 405
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00037791599295517825,
+      "loss": 0.5504,
+      "step": 406
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00037750537652941744,
+      "loss": 0.3561,
+      "step": 407
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.000377091205130642,
+      "loss": 0.4455,
+      "step": 408
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0003766734870536323,
+      "loss": 0.4416,
+      "step": 409
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0003762522306641998,
+      "loss": 0.4755,
+      "step": 410
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00037582744439901896,
+      "loss": 0.3792,
+      "step": 411
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0003753991367654587,
+      "loss": 0.3195,
+      "step": 412
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0003749673163414117,
+      "loss": 0.5866,
+      "step": 413
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0003745319917751229,
+      "loss": 0.5543,
+      "step": 414
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0003740931717850159,
+      "loss": 0.4846,
+      "step": 415
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00037365086515951874,
+      "loss": 0.4445,
+      "step": 416
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00037320508075688776,
+      "loss": 0.4562,
+      "step": 417
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00037275582750503005,
+      "loss": 0.3521,
+      "step": 418
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00037230311440132494,
+      "loss": 0.4617,
+      "step": 419
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0003718469505124434,
+      "loss": 0.4542,
+      "step": 420
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.5359145998954773,
+      "eval_runtime": 19.6805,
+      "eval_samples_per_second": 82.772,
+      "eval_steps_per_second": 41.412,
+      "step": 420
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00037138734497416684,
+      "loss": 0.5988,
+      "step": 421
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00037092430699120407,
+      "loss": 0.4067,
+      "step": 422
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0003704578458370067,
+      "loss": 0.4393,
+      "step": 423
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00036998797085358373,
+      "loss": 0.3647,
+      "step": 424
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0003695146914513142,
+      "loss": 0.4404,
+      "step": 425
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.000369038017108759,
+      "loss": 0.3784,
+      "step": 426
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0003685579573724707,
+      "loss": 0.3774,
+      "step": 427
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0003680745218568026,
+      "loss": 0.5151,
+      "step": 428
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0003675877202437163,
+      "loss": 0.4938,
+      "step": 429
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00036709756228258734,
+      "loss": 0.5074,
+      "step": 430
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0003666040577900104,
+      "loss": 0.5189,
+      "step": 431
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00036610721664960235,
+      "loss": 0.4475,
+      "step": 432
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0003656070488118047,
+      "loss": 0.5143,
+      "step": 433
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.000365103564293684,
+      "loss": 0.3831,
+      "step": 434
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0003645967731787313,
+      "loss": 0.5165,
+      "step": 435
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00036408668561666014,
+      "loss": 0.3781,
+      "step": 436
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00036357331182320344,
+      "loss": 0.3964,
+      "step": 437
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00036305666207990886,
+      "loss": 0.633,
+      "step": 438
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0003625367467339329,
+      "loss": 0.3614,
+      "step": 439
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0003620135761978333,
+      "loss": 0.5392,
+      "step": 440
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.5393971800804138,
+      "eval_runtime": 19.6671,
+      "eval_samples_per_second": 82.829,
+      "eval_steps_per_second": 41.44,
+      "step": 440
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0003614871609493614,
+      "loss": 0.4335,
+      "step": 441
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00036095751153125113,
+      "loss": 0.5452,
+      "step": 442
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0003604246385510088,
+      "loss": 0.4373,
+      "step": 443
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0003598885526807003,
+      "loss": 0.3662,
+      "step": 444
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0003593492646567372,
+      "loss": 0.3444,
+      "step": 445
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00035880678527966224,
+      "loss": 0.449,
+      "step": 446
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0003582611254139324,
+      "loss": 0.6952,
+      "step": 447
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00035771229598770174,
+      "loss": 0.5637,
+      "step": 448
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00035716030799260237,
+      "loss": 0.4937,
+      "step": 449
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0003566051724835245,
+      "loss": 0.3008,
+      "step": 450
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0003560469005783945,
+      "loss": 0.5146,
+      "step": 451
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0003554855034579532,
+      "loss": 0.3873,
+      "step": 452
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0003549209923655309,
+      "loss": 0.4848,
+      "step": 453
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00035435337860682304,
+      "loss": 0.4622,
+      "step": 454
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0003537826735496631,
+      "loss": 0.4216,
+      "step": 455
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0003532088886237956,
+      "loss": 0.4149,
+      "step": 456
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0003526320353206467,
+      "loss": 0.5213,
+      "step": 457
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00035205212519309406,
+      "loss": 0.3278,
+      "step": 458
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00035146916985523603,
+      "loss": 0.5037,
+      "step": 459
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00035088318098215805,
+      "loss": 0.2573,
+      "step": 460
+    },
+    {
+      "epoch": 1.38,
+      "eval_loss": 0.5317687392234802,
+      "eval_runtime": 19.6777,
+      "eval_samples_per_second": 82.784,
+      "eval_steps_per_second": 41.417,
+      "step": 460
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0003502941703097,
+      "loss": 0.3546,
+      "step": 461
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00034970214963422024,
+      "loss": 0.4123,
+      "step": 462
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0003491071308123598,
+      "loss": 0.4477,
+      "step": 463
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0003485091257608047,
+      "loss": 0.5281,
+      "step": 464
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00034790814645604745,
+      "loss": 0.3655,
+      "step": 465
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0003473042049341474,
+      "loss": 0.5804,
+      "step": 466
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0003466973132904892,
+      "loss": 0.5677,
+      "step": 467
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00034608748367954067,
+      "loss": 0.4017,
+      "step": 468
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00034547472831460976,
+      "loss": 0.4458,
+      "step": 469
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00034485905946759967,
+      "loss": 0.545,
+      "step": 470
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00034424048946876294,
+      "loss": 0.3223,
+      "step": 471
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0003436190307064548,
+      "loss": 0.4871,
+      "step": 472
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00034299469562688493,
+      "loss": 0.3844,
+      "step": 473
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0003423674967338681,
+      "loss": 0.4292,
+      "step": 474
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.000341737446588574,
+      "loss": 0.5881,
+      "step": 475
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0003411045578092754,
+      "loss": 0.4427,
+      "step": 476
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00034046884307109554,
+      "loss": 0.4227,
+      "step": 477
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0003398303151057543,
+      "loss": 0.3376,
+      "step": 478
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0003391889867013134,
+      "loss": 0.3996,
+      "step": 479
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00033854487070191994,
+      "loss": 0.5441,
+      "step": 480
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 0.5200814008712769,
+      "eval_runtime": 19.6972,
+      "eval_samples_per_second": 82.702,
+      "eval_steps_per_second": 41.376,
+      "step": 480
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00033789798000754927,
+      "loss": 0.5463,
+      "step": 481
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0003372483275737468,
+      "loss": 0.4824,
+      "step": 482
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0003365959264113683,
+      "loss": 0.4886,
+      "step": 483
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00033594078958631984,
+      "loss": 0.6352,
+      "step": 484
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00033528293021929526,
+      "loss": 0.513,
+      "step": 485
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00033462236148551407,
+      "loss": 0.5665,
+      "step": 486
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00033395909661445737,
+      "loss": 0.2888,
+      "step": 487
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0003332931488896029,
+      "loss": 0.5008,
+      "step": 488
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00033262453164815904,
+      "loss": 0.3498,
+      "step": 489
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0003319532582807977,
+      "loss": 0.3529,
+      "step": 490
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00033127934223138594,
+      "loss": 0.4944,
+      "step": 491
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.000330602796996717,
+      "loss": 0.3927,
+      "step": 492
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0003299236361262401,
+      "loss": 0.4016,
+      "step": 493
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00032924187322178863,
+      "loss": 0.4036,
+      "step": 494
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00032855752193730787,
+      "loss": 0.361,
+      "step": 495
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00032787059597858204,
+      "loss": 0.3037,
+      "step": 496
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.000327181109102959,
+      "loss": 0.4355,
+      "step": 497
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00032648907511907547,
+      "loss": 0.4793,
+      "step": 498
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00032579450788658,
+      "loss": 0.3863,
+      "step": 499
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0003250974213158555,
+      "loss": 0.3758,
+      "step": 500
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.5146722197532654,
+      "eval_runtime": 19.6884,
+      "eval_samples_per_second": 82.739,
+      "eval_steps_per_second": 41.395,
+      "step": 500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0003243978293677408,
+      "loss": 0.4627,
+      "step": 501
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.000323695746053251,
+      "loss": 0.6255,
+      "step": 502
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00032299118543329666,
+      "loss": 0.3893,
+      "step": 503
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00032228416161840246,
+      "loss": 0.4511,
+      "step": 504
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0003215746887684244,
+      "loss": 0.3465,
+      "step": 505
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0003208627810922665,
+      "loss": 0.3162,
+      "step": 506
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0003201484528475958,
+      "loss": 0.5037,
+      "step": 507
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00031943171834055724,
+      "loss": 0.4016,
+      "step": 508
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00031871259192548695,
+      "loss": 0.5064,
+      "step": 509
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00031799108800462464,
+      "loss": 0.3268,
+      "step": 510
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.0003172672210278254,
+      "loss": 0.4825,
+      "step": 511
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00031654100549227026,
+      "loss": 0.5051,
+      "step": 512
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0003158124559421758,
+      "loss": 0.4095,
+      "step": 513
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00031508158696850276,
+      "loss": 0.476,
+      "step": 514
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00031434841320866395,
+      "loss": 0.4871,
+      "step": 515
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00031361294934623114,
+      "loss": 0.5544,
+      "step": 516
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.000312875210110641,
+      "loss": 0.6146,
+      "step": 517
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0003121352102768998,
+      "loss": 0.3261,
+      "step": 518
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0003113929646652879,
+      "loss": 0.4999,
+      "step": 519
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0003106484881410628,
+      "loss": 0.4403,
+      "step": 520
+    },
+    {
+      "epoch": 1.56,
+      "eval_loss": 0.5133521556854248,
+      "eval_runtime": 19.6973,
+      "eval_samples_per_second": 82.702,
+      "eval_steps_per_second": 41.376,
+      "step": 520
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0003099017956141612,
+      "loss": 0.2877,
+      "step": 521
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0003091529020389009,
+      "loss": 0.4409,
+      "step": 522
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0003084018224136808,
+      "loss": 0.4555,
+      "step": 523
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0003076485717806808,
+      "loss": 0.3673,
+      "step": 524
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0003068931652255602,
+      "loss": 0.5537,
+      "step": 525
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00030613561787715636,
+      "loss": 0.4184,
+      "step": 526
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0003053759449071807,
+      "loss": 0.603,
+      "step": 527
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0003046141615299155,
+      "loss": 0.8058,
+      "step": 528
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0003038502830019092,
+      "loss": 0.6798,
+      "step": 529
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00030308432462167043,
+      "loss": 0.49,
+      "step": 530
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00030231630172936205,
+      "loss": 0.473,
+      "step": 531
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0003015462297064936,
+      "loss": 0.5267,
+      "step": 532
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00030077412397561343,
+      "loss": 0.5525,
+      "step": 533
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.3628,
+      "step": 534
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002992238732833518,
+      "loss": 0.49,
+      "step": 535
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00029844575936947696,
+      "loss": 0.3702,
+      "step": 536
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00029766567384198223,
+      "loss": 0.4078,
+      "step": 537
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00029688363232396056,
+      "loss": 0.289,
+      "step": 538
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0002960996504776783,
+      "loss": 0.5381,
+      "step": 539
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0002953137440042616,
+      "loss": 0.3308,
+      "step": 540
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 0.5289412140846252,
+      "eval_runtime": 19.6322,
+      "eval_samples_per_second": 82.976,
+      "eval_steps_per_second": 41.513,
+      "step": 540
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00029452592864338194,
+      "loss": 0.5115,
+      "step": 541
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00029373622017294076,
+      "loss": 0.4632,
+      "step": 542
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0002929446344087537,
+      "loss": 0.3159,
+      "step": 543
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0002921511872042337,
+      "loss": 0.3998,
+      "step": 544
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00029135589445007356,
+      "loss": 0.3087,
+      "step": 545
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00029055877207392753,
+      "loss": 0.3772,
+      "step": 546
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00028975983604009246,
+      "loss": 0.3606,
+      "step": 547
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00028895910234918824,
+      "loss": 0.6869,
+      "step": 548
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00028815658703783715,
+      "loss": 0.5079,
+      "step": 549
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00028735230617834255,
+      "loss": 0.5241,
+      "step": 550
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00028654627587836723,
+      "loss": 0.5162,
+      "step": 551
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00028573851228061084,
+      "loss": 0.6195,
+      "step": 552
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0002849290315624864,
+      "loss": 0.4383,
+      "step": 553
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00028411784993579635,
+      "loss": 0.4843,
+      "step": 554
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00028330498364640804,
+      "loss": 0.4263,
+      "step": 555
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0002824904489739281,
+      "loss": 0.3478,
+      "step": 556
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00028167426223137685,
+      "loss": 0.3659,
+      "step": 557
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.000280856439764861,
+      "loss": 0.4651,
+      "step": 558
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00028003699795324673,
+      "loss": 0.3436,
+      "step": 559
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002792159532078314,
+      "loss": 0.4604,
+      "step": 560
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 0.5204966068267822,
+      "eval_runtime": 19.6795,
+      "eval_samples_per_second": 82.776,
+      "eval_steps_per_second": 41.414,
+      "step": 560
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00027839332197201506,
+      "loss": 0.5602,
+      "step": 561
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.000277569120720971,
+      "loss": 0.5683,
+      "step": 562
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002767433659613159,
+      "loss": 0.5508,
+      "step": 563
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002759160742307793,
+      "loss": 0.4525,
+      "step": 564
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.000275087262097872,
+      "loss": 0.3942,
+      "step": 565
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002742569461615547,
+      "loss": 0.345,
+      "step": 566
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00027342514305090553,
+      "loss": 0.4092,
+      "step": 567
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00027259186942478654,
+      "loss": 0.3513,
+      "step": 568
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0002717571419715107,
+      "loss": 0.4873,
+      "step": 569
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.0002709209774085071,
+      "loss": 0.4367,
+      "step": 570
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00027008339248198675,
+      "loss": 0.586,
+      "step": 571
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00026924440396660656,
+      "loss": 0.4092,
+      "step": 572
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00026840402866513377,
+      "loss": 0.3139,
+      "step": 573
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.0002675622834081095,
+      "loss": 0.6028,
+      "step": 574
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.0002667191850535113,
+      "loss": 0.3964,
+      "step": 575
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00026587475048641594,
+      "loss": 0.4798,
+      "step": 576
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.000265028996618661,
+      "loss": 0.5801,
+      "step": 577
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002641819403885063,
+      "loss": 0.3239,
+      "step": 578
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00026333359876029453,
+      "loss": 0.4352,
+      "step": 579
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0002624839887241115,
+      "loss": 0.4479,
+      "step": 580
+    },
+    {
+      "epoch": 1.74,
+      "eval_loss": 0.5340219140052795,
+      "eval_runtime": 19.6682,
+      "eval_samples_per_second": 82.824,
+      "eval_steps_per_second": 41.437,
+      "step": 580
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00026163312729544615,
+      "loss": 0.3648,
+      "step": 581
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0002607810315148494,
+      "loss": 0.4979,
+      "step": 582
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00025992771844759316,
+      "loss": 0.5609,
+      "step": 583
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00025907320518332825,
+      "loss": 0.4686,
+      "step": 584
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00025821750883574257,
+      "loss": 0.2934,
+      "step": 585
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0002573606465422181,
+      "loss": 0.4577,
+      "step": 586
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0002565026354634874,
+      "loss": 0.4982,
+      "step": 587
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0002556434927832906,
+      "loss": 0.3524,
+      "step": 588
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00025478323570803053,
+      "loss": 0.4743,
+      "step": 589
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0002539218814664288,
+      "loss": 0.6607,
+      "step": 590
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0002530594473091802,
+      "loss": 0.2837,
+      "step": 591
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00025219595050860746,
+      "loss": 0.57,
+      "step": 592
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00025133140835831535,
+      "loss": 0.4833,
+      "step": 593
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00025046583817284434,
+      "loss": 0.6797,
+      "step": 594
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0002495992572873237,
+      "loss": 0.4087,
+      "step": 595
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0002487316830571244,
+      "loss": 0.4091,
+      "step": 596
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0002478631328575116,
+      "loss": 0.2776,
+      "step": 597
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0002469936240832965,
+      "loss": 0.4363,
+      "step": 598
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00024612317414848806,
+      "loss": 0.6171,
+      "step": 599
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.0002452518004859445,
+      "loss": 0.521,
+      "step": 600
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 0.5094448328018188,
+      "eval_runtime": 19.6839,
+      "eval_samples_per_second": 82.758,
+      "eval_steps_per_second": 41.404,
+      "step": 600
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00024437952054702354,
+      "loss": 0.5103,
+      "step": 601
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00024350635180123349,
+      "loss": 0.462,
+      "step": 602
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0002426323117358832,
+      "loss": 0.471,
+      "step": 603
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00024175741785573176,
+      "loss": 0.4568,
+      "step": 604
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0002408816876826378,
+      "loss": 0.4035,
+      "step": 605
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0002400051387552089,
+      "loss": 0.5365,
+      "step": 606
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00023912778862845014,
+      "loss": 0.5665,
+      "step": 607
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00023824965487341247,
+      "loss": 0.4075,
+      "step": 608
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00023737075507684102,
+      "loss": 0.4131,
+      "step": 609
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00023649110684082256,
+      "loss": 0.5442,
+      "step": 610
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00023561072778243336,
+      "loss": 0.7304,
+      "step": 611
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00023472963553338613,
+      "loss": 0.2623,
+      "step": 612
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00023384784773967674,
+      "loss": 0.3267,
+      "step": 613
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00023296538206123133,
+      "loss": 0.503,
+      "step": 614
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00023208225617155206,
+      "loss": 0.4289,
+      "step": 615
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00023119848775736358,
+      "loss": 0.4469,
+      "step": 616
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00023031409451825853,
+      "loss": 0.4354,
+      "step": 617
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00022942909416634325,
+      "loss": 0.4072,
+      "step": 618
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00022854350442588287,
+      "loss": 0.538,
+      "step": 619
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00022765734303294664,
+      "loss": 0.32,
+      "step": 620
+    },
+    {
+      "epoch": 1.86,
+      "eval_loss": 0.49946072697639465,
+      "eval_runtime": 19.6626,
+      "eval_samples_per_second": 82.848,
+      "eval_steps_per_second": 41.449,
+      "step": 620
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00022677062773505236,
+      "loss": 0.3885,
+      "step": 621
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00022588337629081106,
+      "loss": 0.3282,
+      "step": 622
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002249956064695717,
+      "loss": 0.4796,
+      "step": 623
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002241073360510646,
+      "loss": 0.3912,
+      "step": 624
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00022321858282504605,
+      "loss": 0.414,
+      "step": 625
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002223293645909416,
+      "loss": 0.3802,
+      "step": 626
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00022143969915748959,
+      "loss": 0.3726,
+      "step": 627
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00022054960434238487,
+      "loss": 0.6393,
+      "step": 628
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00021965909797192143,
+      "loss": 0.3873,
+      "step": 629
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00021876819788063588,
+      "loss": 0.3838,
+      "step": 630
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00021787692191094986,
+      "loss": 0.4525,
+      "step": 631
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00021698528791281297,
+      "loss": 0.5156,
+      "step": 632
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00021609331374334523,
+      "loss": 0.4736,
+      "step": 633
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00021520101726647922,
+      "loss": 0.4195,
+      "step": 634
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00021430841635260275,
+      "loss": 0.4194,
+      "step": 635
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0002134155288782005,
+      "loss": 0.5804,
+      "step": 636
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0002125223727254964,
+      "loss": 0.5437,
+      "step": 637
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00021162896578209517,
+      "loss": 0.3672,
+      "step": 638
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0002107353259406243,
+      "loss": 0.4619,
+      "step": 639
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00020984147109837564,
+      "loss": 0.3984,
+      "step": 640
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.48778846859931946,
+      "eval_runtime": 19.6743,
+      "eval_samples_per_second": 82.798,
+      "eval_steps_per_second": 41.425,
+      "step": 640
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00020894741915694685,
+      "loss": 0.3651,
+      "step": 641
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00020805318802188304,
+      "loss": 0.4151,
+      "step": 642
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00020715879560231811,
+      "loss": 0.3463,
+      "step": 643
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00020626425981061606,
+      "loss": 0.3934,
+      "step": 644
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00020536959856201227,
+      "loss": 0.3284,
+      "step": 645
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00020447482977425466,
+      "loss": 0.3231,
+      "step": 646
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00020357997136724487,
+      "loss": 0.5848,
+      "step": 647
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.0002026850412626795,
+      "loss": 0.4391,
+      "step": 648
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00020179005738369096,
+      "loss": 0.4436,
+      "step": 649
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0002008950376544887,
+      "loss": 0.5285,
+      "step": 650
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0002,
+      "loss": 0.4018,
+      "step": 651
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00019910496234551133,
+      "loss": 0.4176,
+      "step": 652
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.0001982099426163091,
+      "loss": 0.2915,
+      "step": 653
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00019731495873732055,
+      "loss": 0.4308,
+      "step": 654
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00019642002863275518,
+      "loss": 0.3675,
+      "step": 655
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00019552517022574541,
+      "loss": 0.3477,
+      "step": 656
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0001946304014379878,
+      "loss": 0.3578,
+      "step": 657
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.000193735740189384,
+      "loss": 0.4722,
+      "step": 658
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0001928412043976819,
+      "loss": 0.4991,
+      "step": 659
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00019194681197811704,
+      "loss": 0.3799,
+      "step": 660
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 0.4826065003871918,
+      "eval_runtime": 19.6662,
+      "eval_samples_per_second": 82.832,
+      "eval_steps_per_second": 41.442,
+      "step": 660
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.0001910525808430532,
+      "loss": 0.4474,
+      "step": 661
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00019015852890162438,
+      "loss": 0.2897,
+      "step": 662
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00018926467405937567,
+      "loss": 0.3398,
+      "step": 663
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00018837103421790485,
+      "loss": 0.4521,
+      "step": 664
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00018747762727450363,
+      "loss": 0.5863,
+      "step": 665
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0001865844711217995,
+      "loss": 0.5822,
+      "step": 666
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00018569158364739735,
+      "loss": 0.4556,
+      "step": 667
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00018479898273352082,
+      "loss": 0.3302,
+      "step": 668
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00018390668625665484,
+      "loss": 0.2136,
+      "step": 669
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.00018301471208718702,
+      "loss": 0.2006,
+      "step": 670
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.0001821230780890502,
+      "loss": 0.2273,
+      "step": 671
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.00018123180211936416,
+      "loss": 0.2134,
+      "step": 672
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.00018034090202807859,
+      "loss": 0.2726,
+      "step": 673
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0001794503956576152,
+      "loss": 0.2042,
+      "step": 674
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.00017856030084251046,
+      "loss": 0.2009,
+      "step": 675
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.00017767063540905846,
+      "loss": 0.2342,
+      "step": 676
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.00017678141717495394,
+      "loss": 0.171,
+      "step": 677
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.0001758926639489354,
+      "loss": 0.2627,
+      "step": 678
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.00017500439353042836,
+      "loss": 0.2226,
+      "step": 679
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0001741166237091889,
+      "loss": 0.1484,
+      "step": 680
+    },
+    {
+      "epoch": 2.04,
+      "eval_loss": 0.7260522842407227,
+      "eval_runtime": 19.6873,
+      "eval_samples_per_second": 82.744,
+      "eval_steps_per_second": 41.397,
+      "step": 680
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.00017322937226494774,
+      "loss": 0.1199,
+      "step": 681
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.00017234265696705343,
+      "loss": 0.1587,
+      "step": 682
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.00017145649557411715,
+      "loss": 0.2322,
+      "step": 683
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.00017057090583365677,
+      "loss": 0.2932,
+      "step": 684
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.00016968590548174152,
+      "loss": 0.1118,
+      "step": 685
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.00016880151224263646,
+      "loss": 0.1667,
+      "step": 686
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00016791774382844793,
+      "loss": 0.18,
+      "step": 687
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00016703461793876874,
+      "loss": 0.3654,
+      "step": 688
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00016615215226032333,
+      "loss": 0.1826,
+      "step": 689
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00016527036446661395,
+      "loss": 0.2155,
+      "step": 690
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.0001643892722175667,
+      "loss": 0.202,
+      "step": 691
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.0001635088931591775,
+      "loss": 0.1804,
+      "step": 692
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00016262924492315906,
+      "loss": 0.3135,
+      "step": 693
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.00016175034512658752,
+      "loss": 0.4199,
+      "step": 694
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.00016087221137154996,
+      "loss": 0.229,
+      "step": 695
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.00015999486124479114,
+      "loss": 0.2259,
+      "step": 696
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00015911831231736222,
+      "loss": 0.2246,
+      "step": 697
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00015824258214426832,
+      "loss": 0.2162,
+      "step": 698
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00015736768826411684,
+      "loss": 0.2089,
+      "step": 699
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.00015649364819876656,
+      "loss": 0.3305,
+      "step": 700
+    },
+    {
+      "epoch": 2.1,
+      "eval_loss": 0.6187013387680054,
+      "eval_runtime": 19.6765,
+      "eval_samples_per_second": 82.789,
+      "eval_steps_per_second": 41.42,
+      "step": 700
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.00015562047945297654,
+      "loss": 0.1267,
+      "step": 701
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.0001547481995140556,
+      "loss": 0.1172,
+      "step": 702
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.00015387682585151196,
+      "loss": 0.1527,
+      "step": 703
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00015300637591670357,
+      "loss": 0.2422,
+      "step": 704
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00015213686714248852,
+      "loss": 0.1521,
+      "step": 705
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00015126831694287565,
+      "loss": 0.1898,
+      "step": 706
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00015040074271267632,
+      "loss": 0.2331,
+      "step": 707
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00014953416182715565,
+      "loss": 0.1758,
+      "step": 708
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00014866859164168464,
+      "loss": 0.1554,
+      "step": 709
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0001478040494913926,
+      "loss": 0.3777,
+      "step": 710
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.00014694055269081987,
+      "loss": 0.1897,
+      "step": 711
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.00014607811853357128,
+      "loss": 0.3242,
+      "step": 712
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.00014521676429196952,
+      "loss": 0.1458,
+      "step": 713
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00014435650721670947,
+      "loss": 0.1844,
+      "step": 714
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.0001434973645365126,
+      "loss": 0.187,
+      "step": 715
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00014263935345778202,
+      "loss": 0.1732,
+      "step": 716
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.00014178249116425742,
+      "loss": 0.2765,
+      "step": 717
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.0001409267948166718,
+      "loss": 0.2109,
+      "step": 718
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.00014007228155240694,
+      "loss": 0.1495,
+      "step": 719
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00013921896848515065,
+      "loss": 0.1477,
+      "step": 720
+    },
+    {
+      "epoch": 2.16,
+      "eval_loss": 0.5499276518821716,
+      "eval_runtime": 19.6936,
+      "eval_samples_per_second": 82.717,
+      "eval_steps_per_second": 41.384,
+      "step": 720
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00013836687270455387,
+      "loss": 0.1599,
+      "step": 721
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.0001375160112758885,
+      "loss": 0.1666,
+      "step": 722
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00013666640123970555,
+      "loss": 0.151,
+      "step": 723
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.0001358180596114937,
+      "loss": 0.2861,
+      "step": 724
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.000134971003381339,
+      "loss": 0.2307,
+      "step": 725
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.0001341252495135841,
+      "loss": 0.3584,
+      "step": 726
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.00013328081494648873,
+      "loss": 0.1871,
+      "step": 727
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.0001324377165918906,
+      "loss": 0.1586,
+      "step": 728
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.00013159597133486628,
+      "loss": 0.1594,
+      "step": 729
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.00013075559603339354,
+      "loss": 0.2144,
+      "step": 730
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.0001299166075180133,
+      "loss": 0.155,
+      "step": 731
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.00012907902259149287,
+      "loss": 0.1883,
+      "step": 732
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.0001282428580284894,
+      "loss": 0.2574,
+      "step": 733
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.0001274081305752135,
+      "loss": 0.3116,
+      "step": 734
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.0001265748569490945,
+      "loss": 0.2007,
+      "step": 735
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.00012574305383844528,
+      "loss": 0.0899,
+      "step": 736
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.00012491273790212804,
+      "loss": 0.1351,
+      "step": 737
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.00012408392576922073,
+      "loss": 0.141,
+      "step": 738
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.00012325663403868405,
+      "loss": 0.2153,
+      "step": 739
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.00012243087927902904,
+      "loss": 0.176,
+      "step": 740
+    },
+    {
+      "epoch": 2.22,
+      "eval_loss": 0.5796327590942383,
+      "eval_runtime": 19.6716,
+      "eval_samples_per_second": 82.81,
+      "eval_steps_per_second": 41.43,
+      "step": 740
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.00012160667802798502,
+      "loss": 0.2229,
+      "step": 741
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.00012078404679216864,
+      "loss": 0.2329,
+      "step": 742
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.00011996300204675329,
+      "loss": 0.1224,
+      "step": 743
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.00011914356023513904,
+      "loss": 0.1455,
+      "step": 744
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.00011832573776862319,
+      "loss": 0.2476,
+      "step": 745
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.00011750955102607193,
+      "loss": 0.2597,
+      "step": 746
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.00011669501635359213,
+      "loss": 0.2033,
+      "step": 747
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.00011588215006420372,
+      "loss": 0.1607,
+      "step": 748
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.0001150709684375137,
+      "loss": 0.2667,
+      "step": 749
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00011426148771938914,
+      "loss": 0.165,
+      "step": 750
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00011345372412163276,
+      "loss": 0.1581,
+      "step": 751
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00011264769382165747,
+      "loss": 0.2953,
+      "step": 752
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.0001118434129621628,
+      "loss": 0.1485,
+      "step": 753
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0001110408976508118,
+      "loss": 0.2135,
+      "step": 754
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.00011024016395990757,
+      "loss": 0.2706,
+      "step": 755
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.00010944122792607259,
+      "loss": 0.2308,
+      "step": 756
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00010864410554992654,
+      "loss": 0.3024,
+      "step": 757
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00010784881279576635,
+      "loss": 0.2425,
+      "step": 758
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00010705536559124629,
+      "loss": 0.1998,
+      "step": 759
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00010626377982705929,
+      "loss": 0.1892,
+      "step": 760
+    },
+    {
+      "epoch": 2.28,
+      "eval_loss": 0.571674108505249,
+      "eval_runtime": 19.7173,
+      "eval_samples_per_second": 82.618,
+      "eval_steps_per_second": 41.334,
+      "step": 760
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00010547407135661815,
+      "loss": 0.1864,
+      "step": 761
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00010468625599573842,
+      "loss": 0.1869,
+      "step": 762
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00010390034952232178,
+      "loss": 0.254,
+      "step": 763
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.00010311636767603951,
+      "loss": 0.1409,
+      "step": 764
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.00010233432615801786,
+      "loss": 0.1688,
+      "step": 765
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.00010155424063052306,
+      "loss": 0.2964,
+      "step": 766
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.00010077612671664827,
+      "loss": 0.1832,
+      "step": 767
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.00010000000000000005,
+      "loss": 0.2116,
+      "step": 768
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 9.922587602438655e-05,
+      "loss": 0.1907,
+      "step": 769
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 9.845377029350648e-05,
+      "loss": 0.3456,
+      "step": 770
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 9.768369827063804e-05,
+      "loss": 0.1433,
+      "step": 771
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 9.691567537832964e-05,
+      "loss": 0.2685,
+      "step": 772
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 9.614971699809081e-05,
+      "loss": 0.2576,
+      "step": 773
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 9.538583847008451e-05,
+      "loss": 0.1973,
+      "step": 774
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 9.462405509281938e-05,
+      "loss": 0.113,
+      "step": 775
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 9.386438212284372e-05,
+      "loss": 0.1721,
+      "step": 776
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 9.310683477443977e-05,
+      "loss": 0.3922,
+      "step": 777
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 9.235142821931928e-05,
+      "loss": 0.2183,
+      "step": 778
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 9.159817758631924e-05,
+      "loss": 0.1859,
+      "step": 779
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 9.084709796109906e-05,
+      "loss": 0.1921,
+      "step": 780
+    },
+    {
+      "epoch": 2.34,
+      "eval_loss": 0.5415823459625244,
+      "eval_runtime": 19.7119,
+      "eval_samples_per_second": 82.64,
+      "eval_steps_per_second": 41.346,
+      "step": 780
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 9.00982043858388e-05,
+      "loss": 0.2555,
+      "step": 781
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.935151185893728e-05,
+      "loss": 0.2808,
+      "step": 782
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.860703533471218e-05,
+      "loss": 0.2005,
+      "step": 783
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.786478972310021e-05,
+      "loss": 0.2596,
+      "step": 784
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.712478988935904e-05,
+      "loss": 0.1845,
+      "step": 785
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.638705065376887e-05,
+      "loss": 0.2737,
+      "step": 786
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.565158679133605e-05,
+      "loss": 0.3642,
+      "step": 787
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.491841303149728e-05,
+      "loss": 0.4627,
+      "step": 788
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.418754405782424e-05,
+      "loss": 0.179,
+      "step": 789
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.345899450772976e-05,
+      "loss": 0.2197,
+      "step": 790
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.27327789721746e-05,
+      "loss": 0.1631,
+      "step": 791
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.200891199537548e-05,
+      "loss": 0.2128,
+      "step": 792
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.128740807451311e-05,
+      "loss": 0.1702,
+      "step": 793
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 8.056828165944282e-05,
+      "loss": 0.3395,
+      "step": 794
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 7.98515471524042e-05,
+      "loss": 0.2628,
+      "step": 795
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 7.913721890773353e-05,
+      "loss": 0.1448,
+      "step": 796
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 7.842531123157561e-05,
+      "loss": 0.2338,
+      "step": 797
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 7.771583838159755e-05,
+      "loss": 0.3561,
+      "step": 798
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 7.700881456670341e-05,
+      "loss": 0.2129,
+      "step": 799
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 7.630425394674903e-05,
+      "loss": 0.1366,
+      "step": 800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.5865552425384521,
+      "eval_runtime": 19.7103,
+      "eval_samples_per_second": 82.647,
+      "eval_steps_per_second": 41.349,
+      "step": 800
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 7.560217063225923e-05,
+      "loss": 0.2126,
+      "step": 801
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 7.49025786841445e-05,
+      "loss": 0.2242,
+      "step": 802
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 7.420549211342005e-05,
+      "loss": 0.2595,
+      "step": 803
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 7.351092488092457e-05,
+      "loss": 0.251,
+      "step": 804
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 7.281889089704106e-05,
+      "loss": 0.1774,
+      "step": 805
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 7.212940402141807e-05,
+      "loss": 0.1707,
+      "step": 806
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 7.144247806269213e-05,
+      "loss": 0.1254,
+      "step": 807
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 7.075812677821145e-05,
+      "loss": 0.1843,
+      "step": 808
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 7.007636387375987e-05,
+      "loss": 0.15,
+      "step": 809
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 6.939720300328303e-05,
+      "loss": 0.2446,
+      "step": 810
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 6.872065776861412e-05,
+      "loss": 0.2122,
+      "step": 811
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 6.804674171920238e-05,
+      "loss": 0.157,
+      "step": 812
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 6.7375468351841e-05,
+      "loss": 0.1122,
+      "step": 813
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 6.670685111039709e-05,
+      "loss": 0.2749,
+      "step": 814
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 6.604090338554268e-05,
+      "loss": 0.1298,
+      "step": 815
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 6.537763851448593e-05,
+      "loss": 0.2973,
+      "step": 816
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 6.471706978070483e-05,
+      "loss": 0.3933,
+      "step": 817
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 6.405921041368018e-05,
+      "loss": 0.1181,
+      "step": 818
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 6.340407358863168e-05,
+      "loss": 0.1893,
+      "step": 819
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 6.27516724262533e-05,
+      "loss": 0.1726,
+      "step": 820
+    },
+    {
+      "epoch": 2.46,
+      "eval_loss": 0.5562059283256531,
+      "eval_runtime": 19.7275,
+      "eval_samples_per_second": 82.575,
+      "eval_steps_per_second": 41.313,
+      "step": 820
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 6.210201999245086e-05,
+      "loss": 0.2613,
+      "step": 821
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 6.145512929808012e-05,
+      "loss": 0.1647,
+      "step": 822
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 6.081101329868664e-05,
+      "loss": 0.2425,
+      "step": 823
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 6.016968489424573e-05,
+      "loss": 0.2105,
+      "step": 824
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 5.95311569289045e-05,
+      "loss": 0.1793,
+      "step": 825
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 5.889544219072465e-05,
+      "loss": 0.2819,
+      "step": 826
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 5.826255341142601e-05,
+      "loss": 0.3084,
+      "step": 827
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 5.763250326613192e-05,
+      "loss": 0.1756,
+      "step": 828
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 5.7005304373115085e-05,
+      "loss": 0.207,
+      "step": 829
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5.6380969293545214e-05,
+      "loss": 0.1826,
+      "step": 830
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5.575951053123711e-05,
+      "loss": 0.1455,
+      "step": 831
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5.514094053240035e-05,
+      "loss": 0.187,
+      "step": 832
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5.4525271685390254e-05,
+      "loss": 0.3161,
+      "step": 833
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 5.391251632045939e-05,
+      "loss": 0.1973,
+      "step": 834
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 5.330268670951091e-05,
+      "loss": 0.1946,
+      "step": 835
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 5.269579506585258e-05,
+      "loss": 0.1453,
+      "step": 836
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 5.2091853543952605e-05,
+      "loss": 0.252,
+      "step": 837
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 5.149087423919541e-05,
+      "loss": 0.1989,
+      "step": 838
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 5.089286918764031e-05,
+      "loss": 0.2149,
+      "step": 839
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 5.029785036577976e-05,
+      "loss": 0.1264,
+      "step": 840
+    },
+    {
+      "epoch": 2.51,
+      "eval_loss": 0.5621287822723389,
+      "eval_runtime": 19.7042,
+      "eval_samples_per_second": 82.673,
+      "eval_steps_per_second": 41.362,
+      "step": 840
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 4.97058296903e-05,
+      "loss": 0.1977,
+      "step": 841
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 4.911681901784197e-05,
+      "loss": 0.2018,
+      "step": 842
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 4.853083014476403e-05,
+      "loss": 0.1708,
+      "step": 843
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.7947874806905965e-05,
+      "loss": 0.2215,
+      "step": 844
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.736796467935336e-05,
+      "loss": 0.2424,
+      "step": 845
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.679111137620442e-05,
+      "loss": 0.2005,
+      "step": 846
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 4.621732645033687e-05,
+      "loss": 0.1336,
+      "step": 847
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 4.564662139317699e-05,
+      "loss": 0.1719,
+      "step": 848
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 4.5079007634469107e-05,
+      "loss": 0.2149,
+      "step": 849
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 4.451449654204685e-05,
+      "loss": 0.2564,
+      "step": 850
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 4.39530994216055e-05,
+      "loss": 0.1923,
+      "step": 851
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 4.339482751647557e-05,
+      "loss": 0.1559,
+      "step": 852
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 4.2839692007397634e-05,
+      "loss": 0.4432,
+      "step": 853
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.2287704012298243e-05,
+      "loss": 0.3719,
+      "step": 854
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.173887458606767e-05,
+      "loss": 0.1857,
+      "step": 855
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.119321472033779e-05,
+      "loss": 0.1364,
+      "step": 856
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.065073534326282e-05,
+      "loss": 0.1693,
+      "step": 857
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.011144731929981e-05,
+      "loss": 0.2064,
+      "step": 858
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 3.9575361448991234e-05,
+      "loss": 0.1749,
+      "step": 859
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 3.904248846874894e-05,
+      "loss": 0.2054,
+      "step": 860
+    },
+    {
+      "epoch": 2.57,
+      "eval_loss": 0.5677914023399353,
+      "eval_runtime": 19.7349,
+      "eval_samples_per_second": 82.544,
+      "eval_steps_per_second": 41.297,
+      "step": 860
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 3.8512839050638626e-05,
+      "loss": 0.1736,
+      "step": 861
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 3.7986423802166705e-05,
+      "loss": 0.1988,
+      "step": 862
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 3.7463253266067146e-05,
+      "loss": 0.1911,
+      "step": 863
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 3.694333792009115e-05,
+      "loss": 0.2259,
+      "step": 864
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 3.6426688176796595e-05,
+      "loss": 0.2468,
+      "step": 865
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 3.591331438333994e-05,
+      "loss": 0.2561,
+      "step": 866
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 3.540322682126873e-05,
+      "loss": 0.1137,
+      "step": 867
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 3.4896435706315997e-05,
+      "loss": 0.1373,
+      "step": 868
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 3.43929511881953e-05,
+      "loss": 0.2326,
+      "step": 869
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 3.389278335039767e-05,
+      "loss": 0.1576,
+      "step": 870
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 3.33959422099897e-05,
+      "loss": 0.1468,
+      "step": 871
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 3.290243771741275e-05,
+      "loss": 0.1846,
+      "step": 872
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 3.241227975628378e-05,
+      "loss": 0.2852,
+      "step": 873
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 3.1925478143197416e-05,
+      "loss": 0.1774,
+      "step": 874
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 3.144204262752937e-05,
+      "loss": 0.2,
+      "step": 875
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 3.0961982891241084e-05,
+      "loss": 0.1807,
+      "step": 876
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 3.0485308548685788e-05,
+      "loss": 0.3302,
+      "step": 877
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 3.0012029146416275e-05,
+      "loss": 0.1752,
+      "step": 878
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 2.9542154162993307e-05,
+      "loss": 0.3047,
+      "step": 879
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 2.9075693008795957e-05,
+      "loss": 0.1722,
+      "step": 880
+    },
+    {
+      "epoch": 2.63,
+      "eval_loss": 0.5573097467422485,
+      "eval_runtime": 19.7038,
+      "eval_samples_per_second": 82.674,
+      "eval_steps_per_second": 41.362,
+      "step": 880
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.8612655025833144e-05,
+      "loss": 0.3024,
+      "step": 881
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.8153049487556637e-05,
+      "loss": 0.2344,
+      "step": 882
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2.7696885598675136e-05,
+      "loss": 0.1669,
+      "step": 883
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.7244172494969977e-05,
+      "loss": 0.1621,
+      "step": 884
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.679491924311226e-05,
+      "loss": 0.1964,
+      "step": 885
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.6349134840481294e-05,
+      "loss": 0.1755,
+      "step": 886
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.590682821498416e-05,
+      "loss": 0.2517,
+      "step": 887
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.5468008224877137e-05,
+      "loss": 0.3198,
+      "step": 888
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.5032683658588308e-05,
+      "loss": 0.2393,
+      "step": 889
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.460086323454134e-05,
+      "loss": 0.3719,
+      "step": 890
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.4172555600981108e-05,
+      "loss": 0.1488,
+      "step": 891
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.374776933580025e-05,
+      "loss": 0.2903,
+      "step": 892
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.3326512946367717e-05,
+      "loss": 0.3042,
+      "step": 893
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.2908794869358042e-05,
+      "loss": 0.132,
+      "step": 894
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.249462347058251e-05,
+      "loss": 0.1392,
+      "step": 895
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.2084007044821765e-05,
+      "loss": 0.2447,
+      "step": 896
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.167695381565944e-05,
+      "loss": 0.1972,
+      "step": 897
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.1273471935317568e-05,
+      "loss": 0.1614,
+      "step": 898
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.0873569484493306e-05,
+      "loss": 0.2479,
+      "step": 899
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.0477254472197238e-05,
+      "loss": 0.2399,
+      "step": 900
+    },
+    {
+      "epoch": 2.69,
+      "eval_loss": 0.5553426146507263,
+      "eval_runtime": 19.7366,
+      "eval_samples_per_second": 82.537,
+      "eval_steps_per_second": 41.294,
+      "step": 900
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 2.0084534835592582e-05,
+      "loss": 0.244,
+      "step": 901
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 1.96954184398368e-05,
+      "loss": 0.1855,
+      "step": 902
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 1.930991307792358e-05,
+      "loss": 0.2513,
+      "step": 903
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.8928026470526918e-05,
+      "loss": 0.1895,
+      "step": 904
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.8549766265846725e-05,
+      "loss": 0.1895,
+      "step": 905
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.817514003945524e-05,
+      "loss": 0.2296,
+      "step": 906
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.7804155294145762e-05,
+      "loss": 0.2764,
+      "step": 907
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.7436819459781838e-05,
+      "loss": 0.1448,
+      "step": 908
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.707313989314909e-05,
+      "loss": 0.177,
+      "step": 909
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.6713123877807413e-05,
+      "loss": 0.1312,
+      "step": 910
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.6356778623945223e-05,
+      "loss": 0.1812,
+      "step": 911
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.6004111268235156e-05,
+      "loss": 0.1401,
+      "step": 912
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.565512887369114e-05,
+      "loss": 0.0958,
+      "step": 913
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 1.5309838429526712e-05,
+      "loss": 0.1707,
+      "step": 914
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 1.4968246851015299e-05,
+      "loss": 0.1308,
+      "step": 915
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 1.4630360979351642e-05,
+      "loss": 0.1282,
+      "step": 916
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.4296187581514742e-05,
+      "loss": 0.2066,
+      "step": 917
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.3965733350132359e-05,
+      "loss": 0.2427,
+      "step": 918
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.3639004903346952e-05,
+      "loss": 0.2048,
+      "step": 919
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.3316008784683265e-05,
+      "loss": 0.229,
+      "step": 920
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 0.5565208196640015,
+      "eval_runtime": 19.7076,
+      "eval_samples_per_second": 82.659,
+      "eval_steps_per_second": 41.355,
+      "step": 920
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.2996751462917056e-05,
+      "loss": 0.2165,
+      "step": 921
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.2681239331945693e-05,
+      "loss": 0.2261,
+      "step": 922
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.2369478710660166e-05,
+      "loss": 0.1976,
+      "step": 923
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.2061475842818338e-05,
+      "loss": 0.1483,
+      "step": 924
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.175723689692001e-05,
+      "loss": 0.1529,
+      "step": 925
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.1456767966083392e-05,
+      "loss": 0.2191,
+      "step": 926
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.1160075067923093e-05,
+      "loss": 0.3032,
+      "step": 927
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.086716414442952e-05,
+      "loss": 0.1686,
+      "step": 928
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.0578041061849919e-05,
+      "loss": 0.2305,
+      "step": 929
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.0292711610570904e-05,
+      "loss": 0.2099,
+      "step": 930
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.0011181505002488e-05,
+      "loss": 0.1408,
+      "step": 931
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 9.733456383463657e-06,
+      "loss": 0.3166,
+      "step": 932
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 9.459541808069295e-06,
+      "loss": 0.1775,
+      "step": 933
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 9.189443264619101e-06,
+      "loss": 0.1162,
+      "step": 934
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 8.923166162487406e-06,
+      "loss": 0.2028,
+      "step": 935
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 8.660715834514977e-06,
+      "loss": 0.2241,
+      "step": 936
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.40209753690222e-06,
+      "loss": 0.249,
+      "step": 937
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.14731644910396e-06,
+      "loss": 0.1689,
+      "step": 938
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.896377673725552e-06,
+      "loss": 0.1266,
+      "step": 939
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.649286236420805e-06,
+      "loss": 0.1876,
+      "step": 940
+    },
+    {
+      "epoch": 2.81,
+      "eval_loss": 0.5609006881713867,
+      "eval_runtime": 19.735,
+      "eval_samples_per_second": 82.544,
+      "eval_steps_per_second": 41.297,
+      "step": 940
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 7.406047085791379e-06,
+      "loss": 0.2453,
+      "step": 941
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 7.166665093287539e-06,
+      "loss": 0.1647,
+      "step": 942
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 6.931145053110655e-06,
+      "loss": 0.1295,
+      "step": 943
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 6.699491682117209e-06,
+      "loss": 0.223,
+      "step": 944
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 6.4717096197243865e-06,
+      "loss": 0.2768,
+      "step": 945
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 6.247803427816945e-06,
+      "loss": 0.2538,
+      "step": 946
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 6.027777590656114e-06,
+      "loss": 0.2201,
+      "step": 947
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.811636514789598e-06,
+      "loss": 0.1857,
+      "step": 948
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.599384528963425e-06,
+      "loss": 0.1214,
+      "step": 949
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.391025884035239e-06,
+      "loss": 0.1906,
+      "step": 950
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.1865647528890785e-06,
+      "loss": 0.1997,
+      "step": 951
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 4.986005230351953e-06,
+      "loss": 0.3214,
+      "step": 952
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 4.789351333111691e-06,
+      "loss": 0.3119,
+      "step": 953
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 4.596606999636599e-06,
+      "loss": 0.174,
+      "step": 954
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 4.407776090096527e-06,
+      "loss": 0.1422,
+      "step": 955
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 4.22286238628562e-06,
+      "loss": 0.1416,
+      "step": 956
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 4.0418695915464655e-06,
+      "loss": 0.2623,
+      "step": 957
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 3.8648013306960665e-06,
+      "loss": 0.1478,
+      "step": 958
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 3.691661149953096e-06,
+      "loss": 0.2029,
+      "step": 959
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 3.5224525168670473e-06,
+      "loss": 0.2281,
+      "step": 960
+    },
+    {
+      "epoch": 2.87,
+      "eval_loss": 0.5633081197738647,
+      "eval_runtime": 19.7309,
+      "eval_samples_per_second": 82.561,
+      "eval_steps_per_second": 41.306,
+      "step": 960
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 3.357178820248641e-06,
+      "loss": 0.1241,
+      "step": 961
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 3.1958433701019696e-06,
+      "loss": 0.1691,
+      "step": 962
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 3.0384493975583962e-06,
+      "loss": 0.1907,
+      "step": 963
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 2.885000054811515e-06,
+      "loss": 0.2512,
+      "step": 964
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 2.735498415054294e-06,
+      "loss": 0.2143,
+      "step": 965
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 2.589947472417431e-06,
+      "loss": 0.2822,
+      "step": 966
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2.4483501419093835e-06,
+      "loss": 0.2205,
+      "step": 967
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2.3107092593579904e-06,
+      "loss": 0.2034,
+      "step": 968
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2.1770275813536744e-06,
+      "loss": 0.1592,
+      "step": 969
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2.0473077851942857e-06,
+      "loss": 0.3192,
+      "step": 970
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.921552468831389e-06,
+      "loss": 0.1551,
+      "step": 971
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.7997641508183061e-06,
+      "loss": 0.2066,
+      "step": 972
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.6819452702596883e-06,
+      "loss": 0.2498,
+      "step": 973
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.5680981867625565e-06,
+      "loss": 0.2054,
+      "step": 974
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.4582251803892054e-06,
+      "loss": 0.2541,
+      "step": 975
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.3523284516113955e-06,
+      "loss": 0.1834,
+      "step": 976
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.25041012126641e-06,
+      "loss": 0.1744,
+      "step": 977
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.152472230514423e-06,
+      "loss": 0.2185,
+      "step": 978
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.058516740797777e-06,
+      "loss": 0.2448,
+      "step": 979
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 9.685455338016348e-07,
+      "loss": 0.1727,
+      "step": 980
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 0.5645096302032471,
+      "eval_runtime": 19.7135,
+      "eval_samples_per_second": 82.634,
+      "eval_steps_per_second": 41.342,
+      "step": 980
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 8.825604114162556e-07,
+      "loss": 0.1444,
+      "step": 981
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 8.005630957010013e-07,
+      "loss": 0.2611,
+      "step": 982
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 7.225552288497195e-07,
+      "loss": 0.1487,
+      "step": 983
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 6.485383731580141e-07,
+      "loss": 0.1129,
+      "step": 984
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.785140109917819e-07,
+      "loss": 0.2151,
+      "step": 985
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.124835447576804e-07,
+      "loss": 0.1484,
+      "step": 986
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 4.5044829687497236e-07,
+      "loss": 0.1398,
+      "step": 987
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 3.9240950974899214e-07,
+      "loss": 0.2263,
+      "step": 988
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 3.383683457463649e-07,
+      "loss": 0.2355,
+      "step": 989
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 2.883258871716477e-07,
+      "loss": 0.1428,
+      "step": 990
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 2.422831362456801e-07,
+      "loss": 0.2452,
+      "step": 991
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 2.0024101508555605e-07,
+      "loss": 0.192,
+      "step": 992
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 1.6220036568608267e-07,
+      "loss": 0.3676,
+      "step": 993
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.2816194990292741e-07,
+      "loss": 0.2099,
+      "step": 994
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 9.812644943745231e-08,
+      "loss": 0.1263,
+      "step": 995
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 7.2094465822925e-08,
+      "loss": 0.1562,
+      "step": 996
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.0066520412550554e-08,
+      "loss": 0.2864,
+      "step": 997
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 3.2043054369057524e-08,
+      "loss": 0.1615,
+      "step": 998
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.802442865579401e-08,
+      "loss": 0.2419,
+      "step": 999
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 8.010924029533407e-09,
+      "loss": 0.3536,
+      "step": 1000
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 0.5630822777748108,
+      "eval_runtime": 19.7327,
+      "eval_samples_per_second": 82.554,
+      "eval_steps_per_second": 41.302,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.002741034812239e-09,
+      "loss": 0.2046,
+      "step": 1001
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.2255,
+      "step": 1002
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1002,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.8346686904803e+18,
+  "trial_name": null,
+  "trial_params": null
+}