diff --git "a/checkpoint-580/trainer_state.json" "b/checkpoint-580/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-580/trainer_state.json"
@@ -0,0 +1,4093 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 580,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008620689655172414,
+      "grad_norm": 30.156124114990234,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 3.946,
+      "step": 1
+    },
+    {
+      "epoch": 0.017241379310344827,
+      "grad_norm": 29.95058250427246,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 4.0398,
+      "step": 2
+    },
+    {
+      "epoch": 0.02586206896551724,
+      "grad_norm": 29.866586685180664,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 3.9303,
+      "step": 3
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 30.012300491333008,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 3.9637,
+      "step": 4
+    },
+    {
+      "epoch": 0.04310344827586207,
+      "grad_norm": 30.934751510620117,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 4.0617,
+      "step": 5
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "grad_norm": 30.031415939331055,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 3.9659,
+      "step": 6
+    },
+    {
+      "epoch": 0.0603448275862069,
+      "grad_norm": 29.62813949584961,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 3.9978,
+      "step": 7
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 31.0523681640625,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 4.0237,
+      "step": 8
+    },
+    {
+      "epoch": 0.07758620689655173,
+      "grad_norm": 28.83756446838379,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 3.8214,
+      "step": 9
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 28.1810359954834,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 3.848,
+      "step": 10
+    },
+    {
+      "epoch": 0.09482758620689655,
+      "grad_norm": 28.367570877075195,
+      "learning_rate": 5.5e-07,
+      "loss": 3.7026,
+      "step": 11
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 27.66380500793457,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 3.6833,
+      "step": 12
+    },
+    {
+      "epoch": 0.11206896551724138,
+      "grad_norm": 27.496694564819336,
+      "learning_rate": 6.5e-07,
+      "loss": 3.762,
+      "step": 13
+    },
+    {
+      "epoch": 0.1206896551724138,
+      "grad_norm": 28.319055557250977,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 3.8867,
+      "step": 14
+    },
+    {
+      "epoch": 0.12931034482758622,
+      "grad_norm": 26.112581253051758,
+      "learning_rate": 7.5e-07,
+      "loss": 3.6278,
+      "step": 15
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 25.8245792388916,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 3.7957,
+      "step": 16
+    },
+    {
+      "epoch": 0.14655172413793102,
+      "grad_norm": 23.66245460510254,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 3.4384,
+      "step": 17
+    },
+    {
+      "epoch": 0.15517241379310345,
+      "grad_norm": 21.69405746459961,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 3.2602,
+      "step": 18
+    },
+    {
+      "epoch": 0.16379310344827586,
+      "grad_norm": 20.691402435302734,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 3.2486,
+      "step": 19
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 20.67167854309082,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 3.2401,
+      "step": 20
+    },
+    {
+      "epoch": 0.1810344827586207,
+      "grad_norm": 19.054428100585938,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 3.0375,
+      "step": 21
+    },
+    {
+      "epoch": 0.1896551724137931,
+      "grad_norm": 18.890884399414062,
+      "learning_rate": 1.1e-06,
+      "loss": 2.9677,
+      "step": 22
+    },
+    {
+      "epoch": 0.19827586206896552,
+      "grad_norm": 18.61600112915039,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 2.8387,
+      "step": 23
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 16.910585403442383,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 2.4914,
+      "step": 24
+    },
+    {
+      "epoch": 0.21551724137931033,
+      "grad_norm": 17.708385467529297,
+      "learning_rate": 1.25e-06,
+      "loss": 2.5361,
+      "step": 25
+    },
+    {
+      "epoch": 0.22413793103448276,
+      "grad_norm": 17.07745933532715,
+      "learning_rate": 1.3e-06,
+      "loss": 2.4098,
+      "step": 26
+    },
+    {
+      "epoch": 0.23275862068965517,
+      "grad_norm": 16.244144439697266,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 2.2155,
+      "step": 27
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 16.11887550354004,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 2.0036,
+      "step": 28
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 16.034631729125977,
+      "learning_rate": 1.45e-06,
+      "loss": 1.8617,
+      "step": 29
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 15.437153816223145,
+      "learning_rate": 1.5e-06,
+      "loss": 1.7413,
+      "step": 30
+    },
+    {
+      "epoch": 0.2672413793103448,
+      "grad_norm": 14.188116073608398,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 1.5002,
+      "step": 31
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 14.200998306274414,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.4469,
+      "step": 32
+    },
+    {
+      "epoch": 0.28448275862068967,
+      "grad_norm": 13.209551811218262,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 1.3016,
+      "step": 33
+    },
+    {
+      "epoch": 0.29310344827586204,
+      "grad_norm": 12.631085395812988,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 1.1522,
+      "step": 34
+    },
+    {
+      "epoch": 0.3017241379310345,
+      "grad_norm": 12.504134178161621,
+      "learning_rate": 1.75e-06,
+      "loss": 1.0058,
+      "step": 35
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 12.599784851074219,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.921,
+      "step": 36
+    },
+    {
+      "epoch": 0.31896551724137934,
+      "grad_norm": 11.577665328979492,
+      "learning_rate": 1.85e-06,
+      "loss": 0.8099,
+      "step": 37
+    },
+    {
+      "epoch": 0.3275862068965517,
+      "grad_norm": 10.465872764587402,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.6565,
+      "step": 38
+    },
+    {
+      "epoch": 0.33620689655172414,
+      "grad_norm": 10.161813735961914,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.5712,
+      "step": 39
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 8.384145736694336,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.4265,
+      "step": 40
+    },
+    {
+      "epoch": 0.35344827586206895,
+      "grad_norm": 7.072062015533447,
+      "learning_rate": 2.05e-06,
+      "loss": 0.409,
+      "step": 41
+    },
+    {
+      "epoch": 0.3620689655172414,
+      "grad_norm": 6.072140693664551,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.3263,
+      "step": 42
+    },
+    {
+      "epoch": 0.3706896551724138,
+      "grad_norm": 6.31119441986084,
+      "learning_rate": 2.15e-06,
+      "loss": 0.258,
+      "step": 43
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 6.619389057159424,
+      "learning_rate": 2.2e-06,
+      "loss": 0.2454,
+      "step": 44
+    },
+    {
+      "epoch": 0.3879310344827586,
+      "grad_norm": 6.546375751495361,
+      "learning_rate": 2.25e-06,
+      "loss": 0.2314,
+      "step": 45
+    },
+    {
+      "epoch": 0.39655172413793105,
+      "grad_norm": 5.219631671905518,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.2006,
+      "step": 46
+    },
+    {
+      "epoch": 0.4051724137931034,
+      "grad_norm": 3.1164474487304688,
+      "learning_rate": 2.35e-06,
+      "loss": 0.1677,
+      "step": 47
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 1.872147798538208,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.1339,
+      "step": 48
+    },
+    {
+      "epoch": 0.4224137931034483,
+      "grad_norm": 1.4775545597076416,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.1218,
+      "step": 49
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 1.2931559085845947,
+      "learning_rate": 2.5e-06,
+      "loss": 0.1151,
+      "step": 50
+    },
+    {
+      "epoch": 0.4396551724137931,
+      "grad_norm": 1.3222297430038452,
+      "learning_rate": 2.55e-06,
+      "loss": 0.1164,
+      "step": 51
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 1.393062710762024,
+      "learning_rate": 2.6e-06,
+      "loss": 0.1053,
+      "step": 52
+    },
+    {
+      "epoch": 0.45689655172413796,
+      "grad_norm": 1.0838805437088013,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.105,
+      "step": 53
+    },
+    {
+      "epoch": 0.46551724137931033,
+      "grad_norm": 0.954925537109375,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0922,
+      "step": 54
+    },
+    {
+      "epoch": 0.47413793103448276,
+      "grad_norm": 0.7521713972091675,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0887,
+      "step": 55
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.7261010408401489,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0997,
+      "step": 56
+    },
+    {
+      "epoch": 0.49137931034482757,
+      "grad_norm": 0.6530802845954895,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0882,
+      "step": 57
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.6899245381355286,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0844,
+      "step": 58
+    },
+    {
+      "epoch": 0.5086206896551724,
+      "grad_norm": 0.6771528124809265,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0884,
+      "step": 59
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.6307985782623291,
+      "learning_rate": 3e-06,
+      "loss": 0.0912,
+      "step": 60
+    },
+    {
+      "epoch": 0.5258620689655172,
+      "grad_norm": 0.5869951844215393,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0875,
+      "step": 61
+    },
+    {
+      "epoch": 0.5344827586206896,
+      "grad_norm": 0.6039404273033142,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0768,
+      "step": 62
+    },
+    {
+      "epoch": 0.5431034482758621,
+      "grad_norm": 0.49209344387054443,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0815,
+      "step": 63
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.7383344769477844,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0874,
+      "step": 64
+    },
+    {
+      "epoch": 0.5603448275862069,
+      "grad_norm": 0.5552617311477661,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0762,
+      "step": 65
+    },
+    {
+      "epoch": 0.5689655172413793,
+      "grad_norm": 0.4992441236972809,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0793,
+      "step": 66
+    },
+    {
+      "epoch": 0.5775862068965517,
+      "grad_norm": 0.4979636073112488,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0792,
+      "step": 67
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.4675934612751007,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0766,
+      "step": 68
+    },
+    {
+      "epoch": 0.5948275862068966,
+      "grad_norm": 0.49495571851730347,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0824,
+      "step": 69
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 0.6044315695762634,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0826,
+      "step": 70
+    },
+    {
+      "epoch": 0.6120689655172413,
+      "grad_norm": 0.4898519217967987,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0755,
+      "step": 71
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.4218939244747162,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0762,
+      "step": 72
+    },
+    {
+      "epoch": 0.6293103448275862,
+      "grad_norm": 0.5785802006721497,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0837,
+      "step": 73
+    },
+    {
+      "epoch": 0.6379310344827587,
+      "grad_norm": 0.5505399703979492,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0814,
+      "step": 74
+    },
+    {
+      "epoch": 0.646551724137931,
+      "grad_norm": 0.6062561869621277,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0725,
+      "step": 75
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.707350492477417,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.0913,
+      "step": 76
+    },
+    {
+      "epoch": 0.6637931034482759,
+      "grad_norm": 0.5091889500617981,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0697,
+      "step": 77
+    },
+    {
+      "epoch": 0.6724137931034483,
+      "grad_norm": 0.4801473319530487,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.073,
+      "step": 78
+    },
+    {
+      "epoch": 0.6810344827586207,
+      "grad_norm": 0.462162047624588,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0805,
+      "step": 79
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.463969349861145,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0738,
+      "step": 80
+    },
+    {
+      "epoch": 0.6982758620689655,
+      "grad_norm": 0.3980114161968231,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0742,
+      "step": 81
+    },
+    {
+      "epoch": 0.7068965517241379,
+      "grad_norm": 0.3627180755138397,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0683,
+      "step": 82
+    },
+    {
+      "epoch": 0.7155172413793104,
+      "grad_norm": 0.39726322889328003,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0717,
+      "step": 83
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.48898085951805115,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0676,
+      "step": 84
+    },
+    {
+      "epoch": 0.7327586206896551,
+      "grad_norm": 0.6143100261688232,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0708,
+      "step": 85
+    },
+    {
+      "epoch": 0.7413793103448276,
+      "grad_norm": 0.5028995275497437,
+      "learning_rate": 4.3e-06,
+      "loss": 0.0713,
+      "step": 86
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.5576066970825195,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.078,
+      "step": 87
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.37101301550865173,
+      "learning_rate": 4.4e-06,
+      "loss": 0.071,
+      "step": 88
+    },
+    {
+      "epoch": 0.7672413793103449,
+      "grad_norm": 0.442694753408432,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0791,
+      "step": 89
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 0.48991039395332336,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0681,
+      "step": 90
+    },
+    {
+      "epoch": 0.7844827586206896,
+      "grad_norm": 0.46367791295051575,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0701,
+      "step": 91
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.3454825282096863,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.0774,
+      "step": 92
+    },
+    {
+      "epoch": 0.8017241379310345,
+      "grad_norm": 0.35102447867393494,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0659,
+      "step": 93
+    },
+    {
+      "epoch": 0.8103448275862069,
+      "grad_norm": 0.3791246712207794,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0727,
+      "step": 94
+    },
+    {
+      "epoch": 0.8189655172413793,
+      "grad_norm": 0.3911365270614624,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0641,
+      "step": 95
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.35395047068595886,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0735,
+      "step": 96
+    },
+    {
+      "epoch": 0.8362068965517241,
+      "grad_norm": 0.3499661087989807,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0657,
+      "step": 97
+    },
+    {
+      "epoch": 0.8448275862068966,
+      "grad_norm": 0.34877678751945496,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.0701,
+      "step": 98
+    },
+    {
+      "epoch": 0.853448275862069,
+      "grad_norm": 0.36436647176742554,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0758,
+      "step": 99
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.4726298749446869,
+      "learning_rate": 5e-06,
+      "loss": 0.0731,
+      "step": 100
+    },
+    {
+      "epoch": 0.8706896551724138,
+      "grad_norm": 0.31892526149749756,
+      "learning_rate": 4.999965269084342e-06,
+      "loss": 0.0635,
+      "step": 101
+    },
+    {
+      "epoch": 0.8793103448275862,
+      "grad_norm": 0.3707881569862366,
+      "learning_rate": 4.999861077302358e-06,
+      "loss": 0.0689,
+      "step": 102
+    },
+    {
+      "epoch": 0.8879310344827587,
+      "grad_norm": 0.3244622051715851,
+      "learning_rate": 4.999687427548989e-06,
+      "loss": 0.0645,
+      "step": 103
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.386982262134552,
+      "learning_rate": 4.999444324649045e-06,
+      "loss": 0.0708,
+      "step": 104
+    },
+    {
+      "epoch": 0.9051724137931034,
+      "grad_norm": 0.3552643656730652,
+      "learning_rate": 4.999131775357078e-06,
+      "loss": 0.0766,
+      "step": 105
+    },
+    {
+      "epoch": 0.9137931034482759,
+      "grad_norm": 0.3503671884536743,
+      "learning_rate": 4.998749788357184e-06,
+      "loss": 0.0733,
+      "step": 106
+    },
+    {
+      "epoch": 0.9224137931034483,
+      "grad_norm": 0.4907379746437073,
+      "learning_rate": 4.998298374262771e-06,
+      "loss": 0.0721,
+      "step": 107
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.305571585893631,
+      "learning_rate": 4.997777545616258e-06,
+      "loss": 0.0603,
+      "step": 108
+    },
+    {
+      "epoch": 0.9396551724137931,
+      "grad_norm": 0.3188783824443817,
+      "learning_rate": 4.99718731688873e-06,
+      "loss": 0.0574,
+      "step": 109
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 0.3277616500854492,
+      "learning_rate": 4.996527704479535e-06,
+      "loss": 0.0671,
+      "step": 110
+    },
+    {
+      "epoch": 0.9568965517241379,
+      "grad_norm": 0.38640740513801575,
+      "learning_rate": 4.995798726715826e-06,
+      "loss": 0.0625,
+      "step": 111
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.5463483929634094,
+      "learning_rate": 4.995000403852057e-06,
+      "loss": 0.0718,
+      "step": 112
+    },
+    {
+      "epoch": 0.9741379310344828,
+      "grad_norm": 0.3974014222621918,
+      "learning_rate": 4.994132758069413e-06,
+      "loss": 0.071,
+      "step": 113
+    },
+    {
+      "epoch": 0.9827586206896551,
+      "grad_norm": 0.3642785847187042,
+      "learning_rate": 4.993195813475202e-06,
+      "loss": 0.0658,
+      "step": 114
+    },
+    {
+      "epoch": 0.9913793103448276,
+      "grad_norm": 0.3118143677711487,
+      "learning_rate": 4.992189596102179e-06,
+      "loss": 0.0633,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.41573596000671387,
+      "learning_rate": 4.991114133907822e-06,
+      "loss": 0.0662,
+      "step": 116
+    },
+    {
+      "epoch": 1.0086206896551724,
+      "grad_norm": 0.29761484265327454,
+      "learning_rate": 4.989969456773562e-06,
+      "loss": 0.0649,
+      "step": 117
+    },
+    {
+      "epoch": 1.0172413793103448,
+      "grad_norm": 0.399275004863739,
+      "learning_rate": 4.988755596503948e-06,
+      "loss": 0.0521,
+      "step": 118
+    },
+    {
+      "epoch": 1.0258620689655173,
+      "grad_norm": 0.37820911407470703,
+      "learning_rate": 4.987472586825762e-06,
+      "loss": 0.0596,
+      "step": 119
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.4371725916862488,
+      "learning_rate": 4.986120463387084e-06,
+      "loss": 0.07,
+      "step": 120
+    },
+    {
+      "epoch": 1.043103448275862,
+      "grad_norm": 0.3165535032749176,
+      "learning_rate": 4.984699263756303e-06,
+      "loss": 0.0613,
+      "step": 121
+    },
+    {
+      "epoch": 1.0517241379310345,
+      "grad_norm": 0.40526920557022095,
+      "learning_rate": 4.983209027421072e-06,
+      "loss": 0.0611,
+      "step": 122
+    },
+    {
+      "epoch": 1.0603448275862069,
+      "grad_norm": 0.39523962140083313,
+      "learning_rate": 4.9816497957872055e-06,
+      "loss": 0.0634,
+      "step": 123
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.33234691619873047,
+      "learning_rate": 4.9800216121775404e-06,
+      "loss": 0.0602,
+      "step": 124
+    },
+    {
+      "epoch": 1.0775862068965518,
+      "grad_norm": 0.3455008268356323,
+      "learning_rate": 4.978324521830721e-06,
+      "loss": 0.0624,
+      "step": 125
+    },
+    {
+      "epoch": 1.0862068965517242,
+      "grad_norm": 0.3968574106693268,
+      "learning_rate": 4.97655857189995e-06,
+      "loss": 0.0525,
+      "step": 126
+    },
+    {
+      "epoch": 1.0948275862068966,
+      "grad_norm": 0.47838935256004333,
+      "learning_rate": 4.974723811451673e-06,
+      "loss": 0.0617,
+      "step": 127
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.43055081367492676,
+      "learning_rate": 4.972820291464219e-06,
+      "loss": 0.0484,
+      "step": 128
+    },
+    {
+      "epoch": 1.1120689655172413,
+      "grad_norm": 0.4012243449687958,
+      "learning_rate": 4.97084806482638e-06,
+      "loss": 0.0562,
+      "step": 129
+    },
+    {
+      "epoch": 1.1206896551724137,
+      "grad_norm": 0.586875319480896,
+      "learning_rate": 4.968807186335948e-06,
+      "loss": 0.0633,
+      "step": 130
+    },
+    {
+      "epoch": 1.1293103448275863,
+      "grad_norm": 0.48629340529441833,
+      "learning_rate": 4.966697712698185e-06,
+      "loss": 0.0615,
+      "step": 131
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.41810542345046997,
+      "learning_rate": 4.964519702524251e-06,
+      "loss": 0.0564,
+      "step": 132
+    },
+    {
+      "epoch": 1.146551724137931,
+      "grad_norm": 0.4095732271671295,
+      "learning_rate": 4.962273216329577e-06,
+      "loss": 0.0634,
+      "step": 133
+    },
+    {
+      "epoch": 1.1551724137931034,
+      "grad_norm": 0.3784744441509247,
+      "learning_rate": 4.959958316532181e-06,
+      "loss": 0.0521,
+      "step": 134
+    },
+    {
+      "epoch": 1.1637931034482758,
+      "grad_norm": 0.4087596833705902,
+      "learning_rate": 4.957575067450935e-06,
+      "loss": 0.0569,
+      "step": 135
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.4369741380214691,
+      "learning_rate": 4.955123535303775e-06,
+      "loss": 0.057,
+      "step": 136
+    },
+    {
+      "epoch": 1.1810344827586208,
+      "grad_norm": 0.3851775527000427,
+      "learning_rate": 4.95260378820587e-06,
+      "loss": 0.0521,
+      "step": 137
+    },
+    {
+      "epoch": 1.1896551724137931,
+      "grad_norm": 0.3391599655151367,
+      "learning_rate": 4.950015896167716e-06,
+      "loss": 0.0525,
+      "step": 138
+    },
+    {
+      "epoch": 1.1982758620689655,
+      "grad_norm": 0.4176456332206726,
+      "learning_rate": 4.947359931093202e-06,
+      "loss": 0.0548,
+      "step": 139
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.45864036679267883,
+      "learning_rate": 4.944635966777607e-06,
+      "loss": 0.0578,
+      "step": 140
+    },
+    {
+      "epoch": 1.2155172413793103,
+      "grad_norm": 0.4484093487262726,
+      "learning_rate": 4.941844078905551e-06,
+      "loss": 0.0528,
+      "step": 141
+    },
+    {
+      "epoch": 1.2241379310344827,
+      "grad_norm": 0.42641302943229675,
+      "learning_rate": 4.938984345048892e-06,
+      "loss": 0.0519,
+      "step": 142
+    },
+    {
+      "epoch": 1.2327586206896552,
+      "grad_norm": 0.5111292004585266,
+      "learning_rate": 4.936056844664571e-06,
+      "loss": 0.0639,
+      "step": 143
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.3739636540412903,
+      "learning_rate": 4.933061659092401e-06,
+      "loss": 0.055,
+      "step": 144
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.3896700143814087,
+      "learning_rate": 4.929998871552814e-06,
+      "loss": 0.0548,
+      "step": 145
+    },
+    {
+      "epoch": 1.2586206896551724,
+      "grad_norm": 0.4158782660961151,
+      "learning_rate": 4.926868567144543e-06,
+      "loss": 0.0572,
+      "step": 146
+    },
+    {
+      "epoch": 1.2672413793103448,
+      "grad_norm": 0.4275132715702057,
+      "learning_rate": 4.923670832842256e-06,
+      "loss": 0.0497,
+      "step": 147
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.3890449106693268,
+      "learning_rate": 4.920405757494147e-06,
+      "loss": 0.0584,
+      "step": 148
+    },
+    {
+      "epoch": 1.2844827586206897,
+      "grad_norm": 0.4569760262966156,
+      "learning_rate": 4.917073431819462e-06,
+      "loss": 0.0618,
+      "step": 149
+    },
+    {
+      "epoch": 1.293103448275862,
+      "grad_norm": 0.4232596457004547,
+      "learning_rate": 4.913673948405977e-06,
+      "loss": 0.0516,
+      "step": 150
+    },
+    {
+      "epoch": 1.3017241379310345,
+      "grad_norm": 0.4578849673271179,
+      "learning_rate": 4.910207401707431e-06,
+      "loss": 0.0538,
+      "step": 151
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.39952200651168823,
+      "learning_rate": 4.906673888040895e-06,
+      "loss": 0.0471,
+      "step": 152
+    },
+    {
+      "epoch": 1.3189655172413794,
+      "grad_norm": 0.38846731185913086,
+      "learning_rate": 4.903073505584102e-06,
+      "loss": 0.0437,
+      "step": 153
+    },
+    {
+      "epoch": 1.3275862068965516,
+      "grad_norm": 0.4084296226501465,
+      "learning_rate": 4.899406354372716e-06,
+      "loss": 0.0532,
+      "step": 154
+    },
+    {
+      "epoch": 1.3362068965517242,
+      "grad_norm": 0.4114966094493866,
+      "learning_rate": 4.895672536297551e-06,
+      "loss": 0.0443,
+      "step": 155
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.6465100049972534,
+      "learning_rate": 4.891872155101746e-06,
+      "loss": 0.0605,
+      "step": 156
+    },
+    {
+      "epoch": 1.353448275862069,
+      "grad_norm": 0.43234798312187195,
+      "learning_rate": 4.888005316377873e-06,
+      "loss": 0.0529,
+      "step": 157
+    },
+    {
+      "epoch": 1.3620689655172413,
+      "grad_norm": 0.408527135848999,
+      "learning_rate": 4.884072127565015e-06,
+      "loss": 0.0485,
+      "step": 158
+    },
+    {
+      "epoch": 1.3706896551724137,
+      "grad_norm": 0.45152318477630615,
+      "learning_rate": 4.880072697945768e-06,
+      "loss": 0.0466,
+      "step": 159
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.4669966995716095,
+      "learning_rate": 4.876007138643216e-06,
+      "loss": 0.0438,
+      "step": 160
+    },
+    {
+      "epoch": 1.3879310344827587,
+      "grad_norm": 0.47117388248443604,
+      "learning_rate": 4.871875562617837e-06,
+      "loss": 0.0464,
+      "step": 161
+    },
+    {
+      "epoch": 1.396551724137931,
+      "grad_norm": 0.6085790991783142,
+      "learning_rate": 4.867678084664365e-06,
+      "loss": 0.0574,
+      "step": 162
+    },
+    {
+      "epoch": 1.4051724137931034,
+      "grad_norm": 0.5736953616142273,
+      "learning_rate": 4.863414821408602e-06,
+      "loss": 0.0507,
+      "step": 163
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.5003281831741333,
+      "learning_rate": 4.8590858913041775e-06,
+      "loss": 0.051,
+      "step": 164
+    },
+    {
+      "epoch": 1.4224137931034484,
+      "grad_norm": 0.4361717104911804,
+      "learning_rate": 4.854691414629258e-06,
+      "loss": 0.0476,
+      "step": 165
+    },
+    {
+      "epoch": 1.4310344827586206,
+      "grad_norm": 0.47907084226608276,
+      "learning_rate": 4.8502315134832e-06,
+      "loss": 0.0495,
+      "step": 166
+    },
+    {
+      "epoch": 1.4396551724137931,
+      "grad_norm": 0.46805888414382935,
+      "learning_rate": 4.8457063117831656e-06,
+      "loss": 0.0474,
+      "step": 167
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.5058819651603699,
+      "learning_rate": 4.8411159352606735e-06,
+      "loss": 0.0541,
+      "step": 168
+    },
+    {
+      "epoch": 1.456896551724138,
+      "grad_norm": 0.4632813334465027,
+      "learning_rate": 4.836460511458107e-06,
+      "loss": 0.0409,
+      "step": 169
+    },
+    {
+      "epoch": 1.4655172413793103,
+      "grad_norm": 0.3654536008834839,
+      "learning_rate": 4.831740169725172e-06,
+      "loss": 0.0466,
+      "step": 170
+    },
+    {
+      "epoch": 1.4741379310344827,
+      "grad_norm": 0.4301295578479767,
+      "learning_rate": 4.8269550412153e-06,
+      "loss": 0.0472,
+      "step": 171
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.37643712759017944,
+      "learning_rate": 4.822105258882007e-06,
+      "loss": 0.0445,
+      "step": 172
+    },
+    {
+      "epoch": 1.4913793103448276,
+      "grad_norm": 0.3928871154785156,
+      "learning_rate": 4.817190957475199e-06,
+      "loss": 0.0427,
+      "step": 173
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.39636102318763733,
+      "learning_rate": 4.812212273537426e-06,
+      "loss": 0.0431,
+      "step": 174
+    },
+    {
+      "epoch": 1.5086206896551724,
+      "grad_norm": 0.41640329360961914,
+      "learning_rate": 4.807169345400088e-06,
+      "loss": 0.0442,
+      "step": 175
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.4888840317726135,
+      "learning_rate": 4.802062313179595e-06,
+      "loss": 0.0529,
+      "step": 176
+    },
+    {
+      "epoch": 1.5258620689655173,
+      "grad_norm": 0.4154113829135895,
+      "learning_rate": 4.796891318773472e-06,
+      "loss": 0.0419,
+      "step": 177
+    },
+    {
+      "epoch": 1.5344827586206895,
+      "grad_norm": 0.41872596740722656,
+      "learning_rate": 4.791656505856416e-06,
+      "loss": 0.0411,
+      "step": 178
+    },
+    {
+      "epoch": 1.543103448275862,
+      "grad_norm": 0.4037671983242035,
+      "learning_rate": 4.786358019876301e-06,
+      "loss": 0.0458,
+      "step": 179
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.4356297552585602,
+      "learning_rate": 4.7809960080501464e-06,
+      "loss": 0.0495,
+      "step": 180
+    },
+    {
+      "epoch": 1.5603448275862069,
+      "grad_norm": 0.4112146496772766,
+      "learning_rate": 4.7755706193600135e-06,
+      "loss": 0.0367,
+      "step": 181
+    },
+    {
+      "epoch": 1.5689655172413794,
+      "grad_norm": 0.36699458956718445,
+      "learning_rate": 4.770082004548878e-06,
+      "loss": 0.0427,
+      "step": 182
+    },
+    {
+      "epoch": 1.5775862068965516,
+      "grad_norm": 0.49518612027168274,
+      "learning_rate": 4.764530316116433e-06,
+      "loss": 0.0334,
+      "step": 183
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.3718539774417877,
+      "learning_rate": 4.758915708314858e-06,
+      "loss": 0.0367,
+      "step": 184
+    },
+    {
+      "epoch": 1.5948275862068966,
+      "grad_norm": 0.46727338433265686,
+      "learning_rate": 4.753238337144528e-06,
+      "loss": 0.044,
+      "step": 185
+    },
+    {
+      "epoch": 1.603448275862069,
+      "grad_norm": 0.5345709323883057,
+      "learning_rate": 4.747498360349681e-06,
+      "loss": 0.0401,
+      "step": 186
+    },
+    {
+      "epoch": 1.6120689655172413,
+      "grad_norm": 0.561375617980957,
+      "learning_rate": 4.7416959374140405e-06,
+      "loss": 0.0457,
+      "step": 187
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.4418468773365021,
+      "learning_rate": 4.735831229556374e-06,
+      "loss": 0.0348,
+      "step": 188
+    },
+    {
+      "epoch": 1.6293103448275863,
+      "grad_norm": 0.5142704844474792,
+      "learning_rate": 4.72990439972602e-06,
+      "loss": 0.0391,
+      "step": 189
+    },
+    {
+      "epoch": 1.6379310344827587,
+      "grad_norm": 0.48653194308280945,
+      "learning_rate": 4.72391561259836e-06,
+      "loss": 0.0358,
+      "step": 190
+    },
+    {
+      "epoch": 1.646551724137931,
+      "grad_norm": 0.48498624563217163,
+      "learning_rate": 4.717865034570243e-06,
+      "loss": 0.038,
+      "step": 191
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.4586655795574188,
+      "learning_rate": 4.711752833755362e-06,
+      "loss": 0.0351,
+      "step": 192
+    },
+    {
+      "epoch": 1.6637931034482758,
+      "grad_norm": 0.44023749232292175,
+      "learning_rate": 4.70557917997958e-06,
+      "loss": 0.0277,
+      "step": 193
+    },
+    {
+      "epoch": 1.6724137931034484,
+      "grad_norm": 0.44018658995628357,
+      "learning_rate": 4.6993442447762185e-06,
+      "loss": 0.0382,
+      "step": 194
+    },
+    {
+      "epoch": 1.6810344827586206,
+      "grad_norm": 0.49303099513053894,
+      "learning_rate": 4.693048201381281e-06,
+      "loss": 0.0413,
+      "step": 195
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.572812557220459,
+      "learning_rate": 4.686691224728652e-06,
+      "loss": 0.0389,
+      "step": 196
+    },
+    {
+      "epoch": 1.6982758620689655,
+      "grad_norm": 0.4995497167110443,
+      "learning_rate": 4.680273491445227e-06,
+      "loss": 0.0314,
+      "step": 197
+    },
+    {
+      "epoch": 1.706896551724138,
+      "grad_norm": 0.465404212474823,
+      "learning_rate": 4.673795179846008e-06,
+      "loss": 0.0323,
+      "step": 198
+    },
+    {
+      "epoch": 1.7155172413793105,
+      "grad_norm": 0.45183637738227844,
+      "learning_rate": 4.667256469929149e-06,
+      "loss": 0.0308,
+      "step": 199
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.4891216456890106,
+      "learning_rate": 4.660657543370958e-06,
+      "loss": 0.034,
+      "step": 200
+    },
+    {
+      "epoch": 1.7327586206896552,
+      "grad_norm": 0.5728661417961121,
+      "learning_rate": 4.653998583520844e-06,
+      "loss": 0.0359,
+      "step": 201
+    },
+    {
+      "epoch": 1.7413793103448276,
+      "grad_norm": 0.5465419888496399,
+      "learning_rate": 4.6472797753962255e-06,
+      "loss": 0.0366,
+      "step": 202
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.4671058654785156,
+      "learning_rate": 4.640501305677387e-06,
+      "loss": 0.0345,
+      "step": 203
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.4623485803604126,
+      "learning_rate": 4.6336633627023e-06,
+      "loss": 0.0261,
+      "step": 204
+    },
+    {
+      "epoch": 1.7672413793103448,
+      "grad_norm": 0.4471631944179535,
+      "learning_rate": 4.626766136461378e-06,
+      "loss": 0.0244,
+      "step": 205
+    },
+    {
+      "epoch": 1.7758620689655173,
+      "grad_norm": 0.46128782629966736,
+      "learning_rate": 4.61980981859221e-06,
+      "loss": 0.0301,
+      "step": 206
+    },
+    {
+      "epoch": 1.7844827586206895,
+      "grad_norm": 0.45246005058288574,
+      "learning_rate": 4.612794602374226e-06,
+      "loss": 0.0274,
+      "step": 207
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 0.5971981287002563,
+      "learning_rate": 4.605720682723331e-06,
+      "loss": 0.0387,
+      "step": 208
+    },
+    {
+      "epoch": 1.8017241379310345,
+      "grad_norm": 0.4932047128677368,
+      "learning_rate": 4.598588256186491e-06,
+      "loss": 0.0228,
+      "step": 209
+    },
+    {
+      "epoch": 1.8103448275862069,
+      "grad_norm": 0.6208699345588684,
+      "learning_rate": 4.591397520936271e-06,
+      "loss": 0.0307,
+      "step": 210
+    },
+    {
+      "epoch": 1.8189655172413794,
+      "grad_norm": 0.5628708004951477,
+      "learning_rate": 4.584148676765327e-06,
+      "loss": 0.0262,
+      "step": 211
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.6893038749694824,
+      "learning_rate": 4.576841925080853e-06,
+      "loss": 0.0312,
+      "step": 212
+    },
+    {
+      "epoch": 1.8362068965517242,
+      "grad_norm": 0.5523396134376526,
+      "learning_rate": 4.569477468898992e-06,
+      "loss": 0.0218,
+      "step": 213
+    },
+    {
+      "epoch": 1.8448275862068966,
+      "grad_norm": 0.6797971129417419,
+      "learning_rate": 4.562055512839189e-06,
+      "loss": 0.0232,
+      "step": 214
+    },
+    {
+      "epoch": 1.853448275862069,
+      "grad_norm": 0.7214551568031311,
+      "learning_rate": 4.554576263118506e-06,
+      "loss": 0.0326,
+      "step": 215
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 0.5208979249000549,
+      "learning_rate": 4.547039927545899e-06,
+      "loss": 0.0261,
+      "step": 216
+    },
+    {
+      "epoch": 1.8706896551724137,
+      "grad_norm": 0.5396261215209961,
+      "learning_rate": 4.539446715516434e-06,
+      "loss": 0.0269,
+      "step": 217
+    },
+    {
+      "epoch": 1.8793103448275863,
+      "grad_norm": 0.5789651274681091,
+      "learning_rate": 4.531796838005477e-06,
+      "loss": 0.035,
+      "step": 218
+    },
+    {
+      "epoch": 1.8879310344827587,
+      "grad_norm": 0.5388063192367554,
+      "learning_rate": 4.524090507562828e-06,
+      "loss": 0.0277,
+      "step": 219
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.4727953374385834,
+      "learning_rate": 4.516327938306818e-06,
+      "loss": 0.0225,
+      "step": 220
+    },
+    {
+      "epoch": 1.9051724137931034,
+      "grad_norm": 0.4665185809135437,
+      "learning_rate": 4.508509345918357e-06,
+      "loss": 0.0268,
+      "step": 221
+    },
+    {
+      "epoch": 1.9137931034482758,
+      "grad_norm": 0.5534846186637878,
+      "learning_rate": 4.500634947634943e-06,
+      "loss": 0.0277,
+      "step": 222
+    },
+    {
+      "epoch": 1.9224137931034484,
+      "grad_norm": 0.46098095178604126,
+      "learning_rate": 4.492704962244626e-06,
+      "loss": 0.0274,
+      "step": 223
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.49379560351371765,
+      "learning_rate": 4.4847196100799305e-06,
+      "loss": 0.0252,
+      "step": 224
+    },
+    {
+      "epoch": 1.9396551724137931,
+      "grad_norm": 0.4714183807373047,
+      "learning_rate": 4.476679113011729e-06,
+      "loss": 0.0253,
+      "step": 225
+    },
+    {
+      "epoch": 1.9482758620689655,
+      "grad_norm": 0.6230431199073792,
+      "learning_rate": 4.4685836944430815e-06,
+      "loss": 0.0242,
+      "step": 226
+    },
+    {
+      "epoch": 1.956896551724138,
+      "grad_norm": 0.42832595109939575,
+      "learning_rate": 4.46043357930303e-06,
+      "loss": 0.0165,
+      "step": 227
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.38421332836151123,
+      "learning_rate": 4.452228994040341e-06,
+      "loss": 0.0168,
+      "step": 228
+    },
+    {
+      "epoch": 1.9741379310344827,
+      "grad_norm": 0.5493133664131165,
+      "learning_rate": 4.443970166617223e-06,
+      "loss": 0.0193,
+      "step": 229
+    },
+    {
+      "epoch": 1.9827586206896552,
+      "grad_norm": 0.45186540484428406,
+      "learning_rate": 4.435657326502986e-06,
+      "loss": 0.0165,
+      "step": 230
+    },
+    {
+      "epoch": 1.9913793103448276,
+      "grad_norm": 0.8328711986541748,
+      "learning_rate": 4.4272907046676704e-06,
+      "loss": 0.025,
+      "step": 231
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5378574728965759,
+      "learning_rate": 4.418870533575626e-06,
+      "loss": 0.0166,
+      "step": 232
+    },
+    {
+      "epoch": 2.0086206896551726,
+      "grad_norm": 0.5182176828384399,
+      "learning_rate": 4.410397047179053e-06,
+      "loss": 0.011,
+      "step": 233
+    },
+    {
+      "epoch": 2.0172413793103448,
+      "grad_norm": 0.5283203125,
+      "learning_rate": 4.401870480911505e-06,
+      "loss": 0.0178,
+      "step": 234
+    },
+    {
+      "epoch": 2.0258620689655173,
+      "grad_norm": 0.3926998972892761,
+      "learning_rate": 4.393291071681345e-06,
+      "loss": 0.0121,
+      "step": 235
+    },
+    {
+      "epoch": 2.0344827586206895,
+      "grad_norm": 0.4371504783630371,
+      "learning_rate": 4.384659057865165e-06,
+      "loss": 0.0164,
+      "step": 236
+    },
+    {
+      "epoch": 2.043103448275862,
+      "grad_norm": 0.6982957720756531,
+      "learning_rate": 4.375974679301158e-06,
+      "loss": 0.0192,
+      "step": 237
+    },
+    {
+      "epoch": 2.0517241379310347,
+      "grad_norm": 0.3988925814628601,
+      "learning_rate": 4.367238177282462e-06,
+      "loss": 0.0139,
+      "step": 238
+    },
+    {
+      "epoch": 2.060344827586207,
+      "grad_norm": 0.5101247429847717,
+      "learning_rate": 4.3584497945504465e-06,
+      "loss": 0.0118,
+      "step": 239
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.609987735748291,
+      "learning_rate": 4.349609775287977e-06,
+      "loss": 0.0168,
+      "step": 240
+    },
+    {
+      "epoch": 2.0775862068965516,
+      "grad_norm": 0.37872084975242615,
+      "learning_rate": 4.340718365112623e-06,
+      "loss": 0.009,
+      "step": 241
+    },
+    {
+      "epoch": 2.086206896551724,
+      "grad_norm": 0.5639368891716003,
+      "learning_rate": 4.331775811069837e-06,
+      "loss": 0.0154,
+      "step": 242
+    },
+    {
+      "epoch": 2.0948275862068964,
+      "grad_norm": 0.6034789681434631,
+      "learning_rate": 4.322782361626094e-06,
+      "loss": 0.0174,
+      "step": 243
+    },
+    {
+      "epoch": 2.103448275862069,
+      "grad_norm": 0.46892449259757996,
+      "learning_rate": 4.313738266661979e-06,
+      "loss": 0.0128,
+      "step": 244
+    },
+    {
+      "epoch": 2.1120689655172415,
+      "grad_norm": 0.5814667344093323,
+      "learning_rate": 4.3046437774652525e-06,
+      "loss": 0.0129,
+      "step": 245
+    },
+    {
+      "epoch": 2.1206896551724137,
+      "grad_norm": 0.39165839552879333,
+      "learning_rate": 4.295499146723864e-06,
+      "loss": 0.0133,
+      "step": 246
+    },
+    {
+      "epoch": 2.1293103448275863,
+      "grad_norm": 0.45224517583847046,
+      "learning_rate": 4.286304628518932e-06,
+      "loss": 0.0093,
+      "step": 247
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 0.7525523900985718,
+      "learning_rate": 4.277060478317687e-06,
+      "loss": 0.0159,
+      "step": 248
+    },
+    {
+      "epoch": 2.146551724137931,
+      "grad_norm": 0.6550068259239197,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0126,
+      "step": 249
+    },
+    {
+      "epoch": 2.1551724137931036,
+      "grad_norm": 0.5949872136116028,
+      "learning_rate": 4.258424310683094e-06,
+      "loss": 0.01,
+      "step": 250
+    },
+    {
+      "epoch": 2.163793103448276,
+      "grad_norm": 0.44155633449554443,
+      "learning_rate": 4.24903281105068e-06,
+      "loss": 0.0113,
+      "step": 251
+    },
+    {
+      "epoch": 2.1724137931034484,
+      "grad_norm": 0.7045619487762451,
+      "learning_rate": 4.23959271500943e-06,
+      "loss": 0.0108,
+      "step": 252
+    },
+    {
+      "epoch": 2.1810344827586206,
+      "grad_norm": 0.4648723006248474,
+      "learning_rate": 4.230104284849889e-06,
+      "loss": 0.0104,
+      "step": 253
+    },
+    {
+      "epoch": 2.189655172413793,
+      "grad_norm": 0.4972316026687622,
+      "learning_rate": 4.220567784205551e-06,
+      "loss": 0.0082,
+      "step": 254
+    },
+    {
+      "epoch": 2.1982758620689653,
+      "grad_norm": 0.4233075678348541,
+      "learning_rate": 4.210983478045537e-06,
+      "loss": 0.0088,
+      "step": 255
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 0.5844057202339172,
+      "learning_rate": 4.201351632667227e-06,
+      "loss": 0.0101,
+      "step": 256
+    },
+    {
+      "epoch": 2.2155172413793105,
+      "grad_norm": 0.48759040236473083,
+      "learning_rate": 4.191672515688872e-06,
+      "loss": 0.0097,
+      "step": 257
+    },
+    {
+      "epoch": 2.2241379310344827,
+      "grad_norm": 0.48416000604629517,
+      "learning_rate": 4.181946396042146e-06,
+      "loss": 0.0085,
+      "step": 258
+    },
+    {
+      "epoch": 2.2327586206896552,
+      "grad_norm": 0.5503181219100952,
+      "learning_rate": 4.172173543964682e-06,
+      "loss": 0.0122,
+      "step": 259
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.6163179278373718,
+      "learning_rate": 4.162354230992562e-06,
+      "loss": 0.0119,
+      "step": 260
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.47484147548675537,
+      "learning_rate": 4.1524887299527695e-06,
+      "loss": 0.0142,
+      "step": 261
+    },
+    {
+      "epoch": 2.2586206896551726,
+      "grad_norm": 0.5557327270507812,
+      "learning_rate": 4.142577314955614e-06,
+      "loss": 0.0086,
+      "step": 262
+    },
+    {
+      "epoch": 2.2672413793103448,
+      "grad_norm": 0.3577985465526581,
+      "learning_rate": 4.1326202613871065e-06,
+      "loss": 0.0089,
+      "step": 263
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.33690375089645386,
+      "learning_rate": 4.122617845901322e-06,
+      "loss": 0.0095,
+      "step": 264
+    },
+    {
+      "epoch": 2.2844827586206895,
+      "grad_norm": 0.5704361796379089,
+      "learning_rate": 4.112570346412696e-06,
+      "loss": 0.0078,
+      "step": 265
+    },
+    {
+      "epoch": 2.293103448275862,
+      "grad_norm": 0.4501226544380188,
+      "learning_rate": 4.102478042088315e-06,
+      "loss": 0.0107,
+      "step": 266
+    },
+    {
+      "epoch": 2.3017241379310347,
+      "grad_norm": 0.3546983301639557,
+      "learning_rate": 4.092341213340155e-06,
+      "loss": 0.0087,
+      "step": 267
+    },
+    {
+      "epoch": 2.310344827586207,
+      "grad_norm": 0.6514727473258972,
+      "learning_rate": 4.0821601418172926e-06,
+      "loss": 0.0121,
+      "step": 268
+    },
+    {
+      "epoch": 2.3189655172413794,
+      "grad_norm": 0.5242908596992493,
+      "learning_rate": 4.0719351103980754e-06,
+      "loss": 0.0104,
+      "step": 269
+    },
+    {
+      "epoch": 2.3275862068965516,
+      "grad_norm": 0.40950050950050354,
+      "learning_rate": 4.0616664031822686e-06,
+      "loss": 0.0091,
+      "step": 270
+    },
+    {
+      "epoch": 2.336206896551724,
+      "grad_norm": 0.24205856025218964,
+      "learning_rate": 4.051354305483153e-06,
+      "loss": 0.0043,
+      "step": 271
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 0.35039305686950684,
+      "learning_rate": 4.040999103819606e-06,
+      "loss": 0.0069,
+      "step": 272
+    },
+    {
+      "epoch": 2.353448275862069,
+      "grad_norm": 0.30672788619995117,
+      "learning_rate": 4.030601085908137e-06,
+      "loss": 0.0064,
+      "step": 273
+    },
+    {
+      "epoch": 2.3620689655172415,
+      "grad_norm": 0.26436808705329895,
+      "learning_rate": 4.020160540654892e-06,
+      "loss": 0.0037,
+      "step": 274
+    },
+    {
+      "epoch": 2.3706896551724137,
+      "grad_norm": 0.4178946614265442,
+      "learning_rate": 4.009677758147627e-06,
+      "loss": 0.0041,
+      "step": 275
+    },
+    {
+      "epoch": 2.3793103448275863,
+      "grad_norm": 0.7681214809417725,
+      "learning_rate": 3.999153029647651e-06,
+      "loss": 0.015,
+      "step": 276
+    },
+    {
+      "epoch": 2.3879310344827585,
+      "grad_norm": 0.49876728653907776,
+      "learning_rate": 3.988586647581732e-06,
+      "loss": 0.0082,
+      "step": 277
+    },
+    {
+      "epoch": 2.396551724137931,
+      "grad_norm": 0.5959510207176208,
+      "learning_rate": 3.977978905533966e-06,
+      "loss": 0.0084,
+      "step": 278
+    },
+    {
+      "epoch": 2.405172413793103,
+      "grad_norm": 0.538182258605957,
+      "learning_rate": 3.9673300982376315e-06,
+      "loss": 0.0087,
+      "step": 279
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.6760286688804626,
+      "learning_rate": 3.956640521566989e-06,
+      "loss": 0.0123,
+      "step": 280
+    },
+    {
+      "epoch": 2.4224137931034484,
+      "grad_norm": 0.4143922030925751,
+      "learning_rate": 3.945910472529068e-06,
+      "loss": 0.0056,
+      "step": 281
+    },
+    {
+      "epoch": 2.4310344827586206,
+      "grad_norm": 0.4239058792591095,
+      "learning_rate": 3.935140249255412e-06,
+      "loss": 0.009,
+      "step": 282
+    },
+    {
+      "epoch": 2.439655172413793,
+      "grad_norm": 0.495762437582016,
+      "learning_rate": 3.924330150993793e-06,
+      "loss": 0.0091,
+      "step": 283
+    },
+    {
+      "epoch": 2.4482758620689653,
+      "grad_norm": 0.46725037693977356,
+      "learning_rate": 3.913480478099898e-06,
+      "loss": 0.0066,
+      "step": 284
+    },
+    {
+      "epoch": 2.456896551724138,
+      "grad_norm": 0.501814603805542,
+      "learning_rate": 3.902591532028989e-06,
+      "loss": 0.0087,
+      "step": 285
+    },
+    {
+      "epoch": 2.4655172413793105,
+      "grad_norm": 0.38845211267471313,
+      "learning_rate": 3.891663615327518e-06,
+      "loss": 0.0059,
+      "step": 286
+    },
+    {
+      "epoch": 2.4741379310344827,
+      "grad_norm": 0.3252674639225006,
+      "learning_rate": 3.880697031624729e-06,
+      "loss": 0.0049,
+      "step": 287
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 0.3237666189670563,
+      "learning_rate": 3.869692085624218e-06,
+      "loss": 0.0062,
+      "step": 288
+    },
+    {
+      "epoch": 2.4913793103448274,
+      "grad_norm": 0.4213542342185974,
+      "learning_rate": 3.858649083095463e-06,
+      "loss": 0.0093,
+      "step": 289
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.6313378810882568,
+      "learning_rate": 3.8475683308653385e-06,
+      "loss": 0.0082,
+      "step": 290
+    },
+    {
+      "epoch": 2.5086206896551726,
+      "grad_norm": 1.0402452945709229,
+      "learning_rate": 3.836450136809579e-06,
+      "loss": 0.0078,
+      "step": 291
+    },
+    {
+      "epoch": 2.5172413793103448,
+      "grad_norm": 0.6053091287612915,
+      "learning_rate": 3.825294809844234e-06,
+      "loss": 0.0044,
+      "step": 292
+    },
+    {
+      "epoch": 2.5258620689655173,
+      "grad_norm": 0.6727966666221619,
+      "learning_rate": 3.8141026599170792e-06,
+      "loss": 0.0135,
+      "step": 293
+    },
+    {
+      "epoch": 2.5344827586206895,
+      "grad_norm": 0.3446575105190277,
+      "learning_rate": 3.8028739979990072e-06,
+      "loss": 0.0063,
+      "step": 294
+    },
+    {
+      "epoch": 2.543103448275862,
+      "grad_norm": 0.5400390028953552,
+      "learning_rate": 3.791609136075384e-06,
+      "loss": 0.0094,
+      "step": 295
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 0.2682323157787323,
+      "learning_rate": 3.7803083871373876e-06,
+      "loss": 0.0028,
+      "step": 296
+    },
+    {
+      "epoch": 2.560344827586207,
+      "grad_norm": 0.49711498618125916,
+      "learning_rate": 3.7689720651733034e-06,
+      "loss": 0.0085,
+      "step": 297
+    },
+    {
+      "epoch": 2.5689655172413794,
+      "grad_norm": 0.3905172646045685,
+      "learning_rate": 3.7576004851598052e-06,
+      "loss": 0.0065,
+      "step": 298
+    },
+    {
+      "epoch": 2.5775862068965516,
+      "grad_norm": 0.33470281958580017,
+      "learning_rate": 3.7461939630532018e-06,
+      "loss": 0.0061,
+      "step": 299
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.43622592091560364,
+      "learning_rate": 3.734752815780659e-06,
+      "loss": 0.008,
+      "step": 300
+    },
+    {
+      "epoch": 2.594827586206897,
+      "grad_norm": 0.40031933784484863,
+      "learning_rate": 3.7232773612313945e-06,
+      "loss": 0.0107,
+      "step": 301
+    },
+    {
+      "epoch": 2.603448275862069,
+      "grad_norm": 0.30814412236213684,
+      "learning_rate": 3.7117679182478415e-06,
+      "loss": 0.0042,
+      "step": 302
+    },
+    {
+      "epoch": 2.612068965517241,
+      "grad_norm": 0.16828757524490356,
+      "learning_rate": 3.7002248066167977e-06,
+      "loss": 0.0022,
+      "step": 303
+    },
+    {
+      "epoch": 2.6206896551724137,
+      "grad_norm": 0.3726310729980469,
+      "learning_rate": 3.6886483470605293e-06,
+      "loss": 0.0097,
+      "step": 304
+    },
+    {
+      "epoch": 2.6293103448275863,
+      "grad_norm": 0.47232842445373535,
+      "learning_rate": 3.6770388612278713e-06,
+      "loss": 0.0083,
+      "step": 305
+    },
+    {
+      "epoch": 2.637931034482759,
+      "grad_norm": 0.2700427770614624,
+      "learning_rate": 3.66539667168528e-06,
+      "loss": 0.0017,
+      "step": 306
+    },
+    {
+      "epoch": 2.646551724137931,
+      "grad_norm": 0.3362017273902893,
+      "learning_rate": 3.65372210190788e-06,
+      "loss": 0.0054,
+      "step": 307
+    },
+    {
+      "epoch": 2.655172413793103,
+      "grad_norm": 0.3315584063529968,
+      "learning_rate": 3.6420154762704685e-06,
+      "loss": 0.0032,
+      "step": 308
+    },
+    {
+      "epoch": 2.663793103448276,
+      "grad_norm": 0.656471312046051,
+      "learning_rate": 3.630277120038508e-06,
+      "loss": 0.0093,
+      "step": 309
+    },
+    {
+      "epoch": 2.6724137931034484,
+      "grad_norm": 1.8886873722076416,
+      "learning_rate": 3.6185073593590868e-06,
+      "loss": 0.01,
+      "step": 310
+    },
+    {
+      "epoch": 2.6810344827586206,
+      "grad_norm": 0.3265067934989929,
+      "learning_rate": 3.606706521251857e-06,
+      "loss": 0.0037,
+      "step": 311
+    },
+    {
+      "epoch": 2.689655172413793,
+      "grad_norm": 0.39972051978111267,
+      "learning_rate": 3.5948749335999493e-06,
+      "loss": 0.0066,
+      "step": 312
+    },
+    {
+      "epoch": 2.6982758620689653,
+      "grad_norm": 0.48707249760627747,
+      "learning_rate": 3.583012925140862e-06,
+      "loss": 0.0066,
+      "step": 313
+    },
+    {
+      "epoch": 2.706896551724138,
+      "grad_norm": 0.6093474626541138,
+      "learning_rate": 3.571120825457327e-06,
+      "loss": 0.007,
+      "step": 314
+    },
+    {
+      "epoch": 2.7155172413793105,
+      "grad_norm": 0.3256229758262634,
+      "learning_rate": 3.5591989649681534e-06,
+      "loss": 0.0054,
+      "step": 315
+    },
+    {
+      "epoch": 2.7241379310344827,
+      "grad_norm": 0.47791576385498047,
+      "learning_rate": 3.5472476749190465e-06,
+      "loss": 0.0048,
+      "step": 316
+    },
+    {
+      "epoch": 2.7327586206896552,
+      "grad_norm": 0.7635737061500549,
+      "learning_rate": 3.535267287373403e-06,
+      "loss": 0.006,
+      "step": 317
+    },
+    {
+      "epoch": 2.7413793103448274,
+      "grad_norm": 0.6153246164321899,
+      "learning_rate": 3.523258135203087e-06,
+      "loss": 0.0071,
+      "step": 318
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.22357748448848724,
+      "learning_rate": 3.5112205520791785e-06,
+      "loss": 0.0036,
+      "step": 319
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.3073960840702057,
+      "learning_rate": 3.4991548724627054e-06,
+      "loss": 0.0028,
+      "step": 320
+    },
+    {
+      "epoch": 2.7672413793103448,
+      "grad_norm": 0.17926068603992462,
+      "learning_rate": 3.48706143159535e-06,
+      "loss": 0.0028,
+      "step": 321
+    },
+    {
+      "epoch": 2.7758620689655173,
+      "grad_norm": 0.43959733843803406,
+      "learning_rate": 3.4749405654901297e-06,
+      "loss": 0.0027,
+      "step": 322
+    },
+    {
+      "epoch": 2.7844827586206895,
+      "grad_norm": 0.396281898021698,
+      "learning_rate": 3.4627926109220684e-06,
+      "loss": 0.0048,
+      "step": 323
+    },
+    {
+      "epoch": 2.793103448275862,
+      "grad_norm": 0.33752575516700745,
+      "learning_rate": 3.450617905418834e-06,
+      "loss": 0.0055,
+      "step": 324
+    },
+    {
+      "epoch": 2.8017241379310347,
+      "grad_norm": 0.3482801914215088,
+      "learning_rate": 3.4384167872513642e-06,
+      "loss": 0.0054,
+      "step": 325
+    },
+    {
+      "epoch": 2.810344827586207,
+      "grad_norm": 0.38212546706199646,
+      "learning_rate": 3.4261895954244613e-06,
+      "loss": 0.0051,
+      "step": 326
+    },
+    {
+      "epoch": 2.8189655172413794,
+      "grad_norm": 0.3641749918460846,
+      "learning_rate": 3.4139366696673815e-06,
+      "loss": 0.0056,
+      "step": 327
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.1609128713607788,
+      "learning_rate": 3.4016583504243892e-06,
+      "loss": 0.0028,
+      "step": 328
+    },
+    {
+      "epoch": 2.836206896551724,
+      "grad_norm": 0.2003130167722702,
+      "learning_rate": 3.3893549788453e-06,
+      "loss": 0.0023,
+      "step": 329
+    },
+    {
+      "epoch": 2.844827586206897,
+      "grad_norm": 0.4341651201248169,
+      "learning_rate": 3.3770268967760026e-06,
+      "loss": 0.006,
+      "step": 330
+    },
+    {
+      "epoch": 2.853448275862069,
+      "grad_norm": 0.28961309790611267,
+      "learning_rate": 3.36467444674896e-06,
+      "loss": 0.0022,
+      "step": 331
+    },
+    {
+      "epoch": 2.862068965517241,
+      "grad_norm": 0.35188788175582886,
+      "learning_rate": 3.3522979719736923e-06,
+      "loss": 0.0079,
+      "step": 332
+    },
+    {
+      "epoch": 2.8706896551724137,
+      "grad_norm": 0.3318072259426117,
+      "learning_rate": 3.339897816327241e-06,
+      "loss": 0.0038,
+      "step": 333
+    },
+    {
+      "epoch": 2.8793103448275863,
+      "grad_norm": 0.6669831871986389,
+      "learning_rate": 3.327474324344614e-06,
+      "loss": 0.0048,
+      "step": 334
+    },
+    {
+      "epoch": 2.887931034482759,
+      "grad_norm": 0.4758647084236145,
+      "learning_rate": 3.3150278412092126e-06,
+      "loss": 0.0031,
+      "step": 335
+    },
+    {
+      "epoch": 2.896551724137931,
+      "grad_norm": 0.45927631855010986,
+      "learning_rate": 3.3025587127432414e-06,
+      "loss": 0.0052,
+      "step": 336
+    },
+    {
+      "epoch": 2.905172413793103,
+      "grad_norm": 0.15748094022274017,
+      "learning_rate": 3.2900672853981e-06,
+      "loss": 0.002,
+      "step": 337
+    },
+    {
+      "epoch": 2.913793103448276,
+      "grad_norm": 0.2490128129720688,
+      "learning_rate": 3.2775539062447566e-06,
+      "loss": 0.0024,
+      "step": 338
+    },
+    {
+      "epoch": 2.9224137931034484,
+      "grad_norm": 0.16914480924606323,
+      "learning_rate": 3.265018922964102e-06,
+      "loss": 0.0035,
+      "step": 339
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 0.15188859403133392,
+      "learning_rate": 3.2524626838372976e-06,
+      "loss": 0.0013,
+      "step": 340
+    },
+    {
+      "epoch": 2.939655172413793,
+      "grad_norm": 0.8957772254943848,
+      "learning_rate": 3.239885537736085e-06,
+      "loss": 0.0029,
+      "step": 341
+    },
+    {
+      "epoch": 2.9482758620689653,
+      "grad_norm": 0.11430688202381134,
+      "learning_rate": 3.2272878341131074e-06,
+      "loss": 0.0009,
+      "step": 342
+    },
+    {
+      "epoch": 2.956896551724138,
+      "grad_norm": 0.2879055440425873,
+      "learning_rate": 3.2146699229921884e-06,
+      "loss": 0.0034,
+      "step": 343
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 0.4262220859527588,
+      "learning_rate": 3.202032154958615e-06,
+      "loss": 0.0043,
+      "step": 344
+    },
+    {
+      "epoch": 2.9741379310344827,
+      "grad_norm": 0.26130998134613037,
+      "learning_rate": 3.1893748811493926e-06,
+      "loss": 0.0013,
+      "step": 345
+    },
+    {
+      "epoch": 2.9827586206896552,
+      "grad_norm": 0.29305410385131836,
+      "learning_rate": 3.1766984532434853e-06,
+      "loss": 0.0035,
+      "step": 346
+    },
+    {
+      "epoch": 2.9913793103448274,
+      "grad_norm": 0.3302770256996155,
+      "learning_rate": 3.164003223452055e-06,
+      "loss": 0.0028,
+      "step": 347
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.41331973671913147,
+      "learning_rate": 3.151289544508664e-06,
+      "loss": 0.0042,
+      "step": 348
+    },
+    {
+      "epoch": 3.0086206896551726,
+      "grad_norm": 0.1458461433649063,
+      "learning_rate": 3.1385577696594816e-06,
+      "loss": 0.0012,
+      "step": 349
+    },
+    {
+      "epoch": 3.0172413793103448,
+      "grad_norm": 0.13347488641738892,
+      "learning_rate": 3.1258082526534665e-06,
+      "loss": 0.0012,
+      "step": 350
+    },
+    {
+      "epoch": 3.0258620689655173,
+      "grad_norm": 0.19563832879066467,
+      "learning_rate": 3.1130413477325398e-06,
+      "loss": 0.0013,
+      "step": 351
+    },
+    {
+      "epoch": 3.0344827586206895,
+      "grad_norm": 0.31846922636032104,
+      "learning_rate": 3.100257409621738e-06,
+      "loss": 0.0044,
+      "step": 352
+    },
+    {
+      "epoch": 3.043103448275862,
+      "grad_norm": 0.34810179471969604,
+      "learning_rate": 3.0874567935193624e-06,
+      "loss": 0.0008,
+      "step": 353
+    },
+    {
+      "epoch": 3.0517241379310347,
+      "grad_norm": 0.4476202130317688,
+      "learning_rate": 3.0746398550871093e-06,
+      "loss": 0.0028,
+      "step": 354
+    },
+    {
+      "epoch": 3.060344827586207,
+      "grad_norm": 0.33576491475105286,
+      "learning_rate": 3.061806950440183e-06,
+      "loss": 0.003,
+      "step": 355
+    },
+    {
+      "epoch": 3.0689655172413794,
+      "grad_norm": 0.3481740951538086,
+      "learning_rate": 3.0489584361374073e-06,
+      "loss": 0.0017,
+      "step": 356
+    },
+    {
+      "epoch": 3.0775862068965516,
+      "grad_norm": 0.2126464992761612,
+      "learning_rate": 3.0360946691713163e-06,
+      "loss": 0.0014,
+      "step": 357
+    },
+    {
+      "epoch": 3.086206896551724,
+      "grad_norm": 0.22430169582366943,
+      "learning_rate": 3.0232160069582335e-06,
+      "loss": 0.0012,
+      "step": 358
+    },
+    {
+      "epoch": 3.0948275862068964,
+      "grad_norm": 0.3447754681110382,
+      "learning_rate": 3.010322807328343e-06,
+      "loss": 0.0013,
+      "step": 359
+    },
+    {
+      "epoch": 3.103448275862069,
+      "grad_norm": 0.37295961380004883,
+      "learning_rate": 2.99741542851575e-06,
+      "loss": 0.0031,
+      "step": 360
+    },
+    {
+      "epoch": 3.1120689655172415,
+      "grad_norm": 0.3267655372619629,
+      "learning_rate": 2.98449422914852e-06,
+      "loss": 0.002,
+      "step": 361
+    },
+    {
+      "epoch": 3.1206896551724137,
+      "grad_norm": 0.2811220586299896,
+      "learning_rate": 2.9715595682387243e-06,
+      "loss": 0.0033,
+      "step": 362
+    },
+    {
+      "epoch": 3.1293103448275863,
+      "grad_norm": 0.7849671244621277,
+      "learning_rate": 2.9586118051724532e-06,
+      "loss": 0.0026,
+      "step": 363
+    },
+    {
+      "epoch": 3.1379310344827585,
+      "grad_norm": 0.26505476236343384,
+      "learning_rate": 2.945651299699843e-06,
+      "loss": 0.0039,
+      "step": 364
+    },
+    {
+      "epoch": 3.146551724137931,
+      "grad_norm": 0.3053433299064636,
+      "learning_rate": 2.9326784119250705e-06,
+      "loss": 0.0062,
+      "step": 365
+    },
+    {
+      "epoch": 3.1551724137931036,
+      "grad_norm": 0.3546666204929352,
+      "learning_rate": 2.9196935022963524e-06,
+      "loss": 0.0056,
+      "step": 366
+    },
+    {
+      "epoch": 3.163793103448276,
+      "grad_norm": 0.19328542053699493,
+      "learning_rate": 2.9066969315959305e-06,
+      "loss": 0.0013,
+      "step": 367
+    },
+    {
+      "epoch": 3.1724137931034484,
+      "grad_norm": 0.2915872037410736,
+      "learning_rate": 2.893689060930045e-06,
+      "loss": 0.0008,
+      "step": 368
+    },
+    {
+      "epoch": 3.1810344827586206,
+      "grad_norm": 0.25301098823547363,
+      "learning_rate": 2.8806702517189035e-06,
+      "loss": 0.0018,
+      "step": 369
+    },
+    {
+      "epoch": 3.189655172413793,
+      "grad_norm": 0.2005927562713623,
+      "learning_rate": 2.8676408656866356e-06,
+      "loss": 0.0018,
+      "step": 370
+    },
+    {
+      "epoch": 3.1982758620689653,
+      "grad_norm": 0.1574263870716095,
+      "learning_rate": 2.8546012648512504e-06,
+      "loss": 0.0007,
+      "step": 371
+    },
+    {
+      "epoch": 3.206896551724138,
+      "grad_norm": 0.18230217695236206,
+      "learning_rate": 2.8415518115145673e-06,
+      "loss": 0.0008,
+      "step": 372
+    },
+    {
+      "epoch": 3.2155172413793105,
+      "grad_norm": 0.17362555861473083,
+      "learning_rate": 2.828492868252157e-06,
+      "loss": 0.0012,
+      "step": 373
+    },
+    {
+      "epoch": 3.2241379310344827,
+      "grad_norm": 0.12085027992725372,
+      "learning_rate": 2.815424797903267e-06,
+      "loss": 0.0008,
+      "step": 374
+    },
+    {
+      "epoch": 3.2327586206896552,
+      "grad_norm": 0.08503284305334091,
+      "learning_rate": 2.8023479635607344e-06,
+      "loss": 0.0006,
+      "step": 375
+    },
+    {
+      "epoch": 3.2413793103448274,
+      "grad_norm": 0.32579341530799866,
+      "learning_rate": 2.7892627285609035e-06,
+      "loss": 0.0023,
+      "step": 376
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.11419796198606491,
+      "learning_rate": 2.7761694564735303e-06,
+      "loss": 0.0008,
+      "step": 377
+    },
+    {
+      "epoch": 3.2586206896551726,
+      "grad_norm": 0.2702169418334961,
+      "learning_rate": 2.763068511091678e-06,
+      "loss": 0.0018,
+      "step": 378
+    },
+    {
+      "epoch": 3.2672413793103448,
+      "grad_norm": 0.3495383560657501,
+      "learning_rate": 2.749960256421608e-06,
+      "loss": 0.0026,
+      "step": 379
+    },
+    {
+      "epoch": 3.2758620689655173,
+      "grad_norm": 0.1872117817401886,
+      "learning_rate": 2.7368450566726714e-06,
+      "loss": 0.0009,
+      "step": 380
+    },
+    {
+      "epoch": 3.2844827586206895,
+      "grad_norm": 0.11182069033384323,
+      "learning_rate": 2.7237232762471846e-06,
+      "loss": 0.0008,
+      "step": 381
+    },
+    {
+      "epoch": 3.293103448275862,
+      "grad_norm": 0.03204982727766037,
+      "learning_rate": 2.7105952797303083e-06,
+      "loss": 0.0002,
+      "step": 382
+    },
+    {
+      "epoch": 3.3017241379310347,
+      "grad_norm": 0.10610484331846237,
+      "learning_rate": 2.6974614318799118e-06,
+      "loss": 0.0006,
+      "step": 383
+    },
+    {
+      "epoch": 3.310344827586207,
+      "grad_norm": 0.039000194519758224,
+      "learning_rate": 2.684322097616448e-06,
+      "loss": 0.0003,
+      "step": 384
+    },
+    {
+      "epoch": 3.3189655172413794,
+      "grad_norm": 0.25091490149497986,
+      "learning_rate": 2.671177642012803e-06,
+      "loss": 0.0018,
+      "step": 385
+    },
+    {
+      "epoch": 3.3275862068965516,
+      "grad_norm": 0.03331621363759041,
+      "learning_rate": 2.658028430284159e-06,
+      "loss": 0.0002,
+      "step": 386
+    },
+    {
+      "epoch": 3.336206896551724,
+      "grad_norm": 0.1930539906024933,
+      "learning_rate": 2.644874827777849e-06,
+      "loss": 0.0014,
+      "step": 387
+    },
+    {
+      "epoch": 3.344827586206897,
+      "grad_norm": 0.16782906651496887,
+      "learning_rate": 2.6317171999631992e-06,
+      "loss": 0.0013,
+      "step": 388
+    },
+    {
+      "epoch": 3.353448275862069,
+      "grad_norm": 0.08973520249128342,
+      "learning_rate": 2.6185559124213794e-06,
+      "loss": 0.0004,
+      "step": 389
+    },
+    {
+      "epoch": 3.3620689655172415,
+      "grad_norm": 0.08465900272130966,
+      "learning_rate": 2.605391330835243e-06,
+      "loss": 0.0005,
+      "step": 390
+    },
+    {
+      "epoch": 3.3706896551724137,
+      "grad_norm": 0.1823631227016449,
+      "learning_rate": 2.5922238209791696e-06,
+      "loss": 0.0023,
+      "step": 391
+    },
+    {
+      "epoch": 3.3793103448275863,
+      "grad_norm": 0.07805266231298447,
+      "learning_rate": 2.5790537487088975e-06,
+      "loss": 0.0004,
+      "step": 392
+    },
+    {
+      "epoch": 3.3879310344827585,
+      "grad_norm": 0.1784096211194992,
+      "learning_rate": 2.565881479951362e-06,
+      "loss": 0.0012,
+      "step": 393
+    },
+    {
+      "epoch": 3.396551724137931,
+      "grad_norm": 0.0848960429430008,
+      "learning_rate": 2.552707380694528e-06,
+      "loss": 0.0005,
+      "step": 394
+    },
+    {
+      "epoch": 3.405172413793103,
+      "grad_norm": 0.2038225382566452,
+      "learning_rate": 2.539531816977219e-06,
+      "loss": 0.0012,
+      "step": 395
+    },
+    {
+      "epoch": 3.413793103448276,
+      "grad_norm": 0.2176526039838791,
+      "learning_rate": 2.5263551548789494e-06,
+      "loss": 0.0021,
+      "step": 396
+    },
+    {
+      "epoch": 3.4224137931034484,
+      "grad_norm": 1.042067050933838,
+      "learning_rate": 2.51317776050975e-06,
+      "loss": 0.003,
+      "step": 397
+    },
+    {
+      "epoch": 3.4310344827586206,
+      "grad_norm": 0.08978473395109177,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0007,
+      "step": 398
+    },
+    {
+      "epoch": 3.439655172413793,
+      "grad_norm": 0.07822535932064056,
+      "learning_rate": 2.4868222394902503e-06,
+      "loss": 0.0006,
+      "step": 399
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 0.11348029971122742,
+      "learning_rate": 2.4736448451210514e-06,
+      "loss": 0.0008,
+      "step": 400
+    },
+    {
+      "epoch": 3.456896551724138,
+      "grad_norm": 0.1684485524892807,
+      "learning_rate": 2.460468183022782e-06,
+      "loss": 0.0007,
+      "step": 401
+    },
+    {
+      "epoch": 3.4655172413793105,
+      "grad_norm": 0.2135872095823288,
+      "learning_rate": 2.447292619305473e-06,
+      "loss": 0.0015,
+      "step": 402
+    },
+    {
+      "epoch": 3.4741379310344827,
+      "grad_norm": 0.0703781470656395,
+      "learning_rate": 2.4341185200486387e-06,
+      "loss": 0.0005,
+      "step": 403
+    },
+    {
+      "epoch": 3.4827586206896552,
+      "grad_norm": 0.1052190512418747,
+      "learning_rate": 2.420946251291103e-06,
+      "loss": 0.0004,
+      "step": 404
+    },
+    {
+      "epoch": 3.4913793103448274,
+      "grad_norm": 0.10699443519115448,
+      "learning_rate": 2.4077761790208317e-06,
+      "loss": 0.0006,
+      "step": 405
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.3566197454929352,
+      "learning_rate": 2.3946086691647576e-06,
+      "loss": 0.0004,
+      "step": 406
+    },
+    {
+      "epoch": 3.5086206896551726,
+      "grad_norm": 0.26467472314834595,
+      "learning_rate": 2.3814440875786215e-06,
+      "loss": 0.0011,
+      "step": 407
+    },
+    {
+      "epoch": 3.5172413793103448,
+      "grad_norm": 0.04453529417514801,
+      "learning_rate": 2.368282800036801e-06,
+      "loss": 0.0003,
+      "step": 408
+    },
+    {
+      "epoch": 3.5258620689655173,
+      "grad_norm": 0.3083684742450714,
+      "learning_rate": 2.3551251722221526e-06,
+      "loss": 0.0005,
+      "step": 409
+    },
+    {
+      "epoch": 3.5344827586206895,
+      "grad_norm": 0.11275946348905563,
+      "learning_rate": 2.3419715697158414e-06,
+      "loss": 0.0006,
+      "step": 410
+    },
+    {
+      "epoch": 3.543103448275862,
+      "grad_norm": 0.20643529295921326,
+      "learning_rate": 2.3288223579871984e-06,
+      "loss": 0.0012,
+      "step": 411
+    },
+    {
+      "epoch": 3.5517241379310347,
+      "grad_norm": 0.20463480055332184,
+      "learning_rate": 2.315677902383553e-06,
+      "loss": 0.0008,
+      "step": 412
+    },
+    {
+      "epoch": 3.560344827586207,
+      "grad_norm": 0.05099180340766907,
+      "learning_rate": 2.3025385681200882e-06,
+      "loss": 0.0001,
+      "step": 413
+    },
+    {
+      "epoch": 3.5689655172413794,
+      "grad_norm": 0.0880790427327156,
+      "learning_rate": 2.289404720269693e-06,
+      "loss": 0.0005,
+      "step": 414
+    },
+    {
+      "epoch": 3.5775862068965516,
+      "grad_norm": 0.36317208409309387,
+      "learning_rate": 2.276276723752816e-06,
+      "loss": 0.0027,
+      "step": 415
+    },
+    {
+      "epoch": 3.586206896551724,
+      "grad_norm": 0.09729066491127014,
+      "learning_rate": 2.2631549433273294e-06,
+      "loss": 0.0003,
+      "step": 416
+    },
+    {
+      "epoch": 3.594827586206897,
+      "grad_norm": 0.13390637934207916,
+      "learning_rate": 2.2500397435783925e-06,
+      "loss": 0.0005,
+      "step": 417
+    },
+    {
+      "epoch": 3.603448275862069,
+      "grad_norm": 0.15281806886196136,
+      "learning_rate": 2.2369314889083234e-06,
+      "loss": 0.0009,
+      "step": 418
+    },
+    {
+      "epoch": 3.612068965517241,
+      "grad_norm": 0.05436816066503525,
+      "learning_rate": 2.2238305435264705e-06,
+      "loss": 0.0003,
+      "step": 419
+    },
+    {
+      "epoch": 3.6206896551724137,
+      "grad_norm": 0.20743894577026367,
+      "learning_rate": 2.2107372714390973e-06,
+      "loss": 0.0007,
+      "step": 420
+    },
+    {
+      "epoch": 3.6293103448275863,
+      "grad_norm": 0.0923997238278389,
+      "learning_rate": 2.1976520364392664e-06,
+      "loss": 0.0004,
+      "step": 421
+    },
+    {
+      "epoch": 3.637931034482759,
+      "grad_norm": 0.1782890260219574,
+      "learning_rate": 2.1845752020967335e-06,
+      "loss": 0.0005,
+      "step": 422
+    },
+    {
+      "epoch": 3.646551724137931,
+      "grad_norm": 0.2709210515022278,
+      "learning_rate": 2.1715071317478433e-06,
+      "loss": 0.0016,
+      "step": 423
+    },
+    {
+      "epoch": 3.655172413793103,
+      "grad_norm": 0.03978186100721359,
+      "learning_rate": 2.158448188485433e-06,
+      "loss": 0.0002,
+      "step": 424
+    },
+    {
+      "epoch": 3.663793103448276,
+      "grad_norm": 0.0696793794631958,
+      "learning_rate": 2.1453987351487504e-06,
+      "loss": 0.0003,
+      "step": 425
+    },
+    {
+      "epoch": 3.6724137931034484,
+      "grad_norm": 0.2356308102607727,
+      "learning_rate": 2.1323591343133644e-06,
+      "loss": 0.0013,
+      "step": 426
+    },
+    {
+      "epoch": 3.6810344827586206,
+      "grad_norm": 0.03700773045420647,
+      "learning_rate": 2.119329748281098e-06,
+      "loss": 0.0003,
+      "step": 427
+    },
+    {
+      "epoch": 3.689655172413793,
+      "grad_norm": 0.054152730852365494,
+      "learning_rate": 2.106310939069956e-06,
+      "loss": 0.0002,
+      "step": 428
+    },
+    {
+      "epoch": 3.6982758620689653,
+      "grad_norm": 0.16630911827087402,
+      "learning_rate": 2.0933030684040703e-06,
+      "loss": 0.0014,
+      "step": 429
+    },
+    {
+      "epoch": 3.706896551724138,
+      "grad_norm": 0.07690928876399994,
+      "learning_rate": 2.080306497703648e-06,
+      "loss": 0.0004,
+      "step": 430
+    },
+    {
+      "epoch": 3.7155172413793105,
+      "grad_norm": 0.27894601225852966,
+      "learning_rate": 2.0673215880749307e-06,
+      "loss": 0.0011,
+      "step": 431
+    },
+    {
+      "epoch": 3.7241379310344827,
+      "grad_norm": 0.14092902839183807,
+      "learning_rate": 2.054348700300158e-06,
+      "loss": 0.0005,
+      "step": 432
+    },
+    {
+      "epoch": 3.7327586206896552,
+      "grad_norm": 0.044833749532699585,
+      "learning_rate": 2.0413881948275476e-06,
+      "loss": 0.0003,
+      "step": 433
+    },
+    {
+      "epoch": 3.7413793103448274,
+      "grad_norm": 0.21889886260032654,
+      "learning_rate": 2.0284404317612765e-06,
+      "loss": 0.002,
+      "step": 434
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.07229331135749817,
+      "learning_rate": 2.01550577085148e-06,
+      "loss": 0.0003,
+      "step": 435
+    },
+    {
+      "epoch": 3.7586206896551726,
+      "grad_norm": 0.011932128109037876,
+      "learning_rate": 2.0025845714842514e-06,
+      "loss": 0.0001,
+      "step": 436
+    },
+    {
+      "epoch": 3.7672413793103448,
+      "grad_norm": 0.054304156452417374,
+      "learning_rate": 1.9896771926716574e-06,
+      "loss": 0.0004,
+      "step": 437
+    },
+    {
+      "epoch": 3.7758620689655173,
+      "grad_norm": 0.05861916020512581,
+      "learning_rate": 1.9767839930417673e-06,
+      "loss": 0.0003,
+      "step": 438
+    },
+    {
+      "epoch": 3.7844827586206895,
+      "grad_norm": 0.030074656009674072,
+      "learning_rate": 1.963905330828684e-06,
+      "loss": 0.0001,
+      "step": 439
+    },
+    {
+      "epoch": 3.793103448275862,
+      "grad_norm": 0.09362868964672089,
+      "learning_rate": 1.951041563862593e-06,
+      "loss": 0.0004,
+      "step": 440
+    },
+    {
+      "epoch": 3.8017241379310347,
+      "grad_norm": 0.021378953009843826,
+      "learning_rate": 1.9381930495598176e-06,
+      "loss": 0.0001,
+      "step": 441
+    },
+    {
+      "epoch": 3.810344827586207,
+      "grad_norm": 0.08444344252347946,
+      "learning_rate": 1.9253601449128915e-06,
+      "loss": 0.0005,
+      "step": 442
+    },
+    {
+      "epoch": 3.8189655172413794,
+      "grad_norm": 0.026262691244482994,
+      "learning_rate": 1.9125432064806376e-06,
+      "loss": 0.0002,
+      "step": 443
+    },
+    {
+      "epoch": 3.8275862068965516,
+      "grad_norm": 0.11125782132148743,
+      "learning_rate": 1.899742590378263e-06,
+      "loss": 0.0004,
+      "step": 444
+    },
+    {
+      "epoch": 3.836206896551724,
+      "grad_norm": 0.12721066176891327,
+      "learning_rate": 1.8869586522674615e-06,
+      "loss": 0.0004,
+      "step": 445
+    },
+    {
+      "epoch": 3.844827586206897,
+      "grad_norm": 0.023635324090719223,
+      "learning_rate": 1.8741917473465341e-06,
+      "loss": 0.0002,
+      "step": 446
+    },
+    {
+      "epoch": 3.853448275862069,
+      "grad_norm": 0.5198646783828735,
+      "learning_rate": 1.861442230340519e-06,
+      "loss": 0.0016,
+      "step": 447
+    },
+    {
+      "epoch": 3.862068965517241,
+      "grad_norm": 0.3609335720539093,
+      "learning_rate": 1.8487104554913362e-06,
+      "loss": 0.0013,
+      "step": 448
+    },
+    {
+      "epoch": 3.8706896551724137,
+      "grad_norm": 0.27512818574905396,
+      "learning_rate": 1.8359967765479465e-06,
+      "loss": 0.0011,
+      "step": 449
+    },
+    {
+      "epoch": 3.8793103448275863,
+      "grad_norm": 0.09016284346580505,
+      "learning_rate": 1.823301546756515e-06,
+      "loss": 0.0003,
+      "step": 450
+    },
+    {
+      "epoch": 3.887931034482759,
+      "grad_norm": 0.11690771579742432,
+      "learning_rate": 1.8106251188506082e-06,
+      "loss": 0.0006,
+      "step": 451
+    },
+    {
+      "epoch": 3.896551724137931,
+      "grad_norm": 0.09307470917701721,
+      "learning_rate": 1.7979678450413845e-06,
+      "loss": 0.0003,
+      "step": 452
+    },
+    {
+      "epoch": 3.905172413793103,
+      "grad_norm": 0.04047633707523346,
+      "learning_rate": 1.7853300770078124e-06,
+      "loss": 0.0002,
+      "step": 453
+    },
+    {
+      "epoch": 3.913793103448276,
+      "grad_norm": 0.10549729317426682,
+      "learning_rate": 1.7727121658868934e-06,
+      "loss": 0.0006,
+      "step": 454
+    },
+    {
+      "epoch": 3.9224137931034484,
+      "grad_norm": 0.1153617799282074,
+      "learning_rate": 1.7601144622639154e-06,
+      "loss": 0.0004,
+      "step": 455
+    },
+    {
+      "epoch": 3.9310344827586206,
+      "grad_norm": 0.3109404742717743,
+      "learning_rate": 1.7475373161627034e-06,
+      "loss": 0.0012,
+      "step": 456
+    },
+    {
+      "epoch": 3.939655172413793,
+      "grad_norm": 0.11449936032295227,
+      "learning_rate": 1.7349810770358977e-06,
+      "loss": 0.0004,
+      "step": 457
+    },
+    {
+      "epoch": 3.9482758620689653,
+      "grad_norm": 0.12818413972854614,
+      "learning_rate": 1.7224460937552449e-06,
+      "loss": 0.0009,
+      "step": 458
+    },
+    {
+      "epoch": 3.956896551724138,
+      "grad_norm": 0.05156997591257095,
+      "learning_rate": 1.709932714601901e-06,
+      "loss": 0.0003,
+      "step": 459
+    },
+    {
+      "epoch": 3.9655172413793105,
+      "grad_norm": 0.14590847492218018,
+      "learning_rate": 1.6974412872567598e-06,
+      "loss": 0.0008,
+      "step": 460
+    },
+    {
+      "epoch": 3.9741379310344827,
+      "grad_norm": 0.750783383846283,
+      "learning_rate": 1.6849721587907887e-06,
+      "loss": 0.0019,
+      "step": 461
+    },
+    {
+      "epoch": 3.9827586206896552,
+      "grad_norm": 0.1131512001156807,
+      "learning_rate": 1.672525675655387e-06,
+      "loss": 0.0007,
+      "step": 462
+    },
+    {
+      "epoch": 3.9913793103448274,
+      "grad_norm": 0.42991429567337036,
+      "learning_rate": 1.6601021836727597e-06,
+      "loss": 0.0008,
+      "step": 463
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.11112646013498306,
+      "learning_rate": 1.647702028026308e-06,
+      "loss": 0.0005,
+      "step": 464
+    },
+    {
+      "epoch": 4.008620689655173,
+      "grad_norm": 0.08795543015003204,
+      "learning_rate": 1.63532555325104e-06,
+      "loss": 0.0005,
+      "step": 465
+    },
+    {
+      "epoch": 4.017241379310345,
+      "grad_norm": 0.0381544753909111,
+      "learning_rate": 1.6229731032239986e-06,
+      "loss": 0.0002,
+      "step": 466
+    },
+    {
+      "epoch": 4.025862068965517,
+      "grad_norm": 0.025873109698295593,
+      "learning_rate": 1.6106450211547015e-06,
+      "loss": 0.0001,
+      "step": 467
+    },
+    {
+      "epoch": 4.0344827586206895,
+      "grad_norm": 0.0740472748875618,
+      "learning_rate": 1.5983416495756116e-06,
+      "loss": 0.0003,
+      "step": 468
+    },
+    {
+      "epoch": 4.043103448275862,
+      "grad_norm": 0.02801835909485817,
+      "learning_rate": 1.586063330332619e-06,
+      "loss": 0.0002,
+      "step": 469
+    },
+    {
+      "epoch": 4.051724137931035,
+      "grad_norm": 0.03600400686264038,
+      "learning_rate": 1.573810404575539e-06,
+      "loss": 0.0002,
+      "step": 470
+    },
+    {
+      "epoch": 4.060344827586207,
+      "grad_norm": 0.07549732178449631,
+      "learning_rate": 1.5615832127486368e-06,
+      "loss": 0.0004,
+      "step": 471
+    },
+    {
+      "epoch": 4.068965517241379,
+      "grad_norm": 0.0136073287576437,
+      "learning_rate": 1.549382094581166e-06,
+      "loss": 0.0001,
+      "step": 472
+    },
+    {
+      "epoch": 4.077586206896552,
+      "grad_norm": 0.03338685631752014,
+      "learning_rate": 1.537207389077932e-06,
+      "loss": 0.0002,
+      "step": 473
+    },
+    {
+      "epoch": 4.086206896551724,
+      "grad_norm": 0.018992526456713676,
+      "learning_rate": 1.5250594345098709e-06,
+      "loss": 0.0001,
+      "step": 474
+    },
+    {
+      "epoch": 4.094827586206897,
+      "grad_norm": 0.08795375376939774,
+      "learning_rate": 1.5129385684046512e-06,
+      "loss": 0.0004,
+      "step": 475
+    },
+    {
+      "epoch": 4.103448275862069,
+      "grad_norm": 0.014034583233296871,
+      "learning_rate": 1.5008451275372948e-06,
+      "loss": 0.0001,
+      "step": 476
+    },
+    {
+      "epoch": 4.112068965517241,
+      "grad_norm": 0.10508130490779877,
+      "learning_rate": 1.4887794479208224e-06,
+      "loss": 0.0003,
+      "step": 477
+    },
+    {
+      "epoch": 4.120689655172414,
+      "grad_norm": 0.29925230145454407,
+      "learning_rate": 1.4767418647969134e-06,
+      "loss": 0.0009,
+      "step": 478
+    },
+    {
+      "epoch": 4.129310344827586,
+      "grad_norm": 0.034915853291749954,
+      "learning_rate": 1.464732712626597e-06,
+      "loss": 0.0002,
+      "step": 479
+    },
+    {
+      "epoch": 4.137931034482759,
+      "grad_norm": 0.05039063096046448,
+      "learning_rate": 1.4527523250809544e-06,
+      "loss": 0.0002,
+      "step": 480
+    },
+    {
+      "epoch": 4.146551724137931,
+      "grad_norm": 0.01586967520415783,
+      "learning_rate": 1.4408010350318475e-06,
+      "loss": 0.0001,
+      "step": 481
+    },
+    {
+      "epoch": 4.155172413793103,
+      "grad_norm": 0.12373235076665878,
+      "learning_rate": 1.428879174542674e-06,
+      "loss": 0.0006,
+      "step": 482
+    },
+    {
+      "epoch": 4.163793103448276,
+      "grad_norm": 0.061160214245319366,
+      "learning_rate": 1.4169870748591388e-06,
+      "loss": 0.0002,
+      "step": 483
+    },
+    {
+      "epoch": 4.172413793103448,
+      "grad_norm": 0.0263685192912817,
+      "learning_rate": 1.4051250664000515e-06,
+      "loss": 0.0001,
+      "step": 484
+    },
+    {
+      "epoch": 4.181034482758621,
+      "grad_norm": 0.18039947748184204,
+      "learning_rate": 1.3932934787481437e-06,
+      "loss": 0.0006,
+      "step": 485
+    },
+    {
+      "epoch": 4.189655172413793,
+      "grad_norm": 0.03929466754198074,
+      "learning_rate": 1.381492640640914e-06,
+      "loss": 0.0003,
+      "step": 486
+    },
+    {
+      "epoch": 4.198275862068965,
+      "grad_norm": 0.04226909577846527,
+      "learning_rate": 1.3697228799614926e-06,
+      "loss": 0.0002,
+      "step": 487
+    },
+    {
+      "epoch": 4.206896551724138,
+      "grad_norm": 0.08892680704593658,
+      "learning_rate": 1.357984523729533e-06,
+      "loss": 0.0004,
+      "step": 488
+    },
+    {
+      "epoch": 4.2155172413793105,
+      "grad_norm": 0.034578073769807816,
+      "learning_rate": 1.3462778980921214e-06,
+      "loss": 0.0001,
+      "step": 489
+    },
+    {
+      "epoch": 4.224137931034483,
+      "grad_norm": 0.05692879110574722,
+      "learning_rate": 1.3346033283147196e-06,
+      "loss": 0.0002,
+      "step": 490
+    },
+    {
+      "epoch": 4.232758620689655,
+      "grad_norm": 0.05728021264076233,
+      "learning_rate": 1.3229611387721291e-06,
+      "loss": 0.0002,
+      "step": 491
+    },
+    {
+      "epoch": 4.241379310344827,
+      "grad_norm": 0.0304628424346447,
+      "learning_rate": 1.3113516529394705e-06,
+      "loss": 0.0002,
+      "step": 492
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.03307940065860748,
+      "learning_rate": 1.2997751933832038e-06,
+      "loss": 0.0002,
+      "step": 493
+    },
+    {
+      "epoch": 4.258620689655173,
+      "grad_norm": 0.03960256651043892,
+      "learning_rate": 1.2882320817521587e-06,
+      "loss": 0.0001,
+      "step": 494
+    },
+    {
+      "epoch": 4.267241379310345,
+      "grad_norm": 0.09631030261516571,
+      "learning_rate": 1.2767226387686065e-06,
+      "loss": 0.0004,
+      "step": 495
+    },
+    {
+      "epoch": 4.275862068965517,
+      "grad_norm": 0.048445411026477814,
+      "learning_rate": 1.2652471842193415e-06,
+      "loss": 0.0002,
+      "step": 496
+    },
+    {
+      "epoch": 4.2844827586206895,
+      "grad_norm": 0.019632607698440552,
+      "learning_rate": 1.2538060369467989e-06,
+      "loss": 0.0001,
+      "step": 497
+    },
+    {
+      "epoch": 4.293103448275862,
+      "grad_norm": 0.05726362392306328,
+      "learning_rate": 1.2423995148401954e-06,
+      "loss": 0.0002,
+      "step": 498
+    },
+    {
+      "epoch": 4.301724137931035,
+      "grad_norm": 0.008523290976881981,
+      "learning_rate": 1.231027934826697e-06,
+      "loss": 0.0001,
+      "step": 499
+    },
+    {
+      "epoch": 4.310344827586207,
+      "grad_norm": 0.1245892345905304,
+      "learning_rate": 1.2196916128626126e-06,
+      "loss": 0.0006,
+      "step": 500
+    },
+    {
+      "epoch": 4.318965517241379,
+      "grad_norm": 0.018376415595412254,
+      "learning_rate": 1.2083908639246169e-06,
+      "loss": 0.0001,
+      "step": 501
+    },
+    {
+      "epoch": 4.327586206896552,
+      "grad_norm": 0.027295252308249474,
+      "learning_rate": 1.1971260020009944e-06,
+      "loss": 0.0002,
+      "step": 502
+    },
+    {
+      "epoch": 4.336206896551724,
+      "grad_norm": 0.020805874839425087,
+      "learning_rate": 1.1858973400829208e-06,
+      "loss": 0.0002,
+      "step": 503
+    },
+    {
+      "epoch": 4.344827586206897,
+      "grad_norm": 0.015192719176411629,
+      "learning_rate": 1.174705190155766e-06,
+      "loss": 0.0001,
+      "step": 504
+    },
+    {
+      "epoch": 4.353448275862069,
+      "grad_norm": 0.03198520466685295,
+      "learning_rate": 1.163549863190421e-06,
+      "loss": 0.0002,
+      "step": 505
+    },
+    {
+      "epoch": 4.362068965517241,
+      "grad_norm": 0.038549166172742844,
+      "learning_rate": 1.152431669134663e-06,
+      "loss": 0.0002,
+      "step": 506
+    },
+    {
+      "epoch": 4.370689655172414,
+      "grad_norm": 0.01120319589972496,
+      "learning_rate": 1.1413509169045376e-06,
+      "loss": 0.0001,
+      "step": 507
+    },
+    {
+      "epoch": 4.379310344827586,
+      "grad_norm": 0.07101059705018997,
+      "learning_rate": 1.1303079143757831e-06,
+      "loss": 0.0002,
+      "step": 508
+    },
+    {
+      "epoch": 4.387931034482759,
+      "grad_norm": 0.03514993190765381,
+      "learning_rate": 1.1193029683752712e-06,
+      "loss": 0.0002,
+      "step": 509
+    },
+    {
+      "epoch": 4.396551724137931,
+      "grad_norm": 0.015733392909169197,
+      "learning_rate": 1.1083363846724824e-06,
+      "loss": 0.0001,
+      "step": 510
+    },
+    {
+      "epoch": 4.405172413793103,
+      "grad_norm": 0.07725036144256592,
+      "learning_rate": 1.097408467971012e-06,
+      "loss": 0.0002,
+      "step": 511
+    },
+    {
+      "epoch": 4.413793103448276,
+      "grad_norm": 0.03870030492544174,
+      "learning_rate": 1.0865195219001028e-06,
+      "loss": 0.0001,
+      "step": 512
+    },
+    {
+      "epoch": 4.422413793103448,
+      "grad_norm": 0.041263483464717865,
+      "learning_rate": 1.0756698490062085e-06,
+      "loss": 0.0001,
+      "step": 513
+    },
+    {
+      "epoch": 4.431034482758621,
+      "grad_norm": 0.028052903711795807,
+      "learning_rate": 1.0648597507445884e-06,
+      "loss": 0.0001,
+      "step": 514
+    },
+    {
+      "epoch": 4.439655172413793,
+      "grad_norm": 0.020984163507819176,
+      "learning_rate": 1.0540895274709325e-06,
+      "loss": 0.0001,
+      "step": 515
+    },
+    {
+      "epoch": 4.448275862068965,
+      "grad_norm": 0.006086215376853943,
+      "learning_rate": 1.043359478433012e-06,
+      "loss": 0.0001,
+      "step": 516
+    },
+    {
+      "epoch": 4.456896551724138,
+      "grad_norm": 0.022190986201167107,
+      "learning_rate": 1.0326699017623689e-06,
+      "loss": 0.0001,
+      "step": 517
+    },
+    {
+      "epoch": 4.4655172413793105,
+      "grad_norm": 0.02403254061937332,
+      "learning_rate": 1.022021094466034e-06,
+      "loss": 0.0001,
+      "step": 518
+    },
+    {
+      "epoch": 4.474137931034483,
+      "grad_norm": 0.017441941425204277,
+      "learning_rate": 1.0114133524182696e-06,
+      "loss": 0.0001,
+      "step": 519
+    },
+    {
+      "epoch": 4.482758620689655,
+      "grad_norm": 0.029313763603568077,
+      "learning_rate": 1.0008469703523493e-06,
+      "loss": 0.0001,
+      "step": 520
+    },
+    {
+      "epoch": 4.491379310344827,
+      "grad_norm": 0.016915587708353996,
+      "learning_rate": 9.903222418523739e-07,
+      "loss": 0.0001,
+      "step": 521
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.03886621445417404,
+      "learning_rate": 9.798394593451092e-07,
+      "loss": 0.0001,
+      "step": 522
+    },
+    {
+      "epoch": 4.508620689655173,
+      "grad_norm": 0.007353832945227623,
+      "learning_rate": 9.693989140918635e-07,
+      "loss": 0.0001,
+      "step": 523
+    },
+    {
+      "epoch": 4.517241379310345,
+      "grad_norm": 0.00810723565518856,
+      "learning_rate": 9.590008961803942e-07,
+      "loss": 0.0001,
+      "step": 524
+    },
+    {
+      "epoch": 4.525862068965517,
+      "grad_norm": 0.21131834387779236,
+      "learning_rate": 9.486456945168476e-07,
+      "loss": 0.0003,
+      "step": 525
+    },
+    {
+      "epoch": 4.5344827586206895,
+      "grad_norm": 0.034072235226631165,
+      "learning_rate": 9.383335968177324e-07,
+      "loss": 0.0001,
+      "step": 526
+    },
+    {
+      "epoch": 4.543103448275862,
+      "grad_norm": 0.035911768674850464,
+      "learning_rate": 9.280648896019245e-07,
+      "loss": 0.0001,
+      "step": 527
+    },
+    {
+      "epoch": 4.551724137931035,
+      "grad_norm": 0.027105217799544334,
+      "learning_rate": 9.178398581827086e-07,
+      "loss": 0.0002,
+      "step": 528
+    },
+    {
+      "epoch": 4.560344827586206,
+      "grad_norm": 0.020529363304376602,
+      "learning_rate": 9.07658786659846e-07,
+      "loss": 0.0001,
+      "step": 529
+    },
+    {
+      "epoch": 4.568965517241379,
+      "grad_norm": 0.03402241691946983,
+      "learning_rate": 8.975219579116865e-07,
+      "loss": 0.0001,
+      "step": 530
+    },
+    {
+      "epoch": 4.577586206896552,
+      "grad_norm": 0.03538055345416069,
+      "learning_rate": 8.874296535873044e-07,
+      "loss": 0.0002,
+      "step": 531
+    },
+    {
+      "epoch": 4.586206896551724,
+      "grad_norm": 0.011194778606295586,
+      "learning_rate": 8.77382154098679e-07,
+      "loss": 0.0001,
+      "step": 532
+    },
+    {
+      "epoch": 4.594827586206897,
+      "grad_norm": 0.029824107885360718,
+      "learning_rate": 8.673797386128932e-07,
+      "loss": 0.0001,
+      "step": 533
+    },
+    {
+      "epoch": 4.603448275862069,
+      "grad_norm": 0.04908660054206848,
+      "learning_rate": 8.574226850443873e-07,
+      "loss": 0.0001,
+      "step": 534
+    },
+    {
+      "epoch": 4.612068965517241,
+      "grad_norm": 0.0360528863966465,
+      "learning_rate": 8.475112700472307e-07,
+      "loss": 0.0002,
+      "step": 535
+    },
+    {
+      "epoch": 4.620689655172414,
+      "grad_norm": 0.05588826164603233,
+      "learning_rate": 8.376457690074386e-07,
+      "loss": 0.0002,
+      "step": 536
+    },
+    {
+      "epoch": 4.629310344827586,
+      "grad_norm": 0.23618784546852112,
+      "learning_rate": 8.278264560353183e-07,
+      "loss": 0.0011,
+      "step": 537
+    },
+    {
+      "epoch": 4.637931034482759,
+      "grad_norm": 0.050062019377946854,
+      "learning_rate": 8.180536039578546e-07,
+      "loss": 0.0002,
+      "step": 538
+    },
+    {
+      "epoch": 4.646551724137931,
+      "grad_norm": 0.027577703818678856,
+      "learning_rate": 8.083274843111282e-07,
+      "loss": 0.0001,
+      "step": 539
+    },
+    {
+      "epoch": 4.655172413793103,
+      "grad_norm": 0.01449573878198862,
+      "learning_rate": 7.986483673327724e-07,
+      "loss": 0.0001,
+      "step": 540
+    },
+    {
+      "epoch": 4.663793103448276,
+      "grad_norm": 0.020338334143161774,
+      "learning_rate": 7.89016521954464e-07,
+      "loss": 0.0001,
+      "step": 541
+    },
+    {
+      "epoch": 4.672413793103448,
+      "grad_norm": 0.009396952576935291,
+      "learning_rate": 7.794322157944489e-07,
+      "loss": 0.0001,
+      "step": 542
+    },
+    {
+      "epoch": 4.681034482758621,
+      "grad_norm": 0.012877953238785267,
+      "learning_rate": 7.698957151501113e-07,
+      "loss": 0.0001,
+      "step": 543
+    },
+    {
+      "epoch": 4.689655172413794,
+      "grad_norm": 0.019344555214047432,
+      "learning_rate": 7.604072849905708e-07,
+      "loss": 0.0001,
+      "step": 544
+    },
+    {
+      "epoch": 4.698275862068965,
+      "grad_norm": 0.2258051335811615,
+      "learning_rate": 7.509671889493215e-07,
+      "loss": 0.0005,
+      "step": 545
+    },
+    {
+      "epoch": 4.706896551724138,
+      "grad_norm": 0.022811248898506165,
+      "learning_rate": 7.415756893169063e-07,
+      "loss": 0.0001,
+      "step": 546
+    },
+    {
+      "epoch": 4.7155172413793105,
+      "grad_norm": 0.015631260350346565,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.0001,
+      "step": 547
+    },
+    {
+      "epoch": 4.724137931034483,
+      "grad_norm": 0.014984537847340107,
+      "learning_rate": 7.229395216823132e-07,
+      "loss": 0.0001,
+      "step": 548
+    },
+    {
+      "epoch": 4.732758620689655,
+      "grad_norm": 0.010196071118116379,
+      "learning_rate": 7.136953714810682e-07,
+      "loss": 0.0001,
+      "step": 549
+    },
+    {
+      "epoch": 4.741379310344827,
+      "grad_norm": 0.02455035224556923,
+      "learning_rate": 7.045008532761366e-07,
+      "loss": 0.0001,
+      "step": 550
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 0.010271081700921059,
+      "learning_rate": 6.95356222534748e-07,
+      "loss": 0.0001,
+      "step": 551
+    },
+    {
+      "epoch": 4.758620689655173,
+      "grad_norm": 0.029762504622340202,
+      "learning_rate": 6.862617333380214e-07,
+      "loss": 0.0002,
+      "step": 552
+    },
+    {
+      "epoch": 4.767241379310345,
+      "grad_norm": 0.0284776221960783,
+      "learning_rate": 6.772176383739065e-07,
+      "loss": 0.0001,
+      "step": 553
+    },
+    {
+      "epoch": 4.775862068965517,
+      "grad_norm": 0.046974748373031616,
+      "learning_rate": 6.682241889301636e-07,
+      "loss": 0.0002,
+      "step": 554
+    },
+    {
+      "epoch": 4.7844827586206895,
+      "grad_norm": 0.04300546646118164,
+      "learning_rate": 6.592816348873785e-07,
+      "loss": 0.0001,
+      "step": 555
+    },
+    {
+      "epoch": 4.793103448275862,
+      "grad_norm": 0.10295592993497849,
+      "learning_rate": 6.503902247120239e-07,
+      "loss": 0.0002,
+      "step": 556
+    },
+    {
+      "epoch": 4.801724137931035,
+      "grad_norm": 0.027378961443901062,
+      "learning_rate": 6.41550205449554e-07,
+      "loss": 0.0001,
+      "step": 557
+    },
+    {
+      "epoch": 4.810344827586206,
+      "grad_norm": 0.05989762395620346,
+      "learning_rate": 6.327618227175389e-07,
+      "loss": 0.0002,
+      "step": 558
+    },
+    {
+      "epoch": 4.818965517241379,
+      "grad_norm": 0.019639194011688232,
+      "learning_rate": 6.240253206988422e-07,
+      "loss": 0.0001,
+      "step": 559
+    },
+    {
+      "epoch": 4.827586206896552,
+      "grad_norm": 0.010606248863041401,
+      "learning_rate": 6.153409421348358e-07,
+      "loss": 0.0001,
+      "step": 560
+    },
+    {
+      "epoch": 4.836206896551724,
+      "grad_norm": 0.010039673186838627,
+      "learning_rate": 6.067089283186555e-07,
+      "loss": 0.0001,
+      "step": 561
+    },
+    {
+      "epoch": 4.844827586206897,
+      "grad_norm": 0.01142662763595581,
+      "learning_rate": 5.981295190884962e-07,
+      "loss": 0.0001,
+      "step": 562
+    },
+    {
+      "epoch": 4.853448275862069,
+      "grad_norm": 0.02358933351933956,
+      "learning_rate": 5.89602952820949e-07,
+      "loss": 0.0001,
+      "step": 563
+    },
+    {
+      "epoch": 4.862068965517241,
+      "grad_norm": 0.06325159221887589,
+      "learning_rate": 5.811294664243752e-07,
+      "loss": 0.0002,
+      "step": 564
+    },
+    {
+      "epoch": 4.870689655172414,
+      "grad_norm": 0.022270936518907547,
+      "learning_rate": 5.727092953323299e-07,
+      "loss": 0.0001,
+      "step": 565
+    },
+    {
+      "epoch": 4.879310344827586,
+      "grad_norm": 0.04418841376900673,
+      "learning_rate": 5.64342673497014e-07,
+      "loss": 0.0002,
+      "step": 566
+    },
+    {
+      "epoch": 4.887931034482759,
+      "grad_norm": 0.048862069845199585,
+      "learning_rate": 5.560298333827782e-07,
+      "loss": 0.0002,
+      "step": 567
+    },
+    {
+      "epoch": 4.896551724137931,
+      "grad_norm": 0.022158561274409294,
+      "learning_rate": 5.4777100595966e-07,
+      "loss": 0.0002,
+      "step": 568
+    },
+    {
+      "epoch": 4.905172413793103,
+      "grad_norm": 0.00710646528750658,
+      "learning_rate": 5.395664206969712e-07,
+      "loss": 0.0001,
+      "step": 569
+    },
+    {
+      "epoch": 4.913793103448276,
+      "grad_norm": 0.03146041929721832,
+      "learning_rate": 5.314163055569188e-07,
+      "loss": 0.0002,
+      "step": 570
+    },
+    {
+      "epoch": 4.922413793103448,
+      "grad_norm": 0.048966363072395325,
+      "learning_rate": 5.23320886988272e-07,
+      "loss": 0.0002,
+      "step": 571
+    },
+    {
+      "epoch": 4.931034482758621,
+      "grad_norm": 0.0071070631965994835,
+      "learning_rate": 5.1528038992007e-07,
+      "loss": 0.0001,
+      "step": 572
+    },
+    {
+      "epoch": 4.939655172413794,
+      "grad_norm": 0.06218729913234711,
+      "learning_rate": 5.07295037755374e-07,
+      "loss": 0.0001,
+      "step": 573
+    },
+    {
+      "epoch": 4.948275862068965,
+      "grad_norm": 0.021700145676732063,
+      "learning_rate": 4.993650523650575e-07,
+      "loss": 0.0001,
+      "step": 574
+    },
+    {
+      "epoch": 4.956896551724138,
+      "grad_norm": 0.006461620330810547,
+      "learning_rate": 4.914906540816436e-07,
+      "loss": 0.0001,
+      "step": 575
+    },
+    {
+      "epoch": 4.9655172413793105,
+      "grad_norm": 0.00985821895301342,
+      "learning_rate": 4.836720616931831e-07,
+      "loss": 0.0001,
+      "step": 576
+    },
+    {
+      "epoch": 4.974137931034483,
+      "grad_norm": 0.011432650499045849,
+      "learning_rate": 4.7590949243717323e-07,
+      "loss": 0.0001,
+      "step": 577
+    },
+    {
+      "epoch": 4.982758620689655,
+      "grad_norm": 0.007266015280038118,
+      "learning_rate": 4.682031619945238e-07,
+      "loss": 0.0001,
+      "step": 578
+    },
+    {
+      "epoch": 4.991379310344827,
+      "grad_norm": 0.009189185686409473,
+      "learning_rate": 4.605532844835667e-07,
+      "loss": 0.0001,
+      "step": 579
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.08564585447311401,
+      "learning_rate": 4.5296007245410225e-07,
+      "loss": 0.0003,
+      "step": 580
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 696,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 116,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2992829423248998e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}