diff --git "a/checkpoint-750/trainer_state.json" "b/checkpoint-750/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-750/trainer_state.json"
@@ -0,0 +1,5443 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.525252525252525,
+  "eval_steps": 38,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003367003367003367,
+      "grad_norm": 2.0,
+      "learning_rate": 4.5454545454545457e-07,
+      "loss": 1.0833,
+      "step": 1
+    },
+    {
+      "epoch": 0.003367003367003367,
+      "eval_loss": 1.032954454421997,
+      "eval_runtime": 8.7786,
+      "eval_samples_per_second": 56.957,
+      "eval_steps_per_second": 3.645,
+      "step": 1
+    },
+    {
+      "epoch": 0.006734006734006734,
+      "grad_norm": 2.265625,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.996,
+      "step": 2
+    },
+    {
+      "epoch": 0.010101010101010102,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.3636363636363636e-06,
+      "loss": 1.0487,
+      "step": 3
+    },
+    {
+      "epoch": 0.013468013468013467,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.0554,
+      "step": 4
+    },
+    {
+      "epoch": 0.016835016835016835,
+      "grad_norm": 2.4375,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 1.0341,
+      "step": 5
+    },
+    {
+      "epoch": 0.020202020202020204,
+      "grad_norm": 1.9609375,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 1.0132,
+      "step": 6
+    },
+    {
+      "epoch": 0.02356902356902357,
+      "grad_norm": 2.625,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 1.0298,
+      "step": 7
+    },
+    {
+      "epoch": 0.026936026936026935,
+      "grad_norm": 2.296875,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.0216,
+      "step": 8
+    },
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 2.234375,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 1.0736,
+      "step": 9
+    },
+    {
+      "epoch": 0.03367003367003367,
+      "grad_norm": 2.1875,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.0216,
+      "step": 10
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 2.359375,
+      "learning_rate": 5e-06,
+      "loss": 1.0075,
+      "step": 11
+    },
+    {
+      "epoch": 0.04040404040404041,
+      "grad_norm": 1.890625,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 1.051,
+      "step": 12
+    },
+    {
+      "epoch": 0.04377104377104377,
+      "grad_norm": 1.90625,
+      "learning_rate": 5.90909090909091e-06,
+      "loss": 1.0655,
+      "step": 13
+    },
+    {
+      "epoch": 0.04713804713804714,
+      "grad_norm": 1.6484375,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 1.0297,
+      "step": 14
+    },
+    {
+      "epoch": 0.050505050505050504,
+      "grad_norm": 1.6953125,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 1.0411,
+      "step": 15
+    },
+    {
+      "epoch": 0.05387205387205387,
+      "grad_norm": 1.9921875,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.0618,
+      "step": 16
+    },
+    {
+      "epoch": 0.05723905723905724,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 1.0052,
+      "step": 17
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 1.0053,
+      "step": 18
+    },
+    {
+      "epoch": 0.06397306397306397,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.9786,
+      "step": 19
+    },
+    {
+      "epoch": 0.06734006734006734,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.0419,
+      "step": 20
+    },
+    {
+      "epoch": 0.0707070707070707,
+      "grad_norm": 1.1484375,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 1.0356,
+      "step": 21
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 1.28125,
+      "learning_rate": 1e-05,
+      "loss": 0.9778,
+      "step": 22
+    },
+    {
+      "epoch": 0.07744107744107744,
+      "grad_norm": 1.1875,
+      "learning_rate": 1.0454545454545455e-05,
+      "loss": 0.9691,
+      "step": 23
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 1.1953125,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 1.0408,
+      "step": 24
+    },
+    {
+      "epoch": 0.08417508417508418,
+      "grad_norm": 1.078125,
+      "learning_rate": 1.1363636363636366e-05,
+      "loss": 0.9799,
+      "step": 25
+    },
+    {
+      "epoch": 0.08754208754208755,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.181818181818182e-05,
+      "loss": 0.9756,
+      "step": 26
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 1.1875,
+      "learning_rate": 1.2272727272727274e-05,
+      "loss": 1.0451,
+      "step": 27
+    },
+    {
+      "epoch": 0.09427609427609428,
+      "grad_norm": 1.0546875,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 1.0093,
+      "step": 28
+    },
+    {
+      "epoch": 0.09764309764309764,
+      "grad_norm": 0.96484375,
+      "learning_rate": 1.3181818181818183e-05,
+      "loss": 0.99,
+      "step": 29
+    },
+    {
+      "epoch": 0.10101010101010101,
+      "grad_norm": 1.0703125,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 1.0079,
+      "step": 30
+    },
+    {
+      "epoch": 0.10437710437710437,
+      "grad_norm": 0.89453125,
+      "learning_rate": 1.4090909090909092e-05,
+      "loss": 0.9653,
+      "step": 31
+    },
+    {
+      "epoch": 0.10774410774410774,
+      "grad_norm": 1.0546875,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.9926,
+      "step": 32
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.96875,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.9857,
+      "step": 33
+    },
+    {
+      "epoch": 0.11447811447811448,
+      "grad_norm": 1.1484375,
+      "learning_rate": 1.5454545454545454e-05,
+      "loss": 0.9676,
+      "step": 34
+    },
+    {
+      "epoch": 0.11784511784511785,
+      "grad_norm": 1.078125,
+      "learning_rate": 1.590909090909091e-05,
+      "loss": 0.9686,
+      "step": 35
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 0.8203125,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.9182,
+      "step": 36
+    },
+    {
+      "epoch": 0.12457912457912458,
+      "grad_norm": 0.8515625,
+      "learning_rate": 1.681818181818182e-05,
+      "loss": 0.9506,
+      "step": 37
+    },
+    {
+      "epoch": 0.12794612794612795,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.7272727272727274e-05,
+      "loss": 0.9533,
+      "step": 38
+    },
+    {
+      "epoch": 0.12794612794612795,
+      "eval_loss": 0.9329763054847717,
+      "eval_runtime": 8.7095,
+      "eval_samples_per_second": 57.409,
+      "eval_steps_per_second": 3.674,
+      "step": 38
+    },
+    {
+      "epoch": 0.13131313131313133,
+      "grad_norm": 0.7890625,
+      "learning_rate": 1.772727272727273e-05,
+      "loss": 0.9225,
+      "step": 39
+    },
+    {
+      "epoch": 0.13468013468013468,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.9378,
+      "step": 40
+    },
+    {
+      "epoch": 0.13804713804713806,
+      "grad_norm": 1.046875,
+      "learning_rate": 1.8636363636363638e-05,
+      "loss": 0.8982,
+      "step": 41
+    },
+    {
+      "epoch": 0.1414141414141414,
+      "grad_norm": 0.94921875,
+      "learning_rate": 1.9090909090909094e-05,
+      "loss": 0.8958,
+      "step": 42
+    },
+    {
+      "epoch": 0.1447811447811448,
+      "grad_norm": 0.9765625,
+      "learning_rate": 1.9545454545454546e-05,
+      "loss": 0.8796,
+      "step": 43
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.92578125,
+      "learning_rate": 2e-05,
+      "loss": 0.8808,
+      "step": 44
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 0.94921875,
+      "learning_rate": 1.9999931213623708e-05,
+      "loss": 0.8638,
+      "step": 45
+    },
+    {
+      "epoch": 0.15488215488215487,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.999972485544114e-05,
+      "loss": 0.9124,
+      "step": 46
+    },
+    {
+      "epoch": 0.15824915824915825,
+      "grad_norm": 1.046875,
+      "learning_rate": 1.999938092829122e-05,
+      "loss": 0.8757,
+      "step": 47
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.999889943690545e-05,
+      "loss": 0.885,
+      "step": 48
+    },
+    {
+      "epoch": 0.16498316498316498,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.9998280387907845e-05,
+      "loss": 0.8664,
+      "step": 49
+    },
+    {
+      "epoch": 0.16835016835016836,
+      "grad_norm": 0.87109375,
+      "learning_rate": 1.9997523789814827e-05,
+      "loss": 0.8512,
+      "step": 50
+    },
+    {
+      "epoch": 0.1717171717171717,
+      "grad_norm": 0.80859375,
+      "learning_rate": 1.9996629653035128e-05,
+      "loss": 0.8428,
+      "step": 51
+    },
+    {
+      "epoch": 0.1750841750841751,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.9995597989869625e-05,
+      "loss": 0.8536,
+      "step": 52
+    },
+    {
+      "epoch": 0.17845117845117844,
+      "grad_norm": 0.6171875,
+      "learning_rate": 1.9994428814511205e-05,
+      "loss": 0.82,
+      "step": 53
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.999312214304453e-05,
+      "loss": 0.8043,
+      "step": 54
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 0.8046875,
+      "learning_rate": 1.9991677993445832e-05,
+      "loss": 0.8525,
+      "step": 55
+    },
+    {
+      "epoch": 0.18855218855218855,
+      "grad_norm": 0.6015625,
+      "learning_rate": 1.9990096385582682e-05,
+      "loss": 0.7958,
+      "step": 56
+    },
+    {
+      "epoch": 0.1919191919191919,
+      "grad_norm": 0.79296875,
+      "learning_rate": 1.998837734121369e-05,
+      "loss": 0.8001,
+      "step": 57
+    },
+    {
+      "epoch": 0.19528619528619529,
+      "grad_norm": 0.7109375,
+      "learning_rate": 1.9986520883988233e-05,
+      "loss": 0.805,
+      "step": 58
+    },
+    {
+      "epoch": 0.19865319865319866,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.9984527039446093e-05,
+      "loss": 0.7821,
+      "step": 59
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 1.1015625,
+      "learning_rate": 1.998239583501714e-05,
+      "loss": 0.7932,
+      "step": 60
+    },
+    {
+      "epoch": 0.2053872053872054,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.9980127300020946e-05,
+      "loss": 0.7925,
+      "step": 61
+    },
+    {
+      "epoch": 0.20875420875420875,
+      "grad_norm": 0.60546875,
+      "learning_rate": 1.9977721465666365e-05,
+      "loss": 0.7846,
+      "step": 62
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 0.7265625,
+      "learning_rate": 1.9975178365051123e-05,
+      "loss": 0.7671,
+      "step": 63
+    },
+    {
+      "epoch": 0.21548821548821548,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.997249803316136e-05,
+      "loss": 0.8194,
+      "step": 64
+    },
+    {
+      "epoch": 0.21885521885521886,
+      "grad_norm": 0.81640625,
+      "learning_rate": 1.9969680506871138e-05,
+      "loss": 0.7607,
+      "step": 65
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.9966725824941933e-05,
+      "loss": 0.7858,
+      "step": 66
+    },
+    {
+      "epoch": 0.2255892255892256,
+      "grad_norm": 0.66015625,
+      "learning_rate": 1.9963634028022133e-05,
+      "loss": 0.7546,
+      "step": 67
+    },
+    {
+      "epoch": 0.22895622895622897,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.9960405158646425e-05,
+      "loss": 0.7915,
+      "step": 68
+    },
+    {
+      "epoch": 0.23232323232323232,
+      "grad_norm": 0.59765625,
+      "learning_rate": 1.9957039261235263e-05,
+      "loss": 0.7324,
+      "step": 69
+    },
+    {
+      "epoch": 0.2356902356902357,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.9953536382094218e-05,
+      "loss": 0.7735,
+      "step": 70
+    },
+    {
+      "epoch": 0.23905723905723905,
+      "grad_norm": 0.984375,
+      "learning_rate": 1.9949896569413368e-05,
+      "loss": 0.7356,
+      "step": 71
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.8125,
+      "learning_rate": 1.9946119873266615e-05,
+      "loss": 0.7407,
+      "step": 72
+    },
+    {
+      "epoch": 0.24579124579124578,
+      "grad_norm": 0.76953125,
+      "learning_rate": 1.9942206345611008e-05,
+      "loss": 0.7124,
+      "step": 73
+    },
+    {
+      "epoch": 0.24915824915824916,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.9938156040286027e-05,
+      "loss": 0.7295,
+      "step": 74
+    },
+    {
+      "epoch": 0.25252525252525254,
+      "grad_norm": 0.5546875,
+      "learning_rate": 1.993396901301283e-05,
+      "loss": 0.733,
+      "step": 75
+    },
+    {
+      "epoch": 0.2558922558922559,
+      "grad_norm": 0.5703125,
+      "learning_rate": 1.9929645321393505e-05,
+      "loss": 0.779,
+      "step": 76
+    },
+    {
+      "epoch": 0.2558922558922559,
+      "eval_loss": 0.7325140237808228,
+      "eval_runtime": 8.7635,
+      "eval_samples_per_second": 57.055,
+      "eval_steps_per_second": 3.652,
+      "step": 76
+    },
+    {
+      "epoch": 0.25925925925925924,
+      "grad_norm": 0.67578125,
+      "learning_rate": 1.992518502491028e-05,
+      "loss": 0.7345,
+      "step": 77
+    },
+    {
+      "epoch": 0.26262626262626265,
+      "grad_norm": 0.5,
+      "learning_rate": 1.9920588184924664e-05,
+      "loss": 0.7102,
+      "step": 78
+    },
+    {
+      "epoch": 0.265993265993266,
+      "grad_norm": 0.51953125,
+      "learning_rate": 1.9915854864676665e-05,
+      "loss": 0.7433,
+      "step": 79
+    },
+    {
+      "epoch": 0.26936026936026936,
+      "grad_norm": 0.48828125,
+      "learning_rate": 1.991098512928386e-05,
+      "loss": 0.7628,
+      "step": 80
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 0.55859375,
+      "learning_rate": 1.990597904574055e-05,
+      "loss": 0.6858,
+      "step": 81
+    },
+    {
+      "epoch": 0.2760942760942761,
+      "grad_norm": 0.5390625,
+      "learning_rate": 1.9900836682916796e-05,
+      "loss": 0.7169,
+      "step": 82
+    },
+    {
+      "epoch": 0.27946127946127947,
+      "grad_norm": 0.494140625,
+      "learning_rate": 1.9895558111557503e-05,
+      "loss": 0.6995,
+      "step": 83
+    },
+    {
+      "epoch": 0.2828282828282828,
+      "grad_norm": 0.4765625,
+      "learning_rate": 1.989014340428143e-05,
+      "loss": 0.7234,
+      "step": 84
+    },
+    {
+      "epoch": 0.28619528619528617,
+      "grad_norm": 0.5546875,
+      "learning_rate": 1.98845926355802e-05,
+      "loss": 0.7182,
+      "step": 85
+    },
+    {
+      "epoch": 0.2895622895622896,
+      "grad_norm": 0.51171875,
+      "learning_rate": 1.9878905881817254e-05,
+      "loss": 0.6837,
+      "step": 86
+    },
+    {
+      "epoch": 0.29292929292929293,
+      "grad_norm": 0.54296875,
+      "learning_rate": 1.9873083221226833e-05,
+      "loss": 0.6759,
+      "step": 87
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.52734375,
+      "learning_rate": 1.986712473391289e-05,
+      "loss": 0.7275,
+      "step": 88
+    },
+    {
+      "epoch": 0.2996632996632997,
+      "grad_norm": 0.51171875,
+      "learning_rate": 1.986103050184797e-05,
+      "loss": 0.728,
+      "step": 89
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.9854800608872096e-05,
+      "loss": 0.6865,
+      "step": 90
+    },
+    {
+      "epoch": 0.3063973063973064,
+      "grad_norm": 0.44921875,
+      "learning_rate": 1.9848435140691627e-05,
+      "loss": 0.6816,
+      "step": 91
+    },
+    {
+      "epoch": 0.30976430976430974,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.9841934184878056e-05,
+      "loss": 0.6767,
+      "step": 92
+    },
+    {
+      "epoch": 0.31313131313131315,
+      "grad_norm": 0.546875,
+      "learning_rate": 1.9835297830866827e-05,
+      "loss": 0.7623,
+      "step": 93
+    },
+    {
+      "epoch": 0.3164983164983165,
+      "grad_norm": 0.45703125,
+      "learning_rate": 1.9828526169956083e-05,
+      "loss": 0.7193,
+      "step": 94
+    },
+    {
+      "epoch": 0.31986531986531985,
+      "grad_norm": 0.482421875,
+      "learning_rate": 1.9821619295305432e-05,
+      "loss": 0.6573,
+      "step": 95
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.43359375,
+      "learning_rate": 1.9814577301934647e-05,
+      "loss": 0.7,
+      "step": 96
+    },
+    {
+      "epoch": 0.3265993265993266,
+      "grad_norm": 0.56640625,
+      "learning_rate": 1.980740028672237e-05,
+      "loss": 0.7111,
+      "step": 97
+    },
+    {
+      "epoch": 0.32996632996632996,
+      "grad_norm": 0.47265625,
+      "learning_rate": 1.9800088348404778e-05,
+      "loss": 0.7025,
+      "step": 98
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.51953125,
+      "learning_rate": 1.9792641587574212e-05,
+      "loss": 0.6925,
+      "step": 99
+    },
+    {
+      "epoch": 0.3367003367003367,
+      "grad_norm": 0.484375,
+      "learning_rate": 1.9785060106677818e-05,
+      "loss": 0.6715,
+      "step": 100
+    },
+    {
+      "epoch": 0.3400673400673401,
+      "grad_norm": 0.443359375,
+      "learning_rate": 1.977734401001611e-05,
+      "loss": 0.6929,
+      "step": 101
+    },
+    {
+      "epoch": 0.3434343434343434,
+      "grad_norm": 0.5703125,
+      "learning_rate": 1.9769493403741556e-05,
+      "loss": 0.7126,
+      "step": 102
+    },
+    {
+      "epoch": 0.3468013468013468,
+      "grad_norm": 0.490234375,
+      "learning_rate": 1.9761508395857106e-05,
+      "loss": 0.7012,
+      "step": 103
+    },
+    {
+      "epoch": 0.3501683501683502,
+      "grad_norm": 0.54296875,
+      "learning_rate": 1.9753389096214716e-05,
+      "loss": 0.6819,
+      "step": 104
+    },
+    {
+      "epoch": 0.35353535353535354,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.974513561651382e-05,
+      "loss": 0.7073,
+      "step": 105
+    },
+    {
+      "epoch": 0.3569023569023569,
+      "grad_norm": 0.4296875,
+      "learning_rate": 1.9736748070299813e-05,
+      "loss": 0.6743,
+      "step": 106
+    },
+    {
+      "epoch": 0.3602693602693603,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.9728226572962474e-05,
+      "loss": 0.6746,
+      "step": 107
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.5078125,
+      "learning_rate": 1.9719571241734395e-05,
+      "loss": 0.6729,
+      "step": 108
+    },
+    {
+      "epoch": 0.367003367003367,
+      "grad_norm": 0.74609375,
+      "learning_rate": 1.9710782195689343e-05,
+      "loss": 0.6781,
+      "step": 109
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.462890625,
+      "learning_rate": 1.9701859555740647e-05,
+      "loss": 0.6976,
+      "step": 110
+    },
+    {
+      "epoch": 0.37373737373737376,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.9692803444639517e-05,
+      "loss": 0.6464,
+      "step": 111
+    },
+    {
+      "epoch": 0.3771043771043771,
+      "grad_norm": 0.58203125,
+      "learning_rate": 1.9683613986973373e-05,
+      "loss": 0.6614,
+      "step": 112
+    },
+    {
+      "epoch": 0.38047138047138046,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.967429130916411e-05,
+      "loss": 0.6087,
+      "step": 113
+    },
+    {
+      "epoch": 0.3838383838383838,
+      "grad_norm": 0.431640625,
+      "learning_rate": 1.966483553946637e-05,
+      "loss": 0.6894,
+      "step": 114
+    },
+    {
+      "epoch": 0.3838383838383838,
+      "eval_loss": 0.6650684475898743,
+      "eval_runtime": 8.7352,
+      "eval_samples_per_second": 57.24,
+      "eval_steps_per_second": 3.663,
+      "step": 114
+    },
+    {
+      "epoch": 0.3872053872053872,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.9655246807965786e-05,
+      "loss": 0.6962,
+      "step": 115
+    },
+    {
+      "epoch": 0.39057239057239057,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.9645525246577168e-05,
+      "loss": 0.6614,
+      "step": 116
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.963567098904272e-05,
+      "loss": 0.6889,
+      "step": 117
+    },
+    {
+      "epoch": 0.39730639730639733,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.9625684170930172e-05,
+      "loss": 0.642,
+      "step": 118
+    },
+    {
+      "epoch": 0.4006734006734007,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.9615564929630925e-05,
+      "loss": 0.6185,
+      "step": 119
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.9605313404358176e-05,
+      "loss": 0.6624,
+      "step": 120
+    },
+    {
+      "epoch": 0.4074074074074074,
+      "grad_norm": 0.390625,
+      "learning_rate": 1.9594929736144978e-05,
+      "loss": 0.6632,
+      "step": 121
+    },
+    {
+      "epoch": 0.4107744107744108,
+      "grad_norm": 0.51953125,
+      "learning_rate": 1.9584414067842304e-05,
+      "loss": 0.6504,
+      "step": 122
+    },
+    {
+      "epoch": 0.41414141414141414,
+      "grad_norm": 0.44140625,
+      "learning_rate": 1.957376654411711e-05,
+      "loss": 0.6543,
+      "step": 123
+    },
+    {
+      "epoch": 0.4175084175084175,
+      "grad_norm": 0.48828125,
+      "learning_rate": 1.9562987311450298e-05,
+      "loss": 0.626,
+      "step": 124
+    },
+    {
+      "epoch": 0.4208754208754209,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.955207651813475e-05,
+      "loss": 0.7022,
+      "step": 125
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.954103431427325e-05,
+      "loss": 0.6574,
+      "step": 126
+    },
+    {
+      "epoch": 0.4276094276094276,
+      "grad_norm": 0.3984375,
+      "learning_rate": 1.952986085177643e-05,
+      "loss": 0.6068,
+      "step": 127
+    },
+    {
+      "epoch": 0.43097643097643096,
+      "grad_norm": 0.380859375,
+      "learning_rate": 1.9518556284360696e-05,
+      "loss": 0.6538,
+      "step": 128
+    },
+    {
+      "epoch": 0.43434343434343436,
+      "grad_norm": 0.42578125,
+      "learning_rate": 1.950712076754609e-05,
+      "loss": 0.7139,
+      "step": 129
+    },
+    {
+      "epoch": 0.4377104377104377,
+      "grad_norm": 0.42578125,
+      "learning_rate": 1.949555445865417e-05,
+      "loss": 0.6362,
+      "step": 130
+    },
+    {
+      "epoch": 0.44107744107744107,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.9483857516805823e-05,
+      "loss": 0.6382,
+      "step": 131
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.9472030102919102e-05,
+      "loss": 0.6522,
+      "step": 132
+    },
+    {
+      "epoch": 0.4478114478114478,
+      "grad_norm": 0.390625,
+      "learning_rate": 1.9460072379706995e-05,
+      "loss": 0.6583,
+      "step": 133
+    },
+    {
+      "epoch": 0.4511784511784512,
+      "grad_norm": 0.373046875,
+      "learning_rate": 1.9447984511675192e-05,
+      "loss": 0.6343,
+      "step": 134
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.9435766665119823e-05,
+      "loss": 0.6442,
+      "step": 135
+    },
+    {
+      "epoch": 0.45791245791245794,
+      "grad_norm": 0.375,
+      "learning_rate": 1.942341900812516e-05,
+      "loss": 0.6286,
+      "step": 136
+    },
+    {
+      "epoch": 0.4612794612794613,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.9410941710561323e-05,
+      "loss": 0.6596,
+      "step": 137
+    },
+    {
+      "epoch": 0.46464646464646464,
+      "grad_norm": 0.423828125,
+      "learning_rate": 1.939833494408193e-05,
+      "loss": 0.6632,
+      "step": 138
+    },
+    {
+      "epoch": 0.468013468013468,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.9385598882121735e-05,
+      "loss": 0.6525,
+      "step": 139
+    },
+    {
+      "epoch": 0.4713804713804714,
+      "grad_norm": 0.431640625,
+      "learning_rate": 1.9372733699894253e-05,
+      "loss": 0.6136,
+      "step": 140
+    },
+    {
+      "epoch": 0.47474747474747475,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.935973957438933e-05,
+      "loss": 0.6908,
+      "step": 141
+    },
+    {
+      "epoch": 0.4781144781144781,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.934661668437073e-05,
+      "loss": 0.6374,
+      "step": 142
+    },
+    {
+      "epoch": 0.48148148148148145,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.9333365210373668e-05,
+      "loss": 0.6386,
+      "step": 143
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.9319985334702315e-05,
+      "loss": 0.6775,
+      "step": 144
+    },
+    {
+      "epoch": 0.4882154882154882,
+      "grad_norm": 0.400390625,
+      "learning_rate": 1.9306477241427303e-05,
+      "loss": 0.6006,
+      "step": 145
+    },
+    {
+      "epoch": 0.49158249158249157,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.9292841116383192e-05,
+      "loss": 0.6123,
+      "step": 146
+    },
+    {
+      "epoch": 0.494949494949495,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.9279077147165903e-05,
+      "loss": 0.6198,
+      "step": 147
+    },
+    {
+      "epoch": 0.4983164983164983,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.9265185523130156e-05,
+      "loss": 0.624,
+      "step": 148
+    },
+    {
+      "epoch": 0.5016835016835017,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.9251166435386837e-05,
+      "loss": 0.6348,
+      "step": 149
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.9237020076800407e-05,
+      "loss": 0.6379,
+      "step": 150
+    },
+    {
+      "epoch": 0.5084175084175084,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.9222746641986207e-05,
+      "loss": 0.6065,
+      "step": 151
+    },
+    {
+      "epoch": 0.5117845117845118,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.920834632730781e-05,
+      "loss": 0.6137,
+      "step": 152
+    },
+    {
+      "epoch": 0.5117845117845118,
+      "eval_loss": 0.6364830732345581,
+      "eval_runtime": 8.689,
+      "eval_samples_per_second": 57.544,
+      "eval_steps_per_second": 3.683,
+      "step": 152
+    },
+    {
+      "epoch": 0.5151515151515151,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.919381933087431e-05,
+      "loss": 0.6596,
+      "step": 153
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.9179165852537596e-05,
+      "loss": 0.6292,
+      "step": 154
+    },
+    {
+      "epoch": 0.5218855218855218,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.9164386093889598e-05,
+      "loss": 0.6555,
+      "step": 155
+    },
+    {
+      "epoch": 0.5252525252525253,
+      "grad_norm": 0.376953125,
+      "learning_rate": 1.9149480258259535e-05,
+      "loss": 0.632,
+      "step": 156
+    },
+    {
+      "epoch": 0.5286195286195287,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.9134448550711077e-05,
+      "loss": 0.644,
+      "step": 157
+    },
+    {
+      "epoch": 0.531986531986532,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.9119291178039573e-05,
+      "loss": 0.6549,
+      "step": 158
+    },
+    {
+      "epoch": 0.5353535353535354,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.9104008348769164e-05,
+      "loss": 0.6572,
+      "step": 159
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.9088600273149947e-05,
+      "loss": 0.6284,
+      "step": 160
+    },
+    {
+      "epoch": 0.5420875420875421,
+      "grad_norm": 0.5,
+      "learning_rate": 1.907306716315505e-05,
+      "loss": 0.6495,
+      "step": 161
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.905740923247775e-05,
+      "loss": 0.6357,
+      "step": 162
+    },
+    {
+      "epoch": 0.5488215488215489,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.9041626696528503e-05,
+      "loss": 0.6188,
+      "step": 163
+    },
+    {
+      "epoch": 0.5521885521885522,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.9025719772432006e-05,
+      "loss": 0.6142,
+      "step": 164
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.6339,
+      "step": 165
+    },
+    {
+      "epoch": 0.5589225589225589,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.8993533636849223e-05,
+      "loss": 0.6067,
+      "step": 166
+    },
+    {
+      "epoch": 0.5622895622895623,
+      "grad_norm": 0.494140625,
+      "learning_rate": 1.8977254868156465e-05,
+      "loss": 0.5849,
+      "step": 167
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.896085259689741e-05,
+      "loss": 0.6083,
+      "step": 168
+    },
+    {
+      "epoch": 0.569023569023569,
+      "grad_norm": 0.3984375,
+      "learning_rate": 1.8944327048722634e-05,
+      "loss": 0.6319,
+      "step": 169
+    },
+    {
+      "epoch": 0.5723905723905723,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.892767845097864e-05,
+      "loss": 0.6299,
+      "step": 170
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.891090703270477e-05,
+      "loss": 0.5819,
+      "step": 171
+    },
+    {
+      "epoch": 0.5791245791245792,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.889401302463005e-05,
+      "loss": 0.6166,
+      "step": 172
+    },
+    {
+      "epoch": 0.5824915824915825,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.887699665916999e-05,
+      "loss": 0.605,
+      "step": 173
+    },
+    {
+      "epoch": 0.5858585858585859,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.8859858170423423e-05,
+      "loss": 0.6573,
+      "step": 174
+    },
+    {
+      "epoch": 0.5892255892255892,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.8842597794169245e-05,
+      "loss": 0.5891,
+      "step": 175
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.8825215767863215e-05,
+      "loss": 0.6383,
+      "step": 176
+    },
+    {
+      "epoch": 0.5959595959595959,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.8807712330634645e-05,
+      "loss": 0.5958,
+      "step": 177
+    },
+    {
+      "epoch": 0.5993265993265994,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.879008772328314e-05,
+      "loss": 0.5791,
+      "step": 178
+    },
+    {
+      "epoch": 0.6026936026936027,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.877234218827528e-05,
+      "loss": 0.6294,
+      "step": 179
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.40625,
+      "learning_rate": 1.8754475969741272e-05,
+      "loss": 0.5971,
+      "step": 180
+    },
+    {
+      "epoch": 0.6094276094276094,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.87364893134716e-05,
+      "loss": 0.6078,
+      "step": 181
+    },
+    {
+      "epoch": 0.6127946127946128,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.8718382466913642e-05,
+      "loss": 0.6115,
+      "step": 182
+    },
+    {
+      "epoch": 0.6161616161616161,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.8700155679168277e-05,
+      "loss": 0.6263,
+      "step": 183
+    },
+    {
+      "epoch": 0.6195286195286195,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.868180920098644e-05,
+      "loss": 0.5933,
+      "step": 184
+    },
+    {
+      "epoch": 0.622895622895623,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.866334328476568e-05,
+      "loss": 0.6371,
+      "step": 185
+    },
+    {
+      "epoch": 0.6262626262626263,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1.864475818454669e-05,
+      "loss": 0.6314,
+      "step": 186
+    },
+    {
+      "epoch": 0.6296296296296297,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.8626054156009807e-05,
+      "loss": 0.6802,
+      "step": 187
+    },
+    {
+      "epoch": 0.632996632996633,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.8607231456471505e-05,
+      "loss": 0.6189,
+      "step": 188
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.858829034488084e-05,
+      "loss": 0.5987,
+      "step": 189
+    },
+    {
+      "epoch": 0.6397306397306397,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.8569231081815895e-05,
+      "loss": 0.6492,
+      "step": 190
+    },
+    {
+      "epoch": 0.6397306397306397,
+      "eval_loss": 0.6246641874313354,
+      "eval_runtime": 8.7145,
+      "eval_samples_per_second": 57.375,
+      "eval_steps_per_second": 3.672,
+      "step": 190
+    },
+    {
+      "epoch": 0.6430976430976431,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.8550053929480202e-05,
+      "loss": 0.6198,
+      "step": 191
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.8530759151699122e-05,
+      "loss": 0.6253,
+      "step": 192
+    },
+    {
+      "epoch": 0.6498316498316499,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.8511347013916228e-05,
+      "loss": 0.5804,
+      "step": 193
+    },
+    {
+      "epoch": 0.6531986531986532,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.8491817783189636e-05,
+      "loss": 0.5909,
+      "step": 194
+    },
+    {
+      "epoch": 0.6565656565656566,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.8472171728188356e-05,
+      "loss": 0.5996,
+      "step": 195
+    },
+    {
+      "epoch": 0.6599326599326599,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.845240911918857e-05,
+      "loss": 0.6401,
+      "step": 196
+    },
+    {
+      "epoch": 0.6632996632996633,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.843253022806993e-05,
+      "loss": 0.6576,
+      "step": 197
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.8412535328311813e-05,
+      "loss": 0.5715,
+      "step": 198
+    },
+    {
+      "epoch": 0.67003367003367,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.839242469498956e-05,
+      "loss": 0.5988,
+      "step": 199
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.837219860477069e-05,
+      "loss": 0.5796,
+      "step": 200
+    },
+    {
+      "epoch": 0.6767676767676768,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.8351857335911094e-05,
+      "loss": 0.6329,
+      "step": 201
+    },
+    {
+      "epoch": 0.6801346801346801,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.83314011682512e-05,
+      "loss": 0.6374,
+      "step": 202
+    },
+    {
+      "epoch": 0.6835016835016835,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.831083038321215e-05,
+      "loss": 0.6235,
+      "step": 203
+    },
+    {
+      "epoch": 0.6868686868686869,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.8290145263791883e-05,
+      "loss": 0.621,
+      "step": 204
+    },
+    {
+      "epoch": 0.6902356902356902,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.826934609456129e-05,
+      "loss": 0.6396,
+      "step": 205
+    },
+    {
+      "epoch": 0.6936026936026936,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.824843316166026e-05,
+      "loss": 0.6197,
+      "step": 206
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.822740675279377e-05,
+      "loss": 0.6473,
+      "step": 207
+    },
+    {
+      "epoch": 0.7003367003367004,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.8206267157227918e-05,
+      "loss": 0.6227,
+      "step": 208
+    },
+    {
+      "epoch": 0.7037037037037037,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.8185014665785936e-05,
+      "loss": 0.6009,
+      "step": 209
+    },
+    {
+      "epoch": 0.7070707070707071,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.8163649570844198e-05,
+      "loss": 0.592,
+      "step": 210
+    },
+    {
+      "epoch": 0.7104377104377104,
+      "grad_norm": 0.376953125,
+      "learning_rate": 1.8142172166328198e-05,
+      "loss": 0.6063,
+      "step": 211
+    },
+    {
+      "epoch": 0.7138047138047138,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.8120582747708503e-05,
+      "loss": 0.6315,
+      "step": 212
+    },
+    {
+      "epoch": 0.7171717171717171,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.809888161199668e-05,
+      "loss": 0.6297,
+      "step": 213
+    },
+    {
+      "epoch": 0.7205387205387206,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.8077069057741235e-05,
+      "loss": 0.6079,
+      "step": 214
+    },
+    {
+      "epoch": 0.7239057239057239,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.8055145385023477e-05,
+      "loss": 0.6192,
+      "step": 215
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.803311089545341e-05,
+      "loss": 0.6104,
+      "step": 216
+    },
+    {
+      "epoch": 0.7306397306397306,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.8010965892165568e-05,
+      "loss": 0.6166,
+      "step": 217
+    },
+    {
+      "epoch": 0.734006734006734,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.7988710679814857e-05,
+      "loss": 0.6145,
+      "step": 218
+    },
+    {
+      "epoch": 0.7373737373737373,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.796634556457236e-05,
+      "loss": 0.5994,
+      "step": 219
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.7943870854121126e-05,
+      "loss": 0.586,
+      "step": 220
+    },
+    {
+      "epoch": 0.7441077441077442,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.792128685765193e-05,
+      "loss": 0.582,
+      "step": 221
+    },
+    {
+      "epoch": 0.7474747474747475,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.789859388585903e-05,
+      "loss": 0.6017,
+      "step": 222
+    },
+    {
+      "epoch": 0.7508417508417509,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.7875792250935883e-05,
+      "loss": 0.5864,
+      "step": 223
+    },
+    {
+      "epoch": 0.7542087542087542,
+      "grad_norm": 0.373046875,
+      "learning_rate": 1.785288226657086e-05,
+      "loss": 0.5869,
+      "step": 224
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.782986424794292e-05,
+      "loss": 0.6448,
+      "step": 225
+    },
+    {
+      "epoch": 0.7609427609427609,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.780673851171728e-05,
+      "loss": 0.5895,
+      "step": 226
+    },
+    {
+      "epoch": 0.7643097643097643,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.7783505376041063e-05,
+      "loss": 0.6289,
+      "step": 227
+    },
+    {
+      "epoch": 0.7676767676767676,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.7760165160538907e-05,
+      "loss": 0.6231,
+      "step": 228
+    },
+    {
+      "epoch": 0.7676767676767676,
+      "eval_loss": 0.6190042495727539,
+      "eval_runtime": 8.7179,
+      "eval_samples_per_second": 57.353,
+      "eval_steps_per_second": 3.671,
+      "step": 228
+    },
+    {
+      "epoch": 0.7710437710437711,
+      "grad_norm": 0.384765625,
+      "learning_rate": 1.7736718186308585e-05,
+      "loss": 0.6327,
+      "step": 229
+    },
+    {
+      "epoch": 0.7744107744107744,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.7713164775916573e-05,
+      "loss": 0.5811,
+      "step": 230
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.768950525339362e-05,
+      "loss": 0.5816,
+      "step": 231
+    },
+    {
+      "epoch": 0.7811447811447811,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.7665739944230296e-05,
+      "loss": 0.6046,
+      "step": 232
+    },
+    {
+      "epoch": 0.7845117845117845,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.7641869175372493e-05,
+      "loss": 0.5985,
+      "step": 233
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.7617893275216953e-05,
+      "loss": 0.6226,
+      "step": 234
+    },
+    {
+      "epoch": 0.7912457912457912,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.759381257360673e-05,
+      "loss": 0.6361,
+      "step": 235
+    },
+    {
+      "epoch": 0.7946127946127947,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.7569627401826673e-05,
+      "loss": 0.665,
+      "step": 236
+    },
+    {
+      "epoch": 0.797979797979798,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.754533809259884e-05,
+      "loss": 0.6078,
+      "step": 237
+    },
+    {
+      "epoch": 0.8013468013468014,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.7520944980077948e-05,
+      "loss": 0.6043,
+      "step": 238
+    },
+    {
+      "epoch": 0.8047138047138047,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.7496448399846757e-05,
+      "loss": 0.614,
+      "step": 239
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.7471848688911465e-05,
+      "loss": 0.5756,
+      "step": 240
+    },
+    {
+      "epoch": 0.8114478114478114,
+      "grad_norm": 0.40234375,
+      "learning_rate": 1.744714618569707e-05,
+      "loss": 0.5982,
+      "step": 241
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.74223412300427e-05,
+      "loss": 0.6126,
+      "step": 242
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.7397434163196967e-05,
+      "loss": 0.6281,
+      "step": 243
+    },
+    {
+      "epoch": 0.8215488215488216,
+      "grad_norm": 0.294921875,
+      "learning_rate": 1.737242532781324e-05,
+      "loss": 0.5821,
+      "step": 244
+    },
+    {
+      "epoch": 0.8249158249158249,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.7347315067944955e-05,
+      "loss": 0.6546,
+      "step": 245
+    },
+    {
+      "epoch": 0.8282828282828283,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.7322103729040868e-05,
+      "loss": 0.6301,
+      "step": 246
+    },
+    {
+      "epoch": 0.8316498316498316,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.72967916579403e-05,
+      "loss": 0.585,
+      "step": 247
+    },
+    {
+      "epoch": 0.835016835016835,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.7271379202868394e-05,
+      "loss": 0.6277,
+      "step": 248
+    },
+    {
+      "epoch": 0.8383838383838383,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.7245866713431278e-05,
+      "loss": 0.6536,
+      "step": 249
+    },
+    {
+      "epoch": 0.8417508417508418,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.72202545406113e-05,
+      "loss": 0.6231,
+      "step": 250
+    },
+    {
+      "epoch": 0.8451178451178452,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.7194543036762165e-05,
+      "loss": 0.6102,
+      "step": 251
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.7168732555604114e-05,
+      "loss": 0.6118,
+      "step": 252
+    },
+    {
+      "epoch": 0.8518518518518519,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.7142823452219036e-05,
+      "loss": 0.6323,
+      "step": 253
+    },
+    {
+      "epoch": 0.8552188552188552,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.7116816083045603e-05,
+      "loss": 0.6393,
+      "step": 254
+    },
+    {
+      "epoch": 0.8585858585858586,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.709071080587435e-05,
+      "loss": 0.5845,
+      "step": 255
+    },
+    {
+      "epoch": 0.8619528619528619,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.7064507979842755e-05,
+      "loss": 0.6026,
+      "step": 256
+    },
+    {
+      "epoch": 0.8653198653198653,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.7038207965430316e-05,
+      "loss": 0.5665,
+      "step": 257
+    },
+    {
+      "epoch": 0.8686868686868687,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.7011811124453567e-05,
+      "loss": 0.5787,
+      "step": 258
+    },
+    {
+      "epoch": 0.8720538720538721,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.6985317820061116e-05,
+      "loss": 0.5506,
+      "step": 259
+    },
+    {
+      "epoch": 0.8754208754208754,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.6958728416728644e-05,
+      "loss": 0.5902,
+      "step": 260
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 0.404296875,
+      "learning_rate": 1.6932043280253892e-05,
+      "loss": 0.6037,
+      "step": 261
+    },
+    {
+      "epoch": 0.8821548821548821,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.6905262777751627e-05,
+      "loss": 0.5533,
+      "step": 262
+    },
+    {
+      "epoch": 0.8855218855218855,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.6878387277648593e-05,
+      "loss": 0.5924,
+      "step": 263
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.310546875,
+      "learning_rate": 1.6851417149678442e-05,
+      "loss": 0.5834,
+      "step": 264
+    },
+    {
+      "epoch": 0.8922558922558923,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.6824352764876653e-05,
+      "loss": 0.6527,
+      "step": 265
+    },
+    {
+      "epoch": 0.8956228956228957,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.6797194495575412e-05,
+      "loss": 0.6428,
+      "step": 266
+    },
+    {
+      "epoch": 0.8956228956228957,
+      "eval_loss": 0.6151465773582458,
+      "eval_runtime": 8.6578,
+      "eval_samples_per_second": 57.751,
+      "eval_steps_per_second": 3.696,
+      "step": 266
+    },
+    {
+      "epoch": 0.898989898989899,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.676994271539851e-05,
+      "loss": 0.5817,
+      "step": 267
+    },
+    {
+      "epoch": 0.9023569023569024,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.6742597799256182e-05,
+      "loss": 0.6313,
+      "step": 268
+    },
+    {
+      "epoch": 0.9057239057239057,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.671516012333997e-05,
+      "loss": 0.5895,
+      "step": 269
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.6687630065117536e-05,
+      "loss": 0.6106,
+      "step": 270
+    },
+    {
+      "epoch": 0.9124579124579124,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.666000800332747e-05,
+      "loss": 0.567,
+      "step": 271
+    },
+    {
+      "epoch": 0.9158249158249159,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.663229431797407e-05,
+      "loss": 0.6024,
+      "step": 272
+    },
+    {
+      "epoch": 0.9191919191919192,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.660448939032214e-05,
+      "loss": 0.6348,
+      "step": 273
+    },
+    {
+      "epoch": 0.9225589225589226,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.6576593602891727e-05,
+      "loss": 0.6119,
+      "step": 274
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.6548607339452853e-05,
+      "loss": 0.599,
+      "step": 275
+    },
+    {
+      "epoch": 0.9292929292929293,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.6520530985020243e-05,
+      "loss": 0.587,
+      "step": 276
+    },
+    {
+      "epoch": 0.9326599326599326,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.6492364925848045e-05,
+      "loss": 0.6113,
+      "step": 277
+    },
+    {
+      "epoch": 0.936026936026936,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.6464109549424477e-05,
+      "loss": 0.594,
+      "step": 278
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 0.283203125,
+      "learning_rate": 1.6435765244466536e-05,
+      "loss": 0.5823,
+      "step": 279
+    },
+    {
+      "epoch": 0.9427609427609428,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.6407332400914625e-05,
+      "loss": 0.5871,
+      "step": 280
+    },
+    {
+      "epoch": 0.9461279461279462,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.63788114099272e-05,
+      "loss": 0.6126,
+      "step": 281
+    },
+    {
+      "epoch": 0.9494949494949495,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.6350202663875385e-05,
+      "loss": 0.6343,
+      "step": 282
+    },
+    {
+      "epoch": 0.9528619528619529,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.6321506556337575e-05,
+      "loss": 0.6033,
+      "step": 283
+    },
+    {
+      "epoch": 0.9562289562289562,
+      "grad_norm": 0.400390625,
+      "learning_rate": 1.6292723482094013e-05,
+      "loss": 0.6216,
+      "step": 284
+    },
+    {
+      "epoch": 0.9595959595959596,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.6263853837121384e-05,
+      "loss": 0.5599,
+      "step": 285
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.632,
+      "step": 286
+    },
+    {
+      "epoch": 0.9663299663299664,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.6205856424845038e-05,
+      "loss": 0.5824,
+      "step": 287
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.617672945542768e-05,
+      "loss": 0.628,
+      "step": 288
+    },
+    {
+      "epoch": 0.9730639730639731,
+      "grad_norm": 0.275390625,
+      "learning_rate": 1.614751751104301e-05,
+      "loss": 0.5691,
+      "step": 289
+    },
+    {
+      "epoch": 0.9764309764309764,
+      "grad_norm": 0.310546875,
+      "learning_rate": 1.6118220993567783e-05,
+      "loss": 0.5816,
+      "step": 290
+    },
+    {
+      "epoch": 0.9797979797979798,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.6088840306042247e-05,
+      "loss": 0.5907,
+      "step": 291
+    },
+    {
+      "epoch": 0.9831649831649831,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.605937585266462e-05,
+      "loss": 0.6129,
+      "step": 292
+    },
+    {
+      "epoch": 0.9865319865319865,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1.6029828038785486e-05,
+      "loss": 0.5916,
+      "step": 293
+    },
+    {
+      "epoch": 0.98989898989899,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.600019727090226e-05,
+      "loss": 0.5984,
+      "step": 294
+    },
+    {
+      "epoch": 0.9932659932659933,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.5970483956653572e-05,
+      "loss": 0.5549,
+      "step": 295
+    },
+    {
+      "epoch": 0.9966329966329966,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.5940688504813664e-05,
+      "loss": 0.6102,
+      "step": 296
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.5910811325286768e-05,
+      "loss": 0.6109,
+      "step": 297
+    },
+    {
+      "epoch": 1.0033670033670035,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.5880852829101464e-05,
+      "loss": 0.6281,
+      "step": 298
+    },
+    {
+      "epoch": 1.0067340067340067,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.5850813428405036e-05,
+      "loss": 0.6149,
+      "step": 299
+    },
+    {
+      "epoch": 1.0101010101010102,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.5820693536457787e-05,
+      "loss": 0.6244,
+      "step": 300
+    },
+    {
+      "epoch": 1.0134680134680134,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.5790493567627357e-05,
+      "loss": 0.6052,
+      "step": 301
+    },
+    {
+      "epoch": 1.0168350168350169,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.5760213937383032e-05,
+      "loss": 0.5706,
+      "step": 302
+    },
+    {
+      "epoch": 1.02020202020202,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1.5729855062290024e-05,
+      "loss": 0.5531,
+      "step": 303
+    },
+    {
+      "epoch": 1.0235690235690236,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.5699417360003725e-05,
+      "loss": 0.6111,
+      "step": 304
+    },
+    {
+      "epoch": 1.0235690235690236,
+      "eval_loss": 0.6120156049728394,
+      "eval_runtime": 8.7268,
+      "eval_samples_per_second": 57.295,
+      "eval_steps_per_second": 3.667,
+      "step": 304
+    },
+    {
+      "epoch": 1.026936026936027,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.5668901249263996e-05,
+      "loss": 0.5895,
+      "step": 305
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 0.310546875,
+      "learning_rate": 1.563830714988936e-05,
+      "loss": 0.6005,
+      "step": 306
+    },
+    {
+      "epoch": 1.0336700336700337,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.5607635482771272e-05,
+      "loss": 0.6132,
+      "step": 307
+    },
+    {
+      "epoch": 1.037037037037037,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.5576886669868297e-05,
+      "loss": 0.5946,
+      "step": 308
+    },
+    {
+      "epoch": 1.0404040404040404,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.5546061134200316e-05,
+      "loss": 0.5838,
+      "step": 309
+    },
+    {
+      "epoch": 1.0437710437710437,
+      "grad_norm": 0.306640625,
+      "learning_rate": 1.551515929984271e-05,
+      "loss": 0.5992,
+      "step": 310
+    },
+    {
+      "epoch": 1.0471380471380471,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.5484181591920516e-05,
+      "loss": 0.5773,
+      "step": 311
+    },
+    {
+      "epoch": 1.0505050505050506,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.5453128436602597e-05,
+      "loss": 0.5757,
+      "step": 312
+    },
+    {
+      "epoch": 1.0538720538720538,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.542200026109575e-05,
+      "loss": 0.6248,
+      "step": 313
+    },
+    {
+      "epoch": 1.0572390572390573,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.5390797493638862e-05,
+      "loss": 0.6123,
+      "step": 314
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 0.322265625,
+      "learning_rate": 1.5359520563496985e-05,
+      "loss": 0.5815,
+      "step": 315
+    },
+    {
+      "epoch": 1.063973063973064,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.5328169900955463e-05,
+      "loss": 0.589,
+      "step": 316
+    },
+    {
+      "epoch": 1.0673400673400673,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.529674593731399e-05,
+      "loss": 0.6343,
+      "step": 317
+    },
+    {
+      "epoch": 1.0707070707070707,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.5265249104880675e-05,
+      "loss": 0.6045,
+      "step": 318
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.5233679836966122e-05,
+      "loss": 0.5939,
+      "step": 319
+    },
+    {
+      "epoch": 1.0774410774410774,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.5202038567877436e-05,
+      "loss": 0.6627,
+      "step": 320
+    },
+    {
+      "epoch": 1.0808080808080809,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.517032573291226e-05,
+      "loss": 0.616,
+      "step": 321
+    },
+    {
+      "epoch": 1.0841750841750841,
+      "grad_norm": 0.369140625,
+      "learning_rate": 1.5138541768352802e-05,
+      "loss": 0.587,
+      "step": 322
+    },
+    {
+      "epoch": 1.0875420875420876,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.5106687111459809e-05,
+      "loss": 0.586,
+      "step": 323
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.322265625,
+      "learning_rate": 1.5074762200466557e-05,
+      "loss": 0.6117,
+      "step": 324
+    },
+    {
+      "epoch": 1.0942760942760943,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.5042767474572846e-05,
+      "loss": 0.6171,
+      "step": 325
+    },
+    {
+      "epoch": 1.0976430976430978,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.5010703373938915e-05,
+      "loss": 0.617,
+      "step": 326
+    },
+    {
+      "epoch": 1.101010101010101,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.4978570339679435e-05,
+      "loss": 0.5944,
+      "step": 327
+    },
+    {
+      "epoch": 1.1043771043771045,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.4946368813857393e-05,
+      "loss": 0.5867,
+      "step": 328
+    },
+    {
+      "epoch": 1.1077441077441077,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.4914099239478046e-05,
+      "loss": 0.5639,
+      "step": 329
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.4881762060482814e-05,
+      "loss": 0.6106,
+      "step": 330
+    },
+    {
+      "epoch": 1.1144781144781144,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.4849357721743169e-05,
+      "loss": 0.5997,
+      "step": 331
+    },
+    {
+      "epoch": 1.1178451178451179,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.4816886669054514e-05,
+      "loss": 0.6194,
+      "step": 332
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 0.310546875,
+      "learning_rate": 1.4784349349130063e-05,
+      "loss": 0.5837,
+      "step": 333
+    },
+    {
+      "epoch": 1.1245791245791246,
+      "grad_norm": 0.322265625,
+      "learning_rate": 1.4751746209594683e-05,
+      "loss": 0.5881,
+      "step": 334
+    },
+    {
+      "epoch": 1.127946127946128,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.4719077698978737e-05,
+      "loss": 0.5973,
+      "step": 335
+    },
+    {
+      "epoch": 1.1313131313131313,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.4686344266711916e-05,
+      "loss": 0.5861,
+      "step": 336
+    },
+    {
+      "epoch": 1.1346801346801347,
+      "grad_norm": 0.310546875,
+      "learning_rate": 1.4653546363117063e-05,
+      "loss": 0.5911,
+      "step": 337
+    },
+    {
+      "epoch": 1.138047138047138,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.4620684439403962e-05,
+      "loss": 0.5749,
+      "step": 338
+    },
+    {
+      "epoch": 1.1414141414141414,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.4587758947663146e-05,
+      "loss": 0.6134,
+      "step": 339
+    },
+    {
+      "epoch": 1.144781144781145,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.4554770340859661e-05,
+      "loss": 0.5948,
+      "step": 340
+    },
+    {
+      "epoch": 1.1481481481481481,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.4521719072826858e-05,
+      "loss": 0.5687,
+      "step": 341
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.4488605598260129e-05,
+      "loss": 0.6138,
+      "step": 342
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "eval_loss": 0.6101293563842773,
+      "eval_runtime": 8.7555,
+      "eval_samples_per_second": 57.107,
+      "eval_steps_per_second": 3.655,
+      "step": 342
+    },
+    {
+      "epoch": 1.1548821548821548,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.4455430372710652e-05,
+      "loss": 0.5619,
+      "step": 343
+    },
+    {
+      "epoch": 1.1582491582491583,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.4422193852579144e-05,
+      "loss": 0.6349,
+      "step": 344
+    },
+    {
+      "epoch": 1.1616161616161615,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.438889649510956e-05,
+      "loss": 0.5807,
+      "step": 345
+    },
+    {
+      "epoch": 1.164983164983165,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.4355538758382805e-05,
+      "loss": 0.5874,
+      "step": 346
+    },
+    {
+      "epoch": 1.1683501683501682,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.4322121101310454e-05,
+      "loss": 0.6472,
+      "step": 347
+    },
+    {
+      "epoch": 1.1717171717171717,
+      "grad_norm": 0.369140625,
+      "learning_rate": 1.428864398362841e-05,
+      "loss": 0.638,
+      "step": 348
+    },
+    {
+      "epoch": 1.1750841750841752,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.4255107865890597e-05,
+      "loss": 0.5989,
+      "step": 349
+    },
+    {
+      "epoch": 1.1784511784511784,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.4221513209462615e-05,
+      "loss": 0.6196,
+      "step": 350
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.41878604765154e-05,
+      "loss": 0.6152,
+      "step": 351
+    },
+    {
+      "epoch": 1.1851851851851851,
+      "grad_norm": 0.2890625,
+      "learning_rate": 1.4154150130018867e-05,
+      "loss": 0.6104,
+      "step": 352
+    },
+    {
+      "epoch": 1.1885521885521886,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.4120382633735528e-05,
+      "loss": 0.6012,
+      "step": 353
+    },
+    {
+      "epoch": 1.1919191919191918,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.4086558452214121e-05,
+      "loss": 0.5788,
+      "step": 354
+    },
+    {
+      "epoch": 1.1952861952861953,
+      "grad_norm": 0.369140625,
+      "learning_rate": 1.405267805078323e-05,
+      "loss": 0.6059,
+      "step": 355
+    },
+    {
+      "epoch": 1.1986531986531987,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.401874189554486e-05,
+      "loss": 0.6137,
+      "step": 356
+    },
+    {
+      "epoch": 1.202020202020202,
+      "grad_norm": 0.322265625,
+      "learning_rate": 1.3984750453368033e-05,
+      "loss": 0.5951,
+      "step": 357
+    },
+    {
+      "epoch": 1.2053872053872055,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.3950704191882388e-05,
+      "loss": 0.6272,
+      "step": 358
+    },
+    {
+      "epoch": 1.2087542087542087,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.3916603579471705e-05,
+      "loss": 0.5916,
+      "step": 359
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.3882449085267497e-05,
+      "loss": 0.5745,
+      "step": 360
+    },
+    {
+      "epoch": 1.2154882154882154,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.384824117914255e-05,
+      "loss": 0.6189,
+      "step": 361
+    },
+    {
+      "epoch": 1.2188552188552189,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.3813980331704437e-05,
+      "loss": 0.6032,
+      "step": 362
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.3779667014289067e-05,
+      "loss": 0.6202,
+      "step": 363
+    },
+    {
+      "epoch": 1.2255892255892256,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.3745301698954197e-05,
+      "loss": 0.6272,
+      "step": 364
+    },
+    {
+      "epoch": 1.228956228956229,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.3710884858472926e-05,
+      "loss": 0.6054,
+      "step": 365
+    },
+    {
+      "epoch": 1.2323232323232323,
+      "grad_norm": 0.322265625,
+      "learning_rate": 1.3676416966327201e-05,
+      "loss": 0.5688,
+      "step": 366
+    },
+    {
+      "epoch": 1.2356902356902357,
+      "grad_norm": 0.375,
+      "learning_rate": 1.3641898496701306e-05,
+      "loss": 0.6228,
+      "step": 367
+    },
+    {
+      "epoch": 1.239057239057239,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.360732992447533e-05,
+      "loss": 0.5925,
+      "step": 368
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.357271172521863e-05,
+      "loss": 0.5687,
+      "step": 369
+    },
+    {
+      "epoch": 1.2457912457912457,
+      "grad_norm": 0.283203125,
+      "learning_rate": 1.3538044375183308e-05,
+      "loss": 0.5483,
+      "step": 370
+    },
+    {
+      "epoch": 1.2491582491582491,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.3503328351297635e-05,
+      "loss": 0.5925,
+      "step": 371
+    },
+    {
+      "epoch": 1.2525252525252526,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.3468564131159515e-05,
+      "loss": 0.5782,
+      "step": 372
+    },
+    {
+      "epoch": 1.2558922558922558,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.3433752193029888e-05,
+      "loss": 0.595,
+      "step": 373
+    },
+    {
+      "epoch": 1.2592592592592593,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.3398893015826166e-05,
+      "loss": 0.6001,
+      "step": 374
+    },
+    {
+      "epoch": 1.2626262626262625,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.3363987079115656e-05,
+      "loss": 0.6185,
+      "step": 375
+    },
+    {
+      "epoch": 1.265993265993266,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.3329034863108932e-05,
+      "loss": 0.5738,
+      "step": 376
+    },
+    {
+      "epoch": 1.2693602693602695,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.3294036848653247e-05,
+      "loss": 0.6121,
+      "step": 377
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.3258993517225923e-05,
+      "loss": 0.5751,
+      "step": 378
+    },
+    {
+      "epoch": 1.2760942760942762,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.3223905350927718e-05,
+      "loss": 0.6198,
+      "step": 379
+    },
+    {
+      "epoch": 1.2794612794612794,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.318877283247619e-05,
+      "loss": 0.5938,
+      "step": 380
+    },
+    {
+      "epoch": 1.2794612794612794,
+      "eval_loss": 0.6084044575691223,
+      "eval_runtime": 8.685,
+      "eval_samples_per_second": 57.57,
+      "eval_steps_per_second": 3.685,
+      "step": 380
+    },
+    {
+      "epoch": 1.2828282828282829,
+      "grad_norm": 0.375,
+      "learning_rate": 1.3153596445199063e-05,
+      "loss": 0.6104,
+      "step": 381
+    },
+    {
+      "epoch": 1.2861952861952861,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.3118376673027588e-05,
+      "loss": 0.5953,
+      "step": 382
+    },
+    {
+      "epoch": 1.2895622895622896,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.3083114000489863e-05,
+      "loss": 0.5892,
+      "step": 383
+    },
+    {
+      "epoch": 1.2929292929292928,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.3047808912704178e-05,
+      "loss": 0.6184,
+      "step": 384
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.3012461895372343e-05,
+      "loss": 0.5926,
+      "step": 385
+    },
+    {
+      "epoch": 1.2996632996632997,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.2977073434773009e-05,
+      "loss": 0.571,
+      "step": 386
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.2941644017754964e-05,
+      "loss": 0.6072,
+      "step": 387
+    },
+    {
+      "epoch": 1.3063973063973064,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.2906174131730458e-05,
+      "loss": 0.5968,
+      "step": 388
+    },
+    {
+      "epoch": 1.3097643097643097,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.2870664264668467e-05,
+      "loss": 0.5982,
+      "step": 389
+    },
+    {
+      "epoch": 1.3131313131313131,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.2835114905088013e-05,
+      "loss": 0.5947,
+      "step": 390
+    },
+    {
+      "epoch": 1.3164983164983166,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.2799526542051419e-05,
+      "loss": 0.5942,
+      "step": 391
+    },
+    {
+      "epoch": 1.3198653198653199,
+      "grad_norm": 0.380859375,
+      "learning_rate": 1.2763899665157591e-05,
+      "loss": 0.6106,
+      "step": 392
+    },
+    {
+      "epoch": 1.3232323232323233,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.2728234764535283e-05,
+      "loss": 0.5929,
+      "step": 393
+    },
+    {
+      "epoch": 1.3265993265993266,
+      "grad_norm": 0.29296875,
+      "learning_rate": 1.2692532330836346e-05,
+      "loss": 0.5774,
+      "step": 394
+    },
+    {
+      "epoch": 1.32996632996633,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.2656792855228993e-05,
+      "loss": 0.6024,
+      "step": 395
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.2621016829391022e-05,
+      "loss": 0.6026,
+      "step": 396
+    },
+    {
+      "epoch": 1.3367003367003367,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.2585204745503072e-05,
+      "loss": 0.5987,
+      "step": 397
+    },
+    {
+      "epoch": 1.34006734006734,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.2549357096241841e-05,
+      "loss": 0.6175,
+      "step": 398
+    },
+    {
+      "epoch": 1.3434343434343434,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.25134743747733e-05,
+      "loss": 0.606,
+      "step": 399
+    },
+    {
+      "epoch": 1.3468013468013469,
+      "grad_norm": 0.306640625,
+      "learning_rate": 1.2477557074745932e-05,
+      "loss": 0.5935,
+      "step": 400
+    },
+    {
+      "epoch": 1.3501683501683501,
+      "grad_norm": 0.294921875,
+      "learning_rate": 1.2441605690283915e-05,
+      "loss": 0.6087,
+      "step": 401
+    },
+    {
+      "epoch": 1.3535353535353536,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.2405620715980345e-05,
+      "loss": 0.6107,
+      "step": 402
+    },
+    {
+      "epoch": 1.3569023569023568,
+      "grad_norm": 0.294921875,
+      "learning_rate": 1.2369602646890415e-05,
+      "loss": 0.5924,
+      "step": 403
+    },
+    {
+      "epoch": 1.3602693602693603,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.2333551978524618e-05,
+      "loss": 0.6308,
+      "step": 404
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.2297469206841921e-05,
+      "loss": 0.6212,
+      "step": 405
+    },
+    {
+      "epoch": 1.367003367003367,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.2261354828242948e-05,
+      "loss": 0.5882,
+      "step": 406
+    },
+    {
+      "epoch": 1.3703703703703702,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.6231,
+      "step": 407
+    },
+    {
+      "epoch": 1.3737373737373737,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.218903323806595e-05,
+      "loss": 0.6054,
+      "step": 408
+    },
+    {
+      "epoch": 1.3771043771043772,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.2152827021435946e-05,
+      "loss": 0.6463,
+      "step": 409
+    },
+    {
+      "epoch": 1.3804713804713804,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.2116591187772026e-05,
+      "loss": 0.6015,
+      "step": 410
+    },
+    {
+      "epoch": 1.3838383838383839,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.2080326235580521e-05,
+      "loss": 0.5653,
+      "step": 411
+    },
+    {
+      "epoch": 1.387205387205387,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.204403266376837e-05,
+      "loss": 0.5852,
+      "step": 412
+    },
+    {
+      "epoch": 1.3905723905723906,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.2007710971636221e-05,
+      "loss": 0.5886,
+      "step": 413
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.1971361658871597e-05,
+      "loss": 0.5933,
+      "step": 414
+    },
+    {
+      "epoch": 1.3973063973063973,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1.1934985225541998e-05,
+      "loss": 0.6065,
+      "step": 415
+    },
+    {
+      "epoch": 1.4006734006734007,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.1898582172088027e-05,
+      "loss": 0.595,
+      "step": 416
+    },
+    {
+      "epoch": 1.404040404040404,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.1862152999316517e-05,
+      "loss": 0.6061,
+      "step": 417
+    },
+    {
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.182569820839362e-05,
+      "loss": 0.5592,
+      "step": 418
+    },
+    {
+      "epoch": 1.4074074074074074,
+      "eval_loss": 0.6071019768714905,
+      "eval_runtime": 8.651,
+      "eval_samples_per_second": 57.797,
+      "eval_steps_per_second": 3.699,
+      "step": 418
+    },
+    {
+      "epoch": 1.410774410774411,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1.1789218300837929e-05,
+      "loss": 0.5964,
+      "step": 419
+    },
+    {
+      "epoch": 1.4141414141414141,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.1752713778513576e-05,
+      "loss": 0.588,
+      "step": 420
+    },
+    {
+      "epoch": 1.4175084175084174,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.1716185143623322e-05,
+      "loss": 0.5954,
+      "step": 421
+    },
+    {
+      "epoch": 1.4208754208754208,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.1679632898701649e-05,
+      "loss": 0.5887,
+      "step": 422
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.1643057546607858e-05,
+      "loss": 0.6194,
+      "step": 423
+    },
+    {
+      "epoch": 1.4276094276094276,
+      "grad_norm": 0.29296875,
+      "learning_rate": 1.1606459590519132e-05,
+      "loss": 0.5773,
+      "step": 424
+    },
+    {
+      "epoch": 1.430976430976431,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.1569839533923626e-05,
+      "loss": 0.6031,
+      "step": 425
+    },
+    {
+      "epoch": 1.4343434343434343,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.153319788061354e-05,
+      "loss": 0.6102,
+      "step": 426
+    },
+    {
+      "epoch": 1.4377104377104377,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.1496535134678186e-05,
+      "loss": 0.6135,
+      "step": 427
+    },
+    {
+      "epoch": 1.4410774410774412,
+      "grad_norm": 0.279296875,
+      "learning_rate": 1.1459851800497048e-05,
+      "loss": 0.5686,
+      "step": 428
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 0.5578,
+      "step": 429
+    },
+    {
+      "epoch": 1.4478114478114479,
+      "grad_norm": 0.421875,
+      "learning_rate": 1.1386425386324622e-05,
+      "loss": 0.6305,
+      "step": 430
+    },
+    {
+      "epoch": 1.4511784511784511,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.134968331648073e-05,
+      "loss": 0.6194,
+      "step": 431
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.1312922678671935e-05,
+      "loss": 0.5963,
+      "step": 432
+    },
+    {
+      "epoch": 1.457912457912458,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.1276143978624457e-05,
+      "loss": 0.627,
+      "step": 433
+    },
+    {
+      "epoch": 1.4612794612794613,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.1239347722312997e-05,
+      "loss": 0.587,
+      "step": 434
+    },
+    {
+      "epoch": 1.4646464646464645,
+      "grad_norm": 0.283203125,
+      "learning_rate": 1.120253441595378e-05,
+      "loss": 0.5845,
+      "step": 435
+    },
+    {
+      "epoch": 1.468013468013468,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.1165704565997593e-05,
+      "loss": 0.5788,
+      "step": 436
+    },
+    {
+      "epoch": 1.4713804713804715,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.1128858679122822e-05,
+      "loss": 0.571,
+      "step": 437
+    },
+    {
+      "epoch": 1.4747474747474747,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.1091997262228473e-05,
+      "loss": 0.6235,
+      "step": 438
+    },
+    {
+      "epoch": 1.4781144781144782,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.1055120822427208e-05,
+      "loss": 0.5438,
+      "step": 439
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.1018229867038358e-05,
+      "loss": 0.5704,
+      "step": 440
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.0981324903580945e-05,
+      "loss": 0.5693,
+      "step": 441
+    },
+    {
+      "epoch": 1.4882154882154883,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.0944406439766719e-05,
+      "loss": 0.6106,
+      "step": 442
+    },
+    {
+      "epoch": 1.4915824915824916,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1.0907474983493144e-05,
+      "loss": 0.6313,
+      "step": 443
+    },
+    {
+      "epoch": 1.494949494949495,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.087053104283643e-05,
+      "loss": 0.5699,
+      "step": 444
+    },
+    {
+      "epoch": 1.4983164983164983,
+      "grad_norm": 0.29296875,
+      "learning_rate": 1.083357512604454e-05,
+      "loss": 0.5806,
+      "step": 445
+    },
+    {
+      "epoch": 1.5016835016835017,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.0796607741530191e-05,
+      "loss": 0.5922,
+      "step": 446
+    },
+    {
+      "epoch": 1.5050505050505052,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.075962939786387e-05,
+      "loss": 0.6123,
+      "step": 447
+    },
+    {
+      "epoch": 1.5084175084175084,
+      "grad_norm": 0.2890625,
+      "learning_rate": 1.0722640603766825e-05,
+      "loss": 0.5926,
+      "step": 448
+    },
+    {
+      "epoch": 1.5117845117845117,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.0685641868104085e-05,
+      "loss": 0.6335,
+      "step": 449
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.064863369987743e-05,
+      "loss": 0.5997,
+      "step": 450
+    },
+    {
+      "epoch": 1.5185185185185186,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.0611616608218429e-05,
+      "loss": 0.6001,
+      "step": 451
+    },
+    {
+      "epoch": 1.5218855218855218,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.0574591102381395e-05,
+      "loss": 0.6193,
+      "step": 452
+    },
+    {
+      "epoch": 1.5252525252525253,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.0537557691736402e-05,
+      "loss": 0.5833,
+      "step": 453
+    },
+    {
+      "epoch": 1.5286195286195285,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.0500516885762278e-05,
+      "loss": 0.6065,
+      "step": 454
+    },
+    {
+      "epoch": 1.531986531986532,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.0463469194039584e-05,
+      "loss": 0.6208,
+      "step": 455
+    },
+    {
+      "epoch": 1.5353535353535355,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.0426415126243615e-05,
+      "loss": 0.6041,
+      "step": 456
+    },
+    {
+      "epoch": 1.5353535353535355,
+      "eval_loss": 0.6061655282974243,
+      "eval_runtime": 8.7167,
+      "eval_samples_per_second": 57.361,
+      "eval_steps_per_second": 3.671,
+      "step": 456
+    },
+    {
+      "epoch": 1.5387205387205387,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.0389355192137379e-05,
+      "loss": 0.5762,
+      "step": 457
+    },
+    {
+      "epoch": 1.542087542087542,
+      "grad_norm": 0.306640625,
+      "learning_rate": 1.0352289901564592e-05,
+      "loss": 0.6152,
+      "step": 458
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.0315219764442657e-05,
+      "loss": 0.617,
+      "step": 459
+    },
+    {
+      "epoch": 1.5488215488215489,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.0278145290755657e-05,
+      "loss": 0.5459,
+      "step": 460
+    },
+    {
+      "epoch": 1.5521885521885523,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.0241066990547328e-05,
+      "loss": 0.5702,
+      "step": 461
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.0203985373914056e-05,
+      "loss": 0.591,
+      "step": 462
+    },
+    {
+      "epoch": 1.5589225589225588,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.0166900950997845e-05,
+      "loss": 0.622,
+      "step": 463
+    },
+    {
+      "epoch": 1.5622895622895623,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.012981423197931e-05,
+      "loss": 0.6427,
+      "step": 464
+    },
+    {
+      "epoch": 1.5656565656565657,
+      "grad_norm": 0.310546875,
+      "learning_rate": 1.0092725727070653e-05,
+      "loss": 0.5941,
+      "step": 465
+    },
+    {
+      "epoch": 1.569023569023569,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.0055635946508649e-05,
+      "loss": 0.622,
+      "step": 466
+    },
+    {
+      "epoch": 1.5723905723905722,
+      "grad_norm": 0.484375,
+      "learning_rate": 1.0018545400547609e-05,
+      "loss": 0.591,
+      "step": 467
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 0.291015625,
+      "learning_rate": 9.981454599452391e-06,
+      "loss": 0.5814,
+      "step": 468
+    },
+    {
+      "epoch": 1.5791245791245792,
+      "grad_norm": 0.330078125,
+      "learning_rate": 9.944364053491356e-06,
+      "loss": 0.6045,
+      "step": 469
+    },
+    {
+      "epoch": 1.5824915824915826,
+      "grad_norm": 0.330078125,
+      "learning_rate": 9.90727427292935e-06,
+      "loss": 0.562,
+      "step": 470
+    },
+    {
+      "epoch": 1.5858585858585859,
+      "grad_norm": 0.3125,
+      "learning_rate": 9.870185768020694e-06,
+      "loss": 0.5714,
+      "step": 471
+    },
+    {
+      "epoch": 1.589225589225589,
+      "grad_norm": 0.31640625,
+      "learning_rate": 9.83309904900216e-06,
+      "loss": 0.5765,
+      "step": 472
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "grad_norm": 0.287109375,
+      "learning_rate": 9.79601462608595e-06,
+      "loss": 0.5943,
+      "step": 473
+    },
+    {
+      "epoch": 1.595959595959596,
+      "grad_norm": 0.30078125,
+      "learning_rate": 9.758933009452674e-06,
+      "loss": 0.6049,
+      "step": 474
+    },
+    {
+      "epoch": 1.5993265993265995,
+      "grad_norm": 0.32421875,
+      "learning_rate": 9.721854709244346e-06,
+      "loss": 0.6075,
+      "step": 475
+    },
+    {
+      "epoch": 1.6026936026936027,
+      "grad_norm": 0.37109375,
+      "learning_rate": 9.684780235557346e-06,
+      "loss": 0.6078,
+      "step": 476
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 0.328125,
+      "learning_rate": 9.647710098435413e-06,
+      "loss": 0.6221,
+      "step": 477
+    },
+    {
+      "epoch": 1.6094276094276094,
+      "grad_norm": 0.328125,
+      "learning_rate": 9.610644807862625e-06,
+      "loss": 0.6269,
+      "step": 478
+    },
+    {
+      "epoch": 1.612794612794613,
+      "grad_norm": 0.32421875,
+      "learning_rate": 9.573584873756387e-06,
+      "loss": 0.6095,
+      "step": 479
+    },
+    {
+      "epoch": 1.6161616161616161,
+      "grad_norm": 0.310546875,
+      "learning_rate": 9.536530805960418e-06,
+      "loss": 0.5573,
+      "step": 480
+    },
+    {
+      "epoch": 1.6195286195286194,
+      "grad_norm": 0.30859375,
+      "learning_rate": 9.499483114237726e-06,
+      "loss": 0.6072,
+      "step": 481
+    },
+    {
+      "epoch": 1.6228956228956228,
+      "grad_norm": 0.3125,
+      "learning_rate": 9.4624423082636e-06,
+      "loss": 0.5876,
+      "step": 482
+    },
+    {
+      "epoch": 1.6262626262626263,
+      "grad_norm": 0.287109375,
+      "learning_rate": 9.42540889761861e-06,
+      "loss": 0.605,
+      "step": 483
+    },
+    {
+      "epoch": 1.6296296296296298,
+      "grad_norm": 0.32421875,
+      "learning_rate": 9.388383391781576e-06,
+      "loss": 0.5952,
+      "step": 484
+    },
+    {
+      "epoch": 1.632996632996633,
+      "grad_norm": 0.2890625,
+      "learning_rate": 9.351366300122569e-06,
+      "loss": 0.6113,
+      "step": 485
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.330078125,
+      "learning_rate": 9.314358131895919e-06,
+      "loss": 0.6207,
+      "step": 486
+    },
+    {
+      "epoch": 1.6397306397306397,
+      "grad_norm": 0.35546875,
+      "learning_rate": 9.277359396233176e-06,
+      "loss": 0.6038,
+      "step": 487
+    },
+    {
+      "epoch": 1.6430976430976432,
+      "grad_norm": 0.330078125,
+      "learning_rate": 9.240370602136134e-06,
+      "loss": 0.5764,
+      "step": 488
+    },
+    {
+      "epoch": 1.6464646464646466,
+      "grad_norm": 0.3125,
+      "learning_rate": 9.203392258469814e-06,
+      "loss": 0.5874,
+      "step": 489
+    },
+    {
+      "epoch": 1.6498316498316499,
+      "grad_norm": 0.3125,
+      "learning_rate": 9.166424873955462e-06,
+      "loss": 0.6086,
+      "step": 490
+    },
+    {
+      "epoch": 1.6531986531986531,
+      "grad_norm": 0.326171875,
+      "learning_rate": 9.12946895716357e-06,
+      "loss": 0.6301,
+      "step": 491
+    },
+    {
+      "epoch": 1.6565656565656566,
+      "grad_norm": 0.330078125,
+      "learning_rate": 9.092525016506858e-06,
+      "loss": 0.631,
+      "step": 492
+    },
+    {
+      "epoch": 1.65993265993266,
+      "grad_norm": 0.353515625,
+      "learning_rate": 9.055593560233284e-06,
+      "loss": 0.6312,
+      "step": 493
+    },
+    {
+      "epoch": 1.6632996632996633,
+      "grad_norm": 0.310546875,
+      "learning_rate": 9.018675096419059e-06,
+      "loss": 0.5768,
+      "step": 494
+    },
+    {
+      "epoch": 1.6632996632996633,
+      "eval_loss": 0.6054856777191162,
+      "eval_runtime": 8.7005,
+      "eval_samples_per_second": 57.468,
+      "eval_steps_per_second": 3.678,
+      "step": 494
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.30078125,
+      "learning_rate": 8.981770132961649e-06,
+      "loss": 0.5698,
+      "step": 495
+    },
+    {
+      "epoch": 1.67003367003367,
+      "grad_norm": 0.3359375,
+      "learning_rate": 8.944879177572796e-06,
+      "loss": 0.6081,
+      "step": 496
+    },
+    {
+      "epoch": 1.6734006734006734,
+      "grad_norm": 0.318359375,
+      "learning_rate": 8.908002737771529e-06,
+      "loss": 0.5791,
+      "step": 497
+    },
+    {
+      "epoch": 1.676767676767677,
+      "grad_norm": 0.30078125,
+      "learning_rate": 8.871141320877181e-06,
+      "loss": 0.5912,
+      "step": 498
+    },
+    {
+      "epoch": 1.6801346801346801,
+      "grad_norm": 0.35546875,
+      "learning_rate": 8.83429543400241e-06,
+      "loss": 0.606,
+      "step": 499
+    },
+    {
+      "epoch": 1.6835016835016834,
+      "grad_norm": 0.3046875,
+      "learning_rate": 8.797465584046225e-06,
+      "loss": 0.5852,
+      "step": 500
+    },
+    {
+      "epoch": 1.6868686868686869,
+      "grad_norm": 0.380859375,
+      "learning_rate": 8.760652277687007e-06,
+      "loss": 0.6325,
+      "step": 501
+    },
+    {
+      "epoch": 1.6902356902356903,
+      "grad_norm": 0.337890625,
+      "learning_rate": 8.723856021375543e-06,
+      "loss": 0.6013,
+      "step": 502
+    },
+    {
+      "epoch": 1.6936026936026936,
+      "grad_norm": 0.31640625,
+      "learning_rate": 8.687077321328066e-06,
+      "loss": 0.591,
+      "step": 503
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 0.3359375,
+      "learning_rate": 8.650316683519276e-06,
+      "loss": 0.6132,
+      "step": 504
+    },
+    {
+      "epoch": 1.7003367003367003,
+      "grad_norm": 0.294921875,
+      "learning_rate": 8.61357461367538e-06,
+      "loss": 0.5836,
+      "step": 505
+    },
+    {
+      "epoch": 1.7037037037037037,
+      "grad_norm": 0.302734375,
+      "learning_rate": 8.576851617267151e-06,
+      "loss": 0.6312,
+      "step": 506
+    },
+    {
+      "epoch": 1.7070707070707072,
+      "grad_norm": 0.41796875,
+      "learning_rate": 8.540148199502955e-06,
+      "loss": 0.5807,
+      "step": 507
+    },
+    {
+      "epoch": 1.7104377104377104,
+      "grad_norm": 0.3046875,
+      "learning_rate": 8.503464865321817e-06,
+      "loss": 0.6041,
+      "step": 508
+    },
+    {
+      "epoch": 1.7138047138047137,
+      "grad_norm": 0.287109375,
+      "learning_rate": 8.466802119386462e-06,
+      "loss": 0.5789,
+      "step": 509
+    },
+    {
+      "epoch": 1.7171717171717171,
+      "grad_norm": 0.287109375,
+      "learning_rate": 8.430160466076378e-06,
+      "loss": 0.5908,
+      "step": 510
+    },
+    {
+      "epoch": 1.7205387205387206,
+      "grad_norm": 0.30859375,
+      "learning_rate": 8.393540409480873e-06,
+      "loss": 0.6105,
+      "step": 511
+    },
+    {
+      "epoch": 1.723905723905724,
+      "grad_norm": 0.310546875,
+      "learning_rate": 8.356942453392147e-06,
+      "loss": 0.5964,
+      "step": 512
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.337890625,
+      "learning_rate": 8.320367101298351e-06,
+      "loss": 0.636,
+      "step": 513
+    },
+    {
+      "epoch": 1.7306397306397305,
+      "grad_norm": 0.31640625,
+      "learning_rate": 8.283814856376681e-06,
+      "loss": 0.6001,
+      "step": 514
+    },
+    {
+      "epoch": 1.734006734006734,
+      "grad_norm": 0.2890625,
+      "learning_rate": 8.247286221486429e-06,
+      "loss": 0.5764,
+      "step": 515
+    },
+    {
+      "epoch": 1.7373737373737375,
+      "grad_norm": 0.31640625,
+      "learning_rate": 8.210781699162075e-06,
+      "loss": 0.5564,
+      "step": 516
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 0.3046875,
+      "learning_rate": 8.174301791606384e-06,
+      "loss": 0.5797,
+      "step": 517
+    },
+    {
+      "epoch": 1.7441077441077442,
+      "grad_norm": 0.318359375,
+      "learning_rate": 8.137847000683485e-06,
+      "loss": 0.5987,
+      "step": 518
+    },
+    {
+      "epoch": 1.7474747474747474,
+      "grad_norm": 0.326171875,
+      "learning_rate": 8.101417827911975e-06,
+      "loss": 0.6197,
+      "step": 519
+    },
+    {
+      "epoch": 1.7508417508417509,
+      "grad_norm": 0.375,
+      "learning_rate": 8.065014774458004e-06,
+      "loss": 0.6284,
+      "step": 520
+    },
+    {
+      "epoch": 1.7542087542087543,
+      "grad_norm": 0.3125,
+      "learning_rate": 8.028638341128405e-06,
+      "loss": 0.5972,
+      "step": 521
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 0.2890625,
+      "learning_rate": 7.992289028363782e-06,
+      "loss": 0.5666,
+      "step": 522
+    },
+    {
+      "epoch": 1.7609427609427608,
+      "grad_norm": 0.296875,
+      "learning_rate": 7.955967336231635e-06,
+      "loss": 0.5555,
+      "step": 523
+    },
+    {
+      "epoch": 1.7643097643097643,
+      "grad_norm": 0.357421875,
+      "learning_rate": 7.919673764419479e-06,
+      "loss": 0.5559,
+      "step": 524
+    },
+    {
+      "epoch": 1.7676767676767677,
+      "grad_norm": 0.302734375,
+      "learning_rate": 7.883408812227977e-06,
+      "loss": 0.6168,
+      "step": 525
+    },
+    {
+      "epoch": 1.7710437710437712,
+      "grad_norm": 0.279296875,
+      "learning_rate": 7.847172978564055e-06,
+      "loss": 0.5484,
+      "step": 526
+    },
+    {
+      "epoch": 1.7744107744107744,
+      "grad_norm": 0.3125,
+      "learning_rate": 7.810966761934053e-06,
+      "loss": 0.587,
+      "step": 527
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.333984375,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.5885,
+      "step": 528
+    },
+    {
+      "epoch": 1.7811447811447811,
+      "grad_norm": 0.35546875,
+      "learning_rate": 7.738645171757054e-06,
+      "loss": 0.617,
+      "step": 529
+    },
+    {
+      "epoch": 1.7845117845117846,
+      "grad_norm": 0.287109375,
+      "learning_rate": 7.702530793158079e-06,
+      "loss": 0.5953,
+      "step": 530
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 0.27734375,
+      "learning_rate": 7.666448021475385e-06,
+      "loss": 0.5807,
+      "step": 531
+    },
+    {
+      "epoch": 1.791245791245791,
+      "grad_norm": 0.322265625,
+      "learning_rate": 7.630397353109588e-06,
+      "loss": 0.6238,
+      "step": 532
+    },
+    {
+      "epoch": 1.791245791245791,
+      "eval_loss": 0.6051895618438721,
+      "eval_runtime": 8.6459,
+      "eval_samples_per_second": 57.831,
+      "eval_steps_per_second": 3.701,
+      "step": 532
+    },
+    {
+      "epoch": 1.7946127946127945,
+      "grad_norm": 0.330078125,
+      "learning_rate": 7.594379284019659e-06,
+      "loss": 0.6278,
+      "step": 533
+    },
+    {
+      "epoch": 1.797979797979798,
+      "grad_norm": 0.3046875,
+      "learning_rate": 7.558394309716088e-06,
+      "loss": 0.5459,
+      "step": 534
+    },
+    {
+      "epoch": 1.8013468013468015,
+      "grad_norm": 0.294921875,
+      "learning_rate": 7.522442925254068e-06,
+      "loss": 0.5948,
+      "step": 535
+    },
+    {
+      "epoch": 1.8047138047138047,
+      "grad_norm": 0.310546875,
+      "learning_rate": 7.486525625226699e-06,
+      "loss": 0.5845,
+      "step": 536
+    },
+    {
+      "epoch": 1.808080808080808,
+      "grad_norm": 0.31640625,
+      "learning_rate": 7.450642903758163e-06,
+      "loss": 0.5917,
+      "step": 537
+    },
+    {
+      "epoch": 1.8114478114478114,
+      "grad_norm": 0.306640625,
+      "learning_rate": 7.414795254496929e-06,
+      "loss": 0.5752,
+      "step": 538
+    },
+    {
+      "epoch": 1.8148148148148149,
+      "grad_norm": 0.294921875,
+      "learning_rate": 7.378983170608982e-06,
+      "loss": 0.581,
+      "step": 539
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.302734375,
+      "learning_rate": 7.343207144771012e-06,
+      "loss": 0.5508,
+      "step": 540
+    },
+    {
+      "epoch": 1.8215488215488216,
+      "grad_norm": 0.30078125,
+      "learning_rate": 7.307467669163655e-06,
+      "loss": 0.6313,
+      "step": 541
+    },
+    {
+      "epoch": 1.8249158249158248,
+      "grad_norm": 0.306640625,
+      "learning_rate": 7.27176523546472e-06,
+      "loss": 0.6053,
+      "step": 542
+    },
+    {
+      "epoch": 1.8282828282828283,
+      "grad_norm": 0.31640625,
+      "learning_rate": 7.2361003348424105e-06,
+      "loss": 0.5844,
+      "step": 543
+    },
+    {
+      "epoch": 1.8316498316498318,
+      "grad_norm": 0.310546875,
+      "learning_rate": 7.200473457948584e-06,
+      "loss": 0.5868,
+      "step": 544
+    },
+    {
+      "epoch": 1.835016835016835,
+      "grad_norm": 0.298828125,
+      "learning_rate": 7.164885094911991e-06,
+      "loss": 0.5771,
+      "step": 545
+    },
+    {
+      "epoch": 1.8383838383838382,
+      "grad_norm": 0.30859375,
+      "learning_rate": 7.129335735331537e-06,
+      "loss": 0.6194,
+      "step": 546
+    },
+    {
+      "epoch": 1.8417508417508417,
+      "grad_norm": 0.349609375,
+      "learning_rate": 7.093825868269546e-06,
+      "loss": 0.5942,
+      "step": 547
+    },
+    {
+      "epoch": 1.8451178451178452,
+      "grad_norm": 0.29296875,
+      "learning_rate": 7.058355982245038e-06,
+      "loss": 0.6125,
+      "step": 548
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 0.294921875,
+      "learning_rate": 7.022926565226995e-06,
+      "loss": 0.5879,
+      "step": 549
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.3046875,
+      "learning_rate": 6.9875381046276605e-06,
+      "loss": 0.5829,
+      "step": 550
+    },
+    {
+      "epoch": 1.855218855218855,
+      "grad_norm": 0.287109375,
+      "learning_rate": 6.952191087295827e-06,
+      "loss": 0.5979,
+      "step": 551
+    },
+    {
+      "epoch": 1.8585858585858586,
+      "grad_norm": 0.3359375,
+      "learning_rate": 6.916885999510137e-06,
+      "loss": 0.6034,
+      "step": 552
+    },
+    {
+      "epoch": 1.861952861952862,
+      "grad_norm": 0.34765625,
+      "learning_rate": 6.881623326972412e-06,
+      "loss": 0.6016,
+      "step": 553
+    },
+    {
+      "epoch": 1.8653198653198653,
+      "grad_norm": 0.298828125,
+      "learning_rate": 6.846403554800938e-06,
+      "loss": 0.613,
+      "step": 554
+    },
+    {
+      "epoch": 1.8686868686868687,
+      "grad_norm": 0.29296875,
+      "learning_rate": 6.8112271675238154e-06,
+      "loss": 0.6453,
+      "step": 555
+    },
+    {
+      "epoch": 1.872053872053872,
+      "grad_norm": 0.384765625,
+      "learning_rate": 6.776094649072286e-06,
+      "loss": 0.5958,
+      "step": 556
+    },
+    {
+      "epoch": 1.8754208754208754,
+      "grad_norm": 0.30078125,
+      "learning_rate": 6.7410064827740805e-06,
+      "loss": 0.6212,
+      "step": 557
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 0.328125,
+      "learning_rate": 6.705963151346755e-06,
+      "loss": 0.6009,
+      "step": 558
+    },
+    {
+      "epoch": 1.8821548821548821,
+      "grad_norm": 0.310546875,
+      "learning_rate": 6.670965136891072e-06,
+      "loss": 0.5869,
+      "step": 559
+    },
+    {
+      "epoch": 1.8855218855218854,
+      "grad_norm": 0.328125,
+      "learning_rate": 6.636012920884346e-06,
+      "loss": 0.5877,
+      "step": 560
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.28125,
+      "learning_rate": 6.601106984173835e-06,
+      "loss": 0.5836,
+      "step": 561
+    },
+    {
+      "epoch": 1.8922558922558923,
+      "grad_norm": 0.3046875,
+      "learning_rate": 6.566247806970119e-06,
+      "loss": 0.5899,
+      "step": 562
+    },
+    {
+      "epoch": 1.8956228956228958,
+      "grad_norm": 0.306640625,
+      "learning_rate": 6.531435868840488e-06,
+      "loss": 0.6274,
+      "step": 563
+    },
+    {
+      "epoch": 1.898989898989899,
+      "grad_norm": 0.314453125,
+      "learning_rate": 6.496671648702366e-06,
+      "loss": 0.6088,
+      "step": 564
+    },
+    {
+      "epoch": 1.9023569023569022,
+      "grad_norm": 0.322265625,
+      "learning_rate": 6.461955624816696e-06,
+      "loss": 0.5814,
+      "step": 565
+    },
+    {
+      "epoch": 1.9057239057239057,
+      "grad_norm": 0.28515625,
+      "learning_rate": 6.427288274781372e-06,
+      "loss": 0.6009,
+      "step": 566
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.3046875,
+      "learning_rate": 6.392670075524674e-06,
+      "loss": 0.5995,
+      "step": 567
+    },
+    {
+      "epoch": 1.9124579124579124,
+      "grad_norm": 0.291015625,
+      "learning_rate": 6.3581015032986945e-06,
+      "loss": 0.5983,
+      "step": 568
+    },
+    {
+      "epoch": 1.9158249158249159,
+      "grad_norm": 0.298828125,
+      "learning_rate": 6.323583033672799e-06,
+      "loss": 0.5854,
+      "step": 569
+    },
+    {
+      "epoch": 1.9191919191919191,
+      "grad_norm": 0.34375,
+      "learning_rate": 6.289115141527077e-06,
+      "loss": 0.5944,
+      "step": 570
+    },
+    {
+      "epoch": 1.9191919191919191,
+      "eval_loss": 0.6048124432563782,
+      "eval_runtime": 8.729,
+      "eval_samples_per_second": 57.28,
+      "eval_steps_per_second": 3.666,
+      "step": 570
+    },
+    {
+      "epoch": 1.9225589225589226,
+      "grad_norm": 0.283203125,
+      "learning_rate": 6.254698301045806e-06,
+      "loss": 0.5679,
+      "step": 571
+    },
+    {
+      "epoch": 1.925925925925926,
+      "grad_norm": 0.318359375,
+      "learning_rate": 6.220332985710936e-06,
+      "loss": 0.6005,
+      "step": 572
+    },
+    {
+      "epoch": 1.9292929292929293,
+      "grad_norm": 0.328125,
+      "learning_rate": 6.186019668295568e-06,
+      "loss": 0.569,
+      "step": 573
+    },
+    {
+      "epoch": 1.9326599326599325,
+      "grad_norm": 0.3515625,
+      "learning_rate": 6.151758820857455e-06,
+      "loss": 0.6222,
+      "step": 574
+    },
+    {
+      "epoch": 1.936026936026936,
+      "grad_norm": 0.322265625,
+      "learning_rate": 6.1175509147325015e-06,
+      "loss": 0.6131,
+      "step": 575
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 0.328125,
+      "learning_rate": 6.083396420528298e-06,
+      "loss": 0.6196,
+      "step": 576
+    },
+    {
+      "epoch": 1.942760942760943,
+      "grad_norm": 0.306640625,
+      "learning_rate": 6.0492958081176155e-06,
+      "loss": 0.6235,
+      "step": 577
+    },
+    {
+      "epoch": 1.9461279461279462,
+      "grad_norm": 0.3125,
+      "learning_rate": 6.015249546631969e-06,
+      "loss": 0.5894,
+      "step": 578
+    },
+    {
+      "epoch": 1.9494949494949494,
+      "grad_norm": 0.3125,
+      "learning_rate": 5.9812581044551475e-06,
+      "loss": 0.5872,
+      "step": 579
+    },
+    {
+      "epoch": 1.9528619528619529,
+      "grad_norm": 0.314453125,
+      "learning_rate": 5.947321949216771e-06,
+      "loss": 0.6183,
+      "step": 580
+    },
+    {
+      "epoch": 1.9562289562289563,
+      "grad_norm": 0.306640625,
+      "learning_rate": 5.913441547785879e-06,
+      "loss": 0.5476,
+      "step": 581
+    },
+    {
+      "epoch": 1.9595959595959596,
+      "grad_norm": 0.33203125,
+      "learning_rate": 5.879617366264476e-06,
+      "loss": 0.6052,
+      "step": 582
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 0.28125,
+      "learning_rate": 5.845849869981137e-06,
+      "loss": 0.5703,
+      "step": 583
+    },
+    {
+      "epoch": 1.9663299663299663,
+      "grad_norm": 0.314453125,
+      "learning_rate": 5.812139523484604e-06,
+      "loss": 0.6173,
+      "step": 584
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 0.3125,
+      "learning_rate": 5.778486790537392e-06,
+      "loss": 0.5968,
+      "step": 585
+    },
+    {
+      "epoch": 1.9730639730639732,
+      "grad_norm": 0.302734375,
+      "learning_rate": 5.744892134109406e-06,
+      "loss": 0.587,
+      "step": 586
+    },
+    {
+      "epoch": 1.9764309764309764,
+      "grad_norm": 0.3046875,
+      "learning_rate": 5.711356016371593e-06,
+      "loss": 0.5832,
+      "step": 587
+    },
+    {
+      "epoch": 1.9797979797979797,
+      "grad_norm": 0.30078125,
+      "learning_rate": 5.6778788986895464e-06,
+      "loss": 0.5929,
+      "step": 588
+    },
+    {
+      "epoch": 1.9831649831649831,
+      "grad_norm": 0.3046875,
+      "learning_rate": 5.6444612416171976e-06,
+      "loss": 0.5842,
+      "step": 589
+    },
+    {
+      "epoch": 1.9865319865319866,
+      "grad_norm": 0.306640625,
+      "learning_rate": 5.611103504890444e-06,
+      "loss": 0.6331,
+      "step": 590
+    },
+    {
+      "epoch": 1.98989898989899,
+      "grad_norm": 0.314453125,
+      "learning_rate": 5.5778061474208565e-06,
+      "loss": 0.59,
+      "step": 591
+    },
+    {
+      "epoch": 1.9932659932659933,
+      "grad_norm": 0.2890625,
+      "learning_rate": 5.54456962728935e-06,
+      "loss": 0.5773,
+      "step": 592
+    },
+    {
+      "epoch": 1.9966329966329965,
+      "grad_norm": 0.310546875,
+      "learning_rate": 5.511394401739874e-06,
+      "loss": 0.6032,
+      "step": 593
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.328125,
+      "learning_rate": 5.478280927173145e-06,
+      "loss": 0.6187,
+      "step": 594
+    },
+    {
+      "epoch": 2.0033670033670035,
+      "grad_norm": 0.30859375,
+      "learning_rate": 5.445229659140341e-06,
+      "loss": 0.6078,
+      "step": 595
+    },
+    {
+      "epoch": 2.006734006734007,
+      "grad_norm": 0.31640625,
+      "learning_rate": 5.4122410523368615e-06,
+      "loss": 0.6052,
+      "step": 596
+    },
+    {
+      "epoch": 2.01010101010101,
+      "grad_norm": 0.357421875,
+      "learning_rate": 5.379315560596038e-06,
+      "loss": 0.5684,
+      "step": 597
+    },
+    {
+      "epoch": 2.0134680134680134,
+      "grad_norm": 0.28125,
+      "learning_rate": 5.346453636882939e-06,
+      "loss": 0.5352,
+      "step": 598
+    },
+    {
+      "epoch": 2.016835016835017,
+      "grad_norm": 0.30859375,
+      "learning_rate": 5.313655733288083e-06,
+      "loss": 0.622,
+      "step": 599
+    },
+    {
+      "epoch": 2.0202020202020203,
+      "grad_norm": 0.353515625,
+      "learning_rate": 5.280922301021267e-06,
+      "loss": 0.6034,
+      "step": 600
+    },
+    {
+      "epoch": 2.0235690235690234,
+      "grad_norm": 0.37109375,
+      "learning_rate": 5.2482537904053185e-06,
+      "loss": 0.6358,
+      "step": 601
+    },
+    {
+      "epoch": 2.026936026936027,
+      "grad_norm": 0.298828125,
+      "learning_rate": 5.215650650869941e-06,
+      "loss": 0.5751,
+      "step": 602
+    },
+    {
+      "epoch": 2.0303030303030303,
+      "grad_norm": 0.322265625,
+      "learning_rate": 5.183113330945488e-06,
+      "loss": 0.6599,
+      "step": 603
+    },
+    {
+      "epoch": 2.0336700336700337,
+      "grad_norm": 0.2890625,
+      "learning_rate": 5.1506422782568345e-06,
+      "loss": 0.583,
+      "step": 604
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 0.291015625,
+      "learning_rate": 5.11823793951719e-06,
+      "loss": 0.6011,
+      "step": 605
+    },
+    {
+      "epoch": 2.04040404040404,
+      "grad_norm": 0.314453125,
+      "learning_rate": 5.085900760521955e-06,
+      "loss": 0.5673,
+      "step": 606
+    },
+    {
+      "epoch": 2.0437710437710437,
+      "grad_norm": 0.330078125,
+      "learning_rate": 5.053631186142612e-06,
+      "loss": 0.6132,
+      "step": 607
+    },
+    {
+      "epoch": 2.047138047138047,
+      "grad_norm": 0.287109375,
+      "learning_rate": 5.021429660320565e-06,
+      "loss": 0.588,
+      "step": 608
+    },
+    {
+      "epoch": 2.047138047138047,
+      "eval_loss": 0.6045156717300415,
+      "eval_runtime": 8.6619,
+      "eval_samples_per_second": 57.724,
+      "eval_steps_per_second": 3.694,
+      "step": 608
+    },
+    {
+      "epoch": 2.0505050505050506,
+      "grad_norm": 0.3125,
+      "learning_rate": 4.989296626061084e-06,
+      "loss": 0.6232,
+      "step": 609
+    },
+    {
+      "epoch": 2.053872053872054,
+      "grad_norm": 0.3203125,
+      "learning_rate": 4.957232525427156e-06,
+      "loss": 0.6382,
+      "step": 610
+    },
+    {
+      "epoch": 2.057239057239057,
+      "grad_norm": 0.330078125,
+      "learning_rate": 4.925237799533445e-06,
+      "loss": 0.5681,
+      "step": 611
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 0.30859375,
+      "learning_rate": 4.893312888540195e-06,
+      "loss": 0.6241,
+      "step": 612
+    },
+    {
+      "epoch": 2.063973063973064,
+      "grad_norm": 0.3125,
+      "learning_rate": 4.861458231647202e-06,
+      "loss": 0.5998,
+      "step": 613
+    },
+    {
+      "epoch": 2.0673400673400675,
+      "grad_norm": 0.30859375,
+      "learning_rate": 4.829674267087742e-06,
+      "loss": 0.622,
+      "step": 614
+    },
+    {
+      "epoch": 2.0707070707070705,
+      "grad_norm": 0.310546875,
+      "learning_rate": 4.797961432122568e-06,
+      "loss": 0.5871,
+      "step": 615
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.30078125,
+      "learning_rate": 4.766320163033882e-06,
+      "loss": 0.5808,
+      "step": 616
+    },
+    {
+      "epoch": 2.0774410774410774,
+      "grad_norm": 0.318359375,
+      "learning_rate": 4.734750895119327e-06,
+      "loss": 0.6411,
+      "step": 617
+    },
+    {
+      "epoch": 2.080808080808081,
+      "grad_norm": 0.30078125,
+      "learning_rate": 4.703254062686017e-06,
+      "loss": 0.6223,
+      "step": 618
+    },
+    {
+      "epoch": 2.0841750841750843,
+      "grad_norm": 0.337890625,
+      "learning_rate": 4.671830099044536e-06,
+      "loss": 0.6236,
+      "step": 619
+    },
+    {
+      "epoch": 2.0875420875420874,
+      "grad_norm": 0.294921875,
+      "learning_rate": 4.640479436503016e-06,
+      "loss": 0.5896,
+      "step": 620
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 0.283203125,
+      "learning_rate": 4.60920250636114e-06,
+      "loss": 0.5659,
+      "step": 621
+    },
+    {
+      "epoch": 2.0942760942760943,
+      "grad_norm": 0.30078125,
+      "learning_rate": 4.5779997389042514e-06,
+      "loss": 0.6173,
+      "step": 622
+    },
+    {
+      "epoch": 2.0976430976430978,
+      "grad_norm": 0.330078125,
+      "learning_rate": 4.546871563397409e-06,
+      "loss": 0.6073,
+      "step": 623
+    },
+    {
+      "epoch": 2.101010101010101,
+      "grad_norm": 0.29296875,
+      "learning_rate": 4.515818408079487e-06,
+      "loss": 0.6025,
+      "step": 624
+    },
+    {
+      "epoch": 2.1043771043771042,
+      "grad_norm": 0.3125,
+      "learning_rate": 4.4848407001572945e-06,
+      "loss": 0.5557,
+      "step": 625
+    },
+    {
+      "epoch": 2.1077441077441077,
+      "grad_norm": 0.322265625,
+      "learning_rate": 4.453938865799686e-06,
+      "loss": 0.6205,
+      "step": 626
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 0.337890625,
+      "learning_rate": 4.423113330131708e-06,
+      "loss": 0.5837,
+      "step": 627
+    },
+    {
+      "epoch": 2.1144781144781146,
+      "grad_norm": 0.30078125,
+      "learning_rate": 4.39236451722873e-06,
+      "loss": 0.5702,
+      "step": 628
+    },
+    {
+      "epoch": 2.1178451178451176,
+      "grad_norm": 0.287109375,
+      "learning_rate": 4.361692850110644e-06,
+      "loss": 0.5408,
+      "step": 629
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 0.326171875,
+      "learning_rate": 4.331098750736008e-06,
+      "loss": 0.587,
+      "step": 630
+    },
+    {
+      "epoch": 2.1245791245791246,
+      "grad_norm": 0.30078125,
+      "learning_rate": 4.300582639996274e-06,
+      "loss": 0.5834,
+      "step": 631
+    },
+    {
+      "epoch": 2.127946127946128,
+      "grad_norm": 0.3125,
+      "learning_rate": 4.270144937709981e-06,
+      "loss": 0.6304,
+      "step": 632
+    },
+    {
+      "epoch": 2.1313131313131315,
+      "grad_norm": 0.283203125,
+      "learning_rate": 4.23978606261697e-06,
+      "loss": 0.5277,
+      "step": 633
+    },
+    {
+      "epoch": 2.1346801346801345,
+      "grad_norm": 0.30078125,
+      "learning_rate": 4.2095064323726485e-06,
+      "loss": 0.6237,
+      "step": 634
+    },
+    {
+      "epoch": 2.138047138047138,
+      "grad_norm": 0.2890625,
+      "learning_rate": 4.179306463542217e-06,
+      "loss": 0.5765,
+      "step": 635
+    },
+    {
+      "epoch": 2.1414141414141414,
+      "grad_norm": 0.310546875,
+      "learning_rate": 4.149186571594965e-06,
+      "loss": 0.6166,
+      "step": 636
+    },
+    {
+      "epoch": 2.144781144781145,
+      "grad_norm": 0.3125,
+      "learning_rate": 4.119147170898535e-06,
+      "loss": 0.6053,
+      "step": 637
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.3203125,
+      "learning_rate": 4.0891886747132356e-06,
+      "loss": 0.5521,
+      "step": 638
+    },
+    {
+      "epoch": 2.1515151515151514,
+      "grad_norm": 0.326171875,
+      "learning_rate": 4.059311495186338e-06,
+      "loss": 0.5838,
+      "step": 639
+    },
+    {
+      "epoch": 2.154882154882155,
+      "grad_norm": 0.3359375,
+      "learning_rate": 4.029516043346432e-06,
+      "loss": 0.5826,
+      "step": 640
+    },
+    {
+      "epoch": 2.1582491582491583,
+      "grad_norm": 0.3359375,
+      "learning_rate": 3.999802729097743e-06,
+      "loss": 0.6051,
+      "step": 641
+    },
+    {
+      "epoch": 2.1616161616161618,
+      "grad_norm": 0.29296875,
+      "learning_rate": 3.970171961214515e-06,
+      "loss": 0.6114,
+      "step": 642
+    },
+    {
+      "epoch": 2.164983164983165,
+      "grad_norm": 0.3046875,
+      "learning_rate": 3.940624147335386e-06,
+      "loss": 0.5684,
+      "step": 643
+    },
+    {
+      "epoch": 2.1683501683501682,
+      "grad_norm": 0.31640625,
+      "learning_rate": 3.911159693957755e-06,
+      "loss": 0.5988,
+      "step": 644
+    },
+    {
+      "epoch": 2.1717171717171717,
+      "grad_norm": 0.333984375,
+      "learning_rate": 3.881779006432223e-06,
+      "loss": 0.6126,
+      "step": 645
+    },
+    {
+      "epoch": 2.175084175084175,
+      "grad_norm": 0.37890625,
+      "learning_rate": 3.852482488956992e-06,
+      "loss": 0.5989,
+      "step": 646
+    },
+    {
+      "epoch": 2.175084175084175,
+      "eval_loss": 0.604517936706543,
+      "eval_runtime": 8.7887,
+      "eval_samples_per_second": 56.891,
+      "eval_steps_per_second": 3.641,
+      "step": 646
+    },
+    {
+      "epoch": 2.1784511784511786,
+      "grad_norm": 0.306640625,
+      "learning_rate": 3.823270544572319e-06,
+      "loss": 0.6301,
+      "step": 647
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.296875,
+      "learning_rate": 3.794143575154964e-06,
+      "loss": 0.6072,
+      "step": 648
+    },
+    {
+      "epoch": 2.185185185185185,
+      "grad_norm": 0.3046875,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.5916,
+      "step": 649
+    },
+    {
+      "epoch": 2.1885521885521886,
+      "grad_norm": 0.310546875,
+      "learning_rate": 3.7361461628786167e-06,
+      "loss": 0.5692,
+      "step": 650
+    },
+    {
+      "epoch": 2.191919191919192,
+      "grad_norm": 0.310546875,
+      "learning_rate": 3.707276517905989e-06,
+      "loss": 0.6172,
+      "step": 651
+    },
+    {
+      "epoch": 2.1952861952861955,
+      "grad_norm": 0.302734375,
+      "learning_rate": 3.67849344366243e-06,
+      "loss": 0.6081,
+      "step": 652
+    },
+    {
+      "epoch": 2.1986531986531985,
+      "grad_norm": 0.333984375,
+      "learning_rate": 3.6497973361246153e-06,
+      "loss": 0.588,
+      "step": 653
+    },
+    {
+      "epoch": 2.202020202020202,
+      "grad_norm": 0.330078125,
+      "learning_rate": 3.6211885900728017e-06,
+      "loss": 0.5907,
+      "step": 654
+    },
+    {
+      "epoch": 2.2053872053872055,
+      "grad_norm": 0.369140625,
+      "learning_rate": 3.5926675990853752e-06,
+      "loss": 0.6231,
+      "step": 655
+    },
+    {
+      "epoch": 2.208754208754209,
+      "grad_norm": 0.34765625,
+      "learning_rate": 3.5642347555334665e-06,
+      "loss": 0.6244,
+      "step": 656
+    },
+    {
+      "epoch": 2.212121212121212,
+      "grad_norm": 0.470703125,
+      "learning_rate": 3.5358904505755243e-06,
+      "loss": 0.6093,
+      "step": 657
+    },
+    {
+      "epoch": 2.2154882154882154,
+      "grad_norm": 0.30859375,
+      "learning_rate": 3.5076350741519595e-06,
+      "loss": 0.5834,
+      "step": 658
+    },
+    {
+      "epoch": 2.218855218855219,
+      "grad_norm": 0.326171875,
+      "learning_rate": 3.479469014979754e-06,
+      "loss": 0.5908,
+      "step": 659
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.322265625,
+      "learning_rate": 3.4513926605471504e-06,
+      "loss": 0.5853,
+      "step": 660
+    },
+    {
+      "epoch": 2.225589225589226,
+      "grad_norm": 0.349609375,
+      "learning_rate": 3.423406397108273e-06,
+      "loss": 0.5996,
+      "step": 661
+    },
+    {
+      "epoch": 2.228956228956229,
+      "grad_norm": 0.291015625,
+      "learning_rate": 3.395510609677861e-06,
+      "loss": 0.5806,
+      "step": 662
+    },
+    {
+      "epoch": 2.2323232323232323,
+      "grad_norm": 0.349609375,
+      "learning_rate": 3.3677056820259324e-06,
+      "loss": 0.6239,
+      "step": 663
+    },
+    {
+      "epoch": 2.2356902356902357,
+      "grad_norm": 0.298828125,
+      "learning_rate": 3.3399919966725335e-06,
+      "loss": 0.5602,
+      "step": 664
+    },
+    {
+      "epoch": 2.239057239057239,
+      "grad_norm": 0.31640625,
+      "learning_rate": 3.3123699348824654e-06,
+      "loss": 0.5797,
+      "step": 665
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 0.3125,
+      "learning_rate": 3.2848398766600298e-06,
+      "loss": 0.6125,
+      "step": 666
+    },
+    {
+      "epoch": 2.2457912457912457,
+      "grad_norm": 0.28515625,
+      "learning_rate": 3.257402200743821e-06,
+      "loss": 0.571,
+      "step": 667
+    },
+    {
+      "epoch": 2.249158249158249,
+      "grad_norm": 0.333984375,
+      "learning_rate": 3.2300572846014945e-06,
+      "loss": 0.5868,
+      "step": 668
+    },
+    {
+      "epoch": 2.2525252525252526,
+      "grad_norm": 0.3046875,
+      "learning_rate": 3.202805504424592e-06,
+      "loss": 0.5564,
+      "step": 669
+    },
+    {
+      "epoch": 2.255892255892256,
+      "grad_norm": 0.2890625,
+      "learning_rate": 3.175647235123347e-06,
+      "loss": 0.5532,
+      "step": 670
+    },
+    {
+      "epoch": 2.259259259259259,
+      "grad_norm": 0.28515625,
+      "learning_rate": 3.1485828503215588e-06,
+      "loss": 0.6087,
+      "step": 671
+    },
+    {
+      "epoch": 2.2626262626262625,
+      "grad_norm": 0.33984375,
+      "learning_rate": 3.1216127223514116e-06,
+      "loss": 0.6141,
+      "step": 672
+    },
+    {
+      "epoch": 2.265993265993266,
+      "grad_norm": 0.28125,
+      "learning_rate": 3.0947372222483762e-06,
+      "loss": 0.5687,
+      "step": 673
+    },
+    {
+      "epoch": 2.2693602693602695,
+      "grad_norm": 0.30078125,
+      "learning_rate": 3.0679567197461135e-06,
+      "loss": 0.6028,
+      "step": 674
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.310546875,
+      "learning_rate": 3.0412715832713592e-06,
+      "loss": 0.5933,
+      "step": 675
+    },
+    {
+      "epoch": 2.276094276094276,
+      "grad_norm": 0.3203125,
+      "learning_rate": 3.014682179938886e-06,
+      "loss": 0.5872,
+      "step": 676
+    },
+    {
+      "epoch": 2.2794612794612794,
+      "grad_norm": 0.32421875,
+      "learning_rate": 2.9881888755464337e-06,
+      "loss": 0.6124,
+      "step": 677
+    },
+    {
+      "epoch": 2.282828282828283,
+      "grad_norm": 0.291015625,
+      "learning_rate": 2.961792034569686e-06,
+      "loss": 0.5899,
+      "step": 678
+    },
+    {
+      "epoch": 2.2861952861952863,
+      "grad_norm": 0.35546875,
+      "learning_rate": 2.9354920201572457e-06,
+      "loss": 0.5982,
+      "step": 679
+    },
+    {
+      "epoch": 2.28956228956229,
+      "grad_norm": 0.28515625,
+      "learning_rate": 2.909289194125655e-06,
+      "loss": 0.6073,
+      "step": 680
+    },
+    {
+      "epoch": 2.292929292929293,
+      "grad_norm": 0.302734375,
+      "learning_rate": 2.8831839169543998e-06,
+      "loss": 0.582,
+      "step": 681
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "grad_norm": 0.349609375,
+      "learning_rate": 2.8571765477809645e-06,
+      "loss": 0.6274,
+      "step": 682
+    },
+    {
+      "epoch": 2.2996632996632997,
+      "grad_norm": 0.373046875,
+      "learning_rate": 2.83126744439589e-06,
+      "loss": 0.5879,
+      "step": 683
+    },
+    {
+      "epoch": 2.303030303030303,
+      "grad_norm": 0.298828125,
+      "learning_rate": 2.8054569632378358e-06,
+      "loss": 0.5782,
+      "step": 684
+    },
+    {
+      "epoch": 2.303030303030303,
+      "eval_loss": 0.6042293906211853,
+      "eval_runtime": 8.7252,
+      "eval_samples_per_second": 57.305,
+      "eval_steps_per_second": 3.668,
+      "step": 684
+    },
+    {
+      "epoch": 2.3063973063973062,
+      "grad_norm": 0.3125,
+      "learning_rate": 2.779745459388705e-06,
+      "loss": 0.5804,
+      "step": 685
+    },
+    {
+      "epoch": 2.3097643097643097,
+      "grad_norm": 0.337890625,
+      "learning_rate": 2.7541332865687245e-06,
+      "loss": 0.5851,
+      "step": 686
+    },
+    {
+      "epoch": 2.313131313131313,
+      "grad_norm": 0.306640625,
+      "learning_rate": 2.7286207971316094e-06,
+      "loss": 0.6423,
+      "step": 687
+    },
+    {
+      "epoch": 2.3164983164983166,
+      "grad_norm": 0.3125,
+      "learning_rate": 2.7032083420597e-06,
+      "loss": 0.6143,
+      "step": 688
+    },
+    {
+      "epoch": 2.31986531986532,
+      "grad_norm": 0.330078125,
+      "learning_rate": 2.6778962709591382e-06,
+      "loss": 0.606,
+      "step": 689
+    },
+    {
+      "epoch": 2.323232323232323,
+      "grad_norm": 0.333984375,
+      "learning_rate": 2.6526849320550474e-06,
+      "loss": 0.5796,
+      "step": 690
+    },
+    {
+      "epoch": 2.3265993265993266,
+      "grad_norm": 0.294921875,
+      "learning_rate": 2.6275746721867624e-06,
+      "loss": 0.5879,
+      "step": 691
+    },
+    {
+      "epoch": 2.32996632996633,
+      "grad_norm": 0.314453125,
+      "learning_rate": 2.602565836803036e-06,
+      "loss": 0.6047,
+      "step": 692
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.2734375,
+      "learning_rate": 2.5776587699573007e-06,
+      "loss": 0.5929,
+      "step": 693
+    },
+    {
+      "epoch": 2.3367003367003365,
+      "grad_norm": 0.302734375,
+      "learning_rate": 2.552853814302936e-06,
+      "loss": 0.5845,
+      "step": 694
+    },
+    {
+      "epoch": 2.34006734006734,
+      "grad_norm": 0.318359375,
+      "learning_rate": 2.528151311088537e-06,
+      "loss": 0.5853,
+      "step": 695
+    },
+    {
+      "epoch": 2.3434343434343434,
+      "grad_norm": 0.287109375,
+      "learning_rate": 2.5035516001532467e-06,
+      "loss": 0.5636,
+      "step": 696
+    },
+    {
+      "epoch": 2.346801346801347,
+      "grad_norm": 0.353515625,
+      "learning_rate": 2.4790550199220543e-06,
+      "loss": 0.593,
+      "step": 697
+    },
+    {
+      "epoch": 2.3501683501683504,
+      "grad_norm": 0.287109375,
+      "learning_rate": 2.4546619074011603e-06,
+      "loss": 0.5772,
+      "step": 698
+    },
+    {
+      "epoch": 2.3535353535353534,
+      "grad_norm": 0.28515625,
+      "learning_rate": 2.430372598173326e-06,
+      "loss": 0.5692,
+      "step": 699
+    },
+    {
+      "epoch": 2.356902356902357,
+      "grad_norm": 0.287109375,
+      "learning_rate": 2.406187426393269e-06,
+      "loss": 0.6052,
+      "step": 700
+    },
+    {
+      "epoch": 2.3602693602693603,
+      "grad_norm": 0.3125,
+      "learning_rate": 2.3821067247830488e-06,
+      "loss": 0.5643,
+      "step": 701
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.333984375,
+      "learning_rate": 2.3581308246275103e-06,
+      "loss": 0.5818,
+      "step": 702
+    },
+    {
+      "epoch": 2.3670033670033668,
+      "grad_norm": 0.328125,
+      "learning_rate": 2.334260055769707e-06,
+      "loss": 0.5806,
+      "step": 703
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.28125,
+      "learning_rate": 2.3104947466063785e-06,
+      "loss": 0.5504,
+      "step": 704
+    },
+    {
+      "epoch": 2.3737373737373737,
+      "grad_norm": 0.30078125,
+      "learning_rate": 2.2868352240834304e-06,
+      "loss": 0.6171,
+      "step": 705
+    },
+    {
+      "epoch": 2.377104377104377,
+      "grad_norm": 0.302734375,
+      "learning_rate": 2.263281813691417e-06,
+      "loss": 0.6136,
+      "step": 706
+    },
+    {
+      "epoch": 2.3804713804713806,
+      "grad_norm": 0.271484375,
+      "learning_rate": 2.2398348394610947e-06,
+      "loss": 0.5861,
+      "step": 707
+    },
+    {
+      "epoch": 2.3838383838383836,
+      "grad_norm": 0.33984375,
+      "learning_rate": 2.216494623958939e-06,
+      "loss": 0.5969,
+      "step": 708
+    },
+    {
+      "epoch": 2.387205387205387,
+      "grad_norm": 0.33203125,
+      "learning_rate": 2.1932614882827196e-06,
+      "loss": 0.592,
+      "step": 709
+    },
+    {
+      "epoch": 2.3905723905723906,
+      "grad_norm": 0.337890625,
+      "learning_rate": 2.1701357520570797e-06,
+      "loss": 0.6234,
+      "step": 710
+    },
+    {
+      "epoch": 2.393939393939394,
+      "grad_norm": 0.32421875,
+      "learning_rate": 2.1471177334291404e-06,
+      "loss": 0.5792,
+      "step": 711
+    },
+    {
+      "epoch": 2.3973063973063975,
+      "grad_norm": 0.322265625,
+      "learning_rate": 2.1242077490641157e-06,
+      "loss": 0.5827,
+      "step": 712
+    },
+    {
+      "epoch": 2.4006734006734005,
+      "grad_norm": 0.310546875,
+      "learning_rate": 2.1014061141409715e-06,
+      "loss": 0.571,
+      "step": 713
+    },
+    {
+      "epoch": 2.404040404040404,
+      "grad_norm": 0.34375,
+      "learning_rate": 2.0787131423480722e-06,
+      "loss": 0.5599,
+      "step": 714
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 0.279296875,
+      "learning_rate": 2.0561291458788736e-06,
+      "loss": 0.5955,
+      "step": 715
+    },
+    {
+      "epoch": 2.410774410774411,
+      "grad_norm": 0.30078125,
+      "learning_rate": 2.03365443542764e-06,
+      "loss": 0.6008,
+      "step": 716
+    },
+    {
+      "epoch": 2.4141414141414144,
+      "grad_norm": 0.28515625,
+      "learning_rate": 2.0112893201851435e-06,
+      "loss": 0.5611,
+      "step": 717
+    },
+    {
+      "epoch": 2.4175084175084174,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.9890341078344343e-06,
+      "loss": 0.631,
+      "step": 718
+    },
+    {
+      "epoch": 2.420875420875421,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.966889104546591e-06,
+      "loss": 0.5714,
+      "step": 719
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 0.294921875,
+      "learning_rate": 1.944854614976521e-06,
+      "loss": 0.559,
+      "step": 720
+    },
+    {
+      "epoch": 2.4276094276094278,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.922930942258766e-06,
+      "loss": 0.6012,
+      "step": 721
+    },
+    {
+      "epoch": 2.430976430976431,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.9011183880033203e-06,
+      "loss": 0.5568,
+      "step": 722
+    },
+    {
+      "epoch": 2.430976430976431,
+      "eval_loss": 0.6043210029602051,
+      "eval_runtime": 8.7174,
+      "eval_samples_per_second": 57.357,
+      "eval_steps_per_second": 3.671,
+      "step": 722
+    },
+    {
+      "epoch": 2.4343434343434343,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.8794172522915022e-06,
+      "loss": 0.6018,
+      "step": 723
+    },
+    {
+      "epoch": 2.4377104377104377,
+      "grad_norm": 0.322265625,
+      "learning_rate": 1.8578278336718037e-06,
+      "loss": 0.6034,
+      "step": 724
+    },
+    {
+      "epoch": 2.441077441077441,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.8363504291558053e-06,
+      "loss": 0.5755,
+      "step": 725
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.8149853342140644e-06,
+      "loss": 0.6105,
+      "step": 726
+    },
+    {
+      "epoch": 2.4478114478114477,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.7937328427720834e-06,
+      "loss": 0.6132,
+      "step": 727
+    },
+    {
+      "epoch": 2.451178451178451,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.7725932472062302e-06,
+      "loss": 0.6335,
+      "step": 728
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.7515668383397433e-06,
+      "loss": 0.6079,
+      "step": 729
+    },
+    {
+      "epoch": 2.457912457912458,
+      "grad_norm": 0.306640625,
+      "learning_rate": 1.730653905438714e-06,
+      "loss": 0.5714,
+      "step": 730
+    },
+    {
+      "epoch": 2.461279461279461,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.7098547362081197e-06,
+      "loss": 0.6027,
+      "step": 731
+    },
+    {
+      "epoch": 2.4646464646464645,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.6891696167878535e-06,
+      "loss": 0.6109,
+      "step": 732
+    },
+    {
+      "epoch": 2.468013468013468,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.6685988317487988e-06,
+      "loss": 0.5402,
+      "step": 733
+    },
+    {
+      "epoch": 2.4713804713804715,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.6481426640889098e-06,
+      "loss": 0.5738,
+      "step": 734
+    },
+    {
+      "epoch": 2.474747474747475,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.6278013952293115e-06,
+      "loss": 0.5929,
+      "step": 735
+    },
+    {
+      "epoch": 2.478114478114478,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.6075753050104426e-06,
+      "loss": 0.5775,
+      "step": 736
+    },
+    {
+      "epoch": 2.4814814814814814,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.587464671688187e-06,
+      "loss": 0.6116,
+      "step": 737
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.5674697719300735e-06,
+      "loss": 0.593,
+      "step": 738
+    },
+    {
+      "epoch": 2.4882154882154883,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.5475908808114325e-06,
+      "loss": 0.588,
+      "step": 739
+    },
+    {
+      "epoch": 2.4915824915824913,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.5278282718116477e-06,
+      "loss": 0.605,
+      "step": 740
+    },
+    {
+      "epoch": 2.494949494949495,
+      "grad_norm": 0.322265625,
+      "learning_rate": 1.5081822168103654e-06,
+      "loss": 0.5986,
+      "step": 741
+    },
+    {
+      "epoch": 2.4983164983164983,
+      "grad_norm": 0.28125,
+      "learning_rate": 1.4886529860837772e-06,
+      "loss": 0.5697,
+      "step": 742
+    },
+    {
+      "epoch": 2.5016835016835017,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.4692408483008803e-06,
+      "loss": 0.6327,
+      "step": 743
+    },
+    {
+      "epoch": 2.505050505050505,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.4499460705198e-06,
+      "loss": 0.6197,
+      "step": 744
+    },
+    {
+      "epoch": 2.5084175084175087,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.4307689181841077e-06,
+      "loss": 0.5948,
+      "step": 745
+    },
+    {
+      "epoch": 2.5117845117845117,
+      "grad_norm": 0.306640625,
+      "learning_rate": 1.4117096551191633e-06,
+      "loss": 0.5429,
+      "step": 746
+    },
+    {
+      "epoch": 2.515151515151515,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.3927685435284977e-06,
+      "loss": 0.6162,
+      "step": 747
+    },
+    {
+      "epoch": 2.5185185185185186,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.373945843990192e-06,
+      "loss": 0.5994,
+      "step": 748
+    },
+    {
+      "epoch": 2.5218855218855216,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.355241815453312e-06,
+      "loss": 0.6246,
+      "step": 749
+    },
+    {
+      "epoch": 2.525252525252525,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.33665671523432e-06,
+      "loss": 0.6174,
+      "step": 750
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 891,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 75,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.36437672443904e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}