diff --git "a/checkpoint-6400/trainer_state.json" "b/checkpoint-6400/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-6400/trainer_state.json"
@@ -0,0 +1,4501 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 6400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 9.6875,
+      "learning_rate": 2.0833333333333333e-07,
+      "loss": 1.5494,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.375,
+      "learning_rate": 4.1666666666666667e-07,
+      "loss": 1.6442,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.78125,
+      "learning_rate": 6.25e-07,
+      "loss": 1.5817,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.6262,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.9921875,
+      "learning_rate": 1.0416666666666667e-06,
+      "loss": 1.6365,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.77734375,
+      "learning_rate": 1.25e-06,
+      "loss": 1.5901,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.62109375,
+      "learning_rate": 1.4583333333333335e-06,
+      "loss": 1.5757,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.5234375,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.5956,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 6.75,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.561,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.59375,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 1.5564,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.546875,
+      "learning_rate": 2.2916666666666666e-06,
+      "loss": 1.6172,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.1640625,
+      "learning_rate": 2.5e-06,
+      "loss": 1.6872,
+      "step": 120
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.4765625,
+      "learning_rate": 2.7083333333333334e-06,
+      "loss": 1.577,
+      "step": 130
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.15625,
+      "learning_rate": 2.916666666666667e-06,
+      "loss": 1.56,
+      "step": 140
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.462890625,
+      "learning_rate": 3.125e-06,
+      "loss": 1.552,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.416015625,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.5752,
+      "step": 160
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.41796875,
+      "learning_rate": 3.5416666666666673e-06,
+      "loss": 1.6739,
+      "step": 170
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 13.25,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.5538,
+      "step": 180
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.8984375,
+      "learning_rate": 3.958333333333333e-06,
+      "loss": 1.6864,
+      "step": 190
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 11.1875,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 1.5576,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.546875,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 1.5328,
+      "step": 210
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.357421875,
+      "learning_rate": 4.583333333333333e-06,
+      "loss": 1.4953,
+      "step": 220
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.578125,
+      "learning_rate": 4.791666666666668e-06,
+      "loss": 1.5663,
+      "step": 230
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.2265625,
+      "learning_rate": 5e-06,
+      "loss": 1.5063,
+      "step": 240
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.439453125,
+      "learning_rate": 5.208333333333334e-06,
+      "loss": 1.4404,
+      "step": 250
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.443359375,
+      "learning_rate": 5.416666666666667e-06,
+      "loss": 1.5304,
+      "step": 260
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.44921875,
+      "learning_rate": 5.625e-06,
+      "loss": 1.5536,
+      "step": 270
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.4140625,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 1.5385,
+      "step": 280
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4609375,
+      "learning_rate": 6.041666666666667e-06,
+      "loss": 1.513,
+      "step": 290
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.50390625,
+      "learning_rate": 6.25e-06,
+      "loss": 1.4549,
+      "step": 300
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.6328125,
+      "learning_rate": 6.458333333333334e-06,
+      "loss": 1.4931,
+      "step": 310
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.48046875,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.4201,
+      "step": 320
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.392578125,
+      "learning_rate": 6.875e-06,
+      "loss": 1.5471,
+      "step": 330
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.95703125,
+      "learning_rate": 7.083333333333335e-06,
+      "loss": 1.4287,
+      "step": 340
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.388671875,
+      "learning_rate": 7.291666666666667e-06,
+      "loss": 1.4475,
+      "step": 350
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.33984375,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.477,
+      "step": 360
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.296875,
+      "learning_rate": 7.708333333333334e-06,
+      "loss": 1.4533,
+      "step": 370
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.400390625,
+      "learning_rate": 7.916666666666667e-06,
+      "loss": 1.3663,
+      "step": 380
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.375,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 1.3953,
+      "step": 390
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.471,
+      "step": 400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.392578125,
+      "learning_rate": 8.541666666666666e-06,
+      "loss": 1.4374,
+      "step": 410
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.046875,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.4224,
+      "step": 420
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.5546875,
+      "learning_rate": 8.958333333333334e-06,
+      "loss": 1.3261,
+      "step": 430
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.2578125,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 1.4033,
+      "step": 440
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 1.4237,
+      "step": 450
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.435546875,
+      "learning_rate": 9.583333333333335e-06,
+      "loss": 1.4083,
+      "step": 460
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 9.791666666666666e-06,
+      "loss": 1.3245,
+      "step": 470
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1e-05,
+      "loss": 1.3771,
+      "step": 480
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.5546875,
+      "learning_rate": 1.0208333333333334e-05,
+      "loss": 1.3789,
+      "step": 490
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7578125,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 1.4275,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.0625e-05,
+      "loss": 1.3739,
+      "step": 510
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.0833333333333334e-05,
+      "loss": 1.3758,
+      "step": 520
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.1041666666666668e-05,
+      "loss": 1.412,
+      "step": 530
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.279296875,
+      "learning_rate": 1.125e-05,
+      "loss": 1.4025,
+      "step": 540
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.1458333333333333e-05,
+      "loss": 1.4138,
+      "step": 550
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.259765625,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 1.2598,
+      "step": 560
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.625,
+      "learning_rate": 1.1875e-05,
+      "loss": 1.3543,
+      "step": 570
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.2083333333333333e-05,
+      "loss": 1.273,
+      "step": 580
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.2291666666666668e-05,
+      "loss": 1.2361,
+      "step": 590
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.384765625,
+      "learning_rate": 1.25e-05,
+      "loss": 1.2996,
+      "step": 600
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.2708333333333333e-05,
+      "loss": 1.235,
+      "step": 610
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.2109375,
+      "learning_rate": 1.2916666666666668e-05,
+      "loss": 1.3838,
+      "step": 620
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9765625,
+      "learning_rate": 1.3125e-05,
+      "loss": 1.2292,
+      "step": 630
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8125,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.2698,
+      "step": 640
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.3541666666666668e-05,
+      "loss": 1.3358,
+      "step": 650
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.375e-05,
+      "loss": 1.237,
+      "step": 660
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.3958333333333333e-05,
+      "loss": 1.2976,
+      "step": 670
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.466796875,
+      "learning_rate": 1.416666666666667e-05,
+      "loss": 1.2324,
+      "step": 680
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.4375e-05,
+      "loss": 1.2436,
+      "step": 690
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.125,
+      "learning_rate": 1.4583333333333333e-05,
+      "loss": 1.2607,
+      "step": 700
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.25,
+      "learning_rate": 1.479166666666667e-05,
+      "loss": 1.2724,
+      "step": 710
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.439453125,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.2314,
+      "step": 720
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.375,
+      "learning_rate": 1.5208333333333333e-05,
+      "loss": 1.2632,
+      "step": 730
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.7890625,
+      "learning_rate": 1.5416666666666668e-05,
+      "loss": 1.3291,
+      "step": 740
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.89453125,
+      "learning_rate": 1.5625e-05,
+      "loss": 1.2816,
+      "step": 750
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 1.2163,
+      "step": 760
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.604166666666667e-05,
+      "loss": 1.2693,
+      "step": 770
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.41015625,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 1.2114,
+      "step": 780
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.77734375,
+      "learning_rate": 1.6458333333333335e-05,
+      "loss": 1.1689,
+      "step": 790
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.2469,
+      "step": 800
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.6875e-05,
+      "loss": 1.2159,
+      "step": 810
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.7083333333333333e-05,
+      "loss": 1.2198,
+      "step": 820
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 1.729166666666667e-05,
+      "loss": 1.2687,
+      "step": 830
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.109375,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.2719,
+      "step": 840
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 1.7708333333333335e-05,
+      "loss": 1.2074,
+      "step": 850
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2578125,
+      "learning_rate": 1.7916666666666667e-05,
+      "loss": 1.1637,
+      "step": 860
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.8125e-05,
+      "loss": 1.1775,
+      "step": 870
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.09375,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 1.1949,
+      "step": 880
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.294921875,
+      "learning_rate": 1.854166666666667e-05,
+      "loss": 1.1488,
+      "step": 890
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 1.2244,
+      "step": 900
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.8958333333333334e-05,
+      "loss": 1.1557,
+      "step": 910
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.916666666666667e-05,
+      "loss": 1.1331,
+      "step": 920
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 1.9375e-05,
+      "loss": 1.235,
+      "step": 930
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.9583333333333333e-05,
+      "loss": 1.1916,
+      "step": 940
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.244140625,
+      "learning_rate": 1.979166666666667e-05,
+      "loss": 1.1931,
+      "step": 950
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.455078125,
+      "learning_rate": 2e-05,
+      "loss": 1.1947,
+      "step": 960
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.27734375,
+      "learning_rate": 1.9999933893861945e-05,
+      "loss": 1.123,
+      "step": 970
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.609375,
+      "learning_rate": 1.9999735576321776e-05,
+      "loss": 1.2481,
+      "step": 980
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.203125,
+      "learning_rate": 1.99994050500015e-05,
+      "loss": 1.2567,
+      "step": 990
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.9998942319271076e-05,
+      "loss": 1.1169,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 1.9998347390248377e-05,
+      "loss": 1.1375,
+      "step": 1010
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.999762027079909e-05,
+      "loss": 1.2387,
+      "step": 1020
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2109375,
+      "learning_rate": 1.9996760970536635e-05,
+      "loss": 1.239,
+      "step": 1030
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.9995769500822007e-05,
+      "loss": 1.1548,
+      "step": 1040
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.9994645874763657e-05,
+      "loss": 1.1675,
+      "step": 1050
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.15234375,
+      "learning_rate": 1.9993390107217302e-05,
+      "loss": 1.1675,
+      "step": 1060
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.999200221478573e-05,
+      "loss": 1.1909,
+      "step": 1070
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.999048221581858e-05,
+      "loss": 1.1468,
+      "step": 1080
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.9988830130412106e-05,
+      "loss": 1.2334,
+      "step": 1090
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.62109375,
+      "learning_rate": 1.9987045980408907e-05,
+      "loss": 1.2107,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.24609375,
+      "learning_rate": 1.9985129789397633e-05,
+      "loss": 1.1329,
+      "step": 1110
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.9983081582712684e-05,
+      "loss": 1.2072,
+      "step": 1120
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.25390625,
+      "learning_rate": 1.9980901387433866e-05,
+      "loss": 1.1971,
+      "step": 1130
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.66796875,
+      "learning_rate": 1.9978589232386036e-05,
+      "loss": 1.2553,
+      "step": 1140
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.423828125,
+      "learning_rate": 1.9976145148138727e-05,
+      "loss": 1.1773,
+      "step": 1150
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.15234375,
+      "learning_rate": 1.9973569167005725e-05,
+      "loss": 1.2301,
+      "step": 1160
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.9970861323044667e-05,
+      "loss": 1.1788,
+      "step": 1170
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.1875,
+      "learning_rate": 1.9968021652056578e-05,
+      "loss": 1.2372,
+      "step": 1180
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 1.9965050191585388e-05,
+      "loss": 1.1555,
+      "step": 1190
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.166015625,
+      "learning_rate": 1.9961946980917457e-05,
+      "loss": 1.1395,
+      "step": 1200
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.995871206108104e-05,
+      "loss": 1.2342,
+      "step": 1210
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.995534547484574e-05,
+      "loss": 1.1636,
+      "step": 1220
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.26171875,
+      "learning_rate": 1.995184726672197e-05,
+      "loss": 1.0984,
+      "step": 1230
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.65234375,
+      "learning_rate": 1.9948217482960334e-05,
+      "loss": 1.186,
+      "step": 1240
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.6328125,
+      "learning_rate": 1.9944456171551024e-05,
+      "loss": 1.2151,
+      "step": 1250
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.25390625,
+      "learning_rate": 1.9940563382223196e-05,
+      "loss": 1.1904,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.462890625,
+      "learning_rate": 1.993653916644431e-05,
+      "loss": 1.1485,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.173828125,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 1.1406,
+      "step": 1280
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.40625,
+      "learning_rate": 1.9928096670090552e-05,
+      "loss": 1.1583,
+      "step": 1290
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 1.992367850113585e-05,
+      "loss": 1.1775,
+      "step": 1300
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.9919129128968938e-05,
+      "loss": 1.173,
+      "step": 1310
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 1.9914448613738107e-05,
+      "loss": 1.1648,
+      "step": 1320
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.58203125,
+      "learning_rate": 1.9909637017325508e-05,
+      "loss": 1.0632,
+      "step": 1330
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2470703125,
+      "learning_rate": 1.9904694403346362e-05,
+      "loss": 1.1756,
+      "step": 1340
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.16015625,
+      "learning_rate": 1.989962083714808e-05,
+      "loss": 1.154,
+      "step": 1350
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.9894416385809444e-05,
+      "loss": 1.1659,
+      "step": 1360
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 1.9889081118139694e-05,
+      "loss": 1.1852,
+      "step": 1370
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.2373046875,
+      "learning_rate": 1.988361510467761e-05,
+      "loss": 1.1686,
+      "step": 1380
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.267578125,
+      "learning_rate": 1.9878018417690602e-05,
+      "loss": 1.2461,
+      "step": 1390
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.09375,
+      "learning_rate": 1.9872291131173743e-05,
+      "loss": 1.1913,
+      "step": 1400
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.9866433320848793e-05,
+      "loss": 1.2264,
+      "step": 1410
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.953125,
+      "learning_rate": 1.9860445064163193e-05,
+      "loss": 1.151,
+      "step": 1420
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.1875,
+      "learning_rate": 1.985432644028905e-05,
+      "loss": 1.1306,
+      "step": 1430
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.265625,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 1.19,
+      "step": 1440
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.255859375,
+      "learning_rate": 1.9841698416280554e-05,
+      "loss": 1.0554,
+      "step": 1450
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.983518918310418e-05,
+      "loss": 1.1399,
+      "step": 1460
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.9828549916653013e-05,
+      "loss": 1.1098,
+      "step": 1470
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.982178070470631e-05,
+      "loss": 1.1319,
+      "step": 1480
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.52734375,
+      "learning_rate": 1.9814881636761355e-05,
+      "loss": 1.2344,
+      "step": 1490
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.578125,
+      "learning_rate": 1.9807852804032306e-05,
+      "loss": 1.1336,
+      "step": 1500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.16796875,
+      "learning_rate": 1.980069429944895e-05,
+      "loss": 1.1052,
+      "step": 1510
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.9793406217655516e-05,
+      "loss": 1.1314,
+      "step": 1520
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.169921875,
+      "learning_rate": 1.9785988655009386e-05,
+      "loss": 1.1783,
+      "step": 1530
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.490234375,
+      "learning_rate": 1.977844170957984e-05,
+      "loss": 1.1526,
+      "step": 1540
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.977076548114677e-05,
+      "loss": 1.1069,
+      "step": 1550
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.9762960071199334e-05,
+      "loss": 1.2254,
+      "step": 1560
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.640625,
+      "learning_rate": 1.975502558293464e-05,
+      "loss": 1.1648,
+      "step": 1570
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.279296875,
+      "learning_rate": 1.974696212125635e-05,
+      "loss": 1.1854,
+      "step": 1580
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.9738769792773338e-05,
+      "loss": 1.2473,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 1.1984,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.224609375,
+      "learning_rate": 1.972199897034604e-05,
+      "loss": 1.1372,
+      "step": 1610
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.5703125,
+      "learning_rate": 1.9713420698132614e-05,
+      "loss": 1.123,
+      "step": 1620
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.9704714002573255e-05,
+      "loss": 1.1167,
+      "step": 1630
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 1.9695878998781162e-05,
+      "loss": 1.1196,
+      "step": 1640
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 1.9686915803565934e-05,
+      "loss": 1.1106,
+      "step": 1650
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.9677824535432012e-05,
+      "loss": 1.1101,
+      "step": 1660
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 1.9668605314577124e-05,
+      "loss": 1.1876,
+      "step": 1670
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 1.1827,
+      "step": 1680
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.9649783503952196e-05,
+      "loss": 1.1399,
+      "step": 1690
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.5546875,
+      "learning_rate": 1.9640181163029597e-05,
+      "loss": 1.13,
+      "step": 1700
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 1.963045136707763e-05,
+      "loss": 1.1582,
+      "step": 1710
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 1.9620594244736133e-05,
+      "loss": 1.2255,
+      "step": 1720
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.9610609926328373e-05,
+      "loss": 1.1538,
+      "step": 1730
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 1.960049854385929e-05,
+      "loss": 1.1813,
+      "step": 1740
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.9590260231013774e-05,
+      "loss": 1.202,
+      "step": 1750
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.957989512315489e-05,
+      "loss": 1.1095,
+      "step": 1760
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.956940335732209e-05,
+      "loss": 1.1931,
+      "step": 1770
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.9558785072229395e-05,
+      "loss": 1.1645,
+      "step": 1780
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.181640625,
+      "learning_rate": 1.9548040408263575e-05,
+      "loss": 1.1852,
+      "step": 1790
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.369140625,
+      "learning_rate": 1.953716950748227e-05,
+      "loss": 1.0633,
+      "step": 1800
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 1.952617251361214e-05,
+      "loss": 1.1748,
+      "step": 1810
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 1.951504957204694e-05,
+      "loss": 1.075,
+      "step": 1820
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.16796875,
+      "learning_rate": 1.9503800829845613e-05,
+      "loss": 1.1498,
+      "step": 1830
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.68359375,
+      "learning_rate": 1.949242643573034e-05,
+      "loss": 1.1333,
+      "step": 1840
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.55078125,
+      "learning_rate": 1.9480926540084578e-05,
+      "loss": 1.1932,
+      "step": 1850
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9453125,
+      "learning_rate": 1.946930129495106e-05,
+      "loss": 1.2105,
+      "step": 1860
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 1.9457550854029797e-05,
+      "loss": 1.0915,
+      "step": 1870
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 1.944567537267605e-05,
+      "loss": 1.105,
+      "step": 1880
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.27734375,
+      "learning_rate": 1.9433675007898255e-05,
+      "loss": 1.1275,
+      "step": 1890
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 1.9421549918355965e-05,
+      "loss": 1.1369,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.9409300264357757e-05,
+      "loss": 1.134,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 1.0956,
+      "step": 1920
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.9384427912460172e-05,
+      "loss": 1.1498,
+      "step": 1930
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 1.9371805543403826e-05,
+      "loss": 1.1962,
+      "step": 1940
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.29296875,
+      "learning_rate": 1.935905926757326e-05,
+      "loss": 1.1103,
+      "step": 1950
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.1953125,
+      "learning_rate": 1.9346189253489888e-05,
+      "loss": 1.0858,
+      "step": 1960
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2734375,
+      "learning_rate": 1.9333195671311093e-05,
+      "loss": 1.1537,
+      "step": 1970
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 1.932007869282799e-05,
+      "loss": 1.1339,
+      "step": 1980
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.9306838491463126e-05,
+      "loss": 1.0732,
+      "step": 1990
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.9293475242268224e-05,
+      "loss": 1.1001,
+      "step": 2000
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.9279989121921846e-05,
+      "loss": 1.1295,
+      "step": 2010
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.9266380308727054e-05,
+      "loss": 1.1069,
+      "step": 2020
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.9252648982609065e-05,
+      "loss": 1.1003,
+      "step": 2030
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.255859375,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 1.098,
+      "step": 2040
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.66796875,
+      "learning_rate": 1.9224819519400825e-05,
+      "loss": 1.1447,
+      "step": 2050
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.91796875,
+      "learning_rate": 1.9210721750250237e-05,
+      "loss": 1.0511,
+      "step": 2060
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 1.9196502204050925e-05,
+      "loss": 1.1048,
+      "step": 2070
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.9182161068802742e-05,
+      "loss": 1.2156,
+      "step": 2080
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.16015625,
+      "learning_rate": 1.9167698534113105e-05,
+      "loss": 1.0455,
+      "step": 2090
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.20703125,
+      "learning_rate": 1.9153114791194475e-05,
+      "loss": 1.2662,
+      "step": 2100
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.212890625,
+      "learning_rate": 1.9138410032861833e-05,
+      "loss": 1.1073,
+      "step": 2110
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.20703125,
+      "learning_rate": 1.9123584453530145e-05,
+      "loss": 1.1808,
+      "step": 2120
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 1.910863824921176e-05,
+      "loss": 1.0918,
+      "step": 2130
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 1.9093571617513853e-05,
+      "loss": 1.1115,
+      "step": 2140
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.907838475763579e-05,
+      "loss": 1.1847,
+      "step": 2150
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.9063077870366504e-05,
+      "loss": 1.1355,
+      "step": 2160
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.18359375,
+      "learning_rate": 1.9047651158081827e-05,
+      "loss": 1.1227,
+      "step": 2170
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.9032104824741843e-05,
+      "loss": 1.156,
+      "step": 2180
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.205078125,
+      "learning_rate": 1.901643907588816e-05,
+      "loss": 1.1995,
+      "step": 2190
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.900065411864121e-05,
+      "loss": 1.1294,
+      "step": 2200
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 1.898475016169751e-05,
+      "loss": 1.1487,
+      "step": 2210
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.248046875,
+      "learning_rate": 1.8968727415326885e-05,
+      "loss": 1.1438,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 1.895258609136972e-05,
+      "loss": 1.1341,
+      "step": 2230
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.9765625,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 1.1479,
+      "step": 2240
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.169921875,
+      "learning_rate": 1.8919948565893144e-05,
+      "loss": 1.2063,
+      "step": 2250
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.1923828125,
+      "learning_rate": 1.8903452795881893e-05,
+      "loss": 1.1608,
+      "step": 2260
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 1.8886839311294695e-05,
+      "loss": 1.1145,
+      "step": 2270
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.887010833178222e-05,
+      "loss": 1.0683,
+      "step": 2280
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.19140625,
+      "learning_rate": 1.885326007854855e-05,
+      "loss": 1.1338,
+      "step": 2290
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.883629477434828e-05,
+      "loss": 1.1307,
+      "step": 2300
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.173828125,
+      "learning_rate": 1.881921264348355e-05,
+      "loss": 1.1751,
+      "step": 2310
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.1953125,
+      "learning_rate": 1.880201391180111e-05,
+      "loss": 1.1072,
+      "step": 2320
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.8784698806689308e-05,
+      "loss": 1.1771,
+      "step": 2330
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 1.876726755707508e-05,
+      "loss": 1.1182,
+      "step": 2340
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.8749720393420948e-05,
+      "loss": 1.2228,
+      "step": 2350
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.20703125,
+      "learning_rate": 1.8732057547721962e-05,
+      "loss": 1.1807,
+      "step": 2360
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.205078125,
+      "learning_rate": 1.8714279253502616e-05,
+      "loss": 1.0115,
+      "step": 2370
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.8696385745813793e-05,
+      "loss": 1.0663,
+      "step": 2380
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.8678377261229624e-05,
+      "loss": 1.1894,
+      "step": 2390
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.26171875,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 1.2207,
+      "step": 2400
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.8642016315269345e-05,
+      "loss": 1.092,
+      "step": 2410
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 1.8623664334629576e-05,
+      "loss": 1.1397,
+      "step": 2420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.860519833856079e-05,
+      "loss": 1.1003,
+      "step": 2430
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.267578125,
+      "learning_rate": 1.8586618571206133e-05,
+      "loss": 1.1145,
+      "step": 2440
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.5703125,
+      "learning_rate": 1.856792527821293e-05,
+      "loss": 1.1072,
+      "step": 2450
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.854911870672947e-05,
+      "loss": 1.2103,
+      "step": 2460
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.173828125,
+      "learning_rate": 1.8530199105401705e-05,
+      "loss": 1.2184,
+      "step": 2470
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 1.8511166724369997e-05,
+      "loss": 1.1892,
+      "step": 2480
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.28125,
+      "learning_rate": 1.849202181526579e-05,
+      "loss": 1.1147,
+      "step": 2490
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.177734375,
+      "learning_rate": 1.847276463120828e-05,
+      "loss": 1.1493,
+      "step": 2500
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 1.8453395426801083e-05,
+      "loss": 1.1848,
+      "step": 2510
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.843391445812886e-05,
+      "loss": 1.1074,
+      "step": 2520
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.24609375,
+      "learning_rate": 1.841432198275393e-05,
+      "loss": 1.1532,
+      "step": 2530
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.197265625,
+      "learning_rate": 1.8394618259712866e-05,
+      "loss": 1.1678,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.2138671875,
+      "learning_rate": 1.837480354951308e-05,
+      "loss": 1.1779,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 1.2235,
+      "step": 2560
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.18359375,
+      "learning_rate": 1.833484221700044e-05,
+      "loss": 1.128,
+      "step": 2570
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.8314696123025456e-05,
+      "loss": 1.0884,
+      "step": 2580
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 1.8294440098560508e-05,
+      "loss": 1.152,
+      "step": 2590
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.1962890625,
+      "learning_rate": 1.8274074411415104e-05,
+      "loss": 1.1352,
+      "step": 2600
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.8253599330848638e-05,
+      "loss": 1.129,
+      "step": 2610
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.8233015127566805e-05,
+      "loss": 1.1701,
+      "step": 2620
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.8212322073718042e-05,
+      "loss": 1.1856,
+      "step": 2630
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.255859375,
+      "learning_rate": 1.819152044288992e-05,
+      "loss": 1.1635,
+      "step": 2640
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.817061051010554e-05,
+      "loss": 1.1203,
+      "step": 2650
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.19140625,
+      "learning_rate": 1.8149592551819883e-05,
+      "loss": 1.1662,
+      "step": 2660
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.2353515625,
+      "learning_rate": 1.8128466845916156e-05,
+      "loss": 1.1825,
+      "step": 2670
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.8107233671702123e-05,
+      "loss": 1.1868,
+      "step": 2680
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.212890625,
+      "learning_rate": 1.808589330990642e-05,
+      "loss": 1.1071,
+      "step": 2690
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.806444604267483e-05,
+      "loss": 1.1734,
+      "step": 2700
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.8042892153566543e-05,
+      "loss": 1.213,
+      "step": 2710
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.802123192755044e-05,
+      "loss": 1.1722,
+      "step": 2720
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.220703125,
+      "learning_rate": 1.7999465651001297e-05,
+      "loss": 1.0755,
+      "step": 2730
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.7977593611696017e-05,
+      "loss": 1.1852,
+      "step": 2740
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.79556160988098e-05,
+      "loss": 1.1037,
+      "step": 2750
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.166015625,
+      "learning_rate": 1.7933533402912354e-05,
+      "loss": 1.2323,
+      "step": 2760
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 1.791134581596402e-05,
+      "loss": 1.1885,
+      "step": 2770
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.29296875,
+      "learning_rate": 1.7889053631311947e-05,
+      "loss": 1.1541,
+      "step": 2780
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.2373046875,
+      "learning_rate": 1.786665714368617e-05,
+      "loss": 1.1488,
+      "step": 2790
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.75,
+      "learning_rate": 1.784415664919576e-05,
+      "loss": 1.1424,
+      "step": 2800
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.03125,
+      "learning_rate": 1.782155244532487e-05,
+      "loss": 1.1235,
+      "step": 2810
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.388671875,
+      "learning_rate": 1.7798844830928818e-05,
+      "loss": 1.3127,
+      "step": 2820
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.7776034106230156e-05,
+      "loss": 1.1475,
+      "step": 2830
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.1650390625,
+      "learning_rate": 1.775312057281466e-05,
+      "loss": 1.1558,
+      "step": 2840
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.171875,
+      "learning_rate": 1.773010453362737e-05,
+      "loss": 1.0776,
+      "step": 2850
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.236328125,
+      "learning_rate": 1.770698629296858e-05,
+      "loss": 1.1442,
+      "step": 2860
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.498046875,
+      "learning_rate": 1.7683766156489817e-05,
+      "loss": 1.1917,
+      "step": 2870
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.2439,
+      "step": 2880
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 1.763702142541032e-05,
+      "loss": 1.129,
+      "step": 2890
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 1.761349744883231e-05,
+      "loss": 1.1861,
+      "step": 2900
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.758987281247162e-05,
+      "loss": 1.1001,
+      "step": 2910
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.17578125,
+      "learning_rate": 1.756614782867493e-05,
+      "loss": 1.2019,
+      "step": 2920
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 1.7542322811115657e-05,
+      "loss": 1.1267,
+      "step": 2930
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.158203125,
+      "learning_rate": 1.7518398074789776e-05,
+      "loss": 1.1625,
+      "step": 2940
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 1.7494373936011674e-05,
+      "loss": 1.1846,
+      "step": 2950
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.26171875,
+      "learning_rate": 1.7470250712409963e-05,
+      "loss": 1.0803,
+      "step": 2960
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 1.7446028722923266e-05,
+      "loss": 1.1674,
+      "step": 2970
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.240234375,
+      "learning_rate": 1.7421708287796017e-05,
+      "loss": 1.1976,
+      "step": 2980
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.23828125,
+      "learning_rate": 1.7397289728574234e-05,
+      "loss": 1.1307,
+      "step": 2990
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.737277336810124e-05,
+      "loss": 1.1122,
+      "step": 3000
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 1.7348159530513424e-05,
+      "loss": 1.1558,
+      "step": 3010
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 1.7323448541235922e-05,
+      "loss": 1.1335,
+      "step": 3020
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.2109375,
+      "learning_rate": 1.7298640726978357e-05,
+      "loss": 1.1388,
+      "step": 3030
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.2578125,
+      "learning_rate": 1.7273736415730488e-05,
+      "loss": 1.207,
+      "step": 3040
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.25,
+      "learning_rate": 1.7248735936757882e-05,
+      "loss": 1.113,
+      "step": 3050
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.7223639620597556e-05,
+      "loss": 1.1843,
+      "step": 3060
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.189453125,
+      "learning_rate": 1.719844779905363e-05,
+      "loss": 1.1279,
+      "step": 3070
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.18359375,
+      "learning_rate": 1.7173160805192895e-05,
+      "loss": 1.1639,
+      "step": 3080
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 1.7147778973340466e-05,
+      "loss": 1.1434,
+      "step": 3090
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 1.7122302639075313e-05,
+      "loss": 1.1951,
+      "step": 3100
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.7096732139225853e-05,
+      "loss": 1.1432,
+      "step": 3110
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.1327,
+      "step": 3120
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.7045309996308107e-05,
+      "loss": 1.1622,
+      "step": 3130
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 1.7019459033103684e-05,
+      "loss": 1.1804,
+      "step": 3140
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 1.699351526403367e-05,
+      "loss": 1.0703,
+      "step": 3150
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.6967479032106552e-05,
+      "loss": 1.1724,
+      "step": 3160
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.1953125,
+      "learning_rate": 1.694135068155327e-05,
+      "loss": 1.1547,
+      "step": 3170
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 1.6915130557822698e-05,
+      "loss": 1.1062,
+      "step": 3180
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.6888819007577054e-05,
+      "loss": 1.1308,
+      "step": 3190
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.546875,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 1.0832,
+      "step": 3200
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.6835923020228714e-05,
+      "loss": 1.1029,
+      "step": 3210
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.6809339282475905e-05,
+      "loss": 1.1039,
+      "step": 3220
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 1.678266551689856e-05,
+      "loss": 1.2061,
+      "step": 3230
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 1.6755902076156606e-05,
+      "loss": 1.2829,
+      "step": 3240
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.171875,
+      "learning_rate": 1.6729049314095578e-05,
+      "loss": 1.1065,
+      "step": 3250
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.2578125,
+      "learning_rate": 1.670210758574196e-05,
+      "loss": 1.1086,
+      "step": 3260
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1.6675077247298475e-05,
+      "loss": 1.0745,
+      "step": 3270
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.72265625,
+      "learning_rate": 1.6647958656139377e-05,
+      "loss": 1.1755,
+      "step": 3280
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 1.662075217080574e-05,
+      "loss": 1.2102,
+      "step": 3290
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 1.659345815100069e-05,
+      "loss": 1.1135,
+      "step": 3300
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.656607695758468e-05,
+      "loss": 1.1546,
+      "step": 3310
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.6538608952570698e-05,
+      "loss": 1.0797,
+      "step": 3320
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.125,
+      "learning_rate": 1.6511054499119493e-05,
+      "loss": 1.142,
+      "step": 3330
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.6483413961534764e-05,
+      "loss": 1.1214,
+      "step": 3340
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.21875,
+      "learning_rate": 1.6455687705258348e-05,
+      "loss": 1.1406,
+      "step": 3350
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.7734375,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 1.1028,
+      "step": 3360
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 1.6399979504059506e-05,
+      "loss": 1.1224,
+      "step": 3370
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.609375,
+      "learning_rate": 1.6371998295667885e-05,
+      "loss": 1.1554,
+      "step": 3380
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 1.6343932841636455e-05,
+      "loss": 1.1098,
+      "step": 3390
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 1.6315783513024977e-05,
+      "loss": 1.1195,
+      "step": 3400
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.173828125,
+      "learning_rate": 1.6287550682002126e-05,
+      "loss": 1.069,
+      "step": 3410
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.306640625,
+      "learning_rate": 1.6259234721840595e-05,
+      "loss": 1.241,
+      "step": 3420
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 1.6230836006912127e-05,
+      "loss": 1.0996,
+      "step": 3430
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 1.6202354912682602e-05,
+      "loss": 1.2133,
+      "step": 3440
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.169921875,
+      "learning_rate": 1.6173791815707053e-05,
+      "loss": 1.0838,
+      "step": 3450
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.6145147093624677e-05,
+      "loss": 1.1078,
+      "step": 3460
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 1.6116421125153876e-05,
+      "loss": 1.172,
+      "step": 3470
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.625,
+      "learning_rate": 1.608761429008721e-05,
+      "loss": 1.0926,
+      "step": 3480
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.60587269692864e-05,
+      "loss": 1.0849,
+      "step": 3490
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.21484375,
+      "learning_rate": 1.6029759544677298e-05,
+      "loss": 1.2657,
+      "step": 3500
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 1.6000712399244813e-05,
+      "loss": 1.1805,
+      "step": 3510
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.26953125,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 1.0808,
+      "step": 3520
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.173828125,
+      "learning_rate": 1.5942380483114305e-05,
+      "loss": 1.1493,
+      "step": 3530
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 1.5913096483635827e-05,
+      "loss": 1.1078,
+      "step": 3540
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.20703125,
+      "learning_rate": 1.5883734305762846e-05,
+      "loss": 1.0484,
+      "step": 3550
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.1796875,
+      "learning_rate": 1.5854294337699407e-05,
+      "loss": 1.1525,
+      "step": 3560
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.189453125,
+      "learning_rate": 1.5824776968678024e-05,
+      "loss": 1.0877,
+      "step": 3570
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 1.5795182588954553e-05,
+      "loss": 1.1422,
+      "step": 3580
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.576551158980302e-05,
+      "loss": 1.2228,
+      "step": 3590
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.573576436351046e-05,
+      "loss": 1.0375,
+      "step": 3600
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.570594130337173e-05,
+      "loss": 1.1789,
+      "step": 3610
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1.567604280368429e-05,
+      "loss": 1.1084,
+      "step": 3620
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 1.5646069259743007e-05,
+      "loss": 1.1219,
+      "step": 3630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.561602106783493e-05,
+      "loss": 1.2003,
+      "step": 3640
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 1.5585898625234047e-05,
+      "loss": 1.191,
+      "step": 3650
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 1.5555702330196024e-05,
+      "loss": 1.2076,
+      "step": 3660
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.267578125,
+      "learning_rate": 1.552543258195295e-05,
+      "loss": 1.0907,
+      "step": 3670
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.1875,
+      "learning_rate": 1.5495089780708062e-05,
+      "loss": 1.1739,
+      "step": 3680
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 1.2109375,
+      "learning_rate": 1.5464674327630437e-05,
+      "loss": 1.086,
+      "step": 3690
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.181640625,
+      "learning_rate": 1.54341866248497e-05,
+      "loss": 1.182,
+      "step": 3700
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.5403627075450717e-05,
+      "loss": 1.2353,
+      "step": 3710
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 1.5372996083468242e-05,
+      "loss": 1.0746,
+      "step": 3720
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.534229405388159e-05,
+      "loss": 1.1302,
+      "step": 3730
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.275390625,
+      "learning_rate": 1.5311521392609283e-05,
+      "loss": 1.1688,
+      "step": 3740
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.528067850650368e-05,
+      "loss": 1.1074,
+      "step": 3750
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.1953125,
+      "learning_rate": 1.5249765803345602e-05,
+      "loss": 1.1006,
+      "step": 3760
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.232421875,
+      "learning_rate": 1.5218783691838935e-05,
+      "loss": 1.1077,
+      "step": 3770
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.189453125,
+      "learning_rate": 1.5187732581605217e-05,
+      "loss": 1.0822,
+      "step": 3780
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.1953125,
+      "learning_rate": 1.515661288317825e-05,
+      "loss": 1.1424,
+      "step": 3790
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 1.5125425007998653e-05,
+      "loss": 1.1602,
+      "step": 3800
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.509416936840842e-05,
+      "loss": 1.0829,
+      "step": 3810
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.46484375,
+      "learning_rate": 1.5062846377645476e-05,
+      "loss": 1.1062,
+      "step": 3820
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.66796875,
+      "learning_rate": 1.5031456449838207e-05,
+      "loss": 1.1321,
+      "step": 3830
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.21484375,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.0985,
+      "step": 3840
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.185546875,
+      "learning_rate": 1.4968477444023739e-05,
+      "loss": 1.183,
+      "step": 3850
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.1796875,
+      "learning_rate": 1.4936889198676303e-05,
+      "loss": 1.1727,
+      "step": 3860
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 1.4905235681593079e-05,
+      "loss": 1.0394,
+      "step": 3870
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.4873517311272425e-05,
+      "loss": 1.1763,
+      "step": 3880
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.21875,
+      "learning_rate": 1.484173450707013e-05,
+      "loss": 1.143,
+      "step": 3890
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 1.4809887689193878e-05,
+      "loss": 1.1462,
+      "step": 3900
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.279296875,
+      "learning_rate": 1.4777977278697704e-05,
+      "loss": 1.2094,
+      "step": 3910
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.4746003697476406e-05,
+      "loss": 1.1694,
+      "step": 3920
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.1962890625,
+      "learning_rate": 1.4713967368259981e-05,
+      "loss": 1.1119,
+      "step": 3930
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.17578125,
+      "learning_rate": 1.4681868714608021e-05,
+      "loss": 1.1699,
+      "step": 3940
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.4649708160904142e-05,
+      "loss": 1.1966,
+      "step": 3950
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.158203125,
+      "learning_rate": 1.4617486132350343e-05,
+      "loss": 1.1101,
+      "step": 3960
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.458520305496139e-05,
+      "loss": 1.0989,
+      "step": 3970
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 1.4552859355559205e-05,
+      "loss": 1.1079,
+      "step": 3980
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.55859375,
+      "learning_rate": 1.45204554617672e-05,
+      "loss": 1.1722,
+      "step": 3990
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.1796875,
+      "learning_rate": 1.4487991802004625e-05,
+      "loss": 1.1155,
+      "step": 4000
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.177734375,
+      "learning_rate": 1.4455468805480918e-05,
+      "loss": 1.2127,
+      "step": 4010
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.23828125,
+      "learning_rate": 1.4422886902190014e-05,
+      "loss": 1.0877,
+      "step": 4020
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.2109375,
+      "learning_rate": 1.4390246522904681e-05,
+      "loss": 1.1662,
+      "step": 4030
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.4357548099170794e-05,
+      "loss": 1.0952,
+      "step": 4040
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.375,
+      "learning_rate": 1.4324792063301662e-05,
+      "loss": 1.18,
+      "step": 4050
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.4291978848372292e-05,
+      "loss": 1.1226,
+      "step": 4060
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 1.425910888821366e-05,
+      "loss": 1.1017,
+      "step": 4070
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.443359375,
+      "learning_rate": 1.4226182617406996e-05,
+      "loss": 1.1678,
+      "step": 4080
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.1923828125,
+      "learning_rate": 1.4193200471278019e-05,
+      "loss": 1.16,
+      "step": 4090
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.63671875,
+      "learning_rate": 1.4160162885891193e-05,
+      "loss": 1.1208,
+      "step": 4100
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 1.4127070298043949e-05,
+      "loss": 1.1794,
+      "step": 4110
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.4093923145260926e-05,
+      "loss": 1.0882,
+      "step": 4120
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 1.4060721865788178e-05,
+      "loss": 1.1112,
+      "step": 4130
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.24609375,
+      "learning_rate": 1.4027466898587375e-05,
+      "loss": 1.1513,
+      "step": 4140
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 1.3994158683330006e-05,
+      "loss": 1.1307,
+      "step": 4150
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 1.1097,
+      "step": 4160
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.189453125,
+      "learning_rate": 1.3927384270845744e-05,
+      "loss": 1.1136,
+      "step": 4170
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.267578125,
+      "learning_rate": 1.3893918956458554e-05,
+      "loss": 1.1208,
+      "step": 4180
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.224609375,
+      "learning_rate": 1.3860402159682535e-05,
+      "loss": 1.1909,
+      "step": 4190
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 1.1901,
+      "step": 4200
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.22265625,
+      "learning_rate": 1.3793215892171636e-05,
+      "loss": 1.227,
+      "step": 4210
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.15234375,
+      "learning_rate": 1.3759547309721681e-05,
+      "loss": 1.141,
+      "step": 4220
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.372582902144103e-05,
+      "loss": 1.2137,
+      "step": 4230
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.169921875,
+      "learning_rate": 1.3692061473126845e-05,
+      "loss": 1.0471,
+      "step": 4240
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 1.3658245111227571e-05,
+      "loss": 1.0859,
+      "step": 4250
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.3624380382837017e-05,
+      "loss": 1.135,
+      "step": 4260
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.375,
+      "learning_rate": 1.3590467735688475e-05,
+      "loss": 1.2119,
+      "step": 4270
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 1.3556507618148769e-05,
+      "loss": 1.0579,
+      "step": 4280
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 1.3522500479212337e-05,
+      "loss": 1.1343,
+      "step": 4290
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.185546875,
+      "learning_rate": 1.3488446768495309e-05,
+      "loss": 1.1671,
+      "step": 4300
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 1.3454346936229547e-05,
+      "loss": 1.1931,
+      "step": 4310
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.2265625,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 1.131,
+      "step": 4320
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 1.3386010711022206e-05,
+      "loss": 1.1752,
+      "step": 4330
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.197265625,
+      "learning_rate": 1.3351775221569416e-05,
+      "loss": 1.1737,
+      "step": 4340
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 1.3317495417533523e-05,
+      "loss": 1.0803,
+      "step": 4350
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.56640625,
+      "learning_rate": 1.3283171752135614e-05,
+      "loss": 1.1451,
+      "step": 4360
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.49609375,
+      "learning_rate": 1.3248804679176679e-05,
+      "loss": 1.0968,
+      "step": 4370
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.3214394653031616e-05,
+      "loss": 1.0748,
+      "step": 4380
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.205078125,
+      "learning_rate": 1.3179942128643216e-05,
+      "loss": 1.1289,
+      "step": 4390
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.16015625,
+      "learning_rate": 1.3145447561516138e-05,
+      "loss": 1.1095,
+      "step": 4400
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.5703125,
+      "learning_rate": 1.3110911407710909e-05,
+      "loss": 1.136,
+      "step": 4410
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.267578125,
+      "learning_rate": 1.3076334123837884e-05,
+      "loss": 1.1481,
+      "step": 4420
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.263671875,
+      "learning_rate": 1.3041716167051197e-05,
+      "loss": 1.1945,
+      "step": 4430
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 1.300705799504273e-05,
+      "loss": 1.1104,
+      "step": 4440
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.21484375,
+      "learning_rate": 1.2972360066036078e-05,
+      "loss": 1.1484,
+      "step": 4450
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 1.2937622838780444e-05,
+      "loss": 1.0896,
+      "step": 4460
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.453125,
+      "learning_rate": 1.2902846772544625e-05,
+      "loss": 1.0531,
+      "step": 4470
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 1.1475,
+      "step": 4480
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.2833179962768988e-05,
+      "loss": 1.1864,
+      "step": 4490
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 1.2798290140309924e-05,
+      "loss": 1.1529,
+      "step": 4500
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.2763363321019986e-05,
+      "loss": 1.1534,
+      "step": 4510
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.150390625,
+      "learning_rate": 1.2728399966674612e-05,
+      "loss": 1.089,
+      "step": 4520
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 1.2693400539532263e-05,
+      "loss": 1.128,
+      "step": 4530
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 1.2658365502328329e-05,
+      "loss": 1.0726,
+      "step": 4540
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.27734375,
+      "learning_rate": 1.2623295318269018e-05,
+      "loss": 1.2424,
+      "step": 4550
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.2373046875,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 1.2114,
+      "step": 4560
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 1.2553051364726347e-05,
+      "loss": 1.0968,
+      "step": 4570
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 2.921875,
+      "learning_rate": 1.2517878523954287e-05,
+      "loss": 1.1075,
+      "step": 4580
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.2482672393737164e-05,
+      "loss": 1.1654,
+      "step": 4590
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.15625,
+      "learning_rate": 1.2447433439543239e-05,
+      "loss": 1.0986,
+      "step": 4600
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.40234375,
+      "learning_rate": 1.2412162127274748e-05,
+      "loss": 1.1458,
+      "step": 4610
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.2376858923261732e-05,
+      "loss": 1.1728,
+      "step": 4620
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 1.2341524294255893e-05,
+      "loss": 1.1034,
+      "step": 4630
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.185546875,
+      "learning_rate": 1.2306158707424402e-05,
+      "loss": 1.1559,
+      "step": 4640
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.1865234375,
+      "learning_rate": 1.2270762630343734e-05,
+      "loss": 1.1225,
+      "step": 4650
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.1865234375,
+      "learning_rate": 1.2235336530993475e-05,
+      "loss": 1.1869,
+      "step": 4660
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 1.2199880877750157e-05,
+      "loss": 1.2204,
+      "step": 4670
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.2164396139381029e-05,
+      "loss": 1.0915,
+      "step": 4680
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.234375,
+      "learning_rate": 1.2128882785037905e-05,
+      "loss": 1.1554,
+      "step": 4690
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.1796875,
+      "learning_rate": 1.2093341284250922e-05,
+      "loss": 1.0801,
+      "step": 4700
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.6484375,
+      "learning_rate": 1.205777210692235e-05,
+      "loss": 1.1295,
+      "step": 4710
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.259765625,
+      "learning_rate": 1.2022175723320382e-05,
+      "loss": 1.0752,
+      "step": 4720
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.240234375,
+      "learning_rate": 1.19865526040729e-05,
+      "loss": 1.0692,
+      "step": 4730
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.1950903220161286e-05,
+      "loss": 1.0992,
+      "step": 4740
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.1915228042914144e-05,
+      "loss": 1.1283,
+      "step": 4750
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.185546875,
+      "learning_rate": 1.187952754400112e-05,
+      "loss": 1.1302,
+      "step": 4760
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 1.1843802195426634e-05,
+      "loss": 1.1006,
+      "step": 4770
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.50390625,
+      "learning_rate": 1.1808052469523654e-05,
+      "loss": 1.088,
+      "step": 4780
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.240234375,
+      "learning_rate": 1.1772278838947442e-05,
+      "loss": 1.155,
+      "step": 4790
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.625,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 1.1309,
+      "step": 4800
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 1.1700661755970357e-05,
+      "loss": 1.1405,
+      "step": 4810
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.25,
+      "learning_rate": 1.1664819250435246e-05,
+      "loss": 1.1056,
+      "step": 4820
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.162895473394589e-05,
+      "loss": 1.1191,
+      "step": 4830
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.1593068680675227e-05,
+      "loss": 1.1283,
+      "step": 4840
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 1.155716156508094e-05,
+      "loss": 1.1046,
+      "step": 4850
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.234375,
+      "learning_rate": 1.1521233861899168e-05,
+      "loss": 1.1485,
+      "step": 4860
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 1.1485286046138259e-05,
+      "loss": 1.0905,
+      "step": 4870
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.1449318593072468e-05,
+      "loss": 1.1524,
+      "step": 4880
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.1413331978235677e-05,
+      "loss": 1.206,
+      "step": 4890
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.1377326677415108e-05,
+      "loss": 1.1059,
+      "step": 4900
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.49609375,
+      "learning_rate": 1.1341303166645043e-05,
+      "loss": 1.151,
+      "step": 4910
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 1.130526192220052e-05,
+      "loss": 1.131,
+      "step": 4920
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 1.1269203420591024e-05,
+      "loss": 1.279,
+      "step": 4930
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 1.1233128138554222e-05,
+      "loss": 1.1143,
+      "step": 4940
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.1923828125,
+      "learning_rate": 1.1197036553049626e-05,
+      "loss": 1.1559,
+      "step": 4950
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.48046875,
+      "learning_rate": 1.1160929141252303e-05,
+      "loss": 1.1276,
+      "step": 4960
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.162109375,
+      "learning_rate": 1.1124806380546564e-05,
+      "loss": 1.1622,
+      "step": 4970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.83984375,
+      "learning_rate": 1.1088668748519646e-05,
+      "loss": 1.1724,
+      "step": 4980
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.1052516722955412e-05,
+      "loss": 1.156,
+      "step": 4990
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.404296875,
+      "learning_rate": 1.101635078182802e-05,
+      "loss": 1.1908,
+      "step": 5000
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.15625,
+      "learning_rate": 1.098017140329561e-05,
+      "loss": 1.1212,
+      "step": 5010
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 1.0943979065693974e-05,
+      "loss": 1.1628,
+      "step": 5020
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.1953125,
+      "learning_rate": 1.0907774247530252e-05,
+      "loss": 1.1384,
+      "step": 5030
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.25,
+      "learning_rate": 1.0871557427476585e-05,
+      "loss": 1.1181,
+      "step": 5040
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.0835329084363787e-05,
+      "loss": 1.1326,
+      "step": 5050
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.478515625,
+      "learning_rate": 1.0799089697175041e-05,
+      "loss": 1.1383,
+      "step": 5060
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.0762839745039526e-05,
+      "loss": 1.2123,
+      "step": 5070
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.0726579707226108e-05,
+      "loss": 1.0768,
+      "step": 5080
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.384765625,
+      "learning_rate": 1.0690310063137003e-05,
+      "loss": 1.1651,
+      "step": 5090
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 1.0654031292301432e-05,
+      "loss": 1.0896,
+      "step": 5100
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.0617743874369282e-05,
+      "loss": 1.1552,
+      "step": 5110
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.169921875,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 1.1278,
+      "step": 5120
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.205078125,
+      "learning_rate": 1.0545145016380065e-05,
+      "loss": 1.0809,
+      "step": 5130
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 1.0508834536169028e-05,
+      "loss": 1.1482,
+      "step": 5140
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.72265625,
+      "learning_rate": 1.047251732854077e-05,
+      "loss": 1.1308,
+      "step": 5150
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.0436193873653362e-05,
+      "loss": 1.156,
+      "step": 5160
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.2421875,
+      "learning_rate": 1.0399864651747467e-05,
+      "loss": 1.0906,
+      "step": 5170
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.21484375,
+      "learning_rate": 1.036353014314e-05,
+      "loss": 1.0996,
+      "step": 5180
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.15234375,
+      "learning_rate": 1.0327190828217763e-05,
+      "loss": 1.1608,
+      "step": 5190
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.232421875,
+      "learning_rate": 1.0290847187431115e-05,
+      "loss": 1.1294,
+      "step": 5200
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.0254499701287604e-05,
+      "loss": 1.157,
+      "step": 5210
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 1.0218148850345613e-05,
+      "loss": 1.0994,
+      "step": 5220
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 8.0,
+      "learning_rate": 1.0181795115208017e-05,
+      "loss": 1.1308,
+      "step": 5230
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.443359375,
+      "learning_rate": 1.014543897651583e-05,
+      "loss": 1.1917,
+      "step": 5240
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.48046875,
+      "learning_rate": 1.0109080914941825e-05,
+      "loss": 1.1694,
+      "step": 5250
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.2734375,
+      "learning_rate": 1.007272141118422e-05,
+      "loss": 1.2024,
+      "step": 5260
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.003636094596028e-05,
+      "loss": 1.0688,
+      "step": 5270
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 1e-05,
+      "loss": 1.1478,
+      "step": 5280
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.330078125,
+      "learning_rate": 9.963639054039722e-06,
+      "loss": 1.1068,
+      "step": 5290
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.65234375,
+      "learning_rate": 9.927278588815786e-06,
+      "loss": 1.1371,
+      "step": 5300
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.2109375,
+      "learning_rate": 9.890919085058179e-06,
+      "loss": 1.2268,
+      "step": 5310
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 9.854561023484174e-06,
+      "loss": 1.2387,
+      "step": 5320
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 9.818204884791983e-06,
+      "loss": 1.2898,
+      "step": 5330
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.38671875,
+      "learning_rate": 9.78185114965439e-06,
+      "loss": 1.1426,
+      "step": 5340
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 9.7455002987124e-06,
+      "loss": 1.1677,
+      "step": 5350
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.16015625,
+      "learning_rate": 9.709152812568886e-06,
+      "loss": 1.091,
+      "step": 5360
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 9.67280917178224e-06,
+      "loss": 1.1368,
+      "step": 5370
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.2373046875,
+      "learning_rate": 9.636469856860005e-06,
+      "loss": 1.1298,
+      "step": 5380
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.25390625,
+      "learning_rate": 9.600135348252535e-06,
+      "loss": 1.1522,
+      "step": 5390
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.177734375,
+      "learning_rate": 9.563806126346643e-06,
+      "loss": 1.1137,
+      "step": 5400
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.193359375,
+      "learning_rate": 9.527482671459233e-06,
+      "loss": 1.178,
+      "step": 5410
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.255859375,
+      "learning_rate": 9.491165463830975e-06,
+      "loss": 1.1467,
+      "step": 5420
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.240234375,
+      "learning_rate": 9.454854983619936e-06,
+      "loss": 1.1423,
+      "step": 5430
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.25,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 1.2355,
+      "step": 5440
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 9.382256125630722e-06,
+      "loss": 1.1157,
+      "step": 5450
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.298828125,
+      "learning_rate": 9.34596870769857e-06,
+      "loss": 1.1808,
+      "step": 5460
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.53125,
+      "learning_rate": 9.309689936863002e-06,
+      "loss": 1.1627,
+      "step": 5470
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.2734375,
+      "learning_rate": 9.273420292773895e-06,
+      "loss": 1.2524,
+      "step": 5480
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.16796875,
+      "learning_rate": 9.237160254960477e-06,
+      "loss": 1.247,
+      "step": 5490
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.21484375,
+      "learning_rate": 9.200910302824964e-06,
+      "loss": 1.1416,
+      "step": 5500
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.66796875,
+      "learning_rate": 9.164670915636214e-06,
+      "loss": 1.1514,
+      "step": 5510
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 9.128442572523418e-06,
+      "loss": 1.0619,
+      "step": 5520
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.19140625,
+      "learning_rate": 9.09222575246975e-06,
+      "loss": 1.1393,
+      "step": 5530
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.3984375,
+      "learning_rate": 9.05602093430603e-06,
+      "loss": 1.0532,
+      "step": 5540
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 9.019828596704394e-06,
+      "loss": 1.1563,
+      "step": 5550
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.431640625,
+      "learning_rate": 8.983649218171981e-06,
+      "loss": 1.1124,
+      "step": 5560
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.431640625,
+      "learning_rate": 8.947483277044593e-06,
+      "loss": 1.1028,
+      "step": 5570
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.37109375,
+      "learning_rate": 8.911331251480357e-06,
+      "loss": 1.2788,
+      "step": 5580
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.7734375,
+      "learning_rate": 8.875193619453438e-06,
+      "loss": 1.1199,
+      "step": 5590
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.185546875,
+      "learning_rate": 8.839070858747697e-06,
+      "loss": 1.1208,
+      "step": 5600
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.375,
+      "learning_rate": 8.802963446950378e-06,
+      "loss": 1.1418,
+      "step": 5610
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.470703125,
+      "learning_rate": 8.76687186144578e-06,
+      "loss": 1.0694,
+      "step": 5620
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.255859375,
+      "learning_rate": 8.730796579408976e-06,
+      "loss": 1.1452,
+      "step": 5630
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.439453125,
+      "learning_rate": 8.694738077799487e-06,
+      "loss": 1.1319,
+      "step": 5640
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.2470703125,
+      "learning_rate": 8.658696833354959e-06,
+      "loss": 1.1615,
+      "step": 5650
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.2392578125,
+      "learning_rate": 8.622673322584894e-06,
+      "loss": 1.1194,
+      "step": 5660
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.28125,
+      "learning_rate": 8.586668021764328e-06,
+      "loss": 1.1372,
+      "step": 5670
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.185546875,
+      "learning_rate": 8.550681406927534e-06,
+      "loss": 1.1236,
+      "step": 5680
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.62109375,
+      "learning_rate": 8.514713953861743e-06,
+      "loss": 1.1411,
+      "step": 5690
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 8.478766138100834e-06,
+      "loss": 1.1524,
+      "step": 5700
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.27734375,
+      "learning_rate": 8.442838434919066e-06,
+      "loss": 1.0989,
+      "step": 5710
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 8.406931319324776e-06,
+      "loss": 1.105,
+      "step": 5720
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 8.371045266054114e-06,
+      "loss": 1.1416,
+      "step": 5730
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.484375,
+      "learning_rate": 8.335180749564759e-06,
+      "loss": 0.9857,
+      "step": 5740
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.21875,
+      "learning_rate": 8.299338244029646e-06,
+      "loss": 1.1576,
+      "step": 5750
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.91015625,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 1.2153,
+      "step": 5760
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.169921875,
+      "learning_rate": 8.227721161052564e-06,
+      "loss": 1.1014,
+      "step": 5770
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.2421875,
+      "learning_rate": 8.191947530476349e-06,
+      "loss": 1.1624,
+      "step": 5780
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 8.156197804573368e-06,
+      "loss": 1.0864,
+      "step": 5790
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 8.120472455998882e-06,
+      "loss": 1.219,
+      "step": 5800
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.2265625,
+      "learning_rate": 8.08477195708586e-06,
+      "loss": 1.135,
+      "step": 5810
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.154296875,
+      "learning_rate": 8.04909677983872e-06,
+      "loss": 1.113,
+      "step": 5820
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.4375,
+      "learning_rate": 8.0134473959271e-06,
+      "loss": 1.1021,
+      "step": 5830
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.328125,
+      "learning_rate": 7.977824276679623e-06,
+      "loss": 1.1617,
+      "step": 5840
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 7.942227893077652e-06,
+      "loss": 1.1427,
+      "step": 5850
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 7.90665871574908e-06,
+      "loss": 1.1607,
+      "step": 5860
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.220703125,
+      "learning_rate": 7.871117214962096e-06,
+      "loss": 1.1157,
+      "step": 5870
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 7.835603860618973e-06,
+      "loss": 1.1335,
+      "step": 5880
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.298828125,
+      "learning_rate": 7.800119122249847e-06,
+      "loss": 1.0962,
+      "step": 5890
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.208984375,
+      "learning_rate": 7.764663469006526e-06,
+      "loss": 1.1688,
+      "step": 5900
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.3984375,
+      "learning_rate": 7.72923736965627e-06,
+      "loss": 1.2101,
+      "step": 5910
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.232421875,
+      "learning_rate": 7.6938412925756e-06,
+      "loss": 1.1859,
+      "step": 5920
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 7.658475705744109e-06,
+      "loss": 1.2033,
+      "step": 5930
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.490234375,
+      "learning_rate": 7.623141076738271e-06,
+      "loss": 1.1897,
+      "step": 5940
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.32421875,
+      "learning_rate": 7.5878378727252565e-06,
+      "loss": 1.1947,
+      "step": 5950
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 7.552566560456762e-06,
+      "loss": 1.1671,
+      "step": 5960
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.361328125,
+      "learning_rate": 7.5173276062628364e-06,
+      "loss": 1.1535,
+      "step": 5970
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.443359375,
+      "learning_rate": 7.482121476045716e-06,
+      "loss": 1.1131,
+      "step": 5980
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.255859375,
+      "learning_rate": 7.446948635273655e-06,
+      "loss": 1.1528,
+      "step": 5990
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.21484375,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 1.162,
+      "step": 6000
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.193359375,
+      "learning_rate": 7.376704681730988e-06,
+      "loss": 1.074,
+      "step": 6010
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 7.341634497671673e-06,
+      "loss": 1.1559,
+      "step": 6020
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.326171875,
+      "learning_rate": 7.306599460467741e-06,
+      "loss": 1.1815,
+      "step": 6030
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.169921875,
+      "learning_rate": 7.271600033325393e-06,
+      "loss": 1.1228,
+      "step": 6040
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.88671875,
+      "learning_rate": 7.236636678980018e-06,
+      "loss": 1.1813,
+      "step": 6050
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.83984375,
+      "learning_rate": 7.201709859690081e-06,
+      "loss": 1.1252,
+      "step": 6060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.17578125,
+      "learning_rate": 7.1668200372310124e-06,
+      "loss": 1.0943,
+      "step": 6070
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 1.119,
+      "step": 6080
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.27734375,
+      "learning_rate": 7.097153227455379e-06,
+      "loss": 1.1186,
+      "step": 6090
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.53125,
+      "learning_rate": 7.062377161219556e-06,
+      "loss": 1.1206,
+      "step": 6100
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.2265625,
+      "learning_rate": 7.027639933963928e-06,
+      "loss": 1.2089,
+      "step": 6110
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.400390625,
+      "learning_rate": 6.992942004957271e-06,
+      "loss": 1.1223,
+      "step": 6120
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.154296875,
+      "learning_rate": 6.958283832948807e-06,
+      "loss": 1.123,
+      "step": 6130
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 6.923665876162118e-06,
+      "loss": 1.2252,
+      "step": 6140
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.28515625,
+      "learning_rate": 6.889088592289092e-06,
+      "loss": 1.1673,
+      "step": 6150
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.162109375,
+      "learning_rate": 6.854552438483866e-06,
+      "loss": 1.1382,
+      "step": 6160
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.50390625,
+      "learning_rate": 6.820057871356786e-06,
+      "loss": 1.2062,
+      "step": 6170
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 6.785605346968387e-06,
+      "loss": 1.1328,
+      "step": 6180
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.228515625,
+      "learning_rate": 6.751195320823325e-06,
+      "loss": 1.0434,
+      "step": 6190
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.294921875,
+      "learning_rate": 6.716828247864391e-06,
+      "loss": 1.1365,
+      "step": 6200
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 6.682504582466482e-06,
+      "loss": 1.1761,
+      "step": 6210
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.1923828125,
+      "learning_rate": 6.648224778430585e-06,
+      "loss": 1.2372,
+      "step": 6220
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.171875,
+      "learning_rate": 6.613989288977798e-06,
+      "loss": 1.1305,
+      "step": 6230
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.23828125,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 1.0702,
+      "step": 6240
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.35546875,
+      "learning_rate": 6.545653063770458e-06,
+      "loss": 1.0872,
+      "step": 6250
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.216796875,
+      "learning_rate": 6.5115532315046935e-06,
+      "loss": 1.178,
+      "step": 6260
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.21875,
+      "learning_rate": 6.4774995207876654e-06,
+      "loss": 1.131,
+      "step": 6270
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 6.443492381851237e-06,
+      "loss": 1.1188,
+      "step": 6280
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.21484375,
+      "learning_rate": 6.409532264311529e-06,
+      "loss": 1.1051,
+      "step": 6290
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.2392578125,
+      "learning_rate": 6.375619617162985e-06,
+      "loss": 1.137,
+      "step": 6300
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.359375,
+      "learning_rate": 6.3417548887724354e-06,
+      "loss": 1.1259,
+      "step": 6310
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.38671875,
+      "learning_rate": 6.3079385268731575e-06,
+      "loss": 1.1637,
+      "step": 6320
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.205078125,
+      "learning_rate": 6.274170978558971e-06,
+      "loss": 1.1434,
+      "step": 6330
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 6.2404526902783205e-06,
+      "loss": 1.1927,
+      "step": 6340
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.2890625,
+      "learning_rate": 6.206784107828367e-06,
+      "loss": 1.1617,
+      "step": 6350
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.69921875,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 1.06,
+      "step": 6360
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.169921875,
+      "learning_rate": 6.139597840317464e-06,
+      "loss": 1.1713,
+      "step": 6370
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 6.106081043541452e-06,
+      "loss": 1.1969,
+      "step": 6380
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.22265625,
+      "learning_rate": 6.072615729154261e-06,
+      "loss": 1.0577,
+      "step": 6390
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.28515625,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 1.2017,
+      "step": 6400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 9600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.8772079111558922e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}