diff --git "a/checkpoint-585/trainer_state.json" "b/checkpoint-585/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-585/trainer_state.json"
@@ -0,0 +1,4128 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7509627727856226,
+  "eval_steps": 500,
+  "global_step": 585,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0012836970474967907,
+      "grad_norm": 0.9255548715591431,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.8985,
+      "step": 1
+    },
+    {
+      "epoch": 0.0025673940949935813,
+      "grad_norm": 0.7692601680755615,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.9774,
+      "step": 2
+    },
+    {
+      "epoch": 0.0038510911424903724,
+      "grad_norm": 0.7884671092033386,
+      "learning_rate": 1.5e-06,
+      "loss": 2.9898,
+      "step": 3
+    },
+    {
+      "epoch": 0.005134788189987163,
+      "grad_norm": 0.8319393396377563,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.9573,
+      "step": 4
+    },
+    {
+      "epoch": 0.006418485237483954,
+      "grad_norm": 0.822285532951355,
+      "learning_rate": 2.5e-06,
+      "loss": 2.9316,
+      "step": 5
+    },
+    {
+      "epoch": 0.007702182284980745,
+      "grad_norm": 0.7564650774002075,
+      "learning_rate": 3e-06,
+      "loss": 2.9537,
+      "step": 6
+    },
+    {
+      "epoch": 0.008985879332477536,
+      "grad_norm": 0.9220781922340393,
+      "learning_rate": 3.5000000000000004e-06,
+      "loss": 2.9826,
+      "step": 7
+    },
+    {
+      "epoch": 0.010269576379974325,
+      "grad_norm": 0.7977064847946167,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.8548,
+      "step": 8
+    },
+    {
+      "epoch": 0.011553273427471117,
+      "grad_norm": 0.6889916658401489,
+      "learning_rate": 4.5e-06,
+      "loss": 2.9936,
+      "step": 9
+    },
+    {
+      "epoch": 0.012836970474967908,
+      "grad_norm": 0.9777728915214539,
+      "learning_rate": 5e-06,
+      "loss": 2.9578,
+      "step": 10
+    },
+    {
+      "epoch": 0.014120667522464698,
+      "grad_norm": 0.8187949061393738,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 2.9442,
+      "step": 11
+    },
+    {
+      "epoch": 0.01540436456996149,
+      "grad_norm": 0.7016908526420593,
+      "learning_rate": 6e-06,
+      "loss": 2.9299,
+      "step": 12
+    },
+    {
+      "epoch": 0.01668806161745828,
+      "grad_norm": 0.6974747180938721,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 2.9699,
+      "step": 13
+    },
+    {
+      "epoch": 0.01797175866495507,
+      "grad_norm": 0.8423139452934265,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 2.8706,
+      "step": 14
+    },
+    {
+      "epoch": 0.019255455712451863,
+      "grad_norm": 0.8017705082893372,
+      "learning_rate": 7.5e-06,
+      "loss": 2.8443,
+      "step": 15
+    },
+    {
+      "epoch": 0.02053915275994865,
+      "grad_norm": 0.9362208247184753,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.872,
+      "step": 16
+    },
+    {
+      "epoch": 0.021822849807445442,
+      "grad_norm": 1.013128638267517,
+      "learning_rate": 8.500000000000002e-06,
+      "loss": 2.797,
+      "step": 17
+    },
+    {
+      "epoch": 0.023106546854942234,
+      "grad_norm": 1.255325436592102,
+      "learning_rate": 9e-06,
+      "loss": 2.8109,
+      "step": 18
+    },
+    {
+      "epoch": 0.024390243902439025,
+      "grad_norm": 1.1081339120864868,
+      "learning_rate": 9.5e-06,
+      "loss": 2.6742,
+      "step": 19
+    },
+    {
+      "epoch": 0.025673940949935817,
+      "grad_norm": 0.8878622651100159,
+      "learning_rate": 1e-05,
+      "loss": 2.7251,
+      "step": 20
+    },
+    {
+      "epoch": 0.026957637997432605,
+      "grad_norm": 0.894791305065155,
+      "learning_rate": 1.05e-05,
+      "loss": 2.7127,
+      "step": 21
+    },
+    {
+      "epoch": 0.028241335044929396,
+      "grad_norm": 0.6742448806762695,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 2.6842,
+      "step": 22
+    },
+    {
+      "epoch": 0.029525032092426188,
+      "grad_norm": 0.6250098943710327,
+      "learning_rate": 1.1500000000000002e-05,
+      "loss": 2.6476,
+      "step": 23
+    },
+    {
+      "epoch": 0.03080872913992298,
+      "grad_norm": 0.6331678032875061,
+      "learning_rate": 1.2e-05,
+      "loss": 2.6339,
+      "step": 24
+    },
+    {
+      "epoch": 0.03209242618741977,
+      "grad_norm": 0.4726584255695343,
+      "learning_rate": 1.25e-05,
+      "loss": 2.5994,
+      "step": 25
+    },
+    {
+      "epoch": 0.03337612323491656,
+      "grad_norm": 0.46077489852905273,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 2.5545,
+      "step": 26
+    },
+    {
+      "epoch": 0.03465982028241335,
+      "grad_norm": 0.5746111273765564,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 2.5542,
+      "step": 27
+    },
+    {
+      "epoch": 0.03594351732991014,
+      "grad_norm": 0.47136253118515015,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 2.6138,
+      "step": 28
+    },
+    {
+      "epoch": 0.037227214377406934,
+      "grad_norm": 0.5951219797134399,
+      "learning_rate": 1.45e-05,
+      "loss": 2.5941,
+      "step": 29
+    },
+    {
+      "epoch": 0.038510911424903725,
+      "grad_norm": 0.48593708872795105,
+      "learning_rate": 1.5e-05,
+      "loss": 2.5751,
+      "step": 30
+    },
+    {
+      "epoch": 0.03979460847240052,
+      "grad_norm": 0.482264906167984,
+      "learning_rate": 1.55e-05,
+      "loss": 2.5689,
+      "step": 31
+    },
+    {
+      "epoch": 0.0410783055198973,
+      "grad_norm": 0.4937015175819397,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.5559,
+      "step": 32
+    },
+    {
+      "epoch": 0.04236200256739409,
+      "grad_norm": 0.5136978030204773,
+      "learning_rate": 1.65e-05,
+      "loss": 2.5274,
+      "step": 33
+    },
+    {
+      "epoch": 0.043645699614890884,
+      "grad_norm": 0.40434661507606506,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 2.4391,
+      "step": 34
+    },
+    {
+      "epoch": 0.044929396662387676,
+      "grad_norm": 0.49542951583862305,
+      "learning_rate": 1.75e-05,
+      "loss": 2.5738,
+      "step": 35
+    },
+    {
+      "epoch": 0.04621309370988447,
+      "grad_norm": 0.4381186366081238,
+      "learning_rate": 1.8e-05,
+      "loss": 2.5095,
+      "step": 36
+    },
+    {
+      "epoch": 0.04749679075738126,
+      "grad_norm": 0.486103892326355,
+      "learning_rate": 1.85e-05,
+      "loss": 2.6173,
+      "step": 37
+    },
+    {
+      "epoch": 0.04878048780487805,
+      "grad_norm": 0.4313197135925293,
+      "learning_rate": 1.9e-05,
+      "loss": 2.4951,
+      "step": 38
+    },
+    {
+      "epoch": 0.05006418485237484,
+      "grad_norm": 0.4211004078388214,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 2.5469,
+      "step": 39
+    },
+    {
+      "epoch": 0.051347881899871634,
+      "grad_norm": 0.44780072569847107,
+      "learning_rate": 2e-05,
+      "loss": 2.4437,
+      "step": 40
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.44611668586730957,
+      "learning_rate": 2.05e-05,
+      "loss": 2.4795,
+      "step": 41
+    },
+    {
+      "epoch": 0.05391527599486521,
+      "grad_norm": 0.4598286747932434,
+      "learning_rate": 2.1e-05,
+      "loss": 2.4786,
+      "step": 42
+    },
+    {
+      "epoch": 0.055198973042362,
+      "grad_norm": 0.4416978061199188,
+      "learning_rate": 2.15e-05,
+      "loss": 2.453,
+      "step": 43
+    },
+    {
+      "epoch": 0.05648267008985879,
+      "grad_norm": 0.4136359989643097,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 2.4975,
+      "step": 44
+    },
+    {
+      "epoch": 0.057766367137355584,
+      "grad_norm": 0.44032955169677734,
+      "learning_rate": 2.25e-05,
+      "loss": 2.411,
+      "step": 45
+    },
+    {
+      "epoch": 0.059050064184852376,
+      "grad_norm": 0.49505728483200073,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 2.5049,
+      "step": 46
+    },
+    {
+      "epoch": 0.06033376123234917,
+      "grad_norm": 0.43698814511299133,
+      "learning_rate": 2.35e-05,
+      "loss": 2.5828,
+      "step": 47
+    },
+    {
+      "epoch": 0.06161745827984596,
+      "grad_norm": 0.44550350308418274,
+      "learning_rate": 2.4e-05,
+      "loss": 2.4326,
+      "step": 48
+    },
+    {
+      "epoch": 0.06290115532734275,
+      "grad_norm": 0.38959425687789917,
+      "learning_rate": 2.45e-05,
+      "loss": 2.4684,
+      "step": 49
+    },
+    {
+      "epoch": 0.06418485237483953,
+      "grad_norm": 0.4324244260787964,
+      "learning_rate": 2.5e-05,
+      "loss": 2.4496,
+      "step": 50
+    },
+    {
+      "epoch": 0.06546854942233633,
+      "grad_norm": 0.4213118553161621,
+      "learning_rate": 2.5500000000000003e-05,
+      "loss": 2.4742,
+      "step": 51
+    },
+    {
+      "epoch": 0.06675224646983312,
+      "grad_norm": 0.5279268622398376,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 2.4222,
+      "step": 52
+    },
+    {
+      "epoch": 0.06803594351732992,
+      "grad_norm": 0.40476322174072266,
+      "learning_rate": 2.6500000000000004e-05,
+      "loss": 2.4224,
+      "step": 53
+    },
+    {
+      "epoch": 0.0693196405648267,
+      "grad_norm": 0.6938806176185608,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 2.4194,
+      "step": 54
+    },
+    {
+      "epoch": 0.07060333761232349,
+      "grad_norm": 0.43899399042129517,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 2.4288,
+      "step": 55
+    },
+    {
+      "epoch": 0.07188703465982028,
+      "grad_norm": 0.3968575596809387,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 2.3968,
+      "step": 56
+    },
+    {
+      "epoch": 0.07317073170731707,
+      "grad_norm": 0.6113290786743164,
+      "learning_rate": 2.8499999999999998e-05,
+      "loss": 2.3924,
+      "step": 57
+    },
+    {
+      "epoch": 0.07445442875481387,
+      "grad_norm": 0.35704493522644043,
+      "learning_rate": 2.9e-05,
+      "loss": 2.4004,
+      "step": 58
+    },
+    {
+      "epoch": 0.07573812580231065,
+      "grad_norm": 0.3809000551700592,
+      "learning_rate": 2.95e-05,
+      "loss": 2.4303,
+      "step": 59
+    },
+    {
+      "epoch": 0.07702182284980745,
+      "grad_norm": 0.4394189715385437,
+      "learning_rate": 3e-05,
+      "loss": 2.4716,
+      "step": 60
+    },
+    {
+      "epoch": 0.07830551989730423,
+      "grad_norm": 0.4325893521308899,
+      "learning_rate": 3.05e-05,
+      "loss": 2.4715,
+      "step": 61
+    },
+    {
+      "epoch": 0.07958921694480103,
+      "grad_norm": 0.3560517728328705,
+      "learning_rate": 3.1e-05,
+      "loss": 2.4745,
+      "step": 62
+    },
+    {
+      "epoch": 0.08087291399229782,
+      "grad_norm": 0.37922918796539307,
+      "learning_rate": 3.15e-05,
+      "loss": 2.4789,
+      "step": 63
+    },
+    {
+      "epoch": 0.0821566110397946,
+      "grad_norm": 0.3665093779563904,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 2.4829,
+      "step": 64
+    },
+    {
+      "epoch": 0.0834403080872914,
+      "grad_norm": 0.38106483221054077,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 2.4203,
+      "step": 65
+    },
+    {
+      "epoch": 0.08472400513478819,
+      "grad_norm": 0.5111002326011658,
+      "learning_rate": 3.3e-05,
+      "loss": 2.3302,
+      "step": 66
+    },
+    {
+      "epoch": 0.08600770218228498,
+      "grad_norm": 0.37738922238349915,
+      "learning_rate": 3.35e-05,
+      "loss": 2.4991,
+      "step": 67
+    },
+    {
+      "epoch": 0.08729139922978177,
+      "grad_norm": 0.34703031182289124,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 2.4224,
+      "step": 68
+    },
+    {
+      "epoch": 0.08857509627727857,
+      "grad_norm": 0.48427700996398926,
+      "learning_rate": 3.45e-05,
+      "loss": 2.3946,
+      "step": 69
+    },
+    {
+      "epoch": 0.08985879332477535,
+      "grad_norm": 0.360221266746521,
+      "learning_rate": 3.5e-05,
+      "loss": 2.4853,
+      "step": 70
+    },
+    {
+      "epoch": 0.09114249037227215,
+      "grad_norm": 0.4006412625312805,
+      "learning_rate": 3.55e-05,
+      "loss": 2.4654,
+      "step": 71
+    },
+    {
+      "epoch": 0.09242618741976893,
+      "grad_norm": 0.3662618398666382,
+      "learning_rate": 3.6e-05,
+      "loss": 2.434,
+      "step": 72
+    },
+    {
+      "epoch": 0.09370988446726572,
+      "grad_norm": 0.3694933354854584,
+      "learning_rate": 3.65e-05,
+      "loss": 2.4194,
+      "step": 73
+    },
+    {
+      "epoch": 0.09499358151476252,
+      "grad_norm": 0.34268808364868164,
+      "learning_rate": 3.7e-05,
+      "loss": 2.4922,
+      "step": 74
+    },
+    {
+      "epoch": 0.0962772785622593,
+      "grad_norm": 0.3664718270301819,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 2.4083,
+      "step": 75
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.3909706473350525,
+      "learning_rate": 3.8e-05,
+      "loss": 2.4546,
+      "step": 76
+    },
+    {
+      "epoch": 0.09884467265725289,
+      "grad_norm": 0.36276674270629883,
+      "learning_rate": 3.85e-05,
+      "loss": 2.5313,
+      "step": 77
+    },
+    {
+      "epoch": 0.10012836970474968,
+      "grad_norm": 0.34822535514831543,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 2.4833,
+      "step": 78
+    },
+    {
+      "epoch": 0.10141206675224647,
+      "grad_norm": 0.37480583786964417,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 2.449,
+      "step": 79
+    },
+    {
+      "epoch": 0.10269576379974327,
+      "grad_norm": 0.3415388762950897,
+      "learning_rate": 4e-05,
+      "loss": 2.3953,
+      "step": 80
+    },
+    {
+      "epoch": 0.10397946084724005,
+      "grad_norm": 0.3487205505371094,
+      "learning_rate": 4.05e-05,
+      "loss": 2.4469,
+      "step": 81
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.5083756446838379,
+      "learning_rate": 4.1e-05,
+      "loss": 2.3423,
+      "step": 82
+    },
+    {
+      "epoch": 0.10654685494223363,
+      "grad_norm": 0.3747817575931549,
+      "learning_rate": 4.15e-05,
+      "loss": 2.3919,
+      "step": 83
+    },
+    {
+      "epoch": 0.10783055198973042,
+      "grad_norm": 0.39472389221191406,
+      "learning_rate": 4.2e-05,
+      "loss": 2.5431,
+      "step": 84
+    },
+    {
+      "epoch": 0.10911424903722722,
+      "grad_norm": 0.36542952060699463,
+      "learning_rate": 4.25e-05,
+      "loss": 2.3858,
+      "step": 85
+    },
+    {
+      "epoch": 0.110397946084724,
+      "grad_norm": 0.34629878401756287,
+      "learning_rate": 4.3e-05,
+      "loss": 2.3528,
+      "step": 86
+    },
+    {
+      "epoch": 0.1116816431322208,
+      "grad_norm": 0.36755290627479553,
+      "learning_rate": 4.35e-05,
+      "loss": 2.5329,
+      "step": 87
+    },
+    {
+      "epoch": 0.11296534017971759,
+      "grad_norm": 0.3599033057689667,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.4971,
+      "step": 88
+    },
+    {
+      "epoch": 0.11424903722721438,
+      "grad_norm": 0.3730204701423645,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 2.4082,
+      "step": 89
+    },
+    {
+      "epoch": 0.11553273427471117,
+      "grad_norm": 0.3773551881313324,
+      "learning_rate": 4.5e-05,
+      "loss": 2.3393,
+      "step": 90
+    },
+    {
+      "epoch": 0.11681643132220795,
+      "grad_norm": 0.36052408814430237,
+      "learning_rate": 4.55e-05,
+      "loss": 2.3799,
+      "step": 91
+    },
+    {
+      "epoch": 0.11810012836970475,
+      "grad_norm": 0.32685768604278564,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 2.4284,
+      "step": 92
+    },
+    {
+      "epoch": 0.11938382541720154,
+      "grad_norm": 0.36063292622566223,
+      "learning_rate": 4.6500000000000005e-05,
+      "loss": 2.3903,
+      "step": 93
+    },
+    {
+      "epoch": 0.12066752246469833,
+      "grad_norm": 0.3656150698661804,
+      "learning_rate": 4.7e-05,
+      "loss": 2.4378,
+      "step": 94
+    },
+    {
+      "epoch": 0.12195121951219512,
+      "grad_norm": 0.3563483655452728,
+      "learning_rate": 4.75e-05,
+      "loss": 2.4082,
+      "step": 95
+    },
+    {
+      "epoch": 0.12323491655969192,
+      "grad_norm": 0.35744163393974304,
+      "learning_rate": 4.8e-05,
+      "loss": 2.3979,
+      "step": 96
+    },
+    {
+      "epoch": 0.1245186136071887,
+      "grad_norm": 0.3400294780731201,
+      "learning_rate": 4.85e-05,
+      "loss": 2.4419,
+      "step": 97
+    },
+    {
+      "epoch": 0.1258023106546855,
+      "grad_norm": 0.3691268265247345,
+      "learning_rate": 4.9e-05,
+      "loss": 2.4671,
+      "step": 98
+    },
+    {
+      "epoch": 0.12708600770218229,
+      "grad_norm": 0.3483717739582062,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 2.3947,
+      "step": 99
+    },
+    {
+      "epoch": 0.12836970474967907,
+      "grad_norm": 0.3494178354740143,
+      "learning_rate": 5e-05,
+      "loss": 2.4063,
+      "step": 100
+    },
+    {
+      "epoch": 0.12965340179717585,
+      "grad_norm": 0.3814634680747986,
+      "learning_rate": 4.9999986437272225e-05,
+      "loss": 2.4832,
+      "step": 101
+    },
+    {
+      "epoch": 0.13093709884467267,
+      "grad_norm": 0.378907710313797,
+      "learning_rate": 4.999994574910364e-05,
+      "loss": 2.3272,
+      "step": 102
+    },
+    {
+      "epoch": 0.13222079589216945,
+      "grad_norm": 0.3730032444000244,
+      "learning_rate": 4.999987793553836e-05,
+      "loss": 2.3965,
+      "step": 103
+    },
+    {
+      "epoch": 0.13350449293966624,
+      "grad_norm": 0.3670955002307892,
+      "learning_rate": 4.9999782996649994e-05,
+      "loss": 2.4565,
+      "step": 104
+    },
+    {
+      "epoch": 0.13478818998716302,
+      "grad_norm": 0.36450427770614624,
+      "learning_rate": 4.999966093254153e-05,
+      "loss": 2.5079,
+      "step": 105
+    },
+    {
+      "epoch": 0.13607188703465983,
+      "grad_norm": 0.38658779859542847,
+      "learning_rate": 4.9999511743345426e-05,
+      "loss": 2.4775,
+      "step": 106
+    },
+    {
+      "epoch": 0.13735558408215662,
+      "grad_norm": 0.33551573753356934,
+      "learning_rate": 4.999933542922354e-05,
+      "loss": 2.461,
+      "step": 107
+    },
+    {
+      "epoch": 0.1386392811296534,
+      "grad_norm": 0.3854399025440216,
+      "learning_rate": 4.999913199036719e-05,
+      "loss": 2.4075,
+      "step": 108
+    },
+    {
+      "epoch": 0.1399229781771502,
+      "grad_norm": 0.3932352364063263,
+      "learning_rate": 4.9998901426997104e-05,
+      "loss": 2.4311,
+      "step": 109
+    },
+    {
+      "epoch": 0.14120667522464697,
+      "grad_norm": 0.3379668593406677,
+      "learning_rate": 4.999864373936345e-05,
+      "loss": 2.5016,
+      "step": 110
+    },
+    {
+      "epoch": 0.14249037227214378,
+      "grad_norm": 0.32840296626091003,
+      "learning_rate": 4.9998358927745826e-05,
+      "loss": 2.3176,
+      "step": 111
+    },
+    {
+      "epoch": 0.14377406931964057,
+      "grad_norm": 0.3191027343273163,
+      "learning_rate": 4.999804699245325e-05,
+      "loss": 2.4007,
+      "step": 112
+    },
+    {
+      "epoch": 0.14505776636713735,
+      "grad_norm": 0.3358600437641144,
+      "learning_rate": 4.999770793382418e-05,
+      "loss": 2.3724,
+      "step": 113
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.335860937833786,
+      "learning_rate": 4.99973417522265e-05,
+      "loss": 2.3479,
+      "step": 114
+    },
+    {
+      "epoch": 0.14762516046213095,
+      "grad_norm": 0.34540730714797974,
+      "learning_rate": 4.999694844805753e-05,
+      "loss": 2.3675,
+      "step": 115
+    },
+    {
+      "epoch": 0.14890885750962773,
+      "grad_norm": 0.3298475742340088,
+      "learning_rate": 4.999652802174402e-05,
+      "loss": 2.3948,
+      "step": 116
+    },
+    {
+      "epoch": 0.15019255455712452,
+      "grad_norm": 0.3612127900123596,
+      "learning_rate": 4.999608047374211e-05,
+      "loss": 2.3855,
+      "step": 117
+    },
+    {
+      "epoch": 0.1514762516046213,
+      "grad_norm": 0.4185655415058136,
+      "learning_rate": 4.9995605804537426e-05,
+      "loss": 2.4015,
+      "step": 118
+    },
+    {
+      "epoch": 0.1527599486521181,
+      "grad_norm": 0.3759553134441376,
+      "learning_rate": 4.9995104014644986e-05,
+      "loss": 2.4483,
+      "step": 119
+    },
+    {
+      "epoch": 0.1540436456996149,
+      "grad_norm": 0.35989564657211304,
+      "learning_rate": 4.999457510460923e-05,
+      "loss": 2.4974,
+      "step": 120
+    },
+    {
+      "epoch": 0.15532734274711169,
+      "grad_norm": 0.3161202073097229,
+      "learning_rate": 4.999401907500405e-05,
+      "loss": 2.3712,
+      "step": 121
+    },
+    {
+      "epoch": 0.15661103979460847,
+      "grad_norm": 0.3105814456939697,
+      "learning_rate": 4.999343592643274e-05,
+      "loss": 2.4311,
+      "step": 122
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.3236968517303467,
+      "learning_rate": 4.9992825659528024e-05,
+      "loss": 2.5536,
+      "step": 123
+    },
+    {
+      "epoch": 0.15917843388960207,
+      "grad_norm": 0.3107609748840332,
+      "learning_rate": 4.9992188274952064e-05,
+      "loss": 2.3922,
+      "step": 124
+    },
+    {
+      "epoch": 0.16046213093709885,
+      "grad_norm": 0.39889928698539734,
+      "learning_rate": 4.999152377339642e-05,
+      "loss": 2.3488,
+      "step": 125
+    },
+    {
+      "epoch": 0.16174582798459564,
+      "grad_norm": 0.379323273897171,
+      "learning_rate": 4.99908321555821e-05,
+      "loss": 2.5278,
+      "step": 126
+    },
+    {
+      "epoch": 0.16302952503209242,
+      "grad_norm": 0.35020819306373596,
+      "learning_rate": 4.999011342225952e-05,
+      "loss": 2.3139,
+      "step": 127
+    },
+    {
+      "epoch": 0.1643132220795892,
+      "grad_norm": 0.34851884841918945,
+      "learning_rate": 4.998936757420851e-05,
+      "loss": 2.3495,
+      "step": 128
+    },
+    {
+      "epoch": 0.16559691912708602,
+      "grad_norm": 0.3453572392463684,
+      "learning_rate": 4.9988594612238336e-05,
+      "loss": 2.4128,
+      "step": 129
+    },
+    {
+      "epoch": 0.1668806161745828,
+      "grad_norm": 0.34227538108825684,
+      "learning_rate": 4.998779453718768e-05,
+      "loss": 2.3419,
+      "step": 130
+    },
+    {
+      "epoch": 0.1681643132220796,
+      "grad_norm": 0.3947238028049469,
+      "learning_rate": 4.998696734992462e-05,
+      "loss": 2.3941,
+      "step": 131
+    },
+    {
+      "epoch": 0.16944801026957637,
+      "grad_norm": 0.306533545255661,
+      "learning_rate": 4.998611305134669e-05,
+      "loss": 2.4645,
+      "step": 132
+    },
+    {
+      "epoch": 0.17073170731707318,
+      "grad_norm": 0.35172709822654724,
+      "learning_rate": 4.998523164238082e-05,
+      "loss": 2.4407,
+      "step": 133
+    },
+    {
+      "epoch": 0.17201540436456997,
+      "grad_norm": 0.34511688351631165,
+      "learning_rate": 4.9984323123983334e-05,
+      "loss": 2.3815,
+      "step": 134
+    },
+    {
+      "epoch": 0.17329910141206675,
+      "grad_norm": 0.33132505416870117,
+      "learning_rate": 4.9983387497140006e-05,
+      "loss": 2.3548,
+      "step": 135
+    },
+    {
+      "epoch": 0.17458279845956354,
+      "grad_norm": 0.32891082763671875,
+      "learning_rate": 4.998242476286601e-05,
+      "loss": 2.5308,
+      "step": 136
+    },
+    {
+      "epoch": 0.17586649550706032,
+      "grad_norm": 0.331152081489563,
+      "learning_rate": 4.998143492220592e-05,
+      "loss": 2.3858,
+      "step": 137
+    },
+    {
+      "epoch": 0.17715019255455713,
+      "grad_norm": 0.31813687086105347,
+      "learning_rate": 4.9980417976233735e-05,
+      "loss": 2.3136,
+      "step": 138
+    },
+    {
+      "epoch": 0.17843388960205392,
+      "grad_norm": 0.3268696069717407,
+      "learning_rate": 4.9979373926052865e-05,
+      "loss": 2.3133,
+      "step": 139
+    },
+    {
+      "epoch": 0.1797175866495507,
+      "grad_norm": 0.3389696180820465,
+      "learning_rate": 4.997830277279612e-05,
+      "loss": 2.3983,
+      "step": 140
+    },
+    {
+      "epoch": 0.1810012836970475,
+      "grad_norm": 0.3515508770942688,
+      "learning_rate": 4.997720451762572e-05,
+      "loss": 2.4848,
+      "step": 141
+    },
+    {
+      "epoch": 0.1822849807445443,
+      "grad_norm": 0.3302924335002899,
+      "learning_rate": 4.997607916173329e-05,
+      "loss": 2.3037,
+      "step": 142
+    },
+    {
+      "epoch": 0.18356867779204109,
+      "grad_norm": 0.3332863450050354,
+      "learning_rate": 4.997492670633987e-05,
+      "loss": 2.3563,
+      "step": 143
+    },
+    {
+      "epoch": 0.18485237483953787,
+      "grad_norm": 0.3398495614528656,
+      "learning_rate": 4.997374715269589e-05,
+      "loss": 2.4056,
+      "step": 144
+    },
+    {
+      "epoch": 0.18613607188703465,
+      "grad_norm": 0.3376169502735138,
+      "learning_rate": 4.9972540502081184e-05,
+      "loss": 2.3751,
+      "step": 145
+    },
+    {
+      "epoch": 0.18741976893453144,
+      "grad_norm": 0.33639830350875854,
+      "learning_rate": 4.9971306755804995e-05,
+      "loss": 2.432,
+      "step": 146
+    },
+    {
+      "epoch": 0.18870346598202825,
+      "grad_norm": 0.410265177488327,
+      "learning_rate": 4.9970045915205954e-05,
+      "loss": 2.3647,
+      "step": 147
+    },
+    {
+      "epoch": 0.18998716302952504,
+      "grad_norm": 0.31853362917900085,
+      "learning_rate": 4.99687579816521e-05,
+      "loss": 2.4224,
+      "step": 148
+    },
+    {
+      "epoch": 0.19127086007702182,
+      "grad_norm": 0.3495614230632782,
+      "learning_rate": 4.9967442956540863e-05,
+      "loss": 2.3961,
+      "step": 149
+    },
+    {
+      "epoch": 0.1925545571245186,
+      "grad_norm": 0.33301132917404175,
+      "learning_rate": 4.996610084129908e-05,
+      "loss": 2.359,
+      "step": 150
+    },
+    {
+      "epoch": 0.19383825417201542,
+      "grad_norm": 0.3186255395412445,
+      "learning_rate": 4.996473163738295e-05,
+      "loss": 2.4488,
+      "step": 151
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.3374113142490387,
+      "learning_rate": 4.996333534627809e-05,
+      "loss": 2.4019,
+      "step": 152
+    },
+    {
+      "epoch": 0.196405648267009,
+      "grad_norm": 0.33905014395713806,
+      "learning_rate": 4.996191196949952e-05,
+      "loss": 2.3272,
+      "step": 153
+    },
+    {
+      "epoch": 0.19768934531450577,
+      "grad_norm": 0.3546963036060333,
+      "learning_rate": 4.996046150859161e-05,
+      "loss": 2.4338,
+      "step": 154
+    },
+    {
+      "epoch": 0.19897304236200256,
+      "grad_norm": 0.35965755581855774,
+      "learning_rate": 4.9958983965128145e-05,
+      "loss": 2.3634,
+      "step": 155
+    },
+    {
+      "epoch": 0.20025673940949937,
+      "grad_norm": 0.3362196385860443,
+      "learning_rate": 4.995747934071229e-05,
+      "loss": 2.4457,
+      "step": 156
+    },
+    {
+      "epoch": 0.20154043645699615,
+      "grad_norm": 0.37214434146881104,
+      "learning_rate": 4.995594763697657e-05,
+      "loss": 2.3714,
+      "step": 157
+    },
+    {
+      "epoch": 0.20282413350449294,
+      "grad_norm": 0.3538600206375122,
+      "learning_rate": 4.995438885558294e-05,
+      "loss": 2.4338,
+      "step": 158
+    },
+    {
+      "epoch": 0.20410783055198972,
+      "grad_norm": 0.3853035569190979,
+      "learning_rate": 4.995280299822268e-05,
+      "loss": 2.4036,
+      "step": 159
+    },
+    {
+      "epoch": 0.20539152759948653,
+      "grad_norm": 0.35037294030189514,
+      "learning_rate": 4.9951190066616495e-05,
+      "loss": 2.3846,
+      "step": 160
+    },
+    {
+      "epoch": 0.20667522464698332,
+      "grad_norm": 0.3986567556858063,
+      "learning_rate": 4.994955006251443e-05,
+      "loss": 2.4405,
+      "step": 161
+    },
+    {
+      "epoch": 0.2079589216944801,
+      "grad_norm": 0.385637491941452,
+      "learning_rate": 4.994788298769593e-05,
+      "loss": 2.3237,
+      "step": 162
+    },
+    {
+      "epoch": 0.2092426187419769,
+      "grad_norm": 0.34437429904937744,
+      "learning_rate": 4.994618884396979e-05,
+      "loss": 2.3477,
+      "step": 163
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.34156107902526855,
+      "learning_rate": 4.99444676331742e-05,
+      "loss": 2.3576,
+      "step": 164
+    },
+    {
+      "epoch": 0.21181001283697048,
+      "grad_norm": 0.33888015151023865,
+      "learning_rate": 4.99427193571767e-05,
+      "loss": 2.311,
+      "step": 165
+    },
+    {
+      "epoch": 0.21309370988446727,
+      "grad_norm": 0.34711146354675293,
+      "learning_rate": 4.99409440178742e-05,
+      "loss": 2.293,
+      "step": 166
+    },
+    {
+      "epoch": 0.21437740693196405,
+      "grad_norm": 0.30586686730384827,
+      "learning_rate": 4.993914161719297e-05,
+      "loss": 2.479,
+      "step": 167
+    },
+    {
+      "epoch": 0.21566110397946084,
+      "grad_norm": 0.4145469069480896,
+      "learning_rate": 4.993731215708866e-05,
+      "loss": 2.2754,
+      "step": 168
+    },
+    {
+      "epoch": 0.21694480102695765,
+      "grad_norm": 0.6243994235992432,
+      "learning_rate": 4.993545563954626e-05,
+      "loss": 2.3751,
+      "step": 169
+    },
+    {
+      "epoch": 0.21822849807445444,
+      "grad_norm": 0.3301653265953064,
+      "learning_rate": 4.993357206658011e-05,
+      "loss": 2.6124,
+      "step": 170
+    },
+    {
+      "epoch": 0.21951219512195122,
+      "grad_norm": 0.337147980928421,
+      "learning_rate": 4.993166144023396e-05,
+      "loss": 2.3946,
+      "step": 171
+    },
+    {
+      "epoch": 0.220795892169448,
+      "grad_norm": 0.3796294033527374,
+      "learning_rate": 4.9929723762580835e-05,
+      "loss": 2.3314,
+      "step": 172
+    },
+    {
+      "epoch": 0.2220795892169448,
+      "grad_norm": 0.4021480679512024,
+      "learning_rate": 4.9927759035723175e-05,
+      "loss": 2.3035,
+      "step": 173
+    },
+    {
+      "epoch": 0.2233632862644416,
+      "grad_norm": 0.3196207582950592,
+      "learning_rate": 4.992576726179274e-05,
+      "loss": 2.4047,
+      "step": 174
+    },
+    {
+      "epoch": 0.2246469833119384,
+      "grad_norm": 0.31279096007347107,
+      "learning_rate": 4.992374844295064e-05,
+      "loss": 2.4409,
+      "step": 175
+    },
+    {
+      "epoch": 0.22593068035943517,
+      "grad_norm": 0.3068607747554779,
+      "learning_rate": 4.992170258138732e-05,
+      "loss": 2.4109,
+      "step": 176
+    },
+    {
+      "epoch": 0.22721437740693196,
+      "grad_norm": 0.35363098978996277,
+      "learning_rate": 4.991962967932258e-05,
+      "loss": 2.4083,
+      "step": 177
+    },
+    {
+      "epoch": 0.22849807445442877,
+      "grad_norm": 0.33908936381340027,
+      "learning_rate": 4.9917529739005574e-05,
+      "loss": 2.4129,
+      "step": 178
+    },
+    {
+      "epoch": 0.22978177150192555,
+      "grad_norm": 0.32510805130004883,
+      "learning_rate": 4.991540276271476e-05,
+      "loss": 2.3163,
+      "step": 179
+    },
+    {
+      "epoch": 0.23106546854942234,
+      "grad_norm": 0.32639047503471375,
+      "learning_rate": 4.991324875275794e-05,
+      "loss": 2.3567,
+      "step": 180
+    },
+    {
+      "epoch": 0.23234916559691912,
+      "grad_norm": 0.3410406708717346,
+      "learning_rate": 4.991106771147227e-05,
+      "loss": 2.4137,
+      "step": 181
+    },
+    {
+      "epoch": 0.2336328626444159,
+      "grad_norm": 0.3334997892379761,
+      "learning_rate": 4.990885964122421e-05,
+      "loss": 2.3994,
+      "step": 182
+    },
+    {
+      "epoch": 0.23491655969191272,
+      "grad_norm": 0.3203848600387573,
+      "learning_rate": 4.990662454440956e-05,
+      "loss": 2.4259,
+      "step": 183
+    },
+    {
+      "epoch": 0.2362002567394095,
+      "grad_norm": 0.34999069571495056,
+      "learning_rate": 4.9904362423453446e-05,
+      "loss": 2.413,
+      "step": 184
+    },
+    {
+      "epoch": 0.2374839537869063,
+      "grad_norm": 0.3413456678390503,
+      "learning_rate": 4.990207328081029e-05,
+      "loss": 2.3749,
+      "step": 185
+    },
+    {
+      "epoch": 0.23876765083440307,
+      "grad_norm": 0.3702191114425659,
+      "learning_rate": 4.989975711896388e-05,
+      "loss": 2.4309,
+      "step": 186
+    },
+    {
+      "epoch": 0.24005134788189988,
+      "grad_norm": 0.3365226089954376,
+      "learning_rate": 4.989741394042727e-05,
+      "loss": 2.3708,
+      "step": 187
+    },
+    {
+      "epoch": 0.24133504492939667,
+      "grad_norm": 0.36596447229385376,
+      "learning_rate": 4.989504374774288e-05,
+      "loss": 2.4387,
+      "step": 188
+    },
+    {
+      "epoch": 0.24261874197689345,
+      "grad_norm": 0.3280293941497803,
+      "learning_rate": 4.9892646543482377e-05,
+      "loss": 2.498,
+      "step": 189
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 0.35989147424697876,
+      "learning_rate": 4.989022233024681e-05,
+      "loss": 2.4993,
+      "step": 190
+    },
+    {
+      "epoch": 0.24518613607188702,
+      "grad_norm": 0.3124522268772125,
+      "learning_rate": 4.988777111066646e-05,
+      "loss": 2.3186,
+      "step": 191
+    },
+    {
+      "epoch": 0.24646983311938384,
+      "grad_norm": 0.32323285937309265,
+      "learning_rate": 4.988529288740096e-05,
+      "loss": 2.3859,
+      "step": 192
+    },
+    {
+      "epoch": 0.24775353016688062,
+      "grad_norm": 0.33156561851501465,
+      "learning_rate": 4.988278766313922e-05,
+      "loss": 2.3271,
+      "step": 193
+    },
+    {
+      "epoch": 0.2490372272143774,
+      "grad_norm": 0.32494014501571655,
+      "learning_rate": 4.9880255440599476e-05,
+      "loss": 2.4023,
+      "step": 194
+    },
+    {
+      "epoch": 0.2503209242618742,
+      "grad_norm": 0.3906209468841553,
+      "learning_rate": 4.987769622252921e-05,
+      "loss": 2.4245,
+      "step": 195
+    },
+    {
+      "epoch": 0.251604621309371,
+      "grad_norm": 0.3735322952270508,
+      "learning_rate": 4.987511001170523e-05,
+      "loss": 2.4883,
+      "step": 196
+    },
+    {
+      "epoch": 0.25288831835686776,
+      "grad_norm": 0.30935361981391907,
+      "learning_rate": 4.987249681093362e-05,
+      "loss": 2.5118,
+      "step": 197
+    },
+    {
+      "epoch": 0.25417201540436457,
+      "grad_norm": 0.34933099150657654,
+      "learning_rate": 4.986985662304976e-05,
+      "loss": 2.3138,
+      "step": 198
+    },
+    {
+      "epoch": 0.2554557124518614,
+      "grad_norm": 0.3328215777873993,
+      "learning_rate": 4.9867189450918294e-05,
+      "loss": 2.4475,
+      "step": 199
+    },
+    {
+      "epoch": 0.25673940949935814,
+      "grad_norm": 0.3271300494670868,
+      "learning_rate": 4.986449529743314e-05,
+      "loss": 2.4156,
+      "step": 200
+    },
+    {
+      "epoch": 0.25802310654685495,
+      "grad_norm": 0.296889990568161,
+      "learning_rate": 4.9861774165517536e-05,
+      "loss": 2.4117,
+      "step": 201
+    },
+    {
+      "epoch": 0.2593068035943517,
+      "grad_norm": 0.31897205114364624,
+      "learning_rate": 4.9859026058123925e-05,
+      "loss": 2.4637,
+      "step": 202
+    },
+    {
+      "epoch": 0.2605905006418485,
+      "grad_norm": 0.320688933134079,
+      "learning_rate": 4.985625097823408e-05,
+      "loss": 2.3865,
+      "step": 203
+    },
+    {
+      "epoch": 0.26187419768934533,
+      "grad_norm": 0.29705896973609924,
+      "learning_rate": 4.985344892885899e-05,
+      "loss": 2.365,
+      "step": 204
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.32413363456726074,
+      "learning_rate": 4.985061991303895e-05,
+      "loss": 2.4379,
+      "step": 205
+    },
+    {
+      "epoch": 0.2644415917843389,
+      "grad_norm": 0.38111138343811035,
+      "learning_rate": 4.984776393384348e-05,
+      "loss": 2.4303,
+      "step": 206
+    },
+    {
+      "epoch": 0.26572528883183566,
+      "grad_norm": 0.34943342208862305,
+      "learning_rate": 4.984488099437138e-05,
+      "loss": 2.3508,
+      "step": 207
+    },
+    {
+      "epoch": 0.26700898587933247,
+      "grad_norm": 0.34694743156433105,
+      "learning_rate": 4.984197109775068e-05,
+      "loss": 2.4488,
+      "step": 208
+    },
+    {
+      "epoch": 0.2682926829268293,
+      "grad_norm": 0.3251892626285553,
+      "learning_rate": 4.983903424713868e-05,
+      "loss": 2.4187,
+      "step": 209
+    },
+    {
+      "epoch": 0.26957637997432604,
+      "grad_norm": 0.34391969442367554,
+      "learning_rate": 4.9836070445721924e-05,
+      "loss": 2.4723,
+      "step": 210
+    },
+    {
+      "epoch": 0.27086007702182285,
+      "grad_norm": 0.32182154059410095,
+      "learning_rate": 4.983307969671617e-05,
+      "loss": 2.4282,
+      "step": 211
+    },
+    {
+      "epoch": 0.27214377406931967,
+      "grad_norm": 0.3486088514328003,
+      "learning_rate": 4.983006200336645e-05,
+      "loss": 2.4411,
+      "step": 212
+    },
+    {
+      "epoch": 0.2734274711168164,
+      "grad_norm": 0.3152271807193756,
+      "learning_rate": 4.9827017368947e-05,
+      "loss": 2.3362,
+      "step": 213
+    },
+    {
+      "epoch": 0.27471116816431324,
+      "grad_norm": 0.30361658334732056,
+      "learning_rate": 4.982394579676133e-05,
+      "loss": 2.34,
+      "step": 214
+    },
+    {
+      "epoch": 0.27599486521181,
+      "grad_norm": 0.3163071274757385,
+      "learning_rate": 4.9820847290142135e-05,
+      "loss": 2.3996,
+      "step": 215
+    },
+    {
+      "epoch": 0.2772785622593068,
+      "grad_norm": 0.319831907749176,
+      "learning_rate": 4.981772185245135e-05,
+      "loss": 2.352,
+      "step": 216
+    },
+    {
+      "epoch": 0.2785622593068036,
+      "grad_norm": 0.34143316745758057,
+      "learning_rate": 4.981456948708014e-05,
+      "loss": 2.2837,
+      "step": 217
+    },
+    {
+      "epoch": 0.2798459563543004,
+      "grad_norm": 0.3066380023956299,
+      "learning_rate": 4.981139019744887e-05,
+      "loss": 2.3848,
+      "step": 218
+    },
+    {
+      "epoch": 0.2811296534017972,
+      "grad_norm": 0.32719743251800537,
+      "learning_rate": 4.9808183987007136e-05,
+      "loss": 2.3845,
+      "step": 219
+    },
+    {
+      "epoch": 0.28241335044929394,
+      "grad_norm": 0.384798526763916,
+      "learning_rate": 4.980495085923372e-05,
+      "loss": 2.3767,
+      "step": 220
+    },
+    {
+      "epoch": 0.28369704749679076,
+      "grad_norm": 0.4263782799243927,
+      "learning_rate": 4.980169081763665e-05,
+      "loss": 2.3342,
+      "step": 221
+    },
+    {
+      "epoch": 0.28498074454428757,
+      "grad_norm": 0.3271712064743042,
+      "learning_rate": 4.979840386575311e-05,
+      "loss": 2.4539,
+      "step": 222
+    },
+    {
+      "epoch": 0.2862644415917843,
+      "grad_norm": 0.35880088806152344,
+      "learning_rate": 4.97950900071495e-05,
+      "loss": 2.3488,
+      "step": 223
+    },
+    {
+      "epoch": 0.28754813863928114,
+      "grad_norm": 0.30669230222702026,
+      "learning_rate": 4.9791749245421434e-05,
+      "loss": 2.4084,
+      "step": 224
+    },
+    {
+      "epoch": 0.2888318356867779,
+      "grad_norm": 0.34398922324180603,
+      "learning_rate": 4.9788381584193684e-05,
+      "loss": 2.3226,
+      "step": 225
+    },
+    {
+      "epoch": 0.2901155327342747,
+      "grad_norm": 0.3699093163013458,
+      "learning_rate": 4.9784987027120236e-05,
+      "loss": 2.3608,
+      "step": 226
+    },
+    {
+      "epoch": 0.2913992297817715,
+      "grad_norm": 0.3445926010608673,
+      "learning_rate": 4.978156557788424e-05,
+      "loss": 2.3771,
+      "step": 227
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.33999142050743103,
+      "learning_rate": 4.977811724019802e-05,
+      "loss": 2.3541,
+      "step": 228
+    },
+    {
+      "epoch": 0.2939666238767651,
+      "grad_norm": 0.3054107427597046,
+      "learning_rate": 4.9774642017803106e-05,
+      "loss": 2.4764,
+      "step": 229
+    },
+    {
+      "epoch": 0.2952503209242619,
+      "grad_norm": 0.3072315454483032,
+      "learning_rate": 4.977113991447017e-05,
+      "loss": 2.3055,
+      "step": 230
+    },
+    {
+      "epoch": 0.29653401797175866,
+      "grad_norm": 0.3254982531070709,
+      "learning_rate": 4.9767610933999055e-05,
+      "loss": 2.4659,
+      "step": 231
+    },
+    {
+      "epoch": 0.29781771501925547,
+      "grad_norm": 0.2930049002170563,
+      "learning_rate": 4.976405508021877e-05,
+      "loss": 2.3313,
+      "step": 232
+    },
+    {
+      "epoch": 0.2991014120667522,
+      "grad_norm": 0.30119720101356506,
+      "learning_rate": 4.976047235698747e-05,
+      "loss": 2.2981,
+      "step": 233
+    },
+    {
+      "epoch": 0.30038510911424904,
+      "grad_norm": 0.30038225650787354,
+      "learning_rate": 4.9756862768192504e-05,
+      "loss": 2.2864,
+      "step": 234
+    },
+    {
+      "epoch": 0.30166880616174585,
+      "grad_norm": 0.29573819041252136,
+      "learning_rate": 4.975322631775032e-05,
+      "loss": 2.3508,
+      "step": 235
+    },
+    {
+      "epoch": 0.3029525032092426,
+      "grad_norm": 0.316169798374176,
+      "learning_rate": 4.9749563009606534e-05,
+      "loss": 2.3648,
+      "step": 236
+    },
+    {
+      "epoch": 0.3042362002567394,
+      "grad_norm": 0.3109273910522461,
+      "learning_rate": 4.9745872847735894e-05,
+      "loss": 2.5141,
+      "step": 237
+    },
+    {
+      "epoch": 0.3055198973042362,
+      "grad_norm": 0.34613820910453796,
+      "learning_rate": 4.974215583614232e-05,
+      "loss": 2.333,
+      "step": 238
+    },
+    {
+      "epoch": 0.306803594351733,
+      "grad_norm": 0.34924328327178955,
+      "learning_rate": 4.9738411978858814e-05,
+      "loss": 2.4158,
+      "step": 239
+    },
+    {
+      "epoch": 0.3080872913992298,
+      "grad_norm": 0.2984835207462311,
+      "learning_rate": 4.9734641279947535e-05,
+      "loss": 2.3817,
+      "step": 240
+    },
+    {
+      "epoch": 0.30937098844672656,
+      "grad_norm": 0.3265876770019531,
+      "learning_rate": 4.9730843743499764e-05,
+      "loss": 2.4202,
+      "step": 241
+    },
+    {
+      "epoch": 0.31065468549422337,
+      "grad_norm": 0.31205374002456665,
+      "learning_rate": 4.9727019373635895e-05,
+      "loss": 2.3492,
+      "step": 242
+    },
+    {
+      "epoch": 0.3119383825417201,
+      "grad_norm": 0.3619811534881592,
+      "learning_rate": 4.972316817450544e-05,
+      "loss": 2.481,
+      "step": 243
+    },
+    {
+      "epoch": 0.31322207958921694,
+      "grad_norm": 0.4126303791999817,
+      "learning_rate": 4.9719290150287026e-05,
+      "loss": 2.2388,
+      "step": 244
+    },
+    {
+      "epoch": 0.31450577663671375,
+      "grad_norm": 0.34099090099334717,
+      "learning_rate": 4.971538530518836e-05,
+      "loss": 2.4,
+      "step": 245
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.32491570711135864,
+      "learning_rate": 4.971145364344628e-05,
+      "loss": 2.3854,
+      "step": 246
+    },
+    {
+      "epoch": 0.3170731707317073,
+      "grad_norm": 0.340457022190094,
+      "learning_rate": 4.970749516932672e-05,
+      "loss": 2.4011,
+      "step": 247
+    },
+    {
+      "epoch": 0.31835686777920413,
+      "grad_norm": 0.33701422810554504,
+      "learning_rate": 4.97035098871247e-05,
+      "loss": 2.4188,
+      "step": 248
+    },
+    {
+      "epoch": 0.3196405648267009,
+      "grad_norm": 0.3307265341281891,
+      "learning_rate": 4.969949780116431e-05,
+      "loss": 2.4553,
+      "step": 249
+    },
+    {
+      "epoch": 0.3209242618741977,
+      "grad_norm": 0.38966116309165955,
+      "learning_rate": 4.969545891579873e-05,
+      "loss": 2.3657,
+      "step": 250
+    },
+    {
+      "epoch": 0.32220795892169446,
+      "grad_norm": 0.36796143651008606,
+      "learning_rate": 4.969139323541025e-05,
+      "loss": 2.3044,
+      "step": 251
+    },
+    {
+      "epoch": 0.32349165596919127,
+      "grad_norm": 0.32584547996520996,
+      "learning_rate": 4.968730076441017e-05,
+      "loss": 2.4064,
+      "step": 252
+    },
+    {
+      "epoch": 0.3247753530166881,
+      "grad_norm": 0.3360714316368103,
+      "learning_rate": 4.968318150723893e-05,
+      "loss": 2.4243,
+      "step": 253
+    },
+    {
+      "epoch": 0.32605905006418484,
+      "grad_norm": 0.3058249056339264,
+      "learning_rate": 4.9679035468365986e-05,
+      "loss": 2.3598,
+      "step": 254
+    },
+    {
+      "epoch": 0.32734274711168165,
+      "grad_norm": 0.32182779908180237,
+      "learning_rate": 4.9674862652289865e-05,
+      "loss": 2.3469,
+      "step": 255
+    },
+    {
+      "epoch": 0.3286264441591784,
+      "grad_norm": 0.39011824131011963,
+      "learning_rate": 4.967066306353816e-05,
+      "loss": 2.4215,
+      "step": 256
+    },
+    {
+      "epoch": 0.3299101412066752,
+      "grad_norm": 0.3215901553630829,
+      "learning_rate": 4.966643670666748e-05,
+      "loss": 2.396,
+      "step": 257
+    },
+    {
+      "epoch": 0.33119383825417203,
+      "grad_norm": 0.3239218592643738,
+      "learning_rate": 4.9662183586263514e-05,
+      "loss": 2.4271,
+      "step": 258
+    },
+    {
+      "epoch": 0.3324775353016688,
+      "grad_norm": 0.33229637145996094,
+      "learning_rate": 4.965790370694097e-05,
+      "loss": 2.4345,
+      "step": 259
+    },
+    {
+      "epoch": 0.3337612323491656,
+      "grad_norm": 0.36766308546066284,
+      "learning_rate": 4.9653597073343594e-05,
+      "loss": 2.4257,
+      "step": 260
+    },
+    {
+      "epoch": 0.33504492939666236,
+      "grad_norm": 0.33887600898742676,
+      "learning_rate": 4.964926369014417e-05,
+      "loss": 2.4391,
+      "step": 261
+    },
+    {
+      "epoch": 0.3363286264441592,
+      "grad_norm": 0.3224686086177826,
+      "learning_rate": 4.964490356204449e-05,
+      "loss": 2.3664,
+      "step": 262
+    },
+    {
+      "epoch": 0.337612323491656,
+      "grad_norm": 0.3371565341949463,
+      "learning_rate": 4.964051669377538e-05,
+      "loss": 2.4992,
+      "step": 263
+    },
+    {
+      "epoch": 0.33889602053915274,
+      "grad_norm": 0.3373253345489502,
+      "learning_rate": 4.963610309009665e-05,
+      "loss": 2.3509,
+      "step": 264
+    },
+    {
+      "epoch": 0.34017971758664955,
+      "grad_norm": 0.34519249200820923,
+      "learning_rate": 4.963166275579717e-05,
+      "loss": 2.4388,
+      "step": 265
+    },
+    {
+      "epoch": 0.34146341463414637,
+      "grad_norm": 0.3187866806983948,
+      "learning_rate": 4.9627195695694774e-05,
+      "loss": 2.4655,
+      "step": 266
+    },
+    {
+      "epoch": 0.3427471116816431,
+      "grad_norm": 0.31844937801361084,
+      "learning_rate": 4.962270191463629e-05,
+      "loss": 2.4097,
+      "step": 267
+    },
+    {
+      "epoch": 0.34403080872913994,
+      "grad_norm": 0.359625905752182,
+      "learning_rate": 4.9618181417497566e-05,
+      "loss": 2.4364,
+      "step": 268
+    },
+    {
+      "epoch": 0.3453145057766367,
+      "grad_norm": 0.3335789740085602,
+      "learning_rate": 4.961363420918342e-05,
+      "loss": 2.2316,
+      "step": 269
+    },
+    {
+      "epoch": 0.3465982028241335,
+      "grad_norm": 0.3209823668003082,
+      "learning_rate": 4.960906029462766e-05,
+      "loss": 2.4698,
+      "step": 270
+    },
+    {
+      "epoch": 0.3478818998716303,
+      "grad_norm": 0.3264525532722473,
+      "learning_rate": 4.960445967879307e-05,
+      "loss": 2.3222,
+      "step": 271
+    },
+    {
+      "epoch": 0.3491655969191271,
+      "grad_norm": 0.29652708768844604,
+      "learning_rate": 4.959983236667138e-05,
+      "loss": 2.3258,
+      "step": 272
+    },
+    {
+      "epoch": 0.3504492939666239,
+      "grad_norm": 0.35058003664016724,
+      "learning_rate": 4.959517836328333e-05,
+      "loss": 2.3009,
+      "step": 273
+    },
+    {
+      "epoch": 0.35173299101412064,
+      "grad_norm": 0.29893478751182556,
+      "learning_rate": 4.959049767367859e-05,
+      "loss": 2.463,
+      "step": 274
+    },
+    {
+      "epoch": 0.35301668806161746,
+      "grad_norm": 0.3114057183265686,
+      "learning_rate": 4.95857903029358e-05,
+      "loss": 2.2757,
+      "step": 275
+    },
+    {
+      "epoch": 0.35430038510911427,
+      "grad_norm": 0.3837164640426636,
+      "learning_rate": 4.958105625616253e-05,
+      "loss": 2.445,
+      "step": 276
+    },
+    {
+      "epoch": 0.355584082156611,
+      "grad_norm": 0.3195387125015259,
+      "learning_rate": 4.957629553849532e-05,
+      "loss": 2.4823,
+      "step": 277
+    },
+    {
+      "epoch": 0.35686777920410784,
+      "grad_norm": 0.37014302611351013,
+      "learning_rate": 4.957150815509963e-05,
+      "loss": 2.3322,
+      "step": 278
+    },
+    {
+      "epoch": 0.3581514762516046,
+      "grad_norm": 0.28935369849205017,
+      "learning_rate": 4.9566694111169853e-05,
+      "loss": 2.4336,
+      "step": 279
+    },
+    {
+      "epoch": 0.3594351732991014,
+      "grad_norm": 0.3155868351459503,
+      "learning_rate": 4.956185341192933e-05,
+      "loss": 2.4691,
+      "step": 280
+    },
+    {
+      "epoch": 0.3607188703465982,
+      "grad_norm": 0.33008038997650146,
+      "learning_rate": 4.955698606263028e-05,
+      "loss": 2.3331,
+      "step": 281
+    },
+    {
+      "epoch": 0.362002567394095,
+      "grad_norm": 0.3546096086502075,
+      "learning_rate": 4.95520920685539e-05,
+      "loss": 2.4626,
+      "step": 282
+    },
+    {
+      "epoch": 0.3632862644415918,
+      "grad_norm": 0.3569015562534332,
+      "learning_rate": 4.954717143501024e-05,
+      "loss": 2.4165,
+      "step": 283
+    },
+    {
+      "epoch": 0.3645699614890886,
+      "grad_norm": 0.2979843318462372,
+      "learning_rate": 4.954222416733829e-05,
+      "loss": 2.3322,
+      "step": 284
+    },
+    {
+      "epoch": 0.36585365853658536,
+      "grad_norm": 0.43857890367507935,
+      "learning_rate": 4.953725027090591e-05,
+      "loss": 2.3168,
+      "step": 285
+    },
+    {
+      "epoch": 0.36713735558408217,
+      "grad_norm": 0.32624951004981995,
+      "learning_rate": 4.953224975110988e-05,
+      "loss": 2.3685,
+      "step": 286
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.3195008933544159,
+      "learning_rate": 4.9527222613375855e-05,
+      "loss": 2.4137,
+      "step": 287
+    },
+    {
+      "epoch": 0.36970474967907574,
+      "grad_norm": 0.362567663192749,
+      "learning_rate": 4.952216886315837e-05,
+      "loss": 2.2978,
+      "step": 288
+    },
+    {
+      "epoch": 0.37098844672657255,
+      "grad_norm": 0.31306540966033936,
+      "learning_rate": 4.951708850594083e-05,
+      "loss": 2.4381,
+      "step": 289
+    },
+    {
+      "epoch": 0.3722721437740693,
+      "grad_norm": 0.3275150954723358,
+      "learning_rate": 4.951198154723552e-05,
+      "loss": 2.3528,
+      "step": 290
+    },
+    {
+      "epoch": 0.3735558408215661,
+      "grad_norm": 0.32541584968566895,
+      "learning_rate": 4.9506847992583586e-05,
+      "loss": 2.5023,
+      "step": 291
+    },
+    {
+      "epoch": 0.3748395378690629,
+      "grad_norm": 0.3278298079967499,
+      "learning_rate": 4.9501687847555016e-05,
+      "loss": 2.3745,
+      "step": 292
+    },
+    {
+      "epoch": 0.3761232349165597,
+      "grad_norm": 0.3163221776485443,
+      "learning_rate": 4.949650111774868e-05,
+      "loss": 2.3451,
+      "step": 293
+    },
+    {
+      "epoch": 0.3774069319640565,
+      "grad_norm": 0.30997052788734436,
+      "learning_rate": 4.9491287808792265e-05,
+      "loss": 2.3976,
+      "step": 294
+    },
+    {
+      "epoch": 0.37869062901155326,
+      "grad_norm": 0.3496086597442627,
+      "learning_rate": 4.948604792634229e-05,
+      "loss": 2.4361,
+      "step": 295
+    },
+    {
+      "epoch": 0.37997432605905007,
+      "grad_norm": 0.3483693599700928,
+      "learning_rate": 4.948078147608416e-05,
+      "loss": 2.4022,
+      "step": 296
+    },
+    {
+      "epoch": 0.38125802310654683,
+      "grad_norm": 0.3135087490081787,
+      "learning_rate": 4.947548846373204e-05,
+      "loss": 2.3585,
+      "step": 297
+    },
+    {
+      "epoch": 0.38254172015404364,
+      "grad_norm": 0.323482871055603,
+      "learning_rate": 4.947016889502895e-05,
+      "loss": 2.3958,
+      "step": 298
+    },
+    {
+      "epoch": 0.38382541720154045,
+      "grad_norm": 0.3020581901073456,
+      "learning_rate": 4.946482277574673e-05,
+      "loss": 2.2809,
+      "step": 299
+    },
+    {
+      "epoch": 0.3851091142490372,
+      "grad_norm": 0.31288352608680725,
+      "learning_rate": 4.9459450111686e-05,
+      "loss": 2.3526,
+      "step": 300
+    },
+    {
+      "epoch": 0.386392811296534,
+      "grad_norm": 0.31495004892349243,
+      "learning_rate": 4.945405090867621e-05,
+      "loss": 2.4462,
+      "step": 301
+    },
+    {
+      "epoch": 0.38767650834403083,
+      "grad_norm": 0.3513999581336975,
+      "learning_rate": 4.94486251725756e-05,
+      "loss": 2.3795,
+      "step": 302
+    },
+    {
+      "epoch": 0.3889602053915276,
+      "grad_norm": 0.33559510111808777,
+      "learning_rate": 4.944317290927117e-05,
+      "loss": 2.3002,
+      "step": 303
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.3153408467769623,
+      "learning_rate": 4.943769412467875e-05,
+      "loss": 2.437,
+      "step": 304
+    },
+    {
+      "epoch": 0.39152759948652116,
+      "grad_norm": 0.3177226781845093,
+      "learning_rate": 4.943218882474291e-05,
+      "loss": 2.3447,
+      "step": 305
+    },
+    {
+      "epoch": 0.392811296534018,
+      "grad_norm": 0.3815303146839142,
+      "learning_rate": 4.9426657015436994e-05,
+      "loss": 2.3584,
+      "step": 306
+    },
+    {
+      "epoch": 0.3940949935815148,
+      "grad_norm": 0.34336403012275696,
+      "learning_rate": 4.9421098702763126e-05,
+      "loss": 2.2979,
+      "step": 307
+    },
+    {
+      "epoch": 0.39537869062901154,
+      "grad_norm": 0.33281055092811584,
+      "learning_rate": 4.941551389275217e-05,
+      "loss": 2.4152,
+      "step": 308
+    },
+    {
+      "epoch": 0.39666238767650835,
+      "grad_norm": 0.3309512138366699,
+      "learning_rate": 4.9409902591463756e-05,
+      "loss": 2.361,
+      "step": 309
+    },
+    {
+      "epoch": 0.3979460847240051,
+      "grad_norm": 0.3044840097427368,
+      "learning_rate": 4.940426480498623e-05,
+      "loss": 2.3172,
+      "step": 310
+    },
+    {
+      "epoch": 0.3992297817715019,
+      "grad_norm": 0.32050418853759766,
+      "learning_rate": 4.939860053943671e-05,
+      "loss": 2.374,
+      "step": 311
+    },
+    {
+      "epoch": 0.40051347881899874,
+      "grad_norm": 0.36678293347358704,
+      "learning_rate": 4.939290980096103e-05,
+      "loss": 2.3529,
+      "step": 312
+    },
+    {
+      "epoch": 0.4017971758664955,
+      "grad_norm": 0.32348355650901794,
+      "learning_rate": 4.9387192595733734e-05,
+      "loss": 2.4048,
+      "step": 313
+    },
+    {
+      "epoch": 0.4030808729139923,
+      "grad_norm": 0.3086166977882385,
+      "learning_rate": 4.938144892995809e-05,
+      "loss": 2.4091,
+      "step": 314
+    },
+    {
+      "epoch": 0.40436456996148906,
+      "grad_norm": 0.31869277358055115,
+      "learning_rate": 4.937567880986609e-05,
+      "loss": 2.3594,
+      "step": 315
+    },
+    {
+      "epoch": 0.4056482670089859,
+      "grad_norm": 0.317147821187973,
+      "learning_rate": 4.936988224171842e-05,
+      "loss": 2.2666,
+      "step": 316
+    },
+    {
+      "epoch": 0.4069319640564827,
+      "grad_norm": 0.32587262988090515,
+      "learning_rate": 4.936405923180446e-05,
+      "loss": 2.317,
+      "step": 317
+    },
+    {
+      "epoch": 0.40821566110397944,
+      "grad_norm": 0.3181535005569458,
+      "learning_rate": 4.935820978644228e-05,
+      "loss": 2.3611,
+      "step": 318
+    },
+    {
+      "epoch": 0.40949935815147626,
+      "grad_norm": 0.31699231266975403,
+      "learning_rate": 4.9352333911978625e-05,
+      "loss": 2.4676,
+      "step": 319
+    },
+    {
+      "epoch": 0.41078305519897307,
+      "grad_norm": 0.35386183857917786,
+      "learning_rate": 4.9346431614788945e-05,
+      "loss": 2.3525,
+      "step": 320
+    },
+    {
+      "epoch": 0.4120667522464698,
+      "grad_norm": 0.3134053647518158,
+      "learning_rate": 4.934050290127733e-05,
+      "loss": 2.4045,
+      "step": 321
+    },
+    {
+      "epoch": 0.41335044929396664,
+      "grad_norm": 0.3209103047847748,
+      "learning_rate": 4.933454777787654e-05,
+      "loss": 2.3606,
+      "step": 322
+    },
+    {
+      "epoch": 0.4146341463414634,
+      "grad_norm": 0.3191809356212616,
+      "learning_rate": 4.9328566251048e-05,
+      "loss": 2.4551,
+      "step": 323
+    },
+    {
+      "epoch": 0.4159178433889602,
+      "grad_norm": 0.2983877658843994,
+      "learning_rate": 4.9322558327281773e-05,
+      "loss": 2.3299,
+      "step": 324
+    },
+    {
+      "epoch": 0.417201540436457,
+      "grad_norm": 0.3376917541027069,
+      "learning_rate": 4.931652401309655e-05,
+      "loss": 2.3599,
+      "step": 325
+    },
+    {
+      "epoch": 0.4184852374839538,
+      "grad_norm": 0.36222752928733826,
+      "learning_rate": 4.93104633150397e-05,
+      "loss": 2.4432,
+      "step": 326
+    },
+    {
+      "epoch": 0.4197689345314506,
+      "grad_norm": 0.2962850034236908,
+      "learning_rate": 4.930437623968718e-05,
+      "loss": 2.3965,
+      "step": 327
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.32738175988197327,
+      "learning_rate": 4.929826279364357e-05,
+      "loss": 2.3276,
+      "step": 328
+    },
+    {
+      "epoch": 0.42233632862644416,
+      "grad_norm": 0.3119535446166992,
+      "learning_rate": 4.929212298354207e-05,
+      "loss": 2.3639,
+      "step": 329
+    },
+    {
+      "epoch": 0.42362002567394097,
+      "grad_norm": 0.3193548321723938,
+      "learning_rate": 4.9285956816044486e-05,
+      "loss": 2.4468,
+      "step": 330
+    },
+    {
+      "epoch": 0.4249037227214377,
+      "grad_norm": 0.32102808356285095,
+      "learning_rate": 4.927976429784124e-05,
+      "loss": 2.422,
+      "step": 331
+    },
+    {
+      "epoch": 0.42618741976893454,
+      "grad_norm": 0.3115790784358978,
+      "learning_rate": 4.92735454356513e-05,
+      "loss": 2.2948,
+      "step": 332
+    },
+    {
+      "epoch": 0.4274711168164313,
+      "grad_norm": 0.320351243019104,
+      "learning_rate": 4.926730023622227e-05,
+      "loss": 2.3466,
+      "step": 333
+    },
+    {
+      "epoch": 0.4287548138639281,
+      "grad_norm": 0.30213356018066406,
+      "learning_rate": 4.926102870633029e-05,
+      "loss": 2.3773,
+      "step": 334
+    },
+    {
+      "epoch": 0.4300385109114249,
+      "grad_norm": 0.3080739676952362,
+      "learning_rate": 4.925473085278008e-05,
+      "loss": 2.3822,
+      "step": 335
+    },
+    {
+      "epoch": 0.4313222079589217,
+      "grad_norm": 0.3327421545982361,
+      "learning_rate": 4.924840668240495e-05,
+      "loss": 2.4326,
+      "step": 336
+    },
+    {
+      "epoch": 0.4326059050064185,
+      "grad_norm": 0.34913370013237,
+      "learning_rate": 4.924205620206671e-05,
+      "loss": 2.4491,
+      "step": 337
+    },
+    {
+      "epoch": 0.4338896020539153,
+      "grad_norm": 0.3061310946941376,
+      "learning_rate": 4.923567941865577e-05,
+      "loss": 2.3727,
+      "step": 338
+    },
+    {
+      "epoch": 0.43517329910141206,
+      "grad_norm": 0.3259632885456085,
+      "learning_rate": 4.9229276339091034e-05,
+      "loss": 2.3775,
+      "step": 339
+    },
+    {
+      "epoch": 0.43645699614890887,
+      "grad_norm": 0.29085099697113037,
+      "learning_rate": 4.922284697031999e-05,
+      "loss": 2.3427,
+      "step": 340
+    },
+    {
+      "epoch": 0.43774069319640563,
+      "grad_norm": 0.30840590596199036,
+      "learning_rate": 4.921639131931859e-05,
+      "loss": 2.367,
+      "step": 341
+    },
+    {
+      "epoch": 0.43902439024390244,
+      "grad_norm": 0.32114389538764954,
+      "learning_rate": 4.920990939309135e-05,
+      "loss": 2.4625,
+      "step": 342
+    },
+    {
+      "epoch": 0.44030808729139925,
+      "grad_norm": 0.3091549873352051,
+      "learning_rate": 4.920340119867127e-05,
+      "loss": 2.3571,
+      "step": 343
+    },
+    {
+      "epoch": 0.441591784338896,
+      "grad_norm": 0.2978641092777252,
+      "learning_rate": 4.919686674311987e-05,
+      "loss": 2.3033,
+      "step": 344
+    },
+    {
+      "epoch": 0.4428754813863928,
+      "grad_norm": 0.33106520771980286,
+      "learning_rate": 4.919030603352715e-05,
+      "loss": 2.3276,
+      "step": 345
+    },
+    {
+      "epoch": 0.4441591784338896,
+      "grad_norm": 0.42283540964126587,
+      "learning_rate": 4.918371907701159e-05,
+      "loss": 2.3563,
+      "step": 346
+    },
+    {
+      "epoch": 0.4454428754813864,
+      "grad_norm": 0.32727953791618347,
+      "learning_rate": 4.9177105880720173e-05,
+      "loss": 2.3928,
+      "step": 347
+    },
+    {
+      "epoch": 0.4467265725288832,
+      "grad_norm": 0.3086586892604828,
+      "learning_rate": 4.9170466451828326e-05,
+      "loss": 2.2707,
+      "step": 348
+    },
+    {
+      "epoch": 0.44801026957637996,
+      "grad_norm": 0.28993648290634155,
+      "learning_rate": 4.916380079753995e-05,
+      "loss": 2.3582,
+      "step": 349
+    },
+    {
+      "epoch": 0.4492939666238768,
+      "grad_norm": 0.3154331147670746,
+      "learning_rate": 4.9157108925087405e-05,
+      "loss": 2.4003,
+      "step": 350
+    },
+    {
+      "epoch": 0.45057766367137353,
+      "grad_norm": 0.3312948942184448,
+      "learning_rate": 4.9150390841731485e-05,
+      "loss": 2.3955,
+      "step": 351
+    },
+    {
+      "epoch": 0.45186136071887034,
+      "grad_norm": 0.30381128191947937,
+      "learning_rate": 4.914364655476146e-05,
+      "loss": 2.3737,
+      "step": 352
+    },
+    {
+      "epoch": 0.45314505776636715,
+      "grad_norm": 0.30618736147880554,
+      "learning_rate": 4.9136876071494976e-05,
+      "loss": 2.3602,
+      "step": 353
+    },
+    {
+      "epoch": 0.4544287548138639,
+      "grad_norm": 0.3091343343257904,
+      "learning_rate": 4.913007939927814e-05,
+      "loss": 2.4564,
+      "step": 354
+    },
+    {
+      "epoch": 0.4557124518613607,
+      "grad_norm": 0.311162531375885,
+      "learning_rate": 4.912325654548546e-05,
+      "loss": 2.3133,
+      "step": 355
+    },
+    {
+      "epoch": 0.45699614890885754,
+      "grad_norm": 0.33965715765953064,
+      "learning_rate": 4.911640751751988e-05,
+      "loss": 2.4312,
+      "step": 356
+    },
+    {
+      "epoch": 0.4582798459563543,
+      "grad_norm": 0.3162749111652374,
+      "learning_rate": 4.910953232281269e-05,
+      "loss": 2.3438,
+      "step": 357
+    },
+    {
+      "epoch": 0.4595635430038511,
+      "grad_norm": 0.32984068989753723,
+      "learning_rate": 4.910263096882362e-05,
+      "loss": 2.3823,
+      "step": 358
+    },
+    {
+      "epoch": 0.46084724005134786,
+      "grad_norm": 0.30816513299942017,
+      "learning_rate": 4.909570346304076e-05,
+      "loss": 2.445,
+      "step": 359
+    },
+    {
+      "epoch": 0.4621309370988447,
+      "grad_norm": 0.2928940951824188,
+      "learning_rate": 4.908874981298057e-05,
+      "loss": 2.4538,
+      "step": 360
+    },
+    {
+      "epoch": 0.4634146341463415,
+      "grad_norm": 0.32563963532447815,
+      "learning_rate": 4.9081770026187914e-05,
+      "loss": 2.292,
+      "step": 361
+    },
+    {
+      "epoch": 0.46469833119383824,
+      "grad_norm": 0.29584982991218567,
+      "learning_rate": 4.907476411023596e-05,
+      "loss": 2.4046,
+      "step": 362
+    },
+    {
+      "epoch": 0.46598202824133506,
+      "grad_norm": 0.3291500210762024,
+      "learning_rate": 4.906773207272626e-05,
+      "loss": 2.3186,
+      "step": 363
+    },
+    {
+      "epoch": 0.4672657252888318,
+      "grad_norm": 0.3066290020942688,
+      "learning_rate": 4.9060673921288716e-05,
+      "loss": 2.3266,
+      "step": 364
+    },
+    {
+      "epoch": 0.4685494223363286,
+      "grad_norm": 0.3005695939064026,
+      "learning_rate": 4.905358966358153e-05,
+      "loss": 2.3712,
+      "step": 365
+    },
+    {
+      "epoch": 0.46983311938382544,
+      "grad_norm": 0.32391899824142456,
+      "learning_rate": 4.904647930729128e-05,
+      "loss": 2.3514,
+      "step": 366
+    },
+    {
+      "epoch": 0.4711168164313222,
+      "grad_norm": 0.2915700078010559,
+      "learning_rate": 4.903934286013281e-05,
+      "loss": 2.4646,
+      "step": 367
+    },
+    {
+      "epoch": 0.472400513478819,
+      "grad_norm": 0.34920045733451843,
+      "learning_rate": 4.90321803298493e-05,
+      "loss": 2.3287,
+      "step": 368
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.2955242395401001,
+      "learning_rate": 4.902499172421222e-05,
+      "loss": 2.3654,
+      "step": 369
+    },
+    {
+      "epoch": 0.4749679075738126,
+      "grad_norm": 0.3305751085281372,
+      "learning_rate": 4.901777705102135e-05,
+      "loss": 2.4419,
+      "step": 370
+    },
+    {
+      "epoch": 0.4762516046213094,
+      "grad_norm": 0.30396509170532227,
+      "learning_rate": 4.9010536318104734e-05,
+      "loss": 2.3576,
+      "step": 371
+    },
+    {
+      "epoch": 0.47753530166880614,
+      "grad_norm": 0.2961418330669403,
+      "learning_rate": 4.9003269533318704e-05,
+      "loss": 2.3039,
+      "step": 372
+    },
+    {
+      "epoch": 0.47881899871630296,
+      "grad_norm": 0.35183992981910706,
+      "learning_rate": 4.899597670454785e-05,
+      "loss": 2.3333,
+      "step": 373
+    },
+    {
+      "epoch": 0.48010269576379977,
+      "grad_norm": 0.297158420085907,
+      "learning_rate": 4.8988657839705024e-05,
+      "loss": 2.3514,
+      "step": 374
+    },
+    {
+      "epoch": 0.4813863928112965,
+      "grad_norm": 0.3379060626029968,
+      "learning_rate": 4.8981312946731325e-05,
+      "loss": 2.2811,
+      "step": 375
+    },
+    {
+      "epoch": 0.48267008985879334,
+      "grad_norm": 0.34060969948768616,
+      "learning_rate": 4.897394203359611e-05,
+      "loss": 2.4123,
+      "step": 376
+    },
+    {
+      "epoch": 0.4839537869062901,
+      "grad_norm": 0.3308861255645752,
+      "learning_rate": 4.896654510829694e-05,
+      "loss": 2.4262,
+      "step": 377
+    },
+    {
+      "epoch": 0.4852374839537869,
+      "grad_norm": 0.3043263852596283,
+      "learning_rate": 4.8959122178859616e-05,
+      "loss": 2.4291,
+      "step": 378
+    },
+    {
+      "epoch": 0.4865211810012837,
+      "grad_norm": 0.32594412565231323,
+      "learning_rate": 4.8951673253338156e-05,
+      "loss": 2.3679,
+      "step": 379
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.3090050220489502,
+      "learning_rate": 4.894419833981478e-05,
+      "loss": 2.3933,
+      "step": 380
+    },
+    {
+      "epoch": 0.4890885750962773,
+      "grad_norm": 0.3234407901763916,
+      "learning_rate": 4.8936697446399896e-05,
+      "loss": 2.3156,
+      "step": 381
+    },
+    {
+      "epoch": 0.49037227214377405,
+      "grad_norm": 0.3294239938259125,
+      "learning_rate": 4.892917058123212e-05,
+      "loss": 2.357,
+      "step": 382
+    },
+    {
+      "epoch": 0.49165596919127086,
+      "grad_norm": 0.33215636014938354,
+      "learning_rate": 4.8921617752478235e-05,
+      "loss": 2.4386,
+      "step": 383
+    },
+    {
+      "epoch": 0.49293966623876767,
+      "grad_norm": 0.30511781573295593,
+      "learning_rate": 4.89140389683332e-05,
+      "loss": 2.4283,
+      "step": 384
+    },
+    {
+      "epoch": 0.4942233632862644,
+      "grad_norm": 0.31070634722709656,
+      "learning_rate": 4.890643423702013e-05,
+      "loss": 2.3565,
+      "step": 385
+    },
+    {
+      "epoch": 0.49550706033376124,
+      "grad_norm": 0.3108975291252136,
+      "learning_rate": 4.8898803566790296e-05,
+      "loss": 2.3209,
+      "step": 386
+    },
+    {
+      "epoch": 0.496790757381258,
+      "grad_norm": 0.31348085403442383,
+      "learning_rate": 4.889114696592312e-05,
+      "loss": 2.3707,
+      "step": 387
+    },
+    {
+      "epoch": 0.4980744544287548,
+      "grad_norm": 0.3120376467704773,
+      "learning_rate": 4.8883464442726146e-05,
+      "loss": 2.3743,
+      "step": 388
+    },
+    {
+      "epoch": 0.4993581514762516,
+      "grad_norm": 0.3120869994163513,
+      "learning_rate": 4.887575600553506e-05,
+      "loss": 2.3501,
+      "step": 389
+    },
+    {
+      "epoch": 0.5006418485237484,
+      "grad_norm": 0.28657200932502747,
+      "learning_rate": 4.886802166271364e-05,
+      "loss": 2.365,
+      "step": 390
+    },
+    {
+      "epoch": 0.5019255455712451,
+      "grad_norm": 0.3038496971130371,
+      "learning_rate": 4.886026142265381e-05,
+      "loss": 2.3851,
+      "step": 391
+    },
+    {
+      "epoch": 0.503209242618742,
+      "grad_norm": 0.3245856761932373,
+      "learning_rate": 4.885247529377557e-05,
+      "loss": 2.3996,
+      "step": 392
+    },
+    {
+      "epoch": 0.5044929396662388,
+      "grad_norm": 0.2905268669128418,
+      "learning_rate": 4.8844663284526995e-05,
+      "loss": 2.4106,
+      "step": 393
+    },
+    {
+      "epoch": 0.5057766367137355,
+      "grad_norm": 0.3151610195636749,
+      "learning_rate": 4.883682540338428e-05,
+      "loss": 2.3665,
+      "step": 394
+    },
+    {
+      "epoch": 0.5070603337612324,
+      "grad_norm": 0.3045148253440857,
+      "learning_rate": 4.8828961658851645e-05,
+      "loss": 2.3244,
+      "step": 395
+    },
+    {
+      "epoch": 0.5083440308087291,
+      "grad_norm": 0.33118733763694763,
+      "learning_rate": 4.882107205946142e-05,
+      "loss": 2.3622,
+      "step": 396
+    },
+    {
+      "epoch": 0.5096277278562259,
+      "grad_norm": 0.3078731596469879,
+      "learning_rate": 4.881315661377393e-05,
+      "loss": 2.325,
+      "step": 397
+    },
+    {
+      "epoch": 0.5109114249037228,
+      "grad_norm": 0.33527669310569763,
+      "learning_rate": 4.880521533037762e-05,
+      "loss": 2.4234,
+      "step": 398
+    },
+    {
+      "epoch": 0.5121951219512195,
+      "grad_norm": 0.32107025384902954,
+      "learning_rate": 4.879724821788889e-05,
+      "loss": 2.2833,
+      "step": 399
+    },
+    {
+      "epoch": 0.5134788189987163,
+      "grad_norm": 0.31819841265678406,
+      "learning_rate": 4.878925528495223e-05,
+      "loss": 2.4178,
+      "step": 400
+    },
+    {
+      "epoch": 0.5147625160462131,
+      "grad_norm": 0.31981033086776733,
+      "learning_rate": 4.8781236540240106e-05,
+      "loss": 2.4154,
+      "step": 401
+    },
+    {
+      "epoch": 0.5160462130937099,
+      "grad_norm": 0.39689508080482483,
+      "learning_rate": 4.8773191992453e-05,
+      "loss": 2.3759,
+      "step": 402
+    },
+    {
+      "epoch": 0.5173299101412067,
+      "grad_norm": 0.3065798282623291,
+      "learning_rate": 4.876512165031939e-05,
+      "loss": 2.4322,
+      "step": 403
+    },
+    {
+      "epoch": 0.5186136071887034,
+      "grad_norm": 0.3112392723560333,
+      "learning_rate": 4.8757025522595756e-05,
+      "loss": 2.3008,
+      "step": 404
+    },
+    {
+      "epoch": 0.5198973042362003,
+      "grad_norm": 0.3170951008796692,
+      "learning_rate": 4.874890361806654e-05,
+      "loss": 2.3265,
+      "step": 405
+    },
+    {
+      "epoch": 0.521181001283697,
+      "grad_norm": 0.32137608528137207,
+      "learning_rate": 4.8740755945544156e-05,
+      "loss": 2.4448,
+      "step": 406
+    },
+    {
+      "epoch": 0.5224646983311938,
+      "grad_norm": 0.32462355494499207,
+      "learning_rate": 4.873258251386897e-05,
+      "loss": 2.3504,
+      "step": 407
+    },
+    {
+      "epoch": 0.5237483953786907,
+      "grad_norm": 0.32057517766952515,
+      "learning_rate": 4.872438333190931e-05,
+      "loss": 2.4223,
+      "step": 408
+    },
+    {
+      "epoch": 0.5250320924261874,
+      "grad_norm": 0.3375895917415619,
+      "learning_rate": 4.871615840856144e-05,
+      "loss": 2.3912,
+      "step": 409
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.29747098684310913,
+      "learning_rate": 4.870790775274955e-05,
+      "loss": 2.3684,
+      "step": 410
+    },
+    {
+      "epoch": 0.527599486521181,
+      "grad_norm": 0.31433284282684326,
+      "learning_rate": 4.8699631373425746e-05,
+      "loss": 2.4619,
+      "step": 411
+    },
+    {
+      "epoch": 0.5288831835686778,
+      "grad_norm": 0.31316566467285156,
+      "learning_rate": 4.869132927957007e-05,
+      "loss": 2.45,
+      "step": 412
+    },
+    {
+      "epoch": 0.5301668806161746,
+      "grad_norm": 0.29028958082199097,
+      "learning_rate": 4.8683001480190415e-05,
+      "loss": 2.3539,
+      "step": 413
+    },
+    {
+      "epoch": 0.5314505776636713,
+      "grad_norm": 0.32501766085624695,
+      "learning_rate": 4.867464798432262e-05,
+      "loss": 2.4104,
+      "step": 414
+    },
+    {
+      "epoch": 0.5327342747111682,
+      "grad_norm": 0.31315121054649353,
+      "learning_rate": 4.866626880103036e-05,
+      "loss": 2.4346,
+      "step": 415
+    },
+    {
+      "epoch": 0.5340179717586649,
+      "grad_norm": 0.30741140246391296,
+      "learning_rate": 4.865786393940522e-05,
+      "loss": 2.3253,
+      "step": 416
+    },
+    {
+      "epoch": 0.5353016688061617,
+      "grad_norm": 0.3042595684528351,
+      "learning_rate": 4.8649433408566626e-05,
+      "loss": 2.4107,
+      "step": 417
+    },
+    {
+      "epoch": 0.5365853658536586,
+      "grad_norm": 0.3254822790622711,
+      "learning_rate": 4.864097721766184e-05,
+      "loss": 2.368,
+      "step": 418
+    },
+    {
+      "epoch": 0.5378690629011553,
+      "grad_norm": 0.3164546489715576,
+      "learning_rate": 4.8632495375866004e-05,
+      "loss": 2.3493,
+      "step": 419
+    },
+    {
+      "epoch": 0.5391527599486521,
+      "grad_norm": 0.30588898062705994,
+      "learning_rate": 4.8623987892382066e-05,
+      "loss": 2.3751,
+      "step": 420
+    },
+    {
+      "epoch": 0.540436456996149,
+      "grad_norm": 0.3062260150909424,
+      "learning_rate": 4.861545477644079e-05,
+      "loss": 2.3137,
+      "step": 421
+    },
+    {
+      "epoch": 0.5417201540436457,
+      "grad_norm": 0.3363398611545563,
+      "learning_rate": 4.8606896037300776e-05,
+      "loss": 2.3326,
+      "step": 422
+    },
+    {
+      "epoch": 0.5430038510911425,
+      "grad_norm": 0.33340004086494446,
+      "learning_rate": 4.8598311684248396e-05,
+      "loss": 2.3511,
+      "step": 423
+    },
+    {
+      "epoch": 0.5442875481386393,
+      "grad_norm": 0.2808108329772949,
+      "learning_rate": 4.858970172659785e-05,
+      "loss": 2.4589,
+      "step": 424
+    },
+    {
+      "epoch": 0.5455712451861361,
+      "grad_norm": 0.299396276473999,
+      "learning_rate": 4.8581066173691074e-05,
+      "loss": 2.3481,
+      "step": 425
+    },
+    {
+      "epoch": 0.5468549422336328,
+      "grad_norm": 0.3083891272544861,
+      "learning_rate": 4.857240503489782e-05,
+      "loss": 2.2812,
+      "step": 426
+    },
+    {
+      "epoch": 0.5481386392811296,
+      "grad_norm": 0.3224524259567261,
+      "learning_rate": 4.8563718319615584e-05,
+      "loss": 2.2938,
+      "step": 427
+    },
+    {
+      "epoch": 0.5494223363286265,
+      "grad_norm": 0.2835102379322052,
+      "learning_rate": 4.8555006037269594e-05,
+      "loss": 2.3401,
+      "step": 428
+    },
+    {
+      "epoch": 0.5507060333761232,
+      "grad_norm": 0.28240859508514404,
+      "learning_rate": 4.854626819731284e-05,
+      "loss": 2.4238,
+      "step": 429
+    },
+    {
+      "epoch": 0.55198973042362,
+      "grad_norm": 0.28541532158851624,
+      "learning_rate": 4.853750480922604e-05,
+      "loss": 2.36,
+      "step": 430
+    },
+    {
+      "epoch": 0.5532734274711169,
+      "grad_norm": 0.3530977666378021,
+      "learning_rate": 4.852871588251763e-05,
+      "loss": 2.3936,
+      "step": 431
+    },
+    {
+      "epoch": 0.5545571245186136,
+      "grad_norm": 0.3233661949634552,
+      "learning_rate": 4.851990142672376e-05,
+      "loss": 2.3921,
+      "step": 432
+    },
+    {
+      "epoch": 0.5558408215661104,
+      "grad_norm": 0.34146299958229065,
+      "learning_rate": 4.851106145140827e-05,
+      "loss": 2.4632,
+      "step": 433
+    },
+    {
+      "epoch": 0.5571245186136072,
+      "grad_norm": 0.3273311257362366,
+      "learning_rate": 4.8502195966162694e-05,
+      "loss": 2.3328,
+      "step": 434
+    },
+    {
+      "epoch": 0.558408215661104,
+      "grad_norm": 0.29606807231903076,
+      "learning_rate": 4.8493304980606245e-05,
+      "loss": 2.3077,
+      "step": 435
+    },
+    {
+      "epoch": 0.5596919127086007,
+      "grad_norm": 0.2943183481693268,
+      "learning_rate": 4.8484388504385806e-05,
+      "loss": 2.3786,
+      "step": 436
+    },
+    {
+      "epoch": 0.5609756097560976,
+      "grad_norm": 0.29871752858161926,
+      "learning_rate": 4.847544654717592e-05,
+      "loss": 2.3262,
+      "step": 437
+    },
+    {
+      "epoch": 0.5622593068035944,
+      "grad_norm": 0.3182483911514282,
+      "learning_rate": 4.8466479118678766e-05,
+      "loss": 2.3529,
+      "step": 438
+    },
+    {
+      "epoch": 0.5635430038510911,
+      "grad_norm": 0.34097424149513245,
+      "learning_rate": 4.845748622862417e-05,
+      "loss": 2.3279,
+      "step": 439
+    },
+    {
+      "epoch": 0.5648267008985879,
+      "grad_norm": 0.295391321182251,
+      "learning_rate": 4.8448467886769585e-05,
+      "loss": 2.3059,
+      "step": 440
+    },
+    {
+      "epoch": 0.5661103979460848,
+      "grad_norm": 0.2817283868789673,
+      "learning_rate": 4.8439424102900064e-05,
+      "loss": 2.3056,
+      "step": 441
+    },
+    {
+      "epoch": 0.5673940949935815,
+      "grad_norm": 0.29399430751800537,
+      "learning_rate": 4.84303548868283e-05,
+      "loss": 2.4049,
+      "step": 442
+    },
+    {
+      "epoch": 0.5686777920410783,
+      "grad_norm": 0.32070907950401306,
+      "learning_rate": 4.842126024839453e-05,
+      "loss": 2.3548,
+      "step": 443
+    },
+    {
+      "epoch": 0.5699614890885751,
+      "grad_norm": 0.2972594201564789,
+      "learning_rate": 4.841214019746663e-05,
+      "loss": 2.4239,
+      "step": 444
+    },
+    {
+      "epoch": 0.5712451861360719,
+      "grad_norm": 0.3162088096141815,
+      "learning_rate": 4.840299474394e-05,
+      "loss": 2.4425,
+      "step": 445
+    },
+    {
+      "epoch": 0.5725288831835686,
+      "grad_norm": 0.2938075661659241,
+      "learning_rate": 4.8393823897737634e-05,
+      "loss": 2.3283,
+      "step": 446
+    },
+    {
+      "epoch": 0.5738125802310655,
+      "grad_norm": 0.2970564067363739,
+      "learning_rate": 4.8384627668810064e-05,
+      "loss": 2.3184,
+      "step": 447
+    },
+    {
+      "epoch": 0.5750962772785623,
+      "grad_norm": 0.2736704647541046,
+      "learning_rate": 4.837540606713538e-05,
+      "loss": 2.3115,
+      "step": 448
+    },
+    {
+      "epoch": 0.576379974326059,
+      "grad_norm": 0.3252422511577606,
+      "learning_rate": 4.8366159102719156e-05,
+      "loss": 2.3955,
+      "step": 449
+    },
+    {
+      "epoch": 0.5776636713735558,
+      "grad_norm": 0.3110811114311218,
+      "learning_rate": 4.8356886785594544e-05,
+      "loss": 2.3336,
+      "step": 450
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.2989579141139984,
+      "learning_rate": 4.834758912582217e-05,
+      "loss": 2.3001,
+      "step": 451
+    },
+    {
+      "epoch": 0.5802310654685494,
+      "grad_norm": 0.3055441379547119,
+      "learning_rate": 4.833826613349016e-05,
+      "loss": 2.3683,
+      "step": 452
+    },
+    {
+      "epoch": 0.5815147625160462,
+      "grad_norm": 0.30826109647750854,
+      "learning_rate": 4.832891781871414e-05,
+      "loss": 2.3054,
+      "step": 453
+    },
+    {
+      "epoch": 0.582798459563543,
+      "grad_norm": 0.32700634002685547,
+      "learning_rate": 4.831954419163719e-05,
+      "loss": 2.3865,
+      "step": 454
+    },
+    {
+      "epoch": 0.5840821566110398,
+      "grad_norm": 0.30788737535476685,
+      "learning_rate": 4.831014526242987e-05,
+      "loss": 2.3478,
+      "step": 455
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.28584685921669006,
+      "learning_rate": 4.8300721041290194e-05,
+      "loss": 2.356,
+      "step": 456
+    },
+    {
+      "epoch": 0.5866495507060334,
+      "grad_norm": 0.3295878469944,
+      "learning_rate": 4.829127153844361e-05,
+      "loss": 2.3768,
+      "step": 457
+    },
+    {
+      "epoch": 0.5879332477535302,
+      "grad_norm": 0.31243589520454407,
+      "learning_rate": 4.8281796764143e-05,
+      "loss": 2.365,
+      "step": 458
+    },
+    {
+      "epoch": 0.5892169448010269,
+      "grad_norm": 0.30623236298561096,
+      "learning_rate": 4.8272296728668676e-05,
+      "loss": 2.369,
+      "step": 459
+    },
+    {
+      "epoch": 0.5905006418485238,
+      "grad_norm": 0.2986590564250946,
+      "learning_rate": 4.826277144232834e-05,
+      "loss": 2.3042,
+      "step": 460
+    },
+    {
+      "epoch": 0.5917843388960206,
+      "grad_norm": 0.30335181951522827,
+      "learning_rate": 4.825322091545709e-05,
+      "loss": 2.2763,
+      "step": 461
+    },
+    {
+      "epoch": 0.5930680359435173,
+      "grad_norm": 0.30525484681129456,
+      "learning_rate": 4.824364515841745e-05,
+      "loss": 2.3532,
+      "step": 462
+    },
+    {
+      "epoch": 0.5943517329910141,
+      "grad_norm": 0.2878653109073639,
+      "learning_rate": 4.823404418159927e-05,
+      "loss": 2.4261,
+      "step": 463
+    },
+    {
+      "epoch": 0.5956354300385109,
+      "grad_norm": 0.29711782932281494,
+      "learning_rate": 4.822441799541979e-05,
+      "loss": 2.4149,
+      "step": 464
+    },
+    {
+      "epoch": 0.5969191270860077,
+      "grad_norm": 0.2690982520580292,
+      "learning_rate": 4.82147666103236e-05,
+      "loss": 2.3366,
+      "step": 465
+    },
+    {
+      "epoch": 0.5982028241335045,
+      "grad_norm": 0.2946816682815552,
+      "learning_rate": 4.8205090036782626e-05,
+      "loss": 2.3942,
+      "step": 466
+    },
+    {
+      "epoch": 0.5994865211810013,
+      "grad_norm": 0.3061763346195221,
+      "learning_rate": 4.819538828529613e-05,
+      "loss": 2.4006,
+      "step": 467
+    },
+    {
+      "epoch": 0.6007702182284981,
+      "grad_norm": 0.32586535811424255,
+      "learning_rate": 4.8185661366390676e-05,
+      "loss": 2.3707,
+      "step": 468
+    },
+    {
+      "epoch": 0.6020539152759948,
+      "grad_norm": 0.27984949946403503,
+      "learning_rate": 4.817590929062017e-05,
+      "loss": 2.4379,
+      "step": 469
+    },
+    {
+      "epoch": 0.6033376123234917,
+      "grad_norm": 0.329476922750473,
+      "learning_rate": 4.816613206856577e-05,
+      "loss": 2.4531,
+      "step": 470
+    },
+    {
+      "epoch": 0.6046213093709885,
+      "grad_norm": 0.31376075744628906,
+      "learning_rate": 4.815632971083596e-05,
+      "loss": 2.4197,
+      "step": 471
+    },
+    {
+      "epoch": 0.6059050064184852,
+      "grad_norm": 0.28301122784614563,
+      "learning_rate": 4.814650222806647e-05,
+      "loss": 2.2975,
+      "step": 472
+    },
+    {
+      "epoch": 0.6071887034659821,
+      "grad_norm": 0.30881014466285706,
+      "learning_rate": 4.813664963092029e-05,
+      "loss": 2.3507,
+      "step": 473
+    },
+    {
+      "epoch": 0.6084724005134788,
+      "grad_norm": 0.30735889077186584,
+      "learning_rate": 4.8126771930087674e-05,
+      "loss": 2.2855,
+      "step": 474
+    },
+    {
+      "epoch": 0.6097560975609756,
+      "grad_norm": 0.31143245100975037,
+      "learning_rate": 4.8116869136286106e-05,
+      "loss": 2.3445,
+      "step": 475
+    },
+    {
+      "epoch": 0.6110397946084724,
+      "grad_norm": 0.30091342329978943,
+      "learning_rate": 4.8106941260260296e-05,
+      "loss": 2.3587,
+      "step": 476
+    },
+    {
+      "epoch": 0.6123234916559692,
+      "grad_norm": 0.29558065533638,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 2.4079,
+      "step": 477
+    },
+    {
+      "epoch": 0.613607188703466,
+      "grad_norm": 0.28896674513816833,
+      "learning_rate": 4.8087010304650866e-05,
+      "loss": 2.3141,
+      "step": 478
+    },
+    {
+      "epoch": 0.6148908857509627,
+      "grad_norm": 0.39745038747787476,
+      "learning_rate": 4.8077007246692694e-05,
+      "loss": 2.3588,
+      "step": 479
+    },
+    {
+      "epoch": 0.6161745827984596,
+      "grad_norm": 0.300830602645874,
+      "learning_rate": 4.806697914976116e-05,
+      "loss": 2.4217,
+      "step": 480
+    },
+    {
+      "epoch": 0.6174582798459564,
+      "grad_norm": 0.3155045211315155,
+      "learning_rate": 4.805692602473693e-05,
+      "loss": 2.3939,
+      "step": 481
+    },
+    {
+      "epoch": 0.6187419768934531,
+      "grad_norm": 0.3159199357032776,
+      "learning_rate": 4.8046847882527826e-05,
+      "loss": 2.4239,
+      "step": 482
+    },
+    {
+      "epoch": 0.62002567394095,
+      "grad_norm": 0.299836665391922,
+      "learning_rate": 4.8036744734068826e-05,
+      "loss": 2.4192,
+      "step": 483
+    },
+    {
+      "epoch": 0.6213093709884467,
+      "grad_norm": 0.3199720084667206,
+      "learning_rate": 4.802661659032202e-05,
+      "loss": 2.39,
+      "step": 484
+    },
+    {
+      "epoch": 0.6225930680359435,
+      "grad_norm": 0.29899173974990845,
+      "learning_rate": 4.8016463462276615e-05,
+      "loss": 2.3525,
+      "step": 485
+    },
+    {
+      "epoch": 0.6238767650834403,
+      "grad_norm": 0.2836560904979706,
+      "learning_rate": 4.8006285360948976e-05,
+      "loss": 2.3127,
+      "step": 486
+    },
+    {
+      "epoch": 0.6251604621309371,
+      "grad_norm": 0.31214481592178345,
+      "learning_rate": 4.79960822973825e-05,
+      "loss": 2.4241,
+      "step": 487
+    },
+    {
+      "epoch": 0.6264441591784339,
+      "grad_norm": 0.3114881217479706,
+      "learning_rate": 4.79858542826477e-05,
+      "loss": 2.2663,
+      "step": 488
+    },
+    {
+      "epoch": 0.6277278562259306,
+      "grad_norm": 0.30914467573165894,
+      "learning_rate": 4.7975601327842176e-05,
+      "loss": 2.3633,
+      "step": 489
+    },
+    {
+      "epoch": 0.6290115532734275,
+      "grad_norm": 0.29763662815093994,
+      "learning_rate": 4.796532344409055e-05,
+      "loss": 2.336,
+      "step": 490
+    },
+    {
+      "epoch": 0.6302952503209243,
+      "grad_norm": 0.2814677357673645,
+      "learning_rate": 4.7955020642544515e-05,
+      "loss": 2.4174,
+      "step": 491
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.31262046098709106,
+      "learning_rate": 4.794469293438282e-05,
+      "loss": 2.3888,
+      "step": 492
+    },
+    {
+      "epoch": 0.6328626444159179,
+      "grad_norm": 0.3011872470378876,
+      "learning_rate": 4.7934340330811186e-05,
+      "loss": 2.2837,
+      "step": 493
+    },
+    {
+      "epoch": 0.6341463414634146,
+      "grad_norm": 0.3168891370296478,
+      "learning_rate": 4.79239628430624e-05,
+      "loss": 2.4802,
+      "step": 494
+    },
+    {
+      "epoch": 0.6354300385109114,
+      "grad_norm": 0.2910175621509552,
+      "learning_rate": 4.791356048239622e-05,
+      "loss": 2.3782,
+      "step": 495
+    },
+    {
+      "epoch": 0.6367137355584083,
+      "grad_norm": 0.2881637513637543,
+      "learning_rate": 4.7903133260099385e-05,
+      "loss": 2.3472,
+      "step": 496
+    },
+    {
+      "epoch": 0.637997432605905,
+      "grad_norm": 0.31721916794776917,
+      "learning_rate": 4.789268118748564e-05,
+      "loss": 2.4454,
+      "step": 497
+    },
+    {
+      "epoch": 0.6392811296534018,
+      "grad_norm": 0.2995906472206116,
+      "learning_rate": 4.788220427589566e-05,
+      "loss": 2.2958,
+      "step": 498
+    },
+    {
+      "epoch": 0.6405648267008985,
+      "grad_norm": 0.29439058899879456,
+      "learning_rate": 4.787170253669708e-05,
+      "loss": 2.3642,
+      "step": 499
+    },
+    {
+      "epoch": 0.6418485237483954,
+      "grad_norm": 0.29495733976364136,
+      "learning_rate": 4.78611759812845e-05,
+      "loss": 2.3808,
+      "step": 500
+    },
+    {
+      "epoch": 0.6431322207958922,
+      "grad_norm": 0.3079684376716614,
+      "learning_rate": 4.785062462107941e-05,
+      "loss": 2.3306,
+      "step": 501
+    },
+    {
+      "epoch": 0.6444159178433889,
+      "grad_norm": 0.3264211416244507,
+      "learning_rate": 4.784004846753023e-05,
+      "loss": 2.3811,
+      "step": 502
+    },
+    {
+      "epoch": 0.6456996148908858,
+      "grad_norm": 0.32243621349334717,
+      "learning_rate": 4.782944753211228e-05,
+      "loss": 2.3574,
+      "step": 503
+    },
+    {
+      "epoch": 0.6469833119383825,
+      "grad_norm": 0.33553004264831543,
+      "learning_rate": 4.781882182632776e-05,
+      "loss": 2.2817,
+      "step": 504
+    },
+    {
+      "epoch": 0.6482670089858793,
+      "grad_norm": 0.28932246565818787,
+      "learning_rate": 4.780817136170578e-05,
+      "loss": 2.4276,
+      "step": 505
+    },
+    {
+      "epoch": 0.6495507060333762,
+      "grad_norm": 0.30343809723854065,
+      "learning_rate": 4.7797496149802256e-05,
+      "loss": 2.4455,
+      "step": 506
+    },
+    {
+      "epoch": 0.6508344030808729,
+      "grad_norm": 0.3055610954761505,
+      "learning_rate": 4.77867962022e-05,
+      "loss": 2.318,
+      "step": 507
+    },
+    {
+      "epoch": 0.6521181001283697,
+      "grad_norm": 0.30805933475494385,
+      "learning_rate": 4.777607153050866e-05,
+      "loss": 2.4104,
+      "step": 508
+    },
+    {
+      "epoch": 0.6534017971758665,
+      "grad_norm": 0.2895534038543701,
+      "learning_rate": 4.7765322146364686e-05,
+      "loss": 2.3868,
+      "step": 509
+    },
+    {
+      "epoch": 0.6546854942233633,
+      "grad_norm": 0.3000538647174835,
+      "learning_rate": 4.775454806143137e-05,
+      "loss": 2.3504,
+      "step": 510
+    },
+    {
+      "epoch": 0.6559691912708601,
+      "grad_norm": 0.3021094799041748,
+      "learning_rate": 4.7743749287398776e-05,
+      "loss": 2.3791,
+      "step": 511
+    },
+    {
+      "epoch": 0.6572528883183568,
+      "grad_norm": 0.2954312860965729,
+      "learning_rate": 4.7732925835983775e-05,
+      "loss": 2.3347,
+      "step": 512
+    },
+    {
+      "epoch": 0.6585365853658537,
+      "grad_norm": 0.2947414815425873,
+      "learning_rate": 4.7722077718930014e-05,
+      "loss": 2.3683,
+      "step": 513
+    },
+    {
+      "epoch": 0.6598202824133504,
+      "grad_norm": 0.30434030294418335,
+      "learning_rate": 4.771120494800789e-05,
+      "loss": 2.3666,
+      "step": 514
+    },
+    {
+      "epoch": 0.6611039794608472,
+      "grad_norm": 0.2817016541957855,
+      "learning_rate": 4.7700307535014565e-05,
+      "loss": 2.3736,
+      "step": 515
+    },
+    {
+      "epoch": 0.6623876765083441,
+      "grad_norm": 0.2933237552642822,
+      "learning_rate": 4.768938549177393e-05,
+      "loss": 2.3464,
+      "step": 516
+    },
+    {
+      "epoch": 0.6636713735558408,
+      "grad_norm": 0.3133641481399536,
+      "learning_rate": 4.7678438830136596e-05,
+      "loss": 2.3103,
+      "step": 517
+    },
+    {
+      "epoch": 0.6649550706033376,
+      "grad_norm": 0.2988991439342499,
+      "learning_rate": 4.766746756197989e-05,
+      "loss": 2.4228,
+      "step": 518
+    },
+    {
+      "epoch": 0.6662387676508345,
+      "grad_norm": 0.3129512369632721,
+      "learning_rate": 4.765647169920785e-05,
+      "loss": 2.3711,
+      "step": 519
+    },
+    {
+      "epoch": 0.6675224646983312,
+      "grad_norm": 0.30164363980293274,
+      "learning_rate": 4.764545125375117e-05,
+      "loss": 2.314,
+      "step": 520
+    },
+    {
+      "epoch": 0.668806161745828,
+      "grad_norm": 0.3078322112560272,
+      "learning_rate": 4.7634406237567245e-05,
+      "loss": 2.3583,
+      "step": 521
+    },
+    {
+      "epoch": 0.6700898587933247,
+      "grad_norm": 0.29779842495918274,
+      "learning_rate": 4.7623336662640116e-05,
+      "loss": 2.3329,
+      "step": 522
+    },
+    {
+      "epoch": 0.6713735558408216,
+      "grad_norm": 0.30728939175605774,
+      "learning_rate": 4.761224254098048e-05,
+      "loss": 2.3432,
+      "step": 523
+    },
+    {
+      "epoch": 0.6726572528883183,
+      "grad_norm": 0.28595444560050964,
+      "learning_rate": 4.760112388462564e-05,
+      "loss": 2.3155,
+      "step": 524
+    },
+    {
+      "epoch": 0.6739409499358151,
+      "grad_norm": 0.32341310381889343,
+      "learning_rate": 4.758998070563957e-05,
+      "loss": 2.3919,
+      "step": 525
+    },
+    {
+      "epoch": 0.675224646983312,
+      "grad_norm": 0.33163347840309143,
+      "learning_rate": 4.75788130161128e-05,
+      "loss": 2.2703,
+      "step": 526
+    },
+    {
+      "epoch": 0.6765083440308087,
+      "grad_norm": 0.2895621061325073,
+      "learning_rate": 4.7567620828162486e-05,
+      "loss": 2.3479,
+      "step": 527
+    },
+    {
+      "epoch": 0.6777920410783055,
+      "grad_norm": 0.31375667452812195,
+      "learning_rate": 4.7556404153932356e-05,
+      "loss": 2.4763,
+      "step": 528
+    },
+    {
+      "epoch": 0.6790757381258024,
+      "grad_norm": 0.29855942726135254,
+      "learning_rate": 4.754516300559271e-05,
+      "loss": 2.4154,
+      "step": 529
+    },
+    {
+      "epoch": 0.6803594351732991,
+      "grad_norm": 0.29022201895713806,
+      "learning_rate": 4.7533897395340384e-05,
+      "loss": 2.3614,
+      "step": 530
+    },
+    {
+      "epoch": 0.6816431322207959,
+      "grad_norm": 0.280118852853775,
+      "learning_rate": 4.7522607335398786e-05,
+      "loss": 2.3306,
+      "step": 531
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 0.29326388239860535,
+      "learning_rate": 4.751129283801782e-05,
+      "loss": 2.3219,
+      "step": 532
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.3260889947414398,
+      "learning_rate": 4.7499953915473935e-05,
+      "loss": 2.3952,
+      "step": 533
+    },
+    {
+      "epoch": 0.6854942233632862,
+      "grad_norm": 0.2982180118560791,
+      "learning_rate": 4.7488590580070074e-05,
+      "loss": 2.3165,
+      "step": 534
+    },
+    {
+      "epoch": 0.686777920410783,
+      "grad_norm": 0.303310364484787,
+      "learning_rate": 4.7477202844135646e-05,
+      "loss": 2.2632,
+      "step": 535
+    },
+    {
+      "epoch": 0.6880616174582799,
+      "grad_norm": 0.329369455575943,
+      "learning_rate": 4.746579072002657e-05,
+      "loss": 2.328,
+      "step": 536
+    },
+    {
+      "epoch": 0.6893453145057766,
+      "grad_norm": 0.3056361973285675,
+      "learning_rate": 4.74543542201252e-05,
+      "loss": 2.4139,
+      "step": 537
+    },
+    {
+      "epoch": 0.6906290115532734,
+      "grad_norm": 0.31663402915000916,
+      "learning_rate": 4.744289335684034e-05,
+      "loss": 2.3929,
+      "step": 538
+    },
+    {
+      "epoch": 0.6919127086007703,
+      "grad_norm": 0.3166126012802124,
+      "learning_rate": 4.7431408142607236e-05,
+      "loss": 2.3308,
+      "step": 539
+    },
+    {
+      "epoch": 0.693196405648267,
+      "grad_norm": 0.3111107349395752,
+      "learning_rate": 4.7419898589887566e-05,
+      "loss": 2.3885,
+      "step": 540
+    },
+    {
+      "epoch": 0.6944801026957638,
+      "grad_norm": 0.3381554186344147,
+      "learning_rate": 4.74083647111694e-05,
+      "loss": 2.2421,
+      "step": 541
+    },
+    {
+      "epoch": 0.6957637997432606,
+      "grad_norm": 0.29884985089302063,
+      "learning_rate": 4.73968065189672e-05,
+      "loss": 2.3181,
+      "step": 542
+    },
+    {
+      "epoch": 0.6970474967907574,
+      "grad_norm": 0.2916213274002075,
+      "learning_rate": 4.738522402582183e-05,
+      "loss": 2.3626,
+      "step": 543
+    },
+    {
+      "epoch": 0.6983311938382541,
+      "grad_norm": 0.3153024911880493,
+      "learning_rate": 4.737361724430048e-05,
+      "loss": 2.4354,
+      "step": 544
+    },
+    {
+      "epoch": 0.699614890885751,
+      "grad_norm": 0.2967838644981384,
+      "learning_rate": 4.736198618699675e-05,
+      "loss": 2.4529,
+      "step": 545
+    },
+    {
+      "epoch": 0.7008985879332478,
+      "grad_norm": 0.29753878712654114,
+      "learning_rate": 4.7350330866530536e-05,
+      "loss": 2.3934,
+      "step": 546
+    },
+    {
+      "epoch": 0.7021822849807445,
+      "grad_norm": 0.2958550751209259,
+      "learning_rate": 4.7338651295548065e-05,
+      "loss": 2.2737,
+      "step": 547
+    },
+    {
+      "epoch": 0.7034659820282413,
+      "grad_norm": 0.2889609932899475,
+      "learning_rate": 4.7326947486721894e-05,
+      "loss": 2.3989,
+      "step": 548
+    },
+    {
+      "epoch": 0.7047496790757382,
+      "grad_norm": 0.2951468229293823,
+      "learning_rate": 4.731521945275087e-05,
+      "loss": 2.3909,
+      "step": 549
+    },
+    {
+      "epoch": 0.7060333761232349,
+      "grad_norm": 0.30337998270988464,
+      "learning_rate": 4.730346720636011e-05,
+      "loss": 2.3878,
+      "step": 550
+    },
+    {
+      "epoch": 0.7073170731707317,
+      "grad_norm": 0.2858850359916687,
+      "learning_rate": 4.7291690760301035e-05,
+      "loss": 2.3465,
+      "step": 551
+    },
+    {
+      "epoch": 0.7086007702182285,
+      "grad_norm": 0.2845821678638458,
+      "learning_rate": 4.727989012735129e-05,
+      "loss": 2.385,
+      "step": 552
+    },
+    {
+      "epoch": 0.7098844672657253,
+      "grad_norm": 0.2901153564453125,
+      "learning_rate": 4.726806532031478e-05,
+      "loss": 2.2939,
+      "step": 553
+    },
+    {
+      "epoch": 0.711168164313222,
+      "grad_norm": 0.27658534049987793,
+      "learning_rate": 4.725621635202164e-05,
+      "loss": 2.3292,
+      "step": 554
+    },
+    {
+      "epoch": 0.7124518613607189,
+      "grad_norm": 0.289438933134079,
+      "learning_rate": 4.724434323532821e-05,
+      "loss": 2.3481,
+      "step": 555
+    },
+    {
+      "epoch": 0.7137355584082157,
+      "grad_norm": 0.30061691999435425,
+      "learning_rate": 4.7232445983117045e-05,
+      "loss": 2.2876,
+      "step": 556
+    },
+    {
+      "epoch": 0.7150192554557124,
+      "grad_norm": 0.28911301493644714,
+      "learning_rate": 4.722052460829687e-05,
+      "loss": 2.3649,
+      "step": 557
+    },
+    {
+      "epoch": 0.7163029525032092,
+      "grad_norm": 0.32217785716056824,
+      "learning_rate": 4.720857912380261e-05,
+      "loss": 2.3052,
+      "step": 558
+    },
+    {
+      "epoch": 0.7175866495507061,
+      "grad_norm": 0.3333997428417206,
+      "learning_rate": 4.719660954259532e-05,
+      "loss": 2.3851,
+      "step": 559
+    },
+    {
+      "epoch": 0.7188703465982028,
+      "grad_norm": 0.3150656819343567,
+      "learning_rate": 4.718461587766221e-05,
+      "loss": 2.3354,
+      "step": 560
+    },
+    {
+      "epoch": 0.7201540436456996,
+      "grad_norm": 0.2966265380382538,
+      "learning_rate": 4.7172598142016645e-05,
+      "loss": 2.3681,
+      "step": 561
+    },
+    {
+      "epoch": 0.7214377406931964,
+      "grad_norm": 0.3027741014957428,
+      "learning_rate": 4.716055634869807e-05,
+      "loss": 2.3369,
+      "step": 562
+    },
+    {
+      "epoch": 0.7227214377406932,
+      "grad_norm": 0.32294961810112,
+      "learning_rate": 4.714849051077205e-05,
+      "loss": 2.4019,
+      "step": 563
+    },
+    {
+      "epoch": 0.72400513478819,
+      "grad_norm": 0.30615222454071045,
+      "learning_rate": 4.713640064133025e-05,
+      "loss": 2.4961,
+      "step": 564
+    },
+    {
+      "epoch": 0.7252888318356868,
+      "grad_norm": 0.29600149393081665,
+      "learning_rate": 4.712428675349039e-05,
+      "loss": 2.3446,
+      "step": 565
+    },
+    {
+      "epoch": 0.7265725288831836,
+      "grad_norm": 0.2971326410770416,
+      "learning_rate": 4.7112148860396265e-05,
+      "loss": 2.3006,
+      "step": 566
+    },
+    {
+      "epoch": 0.7278562259306803,
+      "grad_norm": 0.29449960589408875,
+      "learning_rate": 4.7099986975217704e-05,
+      "loss": 2.464,
+      "step": 567
+    },
+    {
+      "epoch": 0.7291399229781772,
+      "grad_norm": 0.27724847197532654,
+      "learning_rate": 4.708780111115057e-05,
+      "loss": 2.4383,
+      "step": 568
+    },
+    {
+      "epoch": 0.730423620025674,
+      "grad_norm": 0.3143709897994995,
+      "learning_rate": 4.7075591281416765e-05,
+      "loss": 2.3377,
+      "step": 569
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.32122036814689636,
+      "learning_rate": 4.706335749926417e-05,
+      "loss": 2.2914,
+      "step": 570
+    },
+    {
+      "epoch": 0.7329910141206675,
+      "grad_norm": 0.28614115715026855,
+      "learning_rate": 4.7051099777966645e-05,
+      "loss": 2.3338,
+      "step": 571
+    },
+    {
+      "epoch": 0.7342747111681643,
+      "grad_norm": 0.30070704221725464,
+      "learning_rate": 4.703881813082406e-05,
+      "loss": 2.3367,
+      "step": 572
+    },
+    {
+      "epoch": 0.7355584082156611,
+      "grad_norm": 0.2799395024776459,
+      "learning_rate": 4.702651257116222e-05,
+      "loss": 2.3604,
+      "step": 573
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.29513630270957947,
+      "learning_rate": 4.7014183112332874e-05,
+      "loss": 2.3487,
+      "step": 574
+    },
+    {
+      "epoch": 0.7381258023106547,
+      "grad_norm": 0.30071401596069336,
+      "learning_rate": 4.7001829767713726e-05,
+      "loss": 2.3422,
+      "step": 575
+    },
+    {
+      "epoch": 0.7394094993581515,
+      "grad_norm": 0.3397565186023712,
+      "learning_rate": 4.698945255070837e-05,
+      "loss": 2.3802,
+      "step": 576
+    },
+    {
+      "epoch": 0.7406931964056482,
+      "grad_norm": 0.32068637013435364,
+      "learning_rate": 4.697705147474631e-05,
+      "loss": 2.3498,
+      "step": 577
+    },
+    {
+      "epoch": 0.7419768934531451,
+      "grad_norm": 0.5262579917907715,
+      "learning_rate": 4.696462655328294e-05,
+      "loss": 2.2523,
+      "step": 578
+    },
+    {
+      "epoch": 0.7432605905006419,
+      "grad_norm": 0.3595364987850189,
+      "learning_rate": 4.695217779979953e-05,
+      "loss": 2.3578,
+      "step": 579
+    },
+    {
+      "epoch": 0.7445442875481386,
+      "grad_norm": 0.3001711964607239,
+      "learning_rate": 4.69397052278032e-05,
+      "loss": 2.2685,
+      "step": 580
+    },
+    {
+      "epoch": 0.7458279845956355,
+      "grad_norm": 0.3520994782447815,
+      "learning_rate": 4.6927208850826925e-05,
+      "loss": 2.364,
+      "step": 581
+    },
+    {
+      "epoch": 0.7471116816431322,
+      "grad_norm": 0.3192301094532013,
+      "learning_rate": 4.6914688682429496e-05,
+      "loss": 2.3454,
+      "step": 582
+    },
+    {
+      "epoch": 0.748395378690629,
+      "grad_norm": 0.28848007321357727,
+      "learning_rate": 4.690214473619552e-05,
+      "loss": 2.5347,
+      "step": 583
+    },
+    {
+      "epoch": 0.7496790757381258,
+      "grad_norm": 0.3215525448322296,
+      "learning_rate": 4.688957702573542e-05,
+      "loss": 2.3881,
+      "step": 584
+    },
+    {
+      "epoch": 0.7509627727856226,
+      "grad_norm": 0.32826587557792664,
+      "learning_rate": 4.687698556468538e-05,
+      "loss": 2.3555,
+      "step": 585
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 3116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 195,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.100186401827717e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}