diff --git "a/trainer_state.json" "b/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/trainer_state.json"
@@ -0,0 +1,3886 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1098,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00546448087431694,
+      "grad_norm": 1.573991060256958,
+      "learning_rate": 4.545454545454545e-07,
+      "loss": 2.660639762878418,
+      "step": 2
+    },
+    {
+      "epoch": 0.01092896174863388,
+      "grad_norm": 0.6165518760681152,
+      "learning_rate": 1.3636363636363636e-06,
+      "loss": 1.9370158910751343,
+      "step": 4
+    },
+    {
+      "epoch": 0.01639344262295082,
+      "grad_norm": 0.5032806992530823,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 1.883617877960205,
+      "step": 6
+    },
+    {
+      "epoch": 0.02185792349726776,
+      "grad_norm": 0.5399006605148315,
+      "learning_rate": 3.1818181818181817e-06,
+      "loss": 1.7472549676895142,
+      "step": 8
+    },
+    {
+      "epoch": 0.0273224043715847,
+      "grad_norm": 0.4401944577693939,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 1.7204209566116333,
+      "step": 10
+    },
+    {
+      "epoch": 0.03278688524590164,
+      "grad_norm": 0.4825930595397949,
+      "learning_rate": 5e-06,
+      "loss": 1.56802499294281,
+      "step": 12
+    },
+    {
+      "epoch": 0.03825136612021858,
+      "grad_norm": 0.3861444294452667,
+      "learning_rate": 5.909090909090909e-06,
+      "loss": 1.478776216506958,
+      "step": 14
+    },
+    {
+      "epoch": 0.04371584699453552,
+      "grad_norm": 0.29860642552375793,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 1.215264916419983,
+      "step": 16
+    },
+    {
+      "epoch": 0.04918032786885246,
+      "grad_norm": 0.3623839318752289,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 1.1711786985397339,
+      "step": 18
+    },
+    {
+      "epoch": 0.0546448087431694,
+      "grad_norm": 0.3934680223464966,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 1.4052964448928833,
+      "step": 20
+    },
+    {
+      "epoch": 0.060109289617486336,
+      "grad_norm": 0.3248288929462433,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 1.337301254272461,
+      "step": 22
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 0.41455528140068054,
+      "learning_rate": 1.0454545454545455e-05,
+      "loss": 1.4091546535491943,
+      "step": 24
+    },
+    {
+      "epoch": 0.07103825136612021,
+      "grad_norm": 0.7718392610549927,
+      "learning_rate": 1.1363636363636365e-05,
+      "loss": 1.608378529548645,
+      "step": 26
+    },
+    {
+      "epoch": 0.07650273224043716,
+      "grad_norm": 0.3031645715236664,
+      "learning_rate": 1.2272727272727273e-05,
+      "loss": 1.3645198345184326,
+      "step": 28
+    },
+    {
+      "epoch": 0.08196721311475409,
+      "grad_norm": 0.3317704200744629,
+      "learning_rate": 1.318181818181818e-05,
+      "loss": 1.2910865545272827,
+      "step": 30
+    },
+    {
+      "epoch": 0.08743169398907104,
+      "grad_norm": 0.3077561855316162,
+      "learning_rate": 1.409090909090909e-05,
+      "loss": 1.2850395441055298,
+      "step": 32
+    },
+    {
+      "epoch": 0.09289617486338798,
+      "grad_norm": 0.6236030459403992,
+      "learning_rate": 1.5e-05,
+      "loss": 1.011098861694336,
+      "step": 34
+    },
+    {
+      "epoch": 0.09836065573770492,
+      "grad_norm": 0.3117682635784149,
+      "learning_rate": 1.590909090909091e-05,
+      "loss": 1.1125837564468384,
+      "step": 36
+    },
+    {
+      "epoch": 0.10382513661202186,
+      "grad_norm": 0.3884047269821167,
+      "learning_rate": 1.6818181818181818e-05,
+      "loss": 1.3625156879425049,
+      "step": 38
+    },
+    {
+      "epoch": 0.1092896174863388,
+      "grad_norm": 0.21100102365016937,
+      "learning_rate": 1.772727272727273e-05,
+      "loss": 1.3091150522232056,
+      "step": 40
+    },
+    {
+      "epoch": 0.11475409836065574,
+      "grad_norm": 0.7283101677894592,
+      "learning_rate": 1.8636363636363638e-05,
+      "loss": 0.9641504883766174,
+      "step": 42
+    },
+    {
+      "epoch": 0.12021857923497267,
+      "grad_norm": 0.27201205492019653,
+      "learning_rate": 1.9545454545454546e-05,
+      "loss": 0.8841361403465271,
+      "step": 44
+    },
+    {
+      "epoch": 0.12568306010928962,
+      "grad_norm": 0.2947981059551239,
+      "learning_rate": 2.0454545454545457e-05,
+      "loss": 1.3351988792419434,
+      "step": 46
+    },
+    {
+      "epoch": 0.13114754098360656,
+      "grad_norm": 0.25678518414497375,
+      "learning_rate": 2.1363636363636362e-05,
+      "loss": 1.305159568786621,
+      "step": 48
+    },
+    {
+      "epoch": 0.1366120218579235,
+      "grad_norm": 0.3346308767795563,
+      "learning_rate": 2.2272727272727274e-05,
+      "loss": 1.2757641077041626,
+      "step": 50
+    },
+    {
+      "epoch": 0.14207650273224043,
+      "grad_norm": 0.39588257670402527,
+      "learning_rate": 2.318181818181818e-05,
+      "loss": 1.2430144548416138,
+      "step": 52
+    },
+    {
+      "epoch": 0.14754098360655737,
+      "grad_norm": 1.0091103315353394,
+      "learning_rate": 2.4090909090909093e-05,
+      "loss": 0.886474609375,
+      "step": 54
+    },
+    {
+      "epoch": 0.15300546448087432,
+      "grad_norm": 0.38303902745246887,
+      "learning_rate": 2.5e-05,
+      "loss": 1.45668363571167,
+      "step": 56
+    },
+    {
+      "epoch": 0.15846994535519127,
+      "grad_norm": 0.5787215828895569,
+      "learning_rate": 2.4999795867415925e-05,
+      "loss": 1.4211903810501099,
+      "step": 58
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "grad_norm": 0.33087924122810364,
+      "learning_rate": 2.499918347707172e-05,
+      "loss": 1.3224607706069946,
+      "step": 60
+    },
+    {
+      "epoch": 0.16939890710382513,
+      "grad_norm": 0.3203301727771759,
+      "learning_rate": 2.499816285119117e-05,
+      "loss": 1.5149167776107788,
+      "step": 62
+    },
+    {
+      "epoch": 0.17486338797814208,
+      "grad_norm": 0.8560717701911926,
+      "learning_rate": 2.499673402681304e-05,
+      "loss": 1.1875461339950562,
+      "step": 64
+    },
+    {
+      "epoch": 0.18032786885245902,
+      "grad_norm": 0.779531717300415,
+      "learning_rate": 2.49948970557897e-05,
+      "loss": 1.3079862594604492,
+      "step": 66
+    },
+    {
+      "epoch": 0.18579234972677597,
+      "grad_norm": 0.3134159743785858,
+      "learning_rate": 2.499265200478526e-05,
+      "loss": 1.2827211618423462,
+      "step": 68
+    },
+    {
+      "epoch": 0.1912568306010929,
+      "grad_norm": 0.5278278589248657,
+      "learning_rate": 2.498999895527316e-05,
+      "loss": 1.3154817819595337,
+      "step": 70
+    },
+    {
+      "epoch": 0.19672131147540983,
+      "grad_norm": 0.34715163707733154,
+      "learning_rate": 2.4986938003533195e-05,
+      "loss": 1.1282734870910645,
+      "step": 72
+    },
+    {
+      "epoch": 0.20218579234972678,
+      "grad_norm": 0.2873562276363373,
+      "learning_rate": 2.498346926064803e-05,
+      "loss": 1.2482017278671265,
+      "step": 74
+    },
+    {
+      "epoch": 0.20765027322404372,
+      "grad_norm": 0.40799790620803833,
+      "learning_rate": 2.497959285249916e-05,
+      "loss": 1.3365082740783691,
+      "step": 76
+    },
+    {
+      "epoch": 0.21311475409836064,
+      "grad_norm": 2.886547565460205,
+      "learning_rate": 2.497530891976237e-05,
+      "loss": 0.8918291926383972,
+      "step": 78
+    },
+    {
+      "epoch": 0.2185792349726776,
+      "grad_norm": 0.35245203971862793,
+      "learning_rate": 2.497061761790258e-05,
+      "loss": 0.6639876961708069,
+      "step": 80
+    },
+    {
+      "epoch": 0.22404371584699453,
+      "grad_norm": 0.48221555352211,
+      "learning_rate": 2.4965519117168257e-05,
+      "loss": 1.4380748271942139,
+      "step": 82
+    },
+    {
+      "epoch": 0.22950819672131148,
+      "grad_norm": 0.51203852891922,
+      "learning_rate": 2.49600136025852e-05,
+      "loss": 0.7898932695388794,
+      "step": 84
+    },
+    {
+      "epoch": 0.23497267759562843,
+      "grad_norm": 0.27620550990104675,
+      "learning_rate": 2.495410127394983e-05,
+      "loss": 1.3038958311080933,
+      "step": 86
+    },
+    {
+      "epoch": 0.24043715846994534,
+      "grad_norm": 0.3855900764465332,
+      "learning_rate": 2.494778234582197e-05,
+      "loss": 1.272139072418213,
+      "step": 88
+    },
+    {
+      "epoch": 0.2459016393442623,
+      "grad_norm": 2.9909884929656982,
+      "learning_rate": 2.494105704751701e-05,
+      "loss": 0.8982883095741272,
+      "step": 90
+    },
+    {
+      "epoch": 0.25136612021857924,
+      "grad_norm": 0.8854891061782837,
+      "learning_rate": 2.4933925623097626e-05,
+      "loss": 1.3485952615737915,
+      "step": 92
+    },
+    {
+      "epoch": 0.2568306010928962,
+      "grad_norm": 0.3434160053730011,
+      "learning_rate": 2.49263883313649e-05,
+      "loss": 1.1437045335769653,
+      "step": 94
+    },
+    {
+      "epoch": 0.26229508196721313,
+      "grad_norm": 0.5682878494262695,
+      "learning_rate": 2.4918445445848933e-05,
+      "loss": 1.5587941408157349,
+      "step": 96
+    },
+    {
+      "epoch": 0.2677595628415301,
+      "grad_norm": 0.2681918740272522,
+      "learning_rate": 2.491009725479893e-05,
+      "loss": 0.9907023906707764,
+      "step": 98
+    },
+    {
+      "epoch": 0.273224043715847,
+      "grad_norm": 0.32420745491981506,
+      "learning_rate": 2.4901344061172718e-05,
+      "loss": 1.0972590446472168,
+      "step": 100
+    },
+    {
+      "epoch": 0.2786885245901639,
+      "grad_norm": 0.3802216053009033,
+      "learning_rate": 2.489218618262578e-05,
+      "loss": 1.2862308025360107,
+      "step": 102
+    },
+    {
+      "epoch": 0.28415300546448086,
+      "grad_norm": 0.9653081297874451,
+      "learning_rate": 2.4882623951499687e-05,
+      "loss": 1.0500785112380981,
+      "step": 104
+    },
+    {
+      "epoch": 0.2896174863387978,
+      "grad_norm": 0.2368626743555069,
+      "learning_rate": 2.4872657714810083e-05,
+      "loss": 1.2645362615585327,
+      "step": 106
+    },
+    {
+      "epoch": 0.29508196721311475,
+      "grad_norm": 0.29273951053619385,
+      "learning_rate": 2.4862287834234058e-05,
+      "loss": 1.4147664308547974,
+      "step": 108
+    },
+    {
+      "epoch": 0.3005464480874317,
+      "grad_norm": 0.3903352618217468,
+      "learning_rate": 2.4851514686097042e-05,
+      "loss": 1.2646139860153198,
+      "step": 110
+    },
+    {
+      "epoch": 0.30601092896174864,
+      "grad_norm": 0.25432300567626953,
+      "learning_rate": 2.4840338661359128e-05,
+      "loss": 1.2783875465393066,
+      "step": 112
+    },
+    {
+      "epoch": 0.3114754098360656,
+      "grad_norm": 0.6913565397262573,
+      "learning_rate": 2.4828760165600914e-05,
+      "loss": 1.4046285152435303,
+      "step": 114
+    },
+    {
+      "epoch": 0.31693989071038253,
+      "grad_norm": 0.7609861493110657,
+      "learning_rate": 2.481677961900875e-05,
+      "loss": 1.2646381855010986,
+      "step": 116
+    },
+    {
+      "epoch": 0.3224043715846995,
+      "grad_norm": 0.3743007481098175,
+      "learning_rate": 2.4804397456359513e-05,
+      "loss": 1.031684160232544,
+      "step": 118
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 0.79277104139328,
+      "learning_rate": 2.4791614127004825e-05,
+      "loss": 1.2975627183914185,
+      "step": 120
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.8501270413398743,
+      "learning_rate": 2.477843009485474e-05,
+      "loss": 1.358191728591919,
+      "step": 122
+    },
+    {
+      "epoch": 0.33879781420765026,
+      "grad_norm": 0.3265473246574402,
+      "learning_rate": 2.4764845838360912e-05,
+      "loss": 1.051877498626709,
+      "step": 124
+    },
+    {
+      "epoch": 0.3442622950819672,
+      "grad_norm": 0.35509005188941956,
+      "learning_rate": 2.475086185049923e-05,
+      "loss": 1.0525556802749634,
+      "step": 126
+    },
+    {
+      "epoch": 0.34972677595628415,
+      "grad_norm": 0.3058815896511078,
+      "learning_rate": 2.473647863875193e-05,
+      "loss": 1.325781226158142,
+      "step": 128
+    },
+    {
+      "epoch": 0.3551912568306011,
+      "grad_norm": 0.3684760332107544,
+      "learning_rate": 2.472169672508918e-05,
+      "loss": 1.2639888525009155,
+      "step": 130
+    },
+    {
+      "epoch": 0.36065573770491804,
+      "grad_norm": 0.31321296095848083,
+      "learning_rate": 2.4706516645950126e-05,
+      "loss": 1.2196840047836304,
+      "step": 132
+    },
+    {
+      "epoch": 0.366120218579235,
+      "grad_norm": 0.6234083771705627,
+      "learning_rate": 2.4690938952223446e-05,
+      "loss": 1.122013807296753,
+      "step": 134
+    },
+    {
+      "epoch": 0.37158469945355194,
+      "grad_norm": 0.5376752614974976,
+      "learning_rate": 2.4674964209227338e-05,
+      "loss": 1.0269572734832764,
+      "step": 136
+    },
+    {
+      "epoch": 0.3770491803278688,
+      "grad_norm": 0.3545861542224884,
+      "learning_rate": 2.4658592996689018e-05,
+      "loss": 0.9930480718612671,
+      "step": 138
+    },
+    {
+      "epoch": 0.3825136612021858,
+      "grad_norm": 0.2623893618583679,
+      "learning_rate": 2.464182590872366e-05,
+      "loss": 0.6596786379814148,
+      "step": 140
+    },
+    {
+      "epoch": 0.3879781420765027,
+      "grad_norm": 0.2950592339038849,
+      "learning_rate": 2.4624663553812876e-05,
+      "loss": 1.2530113458633423,
+      "step": 142
+    },
+    {
+      "epoch": 0.39344262295081966,
+      "grad_norm": 0.36303240060806274,
+      "learning_rate": 2.4607106554782592e-05,
+      "loss": 1.278784155845642,
+      "step": 144
+    },
+    {
+      "epoch": 0.3989071038251366,
+      "grad_norm": 0.28947484493255615,
+      "learning_rate": 2.4589155548780468e-05,
+      "loss": 1.2354241609573364,
+      "step": 146
+    },
+    {
+      "epoch": 0.40437158469945356,
+      "grad_norm": 0.32500797510147095,
+      "learning_rate": 2.4570811187252763e-05,
+      "loss": 1.230383038520813,
+      "step": 148
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "grad_norm": 0.27029216289520264,
+      "learning_rate": 2.4552074135920718e-05,
+      "loss": 1.1657707691192627,
+      "step": 150
+    },
+    {
+      "epoch": 0.41530054644808745,
+      "grad_norm": 0.7339510321617126,
+      "learning_rate": 2.4532945074756356e-05,
+      "loss": 1.271276831626892,
+      "step": 152
+    },
+    {
+      "epoch": 0.4207650273224044,
+      "grad_norm": 0.29380178451538086,
+      "learning_rate": 2.4513424697957853e-05,
+      "loss": 1.2509087324142456,
+      "step": 154
+    },
+    {
+      "epoch": 0.4262295081967213,
+      "grad_norm": 0.3937924802303314,
+      "learning_rate": 2.4493513713924312e-05,
+      "loss": 1.2946242094039917,
+      "step": 156
+    },
+    {
+      "epoch": 0.43169398907103823,
+      "grad_norm": 0.4068252146244049,
+      "learning_rate": 2.4473212845230066e-05,
+      "loss": 1.028969168663025,
+      "step": 158
+    },
+    {
+      "epoch": 0.4371584699453552,
+      "grad_norm": 0.2621578276157379,
+      "learning_rate": 2.4452522828598448e-05,
+      "loss": 1.2205129861831665,
+      "step": 160
+    },
+    {
+      "epoch": 0.4426229508196721,
+      "grad_norm": 0.4484550654888153,
+      "learning_rate": 2.4431444414875076e-05,
+      "loss": 0.7462490797042847,
+      "step": 162
+    },
+    {
+      "epoch": 0.44808743169398907,
+      "grad_norm": 0.3683895170688629,
+      "learning_rate": 2.440997836900058e-05,
+      "loss": 1.6338239908218384,
+      "step": 164
+    },
+    {
+      "epoch": 0.453551912568306,
+      "grad_norm": 3.4501283168792725,
+      "learning_rate": 2.438812546998286e-05,
+      "loss": 0.7732384204864502,
+      "step": 166
+    },
+    {
+      "epoch": 0.45901639344262296,
+      "grad_norm": 0.5550245046615601,
+      "learning_rate": 2.4365886510868798e-05,
+      "loss": 1.1818565130233765,
+      "step": 168
+    },
+    {
+      "epoch": 0.4644808743169399,
+      "grad_norm": 0.39989838004112244,
+      "learning_rate": 2.4343262298715504e-05,
+      "loss": 1.2723463773727417,
+      "step": 170
+    },
+    {
+      "epoch": 0.46994535519125685,
+      "grad_norm": 0.49861252307891846,
+      "learning_rate": 2.4320253654560986e-05,
+      "loss": 1.3423465490341187,
+      "step": 172
+    },
+    {
+      "epoch": 0.47540983606557374,
+      "grad_norm": 0.4895351231098175,
+      "learning_rate": 2.429686141339441e-05,
+      "loss": 1.4451054334640503,
+      "step": 174
+    },
+    {
+      "epoch": 0.4808743169398907,
+      "grad_norm": 0.27367469668388367,
+      "learning_rate": 2.427308642412576e-05,
+      "loss": 1.2423328161239624,
+      "step": 176
+    },
+    {
+      "epoch": 0.48633879781420764,
+      "grad_norm": 0.6150447726249695,
+      "learning_rate": 2.4248929549555024e-05,
+      "loss": 1.208847165107727,
+      "step": 178
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "grad_norm": 0.21229158341884613,
+      "learning_rate": 2.422439166634091e-05,
+      "loss": 1.2032520771026611,
+      "step": 180
+    },
+    {
+      "epoch": 0.4972677595628415,
+      "grad_norm": 0.38285210728645325,
+      "learning_rate": 2.4199473664969033e-05,
+      "loss": 1.1992058753967285,
+      "step": 182
+    },
+    {
+      "epoch": 0.5027322404371585,
+      "grad_norm": 1.3906806707382202,
+      "learning_rate": 2.4174176449719557e-05,
+      "loss": 1.3618383407592773,
+      "step": 184
+    },
+    {
+      "epoch": 0.5081967213114754,
+      "grad_norm": 1.3885375261306763,
+      "learning_rate": 2.4148500938634432e-05,
+      "loss": 1.2250099182128906,
+      "step": 186
+    },
+    {
+      "epoch": 0.5136612021857924,
+      "grad_norm": 0.5974783897399902,
+      "learning_rate": 2.412244806348404e-05,
+      "loss": 1.208520770072937,
+      "step": 188
+    },
+    {
+      "epoch": 0.5191256830601093,
+      "grad_norm": 0.2837812900543213,
+      "learning_rate": 2.4096018769733402e-05,
+      "loss": 1.256629467010498,
+      "step": 190
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 0.5171183943748474,
+      "learning_rate": 2.4069214016507857e-05,
+      "loss": 1.2277578115463257,
+      "step": 192
+    },
+    {
+      "epoch": 0.5300546448087432,
+      "grad_norm": 0.5090808868408203,
+      "learning_rate": 2.4042034776558252e-05,
+      "loss": 1.2597812414169312,
+      "step": 194
+    },
+    {
+      "epoch": 0.5355191256830601,
+      "grad_norm": 0.277024507522583,
+      "learning_rate": 2.4014482036225657e-05,
+      "loss": 1.3096250295639038,
+      "step": 196
+    },
+    {
+      "epoch": 0.5409836065573771,
+      "grad_norm": 0.28094005584716797,
+      "learning_rate": 2.398655679540555e-05,
+      "loss": 1.1250698566436768,
+      "step": 198
+    },
+    {
+      "epoch": 0.546448087431694,
+      "grad_norm": 0.49337470531463623,
+      "learning_rate": 2.3958260067511546e-05,
+      "loss": 1.2817038297653198,
+      "step": 200
+    },
+    {
+      "epoch": 0.5519125683060109,
+      "grad_norm": 0.2434162199497223,
+      "learning_rate": 2.392959287943861e-05,
+      "loss": 1.095908761024475,
+      "step": 202
+    },
+    {
+      "epoch": 0.5573770491803278,
+      "grad_norm": 0.8104755282402039,
+      "learning_rate": 2.390055627152579e-05,
+      "loss": 0.9623884558677673,
+      "step": 204
+    },
+    {
+      "epoch": 0.5628415300546448,
+      "grad_norm": 0.2845552861690521,
+      "learning_rate": 2.3871151297518478e-05,
+      "loss": 1.2727272510528564,
+      "step": 206
+    },
+    {
+      "epoch": 0.5683060109289617,
+      "grad_norm": 0.30428346991539,
+      "learning_rate": 2.384137902453016e-05,
+      "loss": 1.2006559371948242,
+      "step": 208
+    },
+    {
+      "epoch": 0.5737704918032787,
+      "grad_norm": 0.5667380690574646,
+      "learning_rate": 2.381124053300368e-05,
+      "loss": 1.2453666925430298,
+      "step": 210
+    },
+    {
+      "epoch": 0.5792349726775956,
+      "grad_norm": 0.2638285458087921,
+      "learning_rate": 2.378073691667204e-05,
+      "loss": 1.5382798910140991,
+      "step": 212
+    },
+    {
+      "epoch": 0.5846994535519126,
+      "grad_norm": 0.2258531153202057,
+      "learning_rate": 2.3749869282518718e-05,
+      "loss": 1.2467749118804932,
+      "step": 214
+    },
+    {
+      "epoch": 0.5901639344262295,
+      "grad_norm": 0.4023035168647766,
+      "learning_rate": 2.3718638750737472e-05,
+      "loss": 1.6013109683990479,
+      "step": 216
+    },
+    {
+      "epoch": 0.5956284153005464,
+      "grad_norm": 0.2880134582519531,
+      "learning_rate": 2.3687046454691712e-05,
+      "loss": 1.2340466976165771,
+      "step": 218
+    },
+    {
+      "epoch": 0.6010928961748634,
+      "grad_norm": 0.21783682703971863,
+      "learning_rate": 2.3655093540873353e-05,
+      "loss": 1.3127397298812866,
+      "step": 220
+    },
+    {
+      "epoch": 0.6065573770491803,
+      "grad_norm": 0.23105667531490326,
+      "learning_rate": 2.3622781168861214e-05,
+      "loss": 1.1359162330627441,
+      "step": 222
+    },
+    {
+      "epoch": 0.6120218579234973,
+      "grad_norm": 1.055073857307434,
+      "learning_rate": 2.3590110511278933e-05,
+      "loss": 1.0895743370056152,
+      "step": 224
+    },
+    {
+      "epoch": 0.6174863387978142,
+      "grad_norm": 0.22074124217033386,
+      "learning_rate": 2.3557082753752437e-05,
+      "loss": 1.2820183038711548,
+      "step": 226
+    },
+    {
+      "epoch": 0.6229508196721312,
+      "grad_norm": 2.2928848266601562,
+      "learning_rate": 2.352369909486687e-05,
+      "loss": 1.2790377140045166,
+      "step": 228
+    },
+    {
+      "epoch": 0.6284153005464481,
+      "grad_norm": 0.1916349232196808,
+      "learning_rate": 2.3489960746123128e-05,
+      "loss": 0.7690463662147522,
+      "step": 230
+    },
+    {
+      "epoch": 0.6338797814207651,
+      "grad_norm": 0.24763409793376923,
+      "learning_rate": 2.3455868931893894e-05,
+      "loss": 1.2869762182235718,
+      "step": 232
+    },
+    {
+      "epoch": 0.639344262295082,
+      "grad_norm": 1.6581783294677734,
+      "learning_rate": 2.342142488937919e-05,
+      "loss": 0.9537703990936279,
+      "step": 234
+    },
+    {
+      "epoch": 0.644808743169399,
+      "grad_norm": 0.7167282104492188,
+      "learning_rate": 2.3386629868561492e-05,
+      "loss": 0.891618549823761,
+      "step": 236
+    },
+    {
+      "epoch": 0.6502732240437158,
+      "grad_norm": 0.4610043168067932,
+      "learning_rate": 2.3351485132160346e-05,
+      "loss": 1.3490716218948364,
+      "step": 238
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 0.44225654006004333,
+      "learning_rate": 2.331599195558659e-05,
+      "loss": 1.2553770542144775,
+      "step": 240
+    },
+    {
+      "epoch": 0.6612021857923497,
+      "grad_norm": 0.5151908993721008,
+      "learning_rate": 2.3280151626896003e-05,
+      "loss": 1.2040798664093018,
+      "step": 242
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.2373773753643036,
+      "learning_rate": 2.324396544674262e-05,
+      "loss": 1.0659421682357788,
+      "step": 244
+    },
+    {
+      "epoch": 0.6721311475409836,
+      "grad_norm": 0.2626818120479584,
+      "learning_rate": 2.3207434728331502e-05,
+      "loss": 1.2204513549804688,
+      "step": 246
+    },
+    {
+      "epoch": 0.6775956284153005,
+      "grad_norm": 0.29700711369514465,
+      "learning_rate": 2.317056079737108e-05,
+      "loss": 1.2991636991500854,
+      "step": 248
+    },
+    {
+      "epoch": 0.6830601092896175,
+      "grad_norm": 0.3610213100910187,
+      "learning_rate": 2.3133344992025057e-05,
+      "loss": 1.2486889362335205,
+      "step": 250
+    },
+    {
+      "epoch": 0.6885245901639344,
+      "grad_norm": 0.2309371531009674,
+      "learning_rate": 2.3095788662863838e-05,
+      "loss": 1.1427106857299805,
+      "step": 252
+    },
+    {
+      "epoch": 0.6939890710382514,
+      "grad_norm": 0.1426355540752411,
+      "learning_rate": 2.305789317281551e-05,
+      "loss": 1.2058444023132324,
+      "step": 254
+    },
+    {
+      "epoch": 0.6994535519125683,
+      "grad_norm": 0.19725173711776733,
+      "learning_rate": 2.30196598971164e-05,
+      "loss": 1.1971604824066162,
+      "step": 256
+    },
+    {
+      "epoch": 0.7049180327868853,
+      "grad_norm": 0.26061874628067017,
+      "learning_rate": 2.2981090223261146e-05,
+      "loss": 1.1320452690124512,
+      "step": 258
+    },
+    {
+      "epoch": 0.7103825136612022,
+      "grad_norm": 0.1859847754240036,
+      "learning_rate": 2.294218555095236e-05,
+      "loss": 1.1934643983840942,
+      "step": 260
+    },
+    {
+      "epoch": 0.7158469945355191,
+      "grad_norm": 0.21825049817562103,
+      "learning_rate": 2.2902947292049827e-05,
+      "loss": 1.2934924364089966,
+      "step": 262
+    },
+    {
+      "epoch": 0.7213114754098361,
+      "grad_norm": 0.14852340519428253,
+      "learning_rate": 2.2863376870519273e-05,
+      "loss": 1.2320027351379395,
+      "step": 264
+    },
+    {
+      "epoch": 0.726775956284153,
+      "grad_norm": 0.22215086221694946,
+      "learning_rate": 2.282347572238068e-05,
+      "loss": 1.0896164178848267,
+      "step": 266
+    },
+    {
+      "epoch": 0.73224043715847,
+      "grad_norm": 0.2927921414375305,
+      "learning_rate": 2.278324529565617e-05,
+      "loss": 1.2266433238983154,
+      "step": 268
+    },
+    {
+      "epoch": 0.7377049180327869,
+      "grad_norm": 0.19128933548927307,
+      "learning_rate": 2.274268705031748e-05,
+      "loss": 1.2257647514343262,
+      "step": 270
+    },
+    {
+      "epoch": 0.7431693989071039,
+      "grad_norm": 0.18742051720619202,
+      "learning_rate": 2.2701802458232945e-05,
+      "loss": 1.1814370155334473,
+      "step": 272
+    },
+    {
+      "epoch": 0.7486338797814208,
+      "grad_norm": 0.3515142500400543,
+      "learning_rate": 2.266059300311411e-05,
+      "loss": 1.204115867614746,
+      "step": 274
+    },
+    {
+      "epoch": 0.7540983606557377,
+      "grad_norm": 0.19052213430404663,
+      "learning_rate": 2.2619060180461873e-05,
+      "loss": 1.253179907798767,
+      "step": 276
+    },
+    {
+      "epoch": 0.7595628415300546,
+      "grad_norm": 0.21446406841278076,
+      "learning_rate": 2.2577205497512227e-05,
+      "loss": 1.221806526184082,
+      "step": 278
+    },
+    {
+      "epoch": 0.7650273224043715,
+      "grad_norm": 0.4379148483276367,
+      "learning_rate": 2.253503047318153e-05,
+      "loss": 0.8980993628501892,
+      "step": 280
+    },
+    {
+      "epoch": 0.7704918032786885,
+      "grad_norm": 0.6354475021362305,
+      "learning_rate": 2.249253663801143e-05,
+      "loss": 1.2315393686294556,
+      "step": 282
+    },
+    {
+      "epoch": 0.7759562841530054,
+      "grad_norm": 0.16127297282218933,
+      "learning_rate": 2.244972553411328e-05,
+      "loss": 1.2106963396072388,
+      "step": 284
+    },
+    {
+      "epoch": 0.7814207650273224,
+      "grad_norm": 0.16545647382736206,
+      "learning_rate": 2.2406598715112188e-05,
+      "loss": 1.2198878526687622,
+      "step": 286
+    },
+    {
+      "epoch": 0.7868852459016393,
+      "grad_norm": 0.17703773081302643,
+      "learning_rate": 2.2363157746090647e-05,
+      "loss": 1.1894257068634033,
+      "step": 288
+    },
+    {
+      "epoch": 0.7923497267759563,
+      "grad_norm": 0.18015217781066895,
+      "learning_rate": 2.231940420353173e-05,
+      "loss": 1.162126064300537,
+      "step": 290
+    },
+    {
+      "epoch": 0.7978142076502732,
+      "grad_norm": 0.971755862236023,
+      "learning_rate": 2.2275339675261865e-05,
+      "loss": 1.1871088743209839,
+      "step": 292
+    },
+    {
+      "epoch": 0.8032786885245902,
+      "grad_norm": 0.2369270771741867,
+      "learning_rate": 2.2230965760393242e-05,
+      "loss": 1.187207818031311,
+      "step": 294
+    },
+    {
+      "epoch": 0.8087431693989071,
+      "grad_norm": 0.521456778049469,
+      "learning_rate": 2.218628406926575e-05,
+      "loss": 1.5364131927490234,
+      "step": 296
+    },
+    {
+      "epoch": 0.8142076502732241,
+      "grad_norm": 0.5664535164833069,
+      "learning_rate": 2.214129622338856e-05,
+      "loss": 0.925621509552002,
+      "step": 298
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 0.24125301837921143,
+      "learning_rate": 2.2096003855381268e-05,
+      "loss": 1.6008453369140625,
+      "step": 300
+    },
+    {
+      "epoch": 0.825136612021858,
+      "grad_norm": 0.25689688324928284,
+      "learning_rate": 2.2050408608914652e-05,
+      "loss": 1.223463773727417,
+      "step": 302
+    },
+    {
+      "epoch": 0.8306010928961749,
+      "grad_norm": 0.4135361909866333,
+      "learning_rate": 2.200451213865102e-05,
+      "loss": 0.9032531380653381,
+      "step": 304
+    },
+    {
+      "epoch": 0.8360655737704918,
+      "grad_norm": 0.4481862783432007,
+      "learning_rate": 2.195831611018416e-05,
+      "loss": 1.557176113128662,
+      "step": 306
+    },
+    {
+      "epoch": 0.8415300546448088,
+      "grad_norm": 0.598118245601654,
+      "learning_rate": 2.1911822199978905e-05,
+      "loss": 1.0001596212387085,
+      "step": 308
+    },
+    {
+      "epoch": 0.8469945355191257,
+      "grad_norm": 0.1991797536611557,
+      "learning_rate": 2.186503209531028e-05,
+      "loss": 1.2186784744262695,
+      "step": 310
+    },
+    {
+      "epoch": 0.8524590163934426,
+      "grad_norm": 0.23143993318080902,
+      "learning_rate": 2.1817947494202283e-05,
+      "loss": 1.2285571098327637,
+      "step": 312
+    },
+    {
+      "epoch": 0.8579234972677595,
+      "grad_norm": 0.2992916405200958,
+      "learning_rate": 2.1770570105366253e-05,
+      "loss": 1.2401832342147827,
+      "step": 314
+    },
+    {
+      "epoch": 0.8633879781420765,
+      "grad_norm": 0.3111695945262909,
+      "learning_rate": 2.1722901648138872e-05,
+      "loss": 1.2467424869537354,
+      "step": 316
+    },
+    {
+      "epoch": 0.8688524590163934,
+      "grad_norm": 0.29361769556999207,
+      "learning_rate": 2.1674943852419754e-05,
+      "loss": 1.1437691450119019,
+      "step": 318
+    },
+    {
+      "epoch": 0.8743169398907104,
+      "grad_norm": 0.2712153196334839,
+      "learning_rate": 2.1626698458608678e-05,
+      "loss": 1.3648308515548706,
+      "step": 320
+    },
+    {
+      "epoch": 0.8797814207650273,
+      "grad_norm": 0.36124688386917114,
+      "learning_rate": 2.1578167217542434e-05,
+      "loss": 1.098549485206604,
+      "step": 322
+    },
+    {
+      "epoch": 0.8852459016393442,
+      "grad_norm": 0.38840731978416443,
+      "learning_rate": 2.1529351890431267e-05,
+      "loss": 0.7575273513793945,
+      "step": 324
+    },
+    {
+      "epoch": 0.8907103825136612,
+      "grad_norm": 0.26621684432029724,
+      "learning_rate": 2.1480254248794972e-05,
+      "loss": 1.25328528881073,
+      "step": 326
+    },
+    {
+      "epoch": 0.8961748633879781,
+      "grad_norm": 0.3533453643321991,
+      "learning_rate": 2.1430876074398613e-05,
+      "loss": 1.0998711585998535,
+      "step": 328
+    },
+    {
+      "epoch": 0.9016393442622951,
+      "grad_norm": 0.2502342164516449,
+      "learning_rate": 2.138121915918785e-05,
+      "loss": 1.2683922052383423,
+      "step": 330
+    },
+    {
+      "epoch": 0.907103825136612,
+      "grad_norm": 1.4214491844177246,
+      "learning_rate": 2.133128530522391e-05,
+      "loss": 1.303632140159607,
+      "step": 332
+    },
+    {
+      "epoch": 0.912568306010929,
+      "grad_norm": 0.4628271162509918,
+      "learning_rate": 2.1281076324618197e-05,
+      "loss": 1.1815130710601807,
+      "step": 334
+    },
+    {
+      "epoch": 0.9180327868852459,
+      "grad_norm": 0.29728227853775024,
+      "learning_rate": 2.123059403946653e-05,
+      "loss": 1.2302957773208618,
+      "step": 336
+    },
+    {
+      "epoch": 0.9234972677595629,
+      "grad_norm": 0.26023662090301514,
+      "learning_rate": 2.1179840281783002e-05,
+      "loss": 1.2583401203155518,
+      "step": 338
+    },
+    {
+      "epoch": 0.9289617486338798,
+      "grad_norm": 0.20131556689739227,
+      "learning_rate": 2.1128816893433524e-05,
+      "loss": 1.2529937028884888,
+      "step": 340
+    },
+    {
+      "epoch": 0.9344262295081968,
+      "grad_norm": 0.2651193141937256,
+      "learning_rate": 2.107752572606895e-05,
+      "loss": 1.2728800773620605,
+      "step": 342
+    },
+    {
+      "epoch": 0.9398907103825137,
+      "grad_norm": 1.3046387434005737,
+      "learning_rate": 2.1025968641057917e-05,
+      "loss": 1.2606099843978882,
+      "step": 344
+    },
+    {
+      "epoch": 0.9453551912568307,
+      "grad_norm": 0.23248107731342316,
+      "learning_rate": 2.097414750941927e-05,
+      "loss": 1.6241867542266846,
+      "step": 346
+    },
+    {
+      "epoch": 0.9508196721311475,
+      "grad_norm": 0.457072913646698,
+      "learning_rate": 2.092206421175416e-05,
+      "loss": 1.0590146780014038,
+      "step": 348
+    },
+    {
+      "epoch": 0.9562841530054644,
+      "grad_norm": 0.19466765224933624,
+      "learning_rate": 2.0869720638177817e-05,
+      "loss": 0.9096658825874329,
+      "step": 350
+    },
+    {
+      "epoch": 0.9617486338797814,
+      "grad_norm": 0.2271135449409485,
+      "learning_rate": 2.0817118688250933e-05,
+      "loss": 1.2334853410720825,
+      "step": 352
+    },
+    {
+      "epoch": 0.9672131147540983,
+      "grad_norm": 0.2870445251464844,
+      "learning_rate": 2.0764260270910753e-05,
+      "loss": 0.9327258467674255,
+      "step": 354
+    },
+    {
+      "epoch": 0.9726775956284153,
+      "grad_norm": 0.3647417724132538,
+      "learning_rate": 2.0711147304401775e-05,
+      "loss": 1.1043840646743774,
+      "step": 356
+    },
+    {
+      "epoch": 0.9781420765027322,
+      "grad_norm": 0.2910922169685364,
+      "learning_rate": 2.0657781716206156e-05,
+      "loss": 0.7837404608726501,
+      "step": 358
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 0.26856181025505066,
+      "learning_rate": 2.0604165442973738e-05,
+      "loss": 1.2202802896499634,
+      "step": 360
+    },
+    {
+      "epoch": 0.9890710382513661,
+      "grad_norm": 0.7940663695335388,
+      "learning_rate": 2.0550300430451805e-05,
+      "loss": 0.9926665425300598,
+      "step": 362
+    },
+    {
+      "epoch": 0.994535519125683,
+      "grad_norm": 0.3847670257091522,
+      "learning_rate": 2.049618863341443e-05,
+      "loss": 1.2039496898651123,
+      "step": 364
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4092676043510437,
+      "learning_rate": 2.0441832015591565e-05,
+      "loss": 1.1870145797729492,
+      "step": 366
+    },
+    {
+      "epoch": 1.005464480874317,
+      "grad_norm": 0.2678527235984802,
+      "learning_rate": 2.038723254959775e-05,
+      "loss": 1.052931785583496,
+      "step": 368
+    },
+    {
+      "epoch": 1.010928961748634,
+      "grad_norm": 0.3561493158340454,
+      "learning_rate": 2.033239221686057e-05,
+      "loss": 0.9613900780677795,
+      "step": 370
+    },
+    {
+      "epoch": 1.0163934426229508,
+      "grad_norm": 0.3432145416736603,
+      "learning_rate": 2.0277313007548702e-05,
+      "loss": 0.9641975164413452,
+      "step": 372
+    },
+    {
+      "epoch": 1.0218579234972678,
+      "grad_norm": 0.5496553778648376,
+      "learning_rate": 2.022199692049971e-05,
+      "loss": 0.9910390377044678,
+      "step": 374
+    },
+    {
+      "epoch": 1.0273224043715847,
+      "grad_norm": 1.1139615774154663,
+      "learning_rate": 2.0166445963147514e-05,
+      "loss": 0.8240501284599304,
+      "step": 376
+    },
+    {
+      "epoch": 1.0327868852459017,
+      "grad_norm": 0.38149014115333557,
+      "learning_rate": 2.0110662151449538e-05,
+      "loss": 0.9968246817588806,
+      "step": 378
+    },
+    {
+      "epoch": 1.0382513661202186,
+      "grad_norm": 0.41972488164901733,
+      "learning_rate": 2.0054647509813533e-05,
+      "loss": 0.705604612827301,
+      "step": 380
+    },
+    {
+      "epoch": 1.0437158469945356,
+      "grad_norm": 0.7368504405021667,
+      "learning_rate": 1.9998404071024132e-05,
+      "loss": 0.833368718624115,
+      "step": 382
+    },
+    {
+      "epoch": 1.0491803278688525,
+      "grad_norm": 0.2574571967124939,
+      "learning_rate": 1.9941933876169064e-05,
+      "loss": 0.9591267704963684,
+      "step": 384
+    },
+    {
+      "epoch": 1.0546448087431695,
+      "grad_norm": 0.6520720720291138,
+      "learning_rate": 1.9885238974565092e-05,
+      "loss": 0.7256029844284058,
+      "step": 386
+    },
+    {
+      "epoch": 1.0601092896174864,
+      "grad_norm": 0.43294209241867065,
+      "learning_rate": 1.982832142368365e-05,
+      "loss": 0.6323433518409729,
+      "step": 388
+    },
+    {
+      "epoch": 1.0655737704918034,
+      "grad_norm": 0.29659733176231384,
+      "learning_rate": 1.9771183289076148e-05,
+      "loss": 1.1004457473754883,
+      "step": 390
+    },
+    {
+      "epoch": 1.0710382513661203,
+      "grad_norm": 0.19339755177497864,
+      "learning_rate": 1.9713826644299056e-05,
+      "loss": 0.9760780334472656,
+      "step": 392
+    },
+    {
+      "epoch": 1.0765027322404372,
+      "grad_norm": 0.2182750552892685,
+      "learning_rate": 1.96562535708386e-05,
+      "loss": 0.6805109977722168,
+      "step": 394
+    },
+    {
+      "epoch": 1.0819672131147542,
+      "grad_norm": 0.26215946674346924,
+      "learning_rate": 1.959846615803528e-05,
+      "loss": 1.012329339981079,
+      "step": 396
+    },
+    {
+      "epoch": 1.0874316939890711,
+      "grad_norm": 0.220313161611557,
+      "learning_rate": 1.954046650300801e-05,
+      "loss": 0.9814585447311401,
+      "step": 398
+    },
+    {
+      "epoch": 1.092896174863388,
+      "grad_norm": 0.339661568403244,
+      "learning_rate": 1.9482256710578028e-05,
+      "loss": 1.0675204992294312,
+      "step": 400
+    },
+    {
+      "epoch": 1.098360655737705,
+      "grad_norm": 0.5715194344520569,
+      "learning_rate": 1.94238388931925e-05,
+      "loss": 1.002265214920044,
+      "step": 402
+    },
+    {
+      "epoch": 1.1038251366120218,
+      "grad_norm": 0.326412171125412,
+      "learning_rate": 1.9365215170847887e-05,
+      "loss": 1.1493186950683594,
+      "step": 404
+    },
+    {
+      "epoch": 1.1092896174863387,
+      "grad_norm": 0.781463086605072,
+      "learning_rate": 1.9306387671012965e-05,
+      "loss": 0.9932349920272827,
+      "step": 406
+    },
+    {
+      "epoch": 1.1147540983606556,
+      "grad_norm": 0.7584837675094604,
+      "learning_rate": 1.9247358528551662e-05,
+      "loss": 0.6940405368804932,
+      "step": 408
+    },
+    {
+      "epoch": 1.1202185792349726,
+      "grad_norm": 0.2473216950893402,
+      "learning_rate": 1.918812988564555e-05,
+      "loss": 1.1692583560943604,
+      "step": 410
+    },
+    {
+      "epoch": 1.1256830601092895,
+      "grad_norm": 0.4508194923400879,
+      "learning_rate": 1.9128703891716138e-05,
+      "loss": 0.7730159759521484,
+      "step": 412
+    },
+    {
+      "epoch": 1.1311475409836065,
+      "grad_norm": 0.20886428654193878,
+      "learning_rate": 1.906908270334683e-05,
+      "loss": 0.8129177689552307,
+      "step": 414
+    },
+    {
+      "epoch": 1.1366120218579234,
+      "grad_norm": 1.0284196138381958,
+      "learning_rate": 1.90092684842047e-05,
+      "loss": 0.7486385703086853,
+      "step": 416
+    },
+    {
+      "epoch": 1.1420765027322404,
+      "grad_norm": 0.29529622197151184,
+      "learning_rate": 1.8949263404961936e-05,
+      "loss": 0.9710283279418945,
+      "step": 418
+    },
+    {
+      "epoch": 1.1475409836065573,
+      "grad_norm": 0.19345751404762268,
+      "learning_rate": 1.888906964321711e-05,
+      "loss": 0.9194430112838745,
+      "step": 420
+    },
+    {
+      "epoch": 1.1530054644808743,
+      "grad_norm": 0.1850510686635971,
+      "learning_rate": 1.88286893834161e-05,
+      "loss": 1.015109896659851,
+      "step": 422
+    },
+    {
+      "epoch": 1.1584699453551912,
+      "grad_norm": 1.9381911754608154,
+      "learning_rate": 1.8768124816772854e-05,
+      "loss": 0.7446098327636719,
+      "step": 424
+    },
+    {
+      "epoch": 1.1639344262295082,
+      "grad_norm": 0.8182835578918457,
+      "learning_rate": 1.870737814118987e-05,
+      "loss": 0.7042106986045837,
+      "step": 426
+    },
+    {
+      "epoch": 1.169398907103825,
+      "grad_norm": 0.3277008831501007,
+      "learning_rate": 1.86464515611784e-05,
+      "loss": 1.1486928462982178,
+      "step": 428
+    },
+    {
+      "epoch": 1.174863387978142,
+      "grad_norm": 0.23618929088115692,
+      "learning_rate": 1.8585347287778493e-05,
+      "loss": 0.9731719493865967,
+      "step": 430
+    },
+    {
+      "epoch": 1.180327868852459,
+      "grad_norm": 0.2742961645126343,
+      "learning_rate": 1.8524067538478713e-05,
+      "loss": 1.040266752243042,
+      "step": 432
+    },
+    {
+      "epoch": 1.185792349726776,
+      "grad_norm": 0.27158892154693604,
+      "learning_rate": 1.8462614537135708e-05,
+      "loss": 0.8597835898399353,
+      "step": 434
+    },
+    {
+      "epoch": 1.1912568306010929,
+      "grad_norm": 0.2809169292449951,
+      "learning_rate": 1.840099051389346e-05,
+      "loss": 1.0985636711120605,
+      "step": 436
+    },
+    {
+      "epoch": 1.1967213114754098,
+      "grad_norm": 0.27836382389068604,
+      "learning_rate": 1.8339197705102396e-05,
+      "loss": 0.9655686616897583,
+      "step": 438
+    },
+    {
+      "epoch": 1.2021857923497268,
+      "grad_norm": 0.2705060839653015,
+      "learning_rate": 1.8277238353238193e-05,
+      "loss": 0.8749003410339355,
+      "step": 440
+    },
+    {
+      "epoch": 1.2076502732240437,
+      "grad_norm": 0.40282824635505676,
+      "learning_rate": 1.8215114706820435e-05,
+      "loss": 0.9861440062522888,
+      "step": 442
+    },
+    {
+      "epoch": 1.2131147540983607,
+      "grad_norm": 0.28667566180229187,
+      "learning_rate": 1.8152829020330975e-05,
+      "loss": 0.9603111743927002,
+      "step": 444
+    },
+    {
+      "epoch": 1.2185792349726776,
+      "grad_norm": 0.20321297645568848,
+      "learning_rate": 1.8090383554132158e-05,
+      "loss": 0.6063272953033447,
+      "step": 446
+    },
+    {
+      "epoch": 1.2240437158469946,
+      "grad_norm": 0.2519320845603943,
+      "learning_rate": 1.8027780574384753e-05,
+      "loss": 1.0045597553253174,
+      "step": 448
+    },
+    {
+      "epoch": 1.2295081967213115,
+      "grad_norm": 0.2760215401649475,
+      "learning_rate": 1.796502235296575e-05,
+      "loss": 0.9750694036483765,
+      "step": 450
+    },
+    {
+      "epoch": 1.2349726775956285,
+      "grad_norm": 1.3805330991744995,
+      "learning_rate": 1.7902111167385883e-05,
+      "loss": 0.9757618308067322,
+      "step": 452
+    },
+    {
+      "epoch": 1.2404371584699454,
+      "grad_norm": 0.41420966386795044,
+      "learning_rate": 1.7839049300707003e-05,
+      "loss": 1.1883511543273926,
+      "step": 454
+    },
+    {
+      "epoch": 1.2459016393442623,
+      "grad_norm": 3.457296371459961,
+      "learning_rate": 1.7775839041459203e-05,
+      "loss": 0.8075215816497803,
+      "step": 456
+    },
+    {
+      "epoch": 1.2513661202185793,
+      "grad_norm": 0.41424238681793213,
+      "learning_rate": 1.7712482683557778e-05,
+      "loss": 0.7205969095230103,
+      "step": 458
+    },
+    {
+      "epoch": 1.2568306010928962,
+      "grad_norm": 0.23676064610481262,
+      "learning_rate": 1.7648982526219995e-05,
+      "loss": 0.9795306324958801,
+      "step": 460
+    },
+    {
+      "epoch": 1.2622950819672132,
+      "grad_norm": 0.5828472375869751,
+      "learning_rate": 1.7585340873881617e-05,
+      "loss": 0.7240006923675537,
+      "step": 462
+    },
+    {
+      "epoch": 1.2677595628415301,
+      "grad_norm": 0.41735684871673584,
+      "learning_rate": 1.7521560036113303e-05,
+      "loss": 0.9175815582275391,
+      "step": 464
+    },
+    {
+      "epoch": 1.273224043715847,
+      "grad_norm": 1.274187684059143,
+      "learning_rate": 1.7457642327536777e-05,
+      "loss": 1.003617763519287,
+      "step": 466
+    },
+    {
+      "epoch": 1.278688524590164,
+      "grad_norm": 0.19330422580242157,
+      "learning_rate": 1.7393590067740852e-05,
+      "loss": 0.9662733674049377,
+      "step": 468
+    },
+    {
+      "epoch": 1.2841530054644807,
+      "grad_norm": 0.4729224443435669,
+      "learning_rate": 1.732940558119722e-05,
+      "loss": 1.0254093408584595,
+      "step": 470
+    },
+    {
+      "epoch": 1.289617486338798,
+      "grad_norm": 0.2658669352531433,
+      "learning_rate": 1.726509119717612e-05,
+      "loss": 1.1315693855285645,
+      "step": 472
+    },
+    {
+      "epoch": 1.2950819672131146,
+      "grad_norm": 0.17870910465717316,
+      "learning_rate": 1.7200649249661806e-05,
+      "loss": 1.0432623624801636,
+      "step": 474
+    },
+    {
+      "epoch": 1.3005464480874318,
+      "grad_norm": 0.6331385970115662,
+      "learning_rate": 1.7136082077267837e-05,
+      "loss": 0.4694063067436218,
+      "step": 476
+    },
+    {
+      "epoch": 1.3060109289617485,
+      "grad_norm": 0.24067234992980957,
+      "learning_rate": 1.7071392023152208e-05,
+      "loss": 0.9866682291030884,
+      "step": 478
+    },
+    {
+      "epoch": 1.3114754098360657,
+      "grad_norm": 0.2517263889312744,
+      "learning_rate": 1.700658143493233e-05,
+      "loss": 1.1108297109603882,
+      "step": 480
+    },
+    {
+      "epoch": 1.3169398907103824,
+      "grad_norm": 0.15475492179393768,
+      "learning_rate": 1.6941652664599814e-05,
+      "loss": 0.8292356133460999,
+      "step": 482
+    },
+    {
+      "epoch": 1.3224043715846996,
+      "grad_norm": 0.412447988986969,
+      "learning_rate": 1.687660806843514e-05,
+      "loss": 0.6224348545074463,
+      "step": 484
+    },
+    {
+      "epoch": 1.3278688524590163,
+      "grad_norm": 0.20403409004211426,
+      "learning_rate": 1.681145000692213e-05,
+      "loss": 0.9716439843177795,
+      "step": 486
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.32221364974975586,
+      "learning_rate": 1.6746180844662286e-05,
+      "loss": 0.9632929563522339,
+      "step": 488
+    },
+    {
+      "epoch": 1.3387978142076502,
+      "grad_norm": 0.4680832028388977,
+      "learning_rate": 1.6680802950288988e-05,
+      "loss": 0.678726851940155,
+      "step": 490
+    },
+    {
+      "epoch": 1.3442622950819672,
+      "grad_norm": 0.24255001544952393,
+      "learning_rate": 1.661531869638153e-05,
+      "loss": 1.0519957542419434,
+      "step": 492
+    },
+    {
+      "epoch": 1.349726775956284,
+      "grad_norm": 0.14533624053001404,
+      "learning_rate": 1.6549730459379012e-05,
+      "loss": 0.7603930234909058,
+      "step": 494
+    },
+    {
+      "epoch": 1.355191256830601,
+      "grad_norm": 0.29373615980148315,
+      "learning_rate": 1.648404061949412e-05,
+      "loss": 1.014536738395691,
+      "step": 496
+    },
+    {
+      "epoch": 1.360655737704918,
+      "grad_norm": 0.8250491619110107,
+      "learning_rate": 1.641825156062671e-05,
+      "loss": 0.9662138223648071,
+      "step": 498
+    },
+    {
+      "epoch": 1.366120218579235,
+      "grad_norm": 0.2744878828525543,
+      "learning_rate": 1.635236567027734e-05,
+      "loss": 1.1449735164642334,
+      "step": 500
+    },
+    {
+      "epoch": 1.3715846994535519,
+      "grad_norm": 0.3034563362598419,
+      "learning_rate": 1.6286385339460596e-05,
+      "loss": 0.9222993850708008,
+      "step": 502
+    },
+    {
+      "epoch": 1.3770491803278688,
+      "grad_norm": 0.2692282795906067,
+      "learning_rate": 1.6220312962618332e-05,
+      "loss": 0.6134414076805115,
+      "step": 504
+    },
+    {
+      "epoch": 1.3825136612021858,
+      "grad_norm": 0.5227485299110413,
+      "learning_rate": 1.6154150937532775e-05,
+      "loss": 0.9774447679519653,
+      "step": 506
+    },
+    {
+      "epoch": 1.3879781420765027,
+      "grad_norm": 0.2803296148777008,
+      "learning_rate": 1.6087901665239502e-05,
+      "loss": 0.9835152626037598,
+      "step": 508
+    },
+    {
+      "epoch": 1.3934426229508197,
+      "grad_norm": 0.3903689980506897,
+      "learning_rate": 1.602156754994032e-05,
+      "loss": 1.0372285842895508,
+      "step": 510
+    },
+    {
+      "epoch": 1.3989071038251366,
+      "grad_norm": 0.18825502693653107,
+      "learning_rate": 1.5955150998916003e-05,
+      "loss": 0.9928014874458313,
+      "step": 512
+    },
+    {
+      "epoch": 1.4043715846994536,
+      "grad_norm": 0.1467607021331787,
+      "learning_rate": 1.5888654422438946e-05,
+      "loss": 0.793111264705658,
+      "step": 514
+    },
+    {
+      "epoch": 1.4098360655737705,
+      "grad_norm": 0.1626003533601761,
+      "learning_rate": 1.5822080233685678e-05,
+      "loss": 0.6302416324615479,
+      "step": 516
+    },
+    {
+      "epoch": 1.4153005464480874,
+      "grad_norm": 0.21208561956882477,
+      "learning_rate": 1.575543084864929e-05,
+      "loss": 1.056746006011963,
+      "step": 518
+    },
+    {
+      "epoch": 1.4207650273224044,
+      "grad_norm": 0.5272570252418518,
+      "learning_rate": 1.5688708686051784e-05,
+      "loss": 0.6418699026107788,
+      "step": 520
+    },
+    {
+      "epoch": 1.4262295081967213,
+      "grad_norm": 0.2039785534143448,
+      "learning_rate": 1.5621916167256255e-05,
+      "loss": 0.9852989315986633,
+      "step": 522
+    },
+    {
+      "epoch": 1.4316939890710383,
+      "grad_norm": 2.6706042289733887,
+      "learning_rate": 1.555505571617906e-05,
+      "loss": 0.786631166934967,
+      "step": 524
+    },
+    {
+      "epoch": 1.4371584699453552,
+      "grad_norm": 0.8656861186027527,
+      "learning_rate": 1.5488129759201822e-05,
+      "loss": 0.9886066913604736,
+      "step": 526
+    },
+    {
+      "epoch": 1.4426229508196722,
+      "grad_norm": 0.3004356920719147,
+      "learning_rate": 1.5421140725083388e-05,
+      "loss": 0.6762040257453918,
+      "step": 528
+    },
+    {
+      "epoch": 1.4480874316939891,
+      "grad_norm": 0.6082632541656494,
+      "learning_rate": 1.53540910448717e-05,
+      "loss": 0.7938519716262817,
+      "step": 530
+    },
+    {
+      "epoch": 1.453551912568306,
+      "grad_norm": 0.4222017824649811,
+      "learning_rate": 1.5286983151815553e-05,
+      "loss": 0.5967254042625427,
+      "step": 532
+    },
+    {
+      "epoch": 1.459016393442623,
+      "grad_norm": 0.20243442058563232,
+      "learning_rate": 1.52198194812763e-05,
+      "loss": 0.9870072603225708,
+      "step": 534
+    },
+    {
+      "epoch": 1.46448087431694,
+      "grad_norm": 0.21171127259731293,
+      "learning_rate": 1.515260247063948e-05,
+      "loss": 0.9821056127548218,
+      "step": 536
+    },
+    {
+      "epoch": 1.469945355191257,
+      "grad_norm": 0.19740687310695648,
+      "learning_rate": 1.5085334559226342e-05,
+      "loss": 0.9811551570892334,
+      "step": 538
+    },
+    {
+      "epoch": 1.4754098360655736,
+      "grad_norm": 0.1451021134853363,
+      "learning_rate": 1.5018018188205354e-05,
+      "loss": 1.0408740043640137,
+      "step": 540
+    },
+    {
+      "epoch": 1.4808743169398908,
+      "grad_norm": 0.2504618763923645,
+      "learning_rate": 1.4950655800503577e-05,
+      "loss": 0.967536985874176,
+      "step": 542
+    },
+    {
+      "epoch": 1.4863387978142075,
+      "grad_norm": 0.2872159481048584,
+      "learning_rate": 1.4883249840718045e-05,
+      "loss": 0.8747035264968872,
+      "step": 544
+    },
+    {
+      "epoch": 1.4918032786885247,
+      "grad_norm": 0.7941830158233643,
+      "learning_rate": 1.4815802755027019e-05,
+      "loss": 1.1690365076065063,
+      "step": 546
+    },
+    {
+      "epoch": 1.4972677595628414,
+      "grad_norm": 0.818136990070343,
+      "learning_rate": 1.474831699110124e-05,
+      "loss": 0.5261512994766235,
+      "step": 548
+    },
+    {
+      "epoch": 1.5027322404371586,
+      "grad_norm": 0.25710561871528625,
+      "learning_rate": 1.4680794998015081e-05,
+      "loss": 0.9896012544631958,
+      "step": 550
+    },
+    {
+      "epoch": 1.5081967213114753,
+      "grad_norm": 0.2098042219877243,
+      "learning_rate": 1.4613239226157693e-05,
+      "loss": 0.9484928250312805,
+      "step": 552
+    },
+    {
+      "epoch": 1.5136612021857925,
+      "grad_norm": 0.21850721538066864,
+      "learning_rate": 1.4545652127144052e-05,
+      "loss": 0.9997845888137817,
+      "step": 554
+    },
+    {
+      "epoch": 1.5191256830601092,
+      "grad_norm": 0.2467595338821411,
+      "learning_rate": 1.4478036153726013e-05,
+      "loss": 0.9743095636367798,
+      "step": 556
+    },
+    {
+      "epoch": 1.5245901639344264,
+      "grad_norm": 0.23051407933235168,
+      "learning_rate": 1.4410393759703286e-05,
+      "loss": 0.7760718464851379,
+      "step": 558
+    },
+    {
+      "epoch": 1.530054644808743,
+      "grad_norm": 0.29818111658096313,
+      "learning_rate": 1.4342727399834396e-05,
+      "loss": 0.6354138851165771,
+      "step": 560
+    },
+    {
+      "epoch": 1.5355191256830603,
+      "grad_norm": 0.5161439180374146,
+      "learning_rate": 1.4275039529747592e-05,
+      "loss": 0.893290638923645,
+      "step": 562
+    },
+    {
+      "epoch": 1.540983606557377,
+      "grad_norm": 0.8079479336738586,
+      "learning_rate": 1.4207332605851725e-05,
+      "loss": 0.7297835946083069,
+      "step": 564
+    },
+    {
+      "epoch": 1.5464480874316942,
+      "grad_norm": 0.19712623953819275,
+      "learning_rate": 1.413960908524713e-05,
+      "loss": 0.9552266597747803,
+      "step": 566
+    },
+    {
+      "epoch": 1.5519125683060109,
+      "grad_norm": 0.35008788108825684,
+      "learning_rate": 1.407187142563643e-05,
+      "loss": 0.7161392569541931,
+      "step": 568
+    },
+    {
+      "epoch": 1.5573770491803278,
+      "grad_norm": 0.30580294132232666,
+      "learning_rate": 1.4004122085235349e-05,
+      "loss": 1.1108880043029785,
+      "step": 570
+    },
+    {
+      "epoch": 1.5628415300546448,
+      "grad_norm": 0.28407377004623413,
+      "learning_rate": 1.3936363522683532e-05,
+      "loss": 0.9953396916389465,
+      "step": 572
+    },
+    {
+      "epoch": 1.5683060109289617,
+      "grad_norm": 0.3069007396697998,
+      "learning_rate": 1.3868598196955273e-05,
+      "loss": 0.9776367545127869,
+      "step": 574
+    },
+    {
+      "epoch": 1.5737704918032787,
+      "grad_norm": 0.22995546460151672,
+      "learning_rate": 1.3800828567270318e-05,
+      "loss": 0.7785615921020508,
+      "step": 576
+    },
+    {
+      "epoch": 1.5792349726775956,
+      "grad_norm": 0.33251991868019104,
+      "learning_rate": 1.3733057093004605e-05,
+      "loss": 1.0668448209762573,
+      "step": 578
+    },
+    {
+      "epoch": 1.5846994535519126,
+      "grad_norm": 0.46238404512405396,
+      "learning_rate": 1.3665286233601002e-05,
+      "loss": 0.577606201171875,
+      "step": 580
+    },
+    {
+      "epoch": 1.5901639344262295,
+      "grad_norm": 0.29064756631851196,
+      "learning_rate": 1.3597518448480075e-05,
+      "loss": 0.6106272339820862,
+      "step": 582
+    },
+    {
+      "epoch": 1.5956284153005464,
+      "grad_norm": 0.39371079206466675,
+      "learning_rate": 1.3529756196950815e-05,
+      "loss": 0.741959810256958,
+      "step": 584
+    },
+    {
+      "epoch": 1.6010928961748634,
+      "grad_norm": 0.19503989815711975,
+      "learning_rate": 1.3462001938121405e-05,
+      "loss": 1.024315595626831,
+      "step": 586
+    },
+    {
+      "epoch": 1.6065573770491803,
+      "grad_norm": 0.222434401512146,
+      "learning_rate": 1.3394258130809961e-05,
+      "loss": 1.0157414674758911,
+      "step": 588
+    },
+    {
+      "epoch": 1.6120218579234973,
+      "grad_norm": 0.2086457908153534,
+      "learning_rate": 1.332652723345533e-05,
+      "loss": 0.7172755002975464,
+      "step": 590
+    },
+    {
+      "epoch": 1.6174863387978142,
+      "grad_norm": 0.25153470039367676,
+      "learning_rate": 1.3258811704027823e-05,
+      "loss": 0.9605967998504639,
+      "step": 592
+    },
+    {
+      "epoch": 1.6229508196721312,
+      "grad_norm": 1.1914056539535522,
+      "learning_rate": 1.3191113999940072e-05,
+      "loss": 0.7792953252792358,
+      "step": 594
+    },
+    {
+      "epoch": 1.6284153005464481,
+      "grad_norm": 0.3395598828792572,
+      "learning_rate": 1.3123436577957814e-05,
+      "loss": 0.39568331837654114,
+      "step": 596
+    },
+    {
+      "epoch": 1.633879781420765,
+      "grad_norm": 0.21833889186382294,
+      "learning_rate": 1.305578189411075e-05,
+      "loss": 0.997237503528595,
+      "step": 598
+    },
+    {
+      "epoch": 1.639344262295082,
+      "grad_norm": 0.4959961771965027,
+      "learning_rate": 1.2988152403603387e-05,
+      "loss": 1.0844365358352661,
+      "step": 600
+    },
+    {
+      "epoch": 1.644808743169399,
+      "grad_norm": 0.17567996680736542,
+      "learning_rate": 1.2920550560725985e-05,
+      "loss": 1.0519412755966187,
+      "step": 602
+    },
+    {
+      "epoch": 1.650273224043716,
+      "grad_norm": 0.2537671625614166,
+      "learning_rate": 1.2852978818765457e-05,
+      "loss": 1.0641611814498901,
+      "step": 604
+    },
+    {
+      "epoch": 1.6557377049180326,
+      "grad_norm": 0.272575318813324,
+      "learning_rate": 1.2785439629916346e-05,
+      "loss": 1.0360894203186035,
+      "step": 606
+    },
+    {
+      "epoch": 1.6612021857923498,
+      "grad_norm": 0.22028231620788574,
+      "learning_rate": 1.2717935445191823e-05,
+      "loss": 0.8390608429908752,
+      "step": 608
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.2603016793727875,
+      "learning_rate": 1.2650468714334764e-05,
+      "loss": 1.0364290475845337,
+      "step": 610
+    },
+    {
+      "epoch": 1.6721311475409837,
+      "grad_norm": 0.9713470339775085,
+      "learning_rate": 1.2583041885728841e-05,
+      "loss": 0.6826381087303162,
+      "step": 612
+    },
+    {
+      "epoch": 1.6775956284153004,
+      "grad_norm": 0.23464682698249817,
+      "learning_rate": 1.2515657406309653e-05,
+      "loss": 0.9781528115272522,
+      "step": 614
+    },
+    {
+      "epoch": 1.6830601092896176,
+      "grad_norm": 0.2752858102321625,
+      "learning_rate": 1.2448317721475938e-05,
+      "loss": 1.009163737297058,
+      "step": 616
+    },
+    {
+      "epoch": 1.6885245901639343,
+      "grad_norm": 0.19153419137001038,
+      "learning_rate": 1.2381025275000826e-05,
+      "loss": 0.5738469362258911,
+      "step": 618
+    },
+    {
+      "epoch": 1.6939890710382515,
+      "grad_norm": 0.2596787214279175,
+      "learning_rate": 1.2313782508943165e-05,
+      "loss": 0.9725096225738525,
+      "step": 620
+    },
+    {
+      "epoch": 1.6994535519125682,
+      "grad_norm": 0.36354807019233704,
+      "learning_rate": 1.224659186355888e-05,
+      "loss": 1.1703816652297974,
+      "step": 622
+    },
+    {
+      "epoch": 1.7049180327868854,
+      "grad_norm": 0.2569591701030731,
+      "learning_rate": 1.2179455777212426e-05,
+      "loss": 0.6586411595344543,
+      "step": 624
+    },
+    {
+      "epoch": 1.710382513661202,
+      "grad_norm": 0.14563089609146118,
+      "learning_rate": 1.2112376686288302e-05,
+      "loss": 0.5979112386703491,
+      "step": 626
+    },
+    {
+      "epoch": 1.7158469945355193,
+      "grad_norm": 0.17862805724143982,
+      "learning_rate": 1.204535702510263e-05,
+      "loss": 1.0485451221466064,
+      "step": 628
+    },
+    {
+      "epoch": 1.721311475409836,
+      "grad_norm": 0.46438074111938477,
+      "learning_rate": 1.1978399225814802e-05,
+      "loss": 0.7404160499572754,
+      "step": 630
+    },
+    {
+      "epoch": 1.7267759562841531,
+      "grad_norm": 0.16041846573352814,
+      "learning_rate": 1.1911505718339238e-05,
+      "loss": 0.9989252686500549,
+      "step": 632
+    },
+    {
+      "epoch": 1.7322404371584699,
+      "grad_norm": 0.16997864842414856,
+      "learning_rate": 1.1844678930257189e-05,
+      "loss": 1.0865825414657593,
+      "step": 634
+    },
+    {
+      "epoch": 1.737704918032787,
+      "grad_norm": 0.19891749322414398,
+      "learning_rate": 1.1777921286728649e-05,
+      "loss": 0.8886318206787109,
+      "step": 636
+    },
+    {
+      "epoch": 1.7431693989071038,
+      "grad_norm": 0.1822405755519867,
+      "learning_rate": 1.1711235210404322e-05,
+      "loss": 0.9987983107566833,
+      "step": 638
+    },
+    {
+      "epoch": 1.748633879781421,
+      "grad_norm": 0.5658647418022156,
+      "learning_rate": 1.1644623121337744e-05,
+      "loss": 0.8494293689727783,
+      "step": 640
+    },
+    {
+      "epoch": 1.7540983606557377,
+      "grad_norm": 0.2527749836444855,
+      "learning_rate": 1.1578087436897425e-05,
+      "loss": 1.0923233032226562,
+      "step": 642
+    },
+    {
+      "epoch": 1.7595628415300546,
+      "grad_norm": 0.17464260756969452,
+      "learning_rate": 1.1511630571679133e-05,
+      "loss": 0.9967983961105347,
+      "step": 644
+    },
+    {
+      "epoch": 1.7650273224043715,
+      "grad_norm": 0.18370413780212402,
+      "learning_rate": 1.1445254937418262e-05,
+      "loss": 0.6361693739891052,
+      "step": 646
+    },
+    {
+      "epoch": 1.7704918032786885,
+      "grad_norm": 0.277452290058136,
+      "learning_rate": 1.1378962942902325e-05,
+      "loss": 0.9944519996643066,
+      "step": 648
+    },
+    {
+      "epoch": 1.7759562841530054,
+      "grad_norm": 0.17650683224201202,
+      "learning_rate": 1.1312756993883528e-05,
+      "loss": 0.9504789113998413,
+      "step": 650
+    },
+    {
+      "epoch": 1.7814207650273224,
+      "grad_norm": 0.1316922903060913,
+      "learning_rate": 1.1246639492991464e-05,
+      "loss": 0.9381383657455444,
+      "step": 652
+    },
+    {
+      "epoch": 1.7868852459016393,
+      "grad_norm": 0.44887641072273254,
+      "learning_rate": 1.1180612839645918e-05,
+      "loss": 0.9580968022346497,
+      "step": 654
+    },
+    {
+      "epoch": 1.7923497267759563,
+      "grad_norm": 0.5374517440795898,
+      "learning_rate": 1.1114679429969799e-05,
+      "loss": 0.8842057585716248,
+      "step": 656
+    },
+    {
+      "epoch": 1.7978142076502732,
+      "grad_norm": 0.2197987288236618,
+      "learning_rate": 1.1048841656702183e-05,
+      "loss": 0.6668030023574829,
+      "step": 658
+    },
+    {
+      "epoch": 1.8032786885245902,
+      "grad_norm": 0.2299073338508606,
+      "learning_rate": 1.0983101909111476e-05,
+      "loss": 0.9139745831489563,
+      "step": 660
+    },
+    {
+      "epoch": 1.8087431693989071,
+      "grad_norm": 0.17643967270851135,
+      "learning_rate": 1.0917462572908709e-05,
+      "loss": 0.9805459976196289,
+      "step": 662
+    },
+    {
+      "epoch": 1.814207650273224,
+      "grad_norm": 0.23675832152366638,
+      "learning_rate": 1.0851926030160964e-05,
+      "loss": 1.0229063034057617,
+      "step": 664
+    },
+    {
+      "epoch": 1.819672131147541,
+      "grad_norm": 0.3587989807128906,
+      "learning_rate": 1.0786494659204919e-05,
+      "loss": 0.9302806854248047,
+      "step": 666
+    },
+    {
+      "epoch": 1.825136612021858,
+      "grad_norm": 0.18514367938041687,
+      "learning_rate": 1.0721170834560539e-05,
+      "loss": 0.9443346261978149,
+      "step": 668
+    },
+    {
+      "epoch": 1.830601092896175,
+      "grad_norm": 0.1954764574766159,
+      "learning_rate": 1.0655956926844917e-05,
+      "loss": 0.6162158250808716,
+      "step": 670
+    },
+    {
+      "epoch": 1.8360655737704918,
+      "grad_norm": 0.6150888800621033,
+      "learning_rate": 1.0590855302686232e-05,
+      "loss": 0.864729642868042,
+      "step": 672
+    },
+    {
+      "epoch": 1.8415300546448088,
+      "grad_norm": 0.15662595629692078,
+      "learning_rate": 1.0525868324637867e-05,
+      "loss": 0.9829941391944885,
+      "step": 674
+    },
+    {
+      "epoch": 1.8469945355191257,
+      "grad_norm": 0.1537102609872818,
+      "learning_rate": 1.046099835109266e-05,
+      "loss": 0.9522998332977295,
+      "step": 676
+    },
+    {
+      "epoch": 1.8524590163934427,
+      "grad_norm": 0.13544432818889618,
+      "learning_rate": 1.0396247736197342e-05,
+      "loss": 0.22472639381885529,
+      "step": 678
+    },
+    {
+      "epoch": 1.8579234972677594,
+      "grad_norm": 0.214643195271492,
+      "learning_rate": 1.0331618829767084e-05,
+      "loss": 0.9816657900810242,
+      "step": 680
+    },
+    {
+      "epoch": 1.8633879781420766,
+      "grad_norm": 0.14030401408672333,
+      "learning_rate": 1.026711397720023e-05,
+      "loss": 0.9638572931289673,
+      "step": 682
+    },
+    {
+      "epoch": 1.8688524590163933,
+      "grad_norm": 0.23839998245239258,
+      "learning_rate": 1.0202735519393172e-05,
+      "loss": 0.8905544281005859,
+      "step": 684
+    },
+    {
+      "epoch": 1.8743169398907105,
+      "grad_norm": 0.6069282293319702,
+      "learning_rate": 1.013848579265542e-05,
+      "loss": 0.7191258668899536,
+      "step": 686
+    },
+    {
+      "epoch": 1.8797814207650272,
+      "grad_norm": 0.18707877397537231,
+      "learning_rate": 1.0074367128624787e-05,
+      "loss": 0.9472928047180176,
+      "step": 688
+    },
+    {
+      "epoch": 1.8852459016393444,
+      "grad_norm": 0.1760343462228775,
+      "learning_rate": 1.0010381854182808e-05,
+      "loss": 1.0247843265533447,
+      "step": 690
+    },
+    {
+      "epoch": 1.890710382513661,
+      "grad_norm": 0.2688332796096802,
+      "learning_rate": 9.946532291370258e-06,
+      "loss": 0.7216252684593201,
+      "step": 692
+    },
+    {
+      "epoch": 1.8961748633879782,
+      "grad_norm": 0.2513716518878937,
+      "learning_rate": 9.882820757302921e-06,
+      "loss": 0.9491530060768127,
+      "step": 694
+    },
+    {
+      "epoch": 1.901639344262295,
+      "grad_norm": 0.1897820681333542,
+      "learning_rate": 9.819249564087476e-06,
+      "loss": 0.9903871417045593,
+      "step": 696
+    },
+    {
+      "epoch": 1.9071038251366121,
+      "grad_norm": 0.2507593631744385,
+      "learning_rate": 9.755821018737602e-06,
+      "loss": 0.739215075969696,
+      "step": 698
+    },
+    {
+      "epoch": 1.9125683060109289,
+      "grad_norm": 0.2772381901741028,
+      "learning_rate": 9.692537423090254e-06,
+      "loss": 0.9631948471069336,
+      "step": 700
+    },
+    {
+      "epoch": 1.918032786885246,
+      "grad_norm": 0.1794651299715042,
+      "learning_rate": 9.629401073722121e-06,
+      "loss": 0.9130382537841797,
+      "step": 702
+    },
+    {
+      "epoch": 1.9234972677595628,
+      "grad_norm": 0.18744076788425446,
+      "learning_rate": 9.566414261866308e-06,
+      "loss": 0.9499990940093994,
+      "step": 704
+    },
+    {
+      "epoch": 1.92896174863388,
+      "grad_norm": 0.21617577970027924,
+      "learning_rate": 9.503579273329149e-06,
+      "loss": 1.0123318433761597,
+      "step": 706
+    },
+    {
+      "epoch": 1.9344262295081966,
+      "grad_norm": 0.17715895175933838,
+      "learning_rate": 9.440898388407277e-06,
+      "loss": 0.9562976360321045,
+      "step": 708
+    },
+    {
+      "epoch": 1.9398907103825138,
+      "grad_norm": 0.1489608734846115,
+      "learning_rate": 9.378373881804876e-06,
+      "loss": 0.6913546323776245,
+      "step": 710
+    },
+    {
+      "epoch": 1.9453551912568305,
+      "grad_norm": 0.24274346232414246,
+      "learning_rate": 9.316008022551121e-06,
+      "loss": 0.5943477749824524,
+      "step": 712
+    },
+    {
+      "epoch": 1.9508196721311475,
+      "grad_norm": 0.25395557284355164,
+      "learning_rate": 9.253803073917827e-06,
+      "loss": 1.011484146118164,
+      "step": 714
+    },
+    {
+      "epoch": 1.9562841530054644,
+      "grad_norm": 0.38927656412124634,
+      "learning_rate": 9.19176129333734e-06,
+      "loss": 0.6682248115539551,
+      "step": 716
+    },
+    {
+      "epoch": 1.9617486338797814,
+      "grad_norm": 0.25566795468330383,
+      "learning_rate": 9.129884932320593e-06,
+      "loss": 0.9508749842643738,
+      "step": 718
+    },
+    {
+      "epoch": 1.9672131147540983,
+      "grad_norm": 0.4887275993824005,
+      "learning_rate": 9.0681762363754e-06,
+      "loss": 1.0459179878234863,
+      "step": 720
+    },
+    {
+      "epoch": 1.9726775956284153,
+      "grad_norm": 0.3566785454750061,
+      "learning_rate": 9.006637444924973e-06,
+      "loss": 0.9785248041152954,
+      "step": 722
+    },
+    {
+      "epoch": 1.9781420765027322,
+      "grad_norm": 0.5626527667045593,
+      "learning_rate": 8.945270791226646e-06,
+      "loss": 0.945759117603302,
+      "step": 724
+    },
+    {
+      "epoch": 1.9836065573770492,
+      "grad_norm": 5.221266269683838,
+      "learning_rate": 8.884078502290838e-06,
+      "loss": 0.9256299138069153,
+      "step": 726
+    },
+    {
+      "epoch": 1.989071038251366,
+      "grad_norm": 0.2847398519515991,
+      "learning_rate": 8.823062798800233e-06,
+      "loss": 0.9720381498336792,
+      "step": 728
+    },
+    {
+      "epoch": 1.994535519125683,
+      "grad_norm": 0.2270623743534088,
+      "learning_rate": 8.762225895029169e-06,
+      "loss": 0.8780955672264099,
+      "step": 730
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.18520908057689667,
+      "learning_rate": 8.701569998763323e-06,
+      "loss": 0.9250549674034119,
+      "step": 732
+    },
+    {
+      "epoch": 2.0054644808743167,
+      "grad_norm": 0.17245544493198395,
+      "learning_rate": 8.64109731121955e-06,
+      "loss": 0.41599372029304504,
+      "step": 734
+    },
+    {
+      "epoch": 2.010928961748634,
+      "grad_norm": 0.25467920303344727,
+      "learning_rate": 8.580810026966034e-06,
+      "loss": 0.7172941565513611,
+      "step": 736
+    },
+    {
+      "epoch": 2.0163934426229506,
+      "grad_norm": 0.24227584898471832,
+      "learning_rate": 8.520710333842605e-06,
+      "loss": 0.747187614440918,
+      "step": 738
+    },
+    {
+      "epoch": 2.021857923497268,
+      "grad_norm": 0.24147503077983856,
+      "learning_rate": 8.460800412881386e-06,
+      "loss": 0.6775767207145691,
+      "step": 740
+    },
+    {
+      "epoch": 2.0273224043715845,
+      "grad_norm": 0.31402096152305603,
+      "learning_rate": 8.401082438227617e-06,
+      "loss": 0.402444452047348,
+      "step": 742
+    },
+    {
+      "epoch": 2.0327868852459017,
+      "grad_norm": 0.42537474632263184,
+      "learning_rate": 8.341558577060769e-06,
+      "loss": 0.6484034657478333,
+      "step": 744
+    },
+    {
+      "epoch": 2.0382513661202184,
+      "grad_norm": 0.3523010313510895,
+      "learning_rate": 8.282230989515865e-06,
+      "loss": 0.4699830114841461,
+      "step": 746
+    },
+    {
+      "epoch": 2.0437158469945356,
+      "grad_norm": 0.5600184202194214,
+      "learning_rate": 8.223101828605141e-06,
+      "loss": 0.6734252572059631,
+      "step": 748
+    },
+    {
+      "epoch": 2.0491803278688523,
+      "grad_norm": 0.15328167378902435,
+      "learning_rate": 8.164173240139865e-06,
+      "loss": 0.45088091492652893,
+      "step": 750
+    },
+    {
+      "epoch": 2.0546448087431695,
+      "grad_norm": 0.6332978010177612,
+      "learning_rate": 8.105447362652492e-06,
+      "loss": 0.44899141788482666,
+      "step": 752
+    },
+    {
+      "epoch": 2.060109289617486,
+      "grad_norm": 1.7822338342666626,
+      "learning_rate": 8.046926327319037e-06,
+      "loss": 0.5379037857055664,
+      "step": 754
+    },
+    {
+      "epoch": 2.0655737704918034,
+      "grad_norm": 0.3468593657016754,
+      "learning_rate": 7.988612257881757e-06,
+      "loss": 0.6135660409927368,
+      "step": 756
+    },
+    {
+      "epoch": 2.07103825136612,
+      "grad_norm": 0.4308558702468872,
+      "learning_rate": 7.930507270572065e-06,
+      "loss": 0.6905173659324646,
+      "step": 758
+    },
+    {
+      "epoch": 2.0765027322404372,
+      "grad_norm": 0.214769646525383,
+      "learning_rate": 7.872613474033722e-06,
+      "loss": 0.6643854379653931,
+      "step": 760
+    },
+    {
+      "epoch": 2.081967213114754,
+      "grad_norm": 0.2445564866065979,
+      "learning_rate": 7.814932969246342e-06,
+      "loss": 0.5414201021194458,
+      "step": 762
+    },
+    {
+      "epoch": 2.087431693989071,
+      "grad_norm": 0.2596500515937805,
+      "learning_rate": 7.75746784944912e-06,
+      "loss": 0.6696488261222839,
+      "step": 764
+    },
+    {
+      "epoch": 2.092896174863388,
+      "grad_norm": 0.30743348598480225,
+      "learning_rate": 7.700220200064889e-06,
+      "loss": 0.6852096319198608,
+      "step": 766
+    },
+    {
+      "epoch": 2.098360655737705,
+      "grad_norm": 0.9081697463989258,
+      "learning_rate": 7.643192098624413e-06,
+      "loss": 0.665625810623169,
+      "step": 768
+    },
+    {
+      "epoch": 2.1038251366120218,
+      "grad_norm": 0.2047584056854248,
+      "learning_rate": 7.586385614691024e-06,
+      "loss": 0.6999115943908691,
+      "step": 770
+    },
+    {
+      "epoch": 2.109289617486339,
+      "grad_norm": 0.5113670229911804,
+      "learning_rate": 7.529802809785497e-06,
+      "loss": 0.6937403082847595,
+      "step": 772
+    },
+    {
+      "epoch": 2.1147540983606556,
+      "grad_norm": 0.19943810999393463,
+      "learning_rate": 7.473445737311244e-06,
+      "loss": 0.7570751309394836,
+      "step": 774
+    },
+    {
+      "epoch": 2.120218579234973,
+      "grad_norm": 0.24206914007663727,
+      "learning_rate": 7.417316442479783e-06,
+      "loss": 0.4566923677921295,
+      "step": 776
+    },
+    {
+      "epoch": 2.1256830601092895,
+      "grad_norm": 0.5807485580444336,
+      "learning_rate": 7.361416962236542e-06,
+      "loss": 0.617829442024231,
+      "step": 778
+    },
+    {
+      "epoch": 2.1311475409836067,
+      "grad_norm": 0.3329077959060669,
+      "learning_rate": 7.305749325186914e-06,
+      "loss": 0.6804491877555847,
+      "step": 780
+    },
+    {
+      "epoch": 2.1366120218579234,
+      "grad_norm": 0.20504486560821533,
+      "learning_rate": 7.2503155515226575e-06,
+      "loss": 0.7602362632751465,
+      "step": 782
+    },
+    {
+      "epoch": 2.1420765027322406,
+      "grad_norm": 0.1894470453262329,
+      "learning_rate": 7.195117652948555e-06,
+      "loss": 0.6853156089782715,
+      "step": 784
+    },
+    {
+      "epoch": 2.1475409836065573,
+      "grad_norm": 0.11648036539554596,
+      "learning_rate": 7.14015763260944e-06,
+      "loss": 0.3979906439781189,
+      "step": 786
+    },
+    {
+      "epoch": 2.1530054644808745,
+      "grad_norm": 1.0007914304733276,
+      "learning_rate": 7.085437485017487e-06,
+      "loss": 0.640531063079834,
+      "step": 788
+    },
+    {
+      "epoch": 2.158469945355191,
+      "grad_norm": 0.1968093067407608,
+      "learning_rate": 7.030959195979833e-06,
+      "loss": 0.6763147115707397,
+      "step": 790
+    },
+    {
+      "epoch": 2.1639344262295084,
+      "grad_norm": 0.2067585587501526,
+      "learning_rate": 6.976724742526503e-06,
+      "loss": 0.5175256729125977,
+      "step": 792
+    },
+    {
+      "epoch": 2.169398907103825,
+      "grad_norm": 0.7652968764305115,
+      "learning_rate": 6.92273609283868e-06,
+      "loss": 0.4226246774196625,
+      "step": 794
+    },
+    {
+      "epoch": 2.1748633879781423,
+      "grad_norm": 0.21701058745384216,
+      "learning_rate": 6.868995206177264e-06,
+      "loss": 0.6554322838783264,
+      "step": 796
+    },
+    {
+      "epoch": 2.180327868852459,
+      "grad_norm": 1.6271648406982422,
+      "learning_rate": 6.815504032811775e-06,
+      "loss": 0.6646580100059509,
+      "step": 798
+    },
+    {
+      "epoch": 2.185792349726776,
+      "grad_norm": 0.4442613422870636,
+      "learning_rate": 6.7622645139495815e-06,
+      "loss": 0.585219144821167,
+      "step": 800
+    },
+    {
+      "epoch": 2.191256830601093,
+      "grad_norm": 0.23071300983428955,
+      "learning_rate": 6.7092785816654515e-06,
+      "loss": 0.6361981630325317,
+      "step": 802
+    },
+    {
+      "epoch": 2.19672131147541,
+      "grad_norm": 0.15861168503761292,
+      "learning_rate": 6.656548158831436e-06,
+      "loss": 0.7302151322364807,
+      "step": 804
+    },
+    {
+      "epoch": 2.202185792349727,
+      "grad_norm": 0.2113688737154007,
+      "learning_rate": 6.6040751590470825e-06,
+      "loss": 0.6704022884368896,
+      "step": 806
+    },
+    {
+      "epoch": 2.2076502732240435,
+      "grad_norm": 0.13283978402614594,
+      "learning_rate": 6.551861486569997e-06,
+      "loss": 0.38798680901527405,
+      "step": 808
+    },
+    {
+      "epoch": 2.2131147540983607,
+      "grad_norm": 0.23720614612102509,
+      "learning_rate": 6.499909036246738e-06,
+      "loss": 0.37715965509414673,
+      "step": 810
+    },
+    {
+      "epoch": 2.2185792349726774,
+      "grad_norm": 0.23791414499282837,
+      "learning_rate": 6.448219693444056e-06,
+      "loss": 0.7323361039161682,
+      "step": 812
+    },
+    {
+      "epoch": 2.2240437158469946,
+      "grad_norm": 0.24081940948963165,
+      "learning_rate": 6.39679533398045e-06,
+      "loss": 0.5640745759010315,
+      "step": 814
+    },
+    {
+      "epoch": 2.2295081967213113,
+      "grad_norm": 0.3527999222278595,
+      "learning_rate": 6.345637824058126e-06,
+      "loss": 0.673088788986206,
+      "step": 816
+    },
+    {
+      "epoch": 2.2349726775956285,
+      "grad_norm": 0.5025823712348938,
+      "learning_rate": 6.294749020195253e-06,
+      "loss": 0.6976668834686279,
+      "step": 818
+    },
+    {
+      "epoch": 2.240437158469945,
+      "grad_norm": 0.2786237895488739,
+      "learning_rate": 6.244130769158594e-06,
+      "loss": 0.6512521505355835,
+      "step": 820
+    },
+    {
+      "epoch": 2.2459016393442623,
+      "grad_norm": 1.141295313835144,
+      "learning_rate": 6.193784907896478e-06,
+      "loss": 0.6717444062232971,
+      "step": 822
+    },
+    {
+      "epoch": 2.251366120218579,
+      "grad_norm": 0.32836222648620605,
+      "learning_rate": 6.143713263472156e-06,
+      "loss": 0.6926584839820862,
+      "step": 824
+    },
+    {
+      "epoch": 2.2568306010928962,
+      "grad_norm": 0.4723096489906311,
+      "learning_rate": 6.0939176529974765e-06,
+      "loss": 0.46854105591773987,
+      "step": 826
+    },
+    {
+      "epoch": 2.262295081967213,
+      "grad_norm": 0.2536696791648865,
+      "learning_rate": 6.044399883566959e-06,
+      "loss": 0.4778412878513336,
+      "step": 828
+    },
+    {
+      "epoch": 2.26775956284153,
+      "grad_norm": 0.19949211180210114,
+      "learning_rate": 5.995161752192192e-06,
+      "loss": 0.7425835132598877,
+      "step": 830
+    },
+    {
+      "epoch": 2.273224043715847,
+      "grad_norm": 0.6780716180801392,
+      "learning_rate": 5.9462050457366446e-06,
+      "loss": 0.3689644932746887,
+      "step": 832
+    },
+    {
+      "epoch": 2.278688524590164,
+      "grad_norm": 0.22472506761550903,
+      "learning_rate": 5.897531540850807e-06,
+      "loss": 0.3652177155017853,
+      "step": 834
+    },
+    {
+      "epoch": 2.2841530054644807,
+      "grad_norm": 0.26355841755867004,
+      "learning_rate": 5.849143003907717e-06,
+      "loss": 0.632552444934845,
+      "step": 836
+    },
+    {
+      "epoch": 2.289617486338798,
+      "grad_norm": 0.6640907526016235,
+      "learning_rate": 5.801041190938849e-06,
+      "loss": 0.7073798775672913,
+      "step": 838
+    },
+    {
+      "epoch": 2.2950819672131146,
+      "grad_norm": 0.2682071626186371,
+      "learning_rate": 5.75322784757041e-06,
+      "loss": 0.4572494328022003,
+      "step": 840
+    },
+    {
+      "epoch": 2.300546448087432,
+      "grad_norm": 0.23095370829105377,
+      "learning_rate": 5.705704708959968e-06,
+      "loss": 0.7449085712432861,
+      "step": 842
+    },
+    {
+      "epoch": 2.3060109289617485,
+      "grad_norm": 0.19461746513843536,
+      "learning_rate": 5.658473499733499e-06,
+      "loss": 0.6545416712760925,
+      "step": 844
+    },
+    {
+      "epoch": 2.3114754098360657,
+      "grad_norm": 0.1823868453502655,
+      "learning_rate": 5.611535933922781e-06,
+      "loss": 0.29822948575019836,
+      "step": 846
+    },
+    {
+      "epoch": 2.3169398907103824,
+      "grad_norm": 0.19124025106430054,
+      "learning_rate": 5.564893714903211e-06,
+      "loss": 0.7034991383552551,
+      "step": 848
+    },
+    {
+      "epoch": 2.3224043715846996,
+      "grad_norm": 0.19907920062541962,
+      "learning_rate": 5.518548535331984e-06,
+      "loss": 0.6916401386260986,
+      "step": 850
+    },
+    {
+      "epoch": 2.3278688524590163,
+      "grad_norm": 0.3887382447719574,
+      "learning_rate": 5.472502077086653e-06,
+      "loss": 0.6322124004364014,
+      "step": 852
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.23771852254867554,
+      "learning_rate": 5.426756011204108e-06,
+      "loss": 0.6052520871162415,
+      "step": 854
+    },
+    {
+      "epoch": 2.33879781420765,
+      "grad_norm": 0.14829999208450317,
+      "learning_rate": 5.381311997819933e-06,
+      "loss": 0.7813782691955566,
+      "step": 856
+    },
+    {
+      "epoch": 2.3442622950819674,
+      "grad_norm": 0.26474112272262573,
+      "learning_rate": 5.336171686108153e-06,
+      "loss": 0.5027655959129333,
+      "step": 858
+    },
+    {
+      "epoch": 2.349726775956284,
+      "grad_norm": 0.2717822194099426,
+      "learning_rate": 5.291336714221382e-06,
+      "loss": 0.7000398635864258,
+      "step": 860
+    },
+    {
+      "epoch": 2.3551912568306013,
+      "grad_norm": 0.24665828049182892,
+      "learning_rate": 5.246808709231382e-06,
+      "loss": 0.7338890433311462,
+      "step": 862
+    },
+    {
+      "epoch": 2.360655737704918,
+      "grad_norm": 1.1350178718566895,
+      "learning_rate": 5.202589287070019e-06,
+      "loss": 0.5282155275344849,
+      "step": 864
+    },
+    {
+      "epoch": 2.366120218579235,
+      "grad_norm": 1.0712934732437134,
+      "learning_rate": 5.158680052470609e-06,
+      "loss": 0.5917450785636902,
+      "step": 866
+    },
+    {
+      "epoch": 2.371584699453552,
+      "grad_norm": 0.17483752965927124,
+      "learning_rate": 5.115082598909689e-06,
+      "loss": 0.7042443156242371,
+      "step": 868
+    },
+    {
+      "epoch": 2.3770491803278686,
+      "grad_norm": 0.24676814675331116,
+      "learning_rate": 5.071798508549189e-06,
+      "loss": 0.715234100818634,
+      "step": 870
+    },
+    {
+      "epoch": 2.3825136612021858,
+      "grad_norm": 0.22551953792572021,
+      "learning_rate": 5.028829352179017e-06,
+      "loss": 0.804095983505249,
+      "step": 872
+    },
+    {
+      "epoch": 2.387978142076503,
+      "grad_norm": 0.18146005272865295,
+      "learning_rate": 4.986176689160042e-06,
+      "loss": 0.7026334404945374,
+      "step": 874
+    },
+    {
+      "epoch": 2.3934426229508197,
+      "grad_norm": 0.5449501872062683,
+      "learning_rate": 4.943842067367525e-06,
+      "loss": 0.49338310956954956,
+      "step": 876
+    },
+    {
+      "epoch": 2.3989071038251364,
+      "grad_norm": 0.1813872754573822,
+      "learning_rate": 4.901827023134931e-06,
+      "loss": 0.7016088366508484,
+      "step": 878
+    },
+    {
+      "epoch": 2.4043715846994536,
+      "grad_norm": 0.15302123129367828,
+      "learning_rate": 4.86013308119818e-06,
+      "loss": 0.6298723816871643,
+      "step": 880
+    },
+    {
+      "epoch": 2.4098360655737707,
+      "grad_norm": 0.18854597210884094,
+      "learning_rate": 4.818761754640316e-06,
+      "loss": 0.43687549233436584,
+      "step": 882
+    },
+    {
+      "epoch": 2.4153005464480874,
+      "grad_norm": 0.22853216528892517,
+      "learning_rate": 4.777714544836585e-06,
+      "loss": 0.7133804559707642,
+      "step": 884
+    },
+    {
+      "epoch": 2.420765027322404,
+      "grad_norm": 0.19461189210414886,
+      "learning_rate": 4.736992941399972e-06,
+      "loss": 0.7002368569374084,
+      "step": 886
+    },
+    {
+      "epoch": 2.4262295081967213,
+      "grad_norm": 0.2936843931674957,
+      "learning_rate": 4.696598422127119e-06,
+      "loss": 0.3858260214328766,
+      "step": 888
+    },
+    {
+      "epoch": 2.431693989071038,
+      "grad_norm": 0.25543907284736633,
+      "learning_rate": 4.656532452944716e-06,
+      "loss": 0.449078232049942,
+      "step": 890
+    },
+    {
+      "epoch": 2.4371584699453552,
+      "grad_norm": 0.46111661195755005,
+      "learning_rate": 4.616796487856282e-06,
+      "loss": 0.641425371170044,
+      "step": 892
+    },
+    {
+      "epoch": 2.442622950819672,
+      "grad_norm": 0.1983172744512558,
+      "learning_rate": 4.577391968889416e-06,
+      "loss": 0.3780648708343506,
+      "step": 894
+    },
+    {
+      "epoch": 2.448087431693989,
+      "grad_norm": 0.28097936511039734,
+      "learning_rate": 4.53832032604346e-06,
+      "loss": 0.6762884259223938,
+      "step": 896
+    },
+    {
+      "epoch": 2.453551912568306,
+      "grad_norm": 0.234109029173851,
+      "learning_rate": 4.499582977237594e-06,
+      "loss": 0.7201648950576782,
+      "step": 898
+    },
+    {
+      "epoch": 2.459016393442623,
+      "grad_norm": 0.18416042625904083,
+      "learning_rate": 4.461181328259397e-06,
+      "loss": 0.6271026134490967,
+      "step": 900
+    },
+    {
+      "epoch": 2.4644808743169397,
+      "grad_norm": 0.17045891284942627,
+      "learning_rate": 4.423116772713817e-06,
+      "loss": 0.7007759809494019,
+      "step": 902
+    },
+    {
+      "epoch": 2.469945355191257,
+      "grad_norm": 0.1790081411600113,
+      "learning_rate": 4.3853906919726045e-06,
+      "loss": 0.710627019405365,
+      "step": 904
+    },
+    {
+      "epoch": 2.4754098360655736,
+      "grad_norm": 0.8877317309379578,
+      "learning_rate": 4.348004455124173e-06,
+      "loss": 0.4587891399860382,
+      "step": 906
+    },
+    {
+      "epoch": 2.480874316939891,
+      "grad_norm": 0.07845756411552429,
+      "learning_rate": 4.310959418923926e-06,
+      "loss": 0.13992244005203247,
+      "step": 908
+    },
+    {
+      "epoch": 2.4863387978142075,
+      "grad_norm": 0.10895147174596786,
+      "learning_rate": 4.274256927745015e-06,
+      "loss": 0.49745655059814453,
+      "step": 910
+    },
+    {
+      "epoch": 2.4918032786885247,
+      "grad_norm": 0.1617729514837265,
+      "learning_rate": 4.23789831352955e-06,
+      "loss": 0.4288228750228882,
+      "step": 912
+    },
+    {
+      "epoch": 2.4972677595628414,
+      "grad_norm": 0.21319684386253357,
+      "learning_rate": 4.2018848957402605e-06,
+      "loss": 0.6953483819961548,
+      "step": 914
+    },
+    {
+      "epoch": 2.5027322404371586,
+      "grad_norm": 0.2012702375650406,
+      "learning_rate": 4.166217981312621e-06,
+      "loss": 0.5614168047904968,
+      "step": 916
+    },
+    {
+      "epoch": 2.5081967213114753,
+      "grad_norm": 0.20277954638004303,
+      "learning_rate": 4.130898864607417e-06,
+      "loss": 0.6851552724838257,
+      "step": 918
+    },
+    {
+      "epoch": 2.5136612021857925,
+      "grad_norm": 0.2765226662158966,
+      "learning_rate": 4.09592882736377e-06,
+      "loss": 0.6657923460006714,
+      "step": 920
+    },
+    {
+      "epoch": 2.519125683060109,
+      "grad_norm": 0.4667165279388428,
+      "learning_rate": 4.061309138652622e-06,
+      "loss": 0.7339661717414856,
+      "step": 922
+    },
+    {
+      "epoch": 2.5245901639344264,
+      "grad_norm": 0.16822604835033417,
+      "learning_rate": 4.027041054830689e-06,
+      "loss": 0.6094578504562378,
+      "step": 924
+    },
+    {
+      "epoch": 2.530054644808743,
+      "grad_norm": 0.14607980847358704,
+      "learning_rate": 3.993125819494862e-06,
+      "loss": 0.34630584716796875,
+      "step": 926
+    },
+    {
+      "epoch": 2.5355191256830603,
+      "grad_norm": 0.15208321809768677,
+      "learning_rate": 3.9595646634370745e-06,
+      "loss": 0.4717685878276825,
+      "step": 928
+    },
+    {
+      "epoch": 2.540983606557377,
+      "grad_norm": 0.2327331304550171,
+      "learning_rate": 3.926358804599636e-06,
+      "loss": 0.6192865371704102,
+      "step": 930
+    },
+    {
+      "epoch": 2.546448087431694,
+      "grad_norm": 0.757671594619751,
+      "learning_rate": 3.8935094480310425e-06,
+      "loss": 0.5656976103782654,
+      "step": 932
+    },
+    {
+      "epoch": 2.551912568306011,
+      "grad_norm": 0.22793398797512054,
+      "learning_rate": 3.861017785842234e-06,
+      "loss": 0.7342063188552856,
+      "step": 934
+    },
+    {
+      "epoch": 2.557377049180328,
+      "grad_norm": 0.9295087456703186,
+      "learning_rate": 3.828884997163339e-06,
+      "loss": 0.5990333557128906,
+      "step": 936
+    },
+    {
+      "epoch": 2.5628415300546448,
+      "grad_norm": 2.140310764312744,
+      "learning_rate": 3.7971122481008757e-06,
+      "loss": 0.5494145154953003,
+      "step": 938
+    },
+    {
+      "epoch": 2.5683060109289615,
+      "grad_norm": 0.28645941615104675,
+      "learning_rate": 3.7657006916954453e-06,
+      "loss": 0.6415644288063049,
+      "step": 940
+    },
+    {
+      "epoch": 2.5737704918032787,
+      "grad_norm": 0.38164955377578735,
+      "learning_rate": 3.734651467879878e-06,
+      "loss": 0.43504810333251953,
+      "step": 942
+    },
+    {
+      "epoch": 2.579234972677596,
+      "grad_norm": 0.34789642691612244,
+      "learning_rate": 3.7039657034378726e-06,
+      "loss": 0.6228368282318115,
+      "step": 944
+    },
+    {
+      "epoch": 2.5846994535519126,
+      "grad_norm": 0.07762913405895233,
+      "learning_rate": 3.6736445119630964e-06,
+      "loss": 0.16022926568984985,
+      "step": 946
+    },
+    {
+      "epoch": 2.5901639344262293,
+      "grad_norm": 0.28069254755973816,
+      "learning_rate": 3.6436889938187833e-06,
+      "loss": 0.6584885716438293,
+      "step": 948
+    },
+    {
+      "epoch": 2.5956284153005464,
+      "grad_norm": 0.24518746137619019,
+      "learning_rate": 3.6141002360977864e-06,
+      "loss": 0.43174296617507935,
+      "step": 950
+    },
+    {
+      "epoch": 2.6010928961748636,
+      "grad_norm": 0.39224839210510254,
+      "learning_rate": 3.584879312583141e-06,
+      "loss": 0.5712751746177673,
+      "step": 952
+    },
+    {
+      "epoch": 2.6065573770491803,
+      "grad_norm": 0.24317054450511932,
+      "learning_rate": 3.5560272837090935e-06,
+      "loss": 0.37820327281951904,
+      "step": 954
+    },
+    {
+      "epoch": 2.612021857923497,
+      "grad_norm": 0.15435853600502014,
+      "learning_rate": 3.527545196522615e-06,
+      "loss": 0.17984823882579803,
+      "step": 956
+    },
+    {
+      "epoch": 2.6174863387978142,
+      "grad_norm": 0.32159680128097534,
+      "learning_rate": 3.499434084645407e-06,
+      "loss": 0.4029221534729004,
+      "step": 958
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "grad_norm": 0.3094979226589203,
+      "learning_rate": 3.4716949682363803e-06,
+      "loss": 0.739897608757019,
+      "step": 960
+    },
+    {
+      "epoch": 2.628415300546448,
+      "grad_norm": 0.425645112991333,
+      "learning_rate": 3.4443288539546508e-06,
+      "loss": 0.4608995020389557,
+      "step": 962
+    },
+    {
+      "epoch": 2.633879781420765,
+      "grad_norm": 0.22378240525722504,
+      "learning_rate": 3.417336734922998e-06,
+      "loss": 0.6960005760192871,
+      "step": 964
+    },
+    {
+      "epoch": 2.639344262295082,
+      "grad_norm": 0.18555636703968048,
+      "learning_rate": 3.3907195906918236e-06,
+      "loss": 0.7077355980873108,
+      "step": 966
+    },
+    {
+      "epoch": 2.644808743169399,
+      "grad_norm": 0.2145896553993225,
+      "learning_rate": 3.364478387203602e-06,
+      "loss": 0.5513492226600647,
+      "step": 968
+    },
+    {
+      "epoch": 2.650273224043716,
+      "grad_norm": 0.7693909406661987,
+      "learning_rate": 3.338614076757832e-06,
+      "loss": 0.5141048431396484,
+      "step": 970
+    },
+    {
+      "epoch": 2.6557377049180326,
+      "grad_norm": 0.3477981388568878,
+      "learning_rate": 3.3131275979764746e-06,
+      "loss": 0.6895625591278076,
+      "step": 972
+    },
+    {
+      "epoch": 2.66120218579235,
+      "grad_norm": 0.19012540578842163,
+      "learning_rate": 3.288019875769889e-06,
+      "loss": 0.39245468378067017,
+      "step": 974
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.24051906168460846,
+      "learning_rate": 3.2632918213032687e-06,
+      "loss": 0.6571274995803833,
+      "step": 976
+    },
+    {
+      "epoch": 2.6721311475409837,
+      "grad_norm": 0.14302131533622742,
+      "learning_rate": 3.2389443319635762e-06,
+      "loss": 0.6791136860847473,
+      "step": 978
+    },
+    {
+      "epoch": 2.6775956284153004,
+      "grad_norm": 0.21270255744457245,
+      "learning_rate": 3.2149782913269715e-06,
+      "loss": 0.7463234066963196,
+      "step": 980
+    },
+    {
+      "epoch": 2.6830601092896176,
+      "grad_norm": 0.20450647175312042,
+      "learning_rate": 3.1913945691267574e-06,
+      "loss": 0.46346530318260193,
+      "step": 982
+    },
+    {
+      "epoch": 2.6885245901639343,
+      "grad_norm": 0.18693040311336517,
+      "learning_rate": 3.1681940212218013e-06,
+      "loss": 0.3435611426830292,
+      "step": 984
+    },
+    {
+      "epoch": 2.6939890710382515,
+      "grad_norm": 0.20872755348682404,
+      "learning_rate": 3.145377489565492e-06,
+      "loss": 0.6869267225265503,
+      "step": 986
+    },
+    {
+      "epoch": 2.699453551912568,
+      "grad_norm": 0.19473455846309662,
+      "learning_rate": 3.1229458021751754e-06,
+      "loss": 0.7176718711853027,
+      "step": 988
+    },
+    {
+      "epoch": 2.7049180327868854,
+      "grad_norm": 0.17841266095638275,
+      "learning_rate": 3.100899773102103e-06,
+      "loss": 0.618594229221344,
+      "step": 990
+    },
+    {
+      "epoch": 2.710382513661202,
+      "grad_norm": 0.19311846792697906,
+      "learning_rate": 3.0792402024019028e-06,
+      "loss": 0.34453269839286804,
+      "step": 992
+    },
+    {
+      "epoch": 2.7158469945355193,
+      "grad_norm": 0.22827599942684174,
+      "learning_rate": 3.0579678761055294e-06,
+      "loss": 0.6793984770774841,
+      "step": 994
+    },
+    {
+      "epoch": 2.721311475409836,
+      "grad_norm": 0.1737447828054428,
+      "learning_rate": 3.0370835661907522e-06,
+      "loss": 0.7369482517242432,
+      "step": 996
+    },
+    {
+      "epoch": 2.726775956284153,
+      "grad_norm": 0.17720820009708405,
+      "learning_rate": 3.016588030554128e-06,
+      "loss": 0.6935803294181824,
+      "step": 998
+    },
+    {
+      "epoch": 2.73224043715847,
+      "grad_norm": 0.650160551071167,
+      "learning_rate": 2.996482012983508e-06,
+      "loss": 0.5621395707130432,
+      "step": 1000
+    },
+    {
+      "epoch": 2.737704918032787,
+      "grad_norm": 0.23146776854991913,
+      "learning_rate": 2.9767662431310373e-06,
+      "loss": 0.6701301336288452,
+      "step": 1002
+    },
+    {
+      "epoch": 2.7431693989071038,
+      "grad_norm": 0.45669713616371155,
+      "learning_rate": 2.957441436486682e-06,
+      "loss": 0.7368155121803284,
+      "step": 1004
+    },
+    {
+      "epoch": 2.748633879781421,
+      "grad_norm": 0.2950546145439148,
+      "learning_rate": 2.9385082943522553e-06,
+      "loss": 0.2910221815109253,
+      "step": 1006
+    },
+    {
+      "epoch": 2.7540983606557377,
+      "grad_norm": 0.19097362458705902,
+      "learning_rate": 2.9199675038159764e-06,
+      "loss": 0.7412728667259216,
+      "step": 1008
+    },
+    {
+      "epoch": 2.7595628415300544,
+      "grad_norm": 0.24510665237903595,
+      "learning_rate": 2.9018197377275334e-06,
+      "loss": 0.6697684526443481,
+      "step": 1010
+    },
+    {
+      "epoch": 2.7650273224043715,
+      "grad_norm": 0.14479011297225952,
+      "learning_rate": 2.8840656546736607e-06,
+      "loss": 0.5396718978881836,
+      "step": 1012
+    },
+    {
+      "epoch": 2.7704918032786887,
+      "grad_norm": 0.23086193203926086,
+      "learning_rate": 2.866705898954241e-06,
+      "loss": 0.6256304383277893,
+      "step": 1014
+    },
+    {
+      "epoch": 2.7759562841530054,
+      "grad_norm": 0.29304757714271545,
+      "learning_rate": 2.8497411005589283e-06,
+      "loss": 0.6394587755203247,
+      "step": 1016
+    },
+    {
+      "epoch": 2.781420765027322,
+      "grad_norm": 0.3104848265647888,
+      "learning_rate": 2.8331718751442793e-06,
+      "loss": 0.6255086064338684,
+      "step": 1018
+    },
+    {
+      "epoch": 2.7868852459016393,
+      "grad_norm": 0.14495858550071716,
+      "learning_rate": 2.8169988240114145e-06,
+      "loss": 0.40636876225471497,
+      "step": 1020
+    },
+    {
+      "epoch": 2.7923497267759565,
+      "grad_norm": 0.29641368985176086,
+      "learning_rate": 2.801222534084196e-06,
+      "loss": 0.6926835179328918,
+      "step": 1022
+    },
+    {
+      "epoch": 2.797814207650273,
+      "grad_norm": 0.2795805037021637,
+      "learning_rate": 2.785843577887926e-06,
+      "loss": 0.3881547749042511,
+      "step": 1024
+    },
+    {
+      "epoch": 2.80327868852459,
+      "grad_norm": 0.45699605345726013,
+      "learning_rate": 2.7708625135285717e-06,
+      "loss": 0.7579897046089172,
+      "step": 1026
+    },
+    {
+      "epoch": 2.808743169398907,
+      "grad_norm": 1.0389068126678467,
+      "learning_rate": 2.7562798846725133e-06,
+      "loss": 0.2406935691833496,
+      "step": 1028
+    },
+    {
+      "epoch": 2.8142076502732243,
+      "grad_norm": 0.3375071585178375,
+      "learning_rate": 2.742096220526808e-06,
+      "loss": 0.686618447303772,
+      "step": 1030
+    },
+    {
+      "epoch": 2.819672131147541,
+      "grad_norm": 0.18238572776317596,
+      "learning_rate": 2.728312035819995e-06,
+      "loss": 0.667717695236206,
+      "step": 1032
+    },
+    {
+      "epoch": 2.8251366120218577,
+      "grad_norm": 0.49168893694877625,
+      "learning_rate": 2.7149278307834047e-06,
+      "loss": 0.5261977910995483,
+      "step": 1034
+    },
+    {
+      "epoch": 2.830601092896175,
+      "grad_norm": 0.24831274151802063,
+      "learning_rate": 2.701944091133011e-06,
+      "loss": 0.7198750972747803,
+      "step": 1036
+    },
+    {
+      "epoch": 2.836065573770492,
+      "grad_norm": 0.22962301969528198,
+      "learning_rate": 2.6893612880518064e-06,
+      "loss": 0.737044095993042,
+      "step": 1038
+    },
+    {
+      "epoch": 2.841530054644809,
+      "grad_norm": 0.19474509358406067,
+      "learning_rate": 2.677179878172699e-06,
+      "loss": 0.7108073830604553,
+      "step": 1040
+    },
+    {
+      "epoch": 2.8469945355191255,
+      "grad_norm": 0.20618607103824615,
+      "learning_rate": 2.6654003035619427e-06,
+      "loss": 0.6671370267868042,
+      "step": 1042
+    },
+    {
+      "epoch": 2.8524590163934427,
+      "grad_norm": 0.1941603571176529,
+      "learning_rate": 2.654022991703093e-06,
+      "loss": 0.5263208746910095,
+      "step": 1044
+    },
+    {
+      "epoch": 2.8579234972677594,
+      "grad_norm": 0.4619889259338379,
+      "learning_rate": 2.6430483554814956e-06,
+      "loss": 0.6518206596374512,
+      "step": 1046
+    },
+    {
+      "epoch": 2.8633879781420766,
+      "grad_norm": 0.21917857229709625,
+      "learning_rate": 2.632476793169303e-06,
+      "loss": 0.3260215222835541,
+      "step": 1048
+    },
+    {
+      "epoch": 2.8688524590163933,
+      "grad_norm": 0.17283010482788086,
+      "learning_rate": 2.622308688411019e-06,
+      "loss": 0.6257282495498657,
+      "step": 1050
+    },
+    {
+      "epoch": 2.8743169398907105,
+      "grad_norm": 0.23165258765220642,
+      "learning_rate": 2.612544410209574e-06,
+      "loss": 0.6545224189758301,
+      "step": 1052
+    },
+    {
+      "epoch": 2.879781420765027,
+      "grad_norm": 0.2500731945037842,
+      "learning_rate": 2.6031843129129425e-06,
+      "loss": 0.6312705278396606,
+      "step": 1054
+    },
+    {
+      "epoch": 2.8852459016393444,
+      "grad_norm": 0.7894412875175476,
+      "learning_rate": 2.594228736201274e-06,
+      "loss": 0.6379542946815491,
+      "step": 1056
+    },
+    {
+      "epoch": 2.890710382513661,
+      "grad_norm": 1.0066219568252563,
+      "learning_rate": 2.5856780050745726e-06,
+      "loss": 0.44013917446136475,
+      "step": 1058
+    },
+    {
+      "epoch": 2.8961748633879782,
+      "grad_norm": 0.7618535757064819,
+      "learning_rate": 2.577532429840896e-06,
+      "loss": 0.6751360297203064,
+      "step": 1060
+    },
+    {
+      "epoch": 2.901639344262295,
+      "grad_norm": 0.2618259787559509,
+      "learning_rate": 2.5697923061051056e-06,
+      "loss": 0.7184084057807922,
+      "step": 1062
+    },
+    {
+      "epoch": 2.907103825136612,
+      "grad_norm": 0.17739877104759216,
+      "learning_rate": 2.5624579147581233e-06,
+      "loss": 0.8313037753105164,
+      "step": 1064
+    },
+    {
+      "epoch": 2.912568306010929,
+      "grad_norm": 0.09571345150470734,
+      "learning_rate": 2.555529521966754e-06,
+      "loss": 0.3473111391067505,
+      "step": 1066
+    },
+    {
+      "epoch": 2.918032786885246,
+      "grad_norm": 0.21488875150680542,
+      "learning_rate": 2.5490073791640125e-06,
+      "loss": 0.45797085762023926,
+      "step": 1068
+    },
+    {
+      "epoch": 2.9234972677595628,
+      "grad_norm": 0.27381402254104614,
+      "learning_rate": 2.542891723040009e-06,
+      "loss": 0.5820063948631287,
+      "step": 1070
+    },
+    {
+      "epoch": 2.92896174863388,
+      "grad_norm": 0.19229131937026978,
+      "learning_rate": 2.5371827755333562e-06,
+      "loss": 0.7217463254928589,
+      "step": 1072
+    },
+    {
+      "epoch": 2.9344262295081966,
+      "grad_norm": 0.21169181168079376,
+      "learning_rate": 2.5318807438231114e-06,
+      "loss": 0.35460832715034485,
+      "step": 1074
+    },
+    {
+      "epoch": 2.939890710382514,
+      "grad_norm": 0.20496554672718048,
+      "learning_rate": 2.5269858203212634e-06,
+      "loss": 0.3624781668186188,
+      "step": 1076
+    },
+    {
+      "epoch": 2.9453551912568305,
+      "grad_norm": 0.267284095287323,
+      "learning_rate": 2.522498182665746e-06,
+      "loss": 0.4492642879486084,
+      "step": 1078
+    },
+    {
+      "epoch": 2.9508196721311473,
+      "grad_norm": 0.286236971616745,
+      "learning_rate": 2.5184179937139957e-06,
+      "loss": 0.6190025210380554,
+      "step": 1080
+    },
+    {
+      "epoch": 2.9562841530054644,
+      "grad_norm": 0.2303326278924942,
+      "learning_rate": 2.5147454015370368e-06,
+      "loss": 0.5356917977333069,
+      "step": 1082
+    },
+    {
+      "epoch": 2.9617486338797816,
+      "grad_norm": 0.1802782416343689,
+      "learning_rate": 2.511480539414109e-06,
+      "loss": 0.6177518367767334,
+      "step": 1084
+    },
+    {
+      "epoch": 2.9672131147540983,
+      "grad_norm": 0.15038588643074036,
+      "learning_rate": 2.508623525827835e-06,
+      "loss": 0.32314690947532654,
+      "step": 1086
+    },
+    {
+      "epoch": 2.972677595628415,
+      "grad_norm": 0.20698142051696777,
+      "learning_rate": 2.5061744644599134e-06,
+      "loss": 0.6555347442626953,
+      "step": 1088
+    },
+    {
+      "epoch": 2.978142076502732,
+      "grad_norm": 0.1626245528459549,
+      "learning_rate": 2.504133444187364e-06,
+      "loss": 0.5033056139945984,
+      "step": 1090
+    },
+    {
+      "epoch": 2.9836065573770494,
+      "grad_norm": 0.20192566514015198,
+      "learning_rate": 2.5025005390792964e-06,
+      "loss": 0.6249701380729675,
+      "step": 1092
+    },
+    {
+      "epoch": 2.989071038251366,
+      "grad_norm": 0.17979055643081665,
+      "learning_rate": 2.5012758083942227e-06,
+      "loss": 0.5733636021614075,
+      "step": 1094
+    },
+    {
+      "epoch": 2.994535519125683,
+      "grad_norm": 0.41940733790397644,
+      "learning_rate": 2.500459296577912e-06,
+      "loss": 0.4294215440750122,
+      "step": 1096
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.2482825517654419,
+      "learning_rate": 2.5000510332617706e-06,
+      "loss": 0.6288962364196777,
+      "step": 1098
+    },
+    {
+      "epoch": 3.0,
+      "step": 1098,
+      "total_flos": 4.931331991116186e+18,
+      "train_loss": 0.9040751279160407,
+      "train_runtime": 12420.2984,
+      "train_samples_per_second": 5.304,
+      "train_steps_per_second": 0.088
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1098,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 99999,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.931331991116186e+18,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}