diff --git "a/trainer_state.json" "b/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/trainer_state.json"
@@ -0,0 +1,3951 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 183,
+  "global_step": 549,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018214936247723133,
+      "grad_norm": 8.483417195876436,
+      "learning_rate": 4.705882352941176e-07,
+      "loss": 0.792,
+      "step": 1
+    },
+    {
+      "epoch": 0.0036429872495446266,
+      "grad_norm": 7.370293355302168,
+      "learning_rate": 9.411764705882352e-07,
+      "loss": 0.7618,
+      "step": 2
+    },
+    {
+      "epoch": 0.00546448087431694,
+      "grad_norm": 8.828281470296401,
+      "learning_rate": 1.411764705882353e-06,
+      "loss": 0.798,
+      "step": 3
+    },
+    {
+      "epoch": 0.007285974499089253,
+      "grad_norm": 7.996641905843589,
+      "learning_rate": 1.8823529411764705e-06,
+      "loss": 0.799,
+      "step": 4
+    },
+    {
+      "epoch": 0.009107468123861567,
+      "grad_norm": 5.679308683510637,
+      "learning_rate": 2.352941176470588e-06,
+      "loss": 0.703,
+      "step": 5
+    },
+    {
+      "epoch": 0.01092896174863388,
+      "grad_norm": 4.017882280804956,
+      "learning_rate": 2.823529411764706e-06,
+      "loss": 0.6024,
+      "step": 6
+    },
+    {
+      "epoch": 0.012750455373406194,
+      "grad_norm": 2.6645091422211795,
+      "learning_rate": 3.294117647058823e-06,
+      "loss": 0.716,
+      "step": 7
+    },
+    {
+      "epoch": 0.014571948998178506,
+      "grad_norm": 3.0108132390816054,
+      "learning_rate": 3.764705882352941e-06,
+      "loss": 0.6157,
+      "step": 8
+    },
+    {
+      "epoch": 0.01639344262295082,
+      "grad_norm": 2.748696274813349,
+      "learning_rate": 4.235294117647058e-06,
+      "loss": 0.674,
+      "step": 9
+    },
+    {
+      "epoch": 0.018214936247723135,
+      "grad_norm": 2.765963400363717,
+      "learning_rate": 4.705882352941176e-06,
+      "loss": 0.662,
+      "step": 10
+    },
+    {
+      "epoch": 0.020036429872495445,
+      "grad_norm": 2.0283815116624813,
+      "learning_rate": 5.176470588235294e-06,
+      "loss": 0.5478,
+      "step": 11
+    },
+    {
+      "epoch": 0.02185792349726776,
+      "grad_norm": 1.6884205496189686,
+      "learning_rate": 5.647058823529412e-06,
+      "loss": 0.6197,
+      "step": 12
+    },
+    {
+      "epoch": 0.023679417122040074,
+      "grad_norm": 1.9209865174719332,
+      "learning_rate": 6.1176470588235285e-06,
+      "loss": 0.6172,
+      "step": 13
+    },
+    {
+      "epoch": 0.025500910746812388,
+      "grad_norm": 1.6671170743222523,
+      "learning_rate": 6.588235294117646e-06,
+      "loss": 0.7003,
+      "step": 14
+    },
+    {
+      "epoch": 0.0273224043715847,
+      "grad_norm": 1.7653937318251773,
+      "learning_rate": 7.058823529411764e-06,
+      "loss": 0.6144,
+      "step": 15
+    },
+    {
+      "epoch": 0.029143897996357013,
+      "grad_norm": 1.6694163536385278,
+      "learning_rate": 7.529411764705882e-06,
+      "loss": 0.6644,
+      "step": 16
+    },
+    {
+      "epoch": 0.030965391621129327,
+      "grad_norm": 1.24459662447303,
+      "learning_rate": 8e-06,
+      "loss": 0.6239,
+      "step": 17
+    },
+    {
+      "epoch": 0.03278688524590164,
+      "grad_norm": 1.4386147481898333,
+      "learning_rate": 7.999930256262932e-06,
+      "loss": 0.598,
+      "step": 18
+    },
+    {
+      "epoch": 0.03460837887067395,
+      "grad_norm": 1.6183710176455128,
+      "learning_rate": 7.999721027483818e-06,
+      "loss": 0.6282,
+      "step": 19
+    },
+    {
+      "epoch": 0.03642987249544627,
+      "grad_norm": 2.2610452246136794,
+      "learning_rate": 7.999372320958861e-06,
+      "loss": 0.5843,
+      "step": 20
+    },
+    {
+      "epoch": 0.03825136612021858,
+      "grad_norm": 1.7393146801183827,
+      "learning_rate": 7.998884148848109e-06,
+      "loss": 0.6479,
+      "step": 21
+    },
+    {
+      "epoch": 0.04007285974499089,
+      "grad_norm": 1.3703584066908119,
+      "learning_rate": 7.998256528175033e-06,
+      "loss": 0.5559,
+      "step": 22
+    },
+    {
+      "epoch": 0.04189435336976321,
+      "grad_norm": 1.3670186569963991,
+      "learning_rate": 7.997489480825941e-06,
+      "loss": 0.5666,
+      "step": 23
+    },
+    {
+      "epoch": 0.04371584699453552,
+      "grad_norm": 1.383027766675318,
+      "learning_rate": 7.996583033549204e-06,
+      "loss": 0.6172,
+      "step": 24
+    },
+    {
+      "epoch": 0.04553734061930783,
+      "grad_norm": 1.4278949896780369,
+      "learning_rate": 7.995537217954335e-06,
+      "loss": 0.6508,
+      "step": 25
+    },
+    {
+      "epoch": 0.04735883424408015,
+      "grad_norm": 1.3763761366268141,
+      "learning_rate": 7.994352070510876e-06,
+      "loss": 0.5794,
+      "step": 26
+    },
+    {
+      "epoch": 0.04918032786885246,
+      "grad_norm": 1.269210429185682,
+      "learning_rate": 7.993027632547137e-06,
+      "loss": 0.6494,
+      "step": 27
+    },
+    {
+      "epoch": 0.051001821493624776,
+      "grad_norm": 1.293399215498077,
+      "learning_rate": 7.991563950248739e-06,
+      "loss": 0.6337,
+      "step": 28
+    },
+    {
+      "epoch": 0.052823315118397086,
+      "grad_norm": 1.3443794138088765,
+      "learning_rate": 7.989961074657023e-06,
+      "loss": 0.6124,
+      "step": 29
+    },
+    {
+      "epoch": 0.0546448087431694,
+      "grad_norm": 1.4797305271067247,
+      "learning_rate": 7.988219061667252e-06,
+      "loss": 0.64,
+      "step": 30
+    },
+    {
+      "epoch": 0.056466302367941715,
+      "grad_norm": 2.20965791616683,
+      "learning_rate": 7.986337972026678e-06,
+      "loss": 0.5096,
+      "step": 31
+    },
+    {
+      "epoch": 0.058287795992714025,
+      "grad_norm": 1.3472988619381234,
+      "learning_rate": 7.98431787133241e-06,
+      "loss": 0.5845,
+      "step": 32
+    },
+    {
+      "epoch": 0.060109289617486336,
+      "grad_norm": 1.922191039308769,
+      "learning_rate": 7.982158830029133e-06,
+      "loss": 0.5812,
+      "step": 33
+    },
+    {
+      "epoch": 0.061930783242258654,
+      "grad_norm": 1.5178941257266974,
+      "learning_rate": 7.979860923406654e-06,
+      "loss": 0.6065,
+      "step": 34
+    },
+    {
+      "epoch": 0.06375227686703097,
+      "grad_norm": 1.2582259195864762,
+      "learning_rate": 7.977424231597266e-06,
+      "loss": 0.6219,
+      "step": 35
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 1.440820716830347,
+      "learning_rate": 7.97484883957297e-06,
+      "loss": 0.6243,
+      "step": 36
+    },
+    {
+      "epoch": 0.06739526411657559,
+      "grad_norm": 1.2398972840100644,
+      "learning_rate": 7.972134837142497e-06,
+      "loss": 0.5014,
+      "step": 37
+    },
+    {
+      "epoch": 0.0692167577413479,
+      "grad_norm": 1.2685725818359594,
+      "learning_rate": 7.969282318948179e-06,
+      "loss": 0.6028,
+      "step": 38
+    },
+    {
+      "epoch": 0.07103825136612021,
+      "grad_norm": 1.3336293286163448,
+      "learning_rate": 7.966291384462662e-06,
+      "loss": 0.5084,
+      "step": 39
+    },
+    {
+      "epoch": 0.07285974499089254,
+      "grad_norm": 1.3736224319100918,
+      "learning_rate": 7.963162137985416e-06,
+      "loss": 0.6208,
+      "step": 40
+    },
+    {
+      "epoch": 0.07468123861566485,
+      "grad_norm": 1.1372782370001664,
+      "learning_rate": 7.959894688639114e-06,
+      "loss": 0.5566,
+      "step": 41
+    },
+    {
+      "epoch": 0.07650273224043716,
+      "grad_norm": 1.1370294392240514,
+      "learning_rate": 7.956489150365818e-06,
+      "loss": 0.5316,
+      "step": 42
+    },
+    {
+      "epoch": 0.07832422586520947,
+      "grad_norm": 1.3638397949259238,
+      "learning_rate": 7.952945641923014e-06,
+      "loss": 0.5665,
+      "step": 43
+    },
+    {
+      "epoch": 0.08014571948998178,
+      "grad_norm": 1.3721010139488579,
+      "learning_rate": 7.949264286879461e-06,
+      "loss": 0.6686,
+      "step": 44
+    },
+    {
+      "epoch": 0.08196721311475409,
+      "grad_norm": 1.3079030861579901,
+      "learning_rate": 7.94544521361089e-06,
+      "loss": 0.5678,
+      "step": 45
+    },
+    {
+      "epoch": 0.08378870673952642,
+      "grad_norm": 1.3169311772009933,
+      "learning_rate": 7.941488555295519e-06,
+      "loss": 0.5883,
+      "step": 46
+    },
+    {
+      "epoch": 0.08561020036429873,
+      "grad_norm": 1.187489505664262,
+      "learning_rate": 7.937394449909417e-06,
+      "loss": 0.6398,
+      "step": 47
+    },
+    {
+      "epoch": 0.08743169398907104,
+      "grad_norm": 1.3538084566677648,
+      "learning_rate": 7.933163040221691e-06,
+      "loss": 0.6001,
+      "step": 48
+    },
+    {
+      "epoch": 0.08925318761384335,
+      "grad_norm": 1.282030778796261,
+      "learning_rate": 7.928794473789502e-06,
+      "loss": 0.6299,
+      "step": 49
+    },
+    {
+      "epoch": 0.09107468123861566,
+      "grad_norm": 1.291046733294755,
+      "learning_rate": 7.924288902952924e-06,
+      "loss": 0.6643,
+      "step": 50
+    },
+    {
+      "epoch": 0.09289617486338798,
+      "grad_norm": 1.2600029350057804,
+      "learning_rate": 7.91964648482963e-06,
+      "loss": 0.6266,
+      "step": 51
+    },
+    {
+      "epoch": 0.0947176684881603,
+      "grad_norm": 1.383888278177588,
+      "learning_rate": 7.914867381309417e-06,
+      "loss": 0.5565,
+      "step": 52
+    },
+    {
+      "epoch": 0.0965391621129326,
+      "grad_norm": 1.2920207521690645,
+      "learning_rate": 7.909951759048553e-06,
+      "loss": 0.5539,
+      "step": 53
+    },
+    {
+      "epoch": 0.09836065573770492,
+      "grad_norm": 1.4806098875225748,
+      "learning_rate": 7.904899789463974e-06,
+      "loss": 0.4836,
+      "step": 54
+    },
+    {
+      "epoch": 0.10018214936247723,
+      "grad_norm": 1.3236781330536374,
+      "learning_rate": 7.899711648727295e-06,
+      "loss": 0.6716,
+      "step": 55
+    },
+    {
+      "epoch": 0.10200364298724955,
+      "grad_norm": 1.307628398165257,
+      "learning_rate": 7.894387517758679e-06,
+      "loss": 0.5806,
+      "step": 56
+    },
+    {
+      "epoch": 0.10382513661202186,
+      "grad_norm": 1.2494530103588137,
+      "learning_rate": 7.888927582220521e-06,
+      "loss": 0.5255,
+      "step": 57
+    },
+    {
+      "epoch": 0.10564663023679417,
+      "grad_norm": 1.1220353680400945,
+      "learning_rate": 7.883332032510978e-06,
+      "loss": 0.5951,
+      "step": 58
+    },
+    {
+      "epoch": 0.10746812386156648,
+      "grad_norm": 1.2679713293816075,
+      "learning_rate": 7.877601063757322e-06,
+      "loss": 0.6249,
+      "step": 59
+    },
+    {
+      "epoch": 0.1092896174863388,
+      "grad_norm": 1.367413675973217,
+      "learning_rate": 7.871734875809141e-06,
+      "loss": 0.5839,
+      "step": 60
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 1.3310878119591731,
+      "learning_rate": 7.86573367323137e-06,
+      "loss": 0.5441,
+      "step": 61
+    },
+    {
+      "epoch": 0.11293260473588343,
+      "grad_norm": 1.2672834778790825,
+      "learning_rate": 7.859597665297158e-06,
+      "loss": 0.5799,
+      "step": 62
+    },
+    {
+      "epoch": 0.11475409836065574,
+      "grad_norm": 1.4949905078759134,
+      "learning_rate": 7.853327065980567e-06,
+      "loss": 0.5811,
+      "step": 63
+    },
+    {
+      "epoch": 0.11657559198542805,
+      "grad_norm": 1.2772501302963368,
+      "learning_rate": 7.84692209394911e-06,
+      "loss": 0.5454,
+      "step": 64
+    },
+    {
+      "epoch": 0.11839708561020036,
+      "grad_norm": 1.4486798634496518,
+      "learning_rate": 7.84038297255613e-06,
+      "loss": 0.6189,
+      "step": 65
+    },
+    {
+      "epoch": 0.12021857923497267,
+      "grad_norm": 1.247869533369392,
+      "learning_rate": 7.83370992983301e-06,
+      "loss": 0.6109,
+      "step": 66
+    },
+    {
+      "epoch": 0.122040072859745,
+      "grad_norm": 1.4278988044592194,
+      "learning_rate": 7.826903198481218e-06,
+      "loss": 0.6362,
+      "step": 67
+    },
+    {
+      "epoch": 0.12386156648451731,
+      "grad_norm": 1.4421005783850482,
+      "learning_rate": 7.819963015864195e-06,
+      "loss": 0.5953,
+      "step": 68
+    },
+    {
+      "epoch": 0.12568306010928962,
+      "grad_norm": 1.2853062012314034,
+      "learning_rate": 7.812889623999077e-06,
+      "loss": 0.6449,
+      "step": 69
+    },
+    {
+      "epoch": 0.12750455373406194,
+      "grad_norm": 1.1806756552505506,
+      "learning_rate": 7.805683269548253e-06,
+      "loss": 0.4961,
+      "step": 70
+    },
+    {
+      "epoch": 0.12932604735883424,
+      "grad_norm": 1.1874724065893263,
+      "learning_rate": 7.798344203810772e-06,
+      "loss": 0.5731,
+      "step": 71
+    },
+    {
+      "epoch": 0.13114754098360656,
+      "grad_norm": 1.4302204052792575,
+      "learning_rate": 7.790872682713567e-06,
+      "loss": 0.5694,
+      "step": 72
+    },
+    {
+      "epoch": 0.13296903460837886,
+      "grad_norm": 1.621022341496324,
+      "learning_rate": 7.783268966802538e-06,
+      "loss": 0.5683,
+      "step": 73
+    },
+    {
+      "epoch": 0.13479052823315119,
+      "grad_norm": 1.266495179779122,
+      "learning_rate": 7.77553332123347e-06,
+      "loss": 0.6351,
+      "step": 74
+    },
+    {
+      "epoch": 0.1366120218579235,
+      "grad_norm": 1.4124120835397862,
+      "learning_rate": 7.767666015762775e-06,
+      "loss": 0.5941,
+      "step": 75
+    },
+    {
+      "epoch": 0.1384335154826958,
+      "grad_norm": 1.3413868354070095,
+      "learning_rate": 7.7596673247381e-06,
+      "loss": 0.5407,
+      "step": 76
+    },
+    {
+      "epoch": 0.14025500910746813,
+      "grad_norm": 1.305749508434761,
+      "learning_rate": 7.751537527088742e-06,
+      "loss": 0.5331,
+      "step": 77
+    },
+    {
+      "epoch": 0.14207650273224043,
+      "grad_norm": 1.2388240813097555,
+      "learning_rate": 7.743276906315936e-06,
+      "loss": 0.6214,
+      "step": 78
+    },
+    {
+      "epoch": 0.14389799635701275,
+      "grad_norm": 1.4526353435545132,
+      "learning_rate": 7.734885750482967e-06,
+      "loss": 0.5391,
+      "step": 79
+    },
+    {
+      "epoch": 0.14571948998178508,
+      "grad_norm": 1.3313440090499233,
+      "learning_rate": 7.726364352205116e-06,
+      "loss": 0.6254,
+      "step": 80
+    },
+    {
+      "epoch": 0.14754098360655737,
+      "grad_norm": 1.336317757950119,
+      "learning_rate": 7.717713008639463e-06,
+      "loss": 0.4752,
+      "step": 81
+    },
+    {
+      "epoch": 0.1493624772313297,
+      "grad_norm": 1.2089723824473042,
+      "learning_rate": 7.708932021474524e-06,
+      "loss": 0.7128,
+      "step": 82
+    },
+    {
+      "epoch": 0.151183970856102,
+      "grad_norm": 1.4923241883131872,
+      "learning_rate": 7.70002169691973e-06,
+      "loss": 0.6695,
+      "step": 83
+    },
+    {
+      "epoch": 0.15300546448087432,
+      "grad_norm": 1.1956673865353409,
+      "learning_rate": 7.690982345694746e-06,
+      "loss": 0.5046,
+      "step": 84
+    },
+    {
+      "epoch": 0.15482695810564662,
+      "grad_norm": 1.3110716423599806,
+      "learning_rate": 7.68181428301864e-06,
+      "loss": 0.5885,
+      "step": 85
+    },
+    {
+      "epoch": 0.15664845173041894,
+      "grad_norm": 1.340432170090615,
+      "learning_rate": 7.67251782859889e-06,
+      "loss": 0.5455,
+      "step": 86
+    },
+    {
+      "epoch": 0.15846994535519127,
+      "grad_norm": 1.2506027715723123,
+      "learning_rate": 7.663093306620228e-06,
+      "loss": 0.5864,
+      "step": 87
+    },
+    {
+      "epoch": 0.16029143897996356,
+      "grad_norm": 1.3974083197789515,
+      "learning_rate": 7.653541045733351e-06,
+      "loss": 0.5428,
+      "step": 88
+    },
+    {
+      "epoch": 0.1621129326047359,
+      "grad_norm": 1.5848220165792029,
+      "learning_rate": 7.643861379043442e-06,
+      "loss": 0.577,
+      "step": 89
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "grad_norm": 1.319727068673188,
+      "learning_rate": 7.634054644098566e-06,
+      "loss": 0.5787,
+      "step": 90
+    },
+    {
+      "epoch": 0.1657559198542805,
+      "grad_norm": 1.3075529460521724,
+      "learning_rate": 7.624121182877892e-06,
+      "loss": 0.6063,
+      "step": 91
+    },
+    {
+      "epoch": 0.16757741347905283,
+      "grad_norm": 1.3869090444503254,
+      "learning_rate": 7.614061341779777e-06,
+      "loss": 0.5533,
+      "step": 92
+    },
+    {
+      "epoch": 0.16939890710382513,
+      "grad_norm": 1.3038369655118094,
+      "learning_rate": 7.6038754716096755e-06,
+      "loss": 0.6403,
+      "step": 93
+    },
+    {
+      "epoch": 0.17122040072859745,
+      "grad_norm": 1.201815586378659,
+      "learning_rate": 7.593563927567915e-06,
+      "loss": 0.5341,
+      "step": 94
+    },
+    {
+      "epoch": 0.17304189435336975,
+      "grad_norm": 1.2948505897209415,
+      "learning_rate": 7.583127069237302e-06,
+      "loss": 0.5988,
+      "step": 95
+    },
+    {
+      "epoch": 0.17486338797814208,
+      "grad_norm": 1.2777544112935704,
+      "learning_rate": 7.5725652605705876e-06,
+      "loss": 0.5467,
+      "step": 96
+    },
+    {
+      "epoch": 0.1766848816029144,
+      "grad_norm": 1.347734488800424,
+      "learning_rate": 7.561878869877778e-06,
+      "loss": 0.6734,
+      "step": 97
+    },
+    {
+      "epoch": 0.1785063752276867,
+      "grad_norm": 1.3934793951098927,
+      "learning_rate": 7.551068269813282e-06,
+      "loss": 0.5408,
+      "step": 98
+    },
+    {
+      "epoch": 0.18032786885245902,
+      "grad_norm": 1.2265308094279608,
+      "learning_rate": 7.540133837362924e-06,
+      "loss": 0.5798,
+      "step": 99
+    },
+    {
+      "epoch": 0.18214936247723132,
+      "grad_norm": 1.2042353648647974,
+      "learning_rate": 7.5290759538307944e-06,
+      "loss": 0.5349,
+      "step": 100
+    },
+    {
+      "epoch": 0.18397085610200364,
+      "grad_norm": 1.198872560339186,
+      "learning_rate": 7.517895004825955e-06,
+      "loss": 0.6078,
+      "step": 101
+    },
+    {
+      "epoch": 0.18579234972677597,
+      "grad_norm": 1.5341596102925161,
+      "learning_rate": 7.506591380248991e-06,
+      "loss": 0.669,
+      "step": 102
+    },
+    {
+      "epoch": 0.18761384335154827,
+      "grad_norm": 1.2181363687268225,
+      "learning_rate": 7.495165474278411e-06,
+      "loss": 0.5508,
+      "step": 103
+    },
+    {
+      "epoch": 0.1894353369763206,
+      "grad_norm": 1.2061034316572241,
+      "learning_rate": 7.483617685356906e-06,
+      "loss": 0.6374,
+      "step": 104
+    },
+    {
+      "epoch": 0.1912568306010929,
+      "grad_norm": 1.270570136570114,
+      "learning_rate": 7.471948416177452e-06,
+      "loss": 0.6582,
+      "step": 105
+    },
+    {
+      "epoch": 0.1930783242258652,
+      "grad_norm": 1.2220914581087463,
+      "learning_rate": 7.460158073669271e-06,
+      "loss": 0.5195,
+      "step": 106
+    },
+    {
+      "epoch": 0.19489981785063754,
+      "grad_norm": 1.1327340940905815,
+      "learning_rate": 7.448247068983638e-06,
+      "loss": 0.6108,
+      "step": 107
+    },
+    {
+      "epoch": 0.19672131147540983,
+      "grad_norm": 1.2389921551395293,
+      "learning_rate": 7.43621581747954e-06,
+      "loss": 0.5197,
+      "step": 108
+    },
+    {
+      "epoch": 0.19854280510018216,
+      "grad_norm": 1.3119245038499585,
+      "learning_rate": 7.4240647387092e-06,
+      "loss": 0.5787,
+      "step": 109
+    },
+    {
+      "epoch": 0.20036429872495445,
+      "grad_norm": 1.2985603971431927,
+      "learning_rate": 7.411794256403439e-06,
+      "loss": 0.5408,
+      "step": 110
+    },
+    {
+      "epoch": 0.20218579234972678,
+      "grad_norm": 1.3547972287329184,
+      "learning_rate": 7.399404798456901e-06,
+      "loss": 0.5645,
+      "step": 111
+    },
+    {
+      "epoch": 0.2040072859744991,
+      "grad_norm": 1.247671888832723,
+      "learning_rate": 7.3868967969131364e-06,
+      "loss": 0.594,
+      "step": 112
+    },
+    {
+      "epoch": 0.2058287795992714,
+      "grad_norm": 1.1653540957694166,
+      "learning_rate": 7.374270687949531e-06,
+      "loss": 0.6022,
+      "step": 113
+    },
+    {
+      "epoch": 0.20765027322404372,
+      "grad_norm": 1.110075329220651,
+      "learning_rate": 7.3615269118620945e-06,
+      "loss": 0.4952,
+      "step": 114
+    },
+    {
+      "epoch": 0.20947176684881602,
+      "grad_norm": 1.1773358008446368,
+      "learning_rate": 7.348665913050114e-06,
+      "loss": 0.5796,
+      "step": 115
+    },
+    {
+      "epoch": 0.21129326047358835,
+      "grad_norm": 1.1762014415226016,
+      "learning_rate": 7.3356881400006485e-06,
+      "loss": 0.5019,
+      "step": 116
+    },
+    {
+      "epoch": 0.21311475409836064,
+      "grad_norm": 1.2857996230820723,
+      "learning_rate": 7.3225940452728915e-06,
+      "loss": 0.6128,
+      "step": 117
+    },
+    {
+      "epoch": 0.21493624772313297,
+      "grad_norm": 1.278319933723205,
+      "learning_rate": 7.309384085482396e-06,
+      "loss": 0.6233,
+      "step": 118
+    },
+    {
+      "epoch": 0.2167577413479053,
+      "grad_norm": 1.3246399685797854,
+      "learning_rate": 7.29605872128514e-06,
+      "loss": 0.5597,
+      "step": 119
+    },
+    {
+      "epoch": 0.2185792349726776,
+      "grad_norm": 1.3738785761031618,
+      "learning_rate": 7.282618417361476e-06,
+      "loss": 0.6105,
+      "step": 120
+    },
+    {
+      "epoch": 0.2204007285974499,
+      "grad_norm": 1.510255253584312,
+      "learning_rate": 7.269063642399912e-06,
+      "loss": 0.5677,
+      "step": 121
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.3705154463280955,
+      "learning_rate": 7.25539486908078e-06,
+      "loss": 0.5172,
+      "step": 122
+    },
+    {
+      "epoch": 0.22404371584699453,
+      "grad_norm": 1.4229862954590966,
+      "learning_rate": 7.241612574059745e-06,
+      "loss": 0.5987,
+      "step": 123
+    },
+    {
+      "epoch": 0.22586520947176686,
+      "grad_norm": 1.3813913047228632,
+      "learning_rate": 7.227717237951189e-06,
+      "loss": 0.6519,
+      "step": 124
+    },
+    {
+      "epoch": 0.22768670309653916,
+      "grad_norm": 1.4086532700921839,
+      "learning_rate": 7.213709345311444e-06,
+      "loss": 0.5507,
+      "step": 125
+    },
+    {
+      "epoch": 0.22950819672131148,
+      "grad_norm": 1.3222980277500922,
+      "learning_rate": 7.1995893846219035e-06,
+      "loss": 0.5821,
+      "step": 126
+    },
+    {
+      "epoch": 0.23132969034608378,
+      "grad_norm": 1.2772860113277071,
+      "learning_rate": 7.185357848271977e-06,
+      "loss": 0.5552,
+      "step": 127
+    },
+    {
+      "epoch": 0.2331511839708561,
+      "grad_norm": 1.3184892568778903,
+      "learning_rate": 7.17101523254193e-06,
+      "loss": 0.4548,
+      "step": 128
+    },
+    {
+      "epoch": 0.23497267759562843,
+      "grad_norm": 1.417969805143716,
+      "learning_rate": 7.156562037585575e-06,
+      "loss": 0.5907,
+      "step": 129
+    },
+    {
+      "epoch": 0.23679417122040072,
+      "grad_norm": 1.3194920301350814,
+      "learning_rate": 7.1419987674128225e-06,
+      "loss": 0.5377,
+      "step": 130
+    },
+    {
+      "epoch": 0.23861566484517305,
+      "grad_norm": 1.1915857881381822,
+      "learning_rate": 7.127325929872119e-06,
+      "loss": 0.5803,
+      "step": 131
+    },
+    {
+      "epoch": 0.24043715846994534,
+      "grad_norm": 1.294311599245113,
+      "learning_rate": 7.1125440366327245e-06,
+      "loss": 0.533,
+      "step": 132
+    },
+    {
+      "epoch": 0.24225865209471767,
+      "grad_norm": 1.2869026066621274,
+      "learning_rate": 7.0976536031668775e-06,
+      "loss": 0.5978,
+      "step": 133
+    },
+    {
+      "epoch": 0.24408014571949,
+      "grad_norm": 1.2882193076261699,
+      "learning_rate": 7.082655148731815e-06,
+      "loss": 0.5998,
+      "step": 134
+    },
+    {
+      "epoch": 0.2459016393442623,
+      "grad_norm": 1.2783117350056112,
+      "learning_rate": 7.067549196351669e-06,
+      "loss": 0.5792,
+      "step": 135
+    },
+    {
+      "epoch": 0.24772313296903462,
+      "grad_norm": 1.2465596890374582,
+      "learning_rate": 7.052336272799226e-06,
+      "loss": 0.6114,
+      "step": 136
+    },
+    {
+      "epoch": 0.2495446265938069,
+      "grad_norm": 1.3115289926959033,
+      "learning_rate": 7.037016908577555e-06,
+      "loss": 0.5711,
+      "step": 137
+    },
+    {
+      "epoch": 0.25136612021857924,
+      "grad_norm": 1.2945372654161171,
+      "learning_rate": 7.02159163790151e-06,
+      "loss": 0.6108,
+      "step": 138
+    },
+    {
+      "epoch": 0.25318761384335153,
+      "grad_norm": 1.179854303445542,
+      "learning_rate": 7.006060998679105e-06,
+      "loss": 0.5712,
+      "step": 139
+    },
+    {
+      "epoch": 0.2550091074681239,
+      "grad_norm": 1.3505552689452494,
+      "learning_rate": 6.990425532492747e-06,
+      "loss": 0.607,
+      "step": 140
+    },
+    {
+      "epoch": 0.2568306010928962,
+      "grad_norm": 1.293079490327599,
+      "learning_rate": 6.974685784580359e-06,
+      "loss": 0.5907,
+      "step": 141
+    },
+    {
+      "epoch": 0.2586520947176685,
+      "grad_norm": 1.2632127589893052,
+      "learning_rate": 6.958842303816359e-06,
+      "loss": 0.6264,
+      "step": 142
+    },
+    {
+      "epoch": 0.2604735883424408,
+      "grad_norm": 1.3425160590690703,
+      "learning_rate": 6.942895642692527e-06,
+      "loss": 0.4246,
+      "step": 143
+    },
+    {
+      "epoch": 0.26229508196721313,
+      "grad_norm": 1.5771791991344761,
+      "learning_rate": 6.926846357298732e-06,
+      "loss": 0.5806,
+      "step": 144
+    },
+    {
+      "epoch": 0.2641165755919854,
+      "grad_norm": 1.4030090930033172,
+      "learning_rate": 6.910695007303544e-06,
+      "loss": 0.5502,
+      "step": 145
+    },
+    {
+      "epoch": 0.2659380692167577,
+      "grad_norm": 1.3313664381580208,
+      "learning_rate": 6.894442155934719e-06,
+      "loss": 0.5853,
+      "step": 146
+    },
+    {
+      "epoch": 0.2677595628415301,
+      "grad_norm": 1.2706667077309404,
+      "learning_rate": 6.878088369959553e-06,
+      "loss": 0.5632,
+      "step": 147
+    },
+    {
+      "epoch": 0.26958105646630237,
+      "grad_norm": 1.2404396727083782,
+      "learning_rate": 6.861634219665117e-06,
+      "loss": 0.6277,
+      "step": 148
+    },
+    {
+      "epoch": 0.27140255009107467,
+      "grad_norm": 1.266069671654807,
+      "learning_rate": 6.845080278838381e-06,
+      "loss": 0.5883,
+      "step": 149
+    },
+    {
+      "epoch": 0.273224043715847,
+      "grad_norm": 1.4551654748561211,
+      "learning_rate": 6.82842712474619e-06,
+      "loss": 0.5585,
+      "step": 150
+    },
+    {
+      "epoch": 0.2750455373406193,
+      "grad_norm": 1.4120447459169916,
+      "learning_rate": 6.811675338115146e-06,
+      "loss": 0.5859,
+      "step": 151
+    },
+    {
+      "epoch": 0.2768670309653916,
+      "grad_norm": 1.4794301221707373,
+      "learning_rate": 6.7948255031113505e-06,
+      "loss": 0.5735,
+      "step": 152
+    },
+    {
+      "epoch": 0.2786885245901639,
+      "grad_norm": 1.4445882004520383,
+      "learning_rate": 6.777878207320034e-06,
+      "loss": 0.5308,
+      "step": 153
+    },
+    {
+      "epoch": 0.28051001821493626,
+      "grad_norm": 1.259161824393288,
+      "learning_rate": 6.760834041725068e-06,
+      "loss": 0.5683,
+      "step": 154
+    },
+    {
+      "epoch": 0.28233151183970856,
+      "grad_norm": 1.5252085328619271,
+      "learning_rate": 6.743693600688352e-06,
+      "loss": 0.625,
+      "step": 155
+    },
+    {
+      "epoch": 0.28415300546448086,
+      "grad_norm": 1.4215413394995613,
+      "learning_rate": 6.726457481929095e-06,
+      "loss": 0.5376,
+      "step": 156
+    },
+    {
+      "epoch": 0.2859744990892532,
+      "grad_norm": 1.2834803437487838,
+      "learning_rate": 6.7091262865029645e-06,
+      "loss": 0.5586,
+      "step": 157
+    },
+    {
+      "epoch": 0.2877959927140255,
+      "grad_norm": 1.320167275314629,
+      "learning_rate": 6.691700618781126e-06,
+      "loss": 0.5789,
+      "step": 158
+    },
+    {
+      "epoch": 0.2896174863387978,
+      "grad_norm": 1.8005652724042749,
+      "learning_rate": 6.674181086429177e-06,
+      "loss": 0.5188,
+      "step": 159
+    },
+    {
+      "epoch": 0.29143897996357016,
+      "grad_norm": 1.2690750482423212,
+      "learning_rate": 6.656568300385944e-06,
+      "loss": 0.5046,
+      "step": 160
+    },
+    {
+      "epoch": 0.29326047358834245,
+      "grad_norm": 1.31082889556021,
+      "learning_rate": 6.6388628748421895e-06,
+      "loss": 0.578,
+      "step": 161
+    },
+    {
+      "epoch": 0.29508196721311475,
+      "grad_norm": 1.3247928047009208,
+      "learning_rate": 6.62106542721918e-06,
+      "loss": 0.6034,
+      "step": 162
+    },
+    {
+      "epoch": 0.29690346083788705,
+      "grad_norm": 1.2229208641682885,
+      "learning_rate": 6.603176578147174e-06,
+      "loss": 0.4996,
+      "step": 163
+    },
+    {
+      "epoch": 0.2987249544626594,
+      "grad_norm": 1.3325184853391303,
+      "learning_rate": 6.585196951443763e-06,
+      "loss": 0.4985,
+      "step": 164
+    },
+    {
+      "epoch": 0.3005464480874317,
+      "grad_norm": 1.326999208770471,
+      "learning_rate": 6.5671271740921266e-06,
+      "loss": 0.5379,
+      "step": 165
+    },
+    {
+      "epoch": 0.302367941712204,
+      "grad_norm": 1.2382829663292223,
+      "learning_rate": 6.548967876219163e-06,
+      "loss": 0.5481,
+      "step": 166
+    },
+    {
+      "epoch": 0.30418943533697634,
+      "grad_norm": 1.3992391592431397,
+      "learning_rate": 6.530719691073521e-06,
+      "loss": 0.5941,
+      "step": 167
+    },
+    {
+      "epoch": 0.30601092896174864,
+      "grad_norm": 1.4237814669133988,
+      "learning_rate": 6.5123832550035165e-06,
+      "loss": 0.5879,
+      "step": 168
+    },
+    {
+      "epoch": 0.30783242258652094,
+      "grad_norm": 1.2434267947044435,
+      "learning_rate": 6.493959207434934e-06,
+      "loss": 0.5608,
+      "step": 169
+    },
+    {
+      "epoch": 0.30965391621129323,
+      "grad_norm": 1.2949876195852905,
+      "learning_rate": 6.47544819084874e-06,
+      "loss": 0.5477,
+      "step": 170
+    },
+    {
+      "epoch": 0.3114754098360656,
+      "grad_norm": 1.2709700316435848,
+      "learning_rate": 6.4568508507586715e-06,
+      "loss": 0.5913,
+      "step": 171
+    },
+    {
+      "epoch": 0.3132969034608379,
+      "grad_norm": 1.1917528631285046,
+      "learning_rate": 6.438167835688725e-06,
+      "loss": 0.5811,
+      "step": 172
+    },
+    {
+      "epoch": 0.3151183970856102,
+      "grad_norm": 1.4420942251279008,
+      "learning_rate": 6.41939979715055e-06,
+      "loss": 0.5258,
+      "step": 173
+    },
+    {
+      "epoch": 0.31693989071038253,
+      "grad_norm": 1.3898239712198435,
+      "learning_rate": 6.400547389620716e-06,
+      "loss": 0.4382,
+      "step": 174
+    },
+    {
+      "epoch": 0.31876138433515483,
+      "grad_norm": 1.1944425406473265,
+      "learning_rate": 6.3816112705178984e-06,
+      "loss": 0.4981,
+      "step": 175
+    },
+    {
+      "epoch": 0.3205828779599271,
+      "grad_norm": 1.2940463807027722,
+      "learning_rate": 6.362592100179958e-06,
+      "loss": 0.5679,
+      "step": 176
+    },
+    {
+      "epoch": 0.3224043715846995,
+      "grad_norm": 1.1827687350225293,
+      "learning_rate": 6.343490541840899e-06,
+      "loss": 0.5778,
+      "step": 177
+    },
+    {
+      "epoch": 0.3242258652094718,
+      "grad_norm": 1.2684254658308312,
+      "learning_rate": 6.3243072616077535e-06,
+      "loss": 0.5077,
+      "step": 178
+    },
+    {
+      "epoch": 0.32604735883424407,
+      "grad_norm": 1.4375046609341398,
+      "learning_rate": 6.3050429284373465e-06,
+      "loss": 0.5428,
+      "step": 179
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 1.2298035631627269,
+      "learning_rate": 6.285698214112974e-06,
+      "loss": 0.5333,
+      "step": 180
+    },
+    {
+      "epoch": 0.3296903460837887,
+      "grad_norm": 1.3091190041481056,
+      "learning_rate": 6.2662737932209695e-06,
+      "loss": 0.4829,
+      "step": 181
+    },
+    {
+      "epoch": 0.331511839708561,
+      "grad_norm": 1.399739792081344,
+      "learning_rate": 6.246770343127185e-06,
+      "loss": 0.5039,
+      "step": 182
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.4099523447236924,
+      "learning_rate": 6.227188543953368e-06,
+      "loss": 0.4718,
+      "step": 183
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_accuracy": 0.8100095999478772,
+      "eval_accuracy_first_token": 0.9386401326699834,
+      "eval_accuracy_first_token_all": 0.9740702326270558,
+      "eval_accuracy_first_token_all_total": 6749,
+      "eval_accuracy_first_token_calculate": 0.8181818181818182,
+      "eval_accuracy_first_token_calculate_total": 44,
+      "eval_accuracy_first_token_execute": 0.995049504950495,
+      "eval_accuracy_first_token_execute_total": 202,
+      "eval_accuracy_first_token_get": 0.9409190371991247,
+      "eval_accuracy_first_token_get_total": 457,
+      "eval_accuracy_first_token_python": 0.7979899497487437,
+      "eval_accuracy_first_token_python_total": 995,
+      "eval_loss": 0.5817924737930298,
+      "eval_perplexity": 1.1146453885480792,
+      "eval_runtime": 276.9015,
+      "eval_samples_per_second": 2.506,
+      "eval_steps_per_second": 0.628,
+      "eval_total_number_first_token": 9648,
+      "step": 183
+    },
+    {
+      "epoch": 0.33515482695810567,
+      "grad_norm": 1.3753718658598428,
+      "learning_rate": 6.207529078553444e-06,
+      "loss": 0.4554,
+      "step": 184
+    },
+    {
+      "epoch": 0.33697632058287796,
+      "grad_norm": 1.23834147665285,
+      "learning_rate": 6.1877926324897085e-06,
+      "loss": 0.5276,
+      "step": 185
+    },
+    {
+      "epoch": 0.33879781420765026,
+      "grad_norm": 1.4417460479810351,
+      "learning_rate": 6.16797989400891e-06,
+      "loss": 0.5891,
+      "step": 186
+    },
+    {
+      "epoch": 0.3406193078324226,
+      "grad_norm": 1.212881090816042,
+      "learning_rate": 6.148091554018264e-06,
+      "loss": 0.51,
+      "step": 187
+    },
+    {
+      "epoch": 0.3424408014571949,
+      "grad_norm": 1.3090197042208114,
+      "learning_rate": 6.128128306061346e-06,
+      "loss": 0.5551,
+      "step": 188
+    },
+    {
+      "epoch": 0.3442622950819672,
+      "grad_norm": 1.4028504868912617,
+      "learning_rate": 6.108090846293915e-06,
+      "loss": 0.571,
+      "step": 189
+    },
+    {
+      "epoch": 0.3460837887067395,
+      "grad_norm": 1.2383621150830924,
+      "learning_rate": 6.087979873459634e-06,
+      "loss": 0.4812,
+      "step": 190
+    },
+    {
+      "epoch": 0.34790528233151186,
+      "grad_norm": 1.1655822819675992,
+      "learning_rate": 6.0677960888657015e-06,
+      "loss": 0.5027,
+      "step": 191
+    },
+    {
+      "epoch": 0.34972677595628415,
+      "grad_norm": 1.2330586732923372,
+      "learning_rate": 6.047540196358404e-06,
+      "loss": 0.5472,
+      "step": 192
+    },
+    {
+      "epoch": 0.35154826958105645,
+      "grad_norm": 1.2120668135216859,
+      "learning_rate": 6.02721290229856e-06,
+      "loss": 0.4723,
+      "step": 193
+    },
+    {
+      "epoch": 0.3533697632058288,
+      "grad_norm": 1.2127776371529766,
+      "learning_rate": 6.006814915536894e-06,
+      "loss": 0.5994,
+      "step": 194
+    },
+    {
+      "epoch": 0.3551912568306011,
+      "grad_norm": 1.3781231876403488,
+      "learning_rate": 5.9863469473893225e-06,
+      "loss": 0.6055,
+      "step": 195
+    },
+    {
+      "epoch": 0.3570127504553734,
+      "grad_norm": 1.2377625062579942,
+      "learning_rate": 5.965809711612137e-06,
+      "loss": 0.6285,
+      "step": 196
+    },
+    {
+      "epoch": 0.3588342440801457,
+      "grad_norm": 1.2436458612174006,
+      "learning_rate": 5.945203924377125e-06,
+      "loss": 0.5051,
+      "step": 197
+    },
+    {
+      "epoch": 0.36065573770491804,
+      "grad_norm": 1.067560558211732,
+      "learning_rate": 5.92453030424659e-06,
+      "loss": 0.557,
+      "step": 198
+    },
+    {
+      "epoch": 0.36247723132969034,
+      "grad_norm": 1.339153659611944,
+      "learning_rate": 5.903789572148294e-06,
+      "loss": 0.5624,
+      "step": 199
+    },
+    {
+      "epoch": 0.36429872495446264,
+      "grad_norm": 1.3921715569996027,
+      "learning_rate": 5.88298245135032e-06,
+      "loss": 0.6122,
+      "step": 200
+    },
+    {
+      "epoch": 0.366120218579235,
+      "grad_norm": 1.0724617492860091,
+      "learning_rate": 5.862109667435853e-06,
+      "loss": 0.406,
+      "step": 201
+    },
+    {
+      "epoch": 0.3679417122040073,
+      "grad_norm": 1.3579568036237248,
+      "learning_rate": 5.8411719482778645e-06,
+      "loss": 0.5615,
+      "step": 202
+    },
+    {
+      "epoch": 0.3697632058287796,
+      "grad_norm": 1.392362486259979,
+      "learning_rate": 5.820170024013746e-06,
+      "loss": 0.4783,
+      "step": 203
+    },
+    {
+      "epoch": 0.37158469945355194,
+      "grad_norm": 1.4663688083889719,
+      "learning_rate": 5.79910462701984e-06,
+      "loss": 0.6462,
+      "step": 204
+    },
+    {
+      "epoch": 0.37340619307832423,
+      "grad_norm": 1.5906378406347372,
+      "learning_rate": 5.777976491885903e-06,
+      "loss": 0.5989,
+      "step": 205
+    },
+    {
+      "epoch": 0.37522768670309653,
+      "grad_norm": 1.2690398154345799,
+      "learning_rate": 5.756786355389481e-06,
+      "loss": 0.4675,
+      "step": 206
+    },
+    {
+      "epoch": 0.3770491803278688,
+      "grad_norm": 1.340814834772367,
+      "learning_rate": 5.735534956470232e-06,
+      "loss": 0.4978,
+      "step": 207
+    },
+    {
+      "epoch": 0.3788706739526412,
+      "grad_norm": 1.2798668544381595,
+      "learning_rate": 5.714223036204144e-06,
+      "loss": 0.5032,
+      "step": 208
+    },
+    {
+      "epoch": 0.3806921675774135,
+      "grad_norm": 1.2535515686753846,
+      "learning_rate": 5.6928513377777e-06,
+      "loss": 0.53,
+      "step": 209
+    },
+    {
+      "epoch": 0.3825136612021858,
+      "grad_norm": 1.2457137330041876,
+      "learning_rate": 5.671420606461956e-06,
+      "loss": 0.5851,
+      "step": 210
+    },
+    {
+      "epoch": 0.3843351548269581,
+      "grad_norm": 1.4696601482702962,
+      "learning_rate": 5.649931589586557e-06,
+      "loss": 0.654,
+      "step": 211
+    },
+    {
+      "epoch": 0.3861566484517304,
+      "grad_norm": 1.2987011689556953,
+      "learning_rate": 5.628385036513676e-06,
+      "loss": 0.5669,
+      "step": 212
+    },
+    {
+      "epoch": 0.3879781420765027,
+      "grad_norm": 1.3159510108963395,
+      "learning_rate": 5.606781698611878e-06,
+      "loss": 0.5532,
+      "step": 213
+    },
+    {
+      "epoch": 0.38979963570127507,
+      "grad_norm": 1.1640550154922134,
+      "learning_rate": 5.585122329229923e-06,
+      "loss": 0.4804,
+      "step": 214
+    },
+    {
+      "epoch": 0.39162112932604737,
+      "grad_norm": 1.257926153405232,
+      "learning_rate": 5.56340768367049e-06,
+      "loss": 0.5356,
+      "step": 215
+    },
+    {
+      "epoch": 0.39344262295081966,
+      "grad_norm": 1.2768971849963524,
+      "learning_rate": 5.541638519163849e-06,
+      "loss": 0.5141,
+      "step": 216
+    },
+    {
+      "epoch": 0.39526411657559196,
+      "grad_norm": 1.1748448811474719,
+      "learning_rate": 5.51981559484144e-06,
+      "loss": 0.6517,
+      "step": 217
+    },
+    {
+      "epoch": 0.3970856102003643,
+      "grad_norm": 2.0539459488388427,
+      "learning_rate": 5.49793967170941e-06,
+      "loss": 0.5137,
+      "step": 218
+    },
+    {
+      "epoch": 0.3989071038251366,
+      "grad_norm": 1.3340041273272538,
+      "learning_rate": 5.476011512622076e-06,
+      "loss": 0.5224,
+      "step": 219
+    },
+    {
+      "epoch": 0.4007285974499089,
+      "grad_norm": 1.2742409163320605,
+      "learning_rate": 5.454031882255319e-06,
+      "loss": 0.593,
+      "step": 220
+    },
+    {
+      "epoch": 0.40255009107468126,
+      "grad_norm": 1.4312401458156725,
+      "learning_rate": 5.43200154707992e-06,
+      "loss": 0.6052,
+      "step": 221
+    },
+    {
+      "epoch": 0.40437158469945356,
+      "grad_norm": 1.1725298771962427,
+      "learning_rate": 5.4099212753348294e-06,
+      "loss": 0.5926,
+      "step": 222
+    },
+    {
+      "epoch": 0.40619307832422585,
+      "grad_norm": 1.2329994896181276,
+      "learning_rate": 5.3877918370003806e-06,
+      "loss": 0.4412,
+      "step": 223
+    },
+    {
+      "epoch": 0.4080145719489982,
+      "grad_norm": 1.3077181540697282,
+      "learning_rate": 5.365614003771439e-06,
+      "loss": 0.4822,
+      "step": 224
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "grad_norm": 1.3216563432171085,
+      "learning_rate": 5.343388549030491e-06,
+      "loss": 0.5746,
+      "step": 225
+    },
+    {
+      "epoch": 0.4116575591985428,
+      "grad_norm": 1.4069728629721256,
+      "learning_rate": 5.321116247820669e-06,
+      "loss": 0.4688,
+      "step": 226
+    },
+    {
+      "epoch": 0.4134790528233151,
+      "grad_norm": 1.1054828696912837,
+      "learning_rate": 5.298797876818734e-06,
+      "loss": 0.5574,
+      "step": 227
+    },
+    {
+      "epoch": 0.41530054644808745,
+      "grad_norm": 1.3971039327183563,
+      "learning_rate": 5.276434214307986e-06,
+      "loss": 0.5568,
+      "step": 228
+    },
+    {
+      "epoch": 0.41712204007285975,
+      "grad_norm": 1.2052367676116202,
+      "learning_rate": 5.2540260401511255e-06,
+      "loss": 0.4715,
+      "step": 229
+    },
+    {
+      "epoch": 0.41894353369763204,
+      "grad_norm": 1.2975437539065673,
+      "learning_rate": 5.231574135763052e-06,
+      "loss": 0.531,
+      "step": 230
+    },
+    {
+      "epoch": 0.4207650273224044,
+      "grad_norm": 1.2072349064171715,
+      "learning_rate": 5.209079284083626e-06,
+      "loss": 0.4933,
+      "step": 231
+    },
+    {
+      "epoch": 0.4225865209471767,
+      "grad_norm": 1.28034314366732,
+      "learning_rate": 5.186542269550359e-06,
+      "loss": 0.6263,
+      "step": 232
+    },
+    {
+      "epoch": 0.424408014571949,
+      "grad_norm": 1.2774088433481947,
+      "learning_rate": 5.163963878071058e-06,
+      "loss": 0.5761,
+      "step": 233
+    },
+    {
+      "epoch": 0.4262295081967213,
+      "grad_norm": 1.2827700082849656,
+      "learning_rate": 5.141344896996421e-06,
+      "loss": 0.5472,
+      "step": 234
+    },
+    {
+      "epoch": 0.42805100182149364,
+      "grad_norm": 1.2399786652373073,
+      "learning_rate": 5.1186861150925844e-06,
+      "loss": 0.4721,
+      "step": 235
+    },
+    {
+      "epoch": 0.42987249544626593,
+      "grad_norm": 1.4866480679484804,
+      "learning_rate": 5.09598832251361e-06,
+      "loss": 0.5454,
+      "step": 236
+    },
+    {
+      "epoch": 0.43169398907103823,
+      "grad_norm": 1.2892625562378888,
+      "learning_rate": 5.073252310773939e-06,
+      "loss": 0.522,
+      "step": 237
+    },
+    {
+      "epoch": 0.4335154826958106,
+      "grad_norm": 1.4228683878206347,
+      "learning_rate": 5.050478872720782e-06,
+      "loss": 0.5789,
+      "step": 238
+    },
+    {
+      "epoch": 0.4353369763205829,
+      "grad_norm": 1.2557222729475248,
+      "learning_rate": 5.027668802506476e-06,
+      "loss": 0.542,
+      "step": 239
+    },
+    {
+      "epoch": 0.4371584699453552,
+      "grad_norm": 1.3719564205247436,
+      "learning_rate": 5.004822895560794e-06,
+      "loss": 0.5978,
+      "step": 240
+    },
+    {
+      "epoch": 0.43897996357012753,
+      "grad_norm": 1.2002491118216863,
+      "learning_rate": 4.981941948563196e-06,
+      "loss": 0.567,
+      "step": 241
+    },
+    {
+      "epoch": 0.4408014571948998,
+      "grad_norm": 1.23705839412736,
+      "learning_rate": 4.959026759415061e-06,
+      "loss": 0.5622,
+      "step": 242
+    },
+    {
+      "epoch": 0.4426229508196721,
+      "grad_norm": 1.2443680094563607,
+      "learning_rate": 4.936078127211849e-06,
+      "loss": 0.4652,
+      "step": 243
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.2292169146784966,
+      "learning_rate": 4.913096852215248e-06,
+      "loss": 0.4945,
+      "step": 244
+    },
+    {
+      "epoch": 0.44626593806921677,
+      "grad_norm": 1.2199454755400951,
+      "learning_rate": 4.890083735825257e-06,
+      "loss": 0.4975,
+      "step": 245
+    },
+    {
+      "epoch": 0.44808743169398907,
+      "grad_norm": 1.1351286410957175,
+      "learning_rate": 4.867039580552247e-06,
+      "loss": 0.6239,
+      "step": 246
+    },
+    {
+      "epoch": 0.44990892531876137,
+      "grad_norm": 2.489162682585333,
+      "learning_rate": 4.843965189988969e-06,
+      "loss": 0.4521,
+      "step": 247
+    },
+    {
+      "epoch": 0.4517304189435337,
+      "grad_norm": 1.3760193870465582,
+      "learning_rate": 4.820861368782537e-06,
+      "loss": 0.5452,
+      "step": 248
+    },
+    {
+      "epoch": 0.453551912568306,
+      "grad_norm": 1.9314160205055073,
+      "learning_rate": 4.79772892260637e-06,
+      "loss": 0.524,
+      "step": 249
+    },
+    {
+      "epoch": 0.4553734061930783,
+      "grad_norm": 1.381935096821563,
+      "learning_rate": 4.774568658132086e-06,
+      "loss": 0.5054,
+      "step": 250
+    },
+    {
+      "epoch": 0.45719489981785066,
+      "grad_norm": 1.4937455355331937,
+      "learning_rate": 4.751381383001386e-06,
+      "loss": 0.5263,
+      "step": 251
+    },
+    {
+      "epoch": 0.45901639344262296,
+      "grad_norm": 1.2817536849435798,
+      "learning_rate": 4.728167905797877e-06,
+      "loss": 0.4674,
+      "step": 252
+    },
+    {
+      "epoch": 0.46083788706739526,
+      "grad_norm": 1.2354902761906357,
+      "learning_rate": 4.7049290360188875e-06,
+      "loss": 0.4812,
+      "step": 253
+    },
+    {
+      "epoch": 0.46265938069216755,
+      "grad_norm": 1.278394919844599,
+      "learning_rate": 4.681665584047227e-06,
+      "loss": 0.5462,
+      "step": 254
+    },
+    {
+      "epoch": 0.4644808743169399,
+      "grad_norm": 1.2675137056539372,
+      "learning_rate": 4.658378361122936e-06,
+      "loss": 0.5193,
+      "step": 255
+    },
+    {
+      "epoch": 0.4663023679417122,
+      "grad_norm": 1.1337542247765147,
+      "learning_rate": 4.6350681793149884e-06,
+      "loss": 0.4399,
+      "step": 256
+    },
+    {
+      "epoch": 0.4681238615664845,
+      "grad_norm": 1.1926312684911093,
+      "learning_rate": 4.611735851492984e-06,
+      "loss": 0.392,
+      "step": 257
+    },
+    {
+      "epoch": 0.46994535519125685,
+      "grad_norm": 1.5088135476737818,
+      "learning_rate": 4.588382191298787e-06,
+      "loss": 0.6285,
+      "step": 258
+    },
+    {
+      "epoch": 0.47176684881602915,
+      "grad_norm": 1.2008807604194953,
+      "learning_rate": 4.5650080131181675e-06,
+      "loss": 0.6111,
+      "step": 259
+    },
+    {
+      "epoch": 0.47358834244080145,
+      "grad_norm": 1.231409667649599,
+      "learning_rate": 4.541614132052393e-06,
+      "loss": 0.5028,
+      "step": 260
+    },
+    {
+      "epoch": 0.47540983606557374,
+      "grad_norm": 1.0843389080843633,
+      "learning_rate": 4.51820136388981e-06,
+      "loss": 0.5245,
+      "step": 261
+    },
+    {
+      "epoch": 0.4772313296903461,
+      "grad_norm": 1.3503009764858278,
+      "learning_rate": 4.494770525077391e-06,
+      "loss": 0.5069,
+      "step": 262
+    },
+    {
+      "epoch": 0.4790528233151184,
+      "grad_norm": 1.2840200177200862,
+      "learning_rate": 4.4713224326922655e-06,
+      "loss": 0.5877,
+      "step": 263
+    },
+    {
+      "epoch": 0.4808743169398907,
+      "grad_norm": 1.1859994564826624,
+      "learning_rate": 4.447857904413231e-06,
+      "loss": 0.5355,
+      "step": 264
+    },
+    {
+      "epoch": 0.48269581056466304,
+      "grad_norm": 1.1755333908210361,
+      "learning_rate": 4.424377758492232e-06,
+      "loss": 0.5262,
+      "step": 265
+    },
+    {
+      "epoch": 0.48451730418943534,
+      "grad_norm": 1.3928180479700631,
+      "learning_rate": 4.40088281372583e-06,
+      "loss": 0.5019,
+      "step": 266
+    },
+    {
+      "epoch": 0.48633879781420764,
+      "grad_norm": 1.1971102520263333,
+      "learning_rate": 4.377373889426649e-06,
+      "loss": 0.5133,
+      "step": 267
+    },
+    {
+      "epoch": 0.48816029143898,
+      "grad_norm": 1.3847287014410063,
+      "learning_rate": 4.353851805394808e-06,
+      "loss": 0.5929,
+      "step": 268
+    },
+    {
+      "epoch": 0.4899817850637523,
+      "grad_norm": 1.3913642906155013,
+      "learning_rate": 4.33031738188933e-06,
+      "loss": 0.5482,
+      "step": 269
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "grad_norm": 1.2060593356882499,
+      "learning_rate": 4.306771439599534e-06,
+      "loss": 0.5505,
+      "step": 270
+    },
+    {
+      "epoch": 0.4936247723132969,
+      "grad_norm": 1.1459886490704883,
+      "learning_rate": 4.283214799616428e-06,
+      "loss": 0.5472,
+      "step": 271
+    },
+    {
+      "epoch": 0.49544626593806923,
+      "grad_norm": 1.388116383059367,
+      "learning_rate": 4.259648283404062e-06,
+      "loss": 0.5006,
+      "step": 272
+    },
+    {
+      "epoch": 0.4972677595628415,
+      "grad_norm": 1.267084901831605,
+      "learning_rate": 4.236072712770891e-06,
+      "loss": 0.5578,
+      "step": 273
+    },
+    {
+      "epoch": 0.4990892531876138,
+      "grad_norm": 1.2590176689522474,
+      "learning_rate": 4.2124889098411175e-06,
+      "loss": 0.4804,
+      "step": 274
+    },
+    {
+      "epoch": 0.5009107468123861,
+      "grad_norm": 1.2991828184628833,
+      "learning_rate": 4.1888976970260135e-06,
+      "loss": 0.4865,
+      "step": 275
+    },
+    {
+      "epoch": 0.5027322404371585,
+      "grad_norm": 1.3502024483330752,
+      "learning_rate": 4.165299896995252e-06,
+      "loss": 0.6084,
+      "step": 276
+    },
+    {
+      "epoch": 0.5045537340619308,
+      "grad_norm": 1.24662926047003,
+      "learning_rate": 4.141696332648216e-06,
+      "loss": 0.5299,
+      "step": 277
+    },
+    {
+      "epoch": 0.5063752276867031,
+      "grad_norm": 1.1169437339901658,
+      "learning_rate": 4.118087827085294e-06,
+      "loss": 0.4495,
+      "step": 278
+    },
+    {
+      "epoch": 0.5081967213114754,
+      "grad_norm": 1.5004394388158784,
+      "learning_rate": 4.094475203579191e-06,
+      "loss": 0.5311,
+      "step": 279
+    },
+    {
+      "epoch": 0.5100182149362478,
+      "grad_norm": 1.383813491474933,
+      "learning_rate": 4.070859285546209e-06,
+      "loss": 0.5176,
+      "step": 280
+    },
+    {
+      "epoch": 0.51183970856102,
+      "grad_norm": 1.4019514520014746,
+      "learning_rate": 4.047240896517539e-06,
+      "loss": 0.5066,
+      "step": 281
+    },
+    {
+      "epoch": 0.5136612021857924,
+      "grad_norm": 1.2338591970281994,
+      "learning_rate": 4.023620860110533e-06,
+      "loss": 0.5499,
+      "step": 282
+    },
+    {
+      "epoch": 0.5154826958105647,
+      "grad_norm": 1.4230250812531824,
+      "learning_rate": 4e-06,
+      "loss": 0.5209,
+      "step": 283
+    },
+    {
+      "epoch": 0.517304189435337,
+      "grad_norm": 1.3829946645846831,
+      "learning_rate": 3.976379139889467e-06,
+      "loss": 0.5384,
+      "step": 284
+    },
+    {
+      "epoch": 0.5191256830601093,
+      "grad_norm": 1.3807362256783324,
+      "learning_rate": 3.9527591034824616e-06,
+      "loss": 0.4828,
+      "step": 285
+    },
+    {
+      "epoch": 0.5209471766848816,
+      "grad_norm": 1.2837504835980802,
+      "learning_rate": 3.929140714453791e-06,
+      "loss": 0.5297,
+      "step": 286
+    },
+    {
+      "epoch": 0.5227686703096539,
+      "grad_norm": 1.2883082935052266,
+      "learning_rate": 3.9055247964208075e-06,
+      "loss": 0.5485,
+      "step": 287
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 1.2663249100766605,
+      "learning_rate": 3.8819121729147055e-06,
+      "loss": 0.4972,
+      "step": 288
+    },
+    {
+      "epoch": 0.5264116575591985,
+      "grad_norm": 1.325952034342347,
+      "learning_rate": 3.8583036673517845e-06,
+      "loss": 0.529,
+      "step": 289
+    },
+    {
+      "epoch": 0.5282331511839709,
+      "grad_norm": 1.4160215190484486,
+      "learning_rate": 3.834700103004747e-06,
+      "loss": 0.4542,
+      "step": 290
+    },
+    {
+      "epoch": 0.5300546448087432,
+      "grad_norm": 1.2682053508757782,
+      "learning_rate": 3.8111023029739866e-06,
+      "loss": 0.4907,
+      "step": 291
+    },
+    {
+      "epoch": 0.5318761384335154,
+      "grad_norm": 1.1893254878402797,
+      "learning_rate": 3.787511090158884e-06,
+      "loss": 0.5084,
+      "step": 292
+    },
+    {
+      "epoch": 0.5336976320582878,
+      "grad_norm": 1.2969065452294093,
+      "learning_rate": 3.763927287229109e-06,
+      "loss": 0.4577,
+      "step": 293
+    },
+    {
+      "epoch": 0.5355191256830601,
+      "grad_norm": 1.2651027758547007,
+      "learning_rate": 3.740351716595939e-06,
+      "loss": 0.6394,
+      "step": 294
+    },
+    {
+      "epoch": 0.5373406193078324,
+      "grad_norm": 1.3693523974507902,
+      "learning_rate": 3.7167852003835723e-06,
+      "loss": 0.5101,
+      "step": 295
+    },
+    {
+      "epoch": 0.5391621129326047,
+      "grad_norm": 1.2607338758277125,
+      "learning_rate": 3.6932285604004656e-06,
+      "loss": 0.5171,
+      "step": 296
+    },
+    {
+      "epoch": 0.5409836065573771,
+      "grad_norm": 1.3133605575947254,
+      "learning_rate": 3.669682618110671e-06,
+      "loss": 0.5532,
+      "step": 297
+    },
+    {
+      "epoch": 0.5428051001821493,
+      "grad_norm": 1.1776402028496125,
+      "learning_rate": 3.646148194605191e-06,
+      "loss": 0.488,
+      "step": 298
+    },
+    {
+      "epoch": 0.5446265938069217,
+      "grad_norm": 1.3163668976765623,
+      "learning_rate": 3.622626110573351e-06,
+      "loss": 0.5082,
+      "step": 299
+    },
+    {
+      "epoch": 0.546448087431694,
+      "grad_norm": 1.234697706107032,
+      "learning_rate": 3.5991171862741713e-06,
+      "loss": 0.6067,
+      "step": 300
+    },
+    {
+      "epoch": 0.5482695810564663,
+      "grad_norm": 1.4127072359417963,
+      "learning_rate": 3.575622241507768e-06,
+      "loss": 0.5798,
+      "step": 301
+    },
+    {
+      "epoch": 0.5500910746812386,
+      "grad_norm": 1.2117668842288387,
+      "learning_rate": 3.5521420955867683e-06,
+      "loss": 0.5147,
+      "step": 302
+    },
+    {
+      "epoch": 0.5519125683060109,
+      "grad_norm": 1.2967372119013212,
+      "learning_rate": 3.5286775673077332e-06,
+      "loss": 0.5121,
+      "step": 303
+    },
+    {
+      "epoch": 0.5537340619307832,
+      "grad_norm": 1.2224035940340945,
+      "learning_rate": 3.505229474922609e-06,
+      "loss": 0.5522,
+      "step": 304
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 1.249619173678802,
+      "learning_rate": 3.481798636110191e-06,
+      "loss": 0.5408,
+      "step": 305
+    },
+    {
+      "epoch": 0.5573770491803278,
+      "grad_norm": 1.3457532512289554,
+      "learning_rate": 3.458385867947607e-06,
+      "loss": 0.4521,
+      "step": 306
+    },
+    {
+      "epoch": 0.5591985428051002,
+      "grad_norm": 1.360942386694437,
+      "learning_rate": 3.434991986881833e-06,
+      "loss": 0.493,
+      "step": 307
+    },
+    {
+      "epoch": 0.5610200364298725,
+      "grad_norm": 1.3130428998562595,
+      "learning_rate": 3.4116178087012136e-06,
+      "loss": 0.5506,
+      "step": 308
+    },
+    {
+      "epoch": 0.5628415300546448,
+      "grad_norm": 1.1190533809006658,
+      "learning_rate": 3.388264148507016e-06,
+      "loss": 0.5126,
+      "step": 309
+    },
+    {
+      "epoch": 0.5646630236794171,
+      "grad_norm": 1.2987174512716828,
+      "learning_rate": 3.3649318206850116e-06,
+      "loss": 0.4693,
+      "step": 310
+    },
+    {
+      "epoch": 0.5664845173041895,
+      "grad_norm": 1.199702517512821,
+      "learning_rate": 3.3416216388770635e-06,
+      "loss": 0.6163,
+      "step": 311
+    },
+    {
+      "epoch": 0.5683060109289617,
+      "grad_norm": 1.4350182469129544,
+      "learning_rate": 3.3183344159527736e-06,
+      "loss": 0.4995,
+      "step": 312
+    },
+    {
+      "epoch": 0.5701275045537341,
+      "grad_norm": 1.1958548262022524,
+      "learning_rate": 3.2950709639811134e-06,
+      "loss": 0.49,
+      "step": 313
+    },
+    {
+      "epoch": 0.5719489981785064,
+      "grad_norm": 1.3945811458876904,
+      "learning_rate": 3.271832094202123e-06,
+      "loss": 0.5864,
+      "step": 314
+    },
+    {
+      "epoch": 0.5737704918032787,
+      "grad_norm": 1.4302437878542158,
+      "learning_rate": 3.2486186169986153e-06,
+      "loss": 0.5064,
+      "step": 315
+    },
+    {
+      "epoch": 0.575591985428051,
+      "grad_norm": 1.2460171889983833,
+      "learning_rate": 3.2254313418679154e-06,
+      "loss": 0.4993,
+      "step": 316
+    },
+    {
+      "epoch": 0.5774134790528234,
+      "grad_norm": 1.3262935951428076,
+      "learning_rate": 3.2022710773936304e-06,
+      "loss": 0.4744,
+      "step": 317
+    },
+    {
+      "epoch": 0.5792349726775956,
+      "grad_norm": 1.3389955195972856,
+      "learning_rate": 3.1791386312174633e-06,
+      "loss": 0.4928,
+      "step": 318
+    },
+    {
+      "epoch": 0.581056466302368,
+      "grad_norm": 1.2940542358009448,
+      "learning_rate": 3.1560348100110315e-06,
+      "loss": 0.5806,
+      "step": 319
+    },
+    {
+      "epoch": 0.5828779599271403,
+      "grad_norm": 1.3088940762820873,
+      "learning_rate": 3.1329604194477535e-06,
+      "loss": 0.4656,
+      "step": 320
+    },
+    {
+      "epoch": 0.5846994535519126,
+      "grad_norm": 1.27093825835977,
+      "learning_rate": 3.1099162641747427e-06,
+      "loss": 0.4405,
+      "step": 321
+    },
+    {
+      "epoch": 0.5865209471766849,
+      "grad_norm": 1.2054913034625938,
+      "learning_rate": 3.0869031477847507e-06,
+      "loss": 0.5713,
+      "step": 322
+    },
+    {
+      "epoch": 0.5883424408014571,
+      "grad_norm": 1.2012296656668295,
+      "learning_rate": 3.0639218727881508e-06,
+      "loss": 0.5791,
+      "step": 323
+    },
+    {
+      "epoch": 0.5901639344262295,
+      "grad_norm": 1.2982012651862458,
+      "learning_rate": 3.04097324058494e-06,
+      "loss": 0.5778,
+      "step": 324
+    },
+    {
+      "epoch": 0.5919854280510018,
+      "grad_norm": 1.2933931880238856,
+      "learning_rate": 3.0180580514368034e-06,
+      "loss": 0.5219,
+      "step": 325
+    },
+    {
+      "epoch": 0.5938069216757741,
+      "grad_norm": 1.4720885088406803,
+      "learning_rate": 2.9951771044392066e-06,
+      "loss": 0.5007,
+      "step": 326
+    },
+    {
+      "epoch": 0.5956284153005464,
+      "grad_norm": 1.4987465964654607,
+      "learning_rate": 2.972331197493523e-06,
+      "loss": 0.4449,
+      "step": 327
+    },
+    {
+      "epoch": 0.5974499089253188,
+      "grad_norm": 1.24446661500654,
+      "learning_rate": 2.949521127279218e-06,
+      "loss": 0.5865,
+      "step": 328
+    },
+    {
+      "epoch": 0.599271402550091,
+      "grad_norm": 1.2063717392200657,
+      "learning_rate": 2.926747689226062e-06,
+      "loss": 0.5257,
+      "step": 329
+    },
+    {
+      "epoch": 0.6010928961748634,
+      "grad_norm": 1.3076236400800156,
+      "learning_rate": 2.9040116774863896e-06,
+      "loss": 0.4262,
+      "step": 330
+    },
+    {
+      "epoch": 0.6029143897996357,
+      "grad_norm": 1.486619018414579,
+      "learning_rate": 2.881313884907416e-06,
+      "loss": 0.5119,
+      "step": 331
+    },
+    {
+      "epoch": 0.604735883424408,
+      "grad_norm": 1.4291961410481424,
+      "learning_rate": 2.8586551030035797e-06,
+      "loss": 0.5522,
+      "step": 332
+    },
+    {
+      "epoch": 0.6065573770491803,
+      "grad_norm": 1.363647670787008,
+      "learning_rate": 2.836036121928942e-06,
+      "loss": 0.4966,
+      "step": 333
+    },
+    {
+      "epoch": 0.6083788706739527,
+      "grad_norm": 1.3510346555153874,
+      "learning_rate": 2.813457730449641e-06,
+      "loss": 0.557,
+      "step": 334
+    },
+    {
+      "epoch": 0.6102003642987249,
+      "grad_norm": 1.3056707121910645,
+      "learning_rate": 2.790920715916372e-06,
+      "loss": 0.4749,
+      "step": 335
+    },
+    {
+      "epoch": 0.6120218579234973,
+      "grad_norm": 1.2674665608771611,
+      "learning_rate": 2.7684258642369484e-06,
+      "loss": 0.5118,
+      "step": 336
+    },
+    {
+      "epoch": 0.6138433515482696,
+      "grad_norm": 1.1704712319064594,
+      "learning_rate": 2.7459739598488762e-06,
+      "loss": 0.5549,
+      "step": 337
+    },
+    {
+      "epoch": 0.6156648451730419,
+      "grad_norm": 1.4094367691998289,
+      "learning_rate": 2.723565785692013e-06,
+      "loss": 0.5281,
+      "step": 338
+    },
+    {
+      "epoch": 0.6174863387978142,
+      "grad_norm": 1.1692398204308077,
+      "learning_rate": 2.701202123181266e-06,
+      "loss": 0.5117,
+      "step": 339
+    },
+    {
+      "epoch": 0.6193078324225865,
+      "grad_norm": 1.1555269052808808,
+      "learning_rate": 2.6788837521793328e-06,
+      "loss": 0.5099,
+      "step": 340
+    },
+    {
+      "epoch": 0.6211293260473588,
+      "grad_norm": 1.2795356877186783,
+      "learning_rate": 2.6566114509695096e-06,
+      "loss": 0.5776,
+      "step": 341
+    },
+    {
+      "epoch": 0.6229508196721312,
+      "grad_norm": 1.402365827706012,
+      "learning_rate": 2.634385996228561e-06,
+      "loss": 0.5233,
+      "step": 342
+    },
+    {
+      "epoch": 0.6247723132969034,
+      "grad_norm": 1.1473627159160211,
+      "learning_rate": 2.6122081629996195e-06,
+      "loss": 0.6332,
+      "step": 343
+    },
+    {
+      "epoch": 0.6265938069216758,
+      "grad_norm": 1.363153716598952,
+      "learning_rate": 2.5900787246651715e-06,
+      "loss": 0.5023,
+      "step": 344
+    },
+    {
+      "epoch": 0.6284153005464481,
+      "grad_norm": 1.3207498781298728,
+      "learning_rate": 2.567998452920081e-06,
+      "loss": 0.5304,
+      "step": 345
+    },
+    {
+      "epoch": 0.6302367941712204,
+      "grad_norm": 1.3224239362488786,
+      "learning_rate": 2.5459681177446797e-06,
+      "loss": 0.4926,
+      "step": 346
+    },
+    {
+      "epoch": 0.6320582877959927,
+      "grad_norm": 1.1481892109560257,
+      "learning_rate": 2.523988487377924e-06,
+      "loss": 0.4879,
+      "step": 347
+    },
+    {
+      "epoch": 0.6338797814207651,
+      "grad_norm": 1.3002026066911114,
+      "learning_rate": 2.50206032829059e-06,
+      "loss": 0.5203,
+      "step": 348
+    },
+    {
+      "epoch": 0.6357012750455373,
+      "grad_norm": 1.278028126213566,
+      "learning_rate": 2.4801844051585604e-06,
+      "loss": 0.3582,
+      "step": 349
+    },
+    {
+      "epoch": 0.6375227686703097,
+      "grad_norm": 1.2059444131681067,
+      "learning_rate": 2.4583614808361508e-06,
+      "loss": 0.6105,
+      "step": 350
+    },
+    {
+      "epoch": 0.639344262295082,
+      "grad_norm": 1.216009601153044,
+      "learning_rate": 2.4365923163295083e-06,
+      "loss": 0.5276,
+      "step": 351
+    },
+    {
+      "epoch": 0.6411657559198543,
+      "grad_norm": 1.3096172150636922,
+      "learning_rate": 2.4148776707700775e-06,
+      "loss": 0.5187,
+      "step": 352
+    },
+    {
+      "epoch": 0.6429872495446266,
+      "grad_norm": 1.288189929013976,
+      "learning_rate": 2.393218301388123e-06,
+      "loss": 0.5577,
+      "step": 353
+    },
+    {
+      "epoch": 0.644808743169399,
+      "grad_norm": 1.3155373684757863,
+      "learning_rate": 2.3716149634863244e-06,
+      "loss": 0.5057,
+      "step": 354
+    },
+    {
+      "epoch": 0.6466302367941712,
+      "grad_norm": 1.3419874756397705,
+      "learning_rate": 2.3500684104134433e-06,
+      "loss": 0.4088,
+      "step": 355
+    },
+    {
+      "epoch": 0.6484517304189436,
+      "grad_norm": 1.433794079225407,
+      "learning_rate": 2.328579393538046e-06,
+      "loss": 0.5522,
+      "step": 356
+    },
+    {
+      "epoch": 0.6502732240437158,
+      "grad_norm": 1.4381038473896983,
+      "learning_rate": 2.3071486622223e-06,
+      "loss": 0.5745,
+      "step": 357
+    },
+    {
+      "epoch": 0.6520947176684881,
+      "grad_norm": 1.2039623063737521,
+      "learning_rate": 2.2857769637958554e-06,
+      "loss": 0.4083,
+      "step": 358
+    },
+    {
+      "epoch": 0.6539162112932605,
+      "grad_norm": 1.1858586411225656,
+      "learning_rate": 2.2644650435297675e-06,
+      "loss": 0.5221,
+      "step": 359
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 1.2748116882040539,
+      "learning_rate": 2.243213644610519e-06,
+      "loss": 0.5085,
+      "step": 360
+    },
+    {
+      "epoch": 0.6575591985428051,
+      "grad_norm": 1.1732780097848132,
+      "learning_rate": 2.2220235081140985e-06,
+      "loss": 0.4498,
+      "step": 361
+    },
+    {
+      "epoch": 0.6593806921675774,
+      "grad_norm": 1.4343186803172785,
+      "learning_rate": 2.2008953729801583e-06,
+      "loss": 0.4823,
+      "step": 362
+    },
+    {
+      "epoch": 0.6612021857923497,
+      "grad_norm": 1.496026602053126,
+      "learning_rate": 2.1798299759862545e-06,
+      "loss": 0.4367,
+      "step": 363
+    },
+    {
+      "epoch": 0.663023679417122,
+      "grad_norm": 1.3025991152153253,
+      "learning_rate": 2.158828051722137e-06,
+      "loss": 0.571,
+      "step": 364
+    },
+    {
+      "epoch": 0.6648451730418944,
+      "grad_norm": 1.1193584120775901,
+      "learning_rate": 2.137890332564147e-06,
+      "loss": 0.4189,
+      "step": 365
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.2674961696906415,
+      "learning_rate": 2.117017548649678e-06,
+      "loss": 0.5501,
+      "step": 366
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_accuracy": 0.813597109631812,
+      "eval_accuracy_first_token": 0.9505597014925373,
+      "eval_accuracy_first_token_all": 0.9743665728256038,
+      "eval_accuracy_first_token_all_total": 6749,
+      "eval_accuracy_first_token_calculate": 0.8409090909090909,
+      "eval_accuracy_first_token_calculate_total": 44,
+      "eval_accuracy_first_token_execute": 1.0,
+      "eval_accuracy_first_token_execute_total": 202,
+      "eval_accuracy_first_token_get": 0.912472647702407,
+      "eval_accuracy_first_token_get_total": 457,
+      "eval_accuracy_first_token_python": 0.871356783919598,
+      "eval_accuracy_first_token_python_total": 995,
+      "eval_loss": 0.5661724805831909,
+      "eval_perplexity": 1.1117590100934498,
+      "eval_runtime": 274.9553,
+      "eval_samples_per_second": 2.524,
+      "eval_steps_per_second": 0.633,
+      "eval_total_number_first_token": 9648,
+      "step": 366
+    },
+    {
+      "epoch": 0.668488160291439,
+      "grad_norm": 1.2382082369437504,
+      "learning_rate": 2.0962104278517058e-06,
+      "loss": 0.4206,
+      "step": 367
+    },
+    {
+      "epoch": 0.6703096539162113,
+      "grad_norm": 1.3495235838757789,
+      "learning_rate": 2.0754696957534105e-06,
+      "loss": 0.5516,
+      "step": 368
+    },
+    {
+      "epoch": 0.6721311475409836,
+      "grad_norm": 1.192568387623234,
+      "learning_rate": 2.0547960756228746e-06,
+      "loss": 0.4107,
+      "step": 369
+    },
+    {
+      "epoch": 0.6739526411657559,
+      "grad_norm": 1.180512972457561,
+      "learning_rate": 2.0341902883878626e-06,
+      "loss": 0.486,
+      "step": 370
+    },
+    {
+      "epoch": 0.6757741347905283,
+      "grad_norm": 1.4275500278475863,
+      "learning_rate": 2.013653052610678e-06,
+      "loss": 0.4959,
+      "step": 371
+    },
+    {
+      "epoch": 0.6775956284153005,
+      "grad_norm": 1.2902691782551479,
+      "learning_rate": 1.993185084463106e-06,
+      "loss": 0.4299,
+      "step": 372
+    },
+    {
+      "epoch": 0.6794171220400729,
+      "grad_norm": 1.1323245803277089,
+      "learning_rate": 1.97278709770144e-06,
+      "loss": 0.449,
+      "step": 373
+    },
+    {
+      "epoch": 0.6812386156648452,
+      "grad_norm": 1.1729164825962006,
+      "learning_rate": 1.952459803641597e-06,
+      "loss": 0.5054,
+      "step": 374
+    },
+    {
+      "epoch": 0.6830601092896175,
+      "grad_norm": 1.302619775593189,
+      "learning_rate": 1.9322039111342977e-06,
+      "loss": 0.5069,
+      "step": 375
+    },
+    {
+      "epoch": 0.6848816029143898,
+      "grad_norm": 1.3225743591209795,
+      "learning_rate": 1.912020126540366e-06,
+      "loss": 0.4455,
+      "step": 376
+    },
+    {
+      "epoch": 0.6867030965391621,
+      "grad_norm": 1.292024983046111,
+      "learning_rate": 1.8919091537060847e-06,
+      "loss": 0.5328,
+      "step": 377
+    },
+    {
+      "epoch": 0.6885245901639344,
+      "grad_norm": 1.2278749426015196,
+      "learning_rate": 1.8718716939386541e-06,
+      "loss": 0.4648,
+      "step": 378
+    },
+    {
+      "epoch": 0.6903460837887068,
+      "grad_norm": 1.2977606986012467,
+      "learning_rate": 1.8519084459817362e-06,
+      "loss": 0.4924,
+      "step": 379
+    },
+    {
+      "epoch": 0.692167577413479,
+      "grad_norm": 1.227698057643303,
+      "learning_rate": 1.83202010599109e-06,
+      "loss": 0.4792,
+      "step": 380
+    },
+    {
+      "epoch": 0.6939890710382514,
+      "grad_norm": 1.3176757819527871,
+      "learning_rate": 1.8122073675102932e-06,
+      "loss": 0.4661,
+      "step": 381
+    },
+    {
+      "epoch": 0.6958105646630237,
+      "grad_norm": 1.60497524399408,
+      "learning_rate": 1.792470921446557e-06,
+      "loss": 0.4696,
+      "step": 382
+    },
+    {
+      "epoch": 0.697632058287796,
+      "grad_norm": 1.3498126136904973,
+      "learning_rate": 1.7728114560466324e-06,
+      "loss": 0.5222,
+      "step": 383
+    },
+    {
+      "epoch": 0.6994535519125683,
+      "grad_norm": 1.2558395717712512,
+      "learning_rate": 1.753229656872815e-06,
+      "loss": 0.4103,
+      "step": 384
+    },
+    {
+      "epoch": 0.7012750455373407,
+      "grad_norm": 1.3697944306184828,
+      "learning_rate": 1.7337262067790319e-06,
+      "loss": 0.4544,
+      "step": 385
+    },
+    {
+      "epoch": 0.7030965391621129,
+      "grad_norm": 1.368204116383326,
+      "learning_rate": 1.7143017858870259e-06,
+      "loss": 0.4975,
+      "step": 386
+    },
+    {
+      "epoch": 0.7049180327868853,
+      "grad_norm": 1.2028196112608587,
+      "learning_rate": 1.6949570715626532e-06,
+      "loss": 0.5793,
+      "step": 387
+    },
+    {
+      "epoch": 0.7067395264116576,
+      "grad_norm": 1.2193898504656977,
+      "learning_rate": 1.675692738392247e-06,
+      "loss": 0.4841,
+      "step": 388
+    },
+    {
+      "epoch": 0.7085610200364298,
+      "grad_norm": 1.2121663225442056,
+      "learning_rate": 1.6565094581591015e-06,
+      "loss": 0.4891,
+      "step": 389
+    },
+    {
+      "epoch": 0.7103825136612022,
+      "grad_norm": 1.2920888769630756,
+      "learning_rate": 1.6374078998200424e-06,
+      "loss": 0.5242,
+      "step": 390
+    },
+    {
+      "epoch": 0.7122040072859745,
+      "grad_norm": 1.2474786830204843,
+      "learning_rate": 1.6183887294820995e-06,
+      "loss": 0.4941,
+      "step": 391
+    },
+    {
+      "epoch": 0.7140255009107468,
+      "grad_norm": 1.2316800527163396,
+      "learning_rate": 1.5994526103792852e-06,
+      "loss": 0.4402,
+      "step": 392
+    },
+    {
+      "epoch": 0.7158469945355191,
+      "grad_norm": 1.267209993054678,
+      "learning_rate": 1.5806002028494509e-06,
+      "loss": 0.4665,
+      "step": 393
+    },
+    {
+      "epoch": 0.7176684881602914,
+      "grad_norm": 1.0939936334202054,
+      "learning_rate": 1.5618321643112738e-06,
+      "loss": 0.5385,
+      "step": 394
+    },
+    {
+      "epoch": 0.7194899817850637,
+      "grad_norm": 1.2229947652634188,
+      "learning_rate": 1.5431491492413286e-06,
+      "loss": 0.563,
+      "step": 395
+    },
+    {
+      "epoch": 0.7213114754098361,
+      "grad_norm": 1.3179598742616503,
+      "learning_rate": 1.52455180915126e-06,
+      "loss": 0.5043,
+      "step": 396
+    },
+    {
+      "epoch": 0.7231329690346083,
+      "grad_norm": 1.177007091506137,
+      "learning_rate": 1.506040792565066e-06,
+      "loss": 0.5163,
+      "step": 397
+    },
+    {
+      "epoch": 0.7249544626593807,
+      "grad_norm": 1.1922238886428833,
+      "learning_rate": 1.487616744996484e-06,
+      "loss": 0.4374,
+      "step": 398
+    },
+    {
+      "epoch": 0.726775956284153,
+      "grad_norm": 1.434536851445206,
+      "learning_rate": 1.4692803089264772e-06,
+      "loss": 0.4976,
+      "step": 399
+    },
+    {
+      "epoch": 0.7285974499089253,
+      "grad_norm": 1.1083154204777248,
+      "learning_rate": 1.4510321237808377e-06,
+      "loss": 0.4397,
+      "step": 400
+    },
+    {
+      "epoch": 0.7304189435336976,
+      "grad_norm": 1.446108741355073,
+      "learning_rate": 1.4328728259078746e-06,
+      "loss": 0.4707,
+      "step": 401
+    },
+    {
+      "epoch": 0.73224043715847,
+      "grad_norm": 1.3655307747592895,
+      "learning_rate": 1.414803048556236e-06,
+      "loss": 0.4509,
+      "step": 402
+    },
+    {
+      "epoch": 0.7340619307832422,
+      "grad_norm": 1.2590237151009611,
+      "learning_rate": 1.396823421852825e-06,
+      "loss": 0.4137,
+      "step": 403
+    },
+    {
+      "epoch": 0.7358834244080146,
+      "grad_norm": 1.3245324404535452,
+      "learning_rate": 1.3789345727808207e-06,
+      "loss": 0.5792,
+      "step": 404
+    },
+    {
+      "epoch": 0.7377049180327869,
+      "grad_norm": 1.2386242097070082,
+      "learning_rate": 1.3611371251578114e-06,
+      "loss": 0.5098,
+      "step": 405
+    },
+    {
+      "epoch": 0.7395264116575592,
+      "grad_norm": 1.1915406492227152,
+      "learning_rate": 1.3434316996140553e-06,
+      "loss": 0.5163,
+      "step": 406
+    },
+    {
+      "epoch": 0.7413479052823315,
+      "grad_norm": 1.4026256649335254,
+      "learning_rate": 1.3258189135708229e-06,
+      "loss": 0.4404,
+      "step": 407
+    },
+    {
+      "epoch": 0.7431693989071039,
+      "grad_norm": 1.2980107514185337,
+      "learning_rate": 1.3082993812188735e-06,
+      "loss": 0.54,
+      "step": 408
+    },
+    {
+      "epoch": 0.7449908925318761,
+      "grad_norm": 1.2715578342804374,
+      "learning_rate": 1.2908737134970364e-06,
+      "loss": 0.4448,
+      "step": 409
+    },
+    {
+      "epoch": 0.7468123861566485,
+      "grad_norm": 1.143848333980239,
+      "learning_rate": 1.2735425180709039e-06,
+      "loss": 0.4223,
+      "step": 410
+    },
+    {
+      "epoch": 0.7486338797814208,
+      "grad_norm": 1.1255231193873407,
+      "learning_rate": 1.2563063993116482e-06,
+      "loss": 0.46,
+      "step": 411
+    },
+    {
+      "epoch": 0.7504553734061931,
+      "grad_norm": 1.3419216896904982,
+      "learning_rate": 1.239165958274933e-06,
+      "loss": 0.5361,
+      "step": 412
+    },
+    {
+      "epoch": 0.7522768670309654,
+      "grad_norm": 1.4023805964702172,
+      "learning_rate": 1.2221217926799652e-06,
+      "loss": 0.4397,
+      "step": 413
+    },
+    {
+      "epoch": 0.7540983606557377,
+      "grad_norm": 1.330897728853757,
+      "learning_rate": 1.2051744968886489e-06,
+      "loss": 0.4957,
+      "step": 414
+    },
+    {
+      "epoch": 0.75591985428051,
+      "grad_norm": 1.1838422813407694,
+      "learning_rate": 1.1883246618848533e-06,
+      "loss": 0.4462,
+      "step": 415
+    },
+    {
+      "epoch": 0.7577413479052824,
+      "grad_norm": 1.1723617674919102,
+      "learning_rate": 1.1715728752538101e-06,
+      "loss": 0.451,
+      "step": 416
+    },
+    {
+      "epoch": 0.7595628415300546,
+      "grad_norm": 1.206209172251872,
+      "learning_rate": 1.1549197211616203e-06,
+      "loss": 0.415,
+      "step": 417
+    },
+    {
+      "epoch": 0.761384335154827,
+      "grad_norm": 1.3707028766377027,
+      "learning_rate": 1.1383657803348835e-06,
+      "loss": 0.4914,
+      "step": 418
+    },
+    {
+      "epoch": 0.7632058287795993,
+      "grad_norm": 1.8225393046839982,
+      "learning_rate": 1.1219116300404486e-06,
+      "loss": 0.5696,
+      "step": 419
+    },
+    {
+      "epoch": 0.7650273224043715,
+      "grad_norm": 1.2961370764387552,
+      "learning_rate": 1.10555784406528e-06,
+      "loss": 0.4906,
+      "step": 420
+    },
+    {
+      "epoch": 0.7668488160291439,
+      "grad_norm": 1.273661302678146,
+      "learning_rate": 1.089304992696455e-06,
+      "loss": 0.4176,
+      "step": 421
+    },
+    {
+      "epoch": 0.7686703096539163,
+      "grad_norm": 1.1358792116562773,
+      "learning_rate": 1.0731536427012695e-06,
+      "loss": 0.5669,
+      "step": 422
+    },
+    {
+      "epoch": 0.7704918032786885,
+      "grad_norm": 1.1543809051499938,
+      "learning_rate": 1.0571043573074736e-06,
+      "loss": 0.4731,
+      "step": 423
+    },
+    {
+      "epoch": 0.7723132969034608,
+      "grad_norm": 1.268995763936549,
+      "learning_rate": 1.041157696183641e-06,
+      "loss": 0.4944,
+      "step": 424
+    },
+    {
+      "epoch": 0.7741347905282332,
+      "grad_norm": 1.3502204931718385,
+      "learning_rate": 1.0253142154196415e-06,
+      "loss": 0.5632,
+      "step": 425
+    },
+    {
+      "epoch": 0.7759562841530054,
+      "grad_norm": 1.2861585316767994,
+      "learning_rate": 1.0095744675072525e-06,
+      "loss": 0.5321,
+      "step": 426
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 1.2500169007804636,
+      "learning_rate": 9.93939001320895e-07,
+      "loss": 0.5018,
+      "step": 427
+    },
+    {
+      "epoch": 0.7795992714025501,
+      "grad_norm": 1.1927946674927596,
+      "learning_rate": 9.784083620984884e-07,
+      "loss": 0.4495,
+      "step": 428
+    },
+    {
+      "epoch": 0.7814207650273224,
+      "grad_norm": 1.211453529275201,
+      "learning_rate": 9.62983091422446e-07,
+      "loss": 0.459,
+      "step": 429
+    },
+    {
+      "epoch": 0.7832422586520947,
+      "grad_norm": 1.191077248020614,
+      "learning_rate": 9.476637272007746e-07,
+      "loss": 0.5285,
+      "step": 430
+    },
+    {
+      "epoch": 0.785063752276867,
+      "grad_norm": 1.5578769325659387,
+      "learning_rate": 9.324508036483303e-07,
+      "loss": 0.4826,
+      "step": 431
+    },
+    {
+      "epoch": 0.7868852459016393,
+      "grad_norm": 1.143092830687595,
+      "learning_rate": 9.173448512681848e-07,
+      "loss": 0.4689,
+      "step": 432
+    },
+    {
+      "epoch": 0.7887067395264117,
+      "grad_norm": 1.3178766788423166,
+      "learning_rate": 9.023463968331238e-07,
+      "loss": 0.423,
+      "step": 433
+    },
+    {
+      "epoch": 0.7905282331511839,
+      "grad_norm": 1.270598374226235,
+      "learning_rate": 8.874559633672754e-07,
+      "loss": 0.5087,
+      "step": 434
+    },
+    {
+      "epoch": 0.7923497267759563,
+      "grad_norm": 1.3159704576848927,
+      "learning_rate": 8.726740701278808e-07,
+      "loss": 0.4658,
+      "step": 435
+    },
+    {
+      "epoch": 0.7941712204007286,
+      "grad_norm": 1.308828411323957,
+      "learning_rate": 8.580012325871773e-07,
+      "loss": 0.4874,
+      "step": 436
+    },
+    {
+      "epoch": 0.7959927140255009,
+      "grad_norm": 1.1534207003253993,
+      "learning_rate": 8.434379624144261e-07,
+      "loss": 0.559,
+      "step": 437
+    },
+    {
+      "epoch": 0.7978142076502732,
+      "grad_norm": 1.2149317958628532,
+      "learning_rate": 8.289847674580702e-07,
+      "loss": 0.4374,
+      "step": 438
+    },
+    {
+      "epoch": 0.7996357012750456,
+      "grad_norm": 1.7952195261148596,
+      "learning_rate": 8.146421517280226e-07,
+      "loss": 0.4826,
+      "step": 439
+    },
+    {
+      "epoch": 0.8014571948998178,
+      "grad_norm": 1.204321359741705,
+      "learning_rate": 8.004106153780967e-07,
+      "loss": 0.5445,
+      "step": 440
+    },
+    {
+      "epoch": 0.8032786885245902,
+      "grad_norm": 1.3038648482659696,
+      "learning_rate": 7.862906546885559e-07,
+      "loss": 0.4759,
+      "step": 441
+    },
+    {
+      "epoch": 0.8051001821493625,
+      "grad_norm": 1.3025645847276193,
+      "learning_rate": 7.722827620488108e-07,
+      "loss": 0.4493,
+      "step": 442
+    },
+    {
+      "epoch": 0.8069216757741348,
+      "grad_norm": 1.3302596060388403,
+      "learning_rate": 7.583874259402545e-07,
+      "loss": 0.5191,
+      "step": 443
+    },
+    {
+      "epoch": 0.8087431693989071,
+      "grad_norm": 1.2390558736887658,
+      "learning_rate": 7.446051309192203e-07,
+      "loss": 0.5035,
+      "step": 444
+    },
+    {
+      "epoch": 0.8105646630236795,
+      "grad_norm": 1.2987933255329953,
+      "learning_rate": 7.30936357600088e-07,
+      "loss": 0.5051,
+      "step": 445
+    },
+    {
+      "epoch": 0.8123861566484517,
+      "grad_norm": 1.3795445751301032,
+      "learning_rate": 7.173815826385246e-07,
+      "loss": 0.4551,
+      "step": 446
+    },
+    {
+      "epoch": 0.8142076502732241,
+      "grad_norm": 1.2599528493900025,
+      "learning_rate": 7.039412787148586e-07,
+      "loss": 0.4923,
+      "step": 447
+    },
+    {
+      "epoch": 0.8160291438979964,
+      "grad_norm": 1.1755103488000105,
+      "learning_rate": 6.906159145176049e-07,
+      "loss": 0.5205,
+      "step": 448
+    },
+    {
+      "epoch": 0.8178506375227687,
+      "grad_norm": 1.301352850179719,
+      "learning_rate": 6.774059547271087e-07,
+      "loss": 0.516,
+      "step": 449
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 1.2962192786547895,
+      "learning_rate": 6.643118599993518e-07,
+      "loss": 0.4872,
+      "step": 450
+    },
+    {
+      "epoch": 0.8214936247723132,
+      "grad_norm": 1.5585419654309247,
+      "learning_rate": 6.513340869498858e-07,
+      "loss": 0.5804,
+      "step": 451
+    },
+    {
+      "epoch": 0.8233151183970856,
+      "grad_norm": 1.387119348514666,
+      "learning_rate": 6.384730881379048e-07,
+      "loss": 0.5619,
+      "step": 452
+    },
+    {
+      "epoch": 0.825136612021858,
+      "grad_norm": 1.4119192925549904,
+      "learning_rate": 6.257293120504692e-07,
+      "loss": 0.631,
+      "step": 453
+    },
+    {
+      "epoch": 0.8269581056466302,
+      "grad_norm": 1.3308860456915488,
+      "learning_rate": 6.131032030868635e-07,
+      "loss": 0.485,
+      "step": 454
+    },
+    {
+      "epoch": 0.8287795992714025,
+      "grad_norm": 1.4307724793695609,
+      "learning_rate": 6.005952015430993e-07,
+      "loss": 0.5642,
+      "step": 455
+    },
+    {
+      "epoch": 0.8306010928961749,
+      "grad_norm": 1.2106456273020985,
+      "learning_rate": 5.882057435965619e-07,
+      "loss": 0.4985,
+      "step": 456
+    },
+    {
+      "epoch": 0.8324225865209471,
+      "grad_norm": 1.3115620293405426,
+      "learning_rate": 5.759352612907999e-07,
+      "loss": 0.5307,
+      "step": 457
+    },
+    {
+      "epoch": 0.8342440801457195,
+      "grad_norm": 1.248365530305497,
+      "learning_rate": 5.637841825204588e-07,
+      "loss": 0.5194,
+      "step": 458
+    },
+    {
+      "epoch": 0.8360655737704918,
+      "grad_norm": 1.2238266091876802,
+      "learning_rate": 5.517529310163627e-07,
+      "loss": 0.5482,
+      "step": 459
+    },
+    {
+      "epoch": 0.8378870673952641,
+      "grad_norm": 1.4210179624401589,
+      "learning_rate": 5.398419263307281e-07,
+      "loss": 0.4293,
+      "step": 460
+    },
+    {
+      "epoch": 0.8397085610200364,
+      "grad_norm": 1.2412519735070302,
+      "learning_rate": 5.280515838225477e-07,
+      "loss": 0.4852,
+      "step": 461
+    },
+    {
+      "epoch": 0.8415300546448088,
+      "grad_norm": 1.2092346961035594,
+      "learning_rate": 5.163823146430944e-07,
+      "loss": 0.5908,
+      "step": 462
+    },
+    {
+      "epoch": 0.843351548269581,
+      "grad_norm": 1.3880323085259179,
+      "learning_rate": 5.048345257215892e-07,
+      "loss": 0.5084,
+      "step": 463
+    },
+    {
+      "epoch": 0.8451730418943534,
+      "grad_norm": 1.2676463291192996,
+      "learning_rate": 4.934086197510088e-07,
+      "loss": 0.5547,
+      "step": 464
+    },
+    {
+      "epoch": 0.8469945355191257,
+      "grad_norm": 1.2609901690813994,
+      "learning_rate": 4.821049951740441e-07,
+      "loss": 0.5434,
+      "step": 465
+    },
+    {
+      "epoch": 0.848816029143898,
+      "grad_norm": 1.3054902000162272,
+      "learning_rate": 4.7092404616920547e-07,
+      "loss": 0.4394,
+      "step": 466
+    },
+    {
+      "epoch": 0.8506375227686703,
+      "grad_norm": 1.323905342489299,
+      "learning_rate": 4.59866162637077e-07,
+      "loss": 0.5067,
+      "step": 467
+    },
+    {
+      "epoch": 0.8524590163934426,
+      "grad_norm": 1.4483470172100243,
+      "learning_rate": 4.4893173018671816e-07,
+      "loss": 0.4553,
+      "step": 468
+    },
+    {
+      "epoch": 0.8542805100182149,
+      "grad_norm": 1.2403981869880174,
+      "learning_rate": 4.3812113012222164e-07,
+      "loss": 0.5209,
+      "step": 469
+    },
+    {
+      "epoch": 0.8561020036429873,
+      "grad_norm": 1.8179855460416823,
+      "learning_rate": 4.2743473942941177e-07,
+      "loss": 0.4736,
+      "step": 470
+    },
+    {
+      "epoch": 0.8579234972677595,
+      "grad_norm": 1.2339086882585282,
+      "learning_rate": 4.168729307626977e-07,
+      "loss": 0.5098,
+      "step": 471
+    },
+    {
+      "epoch": 0.8597449908925319,
+      "grad_norm": 1.276189228460651,
+      "learning_rate": 4.0643607243208455e-07,
+      "loss": 0.4989,
+      "step": 472
+    },
+    {
+      "epoch": 0.8615664845173042,
+      "grad_norm": 1.2203026643363581,
+      "learning_rate": 3.9612452839032384e-07,
+      "loss": 0.4462,
+      "step": 473
+    },
+    {
+      "epoch": 0.8633879781420765,
+      "grad_norm": 1.242544747026145,
+      "learning_rate": 3.859386582202231e-07,
+      "loss": 0.5232,
+      "step": 474
+    },
+    {
+      "epoch": 0.8652094717668488,
+      "grad_norm": 1.4374137888249117,
+      "learning_rate": 3.758788171221079e-07,
+      "loss": 0.5248,
+      "step": 475
+    },
+    {
+      "epoch": 0.8670309653916212,
+      "grad_norm": 1.1588668244652476,
+      "learning_rate": 3.659453559014345e-07,
+      "loss": 0.4631,
+      "step": 476
+    },
+    {
+      "epoch": 0.8688524590163934,
+      "grad_norm": 1.3937157924335801,
+      "learning_rate": 3.561386209565582e-07,
+      "loss": 0.4675,
+      "step": 477
+    },
+    {
+      "epoch": 0.8706739526411658,
+      "grad_norm": 1.376102069963406,
+      "learning_rate": 3.464589542666485e-07,
+      "loss": 0.458,
+      "step": 478
+    },
+    {
+      "epoch": 0.8724954462659381,
+      "grad_norm": 1.2706836490870992,
+      "learning_rate": 3.3690669337976996e-07,
+      "loss": 0.4851,
+      "step": 479
+    },
+    {
+      "epoch": 0.8743169398907104,
+      "grad_norm": 1.221114304425684,
+      "learning_rate": 3.2748217140111e-07,
+      "loss": 0.5032,
+      "step": 480
+    },
+    {
+      "epoch": 0.8761384335154827,
+      "grad_norm": 1.3883301701023747,
+      "learning_rate": 3.1818571698135976e-07,
+      "loss": 0.4749,
+      "step": 481
+    },
+    {
+      "epoch": 0.8779599271402551,
+      "grad_norm": 1.1787371549756893,
+      "learning_rate": 3.0901765430525337e-07,
+      "loss": 0.5106,
+      "step": 482
+    },
+    {
+      "epoch": 0.8797814207650273,
+      "grad_norm": 1.346207438421883,
+      "learning_rate": 2.9997830308027003e-07,
+      "loss": 0.4383,
+      "step": 483
+    },
+    {
+      "epoch": 0.8816029143897997,
+      "grad_norm": 1.348993463677863,
+      "learning_rate": 2.9106797852547483e-07,
+      "loss": 0.4673,
+      "step": 484
+    },
+    {
+      "epoch": 0.8834244080145719,
+      "grad_norm": 1.201847671893057,
+      "learning_rate": 2.8228699136053726e-07,
+      "loss": 0.5759,
+      "step": 485
+    },
+    {
+      "epoch": 0.8852459016393442,
+      "grad_norm": 1.340461205562142,
+      "learning_rate": 2.7363564779488446e-07,
+      "loss": 0.4465,
+      "step": 486
+    },
+    {
+      "epoch": 0.8870673952641166,
+      "grad_norm": 1.1752701027649086,
+      "learning_rate": 2.6511424951703244e-07,
+      "loss": 0.4118,
+      "step": 487
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.2789959623625877,
+      "learning_rate": 2.567230936840632e-07,
+      "loss": 0.5079,
+      "step": 488
+    },
+    {
+      "epoch": 0.8907103825136612,
+      "grad_norm": 1.2640082921345366,
+      "learning_rate": 2.4846247291125897e-07,
+      "loss": 0.4711,
+      "step": 489
+    },
+    {
+      "epoch": 0.8925318761384335,
+      "grad_norm": 1.1282519699248084,
+      "learning_rate": 2.4033267526190057e-07,
+      "loss": 0.5091,
+      "step": 490
+    },
+    {
+      "epoch": 0.8943533697632058,
+      "grad_norm": 1.2710706301896888,
+      "learning_rate": 2.323339842372234e-07,
+      "loss": 0.4149,
+      "step": 491
+    },
+    {
+      "epoch": 0.8961748633879781,
+      "grad_norm": 1.4092310204502283,
+      "learning_rate": 2.2446667876652968e-07,
+      "loss": 0.5713,
+      "step": 492
+    },
+    {
+      "epoch": 0.8979963570127505,
+      "grad_norm": 1.1624712007482816,
+      "learning_rate": 2.1673103319746146e-07,
+      "loss": 0.4281,
+      "step": 493
+    },
+    {
+      "epoch": 0.8998178506375227,
+      "grad_norm": 1.2035233792963602,
+      "learning_rate": 2.0912731728643362e-07,
+      "loss": 0.4497,
+      "step": 494
+    },
+    {
+      "epoch": 0.9016393442622951,
+      "grad_norm": 1.2087725899212483,
+      "learning_rate": 2.0165579618922757e-07,
+      "loss": 0.4554,
+      "step": 495
+    },
+    {
+      "epoch": 0.9034608378870674,
+      "grad_norm": 1.3284543377876135,
+      "learning_rate": 1.943167304517459e-07,
+      "loss": 0.4693,
+      "step": 496
+    },
+    {
+      "epoch": 0.9052823315118397,
+      "grad_norm": 1.4011820069689847,
+      "learning_rate": 1.871103760009234e-07,
+      "loss": 0.5348,
+      "step": 497
+    },
+    {
+      "epoch": 0.907103825136612,
+      "grad_norm": 1.2193252171112197,
+      "learning_rate": 1.8003698413580427e-07,
+      "loss": 0.4572,
+      "step": 498
+    },
+    {
+      "epoch": 0.9089253187613844,
+      "grad_norm": 1.1222006814434855,
+      "learning_rate": 1.7309680151878126e-07,
+      "loss": 0.5136,
+      "step": 499
+    },
+    {
+      "epoch": 0.9107468123861566,
+      "grad_norm": 1.2891850954780644,
+      "learning_rate": 1.6629007016698916e-07,
+      "loss": 0.4979,
+      "step": 500
+    },
+    {
+      "epoch": 0.912568306010929,
+      "grad_norm": 1.3322769925178861,
+      "learning_rate": 1.5961702744386973e-07,
+      "loss": 0.5423,
+      "step": 501
+    },
+    {
+      "epoch": 0.9143897996357013,
+      "grad_norm": 1.160971888154378,
+      "learning_rate": 1.5307790605089045e-07,
+      "loss": 0.4617,
+      "step": 502
+    },
+    {
+      "epoch": 0.9162112932604736,
+      "grad_norm": 1.364660127297357,
+      "learning_rate": 1.4667293401943393e-07,
+      "loss": 0.4879,
+      "step": 503
+    },
+    {
+      "epoch": 0.9180327868852459,
+      "grad_norm": 1.220502331061608,
+      "learning_rate": 1.404023347028418e-07,
+      "loss": 0.4495,
+      "step": 504
+    },
+    {
+      "epoch": 0.9198542805100182,
+      "grad_norm": 1.5127357404088118,
+      "learning_rate": 1.342663267686297e-07,
+      "loss": 0.4893,
+      "step": 505
+    },
+    {
+      "epoch": 0.9216757741347905,
+      "grad_norm": 1.0948101040744869,
+      "learning_rate": 1.2826512419085922e-07,
+      "loss": 0.4689,
+      "step": 506
+    },
+    {
+      "epoch": 0.9234972677595629,
+      "grad_norm": 1.2102894214186626,
+      "learning_rate": 1.223989362426785e-07,
+      "loss": 0.4728,
+      "step": 507
+    },
+    {
+      "epoch": 0.9253187613843351,
+      "grad_norm": 1.2964990563502878,
+      "learning_rate": 1.1666796748902142e-07,
+      "loss": 0.4591,
+      "step": 508
+    },
+    {
+      "epoch": 0.9271402550091075,
+      "grad_norm": 1.3179562572508972,
+      "learning_rate": 1.1107241777947774e-07,
+      "loss": 0.5085,
+      "step": 509
+    },
+    {
+      "epoch": 0.9289617486338798,
+      "grad_norm": 1.124362582099017,
+      "learning_rate": 1.0561248224132091e-07,
+      "loss": 0.43,
+      "step": 510
+    },
+    {
+      "epoch": 0.930783242258652,
+      "grad_norm": 1.263872009096953,
+      "learning_rate": 1.0028835127270552e-07,
+      "loss": 0.4993,
+      "step": 511
+    },
+    {
+      "epoch": 0.9326047358834244,
+      "grad_norm": 1.2997351666975574,
+      "learning_rate": 9.510021053602679e-08,
+      "loss": 0.4404,
+      "step": 512
+    },
+    {
+      "epoch": 0.9344262295081968,
+      "grad_norm": 1.329253107069971,
+      "learning_rate": 9.004824095144581e-08,
+      "loss": 0.5285,
+      "step": 513
+    },
+    {
+      "epoch": 0.936247723132969,
+      "grad_norm": 1.0886350408667627,
+      "learning_rate": 8.513261869058209e-08,
+      "loss": 0.4606,
+      "step": 514
+    },
+    {
+      "epoch": 0.9380692167577414,
+      "grad_norm": 1.2876516793995008,
+      "learning_rate": 8.035351517036914e-08,
+      "loss": 0.4777,
+      "step": 515
+    },
+    {
+      "epoch": 0.9398907103825137,
+      "grad_norm": 1.2692698581081259,
+      "learning_rate": 7.571109704707623e-08,
+      "loss": 0.4554,
+      "step": 516
+    },
+    {
+      "epoch": 0.941712204007286,
+      "grad_norm": 1.2791868173597516,
+      "learning_rate": 7.120552621049825e-08,
+      "loss": 0.4488,
+      "step": 517
+    },
+    {
+      "epoch": 0.9435336976320583,
+      "grad_norm": 1.208557284284356,
+      "learning_rate": 6.68369597783096e-08,
+      "loss": 0.4034,
+      "step": 518
+    },
+    {
+      "epoch": 0.9453551912568307,
+      "grad_norm": 1.2963091541864111,
+      "learning_rate": 6.260555009058288e-08,
+      "loss": 0.4838,
+      "step": 519
+    },
+    {
+      "epoch": 0.9471766848816029,
+      "grad_norm": 1.3727003252206291,
+      "learning_rate": 5.851144470448144e-08,
+      "loss": 0.4996,
+      "step": 520
+    },
+    {
+      "epoch": 0.9489981785063752,
+      "grad_norm": 1.3210931262200563,
+      "learning_rate": 5.455478638911071e-08,
+      "loss": 0.5332,
+      "step": 521
+    },
+    {
+      "epoch": 0.9508196721311475,
+      "grad_norm": 1.2713274273103237,
+      "learning_rate": 5.073571312053815e-08,
+      "loss": 0.4783,
+      "step": 522
+    },
+    {
+      "epoch": 0.9526411657559198,
+      "grad_norm": 1.2497269961588167,
+      "learning_rate": 4.705435807698555e-08,
+      "loss": 0.4485,
+      "step": 523
+    },
+    {
+      "epoch": 0.9544626593806922,
+      "grad_norm": 1.2309482179042086,
+      "learning_rate": 4.351084963418117e-08,
+      "loss": 0.4331,
+      "step": 524
+    },
+    {
+      "epoch": 0.9562841530054644,
+      "grad_norm": 1.1950945289140942,
+      "learning_rate": 4.010531136088691e-08,
+      "loss": 0.4604,
+      "step": 525
+    },
+    {
+      "epoch": 0.9581056466302368,
+      "grad_norm": 1.2931423414382452,
+      "learning_rate": 3.683786201458439e-08,
+      "loss": 0.3767,
+      "step": 526
+    },
+    {
+      "epoch": 0.9599271402550091,
+      "grad_norm": 1.389899139107159,
+      "learning_rate": 3.370861553733784e-08,
+      "loss": 0.4897,
+      "step": 527
+    },
+    {
+      "epoch": 0.9617486338797814,
+      "grad_norm": 1.362732666201115,
+      "learning_rate": 3.071768105181993e-08,
+      "loss": 0.499,
+      "step": 528
+    },
+    {
+      "epoch": 0.9635701275045537,
+      "grad_norm": 1.1771528381852838,
+      "learning_rate": 2.786516285750373e-08,
+      "loss": 0.5627,
+      "step": 529
+    },
+    {
+      "epoch": 0.9653916211293261,
+      "grad_norm": 1.2404159607795244,
+      "learning_rate": 2.5151160427029582e-08,
+      "loss": 0.4175,
+      "step": 530
+    },
+    {
+      "epoch": 0.9672131147540983,
+      "grad_norm": 1.3555377819209309,
+      "learning_rate": 2.2575768402733232e-08,
+      "loss": 0.4961,
+      "step": 531
+    },
+    {
+      "epoch": 0.9690346083788707,
+      "grad_norm": 1.4576298033097894,
+      "learning_rate": 2.013907659334624e-08,
+      "loss": 0.5458,
+      "step": 532
+    },
+    {
+      "epoch": 0.970856102003643,
+      "grad_norm": 1.4545178388397544,
+      "learning_rate": 1.7841169970866042e-08,
+      "loss": 0.557,
+      "step": 533
+    },
+    {
+      "epoch": 0.9726775956284153,
+      "grad_norm": 1.2516530596811049,
+      "learning_rate": 1.5682128667589e-08,
+      "loss": 0.5176,
+      "step": 534
+    },
+    {
+      "epoch": 0.9744990892531876,
+      "grad_norm": 1.395868262099181,
+      "learning_rate": 1.3662027973320612e-08,
+      "loss": 0.6025,
+      "step": 535
+    },
+    {
+      "epoch": 0.97632058287796,
+      "grad_norm": 1.228580089232679,
+      "learning_rate": 1.1780938332746515e-08,
+      "loss": 0.4352,
+      "step": 536
+    },
+    {
+      "epoch": 0.9781420765027322,
+      "grad_norm": 1.307882851191111,
+      "learning_rate": 1.0038925342977122e-08,
+      "loss": 0.4912,
+      "step": 537
+    },
+    {
+      "epoch": 0.9799635701275046,
+      "grad_norm": 1.412138408392618,
+      "learning_rate": 8.43604975126011e-09,
+      "loss": 0.5536,
+      "step": 538
+    },
+    {
+      "epoch": 0.9817850637522769,
+      "grad_norm": 1.3540327476191583,
+      "learning_rate": 6.972367452863004e-09,
+      "loss": 0.4909,
+      "step": 539
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 1.2531752735063777,
+      "learning_rate": 5.647929489122738e-09,
+      "loss": 0.4375,
+      "step": 540
+    },
+    {
+      "epoch": 0.9854280510018215,
+      "grad_norm": 1.2878472135871981,
+      "learning_rate": 4.462782045664859e-09,
+      "loss": 0.4857,
+      "step": 541
+    },
+    {
+      "epoch": 0.9872495446265938,
+      "grad_norm": 1.2374394809536116,
+      "learning_rate": 3.4169664507959216e-09,
+      "loss": 0.4435,
+      "step": 542
+    },
+    {
+      "epoch": 0.9890710382513661,
+      "grad_norm": 1.3708150206530674,
+      "learning_rate": 2.5105191740597553e-09,
+      "loss": 0.5403,
+      "step": 543
+    },
+    {
+      "epoch": 0.9908925318761385,
+      "grad_norm": 1.1853808948747229,
+      "learning_rate": 1.7434718249664803e-09,
+      "loss": 0.4532,
+      "step": 544
+    },
+    {
+      "epoch": 0.9927140255009107,
+      "grad_norm": 1.190207243267208,
+      "learning_rate": 1.1158511518902791e-09,
+      "loss": 0.4696,
+      "step": 545
+    },
+    {
+      "epoch": 0.994535519125683,
+      "grad_norm": 1.2336375950670702,
+      "learning_rate": 6.276790411372524e-10,
+      "loss": 0.4729,
+      "step": 546
+    },
+    {
+      "epoch": 0.9963570127504554,
+      "grad_norm": 1.1739246355744901,
+      "learning_rate": 2.789725161806977e-10,
+      "loss": 0.5413,
+      "step": 547
+    },
+    {
+      "epoch": 0.9981785063752276,
+      "grad_norm": 1.2297320117715114,
+      "learning_rate": 6.974373706869486e-11,
+      "loss": 0.4542,
+      "step": 548
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2871587171589334,
+      "learning_rate": 0.0,
+      "loss": 0.4884,
+      "step": 549
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8146578886019198,
+      "eval_accuracy_first_token": 0.9528399668325042,
+      "eval_accuracy_first_token_all": 0.9712550007408505,
+      "eval_accuracy_first_token_all_total": 6749,
+      "eval_accuracy_first_token_calculate": 0.8636363636363636,
+      "eval_accuracy_first_token_calculate_total": 44,
+      "eval_accuracy_first_token_execute": 1.0,
+      "eval_accuracy_first_token_execute_total": 202,
+      "eval_accuracy_first_token_get": 0.9343544857768052,
+      "eval_accuracy_first_token_get_total": 457,
+      "eval_accuracy_first_token_python": 0.8753768844221106,
+      "eval_accuracy_first_token_python_total": 995,
+      "eval_loss": 0.5619608163833618,
+      "eval_perplexity": 1.1109600199882654,
+      "eval_runtime": 283.0681,
+      "eval_samples_per_second": 2.452,
+      "eval_steps_per_second": 0.615,
+      "eval_total_number_first_token": 9648,
+      "step": 549
+    },
+    {
+      "epoch": 1.0,
+      "step": 549,
+      "total_flos": 229794172108800.0,
+      "train_loss": 0.5332211447652355,
+      "train_runtime": 12454.5665,
+      "train_samples_per_second": 0.705,
+      "train_steps_per_second": 0.044
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 549,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 229794172108800.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}