diff --git "a/sft_devstral_24B/checkpoints/checkpoint-3000/trainer_state.json" "b/sft_devstral_24B/checkpoints/checkpoint-3000/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/sft_devstral_24B/checkpoints/checkpoint-3000/trainer_state.json"
@@ -0,0 +1,10783 @@
+{
+  "best_global_step": 3000,
+  "best_metric": 0.7160727977752686,
+  "best_model_checkpoint": "runs/instruct_run_24b/checkpoints/checkpoint-3000",
+  "epoch": 1.2942826321467098,
+  "eval_steps": 100,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 1.9118273258209229,
+      "learning_rate": 8.984725965858042e-08,
+      "loss": 1.398809790611267,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 1.785147786140442,
+      "learning_rate": 2.6954177897574125e-07,
+      "loss": 1.3699476718902588,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 1.6857414245605469,
+      "learning_rate": 4.492362982929021e-07,
+      "loss": 1.4487650394439697,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 1.7351312637329102,
+      "learning_rate": 6.28930817610063e-07,
+      "loss": 1.3360817432403564,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 1.7769269943237305,
+      "learning_rate": 8.086253369272238e-07,
+      "loss": 1.4294791221618652,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 1.776668906211853,
+      "learning_rate": 9.883198562443846e-07,
+      "loss": 1.3927934169769287,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 1.500367283821106,
+      "learning_rate": 1.1680143755615454e-06,
+      "loss": 1.4140764474868774,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 1.7255949974060059,
+      "learning_rate": 1.3477088948787064e-06,
+      "loss": 1.3873623609542847,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 1.9073798656463623,
+      "learning_rate": 1.5274034141958671e-06,
+      "loss": 1.4562759399414062,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 1.7253859043121338,
+      "learning_rate": 1.707097933513028e-06,
+      "loss": 1.4264800548553467,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 1.4858287572860718,
+      "learning_rate": 1.8867924528301887e-06,
+      "loss": 1.3717138767242432,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 1.7516961097717285,
+      "learning_rate": 2.0664869721473496e-06,
+      "loss": 1.3605879545211792,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 1.754793643951416,
+      "learning_rate": 2.2461814914645104e-06,
+      "loss": 1.465327262878418,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 1.5204869508743286,
+      "learning_rate": 2.425876010781671e-06,
+      "loss": 1.3205785751342773,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 2.03002667427063,
+      "learning_rate": 2.605570530098832e-06,
+      "loss": 1.4751381874084473,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 1.6153842210769653,
+      "learning_rate": 2.785265049415993e-06,
+      "loss": 1.3976212739944458,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 1.7034062147140503,
+      "learning_rate": 2.964959568733154e-06,
+      "loss": 1.4062179327011108,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 1.5724587440490723,
+      "learning_rate": 3.1446540880503146e-06,
+      "loss": 1.2940696477890015,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 1.7072066068649292,
+      "learning_rate": 3.324348607367475e-06,
+      "loss": 1.4216598272323608,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 1.6051130294799805,
+      "learning_rate": 3.504043126684636e-06,
+      "loss": 1.4204131364822388,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 1.5114386081695557,
+      "learning_rate": 3.683737646001797e-06,
+      "loss": 1.3492953777313232,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 1.5557284355163574,
+      "learning_rate": 3.863432165318958e-06,
+      "loss": 1.4241598844528198,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 1.5814268589019775,
+      "learning_rate": 4.0431266846361185e-06,
+      "loss": 1.3903125524520874,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 1.53256356716156,
+      "learning_rate": 4.22282120395328e-06,
+      "loss": 1.3726638555526733,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 1.5670084953308105,
+      "learning_rate": 4.40251572327044e-06,
+      "loss": 1.2536468505859375,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 1.3708246946334839,
+      "learning_rate": 4.582210242587602e-06,
+      "loss": 1.2309948205947876,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 1.5670109987258911,
+      "learning_rate": 4.7619047619047615e-06,
+      "loss": 1.3564441204071045,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 1.3550655841827393,
+      "learning_rate": 4.941599281221923e-06,
+      "loss": 1.2251620292663574,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 1.4416121244430542,
+      "learning_rate": 5.121293800539084e-06,
+      "loss": 1.2395249605178833,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 1.4638670682907104,
+      "learning_rate": 5.300988319856245e-06,
+      "loss": 1.3229656219482422,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 1.2204002141952515,
+      "learning_rate": 5.4806828391734054e-06,
+      "loss": 1.1076340675354004,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 1.2641915082931519,
+      "learning_rate": 5.660377358490566e-06,
+      "loss": 1.237392544746399,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 1.4635342359542847,
+      "learning_rate": 5.840071877807727e-06,
+      "loss": 1.3567079305648804,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 1.5813465118408203,
+      "learning_rate": 6.019766397124888e-06,
+      "loss": 1.3595421314239502,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 1.435356616973877,
+      "learning_rate": 6.1994609164420485e-06,
+      "loss": 1.2183864116668701,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 1.4559556245803833,
+      "learning_rate": 6.37915543575921e-06,
+      "loss": 1.2084243297576904,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 1.2870471477508545,
+      "learning_rate": 6.558849955076371e-06,
+      "loss": 1.2476426362991333,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 1.3345798254013062,
+      "learning_rate": 6.738544474393531e-06,
+      "loss": 1.2200642824172974,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 1.48223876953125,
+      "learning_rate": 6.918238993710692e-06,
+      "loss": 1.2497955560684204,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 1.2421257495880127,
+      "learning_rate": 7.097933513027853e-06,
+      "loss": 1.1987318992614746,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 1.5042678117752075,
+      "learning_rate": 7.277628032345015e-06,
+      "loss": 1.218438982963562,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 1.3047534227371216,
+      "learning_rate": 7.457322551662174e-06,
+      "loss": 1.1181117296218872,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 1.3297117948532104,
+      "learning_rate": 7.637017070979335e-06,
+      "loss": 1.047302484512329,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 1.4515916109085083,
+      "learning_rate": 7.816711590296496e-06,
+      "loss": 1.1821871995925903,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 1.5435426235198975,
+      "learning_rate": 7.996406109613658e-06,
+      "loss": 1.1171189546585083,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 1.5270947217941284,
+      "learning_rate": 8.176100628930818e-06,
+      "loss": 1.067047357559204,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 2.4402992725372314,
+      "learning_rate": 8.35579514824798e-06,
+      "loss": 1.0745081901550293,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 1.7703081369400024,
+      "learning_rate": 8.53548966756514e-06,
+      "loss": 1.252164602279663,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 1.4324337244033813,
+      "learning_rate": 8.715184186882301e-06,
+      "loss": 1.1030420064926147,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 1.3258590698242188,
+      "learning_rate": 8.89487870619946e-06,
+      "loss": 1.0817893743515015,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.128923773765564,
+      "eval_runtime": 825.0166,
+      "eval_samples_per_second": 2.497,
+      "eval_steps_per_second": 2.497,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 1.5833592414855957,
+      "learning_rate": 9.074573225516622e-06,
+      "loss": 1.0982940196990967,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 1.5289201736450195,
+      "learning_rate": 9.254267744833784e-06,
+      "loss": 1.0529299974441528,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 1.4507837295532227,
+      "learning_rate": 9.433962264150944e-06,
+      "loss": 1.0896434783935547,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 1.3846485614776611,
+      "learning_rate": 9.613656783468104e-06,
+      "loss": 1.1196398735046387,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 1.4094940423965454,
+      "learning_rate": 9.793351302785265e-06,
+      "loss": 1.1305382251739502,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 1.7674189805984497,
+      "learning_rate": 9.973045822102427e-06,
+      "loss": 1.0138700008392334,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 1.6083961725234985,
+      "learning_rate": 1.0152740341419587e-05,
+      "loss": 1.0583173036575317,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 1.7483229637145996,
+      "learning_rate": 1.0332434860736747e-05,
+      "loss": 1.1116671562194824,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 1.8256834745407104,
+      "learning_rate": 1.0512129380053909e-05,
+      "loss": 1.0832366943359375,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 1.5875557661056519,
+      "learning_rate": 1.069182389937107e-05,
+      "loss": 1.1089236736297607,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 1.6553549766540527,
+      "learning_rate": 1.087151841868823e-05,
+      "loss": 1.1191619634628296,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 1.3675798177719116,
+      "learning_rate": 1.1051212938005392e-05,
+      "loss": 1.031973958015442,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 1.5343760251998901,
+      "learning_rate": 1.1230907457322552e-05,
+      "loss": 0.9964010119438171,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 1.5928982496261597,
+      "learning_rate": 1.1410601976639713e-05,
+      "loss": 1.1144609451293945,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 1.6411585807800293,
+      "learning_rate": 1.1590296495956873e-05,
+      "loss": 0.9953935146331787,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 1.6077220439910889,
+      "learning_rate": 1.1769991015274035e-05,
+      "loss": 0.9940203428268433,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 1.7327438592910767,
+      "learning_rate": 1.1949685534591196e-05,
+      "loss": 1.045546293258667,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 1.607404112815857,
+      "learning_rate": 1.2129380053908356e-05,
+      "loss": 0.9932523369789124,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 1.5056802034378052,
+      "learning_rate": 1.2309074573225516e-05,
+      "loss": 0.9584172368049622,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 1.5453966856002808,
+      "learning_rate": 1.2488769092542678e-05,
+      "loss": 0.9733421206474304,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 1.546397089958191,
+      "learning_rate": 1.2668463611859838e-05,
+      "loss": 0.9971115589141846,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 1.5259592533111572,
+      "learning_rate": 1.2848158131177e-05,
+      "loss": 1.0994833707809448,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 1.56397545337677,
+      "learning_rate": 1.302785265049416e-05,
+      "loss": 1.0203801393508911,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 1.618053674697876,
+      "learning_rate": 1.320754716981132e-05,
+      "loss": 1.0223872661590576,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 1.9544042348861694,
+      "learning_rate": 1.3387241689128482e-05,
+      "loss": 1.0207403898239136,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 1.7001299858093262,
+      "learning_rate": 1.3566936208445644e-05,
+      "loss": 1.025482177734375,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 1.9833810329437256,
+      "learning_rate": 1.3746630727762804e-05,
+      "loss": 1.0077980756759644,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 1.6378769874572754,
+      "learning_rate": 1.3926325247079966e-05,
+      "loss": 1.0046619176864624,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 1.762683629989624,
+      "learning_rate": 1.4106019766397124e-05,
+      "loss": 1.0332108736038208,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 1.5698739290237427,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.973042905330658,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 1.6132292747497559,
+      "learning_rate": 1.4465408805031447e-05,
+      "loss": 0.9966566562652588,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 1.989534616470337,
+      "learning_rate": 1.4645103324348609e-05,
+      "loss": 1.078708529472351,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 1.8199284076690674,
+      "learning_rate": 1.4824797843665769e-05,
+      "loss": 0.9075545072555542,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 1.6908831596374512,
+      "learning_rate": 1.500449236298293e-05,
+      "loss": 0.9268680810928345,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 1.5648242235183716,
+      "learning_rate": 1.5184186882300092e-05,
+      "loss": 1.0361101627349854,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 1.8292360305786133,
+      "learning_rate": 1.5363881401617252e-05,
+      "loss": 0.9197717905044556,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 1.6882517337799072,
+      "learning_rate": 1.554357592093441e-05,
+      "loss": 0.9661652445793152,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 1.695921778678894,
+      "learning_rate": 1.572327044025157e-05,
+      "loss": 1.0006932020187378,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 2.0128681659698486,
+      "learning_rate": 1.5902964959568733e-05,
+      "loss": 1.0096064805984497,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 1.6833231449127197,
+      "learning_rate": 1.6082659478885895e-05,
+      "loss": 0.972679853439331,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 1.6940670013427734,
+      "learning_rate": 1.6262353998203056e-05,
+      "loss": 0.9232968091964722,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 2.0851218700408936,
+      "learning_rate": 1.6442048517520218e-05,
+      "loss": 0.981245219707489,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 1.3769028186798096,
+      "learning_rate": 1.662174303683738e-05,
+      "loss": 0.9762678146362305,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 1.85263192653656,
+      "learning_rate": 1.6801437556154538e-05,
+      "loss": 0.9905523061752319,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 1.654221534729004,
+      "learning_rate": 1.69811320754717e-05,
+      "loss": 0.8457058072090149,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 1.7715294361114502,
+      "learning_rate": 1.7160826594788858e-05,
+      "loss": 1.0171988010406494,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 1.7162128686904907,
+      "learning_rate": 1.734052111410602e-05,
+      "loss": 0.9767695069313049,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 1.7938538789749146,
+      "learning_rate": 1.752021563342318e-05,
+      "loss": 0.9786219596862793,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 1.944226861000061,
+      "learning_rate": 1.7699910152740342e-05,
+      "loss": 0.9941093921661377,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 1.816835880279541,
+      "learning_rate": 1.7879604672057504e-05,
+      "loss": 0.8924376964569092,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 0.981117308139801,
+      "eval_runtime": 826.4469,
+      "eval_samples_per_second": 2.493,
+      "eval_steps_per_second": 2.493,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 1.8230189085006714,
+      "learning_rate": 1.8059299191374666e-05,
+      "loss": 0.9908216595649719,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 1.8223077058792114,
+      "learning_rate": 1.8238993710691824e-05,
+      "loss": 0.9657744765281677,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.811195731163025,
+      "learning_rate": 1.8418688230008986e-05,
+      "loss": 0.9397313594818115,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 1.579998254776001,
+      "learning_rate": 1.8598382749326147e-05,
+      "loss": 0.8770087361335754,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 1.592136263847351,
+      "learning_rate": 1.8778077268643305e-05,
+      "loss": 0.922799825668335,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 1.9334869384765625,
+      "learning_rate": 1.8957771787960467e-05,
+      "loss": 0.9007947444915771,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 1.8619475364685059,
+      "learning_rate": 1.913746630727763e-05,
+      "loss": 0.9261049628257751,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 1.751584529876709,
+      "learning_rate": 1.931716082659479e-05,
+      "loss": 0.9319002628326416,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 2.1829185485839844,
+      "learning_rate": 1.9496855345911952e-05,
+      "loss": 0.947629451751709,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 1.8973567485809326,
+      "learning_rate": 1.967654986522911e-05,
+      "loss": 0.9213902354240417,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 1.9995585680007935,
+      "learning_rate": 1.985624438454627e-05,
+      "loss": 0.9058182835578918,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 1.9369088411331177,
+      "learning_rate": 2.0035938903863433e-05,
+      "loss": 0.8918466567993164,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 2.1926183700561523,
+      "learning_rate": 2.0215633423180595e-05,
+      "loss": 1.009294033050537,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 1.872399926185608,
+      "learning_rate": 2.0395327942497757e-05,
+      "loss": 0.9543544054031372,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 2.011009454727173,
+      "learning_rate": 2.0575022461814915e-05,
+      "loss": 0.9188834428787231,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 1.8422952890396118,
+      "learning_rate": 2.0754716981132076e-05,
+      "loss": 0.84498131275177,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 2.208738088607788,
+      "learning_rate": 2.0934411500449238e-05,
+      "loss": 0.9864624738693237,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 1.6119916439056396,
+      "learning_rate": 2.1114106019766396e-05,
+      "loss": 0.928769588470459,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 1.906336784362793,
+      "learning_rate": 2.1293800539083558e-05,
+      "loss": 0.885361909866333,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 2.046064615249634,
+      "learning_rate": 2.147349505840072e-05,
+      "loss": 0.9497957229614258,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 2.1612143516540527,
+      "learning_rate": 2.165318957771788e-05,
+      "loss": 0.958332896232605,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 2.139829635620117,
+      "learning_rate": 2.1832884097035043e-05,
+      "loss": 1.0089390277862549,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 1.9842045307159424,
+      "learning_rate": 2.2012578616352204e-05,
+      "loss": 0.9627355933189392,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 1.968578577041626,
+      "learning_rate": 2.2192273135669366e-05,
+      "loss": 0.9260450601577759,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 2.192275047302246,
+      "learning_rate": 2.2371967654986524e-05,
+      "loss": 1.0654462575912476,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 2.0267577171325684,
+      "learning_rate": 2.2551662174303682e-05,
+      "loss": 0.9680672883987427,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 1.9834461212158203,
+      "learning_rate": 2.2731356693620844e-05,
+      "loss": 1.0027307271957397,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 2.0105156898498535,
+      "learning_rate": 2.2911051212938006e-05,
+      "loss": 1.0050861835479736,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 1.9150307178497314,
+      "learning_rate": 2.3090745732255167e-05,
+      "loss": 0.8955062627792358,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 2.100795269012451,
+      "learning_rate": 2.327044025157233e-05,
+      "loss": 0.941332221031189,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 1.837814211845398,
+      "learning_rate": 2.345013477088949e-05,
+      "loss": 0.9292652606964111,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 1.9122955799102783,
+      "learning_rate": 2.3629829290206652e-05,
+      "loss": 0.9460650682449341,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 1.9168611764907837,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.8730320334434509,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 2.1184403896331787,
+      "learning_rate": 2.3989218328840972e-05,
+      "loss": 0.9194066524505615,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 1.910470962524414,
+      "learning_rate": 2.4168912848158133e-05,
+      "loss": 0.8994337320327759,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 1.9906529188156128,
+      "learning_rate": 2.434860736747529e-05,
+      "loss": 0.8509554266929626,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 2.5982062816619873,
+      "learning_rate": 2.4528301886792453e-05,
+      "loss": 1.0223658084869385,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 1.8959418535232544,
+      "learning_rate": 2.4707996406109615e-05,
+      "loss": 0.8702670931816101,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 2.115907669067383,
+      "learning_rate": 2.4887690925426776e-05,
+      "loss": 0.9471842050552368,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 2.0255353450775146,
+      "learning_rate": 2.5067385444743935e-05,
+      "loss": 0.805242657661438,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 1.9394105672836304,
+      "learning_rate": 2.52470799640611e-05,
+      "loss": 0.9008285999298096,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 2.2017428874969482,
+      "learning_rate": 2.5426774483378258e-05,
+      "loss": 0.950639009475708,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 4.048379421234131,
+      "learning_rate": 2.5606469002695423e-05,
+      "loss": 0.9673396944999695,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 1.812450647354126,
+      "learning_rate": 2.578616352201258e-05,
+      "loss": 0.8251164555549622,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 1.9298596382141113,
+      "learning_rate": 2.596585804132974e-05,
+      "loss": 0.9397821426391602,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 2.0862202644348145,
+      "learning_rate": 2.61455525606469e-05,
+      "loss": 0.95896315574646,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 2.113429307937622,
+      "learning_rate": 2.632524707996406e-05,
+      "loss": 0.9547653198242188,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 2.0666873455047607,
+      "learning_rate": 2.6504941599281224e-05,
+      "loss": 0.9351654052734375,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 2.0679547786712646,
+      "learning_rate": 2.6684636118598382e-05,
+      "loss": 0.9268350005149841,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 2.028594493865967,
+      "learning_rate": 2.6864330637915547e-05,
+      "loss": 0.8522316813468933,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 0.9384957551956177,
+      "eval_runtime": 835.4727,
+      "eval_samples_per_second": 2.466,
+      "eval_steps_per_second": 2.466,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 2.1932919025421143,
+      "learning_rate": 2.7044025157232706e-05,
+      "loss": 0.9460103511810303,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 2.275789737701416,
+      "learning_rate": 2.722371967654987e-05,
+      "loss": 0.9642201662063599,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 1.9120908975601196,
+      "learning_rate": 2.740341419586703e-05,
+      "loss": 0.869883120059967,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 1.9676507711410522,
+      "learning_rate": 2.7583108715184187e-05,
+      "loss": 0.8595444560050964,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 1.7901391983032227,
+      "learning_rate": 2.776280323450135e-05,
+      "loss": 0.8541103601455688,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 2.160867691040039,
+      "learning_rate": 2.7942497753818507e-05,
+      "loss": 1.0146855115890503,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 2.0809009075164795,
+      "learning_rate": 2.8122192273135672e-05,
+      "loss": 0.9228161573410034,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 1.9626725912094116,
+      "learning_rate": 2.830188679245283e-05,
+      "loss": 0.8527485132217407,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 1.9569967985153198,
+      "learning_rate": 2.8481581311769995e-05,
+      "loss": 0.8136687278747559,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 2.301692247390747,
+      "learning_rate": 2.8661275831087153e-05,
+      "loss": 0.8999513387680054,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 2.0247251987457275,
+      "learning_rate": 2.884097035040431e-05,
+      "loss": 0.9751577973365784,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 2.019547462463379,
+      "learning_rate": 2.9020664869721477e-05,
+      "loss": 0.8741729259490967,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 2.3503618240356445,
+      "learning_rate": 2.9200359389038635e-05,
+      "loss": 0.948066234588623,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 2.544365406036377,
+      "learning_rate": 2.9380053908355796e-05,
+      "loss": 1.008673906326294,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 3.1647145748138428,
+      "learning_rate": 2.9559748427672958e-05,
+      "loss": 0.9492161273956299,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 2.0551259517669678,
+      "learning_rate": 2.973944294699012e-05,
+      "loss": 0.9077466130256653,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 1.6792620420455933,
+      "learning_rate": 2.9919137466307278e-05,
+      "loss": 0.8839989304542542,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 1.7771215438842773,
+      "learning_rate": 3.0098831985624436e-05,
+      "loss": 0.855834424495697,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 2.030884027481079,
+      "learning_rate": 3.02785265049416e-05,
+      "loss": 0.8477111458778381,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 2.4177005290985107,
+      "learning_rate": 3.045822102425876e-05,
+      "loss": 0.9139004945755005,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 2.094775438308716,
+      "learning_rate": 3.063791554357592e-05,
+      "loss": 0.8836029767990112,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 2.0046238899230957,
+      "learning_rate": 3.081761006289308e-05,
+      "loss": 0.9318807125091553,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 2.40739369392395,
+      "learning_rate": 3.0997304582210244e-05,
+      "loss": 0.8916489481925964,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 2.1190497875213623,
+      "learning_rate": 3.11769991015274e-05,
+      "loss": 0.90766441822052,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 2.721255302429199,
+      "learning_rate": 3.135669362084457e-05,
+      "loss": 0.9210623502731323,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 2.4988787174224854,
+      "learning_rate": 3.1536388140161726e-05,
+      "loss": 0.9134353399276733,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 2.6075687408447266,
+      "learning_rate": 3.1716082659478884e-05,
+      "loss": 0.9127986431121826,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 1.9883074760437012,
+      "learning_rate": 3.189577717879605e-05,
+      "loss": 0.8019667863845825,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 2.058591365814209,
+      "learning_rate": 3.207547169811321e-05,
+      "loss": 0.8417298197746277,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 2.0510308742523193,
+      "learning_rate": 3.225516621743037e-05,
+      "loss": 0.909717321395874,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 2.3204104900360107,
+      "learning_rate": 3.243486073674753e-05,
+      "loss": 0.9414666295051575,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 1.9658725261688232,
+      "learning_rate": 3.2614555256064695e-05,
+      "loss": 0.8631396889686584,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 2.2223057746887207,
+      "learning_rate": 3.2794249775381853e-05,
+      "loss": 0.8996705412864685,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 1.9815107583999634,
+      "learning_rate": 3.297394429469901e-05,
+      "loss": 0.8185732364654541,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 2.319581985473633,
+      "learning_rate": 3.315363881401618e-05,
+      "loss": 0.9952898025512695,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 1.7916827201843262,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.7604310512542725,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 1.955737590789795,
+      "learning_rate": 3.35130278526505e-05,
+      "loss": 0.7867834568023682,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 2.409783124923706,
+      "learning_rate": 3.369272237196766e-05,
+      "loss": 0.9106539487838745,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 2.2521097660064697,
+      "learning_rate": 3.3872416891284816e-05,
+      "loss": 0.8945732712745667,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 2.357815742492676,
+      "learning_rate": 3.4052111410601975e-05,
+      "loss": 0.8950189352035522,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 2.347301721572876,
+      "learning_rate": 3.423180592991914e-05,
+      "loss": 0.9965803623199463,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 2.054586887359619,
+      "learning_rate": 3.44115004492363e-05,
+      "loss": 0.9081383347511292,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 2.1550471782684326,
+      "learning_rate": 3.4591194968553456e-05,
+      "loss": 0.874001681804657,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 1.6929951906204224,
+      "learning_rate": 3.477088948787062e-05,
+      "loss": 0.9111959934234619,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 2.0102803707122803,
+      "learning_rate": 3.495058400718778e-05,
+      "loss": 0.8915985226631165,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 4.215941429138184,
+      "learning_rate": 3.5130278526504944e-05,
+      "loss": 1.0158213376998901,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 1.864119529724121,
+      "learning_rate": 3.53099730458221e-05,
+      "loss": 0.7811702489852905,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 1.9778105020523071,
+      "learning_rate": 3.548966756513927e-05,
+      "loss": 0.931502103805542,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 2.0757675170898438,
+      "learning_rate": 3.5669362084456426e-05,
+      "loss": 0.9409074187278748,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 1.5847891569137573,
+      "learning_rate": 3.5849056603773584e-05,
+      "loss": 0.8159269094467163,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 0.9124138355255127,
+      "eval_runtime": 832.6331,
+      "eval_samples_per_second": 2.474,
+      "eval_steps_per_second": 2.474,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 1.8158049583435059,
+      "learning_rate": 3.602875112309075e-05,
+      "loss": 0.8901475667953491,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 1.9448504447937012,
+      "learning_rate": 3.620844564240791e-05,
+      "loss": 0.8330907821655273,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 2.028280019760132,
+      "learning_rate": 3.638814016172507e-05,
+      "loss": 0.870513916015625,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 2.2005157470703125,
+      "learning_rate": 3.656783468104223e-05,
+      "loss": 0.8064979910850525,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 2.2756290435791016,
+      "learning_rate": 3.6747529200359395e-05,
+      "loss": 0.8457443714141846,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 2.0970261096954346,
+      "learning_rate": 3.6927223719676554e-05,
+      "loss": 0.7478897571563721,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 1.8917485475540161,
+      "learning_rate": 3.710691823899371e-05,
+      "loss": 0.863377034664154,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 2.0429933071136475,
+      "learning_rate": 3.728661275831088e-05,
+      "loss": 0.8654620051383972,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 2.005125045776367,
+      "learning_rate": 3.7466307277628035e-05,
+      "loss": 0.8295455574989319,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 2.3852169513702393,
+      "learning_rate": 3.764600179694519e-05,
+      "loss": 0.8728633522987366,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 1.8731592893600464,
+      "learning_rate": 3.782569631626235e-05,
+      "loss": 0.8217283487319946,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 2.2818236351013184,
+      "learning_rate": 3.8005390835579516e-05,
+      "loss": 0.8869860172271729,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 2.0646233558654785,
+      "learning_rate": 3.8185085354896675e-05,
+      "loss": 0.9732091426849365,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 1.9991949796676636,
+      "learning_rate": 3.836477987421384e-05,
+      "loss": 0.9012333154678345,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 2.209775447845459,
+      "learning_rate": 3.8544474393531e-05,
+      "loss": 0.867533802986145,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 2.1242146492004395,
+      "learning_rate": 3.8724168912848156e-05,
+      "loss": 0.8697446584701538,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 1.771337628364563,
+      "learning_rate": 3.890386343216532e-05,
+      "loss": 0.8712933659553528,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 2.133652925491333,
+      "learning_rate": 3.908355795148248e-05,
+      "loss": 0.8638070821762085,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 1.9354501962661743,
+      "learning_rate": 3.9263252470799644e-05,
+      "loss": 0.8255205750465393,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 1.9564658403396606,
+      "learning_rate": 3.94429469901168e-05,
+      "loss": 0.9652490019798279,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 1.9733822345733643,
+      "learning_rate": 3.962264150943397e-05,
+      "loss": 0.8960518836975098,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 2.1670451164245605,
+      "learning_rate": 3.9802336028751126e-05,
+      "loss": 0.9555241465568542,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 2.0059614181518555,
+      "learning_rate": 3.9982030548068284e-05,
+      "loss": 0.8238654732704163,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 1.9803026914596558,
+      "learning_rate": 4.016172506738545e-05,
+      "loss": 0.8701026439666748,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 1.8800172805786133,
+      "learning_rate": 4.034141958670261e-05,
+      "loss": 0.8927714228630066,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 1.8555818796157837,
+      "learning_rate": 4.052111410601977e-05,
+      "loss": 0.8635751008987427,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 2.5119166374206543,
+      "learning_rate": 4.070080862533693e-05,
+      "loss": 0.925403892993927,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 2.0825788974761963,
+      "learning_rate": 4.088050314465409e-05,
+      "loss": 0.8917028307914734,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 2.4413394927978516,
+      "learning_rate": 4.1060197663971254e-05,
+      "loss": 0.9097893834114075,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 2.503617286682129,
+      "learning_rate": 4.123989218328841e-05,
+      "loss": 0.8284633755683899,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 1.9360398054122925,
+      "learning_rate": 4.141958670260557e-05,
+      "loss": 0.8743083477020264,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 1.9228297472000122,
+      "learning_rate": 4.159928122192273e-05,
+      "loss": 0.837934136390686,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 2.3240439891815186,
+      "learning_rate": 4.1778975741239893e-05,
+      "loss": 0.831945538520813,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 1.879684329032898,
+      "learning_rate": 4.195867026055705e-05,
+      "loss": 0.8012097477912903,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 2.2995200157165527,
+      "learning_rate": 4.213836477987422e-05,
+      "loss": 0.8670937418937683,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 2.098020553588867,
+      "learning_rate": 4.2318059299191375e-05,
+      "loss": 0.88299161195755,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 2.0588274002075195,
+      "learning_rate": 4.249775381850854e-05,
+      "loss": 0.9045401811599731,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 1.8832436800003052,
+      "learning_rate": 4.26774483378257e-05,
+      "loss": 0.9787635803222656,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 2.3451809883117676,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.8874871730804443,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 1.8093878030776978,
+      "learning_rate": 4.303683737646002e-05,
+      "loss": 0.794157087802887,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 1.8396174907684326,
+      "learning_rate": 4.321653189577718e-05,
+      "loss": 0.792723536491394,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 2.3939783573150635,
+      "learning_rate": 4.3396226415094345e-05,
+      "loss": 0.9221814274787903,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 2.2652194499969482,
+      "learning_rate": 4.35759209344115e-05,
+      "loss": 0.8716039061546326,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 2.068258762359619,
+      "learning_rate": 4.375561545372867e-05,
+      "loss": 0.8517807126045227,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 2.264620542526245,
+      "learning_rate": 4.3935309973045826e-05,
+      "loss": 0.8699264526367188,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 2.0821611881256104,
+      "learning_rate": 4.4115004492362984e-05,
+      "loss": 0.8760254383087158,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 1.9486546516418457,
+      "learning_rate": 4.429469901168015e-05,
+      "loss": 0.8957411050796509,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 2.092957019805908,
+      "learning_rate": 4.447439353099731e-05,
+      "loss": 0.981200635433197,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 2.325758218765259,
+      "learning_rate": 4.4654088050314466e-05,
+      "loss": 0.8295405507087708,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 2.251295566558838,
+      "learning_rate": 4.4833782569631624e-05,
+      "loss": 0.8463165163993835,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 0.8945327997207642,
+      "eval_runtime": 822.9776,
+      "eval_samples_per_second": 2.503,
+      "eval_steps_per_second": 2.503,
+      "step": 500
+    },
+    {
+      "epoch": 0.21661272923408845,
+      "grad_norm": 1.8110703229904175,
+      "learning_rate": 4.501347708894879e-05,
+      "loss": 0.9099015593528748,
+      "step": 502
+    },
+    {
+      "epoch": 0.2174757281553398,
+      "grad_norm": 2.0977623462677,
+      "learning_rate": 4.519317160826595e-05,
+      "loss": 0.875080943107605,
+      "step": 504
+    },
+    {
+      "epoch": 0.21833872707659116,
+      "grad_norm": 1.8648077249526978,
+      "learning_rate": 4.537286612758311e-05,
+      "loss": 0.8511829376220703,
+      "step": 506
+    },
+    {
+      "epoch": 0.2192017259978425,
+      "grad_norm": 1.754744291305542,
+      "learning_rate": 4.555256064690027e-05,
+      "loss": 0.8408182859420776,
+      "step": 508
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 1.9869136810302734,
+      "learning_rate": 4.573225516621743e-05,
+      "loss": 0.8824991583824158,
+      "step": 510
+    },
+    {
+      "epoch": 0.2209277238403452,
+      "grad_norm": 2.4601082801818848,
+      "learning_rate": 4.5911949685534594e-05,
+      "loss": 0.9949447512626648,
+      "step": 512
+    },
+    {
+      "epoch": 0.22179072276159656,
+      "grad_norm": 2.1224238872528076,
+      "learning_rate": 4.609164420485175e-05,
+      "loss": 0.8979368805885315,
+      "step": 514
+    },
+    {
+      "epoch": 0.2226537216828479,
+      "grad_norm": 1.6812392473220825,
+      "learning_rate": 4.627133872416892e-05,
+      "loss": 0.8728249669075012,
+      "step": 516
+    },
+    {
+      "epoch": 0.22351672060409924,
+      "grad_norm": 1.6505497694015503,
+      "learning_rate": 4.6451033243486075e-05,
+      "loss": 0.8083430528640747,
+      "step": 518
+    },
+    {
+      "epoch": 0.2243797195253506,
+      "grad_norm": 1.6454377174377441,
+      "learning_rate": 4.663072776280324e-05,
+      "loss": 0.8042294383049011,
+      "step": 520
+    },
+    {
+      "epoch": 0.22524271844660193,
+      "grad_norm": 2.0974535942077637,
+      "learning_rate": 4.68104222821204e-05,
+      "loss": 0.9263730049133301,
+      "step": 522
+    },
+    {
+      "epoch": 0.2261057173678533,
+      "grad_norm": 1.90152108669281,
+      "learning_rate": 4.6990116801437556e-05,
+      "loss": 0.9090206623077393,
+      "step": 524
+    },
+    {
+      "epoch": 0.22696871628910464,
+      "grad_norm": 1.9843928813934326,
+      "learning_rate": 4.716981132075472e-05,
+      "loss": 0.8310918807983398,
+      "step": 526
+    },
+    {
+      "epoch": 0.227831715210356,
+      "grad_norm": 1.7880226373672485,
+      "learning_rate": 4.734950584007188e-05,
+      "loss": 0.8838925957679749,
+      "step": 528
+    },
+    {
+      "epoch": 0.22869471413160733,
+      "grad_norm": 1.8534979820251465,
+      "learning_rate": 4.7529200359389045e-05,
+      "loss": 0.9431065917015076,
+      "step": 530
+    },
+    {
+      "epoch": 0.2295577130528587,
+      "grad_norm": 1.8936293125152588,
+      "learning_rate": 4.77088948787062e-05,
+      "loss": 0.7988291382789612,
+      "step": 532
+    },
+    {
+      "epoch": 0.23042071197411004,
+      "grad_norm": 1.919683814048767,
+      "learning_rate": 4.788858939802337e-05,
+      "loss": 0.8477044105529785,
+      "step": 534
+    },
+    {
+      "epoch": 0.23128371089536137,
+      "grad_norm": 1.8022494316101074,
+      "learning_rate": 4.8068283917340526e-05,
+      "loss": 0.8482418060302734,
+      "step": 536
+    },
+    {
+      "epoch": 0.23214670981661273,
+      "grad_norm": 1.8628984689712524,
+      "learning_rate": 4.8247978436657684e-05,
+      "loss": 0.8553584814071655,
+      "step": 538
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 1.8644732236862183,
+      "learning_rate": 4.842767295597484e-05,
+      "loss": 0.8287713527679443,
+      "step": 540
+    },
+    {
+      "epoch": 0.23387270765911541,
+      "grad_norm": 2.162926435470581,
+      "learning_rate": 4.8607367475292e-05,
+      "loss": 0.8984123468399048,
+      "step": 542
+    },
+    {
+      "epoch": 0.23473570658036677,
+      "grad_norm": 1.453223466873169,
+      "learning_rate": 4.8787061994609166e-05,
+      "loss": 0.725272536277771,
+      "step": 544
+    },
+    {
+      "epoch": 0.23559870550161813,
+      "grad_norm": 2.2145543098449707,
+      "learning_rate": 4.8966756513926324e-05,
+      "loss": 0.9128344655036926,
+      "step": 546
+    },
+    {
+      "epoch": 0.23646170442286948,
+      "grad_norm": 1.7639187574386597,
+      "learning_rate": 4.914645103324349e-05,
+      "loss": 0.782098114490509,
+      "step": 548
+    },
+    {
+      "epoch": 0.2373247033441208,
+      "grad_norm": 1.6597305536270142,
+      "learning_rate": 4.932614555256065e-05,
+      "loss": 0.8212350010871887,
+      "step": 550
+    },
+    {
+      "epoch": 0.23818770226537217,
+      "grad_norm": 1.9441677331924438,
+      "learning_rate": 4.950584007187781e-05,
+      "loss": 0.9033122062683105,
+      "step": 552
+    },
+    {
+      "epoch": 0.23905070118662353,
+      "grad_norm": 2.0332281589508057,
+      "learning_rate": 4.968553459119497e-05,
+      "loss": 0.9195884466171265,
+      "step": 554
+    },
+    {
+      "epoch": 0.23991370010787486,
+      "grad_norm": 1.9222822189331055,
+      "learning_rate": 4.986522911051213e-05,
+      "loss": 0.8828456401824951,
+      "step": 556
+    },
+    {
+      "epoch": 0.2407766990291262,
+      "grad_norm": 1.9830708503723145,
+      "learning_rate": 5.004492362982929e-05,
+      "loss": 0.9089829921722412,
+      "step": 558
+    },
+    {
+      "epoch": 0.24163969795037757,
+      "grad_norm": 1.99044930934906,
+      "learning_rate": 5.022461814914645e-05,
+      "loss": 0.8747812509536743,
+      "step": 560
+    },
+    {
+      "epoch": 0.2425026968716289,
+      "grad_norm": 1.7961562871932983,
+      "learning_rate": 5.040431266846362e-05,
+      "loss": 0.8421230912208557,
+      "step": 562
+    },
+    {
+      "epoch": 0.24336569579288025,
+      "grad_norm": 1.9798882007598877,
+      "learning_rate": 5.058400718778078e-05,
+      "loss": 0.8669922351837158,
+      "step": 564
+    },
+    {
+      "epoch": 0.2442286947141316,
+      "grad_norm": 2.0138750076293945,
+      "learning_rate": 5.076370170709793e-05,
+      "loss": 0.8596820831298828,
+      "step": 566
+    },
+    {
+      "epoch": 0.24509169363538297,
+      "grad_norm": 2.069021701812744,
+      "learning_rate": 5.09433962264151e-05,
+      "loss": 0.8288601636886597,
+      "step": 568
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 2.6913585662841797,
+      "learning_rate": 5.112309074573226e-05,
+      "loss": 0.8321394324302673,
+      "step": 570
+    },
+    {
+      "epoch": 0.24681769147788565,
+      "grad_norm": 1.8057955503463745,
+      "learning_rate": 5.1302785265049415e-05,
+      "loss": 0.842660129070282,
+      "step": 572
+    },
+    {
+      "epoch": 0.247680690399137,
+      "grad_norm": 1.5741548538208008,
+      "learning_rate": 5.148247978436658e-05,
+      "loss": 0.8431437015533447,
+      "step": 574
+    },
+    {
+      "epoch": 0.24854368932038834,
+      "grad_norm": 2.0329413414001465,
+      "learning_rate": 5.166217430368374e-05,
+      "loss": 0.9046191573143005,
+      "step": 576
+    },
+    {
+      "epoch": 0.2494066882416397,
+      "grad_norm": 1.7638250589370728,
+      "learning_rate": 5.18418688230009e-05,
+      "loss": 0.8108726739883423,
+      "step": 578
+    },
+    {
+      "epoch": 0.25026968716289105,
+      "grad_norm": 2.1088576316833496,
+      "learning_rate": 5.202156334231806e-05,
+      "loss": 0.8621282577514648,
+      "step": 580
+    },
+    {
+      "epoch": 0.2511326860841424,
+      "grad_norm": 2.072145462036133,
+      "learning_rate": 5.220125786163522e-05,
+      "loss": 0.8774182200431824,
+      "step": 582
+    },
+    {
+      "epoch": 0.25199568500539377,
+      "grad_norm": 1.8093693256378174,
+      "learning_rate": 5.2380952380952384e-05,
+      "loss": 0.863322377204895,
+      "step": 584
+    },
+    {
+      "epoch": 0.25285868392664507,
+      "grad_norm": 1.7119505405426025,
+      "learning_rate": 5.2560646900269536e-05,
+      "loss": 0.8493514657020569,
+      "step": 586
+    },
+    {
+      "epoch": 0.2537216828478964,
+      "grad_norm": 2.042052745819092,
+      "learning_rate": 5.27403414195867e-05,
+      "loss": 0.8278731107711792,
+      "step": 588
+    },
+    {
+      "epoch": 0.2545846817691478,
+      "grad_norm": 1.9019906520843506,
+      "learning_rate": 5.2920035938903866e-05,
+      "loss": 0.8388869166374207,
+      "step": 590
+    },
+    {
+      "epoch": 0.25544768069039914,
+      "grad_norm": 1.8072630167007446,
+      "learning_rate": 5.309973045822103e-05,
+      "loss": 0.8666917085647583,
+      "step": 592
+    },
+    {
+      "epoch": 0.2563106796116505,
+      "grad_norm": 1.7099417448043823,
+      "learning_rate": 5.327942497753818e-05,
+      "loss": 0.8114299774169922,
+      "step": 594
+    },
+    {
+      "epoch": 0.25717367853290185,
+      "grad_norm": 1.8132266998291016,
+      "learning_rate": 5.345911949685535e-05,
+      "loss": 0.8842664361000061,
+      "step": 596
+    },
+    {
+      "epoch": 0.2580366774541532,
+      "grad_norm": 1.9578651189804077,
+      "learning_rate": 5.363881401617251e-05,
+      "loss": 0.7954385876655579,
+      "step": 598
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 1.832077145576477,
+      "learning_rate": 5.381850853548968e-05,
+      "loss": 0.912541925907135,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "eval_loss": 0.8770867586135864,
+      "eval_runtime": 827.8893,
+      "eval_samples_per_second": 2.488,
+      "eval_steps_per_second": 2.488,
+      "step": 600
+    },
+    {
+      "epoch": 0.25976267529665586,
+      "grad_norm": 1.7565301656723022,
+      "learning_rate": 5.399820305480683e-05,
+      "loss": 0.8436558246612549,
+      "step": 602
+    },
+    {
+      "epoch": 0.2606256742179072,
+      "grad_norm": 1.9199552536010742,
+      "learning_rate": 5.4177897574123994e-05,
+      "loss": 0.9384433031082153,
+      "step": 604
+    },
+    {
+      "epoch": 0.2614886731391586,
+      "grad_norm": 1.7609341144561768,
+      "learning_rate": 5.435759209344116e-05,
+      "loss": 0.8695753812789917,
+      "step": 606
+    },
+    {
+      "epoch": 0.26235167206040994,
+      "grad_norm": 1.771958589553833,
+      "learning_rate": 5.453728661275831e-05,
+      "loss": 0.8462895154953003,
+      "step": 608
+    },
+    {
+      "epoch": 0.2632146709816613,
+      "grad_norm": 1.8958079814910889,
+      "learning_rate": 5.4716981132075475e-05,
+      "loss": 0.9074611663818359,
+      "step": 610
+    },
+    {
+      "epoch": 0.26407766990291265,
+      "grad_norm": 1.8668403625488281,
+      "learning_rate": 5.489667565139264e-05,
+      "loss": 0.8603307008743286,
+      "step": 612
+    },
+    {
+      "epoch": 0.26494066882416395,
+      "grad_norm": 1.8902733325958252,
+      "learning_rate": 5.50763701707098e-05,
+      "loss": 0.8925216794013977,
+      "step": 614
+    },
+    {
+      "epoch": 0.2658036677454153,
+      "grad_norm": 1.7172386646270752,
+      "learning_rate": 5.525606469002696e-05,
+      "loss": 0.7872517704963684,
+      "step": 616
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.7814518213272095,
+      "learning_rate": 5.5435759209344115e-05,
+      "loss": 0.7951212525367737,
+      "step": 618
+    },
+    {
+      "epoch": 0.267529665587918,
+      "grad_norm": 1.8714463710784912,
+      "learning_rate": 5.561545372866128e-05,
+      "loss": 0.859940230846405,
+      "step": 620
+    },
+    {
+      "epoch": 0.2683926645091694,
+      "grad_norm": 1.9614174365997314,
+      "learning_rate": 5.579514824797844e-05,
+      "loss": 0.8953307867050171,
+      "step": 622
+    },
+    {
+      "epoch": 0.26925566343042073,
+      "grad_norm": 1.7190991640090942,
+      "learning_rate": 5.5974842767295596e-05,
+      "loss": 0.8346402645111084,
+      "step": 624
+    },
+    {
+      "epoch": 0.27011866235167203,
+      "grad_norm": 1.981070876121521,
+      "learning_rate": 5.615453728661276e-05,
+      "loss": 0.8545536398887634,
+      "step": 626
+    },
+    {
+      "epoch": 0.2709816612729234,
+      "grad_norm": 1.9186289310455322,
+      "learning_rate": 5.6334231805929926e-05,
+      "loss": 0.9064128398895264,
+      "step": 628
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 1.9937374591827393,
+      "learning_rate": 5.651392632524708e-05,
+      "loss": 0.883073627948761,
+      "step": 630
+    },
+    {
+      "epoch": 0.2727076591154261,
+      "grad_norm": 1.800236701965332,
+      "learning_rate": 5.669362084456424e-05,
+      "loss": 0.8777942657470703,
+      "step": 632
+    },
+    {
+      "epoch": 0.27357065803667746,
+      "grad_norm": 1.9164050817489624,
+      "learning_rate": 5.687331536388141e-05,
+      "loss": 0.8527862429618835,
+      "step": 634
+    },
+    {
+      "epoch": 0.2744336569579288,
+      "grad_norm": 1.7494043111801147,
+      "learning_rate": 5.705300988319856e-05,
+      "loss": 0.881090521812439,
+      "step": 636
+    },
+    {
+      "epoch": 0.2752966558791802,
+      "grad_norm": 1.9433623552322388,
+      "learning_rate": 5.7232704402515724e-05,
+      "loss": 0.8547250628471375,
+      "step": 638
+    },
+    {
+      "epoch": 0.2761596548004315,
+      "grad_norm": 1.7539145946502686,
+      "learning_rate": 5.741239892183289e-05,
+      "loss": 0.8429408073425293,
+      "step": 640
+    },
+    {
+      "epoch": 0.27702265372168283,
+      "grad_norm": 1.904911756515503,
+      "learning_rate": 5.7592093441150054e-05,
+      "loss": 0.8587079644203186,
+      "step": 642
+    },
+    {
+      "epoch": 0.2778856526429342,
+      "grad_norm": 1.5534838438034058,
+      "learning_rate": 5.7771787960467206e-05,
+      "loss": 0.7795872688293457,
+      "step": 644
+    },
+    {
+      "epoch": 0.27874865156418555,
+      "grad_norm": 1.704798698425293,
+      "learning_rate": 5.795148247978437e-05,
+      "loss": 0.7657744884490967,
+      "step": 646
+    },
+    {
+      "epoch": 0.2796116504854369,
+      "grad_norm": 1.8432048559188843,
+      "learning_rate": 5.8131176999101536e-05,
+      "loss": 0.8119702935218811,
+      "step": 648
+    },
+    {
+      "epoch": 0.28047464940668826,
+      "grad_norm": 1.9495919942855835,
+      "learning_rate": 5.831087151841869e-05,
+      "loss": 0.8846080899238586,
+      "step": 650
+    },
+    {
+      "epoch": 0.2813376483279396,
+      "grad_norm": 1.9626739025115967,
+      "learning_rate": 5.849056603773585e-05,
+      "loss": 0.854324460029602,
+      "step": 652
+    },
+    {
+      "epoch": 0.2822006472491909,
+      "grad_norm": 1.767221212387085,
+      "learning_rate": 5.867026055705302e-05,
+      "loss": 0.7908785939216614,
+      "step": 654
+    },
+    {
+      "epoch": 0.2830636461704423,
+      "grad_norm": 1.8866491317749023,
+      "learning_rate": 5.8849955076370175e-05,
+      "loss": 0.8155530691146851,
+      "step": 656
+    },
+    {
+      "epoch": 0.28392664509169363,
+      "grad_norm": 1.9543417692184448,
+      "learning_rate": 5.9029649595687334e-05,
+      "loss": 0.9833307266235352,
+      "step": 658
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 1.867039680480957,
+      "learning_rate": 5.920934411500449e-05,
+      "loss": 0.7991418242454529,
+      "step": 660
+    },
+    {
+      "epoch": 0.28565264293419634,
+      "grad_norm": 1.8487379550933838,
+      "learning_rate": 5.938903863432166e-05,
+      "loss": 0.8232532143592834,
+      "step": 662
+    },
+    {
+      "epoch": 0.2865156418554477,
+      "grad_norm": 1.5015742778778076,
+      "learning_rate": 5.956873315363881e-05,
+      "loss": 0.76528000831604,
+      "step": 664
+    },
+    {
+      "epoch": 0.287378640776699,
+      "grad_norm": 2.726778268814087,
+      "learning_rate": 5.974842767295597e-05,
+      "loss": 0.8220192790031433,
+      "step": 666
+    },
+    {
+      "epoch": 0.28824163969795036,
+      "grad_norm": 1.6754003763198853,
+      "learning_rate": 5.992812219227314e-05,
+      "loss": 0.7534968256950378,
+      "step": 668
+    },
+    {
+      "epoch": 0.2891046386192017,
+      "grad_norm": 1.9948434829711914,
+      "learning_rate": 6.01078167115903e-05,
+      "loss": 0.8405768871307373,
+      "step": 670
+    },
+    {
+      "epoch": 0.28996763754045307,
+      "grad_norm": 1.7982401847839355,
+      "learning_rate": 6.0287511230907455e-05,
+      "loss": 0.8143276572227478,
+      "step": 672
+    },
+    {
+      "epoch": 0.29083063646170443,
+      "grad_norm": 1.7311779260635376,
+      "learning_rate": 6.046720575022462e-05,
+      "loss": 0.9602267742156982,
+      "step": 674
+    },
+    {
+      "epoch": 0.2916936353829558,
+      "grad_norm": 1.9906021356582642,
+      "learning_rate": 6.0646900269541785e-05,
+      "loss": 0.8628544807434082,
+      "step": 676
+    },
+    {
+      "epoch": 0.29255663430420714,
+      "grad_norm": 1.7477494478225708,
+      "learning_rate": 6.082659478885895e-05,
+      "loss": 0.7800343632698059,
+      "step": 678
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "grad_norm": 1.7978737354278564,
+      "learning_rate": 6.10062893081761e-05,
+      "loss": 0.8722298741340637,
+      "step": 680
+    },
+    {
+      "epoch": 0.2942826321467098,
+      "grad_norm": 2.1463348865509033,
+      "learning_rate": 6.118598382749326e-05,
+      "loss": 0.8895675539970398,
+      "step": 682
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 1.9256783723831177,
+      "learning_rate": 6.136567834681042e-05,
+      "loss": 0.8579491972923279,
+      "step": 684
+    },
+    {
+      "epoch": 0.2960086299892125,
+      "grad_norm": 1.4459543228149414,
+      "learning_rate": 6.154537286612758e-05,
+      "loss": 0.7811232805252075,
+      "step": 686
+    },
+    {
+      "epoch": 0.29687162891046387,
+      "grad_norm": 1.6202397346496582,
+      "learning_rate": 6.172506738544474e-05,
+      "loss": 0.7827678322792053,
+      "step": 688
+    },
+    {
+      "epoch": 0.2977346278317152,
+      "grad_norm": 2.0524775981903076,
+      "learning_rate": 6.19047619047619e-05,
+      "loss": 0.8186459541320801,
+      "step": 690
+    },
+    {
+      "epoch": 0.2985976267529666,
+      "grad_norm": 1.7867428064346313,
+      "learning_rate": 6.208445642407907e-05,
+      "loss": 0.8691027760505676,
+      "step": 692
+    },
+    {
+      "epoch": 0.2994606256742179,
+      "grad_norm": 1.9605737924575806,
+      "learning_rate": 6.226415094339622e-05,
+      "loss": 0.8233416080474854,
+      "step": 694
+    },
+    {
+      "epoch": 0.30032362459546924,
+      "grad_norm": 1.7035984992980957,
+      "learning_rate": 6.244384546271339e-05,
+      "loss": 0.8493421077728271,
+      "step": 696
+    },
+    {
+      "epoch": 0.3011866235167206,
+      "grad_norm": 1.9402128458023071,
+      "learning_rate": 6.262353998203055e-05,
+      "loss": 0.8114250302314758,
+      "step": 698
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "grad_norm": 1.8533520698547363,
+      "learning_rate": 6.28032345013477e-05,
+      "loss": 0.8996106386184692,
+      "step": 700
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "eval_loss": 0.8631294369697571,
+      "eval_runtime": 839.6269,
+      "eval_samples_per_second": 2.453,
+      "eval_steps_per_second": 2.453,
+      "step": 700
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 1.727793574333191,
+      "learning_rate": 6.298292902066487e-05,
+      "loss": 0.7978370189666748,
+      "step": 702
+    },
+    {
+      "epoch": 0.30377562028047467,
+      "grad_norm": 1.9601492881774902,
+      "learning_rate": 6.316262353998203e-05,
+      "loss": 0.8120381236076355,
+      "step": 704
+    },
+    {
+      "epoch": 0.304638619201726,
+      "grad_norm": 1.8380948305130005,
+      "learning_rate": 6.33423180592992e-05,
+      "loss": 0.8005605340003967,
+      "step": 706
+    },
+    {
+      "epoch": 0.3055016181229773,
+      "grad_norm": 1.8210986852645874,
+      "learning_rate": 6.352201257861635e-05,
+      "loss": 0.8967245817184448,
+      "step": 708
+    },
+    {
+      "epoch": 0.3063646170442287,
+      "grad_norm": 3.5359878540039062,
+      "learning_rate": 6.370170709793352e-05,
+      "loss": 0.8271524906158447,
+      "step": 710
+    },
+    {
+      "epoch": 0.30722761596548004,
+      "grad_norm": 1.7943733930587769,
+      "learning_rate": 6.388140161725068e-05,
+      "loss": 0.8759040236473083,
+      "step": 712
+    },
+    {
+      "epoch": 0.3080906148867314,
+      "grad_norm": 1.5483570098876953,
+      "learning_rate": 6.406109613656783e-05,
+      "loss": 0.7872476577758789,
+      "step": 714
+    },
+    {
+      "epoch": 0.30895361380798275,
+      "grad_norm": 1.8044816255569458,
+      "learning_rate": 6.4240790655885e-05,
+      "loss": 0.849986732006073,
+      "step": 716
+    },
+    {
+      "epoch": 0.3098166127292341,
+      "grad_norm": 1.548281192779541,
+      "learning_rate": 6.442048517520216e-05,
+      "loss": 0.8292878866195679,
+      "step": 718
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 1.643020749092102,
+      "learning_rate": 6.460017969451933e-05,
+      "loss": 0.8796502351760864,
+      "step": 720
+    },
+    {
+      "epoch": 0.31154261057173677,
+      "grad_norm": 1.633881688117981,
+      "learning_rate": 6.477987421383648e-05,
+      "loss": 0.806233286857605,
+      "step": 722
+    },
+    {
+      "epoch": 0.3124056094929881,
+      "grad_norm": 1.7712864875793457,
+      "learning_rate": 6.495956873315364e-05,
+      "loss": 0.802722156047821,
+      "step": 724
+    },
+    {
+      "epoch": 0.3132686084142395,
+      "grad_norm": 1.9158337116241455,
+      "learning_rate": 6.513926325247081e-05,
+      "loss": 0.8735752105712891,
+      "step": 726
+    },
+    {
+      "epoch": 0.31413160733549084,
+      "grad_norm": 1.8648416996002197,
+      "learning_rate": 6.531895777178796e-05,
+      "loss": 0.793403148651123,
+      "step": 728
+    },
+    {
+      "epoch": 0.3149946062567422,
+      "grad_norm": 1.5917021036148071,
+      "learning_rate": 6.549865229110512e-05,
+      "loss": 0.7772542834281921,
+      "step": 730
+    },
+    {
+      "epoch": 0.31585760517799355,
+      "grad_norm": 1.8560330867767334,
+      "learning_rate": 6.567834681042229e-05,
+      "loss": 0.8731698989868164,
+      "step": 732
+    },
+    {
+      "epoch": 0.31672060409924485,
+      "grad_norm": 1.6038225889205933,
+      "learning_rate": 6.585804132973945e-05,
+      "loss": 0.8167505264282227,
+      "step": 734
+    },
+    {
+      "epoch": 0.3175836030204962,
+      "grad_norm": 1.6221873760223389,
+      "learning_rate": 6.60377358490566e-05,
+      "loss": 0.7810112237930298,
+      "step": 736
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 1.8528746366500854,
+      "learning_rate": 6.621743036837377e-05,
+      "loss": 0.8735228776931763,
+      "step": 738
+    },
+    {
+      "epoch": 0.3193096008629989,
+      "grad_norm": 1.473233938217163,
+      "learning_rate": 6.639712488769094e-05,
+      "loss": 0.8231552243232727,
+      "step": 740
+    },
+    {
+      "epoch": 0.3201725997842503,
+      "grad_norm": 1.7726222276687622,
+      "learning_rate": 6.657681940700809e-05,
+      "loss": 0.8400886058807373,
+      "step": 742
+    },
+    {
+      "epoch": 0.32103559870550163,
+      "grad_norm": 1.7245025634765625,
+      "learning_rate": 6.675651392632525e-05,
+      "loss": 0.7371112108230591,
+      "step": 744
+    },
+    {
+      "epoch": 0.321898597626753,
+      "grad_norm": 1.6225395202636719,
+      "learning_rate": 6.693620844564242e-05,
+      "loss": 0.8057155013084412,
+      "step": 746
+    },
+    {
+      "epoch": 0.3227615965480043,
+      "grad_norm": 1.607007384300232,
+      "learning_rate": 6.711590296495958e-05,
+      "loss": 0.8471131324768066,
+      "step": 748
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 1.760038137435913,
+      "learning_rate": 6.729559748427673e-05,
+      "loss": 0.8251315951347351,
+      "step": 750
+    },
+    {
+      "epoch": 0.324487594390507,
+      "grad_norm": 1.8012818098068237,
+      "learning_rate": 6.74752920035939e-05,
+      "loss": 0.8215667605400085,
+      "step": 752
+    },
+    {
+      "epoch": 0.32535059331175836,
+      "grad_norm": 1.769614815711975,
+      "learning_rate": 6.765498652291105e-05,
+      "loss": 0.8113123178482056,
+      "step": 754
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 1.7554916143417358,
+      "learning_rate": 6.783468104222822e-05,
+      "loss": 0.8893613219261169,
+      "step": 756
+    },
+    {
+      "epoch": 0.3270765911542611,
+      "grad_norm": 1.5720254182815552,
+      "learning_rate": 6.801437556154538e-05,
+      "loss": 0.8165010809898376,
+      "step": 758
+    },
+    {
+      "epoch": 0.32793959007551243,
+      "grad_norm": 2.1887543201446533,
+      "learning_rate": 6.819407008086253e-05,
+      "loss": 0.8800036311149597,
+      "step": 760
+    },
+    {
+      "epoch": 0.32880258899676373,
+      "grad_norm": 1.63350510597229,
+      "learning_rate": 6.83737646001797e-05,
+      "loss": 0.7268908619880676,
+      "step": 762
+    },
+    {
+      "epoch": 0.3296655879180151,
+      "grad_norm": 1.5838189125061035,
+      "learning_rate": 6.855345911949685e-05,
+      "loss": 0.7695913910865784,
+      "step": 764
+    },
+    {
+      "epoch": 0.33052858683926645,
+      "grad_norm": 1.8752859830856323,
+      "learning_rate": 6.873315363881401e-05,
+      "loss": 0.9005667567253113,
+      "step": 766
+    },
+    {
+      "epoch": 0.3313915857605178,
+      "grad_norm": 1.4201446771621704,
+      "learning_rate": 6.891284815813118e-05,
+      "loss": 0.7960113883018494,
+      "step": 768
+    },
+    {
+      "epoch": 0.33225458468176916,
+      "grad_norm": 1.6665233373641968,
+      "learning_rate": 6.909254267744834e-05,
+      "loss": 0.851472020149231,
+      "step": 770
+    },
+    {
+      "epoch": 0.3331175836030205,
+      "grad_norm": 1.72721266746521,
+      "learning_rate": 6.92722371967655e-05,
+      "loss": 0.8403398990631104,
+      "step": 772
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 1.648680567741394,
+      "learning_rate": 6.945193171608266e-05,
+      "loss": 0.7582393884658813,
+      "step": 774
+    },
+    {
+      "epoch": 0.3348435814455232,
+      "grad_norm": 1.89604651927948,
+      "learning_rate": 6.963162623539982e-05,
+      "loss": 0.8250385522842407,
+      "step": 776
+    },
+    {
+      "epoch": 0.33570658036677453,
+      "grad_norm": 1.4748259782791138,
+      "learning_rate": 6.981132075471698e-05,
+      "loss": 0.7916358709335327,
+      "step": 778
+    },
+    {
+      "epoch": 0.3365695792880259,
+      "grad_norm": 1.4885735511779785,
+      "learning_rate": 6.999101527403414e-05,
+      "loss": 0.7432135939598083,
+      "step": 780
+    },
+    {
+      "epoch": 0.33743257820927725,
+      "grad_norm": 1.5150227546691895,
+      "learning_rate": 7.01707097933513e-05,
+      "loss": 0.7369741201400757,
+      "step": 782
+    },
+    {
+      "epoch": 0.3382955771305286,
+      "grad_norm": 2.0702431201934814,
+      "learning_rate": 7.035040431266847e-05,
+      "loss": 0.8347548246383667,
+      "step": 784
+    },
+    {
+      "epoch": 0.33915857605177996,
+      "grad_norm": 1.8330671787261963,
+      "learning_rate": 7.053009883198562e-05,
+      "loss": 0.7757654190063477,
+      "step": 786
+    },
+    {
+      "epoch": 0.34002157497303126,
+      "grad_norm": 1.6809033155441284,
+      "learning_rate": 7.070979335130279e-05,
+      "loss": 0.7966224551200867,
+      "step": 788
+    },
+    {
+      "epoch": 0.3408845738942826,
+      "grad_norm": 1.5811399221420288,
+      "learning_rate": 7.088948787061995e-05,
+      "loss": 0.7977543473243713,
+      "step": 790
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 1.6572248935699463,
+      "learning_rate": 7.10691823899371e-05,
+      "loss": 0.7842527627944946,
+      "step": 792
+    },
+    {
+      "epoch": 0.34261057173678533,
+      "grad_norm": 1.6138155460357666,
+      "learning_rate": 7.124887690925427e-05,
+      "loss": 0.7586495876312256,
+      "step": 794
+    },
+    {
+      "epoch": 0.3434735706580367,
+      "grad_norm": 1.9198144674301147,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.9010837078094482,
+      "step": 796
+    },
+    {
+      "epoch": 0.34433656957928804,
+      "grad_norm": 1.6212328672409058,
+      "learning_rate": 7.16082659478886e-05,
+      "loss": 0.7857459783554077,
+      "step": 798
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "grad_norm": 2.1088991165161133,
+      "learning_rate": 7.178796046720575e-05,
+      "loss": 0.9087778925895691,
+      "step": 800
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "eval_loss": 0.8476243615150452,
+      "eval_runtime": 831.6735,
+      "eval_samples_per_second": 2.477,
+      "eval_steps_per_second": 2.477,
+      "step": 800
+    },
+    {
+      "epoch": 0.3460625674217907,
+      "grad_norm": 1.6325052976608276,
+      "learning_rate": 7.196765498652292e-05,
+      "loss": 0.7561838626861572,
+      "step": 802
+    },
+    {
+      "epoch": 0.34692556634304206,
+      "grad_norm": 1.8044698238372803,
+      "learning_rate": 7.214734950584008e-05,
+      "loss": 0.7940152883529663,
+      "step": 804
+    },
+    {
+      "epoch": 0.3477885652642934,
+      "grad_norm": 1.4942690134048462,
+      "learning_rate": 7.232704402515723e-05,
+      "loss": 0.8002730011940002,
+      "step": 806
+    },
+    {
+      "epoch": 0.34865156418554477,
+      "grad_norm": 1.5209156274795532,
+      "learning_rate": 7.25067385444744e-05,
+      "loss": 0.8211291432380676,
+      "step": 808
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 1.662622094154358,
+      "learning_rate": 7.268643306379156e-05,
+      "loss": 0.8690080642700195,
+      "step": 810
+    },
+    {
+      "epoch": 0.3503775620280475,
+      "grad_norm": 1.4452823400497437,
+      "learning_rate": 7.286612758310873e-05,
+      "loss": 0.8259872794151306,
+      "step": 812
+    },
+    {
+      "epoch": 0.3512405609492988,
+      "grad_norm": 1.6030809879302979,
+      "learning_rate": 7.304582210242588e-05,
+      "loss": 0.7973082661628723,
+      "step": 814
+    },
+    {
+      "epoch": 0.35210355987055014,
+      "grad_norm": 1.5944641828536987,
+      "learning_rate": 7.322551662174304e-05,
+      "loss": 0.8258423805236816,
+      "step": 816
+    },
+    {
+      "epoch": 0.3529665587918015,
+      "grad_norm": 1.6284228563308716,
+      "learning_rate": 7.340521114106021e-05,
+      "loss": 0.8570499420166016,
+      "step": 818
+    },
+    {
+      "epoch": 0.35382955771305286,
+      "grad_norm": 1.399397373199463,
+      "learning_rate": 7.358490566037736e-05,
+      "loss": 0.7808573842048645,
+      "step": 820
+    },
+    {
+      "epoch": 0.3546925566343042,
+      "grad_norm": 1.6233313083648682,
+      "learning_rate": 7.376460017969452e-05,
+      "loss": 0.7514002323150635,
+      "step": 822
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 3.1610822677612305,
+      "learning_rate": 7.394429469901169e-05,
+      "loss": 0.8392049670219421,
+      "step": 824
+    },
+    {
+      "epoch": 0.3564185544768069,
+      "grad_norm": 1.5170103311538696,
+      "learning_rate": 7.412398921832885e-05,
+      "loss": 0.7574125528335571,
+      "step": 826
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 1.687654733657837,
+      "learning_rate": 7.4303683737646e-05,
+      "loss": 0.8394677639007568,
+      "step": 828
+    },
+    {
+      "epoch": 0.3581445523193096,
+      "grad_norm": 1.6306912899017334,
+      "learning_rate": 7.448337825696317e-05,
+      "loss": 0.7760812044143677,
+      "step": 830
+    },
+    {
+      "epoch": 0.35900755124056094,
+      "grad_norm": 1.4824501276016235,
+      "learning_rate": 7.466307277628034e-05,
+      "loss": 0.8146010041236877,
+      "step": 832
+    },
+    {
+      "epoch": 0.3598705501618123,
+      "grad_norm": 1.962728500366211,
+      "learning_rate": 7.484276729559749e-05,
+      "loss": 0.7824002504348755,
+      "step": 834
+    },
+    {
+      "epoch": 0.36073354908306365,
+      "grad_norm": 1.805561900138855,
+      "learning_rate": 7.502246181491465e-05,
+      "loss": 0.8955144882202148,
+      "step": 836
+    },
+    {
+      "epoch": 0.361596548004315,
+      "grad_norm": 1.6058090925216675,
+      "learning_rate": 7.52021563342318e-05,
+      "loss": 0.7638000249862671,
+      "step": 838
+    },
+    {
+      "epoch": 0.36245954692556637,
+      "grad_norm": 1.5326330661773682,
+      "learning_rate": 7.538185085354897e-05,
+      "loss": 0.8465489745140076,
+      "step": 840
+    },
+    {
+      "epoch": 0.36332254584681767,
+      "grad_norm": 1.563953161239624,
+      "learning_rate": 7.556154537286612e-05,
+      "loss": 0.7809846997261047,
+      "step": 842
+    },
+    {
+      "epoch": 0.364185544768069,
+      "grad_norm": 1.3842798471450806,
+      "learning_rate": 7.574123989218329e-05,
+      "loss": 0.7431546449661255,
+      "step": 844
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 1.843582272529602,
+      "learning_rate": 7.592093441150045e-05,
+      "loss": 0.8984674215316772,
+      "step": 846
+    },
+    {
+      "epoch": 0.36591154261057174,
+      "grad_norm": 1.7077877521514893,
+      "learning_rate": 7.610062893081762e-05,
+      "loss": 0.7809584736824036,
+      "step": 848
+    },
+    {
+      "epoch": 0.3667745415318231,
+      "grad_norm": 1.3528809547424316,
+      "learning_rate": 7.628032345013477e-05,
+      "loss": 0.7576664090156555,
+      "step": 850
+    },
+    {
+      "epoch": 0.36763754045307445,
+      "grad_norm": 1.4391332864761353,
+      "learning_rate": 7.646001796945193e-05,
+      "loss": 0.7666721940040588,
+      "step": 852
+    },
+    {
+      "epoch": 0.3685005393743258,
+      "grad_norm": 1.626839518547058,
+      "learning_rate": 7.66397124887691e-05,
+      "loss": 0.8356342911720276,
+      "step": 854
+    },
+    {
+      "epoch": 0.3693635382955771,
+      "grad_norm": 1.5550813674926758,
+      "learning_rate": 7.681940700808625e-05,
+      "loss": 0.7766274809837341,
+      "step": 856
+    },
+    {
+      "epoch": 0.37022653721682847,
+      "grad_norm": 1.4684302806854248,
+      "learning_rate": 7.699910152740341e-05,
+      "loss": 0.7646660804748535,
+      "step": 858
+    },
+    {
+      "epoch": 0.3710895361380798,
+      "grad_norm": 1.6446272134780884,
+      "learning_rate": 7.717879604672058e-05,
+      "loss": 0.8716844916343689,
+      "step": 860
+    },
+    {
+      "epoch": 0.3719525350593312,
+      "grad_norm": 1.5995690822601318,
+      "learning_rate": 7.735849056603774e-05,
+      "loss": 0.8561879992485046,
+      "step": 862
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 1.632079839706421,
+      "learning_rate": 7.75381850853549e-05,
+      "loss": 0.8795325756072998,
+      "step": 864
+    },
+    {
+      "epoch": 0.3736785329018339,
+      "grad_norm": 1.7169907093048096,
+      "learning_rate": 7.771787960467206e-05,
+      "loss": 0.8779821991920471,
+      "step": 866
+    },
+    {
+      "epoch": 0.3745415318230852,
+      "grad_norm": 1.8590933084487915,
+      "learning_rate": 7.789757412398922e-05,
+      "loss": 0.8811644911766052,
+      "step": 868
+    },
+    {
+      "epoch": 0.37540453074433655,
+      "grad_norm": 1.804978370666504,
+      "learning_rate": 7.807726864330638e-05,
+      "loss": 0.8391726016998291,
+      "step": 870
+    },
+    {
+      "epoch": 0.3762675296655879,
+      "grad_norm": 2.2929575443267822,
+      "learning_rate": 7.825696316262354e-05,
+      "loss": 0.8425854444503784,
+      "step": 872
+    },
+    {
+      "epoch": 0.37713052858683926,
+      "grad_norm": 1.551804780960083,
+      "learning_rate": 7.84366576819407e-05,
+      "loss": 0.8409838080406189,
+      "step": 874
+    },
+    {
+      "epoch": 0.3779935275080906,
+      "grad_norm": 1.4655314683914185,
+      "learning_rate": 7.861635220125787e-05,
+      "loss": 0.7441553473472595,
+      "step": 876
+    },
+    {
+      "epoch": 0.378856526429342,
+      "grad_norm": 1.7886772155761719,
+      "learning_rate": 7.879604672057502e-05,
+      "loss": 0.8850297331809998,
+      "step": 878
+    },
+    {
+      "epoch": 0.37971952535059333,
+      "grad_norm": 1.4744676351547241,
+      "learning_rate": 7.897574123989219e-05,
+      "loss": 0.7991185188293457,
+      "step": 880
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 1.6844931840896606,
+      "learning_rate": 7.915543575920935e-05,
+      "loss": 0.7903867363929749,
+      "step": 882
+    },
+    {
+      "epoch": 0.381445523193096,
+      "grad_norm": 1.674704909324646,
+      "learning_rate": 7.93351302785265e-05,
+      "loss": 0.812190592288971,
+      "step": 884
+    },
+    {
+      "epoch": 0.38230852211434735,
+      "grad_norm": 1.6548097133636475,
+      "learning_rate": 7.951482479784367e-05,
+      "loss": 0.781878650188446,
+      "step": 886
+    },
+    {
+      "epoch": 0.3831715210355987,
+      "grad_norm": 1.3750375509262085,
+      "learning_rate": 7.969451931716083e-05,
+      "loss": 0.8223106861114502,
+      "step": 888
+    },
+    {
+      "epoch": 0.38403451995685006,
+      "grad_norm": 1.42178475856781,
+      "learning_rate": 7.9874213836478e-05,
+      "loss": 0.7170665860176086,
+      "step": 890
+    },
+    {
+      "epoch": 0.3848975188781014,
+      "grad_norm": 1.7126129865646362,
+      "learning_rate": 8.005390835579515e-05,
+      "loss": 0.8533666133880615,
+      "step": 892
+    },
+    {
+      "epoch": 0.3857605177993528,
+      "grad_norm": 1.552474856376648,
+      "learning_rate": 8.023360287511232e-05,
+      "loss": 0.8799889087677002,
+      "step": 894
+    },
+    {
+      "epoch": 0.3866235167206041,
+      "grad_norm": 1.2612507343292236,
+      "learning_rate": 8.041329739442948e-05,
+      "loss": 0.7968940734863281,
+      "step": 896
+    },
+    {
+      "epoch": 0.38748651564185543,
+      "grad_norm": 1.4770987033843994,
+      "learning_rate": 8.059299191374663e-05,
+      "loss": 0.7910935282707214,
+      "step": 898
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 1.4640419483184814,
+      "learning_rate": 8.07726864330638e-05,
+      "loss": 0.7873474955558777,
+      "step": 900
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "eval_loss": 0.8351938128471375,
+      "eval_runtime": 823.5649,
+      "eval_samples_per_second": 2.501,
+      "eval_steps_per_second": 2.501,
+      "step": 900
+    },
+    {
+      "epoch": 0.38921251348435815,
+      "grad_norm": 1.3780814409255981,
+      "learning_rate": 8.095238095238096e-05,
+      "loss": 0.8183950185775757,
+      "step": 902
+    },
+    {
+      "epoch": 0.3900755124056095,
+      "grad_norm": 1.5895066261291504,
+      "learning_rate": 8.113207547169813e-05,
+      "loss": 0.786055326461792,
+      "step": 904
+    },
+    {
+      "epoch": 0.39093851132686086,
+      "grad_norm": 1.6340118646621704,
+      "learning_rate": 8.131176999101528e-05,
+      "loss": 0.8638336658477783,
+      "step": 906
+    },
+    {
+      "epoch": 0.3918015102481122,
+      "grad_norm": 1.3990486860275269,
+      "learning_rate": 8.149146451033244e-05,
+      "loss": 0.702790379524231,
+      "step": 908
+    },
+    {
+      "epoch": 0.3926645091693635,
+      "grad_norm": 1.3703010082244873,
+      "learning_rate": 8.167115902964961e-05,
+      "loss": 0.7845349907875061,
+      "step": 910
+    },
+    {
+      "epoch": 0.3935275080906149,
+      "grad_norm": 1.4194090366363525,
+      "learning_rate": 8.185085354896676e-05,
+      "loss": 0.8117155432701111,
+      "step": 912
+    },
+    {
+      "epoch": 0.39439050701186623,
+      "grad_norm": 1.4716848134994507,
+      "learning_rate": 8.203054806828392e-05,
+      "loss": 0.8229454755783081,
+      "step": 914
+    },
+    {
+      "epoch": 0.3952535059331176,
+      "grad_norm": 1.51328706741333,
+      "learning_rate": 8.221024258760108e-05,
+      "loss": 0.698765218257904,
+      "step": 916
+    },
+    {
+      "epoch": 0.39611650485436894,
+      "grad_norm": 1.4755173921585083,
+      "learning_rate": 8.238993710691824e-05,
+      "loss": 0.7694190144538879,
+      "step": 918
+    },
+    {
+      "epoch": 0.3969795037756203,
+      "grad_norm": 1.5302451848983765,
+      "learning_rate": 8.25696316262354e-05,
+      "loss": 0.779274046421051,
+      "step": 920
+    },
+    {
+      "epoch": 0.3978425026968716,
+      "grad_norm": 1.474968433380127,
+      "learning_rate": 8.274932614555256e-05,
+      "loss": 0.713699221611023,
+      "step": 922
+    },
+    {
+      "epoch": 0.39870550161812296,
+      "grad_norm": 1.4024375677108765,
+      "learning_rate": 8.292902066486972e-05,
+      "loss": 0.7869517803192139,
+      "step": 924
+    },
+    {
+      "epoch": 0.3995685005393743,
+      "grad_norm": 1.5729585886001587,
+      "learning_rate": 8.310871518418689e-05,
+      "loss": 0.9040259718894958,
+      "step": 926
+    },
+    {
+      "epoch": 0.4004314994606257,
+      "grad_norm": 1.609850525856018,
+      "learning_rate": 8.328840970350404e-05,
+      "loss": 0.7589567303657532,
+      "step": 928
+    },
+    {
+      "epoch": 0.40129449838187703,
+      "grad_norm": 1.778781533241272,
+      "learning_rate": 8.34681042228212e-05,
+      "loss": 0.8725809454917908,
+      "step": 930
+    },
+    {
+      "epoch": 0.4021574973031284,
+      "grad_norm": 1.6333881616592407,
+      "learning_rate": 8.364779874213837e-05,
+      "loss": 0.8280068039894104,
+      "step": 932
+    },
+    {
+      "epoch": 0.40302049622437974,
+      "grad_norm": 1.6444122791290283,
+      "learning_rate": 8.382749326145552e-05,
+      "loss": 0.8293300867080688,
+      "step": 934
+    },
+    {
+      "epoch": 0.40388349514563104,
+      "grad_norm": 1.2815860509872437,
+      "learning_rate": 8.400718778077269e-05,
+      "loss": 0.7628244161605835,
+      "step": 936
+    },
+    {
+      "epoch": 0.4047464940668824,
+      "grad_norm": 1.7849020957946777,
+      "learning_rate": 8.418688230008985e-05,
+      "loss": 0.8951035141944885,
+      "step": 938
+    },
+    {
+      "epoch": 0.40560949298813376,
+      "grad_norm": 1.800937294960022,
+      "learning_rate": 8.436657681940702e-05,
+      "loss": 0.7677619457244873,
+      "step": 940
+    },
+    {
+      "epoch": 0.4064724919093851,
+      "grad_norm": 1.5004104375839233,
+      "learning_rate": 8.454627133872417e-05,
+      "loss": 0.8553397059440613,
+      "step": 942
+    },
+    {
+      "epoch": 0.40733549083063647,
+      "grad_norm": 1.3399486541748047,
+      "learning_rate": 8.472596585804133e-05,
+      "loss": 0.7110850811004639,
+      "step": 944
+    },
+    {
+      "epoch": 0.4081984897518878,
+      "grad_norm": 1.8936012983322144,
+      "learning_rate": 8.49056603773585e-05,
+      "loss": 0.9379971623420715,
+      "step": 946
+    },
+    {
+      "epoch": 0.4090614886731392,
+      "grad_norm": 1.2648893594741821,
+      "learning_rate": 8.508535489667565e-05,
+      "loss": 0.7492738366127014,
+      "step": 948
+    },
+    {
+      "epoch": 0.4099244875943905,
+      "grad_norm": 1.5587494373321533,
+      "learning_rate": 8.526504941599281e-05,
+      "loss": 0.7922301292419434,
+      "step": 950
+    },
+    {
+      "epoch": 0.41078748651564184,
+      "grad_norm": 1.5042990446090698,
+      "learning_rate": 8.544474393530998e-05,
+      "loss": 0.7494275569915771,
+      "step": 952
+    },
+    {
+      "epoch": 0.4116504854368932,
+      "grad_norm": 1.4338537454605103,
+      "learning_rate": 8.562443845462714e-05,
+      "loss": 0.7983633279800415,
+      "step": 954
+    },
+    {
+      "epoch": 0.41251348435814456,
+      "grad_norm": 1.6135673522949219,
+      "learning_rate": 8.58041329739443e-05,
+      "loss": 0.813288152217865,
+      "step": 956
+    },
+    {
+      "epoch": 0.4133764832793959,
+      "grad_norm": 1.3761460781097412,
+      "learning_rate": 8.598382749326146e-05,
+      "loss": 0.7794904708862305,
+      "step": 958
+    },
+    {
+      "epoch": 0.41423948220064727,
+      "grad_norm": 1.51504385471344,
+      "learning_rate": 8.616352201257863e-05,
+      "loss": 0.7544562816619873,
+      "step": 960
+    },
+    {
+      "epoch": 0.41510248112189857,
+      "grad_norm": 1.3698909282684326,
+      "learning_rate": 8.634321653189578e-05,
+      "loss": 0.8151395916938782,
+      "step": 962
+    },
+    {
+      "epoch": 0.4159654800431499,
+      "grad_norm": 1.5509650707244873,
+      "learning_rate": 8.652291105121294e-05,
+      "loss": 0.7997464537620544,
+      "step": 964
+    },
+    {
+      "epoch": 0.4168284789644013,
+      "grad_norm": 1.2967383861541748,
+      "learning_rate": 8.67026055705301e-05,
+      "loss": 0.767808735370636,
+      "step": 966
+    },
+    {
+      "epoch": 0.41769147788565264,
+      "grad_norm": 1.2444552183151245,
+      "learning_rate": 8.688230008984727e-05,
+      "loss": 0.7537208795547485,
+      "step": 968
+    },
+    {
+      "epoch": 0.418554476806904,
+      "grad_norm": 1.4390850067138672,
+      "learning_rate": 8.706199460916442e-05,
+      "loss": 0.7796021103858948,
+      "step": 970
+    },
+    {
+      "epoch": 0.41941747572815535,
+      "grad_norm": 1.4822322130203247,
+      "learning_rate": 8.724168912848159e-05,
+      "loss": 0.7812987565994263,
+      "step": 972
+    },
+    {
+      "epoch": 0.4202804746494067,
+      "grad_norm": 1.3770837783813477,
+      "learning_rate": 8.742138364779875e-05,
+      "loss": 0.7396363019943237,
+      "step": 974
+    },
+    {
+      "epoch": 0.421143473570658,
+      "grad_norm": 1.5534236431121826,
+      "learning_rate": 8.76010781671159e-05,
+      "loss": 0.8390982151031494,
+      "step": 976
+    },
+    {
+      "epoch": 0.42200647249190937,
+      "grad_norm": 1.5428354740142822,
+      "learning_rate": 8.778077268643307e-05,
+      "loss": 0.8368987441062927,
+      "step": 978
+    },
+    {
+      "epoch": 0.4228694714131607,
+      "grad_norm": 1.3579497337341309,
+      "learning_rate": 8.796046720575023e-05,
+      "loss": 0.8203011155128479,
+      "step": 980
+    },
+    {
+      "epoch": 0.4237324703344121,
+      "grad_norm": 1.5543184280395508,
+      "learning_rate": 8.81401617250674e-05,
+      "loss": 0.7622520923614502,
+      "step": 982
+    },
+    {
+      "epoch": 0.42459546925566344,
+      "grad_norm": 1.5728850364685059,
+      "learning_rate": 8.831985624438455e-05,
+      "loss": 0.7764845490455627,
+      "step": 984
+    },
+    {
+      "epoch": 0.4254584681769148,
+      "grad_norm": 1.5842933654785156,
+      "learning_rate": 8.849955076370172e-05,
+      "loss": 0.8136081099510193,
+      "step": 986
+    },
+    {
+      "epoch": 0.42632146709816615,
+      "grad_norm": 1.5721858739852905,
+      "learning_rate": 8.867924528301888e-05,
+      "loss": 0.8388259410858154,
+      "step": 988
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 1.6682584285736084,
+      "learning_rate": 8.885893980233603e-05,
+      "loss": 0.8829372525215149,
+      "step": 990
+    },
+    {
+      "epoch": 0.4280474649406688,
+      "grad_norm": 1.7098870277404785,
+      "learning_rate": 8.90386343216532e-05,
+      "loss": 0.8545100688934326,
+      "step": 992
+    },
+    {
+      "epoch": 0.42891046386192017,
+      "grad_norm": 1.5161751508712769,
+      "learning_rate": 8.921832884097035e-05,
+      "loss": 0.8233623504638672,
+      "step": 994
+    },
+    {
+      "epoch": 0.4297734627831715,
+      "grad_norm": 1.457794189453125,
+      "learning_rate": 8.939802336028751e-05,
+      "loss": 0.7576998472213745,
+      "step": 996
+    },
+    {
+      "epoch": 0.4306364617044229,
+      "grad_norm": 1.6383825540542603,
+      "learning_rate": 8.957771787960468e-05,
+      "loss": 0.8089564442634583,
+      "step": 998
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "grad_norm": 1.4149754047393799,
+      "learning_rate": 8.975741239892183e-05,
+      "loss": 0.7791779637336731,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "eval_loss": 0.8266019821166992,
+      "eval_runtime": 835.0044,
+      "eval_samples_per_second": 2.467,
+      "eval_steps_per_second": 2.467,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4323624595469256,
+      "grad_norm": 1.5475730895996094,
+      "learning_rate": 8.9937106918239e-05,
+      "loss": 0.7443642616271973,
+      "step": 1002
+    },
+    {
+      "epoch": 0.4332254584681769,
+      "grad_norm": 1.4621447324752808,
+      "learning_rate": 9.011680143755616e-05,
+      "loss": 0.8210510015487671,
+      "step": 1004
+    },
+    {
+      "epoch": 0.43408845738942825,
+      "grad_norm": 1.3651922941207886,
+      "learning_rate": 9.029649595687331e-05,
+      "loss": 0.8130766153335571,
+      "step": 1006
+    },
+    {
+      "epoch": 0.4349514563106796,
+      "grad_norm": 1.3587357997894287,
+      "learning_rate": 9.047619047619048e-05,
+      "loss": 0.79145747423172,
+      "step": 1008
+    },
+    {
+      "epoch": 0.43581445523193096,
+      "grad_norm": 1.464652180671692,
+      "learning_rate": 9.065588499550764e-05,
+      "loss": 0.8286946415901184,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4366774541531823,
+      "grad_norm": 1.3912625312805176,
+      "learning_rate": 9.083557951482479e-05,
+      "loss": 0.717319667339325,
+      "step": 1012
+    },
+    {
+      "epoch": 0.4375404530744337,
+      "grad_norm": 1.2045491933822632,
+      "learning_rate": 9.101527403414196e-05,
+      "loss": 0.7294418215751648,
+      "step": 1014
+    },
+    {
+      "epoch": 0.438403451995685,
+      "grad_norm": 1.3449069261550903,
+      "learning_rate": 9.119496855345912e-05,
+      "loss": 0.7366700768470764,
+      "step": 1016
+    },
+    {
+      "epoch": 0.43926645091693634,
+      "grad_norm": 2.901384115219116,
+      "learning_rate": 9.137466307277629e-05,
+      "loss": 0.8551293611526489,
+      "step": 1018
+    },
+    {
+      "epoch": 0.4401294498381877,
+      "grad_norm": 1.6648688316345215,
+      "learning_rate": 9.155435759209344e-05,
+      "loss": 0.8944112658500671,
+      "step": 1020
+    },
+    {
+      "epoch": 0.44099244875943905,
+      "grad_norm": 1.3050304651260376,
+      "learning_rate": 9.17340521114106e-05,
+      "loss": 0.7644214630126953,
+      "step": 1022
+    },
+    {
+      "epoch": 0.4418554476806904,
+      "grad_norm": 1.4643231630325317,
+      "learning_rate": 9.191374663072777e-05,
+      "loss": 0.8644799590110779,
+      "step": 1024
+    },
+    {
+      "epoch": 0.44271844660194176,
+      "grad_norm": 1.4690274000167847,
+      "learning_rate": 9.209344115004492e-05,
+      "loss": 0.8281022906303406,
+      "step": 1026
+    },
+    {
+      "epoch": 0.4435814455231931,
+      "grad_norm": 1.3321986198425293,
+      "learning_rate": 9.227313566936209e-05,
+      "loss": 0.7432141900062561,
+      "step": 1028
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.4342927932739258,
+      "learning_rate": 9.245283018867925e-05,
+      "loss": 0.8143638372421265,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4453074433656958,
+      "grad_norm": 1.747295618057251,
+      "learning_rate": 9.263252470799642e-05,
+      "loss": 0.8102239370346069,
+      "step": 1032
+    },
+    {
+      "epoch": 0.44617044228694713,
+      "grad_norm": 1.3273073434829712,
+      "learning_rate": 9.281221922731357e-05,
+      "loss": 0.7768088579177856,
+      "step": 1034
+    },
+    {
+      "epoch": 0.4470334412081985,
+      "grad_norm": 1.5019903182983398,
+      "learning_rate": 9.299191374663073e-05,
+      "loss": 0.7886938452720642,
+      "step": 1036
+    },
+    {
+      "epoch": 0.44789644012944985,
+      "grad_norm": 1.6711527109146118,
+      "learning_rate": 9.31716082659479e-05,
+      "loss": 0.8152258396148682,
+      "step": 1038
+    },
+    {
+      "epoch": 0.4487594390507012,
+      "grad_norm": 1.8504793643951416,
+      "learning_rate": 9.335130278526505e-05,
+      "loss": 0.8339349627494812,
+      "step": 1040
+    },
+    {
+      "epoch": 0.44962243797195256,
+      "grad_norm": 1.4333337545394897,
+      "learning_rate": 9.353099730458221e-05,
+      "loss": 0.7798911929130554,
+      "step": 1042
+    },
+    {
+      "epoch": 0.45048543689320386,
+      "grad_norm": 1.3361700773239136,
+      "learning_rate": 9.371069182389938e-05,
+      "loss": 0.7676728963851929,
+      "step": 1044
+    },
+    {
+      "epoch": 0.4513484358144552,
+      "grad_norm": 1.338934063911438,
+      "learning_rate": 9.389038634321654e-05,
+      "loss": 0.7729206085205078,
+      "step": 1046
+    },
+    {
+      "epoch": 0.4522114347357066,
+      "grad_norm": 1.4347442388534546,
+      "learning_rate": 9.40700808625337e-05,
+      "loss": 0.7923640608787537,
+      "step": 1048
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 1.4451628923416138,
+      "learning_rate": 9.424977538185086e-05,
+      "loss": 0.8068996071815491,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4539374325782093,
+      "grad_norm": 1.1904500722885132,
+      "learning_rate": 9.442946990116803e-05,
+      "loss": 0.7532910704612732,
+      "step": 1052
+    },
+    {
+      "epoch": 0.45480043149946064,
+      "grad_norm": 1.4103976488113403,
+      "learning_rate": 9.460916442048518e-05,
+      "loss": 0.8236854672431946,
+      "step": 1054
+    },
+    {
+      "epoch": 0.455663430420712,
+      "grad_norm": 1.3762754201889038,
+      "learning_rate": 9.478885893980234e-05,
+      "loss": 0.7532716393470764,
+      "step": 1056
+    },
+    {
+      "epoch": 0.4565264293419633,
+      "grad_norm": 1.461421012878418,
+      "learning_rate": 9.496855345911951e-05,
+      "loss": 0.8506031632423401,
+      "step": 1058
+    },
+    {
+      "epoch": 0.45738942826321466,
+      "grad_norm": 1.7207789421081543,
+      "learning_rate": 9.514824797843667e-05,
+      "loss": 0.7824664115905762,
+      "step": 1060
+    },
+    {
+      "epoch": 0.458252427184466,
+      "grad_norm": 1.5946974754333496,
+      "learning_rate": 9.532794249775382e-05,
+      "loss": 0.8674250245094299,
+      "step": 1062
+    },
+    {
+      "epoch": 0.4591154261057174,
+      "grad_norm": 1.3552565574645996,
+      "learning_rate": 9.550763701707099e-05,
+      "loss": 0.7851845622062683,
+      "step": 1064
+    },
+    {
+      "epoch": 0.45997842502696873,
+      "grad_norm": 1.414617657661438,
+      "learning_rate": 9.568733153638815e-05,
+      "loss": 0.8890700936317444,
+      "step": 1066
+    },
+    {
+      "epoch": 0.4608414239482201,
+      "grad_norm": 1.3322749137878418,
+      "learning_rate": 9.58670260557053e-05,
+      "loss": 0.8226593732833862,
+      "step": 1068
+    },
+    {
+      "epoch": 0.4617044228694714,
+      "grad_norm": 1.41420316696167,
+      "learning_rate": 9.604672057502247e-05,
+      "loss": 0.7663303017616272,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46256742179072274,
+      "grad_norm": 1.324967384338379,
+      "learning_rate": 9.622641509433963e-05,
+      "loss": 0.7122516632080078,
+      "step": 1072
+    },
+    {
+      "epoch": 0.4634304207119741,
+      "grad_norm": 1.2046154737472534,
+      "learning_rate": 9.640610961365679e-05,
+      "loss": 0.7177618145942688,
+      "step": 1074
+    },
+    {
+      "epoch": 0.46429341963322546,
+      "grad_norm": 1.5221766233444214,
+      "learning_rate": 9.658580413297395e-05,
+      "loss": 0.7618930339813232,
+      "step": 1076
+    },
+    {
+      "epoch": 0.4651564185544768,
+      "grad_norm": 1.3517179489135742,
+      "learning_rate": 9.67654986522911e-05,
+      "loss": 0.7483780384063721,
+      "step": 1078
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 1.747865080833435,
+      "learning_rate": 9.694519317160827e-05,
+      "loss": 0.8507670164108276,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4668824163969795,
+      "grad_norm": 1.4183019399642944,
+      "learning_rate": 9.712488769092543e-05,
+      "loss": 0.7893540859222412,
+      "step": 1082
+    },
+    {
+      "epoch": 0.46774541531823083,
+      "grad_norm": 1.6290462017059326,
+      "learning_rate": 9.730458221024258e-05,
+      "loss": 0.7891272306442261,
+      "step": 1084
+    },
+    {
+      "epoch": 0.4686084142394822,
+      "grad_norm": 1.6605802774429321,
+      "learning_rate": 9.748427672955975e-05,
+      "loss": 0.841018795967102,
+      "step": 1086
+    },
+    {
+      "epoch": 0.46947141316073354,
+      "grad_norm": 1.388964295387268,
+      "learning_rate": 9.766397124887691e-05,
+      "loss": 0.8099003434181213,
+      "step": 1088
+    },
+    {
+      "epoch": 0.4703344120819849,
+      "grad_norm": 1.3901978731155396,
+      "learning_rate": 9.784366576819407e-05,
+      "loss": 0.7177658677101135,
+      "step": 1090
+    },
+    {
+      "epoch": 0.47119741100323626,
+      "grad_norm": 1.3341423273086548,
+      "learning_rate": 9.802336028751123e-05,
+      "loss": 0.8285676836967468,
+      "step": 1092
+    },
+    {
+      "epoch": 0.4720604099244876,
+      "grad_norm": 1.5451914072036743,
+      "learning_rate": 9.82030548068284e-05,
+      "loss": 0.7582666873931885,
+      "step": 1094
+    },
+    {
+      "epoch": 0.47292340884573897,
+      "grad_norm": 1.5395640134811401,
+      "learning_rate": 9.838274932614556e-05,
+      "loss": 0.7293475270271301,
+      "step": 1096
+    },
+    {
+      "epoch": 0.47378640776699027,
+      "grad_norm": 1.5005141496658325,
+      "learning_rate": 9.856244384546271e-05,
+      "loss": 0.8858493566513062,
+      "step": 1098
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "grad_norm": 1.3562248945236206,
+      "learning_rate": 9.874213836477988e-05,
+      "loss": 0.7176282405853271,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "eval_loss": 0.8152187466621399,
+      "eval_runtime": 835.0394,
+      "eval_samples_per_second": 2.467,
+      "eval_steps_per_second": 2.467,
+      "step": 1100
+    },
+    {
+      "epoch": 0.475512405609493,
+      "grad_norm": 1.5226716995239258,
+      "learning_rate": 9.892183288409704e-05,
+      "loss": 0.8048524856567383,
+      "step": 1102
+    },
+    {
+      "epoch": 0.47637540453074434,
+      "grad_norm": 1.3544842004776,
+      "learning_rate": 9.91015274034142e-05,
+      "loss": 0.7954329252243042,
+      "step": 1104
+    },
+    {
+      "epoch": 0.4772384034519957,
+      "grad_norm": 1.5169771909713745,
+      "learning_rate": 9.928122192273136e-05,
+      "loss": 0.804015040397644,
+      "step": 1106
+    },
+    {
+      "epoch": 0.47810140237324705,
+      "grad_norm": 1.4011081457138062,
+      "learning_rate": 9.946091644204852e-05,
+      "loss": 0.7652344703674316,
+      "step": 1108
+    },
+    {
+      "epoch": 0.47896440129449835,
+      "grad_norm": 1.4163414239883423,
+      "learning_rate": 9.964061096136569e-05,
+      "loss": 0.8501335382461548,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4798274002157497,
+      "grad_norm": 1.7406005859375,
+      "learning_rate": 9.982030548068284e-05,
+      "loss": 0.9024044871330261,
+      "step": 1112
+    },
+    {
+      "epoch": 0.48069039913700107,
+      "grad_norm": 1.1490557193756104,
+      "learning_rate": 0.0001,
+      "loss": 0.7308287024497986,
+      "step": 1114
+    },
+    {
+      "epoch": 0.4815533980582524,
+      "grad_norm": 1.2512775659561157,
+      "learning_rate": 9.99999939713627e-05,
+      "loss": 0.7273974418640137,
+      "step": 1116
+    },
+    {
+      "epoch": 0.4824163969795038,
+      "grad_norm": 1.3944242000579834,
+      "learning_rate": 9.999997588545227e-05,
+      "loss": 0.8071790337562561,
+      "step": 1118
+    },
+    {
+      "epoch": 0.48327939590075514,
+      "grad_norm": 1.2209112644195557,
+      "learning_rate": 9.999994574227303e-05,
+      "loss": 0.6586678624153137,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4841423948220065,
+      "grad_norm": 1.7328095436096191,
+      "learning_rate": 9.999990354183228e-05,
+      "loss": 0.8529233336448669,
+      "step": 1122
+    },
+    {
+      "epoch": 0.4850053937432578,
+      "grad_norm": 1.3309327363967896,
+      "learning_rate": 9.999984928414021e-05,
+      "loss": 0.7529556155204773,
+      "step": 1124
+    },
+    {
+      "epoch": 0.48586839266450915,
+      "grad_norm": 1.22034752368927,
+      "learning_rate": 9.999978296920987e-05,
+      "loss": 0.6780388355255127,
+      "step": 1126
+    },
+    {
+      "epoch": 0.4867313915857605,
+      "grad_norm": 1.975162386894226,
+      "learning_rate": 9.999970459705727e-05,
+      "loss": 0.7941693067550659,
+      "step": 1128
+    },
+    {
+      "epoch": 0.48759439050701187,
+      "grad_norm": 1.4939875602722168,
+      "learning_rate": 9.999961416770132e-05,
+      "loss": 0.7895156145095825,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4884573894282632,
+      "grad_norm": 1.4237034320831299,
+      "learning_rate": 9.999951168116379e-05,
+      "loss": 0.7662149667739868,
+      "step": 1132
+    },
+    {
+      "epoch": 0.4893203883495146,
+      "grad_norm": 1.24979567527771,
+      "learning_rate": 9.999939713746942e-05,
+      "loss": 0.8079231381416321,
+      "step": 1134
+    },
+    {
+      "epoch": 0.49018338727076594,
+      "grad_norm": 1.2252353429794312,
+      "learning_rate": 9.999927053664585e-05,
+      "loss": 0.7616434693336487,
+      "step": 1136
+    },
+    {
+      "epoch": 0.49104638619201724,
+      "grad_norm": 1.2176212072372437,
+      "learning_rate": 9.999913187872357e-05,
+      "loss": 0.8576793074607849,
+      "step": 1138
+    },
+    {
+      "epoch": 0.4919093851132686,
+      "grad_norm": 1.2108005285263062,
+      "learning_rate": 9.999898116373605e-05,
+      "loss": 0.8060292601585388,
+      "step": 1140
+    },
+    {
+      "epoch": 0.49277238403451995,
+      "grad_norm": 1.6340605020523071,
+      "learning_rate": 9.99988183917196e-05,
+      "loss": 0.7532875537872314,
+      "step": 1142
+    },
+    {
+      "epoch": 0.4936353829557713,
+      "grad_norm": 1.261606216430664,
+      "learning_rate": 9.99986435627135e-05,
+      "loss": 0.7241997718811035,
+      "step": 1144
+    },
+    {
+      "epoch": 0.49449838187702266,
+      "grad_norm": 1.2678134441375732,
+      "learning_rate": 9.99984566767599e-05,
+      "loss": 0.78656005859375,
+      "step": 1146
+    },
+    {
+      "epoch": 0.495361380798274,
+      "grad_norm": 1.4185810089111328,
+      "learning_rate": 9.999825773390387e-05,
+      "loss": 0.7423107624053955,
+      "step": 1148
+    },
+    {
+      "epoch": 0.4962243797195254,
+      "grad_norm": 1.3218237161636353,
+      "learning_rate": 9.999804673419338e-05,
+      "loss": 0.8178372383117676,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4970873786407767,
+      "grad_norm": 1.9698240756988525,
+      "learning_rate": 9.99978236776793e-05,
+      "loss": 0.8016347885131836,
+      "step": 1152
+    },
+    {
+      "epoch": 0.49795037756202803,
+      "grad_norm": 1.2228590250015259,
+      "learning_rate": 9.999758856441544e-05,
+      "loss": 0.782421886920929,
+      "step": 1154
+    },
+    {
+      "epoch": 0.4988133764832794,
+      "grad_norm": 1.2753938436508179,
+      "learning_rate": 9.999734139445849e-05,
+      "loss": 0.7235615849494934,
+      "step": 1156
+    },
+    {
+      "epoch": 0.49967637540453075,
+      "grad_norm": 1.353155493736267,
+      "learning_rate": 9.999708216786805e-05,
+      "loss": 0.7686187028884888,
+      "step": 1158
+    },
+    {
+      "epoch": 0.5005393743257821,
+      "grad_norm": 1.4242770671844482,
+      "learning_rate": 9.999681088470663e-05,
+      "loss": 0.7842718362808228,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5014023732470334,
+      "grad_norm": 1.501827359199524,
+      "learning_rate": 9.999652754503966e-05,
+      "loss": 0.8324156999588013,
+      "step": 1162
+    },
+    {
+      "epoch": 0.5022653721682848,
+      "grad_norm": 1.5403931140899658,
+      "learning_rate": 9.999623214893545e-05,
+      "loss": 0.7797855138778687,
+      "step": 1164
+    },
+    {
+      "epoch": 0.5031283710895361,
+      "grad_norm": 1.4075721502304077,
+      "learning_rate": 9.999592469646525e-05,
+      "loss": 0.7667348384857178,
+      "step": 1166
+    },
+    {
+      "epoch": 0.5039913700107875,
+      "grad_norm": 1.4411870241165161,
+      "learning_rate": 9.99956051877032e-05,
+      "loss": 0.8153020739555359,
+      "step": 1168
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 1.4197871685028076,
+      "learning_rate": 9.999527362272632e-05,
+      "loss": 0.8548861742019653,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5057173678532901,
+      "grad_norm": 1.5030468702316284,
+      "learning_rate": 9.999493000161458e-05,
+      "loss": 0.7978097796440125,
+      "step": 1172
+    },
+    {
+      "epoch": 0.5065803667745415,
+      "grad_norm": 1.483534574508667,
+      "learning_rate": 9.999457432445088e-05,
+      "loss": 0.7990087866783142,
+      "step": 1174
+    },
+    {
+      "epoch": 0.5074433656957928,
+      "grad_norm": 1.5424920320510864,
+      "learning_rate": 9.999420659132093e-05,
+      "loss": 0.8072807788848877,
+      "step": 1176
+    },
+    {
+      "epoch": 0.5083063646170443,
+      "grad_norm": 1.129503846168518,
+      "learning_rate": 9.999382680231344e-05,
+      "loss": 0.7216097712516785,
+      "step": 1178
+    },
+    {
+      "epoch": 0.5091693635382956,
+      "grad_norm": 1.3208131790161133,
+      "learning_rate": 9.999343495752001e-05,
+      "loss": 0.8637414574623108,
+      "step": 1180
+    },
+    {
+      "epoch": 0.510032362459547,
+      "grad_norm": 1.5239129066467285,
+      "learning_rate": 9.999303105703508e-05,
+      "loss": 0.8561362028121948,
+      "step": 1182
+    },
+    {
+      "epoch": 0.5108953613807983,
+      "grad_norm": 1.3193504810333252,
+      "learning_rate": 9.99926151009561e-05,
+      "loss": 0.7514780759811401,
+      "step": 1184
+    },
+    {
+      "epoch": 0.5117583603020496,
+      "grad_norm": 1.312649130821228,
+      "learning_rate": 9.999218708938336e-05,
+      "loss": 0.8634516596794128,
+      "step": 1186
+    },
+    {
+      "epoch": 0.512621359223301,
+      "grad_norm": 1.2677429914474487,
+      "learning_rate": 9.999174702242006e-05,
+      "loss": 0.7493832111358643,
+      "step": 1188
+    },
+    {
+      "epoch": 0.5134843581445523,
+      "grad_norm": 1.3901816606521606,
+      "learning_rate": 9.999129490017234e-05,
+      "loss": 0.8981389999389648,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5143473570658037,
+      "grad_norm": 1.232013463973999,
+      "learning_rate": 9.999083072274921e-05,
+      "loss": 0.6771019697189331,
+      "step": 1192
+    },
+    {
+      "epoch": 0.515210355987055,
+      "grad_norm": 1.1299076080322266,
+      "learning_rate": 9.999035449026261e-05,
+      "loss": 0.789888858795166,
+      "step": 1194
+    },
+    {
+      "epoch": 0.5160733549083064,
+      "grad_norm": 1.582215666770935,
+      "learning_rate": 9.998986620282738e-05,
+      "loss": 0.6656325459480286,
+      "step": 1196
+    },
+    {
+      "epoch": 0.5169363538295577,
+      "grad_norm": 1.3438260555267334,
+      "learning_rate": 9.998936586056127e-05,
+      "loss": 0.795595645904541,
+      "step": 1198
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 1.45097017288208,
+      "learning_rate": 9.998885346358495e-05,
+      "loss": 0.7769836187362671,
+      "step": 1200
+    },
+    {
+      "epoch": 0.517799352750809,
+      "eval_loss": 0.8070361018180847,
+      "eval_runtime": 823.9296,
+      "eval_samples_per_second": 2.5,
+      "eval_steps_per_second": 2.5,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5186623516720604,
+      "grad_norm": 1.3791370391845703,
+      "learning_rate": 9.998832901202195e-05,
+      "loss": 0.7527318000793457,
+      "step": 1202
+    },
+    {
+      "epoch": 0.5195253505933117,
+      "grad_norm": 1.2574659585952759,
+      "learning_rate": 9.998779250599876e-05,
+      "loss": 0.8021673560142517,
+      "step": 1204
+    },
+    {
+      "epoch": 0.5203883495145631,
+      "grad_norm": 1.3305809497833252,
+      "learning_rate": 9.998724394564476e-05,
+      "loss": 0.776639461517334,
+      "step": 1206
+    },
+    {
+      "epoch": 0.5212513484358144,
+      "grad_norm": 1.2330507040023804,
+      "learning_rate": 9.998668333109223e-05,
+      "loss": 0.7381181120872498,
+      "step": 1208
+    },
+    {
+      "epoch": 0.5221143473570659,
+      "grad_norm": 1.0482324361801147,
+      "learning_rate": 9.998611066247635e-05,
+      "loss": 0.6595721244812012,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5229773462783172,
+      "grad_norm": 1.5456492900848389,
+      "learning_rate": 9.998552593993522e-05,
+      "loss": 0.8388534784317017,
+      "step": 1212
+    },
+    {
+      "epoch": 0.5238403451995685,
+      "grad_norm": 1.3730167150497437,
+      "learning_rate": 9.998492916360986e-05,
+      "loss": 0.7593658566474915,
+      "step": 1214
+    },
+    {
+      "epoch": 0.5247033441208199,
+      "grad_norm": 1.2668508291244507,
+      "learning_rate": 9.998432033364416e-05,
+      "loss": 0.7796505093574524,
+      "step": 1216
+    },
+    {
+      "epoch": 0.5255663430420712,
+      "grad_norm": 1.1175068616867065,
+      "learning_rate": 9.998369945018493e-05,
+      "loss": 0.7493594288825989,
+      "step": 1218
+    },
+    {
+      "epoch": 0.5264293419633226,
+      "grad_norm": 1.121848464012146,
+      "learning_rate": 9.99830665133819e-05,
+      "loss": 0.7791322469711304,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5272923408845739,
+      "grad_norm": 1.49788236618042,
+      "learning_rate": 9.998242152338772e-05,
+      "loss": 0.8299469947814941,
+      "step": 1222
+    },
+    {
+      "epoch": 0.5281553398058253,
+      "grad_norm": 1.227125644683838,
+      "learning_rate": 9.998176448035791e-05,
+      "loss": 0.7911439538002014,
+      "step": 1224
+    },
+    {
+      "epoch": 0.5290183387270766,
+      "grad_norm": 1.176081895828247,
+      "learning_rate": 9.998109538445091e-05,
+      "loss": 0.6487553119659424,
+      "step": 1226
+    },
+    {
+      "epoch": 0.5298813376483279,
+      "grad_norm": 1.169835090637207,
+      "learning_rate": 9.99804142358281e-05,
+      "loss": 0.7331781983375549,
+      "step": 1228
+    },
+    {
+      "epoch": 0.5307443365695793,
+      "grad_norm": 1.4085001945495605,
+      "learning_rate": 9.997972103465367e-05,
+      "loss": 0.8198121190071106,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5316073354908306,
+      "grad_norm": 1.8634135723114014,
+      "learning_rate": 9.997901578109484e-05,
+      "loss": 0.7099791169166565,
+      "step": 1232
+    },
+    {
+      "epoch": 0.532470334412082,
+      "grad_norm": 1.4719511270523071,
+      "learning_rate": 9.997829847532166e-05,
+      "loss": 0.7416951656341553,
+      "step": 1234
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.2430769205093384,
+      "learning_rate": 9.99775691175071e-05,
+      "loss": 0.7583408355712891,
+      "step": 1236
+    },
+    {
+      "epoch": 0.5341963322545846,
+      "grad_norm": 1.2502130270004272,
+      "learning_rate": 9.997682770782706e-05,
+      "loss": 0.7639391422271729,
+      "step": 1238
+    },
+    {
+      "epoch": 0.535059331175836,
+      "grad_norm": 1.3577396869659424,
+      "learning_rate": 9.997607424646032e-05,
+      "loss": 0.8304449319839478,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5359223300970873,
+      "grad_norm": 1.0986218452453613,
+      "learning_rate": 9.997530873358854e-05,
+      "loss": 0.7331952452659607,
+      "step": 1242
+    },
+    {
+      "epoch": 0.5367853290183388,
+      "grad_norm": 1.4607514142990112,
+      "learning_rate": 9.997453116939637e-05,
+      "loss": 0.8173373341560364,
+      "step": 1244
+    },
+    {
+      "epoch": 0.53764832793959,
+      "grad_norm": 1.2897552251815796,
+      "learning_rate": 9.997374155407128e-05,
+      "loss": 0.7677372694015503,
+      "step": 1246
+    },
+    {
+      "epoch": 0.5385113268608415,
+      "grad_norm": 1.4581117630004883,
+      "learning_rate": 9.997293988780372e-05,
+      "loss": 0.8524296283721924,
+      "step": 1248
+    },
+    {
+      "epoch": 0.5393743257820928,
+      "grad_norm": 1.2029366493225098,
+      "learning_rate": 9.997212617078698e-05,
+      "loss": 0.7920866012573242,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5402373247033441,
+      "grad_norm": 1.109483242034912,
+      "learning_rate": 9.997130040321727e-05,
+      "loss": 0.7889736294746399,
+      "step": 1252
+    },
+    {
+      "epoch": 0.5411003236245955,
+      "grad_norm": 1.1930333375930786,
+      "learning_rate": 9.997046258529377e-05,
+      "loss": 0.6593763828277588,
+      "step": 1254
+    },
+    {
+      "epoch": 0.5419633225458468,
+      "grad_norm": 1.3668162822723389,
+      "learning_rate": 9.996961271721845e-05,
+      "loss": 0.7768212556838989,
+      "step": 1256
+    },
+    {
+      "epoch": 0.5428263214670982,
+      "grad_norm": 1.2901886701583862,
+      "learning_rate": 9.996875079919632e-05,
+      "loss": 0.7392467260360718,
+      "step": 1258
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 1.366720199584961,
+      "learning_rate": 9.996787683143518e-05,
+      "loss": 0.6961479187011719,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5445523193096009,
+      "grad_norm": 1.2925949096679688,
+      "learning_rate": 9.99669908141458e-05,
+      "loss": 0.801517128944397,
+      "step": 1262
+    },
+    {
+      "epoch": 0.5454153182308522,
+      "grad_norm": 1.1967244148254395,
+      "learning_rate": 9.996609274754182e-05,
+      "loss": 0.7287030816078186,
+      "step": 1264
+    },
+    {
+      "epoch": 0.5462783171521035,
+      "grad_norm": 1.419996738433838,
+      "learning_rate": 9.996518263183985e-05,
+      "loss": 0.7791255116462708,
+      "step": 1266
+    },
+    {
+      "epoch": 0.5471413160733549,
+      "grad_norm": 1.3544845581054688,
+      "learning_rate": 9.996426046725933e-05,
+      "loss": 0.6665297150611877,
+      "step": 1268
+    },
+    {
+      "epoch": 0.5480043149946062,
+      "grad_norm": 1.6272345781326294,
+      "learning_rate": 9.996332625402262e-05,
+      "loss": 0.7902728915214539,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5488673139158576,
+      "grad_norm": 1.4264246225357056,
+      "learning_rate": 9.996237999235502e-05,
+      "loss": 0.8483795523643494,
+      "step": 1272
+    },
+    {
+      "epoch": 0.5497303128371089,
+      "grad_norm": 1.3180512189865112,
+      "learning_rate": 9.996142168248473e-05,
+      "loss": 0.7432113289833069,
+      "step": 1274
+    },
+    {
+      "epoch": 0.5505933117583603,
+      "grad_norm": 0.9958710074424744,
+      "learning_rate": 9.996045132464283e-05,
+      "loss": 0.6721545457839966,
+      "step": 1276
+    },
+    {
+      "epoch": 0.5514563106796116,
+      "grad_norm": 1.371719241142273,
+      "learning_rate": 9.995946891906331e-05,
+      "loss": 0.7770468592643738,
+      "step": 1278
+    },
+    {
+      "epoch": 0.552319309600863,
+      "grad_norm": 1.1906969547271729,
+      "learning_rate": 9.995847446598307e-05,
+      "loss": 0.816495418548584,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5531823085221144,
+      "grad_norm": 1.262184977531433,
+      "learning_rate": 9.995746796564195e-05,
+      "loss": 0.7122345566749573,
+      "step": 1282
+    },
+    {
+      "epoch": 0.5540453074433657,
+      "grad_norm": 1.454692006111145,
+      "learning_rate": 9.995644941828262e-05,
+      "loss": 0.8476479649543762,
+      "step": 1284
+    },
+    {
+      "epoch": 0.5549083063646171,
+      "grad_norm": 1.44277024269104,
+      "learning_rate": 9.995541882415072e-05,
+      "loss": 0.7595248818397522,
+      "step": 1286
+    },
+    {
+      "epoch": 0.5557713052858684,
+      "grad_norm": 1.151465654373169,
+      "learning_rate": 9.995437618349478e-05,
+      "loss": 0.7413201928138733,
+      "step": 1288
+    },
+    {
+      "epoch": 0.5566343042071198,
+      "grad_norm": 1.3160182237625122,
+      "learning_rate": 9.995332149656621e-05,
+      "loss": 0.7242997884750366,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5574973031283711,
+      "grad_norm": 1.2748576402664185,
+      "learning_rate": 9.995225476361936e-05,
+      "loss": 0.7779543995857239,
+      "step": 1292
+    },
+    {
+      "epoch": 0.5583603020496224,
+      "grad_norm": 1.3639990091323853,
+      "learning_rate": 9.995117598491145e-05,
+      "loss": 0.8075780868530273,
+      "step": 1294
+    },
+    {
+      "epoch": 0.5592233009708738,
+      "grad_norm": 1.0247999429702759,
+      "learning_rate": 9.995008516070263e-05,
+      "loss": 0.6940524578094482,
+      "step": 1296
+    },
+    {
+      "epoch": 0.5600862998921251,
+      "grad_norm": 1.3383198976516724,
+      "learning_rate": 9.994898229125597e-05,
+      "loss": 0.799100399017334,
+      "step": 1298
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "grad_norm": 1.37660551071167,
+      "learning_rate": 9.994786737683738e-05,
+      "loss": 0.8038942217826843,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "eval_loss": 0.7962777018547058,
+      "eval_runtime": 827.8798,
+      "eval_samples_per_second": 2.488,
+      "eval_steps_per_second": 2.488,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5618122977346278,
+      "grad_norm": 1.5424575805664062,
+      "learning_rate": 9.994674041771574e-05,
+      "loss": 0.8553245067596436,
+      "step": 1302
+    },
+    {
+      "epoch": 0.5626752966558792,
+      "grad_norm": 1.1047813892364502,
+      "learning_rate": 9.994560141416282e-05,
+      "loss": 0.6650274991989136,
+      "step": 1304
+    },
+    {
+      "epoch": 0.5635382955771305,
+      "grad_norm": 1.4532393217086792,
+      "learning_rate": 9.994445036645328e-05,
+      "loss": 0.794471025466919,
+      "step": 1306
+    },
+    {
+      "epoch": 0.5644012944983818,
+      "grad_norm": 1.2588927745819092,
+      "learning_rate": 9.994328727486468e-05,
+      "loss": 0.7241487503051758,
+      "step": 1308
+    },
+    {
+      "epoch": 0.5652642934196332,
+      "grad_norm": 1.4981781244277954,
+      "learning_rate": 9.994211213967748e-05,
+      "loss": 0.7781044244766235,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5661272923408845,
+      "grad_norm": 1.426277995109558,
+      "learning_rate": 9.99409249611751e-05,
+      "loss": 0.7772427201271057,
+      "step": 1312
+    },
+    {
+      "epoch": 0.566990291262136,
+      "grad_norm": 1.1987197399139404,
+      "learning_rate": 9.993972573964379e-05,
+      "loss": 0.7443774342536926,
+      "step": 1314
+    },
+    {
+      "epoch": 0.5678532901833873,
+      "grad_norm": 1.1490470170974731,
+      "learning_rate": 9.993851447537275e-05,
+      "loss": 0.7203393578529358,
+      "step": 1316
+    },
+    {
+      "epoch": 0.5687162891046387,
+      "grad_norm": 1.3586851358413696,
+      "learning_rate": 9.993729116865406e-05,
+      "loss": 0.8038793206214905,
+      "step": 1318
+    },
+    {
+      "epoch": 0.56957928802589,
+      "grad_norm": 1.4160653352737427,
+      "learning_rate": 9.993605581978274e-05,
+      "loss": 0.827308714389801,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5704422869471413,
+      "grad_norm": 1.2725251913070679,
+      "learning_rate": 9.993480842905667e-05,
+      "loss": 0.8183196783065796,
+      "step": 1322
+    },
+    {
+      "epoch": 0.5713052858683927,
+      "grad_norm": 1.3789756298065186,
+      "learning_rate": 9.993354899677665e-05,
+      "loss": 0.8268020153045654,
+      "step": 1324
+    },
+    {
+      "epoch": 0.572168284789644,
+      "grad_norm": 1.2641910314559937,
+      "learning_rate": 9.993227752324639e-05,
+      "loss": 0.7434715628623962,
+      "step": 1326
+    },
+    {
+      "epoch": 0.5730312837108954,
+      "grad_norm": 1.2429786920547485,
+      "learning_rate": 9.99309940087725e-05,
+      "loss": 0.7636955976486206,
+      "step": 1328
+    },
+    {
+      "epoch": 0.5738942826321467,
+      "grad_norm": 1.3281534910202026,
+      "learning_rate": 9.992969845366449e-05,
+      "loss": 0.794617772102356,
+      "step": 1330
+    },
+    {
+      "epoch": 0.574757281553398,
+      "grad_norm": 1.2402182817459106,
+      "learning_rate": 9.992839085823477e-05,
+      "loss": 0.7658806443214417,
+      "step": 1332
+    },
+    {
+      "epoch": 0.5756202804746494,
+      "grad_norm": 1.4143259525299072,
+      "learning_rate": 9.99270712227987e-05,
+      "loss": 0.8483052849769592,
+      "step": 1334
+    },
+    {
+      "epoch": 0.5764832793959007,
+      "grad_norm": 1.2387818098068237,
+      "learning_rate": 9.992573954767449e-05,
+      "loss": 0.8610434532165527,
+      "step": 1336
+    },
+    {
+      "epoch": 0.5773462783171521,
+      "grad_norm": 1.3307154178619385,
+      "learning_rate": 9.992439583318322e-05,
+      "loss": 0.8021210432052612,
+      "step": 1338
+    },
+    {
+      "epoch": 0.5782092772384034,
+      "grad_norm": 1.293459415435791,
+      "learning_rate": 9.992304007964896e-05,
+      "loss": 0.7536460757255554,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5790722761596548,
+      "grad_norm": 1.1508948802947998,
+      "learning_rate": 9.992167228739865e-05,
+      "loss": 0.7519120573997498,
+      "step": 1342
+    },
+    {
+      "epoch": 0.5799352750809061,
+      "grad_norm": 1.5906150341033936,
+      "learning_rate": 9.992029245676211e-05,
+      "loss": 0.784415066242218,
+      "step": 1344
+    },
+    {
+      "epoch": 0.5807982740021574,
+      "grad_norm": 1.1421746015548706,
+      "learning_rate": 9.99189005880721e-05,
+      "loss": 0.8217549324035645,
+      "step": 1346
+    },
+    {
+      "epoch": 0.5816612729234089,
+      "grad_norm": 1.0767277479171753,
+      "learning_rate": 9.991749668166422e-05,
+      "loss": 0.7446820735931396,
+      "step": 1348
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 1.147594928741455,
+      "learning_rate": 9.991608073787706e-05,
+      "loss": 0.8426011800765991,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5833872707659116,
+      "grad_norm": 1.6618242263793945,
+      "learning_rate": 9.991465275705206e-05,
+      "loss": 0.8185623288154602,
+      "step": 1352
+    },
+    {
+      "epoch": 0.5842502696871629,
+      "grad_norm": 1.414926290512085,
+      "learning_rate": 9.991321273953355e-05,
+      "loss": 0.7521756887435913,
+      "step": 1354
+    },
+    {
+      "epoch": 0.5851132686084143,
+      "grad_norm": 1.298245906829834,
+      "learning_rate": 9.991176068566882e-05,
+      "loss": 0.7517471313476562,
+      "step": 1356
+    },
+    {
+      "epoch": 0.5859762675296656,
+      "grad_norm": 1.3243110179901123,
+      "learning_rate": 9.9910296595808e-05,
+      "loss": 0.749305248260498,
+      "step": 1358
+    },
+    {
+      "epoch": 0.5868392664509169,
+      "grad_norm": 1.1953799724578857,
+      "learning_rate": 9.990882047030413e-05,
+      "loss": 0.6883649230003357,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5877022653721683,
+      "grad_norm": 1.3934388160705566,
+      "learning_rate": 9.990733230951322e-05,
+      "loss": 0.7859632968902588,
+      "step": 1362
+    },
+    {
+      "epoch": 0.5885652642934196,
+      "grad_norm": 1.2212340831756592,
+      "learning_rate": 9.990583211379409e-05,
+      "loss": 0.7313099503517151,
+      "step": 1364
+    },
+    {
+      "epoch": 0.589428263214671,
+      "grad_norm": 1.5374075174331665,
+      "learning_rate": 9.990431988350853e-05,
+      "loss": 0.8007960319519043,
+      "step": 1366
+    },
+    {
+      "epoch": 0.5902912621359223,
+      "grad_norm": 1.1826236248016357,
+      "learning_rate": 9.990279561902118e-05,
+      "loss": 0.773026168346405,
+      "step": 1368
+    },
+    {
+      "epoch": 0.5911542610571737,
+      "grad_norm": 1.1181561946868896,
+      "learning_rate": 9.990125932069964e-05,
+      "loss": 0.7469213604927063,
+      "step": 1370
+    },
+    {
+      "epoch": 0.592017259978425,
+      "grad_norm": 1.3735432624816895,
+      "learning_rate": 9.989971098891439e-05,
+      "loss": 0.7788950204849243,
+      "step": 1372
+    },
+    {
+      "epoch": 0.5928802588996763,
+      "grad_norm": 1.1906198263168335,
+      "learning_rate": 9.989815062403877e-05,
+      "loss": 0.8117855191230774,
+      "step": 1374
+    },
+    {
+      "epoch": 0.5937432578209277,
+      "grad_norm": 1.326940894126892,
+      "learning_rate": 9.989657822644907e-05,
+      "loss": 0.7536540627479553,
+      "step": 1376
+    },
+    {
+      "epoch": 0.594606256742179,
+      "grad_norm": 1.4508434534072876,
+      "learning_rate": 9.989499379652447e-05,
+      "loss": 0.860320508480072,
+      "step": 1378
+    },
+    {
+      "epoch": 0.5954692556634305,
+      "grad_norm": 1.114499568939209,
+      "learning_rate": 9.989339733464704e-05,
+      "loss": 0.749508798122406,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5963322545846818,
+      "grad_norm": 1.2856234312057495,
+      "learning_rate": 9.989178884120176e-05,
+      "loss": 0.7294815182685852,
+      "step": 1382
+    },
+    {
+      "epoch": 0.5971952535059332,
+      "grad_norm": 1.291913628578186,
+      "learning_rate": 9.989016831657652e-05,
+      "loss": 0.7797688245773315,
+      "step": 1384
+    },
+    {
+      "epoch": 0.5980582524271845,
+      "grad_norm": 1.1245452165603638,
+      "learning_rate": 9.988853576116208e-05,
+      "loss": 0.7824407815933228,
+      "step": 1386
+    },
+    {
+      "epoch": 0.5989212513484358,
+      "grad_norm": 1.2384979724884033,
+      "learning_rate": 9.988689117535215e-05,
+      "loss": 0.714794933795929,
+      "step": 1388
+    },
+    {
+      "epoch": 0.5997842502696872,
+      "grad_norm": 1.1945903301239014,
+      "learning_rate": 9.988523455954332e-05,
+      "loss": 0.7072597742080688,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6006472491909385,
+      "grad_norm": 1.3414266109466553,
+      "learning_rate": 9.988356591413504e-05,
+      "loss": 0.7075814008712769,
+      "step": 1392
+    },
+    {
+      "epoch": 0.6015102481121899,
+      "grad_norm": 1.4575660228729248,
+      "learning_rate": 9.988188523952973e-05,
+      "loss": 0.8237126469612122,
+      "step": 1394
+    },
+    {
+      "epoch": 0.6023732470334412,
+      "grad_norm": 1.3836476802825928,
+      "learning_rate": 9.988019253613265e-05,
+      "loss": 0.7991626858711243,
+      "step": 1396
+    },
+    {
+      "epoch": 0.6032362459546926,
+      "grad_norm": 1.2176212072372437,
+      "learning_rate": 9.987848780435201e-05,
+      "loss": 0.6936330199241638,
+      "step": 1398
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "grad_norm": 1.171294093132019,
+      "learning_rate": 9.98767710445989e-05,
+      "loss": 0.7834921479225159,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "eval_loss": 0.7866972088813782,
+      "eval_runtime": 836.0759,
+      "eval_samples_per_second": 2.464,
+      "eval_steps_per_second": 2.464,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6049622437971952,
+      "grad_norm": 1.5934456586837769,
+      "learning_rate": 9.987504225728727e-05,
+      "loss": 0.765119194984436,
+      "step": 1402
+    },
+    {
+      "epoch": 0.6058252427184466,
+      "grad_norm": 1.231372356414795,
+      "learning_rate": 9.987330144283407e-05,
+      "loss": 0.752061665058136,
+      "step": 1404
+    },
+    {
+      "epoch": 0.6066882416396979,
+      "grad_norm": 1.315215826034546,
+      "learning_rate": 9.987154860165903e-05,
+      "loss": 0.7475255727767944,
+      "step": 1406
+    },
+    {
+      "epoch": 0.6075512405609493,
+      "grad_norm": 1.2640653848648071,
+      "learning_rate": 9.986978373418488e-05,
+      "loss": 0.777019202709198,
+      "step": 1408
+    },
+    {
+      "epoch": 0.6084142394822006,
+      "grad_norm": 1.085493803024292,
+      "learning_rate": 9.98680068408372e-05,
+      "loss": 0.6682190299034119,
+      "step": 1410
+    },
+    {
+      "epoch": 0.609277238403452,
+      "grad_norm": 1.4247251749038696,
+      "learning_rate": 9.986621792204447e-05,
+      "loss": 0.7765674591064453,
+      "step": 1412
+    },
+    {
+      "epoch": 0.6101402373247033,
+      "grad_norm": 1.2993831634521484,
+      "learning_rate": 9.986441697823808e-05,
+      "loss": 0.7429938316345215,
+      "step": 1414
+    },
+    {
+      "epoch": 0.6110032362459547,
+      "grad_norm": 2.614980936050415,
+      "learning_rate": 9.986260400985233e-05,
+      "loss": 0.7838386297225952,
+      "step": 1416
+    },
+    {
+      "epoch": 0.6118662351672061,
+      "grad_norm": 1.4305615425109863,
+      "learning_rate": 9.98607790173244e-05,
+      "loss": 0.7679475545883179,
+      "step": 1418
+    },
+    {
+      "epoch": 0.6127292340884574,
+      "grad_norm": 1.1412850618362427,
+      "learning_rate": 9.98589420010944e-05,
+      "loss": 0.6889669895172119,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6135922330097088,
+      "grad_norm": 1.372313141822815,
+      "learning_rate": 9.98570929616053e-05,
+      "loss": 0.7659094333648682,
+      "step": 1422
+    },
+    {
+      "epoch": 0.6144552319309601,
+      "grad_norm": 1.2629581689834595,
+      "learning_rate": 9.985523189930297e-05,
+      "loss": 0.7404800653457642,
+      "step": 1424
+    },
+    {
+      "epoch": 0.6153182308522115,
+      "grad_norm": 1.5652254819869995,
+      "learning_rate": 9.985335881463623e-05,
+      "loss": 0.8082308769226074,
+      "step": 1426
+    },
+    {
+      "epoch": 0.6161812297734628,
+      "grad_norm": 1.2268856763839722,
+      "learning_rate": 9.985147370805675e-05,
+      "loss": 0.7773997187614441,
+      "step": 1428
+    },
+    {
+      "epoch": 0.6170442286947141,
+      "grad_norm": 1.2190957069396973,
+      "learning_rate": 9.984957658001912e-05,
+      "loss": 0.7412725687026978,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6179072276159655,
+      "grad_norm": 1.481990098953247,
+      "learning_rate": 9.984766743098081e-05,
+      "loss": 0.7257611751556396,
+      "step": 1432
+    },
+    {
+      "epoch": 0.6187702265372168,
+      "grad_norm": 1.0297027826309204,
+      "learning_rate": 9.984574626140223e-05,
+      "loss": 0.7151464819908142,
+      "step": 1434
+    },
+    {
+      "epoch": 0.6196332254584682,
+      "grad_norm": 1.2404571771621704,
+      "learning_rate": 9.984381307174663e-05,
+      "loss": 0.7855883240699768,
+      "step": 1436
+    },
+    {
+      "epoch": 0.6204962243797195,
+      "grad_norm": 1.2952802181243896,
+      "learning_rate": 9.984186786248023e-05,
+      "loss": 0.6360295414924622,
+      "step": 1438
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 1.5405724048614502,
+      "learning_rate": 9.983991063407206e-05,
+      "loss": 0.7280036807060242,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.303699254989624,
+      "learning_rate": 9.983794138699411e-05,
+      "loss": 0.7553068995475769,
+      "step": 1442
+    },
+    {
+      "epoch": 0.6230852211434735,
+      "grad_norm": 1.1452997922897339,
+      "learning_rate": 9.983596012172127e-05,
+      "loss": 0.7329047918319702,
+      "step": 1444
+    },
+    {
+      "epoch": 0.623948220064725,
+      "grad_norm": 1.2648253440856934,
+      "learning_rate": 9.983396683873133e-05,
+      "loss": 0.753168523311615,
+      "step": 1446
+    },
+    {
+      "epoch": 0.6248112189859762,
+      "grad_norm": 1.2095013856887817,
+      "learning_rate": 9.983196153850493e-05,
+      "loss": 0.7378705739974976,
+      "step": 1448
+    },
+    {
+      "epoch": 0.6256742179072277,
+      "grad_norm": 1.2855647802352905,
+      "learning_rate": 9.982994422152564e-05,
+      "loss": 0.7910448908805847,
+      "step": 1450
+    },
+    {
+      "epoch": 0.626537216828479,
+      "grad_norm": 1.3895999193191528,
+      "learning_rate": 9.982791488827994e-05,
+      "loss": 0.785302996635437,
+      "step": 1452
+    },
+    {
+      "epoch": 0.6274002157497303,
+      "grad_norm": 1.2398446798324585,
+      "learning_rate": 9.982587353925719e-05,
+      "loss": 0.7542029023170471,
+      "step": 1454
+    },
+    {
+      "epoch": 0.6282632146709817,
+      "grad_norm": 1.2903637886047363,
+      "learning_rate": 9.982382017494965e-05,
+      "loss": 0.8081737756729126,
+      "step": 1456
+    },
+    {
+      "epoch": 0.629126213592233,
+      "grad_norm": 1.223611831665039,
+      "learning_rate": 9.98217547958525e-05,
+      "loss": 0.7886892557144165,
+      "step": 1458
+    },
+    {
+      "epoch": 0.6299892125134844,
+      "grad_norm": 1.3036459684371948,
+      "learning_rate": 9.981967740246377e-05,
+      "loss": 0.844115138053894,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6308522114347357,
+      "grad_norm": 1.6421090364456177,
+      "learning_rate": 9.98175879952844e-05,
+      "loss": 0.7784068584442139,
+      "step": 1462
+    },
+    {
+      "epoch": 0.6317152103559871,
+      "grad_norm": 1.244330644607544,
+      "learning_rate": 9.981548657481828e-05,
+      "loss": 0.746979832649231,
+      "step": 1464
+    },
+    {
+      "epoch": 0.6325782092772384,
+      "grad_norm": 1.0323492288589478,
+      "learning_rate": 9.981337314157215e-05,
+      "loss": 0.6680153608322144,
+      "step": 1466
+    },
+    {
+      "epoch": 0.6334412081984897,
+      "grad_norm": 1.2238314151763916,
+      "learning_rate": 9.981124769605563e-05,
+      "loss": 0.7103193402290344,
+      "step": 1468
+    },
+    {
+      "epoch": 0.6343042071197411,
+      "grad_norm": 1.2647801637649536,
+      "learning_rate": 9.98091102387813e-05,
+      "loss": 0.7426751255989075,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6351672060409924,
+      "grad_norm": 1.1923259496688843,
+      "learning_rate": 9.980696077026456e-05,
+      "loss": 0.7664520144462585,
+      "step": 1472
+    },
+    {
+      "epoch": 0.6360302049622438,
+      "grad_norm": 1.0503894090652466,
+      "learning_rate": 9.980479929102377e-05,
+      "loss": 0.7348257899284363,
+      "step": 1474
+    },
+    {
+      "epoch": 0.6368932038834951,
+      "grad_norm": 1.2223190069198608,
+      "learning_rate": 9.980262580158014e-05,
+      "loss": 0.687703013420105,
+      "step": 1476
+    },
+    {
+      "epoch": 0.6377562028047465,
+      "grad_norm": 1.1469025611877441,
+      "learning_rate": 9.980044030245782e-05,
+      "loss": 0.7903051972389221,
+      "step": 1478
+    },
+    {
+      "epoch": 0.6386192017259978,
+      "grad_norm": 1.2581169605255127,
+      "learning_rate": 9.979824279418381e-05,
+      "loss": 0.7920540571212769,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6394822006472491,
+      "grad_norm": 1.2616536617279053,
+      "learning_rate": 9.979603327728806e-05,
+      "loss": 0.7030006647109985,
+      "step": 1482
+    },
+    {
+      "epoch": 0.6403451995685006,
+      "grad_norm": 1.3970606327056885,
+      "learning_rate": 9.979381175230335e-05,
+      "loss": 0.7489339709281921,
+      "step": 1484
+    },
+    {
+      "epoch": 0.6412081984897519,
+      "grad_norm": 1.0060384273529053,
+      "learning_rate": 9.979157821976542e-05,
+      "loss": 0.6733010411262512,
+      "step": 1486
+    },
+    {
+      "epoch": 0.6420711974110033,
+      "grad_norm": 1.4987449645996094,
+      "learning_rate": 9.978933268021286e-05,
+      "loss": 0.8221960663795471,
+      "step": 1488
+    },
+    {
+      "epoch": 0.6429341963322546,
+      "grad_norm": 1.2843966484069824,
+      "learning_rate": 9.978707513418719e-05,
+      "loss": 0.8829001188278198,
+      "step": 1490
+    },
+    {
+      "epoch": 0.643797195253506,
+      "grad_norm": 1.175879955291748,
+      "learning_rate": 9.978480558223278e-05,
+      "loss": 0.7605764269828796,
+      "step": 1492
+    },
+    {
+      "epoch": 0.6446601941747573,
+      "grad_norm": 1.1991835832595825,
+      "learning_rate": 9.978252402489692e-05,
+      "loss": 0.7618141174316406,
+      "step": 1494
+    },
+    {
+      "epoch": 0.6455231930960086,
+      "grad_norm": 1.167635202407837,
+      "learning_rate": 9.978023046272983e-05,
+      "loss": 0.7071146368980408,
+      "step": 1496
+    },
+    {
+      "epoch": 0.64638619201726,
+      "grad_norm": 1.263371229171753,
+      "learning_rate": 9.977792489628456e-05,
+      "loss": 0.7559816837310791,
+      "step": 1498
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 1.2108519077301025,
+      "learning_rate": 9.977560732611713e-05,
+      "loss": 0.7253944873809814,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "eval_loss": 0.778505802154541,
+      "eval_runtime": 836.2317,
+      "eval_samples_per_second": 2.463,
+      "eval_steps_per_second": 2.463,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6481121898597627,
+      "grad_norm": 1.4794813394546509,
+      "learning_rate": 9.977327775278636e-05,
+      "loss": 0.8212620615959167,
+      "step": 1502
+    },
+    {
+      "epoch": 0.648975188781014,
+      "grad_norm": 1.2120516300201416,
+      "learning_rate": 9.977093617685404e-05,
+      "loss": 0.7220476865768433,
+      "step": 1504
+    },
+    {
+      "epoch": 0.6498381877022654,
+      "grad_norm": 1.3129044771194458,
+      "learning_rate": 9.976858259888484e-05,
+      "loss": 0.7791266441345215,
+      "step": 1506
+    },
+    {
+      "epoch": 0.6507011866235167,
+      "grad_norm": 1.146490454673767,
+      "learning_rate": 9.976621701944628e-05,
+      "loss": 0.7052001357078552,
+      "step": 1508
+    },
+    {
+      "epoch": 0.651564185544768,
+      "grad_norm": 1.1903722286224365,
+      "learning_rate": 9.976383943910885e-05,
+      "loss": 0.7135450839996338,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6524271844660194,
+      "grad_norm": 1.4106701612472534,
+      "learning_rate": 9.976144985844589e-05,
+      "loss": 0.8114889860153198,
+      "step": 1512
+    },
+    {
+      "epoch": 0.6532901833872707,
+      "grad_norm": 1.245661973953247,
+      "learning_rate": 9.97590482780336e-05,
+      "loss": 0.7501562237739563,
+      "step": 1514
+    },
+    {
+      "epoch": 0.6541531823085222,
+      "grad_norm": 1.2918543815612793,
+      "learning_rate": 9.975663469845114e-05,
+      "loss": 0.7697334289550781,
+      "step": 1516
+    },
+    {
+      "epoch": 0.6550161812297735,
+      "grad_norm": 1.2699558734893799,
+      "learning_rate": 9.975420912028053e-05,
+      "loss": 0.7457168102264404,
+      "step": 1518
+    },
+    {
+      "epoch": 0.6558791801510249,
+      "grad_norm": 1.3968263864517212,
+      "learning_rate": 9.975177154410668e-05,
+      "loss": 0.8368204236030579,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6567421790722762,
+      "grad_norm": 1.2161848545074463,
+      "learning_rate": 9.974932197051741e-05,
+      "loss": 0.7355788350105286,
+      "step": 1522
+    },
+    {
+      "epoch": 0.6576051779935275,
+      "grad_norm": 1.129886507987976,
+      "learning_rate": 9.974686040010341e-05,
+      "loss": 0.8023449182510376,
+      "step": 1524
+    },
+    {
+      "epoch": 0.6584681769147789,
+      "grad_norm": 1.1114557981491089,
+      "learning_rate": 9.974438683345829e-05,
+      "loss": 0.7965474724769592,
+      "step": 1526
+    },
+    {
+      "epoch": 0.6593311758360302,
+      "grad_norm": 1.5741950273513794,
+      "learning_rate": 9.974190127117853e-05,
+      "loss": 0.7176838517189026,
+      "step": 1528
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 1.1439597606658936,
+      "learning_rate": 9.973940371386352e-05,
+      "loss": 0.7114462852478027,
+      "step": 1530
+    },
+    {
+      "epoch": 0.6610571736785329,
+      "grad_norm": 1.273659348487854,
+      "learning_rate": 9.973689416211553e-05,
+      "loss": 0.754712700843811,
+      "step": 1532
+    },
+    {
+      "epoch": 0.6619201725997842,
+      "grad_norm": 3.9874372482299805,
+      "learning_rate": 9.973437261653973e-05,
+      "loss": 0.6720641255378723,
+      "step": 1534
+    },
+    {
+      "epoch": 0.6627831715210356,
+      "grad_norm": 1.2506502866744995,
+      "learning_rate": 9.973183907774417e-05,
+      "loss": 0.793043851852417,
+      "step": 1536
+    },
+    {
+      "epoch": 0.6636461704422869,
+      "grad_norm": 1.43257737159729,
+      "learning_rate": 9.972929354633982e-05,
+      "loss": 0.7806380987167358,
+      "step": 1538
+    },
+    {
+      "epoch": 0.6645091693635383,
+      "grad_norm": 1.4794938564300537,
+      "learning_rate": 9.97267360229405e-05,
+      "loss": 0.7176088094711304,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6653721682847896,
+      "grad_norm": 1.2398169040679932,
+      "learning_rate": 9.972416650816297e-05,
+      "loss": 0.7145742774009705,
+      "step": 1542
+    },
+    {
+      "epoch": 0.666235167206041,
+      "grad_norm": 1.1309953927993774,
+      "learning_rate": 9.972158500262683e-05,
+      "loss": 0.8025617003440857,
+      "step": 1544
+    },
+    {
+      "epoch": 0.6670981661272923,
+      "grad_norm": 1.2479451894760132,
+      "learning_rate": 9.971899150695463e-05,
+      "loss": 0.7808589339256287,
+      "step": 1546
+    },
+    {
+      "epoch": 0.6679611650485436,
+      "grad_norm": 1.2538350820541382,
+      "learning_rate": 9.971638602177175e-05,
+      "loss": 0.7096936106681824,
+      "step": 1548
+    },
+    {
+      "epoch": 0.668824163969795,
+      "grad_norm": 1.1431525945663452,
+      "learning_rate": 9.97137685477065e-05,
+      "loss": 0.6529367566108704,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6696871628910464,
+      "grad_norm": 1.5966559648513794,
+      "learning_rate": 9.971113908539008e-05,
+      "loss": 0.7780346870422363,
+      "step": 1552
+    },
+    {
+      "epoch": 0.6705501618122978,
+      "grad_norm": 1.186475157737732,
+      "learning_rate": 9.970849763545658e-05,
+      "loss": 0.6889166831970215,
+      "step": 1554
+    },
+    {
+      "epoch": 0.6714131607335491,
+      "grad_norm": 1.1922476291656494,
+      "learning_rate": 9.970584419854295e-05,
+      "loss": 0.7154867649078369,
+      "step": 1556
+    },
+    {
+      "epoch": 0.6722761596548005,
+      "grad_norm": 1.30132257938385,
+      "learning_rate": 9.970317877528906e-05,
+      "loss": 0.7419366240501404,
+      "step": 1558
+    },
+    {
+      "epoch": 0.6731391585760518,
+      "grad_norm": 1.1539888381958008,
+      "learning_rate": 9.970050136633769e-05,
+      "loss": 0.7856602072715759,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6740021574973031,
+      "grad_norm": 1.3056161403656006,
+      "learning_rate": 9.969781197233445e-05,
+      "loss": 0.6834115386009216,
+      "step": 1562
+    },
+    {
+      "epoch": 0.6748651564185545,
+      "grad_norm": 1.2899249792099,
+      "learning_rate": 9.96951105939279e-05,
+      "loss": 0.8490727543830872,
+      "step": 1564
+    },
+    {
+      "epoch": 0.6757281553398058,
+      "grad_norm": 1.2182374000549316,
+      "learning_rate": 9.969239723176946e-05,
+      "loss": 0.7462526559829712,
+      "step": 1566
+    },
+    {
+      "epoch": 0.6765911542610572,
+      "grad_norm": 1.1231273412704468,
+      "learning_rate": 9.968967188651344e-05,
+      "loss": 0.7145209908485413,
+      "step": 1568
+    },
+    {
+      "epoch": 0.6774541531823085,
+      "grad_norm": 1.1776760816574097,
+      "learning_rate": 9.968693455881703e-05,
+      "loss": 0.7911707162857056,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6783171521035599,
+      "grad_norm": 1.3542319536209106,
+      "learning_rate": 9.968418524934035e-05,
+      "loss": 0.6946635246276855,
+      "step": 1572
+    },
+    {
+      "epoch": 0.6791801510248112,
+      "grad_norm": 1.3073060512542725,
+      "learning_rate": 9.96814239587464e-05,
+      "loss": 0.7597488164901733,
+      "step": 1574
+    },
+    {
+      "epoch": 0.6800431499460625,
+      "grad_norm": 1.3205567598342896,
+      "learning_rate": 9.967865068770099e-05,
+      "loss": 0.6763246655464172,
+      "step": 1576
+    },
+    {
+      "epoch": 0.6809061488673139,
+      "grad_norm": 1.1734344959259033,
+      "learning_rate": 9.967586543687295e-05,
+      "loss": 0.7560655474662781,
+      "step": 1578
+    },
+    {
+      "epoch": 0.6817691477885652,
+      "grad_norm": 1.445770025253296,
+      "learning_rate": 9.967306820693388e-05,
+      "loss": 0.8050205707550049,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6826321467098166,
+      "grad_norm": 1.1185686588287354,
+      "learning_rate": 9.967025899855836e-05,
+      "loss": 0.6628211140632629,
+      "step": 1582
+    },
+    {
+      "epoch": 0.683495145631068,
+      "grad_norm": 1.3831934928894043,
+      "learning_rate": 9.966743781242379e-05,
+      "loss": 0.7684114575386047,
+      "step": 1584
+    },
+    {
+      "epoch": 0.6843581445523194,
+      "grad_norm": 1.2417019605636597,
+      "learning_rate": 9.966460464921047e-05,
+      "loss": 0.7084140777587891,
+      "step": 1586
+    },
+    {
+      "epoch": 0.6852211434735707,
+      "grad_norm": 1.2138086557388306,
+      "learning_rate": 9.966175950960163e-05,
+      "loss": 0.6817399263381958,
+      "step": 1588
+    },
+    {
+      "epoch": 0.686084142394822,
+      "grad_norm": 1.399778962135315,
+      "learning_rate": 9.965890239428339e-05,
+      "loss": 0.8422354459762573,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6869471413160734,
+      "grad_norm": 1.4348714351654053,
+      "learning_rate": 9.965603330394468e-05,
+      "loss": 0.7432681322097778,
+      "step": 1592
+    },
+    {
+      "epoch": 0.6878101402373247,
+      "grad_norm": 1.192425012588501,
+      "learning_rate": 9.965315223927741e-05,
+      "loss": 0.7571184635162354,
+      "step": 1594
+    },
+    {
+      "epoch": 0.6886731391585761,
+      "grad_norm": 1.2834038734436035,
+      "learning_rate": 9.96502592009763e-05,
+      "loss": 0.802443265914917,
+      "step": 1596
+    },
+    {
+      "epoch": 0.6895361380798274,
+      "grad_norm": 1.1650444269180298,
+      "learning_rate": 9.964735418973901e-05,
+      "loss": 0.8113405704498291,
+      "step": 1598
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "grad_norm": 1.1714438199996948,
+      "learning_rate": 9.964443720626606e-05,
+      "loss": 0.7507118582725525,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "eval_loss": 0.7706249952316284,
+      "eval_runtime": 821.4894,
+      "eval_samples_per_second": 2.508,
+      "eval_steps_per_second": 2.508,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6912621359223301,
+      "grad_norm": 1.175459861755371,
+      "learning_rate": 9.964150825126088e-05,
+      "loss": 0.7422796487808228,
+      "step": 1602
+    },
+    {
+      "epoch": 0.6921251348435814,
+      "grad_norm": 1.6418036222457886,
+      "learning_rate": 9.963856732542978e-05,
+      "loss": 0.7125853300094604,
+      "step": 1604
+    },
+    {
+      "epoch": 0.6929881337648328,
+      "grad_norm": 1.3256275653839111,
+      "learning_rate": 9.963561442948193e-05,
+      "loss": 0.757859468460083,
+      "step": 1606
+    },
+    {
+      "epoch": 0.6938511326860841,
+      "grad_norm": 1.19981050491333,
+      "learning_rate": 9.963264956412944e-05,
+      "loss": 0.6849292516708374,
+      "step": 1608
+    },
+    {
+      "epoch": 0.6947141316073355,
+      "grad_norm": 1.0392169952392578,
+      "learning_rate": 9.962967273008723e-05,
+      "loss": 0.7636215090751648,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6955771305285868,
+      "grad_norm": 1.1106646060943604,
+      "learning_rate": 9.962668392807318e-05,
+      "loss": 0.7208617329597473,
+      "step": 1612
+    },
+    {
+      "epoch": 0.6964401294498382,
+      "grad_norm": 1.1569621562957764,
+      "learning_rate": 9.962368315880801e-05,
+      "loss": 0.671805739402771,
+      "step": 1614
+    },
+    {
+      "epoch": 0.6973031283710895,
+      "grad_norm": 1.2157769203186035,
+      "learning_rate": 9.962067042301537e-05,
+      "loss": 0.7648762464523315,
+      "step": 1616
+    },
+    {
+      "epoch": 0.6981661272923408,
+      "grad_norm": 1.4804017543792725,
+      "learning_rate": 9.961764572142173e-05,
+      "loss": 0.8490509390830994,
+      "step": 1618
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 1.0344431400299072,
+      "learning_rate": 9.961460905475651e-05,
+      "loss": 0.5950891971588135,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6998921251348436,
+      "grad_norm": 1.1109060049057007,
+      "learning_rate": 9.9611560423752e-05,
+      "loss": 0.7288329005241394,
+      "step": 1622
+    },
+    {
+      "epoch": 0.700755124056095,
+      "grad_norm": 1.096996545791626,
+      "learning_rate": 9.960849982914331e-05,
+      "loss": 0.7074542045593262,
+      "step": 1624
+    },
+    {
+      "epoch": 0.7016181229773463,
+      "grad_norm": 1.3109341859817505,
+      "learning_rate": 9.960542727166853e-05,
+      "loss": 0.7348865270614624,
+      "step": 1626
+    },
+    {
+      "epoch": 0.7024811218985976,
+      "grad_norm": 1.3402032852172852,
+      "learning_rate": 9.96023427520686e-05,
+      "loss": 0.7658320665359497,
+      "step": 1628
+    },
+    {
+      "epoch": 0.703344120819849,
+      "grad_norm": 1.3712561130523682,
+      "learning_rate": 9.959924627108732e-05,
+      "loss": 0.809951901435852,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7042071197411003,
+      "grad_norm": 1.2278292179107666,
+      "learning_rate": 9.959613782947139e-05,
+      "loss": 0.6834598779678345,
+      "step": 1632
+    },
+    {
+      "epoch": 0.7050701186623517,
+      "grad_norm": 1.0510832071304321,
+      "learning_rate": 9.95930174279704e-05,
+      "loss": 0.7416030764579773,
+      "step": 1634
+    },
+    {
+      "epoch": 0.705933117583603,
+      "grad_norm": 1.130991816520691,
+      "learning_rate": 9.958988506733684e-05,
+      "loss": 0.7304092645645142,
+      "step": 1636
+    },
+    {
+      "epoch": 0.7067961165048544,
+      "grad_norm": 1.3328672647476196,
+      "learning_rate": 9.958674074832603e-05,
+      "loss": 0.8230003118515015,
+      "step": 1638
+    },
+    {
+      "epoch": 0.7076591154261057,
+      "grad_norm": 1.3842110633850098,
+      "learning_rate": 9.958358447169625e-05,
+      "loss": 0.8413107991218567,
+      "step": 1640
+    },
+    {
+      "epoch": 0.708522114347357,
+      "grad_norm": 1.3143812417984009,
+      "learning_rate": 9.958041623820858e-05,
+      "loss": 0.77432781457901,
+      "step": 1642
+    },
+    {
+      "epoch": 0.7093851132686084,
+      "grad_norm": 1.4727009534835815,
+      "learning_rate": 9.957723604862704e-05,
+      "loss": 0.7563844323158264,
+      "step": 1644
+    },
+    {
+      "epoch": 0.7102481121898597,
+      "grad_norm": 1.1892327070236206,
+      "learning_rate": 9.957404390371854e-05,
+      "loss": 0.7085853219032288,
+      "step": 1646
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.124180555343628,
+      "learning_rate": 9.957083980425282e-05,
+      "loss": 0.6837730407714844,
+      "step": 1648
+    },
+    {
+      "epoch": 0.7119741100323624,
+      "grad_norm": 1.2224774360656738,
+      "learning_rate": 9.956762375100255e-05,
+      "loss": 0.7255740165710449,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7128371089536139,
+      "grad_norm": 1.360425591468811,
+      "learning_rate": 9.956439574474326e-05,
+      "loss": 0.7849710583686829,
+      "step": 1652
+    },
+    {
+      "epoch": 0.7137001078748652,
+      "grad_norm": 1.2818151712417603,
+      "learning_rate": 9.956115578625338e-05,
+      "loss": 0.7669665813446045,
+      "step": 1654
+    },
+    {
+      "epoch": 0.7145631067961165,
+      "grad_norm": 1.2415164709091187,
+      "learning_rate": 9.95579038763142e-05,
+      "loss": 0.7052890658378601,
+      "step": 1656
+    },
+    {
+      "epoch": 0.7154261057173679,
+      "grad_norm": 1.3983269929885864,
+      "learning_rate": 9.955464001570992e-05,
+      "loss": 0.8300023674964905,
+      "step": 1658
+    },
+    {
+      "epoch": 0.7162891046386192,
+      "grad_norm": 1.1591373682022095,
+      "learning_rate": 9.955136420522759e-05,
+      "loss": 0.7742894887924194,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7171521035598706,
+      "grad_norm": 1.2503128051757812,
+      "learning_rate": 9.954807644565715e-05,
+      "loss": 0.8458141684532166,
+      "step": 1662
+    },
+    {
+      "epoch": 0.7180151024811219,
+      "grad_norm": 1.2954912185668945,
+      "learning_rate": 9.954477673779146e-05,
+      "loss": 0.7044742107391357,
+      "step": 1664
+    },
+    {
+      "epoch": 0.7188781014023733,
+      "grad_norm": 1.1669788360595703,
+      "learning_rate": 9.954146508242619e-05,
+      "loss": 0.7917183041572571,
+      "step": 1666
+    },
+    {
+      "epoch": 0.7197411003236246,
+      "grad_norm": 1.1466871500015259,
+      "learning_rate": 9.953814148035996e-05,
+      "loss": 0.7174562811851501,
+      "step": 1668
+    },
+    {
+      "epoch": 0.7206040992448759,
+      "grad_norm": 1.367224097251892,
+      "learning_rate": 9.953480593239421e-05,
+      "loss": 0.8925880193710327,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7214670981661273,
+      "grad_norm": 1.049497365951538,
+      "learning_rate": 9.953145843933334e-05,
+      "loss": 0.70949387550354,
+      "step": 1672
+    },
+    {
+      "epoch": 0.7223300970873786,
+      "grad_norm": 0.9995084404945374,
+      "learning_rate": 9.952809900198455e-05,
+      "loss": 0.6731935143470764,
+      "step": 1674
+    },
+    {
+      "epoch": 0.72319309600863,
+      "grad_norm": 1.100899577140808,
+      "learning_rate": 9.952472762115794e-05,
+      "loss": 0.7316275835037231,
+      "step": 1676
+    },
+    {
+      "epoch": 0.7240560949298813,
+      "grad_norm": 1.2594135999679565,
+      "learning_rate": 9.952134429766655e-05,
+      "loss": 0.7379520535469055,
+      "step": 1678
+    },
+    {
+      "epoch": 0.7249190938511327,
+      "grad_norm": 1.3124911785125732,
+      "learning_rate": 9.951794903232621e-05,
+      "loss": 0.7072247266769409,
+      "step": 1680
+    },
+    {
+      "epoch": 0.725782092772384,
+      "grad_norm": 1.212144374847412,
+      "learning_rate": 9.95145418259557e-05,
+      "loss": 0.745680034160614,
+      "step": 1682
+    },
+    {
+      "epoch": 0.7266450916936353,
+      "grad_norm": 1.3913586139678955,
+      "learning_rate": 9.951112267937663e-05,
+      "loss": 0.796852707862854,
+      "step": 1684
+    },
+    {
+      "epoch": 0.7275080906148867,
+      "grad_norm": 1.3227289915084839,
+      "learning_rate": 9.950769159341353e-05,
+      "loss": 0.700892984867096,
+      "step": 1686
+    },
+    {
+      "epoch": 0.728371089536138,
+      "grad_norm": 1.4656381607055664,
+      "learning_rate": 9.950424856889378e-05,
+      "loss": 0.7973095178604126,
+      "step": 1688
+    },
+    {
+      "epoch": 0.7292340884573895,
+      "grad_norm": 1.1698973178863525,
+      "learning_rate": 9.950079360664766e-05,
+      "loss": 0.7811378836631775,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7300970873786408,
+      "grad_norm": 1.201695203781128,
+      "learning_rate": 9.949732670750831e-05,
+      "loss": 0.753012478351593,
+      "step": 1692
+    },
+    {
+      "epoch": 0.7309600862998922,
+      "grad_norm": 1.3465325832366943,
+      "learning_rate": 9.949384787231175e-05,
+      "loss": 0.7620642781257629,
+      "step": 1694
+    },
+    {
+      "epoch": 0.7318230852211435,
+      "grad_norm": 1.2191137075424194,
+      "learning_rate": 9.94903571018969e-05,
+      "loss": 0.7479873299598694,
+      "step": 1696
+    },
+    {
+      "epoch": 0.7326860841423948,
+      "grad_norm": 1.1412187814712524,
+      "learning_rate": 9.948685439710554e-05,
+      "loss": 0.7327720522880554,
+      "step": 1698
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "grad_norm": 1.310327410697937,
+      "learning_rate": 9.948333975878233e-05,
+      "loss": 0.761475682258606,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "eval_loss": 0.7649155259132385,
+      "eval_runtime": 828.3542,
+      "eval_samples_per_second": 2.487,
+      "eval_steps_per_second": 2.487,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7344120819848975,
+      "grad_norm": 1.3031405210494995,
+      "learning_rate": 9.947981318777482e-05,
+      "loss": 0.7564467191696167,
+      "step": 1702
+    },
+    {
+      "epoch": 0.7352750809061489,
+      "grad_norm": 1.2672377824783325,
+      "learning_rate": 9.94762746849334e-05,
+      "loss": 0.7689576745033264,
+      "step": 1704
+    },
+    {
+      "epoch": 0.7361380798274002,
+      "grad_norm": 1.1159595251083374,
+      "learning_rate": 9.947272425111138e-05,
+      "loss": 0.7923810482025146,
+      "step": 1706
+    },
+    {
+      "epoch": 0.7370010787486516,
+      "grad_norm": 1.1190921068191528,
+      "learning_rate": 9.946916188716495e-05,
+      "loss": 0.6540790796279907,
+      "step": 1708
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 1.373832106590271,
+      "learning_rate": 9.946558759395312e-05,
+      "loss": 0.7267473936080933,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7387270765911542,
+      "grad_norm": 1.2346374988555908,
+      "learning_rate": 9.946200137233785e-05,
+      "loss": 0.7693060636520386,
+      "step": 1712
+    },
+    {
+      "epoch": 0.7395900755124056,
+      "grad_norm": 1.1629668474197388,
+      "learning_rate": 9.945840322318391e-05,
+      "loss": 0.7751407027244568,
+      "step": 1714
+    },
+    {
+      "epoch": 0.7404530744336569,
+      "grad_norm": 1.2268708944320679,
+      "learning_rate": 9.945479314735899e-05,
+      "loss": 0.7798545360565186,
+      "step": 1716
+    },
+    {
+      "epoch": 0.7413160733549083,
+      "grad_norm": 0.9968738555908203,
+      "learning_rate": 9.945117114573366e-05,
+      "loss": 0.6128867268562317,
+      "step": 1718
+    },
+    {
+      "epoch": 0.7421790722761596,
+      "grad_norm": 1.2135992050170898,
+      "learning_rate": 9.944753721918133e-05,
+      "loss": 0.7536954283714294,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7430420711974111,
+      "grad_norm": 1.1361218690872192,
+      "learning_rate": 9.94438913685783e-05,
+      "loss": 0.7034479379653931,
+      "step": 1722
+    },
+    {
+      "epoch": 0.7439050701186624,
+      "grad_norm": 1.0728967189788818,
+      "learning_rate": 9.944023359480378e-05,
+      "loss": 0.7285382747650146,
+      "step": 1724
+    },
+    {
+      "epoch": 0.7447680690399137,
+      "grad_norm": 1.3613945245742798,
+      "learning_rate": 9.94365638987398e-05,
+      "loss": 0.7865195274353027,
+      "step": 1726
+    },
+    {
+      "epoch": 0.7456310679611651,
+      "grad_norm": 1.0985898971557617,
+      "learning_rate": 9.94328822812713e-05,
+      "loss": 0.7511224746704102,
+      "step": 1728
+    },
+    {
+      "epoch": 0.7464940668824164,
+      "grad_norm": 1.1506208181381226,
+      "learning_rate": 9.942918874328606e-05,
+      "loss": 0.732453465461731,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7473570658036678,
+      "grad_norm": 1.0995100736618042,
+      "learning_rate": 9.94254832856748e-05,
+      "loss": 0.702409029006958,
+      "step": 1732
+    },
+    {
+      "epoch": 0.7482200647249191,
+      "grad_norm": 1.0075604915618896,
+      "learning_rate": 9.942176590933106e-05,
+      "loss": 0.7515703439712524,
+      "step": 1734
+    },
+    {
+      "epoch": 0.7490830636461704,
+      "grad_norm": 1.3360812664031982,
+      "learning_rate": 9.941803661515126e-05,
+      "loss": 0.6910237073898315,
+      "step": 1736
+    },
+    {
+      "epoch": 0.7499460625674218,
+      "grad_norm": 1.0172319412231445,
+      "learning_rate": 9.941429540403471e-05,
+      "loss": 0.7185606956481934,
+      "step": 1738
+    },
+    {
+      "epoch": 0.7508090614886731,
+      "grad_norm": 1.2721658945083618,
+      "learning_rate": 9.941054227688358e-05,
+      "loss": 0.7136536836624146,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7516720604099245,
+      "grad_norm": 1.0775413513183594,
+      "learning_rate": 9.940677723460292e-05,
+      "loss": 0.7595619559288025,
+      "step": 1742
+    },
+    {
+      "epoch": 0.7525350593311758,
+      "grad_norm": 1.3436479568481445,
+      "learning_rate": 9.940300027810067e-05,
+      "loss": 0.7602618336677551,
+      "step": 1744
+    },
+    {
+      "epoch": 0.7533980582524272,
+      "grad_norm": 1.2611958980560303,
+      "learning_rate": 9.93992114082876e-05,
+      "loss": 0.7954604029655457,
+      "step": 1746
+    },
+    {
+      "epoch": 0.7542610571736785,
+      "grad_norm": 1.2794841527938843,
+      "learning_rate": 9.93954106260774e-05,
+      "loss": 0.7661190629005432,
+      "step": 1748
+    },
+    {
+      "epoch": 0.7551240560949298,
+      "grad_norm": 1.3042595386505127,
+      "learning_rate": 9.939159793238661e-05,
+      "loss": 0.6855312585830688,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7559870550161812,
+      "grad_norm": 1.2799923419952393,
+      "learning_rate": 9.938777332813463e-05,
+      "loss": 0.7970905900001526,
+      "step": 1752
+    },
+    {
+      "epoch": 0.7568500539374325,
+      "grad_norm": 1.169205904006958,
+      "learning_rate": 9.938393681424375e-05,
+      "loss": 0.7072843313217163,
+      "step": 1754
+    },
+    {
+      "epoch": 0.757713052858684,
+      "grad_norm": 1.3833354711532593,
+      "learning_rate": 9.938008839163913e-05,
+      "loss": 0.7134629487991333,
+      "step": 1756
+    },
+    {
+      "epoch": 0.7585760517799353,
+      "grad_norm": 1.223452091217041,
+      "learning_rate": 9.93762280612488e-05,
+      "loss": 0.7873107194900513,
+      "step": 1758
+    },
+    {
+      "epoch": 0.7594390507011867,
+      "grad_norm": 1.2740365266799927,
+      "learning_rate": 9.937235582400367e-05,
+      "loss": 0.7680654525756836,
+      "step": 1760
+    },
+    {
+      "epoch": 0.760302049622438,
+      "grad_norm": 1.2564697265625,
+      "learning_rate": 9.93684716808375e-05,
+      "loss": 0.734126627445221,
+      "step": 1762
+    },
+    {
+      "epoch": 0.7611650485436893,
+      "grad_norm": 1.3858847618103027,
+      "learning_rate": 9.936457563268694e-05,
+      "loss": 0.7972320914268494,
+      "step": 1764
+    },
+    {
+      "epoch": 0.7620280474649407,
+      "grad_norm": 1.2705003023147583,
+      "learning_rate": 9.93606676804915e-05,
+      "loss": 0.7904276847839355,
+      "step": 1766
+    },
+    {
+      "epoch": 0.762891046386192,
+      "grad_norm": 1.210766077041626,
+      "learning_rate": 9.935674782519358e-05,
+      "loss": 0.7542425990104675,
+      "step": 1768
+    },
+    {
+      "epoch": 0.7637540453074434,
+      "grad_norm": 1.4367541074752808,
+      "learning_rate": 9.93528160677384e-05,
+      "loss": 0.7975004315376282,
+      "step": 1770
+    },
+    {
+      "epoch": 0.7646170442286947,
+      "grad_norm": 1.0994079113006592,
+      "learning_rate": 9.934887240907414e-05,
+      "loss": 0.7537807822227478,
+      "step": 1772
+    },
+    {
+      "epoch": 0.7654800431499461,
+      "grad_norm": 1.111660122871399,
+      "learning_rate": 9.934491685015174e-05,
+      "loss": 0.7333855628967285,
+      "step": 1774
+    },
+    {
+      "epoch": 0.7663430420711974,
+      "grad_norm": 1.2879043817520142,
+      "learning_rate": 9.934094939192508e-05,
+      "loss": 0.7472840547561646,
+      "step": 1776
+    },
+    {
+      "epoch": 0.7672060409924487,
+      "grad_norm": 1.3618478775024414,
+      "learning_rate": 9.933697003535094e-05,
+      "loss": 0.7644904255867004,
+      "step": 1778
+    },
+    {
+      "epoch": 0.7680690399137001,
+      "grad_norm": 1.1235666275024414,
+      "learning_rate": 9.933297878138887e-05,
+      "loss": 0.7872052192687988,
+      "step": 1780
+    },
+    {
+      "epoch": 0.7689320388349514,
+      "grad_norm": 1.3741775751113892,
+      "learning_rate": 9.932897563100136e-05,
+      "loss": 0.7343124747276306,
+      "step": 1782
+    },
+    {
+      "epoch": 0.7697950377562028,
+      "grad_norm": 1.2115039825439453,
+      "learning_rate": 9.932496058515375e-05,
+      "loss": 0.7486474514007568,
+      "step": 1784
+    },
+    {
+      "epoch": 0.7706580366774541,
+      "grad_norm": 1.183457851409912,
+      "learning_rate": 9.932093364481426e-05,
+      "loss": 0.7333025932312012,
+      "step": 1786
+    },
+    {
+      "epoch": 0.7715210355987056,
+      "grad_norm": 1.2841869592666626,
+      "learning_rate": 9.931689481095394e-05,
+      "loss": 0.7241485118865967,
+      "step": 1788
+    },
+    {
+      "epoch": 0.7723840345199569,
+      "grad_norm": 1.2312977313995361,
+      "learning_rate": 9.931284408454678e-05,
+      "loss": 0.7510396242141724,
+      "step": 1790
+    },
+    {
+      "epoch": 0.7732470334412082,
+      "grad_norm": 1.144895315170288,
+      "learning_rate": 9.930878146656956e-05,
+      "loss": 0.7108346819877625,
+      "step": 1792
+    },
+    {
+      "epoch": 0.7741100323624596,
+      "grad_norm": 1.18603515625,
+      "learning_rate": 9.9304706958002e-05,
+      "loss": 0.7687607407569885,
+      "step": 1794
+    },
+    {
+      "epoch": 0.7749730312837109,
+      "grad_norm": 1.2827935218811035,
+      "learning_rate": 9.93006205598266e-05,
+      "loss": 0.7826682329177856,
+      "step": 1796
+    },
+    {
+      "epoch": 0.7758360302049623,
+      "grad_norm": 1.164852261543274,
+      "learning_rate": 9.929652227302881e-05,
+      "loss": 0.6970428824424744,
+      "step": 1798
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 1.0439956188201904,
+      "learning_rate": 9.92924120985969e-05,
+      "loss": 0.7238826751708984,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "eval_loss": 0.7598537802696228,
+      "eval_runtime": 838.9645,
+      "eval_samples_per_second": 2.455,
+      "eval_steps_per_second": 2.455,
+      "step": 1800
+    },
+    {
+      "epoch": 0.777562028047465,
+      "grad_norm": 1.2464938163757324,
+      "learning_rate": 9.928829003752202e-05,
+      "loss": 0.7723641395568848,
+      "step": 1802
+    },
+    {
+      "epoch": 0.7784250269687163,
+      "grad_norm": 1.2445050477981567,
+      "learning_rate": 9.92841560907982e-05,
+      "loss": 0.7154937982559204,
+      "step": 1804
+    },
+    {
+      "epoch": 0.7792880258899676,
+      "grad_norm": 1.2235661745071411,
+      "learning_rate": 9.928001025942231e-05,
+      "loss": 0.8325800895690918,
+      "step": 1806
+    },
+    {
+      "epoch": 0.780151024811219,
+      "grad_norm": 1.268066644668579,
+      "learning_rate": 9.927585254439409e-05,
+      "loss": 0.7093122601509094,
+      "step": 1808
+    },
+    {
+      "epoch": 0.7810140237324703,
+      "grad_norm": 1.1731390953063965,
+      "learning_rate": 9.927168294671618e-05,
+      "loss": 0.7601775527000427,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7818770226537217,
+      "grad_norm": 1.0685608386993408,
+      "learning_rate": 9.926750146739403e-05,
+      "loss": 0.6889236569404602,
+      "step": 1812
+    },
+    {
+      "epoch": 0.782740021574973,
+      "grad_norm": 1.1098639965057373,
+      "learning_rate": 9.926330810743602e-05,
+      "loss": 0.7397196888923645,
+      "step": 1814
+    },
+    {
+      "epoch": 0.7836030204962244,
+      "grad_norm": 1.3606436252593994,
+      "learning_rate": 9.925910286785332e-05,
+      "loss": 0.7180029153823853,
+      "step": 1816
+    },
+    {
+      "epoch": 0.7844660194174757,
+      "grad_norm": 1.143418550491333,
+      "learning_rate": 9.925488574966004e-05,
+      "loss": 0.7039036750793457,
+      "step": 1818
+    },
+    {
+      "epoch": 0.785329018338727,
+      "grad_norm": 1.180968999862671,
+      "learning_rate": 9.92506567538731e-05,
+      "loss": 0.741872251033783,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7861920172599784,
+      "grad_norm": 1.1953548192977905,
+      "learning_rate": 9.924641588151231e-05,
+      "loss": 0.7580198049545288,
+      "step": 1822
+    },
+    {
+      "epoch": 0.7870550161812297,
+      "grad_norm": 1.3049067258834839,
+      "learning_rate": 9.924216313360033e-05,
+      "loss": 0.7479216456413269,
+      "step": 1824
+    },
+    {
+      "epoch": 0.7879180151024812,
+      "grad_norm": 1.3962669372558594,
+      "learning_rate": 9.92378985111627e-05,
+      "loss": 0.7382357716560364,
+      "step": 1826
+    },
+    {
+      "epoch": 0.7887810140237325,
+      "grad_norm": 1.1519217491149902,
+      "learning_rate": 9.92336220152278e-05,
+      "loss": 0.6356467604637146,
+      "step": 1828
+    },
+    {
+      "epoch": 0.7896440129449838,
+      "grad_norm": 1.2544089555740356,
+      "learning_rate": 9.922933364682689e-05,
+      "loss": 0.7674193978309631,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7905070118662352,
+      "grad_norm": 1.1358295679092407,
+      "learning_rate": 9.922503340699412e-05,
+      "loss": 0.7083898782730103,
+      "step": 1832
+    },
+    {
+      "epoch": 0.7913700107874865,
+      "grad_norm": 1.1744481325149536,
+      "learning_rate": 9.922072129676644e-05,
+      "loss": 0.6273066401481628,
+      "step": 1834
+    },
+    {
+      "epoch": 0.7922330097087379,
+      "grad_norm": 1.20509672164917,
+      "learning_rate": 9.92163973171837e-05,
+      "loss": 0.808181643486023,
+      "step": 1836
+    },
+    {
+      "epoch": 0.7930960086299892,
+      "grad_norm": 1.2035597562789917,
+      "learning_rate": 9.921206146928863e-05,
+      "loss": 0.6631553769111633,
+      "step": 1838
+    },
+    {
+      "epoch": 0.7939590075512406,
+      "grad_norm": 1.058695912361145,
+      "learning_rate": 9.920771375412678e-05,
+      "loss": 0.72016841173172,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7948220064724919,
+      "grad_norm": 1.035791039466858,
+      "learning_rate": 9.92033541727466e-05,
+      "loss": 0.7240060567855835,
+      "step": 1842
+    },
+    {
+      "epoch": 0.7956850053937432,
+      "grad_norm": 1.1845753192901611,
+      "learning_rate": 9.919898272619935e-05,
+      "loss": 0.743224561214447,
+      "step": 1844
+    },
+    {
+      "epoch": 0.7965480043149946,
+      "grad_norm": 1.2942636013031006,
+      "learning_rate": 9.919459941553922e-05,
+      "loss": 0.7064419388771057,
+      "step": 1846
+    },
+    {
+      "epoch": 0.7974110032362459,
+      "grad_norm": 1.2736715078353882,
+      "learning_rate": 9.91902042418232e-05,
+      "loss": 0.805932343006134,
+      "step": 1848
+    },
+    {
+      "epoch": 0.7982740021574973,
+      "grad_norm": 1.2803614139556885,
+      "learning_rate": 9.918579720611119e-05,
+      "loss": 0.8050802946090698,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7991370010787486,
+      "grad_norm": 1.2225072383880615,
+      "learning_rate": 9.91813783094659e-05,
+      "loss": 0.7013180255889893,
+      "step": 1852
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.3375571966171265,
+      "learning_rate": 9.917694755295294e-05,
+      "loss": 0.7415283918380737,
+      "step": 1854
+    },
+    {
+      "epoch": 0.8008629989212513,
+      "grad_norm": 1.2209177017211914,
+      "learning_rate": 9.917250493764079e-05,
+      "loss": 0.7264692783355713,
+      "step": 1856
+    },
+    {
+      "epoch": 0.8017259978425026,
+      "grad_norm": 1.1158864498138428,
+      "learning_rate": 9.916805046460074e-05,
+      "loss": 0.7083719372749329,
+      "step": 1858
+    },
+    {
+      "epoch": 0.8025889967637541,
+      "grad_norm": 1.171000361442566,
+      "learning_rate": 9.916358413490696e-05,
+      "loss": 0.820396900177002,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8034519956850054,
+      "grad_norm": 0.9942941069602966,
+      "learning_rate": 9.91591059496365e-05,
+      "loss": 0.6754014492034912,
+      "step": 1862
+    },
+    {
+      "epoch": 0.8043149946062568,
+      "grad_norm": 1.239795207977295,
+      "learning_rate": 9.915461590986926e-05,
+      "loss": 0.813154399394989,
+      "step": 1864
+    },
+    {
+      "epoch": 0.8051779935275081,
+      "grad_norm": 1.076019525527954,
+      "learning_rate": 9.915011401668796e-05,
+      "loss": 0.745580792427063,
+      "step": 1866
+    },
+    {
+      "epoch": 0.8060409924487595,
+      "grad_norm": 1.2134130001068115,
+      "learning_rate": 9.914560027117826e-05,
+      "loss": 0.7564949989318848,
+      "step": 1868
+    },
+    {
+      "epoch": 0.8069039913700108,
+      "grad_norm": 1.1774994134902954,
+      "learning_rate": 9.914107467442859e-05,
+      "loss": 0.665183424949646,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8077669902912621,
+      "grad_norm": 1.0606465339660645,
+      "learning_rate": 9.91365372275303e-05,
+      "loss": 0.7597744464874268,
+      "step": 1872
+    },
+    {
+      "epoch": 0.8086299892125135,
+      "grad_norm": 1.397161841392517,
+      "learning_rate": 9.913198793157757e-05,
+      "loss": 0.7453591227531433,
+      "step": 1874
+    },
+    {
+      "epoch": 0.8094929881337648,
+      "grad_norm": 1.250003695487976,
+      "learning_rate": 9.912742678766742e-05,
+      "loss": 0.715792179107666,
+      "step": 1876
+    },
+    {
+      "epoch": 0.8103559870550162,
+      "grad_norm": 1.2343473434448242,
+      "learning_rate": 9.912285379689979e-05,
+      "loss": 0.7094268798828125,
+      "step": 1878
+    },
+    {
+      "epoch": 0.8112189859762675,
+      "grad_norm": 1.453764796257019,
+      "learning_rate": 9.911826896037739e-05,
+      "loss": 0.6652816534042358,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8120819848975189,
+      "grad_norm": 1.030903935432434,
+      "learning_rate": 9.911367227920587e-05,
+      "loss": 0.6764529347419739,
+      "step": 1882
+    },
+    {
+      "epoch": 0.8129449838187702,
+      "grad_norm": 1.2725969552993774,
+      "learning_rate": 9.91090637544937e-05,
+      "loss": 0.7043389678001404,
+      "step": 1884
+    },
+    {
+      "epoch": 0.8138079827400215,
+      "grad_norm": 1.1610769033432007,
+      "learning_rate": 9.910444338735216e-05,
+      "loss": 0.6960558295249939,
+      "step": 1886
+    },
+    {
+      "epoch": 0.8146709816612729,
+      "grad_norm": 1.2049180269241333,
+      "learning_rate": 9.909981117889548e-05,
+      "loss": 0.8029319643974304,
+      "step": 1888
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 1.1671873331069946,
+      "learning_rate": 9.909516713024068e-05,
+      "loss": 0.683114767074585,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8163969795037757,
+      "grad_norm": 1.247768759727478,
+      "learning_rate": 9.909051124250764e-05,
+      "loss": 0.7193703055381775,
+      "step": 1892
+    },
+    {
+      "epoch": 0.817259978425027,
+      "grad_norm": 1.1376357078552246,
+      "learning_rate": 9.908584351681911e-05,
+      "loss": 0.7957084774971008,
+      "step": 1894
+    },
+    {
+      "epoch": 0.8181229773462784,
+      "grad_norm": 1.1918323040008545,
+      "learning_rate": 9.90811639543007e-05,
+      "loss": 0.7168112993240356,
+      "step": 1896
+    },
+    {
+      "epoch": 0.8189859762675297,
+      "grad_norm": 1.1249650716781616,
+      "learning_rate": 9.907647255608087e-05,
+      "loss": 0.7519245147705078,
+      "step": 1898
+    },
+    {
+      "epoch": 0.819848975188781,
+      "grad_norm": 1.0688576698303223,
+      "learning_rate": 9.907176932329092e-05,
+      "loss": 0.7496176362037659,
+      "step": 1900
+    },
+    {
+      "epoch": 0.819848975188781,
+      "eval_loss": 0.7533769607543945,
+      "eval_runtime": 830.2894,
+      "eval_samples_per_second": 2.481,
+      "eval_steps_per_second": 2.481,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8207119741100324,
+      "grad_norm": 0.9264270663261414,
+      "learning_rate": 9.906705425706499e-05,
+      "loss": 0.639653205871582,
+      "step": 1902
+    },
+    {
+      "epoch": 0.8215749730312837,
+      "grad_norm": 1.2231628894805908,
+      "learning_rate": 9.906232735854016e-05,
+      "loss": 0.7555551528930664,
+      "step": 1904
+    },
+    {
+      "epoch": 0.8224379719525351,
+      "grad_norm": 1.3369156122207642,
+      "learning_rate": 9.905758862885624e-05,
+      "loss": 0.7113592028617859,
+      "step": 1906
+    },
+    {
+      "epoch": 0.8233009708737864,
+      "grad_norm": 1.217238187789917,
+      "learning_rate": 9.905283806915597e-05,
+      "loss": 0.6823481321334839,
+      "step": 1908
+    },
+    {
+      "epoch": 0.8241639697950378,
+      "grad_norm": 1.2462831735610962,
+      "learning_rate": 9.904807568058495e-05,
+      "loss": 0.7347100377082825,
+      "step": 1910
+    },
+    {
+      "epoch": 0.8250269687162891,
+      "grad_norm": 1.2507221698760986,
+      "learning_rate": 9.904330146429157e-05,
+      "loss": 0.7981513738632202,
+      "step": 1912
+    },
+    {
+      "epoch": 0.8258899676375404,
+      "grad_norm": 1.2246814966201782,
+      "learning_rate": 9.903851542142715e-05,
+      "loss": 0.759779155254364,
+      "step": 1914
+    },
+    {
+      "epoch": 0.8267529665587918,
+      "grad_norm": 1.1746087074279785,
+      "learning_rate": 9.903371755314579e-05,
+      "loss": 0.741083562374115,
+      "step": 1916
+    },
+    {
+      "epoch": 0.8276159654800431,
+      "grad_norm": 1.1913539171218872,
+      "learning_rate": 9.902890786060448e-05,
+      "loss": 0.7491101622581482,
+      "step": 1918
+    },
+    {
+      "epoch": 0.8284789644012945,
+      "grad_norm": 1.2342501878738403,
+      "learning_rate": 9.902408634496307e-05,
+      "loss": 0.7655978202819824,
+      "step": 1920
+    },
+    {
+      "epoch": 0.8293419633225458,
+      "grad_norm": 1.075892686843872,
+      "learning_rate": 9.901925300738424e-05,
+      "loss": 0.7199848890304565,
+      "step": 1922
+    },
+    {
+      "epoch": 0.8302049622437971,
+      "grad_norm": 1.1517611742019653,
+      "learning_rate": 9.901440784903353e-05,
+      "loss": 0.8325693011283875,
+      "step": 1924
+    },
+    {
+      "epoch": 0.8310679611650486,
+      "grad_norm": 1.2084628343582153,
+      "learning_rate": 9.900955087107933e-05,
+      "loss": 0.7674157023429871,
+      "step": 1926
+    },
+    {
+      "epoch": 0.8319309600862999,
+      "grad_norm": 1.334679365158081,
+      "learning_rate": 9.900468207469287e-05,
+      "loss": 0.7415181398391724,
+      "step": 1928
+    },
+    {
+      "epoch": 0.8327939590075513,
+      "grad_norm": 1.0505887269973755,
+      "learning_rate": 9.899980146104824e-05,
+      "loss": 0.672336220741272,
+      "step": 1930
+    },
+    {
+      "epoch": 0.8336569579288026,
+      "grad_norm": 1.415797233581543,
+      "learning_rate": 9.899490903132238e-05,
+      "loss": 0.8077969551086426,
+      "step": 1932
+    },
+    {
+      "epoch": 0.834519956850054,
+      "grad_norm": 1.1793439388275146,
+      "learning_rate": 9.899000478669507e-05,
+      "loss": 0.8053045272827148,
+      "step": 1934
+    },
+    {
+      "epoch": 0.8353829557713053,
+      "grad_norm": 1.196115493774414,
+      "learning_rate": 9.898508872834896e-05,
+      "loss": 0.7585914731025696,
+      "step": 1936
+    },
+    {
+      "epoch": 0.8362459546925566,
+      "grad_norm": 1.2181763648986816,
+      "learning_rate": 9.898016085746953e-05,
+      "loss": 0.691072940826416,
+      "step": 1938
+    },
+    {
+      "epoch": 0.837108953613808,
+      "grad_norm": 1.2929240465164185,
+      "learning_rate": 9.897522117524512e-05,
+      "loss": 0.7723121643066406,
+      "step": 1940
+    },
+    {
+      "epoch": 0.8379719525350593,
+      "grad_norm": 1.2859764099121094,
+      "learning_rate": 9.89702696828669e-05,
+      "loss": 0.8236626386642456,
+      "step": 1942
+    },
+    {
+      "epoch": 0.8388349514563107,
+      "grad_norm": 1.2043784856796265,
+      "learning_rate": 9.89653063815289e-05,
+      "loss": 0.7315511703491211,
+      "step": 1944
+    },
+    {
+      "epoch": 0.839697950377562,
+      "grad_norm": 1.2063398361206055,
+      "learning_rate": 9.896033127242802e-05,
+      "loss": 0.6707082986831665,
+      "step": 1946
+    },
+    {
+      "epoch": 0.8405609492988134,
+      "grad_norm": 1.1906715631484985,
+      "learning_rate": 9.895534435676393e-05,
+      "loss": 0.6920633912086487,
+      "step": 1948
+    },
+    {
+      "epoch": 0.8414239482200647,
+      "grad_norm": 1.122567892074585,
+      "learning_rate": 9.895034563573926e-05,
+      "loss": 0.7134768962860107,
+      "step": 1950
+    },
+    {
+      "epoch": 0.842286947141316,
+      "grad_norm": 1.0681787729263306,
+      "learning_rate": 9.894533511055943e-05,
+      "loss": 0.6333967447280884,
+      "step": 1952
+    },
+    {
+      "epoch": 0.8431499460625674,
+      "grad_norm": 1.5216220617294312,
+      "learning_rate": 9.894031278243266e-05,
+      "loss": 0.7744026780128479,
+      "step": 1954
+    },
+    {
+      "epoch": 0.8440129449838187,
+      "grad_norm": 1.0934535264968872,
+      "learning_rate": 9.89352786525701e-05,
+      "loss": 0.7678086757659912,
+      "step": 1956
+    },
+    {
+      "epoch": 0.8448759439050701,
+      "grad_norm": 1.223285436630249,
+      "learning_rate": 9.89302327221857e-05,
+      "loss": 0.7344630360603333,
+      "step": 1958
+    },
+    {
+      "epoch": 0.8457389428263214,
+      "grad_norm": 1.1123322248458862,
+      "learning_rate": 9.892517499249623e-05,
+      "loss": 0.76033616065979,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8466019417475729,
+      "grad_norm": 1.0472193956375122,
+      "learning_rate": 9.89201054647214e-05,
+      "loss": 0.7176017761230469,
+      "step": 1962
+    },
+    {
+      "epoch": 0.8474649406688242,
+      "grad_norm": 1.8538368940353394,
+      "learning_rate": 9.891502414008365e-05,
+      "loss": 0.7220107316970825,
+      "step": 1964
+    },
+    {
+      "epoch": 0.8483279395900755,
+      "grad_norm": 1.2280668020248413,
+      "learning_rate": 9.890993101980834e-05,
+      "loss": 0.7399556636810303,
+      "step": 1966
+    },
+    {
+      "epoch": 0.8491909385113269,
+      "grad_norm": 1.1482552289962769,
+      "learning_rate": 9.890482610512364e-05,
+      "loss": 0.7700466513633728,
+      "step": 1968
+    },
+    {
+      "epoch": 0.8500539374325782,
+      "grad_norm": 1.1877986192703247,
+      "learning_rate": 9.889970939726061e-05,
+      "loss": 0.6666419506072998,
+      "step": 1970
+    },
+    {
+      "epoch": 0.8509169363538296,
+      "grad_norm": 1.407792329788208,
+      "learning_rate": 9.88945808974531e-05,
+      "loss": 0.7883278131484985,
+      "step": 1972
+    },
+    {
+      "epoch": 0.8517799352750809,
+      "grad_norm": 1.1426323652267456,
+      "learning_rate": 9.888944060693781e-05,
+      "loss": 0.7441611289978027,
+      "step": 1974
+    },
+    {
+      "epoch": 0.8526429341963323,
+      "grad_norm": 1.2660622596740723,
+      "learning_rate": 9.888428852695432e-05,
+      "loss": 0.6464171409606934,
+      "step": 1976
+    },
+    {
+      "epoch": 0.8535059331175836,
+      "grad_norm": 1.1639022827148438,
+      "learning_rate": 9.887912465874502e-05,
+      "loss": 0.7242478728294373,
+      "step": 1978
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 1.2546422481536865,
+      "learning_rate": 9.887394900355516e-05,
+      "loss": 0.7431875467300415,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8552319309600863,
+      "grad_norm": 1.1057130098342896,
+      "learning_rate": 9.886876156263282e-05,
+      "loss": 0.7662370204925537,
+      "step": 1982
+    },
+    {
+      "epoch": 0.8560949298813376,
+      "grad_norm": 1.1017125844955444,
+      "learning_rate": 9.886356233722894e-05,
+      "loss": 0.7120938897132874,
+      "step": 1984
+    },
+    {
+      "epoch": 0.856957928802589,
+      "grad_norm": 1.3548704385757446,
+      "learning_rate": 9.885835132859727e-05,
+      "loss": 0.789219856262207,
+      "step": 1986
+    },
+    {
+      "epoch": 0.8578209277238403,
+      "grad_norm": 1.1920398473739624,
+      "learning_rate": 9.885312853799443e-05,
+      "loss": 0.7599530816078186,
+      "step": 1988
+    },
+    {
+      "epoch": 0.8586839266450917,
+      "grad_norm": 1.170946478843689,
+      "learning_rate": 9.884789396667988e-05,
+      "loss": 0.8315809369087219,
+      "step": 1990
+    },
+    {
+      "epoch": 0.859546925566343,
+      "grad_norm": 1.2530180215835571,
+      "learning_rate": 9.88426476159159e-05,
+      "loss": 0.713994026184082,
+      "step": 1992
+    },
+    {
+      "epoch": 0.8604099244875943,
+      "grad_norm": 1.1056885719299316,
+      "learning_rate": 9.883738948696765e-05,
+      "loss": 0.6656507849693298,
+      "step": 1994
+    },
+    {
+      "epoch": 0.8612729234088458,
+      "grad_norm": 1.169382929801941,
+      "learning_rate": 9.883211958110308e-05,
+      "loss": 0.7164257764816284,
+      "step": 1996
+    },
+    {
+      "epoch": 0.8621359223300971,
+      "grad_norm": 1.1970325708389282,
+      "learning_rate": 9.882683789959299e-05,
+      "loss": 0.6885558366775513,
+      "step": 1998
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "grad_norm": 1.1700761318206787,
+      "learning_rate": 9.882154444371107e-05,
+      "loss": 0.7265812754631042,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "eval_loss": 0.7487027645111084,
+      "eval_runtime": 825.141,
+      "eval_samples_per_second": 2.497,
+      "eval_steps_per_second": 2.497,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8638619201725998,
+      "grad_norm": 1.3120243549346924,
+      "learning_rate": 9.88162392147338e-05,
+      "loss": 0.7371920347213745,
+      "step": 2002
+    },
+    {
+      "epoch": 0.8647249190938512,
+      "grad_norm": 1.098697304725647,
+      "learning_rate": 9.881092221394049e-05,
+      "loss": 0.7453275918960571,
+      "step": 2004
+    },
+    {
+      "epoch": 0.8655879180151025,
+      "grad_norm": 1.1961677074432373,
+      "learning_rate": 9.880559344261334e-05,
+      "loss": 0.7562432289123535,
+      "step": 2006
+    },
+    {
+      "epoch": 0.8664509169363538,
+      "grad_norm": 1.1655291318893433,
+      "learning_rate": 9.880025290203735e-05,
+      "loss": 0.7654905319213867,
+      "step": 2008
+    },
+    {
+      "epoch": 0.8673139158576052,
+      "grad_norm": 1.0979351997375488,
+      "learning_rate": 9.879490059350036e-05,
+      "loss": 0.6807888746261597,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8681769147788565,
+      "grad_norm": 1.0378475189208984,
+      "learning_rate": 9.878953651829306e-05,
+      "loss": 0.6887364387512207,
+      "step": 2012
+    },
+    {
+      "epoch": 0.8690399137001079,
+      "grad_norm": 2.0228428840637207,
+      "learning_rate": 9.878416067770898e-05,
+      "loss": 0.718578577041626,
+      "step": 2014
+    },
+    {
+      "epoch": 0.8699029126213592,
+      "grad_norm": 1.1610580682754517,
+      "learning_rate": 9.877877307304446e-05,
+      "loss": 0.7424600720405579,
+      "step": 2016
+    },
+    {
+      "epoch": 0.8707659115426106,
+      "grad_norm": 1.1415833234786987,
+      "learning_rate": 9.877337370559873e-05,
+      "loss": 0.7450630068778992,
+      "step": 2018
+    },
+    {
+      "epoch": 0.8716289104638619,
+      "grad_norm": 1.1008672714233398,
+      "learning_rate": 9.876796257667379e-05,
+      "loss": 0.7398725748062134,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8724919093851132,
+      "grad_norm": 1.1662763357162476,
+      "learning_rate": 9.876253968757452e-05,
+      "loss": 0.7122271060943604,
+      "step": 2022
+    },
+    {
+      "epoch": 0.8733549083063646,
+      "grad_norm": 1.1835166215896606,
+      "learning_rate": 9.875710503960862e-05,
+      "loss": 0.7026485800743103,
+      "step": 2024
+    },
+    {
+      "epoch": 0.8742179072276159,
+      "grad_norm": 1.1602214574813843,
+      "learning_rate": 9.875165863408666e-05,
+      "loss": 0.7211011052131653,
+      "step": 2026
+    },
+    {
+      "epoch": 0.8750809061488674,
+      "grad_norm": 1.222589373588562,
+      "learning_rate": 9.874620047232198e-05,
+      "loss": 0.7565322518348694,
+      "step": 2028
+    },
+    {
+      "epoch": 0.8759439050701187,
+      "grad_norm": 1.203661561012268,
+      "learning_rate": 9.87407305556308e-05,
+      "loss": 0.7173075675964355,
+      "step": 2030
+    },
+    {
+      "epoch": 0.87680690399137,
+      "grad_norm": 1.3316307067871094,
+      "learning_rate": 9.87352488853322e-05,
+      "loss": 0.820809006690979,
+      "step": 2032
+    },
+    {
+      "epoch": 0.8776699029126214,
+      "grad_norm": 1.3071057796478271,
+      "learning_rate": 9.872975546274799e-05,
+      "loss": 0.8689352869987488,
+      "step": 2034
+    },
+    {
+      "epoch": 0.8785329018338727,
+      "grad_norm": 1.3557701110839844,
+      "learning_rate": 9.872425028920294e-05,
+      "loss": 0.7090175151824951,
+      "step": 2036
+    },
+    {
+      "epoch": 0.8793959007551241,
+      "grad_norm": 1.2234264612197876,
+      "learning_rate": 9.871873336602459e-05,
+      "loss": 0.6883202195167542,
+      "step": 2038
+    },
+    {
+      "epoch": 0.8802588996763754,
+      "grad_norm": 1.3064714670181274,
+      "learning_rate": 9.87132046945433e-05,
+      "loss": 0.7134175896644592,
+      "step": 2040
+    },
+    {
+      "epoch": 0.8811218985976268,
+      "grad_norm": 1.2502511739730835,
+      "learning_rate": 9.870766427609232e-05,
+      "loss": 0.7127227783203125,
+      "step": 2042
+    },
+    {
+      "epoch": 0.8819848975188781,
+      "grad_norm": 1.1354259252548218,
+      "learning_rate": 9.870211211200766e-05,
+      "loss": 0.719437301158905,
+      "step": 2044
+    },
+    {
+      "epoch": 0.8828478964401294,
+      "grad_norm": 1.1706442832946777,
+      "learning_rate": 9.869654820362821e-05,
+      "loss": 0.6933091282844543,
+      "step": 2046
+    },
+    {
+      "epoch": 0.8837108953613808,
+      "grad_norm": 1.0227864980697632,
+      "learning_rate": 9.86909725522957e-05,
+      "loss": 0.6825079321861267,
+      "step": 2048
+    },
+    {
+      "epoch": 0.8845738942826321,
+      "grad_norm": 1.103418231010437,
+      "learning_rate": 9.868538515935465e-05,
+      "loss": 0.7306133508682251,
+      "step": 2050
+    },
+    {
+      "epoch": 0.8854368932038835,
+      "grad_norm": 1.0938395261764526,
+      "learning_rate": 9.867978602615245e-05,
+      "loss": 0.6956495046615601,
+      "step": 2052
+    },
+    {
+      "epoch": 0.8862998921251348,
+      "grad_norm": 1.115692377090454,
+      "learning_rate": 9.86741751540393e-05,
+      "loss": 0.7740456461906433,
+      "step": 2054
+    },
+    {
+      "epoch": 0.8871628910463862,
+      "grad_norm": 1.0264382362365723,
+      "learning_rate": 9.866855254436824e-05,
+      "loss": 0.6996002197265625,
+      "step": 2056
+    },
+    {
+      "epoch": 0.8880258899676375,
+      "grad_norm": 1.2523163557052612,
+      "learning_rate": 9.866291819849511e-05,
+      "loss": 0.760357677936554,
+      "step": 2058
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.0595446825027466,
+      "learning_rate": 9.865727211777864e-05,
+      "loss": 0.6389813423156738,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8897518878101403,
+      "grad_norm": 1.198530912399292,
+      "learning_rate": 9.865161430358036e-05,
+      "loss": 0.7859060168266296,
+      "step": 2062
+    },
+    {
+      "epoch": 0.8906148867313916,
+      "grad_norm": 1.0271193981170654,
+      "learning_rate": 9.864594475726461e-05,
+      "loss": 0.7120063900947571,
+      "step": 2064
+    },
+    {
+      "epoch": 0.891477885652643,
+      "grad_norm": 1.1619046926498413,
+      "learning_rate": 9.864026348019857e-05,
+      "loss": 0.6751878261566162,
+      "step": 2066
+    },
+    {
+      "epoch": 0.8923408845738943,
+      "grad_norm": 1.2812464237213135,
+      "learning_rate": 9.863457047375227e-05,
+      "loss": 0.610360860824585,
+      "step": 2068
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 1.112628698348999,
+      "learning_rate": 9.862886573929855e-05,
+      "loss": 0.6540104746818542,
+      "step": 2070
+    },
+    {
+      "epoch": 0.894066882416397,
+      "grad_norm": 1.6257048845291138,
+      "learning_rate": 9.862314927821306e-05,
+      "loss": 0.726277232170105,
+      "step": 2072
+    },
+    {
+      "epoch": 0.8949298813376483,
+      "grad_norm": 1.227334976196289,
+      "learning_rate": 9.861742109187432e-05,
+      "loss": 0.7798765301704407,
+      "step": 2074
+    },
+    {
+      "epoch": 0.8957928802588997,
+      "grad_norm": 1.0728148221969604,
+      "learning_rate": 9.861168118166366e-05,
+      "loss": 0.637127161026001,
+      "step": 2076
+    },
+    {
+      "epoch": 0.896655879180151,
+      "grad_norm": 1.220282793045044,
+      "learning_rate": 9.860592954896523e-05,
+      "loss": 0.7332831025123596,
+      "step": 2078
+    },
+    {
+      "epoch": 0.8975188781014024,
+      "grad_norm": 1.2287596464157104,
+      "learning_rate": 9.8600166195166e-05,
+      "loss": 0.7337175607681274,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8983818770226537,
+      "grad_norm": 1.0701712369918823,
+      "learning_rate": 9.859439112165579e-05,
+      "loss": 0.7422571182250977,
+      "step": 2082
+    },
+    {
+      "epoch": 0.8992448759439051,
+      "grad_norm": 1.1583118438720703,
+      "learning_rate": 9.858860432982721e-05,
+      "loss": 0.7010003328323364,
+      "step": 2084
+    },
+    {
+      "epoch": 0.9001078748651564,
+      "grad_norm": 0.9644797444343567,
+      "learning_rate": 9.858280582107575e-05,
+      "loss": 0.6211312413215637,
+      "step": 2086
+    },
+    {
+      "epoch": 0.9009708737864077,
+      "grad_norm": 1.2448554039001465,
+      "learning_rate": 9.857699559679968e-05,
+      "loss": 0.7299860715866089,
+      "step": 2088
+    },
+    {
+      "epoch": 0.9018338727076591,
+      "grad_norm": 1.2735580205917358,
+      "learning_rate": 9.85711736584001e-05,
+      "loss": 0.7461655735969543,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9026968716289104,
+      "grad_norm": 1.36841881275177,
+      "learning_rate": 9.856534000728093e-05,
+      "loss": 0.7218145132064819,
+      "step": 2092
+    },
+    {
+      "epoch": 0.9035598705501618,
+      "grad_norm": 1.1471478939056396,
+      "learning_rate": 9.855949464484898e-05,
+      "loss": 0.7045709490776062,
+      "step": 2094
+    },
+    {
+      "epoch": 0.9044228694714131,
+      "grad_norm": 1.058254361152649,
+      "learning_rate": 9.85536375725138e-05,
+      "loss": 0.7189744710922241,
+      "step": 2096
+    },
+    {
+      "epoch": 0.9052858683926646,
+      "grad_norm": 1.4070709943771362,
+      "learning_rate": 9.854776879168779e-05,
+      "loss": 0.740775465965271,
+      "step": 2098
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "grad_norm": 1.2182649374008179,
+      "learning_rate": 9.854188830378622e-05,
+      "loss": 0.8191262483596802,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "eval_loss": 0.7449111342430115,
+      "eval_runtime": 832.5135,
+      "eval_samples_per_second": 2.474,
+      "eval_steps_per_second": 2.474,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9070118662351672,
+      "grad_norm": 1.139978289604187,
+      "learning_rate": 9.853599611022708e-05,
+      "loss": 0.7295873761177063,
+      "step": 2102
+    },
+    {
+      "epoch": 0.9078748651564186,
+      "grad_norm": 1.1802685260772705,
+      "learning_rate": 9.853009221243127e-05,
+      "loss": 0.7141753435134888,
+      "step": 2104
+    },
+    {
+      "epoch": 0.9087378640776699,
+      "grad_norm": 1.076759934425354,
+      "learning_rate": 9.852417661182253e-05,
+      "loss": 0.7557607293128967,
+      "step": 2106
+    },
+    {
+      "epoch": 0.9096008629989213,
+      "grad_norm": 1.1000943183898926,
+      "learning_rate": 9.851824930982733e-05,
+      "loss": 0.7025325298309326,
+      "step": 2108
+    },
+    {
+      "epoch": 0.9104638619201726,
+      "grad_norm": 1.0235389471054077,
+      "learning_rate": 9.851231030787504e-05,
+      "loss": 0.6967638731002808,
+      "step": 2110
+    },
+    {
+      "epoch": 0.911326860841424,
+      "grad_norm": 1.2311428785324097,
+      "learning_rate": 9.850635960739782e-05,
+      "loss": 0.7890311479568481,
+      "step": 2112
+    },
+    {
+      "epoch": 0.9121898597626753,
+      "grad_norm": 1.173770785331726,
+      "learning_rate": 9.850039720983064e-05,
+      "loss": 0.6824729442596436,
+      "step": 2114
+    },
+    {
+      "epoch": 0.9130528586839266,
+      "grad_norm": 1.2165251970291138,
+      "learning_rate": 9.849442311661131e-05,
+      "loss": 0.7157722115516663,
+      "step": 2116
+    },
+    {
+      "epoch": 0.913915857605178,
+      "grad_norm": 1.251520037651062,
+      "learning_rate": 9.848843732918047e-05,
+      "loss": 0.7164111733436584,
+      "step": 2118
+    },
+    {
+      "epoch": 0.9147788565264293,
+      "grad_norm": 1.1330616474151611,
+      "learning_rate": 9.848243984898153e-05,
+      "loss": 0.6830796003341675,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9156418554476807,
+      "grad_norm": 1.1052451133728027,
+      "learning_rate": 9.847643067746081e-05,
+      "loss": 0.7149171829223633,
+      "step": 2122
+    },
+    {
+      "epoch": 0.916504854368932,
+      "grad_norm": 1.0389703512191772,
+      "learning_rate": 9.847040981606735e-05,
+      "loss": 0.7213287949562073,
+      "step": 2124
+    },
+    {
+      "epoch": 0.9173678532901833,
+      "grad_norm": 1.151895523071289,
+      "learning_rate": 9.846437726625308e-05,
+      "loss": 0.703312873840332,
+      "step": 2126
+    },
+    {
+      "epoch": 0.9182308522114347,
+      "grad_norm": 1.1624029874801636,
+      "learning_rate": 9.845833302947269e-05,
+      "loss": 0.8059951066970825,
+      "step": 2128
+    },
+    {
+      "epoch": 0.919093851132686,
+      "grad_norm": 1.2247511148452759,
+      "learning_rate": 9.845227710718377e-05,
+      "loss": 0.735476553440094,
+      "step": 2130
+    },
+    {
+      "epoch": 0.9199568500539375,
+      "grad_norm": 1.1649967432022095,
+      "learning_rate": 9.844620950084661e-05,
+      "loss": 0.8130571842193604,
+      "step": 2132
+    },
+    {
+      "epoch": 0.9208198489751888,
+      "grad_norm": 1.1915717124938965,
+      "learning_rate": 9.844013021192447e-05,
+      "loss": 0.6908681392669678,
+      "step": 2134
+    },
+    {
+      "epoch": 0.9216828478964402,
+      "grad_norm": 1.211199164390564,
+      "learning_rate": 9.843403924188328e-05,
+      "loss": 0.652173638343811,
+      "step": 2136
+    },
+    {
+      "epoch": 0.9225458468176915,
+      "grad_norm": 1.267242193222046,
+      "learning_rate": 9.842793659219186e-05,
+      "loss": 0.6672233939170837,
+      "step": 2138
+    },
+    {
+      "epoch": 0.9234088457389428,
+      "grad_norm": 1.7038761377334595,
+      "learning_rate": 9.842182226432186e-05,
+      "loss": 0.7274143695831299,
+      "step": 2140
+    },
+    {
+      "epoch": 0.9242718446601942,
+      "grad_norm": 1.151426076889038,
+      "learning_rate": 9.841569625974769e-05,
+      "loss": 0.707998514175415,
+      "step": 2142
+    },
+    {
+      "epoch": 0.9251348435814455,
+      "grad_norm": 1.0414749383926392,
+      "learning_rate": 9.840955857994663e-05,
+      "loss": 0.6639942526817322,
+      "step": 2144
+    },
+    {
+      "epoch": 0.9259978425026969,
+      "grad_norm": 1.1045551300048828,
+      "learning_rate": 9.840340922639875e-05,
+      "loss": 0.7096070647239685,
+      "step": 2146
+    },
+    {
+      "epoch": 0.9268608414239482,
+      "grad_norm": 1.1193996667861938,
+      "learning_rate": 9.839724820058695e-05,
+      "loss": 0.71246737241745,
+      "step": 2148
+    },
+    {
+      "epoch": 0.9277238403451996,
+      "grad_norm": 1.2609117031097412,
+      "learning_rate": 9.839107550399692e-05,
+      "loss": 0.7351052761077881,
+      "step": 2150
+    },
+    {
+      "epoch": 0.9285868392664509,
+      "grad_norm": 1.1127749681472778,
+      "learning_rate": 9.838489113811717e-05,
+      "loss": 0.7125008702278137,
+      "step": 2152
+    },
+    {
+      "epoch": 0.9294498381877022,
+      "grad_norm": 1.4771665334701538,
+      "learning_rate": 9.837869510443905e-05,
+      "loss": 0.7891085743904114,
+      "step": 2154
+    },
+    {
+      "epoch": 0.9303128371089536,
+      "grad_norm": 1.0701470375061035,
+      "learning_rate": 9.83724874044567e-05,
+      "loss": 0.7370918393135071,
+      "step": 2156
+    },
+    {
+      "epoch": 0.9311758360302049,
+      "grad_norm": 1.2045820951461792,
+      "learning_rate": 9.836626803966708e-05,
+      "loss": 0.7543193697929382,
+      "step": 2158
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 1.1944687366485596,
+      "learning_rate": 9.836003701156996e-05,
+      "loss": 0.6903626322746277,
+      "step": 2160
+    },
+    {
+      "epoch": 0.9329018338727076,
+      "grad_norm": 1.1035394668579102,
+      "learning_rate": 9.83537943216679e-05,
+      "loss": 0.6923050880432129,
+      "step": 2162
+    },
+    {
+      "epoch": 0.933764832793959,
+      "grad_norm": 1.3766103982925415,
+      "learning_rate": 9.834753997146633e-05,
+      "loss": 0.8099993467330933,
+      "step": 2164
+    },
+    {
+      "epoch": 0.9346278317152104,
+      "grad_norm": 1.0874576568603516,
+      "learning_rate": 9.834127396247346e-05,
+      "loss": 0.7896219491958618,
+      "step": 2166
+    },
+    {
+      "epoch": 0.9354908306364617,
+      "grad_norm": 1.1633459329605103,
+      "learning_rate": 9.833499629620028e-05,
+      "loss": 0.7659367918968201,
+      "step": 2168
+    },
+    {
+      "epoch": 0.9363538295577131,
+      "grad_norm": 1.405423641204834,
+      "learning_rate": 9.832870697416066e-05,
+      "loss": 0.7474715709686279,
+      "step": 2170
+    },
+    {
+      "epoch": 0.9372168284789644,
+      "grad_norm": 1.1794270277023315,
+      "learning_rate": 9.83224059978712e-05,
+      "loss": 0.7018750905990601,
+      "step": 2172
+    },
+    {
+      "epoch": 0.9380798274002158,
+      "grad_norm": 1.082466959953308,
+      "learning_rate": 9.831609336885139e-05,
+      "loss": 0.6477128267288208,
+      "step": 2174
+    },
+    {
+      "epoch": 0.9389428263214671,
+      "grad_norm": 0.9830297827720642,
+      "learning_rate": 9.830976908862346e-05,
+      "loss": 0.6516029238700867,
+      "step": 2176
+    },
+    {
+      "epoch": 0.9398058252427185,
+      "grad_norm": 1.112289309501648,
+      "learning_rate": 9.83034331587125e-05,
+      "loss": 0.6793080568313599,
+      "step": 2178
+    },
+    {
+      "epoch": 0.9406688241639698,
+      "grad_norm": 1.1212154626846313,
+      "learning_rate": 9.829708558064638e-05,
+      "loss": 0.7220560312271118,
+      "step": 2180
+    },
+    {
+      "epoch": 0.9415318230852211,
+      "grad_norm": 1.246471643447876,
+      "learning_rate": 9.829072635595582e-05,
+      "loss": 0.7621577978134155,
+      "step": 2182
+    },
+    {
+      "epoch": 0.9423948220064725,
+      "grad_norm": 1.1732288599014282,
+      "learning_rate": 9.828435548617428e-05,
+      "loss": 0.6988050937652588,
+      "step": 2184
+    },
+    {
+      "epoch": 0.9432578209277238,
+      "grad_norm": 1.1767359972000122,
+      "learning_rate": 9.827797297283808e-05,
+      "loss": 0.7909345626831055,
+      "step": 2186
+    },
+    {
+      "epoch": 0.9441208198489752,
+      "grad_norm": 1.007215976715088,
+      "learning_rate": 9.827157881748633e-05,
+      "loss": 0.6651493310928345,
+      "step": 2188
+    },
+    {
+      "epoch": 0.9449838187702265,
+      "grad_norm": 1.184118628501892,
+      "learning_rate": 9.826517302166096e-05,
+      "loss": 0.7742198705673218,
+      "step": 2190
+    },
+    {
+      "epoch": 0.9458468176914779,
+      "grad_norm": 1.1227030754089355,
+      "learning_rate": 9.82587555869067e-05,
+      "loss": 0.7614272236824036,
+      "step": 2192
+    },
+    {
+      "epoch": 0.9467098166127292,
+      "grad_norm": 1.1030738353729248,
+      "learning_rate": 9.825232651477109e-05,
+      "loss": 0.7302108407020569,
+      "step": 2194
+    },
+    {
+      "epoch": 0.9475728155339805,
+      "grad_norm": 1.5209563970565796,
+      "learning_rate": 9.824588580680445e-05,
+      "loss": 0.7408936023712158,
+      "step": 2196
+    },
+    {
+      "epoch": 0.948435814455232,
+      "grad_norm": 1.1853431463241577,
+      "learning_rate": 9.823943346455995e-05,
+      "loss": 0.8050196766853333,
+      "step": 2198
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "grad_norm": 1.285551905632019,
+      "learning_rate": 9.823296948959354e-05,
+      "loss": 0.726731538772583,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "eval_loss": 0.7400083541870117,
+      "eval_runtime": 838.7633,
+      "eval_samples_per_second": 2.456,
+      "eval_steps_per_second": 2.456,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9501618122977347,
+      "grad_norm": 1.2159804105758667,
+      "learning_rate": 9.822649388346396e-05,
+      "loss": 0.7061861753463745,
+      "step": 2202
+    },
+    {
+      "epoch": 0.951024811218986,
+      "grad_norm": 1.1189815998077393,
+      "learning_rate": 9.822000664773278e-05,
+      "loss": 0.824293851852417,
+      "step": 2204
+    },
+    {
+      "epoch": 0.9518878101402374,
+      "grad_norm": 0.9968506097793579,
+      "learning_rate": 9.821350778396439e-05,
+      "loss": 0.7230689525604248,
+      "step": 2206
+    },
+    {
+      "epoch": 0.9527508090614887,
+      "grad_norm": 1.101393222808838,
+      "learning_rate": 9.820699729372593e-05,
+      "loss": 0.6633790135383606,
+      "step": 2208
+    },
+    {
+      "epoch": 0.95361380798274,
+      "grad_norm": 1.084307312965393,
+      "learning_rate": 9.820047517858741e-05,
+      "loss": 0.6548227071762085,
+      "step": 2210
+    },
+    {
+      "epoch": 0.9544768069039914,
+      "grad_norm": 1.1291496753692627,
+      "learning_rate": 9.819394144012158e-05,
+      "loss": 0.6434295177459717,
+      "step": 2212
+    },
+    {
+      "epoch": 0.9553398058252427,
+      "grad_norm": 2.303483724594116,
+      "learning_rate": 9.818739607990404e-05,
+      "loss": 0.8122013211250305,
+      "step": 2214
+    },
+    {
+      "epoch": 0.9562028047464941,
+      "grad_norm": 1.244541883468628,
+      "learning_rate": 9.818083909951315e-05,
+      "loss": 0.6120955348014832,
+      "step": 2216
+    },
+    {
+      "epoch": 0.9570658036677454,
+      "grad_norm": 1.1051502227783203,
+      "learning_rate": 9.817427050053012e-05,
+      "loss": 0.7569628953933716,
+      "step": 2218
+    },
+    {
+      "epoch": 0.9579288025889967,
+      "grad_norm": 1.3161911964416504,
+      "learning_rate": 9.816769028453893e-05,
+      "loss": 0.7588980197906494,
+      "step": 2220
+    },
+    {
+      "epoch": 0.9587918015102481,
+      "grad_norm": 1.2526928186416626,
+      "learning_rate": 9.816109845312636e-05,
+      "loss": 0.743370771408081,
+      "step": 2222
+    },
+    {
+      "epoch": 0.9596548004314994,
+      "grad_norm": 1.196215033531189,
+      "learning_rate": 9.815449500788202e-05,
+      "loss": 0.80516517162323,
+      "step": 2224
+    },
+    {
+      "epoch": 0.9605177993527508,
+      "grad_norm": 1.3204832077026367,
+      "learning_rate": 9.81478799503983e-05,
+      "loss": 0.7331632971763611,
+      "step": 2226
+    },
+    {
+      "epoch": 0.9613807982740021,
+      "grad_norm": 1.2442790269851685,
+      "learning_rate": 9.814125328227035e-05,
+      "loss": 0.6810339093208313,
+      "step": 2228
+    },
+    {
+      "epoch": 0.9622437971952535,
+      "grad_norm": 1.1739158630371094,
+      "learning_rate": 9.813461500509623e-05,
+      "loss": 0.7269608378410339,
+      "step": 2230
+    },
+    {
+      "epoch": 0.9631067961165048,
+      "grad_norm": 1.1016241312026978,
+      "learning_rate": 9.812796512047666e-05,
+      "loss": 0.7159227132797241,
+      "step": 2232
+    },
+    {
+      "epoch": 0.9639697950377561,
+      "grad_norm": 1.1654549837112427,
+      "learning_rate": 9.812130363001529e-05,
+      "loss": 0.7145758867263794,
+      "step": 2234
+    },
+    {
+      "epoch": 0.9648327939590076,
+      "grad_norm": 1.0521938800811768,
+      "learning_rate": 9.811463053531846e-05,
+      "loss": 0.6873835325241089,
+      "step": 2236
+    },
+    {
+      "epoch": 0.9656957928802589,
+      "grad_norm": 1.2285776138305664,
+      "learning_rate": 9.810794583799538e-05,
+      "loss": 0.6683027148246765,
+      "step": 2238
+    },
+    {
+      "epoch": 0.9665587918015103,
+      "grad_norm": 0.9826368689537048,
+      "learning_rate": 9.810124953965805e-05,
+      "loss": 0.663141131401062,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9674217907227616,
+      "grad_norm": 1.0102336406707764,
+      "learning_rate": 9.809454164192123e-05,
+      "loss": 0.6688778400421143,
+      "step": 2242
+    },
+    {
+      "epoch": 0.968284789644013,
+      "grad_norm": 0.9781575202941895,
+      "learning_rate": 9.808782214640251e-05,
+      "loss": 0.671240508556366,
+      "step": 2244
+    },
+    {
+      "epoch": 0.9691477885652643,
+      "grad_norm": 1.137385368347168,
+      "learning_rate": 9.808109105472225e-05,
+      "loss": 0.7673252820968628,
+      "step": 2246
+    },
+    {
+      "epoch": 0.9700107874865156,
+      "grad_norm": 1.3359450101852417,
+      "learning_rate": 9.807434836850362e-05,
+      "loss": 0.8085554838180542,
+      "step": 2248
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 1.150694727897644,
+      "learning_rate": 9.806759408937262e-05,
+      "loss": 0.6750202178955078,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9717367853290183,
+      "grad_norm": 1.080316424369812,
+      "learning_rate": 9.8060828218958e-05,
+      "loss": 0.5928418040275574,
+      "step": 2252
+    },
+    {
+      "epoch": 0.9725997842502697,
+      "grad_norm": 1.0489610433578491,
+      "learning_rate": 9.805405075889129e-05,
+      "loss": 0.6947471499443054,
+      "step": 2254
+    },
+    {
+      "epoch": 0.973462783171521,
+      "grad_norm": 1.199119210243225,
+      "learning_rate": 9.80472617108069e-05,
+      "loss": 0.7273924350738525,
+      "step": 2256
+    },
+    {
+      "epoch": 0.9743257820927724,
+      "grad_norm": 0.9830896258354187,
+      "learning_rate": 9.804046107634193e-05,
+      "loss": 0.668613612651825,
+      "step": 2258
+    },
+    {
+      "epoch": 0.9751887810140237,
+      "grad_norm": 1.1655877828598022,
+      "learning_rate": 9.803364885713633e-05,
+      "loss": 0.7255772352218628,
+      "step": 2260
+    },
+    {
+      "epoch": 0.976051779935275,
+      "grad_norm": 1.0289462804794312,
+      "learning_rate": 9.802682505483284e-05,
+      "loss": 0.6865858435630798,
+      "step": 2262
+    },
+    {
+      "epoch": 0.9769147788565264,
+      "grad_norm": 1.1020126342773438,
+      "learning_rate": 9.801998967107702e-05,
+      "loss": 0.6680663228034973,
+      "step": 2264
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.0846027135849,
+      "learning_rate": 9.801314270751716e-05,
+      "loss": 0.7476468086242676,
+      "step": 2266
+    },
+    {
+      "epoch": 0.9786407766990292,
+      "grad_norm": 1.1834278106689453,
+      "learning_rate": 9.800628416580437e-05,
+      "loss": 0.7173228859901428,
+      "step": 2268
+    },
+    {
+      "epoch": 0.9795037756202805,
+      "grad_norm": 1.0082321166992188,
+      "learning_rate": 9.799941404759257e-05,
+      "loss": 0.6768618226051331,
+      "step": 2270
+    },
+    {
+      "epoch": 0.9803667745415319,
+      "grad_norm": 1.1573102474212646,
+      "learning_rate": 9.799253235453846e-05,
+      "loss": 0.7877311110496521,
+      "step": 2272
+    },
+    {
+      "epoch": 0.9812297734627832,
+      "grad_norm": 1.2030092477798462,
+      "learning_rate": 9.798563908830152e-05,
+      "loss": 0.6843966841697693,
+      "step": 2274
+    },
+    {
+      "epoch": 0.9820927723840345,
+      "grad_norm": 1.080560564994812,
+      "learning_rate": 9.797873425054404e-05,
+      "loss": 0.6084349155426025,
+      "step": 2276
+    },
+    {
+      "epoch": 0.9829557713052859,
+      "grad_norm": 1.1488033533096313,
+      "learning_rate": 9.797181784293107e-05,
+      "loss": 0.6784868836402893,
+      "step": 2278
+    },
+    {
+      "epoch": 0.9838187702265372,
+      "grad_norm": 1.144773006439209,
+      "learning_rate": 9.796488986713049e-05,
+      "loss": 0.6111500263214111,
+      "step": 2280
+    },
+    {
+      "epoch": 0.9846817691477886,
+      "grad_norm": 1.1356254816055298,
+      "learning_rate": 9.795795032481297e-05,
+      "loss": 0.7634603977203369,
+      "step": 2282
+    },
+    {
+      "epoch": 0.9855447680690399,
+      "grad_norm": 1.139446496963501,
+      "learning_rate": 9.79509992176519e-05,
+      "loss": 0.6470903158187866,
+      "step": 2284
+    },
+    {
+      "epoch": 0.9864077669902913,
+      "grad_norm": 1.1564133167266846,
+      "learning_rate": 9.794403654732354e-05,
+      "loss": 0.71474289894104,
+      "step": 2286
+    },
+    {
+      "epoch": 0.9872707659115426,
+      "grad_norm": 1.0605655908584595,
+      "learning_rate": 9.793706231550689e-05,
+      "loss": 0.6413968801498413,
+      "step": 2288
+    },
+    {
+      "epoch": 0.9881337648327939,
+      "grad_norm": 1.1660863161087036,
+      "learning_rate": 9.793007652388378e-05,
+      "loss": 0.6595705151557922,
+      "step": 2290
+    },
+    {
+      "epoch": 0.9889967637540453,
+      "grad_norm": 1.1661914587020874,
+      "learning_rate": 9.792307917413877e-05,
+      "loss": 0.7144066095352173,
+      "step": 2292
+    },
+    {
+      "epoch": 0.9898597626752966,
+      "grad_norm": 1.2250727415084839,
+      "learning_rate": 9.791607026795926e-05,
+      "loss": 0.7956018447875977,
+      "step": 2294
+    },
+    {
+      "epoch": 0.990722761596548,
+      "grad_norm": 0.9593650698661804,
+      "learning_rate": 9.790904980703541e-05,
+      "loss": 0.5786031484603882,
+      "step": 2296
+    },
+    {
+      "epoch": 0.9915857605177993,
+      "grad_norm": 1.0697777271270752,
+      "learning_rate": 9.790201779306018e-05,
+      "loss": 0.6817460656166077,
+      "step": 2298
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "grad_norm": 1.2658408880233765,
+      "learning_rate": 9.789497422772931e-05,
+      "loss": 0.6845148801803589,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "eval_loss": 0.7360134720802307,
+      "eval_runtime": 825.8559,
+      "eval_samples_per_second": 2.494,
+      "eval_steps_per_second": 2.494,
+      "step": 2300
+    },
+    {
+      "epoch": 0.993311758360302,
+      "grad_norm": 1.0869544744491577,
+      "learning_rate": 9.788791911274131e-05,
+      "loss": 0.6689707040786743,
+      "step": 2302
+    },
+    {
+      "epoch": 0.9941747572815534,
+      "grad_norm": 1.0049875974655151,
+      "learning_rate": 9.788085244979748e-05,
+      "loss": 0.6470839381217957,
+      "step": 2304
+    },
+    {
+      "epoch": 0.9950377562028048,
+      "grad_norm": 1.4471046924591064,
+      "learning_rate": 9.787377424060196e-05,
+      "loss": 0.8018016815185547,
+      "step": 2306
+    },
+    {
+      "epoch": 0.9959007551240561,
+      "grad_norm": 1.3750648498535156,
+      "learning_rate": 9.786668448686159e-05,
+      "loss": 0.8078322410583496,
+      "step": 2308
+    },
+    {
+      "epoch": 0.9967637540453075,
+      "grad_norm": 1.098283290863037,
+      "learning_rate": 9.7859583190286e-05,
+      "loss": 0.6740908622741699,
+      "step": 2310
+    },
+    {
+      "epoch": 0.9976267529665588,
+      "grad_norm": 1.0312142372131348,
+      "learning_rate": 9.785247035258773e-05,
+      "loss": 0.6844386458396912,
+      "step": 2312
+    },
+    {
+      "epoch": 0.9984897518878102,
+      "grad_norm": 1.4482319355010986,
+      "learning_rate": 9.784534597548193e-05,
+      "loss": 0.7547479271888733,
+      "step": 2314
+    },
+    {
+      "epoch": 0.9993527508090615,
+      "grad_norm": 1.0897735357284546,
+      "learning_rate": 9.783821006068663e-05,
+      "loss": 0.7713987231254578,
+      "step": 2316
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7887805700302124,
+      "learning_rate": 9.783106260992264e-05,
+      "loss": 0.6868399381637573,
+      "step": 2318
+    },
+    {
+      "epoch": 1.0008629989212514,
+      "grad_norm": 1.0021663904190063,
+      "learning_rate": 9.782390362491353e-05,
+      "loss": 0.696355938911438,
+      "step": 2320
+    },
+    {
+      "epoch": 1.0017259978425026,
+      "grad_norm": 1.3650091886520386,
+      "learning_rate": 9.781673310738564e-05,
+      "loss": 0.7315902709960938,
+      "step": 2322
+    },
+    {
+      "epoch": 1.002588996763754,
+      "grad_norm": 1.2247875928878784,
+      "learning_rate": 9.780955105906813e-05,
+      "loss": 0.7667547464370728,
+      "step": 2324
+    },
+    {
+      "epoch": 1.0034519956850054,
+      "grad_norm": 1.1917641162872314,
+      "learning_rate": 9.780235748169291e-05,
+      "loss": 0.7380582094192505,
+      "step": 2326
+    },
+    {
+      "epoch": 1.0043149946062568,
+      "grad_norm": 1.146159052848816,
+      "learning_rate": 9.779515237699466e-05,
+      "loss": 0.6780733466148376,
+      "step": 2328
+    },
+    {
+      "epoch": 1.005177993527508,
+      "grad_norm": 1.4877620935440063,
+      "learning_rate": 9.778793574671089e-05,
+      "loss": 0.8116409182548523,
+      "step": 2330
+    },
+    {
+      "epoch": 1.0060409924487594,
+      "grad_norm": 1.3488554954528809,
+      "learning_rate": 9.778070759258185e-05,
+      "loss": 0.65245521068573,
+      "step": 2332
+    },
+    {
+      "epoch": 1.0069039913700109,
+      "grad_norm": 1.096686840057373,
+      "learning_rate": 9.777346791635056e-05,
+      "loss": 0.584334135055542,
+      "step": 2334
+    },
+    {
+      "epoch": 1.007766990291262,
+      "grad_norm": 1.063981056213379,
+      "learning_rate": 9.776621671976285e-05,
+      "loss": 0.6594714522361755,
+      "step": 2336
+    },
+    {
+      "epoch": 1.0086299892125135,
+      "grad_norm": 1.2811797857284546,
+      "learning_rate": 9.775895400456729e-05,
+      "loss": 0.6963099837303162,
+      "step": 2338
+    },
+    {
+      "epoch": 1.0094929881337649,
+      "grad_norm": 0.9491971731185913,
+      "learning_rate": 9.775167977251529e-05,
+      "loss": 0.6246375441551208,
+      "step": 2340
+    },
+    {
+      "epoch": 1.0103559870550163,
+      "grad_norm": 1.198683500289917,
+      "learning_rate": 9.774439402536098e-05,
+      "loss": 0.6352161169052124,
+      "step": 2342
+    },
+    {
+      "epoch": 1.0112189859762675,
+      "grad_norm": 1.2178813219070435,
+      "learning_rate": 9.773709676486129e-05,
+      "loss": 0.6884894967079163,
+      "step": 2344
+    },
+    {
+      "epoch": 1.0120819848975189,
+      "grad_norm": 1.1905319690704346,
+      "learning_rate": 9.77297879927759e-05,
+      "loss": 0.5945048928260803,
+      "step": 2346
+    },
+    {
+      "epoch": 1.0129449838187703,
+      "grad_norm": 1.210302710533142,
+      "learning_rate": 9.77224677108673e-05,
+      "loss": 0.6533923149108887,
+      "step": 2348
+    },
+    {
+      "epoch": 1.0138079827400215,
+      "grad_norm": 1.15508234500885,
+      "learning_rate": 9.771513592090076e-05,
+      "loss": 0.6619405746459961,
+      "step": 2350
+    },
+    {
+      "epoch": 1.014670981661273,
+      "grad_norm": 1.0833762884140015,
+      "learning_rate": 9.77077926246443e-05,
+      "loss": 0.6581310033798218,
+      "step": 2352
+    },
+    {
+      "epoch": 1.0155339805825243,
+      "grad_norm": 1.0330514907836914,
+      "learning_rate": 9.770043782386869e-05,
+      "loss": 0.6670945882797241,
+      "step": 2354
+    },
+    {
+      "epoch": 1.0163969795037757,
+      "grad_norm": 1.1472195386886597,
+      "learning_rate": 9.769307152034755e-05,
+      "loss": 0.6801814436912537,
+      "step": 2356
+    },
+    {
+      "epoch": 1.017259978425027,
+      "grad_norm": 1.2204132080078125,
+      "learning_rate": 9.76856937158572e-05,
+      "loss": 0.7206465005874634,
+      "step": 2358
+    },
+    {
+      "epoch": 1.0181229773462783,
+      "grad_norm": 1.2335962057113647,
+      "learning_rate": 9.76783044121768e-05,
+      "loss": 0.6884574294090271,
+      "step": 2360
+    },
+    {
+      "epoch": 1.0189859762675297,
+      "grad_norm": 1.0858685970306396,
+      "learning_rate": 9.767090361108822e-05,
+      "loss": 0.655097484588623,
+      "step": 2362
+    },
+    {
+      "epoch": 1.019848975188781,
+      "grad_norm": 1.117907166481018,
+      "learning_rate": 9.766349131437614e-05,
+      "loss": 0.6478561758995056,
+      "step": 2364
+    },
+    {
+      "epoch": 1.0207119741100323,
+      "grad_norm": 1.1995056867599487,
+      "learning_rate": 9.765606752382797e-05,
+      "loss": 0.6310951113700867,
+      "step": 2366
+    },
+    {
+      "epoch": 1.0215749730312838,
+      "grad_norm": 1.354819655418396,
+      "learning_rate": 9.764863224123397e-05,
+      "loss": 0.6373490691184998,
+      "step": 2368
+    },
+    {
+      "epoch": 1.0224379719525352,
+      "grad_norm": 1.2194819450378418,
+      "learning_rate": 9.764118546838712e-05,
+      "loss": 0.6595761179924011,
+      "step": 2370
+    },
+    {
+      "epoch": 1.0233009708737864,
+      "grad_norm": 1.1485158205032349,
+      "learning_rate": 9.763372720708314e-05,
+      "loss": 0.6299480199813843,
+      "step": 2372
+    },
+    {
+      "epoch": 1.0241639697950378,
+      "grad_norm": 1.1153662204742432,
+      "learning_rate": 9.76262574591206e-05,
+      "loss": 0.6788742542266846,
+      "step": 2374
+    },
+    {
+      "epoch": 1.0250269687162892,
+      "grad_norm": 1.0690817832946777,
+      "learning_rate": 9.761877622630075e-05,
+      "loss": 0.559056282043457,
+      "step": 2376
+    },
+    {
+      "epoch": 1.0258899676375404,
+      "grad_norm": 1.1896858215332031,
+      "learning_rate": 9.76112835104277e-05,
+      "loss": 0.7164555191993713,
+      "step": 2378
+    },
+    {
+      "epoch": 1.0267529665587918,
+      "grad_norm": 1.1792134046554565,
+      "learning_rate": 9.760377931330824e-05,
+      "loss": 0.6791456937789917,
+      "step": 2380
+    },
+    {
+      "epoch": 1.0276159654800432,
+      "grad_norm": 1.361763834953308,
+      "learning_rate": 9.759626363675202e-05,
+      "loss": 0.7421526312828064,
+      "step": 2382
+    },
+    {
+      "epoch": 1.0284789644012946,
+      "grad_norm": 1.1960662603378296,
+      "learning_rate": 9.758873648257138e-05,
+      "loss": 0.7032517194747925,
+      "step": 2384
+    },
+    {
+      "epoch": 1.0293419633225458,
+      "grad_norm": 1.323255181312561,
+      "learning_rate": 9.758119785258146e-05,
+      "loss": 0.6953344345092773,
+      "step": 2386
+    },
+    {
+      "epoch": 1.0302049622437972,
+      "grad_norm": 1.2343937158584595,
+      "learning_rate": 9.75736477486002e-05,
+      "loss": 0.7287829518318176,
+      "step": 2388
+    },
+    {
+      "epoch": 1.0310679611650486,
+      "grad_norm": 1.0712062120437622,
+      "learning_rate": 9.756608617244823e-05,
+      "loss": 0.6812928915023804,
+      "step": 2390
+    },
+    {
+      "epoch": 1.0319309600862998,
+      "grad_norm": 1.264726996421814,
+      "learning_rate": 9.755851312594902e-05,
+      "loss": 0.7173963785171509,
+      "step": 2392
+    },
+    {
+      "epoch": 1.0327939590075512,
+      "grad_norm": 1.1563389301300049,
+      "learning_rate": 9.755092861092874e-05,
+      "loss": 0.6509836316108704,
+      "step": 2394
+    },
+    {
+      "epoch": 1.0336569579288026,
+      "grad_norm": 1.326188087463379,
+      "learning_rate": 9.75433326292164e-05,
+      "loss": 0.718437135219574,
+      "step": 2396
+    },
+    {
+      "epoch": 1.0345199568500538,
+      "grad_norm": 1.2263392210006714,
+      "learning_rate": 9.753572518264373e-05,
+      "loss": 0.664516031742096,
+      "step": 2398
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "grad_norm": 1.2874478101730347,
+      "learning_rate": 9.752810627304523e-05,
+      "loss": 0.6754546165466309,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "eval_loss": 0.7346783876419067,
+      "eval_runtime": 825.8356,
+      "eval_samples_per_second": 2.494,
+      "eval_steps_per_second": 2.494,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0362459546925566,
+      "grad_norm": 1.304518461227417,
+      "learning_rate": 9.752047590225814e-05,
+      "loss": 0.708167314529419,
+      "step": 2402
+    },
+    {
+      "epoch": 1.037108953613808,
+      "grad_norm": 1.21835196018219,
+      "learning_rate": 9.751283407212252e-05,
+      "loss": 0.7213018536567688,
+      "step": 2404
+    },
+    {
+      "epoch": 1.0379719525350593,
+      "grad_norm": 1.2947579622268677,
+      "learning_rate": 9.750518078448116e-05,
+      "loss": 0.6739231944084167,
+      "step": 2406
+    },
+    {
+      "epoch": 1.0388349514563107,
+      "grad_norm": 1.138368010520935,
+      "learning_rate": 9.749751604117959e-05,
+      "loss": 0.7671371102333069,
+      "step": 2408
+    },
+    {
+      "epoch": 1.039697950377562,
+      "grad_norm": 1.1255316734313965,
+      "learning_rate": 9.748983984406616e-05,
+      "loss": 0.6593353748321533,
+      "step": 2410
+    },
+    {
+      "epoch": 1.0405609492988135,
+      "grad_norm": 1.2362794876098633,
+      "learning_rate": 9.748215219499193e-05,
+      "loss": 0.713056743144989,
+      "step": 2412
+    },
+    {
+      "epoch": 1.0414239482200647,
+      "grad_norm": 1.2021304368972778,
+      "learning_rate": 9.747445309581076e-05,
+      "loss": 0.6989394426345825,
+      "step": 2414
+    },
+    {
+      "epoch": 1.042286947141316,
+      "grad_norm": 1.127341389656067,
+      "learning_rate": 9.746674254837925e-05,
+      "loss": 0.623035192489624,
+      "step": 2416
+    },
+    {
+      "epoch": 1.0431499460625675,
+      "grad_norm": 1.1254255771636963,
+      "learning_rate": 9.745902055455672e-05,
+      "loss": 0.6490310430526733,
+      "step": 2418
+    },
+    {
+      "epoch": 1.0440129449838187,
+      "grad_norm": 1.2142512798309326,
+      "learning_rate": 9.745128711620535e-05,
+      "loss": 0.6210505366325378,
+      "step": 2420
+    },
+    {
+      "epoch": 1.04487594390507,
+      "grad_norm": 1.1306709051132202,
+      "learning_rate": 9.744354223519001e-05,
+      "loss": 0.6243326663970947,
+      "step": 2422
+    },
+    {
+      "epoch": 1.0457389428263215,
+      "grad_norm": 1.202621340751648,
+      "learning_rate": 9.743578591337833e-05,
+      "loss": 0.6312575340270996,
+      "step": 2424
+    },
+    {
+      "epoch": 1.0466019417475727,
+      "grad_norm": 1.0556137561798096,
+      "learning_rate": 9.742801815264072e-05,
+      "loss": 0.6190714836120605,
+      "step": 2426
+    },
+    {
+      "epoch": 1.0474649406688241,
+      "grad_norm": 1.5071814060211182,
+      "learning_rate": 9.742023895485033e-05,
+      "loss": 0.7496671080589294,
+      "step": 2428
+    },
+    {
+      "epoch": 1.0483279395900755,
+      "grad_norm": 1.1448185443878174,
+      "learning_rate": 9.74124483218831e-05,
+      "loss": 0.6288847327232361,
+      "step": 2430
+    },
+    {
+      "epoch": 1.049190938511327,
+      "grad_norm": 1.0072964429855347,
+      "learning_rate": 9.74046462556177e-05,
+      "loss": 0.6938424706459045,
+      "step": 2432
+    },
+    {
+      "epoch": 1.0500539374325781,
+      "grad_norm": 1.198836326599121,
+      "learning_rate": 9.739683275793554e-05,
+      "loss": 0.7529639601707458,
+      "step": 2434
+    },
+    {
+      "epoch": 1.0509169363538295,
+      "grad_norm": 1.2170380353927612,
+      "learning_rate": 9.738900783072083e-05,
+      "loss": 0.7193960547447205,
+      "step": 2436
+    },
+    {
+      "epoch": 1.051779935275081,
+      "grad_norm": 1.0384336709976196,
+      "learning_rate": 9.738117147586051e-05,
+      "loss": 0.6488150954246521,
+      "step": 2438
+    },
+    {
+      "epoch": 1.0526429341963321,
+      "grad_norm": 1.1562492847442627,
+      "learning_rate": 9.737332369524429e-05,
+      "loss": 0.6672247052192688,
+      "step": 2440
+    },
+    {
+      "epoch": 1.0535059331175836,
+      "grad_norm": 1.1553802490234375,
+      "learning_rate": 9.736546449076462e-05,
+      "loss": 0.651012122631073,
+      "step": 2442
+    },
+    {
+      "epoch": 1.054368932038835,
+      "grad_norm": 1.136838674545288,
+      "learning_rate": 9.735759386431671e-05,
+      "loss": 0.681246817111969,
+      "step": 2444
+    },
+    {
+      "epoch": 1.0552319309600864,
+      "grad_norm": 1.177869200706482,
+      "learning_rate": 9.734971181779854e-05,
+      "loss": 0.7331019639968872,
+      "step": 2446
+    },
+    {
+      "epoch": 1.0560949298813376,
+      "grad_norm": 1.2983415126800537,
+      "learning_rate": 9.73418183531108e-05,
+      "loss": 0.7316935658454895,
+      "step": 2448
+    },
+    {
+      "epoch": 1.056957928802589,
+      "grad_norm": 1.1189959049224854,
+      "learning_rate": 9.733391347215699e-05,
+      "loss": 0.6513608694076538,
+      "step": 2450
+    },
+    {
+      "epoch": 1.0578209277238404,
+      "grad_norm": 1.3256937265396118,
+      "learning_rate": 9.732599717684334e-05,
+      "loss": 0.6469123363494873,
+      "step": 2452
+    },
+    {
+      "epoch": 1.0586839266450916,
+      "grad_norm": 0.9766954779624939,
+      "learning_rate": 9.731806946907881e-05,
+      "loss": 0.5860153436660767,
+      "step": 2454
+    },
+    {
+      "epoch": 1.059546925566343,
+      "grad_norm": 1.1360441446304321,
+      "learning_rate": 9.731013035077514e-05,
+      "loss": 0.6783872842788696,
+      "step": 2456
+    },
+    {
+      "epoch": 1.0604099244875944,
+      "grad_norm": 1.3483080863952637,
+      "learning_rate": 9.73021798238468e-05,
+      "loss": 0.7894490361213684,
+      "step": 2458
+    },
+    {
+      "epoch": 1.0612729234088458,
+      "grad_norm": 1.1412159204483032,
+      "learning_rate": 9.729421789021105e-05,
+      "loss": 0.7098361849784851,
+      "step": 2460
+    },
+    {
+      "epoch": 1.062135922330097,
+      "grad_norm": 1.2670512199401855,
+      "learning_rate": 9.728624455178785e-05,
+      "loss": 0.7138097286224365,
+      "step": 2462
+    },
+    {
+      "epoch": 1.0629989212513484,
+      "grad_norm": 1.2577205896377563,
+      "learning_rate": 9.727825981049994e-05,
+      "loss": 0.7136340141296387,
+      "step": 2464
+    },
+    {
+      "epoch": 1.0638619201725998,
+      "grad_norm": 1.098997712135315,
+      "learning_rate": 9.727026366827283e-05,
+      "loss": 0.6273087859153748,
+      "step": 2466
+    },
+    {
+      "epoch": 1.064724919093851,
+      "grad_norm": 1.1550003290176392,
+      "learning_rate": 9.72622561270347e-05,
+      "loss": 0.7076449394226074,
+      "step": 2468
+    },
+    {
+      "epoch": 1.0655879180151024,
+      "grad_norm": 1.0861129760742188,
+      "learning_rate": 9.725423718871659e-05,
+      "loss": 0.6856985092163086,
+      "step": 2470
+    },
+    {
+      "epoch": 1.0664509169363539,
+      "grad_norm": 1.2742570638656616,
+      "learning_rate": 9.724620685525219e-05,
+      "loss": 0.7311446070671082,
+      "step": 2472
+    },
+    {
+      "epoch": 1.0673139158576053,
+      "grad_norm": 1.504339337348938,
+      "learning_rate": 9.7238165128578e-05,
+      "loss": 0.7728472948074341,
+      "step": 2474
+    },
+    {
+      "epoch": 1.0681769147788565,
+      "grad_norm": 1.2232030630111694,
+      "learning_rate": 9.723011201063323e-05,
+      "loss": 0.6259000301361084,
+      "step": 2476
+    },
+    {
+      "epoch": 1.0690399137001079,
+      "grad_norm": 1.3238953351974487,
+      "learning_rate": 9.722204750335989e-05,
+      "loss": 0.7132798433303833,
+      "step": 2478
+    },
+    {
+      "epoch": 1.0699029126213593,
+      "grad_norm": 1.2286484241485596,
+      "learning_rate": 9.721397160870265e-05,
+      "loss": 0.6067986488342285,
+      "step": 2480
+    },
+    {
+      "epoch": 1.0707659115426105,
+      "grad_norm": 1.3101580142974854,
+      "learning_rate": 9.7205884328609e-05,
+      "loss": 0.6884648203849792,
+      "step": 2482
+    },
+    {
+      "epoch": 1.0716289104638619,
+      "grad_norm": 1.437833309173584,
+      "learning_rate": 9.719778566502915e-05,
+      "loss": 0.7164831757545471,
+      "step": 2484
+    },
+    {
+      "epoch": 1.0724919093851133,
+      "grad_norm": 1.0980390310287476,
+      "learning_rate": 9.718967561991606e-05,
+      "loss": 0.6326627731323242,
+      "step": 2486
+    },
+    {
+      "epoch": 1.0733549083063647,
+      "grad_norm": 0.9919570088386536,
+      "learning_rate": 9.718155419522543e-05,
+      "loss": 0.5712647438049316,
+      "step": 2488
+    },
+    {
+      "epoch": 1.074217907227616,
+      "grad_norm": 1.0773793458938599,
+      "learning_rate": 9.717342139291569e-05,
+      "loss": 0.6923331022262573,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0750809061488673,
+      "grad_norm": 1.1553318500518799,
+      "learning_rate": 9.716527721494805e-05,
+      "loss": 0.6737485527992249,
+      "step": 2492
+    },
+    {
+      "epoch": 1.0759439050701187,
+      "grad_norm": 1.112865924835205,
+      "learning_rate": 9.715712166328644e-05,
+      "loss": 0.6422063708305359,
+      "step": 2494
+    },
+    {
+      "epoch": 1.07680690399137,
+      "grad_norm": 1.0651512145996094,
+      "learning_rate": 9.71489547398975e-05,
+      "loss": 0.6399799585342407,
+      "step": 2496
+    },
+    {
+      "epoch": 1.0776699029126213,
+      "grad_norm": 1.1394895315170288,
+      "learning_rate": 9.71407764467507e-05,
+      "loss": 0.6218312382698059,
+      "step": 2498
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "grad_norm": 1.3323278427124023,
+      "learning_rate": 9.713258678581815e-05,
+      "loss": 0.65947425365448,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "eval_loss": 0.7294915914535522,
+      "eval_runtime": 836.4643,
+      "eval_samples_per_second": 2.463,
+      "eval_steps_per_second": 2.463,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0793959007551241,
+      "grad_norm": 1.3122533559799194,
+      "learning_rate": 9.712438575907479e-05,
+      "loss": 0.66681307554245,
+      "step": 2502
+    },
+    {
+      "epoch": 1.0802588996763753,
+      "grad_norm": 1.3631974458694458,
+      "learning_rate": 9.711617336849824e-05,
+      "loss": 0.6926553249359131,
+      "step": 2504
+    },
+    {
+      "epoch": 1.0811218985976268,
+      "grad_norm": 1.2383692264556885,
+      "learning_rate": 9.710794961606886e-05,
+      "loss": 0.6706596612930298,
+      "step": 2506
+    },
+    {
+      "epoch": 1.0819848975188782,
+      "grad_norm": 1.1660504341125488,
+      "learning_rate": 9.709971450376982e-05,
+      "loss": 0.6011359095573425,
+      "step": 2508
+    },
+    {
+      "epoch": 1.0828478964401294,
+      "grad_norm": 1.3021246194839478,
+      "learning_rate": 9.709146803358693e-05,
+      "loss": 0.689009428024292,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0837108953613808,
+      "grad_norm": 1.0553252696990967,
+      "learning_rate": 9.708321020750883e-05,
+      "loss": 0.6216740012168884,
+      "step": 2512
+    },
+    {
+      "epoch": 1.0845738942826322,
+      "grad_norm": 1.1862177848815918,
+      "learning_rate": 9.707494102752683e-05,
+      "loss": 0.6439616680145264,
+      "step": 2514
+    },
+    {
+      "epoch": 1.0854368932038836,
+      "grad_norm": 1.1166558265686035,
+      "learning_rate": 9.706666049563504e-05,
+      "loss": 0.6825361251831055,
+      "step": 2516
+    },
+    {
+      "epoch": 1.0862998921251348,
+      "grad_norm": 1.128812551498413,
+      "learning_rate": 9.705836861383022e-05,
+      "loss": 0.6471308469772339,
+      "step": 2518
+    },
+    {
+      "epoch": 1.0871628910463862,
+      "grad_norm": 1.324802279472351,
+      "learning_rate": 9.705006538411197e-05,
+      "loss": 0.6535511016845703,
+      "step": 2520
+    },
+    {
+      "epoch": 1.0880258899676376,
+      "grad_norm": 1.3586591482162476,
+      "learning_rate": 9.704175080848255e-05,
+      "loss": 0.678022563457489,
+      "step": 2522
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 1.1334232091903687,
+      "learning_rate": 9.703342488894697e-05,
+      "loss": 0.5904073119163513,
+      "step": 2524
+    },
+    {
+      "epoch": 1.0897518878101402,
+      "grad_norm": 1.182215929031372,
+      "learning_rate": 9.702508762751303e-05,
+      "loss": 0.6072601079940796,
+      "step": 2526
+    },
+    {
+      "epoch": 1.0906148867313916,
+      "grad_norm": 1.2525769472122192,
+      "learning_rate": 9.701673902619119e-05,
+      "loss": 0.6752429604530334,
+      "step": 2528
+    },
+    {
+      "epoch": 1.091477885652643,
+      "grad_norm": 1.2811026573181152,
+      "learning_rate": 9.70083790869947e-05,
+      "loss": 0.7192611694335938,
+      "step": 2530
+    },
+    {
+      "epoch": 1.0923408845738942,
+      "grad_norm": 1.1434061527252197,
+      "learning_rate": 9.700000781193949e-05,
+      "loss": 0.6991751194000244,
+      "step": 2532
+    },
+    {
+      "epoch": 1.0932038834951456,
+      "grad_norm": 1.26658296585083,
+      "learning_rate": 9.699162520304428e-05,
+      "loss": 0.7010498046875,
+      "step": 2534
+    },
+    {
+      "epoch": 1.094066882416397,
+      "grad_norm": 1.2083529233932495,
+      "learning_rate": 9.698323126233048e-05,
+      "loss": 0.6945615410804749,
+      "step": 2536
+    },
+    {
+      "epoch": 1.0949298813376482,
+      "grad_norm": 1.2064114809036255,
+      "learning_rate": 9.697482599182227e-05,
+      "loss": 0.689496636390686,
+      "step": 2538
+    },
+    {
+      "epoch": 1.0957928802588996,
+      "grad_norm": 1.17113196849823,
+      "learning_rate": 9.696640939354655e-05,
+      "loss": 0.6966884136199951,
+      "step": 2540
+    },
+    {
+      "epoch": 1.096655879180151,
+      "grad_norm": 1.1551356315612793,
+      "learning_rate": 9.695798146953291e-05,
+      "loss": 0.6524666547775269,
+      "step": 2542
+    },
+    {
+      "epoch": 1.0975188781014025,
+      "grad_norm": 1.0966521501541138,
+      "learning_rate": 9.694954222181374e-05,
+      "loss": 0.5769726037979126,
+      "step": 2544
+    },
+    {
+      "epoch": 1.0983818770226537,
+      "grad_norm": 1.320669174194336,
+      "learning_rate": 9.694109165242411e-05,
+      "loss": 0.6986333727836609,
+      "step": 2546
+    },
+    {
+      "epoch": 1.099244875943905,
+      "grad_norm": 1.1678471565246582,
+      "learning_rate": 9.693262976340183e-05,
+      "loss": 0.7014455199241638,
+      "step": 2548
+    },
+    {
+      "epoch": 1.1001078748651565,
+      "grad_norm": 1.1527155637741089,
+      "learning_rate": 9.692415655678745e-05,
+      "loss": 0.5786730647087097,
+      "step": 2550
+    },
+    {
+      "epoch": 1.1009708737864077,
+      "grad_norm": 1.2511217594146729,
+      "learning_rate": 9.691567203462428e-05,
+      "loss": 0.755945086479187,
+      "step": 2552
+    },
+    {
+      "epoch": 1.101833872707659,
+      "grad_norm": 1.0910221338272095,
+      "learning_rate": 9.690717619895828e-05,
+      "loss": 0.6487610936164856,
+      "step": 2554
+    },
+    {
+      "epoch": 1.1026968716289105,
+      "grad_norm": 1.3682197332382202,
+      "learning_rate": 9.68986690518382e-05,
+      "loss": 0.6346665024757385,
+      "step": 2556
+    },
+    {
+      "epoch": 1.103559870550162,
+      "grad_norm": 1.2161564826965332,
+      "learning_rate": 9.68901505953155e-05,
+      "loss": 0.647144615650177,
+      "step": 2558
+    },
+    {
+      "epoch": 1.104422869471413,
+      "grad_norm": 1.2559088468551636,
+      "learning_rate": 9.688162083144436e-05,
+      "loss": 0.6461755633354187,
+      "step": 2560
+    },
+    {
+      "epoch": 1.1052858683926645,
+      "grad_norm": 1.1260225772857666,
+      "learning_rate": 9.68730797622817e-05,
+      "loss": 0.6888763904571533,
+      "step": 2562
+    },
+    {
+      "epoch": 1.106148867313916,
+      "grad_norm": 1.1499868631362915,
+      "learning_rate": 9.686452738988716e-05,
+      "loss": 0.6318327784538269,
+      "step": 2564
+    },
+    {
+      "epoch": 1.1070118662351671,
+      "grad_norm": 1.1775025129318237,
+      "learning_rate": 9.68559637163231e-05,
+      "loss": 0.6538340449333191,
+      "step": 2566
+    },
+    {
+      "epoch": 1.1078748651564185,
+      "grad_norm": 1.264656901359558,
+      "learning_rate": 9.684738874365465e-05,
+      "loss": 0.6706726551055908,
+      "step": 2568
+    },
+    {
+      "epoch": 1.10873786407767,
+      "grad_norm": 1.1130270957946777,
+      "learning_rate": 9.683880247394956e-05,
+      "loss": 0.7573289275169373,
+      "step": 2570
+    },
+    {
+      "epoch": 1.1096008629989211,
+      "grad_norm": 1.2781217098236084,
+      "learning_rate": 9.683020490927841e-05,
+      "loss": 0.6603306531906128,
+      "step": 2572
+    },
+    {
+      "epoch": 1.1104638619201725,
+      "grad_norm": 1.251062035560608,
+      "learning_rate": 9.682159605171446e-05,
+      "loss": 0.6523779630661011,
+      "step": 2574
+    },
+    {
+      "epoch": 1.111326860841424,
+      "grad_norm": 1.2631903886795044,
+      "learning_rate": 9.68129759033337e-05,
+      "loss": 0.677550733089447,
+      "step": 2576
+    },
+    {
+      "epoch": 1.1121898597626754,
+      "grad_norm": 1.0212602615356445,
+      "learning_rate": 9.680434446621483e-05,
+      "loss": 0.666540801525116,
+      "step": 2578
+    },
+    {
+      "epoch": 1.1130528586839266,
+      "grad_norm": 1.221718430519104,
+      "learning_rate": 9.679570174243929e-05,
+      "loss": 0.7467086315155029,
+      "step": 2580
+    },
+    {
+      "epoch": 1.113915857605178,
+      "grad_norm": 1.1175146102905273,
+      "learning_rate": 9.678704773409124e-05,
+      "loss": 0.673492968082428,
+      "step": 2582
+    },
+    {
+      "epoch": 1.1147788565264294,
+      "grad_norm": 1.1274988651275635,
+      "learning_rate": 9.677838244325754e-05,
+      "loss": 0.5724847912788391,
+      "step": 2584
+    },
+    {
+      "epoch": 1.1156418554476808,
+      "grad_norm": 1.297654390335083,
+      "learning_rate": 9.676970587202779e-05,
+      "loss": 0.634985625743866,
+      "step": 2586
+    },
+    {
+      "epoch": 1.116504854368932,
+      "grad_norm": 1.1908061504364014,
+      "learning_rate": 9.67610180224943e-05,
+      "loss": 0.6813890933990479,
+      "step": 2588
+    },
+    {
+      "epoch": 1.1173678532901834,
+      "grad_norm": 1.1787118911743164,
+      "learning_rate": 9.675231889675212e-05,
+      "loss": 0.6738101243972778,
+      "step": 2590
+    },
+    {
+      "epoch": 1.1182308522114348,
+      "grad_norm": 1.1327152252197266,
+      "learning_rate": 9.674360849689899e-05,
+      "loss": 0.6662938594818115,
+      "step": 2592
+    },
+    {
+      "epoch": 1.119093851132686,
+      "grad_norm": 1.1246299743652344,
+      "learning_rate": 9.67348868250354e-05,
+      "loss": 0.677423357963562,
+      "step": 2594
+    },
+    {
+      "epoch": 1.1199568500539374,
+      "grad_norm": 1.1411702632904053,
+      "learning_rate": 9.672615388326454e-05,
+      "loss": 0.6257020235061646,
+      "step": 2596
+    },
+    {
+      "epoch": 1.1208198489751888,
+      "grad_norm": 1.1607346534729004,
+      "learning_rate": 9.671740967369231e-05,
+      "loss": 0.7029470205307007,
+      "step": 2598
+    },
+    {
+      "epoch": 1.12168284789644,
+      "grad_norm": 1.047934651374817,
+      "learning_rate": 9.670865419842735e-05,
+      "loss": 0.6040990352630615,
+      "step": 2600
+    },
+    {
+      "epoch": 1.12168284789644,
+      "eval_loss": 0.7287447452545166,
+      "eval_runtime": 831.8138,
+      "eval_samples_per_second": 2.477,
+      "eval_steps_per_second": 2.477,
+      "step": 2600
+    },
+    {
+      "epoch": 1.1225458468176914,
+      "grad_norm": 1.0571783781051636,
+      "learning_rate": 9.669988745958098e-05,
+      "loss": 0.6872879266738892,
+      "step": 2602
+    },
+    {
+      "epoch": 1.1234088457389428,
+      "grad_norm": 1.0940403938293457,
+      "learning_rate": 9.669110945926727e-05,
+      "loss": 0.6173275113105774,
+      "step": 2604
+    },
+    {
+      "epoch": 1.1242718446601943,
+      "grad_norm": 1.1180222034454346,
+      "learning_rate": 9.6682320199603e-05,
+      "loss": 0.6142664551734924,
+      "step": 2606
+    },
+    {
+      "epoch": 1.1251348435814454,
+      "grad_norm": 1.251098871231079,
+      "learning_rate": 9.667351968270768e-05,
+      "loss": 0.7225713133811951,
+      "step": 2608
+    },
+    {
+      "epoch": 1.1259978425026969,
+      "grad_norm": 1.2333059310913086,
+      "learning_rate": 9.666470791070347e-05,
+      "loss": 0.6830481290817261,
+      "step": 2610
+    },
+    {
+      "epoch": 1.1268608414239483,
+      "grad_norm": 1.2904123067855835,
+      "learning_rate": 9.665588488571531e-05,
+      "loss": 0.6835238337516785,
+      "step": 2612
+    },
+    {
+      "epoch": 1.1277238403451997,
+      "grad_norm": 1.4779443740844727,
+      "learning_rate": 9.664705060987085e-05,
+      "loss": 0.6993544697761536,
+      "step": 2614
+    },
+    {
+      "epoch": 1.1285868392664509,
+      "grad_norm": 1.267021656036377,
+      "learning_rate": 9.663820508530042e-05,
+      "loss": 0.6819394826889038,
+      "step": 2616
+    },
+    {
+      "epoch": 1.1294498381877023,
+      "grad_norm": 1.0755046606063843,
+      "learning_rate": 9.662934831413708e-05,
+      "loss": 0.6200308799743652,
+      "step": 2618
+    },
+    {
+      "epoch": 1.1303128371089537,
+      "grad_norm": 1.2043033838272095,
+      "learning_rate": 9.66204802985166e-05,
+      "loss": 0.7138658165931702,
+      "step": 2620
+    },
+    {
+      "epoch": 1.1311758360302049,
+      "grad_norm": 1.2641128301620483,
+      "learning_rate": 9.661160104057744e-05,
+      "loss": 0.7238332033157349,
+      "step": 2622
+    },
+    {
+      "epoch": 1.1320388349514563,
+      "grad_norm": 1.0422990322113037,
+      "learning_rate": 9.660271054246085e-05,
+      "loss": 0.6401007175445557,
+      "step": 2624
+    },
+    {
+      "epoch": 1.1329018338727077,
+      "grad_norm": 1.2298130989074707,
+      "learning_rate": 9.659380880631068e-05,
+      "loss": 0.6305879950523376,
+      "step": 2626
+    },
+    {
+      "epoch": 1.133764832793959,
+      "grad_norm": 1.254573106765747,
+      "learning_rate": 9.658489583427357e-05,
+      "loss": 0.5751872062683105,
+      "step": 2628
+    },
+    {
+      "epoch": 1.1346278317152103,
+      "grad_norm": 1.15679132938385,
+      "learning_rate": 9.657597162849883e-05,
+      "loss": 0.6629595756530762,
+      "step": 2630
+    },
+    {
+      "epoch": 1.1354908306364617,
+      "grad_norm": 1.193629264831543,
+      "learning_rate": 9.656703619113849e-05,
+      "loss": 0.6832258105278015,
+      "step": 2632
+    },
+    {
+      "epoch": 1.1363538295577131,
+      "grad_norm": 1.2330398559570312,
+      "learning_rate": 9.655808952434732e-05,
+      "loss": 0.6823931932449341,
+      "step": 2634
+    },
+    {
+      "epoch": 1.1372168284789643,
+      "grad_norm": 1.3926069736480713,
+      "learning_rate": 9.654913163028272e-05,
+      "loss": 0.6671395897865295,
+      "step": 2636
+    },
+    {
+      "epoch": 1.1380798274002157,
+      "grad_norm": 1.2995383739471436,
+      "learning_rate": 9.65401625111049e-05,
+      "loss": 0.662219226360321,
+      "step": 2638
+    },
+    {
+      "epoch": 1.1389428263214671,
+      "grad_norm": 1.1584415435791016,
+      "learning_rate": 9.653118216897667e-05,
+      "loss": 0.6419461965560913,
+      "step": 2640
+    },
+    {
+      "epoch": 1.1398058252427186,
+      "grad_norm": 1.3584444522857666,
+      "learning_rate": 9.652219060606364e-05,
+      "loss": 0.6844428181648254,
+      "step": 2642
+    },
+    {
+      "epoch": 1.1406688241639698,
+      "grad_norm": 1.2619858980178833,
+      "learning_rate": 9.651318782453407e-05,
+      "loss": 0.6761999130249023,
+      "step": 2644
+    },
+    {
+      "epoch": 1.1415318230852212,
+      "grad_norm": 1.2202177047729492,
+      "learning_rate": 9.650417382655892e-05,
+      "loss": 0.7258123159408569,
+      "step": 2646
+    },
+    {
+      "epoch": 1.1423948220064726,
+      "grad_norm": 1.0225578546524048,
+      "learning_rate": 9.64951486143119e-05,
+      "loss": 0.5709917545318604,
+      "step": 2648
+    },
+    {
+      "epoch": 1.1432578209277238,
+      "grad_norm": 1.0961005687713623,
+      "learning_rate": 9.64861121899694e-05,
+      "loss": 0.7353709936141968,
+      "step": 2650
+    },
+    {
+      "epoch": 1.1441208198489752,
+      "grad_norm": 0.9393200874328613,
+      "learning_rate": 9.64770645557105e-05,
+      "loss": 0.7083833813667297,
+      "step": 2652
+    },
+    {
+      "epoch": 1.1449838187702266,
+      "grad_norm": 1.089733362197876,
+      "learning_rate": 9.646800571371701e-05,
+      "loss": 0.6405303478240967,
+      "step": 2654
+    },
+    {
+      "epoch": 1.1458468176914778,
+      "grad_norm": 1.1581398248672485,
+      "learning_rate": 9.645893566617341e-05,
+      "loss": 0.617733359336853,
+      "step": 2656
+    },
+    {
+      "epoch": 1.1467098166127292,
+      "grad_norm": 1.1336220502853394,
+      "learning_rate": 9.644985441526693e-05,
+      "loss": 0.6948232650756836,
+      "step": 2658
+    },
+    {
+      "epoch": 1.1475728155339806,
+      "grad_norm": 1.028591513633728,
+      "learning_rate": 9.644076196318743e-05,
+      "loss": 0.6392919421195984,
+      "step": 2660
+    },
+    {
+      "epoch": 1.148435814455232,
+      "grad_norm": 1.2088173627853394,
+      "learning_rate": 9.643165831212756e-05,
+      "loss": 0.6384931206703186,
+      "step": 2662
+    },
+    {
+      "epoch": 1.1492988133764832,
+      "grad_norm": 0.9905838966369629,
+      "learning_rate": 9.642254346428259e-05,
+      "loss": 0.5909387469291687,
+      "step": 2664
+    },
+    {
+      "epoch": 1.1501618122977346,
+      "grad_norm": 1.1670424938201904,
+      "learning_rate": 9.641341742185054e-05,
+      "loss": 0.700904130935669,
+      "step": 2666
+    },
+    {
+      "epoch": 1.151024811218986,
+      "grad_norm": 1.164746880531311,
+      "learning_rate": 9.640428018703211e-05,
+      "loss": 0.6036953330039978,
+      "step": 2668
+    },
+    {
+      "epoch": 1.1518878101402374,
+      "grad_norm": 1.00895357131958,
+      "learning_rate": 9.639513176203072e-05,
+      "loss": 0.6158549785614014,
+      "step": 2670
+    },
+    {
+      "epoch": 1.1527508090614886,
+      "grad_norm": 1.2236207723617554,
+      "learning_rate": 9.638597214905244e-05,
+      "loss": 0.7280431389808655,
+      "step": 2672
+    },
+    {
+      "epoch": 1.15361380798274,
+      "grad_norm": 1.0930732488632202,
+      "learning_rate": 9.637680135030609e-05,
+      "loss": 0.6434410810470581,
+      "step": 2674
+    },
+    {
+      "epoch": 1.1544768069039915,
+      "grad_norm": 1.366325855255127,
+      "learning_rate": 9.636761936800315e-05,
+      "loss": 0.6771191954612732,
+      "step": 2676
+    },
+    {
+      "epoch": 1.1553398058252426,
+      "grad_norm": 2.249835968017578,
+      "learning_rate": 9.635842620435785e-05,
+      "loss": 0.6382432579994202,
+      "step": 2678
+    },
+    {
+      "epoch": 1.156202804746494,
+      "grad_norm": 1.274483561515808,
+      "learning_rate": 9.634922186158704e-05,
+      "loss": 0.6733657121658325,
+      "step": 2680
+    },
+    {
+      "epoch": 1.1570658036677455,
+      "grad_norm": 1.3715782165527344,
+      "learning_rate": 9.634000634191033e-05,
+      "loss": 0.7601200938224792,
+      "step": 2682
+    },
+    {
+      "epoch": 1.1579288025889967,
+      "grad_norm": 1.1312460899353027,
+      "learning_rate": 9.633077964754998e-05,
+      "loss": 0.5959098935127258,
+      "step": 2684
+    },
+    {
+      "epoch": 1.158791801510248,
+      "grad_norm": 1.063233494758606,
+      "learning_rate": 9.632154178073098e-05,
+      "loss": 0.615096926689148,
+      "step": 2686
+    },
+    {
+      "epoch": 1.1596548004314995,
+      "grad_norm": 1.074887752532959,
+      "learning_rate": 9.6312292743681e-05,
+      "loss": 0.6553784608840942,
+      "step": 2688
+    },
+    {
+      "epoch": 1.160517799352751,
+      "grad_norm": 1.17954683303833,
+      "learning_rate": 9.630303253863042e-05,
+      "loss": 0.6963269114494324,
+      "step": 2690
+    },
+    {
+      "epoch": 1.161380798274002,
+      "grad_norm": 1.2549158334732056,
+      "learning_rate": 9.629376116781226e-05,
+      "loss": 0.6633999347686768,
+      "step": 2692
+    },
+    {
+      "epoch": 1.1622437971952535,
+      "grad_norm": 1.237196683883667,
+      "learning_rate": 9.628447863346229e-05,
+      "loss": 0.6727597117424011,
+      "step": 2694
+    },
+    {
+      "epoch": 1.163106796116505,
+      "grad_norm": 1.4047741889953613,
+      "learning_rate": 9.627518493781895e-05,
+      "loss": 0.7018169164657593,
+      "step": 2696
+    },
+    {
+      "epoch": 1.1639697950377563,
+      "grad_norm": 1.15412175655365,
+      "learning_rate": 9.626588008312339e-05,
+      "loss": 0.6566510796546936,
+      "step": 2698
+    },
+    {
+      "epoch": 1.1648327939590075,
+      "grad_norm": 1.194110631942749,
+      "learning_rate": 9.625656407161938e-05,
+      "loss": 0.7017931342124939,
+      "step": 2700
+    },
+    {
+      "epoch": 1.1648327939590075,
+      "eval_loss": 0.72404944896698,
+      "eval_runtime": 824.2877,
+      "eval_samples_per_second": 2.499,
+      "eval_steps_per_second": 2.499,
+      "step": 2700
+    },
+    {
+      "epoch": 1.165695792880259,
+      "grad_norm": 1.1512954235076904,
+      "learning_rate": 9.62472369055535e-05,
+      "loss": 0.7058532238006592,
+      "step": 2702
+    },
+    {
+      "epoch": 1.1665587918015103,
+      "grad_norm": 1.4743460416793823,
+      "learning_rate": 9.623789858717492e-05,
+      "loss": 0.7458376288414001,
+      "step": 2704
+    },
+    {
+      "epoch": 1.1674217907227615,
+      "grad_norm": 1.0526450872421265,
+      "learning_rate": 9.622854911873551e-05,
+      "loss": 0.6526424288749695,
+      "step": 2706
+    },
+    {
+      "epoch": 1.168284789644013,
+      "grad_norm": 1.0408949851989746,
+      "learning_rate": 9.62191885024899e-05,
+      "loss": 0.6055451035499573,
+      "step": 2708
+    },
+    {
+      "epoch": 1.1691477885652644,
+      "grad_norm": 1.214052677154541,
+      "learning_rate": 9.620981674069534e-05,
+      "loss": 0.666462779045105,
+      "step": 2710
+    },
+    {
+      "epoch": 1.1700107874865155,
+      "grad_norm": 1.2526963949203491,
+      "learning_rate": 9.62004338356118e-05,
+      "loss": 0.7208677530288696,
+      "step": 2712
+    },
+    {
+      "epoch": 1.170873786407767,
+      "grad_norm": 1.2097395658493042,
+      "learning_rate": 9.61910397895019e-05,
+      "loss": 0.6269269585609436,
+      "step": 2714
+    },
+    {
+      "epoch": 1.1717367853290184,
+      "grad_norm": 1.035733699798584,
+      "learning_rate": 9.618163460463096e-05,
+      "loss": 0.6063299179077148,
+      "step": 2716
+    },
+    {
+      "epoch": 1.1725997842502698,
+      "grad_norm": 1.2881336212158203,
+      "learning_rate": 9.617221828326706e-05,
+      "loss": 0.7084641456604004,
+      "step": 2718
+    },
+    {
+      "epoch": 1.173462783171521,
+      "grad_norm": 1.2808257341384888,
+      "learning_rate": 9.616279082768085e-05,
+      "loss": 0.6515718102455139,
+      "step": 2720
+    },
+    {
+      "epoch": 1.1743257820927724,
+      "grad_norm": 1.1174249649047852,
+      "learning_rate": 9.615335224014574e-05,
+      "loss": 0.6745902299880981,
+      "step": 2722
+    },
+    {
+      "epoch": 1.1751887810140238,
+      "grad_norm": 1.1222290992736816,
+      "learning_rate": 9.61439025229378e-05,
+      "loss": 0.6824861168861389,
+      "step": 2724
+    },
+    {
+      "epoch": 1.176051779935275,
+      "grad_norm": 1.156187891960144,
+      "learning_rate": 9.613444167833579e-05,
+      "loss": 0.6020817160606384,
+      "step": 2726
+    },
+    {
+      "epoch": 1.1769147788565264,
+      "grad_norm": 1.2502888441085815,
+      "learning_rate": 9.612496970862113e-05,
+      "loss": 0.6430572271347046,
+      "step": 2728
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 1.6157052516937256,
+      "learning_rate": 9.611548661607797e-05,
+      "loss": 0.7195103168487549,
+      "step": 2730
+    },
+    {
+      "epoch": 1.1786407766990292,
+      "grad_norm": 1.3196234703063965,
+      "learning_rate": 9.610599240299308e-05,
+      "loss": 0.710418164730072,
+      "step": 2732
+    },
+    {
+      "epoch": 1.1795037756202804,
+      "grad_norm": 1.2117719650268555,
+      "learning_rate": 9.6096487071656e-05,
+      "loss": 0.650095522403717,
+      "step": 2734
+    },
+    {
+      "epoch": 1.1803667745415318,
+      "grad_norm": 2.2723631858825684,
+      "learning_rate": 9.608697062435884e-05,
+      "loss": 0.7150285243988037,
+      "step": 2736
+    },
+    {
+      "epoch": 1.1812297734627832,
+      "grad_norm": 1.0523152351379395,
+      "learning_rate": 9.607744306339647e-05,
+      "loss": 0.6271997690200806,
+      "step": 2738
+    },
+    {
+      "epoch": 1.1820927723840344,
+      "grad_norm": 1.2567129135131836,
+      "learning_rate": 9.606790439106646e-05,
+      "loss": 0.659799337387085,
+      "step": 2740
+    },
+    {
+      "epoch": 1.1829557713052858,
+      "grad_norm": 1.1448849439620972,
+      "learning_rate": 9.605835460966896e-05,
+      "loss": 0.7097326517105103,
+      "step": 2742
+    },
+    {
+      "epoch": 1.1838187702265373,
+      "grad_norm": 1.3698351383209229,
+      "learning_rate": 9.604879372150688e-05,
+      "loss": 0.6692788004875183,
+      "step": 2744
+    },
+    {
+      "epoch": 1.1846817691477884,
+      "grad_norm": 1.1424204111099243,
+      "learning_rate": 9.603922172888577e-05,
+      "loss": 0.6453474760055542,
+      "step": 2746
+    },
+    {
+      "epoch": 1.1855447680690399,
+      "grad_norm": 1.2701301574707031,
+      "learning_rate": 9.60296386341139e-05,
+      "loss": 0.6197408437728882,
+      "step": 2748
+    },
+    {
+      "epoch": 1.1864077669902913,
+      "grad_norm": 1.1171884536743164,
+      "learning_rate": 9.602004443950217e-05,
+      "loss": 0.6525035500526428,
+      "step": 2750
+    },
+    {
+      "epoch": 1.1872707659115427,
+      "grad_norm": 1.132633090019226,
+      "learning_rate": 9.60104391473642e-05,
+      "loss": 0.6459797620773315,
+      "step": 2752
+    },
+    {
+      "epoch": 1.1881337648327939,
+      "grad_norm": 1.1362011432647705,
+      "learning_rate": 9.600082276001623e-05,
+      "loss": 0.6175895929336548,
+      "step": 2754
+    },
+    {
+      "epoch": 1.1889967637540453,
+      "grad_norm": 1.1216920614242554,
+      "learning_rate": 9.599119527977722e-05,
+      "loss": 0.6782001852989197,
+      "step": 2756
+    },
+    {
+      "epoch": 1.1898597626752967,
+      "grad_norm": 1.024833083152771,
+      "learning_rate": 9.59815567089688e-05,
+      "loss": 0.6387497782707214,
+      "step": 2758
+    },
+    {
+      "epoch": 1.190722761596548,
+      "grad_norm": 1.3539615869522095,
+      "learning_rate": 9.597190704991527e-05,
+      "loss": 0.6974280476570129,
+      "step": 2760
+    },
+    {
+      "epoch": 1.1915857605177993,
+      "grad_norm": 1.002167820930481,
+      "learning_rate": 9.59622463049436e-05,
+      "loss": 0.6039770245552063,
+      "step": 2762
+    },
+    {
+      "epoch": 1.1924487594390507,
+      "grad_norm": 1.150636076927185,
+      "learning_rate": 9.595257447638343e-05,
+      "loss": 0.6543651819229126,
+      "step": 2764
+    },
+    {
+      "epoch": 1.1933117583603021,
+      "grad_norm": 1.413001537322998,
+      "learning_rate": 9.594289156656709e-05,
+      "loss": 0.7388567328453064,
+      "step": 2766
+    },
+    {
+      "epoch": 1.1941747572815533,
+      "grad_norm": 1.2041958570480347,
+      "learning_rate": 9.593319757782955e-05,
+      "loss": 0.7128161191940308,
+      "step": 2768
+    },
+    {
+      "epoch": 1.1950377562028047,
+      "grad_norm": 1.2151374816894531,
+      "learning_rate": 9.592349251250847e-05,
+      "loss": 0.6593868136405945,
+      "step": 2770
+    },
+    {
+      "epoch": 1.1959007551240561,
+      "grad_norm": 1.6225353479385376,
+      "learning_rate": 9.59137763729442e-05,
+      "loss": 0.6128022074699402,
+      "step": 2772
+    },
+    {
+      "epoch": 1.1967637540453073,
+      "grad_norm": 1.1904171705245972,
+      "learning_rate": 9.590404916147976e-05,
+      "loss": 0.6537567377090454,
+      "step": 2774
+    },
+    {
+      "epoch": 1.1976267529665587,
+      "grad_norm": 1.159506916999817,
+      "learning_rate": 9.589431088046079e-05,
+      "loss": 0.6325924396514893,
+      "step": 2776
+    },
+    {
+      "epoch": 1.1984897518878102,
+      "grad_norm": 1.1314560174942017,
+      "learning_rate": 9.588456153223565e-05,
+      "loss": 0.6438963413238525,
+      "step": 2778
+    },
+    {
+      "epoch": 1.1993527508090616,
+      "grad_norm": 1.0182478427886963,
+      "learning_rate": 9.587480111915532e-05,
+      "loss": 0.6703475117683411,
+      "step": 2780
+    },
+    {
+      "epoch": 1.2002157497303128,
+      "grad_norm": 1.5506517887115479,
+      "learning_rate": 9.586502964357352e-05,
+      "loss": 0.7694190144538879,
+      "step": 2782
+    },
+    {
+      "epoch": 1.2010787486515642,
+      "grad_norm": 1.0769826173782349,
+      "learning_rate": 9.585524710784659e-05,
+      "loss": 0.6117724180221558,
+      "step": 2784
+    },
+    {
+      "epoch": 1.2019417475728156,
+      "grad_norm": 1.207175850868225,
+      "learning_rate": 9.584545351433352e-05,
+      "loss": 0.6375927329063416,
+      "step": 2786
+    },
+    {
+      "epoch": 1.202804746494067,
+      "grad_norm": 1.1291100978851318,
+      "learning_rate": 9.583564886539602e-05,
+      "loss": 0.6526537537574768,
+      "step": 2788
+    },
+    {
+      "epoch": 1.2036677454153182,
+      "grad_norm": 1.3076926469802856,
+      "learning_rate": 9.582583316339843e-05,
+      "loss": 0.7080113887786865,
+      "step": 2790
+    },
+    {
+      "epoch": 1.2045307443365696,
+      "grad_norm": 1.166823148727417,
+      "learning_rate": 9.581600641070773e-05,
+      "loss": 0.6415606141090393,
+      "step": 2792
+    },
+    {
+      "epoch": 1.205393743257821,
+      "grad_norm": 1.1248292922973633,
+      "learning_rate": 9.580616860969364e-05,
+      "loss": 0.6538968086242676,
+      "step": 2794
+    },
+    {
+      "epoch": 1.2062567421790722,
+      "grad_norm": 1.406731128692627,
+      "learning_rate": 9.579631976272849e-05,
+      "loss": 0.694507896900177,
+      "step": 2796
+    },
+    {
+      "epoch": 1.2071197411003236,
+      "grad_norm": 1.185895562171936,
+      "learning_rate": 9.578645987218728e-05,
+      "loss": 0.7064871788024902,
+      "step": 2798
+    },
+    {
+      "epoch": 1.207982740021575,
+      "grad_norm": 1.0860708951950073,
+      "learning_rate": 9.577658894044768e-05,
+      "loss": 0.5790154933929443,
+      "step": 2800
+    },
+    {
+      "epoch": 1.207982740021575,
+      "eval_loss": 0.7220398187637329,
+      "eval_runtime": 831.5812,
+      "eval_samples_per_second": 2.477,
+      "eval_steps_per_second": 2.477,
+      "step": 2800
+    },
+    {
+      "epoch": 1.2088457389428262,
+      "grad_norm": 1.2761744260787964,
+      "learning_rate": 9.576670696989001e-05,
+      "loss": 0.6645335555076599,
+      "step": 2802
+    },
+    {
+      "epoch": 1.2097087378640776,
+      "grad_norm": 1.3502917289733887,
+      "learning_rate": 9.575681396289728e-05,
+      "loss": 0.6320346593856812,
+      "step": 2804
+    },
+    {
+      "epoch": 1.210571736785329,
+      "grad_norm": 1.2638593912124634,
+      "learning_rate": 9.574690992185514e-05,
+      "loss": 0.6297362446784973,
+      "step": 2806
+    },
+    {
+      "epoch": 1.2114347357065804,
+      "grad_norm": 1.0787774324417114,
+      "learning_rate": 9.573699484915189e-05,
+      "loss": 0.7569923996925354,
+      "step": 2808
+    },
+    {
+      "epoch": 1.2122977346278316,
+      "grad_norm": 1.097254991531372,
+      "learning_rate": 9.572706874717851e-05,
+      "loss": 0.6712964773178101,
+      "step": 2810
+    },
+    {
+      "epoch": 1.213160733549083,
+      "grad_norm": 1.0995726585388184,
+      "learning_rate": 9.571713161832865e-05,
+      "loss": 0.6775450706481934,
+      "step": 2812
+    },
+    {
+      "epoch": 1.2140237324703345,
+      "grad_norm": 1.7386797666549683,
+      "learning_rate": 9.570718346499859e-05,
+      "loss": 0.6691418290138245,
+      "step": 2814
+    },
+    {
+      "epoch": 1.2148867313915859,
+      "grad_norm": 1.2281049489974976,
+      "learning_rate": 9.569722428958728e-05,
+      "loss": 0.6406403183937073,
+      "step": 2816
+    },
+    {
+      "epoch": 1.215749730312837,
+      "grad_norm": 1.1326305866241455,
+      "learning_rate": 9.568725409449635e-05,
+      "loss": 0.7008584141731262,
+      "step": 2818
+    },
+    {
+      "epoch": 1.2166127292340885,
+      "grad_norm": 1.3039381504058838,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.7438415288925171,
+      "step": 2820
+    },
+    {
+      "epoch": 1.2174757281553399,
+      "grad_norm": 1.219136357307434,
+      "learning_rate": 9.566728065489531e-05,
+      "loss": 0.6937777996063232,
+      "step": 2822
+    },
+    {
+      "epoch": 1.218338727076591,
+      "grad_norm": 1.321285605430603,
+      "learning_rate": 9.56572774152017e-05,
+      "loss": 0.7586468458175659,
+      "step": 2824
+    },
+    {
+      "epoch": 1.2192017259978425,
+      "grad_norm": 1.3538484573364258,
+      "learning_rate": 9.564726316546147e-05,
+      "loss": 0.6356340050697327,
+      "step": 2826
+    },
+    {
+      "epoch": 1.220064724919094,
+      "grad_norm": 1.1015816926956177,
+      "learning_rate": 9.563723790808952e-05,
+      "loss": 0.6304616928100586,
+      "step": 2828
+    },
+    {
+      "epoch": 1.220927723840345,
+      "grad_norm": 0.9658390283584595,
+      "learning_rate": 9.562720164550337e-05,
+      "loss": 0.6459048986434937,
+      "step": 2830
+    },
+    {
+      "epoch": 1.2217907227615965,
+      "grad_norm": 1.3981443643569946,
+      "learning_rate": 9.561715438012323e-05,
+      "loss": 0.7034182548522949,
+      "step": 2832
+    },
+    {
+      "epoch": 1.222653721682848,
+      "grad_norm": 1.1737093925476074,
+      "learning_rate": 9.560709611437195e-05,
+      "loss": 0.6629860997200012,
+      "step": 2834
+    },
+    {
+      "epoch": 1.2235167206040993,
+      "grad_norm": 1.2071303129196167,
+      "learning_rate": 9.559702685067506e-05,
+      "loss": 0.7166537642478943,
+      "step": 2836
+    },
+    {
+      "epoch": 1.2243797195253505,
+      "grad_norm": 1.2520930767059326,
+      "learning_rate": 9.558694659146068e-05,
+      "loss": 0.6711867451667786,
+      "step": 2838
+    },
+    {
+      "epoch": 1.225242718446602,
+      "grad_norm": 1.2304543256759644,
+      "learning_rate": 9.557685533915964e-05,
+      "loss": 0.7135099768638611,
+      "step": 2840
+    },
+    {
+      "epoch": 1.2261057173678533,
+      "grad_norm": 1.1509613990783691,
+      "learning_rate": 9.556675309620539e-05,
+      "loss": 0.6279205083847046,
+      "step": 2842
+    },
+    {
+      "epoch": 1.2269687162891048,
+      "grad_norm": 1.2024176120758057,
+      "learning_rate": 9.555663986503406e-05,
+      "loss": 0.6848570704460144,
+      "step": 2844
+    },
+    {
+      "epoch": 1.227831715210356,
+      "grad_norm": 1.360257863998413,
+      "learning_rate": 9.55465156480844e-05,
+      "loss": 0.7109206914901733,
+      "step": 2846
+    },
+    {
+      "epoch": 1.2286947141316074,
+      "grad_norm": 1.1556848287582397,
+      "learning_rate": 9.55363804477978e-05,
+      "loss": 0.5983237028121948,
+      "step": 2848
+    },
+    {
+      "epoch": 1.2295577130528588,
+      "grad_norm": 1.131439447402954,
+      "learning_rate": 9.552623426661836e-05,
+      "loss": 0.6387401223182678,
+      "step": 2850
+    },
+    {
+      "epoch": 1.23042071197411,
+      "grad_norm": 1.1854766607284546,
+      "learning_rate": 9.551607710699273e-05,
+      "loss": 0.6584593057632446,
+      "step": 2852
+    },
+    {
+      "epoch": 1.2312837108953614,
+      "grad_norm": 1.1811782121658325,
+      "learning_rate": 9.55059089713703e-05,
+      "loss": 0.6284405589103699,
+      "step": 2854
+    },
+    {
+      "epoch": 1.2321467098166128,
+      "grad_norm": 1.1038708686828613,
+      "learning_rate": 9.549572986220307e-05,
+      "loss": 0.6183417439460754,
+      "step": 2856
+    },
+    {
+      "epoch": 1.233009708737864,
+      "grad_norm": 1.3645228147506714,
+      "learning_rate": 9.548553978194567e-05,
+      "loss": 0.7266764640808105,
+      "step": 2858
+    },
+    {
+      "epoch": 1.2338727076591154,
+      "grad_norm": 1.1896798610687256,
+      "learning_rate": 9.547533873305542e-05,
+      "loss": 0.6580738425254822,
+      "step": 2860
+    },
+    {
+      "epoch": 1.2347357065803668,
+      "grad_norm": 1.1351168155670166,
+      "learning_rate": 9.546512671799224e-05,
+      "loss": 0.669810950756073,
+      "step": 2862
+    },
+    {
+      "epoch": 1.2355987055016182,
+      "grad_norm": 1.1937936544418335,
+      "learning_rate": 9.545490373921869e-05,
+      "loss": 0.730329155921936,
+      "step": 2864
+    },
+    {
+      "epoch": 1.2364617044228694,
+      "grad_norm": 1.094347357749939,
+      "learning_rate": 9.544466979920002e-05,
+      "loss": 0.6867446303367615,
+      "step": 2866
+    },
+    {
+      "epoch": 1.2373247033441208,
+      "grad_norm": 1.4509600400924683,
+      "learning_rate": 9.54344249004041e-05,
+      "loss": 0.735468327999115,
+      "step": 2868
+    },
+    {
+      "epoch": 1.2381877022653722,
+      "grad_norm": 1.1195857524871826,
+      "learning_rate": 9.542416904530142e-05,
+      "loss": 0.6316167116165161,
+      "step": 2870
+    },
+    {
+      "epoch": 1.2390507011866236,
+      "grad_norm": 1.0227746963500977,
+      "learning_rate": 9.541390223636517e-05,
+      "loss": 0.6637873649597168,
+      "step": 2872
+    },
+    {
+      "epoch": 1.2399137001078748,
+      "grad_norm": 1.1871414184570312,
+      "learning_rate": 9.540362447607111e-05,
+      "loss": 0.6579877734184265,
+      "step": 2874
+    },
+    {
+      "epoch": 1.2407766990291262,
+      "grad_norm": 1.3265694379806519,
+      "learning_rate": 9.539333576689768e-05,
+      "loss": 0.7563158273696899,
+      "step": 2876
+    },
+    {
+      "epoch": 1.2416396979503777,
+      "grad_norm": 1.0074095726013184,
+      "learning_rate": 9.538303611132598e-05,
+      "loss": 0.6373291015625,
+      "step": 2878
+    },
+    {
+      "epoch": 1.2425026968716288,
+      "grad_norm": 1.421204924583435,
+      "learning_rate": 9.537272551183971e-05,
+      "loss": 0.6989303827285767,
+      "step": 2880
+    },
+    {
+      "epoch": 1.2433656957928803,
+      "grad_norm": 1.256486415863037,
+      "learning_rate": 9.536240397092522e-05,
+      "loss": 0.7590261697769165,
+      "step": 2882
+    },
+    {
+      "epoch": 1.2442286947141317,
+      "grad_norm": 1.1513274908065796,
+      "learning_rate": 9.53520714910715e-05,
+      "loss": 0.6652005314826965,
+      "step": 2884
+    },
+    {
+      "epoch": 1.2450916936353829,
+      "grad_norm": 1.2129496335983276,
+      "learning_rate": 9.53417280747702e-05,
+      "loss": 0.6510938405990601,
+      "step": 2886
+    },
+    {
+      "epoch": 1.2459546925566343,
+      "grad_norm": 1.1393296718597412,
+      "learning_rate": 9.533137372451557e-05,
+      "loss": 0.6405928730964661,
+      "step": 2888
+    },
+    {
+      "epoch": 1.2468176914778857,
+      "grad_norm": 1.1467162370681763,
+      "learning_rate": 9.532100844280451e-05,
+      "loss": 0.6819307208061218,
+      "step": 2890
+    },
+    {
+      "epoch": 1.247680690399137,
+      "grad_norm": 1.1516613960266113,
+      "learning_rate": 9.531063223213659e-05,
+      "loss": 0.6333560347557068,
+      "step": 2892
+    },
+    {
+      "epoch": 1.2485436893203883,
+      "grad_norm": 1.463189959526062,
+      "learning_rate": 9.530024509501396e-05,
+      "loss": 0.7259839177131653,
+      "step": 2894
+    },
+    {
+      "epoch": 1.2494066882416397,
+      "grad_norm": 1.0450547933578491,
+      "learning_rate": 9.528984703394144e-05,
+      "loss": 0.661693811416626,
+      "step": 2896
+    },
+    {
+      "epoch": 1.250269687162891,
+      "grad_norm": 1.0525774955749512,
+      "learning_rate": 9.527943805142648e-05,
+      "loss": 0.5889303684234619,
+      "step": 2898
+    },
+    {
+      "epoch": 1.2511326860841425,
+      "grad_norm": 1.130048394203186,
+      "learning_rate": 9.526901814997914e-05,
+      "loss": 0.6380610466003418,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2511326860841425,
+      "eval_loss": 0.7182289958000183,
+      "eval_runtime": 840.8156,
+      "eval_samples_per_second": 2.45,
+      "eval_steps_per_second": 2.45,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2519956850053937,
+      "grad_norm": 1.0194777250289917,
+      "learning_rate": 9.525858733211217e-05,
+      "loss": 0.6397356986999512,
+      "step": 2902
+    },
+    {
+      "epoch": 1.2528586839266451,
+      "grad_norm": 1.3902885913848877,
+      "learning_rate": 9.524814560034087e-05,
+      "loss": 0.7931577563285828,
+      "step": 2904
+    },
+    {
+      "epoch": 1.2537216828478965,
+      "grad_norm": 1.258169412612915,
+      "learning_rate": 9.523769295718325e-05,
+      "loss": 0.6997087597846985,
+      "step": 2906
+    },
+    {
+      "epoch": 1.2545846817691477,
+      "grad_norm": 1.3403711318969727,
+      "learning_rate": 9.522722940515991e-05,
+      "loss": 0.6946825385093689,
+      "step": 2908
+    },
+    {
+      "epoch": 1.2554476806903991,
+      "grad_norm": 1.1724950075149536,
+      "learning_rate": 9.521675494679409e-05,
+      "loss": 0.6309347748756409,
+      "step": 2910
+    },
+    {
+      "epoch": 1.2563106796116505,
+      "grad_norm": 1.210274338722229,
+      "learning_rate": 9.520626958461163e-05,
+      "loss": 0.6453542113304138,
+      "step": 2912
+    },
+    {
+      "epoch": 1.2571736785329017,
+      "grad_norm": 1.233112096786499,
+      "learning_rate": 9.519577332114106e-05,
+      "loss": 0.6747867465019226,
+      "step": 2914
+    },
+    {
+      "epoch": 1.2580366774541532,
+      "grad_norm": 1.1785951852798462,
+      "learning_rate": 9.51852661589135e-05,
+      "loss": 0.6729235053062439,
+      "step": 2916
+    },
+    {
+      "epoch": 1.2588996763754046,
+      "grad_norm": 1.0781456232070923,
+      "learning_rate": 9.51747481004627e-05,
+      "loss": 0.6581047177314758,
+      "step": 2918
+    },
+    {
+      "epoch": 1.2597626752966558,
+      "grad_norm": 1.1122184991836548,
+      "learning_rate": 9.516421914832506e-05,
+      "loss": 0.6576398015022278,
+      "step": 2920
+    },
+    {
+      "epoch": 1.2606256742179072,
+      "grad_norm": 1.3378703594207764,
+      "learning_rate": 9.515367930503956e-05,
+      "loss": 0.7026275396347046,
+      "step": 2922
+    },
+    {
+      "epoch": 1.2614886731391586,
+      "grad_norm": 1.127657175064087,
+      "learning_rate": 9.514312857314785e-05,
+      "loss": 0.6111703515052795,
+      "step": 2924
+    },
+    {
+      "epoch": 1.26235167206041,
+      "grad_norm": 1.2058607339859009,
+      "learning_rate": 9.513256695519419e-05,
+      "loss": 0.6698760986328125,
+      "step": 2926
+    },
+    {
+      "epoch": 1.2632146709816614,
+      "grad_norm": 1.2206004858016968,
+      "learning_rate": 9.512199445372546e-05,
+      "loss": 0.6793603897094727,
+      "step": 2928
+    },
+    {
+      "epoch": 1.2640776699029126,
+      "grad_norm": 1.167311668395996,
+      "learning_rate": 9.511141107129119e-05,
+      "loss": 0.709406316280365,
+      "step": 2930
+    },
+    {
+      "epoch": 1.264940668824164,
+      "grad_norm": 1.3347517251968384,
+      "learning_rate": 9.51008168104435e-05,
+      "loss": 0.685570240020752,
+      "step": 2932
+    },
+    {
+      "epoch": 1.2658036677454154,
+      "grad_norm": 1.186468482017517,
+      "learning_rate": 9.509021167373714e-05,
+      "loss": 0.6775280833244324,
+      "step": 2934
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 1.3934271335601807,
+      "learning_rate": 9.507959566372953e-05,
+      "loss": 0.6587507128715515,
+      "step": 2936
+    },
+    {
+      "epoch": 1.267529665587918,
+      "grad_norm": 1.3766281604766846,
+      "learning_rate": 9.506896878298061e-05,
+      "loss": 0.692707896232605,
+      "step": 2938
+    },
+    {
+      "epoch": 1.2683926645091694,
+      "grad_norm": 1.034883975982666,
+      "learning_rate": 9.505833103405307e-05,
+      "loss": 0.6481655836105347,
+      "step": 2940
+    },
+    {
+      "epoch": 1.2692556634304206,
+      "grad_norm": 1.113044261932373,
+      "learning_rate": 9.504768241951212e-05,
+      "loss": 0.5867606997489929,
+      "step": 2942
+    },
+    {
+      "epoch": 1.270118662351672,
+      "grad_norm": 1.0769455432891846,
+      "learning_rate": 9.503702294192563e-05,
+      "loss": 0.6147398948669434,
+      "step": 2944
+    },
+    {
+      "epoch": 1.2709816612729234,
+      "grad_norm": 1.100616216659546,
+      "learning_rate": 9.502635260386408e-05,
+      "loss": 0.650299608707428,
+      "step": 2946
+    },
+    {
+      "epoch": 1.2718446601941746,
+      "grad_norm": 1.1982520818710327,
+      "learning_rate": 9.501567140790057e-05,
+      "loss": 0.6896426677703857,
+      "step": 2948
+    },
+    {
+      "epoch": 1.272707659115426,
+      "grad_norm": 1.276911735534668,
+      "learning_rate": 9.500497935661085e-05,
+      "loss": 0.6780133247375488,
+      "step": 2950
+    },
+    {
+      "epoch": 1.2735706580366775,
+      "grad_norm": 1.131345272064209,
+      "learning_rate": 9.499427645257323e-05,
+      "loss": 0.6906163692474365,
+      "step": 2952
+    },
+    {
+      "epoch": 1.2744336569579289,
+      "grad_norm": 1.125251293182373,
+      "learning_rate": 9.498356269836868e-05,
+      "loss": 0.6418634057044983,
+      "step": 2954
+    },
+    {
+      "epoch": 1.2752966558791803,
+      "grad_norm": 1.2508443593978882,
+      "learning_rate": 9.497283809658078e-05,
+      "loss": 0.690779983997345,
+      "step": 2956
+    },
+    {
+      "epoch": 1.2761596548004315,
+      "grad_norm": 0.9558717608451843,
+      "learning_rate": 9.49621026497957e-05,
+      "loss": 0.645685613155365,
+      "step": 2958
+    },
+    {
+      "epoch": 1.2770226537216829,
+      "grad_norm": 1.1781591176986694,
+      "learning_rate": 9.495135636060226e-05,
+      "loss": 0.6313972473144531,
+      "step": 2960
+    },
+    {
+      "epoch": 1.2778856526429343,
+      "grad_norm": 0.9713736772537231,
+      "learning_rate": 9.494059923159189e-05,
+      "loss": 0.5853794813156128,
+      "step": 2962
+    },
+    {
+      "epoch": 1.2787486515641855,
+      "grad_norm": 1.3793153762817383,
+      "learning_rate": 9.492983126535859e-05,
+      "loss": 0.6966362595558167,
+      "step": 2964
+    },
+    {
+      "epoch": 1.279611650485437,
+      "grad_norm": 1.250563383102417,
+      "learning_rate": 9.491905246449903e-05,
+      "loss": 0.7281587719917297,
+      "step": 2966
+    },
+    {
+      "epoch": 1.2804746494066883,
+      "grad_norm": 1.3268930912017822,
+      "learning_rate": 9.490826283161247e-05,
+      "loss": 0.7322974801063538,
+      "step": 2968
+    },
+    {
+      "epoch": 1.2813376483279395,
+      "grad_norm": 1.3876935243606567,
+      "learning_rate": 9.489746236930077e-05,
+      "loss": 0.7875081896781921,
+      "step": 2970
+    },
+    {
+      "epoch": 1.282200647249191,
+      "grad_norm": 1.02049720287323,
+      "learning_rate": 9.488665108016842e-05,
+      "loss": 0.601652979850769,
+      "step": 2972
+    },
+    {
+      "epoch": 1.2830636461704423,
+      "grad_norm": 1.0868756771087646,
+      "learning_rate": 9.487582896682252e-05,
+      "loss": 0.6255780458450317,
+      "step": 2974
+    },
+    {
+      "epoch": 1.2839266450916935,
+      "grad_norm": 1.00597083568573,
+      "learning_rate": 9.486499603187275e-05,
+      "loss": 0.5967418551445007,
+      "step": 2976
+    },
+    {
+      "epoch": 1.284789644012945,
+      "grad_norm": 1.3068969249725342,
+      "learning_rate": 9.485415227793145e-05,
+      "loss": 0.719573438167572,
+      "step": 2978
+    },
+    {
+      "epoch": 1.2856526429341963,
+      "grad_norm": 1.2478386163711548,
+      "learning_rate": 9.484329770761353e-05,
+      "loss": 0.665522038936615,
+      "step": 2980
+    },
+    {
+      "epoch": 1.2865156418554478,
+      "grad_norm": 1.1220918893814087,
+      "learning_rate": 9.483243232353652e-05,
+      "loss": 0.6798994541168213,
+      "step": 2982
+    },
+    {
+      "epoch": 1.287378640776699,
+      "grad_norm": 1.1369609832763672,
+      "learning_rate": 9.482155612832057e-05,
+      "loss": 0.672002911567688,
+      "step": 2984
+    },
+    {
+      "epoch": 1.2882416396979504,
+      "grad_norm": 1.2077715396881104,
+      "learning_rate": 9.48106691245884e-05,
+      "loss": 0.6755662560462952,
+      "step": 2986
+    },
+    {
+      "epoch": 1.2891046386192018,
+      "grad_norm": 1.3299074172973633,
+      "learning_rate": 9.479977131496539e-05,
+      "loss": 0.7504231333732605,
+      "step": 2988
+    },
+    {
+      "epoch": 1.2899676375404532,
+      "grad_norm": 1.08982253074646,
+      "learning_rate": 9.478886270207948e-05,
+      "loss": 0.6837405562400818,
+      "step": 2990
+    },
+    {
+      "epoch": 1.2908306364617044,
+      "grad_norm": 1.1015464067459106,
+      "learning_rate": 9.477794328856124e-05,
+      "loss": 0.6552648544311523,
+      "step": 2992
+    },
+    {
+      "epoch": 1.2916936353829558,
+      "grad_norm": 1.1793229579925537,
+      "learning_rate": 9.476701307704384e-05,
+      "loss": 0.6160483360290527,
+      "step": 2994
+    },
+    {
+      "epoch": 1.2925566343042072,
+      "grad_norm": 1.4781638383865356,
+      "learning_rate": 9.475607207016306e-05,
+      "loss": 0.7406170964241028,
+      "step": 2996
+    },
+    {
+      "epoch": 1.2934196332254584,
+      "grad_norm": 1.2391449213027954,
+      "learning_rate": 9.474512027055724e-05,
+      "loss": 0.5950883626937866,
+      "step": 2998
+    },
+    {
+      "epoch": 1.2942826321467098,
+      "grad_norm": 1.166535496711731,
+      "learning_rate": 9.473415768086738e-05,
+      "loss": 0.6587089896202087,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2942826321467098,
+      "eval_loss": 0.7160727977752686,
+      "eval_runtime": 830.8186,
+      "eval_samples_per_second": 2.479,
+      "eval_steps_per_second": 2.479,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.1265100707984364e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}