Training in progress, step 150, checkpoint

last-checkpoint/adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 8,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
-    "down_proj",
-    "v_proj",
+    "up_proj",
     "gate_proj",
+    "v_proj",
     "k_proj",
-    "up_proj"
+    "o_proj",
+    "down_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a742c2056287a3329a44426eda37458f23296f011b4ed53c6334585d6741a3
-size 83945296
+oid sha256:0fd7e85b83a3efada449a0358e71243a0d9a75097fcec2a0ce8ef70f99b01767
+size 42002136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b913db07e3389bfb498ea92259680ba35ec92d6e2541596498a37ae89d732a
-size 43122580
+oid sha256:bc4211a5599978199be6292961977ab6990588c37f02c9a8742925ba16b07231
+size 21822612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b36b559f2798c5f6215f9dc5a59007379844c037309e0319d60c27102e2d736f
+oid sha256:a4a409f1004ef8c520e9da1d504c2610e471045707c04ccc707b15515147d226
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba5b1eceb58ed8e1d6e1125a30f45797ddcd98d1f22ce2c95178f34f64b52bf
+oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,756 +1,1098 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005614783725549371,
-  "eval_steps": 25,
-  "global_step": 100,
+  "epoch": 0.0008422175588324057,
+  "eval_steps": 50,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 5.614783725549371e-06,
-      "grad_norm": 1.063336968421936,
-      "learning_rate": 0.0002,
-      "loss": 1.0718,
+      "grad_norm": 0.6202379465103149,
+      "learning_rate": 2e-05,
+      "loss": 1.0531,
       "step": 1
     },
     {
       "epoch": 5.614783725549371e-06,
-      "eval_loss": 1.0175169706344604,
-      "eval_runtime": 13561.1744,
-      "eval_samples_per_second": 2.765,
-      "eval_steps_per_second": 2.765,
+      "eval_loss": 1.0175226926803589,
+      "eval_runtime": 21573.5423,
+      "eval_samples_per_second": 1.738,
+      "eval_steps_per_second": 1.738,
       "step": 1
     },
     {
       "epoch": 1.1229567451098743e-05,
-      "grad_norm": 0.9254959225654602,
-      "learning_rate": 0.0004,
-      "loss": 1.26,
+      "grad_norm": 0.5498092770576477,
+      "learning_rate": 4e-05,
+      "loss": 1.2547,
       "step": 2
     },
     {
       "epoch": 1.6844351176648115e-05,
-      "grad_norm": 0.4091038107872009,
-      "learning_rate": 0.0006,
-      "loss": 0.7047,
+      "grad_norm": 0.2675076127052307,
+      "learning_rate": 6e-05,
+      "loss": 0.7059,
       "step": 3
     },
     {
       "epoch": 2.2459134902197485e-05,
-      "grad_norm": 0.8800899982452393,
-      "learning_rate": 0.0008,
-      "loss": 0.9239,
+      "grad_norm": 0.6060311198234558,
+      "learning_rate": 8e-05,
+      "loss": 1.031,
       "step": 4
     },
     {
       "epoch": 2.8073918627746856e-05,
-      "grad_norm": 1.2747443914413452,
-      "learning_rate": 0.001,
-      "loss": 0.7746,
+      "grad_norm": 0.43954452872276306,
+      "learning_rate": 0.0001,
+      "loss": 0.9217,
       "step": 5
     },
     {
       "epoch": 3.368870235329623e-05,
-      "grad_norm": 1.434735894203186,
-      "learning_rate": 0.0012,
-      "loss": 1.1616,
+      "grad_norm": 0.5848556160926819,
+      "learning_rate": 0.00012,
+      "loss": 1.3786,
       "step": 6
     },
     {
       "epoch": 3.9303486078845604e-05,
-      "grad_norm": 1.1246367692947388,
-      "learning_rate": 0.0014,
-      "loss": 0.7168,
+      "grad_norm": 0.6156655550003052,
+      "learning_rate": 0.00014,
+      "loss": 0.8794,
       "step": 7
     },
     {
       "epoch": 4.491826980439497e-05,
-      "grad_norm": 0.9489652514457703,
-      "learning_rate": 0.0016,
-      "loss": 0.9415,
+      "grad_norm": 0.48315155506134033,
+      "learning_rate": 0.00016,
+      "loss": 1.0659,
       "step": 8
     },
     {
       "epoch": 5.0533053529944345e-05,
-      "grad_norm": 0.6757056713104248,
-      "learning_rate": 0.0018000000000000002,
-      "loss": 0.6533,
+      "grad_norm": 0.4259559214115143,
+      "learning_rate": 0.00018,
+      "loss": 0.702,
       "step": 9
     },
     {
       "epoch": 5.614783725549371e-05,
-      "grad_norm": 1.3025261163711548,
-      "learning_rate": 0.002,
-      "loss": 0.6712,
+      "grad_norm": 0.8003010153770447,
+      "learning_rate": 0.0002,
+      "loss": 0.8346,
       "step": 10
     },
     {
       "epoch": 6.176262098104309e-05,
-      "grad_norm": 1.0577226877212524,
-      "learning_rate": 0.0019993908270190958,
-      "loss": 0.7631,
+      "grad_norm": 0.4740721583366394,
+      "learning_rate": 0.0001999863304992469,
+      "loss": 0.7311,
       "step": 11
     },
     {
       "epoch": 6.737740470659246e-05,
-      "grad_norm": 1.5588256120681763,
-      "learning_rate": 0.0019975640502598244,
-      "loss": 1.1228,
+      "grad_norm": 1.4049946069717407,
+      "learning_rate": 0.00019994532573409262,
+      "loss": 1.0161,
       "step": 12
     },
     {
       "epoch": 7.299218843214183e-05,
-      "grad_norm": 1.1976680755615234,
-      "learning_rate": 0.0019945218953682734,
-      "loss": 0.6171,
+      "grad_norm": 1.7016016244888306,
+      "learning_rate": 0.00019987699691483048,
+      "loss": 0.565,
       "step": 13
     },
     {
       "epoch": 7.860697215769121e-05,
-      "grad_norm": 1.1977174282073975,
-      "learning_rate": 0.0019902680687415705,
-      "loss": 0.7131,
+      "grad_norm": 0.5531960129737854,
+      "learning_rate": 0.00019978136272187747,
+      "loss": 0.5972,
       "step": 14
     },
     {
       "epoch": 8.422175588324057e-05,
-      "grad_norm": 1.8031384944915771,
-      "learning_rate": 0.001984807753012208,
-      "loss": 1.1394,
+      "grad_norm": 1.0788118839263916,
+      "learning_rate": 0.000199658449300667,
+      "loss": 1.0518,
       "step": 15
     },
     {
       "epoch": 8.983653960878994e-05,
-      "grad_norm": 2.389751434326172,
-      "learning_rate": 0.0019781476007338056,
-      "loss": 0.822,
+      "grad_norm": 1.4083199501037598,
+      "learning_rate": 0.00019950829025450114,
+      "loss": 0.7576,
       "step": 16
     },
     {
       "epoch": 9.545132333433932e-05,
-      "grad_norm": 2.088827610015869,
-      "learning_rate": 0.0019702957262759963,
-      "loss": 1.0301,
+      "grad_norm": 0.8020849823951721,
+      "learning_rate": 0.00019933092663536382,
+      "loss": 0.7487,
       "step": 17
     },
     {
       "epoch": 0.00010106610705988869,
-      "grad_norm": 1.35056734085083,
-      "learning_rate": 0.001961261695938319,
-      "loss": 0.6762,
+      "grad_norm": 0.5158109068870544,
+      "learning_rate": 0.00019912640693269752,
+      "loss": 0.5468,
       "step": 18
     },
     {
       "epoch": 0.00010668089078543806,
-      "grad_norm": 1.7480477094650269,
-      "learning_rate": 0.0019510565162951536,
-      "loss": 0.9004,
+      "grad_norm": 0.7264314889907837,
+      "learning_rate": 0.00019889478706014687,
+      "loss": 0.679,
       "step": 19
     },
     {
       "epoch": 0.00011229567451098742,
-      "grad_norm": 1.480393409729004,
-      "learning_rate": 0.0019396926207859084,
-      "loss": 0.9562,
+      "grad_norm": 0.676001787185669,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 0.8173,
       "step": 20
     },
     {
       "epoch": 0.0001179104582365368,
-      "grad_norm": 1.6566611528396606,
-      "learning_rate": 0.0019271838545667874,
-      "loss": 0.8456,
+      "grad_norm": 0.5240503549575806,
+      "learning_rate": 0.00019835050748723824,
+      "loss": 0.6014,
       "step": 21
     },
     {
       "epoch": 0.00012352524196208617,
-      "grad_norm": 1.7289091348648071,
-      "learning_rate": 0.001913545457642601,
-      "loss": 1.0861,
+      "grad_norm": 0.7221630811691284,
+      "learning_rate": 0.00019803799658748094,
+      "loss": 0.7016,
       "step": 22
     },
     {
       "epoch": 0.00012914002568763553,
-      "grad_norm": 2.511488914489746,
-      "learning_rate": 0.001898794046299167,
-      "loss": 0.9673,
+      "grad_norm": 0.8355087041854858,
+      "learning_rate": 0.00019769868307835994,
+      "loss": 0.7144,
       "step": 23
     },
     {
       "epoch": 0.00013475480941318492,
-      "grad_norm": 2.9465174674987793,
-      "learning_rate": 0.001882947592858927,
-      "loss": 1.0684,
+      "grad_norm": 0.9996209144592285,
+      "learning_rate": 0.0001973326597248006,
+      "loss": 0.8338,
       "step": 24
     },
     {
       "epoch": 0.00014036959313873428,
-      "grad_norm": 2.350576400756836,
-      "learning_rate": 0.001866025403784439,
-      "loss": 1.1737,
-      "step": 25
-    },
-    {
-      "epoch": 0.00014036959313873428,
-      "eval_loss": 1.0244402885437012,
-      "eval_runtime": 13567.5847,
-      "eval_samples_per_second": 2.764,
-      "eval_steps_per_second": 2.764,
+      "grad_norm": 0.6815698742866516,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 0.8459,
       "step": 25
     },
     {
       "epoch": 0.00014598437686428367,
-      "grad_norm": 2.190694570541382,
-      "learning_rate": 0.0018480480961564258,
-      "loss": 0.9693,
+      "grad_norm": 0.9234247207641602,
+      "learning_rate": 0.00019652089102773488,
+      "loss": 0.6576,
       "step": 26
     },
     {
       "epoch": 0.00015159916058983303,
-      "grad_norm": 3.3499956130981445,
-      "learning_rate": 0.0018290375725550417,
-      "loss": 1.3869,
+      "grad_norm": 1.3168270587921143,
+      "learning_rate": 0.00019607536761368484,
+      "loss": 0.9701,
       "step": 27
     },
     {
       "epoch": 0.00015721394431538241,
-      "grad_norm": 2.3959763050079346,
-      "learning_rate": 0.0018090169943749475,
-      "loss": 0.9052,
+      "grad_norm": 0.7586074471473694,
+      "learning_rate": 0.00019560357815343577,
+      "loss": 0.6198,
       "step": 28
     },
     {
       "epoch": 0.00016282872804093177,
-      "grad_norm": 1.8362096548080444,
-      "learning_rate": 0.0017880107536067218,
-      "loss": 1.1557,
+      "grad_norm": 0.6276509761810303,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.912,
       "step": 29
     },
     {
       "epoch": 0.00016844351176648113,
-      "grad_norm": 2.4866271018981934,
-      "learning_rate": 0.001766044443118978,
-      "loss": 1.2626,
+      "grad_norm": 0.9944347739219666,
+      "learning_rate": 0.00019458172417006347,
+      "loss": 0.9922,
       "step": 30
     },
     {
       "epoch": 0.00017405829549203052,
-      "grad_norm": 3.59562349319458,
-      "learning_rate": 0.0017431448254773942,
-      "loss": 1.3407,
+      "grad_norm": 0.772435188293457,
+      "learning_rate": 0.00019403193901161613,
+      "loss": 0.7621,
       "step": 31
     },
     {
       "epoch": 0.00017967307921757988,
-      "grad_norm": 2.424304723739624,
-      "learning_rate": 0.001719339800338651,
-      "loss": 0.9181,
+      "grad_norm": 0.5932286977767944,
+      "learning_rate": 0.0001934564464599461,
+      "loss": 0.6246,
       "step": 32
     },
     {
       "epoch": 0.00018528786294312927,
-      "grad_norm": 3.3184380531311035,
-      "learning_rate": 0.0016946583704589974,
-      "loss": 0.9443,
+      "grad_norm": 0.44153475761413574,
+      "learning_rate": 0.00019285540384897073,
+      "loss": 0.659,
       "step": 33
     },
     {
       "epoch": 0.00019090264666867863,
-      "grad_norm": 3.005448579788208,
-      "learning_rate": 0.0016691306063588583,
-      "loss": 1.0322,
+      "grad_norm": 0.5189090967178345,
+      "learning_rate": 0.00019222897549773848,
+      "loss": 0.6122,
       "step": 34
     },
     {
       "epoch": 0.000196517430394228,
-      "grad_norm": 1.865719199180603,
-      "learning_rate": 0.0016427876096865393,
-      "loss": 0.8881,
+      "grad_norm": 0.6731717586517334,
+      "learning_rate": 0.00019157733266550575,
+      "loss": 0.6224,
       "step": 35
     },
     {
       "epoch": 0.00020213221411977738,
-      "grad_norm": 1.9284836053848267,
-      "learning_rate": 0.0016156614753256582,
-      "loss": 1.0125,
+      "grad_norm": 0.5189567804336548,
+      "learning_rate": 0.00019090065350491626,
+      "loss": 0.7545,
       "step": 36
     },
     {
       "epoch": 0.00020774699784532674,
-      "grad_norm": 3.410578489303589,
-      "learning_rate": 0.0015877852522924731,
-      "loss": 1.1619,
+      "grad_norm": 0.8409593105316162,
+      "learning_rate": 0.00019019912301329592,
+      "loss": 0.7632,
       "step": 37
     },
     {
       "epoch": 0.00021336178157087613,
-      "grad_norm": 2.3564658164978027,
-      "learning_rate": 0.0015591929034707468,
-      "loss": 1.3581,
+      "grad_norm": 0.5888797044754028,
+      "learning_rate": 0.00018947293298207635,
+      "loss": 0.9602,
       "step": 38
     },
     {
       "epoch": 0.00021897656529642549,
-      "grad_norm": 1.6943787336349487,
-      "learning_rate": 0.001529919264233205,
-      "loss": 0.7817,
+      "grad_norm": 0.4639832377433777,
+      "learning_rate": 0.0001887222819443612,
+      "loss": 0.5281,
       "step": 39
     },
     {
       "epoch": 0.00022459134902197485,
-      "grad_norm": 2.2240307331085205,
-      "learning_rate": 0.0015,
-      "loss": 0.8353,
+      "grad_norm": 0.7274787425994873,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 0.5447,
       "step": 40
     },
     {
       "epoch": 0.00023020613274752423,
-      "grad_norm": 3.0564215183258057,
-      "learning_rate": 0.0014694715627858908,
-      "loss": 1.0998,
+      "grad_norm": 0.5326807498931885,
+      "learning_rate": 0.00018714842436272773,
+      "loss": 0.7716,
       "step": 41
     },
     {
       "epoch": 0.0002358209164730736,
-      "grad_norm": 3.891338348388672,
-      "learning_rate": 0.0014383711467890773,
-      "loss": 1.4342,
+      "grad_norm": 0.5459308624267578,
+      "learning_rate": 0.00018632564809575742,
+      "loss": 1.0218,
       "step": 42
     },
     {
       "epoch": 0.00024143570019862298,
-      "grad_norm": 1.7128349542617798,
-      "learning_rate": 0.0014067366430758003,
-      "loss": 0.9709,
+      "grad_norm": 0.4652407467365265,
+      "learning_rate": 0.0001854792712585539,
+      "loss": 0.6814,
       "step": 43
     },
     {
       "epoch": 0.00024705048392417234,
-      "grad_norm": 4.62891960144043,
-      "learning_rate": 0.0013746065934159121,
-      "loss": 1.0202,
+      "grad_norm": 0.4710409641265869,
+      "learning_rate": 0.00018460952524209355,
+      "loss": 0.624,
       "step": 44
     },
     {
       "epoch": 0.00025266526764972173,
-      "grad_norm": 4.355927467346191,
-      "learning_rate": 0.0013420201433256688,
-      "loss": 1.0459,
+      "grad_norm": 0.5593191385269165,
+      "learning_rate": 0.00018371664782625287,
+      "loss": 0.6167,
       "step": 45
     },
     {
       "epoch": 0.00025828005137527106,
-      "grad_norm": 2.2983617782592773,
-      "learning_rate": 0.0013090169943749475,
-      "loss": 1.1911,
+      "grad_norm": 0.876891553401947,
+      "learning_rate": 0.00018280088311480201,
+      "loss": 0.7577,
       "step": 46
     },
     {
       "epoch": 0.00026389483510082045,
-      "grad_norm": 2.7273306846618652,
-      "learning_rate": 0.0012756373558169992,
-      "loss": 0.6804,
+      "grad_norm": 0.6078484654426575,
+      "learning_rate": 0.00018186248146866927,
+      "loss": 0.4229,
       "step": 47
     },
     {
       "epoch": 0.00026950961882636984,
-      "grad_norm": 3.133652687072754,
-      "learning_rate": 0.0012419218955996676,
-      "loss": 0.9479,
+      "grad_norm": 0.6034438014030457,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.5671,
       "step": 48
     },
     {
       "epoch": 0.0002751244025519192,
-      "grad_norm": 1.5990813970565796,
-      "learning_rate": 0.0012079116908177592,
-      "loss": 1.1125,
+      "grad_norm": 0.48336154222488403,
+      "learning_rate": 0.0001799187996894925,
+      "loss": 0.8663,
       "step": 49
     },
     {
       "epoch": 0.00028073918627746856,
-      "grad_norm": 3.576906204223633,
-      "learning_rate": 0.0011736481776669307,
-      "loss": 1.1765,
+      "grad_norm": 0.917046844959259,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 0.8188,
       "step": 50
     },
     {
       "epoch": 0.00028073918627746856,
-      "eval_loss": 1.0542502403259277,
-      "eval_runtime": 13596.4994,
-      "eval_samples_per_second": 2.758,
-      "eval_steps_per_second": 2.758,
+      "eval_loss": 0.7379979491233826,
+      "eval_runtime": 21585.5399,
+      "eval_samples_per_second": 1.737,
+      "eval_steps_per_second": 1.737,
       "step": 50
     },
     {
       "epoch": 0.00028635397000301795,
-      "grad_norm": 3.177819013595581,
-      "learning_rate": 0.0011391731009600654,
-      "loss": 1.0826,
+      "grad_norm": 0.6631708145141602,
+      "learning_rate": 0.00017788772787621126,
+      "loss": 0.7043,
       "step": 51
     },
     {
       "epoch": 0.00029196875372856733,
-      "grad_norm": 1.8690358400344849,
-      "learning_rate": 0.0011045284632676536,
-      "loss": 1.1652,
+      "grad_norm": 0.6282797455787659,
+      "learning_rate": 0.00017684011108568592,
+      "loss": 0.8696,
       "step": 52
     },
     {
       "epoch": 0.00029758353745411667,
-      "grad_norm": 2.333109140396118,
-      "learning_rate": 0.0010697564737441251,
-      "loss": 0.9394,
+      "grad_norm": 0.6374572515487671,
+      "learning_rate": 0.0001757714869760335,
+      "loss": 0.6252,
       "step": 53
     },
     {
       "epoch": 0.00030319832117966605,
-      "grad_norm": 2.443849802017212,
-      "learning_rate": 0.0010348994967025011,
-      "loss": 1.1265,
+      "grad_norm": 0.6826508045196533,
+      "learning_rate": 0.0001746821476984154,
+      "loss": 0.7257,
       "step": 54
     },
     {
       "epoch": 0.00030881310490521544,
-      "grad_norm": 2.8769495487213135,
-      "learning_rate": 0.001,
-      "loss": 1.2229,
+      "grad_norm": 0.6594266891479492,
+      "learning_rate": 0.00017357239106731317,
+      "loss": 0.9205,
       "step": 55
     },
     {
       "epoch": 0.00031442788863076483,
-      "grad_norm": 2.619149684906006,
-      "learning_rate": 0.0009651005032974994,
-      "loss": 0.9862,
+      "grad_norm": 0.6436939835548401,
+      "learning_rate": 0.00017244252047910892,
+      "loss": 0.6385,
       "step": 56
     },
     {
       "epoch": 0.00032004267235631416,
-      "grad_norm": 2.4989588260650635,
-      "learning_rate": 0.0009302435262558747,
-      "loss": 1.2905,
+      "grad_norm": 0.5752350687980652,
+      "learning_rate": 0.00017129284482913972,
+      "loss": 0.7424,
       "step": 57
     },
     {
       "epoch": 0.00032565745608186355,
-      "grad_norm": 2.512277841567993,
-      "learning_rate": 0.0008954715367323467,
-      "loss": 1.154,
+      "grad_norm": 0.7134163975715637,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.7284,
       "step": 58
     },
     {
       "epoch": 0.00033127223980741294,
-      "grad_norm": 2.4800610542297363,
-      "learning_rate": 0.0008608268990399348,
-      "loss": 1.5995,
+      "grad_norm": 2.738507032394409,
+      "learning_rate": 0.0001689353409118566,
+      "loss": 0.6917,
       "step": 59
     },
     {
       "epoch": 0.00033688702353296227,
-      "grad_norm": 2.3938980102539062,
-      "learning_rate": 0.0008263518223330697,
-      "loss": 1.319,
+      "grad_norm": 0.6593369245529175,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 1.0237,
       "step": 60
     },
     {
       "epoch": 0.00034250180725851166,
-      "grad_norm": 2.4228010177612305,
-      "learning_rate": 0.0007920883091822408,
-      "loss": 0.8742,
+      "grad_norm": 0.5328947305679321,
+      "learning_rate": 0.0001665024572113848,
+      "loss": 0.5792,
       "step": 61
     },
     {
       "epoch": 0.00034811659098406104,
-      "grad_norm": 2.0796005725860596,
-      "learning_rate": 0.0007580781044003324,
-      "loss": 1.1228,
+      "grad_norm": 1.0252548456192017,
+      "learning_rate": 0.00016525857615241687,
+      "loss": 0.7674,
       "step": 62
     },
     {
       "epoch": 0.0003537313747096104,
-      "grad_norm": 2.852293014526367,
-      "learning_rate": 0.0007243626441830009,
-      "loss": 0.9704,
+      "grad_norm": 0.7161698937416077,
+      "learning_rate": 0.00016399685405033167,
+      "loss": 0.6849,
       "step": 63
     },
     {
       "epoch": 0.00035934615843515977,
-      "grad_norm": 2.3396663665771484,
-      "learning_rate": 0.0006909830056250527,
-      "loss": 0.6046,
+      "grad_norm": 0.4108976721763611,
+      "learning_rate": 0.0001627176358473537,
+      "loss": 0.3426,
       "step": 64
     },
     {
       "epoch": 0.00036496094216070915,
-      "grad_norm": 2.455451488494873,
-      "learning_rate": 0.0006579798566743314,
-      "loss": 1.1228,
+      "grad_norm": 0.8395034670829773,
+      "learning_rate": 0.0001614212712689668,
+      "loss": 0.7893,
       "step": 65
     },
     {
       "epoch": 0.00037057572588625854,
-      "grad_norm": 2.2324576377868652,
-      "learning_rate": 0.0006253934065840879,
-      "loss": 0.8794,
+      "grad_norm": 1.7357856035232544,
+      "learning_rate": 0.00016010811472830252,
+      "loss": 0.6872,
       "step": 66
     },
     {
       "epoch": 0.0003761905096118079,
-      "grad_norm": 1.5327250957489014,
-      "learning_rate": 0.0005932633569242,
-      "loss": 0.9488,
+      "grad_norm": 0.6169449687004089,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.7493,
       "step": 67
     },
     {
       "epoch": 0.00038180529333735726,
-      "grad_norm": 1.51426362991333,
-      "learning_rate": 0.0005616288532109225,
-      "loss": 0.5928,
+      "grad_norm": 0.40986934304237366,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 0.4622,
       "step": 68
     },
     {
       "epoch": 0.00038742007706290665,
-      "grad_norm": 2.4975624084472656,
-      "learning_rate": 0.0005305284372141095,
-      "loss": 0.8214,
+      "grad_norm": 0.9793535470962524,
+      "learning_rate": 0.0001560715057351673,
+      "loss": 0.6613,
       "step": 69
     },
     {
       "epoch": 0.000393034860788456,
-      "grad_norm": 2.9134929180145264,
-      "learning_rate": 0.0005000000000000002,
-      "loss": 1.1048,
+      "grad_norm": 0.8405007123947144,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.7482,
       "step": 70
     },
     {
       "epoch": 0.00039864964451400537,
-      "grad_norm": 2.5357260704040527,
-      "learning_rate": 0.0004700807357667952,
-      "loss": 1.4895,
+      "grad_norm": 0.9131999611854553,
+      "learning_rate": 0.0001533031728727994,
+      "loss": 1.1605,
       "step": 71
     },
     {
       "epoch": 0.00040426442823955476,
-      "grad_norm": 1.9591279029846191,
-      "learning_rate": 0.0004408070965292533,
-      "loss": 0.8524,
+      "grad_norm": 0.47172001004219055,
+      "learning_rate": 0.00015189695737812152,
+      "loss": 0.659,
       "step": 72
     },
     {
       "epoch": 0.00040987921196510414,
-      "grad_norm": 1.8926405906677246,
-      "learning_rate": 0.00041221474770752696,
-      "loss": 0.9163,
+      "grad_norm": 0.5213868021965027,
+      "learning_rate": 0.0001504765537734844,
+      "loss": 0.6634,
       "step": 73
     },
     {
       "epoch": 0.0004154939956906535,
-      "grad_norm": 1.8855713605880737,
-      "learning_rate": 0.0003843385246743417,
-      "loss": 1.4346,
+      "grad_norm": 0.8890513181686401,
+      "learning_rate": 0.00014904235038305083,
+      "loss": 1.0718,
       "step": 74
     },
     {
       "epoch": 0.00042110877941620286,
-      "grad_norm": 3.0587925910949707,
-      "learning_rate": 0.0003572123903134606,
-      "loss": 0.9795,
-      "step": 75
-    },
-    {
-      "epoch": 0.00042110877941620286,
-      "eval_loss": 0.9440500140190125,
-      "eval_runtime": 13647.0704,
-      "eval_samples_per_second": 2.747,
-      "eval_steps_per_second": 2.747,
+      "grad_norm": 0.9680766463279724,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 0.7103,
       "step": 75
     },
     {
       "epoch": 0.00042672356314175225,
-      "grad_norm": 1.1029833555221558,
-      "learning_rate": 0.0003308693936411421,
-      "loss": 0.8496,
+      "grad_norm": 0.4047940969467163,
+      "learning_rate": 0.0001461341162978688,
+      "loss": 0.71,
       "step": 76
     },
     {
       "epoch": 0.0004323383468673016,
-      "grad_norm": 1.740774393081665,
-      "learning_rate": 0.00030534162954100265,
-      "loss": 0.8706,
+      "grad_norm": 0.5290956497192383,
+      "learning_rate": 0.00014466088068528068,
+      "loss": 0.6457,
       "step": 77
     },
     {
       "epoch": 0.00043795313059285097,
-      "grad_norm": 1.9898922443389893,
-      "learning_rate": 0.00028066019966134904,
-      "loss": 0.8711,
+      "grad_norm": 0.6832664012908936,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 0.6552,
       "step": 78
     },
     {
       "epoch": 0.00044356791431840036,
-      "grad_norm": 1.1141417026519775,
-      "learning_rate": 0.00025685517452260563,
-      "loss": 0.7094,
+      "grad_norm": 0.4100581407546997,
+      "learning_rate": 0.00014167818604952906,
+      "loss": 0.5278,
       "step": 79
     },
     {
       "epoch": 0.0004491826980439497,
-      "grad_norm": 1.7842293977737427,
-      "learning_rate": 0.0002339555568810221,
-      "loss": 1.0987,
+      "grad_norm": 0.7382338643074036,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.8645,
       "step": 80
     },
     {
       "epoch": 0.0004547974817694991,
-      "grad_norm": 1.4790884256362915,
-      "learning_rate": 0.00021198924639327811,
-      "loss": 0.6301,
+      "grad_norm": 0.2650225758552551,
+      "learning_rate": 0.00013864991692924523,
+      "loss": 0.4649,
       "step": 81
     },
     {
       "epoch": 0.00046041226549504847,
-      "grad_norm": 0.9781002998352051,
-      "learning_rate": 0.00019098300562505265,
-      "loss": 0.893,
+      "grad_norm": 0.367811918258667,
+      "learning_rate": 0.00013711972489182208,
+      "loss": 0.7294,
       "step": 82
     },
     {
       "epoch": 0.00046602704922059786,
-      "grad_norm": 1.3697646856307983,
-      "learning_rate": 0.00017096242744495837,
-      "loss": 0.6985,
+      "grad_norm": 0.4647292494773865,
+      "learning_rate": 0.00013557938469225167,
+      "loss": 0.5452,
       "step": 83
     },
     {
       "epoch": 0.0004716418329461472,
-      "grad_norm": 1.812117576599121,
-      "learning_rate": 0.00015195190384357404,
-      "loss": 1.1954,
+      "grad_norm": 0.6576372385025024,
+      "learning_rate": 0.00013402931744416433,
+      "loss": 0.9787,
       "step": 84
     },
     {
       "epoch": 0.0004772566166716966,
-      "grad_norm": 1.748288631439209,
-      "learning_rate": 0.0001339745962155613,
-      "loss": 0.9258,
+      "grad_norm": 0.5366365313529968,
+      "learning_rate": 0.00013246994692046836,
+      "loss": 0.7488,
       "step": 85
     },
     {
       "epoch": 0.00048287140039724596,
-      "grad_norm": 1.5759660005569458,
-      "learning_rate": 0.00011705240714107302,
-      "loss": 0.8344,
+      "grad_norm": 0.5728768706321716,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6648,
       "step": 86
     },
     {
       "epoch": 0.0004884861841227954,
-      "grad_norm": 1.638961911201477,
-      "learning_rate": 0.00010120595370083318,
-      "loss": 1.0205,
+      "grad_norm": 0.6398264169692993,
+      "learning_rate": 0.0001293250037384465,
+      "loss": 0.8214,
       "step": 87
     },
     {
       "epoch": 0.0004941009678483447,
-      "grad_norm": 1.6769089698791504,
-      "learning_rate": 8.645454235739902e-05,
-      "loss": 0.9673,
+      "grad_norm": 1.2357827425003052,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 0.8501,
       "step": 88
     },
     {
       "epoch": 0.000499715751573894,
-      "grad_norm": 1.4740527868270874,
-      "learning_rate": 7.281614543321269e-05,
-      "loss": 0.5517,
+      "grad_norm": 0.394092321395874,
+      "learning_rate": 0.00012614799409538198,
+      "loss": 0.3837,
       "step": 89
     },
     {
       "epoch": 0.0005053305352994435,
-      "grad_norm": 1.8537969589233398,
-      "learning_rate": 6.0307379214091684e-05,
-      "loss": 1.0717,
+      "grad_norm": 0.6195949912071228,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.8326,
       "step": 90
     },
     {
       "epoch": 0.0005109453190249928,
-      "grad_norm": 1.06834077835083,
-      "learning_rate": 4.894348370484647e-05,
-      "loss": 0.833,
+      "grad_norm": 0.435367226600647,
+      "learning_rate": 0.00012294239200467516,
+      "loss": 0.7117,
       "step": 91
     },
     {
       "epoch": 0.0005165601027505421,
-      "grad_norm": 2.1590793132781982,
-      "learning_rate": 3.873830406168111e-05,
-      "loss": 1.2292,
+      "grad_norm": 1.041673183441162,
+      "learning_rate": 0.0001213299630743747,
+      "loss": 1.0454,
       "step": 92
     },
     {
       "epoch": 0.0005221748864760916,
-      "grad_norm": 1.418778419494629,
-      "learning_rate": 2.9704273724003528e-05,
-      "loss": 0.7584,
+      "grad_norm": 0.5448310375213623,
+      "learning_rate": 0.00011971170274514802,
+      "loss": 0.6795,
       "step": 93
     },
     {
       "epoch": 0.0005277896702016409,
-      "grad_norm": 1.332282543182373,
-      "learning_rate": 2.1852399266194312e-05,
-      "loss": 0.8623,
+      "grad_norm": 0.5703837275505066,
+      "learning_rate": 0.000118088053433211,
+      "loss": 0.6598,
       "step": 94
     },
     {
       "epoch": 0.0005334044539271903,
-      "grad_norm": 1.214484691619873,
-      "learning_rate": 1.519224698779198e-05,
-      "loss": 0.5786,
+      "grad_norm": 0.4229240417480469,
+      "learning_rate": 0.00011645945902807341,
+      "loss": 0.4612,
       "step": 95
     },
     {
       "epoch": 0.0005390192376527397,
-      "grad_norm": 1.5501805543899536,
-      "learning_rate": 9.731931258429638e-06,
-      "loss": 1.0117,
+      "grad_norm": 0.6660332679748535,
+      "learning_rate": 0.0001148263647711842,
+      "loss": 0.8873,
       "step": 96
     },
     {
       "epoch": 0.000544634021378289,
-      "grad_norm": 1.5862345695495605,
-      "learning_rate": 5.47810463172671e-06,
-      "loss": 0.88,
+      "grad_norm": 0.6834558248519897,
+      "learning_rate": 0.00011318921713420691,
+      "loss": 0.7653,
       "step": 97
     },
     {
       "epoch": 0.0005502488051038384,
-      "grad_norm": 1.6535526514053345,
-      "learning_rate": 2.4359497401758024e-06,
-      "loss": 0.6076,
+      "grad_norm": 0.4525357186794281,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 0.4677,
       "step": 98
     },
     {
       "epoch": 0.0005558635888293878,
-      "grad_norm": 0.9868706464767456,
-      "learning_rate": 6.091729809042379e-07,
-      "loss": 0.6062,
+      "grad_norm": 0.34924590587615967,
+      "learning_rate": 0.0001099045530250463,
+      "loss": 0.4567,
       "step": 99
     },
     {
       "epoch": 0.0005614783725549371,
-      "grad_norm": 1.6027213335037231,
-      "learning_rate": 0.0,
-      "loss": 0.56,
+      "grad_norm": 0.7102425694465637,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.4776,
       "step": 100
     },
     {
       "epoch": 0.0005614783725549371,
-      "eval_loss": 0.8763332962989807,
-      "eval_runtime": 13589.0012,
-      "eval_samples_per_second": 2.759,
-      "eval_steps_per_second": 2.759,
+      "eval_loss": 0.7291257977485657,
+      "eval_runtime": 21564.2046,
+      "eval_samples_per_second": 1.739,
+      "eval_steps_per_second": 1.739,
       "step": 100
+    },
+    {
+      "epoch": 0.0005670931562804866,
+      "grad_norm": 0.8440341949462891,
+      "learning_rate": 0.00010660905843256994,
+      "loss": 0.5559,
+      "step": 101
+    },
+    {
+      "epoch": 0.0005727079400060359,
+      "grad_norm": 0.8778635859489441,
+      "learning_rate": 0.00010495837546732224,
+      "loss": 0.8599,
+      "step": 102
+    },
+    {
+      "epoch": 0.0005783227237315852,
+      "grad_norm": 0.5961638689041138,
+      "learning_rate": 0.00010330633693173082,
+      "loss": 0.6385,
+      "step": 103
+    },
+    {
+      "epoch": 0.0005839375074571347,
+      "grad_norm": 0.460720956325531,
+      "learning_rate": 0.00010165339447663587,
+      "loss": 0.4011,
+      "step": 104
+    },
+    {
+      "epoch": 0.000589552291182684,
+      "grad_norm": 0.8094878196716309,
+      "learning_rate": 0.0001,
+      "loss": 0.7205,
+      "step": 105
+    },
+    {
+      "epoch": 0.0005951670749082333,
+      "grad_norm": 0.5714880228042603,
+      "learning_rate": 9.834660552336415e-05,
+      "loss": 0.7492,
+      "step": 106
+    },
+    {
+      "epoch": 0.0006007818586337828,
+      "grad_norm": 0.8501264452934265,
+      "learning_rate": 9.669366306826919e-05,
+      "loss": 0.8841,
+      "step": 107
+    },
+    {
+      "epoch": 0.0006063966423593321,
+      "grad_norm": 0.6514793634414673,
+      "learning_rate": 9.504162453267777e-05,
+      "loss": 0.6724,
+      "step": 108
+    },
+    {
+      "epoch": 0.0006120114260848814,
+      "grad_norm": 0.7907955050468445,
+      "learning_rate": 9.339094156743007e-05,
+      "loss": 0.454,
+      "step": 109
+    },
+    {
+      "epoch": 0.0006176262098104309,
+      "grad_norm": 0.6769828200340271,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 0.7664,
+      "step": 110
+    },
+    {
+      "epoch": 0.0006232409935359802,
+      "grad_norm": 0.6691708564758301,
+      "learning_rate": 9.009544697495374e-05,
+      "loss": 1.1113,
+      "step": 111
+    },
+    {
+      "epoch": 0.0006288557772615297,
+      "grad_norm": 0.603244960308075,
+      "learning_rate": 8.845153630304139e-05,
+      "loss": 0.7398,
+      "step": 112
+    },
+    {
+      "epoch": 0.000634470560987079,
+      "grad_norm": 0.5727530121803284,
+      "learning_rate": 8.681078286579311e-05,
+      "loss": 0.5164,
+      "step": 113
+    },
+    {
+      "epoch": 0.0006400853447126283,
+      "grad_norm": 0.45102572441101074,
+      "learning_rate": 8.517363522881579e-05,
+      "loss": 0.4242,
+      "step": 114
+    },
+    {
+      "epoch": 0.0006457001284381778,
+      "grad_norm": 0.5324817895889282,
+      "learning_rate": 8.35405409719266e-05,
+      "loss": 0.7243,
+      "step": 115
+    },
+    {
+      "epoch": 0.0006513149121637271,
+      "grad_norm": 0.6306778788566589,
+      "learning_rate": 8.191194656678904e-05,
+      "loss": 0.8012,
+      "step": 116
+    },
+    {
+      "epoch": 0.0006569296958892764,
+      "grad_norm": 0.6321919560432434,
+      "learning_rate": 8.028829725485199e-05,
+      "loss": 0.7433,
+      "step": 117
+    },
+    {
+      "epoch": 0.0006625444796148259,
+      "grad_norm": 0.7640076279640198,
+      "learning_rate": 7.867003692562534e-05,
+      "loss": 0.6027,
+      "step": 118
+    },
+    {
+      "epoch": 0.0006681592633403752,
+      "grad_norm": 0.4536445438861847,
+      "learning_rate": 7.705760799532485e-05,
+      "loss": 0.3564,
+      "step": 119
+    },
+    {
+      "epoch": 0.0006737740470659245,
+      "grad_norm": 0.7957231998443604,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 0.7709,
+      "step": 120
+    },
+    {
+      "epoch": 0.000679388830791474,
+      "grad_norm": 0.354618102312088,
+      "learning_rate": 7.385200590461803e-05,
+      "loss": 0.458,
+      "step": 121
+    },
+    {
+      "epoch": 0.0006850036145170233,
+      "grad_norm": 0.6814515590667725,
+      "learning_rate": 7.225970912381556e-05,
+      "loss": 0.5223,
+      "step": 122
+    },
+    {
+      "epoch": 0.0006906183982425726,
+      "grad_norm": 0.695183515548706,
+      "learning_rate": 7.067499626155354e-05,
+      "loss": 0.5944,
+      "step": 123
+    },
+    {
+      "epoch": 0.0006962331819681221,
+      "grad_norm": 0.5911761522293091,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.57,
+      "step": 124
+    },
+    {
+      "epoch": 0.0007018479656936714,
+      "grad_norm": 0.8290671110153198,
+      "learning_rate": 6.753005307953167e-05,
+      "loss": 0.7753,
+      "step": 125
+    },
+    {
+      "epoch": 0.0007074627494192208,
+      "grad_norm": 0.5861778259277344,
+      "learning_rate": 6.59706825558357e-05,
+      "loss": 0.7765,
+      "step": 126
+    },
+    {
+      "epoch": 0.0007130775331447702,
+      "grad_norm": 0.4672585725784302,
+      "learning_rate": 6.442061530774834e-05,
+      "loss": 0.4829,
+      "step": 127
+    },
+    {
+      "epoch": 0.0007186923168703195,
+      "grad_norm": 0.47954103350639343,
+      "learning_rate": 6.28802751081779e-05,
+      "loss": 0.7241,
+      "step": 128
+    },
+    {
+      "epoch": 0.000724307100595869,
+      "grad_norm": 0.45866596698760986,
+      "learning_rate": 6.135008307075481e-05,
+      "loss": 0.4806,
+      "step": 129
+    },
+    {
+      "epoch": 0.0007299218843214183,
+      "grad_norm": 0.8541582226753235,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 0.6784,
+      "step": 130
+    },
+    {
+      "epoch": 0.0007355366680469676,
+      "grad_norm": 0.6664092540740967,
+      "learning_rate": 5.832181395047098e-05,
+      "loss": 0.8403,
+      "step": 131
+    },
+    {
+      "epoch": 0.0007411514517725171,
+      "grad_norm": 1.3184312582015991,
+      "learning_rate": 5.6824564766150726e-05,
+      "loss": 0.6905,
+      "step": 132
+    },
+    {
+      "epoch": 0.0007467662354980664,
+      "grad_norm": 0.5796993374824524,
+      "learning_rate": 5.533911931471936e-05,
+      "loss": 0.61,
+      "step": 133
+    },
+    {
+      "epoch": 0.0007523810192236157,
+      "grad_norm": 0.3954677879810333,
+      "learning_rate": 5.386588370213124e-05,
+      "loss": 0.4762,
+      "step": 134
+    },
+    {
+      "epoch": 0.0007579958029491652,
+      "grad_norm": 0.2643950581550598,
+      "learning_rate": 5.240526069629265e-05,
+      "loss": 0.3033,
+      "step": 135
+    },
+    {
+      "epoch": 0.0007636105866747145,
+      "grad_norm": 0.749079167842865,
+      "learning_rate": 5.095764961694922e-05,
+      "loss": 0.8238,
+      "step": 136
+    },
+    {
+      "epoch": 0.0007692253704002639,
+      "grad_norm": 0.5847424268722534,
+      "learning_rate": 4.952344622651566e-05,
+      "loss": 0.5255,
+      "step": 137
+    },
+    {
+      "epoch": 0.0007748401541258133,
+      "grad_norm": 0.46530458331108093,
+      "learning_rate": 4.810304262187852e-05,
+      "loss": 0.5624,
+      "step": 138
+    },
+    {
+      "epoch": 0.0007804549378513626,
+      "grad_norm": 0.49851590394973755,
+      "learning_rate": 4.669682712720065e-05,
+      "loss": 0.7465,
+      "step": 139
+    },
+    {
+      "epoch": 0.000786069721576912,
+      "grad_norm": 0.7142413258552551,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 0.7593,
+      "step": 140
+    },
+    {
+      "epoch": 0.0007916845053024614,
+      "grad_norm": 0.6527928113937378,
+      "learning_rate": 4.392849426483274e-05,
+      "loss": 0.7741,
+      "step": 141
+    },
+    {
+      "epoch": 0.0007972992890280107,
+      "grad_norm": 0.377798855304718,
+      "learning_rate": 4.256713373170564e-05,
+      "loss": 0.3863,
+      "step": 142
+    },
+    {
+      "epoch": 0.0008029140727535601,
+      "grad_norm": 0.6521917581558228,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.6036,
+      "step": 143
+    },
+    {
+      "epoch": 0.0008085288564791095,
+      "grad_norm": 0.6146506071090698,
+      "learning_rate": 3.9891885271697496e-05,
+      "loss": 0.6178,
+      "step": 144
+    },
+    {
+      "epoch": 0.0008141436402046588,
+      "grad_norm": 0.36121559143066406,
+      "learning_rate": 3.857872873103322e-05,
+      "loss": 0.4544,
+      "step": 145
+    },
+    {
+      "epoch": 0.0008197584239302083,
+      "grad_norm": 0.3757206201553345,
+      "learning_rate": 3.7282364152646297e-05,
+      "loss": 0.6141,
+      "step": 146
+    },
+    {
+      "epoch": 0.0008253732076557576,
+      "grad_norm": 0.604722261428833,
+      "learning_rate": 3.600314594966834e-05,
+      "loss": 0.6223,
+      "step": 147
+    },
+    {
+      "epoch": 0.000830987991381307,
+      "grad_norm": 0.761726438999176,
+      "learning_rate": 3.4741423847583134e-05,
+      "loss": 0.725,
+      "step": 148
+    },
+    {
+      "epoch": 0.0008366027751068564,
+      "grad_norm": 0.586891233921051,
+      "learning_rate": 3.349754278861517e-05,
+      "loss": 0.936,
+      "step": 149
+    },
+    {
+      "epoch": 0.0008422175588324057,
+      "grad_norm": 0.6373620629310608,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 0.9005,
+      "step": 150
+    },
+    {
+      "epoch": 0.0008422175588324057,
+      "eval_loss": 0.7196696400642395,
+      "eval_runtime": 21575.1375,
+      "eval_samples_per_second": 1.738,
+      "eval_steps_per_second": 1.738,
+      "step": 150
     }
   ],
   "logging_steps": 1,
-  "max_steps": 100,
+  "max_steps": 200,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 5,
@@ -761,12 +1103,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.70837631753257e+16,
+  "total_flos": 1.108192360660992e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc4c339d5730e6ec9d0d548b10a92b6b67b7c212c9d1c201a554ed13523e0a6
+oid sha256:cda6572949e2823163e920fde2833ddb39e3300db4fceb5dc6cf9e08468745fc
 size 6712