Model save

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.49109079287602353,
-    "train_runtime": 5330.839,
-    "train_samples": 46672,
-    "train_samples_per_second": 8.755,
+    "train_loss": 0.5129612217778745,
+    "train_runtime": 5390.6556,
+    "train_samples": 47205,
+    "train_samples_per_second": 8.757,
     "train_steps_per_second": 0.034
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c511d14471ab18870f10f923c8787de845cdc70bd963e129a608dd18f3fc60
+oid sha256:8cf429f2365d057d537eb6eb684ec0e28181ee38fa55cd21735e7e6f691bdff9
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c474648050e838c831aabb3699a61ac3756493e671f2a842828d65675367af
+oid sha256:9331d412f5bc9c44c9792f8a2afaa5a28095041cc6f7c254ae83a5ed634d33d8
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2335066937ff02bdedb3b53830a851b36f4126b5264e844e5f7337e06e1c6efd
+oid sha256:43b920dd703fb81aa8790bea0c995d0448371190e6f8d23f5e71d685ce1bda1e
 size 4540516344

runs/Jun18_02-36-18_n136-100-194/events.out.tfevents.1718649412.n136-100-194.2675446.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a4afc6f6da88432b058dbad4c784dbc32dbdec44a9ecfd785bdc35d4947e5ce
-size 12323
+oid sha256:72febef4cdd2fc0e0c7f5f1f5d588ce85dd8f4850a1a3eb70382c76988f19607
+size 18157

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.49109079287602353,
-    "train_runtime": 5330.839,
-    "train_samples": 46672,
-    "train_samples_per_second": 8.755,
+    "train_loss": 0.5129612217778745,
+    "train_runtime": 5390.6556,
+    "train_samples": 47205,
+    "train_samples_per_second": 8.757,
     "train_steps_per_second": 0.034
 }

trainer_state.json

@@ -1,22 +1,22 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9972602739726028,
+  "epoch": 0.997289972899729,
   "eval_steps": 500,
-  "global_step": 182,
+  "global_step": 184,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.01,
-      "grad_norm": 450.1434249789045,
+      "grad_norm": 699.419624450993,
       "learning_rate": 2.6315789473684206e-09,
-      "logits/chosen": -0.7030794620513916,
-      "logits/rejected": -0.3951629400253296,
-      "logps/chosen": -341.73382568359375,
-      "logps/rejected": -292.9862060546875,
-      "loss": 0.6931,
+      "logits/chosen": -0.8214728236198425,
+      "logits/rejected": -0.3221539855003357,
+      "logps/chosen": -281.03485107421875,
+      "logps/rejected": -258.44012451171875,
+      "loss": 0.6984,
       "rewards/accuracies": 0.0,
       "rewards/chosen": 0.0,
       "rewards/margins": 0.0,
@@ -25,286 +25,286 @@
     },
     {
       "epoch": 0.05,
-      "grad_norm": 427.11862533612515,
+      "grad_norm": 688.9664821722622,
       "learning_rate": 2.6315789473684208e-08,
-      "logits/chosen": -0.8544511795043945,
-      "logits/rejected": -0.5010538101196289,
-      "logps/chosen": -343.0840148925781,
-      "logps/rejected": -297.6950378417969,
-      "loss": 0.6989,
-      "rewards/accuracies": 0.4201388955116272,
-      "rewards/chosen": 0.006387188099324703,
-      "rewards/margins": -0.002455425448715687,
-      "rewards/rejected": 0.008842612616717815,
+      "logits/chosen": -0.8804507255554199,
+      "logits/rejected": -0.6175813674926758,
+      "logps/chosen": -333.9942932128906,
+      "logps/rejected": -301.1158142089844,
+      "loss": 0.7112,
+      "rewards/accuracies": 0.4583333432674408,
+      "rewards/chosen": 0.02290305122733116,
+      "rewards/margins": 0.000978956581093371,
+      "rewards/rejected": 0.0219240952283144,
       "step": 10
     },
     {
       "epoch": 0.11,
-      "grad_norm": 420.6890953363653,
-      "learning_rate": 4.9995356760283366e-08,
-      "logits/chosen": -0.8882249593734741,
-      "logits/rejected": -0.5170028805732727,
-      "logps/chosen": -333.65777587890625,
-      "logps/rejected": -287.80816650390625,
-      "loss": 0.6881,
-      "rewards/accuracies": 0.5375000238418579,
-      "rewards/chosen": -0.012563005089759827,
-      "rewards/margins": 0.03462809696793556,
-      "rewards/rejected": -0.04719109833240509,
+      "grad_norm": 708.2483637617346,
+      "learning_rate": 4.9995468638088146e-08,
+      "logits/chosen": -0.8514911532402039,
+      "logits/rejected": -0.6387242078781128,
+      "logps/chosen": -341.757080078125,
+      "logps/rejected": -314.51751708984375,
+      "loss": 0.7023,
+      "rewards/accuracies": 0.4906249940395355,
+      "rewards/chosen": 0.009864812716841698,
+      "rewards/margins": 0.0014371216529980302,
+      "rewards/rejected": 0.008427691645920277,
       "step": 20
     },
     {
       "epoch": 0.16,
-      "grad_norm": 398.42327340439533,
-      "learning_rate": 4.944025194969586e-08,
-      "logits/chosen": -0.9182589650154114,
-      "logits/rejected": -0.5222188234329224,
-      "logps/chosen": -332.426025390625,
-      "logps/rejected": -290.18304443359375,
-      "loss": 0.6356,
-      "rewards/accuracies": 0.640625,
-      "rewards/chosen": -0.035035934299230576,
-      "rewards/margins": 0.15518921613693237,
-      "rewards/rejected": -0.19022515416145325,
+      "grad_norm": 577.1248066355766,
+      "learning_rate": 4.945369001834514e-08,
+      "logits/chosen": -0.9569602012634277,
+      "logits/rejected": -0.7534269690513611,
+      "logps/chosen": -346.7052001953125,
+      "logps/rejected": -312.9559631347656,
+      "loss": 0.6348,
+      "rewards/accuracies": 0.596875011920929,
+      "rewards/chosen": 0.04675150662660599,
+      "rewards/margins": 0.11421873420476913,
+      "rewards/rejected": -0.06746722757816315,
       "step": 30
     },
     {
       "epoch": 0.22,
-      "grad_norm": 361.5856784181511,
-      "learning_rate": 4.798007040388211e-08,
-      "logits/chosen": -0.8608843684196472,
-      "logits/rejected": -0.5015160441398621,
-      "logps/chosen": -337.7128601074219,
-      "logps/rejected": -307.75726318359375,
-      "loss": 0.5811,
-      "rewards/accuracies": 0.7406250238418579,
-      "rewards/chosen": 0.006648591253906488,
-      "rewards/margins": 0.3918178081512451,
-      "rewards/rejected": -0.38516920804977417,
+      "grad_norm": 579.099443117778,
+      "learning_rate": 4.802809132787125e-08,
+      "logits/chosen": -0.9495086669921875,
+      "logits/rejected": -0.69568932056427,
+      "logps/chosen": -342.0091247558594,
+      "logps/rejected": -313.8953552246094,
+      "loss": 0.5992,
+      "rewards/accuracies": 0.715624988079071,
+      "rewards/chosen": 0.18988165259361267,
+      "rewards/margins": 0.39908966422080994,
+      "rewards/rejected": -0.20920801162719727,
       "step": 40
     },
     {
       "epoch": 0.27,
-      "grad_norm": 334.47329593106986,
-      "learning_rate": 4.5668885883990063e-08,
-      "logits/chosen": -0.8879793286323547,
-      "logits/rejected": -0.4423498511314392,
-      "logps/chosen": -332.4192199707031,
-      "logps/rejected": -296.57025146484375,
-      "loss": 0.5272,
-      "rewards/accuracies": 0.78125,
-      "rewards/chosen": 0.24052493274211884,
-      "rewards/margins": 0.5968745946884155,
-      "rewards/rejected": -0.3563496172428131,
+      "grad_norm": 522.7924733724386,
+      "learning_rate": 4.577019741770136e-08,
+      "logits/chosen": -0.9217802882194519,
+      "logits/rejected": -0.5782603025436401,
+      "logps/chosen": -324.60467529296875,
+      "logps/rejected": -291.2610778808594,
+      "loss": 0.5445,
+      "rewards/accuracies": 0.734375,
+      "rewards/chosen": 0.451026976108551,
+      "rewards/margins": 0.6606618762016296,
+      "rewards/rejected": -0.209634929895401,
       "step": 50
     },
     {
       "epoch": 0.33,
-      "grad_norm": 339.682806652983,
-      "learning_rate": 4.2592286678719626e-08,
-      "logits/chosen": -0.8047763109207153,
-      "logits/rejected": -0.4120696485042572,
-      "logps/chosen": -330.0352478027344,
-      "logps/rejected": -295.6581726074219,
-      "loss": 0.5016,
+      "grad_norm": 441.70974291440746,
+      "learning_rate": 4.276161445663422e-08,
+      "logits/chosen": -0.9271470308303833,
+      "logits/rejected": -0.5116554498672485,
+      "logps/chosen": -351.0398864746094,
+      "logps/rejected": -313.02984619140625,
+      "loss": 0.5198,
       "rewards/accuracies": 0.7718750238418579,
-      "rewards/chosen": 0.5128915905952454,
-      "rewards/margins": 0.7231279015541077,
-      "rewards/rejected": -0.21023626625537872,
+      "rewards/chosen": 0.6475666761398315,
+      "rewards/margins": 0.7143425941467285,
+      "rewards/rejected": -0.06677587330341339,
       "step": 60
     },
     {
       "epoch": 0.38,
-      "grad_norm": 294.8745864628234,
-      "learning_rate": 3.886420608016766e-08,
-      "logits/chosen": -1.0426691770553589,
-      "logits/rejected": -0.600997805595398,
-      "logps/chosen": -348.37408447265625,
-      "logps/rejected": -304.3432922363281,
-      "loss": 0.4851,
-      "rewards/accuracies": 0.753125011920929,
-      "rewards/chosen": 0.823379397392273,
-      "rewards/margins": 0.7953158617019653,
-      "rewards/rejected": 0.02806355059146881,
+      "grad_norm": 542.2213130459819,
+      "learning_rate": 3.9111080471669236e-08,
+      "logits/chosen": -0.8212447166442871,
+      "logits/rejected": -0.4982244372367859,
+      "logps/chosen": -323.27349853515625,
+      "logps/rejected": -298.29718017578125,
+      "loss": 0.4963,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": 0.8154565095901489,
+      "rewards/margins": 0.7821646928787231,
+      "rewards/rejected": 0.033291809260845184,
       "step": 70
     },
     {
-      "epoch": 0.44,
-      "grad_norm": 272.6474819647033,
-      "learning_rate": 3.462270318133136e-08,
-      "logits/chosen": -0.9253625869750977,
-      "logits/rejected": -0.3548746705055237,
-      "logps/chosen": -341.5060119628906,
-      "logps/rejected": -294.5276794433594,
-      "loss": 0.4535,
-      "rewards/accuracies": 0.815625011920929,
-      "rewards/chosen": 0.7518247961997986,
-      "rewards/margins": 0.94850093126297,
-      "rewards/rejected": -0.19667614996433258,
+      "epoch": 0.43,
+      "grad_norm": 474.1471440060756,
+      "learning_rate": 3.495053527239656e-08,
+      "logits/chosen": -0.853967547416687,
+      "logits/rejected": -0.506403923034668,
+      "logps/chosen": -326.6103820800781,
+      "logps/rejected": -298.58380126953125,
+      "loss": 0.4837,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.8894384503364563,
+      "rewards/margins": 0.8635719418525696,
+      "rewards/rejected": 0.025866415351629257,
       "step": 80
     },
     {
       "epoch": 0.49,
-      "grad_norm": 281.1147370449449,
-      "learning_rate": 3.0024850241696124e-08,
-      "logits/chosen": -1.0233888626098633,
-      "logits/rejected": -0.6329795122146606,
-      "logps/chosen": -337.8768310546875,
-      "logps/rejected": -307.80621337890625,
-      "loss": 0.4505,
-      "rewards/accuracies": 0.796875,
-      "rewards/chosen": 0.9118101000785828,
-      "rewards/margins": 1.0233700275421143,
-      "rewards/rejected": -0.1115599274635315,
+      "grad_norm": 425.2259909957891,
+      "learning_rate": 3.0430351802512695e-08,
+      "logits/chosen": -0.9206312298774719,
+      "logits/rejected": -0.5899518728256226,
+      "logps/chosen": -332.1669921875,
+      "logps/rejected": -301.76629638671875,
+      "loss": 0.4805,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 1.0642414093017578,
+      "rewards/margins": 0.9260485768318176,
+      "rewards/rejected": 0.13819284737110138,
       "step": 90
     },
     {
-      "epoch": 0.55,
-      "grad_norm": 270.95326246127075,
-      "learning_rate": 2.5240915953099518e-08,
-      "logits/chosen": -0.8435468673706055,
-      "logits/rejected": -0.528495192527771,
-      "logps/chosen": -316.45147705078125,
-      "logps/rejected": -284.6639099121094,
-      "loss": 0.434,
-      "rewards/accuracies": 0.7875000238418579,
-      "rewards/chosen": 0.6949013471603394,
-      "rewards/margins": 0.9432865381240845,
-      "rewards/rejected": -0.24838528037071228,
+      "epoch": 0.54,
+      "grad_norm": 522.4112789139864,
+      "learning_rate": 2.5713901269842402e-08,
+      "logits/chosen": -0.9058634042739868,
+      "logits/rejected": -0.5568256974220276,
+      "logps/chosen": -339.79473876953125,
+      "logps/rejected": -303.04571533203125,
+      "loss": 0.4627,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 1.063265085220337,
+      "rewards/margins": 1.0086718797683716,
+      "rewards/rejected": 0.05459331348538399,
       "step": 100
     },
     {
       "epoch": 0.6,
-      "grad_norm": 246.8924504601372,
-      "learning_rate": 2.0448060012437142e-08,
-      "logits/chosen": -0.7631230354309082,
-      "logits/rejected": -0.46078410744667053,
-      "logps/chosen": -332.81842041015625,
-      "logps/rejected": -302.547119140625,
-      "loss": 0.4323,
-      "rewards/accuracies": 0.8125,
-      "rewards/chosen": 0.88267582654953,
-      "rewards/margins": 1.0535722970962524,
-      "rewards/rejected": -0.17089635133743286,
+      "grad_norm": 559.2014619266797,
+      "learning_rate": 2.09716484852284e-08,
+      "logits/chosen": -0.8277750015258789,
+      "logits/rejected": -0.4014664590358734,
+      "logps/chosen": -327.2757568359375,
+      "logps/rejected": -290.67767333984375,
+      "loss": 0.4654,
+      "rewards/accuracies": 0.784375011920929,
+      "rewards/chosen": 1.061645269393921,
+      "rewards/margins": 1.108440637588501,
+      "rewards/rejected": -0.04679515212774277,
       "step": 110
     },
     {
-      "epoch": 0.66,
-      "grad_norm": 249.2911347992777,
-      "learning_rate": 1.5823772505167697e-08,
-      "logits/chosen": -0.8469772338867188,
-      "logits/rejected": -0.47505950927734375,
-      "logps/chosen": -345.8771667480469,
-      "logps/rejected": -308.70025634765625,
-      "loss": 0.421,
-      "rewards/accuracies": 0.8343750238418579,
-      "rewards/chosen": 1.0309433937072754,
-      "rewards/margins": 1.2240039110183716,
-      "rewards/rejected": -0.19306042790412903,
+      "epoch": 0.65,
+      "grad_norm": 422.80636655795246,
+      "learning_rate": 1.637499082012574e-08,
+      "logits/chosen": -0.8766531944274902,
+      "logits/rejected": -0.6933692097663879,
+      "logps/chosen": -318.14697265625,
+      "logps/rejected": -298.24462890625,
+      "loss": 0.4535,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.206791639328003,
+      "rewards/margins": 1.0834404230117798,
+      "rewards/rejected": 0.12335111945867538,
       "step": 120
     },
     {
-      "epoch": 0.71,
-      "grad_norm": 236.63634286693804,
-      "learning_rate": 1.1539301053796948e-08,
-      "logits/chosen": -0.8259572982788086,
-      "logits/rejected": -0.48908624053001404,
-      "logps/chosen": -326.006591796875,
-      "logps/rejected": -298.5427551269531,
-      "loss": 0.4317,
-      "rewards/accuracies": 0.7406250238418579,
-      "rewards/chosen": 0.7692808508872986,
-      "rewards/margins": 0.9658697843551636,
-      "rewards/rejected": -0.1965889036655426,
+      "epoch": 0.7,
+      "grad_norm": 446.84426011615477,
+      "learning_rate": 1.2090063459025954e-08,
+      "logits/chosen": -0.9841381907463074,
+      "logits/rejected": -0.7362494468688965,
+      "logps/chosen": -345.0978088378906,
+      "logps/rejected": -313.47198486328125,
+      "loss": 0.4637,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": 1.106555700302124,
+      "rewards/margins": 1.0541633367538452,
+      "rewards/rejected": 0.05239236354827881,
       "step": 130
     },
     {
-      "epoch": 0.77,
-      "grad_norm": 277.9055914170381,
-      "learning_rate": 7.753309138609703e-09,
-      "logits/chosen": -1.0100657939910889,
-      "logits/rejected": -0.518832266330719,
-      "logps/chosen": -335.1830749511719,
-      "logps/rejected": -293.55389404296875,
-      "loss": 0.4203,
-      "rewards/accuracies": 0.7906249761581421,
-      "rewards/chosen": 0.938341498374939,
-      "rewards/margins": 1.1349132061004639,
-      "rewards/rejected": -0.19657166302204132,
+      "epoch": 0.76,
+      "grad_norm": 437.6664172133176,
+      "learning_rate": 8.271734841028552e-09,
+      "logits/chosen": -0.9155263900756836,
+      "logits/rejected": -0.6956790685653687,
+      "logps/chosen": -343.3347473144531,
+      "logps/rejected": -319.8084411621094,
+      "loss": 0.4456,
+      "rewards/accuracies": 0.778124988079071,
+      "rewards/chosen": 1.1650675535202026,
+      "rewards/margins": 1.0745846033096313,
+      "rewards/rejected": 0.09048305451869965,
       "step": 140
     },
     {
-      "epoch": 0.82,
-      "grad_norm": 280.40678633901416,
-      "learning_rate": 4.606000437098476e-09,
-      "logits/chosen": -0.9020172953605652,
-      "logits/rejected": -0.5801359415054321,
-      "logps/chosen": -328.5782775878906,
-      "logps/rejected": -298.58416748046875,
-      "loss": 0.417,
-      "rewards/accuracies": 0.768750011920929,
-      "rewards/chosen": 0.8313944935798645,
-      "rewards/margins": 1.0033814907073975,
-      "rewards/rejected": -0.1719868779182434,
+      "epoch": 0.81,
+      "grad_norm": 547.6078246967138,
+      "learning_rate": 5.0580093109461184e-09,
+      "logits/chosen": -0.8691400289535522,
+      "logits/rejected": -0.42544013261795044,
+      "logps/chosen": -331.86328125,
+      "logps/rejected": -290.8024597167969,
+      "loss": 0.4532,
+      "rewards/accuracies": 0.7906249761581421,
+      "rewards/chosen": 1.2534332275390625,
+      "rewards/margins": 1.3035576343536377,
+      "rewards/rejected": -0.05012448504567146,
       "step": 150
     },
     {
-      "epoch": 0.88,
-      "grad_norm": 281.95412461514485,
-      "learning_rate": 2.2139267708310455e-09,
-      "logits/chosen": -0.941261887550354,
-      "logits/rejected": -0.5286608934402466,
-      "logps/chosen": -337.65704345703125,
-      "logps/rejected": -302.15557861328125,
-      "loss": 0.4195,
-      "rewards/accuracies": 0.831250011920929,
-      "rewards/chosen": 1.0939249992370605,
-      "rewards/margins": 1.298884391784668,
-      "rewards/rejected": -0.20495939254760742,
+      "epoch": 0.87,
+      "grad_norm": 491.3660284508518,
+      "learning_rate": 2.5650392827160444e-09,
+      "logits/chosen": -0.8275870084762573,
+      "logits/rejected": -0.5543009042739868,
+      "logps/chosen": -331.1053466796875,
+      "logps/rejected": -297.59521484375,
+      "loss": 0.4545,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": 1.089099645614624,
+      "rewards/margins": 1.1679441928863525,
+      "rewards/rejected": -0.07884454727172852,
       "step": 160
     },
     {
-      "epoch": 0.93,
-      "grad_norm": 257.0608061838707,
-      "learning_rate": 6.656719329999699e-10,
-      "logits/chosen": -0.6665180921554565,
-      "logits/rejected": -0.36475566029548645,
-      "logps/chosen": -323.7983703613281,
-      "logps/rejected": -292.5258483886719,
-      "loss": 0.4248,
-      "rewards/accuracies": 0.8343750238418579,
-      "rewards/chosen": 1.0974645614624023,
-      "rewards/margins": 1.273900032043457,
-      "rewards/rejected": -0.1764354258775711,
+      "epoch": 0.92,
+      "grad_norm": 411.0060600793946,
+      "learning_rate": 8.829271885286093e-10,
+      "logits/chosen": -0.9505836367607117,
+      "logits/rejected": -0.7405703067779541,
+      "logps/chosen": -334.4549865722656,
+      "logps/rejected": -305.47021484375,
+      "loss": 0.4601,
+      "rewards/accuracies": 0.796875,
+      "rewards/chosen": 1.0208919048309326,
+      "rewards/margins": 1.136797308921814,
+      "rewards/rejected": -0.11590544134378433,
       "step": 170
     },
     {
-      "epoch": 0.99,
-      "grad_norm": 245.05015884181918,
-      "learning_rate": 1.8571234092507048e-11,
-      "logits/chosen": -0.8604642152786255,
-      "logits/rejected": -0.526264488697052,
-      "logps/chosen": -320.47540283203125,
-      "logps/rejected": -290.77569580078125,
-      "loss": 0.4234,
-      "rewards/accuracies": 0.856249988079071,
-      "rewards/chosen": 0.9940341711044312,
-      "rewards/margins": 1.222551941871643,
-      "rewards/rejected": -0.22851786017417908,
+      "epoch": 0.98,
+      "grad_norm": 459.96112806668134,
+      "learning_rate": 7.246894216806354e-11,
+      "logits/chosen": -0.7150970697402954,
+      "logits/rejected": -0.2916146218776703,
+      "logps/chosen": -316.0776062011719,
+      "logps/rejected": -275.6624450683594,
+      "loss": 0.4537,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.0451656579971313,
+      "rewards/margins": 1.1178200244903564,
+      "rewards/rejected": -0.07265423238277435,
       "step": 180
     },
     {
       "epoch": 1.0,
-      "step": 182,
+      "step": 184,
       "total_flos": 0.0,
-      "train_loss": 0.49109079287602353,
-      "train_runtime": 5330.839,
-      "train_samples_per_second": 8.755,
+      "train_loss": 0.5129612217778745,
+      "train_runtime": 5390.6556,
+      "train_samples_per_second": 8.757,
       "train_steps_per_second": 0.034
     }
   ],
   "logging_steps": 10,
-  "max_steps": 182,
+  "max_steps": 184,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe7ad1d1edbbc30b461a2666bb026f02d74c0c127226e41e03c561f18f18d157
-size 6328
+oid sha256:2ca21fcd79c3354846e41641aa75c59cd98e420df7941b233d35b073affbb313
+size 6264