Upload folder using huggingface_hub

checkpoint-300/adapter_config.json

@@ -34,13 +34,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
     "v_proj",
-    "k_proj",
-    "up_proj",
     "o_proj",
-    "q_proj",
-    "down_proj",
-    "gate_proj"
+    "up_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

checkpoint-300/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bdb644c2a55d65ee948d959dacacce36039526da0dcb05e42f867896427334b
+oid sha256:7ef1917467f2ddc313e2c1b9031e702ba14ea35815ecdc64c1d6bc8b9b0c62f9
 size 59933632

checkpoint-300/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d305c48ef5e2fa8da94ecea579db6eeecbddb8b601bfefe66c30bad9889f8798
+oid sha256:b13f2b31bac5e5a03c946db7679f1f4577e416df3d99679177b36e222cdb3de5
 size 120166091

checkpoint-300/trainer_state.json

@@ -18,2095 +18,2095 @@
     },
     {
       "epoch": 0.013186813186813187,
-      "grad_norm": 1.763085961341858,
+      "grad_norm": 1.7631034851074219,
       "learning_rate": 4e-05,
       "loss": 2.5632,
       "step": 2
     },
     {
       "epoch": 0.01978021978021978,
-      "grad_norm": 1.9745841026306152,
+      "grad_norm": 1.979168176651001,
       "learning_rate": 8e-05,
-      "loss": 2.8958,
+      "loss": 2.8893,
       "step": 3
     },
     {
       "epoch": 0.026373626373626374,
-      "grad_norm": 1.631658673286438,
+      "grad_norm": 1.628666639328003,
       "learning_rate": 0.00012,
-      "loss": 2.63,
+      "loss": 2.6316,
       "step": 4
     },
     {
       "epoch": 0.03296703296703297,
-      "grad_norm": 2.2012367248535156,
+      "grad_norm": 2.1780693531036377,
       "learning_rate": 0.00016,
-      "loss": 2.9104,
+      "loss": 2.9097,
       "step": 5
     },
     {
       "epoch": 0.03956043956043956,
-      "grad_norm": 2.349783182144165,
+      "grad_norm": 2.302360773086548,
       "learning_rate": 0.0002,
-      "loss": 2.1203,
+      "loss": 2.1123,
       "step": 6
     },
     {
       "epoch": 0.046153846153846156,
-      "grad_norm": 2.8892629146575928,
+      "grad_norm": 2.914445400238037,
       "learning_rate": 0.00019955654101995565,
-      "loss": 2.2016,
+      "loss": 2.1906,
       "step": 7
     },
     {
       "epoch": 0.05274725274725275,
-      "grad_norm": 1.50764799118042,
+      "grad_norm": 1.5178985595703125,
       "learning_rate": 0.00019911308203991133,
-      "loss": 1.1277,
+      "loss": 1.1279,
       "step": 8
     },
     {
       "epoch": 0.05934065934065934,
-      "grad_norm": 0.9404298663139343,
+      "grad_norm": 0.929740846157074,
       "learning_rate": 0.00019866962305986697,
-      "loss": 1.3232,
+      "loss": 1.3212,
       "step": 9
     },
     {
       "epoch": 0.06593406593406594,
-      "grad_norm": 1.6010360717773438,
+      "grad_norm": 1.4806253910064697,
       "learning_rate": 0.00019822616407982261,
-      "loss": 1.3906,
+      "loss": 1.3838,
       "step": 10
     },
     {
       "epoch": 0.07252747252747253,
-      "grad_norm": 1.129049301147461,
+      "grad_norm": 1.0875375270843506,
       "learning_rate": 0.00019778270509977829,
-      "loss": 1.2764,
+      "loss": 1.2722,
       "step": 11
     },
     {
       "epoch": 0.07912087912087912,
-      "grad_norm": 0.5270851850509644,
+      "grad_norm": 0.5247994065284729,
       "learning_rate": 0.00019733924611973393,
-      "loss": 1.0322,
+      "loss": 1.033,
       "step": 12
     },
     {
       "epoch": 0.08571428571428572,
-      "grad_norm": 0.4870684742927551,
+      "grad_norm": 0.4811086654663086,
       "learning_rate": 0.0001968957871396896,
-      "loss": 1.171,
+      "loss": 1.1717,
       "step": 13
     },
     {
       "epoch": 0.09230769230769231,
-      "grad_norm": 0.4912433624267578,
+      "grad_norm": 0.48578667640686035,
       "learning_rate": 0.00019645232815964525,
-      "loss": 1.0361,
+      "loss": 1.0371,
       "step": 14
     },
     {
       "epoch": 0.0989010989010989,
-      "grad_norm": 0.5587503910064697,
+      "grad_norm": 0.5592583417892456,
       "learning_rate": 0.00019600886917960092,
       "loss": 1.0944,
       "step": 15
     },
     {
       "epoch": 0.1054945054945055,
-      "grad_norm": 0.4623633027076721,
+      "grad_norm": 0.4616752564907074,
       "learning_rate": 0.00019556541019955653,
-      "loss": 1.2065,
+      "loss": 1.2038,
       "step": 16
     },
     {
       "epoch": 0.11208791208791209,
-      "grad_norm": 0.3551870286464691,
+      "grad_norm": 0.35458147525787354,
       "learning_rate": 0.0001951219512195122,
-      "loss": 0.947,
+      "loss": 0.9475,
       "step": 17
     },
     {
       "epoch": 0.11868131868131868,
-      "grad_norm": 0.4422236979007721,
+      "grad_norm": 0.4379289746284485,
       "learning_rate": 0.00019467849223946785,
-      "loss": 1.1564,
+      "loss": 1.1557,
       "step": 18
     },
     {
       "epoch": 0.12527472527472527,
-      "grad_norm": 0.47875988483428955,
+      "grad_norm": 0.47600260376930237,
       "learning_rate": 0.00019423503325942352,
-      "loss": 1.0302,
+      "loss": 1.0279,
       "step": 19
     },
     {
       "epoch": 0.13186813186813187,
-      "grad_norm": 0.4088643789291382,
+      "grad_norm": 0.41127586364746094,
       "learning_rate": 0.00019379157427937917,
-      "loss": 1.0026,
+      "loss": 1.0024,
       "step": 20
     },
     {
       "epoch": 0.13846153846153847,
-      "grad_norm": 0.4109182357788086,
+      "grad_norm": 0.4124883711338043,
       "learning_rate": 0.00019334811529933484,
-      "loss": 1.1147,
+      "loss": 1.1145,
       "step": 21
     },
     {
       "epoch": 0.14505494505494507,
-      "grad_norm": 0.29138490557670593,
+      "grad_norm": 0.46736782789230347,
       "learning_rate": 0.00019290465631929045,
-      "loss": 0.8815,
+      "loss": 0.8806,
       "step": 22
     },
     {
       "epoch": 0.15164835164835164,
-      "grad_norm": 0.4136905372142792,
+      "grad_norm": 0.41343656182289124,
       "learning_rate": 0.00019246119733924613,
-      "loss": 1.1175,
+      "loss": 1.1182,
       "step": 23
     },
     {
       "epoch": 0.15824175824175823,
-      "grad_norm": 0.3253101110458374,
+      "grad_norm": 0.3253372013568878,
       "learning_rate": 0.00019201773835920177,
-      "loss": 1.231,
+      "loss": 1.2312,
       "step": 24
     },
     {
       "epoch": 0.16483516483516483,
-      "grad_norm": 0.2889423072338104,
+      "grad_norm": 0.292022168636322,
       "learning_rate": 0.00019157427937915744,
-      "loss": 0.917,
+      "loss": 0.918,
       "step": 25
     },
     {
       "epoch": 0.17142857142857143,
-      "grad_norm": 0.3228849172592163,
+      "grad_norm": 0.3209899067878723,
       "learning_rate": 0.00019113082039911309,
-      "loss": 0.9848,
+      "loss": 0.9837,
       "step": 26
     },
     {
       "epoch": 0.17802197802197803,
-      "grad_norm": 0.3494730293750763,
+      "grad_norm": 0.34899088740348816,
       "learning_rate": 0.00019068736141906876,
-      "loss": 1.3126,
+      "loss": 1.3112,
       "step": 27
     },
     {
       "epoch": 0.18461538461538463,
-      "grad_norm": 0.3458717167377472,
+      "grad_norm": 0.3487248420715332,
       "learning_rate": 0.0001902439024390244,
-      "loss": 0.958,
+      "loss": 0.9571,
       "step": 28
     },
     {
       "epoch": 0.1912087912087912,
-      "grad_norm": 0.3019975423812866,
+      "grad_norm": 0.3065617084503174,
       "learning_rate": 0.00018980044345898005,
-      "loss": 0.9278,
+      "loss": 0.9281,
       "step": 29
     },
     {
       "epoch": 0.1978021978021978,
-      "grad_norm": 0.2779475748538971,
+      "grad_norm": 0.2781093418598175,
       "learning_rate": 0.00018935698447893572,
-      "loss": 0.8695,
+      "loss": 0.8696,
       "step": 30
     },
     {
       "epoch": 0.2043956043956044,
-      "grad_norm": 0.39661386609077454,
+      "grad_norm": 0.39035555720329285,
       "learning_rate": 0.00018891352549889136,
-      "loss": 1.0665,
+      "loss": 1.0626,
       "step": 31
     },
     {
       "epoch": 0.210989010989011,
-      "grad_norm": 0.29335296154022217,
+      "grad_norm": 0.29400211572647095,
       "learning_rate": 0.00018847006651884703,
-      "loss": 1.1772,
+      "loss": 1.1782,
       "step": 32
     },
     {
       "epoch": 0.2175824175824176,
-      "grad_norm": 0.3007265627384186,
+      "grad_norm": 0.3062567412853241,
       "learning_rate": 0.00018802660753880268,
-      "loss": 0.8983,
+      "loss": 0.9014,
       "step": 33
     },
     {
       "epoch": 0.22417582417582418,
-      "grad_norm": 0.34418708086013794,
+      "grad_norm": 0.3487623929977417,
       "learning_rate": 0.00018758314855875832,
-      "loss": 0.9198,
+      "loss": 0.9203,
       "step": 34
     },
     {
       "epoch": 0.23076923076923078,
-      "grad_norm": 0.3824678957462311,
+      "grad_norm": 0.3516588509082794,
       "learning_rate": 0.00018713968957871397,
-      "loss": 0.9413,
+      "loss": 0.9392,
       "step": 35
     },
     {
       "epoch": 0.23736263736263735,
-      "grad_norm": 0.31358611583709717,
+      "grad_norm": 0.31045418977737427,
       "learning_rate": 0.00018669623059866964,
-      "loss": 1.0137,
+      "loss": 1.0123,
       "step": 36
     },
     {
       "epoch": 0.24395604395604395,
-      "grad_norm": 0.31992650032043457,
+      "grad_norm": 0.32259854674339294,
       "learning_rate": 0.00018625277161862528,
-      "loss": 1.0936,
+      "loss": 1.0941,
       "step": 37
     },
     {
       "epoch": 0.25054945054945055,
-      "grad_norm": 0.3005980849266052,
+      "grad_norm": 0.3016436696052551,
       "learning_rate": 0.00018580931263858095,
-      "loss": 0.8644,
+      "loss": 0.8656,
       "step": 38
     },
     {
       "epoch": 0.2571428571428571,
-      "grad_norm": 0.3336191773414612,
+      "grad_norm": 0.3304094672203064,
       "learning_rate": 0.0001853658536585366,
-      "loss": 1.0792,
+      "loss": 1.0784,
       "step": 39
     },
     {
       "epoch": 0.26373626373626374,
-      "grad_norm": 0.30710798501968384,
+      "grad_norm": 0.30421414971351624,
       "learning_rate": 0.00018492239467849224,
-      "loss": 1.0308,
+      "loss": 1.0333,
       "step": 40
     },
     {
       "epoch": 0.2703296703296703,
-      "grad_norm": 0.3451807200908661,
+      "grad_norm": 0.34875184297561646,
       "learning_rate": 0.0001844789356984479,
-      "loss": 1.0158,
+      "loss": 1.0155,
       "step": 41
     },
     {
       "epoch": 0.27692307692307694,
-      "grad_norm": 0.2870407700538635,
+      "grad_norm": 0.3075156807899475,
       "learning_rate": 0.00018403547671840356,
-      "loss": 0.8457,
+      "loss": 0.8472,
       "step": 42
     },
     {
       "epoch": 0.2835164835164835,
-      "grad_norm": 0.3287088871002197,
+      "grad_norm": 0.33417773246765137,
       "learning_rate": 0.0001835920177383592,
-      "loss": 1.1339,
+      "loss": 1.132,
       "step": 43
     },
     {
       "epoch": 0.29010989010989013,
-      "grad_norm": 0.26506197452545166,
+      "grad_norm": 0.26805588603019714,
       "learning_rate": 0.00018314855875831487,
-      "loss": 1.0233,
+      "loss": 1.0217,
       "step": 44
     },
     {
       "epoch": 0.2967032967032967,
-      "grad_norm": 0.30936315655708313,
+      "grad_norm": 0.3158379793167114,
       "learning_rate": 0.00018270509977827052,
-      "loss": 1.1225,
+      "loss": 1.1234,
       "step": 45
     },
     {
       "epoch": 0.3032967032967033,
-      "grad_norm": 0.2476174533367157,
+      "grad_norm": 0.24774910509586334,
       "learning_rate": 0.00018226164079822616,
-      "loss": 0.8881,
+      "loss": 0.8902,
       "step": 46
     },
     {
       "epoch": 0.3098901098901099,
-      "grad_norm": 0.31316661834716797,
+      "grad_norm": 0.31354963779449463,
       "learning_rate": 0.00018181818181818183,
-      "loss": 0.9629,
+      "loss": 0.9622,
       "step": 47
     },
     {
       "epoch": 0.31648351648351647,
-      "grad_norm": 0.26468923687934875,
+      "grad_norm": 0.26874473690986633,
       "learning_rate": 0.00018137472283813748,
-      "loss": 0.9877,
+      "loss": 0.9882,
       "step": 48
     },
     {
       "epoch": 0.3230769230769231,
-      "grad_norm": 0.3120814263820648,
+      "grad_norm": 0.3208855092525482,
       "learning_rate": 0.00018093126385809312,
-      "loss": 0.9647,
+      "loss": 0.9669,
       "step": 49
     },
     {
       "epoch": 0.32967032967032966,
-      "grad_norm": 0.2931019961833954,
+      "grad_norm": 0.29467493295669556,
       "learning_rate": 0.0001804878048780488,
-      "loss": 1.0234,
+      "loss": 1.0222,
       "step": 50
     },
     {
       "epoch": 0.3362637362637363,
-      "grad_norm": 0.2669380307197571,
+      "grad_norm": 0.2658853232860565,
       "learning_rate": 0.00018004434589800444,
-      "loss": 0.7157,
+      "loss": 0.7179,
       "step": 51
     },
     {
       "epoch": 0.34285714285714286,
-      "grad_norm": 0.40644407272338867,
+      "grad_norm": 0.4095586836338043,
       "learning_rate": 0.00017960088691796008,
-      "loss": 0.9324,
+      "loss": 0.9298,
       "step": 52
     },
     {
       "epoch": 0.34945054945054943,
-      "grad_norm": 0.3617885708808899,
+      "grad_norm": 0.3588062524795532,
       "learning_rate": 0.00017915742793791575,
-      "loss": 1.2954,
+      "loss": 1.2951,
       "step": 53
     },
     {
       "epoch": 0.35604395604395606,
-      "grad_norm": 0.31928303837776184,
+      "grad_norm": 0.3221994936466217,
       "learning_rate": 0.0001787139689578714,
-      "loss": 1.164,
+      "loss": 1.1634,
       "step": 54
     },
     {
       "epoch": 0.3626373626373626,
-      "grad_norm": 0.32986125349998474,
+      "grad_norm": 0.33207544684410095,
       "learning_rate": 0.00017827050997782707,
-      "loss": 1.0121,
+      "loss": 1.0126,
       "step": 55
     },
     {
       "epoch": 0.36923076923076925,
-      "grad_norm": 0.3108706772327423,
+      "grad_norm": 0.3135206401348114,
       "learning_rate": 0.00017782705099778271,
-      "loss": 0.8349,
+      "loss": 0.8339,
       "step": 56
     },
     {
       "epoch": 0.3758241758241758,
-      "grad_norm": 0.29143011569976807,
+      "grad_norm": 0.2858564555644989,
       "learning_rate": 0.00017738359201773839,
-      "loss": 0.892,
+      "loss": 0.8908,
       "step": 57
     },
     {
       "epoch": 0.3824175824175824,
-      "grad_norm": 0.40203559398651123,
+      "grad_norm": 0.40534305572509766,
       "learning_rate": 0.000176940133037694,
-      "loss": 0.9835,
+      "loss": 0.9854,
       "step": 58
     },
     {
       "epoch": 0.389010989010989,
-      "grad_norm": 0.4341263771057129,
+      "grad_norm": 0.4386303722858429,
       "learning_rate": 0.00017649667405764967,
-      "loss": 1.0466,
+      "loss": 1.0455,
       "step": 59
     },
     {
       "epoch": 0.3956043956043956,
-      "grad_norm": 0.2884133458137512,
+      "grad_norm": 0.3208898603916168,
       "learning_rate": 0.00017605321507760532,
-      "loss": 1.0288,
+      "loss": 1.029,
       "step": 60
     },
     {
       "epoch": 0.4021978021978022,
-      "grad_norm": 0.30322492122650146,
+      "grad_norm": 1.0228146314620972,
       "learning_rate": 0.000175609756097561,
-      "loss": 1.0139,
+      "loss": 1.018,
       "step": 61
     },
     {
       "epoch": 0.4087912087912088,
-      "grad_norm": 0.32310283184051514,
+      "grad_norm": 0.3353184461593628,
       "learning_rate": 0.00017516629711751663,
-      "loss": 0.9209,
+      "loss": 0.9225,
       "step": 62
     },
     {
       "epoch": 0.4153846153846154,
-      "grad_norm": 0.353019118309021,
+      "grad_norm": 0.3532666265964508,
       "learning_rate": 0.0001747228381374723,
-      "loss": 0.891,
+      "loss": 0.8927,
       "step": 63
     },
     {
       "epoch": 0.421978021978022,
-      "grad_norm": 0.35450732707977295,
+      "grad_norm": 0.351450115442276,
       "learning_rate": 0.00017427937915742792,
-      "loss": 0.8768,
+      "loss": 0.8763,
       "step": 64
     },
     {
       "epoch": 0.42857142857142855,
-      "grad_norm": 0.36479318141937256,
+      "grad_norm": 0.3587055802345276,
       "learning_rate": 0.0001738359201773836,
-      "loss": 0.9105,
+      "loss": 0.9099,
       "step": 65
     },
     {
       "epoch": 0.4351648351648352,
-      "grad_norm": 0.3024522364139557,
+      "grad_norm": 0.30922290682792664,
       "learning_rate": 0.00017339246119733924,
-      "loss": 0.9763,
+      "loss": 0.9751,
       "step": 66
     },
     {
       "epoch": 0.44175824175824174,
-      "grad_norm": 0.39104923605918884,
+      "grad_norm": 0.3808385133743286,
       "learning_rate": 0.0001729490022172949,
-      "loss": 0.9039,
+      "loss": 0.9033,
       "step": 67
     },
     {
       "epoch": 0.44835164835164837,
-      "grad_norm": 0.32236361503601074,
+      "grad_norm": 0.3210577368736267,
       "learning_rate": 0.00017250554323725056,
-      "loss": 0.9488,
+      "loss": 0.9509,
       "step": 68
     },
     {
       "epoch": 0.45494505494505494,
-      "grad_norm": 0.26719701290130615,
+      "grad_norm": 0.26781076192855835,
       "learning_rate": 0.00017206208425720623,
       "loss": 0.7911,
       "step": 69
     },
     {
       "epoch": 0.46153846153846156,
-      "grad_norm": 0.3035319745540619,
+      "grad_norm": 0.3017228841781616,
       "learning_rate": 0.00017161862527716187,
-      "loss": 0.9286,
+      "loss": 0.9287,
       "step": 70
     },
     {
       "epoch": 0.46813186813186813,
-      "grad_norm": 0.28114110231399536,
+      "grad_norm": 0.2805789113044739,
       "learning_rate": 0.00017117516629711752,
-      "loss": 0.9325,
+      "loss": 0.9327,
       "step": 71
     },
     {
       "epoch": 0.4747252747252747,
-      "grad_norm": 0.28424951434135437,
+      "grad_norm": 0.27982276678085327,
       "learning_rate": 0.0001707317073170732,
-      "loss": 0.8176,
+      "loss": 0.815,
       "step": 72
     },
     {
       "epoch": 0.48131868131868133,
-      "grad_norm": 0.2876507341861725,
+      "grad_norm": 0.29375341534614563,
       "learning_rate": 0.00017028824833702883,
-      "loss": 0.9914,
+      "loss": 0.9923,
       "step": 73
     },
     {
       "epoch": 0.4879120879120879,
-      "grad_norm": 0.3052023947238922,
+      "grad_norm": 0.3183509409427643,
       "learning_rate": 0.0001698447893569845,
-      "loss": 0.7942,
+      "loss": 0.7957,
       "step": 74
     },
     {
       "epoch": 0.4945054945054945,
-      "grad_norm": 0.3839518129825592,
+      "grad_norm": 0.38404369354248047,
       "learning_rate": 0.00016940133037694015,
-      "loss": 1.0096,
+      "loss": 1.01,
       "step": 75
     },
     {
       "epoch": 0.5010989010989011,
-      "grad_norm": 0.35913559794425964,
+      "grad_norm": 0.3639436960220337,
       "learning_rate": 0.00016895787139689582,
-      "loss": 1.0428,
+      "loss": 1.0429,
       "step": 76
     },
     {
       "epoch": 0.5076923076923077,
-      "grad_norm": 0.34896889328956604,
+      "grad_norm": 0.3531999886035919,
       "learning_rate": 0.00016851441241685144,
-      "loss": 0.8869,
+      "loss": 0.8894,
       "step": 77
     },
     {
       "epoch": 0.5142857142857142,
-      "grad_norm": 0.2883763313293457,
+      "grad_norm": 0.2900453805923462,
       "learning_rate": 0.0001680709534368071,
-      "loss": 1.0094,
+      "loss": 1.01,
       "step": 78
     },
     {
       "epoch": 0.5208791208791209,
-      "grad_norm": 0.3298456370830536,
+      "grad_norm": 0.32503485679626465,
       "learning_rate": 0.00016762749445676275,
-      "loss": 1.0698,
+      "loss": 1.0691,
       "step": 79
     },
     {
       "epoch": 0.5274725274725275,
-      "grad_norm": 0.3295091688632965,
+      "grad_norm": 0.33818212151527405,
       "learning_rate": 0.00016718403547671842,
-      "loss": 0.9751,
+      "loss": 0.9772,
       "step": 80
     },
     {
       "epoch": 0.5340659340659341,
-      "grad_norm": 0.32478851079940796,
+      "grad_norm": 0.3284465968608856,
       "learning_rate": 0.00016674057649667407,
-      "loss": 1.1535,
+      "loss": 1.1549,
       "step": 81
     },
     {
       "epoch": 0.5406593406593406,
-      "grad_norm": 0.2923767566680908,
+      "grad_norm": 0.29464396834373474,
       "learning_rate": 0.00016629711751662974,
-      "loss": 1.0731,
+      "loss": 1.0735,
       "step": 82
     },
     {
       "epoch": 0.5472527472527473,
-      "grad_norm": 0.26956698298454285,
+      "grad_norm": 0.27115604281425476,
       "learning_rate": 0.00016585365853658536,
-      "loss": 0.9208,
+      "loss": 0.9209,
       "step": 83
     },
     {
       "epoch": 0.5538461538461539,
-      "grad_norm": 0.47506311535835266,
+      "grad_norm": 0.4824427664279938,
       "learning_rate": 0.00016541019955654103,
-      "loss": 1.0085,
+      "loss": 1.0107,
       "step": 84
     },
     {
       "epoch": 0.5604395604395604,
-      "grad_norm": 0.22985781729221344,
+      "grad_norm": 0.2313273847103119,
       "learning_rate": 0.00016496674057649667,
-      "loss": 0.7752,
+      "loss": 0.7762,
       "step": 85
     },
     {
       "epoch": 0.567032967032967,
-      "grad_norm": 0.3916805386543274,
+      "grad_norm": 0.4009738266468048,
       "learning_rate": 0.00016452328159645234,
-      "loss": 0.9247,
+      "loss": 0.9261,
       "step": 86
     },
     {
       "epoch": 0.5736263736263736,
-      "grad_norm": 0.3190164864063263,
+      "grad_norm": 0.31743648648262024,
       "learning_rate": 0.000164079822616408,
-      "loss": 1.0078,
+      "loss": 1.0042,
       "step": 87
     },
     {
       "epoch": 0.5802197802197803,
-      "grad_norm": 0.39781248569488525,
+      "grad_norm": 0.4018518030643463,
       "learning_rate": 0.00016363636363636366,
-      "loss": 1.0832,
+      "loss": 1.0824,
       "step": 88
     },
     {
       "epoch": 0.5868131868131868,
-      "grad_norm": 0.3169863820075989,
+      "grad_norm": 0.31311529874801636,
       "learning_rate": 0.0001631929046563193,
-      "loss": 0.8285,
+      "loss": 0.8282,
       "step": 89
     },
     {
       "epoch": 0.5934065934065934,
-      "grad_norm": 0.33837491273880005,
+      "grad_norm": 0.3358812630176544,
       "learning_rate": 0.00016274944567627495,
-      "loss": 1.0982,
+      "loss": 1.0986,
       "step": 90
     },
     {
       "epoch": 0.6,
-      "grad_norm": 0.3353993594646454,
+      "grad_norm": 0.33934324979782104,
       "learning_rate": 0.0001623059866962306,
-      "loss": 0.8894,
+      "loss": 0.8888,
       "step": 91
     },
     {
       "epoch": 0.6065934065934065,
-      "grad_norm": 0.29551026225090027,
+      "grad_norm": 0.29767975211143494,
       "learning_rate": 0.00016186252771618626,
-      "loss": 0.876,
+      "loss": 0.8761,
       "step": 92
     },
     {
       "epoch": 0.6131868131868132,
-      "grad_norm": 0.34726232290267944,
+      "grad_norm": 0.3453633785247803,
       "learning_rate": 0.0001614190687361419,
-      "loss": 1.076,
+      "loss": 1.0768,
       "step": 93
     },
     {
       "epoch": 0.6197802197802198,
-      "grad_norm": 0.3181212544441223,
+      "grad_norm": 0.321541428565979,
       "learning_rate": 0.00016097560975609758,
       "loss": 0.9561,
       "step": 94
     },
     {
       "epoch": 0.6263736263736264,
-      "grad_norm": 0.34516891837120056,
+      "grad_norm": 0.35036543011665344,
       "learning_rate": 0.00016053215077605322,
-      "loss": 0.9267,
+      "loss": 0.9255,
       "step": 95
     },
     {
       "epoch": 0.6329670329670329,
-      "grad_norm": 0.2982713580131531,
+      "grad_norm": 0.29597529768943787,
       "learning_rate": 0.00016008869179600887,
-      "loss": 0.9852,
+      "loss": 0.9833,
       "step": 96
     },
     {
       "epoch": 0.6395604395604395,
-      "grad_norm": 0.40911373496055603,
+      "grad_norm": 0.40686383843421936,
       "learning_rate": 0.00015964523281596454,
-      "loss": 0.9486,
+      "loss": 0.9489,
       "step": 97
     },
     {
       "epoch": 0.6461538461538462,
-      "grad_norm": 0.3304843306541443,
+      "grad_norm": 0.33007949590682983,
       "learning_rate": 0.00015920177383592018,
-      "loss": 0.875,
+      "loss": 0.8745,
       "step": 98
     },
     {
       "epoch": 0.6527472527472528,
-      "grad_norm": 0.390322744846344,
+      "grad_norm": 0.39512237906455994,
       "learning_rate": 0.00015875831485587586,
-      "loss": 0.8462,
+      "loss": 0.8482,
       "step": 99
     },
     {
       "epoch": 0.6593406593406593,
-      "grad_norm": 0.33066320419311523,
+      "grad_norm": 0.3318308889865875,
       "learning_rate": 0.0001583148558758315,
-      "loss": 0.9924,
+      "loss": 0.9927,
       "step": 100
     },
     {
       "epoch": 0.6659340659340659,
-      "grad_norm": 0.2774959206581116,
+      "grad_norm": 0.27740347385406494,
       "learning_rate": 0.00015787139689578714,
-      "loss": 1.0743,
+      "loss": 1.0758,
       "step": 101
     },
     {
       "epoch": 0.6725274725274726,
-      "grad_norm": 0.2788892388343811,
+      "grad_norm": 0.2783048152923584,
       "learning_rate": 0.0001574279379157428,
-      "loss": 0.8422,
+      "loss": 0.8432,
       "step": 102
     },
     {
       "epoch": 0.6791208791208792,
-      "grad_norm": 0.32479622960090637,
+      "grad_norm": 0.3250581920146942,
       "learning_rate": 0.00015698447893569846,
-      "loss": 1.0833,
+      "loss": 1.0842,
       "step": 103
     },
     {
       "epoch": 0.6857142857142857,
-      "grad_norm": 0.4143581986427307,
+      "grad_norm": 0.41406434774398804,
       "learning_rate": 0.0001565410199556541,
-      "loss": 1.1276,
+      "loss": 1.1273,
       "step": 104
     },
     {
       "epoch": 0.6923076923076923,
-      "grad_norm": 0.311646968126297,
+      "grad_norm": 0.3118138313293457,
       "learning_rate": 0.00015609756097560978,
-      "loss": 0.7916,
+      "loss": 0.7922,
       "step": 105
     },
     {
       "epoch": 0.6989010989010989,
-      "grad_norm": 0.2998006045818329,
+      "grad_norm": 0.30124473571777344,
       "learning_rate": 0.00015565410199556542,
-      "loss": 1.0005,
+      "loss": 0.9999,
       "step": 106
     },
     {
       "epoch": 0.7054945054945055,
-      "grad_norm": 0.39382779598236084,
+      "grad_norm": 0.39211058616638184,
       "learning_rate": 0.00015521064301552106,
-      "loss": 0.878,
+      "loss": 0.8776,
       "step": 107
     },
     {
       "epoch": 0.7120879120879121,
-      "grad_norm": 0.27402716875076294,
+      "grad_norm": 0.27413809299468994,
       "learning_rate": 0.0001547671840354767,
-      "loss": 0.8881,
+      "loss": 0.8893,
       "step": 108
     },
     {
       "epoch": 0.7186813186813187,
-      "grad_norm": 0.34758150577545166,
+      "grad_norm": 0.34604713320732117,
       "learning_rate": 0.00015432372505543238,
-      "loss": 0.8852,
+      "loss": 0.8873,
       "step": 109
     },
     {
       "epoch": 0.7252747252747253,
-      "grad_norm": 0.3154073655605316,
+      "grad_norm": 0.3172498345375061,
       "learning_rate": 0.00015388026607538802,
-      "loss": 0.8393,
+      "loss": 0.838,
       "step": 110
     },
     {
       "epoch": 0.7318681318681318,
-      "grad_norm": 0.3615870475769043,
+      "grad_norm": 0.36244919896125793,
       "learning_rate": 0.0001534368070953437,
-      "loss": 0.9925,
+      "loss": 0.9934,
       "step": 111
     },
     {
       "epoch": 0.7384615384615385,
-      "grad_norm": 0.2865363359451294,
+      "grad_norm": 0.2877050042152405,
       "learning_rate": 0.00015299334811529934,
-      "loss": 0.8645,
+      "loss": 0.8643,
       "step": 112
     },
     {
       "epoch": 0.7450549450549451,
-      "grad_norm": 0.3382522463798523,
+      "grad_norm": 0.33848118782043457,
       "learning_rate": 0.00015254988913525498,
-      "loss": 0.8893,
+      "loss": 0.8918,
       "step": 113
     },
     {
       "epoch": 0.7516483516483516,
-      "grad_norm": 0.31393519043922424,
+      "grad_norm": 0.3151146173477173,
       "learning_rate": 0.00015210643015521066,
-      "loss": 0.8456,
+      "loss": 0.8461,
       "step": 114
     },
     {
       "epoch": 0.7582417582417582,
-      "grad_norm": 0.35148605704307556,
+      "grad_norm": 0.3527005612850189,
       "learning_rate": 0.0001516629711751663,
       "loss": 1.0163,
       "step": 115
     },
     {
       "epoch": 0.7648351648351648,
-      "grad_norm": 0.35740578174591064,
+      "grad_norm": 0.35679927468299866,
       "learning_rate": 0.00015121951219512197,
-      "loss": 1.0213,
+      "loss": 1.0204,
       "step": 116
     },
     {
       "epoch": 0.7714285714285715,
-      "grad_norm": 0.3053258955478668,
+      "grad_norm": 0.30327364802360535,
       "learning_rate": 0.00015077605321507762,
       "loss": 0.8969,
       "step": 117
     },
     {
       "epoch": 0.778021978021978,
-      "grad_norm": 0.3639404773712158,
+      "grad_norm": 0.36506813764572144,
       "learning_rate": 0.0001503325942350333,
-      "loss": 1.0296,
+      "loss": 1.0288,
       "step": 118
     },
     {
       "epoch": 0.7846153846153846,
-      "grad_norm": 0.3937147855758667,
+      "grad_norm": 0.3919162154197693,
       "learning_rate": 0.0001498891352549889,
-      "loss": 1.0172,
+      "loss": 1.0183,
       "step": 119
     },
     {
       "epoch": 0.7912087912087912,
-      "grad_norm": 0.32780930399894714,
+      "grad_norm": 0.3326948583126068,
       "learning_rate": 0.00014944567627494458,
-      "loss": 1.0885,
+      "loss": 1.0916,
       "step": 120
     },
     {
       "epoch": 0.7978021978021979,
-      "grad_norm": 0.36013567447662354,
+      "grad_norm": 0.35894864797592163,
       "learning_rate": 0.00014900221729490022,
-      "loss": 0.9137,
+      "loss": 0.914,
       "step": 121
     },
     {
       "epoch": 0.8043956043956044,
-      "grad_norm": 0.28383418917655945,
+      "grad_norm": 0.2828134596347809,
       "learning_rate": 0.0001485587583148559,
-      "loss": 0.8205,
+      "loss": 0.8214,
       "step": 122
     },
     {
       "epoch": 0.810989010989011,
-      "grad_norm": 0.2750217914581299,
+      "grad_norm": 0.2736477851867676,
       "learning_rate": 0.00014811529933481154,
-      "loss": 0.7234,
+      "loss": 0.7242,
       "step": 123
     },
     {
       "epoch": 0.8175824175824176,
-      "grad_norm": 0.33263805508613586,
+      "grad_norm": 0.33269619941711426,
       "learning_rate": 0.0001476718403547672,
-      "loss": 0.9268,
+      "loss": 0.9283,
       "step": 124
     },
     {
       "epoch": 0.8241758241758241,
-      "grad_norm": 0.30595824122428894,
+      "grad_norm": 0.3049944043159485,
       "learning_rate": 0.00014722838137472282,
-      "loss": 0.9338,
+      "loss": 0.9345,
       "step": 125
     },
     {
       "epoch": 0.8307692307692308,
-      "grad_norm": 0.25947901606559753,
+      "grad_norm": 0.2589491903781891,
       "learning_rate": 0.0001467849223946785,
-      "loss": 0.8766,
+      "loss": 0.8777,
       "step": 126
     },
     {
       "epoch": 0.8373626373626374,
-      "grad_norm": 0.32689163088798523,
+      "grad_norm": 0.3275723159313202,
       "learning_rate": 0.00014634146341463414,
-      "loss": 0.8883,
+      "loss": 0.887,
       "step": 127
     },
     {
       "epoch": 0.843956043956044,
-      "grad_norm": 0.3308884799480438,
+      "grad_norm": 0.3315989673137665,
       "learning_rate": 0.0001458980044345898,
-      "loss": 0.9949,
+      "loss": 0.997,
       "step": 128
     },
     {
       "epoch": 0.8505494505494505,
-      "grad_norm": 0.4053676724433899,
+      "grad_norm": 0.39565399289131165,
       "learning_rate": 0.00014545454545454546,
-      "loss": 0.9587,
+      "loss": 0.9566,
       "step": 129
     },
     {
       "epoch": 0.8571428571428571,
-      "grad_norm": 0.3362829387187958,
+      "grad_norm": 0.33553048968315125,
       "learning_rate": 0.00014501108647450113,
-      "loss": 0.9307,
+      "loss": 0.9301,
       "step": 130
     },
     {
       "epoch": 0.8637362637362638,
-      "grad_norm": 0.34943220019340515,
+      "grad_norm": 0.3543066680431366,
       "learning_rate": 0.00014456762749445675,
-      "loss": 0.806,
+      "loss": 0.8064,
       "step": 131
     },
     {
       "epoch": 0.8703296703296703,
-      "grad_norm": 0.3092266917228699,
+      "grad_norm": 0.30633488297462463,
       "learning_rate": 0.00014412416851441242,
-      "loss": 0.7973,
+      "loss": 0.7978,
       "step": 132
     },
     {
       "epoch": 0.8769230769230769,
-      "grad_norm": 0.3574323356151581,
+      "grad_norm": 0.35713377594947815,
       "learning_rate": 0.00014368070953436806,
-      "loss": 0.8379,
+      "loss": 0.8389,
       "step": 133
     },
     {
       "epoch": 0.8835164835164835,
-      "grad_norm": 0.3552650809288025,
+      "grad_norm": 0.3552398383617401,
       "learning_rate": 0.00014323725055432373,
-      "loss": 0.954,
+      "loss": 0.955,
       "step": 134
     },
     {
       "epoch": 0.8901098901098901,
-      "grad_norm": 0.2729194164276123,
+      "grad_norm": 0.27409443259239197,
       "learning_rate": 0.00014279379157427938,
-      "loss": 0.6747,
+      "loss": 0.6737,
       "step": 135
     },
     {
       "epoch": 0.8967032967032967,
-      "grad_norm": 0.25678497552871704,
+      "grad_norm": 0.2564390301704407,
       "learning_rate": 0.00014235033259423505,
-      "loss": 0.7754,
+      "loss": 0.7739,
       "step": 136
     },
     {
       "epoch": 0.9032967032967033,
-      "grad_norm": 0.4493165910243988,
+      "grad_norm": 0.44198542833328247,
       "learning_rate": 0.0001419068736141907,
-      "loss": 1.051,
+      "loss": 1.0518,
       "step": 137
     },
     {
       "epoch": 0.9098901098901099,
-      "grad_norm": 0.3436213731765747,
+      "grad_norm": 0.3410949110984802,
       "learning_rate": 0.00014146341463414634,
-      "loss": 1.1412,
+      "loss": 1.1424,
       "step": 138
     },
     {
       "epoch": 0.9164835164835164,
-      "grad_norm": 0.2819158732891083,
+      "grad_norm": 0.282086044549942,
       "learning_rate": 0.000141019955654102,
-      "loss": 0.9642,
+      "loss": 0.9633,
       "step": 139
     },
     {
       "epoch": 0.9230769230769231,
-      "grad_norm": 0.3211461901664734,
+      "grad_norm": 0.31943991780281067,
       "learning_rate": 0.00014057649667405765,
-      "loss": 0.7827,
+      "loss": 0.7823,
       "step": 140
     },
     {
       "epoch": 0.9296703296703297,
-      "grad_norm": 0.37269163131713867,
+      "grad_norm": 0.37289759516716003,
       "learning_rate": 0.00014013303769401332,
-      "loss": 0.9285,
+      "loss": 0.9284,
       "step": 141
     },
     {
       "epoch": 0.9362637362637363,
-      "grad_norm": 0.3766298294067383,
+      "grad_norm": 0.3795759081840515,
       "learning_rate": 0.00013968957871396897,
-      "loss": 1.0056,
+      "loss": 1.0047,
       "step": 142
     },
     {
       "epoch": 0.9428571428571428,
-      "grad_norm": 0.3644619584083557,
+      "grad_norm": 0.3668331801891327,
       "learning_rate": 0.00013924611973392464,
-      "loss": 1.2948,
+      "loss": 1.295,
       "step": 143
     },
     {
       "epoch": 0.9494505494505494,
-      "grad_norm": 0.33665940165519714,
+      "grad_norm": 0.33693453669548035,
       "learning_rate": 0.00013880266075388026,
-      "loss": 0.9517,
+      "loss": 0.951,
       "step": 144
     },
     {
       "epoch": 0.9560439560439561,
-      "grad_norm": 0.3173293173313141,
+      "grad_norm": 0.32185056805610657,
       "learning_rate": 0.00013835920177383593,
-      "loss": 0.938,
+      "loss": 0.9373,
       "step": 145
     },
     {
       "epoch": 0.9626373626373627,
-      "grad_norm": 0.33808133006095886,
+      "grad_norm": 0.33747026324272156,
       "learning_rate": 0.00013791574279379157,
-      "loss": 0.9878,
+      "loss": 0.9877,
       "step": 146
     },
     {
       "epoch": 0.9692307692307692,
-      "grad_norm": 0.35847944021224976,
+      "grad_norm": 0.3621857166290283,
       "learning_rate": 0.00013747228381374724,
-      "loss": 1.0098,
+      "loss": 1.0127,
       "step": 147
     },
     {
       "epoch": 0.9758241758241758,
-      "grad_norm": 0.47123852372169495,
+      "grad_norm": 0.4637271463871002,
       "learning_rate": 0.0001370288248337029,
-      "loss": 1.0347,
+      "loss": 1.0362,
       "step": 148
     },
     {
       "epoch": 0.9824175824175824,
-      "grad_norm": 0.33362922072410583,
+      "grad_norm": 0.3329949676990509,
       "learning_rate": 0.00013658536585365856,
-      "loss": 1.0041,
+      "loss": 1.0029,
       "step": 149
     },
     {
       "epoch": 0.989010989010989,
-      "grad_norm": 0.3056139051914215,
+      "grad_norm": 0.30521491169929504,
       "learning_rate": 0.00013614190687361418,
-      "loss": 0.9385,
+      "loss": 0.94,
       "step": 150
     },
     {
       "epoch": 0.9956043956043956,
-      "grad_norm": 0.39551842212677,
+      "grad_norm": 0.39264100790023804,
       "learning_rate": 0.00013569844789356985,
-      "loss": 0.9171,
+      "loss": 0.9168,
       "step": 151
     },
     {
       "epoch": 1.0,
-      "grad_norm": 0.6587658524513245,
+      "grad_norm": 0.671869695186615,
       "learning_rate": 0.0001352549889135255,
-      "loss": 1.105,
+      "loss": 1.1048,
       "step": 152
     },
     {
       "epoch": 1.0065934065934066,
-      "grad_norm": 0.2951638996601105,
+      "grad_norm": 0.2927721440792084,
       "learning_rate": 0.00013481152993348116,
-      "loss": 0.9156,
+      "loss": 0.9166,
       "step": 153
     },
     {
       "epoch": 1.0131868131868131,
-      "grad_norm": 0.38656049966812134,
+      "grad_norm": 0.387698769569397,
       "learning_rate": 0.0001343680709534368,
-      "loss": 0.8238,
+      "loss": 0.8232,
       "step": 154
     },
     {
       "epoch": 1.0197802197802197,
-      "grad_norm": 0.37417981028556824,
+      "grad_norm": 0.37951597571372986,
       "learning_rate": 0.00013392461197339248,
-      "loss": 0.9906,
+      "loss": 0.9917,
       "step": 155
     },
     {
       "epoch": 1.0263736263736263,
-      "grad_norm": 0.3245986998081207,
+      "grad_norm": 0.3240644335746765,
       "learning_rate": 0.00013348115299334812,
-      "loss": 0.9764,
+      "loss": 0.9765,
       "step": 156
     },
     {
       "epoch": 1.032967032967033,
-      "grad_norm": 0.34828925132751465,
+      "grad_norm": 0.34418824315071106,
       "learning_rate": 0.00013303769401330377,
-      "loss": 0.9119,
+      "loss": 0.9116,
       "step": 157
     },
     {
       "epoch": 1.0395604395604396,
-      "grad_norm": 0.24476902186870575,
+      "grad_norm": 0.2417616844177246,
       "learning_rate": 0.00013259423503325944,
-      "loss": 0.6357,
+      "loss": 0.6363,
       "step": 158
     },
     {
       "epoch": 1.0461538461538462,
-      "grad_norm": 0.31006908416748047,
+      "grad_norm": 0.3096141219139099,
       "learning_rate": 0.00013215077605321509,
-      "loss": 0.8791,
+      "loss": 0.8797,
       "step": 159
     },
     {
       "epoch": 1.0527472527472528,
-      "grad_norm": 0.30046963691711426,
+      "grad_norm": 0.29916486144065857,
       "learning_rate": 0.00013170731707317076,
-      "loss": 0.738,
+      "loss": 0.7378,
       "step": 160
     },
     {
       "epoch": 1.0593406593406594,
-      "grad_norm": 0.463894248008728,
+      "grad_norm": 0.460305392742157,
       "learning_rate": 0.0001312638580931264,
-      "loss": 0.8283,
+      "loss": 0.8265,
       "step": 161
     },
     {
       "epoch": 1.065934065934066,
-      "grad_norm": 0.3443954288959503,
+      "grad_norm": 0.3416884243488312,
       "learning_rate": 0.00013082039911308205,
-      "loss": 0.9068,
+      "loss": 0.9072,
       "step": 162
     },
     {
       "epoch": 1.0725274725274725,
-      "grad_norm": 0.33303964138031006,
+      "grad_norm": 0.33094775676727295,
       "learning_rate": 0.0001303769401330377,
-      "loss": 0.8687,
+      "loss": 0.8692,
       "step": 163
     },
     {
       "epoch": 1.079120879120879,
-      "grad_norm": 0.34858575463294983,
+      "grad_norm": 0.34467509388923645,
       "learning_rate": 0.00012993348115299336,
-      "loss": 0.8246,
+      "loss": 0.8256,
       "step": 164
     },
     {
       "epoch": 1.0857142857142856,
-      "grad_norm": 0.362323135137558,
+      "grad_norm": 0.3599700629711151,
       "learning_rate": 0.000129490022172949,
-      "loss": 0.8408,
+      "loss": 0.8399,
       "step": 165
     },
     {
       "epoch": 1.0923076923076924,
-      "grad_norm": 0.3863198459148407,
+      "grad_norm": 0.38290295004844666,
       "learning_rate": 0.00012904656319290468,
-      "loss": 0.8833,
+      "loss": 0.8801,
       "step": 166
     },
     {
       "epoch": 1.098901098901099,
-      "grad_norm": 0.3517734110355377,
+      "grad_norm": 0.3479115068912506,
       "learning_rate": 0.00012860310421286032,
-      "loss": 0.8537,
+      "loss": 0.8513,
       "step": 167
     },
     {
       "epoch": 1.1054945054945056,
-      "grad_norm": 0.45986834168434143,
+      "grad_norm": 0.4579565227031708,
       "learning_rate": 0.00012815964523281597,
-      "loss": 0.911,
+      "loss": 0.9113,
       "step": 168
     },
     {
       "epoch": 1.1120879120879121,
-      "grad_norm": 0.40409037470817566,
+      "grad_norm": 0.4047691524028778,
       "learning_rate": 0.0001277161862527716,
-      "loss": 0.9145,
+      "loss": 0.915,
       "step": 169
     },
     {
       "epoch": 1.1186813186813187,
-      "grad_norm": 0.39690113067626953,
+      "grad_norm": 0.396960973739624,
       "learning_rate": 0.00012727272727272728,
-      "loss": 0.869,
+      "loss": 0.8687,
       "step": 170
     },
     {
       "epoch": 1.1252747252747253,
-      "grad_norm": 0.4133467376232147,
+      "grad_norm": 0.4195733070373535,
       "learning_rate": 0.00012682926829268293,
-      "loss": 0.948,
+      "loss": 0.9494,
       "step": 171
     },
     {
       "epoch": 1.1318681318681318,
-      "grad_norm": 0.36861518025398254,
+      "grad_norm": 0.3728105425834656,
       "learning_rate": 0.0001263858093126386,
-      "loss": 0.7628,
+      "loss": 0.7637,
       "step": 172
     },
     {
       "epoch": 1.1384615384615384,
-      "grad_norm": 0.3096456229686737,
+      "grad_norm": 0.3100377023220062,
       "learning_rate": 0.00012594235033259424,
-      "loss": 0.6898,
+      "loss": 0.6897,
       "step": 173
     },
     {
       "epoch": 1.145054945054945,
-      "grad_norm": 0.330940306186676,
+      "grad_norm": 0.32927340269088745,
       "learning_rate": 0.00012549889135254989,
-      "loss": 0.9147,
+      "loss": 0.9149,
       "step": 174
     },
     {
       "epoch": 1.1516483516483516,
-      "grad_norm": 0.42627230286598206,
+      "grad_norm": 0.42513713240623474,
       "learning_rate": 0.00012505543237250553,
-      "loss": 0.9223,
+      "loss": 0.9242,
       "step": 175
     },
     {
       "epoch": 1.1582417582417581,
-      "grad_norm": 0.35968711972236633,
+      "grad_norm": 0.3596545159816742,
       "learning_rate": 0.0001246119733924612,
-      "loss": 0.9469,
+      "loss": 0.9459,
       "step": 176
     },
     {
       "epoch": 1.164835164835165,
-      "grad_norm": 0.353548139333725,
+      "grad_norm": 0.34985214471817017,
       "learning_rate": 0.00012416851441241685,
       "loss": 0.803,
       "step": 177
     },
     {
       "epoch": 1.1714285714285715,
-      "grad_norm": 0.39513444900512695,
+      "grad_norm": 0.3914942741394043,
       "learning_rate": 0.00012372505543237252,
-      "loss": 0.8474,
+      "loss": 0.8478,
       "step": 178
     },
     {
       "epoch": 1.178021978021978,
-      "grad_norm": 0.34246373176574707,
+      "grad_norm": 0.34107282757759094,
       "learning_rate": 0.00012328159645232816,
-      "loss": 0.8393,
+      "loss": 0.8418,
       "step": 179
     },
     {
       "epoch": 1.1846153846153846,
-      "grad_norm": 0.36857300996780396,
+      "grad_norm": 0.3705905079841614,
       "learning_rate": 0.0001228381374722838,
-      "loss": 0.8789,
+      "loss": 0.8819,
       "step": 180
     },
     {
       "epoch": 1.1912087912087912,
-      "grad_norm": 0.443073034286499,
+      "grad_norm": 0.44214513897895813,
       "learning_rate": 0.00012239467849223948,
       "loss": 0.9238,
       "step": 181
     },
     {
       "epoch": 1.1978021978021978,
-      "grad_norm": 0.37916645407676697,
+      "grad_norm": 0.3772227168083191,
       "learning_rate": 0.00012195121951219512,
-      "loss": 0.9882,
+      "loss": 0.9887,
       "step": 182
     },
     {
       "epoch": 1.2043956043956043,
-      "grad_norm": 0.41292667388916016,
+      "grad_norm": 0.411452054977417,
       "learning_rate": 0.00012150776053215078,
-      "loss": 0.72,
+      "loss": 0.7212,
       "step": 183
     },
     {
       "epoch": 1.210989010989011,
-      "grad_norm": 0.536925196647644,
+      "grad_norm": 0.5291978716850281,
       "learning_rate": 0.00012106430155210644,
-      "loss": 1.1482,
+      "loss": 1.148,
       "step": 184
     },
     {
       "epoch": 1.2175824175824177,
-      "grad_norm": 0.4510507583618164,
+      "grad_norm": 0.45357951521873474,
       "learning_rate": 0.0001206208425720621,
-      "loss": 0.995,
+      "loss": 0.9959,
       "step": 185
     },
     {
       "epoch": 1.2241758241758243,
-      "grad_norm": 0.365630567073822,
+      "grad_norm": 0.36383458971977234,
       "learning_rate": 0.00012017738359201774,
-      "loss": 0.9579,
+      "loss": 0.9581,
       "step": 186
     },
     {
       "epoch": 1.2307692307692308,
-      "grad_norm": 0.4479317367076874,
+      "grad_norm": 0.440993070602417,
       "learning_rate": 0.0001197339246119734,
-      "loss": 0.8552,
+      "loss": 0.8574,
       "step": 187
     },
     {
       "epoch": 1.2373626373626374,
-      "grad_norm": 0.34112170338630676,
+      "grad_norm": 0.33490514755249023,
       "learning_rate": 0.00011929046563192906,
-      "loss": 0.8073,
+      "loss": 0.8063,
       "step": 188
     },
     {
       "epoch": 1.243956043956044,
-      "grad_norm": 0.4030703604221344,
+      "grad_norm": 0.38672971725463867,
       "learning_rate": 0.00011884700665188471,
-      "loss": 0.8712,
+      "loss": 0.8699,
       "step": 189
     },
     {
       "epoch": 1.2505494505494505,
-      "grad_norm": 0.3965626657009125,
+      "grad_norm": 0.39427709579467773,
       "learning_rate": 0.00011840354767184036,
-      "loss": 0.8579,
+      "loss": 0.856,
       "step": 190
     },
     {
       "epoch": 1.2571428571428571,
-      "grad_norm": 0.5259565114974976,
+      "grad_norm": 0.5170843601226807,
       "learning_rate": 0.00011796008869179602,
-      "loss": 0.8787,
+      "loss": 0.8792,
       "step": 191
     },
     {
       "epoch": 1.2637362637362637,
-      "grad_norm": 0.3695710599422455,
+      "grad_norm": 0.3649735748767853,
       "learning_rate": 0.00011751662971175166,
-      "loss": 0.8094,
+      "loss": 0.8092,
       "step": 192
     },
     {
       "epoch": 1.2703296703296703,
-      "grad_norm": 0.4516051411628723,
+      "grad_norm": 0.44831663370132446,
       "learning_rate": 0.00011707317073170732,
-      "loss": 0.9375,
+      "loss": 0.9371,
       "step": 193
     },
     {
       "epoch": 1.2769230769230768,
-      "grad_norm": 0.5009087920188904,
+      "grad_norm": 0.4926474690437317,
       "learning_rate": 0.00011662971175166298,
-      "loss": 1.0012,
+      "loss": 0.9969,
       "step": 194
     },
     {
       "epoch": 1.2835164835164834,
-      "grad_norm": 0.4348149597644806,
+      "grad_norm": 0.4347097873687744,
       "learning_rate": 0.00011618625277161863,
-      "loss": 0.7739,
+      "loss": 0.7737,
       "step": 195
     },
     {
       "epoch": 1.2901098901098902,
-      "grad_norm": 0.46521419286727905,
+      "grad_norm": 0.46267786622047424,
       "learning_rate": 0.00011574279379157429,
-      "loss": 0.9481,
+      "loss": 0.949,
       "step": 196
     },
     {
       "epoch": 1.2967032967032968,
-      "grad_norm": 0.4420302212238312,
+      "grad_norm": 0.4386684000492096,
       "learning_rate": 0.00011529933481152995,
-      "loss": 0.8687,
+      "loss": 0.869,
       "step": 197
     },
     {
       "epoch": 1.3032967032967033,
-      "grad_norm": 0.49480170011520386,
+      "grad_norm": 0.4944095015525818,
       "learning_rate": 0.00011485587583148558,
-      "loss": 0.9039,
+      "loss": 0.9093,
       "step": 198
     },
     {
       "epoch": 1.30989010989011,
-      "grad_norm": 0.48179519176483154,
+      "grad_norm": 0.483806312084198,
       "learning_rate": 0.00011441241685144124,
-      "loss": 0.8111,
+      "loss": 0.8142,
       "step": 199
     },
     {
       "epoch": 1.3164835164835165,
-      "grad_norm": 0.4502580165863037,
+      "grad_norm": 0.4529300034046173,
       "learning_rate": 0.0001139689578713969,
-      "loss": 0.8463,
+      "loss": 0.8476,
       "step": 200
     },
     {
       "epoch": 1.323076923076923,
-      "grad_norm": 0.4146755635738373,
+      "grad_norm": 0.4150141179561615,
       "learning_rate": 0.00011352549889135255,
-      "loss": 0.7566,
+      "loss": 0.7587,
       "step": 201
     },
     {
       "epoch": 1.3296703296703296,
-      "grad_norm": 0.4209192991256714,
+      "grad_norm": 0.41961854696273804,
       "learning_rate": 0.00011308203991130821,
-      "loss": 0.8378,
+      "loss": 0.838,
       "step": 202
     },
     {
       "epoch": 1.3362637362637364,
-      "grad_norm": 0.4668080508708954,
+      "grad_norm": 0.46653783321380615,
       "learning_rate": 0.00011263858093126387,
-      "loss": 0.9084,
+      "loss": 0.9107,
       "step": 203
     },
     {
       "epoch": 1.342857142857143,
-      "grad_norm": 0.46928924322128296,
+      "grad_norm": 0.4648878574371338,
       "learning_rate": 0.00011219512195121953,
-      "loss": 0.8272,
+      "loss": 0.8256,
       "step": 204
     },
     {
       "epoch": 1.3494505494505495,
-      "grad_norm": 0.514475405216217,
+      "grad_norm": 0.5138787627220154,
       "learning_rate": 0.00011175166297117516,
-      "loss": 0.8911,
+      "loss": 0.8924,
       "step": 205
     },
     {
       "epoch": 1.3560439560439561,
-      "grad_norm": 0.4661032557487488,
+      "grad_norm": 0.4668973982334137,
       "learning_rate": 0.00011130820399113082,
-      "loss": 0.9468,
+      "loss": 0.9472,
       "step": 206
     },
     {
       "epoch": 1.3626373626373627,
-      "grad_norm": 0.44308915734291077,
+      "grad_norm": 0.44494184851646423,
       "learning_rate": 0.00011086474501108647,
-      "loss": 0.816,
+      "loss": 0.8189,
       "step": 207
     },
     {
       "epoch": 1.3692307692307693,
-      "grad_norm": 0.5306631326675415,
+      "grad_norm": 0.5250690579414368,
       "learning_rate": 0.00011042128603104213,
-      "loss": 1.0484,
+      "loss": 1.0464,
       "step": 208
     },
     {
       "epoch": 1.3758241758241758,
-      "grad_norm": 0.4230473041534424,
+      "grad_norm": 0.42257294058799744,
       "learning_rate": 0.00010997782705099779,
-      "loss": 0.9323,
+      "loss": 0.9341,
       "step": 209
     },
     {
       "epoch": 1.3824175824175824,
-      "grad_norm": 0.4156879186630249,
+      "grad_norm": 0.41006898880004883,
       "learning_rate": 0.00010953436807095345,
-      "loss": 0.8222,
+      "loss": 0.8225,
       "step": 210
     },
     {
       "epoch": 1.389010989010989,
-      "grad_norm": 0.5581250190734863,
+      "grad_norm": 0.5519815683364868,
       "learning_rate": 0.00010909090909090909,
-      "loss": 0.8185,
+      "loss": 0.8172,
       "step": 211
     },
     {
       "epoch": 1.3956043956043955,
-      "grad_norm": 0.4807477593421936,
+      "grad_norm": 0.48063287138938904,
       "learning_rate": 0.00010864745011086475,
-      "loss": 1.081,
+      "loss": 1.0825,
       "step": 212
     },
     {
       "epoch": 1.402197802197802,
-      "grad_norm": 0.5016228556632996,
+      "grad_norm": 0.49912452697753906,
       "learning_rate": 0.00010820399113082041,
-      "loss": 0.9993,
+      "loss": 1.0026,
       "step": 213
     },
     {
       "epoch": 1.4087912087912087,
-      "grad_norm": 0.6151775121688843,
+      "grad_norm": 0.6037291288375854,
       "learning_rate": 0.00010776053215077607,
-      "loss": 0.9321,
+      "loss": 0.9335,
       "step": 214
     },
     {
       "epoch": 1.4153846153846155,
-      "grad_norm": 0.4516322910785675,
+      "grad_norm": 0.44459089636802673,
       "learning_rate": 0.00010731707317073172,
-      "loss": 0.8723,
+      "loss": 0.8709,
       "step": 215
     },
     {
       "epoch": 1.421978021978022,
-      "grad_norm": 0.5124024152755737,
+      "grad_norm": 0.5097314715385437,
       "learning_rate": 0.00010687361419068738,
-      "loss": 0.9731,
+      "loss": 0.9725,
       "step": 216
     },
     {
       "epoch": 1.4285714285714286,
-      "grad_norm": 0.48399755358695984,
+      "grad_norm": 0.48173102736473083,
       "learning_rate": 0.00010643015521064301,
-      "loss": 0.8758,
+      "loss": 0.8747,
       "step": 217
     },
     {
       "epoch": 1.4351648351648352,
-      "grad_norm": 0.6074462532997131,
+      "grad_norm": 0.595790445804596,
       "learning_rate": 0.00010598669623059867,
-      "loss": 0.9316,
+      "loss": 0.9314,
       "step": 218
     },
     {
       "epoch": 1.4417582417582417,
-      "grad_norm": 0.3736724257469177,
+      "grad_norm": 0.3740411698818207,
       "learning_rate": 0.00010554323725055433,
-      "loss": 0.6633,
+      "loss": 0.6639,
       "step": 219
     },
     {
       "epoch": 1.4483516483516483,
-      "grad_norm": 0.48934102058410645,
+      "grad_norm": 0.48830151557922363,
       "learning_rate": 0.00010509977827050999,
-      "loss": 1.0249,
+      "loss": 1.0253,
       "step": 220
     },
     {
       "epoch": 1.4549450549450549,
-      "grad_norm": 0.6320819854736328,
+      "grad_norm": 0.6357678174972534,
       "learning_rate": 0.00010465631929046564,
       "loss": 0.903,
       "step": 221
     },
     {
       "epoch": 1.4615384615384617,
-      "grad_norm": 0.37240004539489746,
+      "grad_norm": 0.3743964433670044,
       "learning_rate": 0.0001042128603104213,
-      "loss": 0.6199,
+      "loss": 0.6212,
       "step": 222
     },
     {
       "epoch": 1.4681318681318682,
-      "grad_norm": 0.5312840938568115,
+      "grad_norm": 0.5299751162528992,
       "learning_rate": 0.00010376940133037693,
-      "loss": 0.9869,
+      "loss": 0.9885,
       "step": 223
     },
     {
       "epoch": 1.4747252747252748,
-      "grad_norm": 0.4181971549987793,
+      "grad_norm": 0.40817078948020935,
       "learning_rate": 0.00010332594235033259,
-      "loss": 0.6283,
+      "loss": 0.6275,
       "step": 224
     },
     {
       "epoch": 1.4813186813186814,
-      "grad_norm": 0.48793771862983704,
+      "grad_norm": 0.48665180802345276,
       "learning_rate": 0.00010288248337028825,
-      "loss": 0.8535,
+      "loss": 0.856,
       "step": 225
     },
     {
       "epoch": 1.487912087912088,
-      "grad_norm": 0.4725757837295532,
+      "grad_norm": 0.4728790521621704,
       "learning_rate": 0.0001024390243902439,
-      "loss": 0.9046,
+      "loss": 0.9029,
       "step": 226
     },
     {
       "epoch": 1.4945054945054945,
-      "grad_norm": 0.4119425117969513,
+      "grad_norm": 0.4079543650150299,
       "learning_rate": 0.00010199556541019956,
-      "loss": 0.7623,
+      "loss": 0.7612,
       "step": 227
     },
     {
       "epoch": 1.501098901098901,
-      "grad_norm": 0.4078834652900696,
+      "grad_norm": 0.405803918838501,
       "learning_rate": 0.00010155210643015522,
-      "loss": 0.8767,
+      "loss": 0.8774,
       "step": 228
     },
     {
       "epoch": 1.5076923076923077,
-      "grad_norm": 0.5141413807868958,
+      "grad_norm": 0.5138741731643677,
       "learning_rate": 0.00010110864745011087,
-      "loss": 0.9208,
+      "loss": 0.9248,
       "step": 229
     },
     {
       "epoch": 1.5142857142857142,
-      "grad_norm": 0.4738907814025879,
+      "grad_norm": 0.47216805815696716,
       "learning_rate": 0.00010066518847006652,
-      "loss": 0.8086,
+      "loss": 0.8091,
       "step": 230
     },
     {
       "epoch": 1.5208791208791208,
-      "grad_norm": 0.48960021138191223,
+      "grad_norm": 0.4865991473197937,
       "learning_rate": 0.00010022172949002218,
       "loss": 0.8186,
       "step": 231
     },
     {
       "epoch": 1.5274725274725274,
-      "grad_norm": 0.3945757746696472,
+      "grad_norm": 0.39264634251594543,
       "learning_rate": 9.977827050997783e-05,
-      "loss": 0.8251,
+      "loss": 0.825,
       "step": 232
     },
     {
       "epoch": 1.534065934065934,
-      "grad_norm": 0.503917396068573,
+      "grad_norm": 0.5051296353340149,
       "learning_rate": 9.933481152993348e-05,
-      "loss": 0.6703,
+      "loss": 0.673,
       "step": 233
     },
     {
       "epoch": 1.5406593406593405,
-      "grad_norm": 0.5501249432563782,
+      "grad_norm": 0.5474859476089478,
       "learning_rate": 9.889135254988914e-05,
-      "loss": 0.7364,
+      "loss": 0.7381,
       "step": 234
     },
     {
       "epoch": 1.5472527472527473,
-      "grad_norm": 0.5089092254638672,
+      "grad_norm": 0.5066180229187012,
       "learning_rate": 9.84478935698448e-05,
-      "loss": 0.9267,
+      "loss": 0.9272,
       "step": 235
     },
     {
       "epoch": 1.5538461538461539,
-      "grad_norm": 0.5353138446807861,
+      "grad_norm": 0.5217230916023254,
       "learning_rate": 9.800443458980046e-05,
-      "loss": 0.9295,
+      "loss": 0.9266,
       "step": 236
     },
     {
       "epoch": 1.5604395604395604,
-      "grad_norm": 0.5003825426101685,
+      "grad_norm": 0.499291330575943,
       "learning_rate": 9.75609756097561e-05,
-      "loss": 0.7878,
+      "loss": 0.7897,
       "step": 237
     },
     {
       "epoch": 1.567032967032967,
-      "grad_norm": 0.49696147441864014,
+      "grad_norm": 0.49313968420028687,
       "learning_rate": 9.711751662971176e-05,
-      "loss": 0.7435,
+      "loss": 0.7431,
       "step": 238
     },
     {
       "epoch": 1.5736263736263736,
-      "grad_norm": 0.5352329015731812,
+      "grad_norm": 0.533292829990387,
       "learning_rate": 9.667405764966742e-05,
-      "loss": 1.0217,
+      "loss": 1.0228,
       "step": 239
     },
     {
       "epoch": 1.5802197802197804,
-      "grad_norm": 0.623694658279419,
+      "grad_norm": 0.6194470524787903,
       "learning_rate": 9.623059866962306e-05,
-      "loss": 0.8223,
+      "loss": 0.8219,
       "step": 240
     },
     {
       "epoch": 1.586813186813187,
-      "grad_norm": 0.5698736310005188,
+      "grad_norm": 0.5656863451004028,
       "learning_rate": 9.578713968957872e-05,
-      "loss": 0.8657,
+      "loss": 0.8669,
       "step": 241
     },
     {
       "epoch": 1.5934065934065935,
-      "grad_norm": 0.6287338733673096,
+      "grad_norm": 0.6176244020462036,
       "learning_rate": 9.534368070953438e-05,
-      "loss": 0.9513,
+      "loss": 0.9491,
       "step": 242
     },
     {
       "epoch": 1.6,
-      "grad_norm": 0.5584443807601929,
+      "grad_norm": 0.5575570464134216,
       "learning_rate": 9.490022172949002e-05,
-      "loss": 0.8818,
+      "loss": 0.8817,
       "step": 243
     },
     {
       "epoch": 1.6065934065934067,
-      "grad_norm": 0.43259549140930176,
+      "grad_norm": 0.4302368760108948,
       "learning_rate": 9.445676274944568e-05,
-      "loss": 0.7049,
+      "loss": 0.7041,
       "step": 244
     },
     {
       "epoch": 1.6131868131868132,
-      "grad_norm": 0.5205944180488586,
+      "grad_norm": 0.5209348797798157,
       "learning_rate": 9.401330376940134e-05,
-      "loss": 0.9336,
+      "loss": 0.9347,
       "step": 245
     },
     {
       "epoch": 1.6197802197802198,
-      "grad_norm": 0.4521995782852173,
+      "grad_norm": 0.45345011353492737,
       "learning_rate": 9.356984478935698e-05,
-      "loss": 0.8326,
+      "loss": 0.8301,
       "step": 246
     },
     {
       "epoch": 1.6263736263736264,
-      "grad_norm": 0.6240835785865784,
+      "grad_norm": 0.6277614831924438,
       "learning_rate": 9.312638580931264e-05,
-      "loss": 0.7297,
+      "loss": 0.7309,
       "step": 247
     },
     {
       "epoch": 1.632967032967033,
-      "grad_norm": 0.6473103761672974,
+      "grad_norm": 0.6505606770515442,
       "learning_rate": 9.26829268292683e-05,
-      "loss": 0.9515,
+      "loss": 0.9511,
       "step": 248
     },
     {
       "epoch": 1.6395604395604395,
-      "grad_norm": 0.5175931453704834,
+      "grad_norm": 0.517275333404541,
       "learning_rate": 9.223946784922394e-05,
-      "loss": 0.8842,
+      "loss": 0.884,
       "step": 249
     },
     {
       "epoch": 1.646153846153846,
-      "grad_norm": 0.5029516816139221,
+      "grad_norm": 0.5025702714920044,
       "learning_rate": 9.17960088691796e-05,
-      "loss": 0.8379,
+      "loss": 0.8365,
       "step": 250
     },
     {
       "epoch": 1.6527472527472526,
-      "grad_norm": 0.48112156987190247,
+      "grad_norm": 0.48442235589027405,
       "learning_rate": 9.135254988913526e-05,
-      "loss": 0.8184,
+      "loss": 0.8194,
       "step": 251
     },
     {
       "epoch": 1.6593406593406592,
-      "grad_norm": 0.5661594271659851,
+      "grad_norm": 0.5697636008262634,
       "learning_rate": 9.090909090909092e-05,
-      "loss": 0.8452,
+      "loss": 0.8483,
       "step": 252
     },
     {
       "epoch": 1.6659340659340658,
-      "grad_norm": 0.4606223702430725,
+      "grad_norm": 0.46080318093299866,
       "learning_rate": 9.046563192904656e-05,
-      "loss": 0.9318,
+      "loss": 0.9333,
       "step": 253
     },
     {
       "epoch": 1.6725274725274726,
-      "grad_norm": 0.6081652641296387,
+      "grad_norm": 0.608308732509613,
       "learning_rate": 9.002217294900222e-05,
-      "loss": 0.868,
+      "loss": 0.8664,
       "step": 254
     },
     {
       "epoch": 1.6791208791208792,
-      "grad_norm": 0.5501449108123779,
+      "grad_norm": 0.5430044531822205,
       "learning_rate": 8.957871396895788e-05,
-      "loss": 0.7554,
+      "loss": 0.7544,
       "step": 255
     },
     {
       "epoch": 1.6857142857142857,
-      "grad_norm": 0.5132472515106201,
+      "grad_norm": 0.5087573528289795,
       "learning_rate": 8.913525498891354e-05,
-      "loss": 0.8358,
+      "loss": 0.8334,
       "step": 256
     },
     {
       "epoch": 1.6923076923076923,
-      "grad_norm": 0.58882075548172,
+      "grad_norm": 0.5861541032791138,
       "learning_rate": 8.869179600886919e-05,
-      "loss": 0.8121,
+      "loss": 0.8126,
       "step": 257
     },
     {
       "epoch": 1.6989010989010989,
-      "grad_norm": 0.4934251308441162,
+      "grad_norm": 0.49458786845207214,
       "learning_rate": 8.824833702882484e-05,
-      "loss": 0.6498,
+      "loss": 0.651,
       "step": 258
     },
     {
       "epoch": 1.7054945054945057,
-      "grad_norm": 0.527324914932251,
+      "grad_norm": 0.5279380083084106,
       "learning_rate": 8.78048780487805e-05,
-      "loss": 0.8831,
+      "loss": 0.884,
       "step": 259
     },
     {
       "epoch": 1.7120879120879122,
-      "grad_norm": 0.5594726204872131,
+      "grad_norm": 0.5632112622261047,
       "learning_rate": 8.736141906873615e-05,
-      "loss": 0.7615,
+      "loss": 0.7629,
       "step": 260
     },
     {
       "epoch": 1.7186813186813188,
-      "grad_norm": 0.4157647490501404,
+      "grad_norm": 0.4152830243110657,
       "learning_rate": 8.69179600886918e-05,
-      "loss": 0.6352,
+      "loss": 0.6359,
       "step": 261
     },
     {
       "epoch": 1.7252747252747254,
-      "grad_norm": 0.5544142127037048,
+      "grad_norm": 0.5582665801048279,
       "learning_rate": 8.647450110864746e-05,
-      "loss": 0.7647,
+      "loss": 0.7673,
       "step": 262
     },
     {
       "epoch": 1.731868131868132,
-      "grad_norm": 0.5794146656990051,
+      "grad_norm": 0.5803923010826111,
       "learning_rate": 8.603104212860311e-05,
-      "loss": 0.8193,
+      "loss": 0.8208,
       "step": 263
     },
     {
       "epoch": 1.7384615384615385,
-      "grad_norm": 0.5707643628120422,
+      "grad_norm": 0.5731257200241089,
       "learning_rate": 8.558758314855876e-05,
-      "loss": 0.9284,
+      "loss": 0.9294,
       "step": 264
     },
     {
       "epoch": 1.745054945054945,
-      "grad_norm": 0.5336015224456787,
+      "grad_norm": 0.5312943458557129,
       "learning_rate": 8.514412416851442e-05,
-      "loss": 0.7651,
+      "loss": 0.7645,
       "step": 265
     },
     {
       "epoch": 1.7516483516483516,
-      "grad_norm": 0.570565938949585,
+      "grad_norm": 0.5703001618385315,
       "learning_rate": 8.470066518847007e-05,
-      "loss": 0.8801,
+      "loss": 0.8792,
       "step": 266
     },
     {
       "epoch": 1.7582417582417582,
-      "grad_norm": 0.4774629771709442,
+      "grad_norm": 0.4772545099258423,
       "learning_rate": 8.425720620842572e-05,
-      "loss": 0.6867,
+      "loss": 0.685,
       "step": 267
     },
     {
       "epoch": 1.7648351648351648,
-      "grad_norm": 0.5763434171676636,
+      "grad_norm": 0.5768313407897949,
       "learning_rate": 8.381374722838138e-05,
-      "loss": 0.871,
+      "loss": 0.8711,
       "step": 268
     },
     {
       "epoch": 1.7714285714285714,
-      "grad_norm": 0.5346274375915527,
+      "grad_norm": 0.5340241193771362,
       "learning_rate": 8.337028824833703e-05,
-      "loss": 0.7595,
+      "loss": 0.7604,
       "step": 269
     },
     {
       "epoch": 1.778021978021978,
-      "grad_norm": 0.4729682505130768,
+      "grad_norm": 0.46766021847724915,
       "learning_rate": 8.292682926829268e-05,
-      "loss": 0.8858,
+      "loss": 0.8833,
       "step": 270
     },
     {
       "epoch": 1.7846153846153845,
-      "grad_norm": 0.5091648101806641,
+      "grad_norm": 0.504288375377655,
       "learning_rate": 8.248337028824834e-05,
-      "loss": 0.8684,
+      "loss": 0.8686,
       "step": 271
     },
     {
       "epoch": 1.791208791208791,
-      "grad_norm": 0.5616800785064697,
+      "grad_norm": 0.5594892501831055,
       "learning_rate": 8.2039911308204e-05,
-      "loss": 0.8894,
+      "loss": 0.8893,
       "step": 272
     },
     {
       "epoch": 1.7978021978021979,
-      "grad_norm": 0.674109697341919,
+      "grad_norm": 0.6431511640548706,
       "learning_rate": 8.159645232815965e-05,
-      "loss": 0.9287,
+      "loss": 0.9268,
       "step": 273
     },
     {
       "epoch": 1.8043956043956044,
-      "grad_norm": 0.49833887815475464,
+      "grad_norm": 0.49714767932891846,
       "learning_rate": 8.11529933481153e-05,
-      "loss": 0.9106,
+      "loss": 0.911,
       "step": 274
     },
     {
       "epoch": 1.810989010989011,
-      "grad_norm": 0.4930139482021332,
+      "grad_norm": 0.49170583486557007,
       "learning_rate": 8.070953436807095e-05,
-      "loss": 0.7703,
+      "loss": 0.7715,
       "step": 275
     },
     {
       "epoch": 1.8175824175824176,
-      "grad_norm": 0.5709042549133301,
+      "grad_norm": 0.5718923211097717,
       "learning_rate": 8.026607538802661e-05,
-      "loss": 0.8175,
+      "loss": 0.8184,
       "step": 276
     },
     {
       "epoch": 1.8241758241758241,
-      "grad_norm": 0.5040735602378845,
+      "grad_norm": 0.5025438666343689,
       "learning_rate": 7.982261640798227e-05,
-      "loss": 0.7684,
+      "loss": 0.7682,
       "step": 277
     },
     {
       "epoch": 1.830769230769231,
-      "grad_norm": 0.5715399384498596,
+      "grad_norm": 0.5658840537071228,
       "learning_rate": 7.937915742793793e-05,
-      "loss": 0.8707,
+      "loss": 0.871,
       "step": 278
     },
     {
       "epoch": 1.8373626373626375,
-      "grad_norm": 0.598209798336029,
+      "grad_norm": 0.599318265914917,
       "learning_rate": 7.893569844789357e-05,
-      "loss": 0.7617,
+      "loss": 0.7616,
       "step": 279
     },
     {
       "epoch": 1.843956043956044,
-      "grad_norm": 0.4840480387210846,
+      "grad_norm": 0.4796925187110901,
       "learning_rate": 7.849223946784923e-05,
-      "loss": 0.673,
+      "loss": 0.6709,
       "step": 280
     },
     {
       "epoch": 1.8505494505494506,
-      "grad_norm": 0.6277756690979004,
+      "grad_norm": 0.6288089752197266,
       "learning_rate": 7.804878048780489e-05,
-      "loss": 0.9212,
+      "loss": 0.9234,
       "step": 281
     },
     {
       "epoch": 1.8571428571428572,
-      "grad_norm": 0.43180781602859497,
+      "grad_norm": 0.4306858777999878,
       "learning_rate": 7.760532150776053e-05,
-      "loss": 0.7897,
+      "loss": 0.7884,
       "step": 282
     },
     {
       "epoch": 1.8637362637362638,
-      "grad_norm": 0.6619057059288025,
+      "grad_norm": 0.6535850763320923,
       "learning_rate": 7.716186252771619e-05,
-      "loss": 0.8536,
+      "loss": 0.8589,
       "step": 283
     },
     {
       "epoch": 1.8703296703296703,
-      "grad_norm": 0.5808956623077393,
+      "grad_norm": 0.580440104007721,
       "learning_rate": 7.671840354767185e-05,
-      "loss": 0.744,
+      "loss": 0.7448,
       "step": 284
     },
     {
       "epoch": 1.876923076923077,
-      "grad_norm": 0.5059854388237,
+      "grad_norm": 0.5104124546051025,
       "learning_rate": 7.627494456762749e-05,
-      "loss": 0.8277,
+      "loss": 0.8256,
       "step": 285
     },
     {
       "epoch": 1.8835164835164835,
-      "grad_norm": 0.6028903126716614,
+      "grad_norm": 0.6120128631591797,
       "learning_rate": 7.583148558758315e-05,
-      "loss": 0.8164,
+      "loss": 0.8174,
       "step": 286
     },
     {
       "epoch": 1.89010989010989,
-      "grad_norm": 0.5524346828460693,
+      "grad_norm": 0.5515565872192383,
       "learning_rate": 7.538802660753881e-05,
-      "loss": 0.8946,
+      "loss": 0.8941,
       "step": 287
     },
     {
       "epoch": 1.8967032967032966,
-      "grad_norm": 0.5920316576957703,
+      "grad_norm": 0.5927900075912476,
       "learning_rate": 7.494456762749445e-05,
-      "loss": 0.8985,
+      "loss": 0.9,
       "step": 288
     },
     {
       "epoch": 1.9032967032967032,
-      "grad_norm": 0.526829183101654,
+      "grad_norm": 0.5271000266075134,
       "learning_rate": 7.450110864745011e-05,
-      "loss": 0.7886,
+      "loss": 0.7902,
       "step": 289
     },
     {
       "epoch": 1.9098901098901098,
-      "grad_norm": 0.5900607705116272,
+      "grad_norm": 0.5868595242500305,
       "learning_rate": 7.405764966740577e-05,
-      "loss": 0.8317,
+      "loss": 0.832,
       "step": 290
     },
     {
       "epoch": 1.9164835164835163,
-      "grad_norm": 0.5781202912330627,
+      "grad_norm": 0.5776485204696655,
       "learning_rate": 7.361419068736141e-05,
-      "loss": 0.8963,
+      "loss": 0.898,
       "step": 291
     },
     {
       "epoch": 1.9230769230769231,
-      "grad_norm": 0.5648344159126282,
+      "grad_norm": 0.5612866878509521,
       "learning_rate": 7.317073170731707e-05,
-      "loss": 0.9504,
+      "loss": 0.9498,
       "step": 292
     },
     {
       "epoch": 1.9296703296703297,
-      "grad_norm": 0.5043098330497742,
+      "grad_norm": 0.5058277249336243,
       "learning_rate": 7.272727272727273e-05,
-      "loss": 0.7105,
+      "loss": 0.7128,
       "step": 293
     },
     {
       "epoch": 1.9362637362637363,
-      "grad_norm": 0.6060357689857483,
+      "grad_norm": 0.6034194827079773,
       "learning_rate": 7.228381374722837e-05,
-      "loss": 0.8359,
+      "loss": 0.8362,
       "step": 294
     },
     {
       "epoch": 1.9428571428571428,
-      "grad_norm": 0.5285889506340027,
+      "grad_norm": 0.5308236479759216,
       "learning_rate": 7.184035476718403e-05,
-      "loss": 0.8729,
+      "loss": 0.8766,
       "step": 295
     },
     {
       "epoch": 1.9494505494505494,
-      "grad_norm": 0.5470148324966431,
+      "grad_norm": 0.5458571910858154,
       "learning_rate": 7.139689578713969e-05,
-      "loss": 0.8372,
+      "loss": 0.8377,
       "step": 296
     },
     {
       "epoch": 1.9560439560439562,
-      "grad_norm": 0.5567497611045837,
+      "grad_norm": 0.5560564398765564,
       "learning_rate": 7.095343680709535e-05,
-      "loss": 0.9714,
+      "loss": 0.9705,
       "step": 297
     },
     {
       "epoch": 1.9626373626373628,
-      "grad_norm": 0.5564576983451843,
+      "grad_norm": 0.5563681721687317,
       "learning_rate": 7.0509977827051e-05,
       "loss": 0.8965,
       "step": 298
     },
     {
       "epoch": 1.9692307692307693,
-      "grad_norm": 0.589551568031311,
+      "grad_norm": 0.5891811847686768,
       "learning_rate": 7.006651884700666e-05,
-      "loss": 0.9231,
+      "loss": 0.9244,
       "step": 299
     },
     {
       "epoch": 1.975824175824176,
-      "grad_norm": 0.5011605024337769,
+      "grad_norm": 0.499325692653656,
       "learning_rate": 6.962305986696232e-05,
-      "loss": 0.775,
+      "loss": 0.7758,
       "step": 300
     }
   ],

checkpoint-300/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f89cc27d59aec0e431061d1799f46236096c2f54579a6de4e23dfbd5ccc6993
+oid sha256:861fe82cdf523b5f92a3195edb82a6758130d64d6670a7f710a80c6ba4297095
 size 6417