Upload folder using huggingface_hub

checkpoint-240/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-240/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4211330949023f6836a7b67cd7ed5a7cfb47357ef32aa618367fb580c01aaf17
+oid sha256:9fc6b1b778ca3f5c5005f2460795101214cc0aa1afbc6b754bc1ae7e12ff0572
 size 59933632

checkpoint-240/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40fc407bb92e827c6da3dcc86a703bd1435d4cf7b6daf320e2df51cbc0f982d5
+oid sha256:098d9125fe6e819172d461380d770a1ad6fdef590fe15afda4f74220df0b9b5d
 size 120166091

checkpoint-240/trainer_state.json

@@ -67,1626 +67,1626 @@
     },
     {
       "epoch": 0.05934065934065934,
-      "grad_norm": 0.8124693632125854,
+      "grad_norm": 0.812495768070221,
       "learning_rate": 0.00019866962305986697,
       "loss": 1.3178,
       "step": 9
     },
     {
       "epoch": 0.06593406593406594,
-      "grad_norm": 1.4746452569961548,
+      "grad_norm": 1.4647173881530762,
       "learning_rate": 0.00019822616407982261,
-      "loss": 1.3747,
+      "loss": 1.3721,
       "step": 10
     },
     {
       "epoch": 0.07252747252747253,
-      "grad_norm": 1.0956214666366577,
+      "grad_norm": 1.0903385877609253,
       "learning_rate": 0.00019778270509977829,
-      "loss": 1.2291,
+      "loss": 1.2288,
       "step": 11
     },
     {
       "epoch": 0.07912087912087912,
-      "grad_norm": 0.5584886074066162,
+      "grad_norm": 0.5566668510437012,
       "learning_rate": 0.00019733924611973393,
-      "loss": 1.2929,
+      "loss": 1.2958,
       "step": 12
     },
     {
       "epoch": 0.08571428571428572,
-      "grad_norm": 0.8778825402259827,
+      "grad_norm": 0.9000307321548462,
       "learning_rate": 0.0001968957871396896,
-      "loss": 1.0355,
+      "loss": 1.0353,
       "step": 13
     },
     {
       "epoch": 0.09230769230769231,
-      "grad_norm": 0.5020594596862793,
+      "grad_norm": 0.5002865791320801,
       "learning_rate": 0.00019645232815964525,
-      "loss": 1.1668,
+      "loss": 1.1657,
       "step": 14
     },
     {
       "epoch": 0.0989010989010989,
-      "grad_norm": 0.4985601305961609,
+      "grad_norm": 0.4956091344356537,
       "learning_rate": 0.00019600886917960092,
-      "loss": 1.1048,
+      "loss": 1.1026,
       "step": 15
     },
     {
       "epoch": 0.1054945054945055,
-      "grad_norm": 0.4597553312778473,
+      "grad_norm": 0.46295931935310364,
       "learning_rate": 0.00019556541019955653,
-      "loss": 1.0144,
+      "loss": 1.0131,
       "step": 16
     },
     {
       "epoch": 0.11208791208791209,
-      "grad_norm": 0.44980549812316895,
+      "grad_norm": 0.44878455996513367,
       "learning_rate": 0.0001951219512195122,
-      "loss": 1.128,
+      "loss": 1.1302,
       "step": 17
     },
     {
       "epoch": 0.11868131868131868,
-      "grad_norm": 0.33276212215423584,
+      "grad_norm": 0.3325801193714142,
       "learning_rate": 0.00019467849223946785,
-      "loss": 0.9434,
+      "loss": 0.9445,
       "step": 18
     },
     {
       "epoch": 0.12527472527472527,
-      "grad_norm": 0.46772485971450806,
+      "grad_norm": 0.46596264839172363,
       "learning_rate": 0.00019423503325942352,
-      "loss": 1.2302,
+      "loss": 1.2325,
       "step": 19
     },
     {
       "epoch": 0.13186813186813187,
-      "grad_norm": 0.3876091241836548,
+      "grad_norm": 0.38645994663238525,
       "learning_rate": 0.00019379157427937917,
-      "loss": 1.0448,
+      "loss": 1.0453,
       "step": 20
     },
     {
       "epoch": 0.13846153846153847,
-      "grad_norm": 0.3786633610725403,
+      "grad_norm": 0.3800373375415802,
       "learning_rate": 0.00019334811529933484,
-      "loss": 1.0449,
+      "loss": 1.045,
       "step": 21
     },
     {
       "epoch": 0.14505494505494507,
-      "grad_norm": 0.4180683195590973,
+      "grad_norm": 0.4129738211631775,
       "learning_rate": 0.00019290465631929045,
-      "loss": 1.1112,
+      "loss": 1.1104,
       "step": 22
     },
     {
       "epoch": 0.15164835164835164,
-      "grad_norm": 0.4051693081855774,
+      "grad_norm": 0.40392687916755676,
       "learning_rate": 0.00019246119733924613,
-      "loss": 1.0586,
+      "loss": 1.0589,
       "step": 23
     },
     {
       "epoch": 0.15824175824175823,
-      "grad_norm": 0.30783703923225403,
+      "grad_norm": 0.3075926899909973,
       "learning_rate": 0.00019201773835920177,
-      "loss": 0.9412,
+      "loss": 0.9411,
       "step": 24
     },
     {
       "epoch": 0.16483516483516483,
-      "grad_norm": 0.3420283794403076,
+      "grad_norm": 0.3475458323955536,
       "learning_rate": 0.00019157427937915744,
-      "loss": 0.9213,
+      "loss": 0.9233,
       "step": 25
     },
     {
       "epoch": 0.17142857142857143,
-      "grad_norm": 0.47376200556755066,
+      "grad_norm": 0.49025434255599976,
       "learning_rate": 0.00019113082039911309,
-      "loss": 0.9635,
+      "loss": 0.9665,
       "step": 26
     },
     {
       "epoch": 0.17802197802197803,
-      "grad_norm": 0.3626822233200073,
+      "grad_norm": 0.3652801215648651,
       "learning_rate": 0.00019068736141906876,
-      "loss": 0.7696,
+      "loss": 0.7703,
       "step": 27
     },
     {
       "epoch": 0.18461538461538463,
-      "grad_norm": 0.46646377444267273,
+      "grad_norm": 0.45883381366729736,
       "learning_rate": 0.0001902439024390244,
-      "loss": 1.098,
+      "loss": 1.0975,
       "step": 28
     },
     {
       "epoch": 0.1912087912087912,
-      "grad_norm": 0.38763922452926636,
+      "grad_norm": 0.3874357044696808,
       "learning_rate": 0.00018980044345898005,
-      "loss": 1.1587,
+      "loss": 1.1598,
       "step": 29
     },
     {
       "epoch": 0.1978021978021978,
-      "grad_norm": 0.3439793288707733,
+      "grad_norm": 0.34444889426231384,
       "learning_rate": 0.00018935698447893572,
-      "loss": 1.1153,
+      "loss": 1.115,
       "step": 30
     },
     {
       "epoch": 0.2043956043956044,
-      "grad_norm": 0.30000773072242737,
+      "grad_norm": 0.29951217770576477,
       "learning_rate": 0.00018891352549889136,
-      "loss": 0.9554,
+      "loss": 0.954,
       "step": 31
     },
     {
       "epoch": 0.210989010989011,
-      "grad_norm": 0.3823530972003937,
+      "grad_norm": 0.3819473087787628,
       "learning_rate": 0.00018847006651884703,
       "loss": 0.8394,
       "step": 32
     },
     {
       "epoch": 0.2175824175824176,
-      "grad_norm": 0.34664639830589294,
+      "grad_norm": 0.34401172399520874,
       "learning_rate": 0.00018802660753880268,
-      "loss": 0.9849,
+      "loss": 0.9835,
       "step": 33
     },
     {
       "epoch": 0.22417582417582418,
-      "grad_norm": 0.3785923719406128,
+      "grad_norm": 0.37742576003074646,
       "learning_rate": 0.00018758314855875832,
-      "loss": 0.9833,
+      "loss": 0.9849,
       "step": 34
     },
     {
       "epoch": 0.23076923076923078,
-      "grad_norm": 0.2902650535106659,
+      "grad_norm": 0.2915305495262146,
       "learning_rate": 0.00018713968957871397,
-      "loss": 0.8436,
+      "loss": 0.8447,
       "step": 35
     },
     {
       "epoch": 0.23736263736263735,
-      "grad_norm": 0.3445191979408264,
+      "grad_norm": 0.3420809507369995,
       "learning_rate": 0.00018669623059866964,
-      "loss": 1.1307,
+      "loss": 1.1309,
       "step": 36
     },
     {
       "epoch": 0.24395604395604395,
-      "grad_norm": 0.3029124438762665,
+      "grad_norm": 0.29988887906074524,
       "learning_rate": 0.00018625277161862528,
-      "loss": 0.9933,
+      "loss": 0.9923,
       "step": 37
     },
     {
       "epoch": 0.25054945054945055,
-      "grad_norm": 0.35134652256965637,
+      "grad_norm": 0.34842392802238464,
       "learning_rate": 0.00018580931263858095,
-      "loss": 1.0888,
+      "loss": 1.0878,
       "step": 38
     },
     {
       "epoch": 0.2571428571428571,
-      "grad_norm": 0.3323468863964081,
+      "grad_norm": 0.33255407214164734,
       "learning_rate": 0.0001853658536585366,
-      "loss": 0.9426,
+      "loss": 0.9427,
       "step": 39
     },
     {
       "epoch": 0.26373626373626374,
-      "grad_norm": 0.30780231952667236,
+      "grad_norm": 0.3048710525035858,
       "learning_rate": 0.00018492239467849224,
-      "loss": 1.0471,
+      "loss": 1.046,
       "step": 40
     },
     {
       "epoch": 0.2703296703296703,
-      "grad_norm": 0.33622869849205017,
+      "grad_norm": 0.3348377048969269,
       "learning_rate": 0.0001844789356984479,
-      "loss": 1.0502,
+      "loss": 1.0524,
       "step": 41
     },
     {
       "epoch": 0.27692307692307694,
-      "grad_norm": 0.27680298686027527,
+      "grad_norm": 0.27776357531547546,
       "learning_rate": 0.00018403547671840356,
-      "loss": 0.9102,
+      "loss": 0.9091,
       "step": 42
     },
     {
       "epoch": 0.2835164835164835,
-      "grad_norm": 0.30690091848373413,
+      "grad_norm": 0.3071886897087097,
       "learning_rate": 0.0001835920177383592,
-      "loss": 0.8996,
+      "loss": 0.8991,
       "step": 43
     },
     {
       "epoch": 0.29010989010989013,
-      "grad_norm": 0.25448524951934814,
+      "grad_norm": 0.25560522079467773,
       "learning_rate": 0.00018314855875831487,
-      "loss": 1.1005,
+      "loss": 1.1003,
       "step": 44
     },
     {
       "epoch": 0.2967032967032967,
-      "grad_norm": 0.34958240389823914,
+      "grad_norm": 0.35056671500205994,
       "learning_rate": 0.00018270509977827052,
-      "loss": 1.0281,
+      "loss": 1.0294,
       "step": 45
     },
     {
       "epoch": 0.3032967032967033,
-      "grad_norm": 0.4468621015548706,
+      "grad_norm": 0.4527668356895447,
       "learning_rate": 0.00018226164079822616,
-      "loss": 1.0252,
+      "loss": 1.0258,
       "step": 46
     },
     {
       "epoch": 0.3098901098901099,
-      "grad_norm": 0.31876784563064575,
+      "grad_norm": 0.3258602023124695,
       "learning_rate": 0.00018181818181818183,
-      "loss": 0.8992,
+      "loss": 0.8985,
       "step": 47
     },
     {
       "epoch": 0.31648351648351647,
-      "grad_norm": 0.34545132517814636,
+      "grad_norm": 0.34211626648902893,
       "learning_rate": 0.00018137472283813748,
-      "loss": 1.068,
+      "loss": 1.0694,
       "step": 48
     },
     {
       "epoch": 0.3230769230769231,
-      "grad_norm": 0.32640132308006287,
+      "grad_norm": 0.33114686608314514,
       "learning_rate": 0.00018093126385809312,
-      "loss": 1.1285,
+      "loss": 1.1302,
       "step": 49
     },
     {
       "epoch": 0.32967032967032966,
-      "grad_norm": 0.3564831018447876,
+      "grad_norm": 0.3916858732700348,
       "learning_rate": 0.0001804878048780488,
-      "loss": 1.2185,
+      "loss": 1.2209,
       "step": 50
     },
     {
       "epoch": 0.3362637362637363,
-      "grad_norm": 0.32339203357696533,
+      "grad_norm": 0.3141515851020813,
       "learning_rate": 0.00018004434589800444,
-      "loss": 1.0446,
+      "loss": 1.0462,
       "step": 51
     },
     {
       "epoch": 0.34285714285714286,
-      "grad_norm": 0.35078808665275574,
+      "grad_norm": 0.3583016097545624,
       "learning_rate": 0.00017960088691796008,
-      "loss": 1.1539,
+      "loss": 1.1564,
       "step": 52
     },
     {
       "epoch": 0.34945054945054943,
-      "grad_norm": 0.2938004732131958,
+      "grad_norm": 0.3011229634284973,
       "learning_rate": 0.00017915742793791575,
-      "loss": 0.9885,
+      "loss": 0.9886,
       "step": 53
     },
     {
       "epoch": 0.35604395604395606,
-      "grad_norm": 0.3535275459289551,
+      "grad_norm": 0.35539111495018005,
       "learning_rate": 0.0001787139689578714,
       "loss": 1.2243,
       "step": 54
     },
     {
       "epoch": 0.3626373626373626,
-      "grad_norm": 0.27938902378082275,
+      "grad_norm": 0.2820283770561218,
       "learning_rate": 0.00017827050997782707,
-      "loss": 0.8127,
+      "loss": 0.8119,
       "step": 55
     },
     {
       "epoch": 0.36923076923076925,
-      "grad_norm": 0.3669883906841278,
+      "grad_norm": 0.3814904987812042,
       "learning_rate": 0.00017782705099778271,
-      "loss": 1.1137,
+      "loss": 1.1126,
       "step": 56
     },
     {
       "epoch": 0.3758241758241758,
-      "grad_norm": 0.29758307337760925,
+      "grad_norm": 0.2957267761230469,
       "learning_rate": 0.00017738359201773839,
-      "loss": 0.8903,
+      "loss": 0.8904,
       "step": 57
     },
     {
       "epoch": 0.3824175824175824,
-      "grad_norm": 0.33421579003334045,
+      "grad_norm": 0.33433598279953003,
       "learning_rate": 0.000176940133037694,
-      "loss": 0.9599,
+      "loss": 0.9598,
       "step": 58
     },
     {
       "epoch": 0.389010989010989,
-      "grad_norm": 0.2770750820636749,
+      "grad_norm": 0.29762426018714905,
       "learning_rate": 0.00017649667405764967,
-      "loss": 0.8669,
+      "loss": 0.8673,
       "step": 59
     },
     {
       "epoch": 0.3956043956043956,
-      "grad_norm": 0.30138126015663147,
+      "grad_norm": 0.2994730770587921,
       "learning_rate": 0.00017605321507760532,
-      "loss": 0.9341,
+      "loss": 0.9338,
       "step": 60
     },
     {
       "epoch": 0.4021978021978022,
-      "grad_norm": 0.40909135341644287,
+      "grad_norm": 0.4122157394886017,
       "learning_rate": 0.000175609756097561,
-      "loss": 0.9882,
+      "loss": 0.9901,
       "step": 61
     },
     {
       "epoch": 0.4087912087912088,
-      "grad_norm": 0.3172509968280792,
+      "grad_norm": 0.31992846727371216,
       "learning_rate": 0.00017516629711751663,
-      "loss": 0.947,
+      "loss": 0.9478,
       "step": 62
     },
     {
       "epoch": 0.4153846153846154,
-      "grad_norm": 0.3970111012458801,
+      "grad_norm": 0.3978268802165985,
       "learning_rate": 0.0001747228381374723,
-      "loss": 1.0486,
+      "loss": 1.0468,
       "step": 63
     },
     {
       "epoch": 0.421978021978022,
-      "grad_norm": 0.31454795598983765,
+      "grad_norm": 0.31832677125930786,
       "learning_rate": 0.00017427937915742792,
       "loss": 1.0186,
       "step": 64
     },
     {
       "epoch": 0.42857142857142855,
-      "grad_norm": 0.3479641079902649,
+      "grad_norm": 0.34894299507141113,
       "learning_rate": 0.0001738359201773836,
-      "loss": 0.9327,
+      "loss": 0.9357,
       "step": 65
     },
     {
       "epoch": 0.4351648351648352,
-      "grad_norm": 0.3524766266345978,
+      "grad_norm": 0.3534030318260193,
       "learning_rate": 0.00017339246119733924,
-      "loss": 0.9507,
+      "loss": 0.9494,
       "step": 66
     },
     {
       "epoch": 0.44175824175824174,
-      "grad_norm": 0.2844376266002655,
+      "grad_norm": 0.2846975326538086,
       "learning_rate": 0.0001729490022172949,
-      "loss": 0.7746,
+      "loss": 0.7745,
       "step": 67
     },
     {
       "epoch": 0.44835164835164837,
-      "grad_norm": 0.3422749638557434,
+      "grad_norm": 0.3415786325931549,
       "learning_rate": 0.00017250554323725056,
-      "loss": 1.0457,
+      "loss": 1.0462,
       "step": 68
     },
     {
       "epoch": 0.45494505494505494,
-      "grad_norm": 0.4011959135532379,
+      "grad_norm": 0.3965073823928833,
       "learning_rate": 0.00017206208425720623,
-      "loss": 1.007,
+      "loss": 1.0058,
       "step": 69
     },
     {
       "epoch": 0.46153846153846156,
-      "grad_norm": 0.4012478291988373,
+      "grad_norm": 0.3992333710193634,
       "learning_rate": 0.00017161862527716187,
-      "loss": 1.0548,
+      "loss": 1.055,
       "step": 70
     },
     {
       "epoch": 0.46813186813186813,
-      "grad_norm": 0.3155313730239868,
+      "grad_norm": 0.31529131531715393,
       "learning_rate": 0.00017117516629711752,
-      "loss": 1.0115,
+      "loss": 1.0131,
       "step": 71
     },
     {
       "epoch": 0.4747252747252747,
-      "grad_norm": 0.42125996947288513,
+      "grad_norm": 0.4225400686264038,
       "learning_rate": 0.0001707317073170732,
-      "loss": 1.0328,
+      "loss": 1.0361,
       "step": 72
     },
     {
       "epoch": 0.48131868131868133,
-      "grad_norm": 0.24873152375221252,
+      "grad_norm": 0.24861474335193634,
       "learning_rate": 0.00017028824833702883,
       "loss": 0.8636,
       "step": 73
     },
     {
       "epoch": 0.4879120879120879,
-      "grad_norm": 0.3159611225128174,
+      "grad_norm": 0.3111610412597656,
       "learning_rate": 0.0001698447893569845,
-      "loss": 0.8,
+      "loss": 0.8018,
       "step": 74
     },
     {
       "epoch": 0.4945054945054945,
-      "grad_norm": 0.33214104175567627,
+      "grad_norm": 0.3332616090774536,
       "learning_rate": 0.00016940133037694015,
-      "loss": 0.9654,
+      "loss": 0.9639,
       "step": 75
     },
     {
       "epoch": 0.5010989010989011,
-      "grad_norm": 0.347202867269516,
+      "grad_norm": 0.34602120518684387,
       "learning_rate": 0.00016895787139689582,
-      "loss": 0.9652,
+      "loss": 0.9634,
       "step": 76
     },
     {
       "epoch": 0.5076923076923077,
-      "grad_norm": 0.2956635653972626,
+      "grad_norm": 0.30103614926338196,
       "learning_rate": 0.00016851441241685144,
-      "loss": 0.8443,
+      "loss": 0.8445,
       "step": 77
     },
     {
       "epoch": 0.5142857142857142,
-      "grad_norm": 0.32437971234321594,
+      "grad_norm": 0.32351967692375183,
       "learning_rate": 0.0001680709534368071,
-      "loss": 0.7974,
+      "loss": 0.7971,
       "step": 78
     },
     {
       "epoch": 0.5208791208791209,
-      "grad_norm": 0.34554967284202576,
+      "grad_norm": 0.34235212206840515,
       "learning_rate": 0.00016762749445676275,
-      "loss": 0.8792,
+      "loss": 0.8789,
       "step": 79
     },
     {
       "epoch": 0.5274725274725275,
-      "grad_norm": 0.36469560861587524,
+      "grad_norm": 0.37176913022994995,
       "learning_rate": 0.00016718403547671842,
-      "loss": 0.866,
+      "loss": 0.8665,
       "step": 80
     },
     {
       "epoch": 0.5340659340659341,
-      "grad_norm": 0.344759076833725,
+      "grad_norm": 0.3396773636341095,
       "learning_rate": 0.00016674057649667407,
-      "loss": 0.8353,
+      "loss": 0.8336,
       "step": 81
     },
     {
       "epoch": 0.5406593406593406,
-      "grad_norm": 0.34023046493530273,
+      "grad_norm": 0.34001272916793823,
       "learning_rate": 0.00016629711751662974,
-      "loss": 1.02,
+      "loss": 1.0193,
       "step": 82
     },
     {
       "epoch": 0.5472527472527473,
-      "grad_norm": 0.333598256111145,
+      "grad_norm": 0.331545889377594,
       "learning_rate": 0.00016585365853658536,
-      "loss": 1.0249,
+      "loss": 1.0259,
       "step": 83
     },
     {
       "epoch": 0.5538461538461539,
-      "grad_norm": 0.3101555109024048,
+      "grad_norm": 0.3043355941772461,
       "learning_rate": 0.00016541019955654103,
-      "loss": 0.9582,
+      "loss": 0.9557,
       "step": 84
     },
     {
       "epoch": 0.5604395604395604,
-      "grad_norm": 0.33129116892814636,
+      "grad_norm": 0.3296355903148651,
       "learning_rate": 0.00016496674057649667,
-      "loss": 1.1624,
+      "loss": 1.1619,
       "step": 85
     },
     {
       "epoch": 0.567032967032967,
-      "grad_norm": 0.30904698371887207,
+      "grad_norm": 0.3109373450279236,
       "learning_rate": 0.00016452328159645234,
-      "loss": 0.9186,
+      "loss": 0.9192,
       "step": 86
     },
     {
       "epoch": 0.5736263736263736,
-      "grad_norm": 0.3824373483657837,
+      "grad_norm": 0.38110268115997314,
       "learning_rate": 0.000164079822616408,
       "loss": 1.0527,
       "step": 87
     },
     {
       "epoch": 0.5802197802197803,
-      "grad_norm": 0.32758963108062744,
+      "grad_norm": 0.3296146094799042,
       "learning_rate": 0.00016363636363636366,
-      "loss": 1.1586,
+      "loss": 1.1576,
       "step": 88
     },
     {
       "epoch": 0.5868131868131868,
-      "grad_norm": 0.39826932549476624,
+      "grad_norm": 0.40074533224105835,
       "learning_rate": 0.0001631929046563193,
-      "loss": 1.2648,
+      "loss": 1.2656,
       "step": 89
     },
     {
       "epoch": 0.5934065934065934,
-      "grad_norm": 0.3101160526275635,
+      "grad_norm": 0.31375083327293396,
       "learning_rate": 0.00016274944567627495,
-      "loss": 1.0503,
+      "loss": 1.0495,
       "step": 90
     },
     {
       "epoch": 0.6,
-      "grad_norm": 0.5018938183784485,
+      "grad_norm": 0.5065087080001831,
       "learning_rate": 0.0001623059866962306,
-      "loss": 0.8718,
+      "loss": 0.8724,
       "step": 91
     },
     {
       "epoch": 0.6065934065934065,
-      "grad_norm": 0.314115434885025,
+      "grad_norm": 0.3122287392616272,
       "learning_rate": 0.00016186252771618626,
-      "loss": 0.9757,
+      "loss": 0.976,
       "step": 92
     },
     {
       "epoch": 0.6131868131868132,
-      "grad_norm": 0.3091287314891815,
+      "grad_norm": 0.32005181908607483,
       "learning_rate": 0.0001614190687361419,
-      "loss": 0.9042,
+      "loss": 0.9045,
       "step": 93
     },
     {
       "epoch": 0.6197802197802198,
-      "grad_norm": 0.3007432520389557,
+      "grad_norm": 0.30076995491981506,
       "learning_rate": 0.00016097560975609758,
-      "loss": 0.9866,
+      "loss": 0.9879,
       "step": 94
     },
     {
       "epoch": 0.6263736263736264,
-      "grad_norm": 0.33295589685440063,
+      "grad_norm": 0.3367771804332733,
       "learning_rate": 0.00016053215077605322,
-      "loss": 0.8291,
+      "loss": 0.8272,
       "step": 95
     },
     {
       "epoch": 0.6329670329670329,
-      "grad_norm": 0.3381161689758301,
+      "grad_norm": 0.3340472877025604,
       "learning_rate": 0.00016008869179600887,
-      "loss": 1.0308,
+      "loss": 1.0321,
       "step": 96
     },
     {
       "epoch": 0.6395604395604395,
-      "grad_norm": 0.3053942024707794,
+      "grad_norm": 0.303377240896225,
       "learning_rate": 0.00015964523281596454,
-      "loss": 0.7676,
+      "loss": 0.7673,
       "step": 97
     },
     {
       "epoch": 0.6461538461538462,
-      "grad_norm": 0.32999739050865173,
+      "grad_norm": 0.32706865668296814,
       "learning_rate": 0.00015920177383592018,
-      "loss": 0.7638,
+      "loss": 0.7637,
       "step": 98
     },
     {
       "epoch": 0.6527472527472528,
-      "grad_norm": 0.4934881627559662,
+      "grad_norm": 0.49776825308799744,
       "learning_rate": 0.00015875831485587586,
-      "loss": 0.9291,
+      "loss": 0.9296,
       "step": 99
     },
     {
       "epoch": 0.6593406593406593,
-      "grad_norm": 0.36715981364250183,
+      "grad_norm": 0.369322806596756,
       "learning_rate": 0.0001583148558758315,
-      "loss": 0.9131,
+      "loss": 0.9106,
       "step": 100
     },
     {
       "epoch": 0.6659340659340659,
-      "grad_norm": 0.3625679314136505,
+      "grad_norm": 0.3643234074115753,
       "learning_rate": 0.00015787139689578714,
-      "loss": 1.0562,
+      "loss": 1.056,
       "step": 101
     },
     {
       "epoch": 0.6725274725274726,
-      "grad_norm": 0.36306384205818176,
+      "grad_norm": 0.3607897460460663,
       "learning_rate": 0.0001574279379157428,
-      "loss": 0.9225,
+      "loss": 0.9218,
       "step": 102
     },
     {
       "epoch": 0.6791208791208792,
-      "grad_norm": 0.2506583333015442,
+      "grad_norm": 0.2506844401359558,
       "learning_rate": 0.00015698447893569846,
-      "loss": 0.7906,
+      "loss": 0.7911,
       "step": 103
     },
     {
       "epoch": 0.6857142857142857,
-      "grad_norm": 0.34501585364341736,
+      "grad_norm": 0.3446638584136963,
       "learning_rate": 0.0001565410199556541,
-      "loss": 0.866,
+      "loss": 0.8677,
       "step": 104
     },
     {
       "epoch": 0.6923076923076923,
-      "grad_norm": 0.3541669547557831,
+      "grad_norm": 0.35222387313842773,
       "learning_rate": 0.00015609756097560978,
-      "loss": 0.936,
+      "loss": 0.9361,
       "step": 105
     },
     {
       "epoch": 0.6989010989010989,
-      "grad_norm": 0.3231780230998993,
+      "grad_norm": 0.32228022813796997,
       "learning_rate": 0.00015565410199556542,
-      "loss": 1.009,
+      "loss": 1.0088,
       "step": 106
     },
     {
       "epoch": 0.7054945054945055,
-      "grad_norm": 0.30839109420776367,
+      "grad_norm": 0.3090541958808899,
       "learning_rate": 0.00015521064301552106,
-      "loss": 1.192,
+      "loss": 1.1929,
       "step": 107
     },
     {
       "epoch": 0.7120879120879121,
-      "grad_norm": 0.2860703468322754,
+      "grad_norm": 0.28619226813316345,
       "learning_rate": 0.0001547671840354767,
-      "loss": 0.8922,
+      "loss": 0.8911,
       "step": 108
     },
     {
       "epoch": 0.7186813186813187,
-      "grad_norm": 0.3583816885948181,
+      "grad_norm": 0.35866305232048035,
       "learning_rate": 0.00015432372505543238,
-      "loss": 1.0708,
+      "loss": 1.0714,
       "step": 109
     },
     {
       "epoch": 0.7252747252747253,
-      "grad_norm": 0.33360984921455383,
+      "grad_norm": 0.33254724740982056,
       "learning_rate": 0.00015388026607538802,
-      "loss": 1.0233,
+      "loss": 1.0228,
       "step": 110
     },
     {
       "epoch": 0.7318681318681318,
-      "grad_norm": 0.34765884280204773,
+      "grad_norm": 0.35273459553718567,
       "learning_rate": 0.0001534368070953437,
-      "loss": 0.913,
+      "loss": 0.9127,
       "step": 111
     },
     {
       "epoch": 0.7384615384615385,
-      "grad_norm": 0.326040655374527,
+      "grad_norm": 0.3310684859752655,
       "learning_rate": 0.00015299334811529934,
-      "loss": 0.8333,
+      "loss": 0.832,
       "step": 112
     },
     {
       "epoch": 0.7450549450549451,
-      "grad_norm": 0.3660181760787964,
+      "grad_norm": 0.3684999942779541,
       "learning_rate": 0.00015254988913525498,
-      "loss": 1.0709,
+      "loss": 1.0707,
       "step": 113
     },
     {
       "epoch": 0.7516483516483516,
-      "grad_norm": 0.37662452459335327,
+      "grad_norm": 0.3729608952999115,
       "learning_rate": 0.00015210643015521066,
-      "loss": 1.1435,
+      "loss": 1.1418,
       "step": 114
     },
     {
       "epoch": 0.7582417582417582,
-      "grad_norm": 0.3499009907245636,
+      "grad_norm": 0.3481763005256653,
       "learning_rate": 0.0001516629711751663,
-      "loss": 0.9603,
+      "loss": 0.9622,
       "step": 115
     },
     {
       "epoch": 0.7648351648351648,
-      "grad_norm": 0.25945529341697693,
+      "grad_norm": 0.26267939805984497,
       "learning_rate": 0.00015121951219512197,
-      "loss": 0.9645,
+      "loss": 0.9652,
       "step": 116
     },
     {
       "epoch": 0.7714285714285715,
-      "grad_norm": 0.34172216057777405,
+      "grad_norm": 0.3408680260181427,
       "learning_rate": 0.00015077605321507762,
-      "loss": 0.9783,
+      "loss": 0.9778,
       "step": 117
     },
     {
       "epoch": 0.778021978021978,
-      "grad_norm": 0.2964763045310974,
+      "grad_norm": 0.30004823207855225,
       "learning_rate": 0.0001503325942350333,
-      "loss": 1.0131,
+      "loss": 1.0143,
       "step": 118
     },
     {
       "epoch": 0.7846153846153846,
-      "grad_norm": 0.280081570148468,
+      "grad_norm": 0.27949169278144836,
       "learning_rate": 0.0001498891352549889,
       "loss": 1.0352,
       "step": 119
     },
     {
       "epoch": 0.7912087912087912,
-      "grad_norm": 0.4915473461151123,
+      "grad_norm": 0.48710429668426514,
       "learning_rate": 0.00014944567627494458,
-      "loss": 1.1019,
+      "loss": 1.1032,
       "step": 120
     },
     {
       "epoch": 0.7978021978021979,
-      "grad_norm": 0.3027263581752777,
+      "grad_norm": 0.3039475083351135,
       "learning_rate": 0.00014900221729490022,
-      "loss": 1.0324,
+      "loss": 1.0314,
       "step": 121
     },
     {
       "epoch": 0.8043956043956044,
-      "grad_norm": 0.31653857231140137,
+      "grad_norm": 0.31663140654563904,
       "learning_rate": 0.0001485587583148559,
-      "loss": 0.9722,
+      "loss": 0.9715,
       "step": 122
     },
     {
       "epoch": 0.810989010989011,
-      "grad_norm": 0.3870300054550171,
+      "grad_norm": 0.38560619950294495,
       "learning_rate": 0.00014811529933481154,
-      "loss": 0.9521,
+      "loss": 0.9549,
       "step": 123
     },
     {
       "epoch": 0.8175824175824176,
-      "grad_norm": 0.31218865513801575,
+      "grad_norm": 0.31067079305648804,
       "learning_rate": 0.0001476718403547672,
-      "loss": 1.0037,
+      "loss": 1.0043,
       "step": 124
     },
     {
       "epoch": 0.8241758241758241,
-      "grad_norm": 0.3220807909965515,
+      "grad_norm": 0.3217318654060364,
       "learning_rate": 0.00014722838137472282,
-      "loss": 1.089,
+      "loss": 1.0895,
       "step": 125
     },
     {
       "epoch": 0.8307692307692308,
-      "grad_norm": 0.2677379548549652,
+      "grad_norm": 0.2660461664199829,
       "learning_rate": 0.0001467849223946785,
-      "loss": 0.7959,
+      "loss": 0.7951,
       "step": 126
     },
     {
       "epoch": 0.8373626373626374,
-      "grad_norm": 0.33389076590538025,
+      "grad_norm": 0.3334052562713623,
       "learning_rate": 0.00014634146341463414,
-      "loss": 0.8544,
+      "loss": 0.8546,
       "step": 127
     },
     {
       "epoch": 0.843956043956044,
-      "grad_norm": 0.3093551695346832,
+      "grad_norm": 0.3095804452896118,
       "learning_rate": 0.0001458980044345898,
-      "loss": 0.9041,
+      "loss": 0.9054,
       "step": 128
     },
     {
       "epoch": 0.8505494505494505,
-      "grad_norm": 0.2977532148361206,
+      "grad_norm": 0.2950759530067444,
       "learning_rate": 0.00014545454545454546,
-      "loss": 0.9339,
+      "loss": 0.9328,
       "step": 129
     },
     {
       "epoch": 0.8571428571428571,
-      "grad_norm": 0.2609766125679016,
+      "grad_norm": 0.2596442997455597,
       "learning_rate": 0.00014501108647450113,
-      "loss": 0.8509,
+      "loss": 0.8502,
       "step": 130
     },
     {
       "epoch": 0.8637362637362638,
-      "grad_norm": 0.328764408826828,
+      "grad_norm": 0.33304402232170105,
       "learning_rate": 0.00014456762749445675,
-      "loss": 0.9613,
+      "loss": 0.9601,
       "step": 131
     },
     {
       "epoch": 0.8703296703296703,
-      "grad_norm": 0.34873923659324646,
+      "grad_norm": 0.34867429733276367,
       "learning_rate": 0.00014412416851441242,
-      "loss": 0.8578,
+      "loss": 0.8534,
       "step": 132
     },
     {
       "epoch": 0.8769230769230769,
-      "grad_norm": 0.3248665928840637,
+      "grad_norm": 0.32560715079307556,
       "learning_rate": 0.00014368070953436806,
-      "loss": 0.9369,
+      "loss": 0.9375,
       "step": 133
     },
     {
       "epoch": 0.8835164835164835,
-      "grad_norm": 0.33797210454940796,
+      "grad_norm": 0.3292778432369232,
       "learning_rate": 0.00014323725055432373,
-      "loss": 1.0622,
+      "loss": 1.0627,
       "step": 134
     },
     {
       "epoch": 0.8901098901098901,
-      "grad_norm": 0.3088889420032501,
+      "grad_norm": 0.31127217411994934,
       "learning_rate": 0.00014279379157427938,
-      "loss": 0.9253,
+      "loss": 0.9267,
       "step": 135
     },
     {
       "epoch": 0.8967032967032967,
-      "grad_norm": 0.3533850908279419,
+      "grad_norm": 0.34771570563316345,
       "learning_rate": 0.00014235033259423505,
-      "loss": 0.9182,
+      "loss": 0.9175,
       "step": 136
     },
     {
       "epoch": 0.9032967032967033,
-      "grad_norm": 0.40451779961586,
+      "grad_norm": 0.40337350964546204,
       "learning_rate": 0.0001419068736141907,
-      "loss": 0.8442,
+      "loss": 0.8435,
       "step": 137
     },
     {
       "epoch": 0.9098901098901099,
-      "grad_norm": 0.33084341883659363,
+      "grad_norm": 0.32939478754997253,
       "learning_rate": 0.00014146341463414634,
-      "loss": 0.824,
+      "loss": 0.8248,
       "step": 138
     },
     {
       "epoch": 0.9164835164835164,
-      "grad_norm": 0.31345072388648987,
+      "grad_norm": 0.3135848045349121,
       "learning_rate": 0.000141019955654102,
-      "loss": 0.9001,
+      "loss": 0.9002,
       "step": 139
     },
     {
       "epoch": 0.9230769230769231,
-      "grad_norm": 0.3291054666042328,
+      "grad_norm": 0.3289794325828552,
       "learning_rate": 0.00014057649667405765,
-      "loss": 0.9342,
+      "loss": 0.9327,
       "step": 140
     },
     {
       "epoch": 0.9296703296703297,
-      "grad_norm": 0.3141261339187622,
+      "grad_norm": 0.3147788345813751,
       "learning_rate": 0.00014013303769401332,
-      "loss": 0.897,
+      "loss": 0.8973,
       "step": 141
     },
     {
       "epoch": 0.9362637362637363,
-      "grad_norm": 0.31741398572921753,
+      "grad_norm": 0.31705793738365173,
       "learning_rate": 0.00013968957871396897,
-      "loss": 0.9915,
+      "loss": 0.9906,
       "step": 142
     },
     {
       "epoch": 0.9428571428571428,
-      "grad_norm": 0.3589644432067871,
+      "grad_norm": 0.35615408420562744,
       "learning_rate": 0.00013924611973392464,
-      "loss": 0.8985,
+      "loss": 0.8955,
       "step": 143
     },
     {
       "epoch": 0.9494505494505494,
-      "grad_norm": 0.36022889614105225,
+      "grad_norm": 0.36079058051109314,
       "learning_rate": 0.00013880266075388026,
-      "loss": 1.023,
+      "loss": 1.0226,
       "step": 144
     },
     {
       "epoch": 0.9560439560439561,
-      "grad_norm": 0.37724706530570984,
+      "grad_norm": 0.37574851512908936,
       "learning_rate": 0.00013835920177383593,
-      "loss": 1.0334,
+      "loss": 1.0343,
       "step": 145
     },
     {
       "epoch": 0.9626373626373627,
-      "grad_norm": 0.3073366582393646,
+      "grad_norm": 0.3110910654067993,
       "learning_rate": 0.00013791574279379157,
-      "loss": 0.9127,
+      "loss": 0.9131,
       "step": 146
     },
     {
       "epoch": 0.9692307692307692,
-      "grad_norm": 0.3582838177680969,
+      "grad_norm": 0.36165574193000793,
       "learning_rate": 0.00013747228381374724,
-      "loss": 0.9063,
+      "loss": 0.9089,
       "step": 147
     },
     {
       "epoch": 0.9758241758241758,
-      "grad_norm": 0.32595396041870117,
+      "grad_norm": 0.325730562210083,
       "learning_rate": 0.0001370288248337029,
-      "loss": 0.7566,
+      "loss": 0.7573,
       "step": 148
     },
     {
       "epoch": 0.9824175824175824,
-      "grad_norm": 0.3323315680027008,
+      "grad_norm": 0.33553481101989746,
       "learning_rate": 0.00013658536585365856,
-      "loss": 0.8991,
+      "loss": 0.899,
       "step": 149
     },
     {
       "epoch": 0.989010989010989,
-      "grad_norm": 0.31097739934921265,
+      "grad_norm": 0.3051551878452301,
       "learning_rate": 0.00013614190687361418,
-      "loss": 0.8336,
+      "loss": 0.832,
       "step": 150
     },
     {
       "epoch": 0.9956043956043956,
-      "grad_norm": 0.28176063299179077,
+      "grad_norm": 0.2811763286590576,
       "learning_rate": 0.00013569844789356985,
-      "loss": 0.8019,
+      "loss": 0.8004,
       "step": 151
     },
     {
       "epoch": 1.0,
-      "grad_norm": 0.5535985827445984,
+      "grad_norm": 0.5527960062026978,
       "learning_rate": 0.0001352549889135255,
-      "loss": 1.0361,
+      "loss": 1.0357,
       "step": 152
     },
     {
       "epoch": 1.0065934065934066,
-      "grad_norm": 0.29516372084617615,
+      "grad_norm": 0.2979411482810974,
       "learning_rate": 0.00013481152993348116,
-      "loss": 0.91,
+      "loss": 0.9098,
       "step": 153
     },
     {
       "epoch": 1.0131868131868131,
-      "grad_norm": 0.3543173670768738,
+      "grad_norm": 0.3536434471607208,
       "learning_rate": 0.0001343680709534368,
-      "loss": 1.0058,
+      "loss": 1.0057,
       "step": 154
     },
     {
       "epoch": 1.0197802197802197,
-      "grad_norm": 0.38949835300445557,
+      "grad_norm": 0.3880802392959595,
       "learning_rate": 0.00013392461197339248,
-      "loss": 0.7881,
+      "loss": 0.7872,
       "step": 155
     },
     {
       "epoch": 1.0263736263736263,
-      "grad_norm": 0.3360844552516937,
+      "grad_norm": 0.33501604199409485,
       "learning_rate": 0.00013348115299334812,
-      "loss": 0.7793,
+      "loss": 0.7772,
       "step": 156
     },
     {
       "epoch": 1.032967032967033,
-      "grad_norm": 0.32752725481987,
+      "grad_norm": 0.33055397868156433,
       "learning_rate": 0.00013303769401330377,
-      "loss": 0.9641,
+      "loss": 0.9644,
       "step": 157
     },
     {
       "epoch": 1.0395604395604396,
-      "grad_norm": 0.3531540036201477,
+      "grad_norm": 0.3591103255748749,
       "learning_rate": 0.00013259423503325944,
-      "loss": 1.0192,
+      "loss": 1.0195,
       "step": 158
     },
     {
       "epoch": 1.0461538461538462,
-      "grad_norm": 0.33559122681617737,
+      "grad_norm": 0.33755481243133545,
       "learning_rate": 0.00013215077605321509,
-      "loss": 0.8055,
+      "loss": 0.8034,
       "step": 159
     },
     {
       "epoch": 1.0527472527472528,
-      "grad_norm": 0.3770013153553009,
+      "grad_norm": 0.37597209215164185,
       "learning_rate": 0.00013170731707317076,
-      "loss": 0.8351,
+      "loss": 0.8358,
       "step": 160
     },
     {
       "epoch": 1.0593406593406594,
-      "grad_norm": 0.3123881220817566,
+      "grad_norm": 0.31446924805641174,
       "learning_rate": 0.0001312638580931264,
-      "loss": 0.7128,
+      "loss": 0.7136,
       "step": 161
     },
     {
       "epoch": 1.065934065934066,
-      "grad_norm": 0.26182934641838074,
+      "grad_norm": 0.2608824074268341,
       "learning_rate": 0.00013082039911308205,
-      "loss": 0.7649,
+      "loss": 0.7655,
       "step": 162
     },
     {
       "epoch": 1.0725274725274725,
-      "grad_norm": 0.26431235671043396,
+      "grad_norm": 0.2637079656124115,
       "learning_rate": 0.0001303769401330377,
-      "loss": 0.7429,
+      "loss": 0.7426,
       "step": 163
     },
     {
       "epoch": 1.079120879120879,
-      "grad_norm": 0.43121954798698425,
+      "grad_norm": 0.4300684928894043,
       "learning_rate": 0.00012993348115299336,
-      "loss": 0.8651,
+      "loss": 0.8642,
       "step": 164
     },
     {
       "epoch": 1.0857142857142856,
-      "grad_norm": 0.309425413608551,
+      "grad_norm": 0.309948205947876,
       "learning_rate": 0.000129490022172949,
       "loss": 0.6285,
       "step": 165
     },
     {
       "epoch": 1.0923076923076924,
-      "grad_norm": 0.3685239255428314,
+      "grad_norm": 0.36743223667144775,
       "learning_rate": 0.00012904656319290468,
-      "loss": 1.0647,
+      "loss": 1.0651,
       "step": 166
     },
     {
       "epoch": 1.098901098901099,
-      "grad_norm": 0.26674482226371765,
+      "grad_norm": 0.26627010107040405,
       "learning_rate": 0.00012860310421286032,
-      "loss": 0.7441,
+      "loss": 0.7426,
       "step": 167
     },
     {
       "epoch": 1.1054945054945056,
-      "grad_norm": 0.48278793692588806,
+      "grad_norm": 0.494009405374527,
       "learning_rate": 0.00012815964523281597,
-      "loss": 1.0298,
+      "loss": 1.0305,
       "step": 168
     },
     {
       "epoch": 1.1120879120879121,
-      "grad_norm": 0.3902539014816284,
+      "grad_norm": 0.3971461355686188,
       "learning_rate": 0.0001277161862527716,
-      "loss": 0.8763,
+      "loss": 0.88,
       "step": 169
     },
     {
       "epoch": 1.1186813186813187,
-      "grad_norm": 0.43501222133636475,
+      "grad_norm": 0.4308566153049469,
       "learning_rate": 0.00012727272727272728,
-      "loss": 1.0258,
+      "loss": 1.026,
       "step": 170
     },
     {
       "epoch": 1.1252747252747253,
-      "grad_norm": 0.36463525891304016,
+      "grad_norm": 0.4727324843406677,
       "learning_rate": 0.00012682926829268293,
-      "loss": 0.9459,
+      "loss": 0.9454,
       "step": 171
     },
     {
       "epoch": 1.1318681318681318,
-      "grad_norm": 0.3361537456512451,
+      "grad_norm": 0.33626386523246765,
       "learning_rate": 0.0001263858093126386,
-      "loss": 0.8334,
+      "loss": 0.8337,
       "step": 172
     },
     {
       "epoch": 1.1384615384615384,
-      "grad_norm": 0.3888196349143982,
+      "grad_norm": 0.3919509947299957,
       "learning_rate": 0.00012594235033259424,
-      "loss": 1.112,
+      "loss": 1.1133,
       "step": 173
     },
     {
       "epoch": 1.145054945054945,
-      "grad_norm": 0.4237583875656128,
+      "grad_norm": 0.4251704514026642,
       "learning_rate": 0.00012549889135254989,
       "loss": 0.8316,
       "step": 174
     },
     {
       "epoch": 1.1516483516483516,
-      "grad_norm": 0.37899884581565857,
+      "grad_norm": 0.3847855031490326,
       "learning_rate": 0.00012505543237250553,
-      "loss": 0.8125,
+      "loss": 0.8132,
       "step": 175
     },
     {
       "epoch": 1.1582417582417581,
-      "grad_norm": 0.30603137612342834,
+      "grad_norm": 0.3070230484008789,
       "learning_rate": 0.0001246119733924612,
-      "loss": 0.79,
+      "loss": 0.7911,
       "step": 176
     },
     {
       "epoch": 1.164835164835165,
-      "grad_norm": 0.38935360312461853,
+      "grad_norm": 0.38822463154792786,
       "learning_rate": 0.00012416851441241685,
-      "loss": 0.8449,
+      "loss": 0.8434,
       "step": 177
     },
     {
       "epoch": 1.1714285714285715,
-      "grad_norm": 0.46504923701286316,
+      "grad_norm": 0.4665367305278778,
       "learning_rate": 0.00012372505543237252,
-      "loss": 1.1637,
+      "loss": 1.1649,
       "step": 178
     },
     {
       "epoch": 1.178021978021978,
-      "grad_norm": 0.37974920868873596,
+      "grad_norm": 0.37929290533065796,
       "learning_rate": 0.00012328159645232816,
-      "loss": 0.7895,
+      "loss": 0.7879,
       "step": 179
     },
     {
       "epoch": 1.1846153846153846,
-      "grad_norm": 0.44517454504966736,
+      "grad_norm": 0.44563302397727966,
       "learning_rate": 0.0001228381374722838,
-      "loss": 0.8115,
+      "loss": 0.8108,
       "step": 180
     },
     {
       "epoch": 1.1912087912087912,
-      "grad_norm": 0.31400156021118164,
+      "grad_norm": 0.3140140473842621,
       "learning_rate": 0.00012239467849223948,
-      "loss": 0.8794,
+      "loss": 0.8808,
       "step": 181
     },
     {
       "epoch": 1.1978021978021978,
-      "grad_norm": 0.4058041274547577,
+      "grad_norm": 0.4071938991546631,
       "learning_rate": 0.00012195121951219512,
-      "loss": 0.837,
+      "loss": 0.8348,
       "step": 182
     },
     {
       "epoch": 1.2043956043956043,
-      "grad_norm": 0.3683865964412689,
+      "grad_norm": 0.3701671063899994,
       "learning_rate": 0.00012150776053215078,
-      "loss": 0.8219,
+      "loss": 0.8236,
       "step": 183
     },
     {
       "epoch": 1.210989010989011,
-      "grad_norm": 0.3810867369174957,
+      "grad_norm": 0.37995103001594543,
       "learning_rate": 0.00012106430155210644,
-      "loss": 1.0203,
+      "loss": 1.0202,
       "step": 184
     },
     {
       "epoch": 1.2175824175824177,
-      "grad_norm": 0.4762330651283264,
+      "grad_norm": 0.47262856364250183,
       "learning_rate": 0.0001206208425720621,
-      "loss": 0.926,
+      "loss": 0.9254,
       "step": 185
     },
     {
       "epoch": 1.2241758241758243,
-      "grad_norm": 0.4322555363178253,
+      "grad_norm": 0.43184059858322144,
       "learning_rate": 0.00012017738359201774,
-      "loss": 0.9294,
+      "loss": 0.9291,
       "step": 186
     },
     {
       "epoch": 1.2307692307692308,
-      "grad_norm": 0.3780699074268341,
+      "grad_norm": 0.3796391189098358,
       "learning_rate": 0.0001197339246119734,
-      "loss": 0.8904,
+      "loss": 0.8917,
       "step": 187
     },
     {
       "epoch": 1.2373626373626374,
-      "grad_norm": 0.44516417384147644,
+      "grad_norm": 0.4447823464870453,
       "learning_rate": 0.00011929046563192906,
-      "loss": 0.7837,
+      "loss": 0.783,
       "step": 188
     },
     {
       "epoch": 1.243956043956044,
-      "grad_norm": 0.4465552568435669,
+      "grad_norm": 0.4512619972229004,
       "learning_rate": 0.00011884700665188471,
-      "loss": 0.96,
+      "loss": 0.9589,
       "step": 189
     },
     {
       "epoch": 1.2505494505494505,
-      "grad_norm": 0.43639782071113586,
+      "grad_norm": 0.4365478754043579,
       "learning_rate": 0.00011840354767184036,
-      "loss": 0.8267,
+      "loss": 0.8257,
       "step": 190
     },
     {
       "epoch": 1.2571428571428571,
-      "grad_norm": 0.5585591197013855,
+      "grad_norm": 0.5556828379631042,
       "learning_rate": 0.00011796008869179602,
-      "loss": 1.0051,
+      "loss": 1.0031,
       "step": 191
     },
     {
       "epoch": 1.2637362637362637,
-      "grad_norm": 0.4337552487850189,
+      "grad_norm": 0.4336020350456238,
       "learning_rate": 0.00011751662971175166,
-      "loss": 1.0171,
+      "loss": 1.0195,
       "step": 192
     },
     {
       "epoch": 1.2703296703296703,
-      "grad_norm": 0.4324861764907837,
+      "grad_norm": 0.4324263632297516,
       "learning_rate": 0.00011707317073170732,
-      "loss": 0.8813,
+      "loss": 0.8825,
       "step": 193
     },
     {
       "epoch": 1.2769230769230768,
-      "grad_norm": 0.4322637915611267,
+      "grad_norm": 0.4330337345600128,
       "learning_rate": 0.00011662971175166298,
-      "loss": 0.8898,
+      "loss": 0.8899,
       "step": 194
     },
     {
       "epoch": 1.2835164835164834,
-      "grad_norm": 0.5295554995536804,
+      "grad_norm": 0.5317378044128418,
       "learning_rate": 0.00011618625277161863,
-      "loss": 0.9328,
+      "loss": 0.9343,
       "step": 195
     },
     {
       "epoch": 1.2901098901098902,
-      "grad_norm": 0.44548794627189636,
+      "grad_norm": 0.4423321485519409,
       "learning_rate": 0.00011574279379157429,
-      "loss": 0.7084,
+      "loss": 0.709,
       "step": 196
     },
     {
       "epoch": 1.2967032967032968,
-      "grad_norm": 0.4655121862888336,
+      "grad_norm": 0.46634191274642944,
       "learning_rate": 0.00011529933481152995,
-      "loss": 0.925,
+      "loss": 0.9258,
       "step": 197
     },
     {
       "epoch": 1.3032967032967033,
-      "grad_norm": 0.465004563331604,
+      "grad_norm": 0.46565860509872437,
       "learning_rate": 0.00011485587583148558,
-      "loss": 1.0436,
+      "loss": 1.0451,
       "step": 198
     },
     {
       "epoch": 1.30989010989011,
-      "grad_norm": 0.4021751582622528,
+      "grad_norm": 0.4041418731212616,
       "learning_rate": 0.00011441241685144124,
-      "loss": 0.7306,
+      "loss": 0.7305,
       "step": 199
     },
     {
       "epoch": 1.3164835164835165,
-      "grad_norm": 0.3959920406341553,
+      "grad_norm": 0.3930712938308716,
       "learning_rate": 0.0001139689578713969,
-      "loss": 0.7864,
+      "loss": 0.7848,
       "step": 200
     },
     {
       "epoch": 1.323076923076923,
-      "grad_norm": 0.4573391377925873,
+      "grad_norm": 0.459338515996933,
       "learning_rate": 0.00011352549889135255,
-      "loss": 0.9226,
+      "loss": 0.923,
       "step": 201
     },
     {
       "epoch": 1.3296703296703296,
-      "grad_norm": 0.5056650042533875,
+      "grad_norm": 0.504289448261261,
       "learning_rate": 0.00011308203991130821,
-      "loss": 0.8219,
+      "loss": 0.8193,
       "step": 202
     },
     {
       "epoch": 1.3362637362637364,
-      "grad_norm": 0.4371558129787445,
+      "grad_norm": 0.4346235990524292,
       "learning_rate": 0.00011263858093126387,
-      "loss": 1.0047,
+      "loss": 1.0045,
       "step": 203
     },
     {
       "epoch": 1.342857142857143,
-      "grad_norm": 0.4842739999294281,
+      "grad_norm": 0.4848323166370392,
       "learning_rate": 0.00011219512195121953,
-      "loss": 0.7322,
+      "loss": 0.7334,
       "step": 204
     },
     {
       "epoch": 1.3494505494505495,
-      "grad_norm": 0.8172526955604553,
+      "grad_norm": 0.7272546291351318,
       "learning_rate": 0.00011175166297117516,
-      "loss": 1.0128,
+      "loss": 1.0148,
       "step": 205
     },
     {
       "epoch": 1.3560439560439561,
-      "grad_norm": 0.44949787855148315,
+      "grad_norm": 0.4481602907180786,
       "learning_rate": 0.00011130820399113082,
-      "loss": 0.85,
+      "loss": 0.8518,
       "step": 206
     },
     {
       "epoch": 1.3626373626373627,
-      "grad_norm": 0.45186272263526917,
+      "grad_norm": 0.4542093276977539,
       "learning_rate": 0.00011086474501108647,
-      "loss": 0.6802,
+      "loss": 0.6812,
       "step": 207
     },
     {
       "epoch": 1.3692307692307693,
-      "grad_norm": 0.4584757089614868,
+      "grad_norm": 0.45682492852211,
       "learning_rate": 0.00011042128603104213,
-      "loss": 0.8161,
+      "loss": 0.817,
       "step": 208
     },
     {
       "epoch": 1.3758241758241758,
-      "grad_norm": 0.4862142503261566,
+      "grad_norm": 0.48963284492492676,
       "learning_rate": 0.00010997782705099779,
-      "loss": 0.8785,
+      "loss": 0.8779,
       "step": 209
     },
     {
       "epoch": 1.3824175824175824,
-      "grad_norm": 0.5115880370140076,
+      "grad_norm": 0.5118657946586609,
       "learning_rate": 0.00010953436807095345,
-      "loss": 0.8237,
+      "loss": 0.8226,
       "step": 210
     },
     {
       "epoch": 1.389010989010989,
-      "grad_norm": 0.5136667490005493,
+      "grad_norm": 0.5167934894561768,
       "learning_rate": 0.00010909090909090909,
-      "loss": 0.894,
+      "loss": 0.8926,
       "step": 211
     },
     {
       "epoch": 1.3956043956043955,
-      "grad_norm": 0.4120652973651886,
+      "grad_norm": 0.4143112003803253,
       "learning_rate": 0.00010864745011086475,
-      "loss": 0.8051,
+      "loss": 0.8047,
       "step": 212
     },
     {
       "epoch": 1.402197802197802,
-      "grad_norm": 0.5302851796150208,
+      "grad_norm": 0.5308634042739868,
       "learning_rate": 0.00010820399113082041,
-      "loss": 0.8395,
+      "loss": 0.8406,
       "step": 213
     },
     {
       "epoch": 1.4087912087912087,
-      "grad_norm": 0.38329094648361206,
+      "grad_norm": 0.384340763092041,
       "learning_rate": 0.00010776053215077607,
-      "loss": 0.7402,
+      "loss": 0.7409,
       "step": 214
     },
     {
       "epoch": 1.4153846153846155,
-      "grad_norm": 0.4526435434818268,
+      "grad_norm": 0.4551766812801361,
       "learning_rate": 0.00010731707317073172,
       "loss": 0.6514,
       "step": 215
     },
     {
       "epoch": 1.421978021978022,
-      "grad_norm": 0.46651050448417664,
+      "grad_norm": 0.46713122725486755,
       "learning_rate": 0.00010687361419068738,
       "loss": 0.8064,
       "step": 216
     },
     {
       "epoch": 1.4285714285714286,
-      "grad_norm": 0.4789561927318573,
+      "grad_norm": 0.48027050495147705,
       "learning_rate": 0.00010643015521064301,
       "loss": 0.7965,
       "step": 217
     },
     {
       "epoch": 1.4351648351648352,
-      "grad_norm": 0.504118800163269,
+      "grad_norm": 0.5037854909896851,
       "learning_rate": 0.00010598669623059867,
-      "loss": 1.0565,
+      "loss": 1.057,
       "step": 218
     },
     {
       "epoch": 1.4417582417582417,
-      "grad_norm": 0.5061677694320679,
+      "grad_norm": 0.5078508257865906,
       "learning_rate": 0.00010554323725055433,
-      "loss": 0.9476,
+      "loss": 0.9463,
       "step": 219
     },
     {
       "epoch": 1.4483516483516483,
-      "grad_norm": 0.4608421325683594,
+      "grad_norm": 0.46149665117263794,
       "learning_rate": 0.00010509977827050999,
-      "loss": 0.8965,
+      "loss": 0.8976,
       "step": 220
     },
     {
       "epoch": 1.4549450549450549,
-      "grad_norm": 0.3995113968849182,
+      "grad_norm": 0.3994401693344116,
       "learning_rate": 0.00010465631929046564,
-      "loss": 0.8571,
+      "loss": 0.8577,
       "step": 221
     },
     {
       "epoch": 1.4615384615384617,
-      "grad_norm": 0.3929450511932373,
+      "grad_norm": 0.3923702538013458,
       "learning_rate": 0.0001042128603104213,
-      "loss": 0.803,
+      "loss": 0.8028,
       "step": 222
     },
     {
       "epoch": 1.4681318681318682,
-      "grad_norm": 0.47698885202407837,
+      "grad_norm": 0.48305079340934753,
       "learning_rate": 0.00010376940133037693,
-      "loss": 0.9712,
+      "loss": 0.9734,
       "step": 223
     },
     {
       "epoch": 1.4747252747252748,
-      "grad_norm": 0.36496636271476746,
+      "grad_norm": 0.36333736777305603,
       "learning_rate": 0.00010332594235033259,
-      "loss": 1.0349,
+      "loss": 1.0356,
       "step": 224
     },
     {
       "epoch": 1.4813186813186814,
-      "grad_norm": 0.543424129486084,
+      "grad_norm": 0.5412334203720093,
       "learning_rate": 0.00010288248337028825,
-      "loss": 0.8917,
+      "loss": 0.8889,
       "step": 225
     },
     {
       "epoch": 1.487912087912088,
-      "grad_norm": 0.4975453019142151,
+      "grad_norm": 0.4977543354034424,
       "learning_rate": 0.0001024390243902439,
-      "loss": 0.9042,
+      "loss": 0.906,
       "step": 226
     },
     {
       "epoch": 1.4945054945054945,
-      "grad_norm": 0.513408362865448,
+      "grad_norm": 0.515978991985321,
       "learning_rate": 0.00010199556541019956,
-      "loss": 0.8378,
+      "loss": 0.8412,
       "step": 227
     },
     {
       "epoch": 1.501098901098901,
-      "grad_norm": 0.5649193525314331,
+      "grad_norm": 0.567008912563324,
       "learning_rate": 0.00010155210643015522,
-      "loss": 1.0589,
+      "loss": 1.0593,
       "step": 228
     },
     {
       "epoch": 1.5076923076923077,
-      "grad_norm": 0.6057289838790894,
+      "grad_norm": 0.6032895445823669,
       "learning_rate": 0.00010110864745011087,
-      "loss": 0.997,
+      "loss": 0.9987,
       "step": 229
     },
     {
       "epoch": 1.5142857142857142,
-      "grad_norm": 0.5099395513534546,
+      "grad_norm": 0.506767988204956,
       "learning_rate": 0.00010066518847006652,
-      "loss": 0.998,
+      "loss": 0.9973,
       "step": 230
     },
     {
       "epoch": 1.5208791208791208,
-      "grad_norm": 0.4942122995853424,
+      "grad_norm": 0.4916362464427948,
       "learning_rate": 0.00010022172949002218,
-      "loss": 0.8104,
+      "loss": 0.8118,
       "step": 231
     },
     {
       "epoch": 1.5274725274725274,
-      "grad_norm": 0.5093843340873718,
+      "grad_norm": 0.5088720917701721,
       "learning_rate": 9.977827050997783e-05,
-      "loss": 0.7819,
+      "loss": 0.7818,
       "step": 232
     },
     {
       "epoch": 1.534065934065934,
-      "grad_norm": 0.511997401714325,
+      "grad_norm": 0.5120078325271606,
       "learning_rate": 9.933481152993348e-05,
-      "loss": 0.8423,
+      "loss": 0.8439,
       "step": 233
     },
     {
       "epoch": 1.5406593406593405,
-      "grad_norm": 0.5232946276664734,
+      "grad_norm": 0.523810088634491,
       "learning_rate": 9.889135254988914e-05,
-      "loss": 0.8661,
+      "loss": 0.8663,
       "step": 234
     },
     {
       "epoch": 1.5472527472527473,
-      "grad_norm": 0.5954769849777222,
+      "grad_norm": 0.5985426902770996,
       "learning_rate": 9.84478935698448e-05,
-      "loss": 0.8877,
+      "loss": 0.8886,
       "step": 235
     },
     {
       "epoch": 1.5538461538461539,
-      "grad_norm": 0.44104084372520447,
+      "grad_norm": 0.43574684858322144,
       "learning_rate": 9.800443458980046e-05,
-      "loss": 0.8592,
+      "loss": 0.8594,
       "step": 236
     },
     {
       "epoch": 1.5604395604395604,
-      "grad_norm": 0.5269781351089478,
+      "grad_norm": 0.5211787223815918,
       "learning_rate": 9.75609756097561e-05,
-      "loss": 0.8698,
+      "loss": 0.8704,
       "step": 237
     },
     {
       "epoch": 1.567032967032967,
-      "grad_norm": 0.6050085425376892,
+      "grad_norm": 0.6048451662063599,
       "learning_rate": 9.711751662971176e-05,
-      "loss": 0.9756,
+      "loss": 0.9754,
       "step": 238
     },
     {
       "epoch": 1.5736263736263736,
-      "grad_norm": 0.4890908896923065,
+      "grad_norm": 0.48914510011672974,
       "learning_rate": 9.667405764966742e-05,
-      "loss": 0.7871,
+      "loss": 0.7851,
       "step": 239
     },
     {
       "epoch": 1.5802197802197804,
-      "grad_norm": 0.5456884503364563,
+      "grad_norm": 0.5413491725921631,
       "learning_rate": 9.623059866962306e-05,
-      "loss": 0.8255,
+      "loss": 0.8258,
       "step": 240
     }
   ],

checkpoint-240/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e6107b40730f00b0ecebeb53261d03c090314acc28d156f0c2a1f966f3cdca
+oid sha256:0f4aaa76910e776691a8e236eac6a84769f2e9172a54a9d30fe100706079516a
 size 6417