Add checkpoint-600

checkpoints/checkpoint-600/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36802883d2c04eaebf13ace48b1ff6c2f381de6044ef41497e09606bc0ab069
+oid sha256:62a04ec664f2b4a37195ff6f69d84017d17219e748b4e8eee1b32a4c7853c46b
 size 4724960

checkpoints/checkpoint-600/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ae4c98c98702037a4bc485bc4c9317686b9517c13f2276d46a4c44e6db719e
+oid sha256:98cfb5b7b5d7f473e10da5601b2ca5605a0e76e2d46599fff29f84592fa50d31
 size 2455755

checkpoints/checkpoint-600/trainer_state.json

@@ -11,422 +11,422 @@
   "log_history": [
     {
       "epoch": 0.0054010261949770455,
-      "grad_norm": 1.428126573562622,
+      "grad_norm": 1.4275089502334595,
       "learning_rate": 0.00016,
-      "loss": 3.4878021240234376,
+      "loss": 3.4877567291259766,
       "step": 10
     },
     {
       "epoch": 0.010802052389954091,
-      "grad_norm": 1.4069736003875732,
+      "grad_norm": 1.4062877893447876,
       "learning_rate": 0.00019971150378651282,
-      "loss": 3.1774940490722656,
+      "loss": 3.177476501464844,
       "step": 20
     },
     {
       "epoch": 0.016203078584931137,
-      "grad_norm": 1.4898899793624878,
+      "grad_norm": 1.4894630908966064,
       "learning_rate": 0.0001993508835196538,
-      "loss": 2.949423408508301,
+      "loss": 2.949508857727051,
       "step": 30
     },
     {
       "epoch": 0.021604104779908182,
-      "grad_norm": 1.1627568006515503,
+      "grad_norm": 1.1637152433395386,
       "learning_rate": 0.00019899026325279482,
-      "loss": 3.2568889617919923,
+      "loss": 3.2568588256835938,
       "step": 40
     },
     {
       "epoch": 0.027005130974885227,
-      "grad_norm": 1.071158528327942,
+      "grad_norm": 1.0710796117782593,
       "learning_rate": 0.00019862964298593581,
-      "loss": 3.033279609680176,
+      "loss": 3.033162307739258,
       "step": 50
     },
     {
       "epoch": 0.032406157169862275,
-      "grad_norm": 1.03691565990448,
+      "grad_norm": 1.036720633506775,
       "learning_rate": 0.0001982690227190768,
-      "loss": 2.9209321975708007,
+      "loss": 2.9209388732910155,
       "step": 60
     },
     {
       "epoch": 0.03780718336483932,
-      "grad_norm": 1.5099613666534424,
+      "grad_norm": 1.5094584226608276,
       "learning_rate": 0.00019790840245221782,
-      "loss": 3.1997047424316407,
+      "loss": 3.199975776672363,
       "step": 70
     },
     {
       "epoch": 0.043208209559816364,
-      "grad_norm": 1.2505701780319214,
+      "grad_norm": 1.25065016746521,
       "learning_rate": 0.00019754778218535884,
-      "loss": 3.158730316162109,
+      "loss": 3.1586023330688477,
       "step": 80
     },
     {
       "epoch": 0.04860923575479341,
-      "grad_norm": 1.0929311513900757,
+      "grad_norm": 1.093263864517212,
       "learning_rate": 0.00019718716191849983,
-      "loss": 3.16729679107666,
+      "loss": 3.1673559188842773,
       "step": 90
     },
     {
       "epoch": 0.054010261949770454,
-      "grad_norm": 1.7020047903060913,
+      "grad_norm": 1.7025214433670044,
       "learning_rate": 0.00019682654165164082,
-      "loss": 3.009043502807617,
+      "loss": 3.0090349197387694,
       "step": 100
     },
     {
       "epoch": 0.059411288144747505,
-      "grad_norm": 1.0370606184005737,
+      "grad_norm": 1.0379327535629272,
       "learning_rate": 0.00019646592138478184,
-      "loss": 3.086234283447266,
+      "loss": 3.0862411499023437,
       "step": 110
     },
     {
       "epoch": 0.06481231433972455,
-      "grad_norm": 1.0744086503982544,
+      "grad_norm": 1.0767595767974854,
       "learning_rate": 0.00019610530111792285,
-      "loss": 2.934561538696289,
+      "loss": 2.9345855712890625,
       "step": 120
     },
     {
       "epoch": 0.07021334053470159,
-      "grad_norm": 1.2475906610488892,
+      "grad_norm": 1.2473753690719604,
       "learning_rate": 0.00019574468085106384,
-      "loss": 3.168362617492676,
+      "loss": 3.168864440917969,
       "step": 130
     },
     {
       "epoch": 0.07561436672967864,
-      "grad_norm": 1.154983639717102,
+      "grad_norm": 1.1580232381820679,
       "learning_rate": 0.00019538406058420483,
-      "loss": 3.0430318832397463,
+      "loss": 3.0444286346435545,
       "step": 140
     },
     {
       "epoch": 0.08101539292465569,
-      "grad_norm": 1.1540956497192383,
+      "grad_norm": 1.1562517881393433,
       "learning_rate": 0.00019502344031734585,
-      "loss": 3.067497444152832,
+      "loss": 3.0681676864624023,
       "step": 150
     },
     {
       "epoch": 0.08641641911963273,
-      "grad_norm": 1.2023861408233643,
+      "grad_norm": 1.2069370746612549,
       "learning_rate": 0.00019466282005048684,
-      "loss": 3.147787857055664,
+      "loss": 3.147779846191406,
       "step": 160
     },
     {
       "epoch": 0.09181744531460978,
-      "grad_norm": 1.1540592908859253,
+      "grad_norm": 1.1520271301269531,
       "learning_rate": 0.00019430219978362786,
-      "loss": 3.2142364501953127,
+      "loss": 3.2159664154052736,
       "step": 170
     },
     {
       "epoch": 0.09721847150958682,
-      "grad_norm": 1.3427095413208008,
+      "grad_norm": 1.3290963172912598,
       "learning_rate": 0.00019394157951676885,
-      "loss": 3.1775146484375,
+      "loss": 3.17901668548584,
       "step": 180
     },
     {
       "epoch": 0.10261949770456387,
-      "grad_norm": 1.453772783279419,
+      "grad_norm": 1.4537458419799805,
       "learning_rate": 0.00019358095924990984,
-      "loss": 3.076451301574707,
+      "loss": 3.076709747314453,
       "step": 190
     },
     {
       "epoch": 0.10802052389954091,
-      "grad_norm": 1.6937741041183472,
+      "grad_norm": 1.6899892091751099,
       "learning_rate": 0.00019322033898305085,
-      "loss": 2.9374858856201174,
+      "loss": 2.9362957000732424,
       "step": 200
     },
     {
       "epoch": 0.11342155009451796,
-      "grad_norm": 1.2238482236862183,
+      "grad_norm": 1.218902349472046,
       "learning_rate": 0.00019289578074287774,
-      "loss": 3.08709659576416,
+      "loss": 3.0862009048461916,
       "step": 210
     },
     {
       "epoch": 0.11882257628949501,
-      "grad_norm": 1.2522649765014648,
+      "grad_norm": 1.253646969795227,
       "learning_rate": 0.00019253516047601876,
-      "loss": 3.0421375274658202,
+      "loss": 3.0416831970214844,
       "step": 220
     },
     {
       "epoch": 0.12422360248447205,
-      "grad_norm": 1.1824394464492798,
+      "grad_norm": 1.1816236972808838,
       "learning_rate": 0.00019217454020915977,
-      "loss": 3.091483497619629,
+      "loss": 3.09185791015625,
       "step": 230
     },
     {
       "epoch": 0.1296246286794491,
-      "grad_norm": 1.2253663539886475,
+      "grad_norm": 1.2364989519119263,
       "learning_rate": 0.00019181391994230076,
-      "loss": 3.1255870819091798,
+      "loss": 3.1257530212402345,
       "step": 240
     },
     {
       "epoch": 0.13502565487442614,
-      "grad_norm": 1.309012770652771,
+      "grad_norm": 1.3117403984069824,
       "learning_rate": 0.00019145329967544175,
-      "loss": 3.0072154998779297,
+      "loss": 3.0078147888183593,
       "step": 250
     },
     {
       "epoch": 0.14042668106940318,
-      "grad_norm": 1.0617231130599976,
+      "grad_norm": 1.060840368270874,
       "learning_rate": 0.00019109267940858277,
-      "loss": 3.2057498931884765,
+      "loss": 3.205386734008789,
       "step": 260
     },
     {
       "epoch": 0.14582770726438024,
-      "grad_norm": 1.0825862884521484,
+      "grad_norm": 1.0836883783340454,
       "learning_rate": 0.0001907320591417238,
-      "loss": 3.0084716796875,
+      "loss": 3.00787410736084,
       "step": 270
     },
     {
       "epoch": 0.15122873345935728,
-      "grad_norm": 1.168721079826355,
+      "grad_norm": 1.1705331802368164,
       "learning_rate": 0.00019037143887486478,
-      "loss": 3.141677665710449,
+      "loss": 3.1415082931518556,
       "step": 280
     },
     {
       "epoch": 0.15662975965433432,
-      "grad_norm": 1.1489522457122803,
+      "grad_norm": 1.1469744443893433,
       "learning_rate": 0.00019001081860800577,
-      "loss": 3.0708972930908205,
+      "loss": 3.0711442947387697,
       "step": 290
     },
     {
       "epoch": 0.16203078584931138,
-      "grad_norm": 1.720065951347351,
+      "grad_norm": 1.7230859994888306,
       "learning_rate": 0.00018965019834114679,
-      "loss": 3.0757408142089844,
+      "loss": 3.0760629653930662,
       "step": 300
     },
     {
       "epoch": 0.16743181204428842,
-      "grad_norm": 1.3358254432678223,
+      "grad_norm": 1.3305317163467407,
       "learning_rate": 0.00018928957807428778,
-      "loss": 3.0111953735351564,
+      "loss": 3.0109764099121095,
       "step": 310
     },
     {
       "epoch": 0.17283283823926546,
-      "grad_norm": 1.1454875469207764,
+      "grad_norm": 1.1433296203613281,
       "learning_rate": 0.0001889289578074288,
-      "loss": 2.9005817413330077,
+      "loss": 2.900168228149414,
       "step": 320
     },
     {
       "epoch": 0.1782338644342425,
-      "grad_norm": 1.4062997102737427,
+      "grad_norm": 1.4017837047576904,
       "learning_rate": 0.00018856833754056978,
-      "loss": 2.9263254165649415,
+      "loss": 2.9257192611694336,
       "step": 330
     },
     {
       "epoch": 0.18363489062921956,
-      "grad_norm": 1.416684865951538,
+      "grad_norm": 1.418676495552063,
       "learning_rate": 0.00018820771727371077,
-      "loss": 3.1220844268798826,
+      "loss": 3.1230239868164062,
       "step": 340
     },
     {
       "epoch": 0.1890359168241966,
-      "grad_norm": 1.2184299230575562,
+      "grad_norm": 1.2229913473129272,
       "learning_rate": 0.0001878470970068518,
-      "loss": 2.8639949798583983,
+      "loss": 2.8634975433349608,
       "step": 350
     },
     {
       "epoch": 0.19443694301917364,
-      "grad_norm": 1.2897292375564575,
+      "grad_norm": 1.2936865091323853,
       "learning_rate": 0.0001874864767399928,
-      "loss": 3.0422386169433593,
+      "loss": 3.0415794372558596,
       "step": 360
     },
     {
       "epoch": 0.1998379692141507,
-      "grad_norm": 1.3933805227279663,
+      "grad_norm": 1.3978519439697266,
       "learning_rate": 0.0001871258564731338,
-      "loss": 2.9331783294677733,
+      "loss": 2.9328636169433593,
       "step": 370
     },
     {
       "epoch": 0.20523899540912774,
-      "grad_norm": 1.0702441930770874,
+      "grad_norm": 1.0732481479644775,
       "learning_rate": 0.0001867652362062748,
-      "loss": 3.1468505859375,
+      "loss": 3.147154426574707,
       "step": 380
     },
     {
       "epoch": 0.21064002160410478,
-      "grad_norm": 1.3059329986572266,
+      "grad_norm": 1.304332971572876,
       "learning_rate": 0.0001864046159394158,
-      "loss": 2.987403678894043,
+      "loss": 2.98757266998291,
       "step": 390
     },
     {
       "epoch": 0.21604104779908181,
-      "grad_norm": 1.271935224533081,
+      "grad_norm": 1.2670519351959229,
       "learning_rate": 0.00018604399567255682,
-      "loss": 3.0831995010375977,
+      "loss": 3.0830259323120117,
       "step": 400
     },
     {
       "epoch": 0.22144207399405888,
-      "grad_norm": 1.3448420763015747,
+      "grad_norm": 1.3472830057144165,
       "learning_rate": 0.0001856833754056978,
-      "loss": 3.0728456497192385,
+      "loss": 3.0725728988647463,
       "step": 410
     },
     {
       "epoch": 0.22684310018903592,
-      "grad_norm": 1.5971468687057495,
+      "grad_norm": 1.5913994312286377,
       "learning_rate": 0.0001853227551388388,
-      "loss": 2.872736358642578,
+      "loss": 2.872740936279297,
       "step": 420
     },
     {
       "epoch": 0.23224412638401296,
-      "grad_norm": 1.5025312900543213,
+      "grad_norm": 1.4995367527008057,
       "learning_rate": 0.00018496213487197982,
-      "loss": 3.1988616943359376,
+      "loss": 3.1985055923461916,
       "step": 430
     },
     {
       "epoch": 0.23764515257899002,
-      "grad_norm": 1.3233635425567627,
+      "grad_norm": 1.3097314834594727,
       "learning_rate": 0.0001846015146051208,
-      "loss": 2.9131952285766602,
+      "loss": 2.9131542205810548,
       "step": 440
     },
     {
       "epoch": 0.24304617877396706,
-      "grad_norm": 1.2196204662322998,
+      "grad_norm": 1.2168841361999512,
       "learning_rate": 0.00018424089433826182,
-      "loss": 3.0023128509521486,
+      "loss": 3.0022405624389648,
       "step": 450
     },
     {
       "epoch": 0.2484472049689441,
-      "grad_norm": 1.2493833303451538,
+      "grad_norm": 1.2428247928619385,
       "learning_rate": 0.00018388027407140281,
-      "loss": 3.1350614547729494,
+      "loss": 3.13458194732666,
       "step": 460
     },
     {
       "epoch": 0.25384823116392113,
-      "grad_norm": 1.0759880542755127,
+      "grad_norm": 1.0732594728469849,
       "learning_rate": 0.00018351965380454383,
-      "loss": 2.9948074340820314,
+      "loss": 2.995112991333008,
       "step": 470
     },
     {
       "epoch": 0.2592492573588982,
-      "grad_norm": 1.0177220106124878,
+      "grad_norm": 1.0187745094299316,
       "learning_rate": 0.00018315903353768482,
-      "loss": 2.9629610061645506,
+      "loss": 2.9637735366821287,
       "step": 480
     },
     {
       "epoch": 0.2646502835538752,
-      "grad_norm": 1.2795182466506958,
+      "grad_norm": 1.2797402143478394,
       "learning_rate": 0.00018279841327082584,
-      "loss": 2.9931074142456056,
+      "loss": 2.9933282852172853,
       "step": 490
     },
     {
       "epoch": 0.2700513097488523,
-      "grad_norm": 0.9945526123046875,
+      "grad_norm": 0.9948688745498657,
       "learning_rate": 0.00018243779300396683,
-      "loss": 3.0773736953735353,
+      "loss": 3.078018569946289,
       "step": 500
     },
     {
       "epoch": 0.27545233594382934,
-      "grad_norm": 1.0305508375167847,
+      "grad_norm": 1.0406428575515747,
       "learning_rate": 0.00018207717273710782,
-      "loss": 2.9697338104248048,
+      "loss": 2.9701290130615234,
       "step": 510
     },
     {
       "epoch": 0.28085336213880635,
-      "grad_norm": 1.1842334270477295,
+      "grad_norm": 1.184054970741272,
       "learning_rate": 0.00018171655247024884,
-      "loss": 3.0945035934448244,
+      "loss": 3.094232368469238,
       "step": 520
     },
     {
       "epoch": 0.2862543883337834,
-      "grad_norm": 1.2626765966415405,
+      "grad_norm": 1.2439318895339966,
       "learning_rate": 0.00018135593220338985,
-      "loss": 3.0946796417236326,
+      "loss": 3.0941631317138674,
       "step": 530
     },
     {
       "epoch": 0.2916554145287605,
-      "grad_norm": 1.0872550010681152,
+      "grad_norm": 1.3002263307571411,
       "learning_rate": 0.00018099531193653084,
-      "loss": 2.9620519638061524,
+      "loss": 2.9608373641967773,
       "step": 540
     },
     {
       "epoch": 0.2970564407237375,
-      "grad_norm": 1.570915937423706,
+      "grad_norm": 1.5705729722976685,
       "learning_rate": 0.00018063469166967183,
-      "loss": 3.0281347274780273,
+      "loss": 3.026919364929199,
       "step": 550
     },
     {
       "epoch": 0.30245746691871456,
-      "grad_norm": 1.1675987243652344,
+      "grad_norm": 1.1658886671066284,
       "learning_rate": 0.00018027407140281285,
-      "loss": 2.9999523162841797,
+      "loss": 2.9997627258300783,
       "step": 560
     },
     {
       "epoch": 0.3078584931136916,
-      "grad_norm": 1.0013808012008667,
+      "grad_norm": 1.0013272762298584,
       "learning_rate": 0.00017991345113595387,
-      "loss": 2.919264221191406,
+      "loss": 2.919036865234375,
       "step": 570
     },
     {
       "epoch": 0.31325951930866863,
-      "grad_norm": 1.1768618822097778,
+      "grad_norm": 1.1810517311096191,
       "learning_rate": 0.00017955283086909486,
-      "loss": 3.02783145904541,
+      "loss": 3.0280284881591797,
       "step": 580
     },
     {
       "epoch": 0.3186605455036457,
-      "grad_norm": 1.419691801071167,
+      "grad_norm": 1.4247483015060425,
       "learning_rate": 0.00017919221060223585,
-      "loss": 2.9450830459594726,
+      "loss": 2.944463920593262,
       "step": 590
     },
     {
       "epoch": 0.32406157169862276,
-      "grad_norm": 1.1855523586273193,
+      "grad_norm": 1.1780109405517578,
       "learning_rate": 0.00017883159033537686,
-      "loss": 3.1668718338012694,
+      "loss": 3.165457534790039,
       "step": 600
     }
   ],