Add checkpoint-1400

checkpoints/checkpoint-1400/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125ff81a24da1c88125223cf4a35f22e4ba5d9d560d459948a0c0ccee9a3bfc6
+oid sha256:cfde2e5ec0e6d6d7c8af1a0e81f10ddf70c5a94229ee45566c0e09b31b1a8d07
 size 4724960

checkpoints/checkpoint-1400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:678885d7ac95d5895ee25e0fc0a4a86ccfc75762d29f7bfaf6c288f2bf48e2b7
+oid sha256:45a5fba9867a21080a8cb6d4bc16caa4ad4c643cc20c356166dafbab415b9431
 size 2578187

checkpoints/checkpoint-1400/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33411e95065fdb5c533c593b0ff331c40d6b4244480c3c957ce9d8b25e8372db
+oid sha256:7acacbd4e1d20771f45d0ac642f2b85624ded24a2c8bcfa17124017a44104725
 size 14645

checkpoints/checkpoint-1400/trainer_state.json

@@ -571,422 +571,422 @@
     },
     {
       "epoch": 0.32155617308455736,
-      "grad_norm": 1.0162802934646606,
+      "grad_norm": 0.9609226584434509,
       "learning_rate": 0.0001788525241817941,
-      "loss": 2.9229061126708986,
+      "loss": 2.8289106369018553,
       "step": 810
     },
     {
       "epoch": 0.3255260023818976,
-      "grad_norm": 0.9440785646438599,
+      "grad_norm": 1.339521050453186,
       "learning_rate": 0.00017858751821915993,
-      "loss": 3.0203786849975587,
+      "loss": 3.0263460159301756,
       "step": 820
     },
     {
       "epoch": 0.3294958316792378,
-      "grad_norm": 0.9915809035301208,
+      "grad_norm": 0.8593433499336243,
       "learning_rate": 0.0001783225122565258,
-      "loss": 3.0121458053588865,
+      "loss": 3.0060649871826173,
       "step": 830
     },
     {
       "epoch": 0.333465660976578,
-      "grad_norm": 0.9717929363250732,
+      "grad_norm": 1.0417287349700928,
       "learning_rate": 0.00017805750629389162,
-      "loss": 2.971171569824219,
+      "loss": 3.0265331268310547,
       "step": 840
     },
     {
       "epoch": 0.3374354902739182,
-      "grad_norm": 1.145629644393921,
+      "grad_norm": 1.1134616136550903,
       "learning_rate": 0.00017779250033125748,
-      "loss": 3.0685672760009766,
+      "loss": 3.057025146484375,
       "step": 850
     },
     {
       "epoch": 0.3414053195712584,
-      "grad_norm": 1.0309630632400513,
+      "grad_norm": 1.0823781490325928,
       "learning_rate": 0.0001775274943686233,
-      "loss": 2.870728302001953,
+      "loss": 3.0840169906616213,
       "step": 860
     },
     {
       "epoch": 0.34537514886859866,
-      "grad_norm": 0.8991674780845642,
+      "grad_norm": 1.304033637046814,
       "learning_rate": 0.00017726248840598913,
-      "loss": 2.9863655090332033,
+      "loss": 2.9510980606079102,
       "step": 870
     },
     {
       "epoch": 0.34934497816593885,
-      "grad_norm": 1.1400610208511353,
+      "grad_norm": 0.9548248052597046,
       "learning_rate": 0.00017699748244335499,
-      "loss": 2.98059139251709,
+      "loss": 3.0062685012817383,
       "step": 880
     },
     {
       "epoch": 0.3533148074632791,
-      "grad_norm": 1.8383524417877197,
+      "grad_norm": 0.9844130277633667,
       "learning_rate": 0.00017673247648072082,
-      "loss": 2.8302703857421876,
+      "loss": 2.9815792083740233,
       "step": 890
     },
     {
       "epoch": 0.3572846367606193,
-      "grad_norm": 1.1270629167556763,
+      "grad_norm": 1.1588873863220215,
       "learning_rate": 0.00017646747051808668,
-      "loss": 2.981347846984863,
+      "loss": 3.143498992919922,
       "step": 900
     },
     {
       "epoch": 0.3612544660579595,
-      "grad_norm": 0.9985610842704773,
+      "grad_norm": 0.9818010926246643,
       "learning_rate": 0.00017620246455545251,
-      "loss": 2.956617736816406,
+      "loss": 2.973097229003906,
       "step": 910
     },
     {
       "epoch": 0.3652242953552997,
-      "grad_norm": 0.9641323089599609,
+      "grad_norm": 1.0033776760101318,
       "learning_rate": 0.00017593745859281835,
-      "loss": 3.0457557678222655,
+      "loss": 3.0639650344848635,
       "step": 920
     },
     {
       "epoch": 0.36919412465263995,
-      "grad_norm": 1.17633855342865,
+      "grad_norm": 1.1256245374679565,
       "learning_rate": 0.00017567245263018418,
-      "loss": 3.073198699951172,
+      "loss": 3.0972034454345705,
       "step": 930
     },
     {
       "epoch": 0.37316395394998014,
-      "grad_norm": 1.0620558261871338,
+      "grad_norm": 1.1515825986862183,
       "learning_rate": 0.00017540744666755002,
-      "loss": 2.8887912750244142,
+      "loss": 2.954210090637207,
       "step": 940
     },
     {
       "epoch": 0.3771337832473204,
-      "grad_norm": 0.9436220526695251,
+      "grad_norm": 1.0679875612258911,
       "learning_rate": 0.00017514244070491588,
-      "loss": 3.1275503158569338,
+      "loss": 2.9248802185058596,
       "step": 950
     },
     {
       "epoch": 0.3811036125446606,
-      "grad_norm": 1.0516761541366577,
+      "grad_norm": 1.3141388893127441,
       "learning_rate": 0.0001748774347422817,
-      "loss": 2.925854301452637,
+      "loss": 2.9732879638671874,
       "step": 960
     },
     {
       "epoch": 0.3850734418420008,
-      "grad_norm": 1.0422406196594238,
+      "grad_norm": 0.9422619938850403,
       "learning_rate": 0.00017461242877964754,
-      "loss": 2.9021322250366213,
+      "loss": 2.8527624130249025,
       "step": 970
     },
     {
       "epoch": 0.389043271139341,
-      "grad_norm": 0.8913261890411377,
+      "grad_norm": 1.1796400547027588,
       "learning_rate": 0.0001743474228170134,
-      "loss": 3.171915817260742,
+      "loss": 3.081935691833496,
       "step": 980
     },
     {
       "epoch": 0.3930131004366812,
-      "grad_norm": 1.109357476234436,
+      "grad_norm": 0.9901096820831299,
       "learning_rate": 0.00017408241685437924,
-      "loss": 2.9540994644165037,
+      "loss": 2.9871950149536133,
       "step": 990
     },
     {
       "epoch": 0.39698292973402144,
-      "grad_norm": 1.192381739616394,
+      "grad_norm": 0.9635742902755737,
       "learning_rate": 0.00017381741089174507,
-      "loss": 3.038303184509277,
+      "loss": 2.909952735900879,
       "step": 1000
     },
     {
       "epoch": 0.4009527590313616,
-      "grad_norm": 1.0390175580978394,
+      "grad_norm": 1.094767451286316,
       "learning_rate": 0.0001735524049291109,
-      "loss": 2.986875534057617,
+      "loss": 2.886246681213379,
       "step": 1010
     },
     {
       "epoch": 0.40492258832870187,
-      "grad_norm": 1.1844251155853271,
+      "grad_norm": 0.9883092045783997,
       "learning_rate": 0.00017328739896647674,
-      "loss": 3.0509342193603515,
+      "loss": 2.941468048095703,
       "step": 1020
     },
     {
       "epoch": 0.40889241762604206,
-      "grad_norm": 1.1736098527908325,
+      "grad_norm": 1.082886815071106,
       "learning_rate": 0.0001730223930038426,
-      "loss": 2.9463253021240234,
+      "loss": 2.8721885681152344,
       "step": 1030
     },
     {
       "epoch": 0.4128622469233823,
-      "grad_norm": 1.0445928573608398,
+      "grad_norm": 0.9654253125190735,
       "learning_rate": 0.00017275738704120844,
-      "loss": 2.8047935485839846,
+      "loss": 3.0437408447265626,
       "step": 1040
     },
     {
       "epoch": 0.4168320762207225,
-      "grad_norm": 1.3494070768356323,
+      "grad_norm": 0.9620010256767273,
       "learning_rate": 0.0001724923810785743,
-      "loss": 2.884739875793457,
+      "loss": 2.9390357971191405,
       "step": 1050
     },
     {
       "epoch": 0.42080190551806274,
-      "grad_norm": 1.2732553482055664,
+      "grad_norm": 1.042639136314392,
       "learning_rate": 0.0001722273751159401,
-      "loss": 3.0882823944091795,
+      "loss": 2.928664207458496,
       "step": 1060
     },
     {
       "epoch": 0.4247717348154029,
-      "grad_norm": 1.0540122985839844,
+      "grad_norm": 1.1499779224395752,
       "learning_rate": 0.00017196236915330594,
-      "loss": 3.0128715515136717,
+      "loss": 2.9631744384765626,
       "step": 1070
     },
     {
       "epoch": 0.42874156411274317,
-      "grad_norm": 1.1293870210647583,
+      "grad_norm": 1.0400148630142212,
       "learning_rate": 0.0001716973631906718,
-      "loss": 2.8330524444580076,
+      "loss": 2.9788026809692383,
       "step": 1080
     },
     {
       "epoch": 0.43271139341008336,
-      "grad_norm": 1.1059350967407227,
+      "grad_norm": 1.0587307214736938,
       "learning_rate": 0.00017143235722803763,
-      "loss": 2.9470712661743166,
+      "loss": 2.9872905731201174,
       "step": 1090
     },
     {
       "epoch": 0.4366812227074236,
-      "grad_norm": 1.104884386062622,
+      "grad_norm": 0.9863898158073425,
       "learning_rate": 0.0001711673512654035,
-      "loss": 2.954976272583008,
+      "loss": 2.959150505065918,
       "step": 1100
     },
     {
       "epoch": 0.4406510520047638,
-      "grad_norm": 0.9902713894844055,
+      "grad_norm": 1.024854302406311,
       "learning_rate": 0.00017090234530276933,
-      "loss": 3.006356430053711,
+      "loss": 2.906721496582031,
       "step": 1110
     },
     {
       "epoch": 0.44462088130210403,
-      "grad_norm": 1.3315637111663818,
+      "grad_norm": 1.2431564331054688,
       "learning_rate": 0.00017063733934013516,
-      "loss": 2.917298126220703,
+      "loss": 2.959243583679199,
       "step": 1120
     },
     {
       "epoch": 0.4485907105994442,
-      "grad_norm": 1.1523933410644531,
+      "grad_norm": 1.0118112564086914,
       "learning_rate": 0.000170372333377501,
-      "loss": 2.952730178833008,
+      "loss": 2.837575149536133,
       "step": 1130
     },
     {
       "epoch": 0.45256053989678446,
-      "grad_norm": 1.1412173509597778,
+      "grad_norm": 1.1883628368377686,
       "learning_rate": 0.00017010732741486683,
-      "loss": 3.0070873260498048,
+      "loss": 3.088572692871094,
       "step": 1140
     },
     {
       "epoch": 0.45653036919412465,
-      "grad_norm": 1.8569163084030151,
+      "grad_norm": 0.902087926864624,
       "learning_rate": 0.0001698423214522327,
-      "loss": 2.9984619140625,
+      "loss": 2.870463180541992,
       "step": 1150
     },
     {
       "epoch": 0.46050019849146484,
-      "grad_norm": 1.001707673072815,
+      "grad_norm": 1.1765600442886353,
       "learning_rate": 0.00016957731548959852,
-      "loss": 2.922855567932129,
+      "loss": 2.907725143432617,
       "step": 1160
     },
     {
       "epoch": 0.4644700277888051,
-      "grad_norm": 1.0932331085205078,
+      "grad_norm": 0.9849786162376404,
       "learning_rate": 0.00016931230952696438,
-      "loss": 2.927391242980957,
+      "loss": 2.975267791748047,
       "step": 1170
     },
     {
       "epoch": 0.4684398570861453,
-      "grad_norm": 1.1166234016418457,
+      "grad_norm": 1.0879027843475342,
       "learning_rate": 0.00016904730356433022,
-      "loss": 2.9800926208496095,
+      "loss": 2.9905019760131837,
       "step": 1180
     },
     {
       "epoch": 0.4724096863834855,
-      "grad_norm": 1.187969446182251,
+      "grad_norm": 1.159298300743103,
       "learning_rate": 0.00016878229760169605,
-      "loss": 3.054571342468262,
+      "loss": 2.9706029891967773,
       "step": 1190
     },
     {
       "epoch": 0.4763795156808257,
-      "grad_norm": 0.9883167147636414,
+      "grad_norm": 1.0128686428070068,
       "learning_rate": 0.00016851729163906189,
-      "loss": 2.7146305084228515,
+      "loss": 2.929449462890625,
       "step": 1200
     },
     {
       "epoch": 0.48034934497816595,
-      "grad_norm": 1.0295473337173462,
+      "grad_norm": 1.3239126205444336,
       "learning_rate": 0.00016825228567642772,
-      "loss": 2.925537872314453,
+      "loss": 2.854958343505859,
       "step": 1210
     },
     {
       "epoch": 0.48431917427550614,
-      "grad_norm": 1.1263221502304077,
+      "grad_norm": 1.1641817092895508,
       "learning_rate": 0.00016798727971379358,
-      "loss": 2.8725427627563476,
+      "loss": 2.8924772262573244,
       "step": 1220
     },
     {
       "epoch": 0.4882890035728464,
-      "grad_norm": 1.0885660648345947,
+      "grad_norm": 1.0055742263793945,
       "learning_rate": 0.00016772227375115941,
-      "loss": 2.816706657409668,
+      "loss": 2.9655168533325194,
       "step": 1230
     },
     {
       "epoch": 0.49225883287018657,
-      "grad_norm": 1.125899076461792,
+      "grad_norm": 1.029150128364563,
       "learning_rate": 0.00016745726778852525,
-      "loss": 2.958983039855957,
+      "loss": 2.953019905090332,
       "step": 1240
     },
     {
       "epoch": 0.4962286621675268,
-      "grad_norm": 1.0890135765075684,
+      "grad_norm": 1.0731725692749023,
       "learning_rate": 0.00016719226182589108,
-      "loss": 2.976550483703613,
+      "loss": 2.8922054290771486,
       "step": 1250
     },
     {
       "epoch": 0.5001984914648671,
-      "grad_norm": 0.9909167289733887,
+      "grad_norm": 1.1343021392822266,
       "learning_rate": 0.00016692725586325692,
-      "loss": 2.901120185852051,
+      "loss": 2.944770622253418,
       "step": 1260
     },
     {
       "epoch": 0.5041683207622072,
-      "grad_norm": 1.0964889526367188,
+      "grad_norm": 1.2642573118209839,
       "learning_rate": 0.00016666224990062278,
-      "loss": 3.0231674194335936,
+      "loss": 3.03311710357666,
       "step": 1270
     },
     {
       "epoch": 0.5081381500595474,
-      "grad_norm": 0.9550081491470337,
+      "grad_norm": 1.0998749732971191,
       "learning_rate": 0.0001663972439379886,
-      "loss": 2.9369964599609375,
+      "loss": 2.901491165161133,
       "step": 1280
     },
     {
       "epoch": 0.5121079793568877,
-      "grad_norm": 1.085239052772522,
+      "grad_norm": 1.1051859855651855,
       "learning_rate": 0.00016613223797535444,
-      "loss": 2.9554466247558593,
+      "loss": 3.012837600708008,
       "step": 1290
     },
     {
       "epoch": 0.5160778086542279,
-      "grad_norm": 0.9860292673110962,
+      "grad_norm": 1.2365621328353882,
       "learning_rate": 0.0001658672320127203,
-      "loss": 2.869415283203125,
+      "loss": 2.9026336669921875,
       "step": 1300
     },
     {
       "epoch": 0.520047637951568,
-      "grad_norm": 1.2385687828063965,
+      "grad_norm": 1.0339555740356445,
       "learning_rate": 0.00016560222605008614,
-      "loss": 2.9756792068481444,
+      "loss": 2.922551727294922,
       "step": 1310
     },
     {
       "epoch": 0.5240174672489083,
-      "grad_norm": 0.9716790914535522,
+      "grad_norm": 1.0754799842834473,
       "learning_rate": 0.00016533722008745197,
-      "loss": 3.0151626586914064,
+      "loss": 3.07440071105957,
       "step": 1320
     },
     {
       "epoch": 0.5279872965462485,
-      "grad_norm": 0.9712513089179993,
+      "grad_norm": 0.9746431708335876,
       "learning_rate": 0.0001650722141248178,
-      "loss": 2.7928401947021486,
+      "loss": 3.0004465103149416,
       "step": 1330
     },
     {
       "epoch": 0.5319571258435887,
-      "grad_norm": 1.3408395051956177,
+      "grad_norm": 1.1726387739181519,
       "learning_rate": 0.00016480720816218364,
-      "loss": 3.0238697052001955,
+      "loss": 2.94736270904541,
       "step": 1340
     },
     {
       "epoch": 0.5359269551409289,
-      "grad_norm": 1.1318269968032837,
+      "grad_norm": 1.149013638496399,
       "learning_rate": 0.0001645422021995495,
-      "loss": 2.937571716308594,
+      "loss": 2.9215377807617187,
       "step": 1350
     },
     {
       "epoch": 0.5398967844382692,
-      "grad_norm": 1.1990132331848145,
+      "grad_norm": 1.0117363929748535,
       "learning_rate": 0.00016427719623691533,
-      "loss": 2.9626527786254884,
+      "loss": 2.914345932006836,
       "step": 1360
     },
     {
       "epoch": 0.5438666137356094,
-      "grad_norm": 1.0656794309616089,
+      "grad_norm": 1.356374979019165,
       "learning_rate": 0.0001640121902742812,
-      "loss": 2.9569423675537108,
+      "loss": 2.9556610107421877,
       "step": 1370
     },
     {
       "epoch": 0.5478364430329495,
-      "grad_norm": 1.0160715579986572,
+      "grad_norm": 1.0233981609344482,
       "learning_rate": 0.00016374718431164703,
-      "loss": 2.8554924011230467,
+      "loss": 2.7411882400512697,
       "step": 1380
     },
     {
       "epoch": 0.5518062723302898,
-      "grad_norm": 1.0655139684677124,
+      "grad_norm": 0.9782310128211975,
       "learning_rate": 0.00016348217834901286,
-      "loss": 3.001082992553711,
+      "loss": 2.8227493286132814,
       "step": 1390
     },
     {
       "epoch": 0.55577610162763,
-      "grad_norm": 1.1931873559951782,
+      "grad_norm": 1.1206411123275757,
       "learning_rate": 0.0001632171723863787,
-      "loss": 2.9448843002319336,
+      "loss": 2.9366016387939453,
       "step": 1400
     }
   ],
@@ -1007,7 +1007,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.1738804486656e+16,
+  "total_flos": 6.181461035126784e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null