Add checkpoint-1200

checkpoints/checkpoint-1200/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16925291be8122aba0fa528167c2bf2ff449e91e6a334ab1d3ef59b560136674
+oid sha256:9f4a073fe9f0d66e418b172af586ae8856cfb9067e4b4ea2e625cc8578e40993
 size 4724960

checkpoints/checkpoint-1200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42f611f05a4ee293ed12ffc1b6d094b0de0e3f4627e064f8ad08b8963d9f6d92
+oid sha256:534da18f7da72b365faf06e8b8f77793c13839ba42b1fe2f2e678a9d439b432b
 size 2578187

checkpoints/checkpoint-1200/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9775ae43cdf95edc23ae70877435ad662ba7a1243f5c942afdd18c1f76fb028e
+oid sha256:c7ac0b1d503511a7ecbf106d89f6ad29fc5ca6fee450bdbaa99672a6029a55ff
 size 14645

checkpoints/checkpoint-1200/trainer_state.json

@@ -571,282 +571,282 @@
     },
     {
       "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
     }
   ],
@@ -867,7 +867,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.297385736710144e+16,
+  "total_flos": 5.307252485382144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null