Training in progress, step 1500

config.json

@@ -21,7 +21,7 @@
   "sliding_window": 32768,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.40.0",
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936

merges.txt

@@ -308,6 +308,7 @@ tr ing
 o k
 _ _
 c l
+# #
 Ġh e
 ar d
 ) .
@@ -562,6 +563,7 @@ i eld
 Ġp er
 C ont
 ing s
+## ##
 Ġd ata
 Ġs a
 e f
@@ -808,6 +810,7 @@ R es
 is e
 m in
 ĠĠĠĠ Ċ
+# include
 eth od
 . P
 ut e
@@ -1097,6 +1100,7 @@ pr int
 Ex ception
 in put
 Ġtr ans
+#### ####
 ord er
 B y
 Ġa w
@@ -1180,6 +1184,7 @@ if y
 Ġb reak
 Ġ );Ċ
 re n
+# define
 it t
 Ġa p
 ĉ c
@@ -2169,6 +2174,7 @@ s ource
 http s
 Ġd em
 Ġe ar
+######## ########
 Ġm atch
 or ies
 ac es
@@ -2390,6 +2396,7 @@ a ff
 ER R
 Ġ< =
 at ely
+# if
 u ction
 ĠT e
 Ġl ink
@@ -2399,6 +2406,7 @@ u ction
 m e
 Ġg iven
 O ut
+# endif
 Ġbet ter
 P age
 Ġfe el
@@ -4691,6 +4699,7 @@ c ard
 o ch
 _ image
 \ t
+# Ċ
 ( L
 Ġindu stry
 com ing
@@ -4760,6 +4769,7 @@ SS ION
 Ġcurrent ly
 se c
 Ġrelations hip
+################ ################
 ĠM ap
 as et
 Ġparam eters
@@ -5261,6 +5271,7 @@ l at
 ast e
 Ġpro file
 Ġread y
+#if ndef
 ro te
 Ġs ense
 G ener
@@ -5485,6 +5496,7 @@ ag ram
 Ġp en
 .b tn
 ĠA S
+#if def
 Ġcho ice
 ĠP age
 _P RO
@@ -5644,6 +5656,7 @@ b uf
 S cript
 d at
 Ġr ule
+# import
 =" /
 S erial
 Ġstart ing
@@ -6220,6 +6233,7 @@ C D
 ib ly
 .e quals
 Ġintern ational
+# pragma
 oo th
 W riter
 i ate
@@ -7739,6 +7753,7 @@ D on
 ĠH ot
 ĠInd ex
 ; &
+# !
 ĠN or
 ĠC ap
 - (
@@ -7893,6 +7908,7 @@ ant ic
 ĠApp le
 g in
 Re quired
+# +
 land s
 Ġs qu
 Ġfact or
@@ -8428,6 +8444,7 @@ C OM
 i ro
 Ġrem ote
 ĠI T
+#! /
 Ġred istrib
 ra z
 ĠS ince
@@ -9665,6 +9682,7 @@ ont o
 ĠJ ournal
 r outer
 Ġmys qli
+# else
 ) "
 -x s
 let s
@@ -11753,6 +11771,7 @@ R et
 -d anger
 Ġroom s
 con v
+# {
 . op
 ĠA rea
 _S C
@@ -12791,6 +12810,7 @@ Th ank
 Ġfact s
 Ġun t
 .in stance
+################################ ################################
 - end
 ĠJO IN
 ĠH en
@@ -13076,6 +13096,7 @@ id os
 ĠJew ish
 Ġre covery
 Ġstand s
+# [
 Ġafter noon
 ĠArt icle
 _ att
@@ -13611,6 +13632,7 @@ un ge
 err a
 Ċ ĠĠĊ
 utor ial
+# a
 p ay
 char ge
 ĠI re
@@ -14095,6 +14117,7 @@ im plementation
 Ġstre ets
 _M SG
 New s
+## #
 : /
 Ġcut ting
 x B
@@ -15910,6 +15933,7 @@ param eter
 gener ated
 Ġad mitted
 Ġp ussy
+# w
 Ġsw im
 un ion
 N a
@@ -15961,6 +15985,7 @@ _ div
 vel y
 } );čĊ
 _ ENT
+#+ #+
 art icles
 ĠSou thern
 Ġstrong er
@@ -17173,6 +17198,7 @@ _f ont
 Ġcharacter istics
 D one
 el n
+######## ####
 PO S
 Ġd ensity
 ĠPl atform
@@ -18177,6 +18203,7 @@ W T
 d og
 Ġclick ing
 ), ĊĊ
+# line
 Oper ator
 Ġc iv
 Ġm erg
@@ -19588,6 +19615,7 @@ _th eme
 Ġdemonstr ate
 ĠHow ard
 D rop
+# undef
 Ġinv oke
 ĠB ridge
 end en
@@ -22329,6 +22357,7 @@ L F
 ĠP ub
 Ġâ Ķ
 c ion
+## Ċ
 II I
 Tag Name
 Ġam id
@@ -23378,6 +23407,7 @@ w ers
 .m aterial
 ĠD ue
 ĠP el
+# print
 Ġindepend ence
 ex us
 Sh adow
@@ -26200,6 +26230,7 @@ p icture
 ĠFant asy
 st ory
 Ġm ême
+# ĊĊ
 _s lice
 olt age
 H ar
@@ -26552,6 +26583,7 @@ j query
 am ination
 [ @"
 Ġm uj
+## #Ċ
 First OrDefault
 then Return
 C he
@@ -26723,6 +26755,7 @@ enc oder
 ather ine
 ( dest
 az ed
+# endregion
 sem bl
 , M
 ob y
@@ -28559,6 +28592,7 @@ _S M
 ib o
 Ġlo yal
 Ġuse less
+# elif
 ĠUlt imate
 C ome
 g el
@@ -28766,6 +28800,7 @@ as il
 ation ally
 ĠMe eting
 è¯ ¯
+# region
 Ġrout ing
 .f ocus
 ĠYou th
@@ -29562,6 +29597,7 @@ index Of
 .prot ocol
 AF E
 Ġtext ures
+################################ ################
 umb ai
 .st ats
 ĠG E
@@ -31748,6 +31784,7 @@ k now
 .F ull
 . undefined
 ĠSequ elize
+################################################################ ############
 Ġeduc ated
 _O VER
 åº ı
@@ -33359,6 +33396,7 @@ M id
 dd s
 Ġdepos its
 ĉd river
+# ga
 pr ising
 print ln
 Ġpres enter
@@ -40191,6 +40229,7 @@ M ade
 ac ific
 .v olume
 Ġmir rors
+################################################################ ################
 Ġviol ate
 ars ers
 Ġsoc io
@@ -41048,6 +41087,7 @@ _N ode
 ar de
 Ġfier ce
 lic ted
+# čĊ
 Ġbreak through
 ĠE rik
 Ġb ride
@@ -43790,6 +43830,7 @@ _ Log
 rown ed
 _m ed
 ĉ date
+# __
 Ġcost umes
 ĠRe quires
 aff le
@@ -45854,6 +45895,7 @@ Progress HUD
 Ġmock ed
 ĠT ory
 Ġ") ";Ċ
+# g
 Ġli ed
 Ġs vc
 _g ui
@@ -47778,10 +47820,12 @@ Num ero
 d aily
 ĠC oding
 ( destination
+# $
 uj Äħ
 Ġemerg ence
 _p ara
 _IN CLUDE
+# :
 Ġrecogn izing
 Ġf ug
 "} },Ċ
@@ -48197,6 +48241,7 @@ b stract
 k p
 IT ES
 Ġ ################################################################
+# get
 / Desktop
 ĉgl m
 Ġz inc
@@ -50222,6 +50267,7 @@ _L AYER
 Ġdee pest
 w k
 ĠNo ise
+### ĊĊ
 Ġpr éc
 ot le
 ÑĤ е
@@ -52021,6 +52067,7 @@ C OR
 -effect ive
 Ġsk u
 ed ly
+## ĊĊ
 ĠH olly
 ĠFL ASH
 / TR
@@ -55239,6 +55286,7 @@ keep ers
 _s b
 om ens
 ĠExec utes
+# "
 TT Y
 ĠValue Type
 ); */Ċ
@@ -55638,6 +55686,7 @@ S cores
 E OS
 H al
 Ġtrust worthy
+# =
 .EX TRA
 Ġman o
 is icing
@@ -60472,6 +60521,7 @@ m om
 / place
 Ġhol istic
 : t
+# ,
 Ġb oto
 Ġnause a
 ĠSh ooting
@@ -60608,6 +60658,7 @@ IM ATION
 C ause
 at ypes
 man ufacturer
+# ----------------------------------------------------------------------------
 Ġsp or
 es on
 Ġpun ched
@@ -62217,6 +62268,7 @@ Set Branch
 S creenshot
 esthes ia
 Ġwalk er
+# from
 co ordinate
 _ interest
 Ġhelp less
@@ -63427,6 +63479,7 @@ Count s
 Field Type
 ok able
 ĠRT L
+# index
 Ġ% {
 Ġar ist
 .Get Mapping
@@ -65749,6 +65802,7 @@ tr uncate
 so on
 Ġdis fr
 ĉ Vec
+## _
 .s chool
 Ġbl inds
 Ġac ab
@@ -67020,6 +67074,7 @@ _IO CTL
 ĉex ec
 EN AME
 _ letters
+#### #
 ĠC s
 '] =="
 Ġ" ')
@@ -67221,6 +67276,7 @@ _ asm
 Ġtem pl
 ĠExp ense
 e ight
+# SBATCH
 z ones
 .p arts
 at rice
@@ -67555,6 +67611,7 @@ ra i
 i ard
 Theme Provider
 Ġevent Data
+# ad
 .get Url
 Ġtool box
 Ġover riding
@@ -68399,6 +68456,7 @@ _PRE SENT
 ĠTh eta
 _inter p
 R aster
+# error
 , obj
 Ġtweet ing
 _G PU
@@ -68746,6 +68804,7 @@ imm une
 Ġè¾ĵ åħ¥
 Ġintimid ation
 end ale
+################################################################ ########
 Ġinsight ful
 Ġs ands
 Ġphotograph ic
@@ -69151,6 +69210,7 @@ sh ed
 Dep loy
 .Con tract
 - bo
+# /
 Ġinter ception
 Ġis bn
 Ġman ners
@@ -69633,6 +69693,7 @@ PO CH
 \ \"
 - job
 Ġsevent y
+#### Ċ
 ĠMan or
 Ġdown right
 Ġtime frame
@@ -71438,6 +71499,7 @@ _BR ANCH
 /m essages
 Ġof Type
 ĉs wap
+# plt
 ĠTur ks
 N ES
 Ġprogress ively
@@ -71685,6 +71747,7 @@ L ik
 _T itle
 (G tk
 Ġc elle
+# ================================================================
 ĠJ oomla
 "> //
 Month ly
@@ -75190,6 +75253,7 @@ s olver
 ĠRevel ation
 Ġrap ide
 p unk
+# ----------------------------------------------------------------
 Object Id
 abin et
 extr acomment
@@ -75594,6 +75658,7 @@ h ari
 (c d
 Ġun zip
 Ġglam orous
+# ",
 Ġn aw
 Ġmin ib
 ĠBr an
@@ -75876,6 +75941,7 @@ Button Type
 Ġragaz za
 / tag
 Ġirres ist
+# End
 ****** *čĊ
 Ġrestr ained
 Ġch iropr
@@ -76013,6 +76079,7 @@ cast ing
 Ġgr âce
 ĠH elsinki
 G ro
+# af
 ìĭ Ŀ
 Ġsou ha
 ĠInd ie
@@ -76805,6 +76872,7 @@ x EE
 .M ESSAGE
 (de g
 å¿ Ĺ
+#### ##
 Ġ"" ),
 kl är
 \M ail
@@ -77019,6 +77087,7 @@ ren s
 / grid
 Ġfil thy
 .e v
+#### #Ċ
 Ġs are
 Ġso aking
 ĠReg ions
@@ -77259,6 +77328,7 @@ IFICATION S
 ` ;
 ãĥ ĭ
 cent e
+# ab
 Ġlex ical
 ĠB RO
 Ġr ulings
@@ -77367,6 +77437,7 @@ U PI
 ĉ props
 Ġrot ten
 Re jected
+# ac
 . ua
 ĠAm nesty
 Ġpenn ed
@@ -77709,6 +77780,7 @@ d pi
 cul os
 _person al
 Ġanaly tic
+# create
 _mem cpy
 (List Node
 _T ag
@@ -78626,6 +78698,7 @@ b anks
 ìŀħ ëĭĪëĭ¤
 Ġsid eline
 .Array Adapter
+#### ##Ċ
 ĠSy rians
 ĠAtt endance
 -es que
@@ -79118,6 +79191,7 @@ Image Url
 ALL ERY
 c j
 x AD
+############################################################################ ###Ċ
 Ġitalian i
 | #
 Ġreg enerate
@@ -80086,6 +80160,7 @@ op he
 _C ategory
 ĠBT N
 ĠDar th
+# for
 eth nic
 arch itecture
 ĠCou pe
@@ -81160,6 +81235,7 @@ _TRA IN
 Ġcooper ating
 ung i
 Ar izona
+# echo
 -ex pression
 .min utes
 Ġpref ixed
@@ -81691,6 +81767,7 @@ customer Id
 ĠMom ents
 enu ous
 IFIC ATE
+#### ###Ċ
 æĸĩ ç«ł
 á»į c
 orm sg
@@ -81738,6 +81815,7 @@ Environment al
 ĠIS IL
 Ġco op
 h ores
+# @
 Ġcomp el
 (s kip
 éĺ ³
@@ -81962,6 +82040,7 @@ ia ux
 Ġ-*- čĊ
 if es
 ĠM ansion
+# Region
 C ancellation
 Ġnear ing
 Ġl angu
@@ -82242,6 +82321,7 @@ M ismatch
 Ġw reak
 Mar vel
 /s l
+################################ ########
 Ġmov able
 Ñĥ й
 ĠDr inking
@@ -83817,6 +83897,7 @@ M iami
 ĠPal o
 ĠSuz anne
 _m appings
+#{ @
 ĠOccup ational
 _b uckets
 go als
@@ -83961,6 +84042,7 @@ so v
 -w atch
 ĠHosp itals
 } while
+################ ########
 á» £
 Ġakt ual
 Ġkil ograms
@@ -84082,6 +84164,7 @@ CH AN
 Ġcurrent Position
 ĠCaucas ian
 $ img
+# aa
 Ġse an
 M ess
 *= *=
@@ -85026,6 +85109,7 @@ py x
 ĠR udd
 ĠPres byterian
 und ler
+#! [
 _l ahir
 () =="
 Access ibility
@@ -87505,6 +87589,7 @@ C ouncil
 _AT OMIC
 Sub Menu
 _com press
+# .
 Dr v
 .push Button
 Ġsuit case
@@ -87563,6 +87648,7 @@ ch ine
 Ġe books
 ) size
 Ġspecial ised
+# ae
 Ġmich ael
 ĠSTD OUT
 ĠP ell
@@ -87741,6 +87827,7 @@ t ournament
 ĠEisen hower
 File d
 Ġhe bt
+# \
 create QueryBuilder
 æľī æķĪ
 v anced
@@ -87756,6 +87843,7 @@ Inst aller
 ol vable
 Ġal as
 (sp ell
+################ ############
 Ġdef amation
 ( Arg
 Ġuser Details
@@ -89693,6 +89781,7 @@ ict ory
 Ġsup p
 pe on
 v rier
+################################################ ########
 Ġtrot z
 Ġmel tdown
 ark ers
@@ -90384,6 +90473,7 @@ Gr an
 ser ter
 Ġstore front
 _ ends
+################################################################################ Ċ
 ĉg it
 D SP
 CH AIN
@@ -91906,6 +91996,7 @@ arg ed
 ĠST ILL
 Qualified Name
 . RES
+# c
 .w riteln
 ĠImmutable List
 ĠTh umb
@@ -92887,6 +92978,7 @@ Sc ala
 in ne
 ĠCONST ANTS
 _P rice
+# %%
 Ġar sch
 ĠNS AttributedString
 ĠFile Type
@@ -93833,6 +93925,7 @@ _TRI ANGLE
 _P ICTURE
 _OR IENTATION
 ĠO PP
+# '
 áf ico
 .h istogram
 ĠB enny
@@ -94103,6 +94196,7 @@ Owner Id
 ew n
 Ġpop ulous
 ĠSh ed
+# ${
 ĠA lo
 Device Info
 (IN VOKE
@@ -97493,6 +97587,7 @@ F el
 ĠD ISTRIBUT
 é ments
 ĠValid ates
+################################################ ############
 Ġ| /
 Ġes l
 Ġré seau
@@ -97512,6 +97607,7 @@ Ne o
 ime i
 .get Bounds
 .Mouse EventHandler
+#### ###
 Generic Type
 /c ms
 Ġturn o

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c79e77860816fc69e2fec4cb5801afdd1af0a33532210ea4c187a507b9e991
+oid sha256:24a1d6cefdb52a8336183f54fedd59ecc2e145dbdf148edbd77c1bf83c753d77
 size 3673690696

trainer_log.jsonl

@@ -1,5 +1,13 @@
-{"current_steps": 10, "total_steps": 129, "loss": 1.6271, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0000000000000002e-06, "epoch": 0.08, "percentage": 7.75, "elapsed_time": "0:01:49", "remaining_time": "0:21:47"}
-{"current_steps": 20, "total_steps": 129, "loss": 1.5888, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0000000000000003e-06, "epoch": 0.16, "percentage": 15.5, "elapsed_time": "0:02:02", "remaining_time": "0:11:10"}
-{"current_steps": 30, "total_steps": 129, "loss": 1.6088, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-06, "epoch": 0.23, "percentage": 23.26, "elapsed_time": "0:02:16", "remaining_time": "0:07:28"}
-{"current_steps": 30, "total_steps": 129, "loss": null, "eval_loss": 1.6200140714645386, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.23, "percentage": 23.26, "elapsed_time": "0:02:16", "remaining_time": "0:07:28"}
-{"current_steps": 40, "total_steps": 129, "loss": 1.557, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.000000000000001e-06, "epoch": 0.31, "percentage": 31.01, "elapsed_time": "0:02:45", "remaining_time": "0:06:08"}
+{"current_steps": 150, "total_steps": 3232, "loss": 1.0929, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5e-05, "epoch": 0.046407301415422694, "percentage": 4.64, "elapsed_time": "0:14:02", "remaining_time": "4:48:34"}
+{"current_steps": 300, "total_steps": 3232, "loss": 0.0827, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.09281460283084539, "percentage": 9.28, "elapsed_time": "0:28:05", "remaining_time": "4:34:31"}
+{"current_steps": 450, "total_steps": 3232, "loss": 0.0342, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5e-05, "epoch": 0.13922190424626807, "percentage": 13.92, "elapsed_time": "0:42:09", "remaining_time": "4:20:34"}
+{"current_steps": 500, "total_steps": 3232, "loss": null, "eval_loss": 0.028695255517959595, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.15469100471807565, "percentage": 15.47, "elapsed_time": "0:46:17", "remaining_time": "4:12:56"}
+{"current_steps": 600, "total_steps": 3232, "loss": 0.0272, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9834891379023305e-05, "epoch": 0.18562920566169078, "percentage": 18.56, "elapsed_time": "0:54:43", "remaining_time": "4:00:03"}
+{"current_steps": 750, "total_steps": 3232, "loss": 0.0263, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.89740285199002e-05, "epoch": 0.23203650707711346, "percentage": 23.21, "elapsed_time": "1:08:47", "remaining_time": "3:47:40"}
+{"current_steps": 900, "total_steps": 3232, "loss": 0.0256, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.74016493642952e-05, "epoch": 0.27844380849253614, "percentage": 27.85, "elapsed_time": "1:22:51", "remaining_time": "3:34:42"}
+{"current_steps": 1000, "total_steps": 3232, "loss": null, "eval_loss": 0.024917807430028915, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.3093820094361513, "percentage": 30.94, "elapsed_time": "1:31:09", "remaining_time": "3:23:26"}
+{"current_steps": 1050, "total_steps": 3232, "loss": 0.0243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.516441996971018e-05, "epoch": 0.32485110990795885, "percentage": 32.49, "elapsed_time": "1:37:04", "remaining_time": "3:21:43"}
+{"current_steps": 1200, "total_steps": 3232, "loss": 0.0245, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.232873823718602e-05, "epoch": 0.37125841132338155, "percentage": 37.13, "elapsed_time": "1:49:29", "remaining_time": "3:05:24"}
+{"current_steps": 1350, "total_steps": 3232, "loss": 0.0235, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8978763312635645e-05, "epoch": 0.41766571273880426, "percentage": 41.77, "elapsed_time": "2:03:34", "remaining_time": "2:52:15"}
+{"current_steps": 1500, "total_steps": 3232, "loss": 0.0242, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.521391785878114e-05, "epoch": 0.4640730141542269, "percentage": 46.41, "elapsed_time": "2:17:36", "remaining_time": "2:38:53"}
+{"current_steps": 1500, "total_steps": 3232, "loss": null, "eval_loss": 0.023714479058980942, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.4640730141542269, "percentage": 46.41, "elapsed_time": "2:17:36", "remaining_time": "2:38:53"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02bb292edf81b3301abec77493d5e806a61450dc4760dc264c424c9878fd1bd5
-size 4603
+oid sha256:1ff968fa226563b0bb984c4fed8a7d56de79150cd5999dc15d438c6d055e415d
+size 5176