CoolFace
Modelpublic

Taywon/A1plus_v4_e1

sourceHugging Faceupdated 4mo agoView on Hugging Face
0likes8downloads
trainer_state.json815 linesDownload Raw Back to root
1{2  "best_global_step": null,3  "best_metric": null,4  "best_model_checkpoint": null,5  "epoch": 1.0,6  "eval_steps": 500,7  "global_step": 78,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "entropy": 1.3651542961597443,14      "epoch": 0.012944983818770227,15      "grad_norm": 1.3304885625839233,16      "learning_rate": 0.0,17      "loss": 2.1373414993286133,18      "mean_token_accuracy": 0.5150357112288475,19      "num_tokens": 129715.0,20      "step": 121    },22    {23      "entropy": 1.3770242929458618,24      "epoch": 0.025889967637540454,25      "grad_norm": 1.3239294290542603,26      "learning_rate": 4.166666666666667e-06,27      "loss": 2.154482841491699,28      "mean_token_accuracy": 0.5157716199755669,29      "num_tokens": 259772.0,30      "step": 231    },32    {33      "entropy": 1.4346312582492828,34      "epoch": 0.038834951456310676,35      "grad_norm": 1.1268572807312012,36      "learning_rate": 8.333333333333334e-06,37      "loss": 2.0695247650146484,38      "mean_token_accuracy": 0.5210058130323887,39      "num_tokens": 389849.0,40      "step": 341    },42    {43      "entropy": 1.5402012169361115,44      "epoch": 0.05177993527508091,45      "grad_norm": 0.9283472299575806,46      "learning_rate": 1.25e-05,47      "loss": 2.032970905303955,48      "mean_token_accuracy": 0.5240041315555573,49      "num_tokens": 518576.0,50      "step": 451    },52    {53      "entropy": 1.6357156783342361,54      "epoch": 0.06472491909385113,55      "grad_norm": 0.5993914604187012,56      "learning_rate": 1.6666666666666667e-05,57      "loss": 1.8982824087142944,58      "mean_token_accuracy": 0.5411873385310173,59      "num_tokens": 648530.0,60      "step": 561    },62    {63      "entropy": 1.834080547094345,64      "epoch": 0.07766990291262135,65      "grad_norm": 0.41406694054603577,66      "learning_rate": 2.0833333333333336e-05,67      "loss": 1.8447895050048828,68      "mean_token_accuracy": 0.5445547252893448,69      "num_tokens": 778260.0,70      "step": 671    },72    {73      "entropy": 1.9631124883890152,74      "epoch": 0.09061488673139159,75      "grad_norm": 0.5057855844497681,76      "learning_rate": 2.5e-05,77      "loss": 1.791555404663086,78      "mean_token_accuracy": 0.5538995414972305,79      "num_tokens": 908287.0,80      "step": 781    },82    {83      "entropy": 2.0287728756666183,84      "epoch": 0.10355987055016182,85      "grad_norm": 0.5796622633934021,86      "learning_rate": 2.916666666666667e-05,87      "loss": 1.7787578105926514,88      "mean_token_accuracy": 0.5525580644607544,89      "num_tokens": 1038626.0,90      "step": 891    },92    {93      "entropy": 1.8969777673482895,94      "epoch": 0.11650485436893204,95      "grad_norm": 0.49578264355659485,96      "learning_rate": 3.3333333333333335e-05,97      "loss": 1.6710119247436523,98      "mean_token_accuracy": 0.5709376186132431,99      "num_tokens": 1168231.0,100      "step": 9101    },102    {103      "entropy": 1.7819280922412872,104      "epoch": 0.12944983818770225,105      "grad_norm": 0.39638879895210266,106      "learning_rate": 3.7500000000000003e-05,107      "loss": 1.6355412006378174,108      "mean_token_accuracy": 0.5758759081363678,109      "num_tokens": 1298953.0,110      "step": 10111    },112    {113      "entropy": 1.6452170461416245,114      "epoch": 0.1423948220064725,115      "grad_norm": 0.31017157435417175,116      "learning_rate": 4.166666666666667e-05,117      "loss": 1.605017066001892,118      "mean_token_accuracy": 0.5790466815233231,119      "num_tokens": 1429030.0,120      "step": 11121    },122    {123      "entropy": 1.5164579153060913,124      "epoch": 0.1553398058252427,125      "grad_norm": 0.29436805844306946,126      "learning_rate": 4.5833333333333334e-05,127      "loss": 1.5629851818084717,128      "mean_token_accuracy": 0.5837943032383919,129      "num_tokens": 1556810.0,130      "step": 12131    },132    {133      "entropy": 1.4386323243379593,134      "epoch": 0.16828478964401294,135      "grad_norm": 0.2829895317554474,136      "learning_rate": 5e-05,137      "loss": 1.5202760696411133,138      "mean_token_accuracy": 0.5939656496047974,139      "num_tokens": 1687660.0,140      "step": 13141    },142    {143      "entropy": 1.3815916031599045,144      "epoch": 0.18122977346278318,145      "grad_norm": 0.25666117668151855,146      "learning_rate": 4.9997496794168726e-05,147      "loss": 1.4685187339782715,148      "mean_token_accuracy": 0.6037300601601601,149      "num_tokens": 1818622.0,150      "step": 14151    },152    {153      "entropy": 1.4070003181695938,154      "epoch": 0.1941747572815534,155      "grad_norm": 0.2441503256559372,156      "learning_rate": 4.998998767795805e-05,157      "loss": 1.447906732559204,158      "mean_token_accuracy": 0.6062909737229347,159      "num_tokens": 1948742.0,160      "step": 15161    },162    {163      "entropy": 1.4435111433267593,164      "epoch": 0.20711974110032363,165      "grad_norm": 0.26153597235679626,166      "learning_rate": 4.9977474155117045e-05,167      "loss": 1.4333127737045288,168      "mean_token_accuracy": 0.607229471206665,169      "num_tokens": 2078651.0,170      "step": 16171    },172    {173      "entropy": 1.427567034959793,174      "epoch": 0.22006472491909385,175      "grad_norm": 0.23656481504440308,176      "learning_rate": 4.995995873155958e-05,177      "loss": 1.396224021911621,178      "mean_token_accuracy": 0.6134042665362358,179      "num_tokens": 2205557.0,180      "step": 17181    },182    {183      "entropy": 1.433149129152298,184      "epoch": 0.23300970873786409,185      "grad_norm": 0.20005719363689423,186      "learning_rate": 4.99374449148625e-05,187      "loss": 1.392409324645996,188      "mean_token_accuracy": 0.6163519993424416,189      "num_tokens": 2332593.0,190      "step": 18191    },192    {193      "entropy": 1.4219946712255478,194      "epoch": 0.2459546925566343,195      "grad_norm": 0.19785650074481964,196      "learning_rate": 4.9909937213563165e-05,197      "loss": 1.3844692707061768,198      "mean_token_accuracy": 0.6169420257210732,199      "num_tokens": 2461816.0,200      "step": 19201    },202    {203      "entropy": 1.3724359720945358,204      "epoch": 0.2588996763754045,205      "grad_norm": 0.1962433159351349,206      "learning_rate": 4.987744113625665e-05,207      "loss": 1.3383996486663818,208      "mean_token_accuracy": 0.6265854984521866,209      "num_tokens": 2592376.0,210      "step": 20211    },212    {213      "entropy": 1.35466168820858,214      "epoch": 0.27184466019417475,215      "grad_norm": 0.19052749872207642,216      "learning_rate": 4.9839963190492576e-05,217      "loss": 1.326986312866211,218      "mean_token_accuracy": 0.6285954564809799,219      "num_tokens": 2722180.0,220      "step": 21221    },222    {223      "entropy": 1.324196070432663,224      "epoch": 0.284789644012945,225      "grad_norm": 0.1686500757932663,226      "learning_rate": 4.979751088147192e-05,227      "loss": 1.307222604751587,228      "mean_token_accuracy": 0.6329604238271713,229      "num_tokens": 2852915.0,230      "step": 22231    },232    {233      "entropy": 1.3377470970153809,234      "epoch": 0.2977346278317152,235      "grad_norm": 0.16810794174671173,236      "learning_rate": 4.975009271054409e-05,237      "loss": 1.3078091144561768,238      "mean_token_accuracy": 0.6321637183427811,239      "num_tokens": 2983811.0,240      "step": 23241    },242    {243      "entropy": 1.3341724425554276,244      "epoch": 0.3106796116504854,245      "grad_norm": 0.18940500915050507,246      "learning_rate": 4.969771817350445e-05,247      "loss": 1.312269926071167,248      "mean_token_accuracy": 0.6310013681650162,249      "num_tokens": 3114232.0,250      "step": 24251    },252    {253      "entropy": 1.310901552438736,254      "epoch": 0.32362459546925565,255      "grad_norm": 0.1773822158575058,256      "learning_rate": 4.9640397758692715e-05,257      "loss": 1.2985689640045166,258      "mean_token_accuracy": 0.6327972114086151,259      "num_tokens": 3239638.0,260      "step": 25261    },262    {263      "entropy": 1.2651723623275757,264      "epoch": 0.3365695792880259,265      "grad_norm": 0.17164088785648346,266      "learning_rate": 4.957814294489261e-05,267      "loss": 1.2655669450759888,268      "mean_token_accuracy": 0.6391567513346672,269      "num_tokens": 3369129.0,270      "step": 26271    },272    {273      "entropy": 1.2860137075185776,274      "epoch": 0.34951456310679613,275      "grad_norm": 0.16309353709220886,276      "learning_rate": 4.9510966199033174e-05,277      "loss": 1.2871453762054443,278      "mean_token_accuracy": 0.6366170793771744,279      "num_tokens": 3498592.0,280      "step": 27281    },282    {283      "entropy": 1.2693277299404144,284      "epoch": 0.36245954692556637,285      "grad_norm": 0.15370261669158936,286      "learning_rate": 4.943888097369216e-05,287      "loss": 1.264456033706665,288      "mean_token_accuracy": 0.6402129605412483,289      "num_tokens": 3628933.0,290      "step": 28291    },292    {293      "entropy": 1.250020757317543,294      "epoch": 0.37540453074433655,295      "grad_norm": 0.15371794998645782,296      "learning_rate": 4.936190170440208e-05,297      "loss": 1.2349557876586914,298      "mean_token_accuracy": 0.6465005129575729,299      "num_tokens": 3759250.0,300      "step": 29301    },302    {303      "entropy": 1.2473177313804626,304      "epoch": 0.3883495145631068,305      "grad_norm": 0.156179279088974,306      "learning_rate": 4.928004380675941e-05,307      "loss": 1.2247097492218018,308      "mean_token_accuracy": 0.6490338742733002,309      "num_tokens": 3888347.0,310      "step": 30311    },312    {313      "entropy": 1.2503016591072083,314      "epoch": 0.40129449838187703,315      "grad_norm": 0.16324147582054138,316      "learning_rate": 4.9193323673337476e-05,317      "loss": 1.2284612655639648,318      "mean_token_accuracy": 0.6461184471845627,319      "num_tokens": 4018991.0,320      "step": 31321    },322    {323      "entropy": 1.2558909952640533,324      "epoch": 0.41423948220064727,325      "grad_norm": 0.14576396346092224,326      "learning_rate": 4.910175867040377e-05,327      "loss": 1.2321372032165527,328      "mean_token_accuracy": 0.645910307765007,329      "num_tokens": 4149100.0,330      "step": 32331    },332    {333      "entropy": 1.2409392595291138,334      "epoch": 0.42718446601941745,335      "grad_norm": 0.14837919175624847,336      "learning_rate": 4.9005367134442235e-05,337      "loss": 1.2166019678115845,338      "mean_token_accuracy": 0.6500448063015938,339      "num_tokens": 4279686.0,340      "step": 33341    },342    {343      "entropy": 1.2073234170675278,344      "epoch": 0.4401294498381877,345      "grad_norm": 0.1407850831747055,346      "learning_rate": 4.890416836848127e-05,347      "loss": 1.191582441329956,348      "mean_token_accuracy": 0.654162771999836,349      "num_tokens": 4409879.0,350      "step": 34351    },352    {353      "entropy": 1.224804401397705,354      "epoch": 0.45307443365695793,355      "grad_norm": 0.14388902485370636,356      "learning_rate": 4.8798182638228166e-05,357      "loss": 1.2188255786895752,358      "mean_token_accuracy": 0.649294339120388,359      "num_tokens": 4539958.0,360      "step": 35361    },362    {363      "entropy": 1.1996213346719742,364      "epoch": 0.46601941747572817,365      "grad_norm": 0.13835251331329346,366      "learning_rate": 4.868743116801074e-05,367      "loss": 1.1903774738311768,368      "mean_token_accuracy": 0.6544475257396698,369      "num_tokens": 4668863.0,370      "step": 36371    },372    {373      "entropy": 1.166234239935875,374      "epoch": 0.47896440129449835,375      "grad_norm": 0.13608549535274506,376      "learning_rate": 4.857193613652711e-05,377      "loss": 1.1813488006591797,378      "mean_token_accuracy": 0.6577481329441071,379      "num_tokens": 4799874.0,380      "step": 37381    },382    {383      "entropy": 1.197123497724533,384      "epoch": 0.4919093851132686,385      "grad_norm": 0.13925297558307648,386      "learning_rate": 4.845172067240415e-05,387      "loss": 1.2087821960449219,388      "mean_token_accuracy": 0.6513781398534775,389      "num_tokens": 4929372.0,390      "step": 38391    },392    {393      "entropy": 1.1750382333993912,394      "epoch": 0.5048543689320388,395      "grad_norm": 0.13949091732501984,396      "learning_rate": 4.8326808849565936e-05,397      "loss": 1.177015781402588,398      "mean_token_accuracy": 0.6557950600981712,399      "num_tokens": 5059840.0,400      "step": 39401    },402    {403      "entropy": 1.1692189127206802,404      "epoch": 0.517799352750809,405      "grad_norm": 0.14397211372852325,406      "learning_rate": 4.819722568241274e-05,407      "loss": 1.1632399559020996,408      "mean_token_accuracy": 0.6591483578085899,409      "num_tokens": 5189026.0,410      "step": 40411    },412    {413      "entropy": 1.1593063026666641,414      "epoch": 0.5307443365695793,415      "grad_norm": 0.13899798691272736,416      "learning_rate": 4.806299712081172e-05,417      "loss": 1.1517739295959473,418      "mean_token_accuracy": 0.6616862490773201,419      "num_tokens": 5319304.0,420      "step": 41421    },422    {423      "entropy": 1.1965416818857193,424      "epoch": 0.5436893203883495,425      "grad_norm": 0.13963711261749268,426      "learning_rate": 4.792415004490034e-05,427      "loss": 1.1859239339828491,428      "mean_token_accuracy": 0.6556195169687271,429      "num_tokens": 5449076.0,430      "step": 42431    },432    {433      "entropy": 1.1787460893392563,434      "epoch": 0.5566343042071198,435      "grad_norm": 0.13826416432857513,436      "learning_rate": 4.77807122597034e-05,437      "loss": 1.154212236404419,438      "mean_token_accuracy": 0.6633580550551414,439      "num_tokens": 5578972.0,440      "step": 43441    },442    {443      "entropy": 1.1719040125608444,444      "epoch": 0.56957928802589,445      "grad_norm": 0.13135474920272827,446      "learning_rate": 4.7632712489564926e-05,447      "loss": 1.152864694595337,448      "mean_token_accuracy": 0.6626269146800041,449      "num_tokens": 5709351.0,450      "step": 44451    },452    {453      "entropy": 1.1761715561151505,454      "epoch": 0.5825242718446602,455      "grad_norm": 0.1382664293050766,456      "learning_rate": 4.748018037239592e-05,457      "loss": 1.1596863269805908,458      "mean_token_accuracy": 0.66019656509161,459      "num_tokens": 5839241.0,460      "step": 45461    },462    {463      "entropy": 1.1685755103826523,464      "epoch": 0.5954692556634305,465      "grad_norm": 0.1334962695837021,466      "learning_rate": 4.732314645373921e-05,467      "loss": 1.1554309129714966,468      "mean_token_accuracy": 0.6611259058117867,469      "num_tokens": 5969064.0,470      "step": 46471    },472    {473      "entropy": 1.143287107348442,474      "epoch": 0.6084142394822006,475      "grad_norm": 0.13915717601776123,476      "learning_rate": 4.7161642180652464e-05,477      "loss": 1.13901948928833,478      "mean_token_accuracy": 0.6638868674635887,479      "num_tokens": 6099092.0,480      "step": 47481    },482    {483      "entropy": 1.1229832172393799,484      "epoch": 0.6213592233009708,485      "grad_norm": 0.16735908389091492,486      "learning_rate": 4.699569989541074e-05,487      "loss": 1.1253852844238281,488      "mean_token_accuracy": 0.6694925650954247,489      "num_tokens": 6229169.0,490      "step": 48491    },492    {493      "entropy": 1.142636001110077,494      "epoch": 0.6343042071197411,495      "grad_norm": 0.1340433806180954,496      "learning_rate": 4.6825352829029705e-05,497      "loss": 1.1438826322555542,498      "mean_token_accuracy": 0.6639438346028328,499      "num_tokens": 6359167.0,500      "step": 49501    },502    {503      "entropy": 1.1389989107847214,504      "epoch": 0.6472491909385113,505      "grad_norm": 0.1330229490995407,506      "learning_rate": 4.665063509461097e-05,507      "loss": 1.1328400373458862,508      "mean_token_accuracy": 0.668202169239521,509      "num_tokens": 6489483.0,510      "step": 50511    },512    {513      "entropy": 1.1350421458482742,514      "epoch": 0.6601941747572816,515      "grad_norm": 0.13832047581672668,516      "learning_rate": 4.647158168051066e-05,517      "loss": 1.134395956993103,518      "mean_token_accuracy": 0.6662710979580879,519      "num_tokens": 6618304.0,520      "step": 51521    },522    {523      "entropy": 1.1280719488859177,524      "epoch": 0.6731391585760518,525      "grad_norm": 0.13961584866046906,526      "learning_rate": 4.628822844333278e-05,527      "loss": 1.1157816648483276,528      "mean_token_accuracy": 0.6674881353974342,529      "num_tokens": 6748534.0,530      "step": 52531    },532    {533      "entropy": 1.1400533020496368,534      "epoch": 0.686084142394822,535      "grad_norm": 0.13416820764541626,536      "learning_rate": 4.6100612100748765e-05,537      "loss": 1.1322004795074463,538      "mean_token_accuracy": 0.664855606853962,539      "num_tokens": 6878351.0,540      "step": 53541    },542    {543      "entropy": 1.117271676659584,544      "epoch": 0.6990291262135923,545      "grad_norm": 0.13155770301818848,546      "learning_rate": 4.59087702241444e-05,547      "loss": 1.1148383617401123,548      "mean_token_accuracy": 0.6699468269944191,549      "num_tokens": 7008842.0,550      "step": 54551    },552    {553      "entropy": 1.1524481028318405,554      "epoch": 0.7119741100323624,555      "grad_norm": 0.13490092754364014,556      "learning_rate": 4.571274123109606e-05,557      "loss": 1.1433762311935425,558      "mean_token_accuracy": 0.6656594127416611,559      "num_tokens": 7139302.0,560      "step": 55561    },562    {563      "entropy": 1.128203958272934,564      "epoch": 0.7249190938511327,565      "grad_norm": 0.13910333812236786,566      "learning_rate": 4.551256437767719e-05,567      "loss": 1.1198092699050903,568      "mean_token_accuracy": 0.6694299727678299,569      "num_tokens": 7268920.0,570      "step": 56571    },572    {573      "entropy": 1.1252606362104416,574      "epoch": 0.7378640776699029,575      "grad_norm": 0.13880470395088196,576      "learning_rate": 4.530827975059715e-05,577      "loss": 1.1268362998962402,578      "mean_token_accuracy": 0.6689485609531403,579      "num_tokens": 7399537.0,580      "step": 57581    },582    {583      "entropy": 1.1418287009000778,584      "epoch": 0.7508090614886731,585      "grad_norm": 0.1401115506887436,586      "learning_rate": 4.5099928259173516e-05,587      "loss": 1.1322367191314697,588      "mean_token_accuracy": 0.6656085550785065,589      "num_tokens": 7525788.0,590      "step": 58591    },592    {593      "entropy": 1.1480491310358047,594      "epoch": 0.7637540453074434,595      "grad_norm": 0.14310455322265625,596      "learning_rate": 4.488755162713975e-05,597      "loss": 1.1316089630126953,598      "mean_token_accuracy": 0.6664536520838737,599      "num_tokens": 7656150.0,600      "step": 59601    },602    {603      "entropy": 1.1366282999515533,604      "epoch": 0.7766990291262136,605      "grad_norm": 0.12998667359352112,606      "learning_rate": 4.467119238428975e-05,607      "loss": 1.1231651306152344,608      "mean_token_accuracy": 0.6681933254003525,609      "num_tokens": 7786291.0,610      "step": 60611    },612    {613      "entropy": 1.105496659874916,614      "epoch": 0.7896440129449838,615      "grad_norm": 0.1398758739233017,616      "learning_rate": 4.445089385796099e-05,617      "loss": 1.0939688682556152,618      "mean_token_accuracy": 0.6759221702814102,619      "num_tokens": 7916189.0,620      "step": 61621    },622    {623      "entropy": 1.1114656925201416,624      "epoch": 0.8025889967637541,625      "grad_norm": 0.13194960355758667,626      "learning_rate": 4.422670016435792e-05,627      "loss": 1.1039596796035767,628      "mean_token_accuracy": 0.6731015890836716,629      "num_tokens": 8046519.0,630      "step": 62631    },632    {633      "entropy": 1.0888657569885254,634      "epoch": 0.8155339805825242,635      "grad_norm": 0.1397247463464737,636      "learning_rate": 4.3998656199717435e-05,637      "loss": 1.0911369323730469,638      "mean_token_accuracy": 0.6746554225683212,639      "num_tokens": 8176740.0,640      "step": 63641    },642    {643      "entropy": 1.1219657808542252,644      "epoch": 0.8284789644012945,645      "grad_norm": 0.13516487181186676,646      "learning_rate": 4.3766807631318106e-05,647      "loss": 1.1249346733093262,648      "mean_token_accuracy": 0.668804943561554,649      "num_tokens": 8306981.0,650      "step": 64651    },652    {653      "entropy": 1.096419408917427,654      "epoch": 0.8414239482200647,655      "grad_norm": 0.13442112505435944,656      "learning_rate": 4.353120088833501e-05,657      "loss": 1.0880069732666016,658      "mean_token_accuracy": 0.675564743578434,659      "num_tokens": 8437012.0,660      "step": 65661    },662    {663      "entropy": 1.0983364135026932,664      "epoch": 0.8543689320388349,665      "grad_norm": 0.1384594589471817,666      "learning_rate": 4.329188315254196e-05,667      "loss": 1.0896861553192139,668      "mean_token_accuracy": 0.6748483330011368,669      "num_tokens": 8567432.0,670      "step": 66671    },672    {673      "entropy": 1.1061086654663086,674      "epoch": 0.8673139158576052,675      "grad_norm": 0.12975235283374786,676      "learning_rate": 4.3048902348863116e-05,677      "loss": 1.092883825302124,678      "mean_token_accuracy": 0.6738436594605446,679      "num_tokens": 8697482.0,680      "step": 67681    },682    {683      "entropy": 1.1013841927051544,684      "epoch": 0.8802588996763754,685      "grad_norm": 0.13858407735824585,686      "learning_rate": 4.280230713577564e-05,687      "loss": 1.0877230167388916,688      "mean_token_accuracy": 0.6764405071735382,689      "num_tokens": 8826353.0,690      "step": 68691    },692    {693      "entropy": 1.1029959172010422,694      "epoch": 0.8932038834951457,695      "grad_norm": 0.13860292732715607,696      "learning_rate": 4.255214689556557e-05,697      "loss": 1.1019368171691895,698      "mean_token_accuracy": 0.6718069836497307,699      "num_tokens": 8955338.0,700      "step": 69701    },702    {703      "entropy": 1.1007527112960815,704      "epoch": 0.9061488673139159,705      "grad_norm": 0.13615350425243378,706      "learning_rate": 4.229847172443866e-05,707      "loss": 1.1066391468048096,708      "mean_token_accuracy": 0.6710008159279823,709      "num_tokens": 9085706.0,710      "step": 70711    },712    {713      "entropy": 1.0915730148553848,714      "epoch": 0.919093851132686,715      "grad_norm": 0.1343710720539093,716      "learning_rate": 4.204133242248832e-05,717      "loss": 1.0948892831802368,718      "mean_token_accuracy": 0.6748337969183922,719      "num_tokens": 9216028.0,720      "step": 71721    },722    {723      "entropy": 1.1037265211343765,724      "epoch": 0.9320388349514563,725      "grad_norm": 0.13998186588287354,726      "learning_rate": 4.1780780483522575e-05,727      "loss": 1.097463607788086,728      "mean_token_accuracy": 0.6743032932281494,729      "num_tokens": 9346732.0,730      "step": 72731    },732    {733      "entropy": 1.081187054514885,734      "epoch": 0.9449838187702265,735      "grad_norm": 0.13939902186393738,736      "learning_rate": 4.151686808475204e-05,737      "loss": 1.0713167190551758,738      "mean_token_accuracy": 0.6809784397482872,739      "num_tokens": 9477265.0,740      "step": 73741    },742    {743      "entropy": 1.092852994799614,744      "epoch": 0.9579288025889967,745      "grad_norm": 0.13595172762870789,746      "learning_rate": 4.1249648076341165e-05,747      "loss": 1.085597038269043,748      "mean_token_accuracy": 0.6780063956975937,749      "num_tokens": 9606420.0,750      "step": 74751    },752    {753      "entropy": 1.09284046292305,754      "epoch": 0.970873786407767,755      "grad_norm": 0.12815804779529572,756      "learning_rate": 4.0979173970824626e-05,757      "loss": 1.0821534395217896,758      "mean_token_accuracy": 0.6755026131868362,759      "num_tokens": 9737245.0,760      "step": 75761    },762    {763      "entropy": 1.0906607061624527,764      "epoch": 0.9838187702265372,765      "grad_norm": 0.14664161205291748,766      "learning_rate": 4.070549993239106e-05,767      "loss": 1.0785982608795166,768      "mean_token_accuracy": 0.6788846999406815,769      "num_tokens": 9867367.0,770      "step": 76771    },772    {773      "entropy": 1.0882694870233536,774      "epoch": 0.9967637540453075,775      "grad_norm": 0.13629893958568573,776      "learning_rate": 4.0428680766036384e-05,777      "loss": 1.0791587829589844,778      "mean_token_accuracy": 0.6776749864220619,779      "num_tokens": 9998012.0,780      "step": 77781    },782    {783      "entropy": 1.1047788858413696,784      "epoch": 1.0,785      "grad_norm": 0.24593353271484375,786      "learning_rate": 4.0148771906588706e-05,787      "loss": 1.063537359237671,788      "mean_token_accuracy": 0.6715989708900452,789      "num_tokens": 10006202.0,790      "step": 78791    }792  ],793  "logging_steps": 1,794  "max_steps": 234,795  "num_input_tokens_seen": 0,796  "num_train_epochs": 3,797  "save_steps": 500,798  "stateful_callbacks": {799    "TrainerControl": {800      "args": {801        "should_epoch_stop": false,802        "should_evaluate": false,803        "should_log": false,804        "should_save": true,805        "should_training_stop": false806      },807      "attributes": {}808    }809  },810  "total_flos": 1.0582235533772063e+18,811  "train_batch_size": 1,812  "trial_name": null,813  "trial_params": null814}815