CoolFace
Modelpublic

Alibaba-NLP/Simulation_LLM_google_14B_V2

sourceHugging Faceupdated 1y agoView on Hugging Face
1likes99downloads
trainer_state.json734 linesDownload Raw Back to root
1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 1.2953367875647668,5  "eval_steps": 10000000,6  "global_step": 1000,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.012953367875647668,13      "grad_norm": 43.076076550077694,14      "learning_rate": 6.476683937823834e-09,15      "loss": 3.0704,16      "step": 1017    },18    {19      "epoch": 0.025906735751295335,20      "grad_norm": 40.9396389995215,21      "learning_rate": 1.2953367875647667e-08,22      "loss": 2.9515,23      "step": 2024    },25    {26      "epoch": 0.038860103626943004,27      "grad_norm": 40.97955285652574,28      "learning_rate": 1.9430051813471502e-08,29      "loss": 3.0545,30      "step": 3031    },32    {33      "epoch": 0.05181347150259067,34      "grad_norm": 41.33204715803873,35      "learning_rate": 2.5906735751295334e-08,36      "loss": 3.0228,37      "step": 4038    },39    {40      "epoch": 0.06476683937823834,41      "grad_norm": 42.23332442613627,42      "learning_rate": 3.238341968911917e-08,43      "loss": 3.0354,44      "step": 5045    },46    {47      "epoch": 0.07772020725388601,48      "grad_norm": 44.56518138334028,49      "learning_rate": 3.8860103626943005e-08,50      "loss": 3.0051,51      "step": 6052    },53    {54      "epoch": 0.09067357512953368,55      "grad_norm": 40.7767523212035,56      "learning_rate": 4.533678756476684e-08,57      "loss": 3.0326,58      "step": 7059    },60    {61      "epoch": 0.10362694300518134,62      "grad_norm": 37.191408333303734,63      "learning_rate": 5.181347150259067e-08,64      "loss": 2.97,65      "step": 8066    },67    {68      "epoch": 0.11658031088082901,69      "grad_norm": 37.31766884591996,70      "learning_rate": 5.8290155440414504e-08,71      "loss": 2.8748,72      "step": 9073    },74    {75      "epoch": 0.12953367875647667,76      "grad_norm": 36.208356127388186,77      "learning_rate": 6.476683937823834e-08,78      "loss": 2.8776,79      "step": 10080    },81    {82      "epoch": 0.14248704663212436,83      "grad_norm": 33.13789071114948,84      "learning_rate": 7.124352331606218e-08,85      "loss": 2.8728,86      "step": 11087    },88    {89      "epoch": 0.15544041450777202,90      "grad_norm": 25.73482630280206,91      "learning_rate": 7.772020725388601e-08,92      "loss": 2.709,93      "step": 12094    },95    {96      "epoch": 0.16839378238341968,97      "grad_norm": 22.038324890804294,98      "learning_rate": 8.419689119170984e-08,99      "loss": 2.6382,100      "step": 130101    },102    {103      "epoch": 0.18134715025906736,104      "grad_norm": 22.185048967857036,105      "learning_rate": 9.067357512953368e-08,106      "loss": 2.5554,107      "step": 140108    },109    {110      "epoch": 0.19430051813471502,111      "grad_norm": 18.083733865410974,112      "learning_rate": 9.715025906735751e-08,113      "loss": 2.4812,114      "step": 150115    },116    {117      "epoch": 0.20725388601036268,118      "grad_norm": 9.017324625226863,119      "learning_rate": 1.0362694300518134e-07,120      "loss": 2.3281,121      "step": 160122    },123    {124      "epoch": 0.22020725388601037,125      "grad_norm": 7.678118962268154,126      "learning_rate": 1.1010362694300518e-07,127      "loss": 2.2715,128      "step": 170129    },130    {131      "epoch": 0.23316062176165803,132      "grad_norm": 6.290504564645648,133      "learning_rate": 1.1658031088082901e-07,134      "loss": 2.2517,135      "step": 180136    },137    {138      "epoch": 0.24611398963730569,139      "grad_norm": 5.562957539224074,140      "learning_rate": 1.2305699481865284e-07,141      "loss": 2.2002,142      "step": 190143    },144    {145      "epoch": 0.25906735751295334,146      "grad_norm": 4.640851265650242,147      "learning_rate": 1.2953367875647668e-07,148      "loss": 2.2032,149      "step": 200150    },151    {152      "epoch": 0.27202072538860106,153      "grad_norm": 4.098319743680852,154      "learning_rate": 1.3601036269430052e-07,155      "loss": 2.1007,156      "step": 210157    },158    {159      "epoch": 0.2849740932642487,160      "grad_norm": 3.8703435452061665,161      "learning_rate": 1.4248704663212436e-07,162      "loss": 2.1256,163      "step": 220164    },165    {166      "epoch": 0.2979274611398964,167      "grad_norm": 3.804744602548621,168      "learning_rate": 1.4896373056994818e-07,169      "loss": 2.1334,170      "step": 230171    },172    {173      "epoch": 0.31088082901554404,174      "grad_norm": 3.72894289463076,175      "learning_rate": 1.5544041450777202e-07,176      "loss": 2.1497,177      "step": 240178    },179    {180      "epoch": 0.3238341968911917,181      "grad_norm": 3.6159970324410975,182      "learning_rate": 1.6191709844559583e-07,183      "loss": 2.1146,184      "step": 250185    },186    {187      "epoch": 0.33678756476683935,188      "grad_norm": 3.4513794224622187,189      "learning_rate": 1.6839378238341968e-07,190      "loss": 2.0987,191      "step": 260192    },193    {194      "epoch": 0.34974093264248707,195      "grad_norm": 3.4264148655282707,196      "learning_rate": 1.7487046632124352e-07,197      "loss": 2.0694,198      "step": 270199    },200    {201      "epoch": 0.3626943005181347,202      "grad_norm": 3.2474565476427633,203      "learning_rate": 1.8134715025906736e-07,204      "loss": 2.087,205      "step": 280206    },207    {208      "epoch": 0.3756476683937824,209      "grad_norm": 3.5065133087524027,210      "learning_rate": 1.8782383419689118e-07,211      "loss": 2.1012,212      "step": 290213    },214    {215      "epoch": 0.38860103626943004,216      "grad_norm": 3.2610500040097623,217      "learning_rate": 1.9430051813471502e-07,218      "loss": 2.0864,219      "step": 300220    },221    {222      "epoch": 0.4015544041450777,223      "grad_norm": 3.46273816431845,224      "learning_rate": 2.0077720207253883e-07,225      "loss": 2.1223,226      "step": 310227    },228    {229      "epoch": 0.41450777202072536,230      "grad_norm": 3.4591348076759,231      "learning_rate": 2.0725388601036267e-07,232      "loss": 2.0511,233      "step": 320234    },235    {236      "epoch": 0.4274611398963731,237      "grad_norm": 3.143552612232648,238      "learning_rate": 2.1373056994818652e-07,239      "loss": 2.0698,240      "step": 330241    },242    {243      "epoch": 0.44041450777202074,244      "grad_norm": 3.3930346159225193,245      "learning_rate": 2.2020725388601036e-07,246      "loss": 2.062,247      "step": 340248    },249    {250      "epoch": 0.4533678756476684,251      "grad_norm": 3.1968277262246785,252      "learning_rate": 2.2668393782383417e-07,253      "loss": 2.0499,254      "step": 350255    },256    {257      "epoch": 0.46632124352331605,258      "grad_norm": 3.1762842339842545,259      "learning_rate": 2.3316062176165802e-07,260      "loss": 2.0388,261      "step": 360262    },263    {264      "epoch": 0.4792746113989637,265      "grad_norm": 3.1131594154841404,266      "learning_rate": 2.3963730569948183e-07,267      "loss": 2.071,268      "step": 370269    },270    {271      "epoch": 0.49222797927461137,272      "grad_norm": 3.4012154706204187,273      "learning_rate": 2.4611398963730567e-07,274      "loss": 2.0207,275      "step": 380276    },277    {278      "epoch": 0.5051813471502591,279      "grad_norm": 3.32603264761156,280      "learning_rate": 2.525906735751295e-07,281      "loss": 2.0551,282      "step": 390283    },284    {285      "epoch": 0.5181347150259067,286      "grad_norm": 3.0793049667074555,287      "learning_rate": 2.5906735751295336e-07,288      "loss": 2.0076,289      "step": 400290    },291    {292      "epoch": 0.5310880829015544,293      "grad_norm": 3.3022746352622536,294      "learning_rate": 2.655440414507772e-07,295      "loss": 2.0483,296      "step": 410297    },298    {299      "epoch": 0.5440414507772021,300      "grad_norm": 3.231444229889239,301      "learning_rate": 2.7202072538860104e-07,302      "loss": 2.0366,303      "step": 420304    },305    {306      "epoch": 0.5569948186528497,307      "grad_norm": 3.168051485737994,308      "learning_rate": 2.7849740932642483e-07,309      "loss": 2.0352,310      "step": 430311    },312    {313      "epoch": 0.5699481865284974,314      "grad_norm": 3.3177612879303284,315      "learning_rate": 2.849740932642487e-07,316      "loss": 2.0783,317      "step": 440318    },319    {320      "epoch": 0.582901554404145,321      "grad_norm": 3.0961489412889542,322      "learning_rate": 2.914507772020725e-07,323      "loss": 2.0185,324      "step": 450325    },326    {327      "epoch": 0.5958549222797928,328      "grad_norm": 3.192249587055236,329      "learning_rate": 2.9792746113989635e-07,330      "loss": 2.0432,331      "step": 460332    },333    {334      "epoch": 0.6088082901554405,335      "grad_norm": 3.2200126119045698,336      "learning_rate": 3.044041450777202e-07,337      "loss": 2.0553,338      "step": 470339    },340    {341      "epoch": 0.6217616580310881,342      "grad_norm": 3.207430731372013,343      "learning_rate": 3.1088082901554404e-07,344      "loss": 2.0304,345      "step": 480346    },347    {348      "epoch": 0.6347150259067358,349      "grad_norm": 3.196953450486009,350      "learning_rate": 3.173575129533679e-07,351      "loss": 2.0417,352      "step": 490353    },354    {355      "epoch": 0.6476683937823834,356      "grad_norm": 3.0518436646257334,357      "learning_rate": 3.2383419689119167e-07,358      "loss": 1.9995,359      "step": 500360    },361    {362      "epoch": 0.6606217616580311,363      "grad_norm": 3.0960475518738546,364      "learning_rate": 3.303108808290155e-07,365      "loss": 2.0019,366      "step": 510367    },368    {369      "epoch": 0.6735751295336787,370      "grad_norm": 3.4734729489261253,371      "learning_rate": 3.3678756476683935e-07,372      "loss": 2.0214,373      "step": 520374    },375    {376      "epoch": 0.6865284974093264,377      "grad_norm": 3.0715495927160106,378      "learning_rate": 3.432642487046632e-07,379      "loss": 2.0165,380      "step": 530381    },382    {383      "epoch": 0.6994818652849741,384      "grad_norm": 3.298121733914402,385      "learning_rate": 3.4974093264248704e-07,386      "loss": 1.9978,387      "step": 540388    },389    {390      "epoch": 0.7124352331606217,391      "grad_norm": 3.224003768850699,392      "learning_rate": 3.562176165803109e-07,393      "loss": 2.0165,394      "step": 550395    },396    {397      "epoch": 0.7253886010362695,398      "grad_norm": 3.207845261761618,399      "learning_rate": 3.626943005181347e-07,400      "loss": 2.0213,401      "step": 560402    },403    {404      "epoch": 0.7383419689119171,405      "grad_norm": 2.9379832555269103,406      "learning_rate": 3.691709844559585e-07,407      "loss": 1.9945,408      "step": 570409    },410    {411      "epoch": 0.7512953367875648,412      "grad_norm": 3.1048255292841542,413      "learning_rate": 3.7564766839378235e-07,414      "loss": 2.0447,415      "step": 580416    },417    {418      "epoch": 0.7642487046632125,419      "grad_norm": 3.1559283368532727,420      "learning_rate": 3.8212435233160625e-07,421      "loss": 2.0091,422      "step": 590423    },424    {425      "epoch": 0.7772020725388601,426      "grad_norm": 3.0089470388517148,427      "learning_rate": 3.8860103626943004e-07,428      "loss": 2.024,429      "step": 600430    },431    {432      "epoch": 0.7901554404145078,433      "grad_norm": 2.989858285669738,434      "learning_rate": 3.950777202072539e-07,435      "loss": 2.0211,436      "step": 610437    },438    {439      "epoch": 0.8031088082901554,440      "grad_norm": 2.9838710647706184,441      "learning_rate": 4.0155440414507767e-07,442      "loss": 2.0124,443      "step": 620444    },445    {446      "epoch": 0.8160621761658031,447      "grad_norm": 3.1331786862223545,448      "learning_rate": 4.0803108808290156e-07,449      "loss": 2.0164,450      "step": 630451    },452    {453      "epoch": 0.8290155440414507,454      "grad_norm": 2.8882108643266484,455      "learning_rate": 4.1450777202072535e-07,456      "loss": 1.9743,457      "step": 640458    },459    {460      "epoch": 0.8419689119170984,461      "grad_norm": 3.1820944740927946,462      "learning_rate": 4.209844559585492e-07,463      "loss": 1.9973,464      "step": 650465    },466    {467      "epoch": 0.8549222797927462,468      "grad_norm": 3.1018459499442184,469      "learning_rate": 4.2746113989637303e-07,470      "loss": 2.0062,471      "step": 660472    },473    {474      "epoch": 0.8678756476683938,475      "grad_norm": 3.08458871931019,476      "learning_rate": 4.339378238341969e-07,477      "loss": 1.9692,478      "step": 670479    },480    {481      "epoch": 0.8808290155440415,482      "grad_norm": 3.113974525500442,483      "learning_rate": 4.404145077720207e-07,484      "loss": 2.0378,485      "step": 680486    },487    {488      "epoch": 0.8937823834196891,489      "grad_norm": 3.376694314365291,490      "learning_rate": 4.468911917098445e-07,491      "loss": 1.9943,492      "step": 690493    },494    {495      "epoch": 0.9067357512953368,496      "grad_norm": 3.268661205585023,497      "learning_rate": 4.5336787564766835e-07,498      "loss": 1.9977,499      "step": 700500    },501    {502      "epoch": 0.9196891191709845,503      "grad_norm": 2.996627195399274,504      "learning_rate": 4.5984455958549224e-07,505      "loss": 1.9782,506      "step": 710507    },508    {509      "epoch": 0.9326424870466321,510      "grad_norm": 2.932454046391058,511      "learning_rate": 4.6632124352331603e-07,512      "loss": 1.9766,513      "step": 720514    },515    {516      "epoch": 0.9455958549222798,517      "grad_norm": 3.2738206104680088,518      "learning_rate": 4.7279792746113987e-07,519      "loss": 1.9388,520      "step": 730521    },522    {523      "epoch": 0.9585492227979274,524      "grad_norm": 2.9239778843618884,525      "learning_rate": 4.792746113989637e-07,526      "loss": 1.9716,527      "step": 740528    },529    {530      "epoch": 0.9715025906735751,531      "grad_norm": 3.1972940346458265,532      "learning_rate": 4.857512953367875e-07,533      "loss": 2.0161,534      "step": 750535    },536    {537      "epoch": 0.9844559585492227,538      "grad_norm": 3.3347499347681016,539      "learning_rate": 4.922279792746113e-07,540      "loss": 1.9765,541      "step": 760542    },543    {544      "epoch": 0.9974093264248705,545      "grad_norm": 3.0568292052459585,546      "learning_rate": 4.987046632124352e-07,547      "loss": 1.9368,548      "step": 770549    },550    {551      "epoch": 1.0103626943005182,552      "grad_norm": 2.9881753806367066,553      "learning_rate": 5.05181347150259e-07,554      "loss": 1.9666,555      "step": 780556    },557    {558      "epoch": 1.0233160621761659,559      "grad_norm": 3.2370659549778074,560      "learning_rate": 5.116580310880829e-07,561      "loss": 1.9904,562      "step": 790563    },564    {565      "epoch": 1.0362694300518134,566      "grad_norm": 3.0236879879482945,567      "learning_rate": 5.181347150259067e-07,568      "loss": 1.9652,569      "step": 800570    },571    {572      "epoch": 1.049222797927461,573      "grad_norm": 2.905006361103011,574      "learning_rate": 5.246113989637306e-07,575      "loss": 1.9845,576      "step": 810577    },578    {579      "epoch": 1.0621761658031088,580      "grad_norm": 3.155651179064785,581      "learning_rate": 5.310880829015544e-07,582      "loss": 1.9439,583      "step": 820584    },585    {586      "epoch": 1.0751295336787565,587      "grad_norm": 3.0538373364331957,588      "learning_rate": 5.375647668393782e-07,589      "loss": 1.9636,590      "step": 830591    },592    {593      "epoch": 1.0880829015544042,594      "grad_norm": 2.941917535285299,595      "learning_rate": 5.440414507772021e-07,596      "loss": 1.928,597      "step": 840598    },599    {600      "epoch": 1.1010362694300517,601      "grad_norm": 3.143750273608143,602      "learning_rate": 5.505181347150258e-07,603      "loss": 1.988,604      "step": 850605    },606    {607      "epoch": 1.1139896373056994,608      "grad_norm": 3.0526575513233576,609      "learning_rate": 5.569948186528497e-07,610      "loss": 2.0298,611      "step": 860612    },613    {614      "epoch": 1.1269430051813472,615      "grad_norm": 3.139974022960326,616      "learning_rate": 5.634715025906735e-07,617      "loss": 1.9806,618      "step": 870619    },620    {621      "epoch": 1.1398963730569949,622      "grad_norm": 2.962182207514898,623      "learning_rate": 5.699481865284974e-07,624      "loss": 2.0052,625      "step": 880626    },627    {628      "epoch": 1.1528497409326426,629      "grad_norm": 3.332736006863561,630      "learning_rate": 5.764248704663213e-07,631      "loss": 1.9777,632      "step": 890633    },634    {635      "epoch": 1.16580310880829,636      "grad_norm": 3.047159518577182,637      "learning_rate": 5.82901554404145e-07,638      "loss": 1.9816,639      "step": 900640    },641    {642      "epoch": 1.1787564766839378,643      "grad_norm": 3.0900251170460473,644      "learning_rate": 5.893782383419689e-07,645      "loss": 1.9539,646      "step": 910647    },648    {649      "epoch": 1.1917098445595855,650      "grad_norm": 3.2156155562663415,651      "learning_rate": 5.958549222797927e-07,652      "loss": 1.9271,653      "step": 920654    },655    {656      "epoch": 1.2046632124352332,657      "grad_norm": 3.087118578541963,658      "learning_rate": 6.023316062176166e-07,659      "loss": 1.9906,660      "step": 930661    },662    {663      "epoch": 1.2176165803108807,664      "grad_norm": 2.972038701138991,665      "learning_rate": 6.088082901554404e-07,666      "loss": 1.9839,667      "step": 940668    },669    {670      "epoch": 1.2305699481865284,671      "grad_norm": 2.953738637620668,672      "learning_rate": 6.152849740932642e-07,673      "loss": 1.9457,674      "step": 950675    },676    {677      "epoch": 1.2435233160621761,678      "grad_norm": 3.307869579476457,679      "learning_rate": 6.217616580310881e-07,680      "loss": 1.9658,681      "step": 960682    },683    {684      "epoch": 1.2564766839378239,685      "grad_norm": 2.8754881477979253,686      "learning_rate": 6.282383419689119e-07,687      "loss": 1.9479,688      "step": 970689    },690    {691      "epoch": 1.2694300518134716,692      "grad_norm": 3.516289819557544,693      "learning_rate": 6.347150259067358e-07,694      "loss": 1.9684,695      "step": 980696    },697    {698      "epoch": 1.2823834196891193,699      "grad_norm": 3.173293560970888,700      "learning_rate": 6.411917098445595e-07,701      "loss": 1.9508,702      "step": 990703    },704    {705      "epoch": 1.2953367875647668,706      "grad_norm": 3.167031160499092,707      "learning_rate": 6.476683937823833e-07,708      "loss": 1.9548,709      "step": 1000710    }711  ],712  "logging_steps": 10,713  "max_steps": 15440,714  "num_input_tokens_seen": 0,715  "num_train_epochs": 20,716  "save_steps": 1000,717  "stateful_callbacks": {718    "TrainerControl": {719      "args": {720        "should_epoch_stop": false,721        "should_evaluate": false,722        "should_log": false,723        "should_save": true,724        "should_training_stop": false725      },726      "attributes": {}727    }728  },729  "total_flos": 53264261382144.0,730  "train_batch_size": 2,731  "trial_name": null,732  "trial_params": null733}734