CoolFace
Modelpublic

Alibaba-NLP/Simulation_LLM_wiki_14B_V2

sourceHugging Faceupdated 1y agoView on Hugging Face
1likes101downloads
trainer_state.json734 linesDownload Raw Back to root
1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 1.2738853503184713,5  "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": 0.012738853503184714,13      "grad_norm": 14.034008421036804,14      "learning_rate": 6.369426751592357e-09,15      "loss": 1.9212,16      "step": 1017    },18    {19      "epoch": 0.025477707006369428,20      "grad_norm": 14.324525585475893,21      "learning_rate": 1.2738853503184714e-08,22      "loss": 1.9573,23      "step": 2024    },25    {26      "epoch": 0.03821656050955414,27      "grad_norm": 13.359417294747553,28      "learning_rate": 1.910828025477707e-08,29      "loss": 1.9572,30      "step": 3031    },32    {33      "epoch": 0.050955414012738856,34      "grad_norm": 14.330701922979292,35      "learning_rate": 2.5477707006369427e-08,36      "loss": 1.9322,37      "step": 4038    },39    {40      "epoch": 0.06369426751592357,41      "grad_norm": 14.315516059019966,42      "learning_rate": 3.184713375796178e-08,43      "loss": 1.924,44      "step": 5045    },46    {47      "epoch": 0.07643312101910828,48      "grad_norm": 13.502552068344668,49      "learning_rate": 3.821656050955414e-08,50      "loss": 1.9413,51      "step": 6052    },53    {54      "epoch": 0.08917197452229299,55      "grad_norm": 13.518442083664025,56      "learning_rate": 4.458598726114649e-08,57      "loss": 1.9446,58      "step": 7059    },60    {61      "epoch": 0.10191082802547771,62      "grad_norm": 12.383858046483768,63      "learning_rate": 5.0955414012738854e-08,64      "loss": 1.9417,65      "step": 8066    },67    {68      "epoch": 0.11464968152866242,69      "grad_norm": 11.723789916894649,70      "learning_rate": 5.732484076433121e-08,71      "loss": 1.8923,72      "step": 9073    },74    {75      "epoch": 0.12738853503184713,76      "grad_norm": 11.079881895874683,77      "learning_rate": 6.369426751592356e-08,78      "loss": 1.8899,79      "step": 10080    },81    {82      "epoch": 0.14012738853503184,83      "grad_norm": 11.331614677061625,84      "learning_rate": 7.006369426751591e-08,85      "loss": 1.8947,86      "step": 11087    },88    {89      "epoch": 0.15286624203821655,90      "grad_norm": 8.897895249557337,91      "learning_rate": 7.643312101910828e-08,92      "loss": 1.8655,93      "step": 12094    },95    {96      "epoch": 0.16560509554140126,97      "grad_norm": 7.851143763222098,98      "learning_rate": 8.280254777070063e-08,99      "loss": 1.8388,100      "step": 130101    },102    {103      "epoch": 0.17834394904458598,104      "grad_norm": 7.651003274597473,105      "learning_rate": 8.917197452229298e-08,106      "loss": 1.8185,107      "step": 140108    },109    {110      "epoch": 0.1910828025477707,111      "grad_norm": 6.852701313431956,112      "learning_rate": 9.554140127388536e-08,113      "loss": 1.7775,114      "step": 150115    },116    {117      "epoch": 0.20382165605095542,118      "grad_norm": 4.332528021529095,119      "learning_rate": 1.0191082802547771e-07,120      "loss": 1.7623,121      "step": 160122    },123    {124      "epoch": 0.21656050955414013,125      "grad_norm": 3.5221886562887184,126      "learning_rate": 1.0828025477707006e-07,127      "loss": 1.6837,128      "step": 170129    },130    {131      "epoch": 0.22929936305732485,132      "grad_norm": 3.149818516156245,133      "learning_rate": 1.1464968152866242e-07,134      "loss": 1.6979,135      "step": 180136    },137    {138      "epoch": 0.24203821656050956,139      "grad_norm": 2.9107656285941355,140      "learning_rate": 1.2101910828025477e-07,141      "loss": 1.6961,142      "step": 190143    },144    {145      "epoch": 0.25477707006369427,146      "grad_norm": 2.795449899540731,147      "learning_rate": 1.2738853503184713e-07,148      "loss": 1.6375,149      "step": 200150    },151    {152      "epoch": 0.267515923566879,153      "grad_norm": 2.28687122905737,154      "learning_rate": 1.3375796178343948e-07,155      "loss": 1.6353,156      "step": 210157    },158    {159      "epoch": 0.2802547770700637,160      "grad_norm": 2.1744397918507112,161      "learning_rate": 1.4012738853503183e-07,162      "loss": 1.6551,163      "step": 220164    },165    {166      "epoch": 0.2929936305732484,167      "grad_norm": 1.9913861609957166,168      "learning_rate": 1.464968152866242e-07,169      "loss": 1.6084,170      "step": 230171    },172    {173      "epoch": 0.3057324840764331,174      "grad_norm": 3.6644916122308606,175      "learning_rate": 1.5286624203821656e-07,176      "loss": 1.6159,177      "step": 240178    },179    {180      "epoch": 0.3184713375796178,181      "grad_norm": 1.9386884261467865,182      "learning_rate": 1.592356687898089e-07,183      "loss": 1.5966,184      "step": 250185    },186    {187      "epoch": 0.33121019108280253,188      "grad_norm": 1.801727064360074,189      "learning_rate": 1.6560509554140126e-07,190      "loss": 1.5382,191      "step": 260192    },193    {194      "epoch": 0.34394904458598724,195      "grad_norm": 1.791207448353307,196      "learning_rate": 1.719745222929936e-07,197      "loss": 1.5677,198      "step": 270199    },200    {201      "epoch": 0.35668789808917195,202      "grad_norm": 1.785800105876019,203      "learning_rate": 1.7834394904458596e-07,204      "loss": 1.5679,205      "step": 280206    },207    {208      "epoch": 0.36942675159235666,209      "grad_norm": 1.7105114239580628,210      "learning_rate": 1.847133757961783e-07,211      "loss": 1.5676,212      "step": 290213    },214    {215      "epoch": 0.3821656050955414,216      "grad_norm": 1.635688328958137,217      "learning_rate": 1.9108280254777072e-07,218      "loss": 1.5159,219      "step": 300220    },221    {222      "epoch": 0.39490445859872614,223      "grad_norm": 1.672905022352275,224      "learning_rate": 1.9745222929936307e-07,225      "loss": 1.5458,226      "step": 310227    },228    {229      "epoch": 0.40764331210191085,230      "grad_norm": 1.667559991729344,231      "learning_rate": 2.0382165605095542e-07,232      "loss": 1.5553,233      "step": 320234    },235    {236      "epoch": 0.42038216560509556,237      "grad_norm": 1.8961844126982597,238      "learning_rate": 2.1019108280254777e-07,239      "loss": 1.5726,240      "step": 330241    },242    {243      "epoch": 0.43312101910828027,244      "grad_norm": 1.704794668355483,245      "learning_rate": 2.1656050955414012e-07,246      "loss": 1.5338,247      "step": 340248    },249    {250      "epoch": 0.445859872611465,251      "grad_norm": 1.7655206338682627,252      "learning_rate": 2.2292993630573247e-07,253      "loss": 1.5407,254      "step": 350255    },256    {257      "epoch": 0.4585987261146497,258      "grad_norm": 1.6563900983762812,259      "learning_rate": 2.2929936305732485e-07,260      "loss": 1.5357,261      "step": 360262    },263    {264      "epoch": 0.4713375796178344,265      "grad_norm": 1.8360088416494706,266      "learning_rate": 2.356687898089172e-07,267      "loss": 1.5579,268      "step": 370269    },270    {271      "epoch": 0.4840764331210191,272      "grad_norm": 1.6539352097565592,273      "learning_rate": 2.4203821656050955e-07,274      "loss": 1.5138,275      "step": 380276    },277    {278      "epoch": 0.4968152866242038,279      "grad_norm": 1.6386927867862713,280      "learning_rate": 2.484076433121019e-07,281      "loss": 1.5311,282      "step": 390283    },284    {285      "epoch": 0.5095541401273885,286      "grad_norm": 1.6316402031128345,287      "learning_rate": 2.5477707006369425e-07,288      "loss": 1.4975,289      "step": 400290    },291    {292      "epoch": 0.5222929936305732,293      "grad_norm": 1.6279765149394207,294      "learning_rate": 2.611464968152866e-07,295      "loss": 1.5508,296      "step": 410297    },298    {299      "epoch": 0.535031847133758,300      "grad_norm": 1.7198212849602736,301      "learning_rate": 2.6751592356687895e-07,302      "loss": 1.5293,303      "step": 420304    },305    {306      "epoch": 0.5477707006369427,307      "grad_norm": 1.6536550947528905,308      "learning_rate": 2.738853503184713e-07,309      "loss": 1.5422,310      "step": 430311    },312    {313      "epoch": 0.5605095541401274,314      "grad_norm": 1.7104890897146838,315      "learning_rate": 2.8025477707006366e-07,316      "loss": 1.505,317      "step": 440318    },319    {320      "epoch": 0.5732484076433121,321      "grad_norm": 1.7028427858115733,322      "learning_rate": 2.86624203821656e-07,323      "loss": 1.5273,324      "step": 450325    },326    {327      "epoch": 0.5859872611464968,328      "grad_norm": 1.606699689644091,329      "learning_rate": 2.929936305732484e-07,330      "loss": 1.5315,331      "step": 460332    },333    {334      "epoch": 0.5987261146496815,335      "grad_norm": 1.7074522582102618,336      "learning_rate": 2.9936305732484076e-07,337      "loss": 1.5321,338      "step": 470339    },340    {341      "epoch": 0.6114649681528662,342      "grad_norm": 2.1566787662429756,343      "learning_rate": 3.057324840764331e-07,344      "loss": 1.5356,345      "step": 480346    },347    {348      "epoch": 0.6242038216560509,349      "grad_norm": 1.6361324291726362,350      "learning_rate": 3.1210191082802546e-07,351      "loss": 1.5333,352      "step": 490353    },354    {355      "epoch": 0.6369426751592356,356      "grad_norm": 1.5544549161506893,357      "learning_rate": 3.184713375796178e-07,358      "loss": 1.4812,359      "step": 500360    },361    {362      "epoch": 0.6496815286624203,363      "grad_norm": 1.8652030639545352,364      "learning_rate": 3.2484076433121017e-07,365      "loss": 1.5465,366      "step": 510367    },368    {369      "epoch": 0.6624203821656051,370      "grad_norm": 1.713752710097288,371      "learning_rate": 3.312101910828025e-07,372      "loss": 1.5054,373      "step": 520374    },375    {376      "epoch": 0.6751592356687898,377      "grad_norm": 1.6986436389098123,378      "learning_rate": 3.3757961783439487e-07,379      "loss": 1.5356,380      "step": 530381    },382    {383      "epoch": 0.6878980891719745,384      "grad_norm": 1.6494260445407405,385      "learning_rate": 3.439490445859872e-07,386      "loss": 1.4968,387      "step": 540388    },389    {390      "epoch": 0.7006369426751592,391      "grad_norm": 1.6145130069998217,392      "learning_rate": 3.5031847133757957e-07,393      "loss": 1.5371,394      "step": 550395    },396    {397      "epoch": 0.7133757961783439,398      "grad_norm": 1.5117351196478945,399      "learning_rate": 3.566878980891719e-07,400      "loss": 1.5064,401      "step": 560402    },403    {404      "epoch": 0.7261146496815286,405      "grad_norm": 1.5389329444189115,406      "learning_rate": 3.6305732484076427e-07,407      "loss": 1.4885,408      "step": 570409    },410    {411      "epoch": 0.7388535031847133,412      "grad_norm": 1.7080520598619022,413      "learning_rate": 3.694267515923566e-07,414      "loss": 1.491,415      "step": 580416    },417    {418      "epoch": 0.7515923566878981,419      "grad_norm": 1.4506261889056746,420      "learning_rate": 3.757961783439491e-07,421      "loss": 1.4792,422      "step": 590423    },424    {425      "epoch": 0.7643312101910829,426      "grad_norm": 1.5912892418189286,427      "learning_rate": 3.8216560509554143e-07,428      "loss": 1.5181,429      "step": 600430    },431    {432      "epoch": 0.7770700636942676,433      "grad_norm": 1.7347562868273487,434      "learning_rate": 3.885350318471338e-07,435      "loss": 1.5001,436      "step": 610437    },438    {439      "epoch": 0.7898089171974523,440      "grad_norm": 1.7247795867566735,441      "learning_rate": 3.9490445859872613e-07,442      "loss": 1.5643,443      "step": 620444    },445    {446      "epoch": 0.802547770700637,447      "grad_norm": 1.8030660386471178,448      "learning_rate": 4.012738853503185e-07,449      "loss": 1.4885,450      "step": 630451    },452    {453      "epoch": 0.8152866242038217,454      "grad_norm": 1.847905567407947,455      "learning_rate": 4.0764331210191083e-07,456      "loss": 1.5169,457      "step": 640458    },459    {460      "epoch": 0.8280254777070064,461      "grad_norm": 1.7953671081333586,462      "learning_rate": 4.140127388535032e-07,463      "loss": 1.5251,464      "step": 650465    },466    {467      "epoch": 0.8407643312101911,468      "grad_norm": 1.588856325601936,469      "learning_rate": 4.2038216560509554e-07,470      "loss": 1.4935,471      "step": 660472    },473    {474      "epoch": 0.8535031847133758,475      "grad_norm": 1.6474093001494565,476      "learning_rate": 4.267515923566879e-07,477      "loss": 1.5197,478      "step": 670479    },480    {481      "epoch": 0.8662420382165605,482      "grad_norm": 1.8040366493948004,483      "learning_rate": 4.3312101910828024e-07,484      "loss": 1.532,485      "step": 680486    },487    {488      "epoch": 0.8789808917197452,489      "grad_norm": 1.649448453977979,490      "learning_rate": 4.394904458598726e-07,491      "loss": 1.5326,492      "step": 690493    },494    {495      "epoch": 0.89171974522293,496      "grad_norm": 1.7529453909608548,497      "learning_rate": 4.4585987261146494e-07,498      "loss": 1.5016,499      "step": 700500    },501    {502      "epoch": 0.9044585987261147,503      "grad_norm": 1.6610601648124064,504      "learning_rate": 4.522292993630573e-07,505      "loss": 1.5081,506      "step": 710507    },508    {509      "epoch": 0.9171974522292994,510      "grad_norm": 1.4933572459758815,511      "learning_rate": 4.585987261146497e-07,512      "loss": 1.508,513      "step": 720514    },515    {516      "epoch": 0.9299363057324841,517      "grad_norm": 1.5974193238698267,518      "learning_rate": 4.6496815286624205e-07,519      "loss": 1.5202,520      "step": 730521    },522    {523      "epoch": 0.9426751592356688,524      "grad_norm": 1.619176263750235,525      "learning_rate": 4.713375796178344e-07,526      "loss": 1.4972,527      "step": 740528    },529    {530      "epoch": 0.9554140127388535,531      "grad_norm": 1.5369589866278408,532      "learning_rate": 4.777070063694267e-07,533      "loss": 1.4748,534      "step": 750535    },536    {537      "epoch": 0.9681528662420382,538      "grad_norm": 1.7257692046855166,539      "learning_rate": 4.840764331210191e-07,540      "loss": 1.5267,541      "step": 760542    },543    {544      "epoch": 0.9808917197452229,545      "grad_norm": 2.1407422935686338,546      "learning_rate": 4.904458598726115e-07,547      "loss": 1.5097,548      "step": 770549    },550    {551      "epoch": 0.9936305732484076,552      "grad_norm": 1.9406879702100648,553      "learning_rate": 4.968152866242038e-07,554      "loss": 1.511,555      "step": 780556    },557    {558      "epoch": 1.0063694267515924,559      "grad_norm": 1.439554415506634,560      "learning_rate": 5.031847133757962e-07,561      "loss": 1.5122,562      "step": 790563    },564    {565      "epoch": 1.019108280254777,566      "grad_norm": 1.5106128675527724,567      "learning_rate": 5.095541401273885e-07,568      "loss": 1.4956,569      "step": 800570    },571    {572      "epoch": 1.0318471337579618,573      "grad_norm": 1.6554308659382122,574      "learning_rate": 5.159235668789809e-07,575      "loss": 1.5018,576      "step": 810577    },578    {579      "epoch": 1.0445859872611465,580      "grad_norm": 2.026680377715203,581      "learning_rate": 5.222929936305732e-07,582      "loss": 1.4776,583      "step": 820584    },585    {586      "epoch": 1.0573248407643312,587      "grad_norm": 1.5139010788192246,588      "learning_rate": 5.286624203821656e-07,589      "loss": 1.4545,590      "step": 830591    },592    {593      "epoch": 1.070063694267516,594      "grad_norm": 1.4273185604405294,595      "learning_rate": 5.350318471337579e-07,596      "loss": 1.4834,597      "step": 840598    },599    {600      "epoch": 1.0828025477707006,601      "grad_norm": 1.4905172698067897,602      "learning_rate": 5.414012738853503e-07,603      "loss": 1.5482,604      "step": 850605    },606    {607      "epoch": 1.0955414012738853,608      "grad_norm": 1.507962232188269,609      "learning_rate": 5.477707006369426e-07,610      "loss": 1.4802,611      "step": 860612    },613    {614      "epoch": 1.10828025477707,615      "grad_norm": 1.738422445567781,616      "learning_rate": 5.54140127388535e-07,617      "loss": 1.5378,618      "step": 870619    },620    {621      "epoch": 1.1210191082802548,622      "grad_norm": 1.4572453197036355,623      "learning_rate": 5.605095541401273e-07,624      "loss": 1.5151,625      "step": 880626    },627    {628      "epoch": 1.1337579617834395,629      "grad_norm": 2.003605940138242,630      "learning_rate": 5.668789808917197e-07,631      "loss": 1.4804,632      "step": 890633    },634    {635      "epoch": 1.1464968152866242,636      "grad_norm": 1.6149829006958483,637      "learning_rate": 5.73248407643312e-07,638      "loss": 1.5131,639      "step": 900640    },641    {642      "epoch": 1.1592356687898089,643      "grad_norm": 1.6728742331262298,644      "learning_rate": 5.796178343949044e-07,645      "loss": 1.5034,646      "step": 910647    },648    {649      "epoch": 1.1719745222929936,650      "grad_norm": 1.5431486794721163,651      "learning_rate": 5.859872611464968e-07,652      "loss": 1.5124,653      "step": 920654    },655    {656      "epoch": 1.1847133757961783,657      "grad_norm": 1.6476023906777157,658      "learning_rate": 5.923566878980892e-07,659      "loss": 1.4764,660      "step": 930661    },662    {663      "epoch": 1.197452229299363,664      "grad_norm": 1.6894401103415613,665      "learning_rate": 5.987261146496815e-07,666      "loss": 1.5029,667      "step": 940668    },669    {670      "epoch": 1.2101910828025477,671      "grad_norm": 1.6691648931963563,672      "learning_rate": 6.050955414012739e-07,673      "loss": 1.4969,674      "step": 950675    },676    {677      "epoch": 1.2229299363057324,678      "grad_norm": 2.051456115160016,679      "learning_rate": 6.114649681528662e-07,680      "loss": 1.4744,681      "step": 960682    },683    {684      "epoch": 1.2356687898089171,685      "grad_norm": 2.1062990461224245,686      "learning_rate": 6.178343949044586e-07,687      "loss": 1.4882,688      "step": 970689    },690    {691      "epoch": 1.2484076433121019,692      "grad_norm": 1.6527758494430145,693      "learning_rate": 6.242038216560509e-07,694      "loss": 1.4664,695      "step": 980696    },697    {698      "epoch": 1.2611464968152866,699      "grad_norm": 1.4778661306564593,700      "learning_rate": 6.305732484076433e-07,701      "loss": 1.5409,702      "step": 990703    },704    {705      "epoch": 1.2738853503184713,706      "grad_norm": 1.635617614245788,707      "learning_rate": 6.369426751592356e-07,708      "loss": 1.4478,709      "step": 1000710    }711  ],712  "logging_steps": 10,713  "max_steps": 15700,714  "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": 152037753618432.0,730  "train_batch_size": 2,731  "trial_name": null,732  "trial_params": null733}734