Team Ai
Modelpublic

rsh-raj/codellama-monolith-commit-msg

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes9downloads
trainer_state.json524 linesDownload Raw Back to root
1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 5.0,5  "eval_steps": 500,6  "global_step": 700,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.07142857142857142,13      "grad_norm": 0.1414046734571457,14      "learning_rate": 9.928057553956835e-05,15      "loss": 1.1265,16      "step": 1017    },18    {19      "epoch": 0.14285714285714285,20      "grad_norm": 0.23442833125591278,21      "learning_rate": 9.784172661870504e-05,22      "loss": 0.8753,23      "step": 2024    },25    {26      "epoch": 0.21428571428571427,27      "grad_norm": 0.11814242601394653,28      "learning_rate": 9.640287769784174e-05,29      "loss": 0.5855,30      "step": 3031    },32    {33      "epoch": 0.2857142857142857,34      "grad_norm": 0.05237620323896408,35      "learning_rate": 9.496402877697842e-05,36      "loss": 0.4907,37      "step": 4038    },39    {40      "epoch": 0.35714285714285715,41      "grad_norm": 0.05932621285319328,42      "learning_rate": 9.35251798561151e-05,43      "loss": 0.4305,44      "step": 5045    },46    {47      "epoch": 0.42857142857142855,48      "grad_norm": 0.04958653822541237,49      "learning_rate": 9.20863309352518e-05,50      "loss": 0.5171,51      "step": 6052    },53    {54      "epoch": 0.5,55      "grad_norm": 0.048759087920188904,56      "learning_rate": 9.06474820143885e-05,57      "loss": 0.4467,58      "step": 7059    },60    {61      "epoch": 0.5714285714285714,62      "grad_norm": 0.05054762214422226,63      "learning_rate": 8.920863309352519e-05,64      "loss": 0.4075,65      "step": 8066    },67    {68      "epoch": 0.6428571428571429,69      "grad_norm": 0.06276834011077881,70      "learning_rate": 8.776978417266187e-05,71      "loss": 0.4623,72      "step": 9073    },74    {75      "epoch": 0.7142857142857143,76      "grad_norm": 0.07741520553827286,77      "learning_rate": 8.633093525179857e-05,78      "loss": 0.4436,79      "step": 10080    },81    {82      "epoch": 0.7857142857142857,83      "grad_norm": 0.1285954713821411,84      "learning_rate": 8.489208633093527e-05,85      "loss": 0.4712,86      "step": 11087    },88    {89      "epoch": 0.8571428571428571,90      "grad_norm": 0.05844992771744728,91      "learning_rate": 8.345323741007195e-05,92      "loss": 0.4982,93      "step": 12094    },95    {96      "epoch": 0.9285714285714286,97      "grad_norm": 0.052849628031253815,98      "learning_rate": 8.201438848920863e-05,99      "loss": 0.447,100      "step": 130101    },102    {103      "epoch": 1.0,104      "grad_norm": 0.0573391392827034,105      "learning_rate": 8.057553956834533e-05,106      "loss": 0.4372,107      "step": 140108    },109    {110      "epoch": 1.0714285714285714,111      "grad_norm": 0.05234351009130478,112      "learning_rate": 7.913669064748202e-05,113      "loss": 0.4513,114      "step": 150115    },116    {117      "epoch": 1.1428571428571428,118      "grad_norm": 0.06302867084741592,119      "learning_rate": 7.769784172661872e-05,120      "loss": 0.411,121      "step": 160122    },123    {124      "epoch": 1.2142857142857142,125      "grad_norm": 0.0785873532295227,126      "learning_rate": 7.62589928057554e-05,127      "loss": 0.4484,128      "step": 170129    },130    {131      "epoch": 1.2857142857142856,132      "grad_norm": 0.07119076699018478,133      "learning_rate": 7.48201438848921e-05,134      "loss": 0.4424,135      "step": 180136    },137    {138      "epoch": 1.3571428571428572,139      "grad_norm": 0.06240012124180794,140      "learning_rate": 7.338129496402878e-05,141      "loss": 0.4841,142      "step": 190143    },144    {145      "epoch": 1.4285714285714286,146      "grad_norm": 0.07473210990428925,147      "learning_rate": 7.194244604316547e-05,148      "loss": 0.4021,149      "step": 200150    },151    {152      "epoch": 1.5,153      "grad_norm": 0.07750649005174637,154      "learning_rate": 7.050359712230215e-05,155      "loss": 0.4076,156      "step": 210157    },158    {159      "epoch": 1.5714285714285714,160      "grad_norm": 0.06524751335382462,161      "learning_rate": 6.906474820143886e-05,162      "loss": 0.4115,163      "step": 220164    },165    {166      "epoch": 1.6428571428571428,167      "grad_norm": 0.07310232520103455,168      "learning_rate": 6.762589928057555e-05,169      "loss": 0.427,170      "step": 230171    },172    {173      "epoch": 1.7142857142857144,174      "grad_norm": 0.0707428976893425,175      "learning_rate": 6.618705035971223e-05,176      "loss": 0.4553,177      "step": 240178    },179    {180      "epoch": 1.7857142857142856,181      "grad_norm": 0.07167942821979523,182      "learning_rate": 6.474820143884892e-05,183      "loss": 0.403,184      "step": 250185    },186    {187      "epoch": 1.8571428571428572,188      "grad_norm": 0.07124218344688416,189      "learning_rate": 6.330935251798561e-05,190      "loss": 0.4217,191      "step": 260192    },193    {194      "epoch": 1.9285714285714286,195      "grad_norm": 0.07448463141918182,196      "learning_rate": 6.187050359712231e-05,197      "loss": 0.4838,198      "step": 270199    },200    {201      "epoch": 2.0,202      "grad_norm": 0.07304704189300537,203      "learning_rate": 6.0431654676258996e-05,204      "loss": 0.421,205      "step": 280206    },207    {208      "epoch": 2.0714285714285716,209      "grad_norm": 0.07001727819442749,210      "learning_rate": 5.899280575539569e-05,211      "loss": 0.4143,212      "step": 290213    },214    {215      "epoch": 2.142857142857143,216      "grad_norm": 0.06686381250619888,217      "learning_rate": 5.755395683453237e-05,218      "loss": 0.4003,219      "step": 300220    },221    {222      "epoch": 2.2142857142857144,223      "grad_norm": 0.08049935102462769,224      "learning_rate": 5.611510791366906e-05,225      "loss": 0.4134,226      "step": 310227    },228    {229      "epoch": 2.2857142857142856,230      "grad_norm": 0.08297842741012573,231      "learning_rate": 5.467625899280576e-05,232      "loss": 0.4763,233      "step": 320234    },235    {236      "epoch": 2.357142857142857,237      "grad_norm": 0.08368254452943802,238      "learning_rate": 5.323741007194245e-05,239      "loss": 0.3781,240      "step": 330241    },242    {243      "epoch": 2.4285714285714284,244      "grad_norm": 0.09217505902051926,245      "learning_rate": 5.179856115107914e-05,246      "loss": 0.4143,247      "step": 340248    },249    {250      "epoch": 2.5,251      "grad_norm": 0.08572608232498169,252      "learning_rate": 5.035971223021583e-05,253      "loss": 0.4013,254      "step": 350255    },256    {257      "epoch": 2.571428571428571,258      "grad_norm": 0.08441212773323059,259      "learning_rate": 4.892086330935252e-05,260      "loss": 0.4087,261      "step": 360262    },263    {264      "epoch": 2.642857142857143,265      "grad_norm": 0.09245694428682327,266      "learning_rate": 4.748201438848921e-05,267      "loss": 0.4241,268      "step": 370269    },270    {271      "epoch": 2.7142857142857144,272      "grad_norm": 0.08556502312421799,273      "learning_rate": 4.60431654676259e-05,274      "loss": 0.4143,275      "step": 380276    },277    {278      "epoch": 2.7857142857142856,279      "grad_norm": 0.0849672332406044,280      "learning_rate": 4.460431654676259e-05,281      "loss": 0.4039,282      "step": 390283    },284    {285      "epoch": 2.857142857142857,286      "grad_norm": 0.10437279939651489,287      "learning_rate": 4.3165467625899284e-05,288      "loss": 0.4391,289      "step": 400290    },291    {292      "epoch": 2.928571428571429,293      "grad_norm": 0.09709574282169342,294      "learning_rate": 4.1726618705035975e-05,295      "loss": 0.3981,296      "step": 410297    },298    {299      "epoch": 3.0,300      "grad_norm": 0.1039663776755333,301      "learning_rate": 4.0287769784172666e-05,302      "loss": 0.4035,303      "step": 420304    },305    {306      "epoch": 3.0714285714285716,307      "grad_norm": 0.10183094441890717,308      "learning_rate": 3.884892086330936e-05,309      "loss": 0.3663,310      "step": 430311    },312    {313      "epoch": 3.142857142857143,314      "grad_norm": 0.09032372385263443,315      "learning_rate": 3.741007194244605e-05,316      "loss": 0.4241,317      "step": 440318    },319    {320      "epoch": 3.2142857142857144,321      "grad_norm": 0.09723355621099472,322      "learning_rate": 3.597122302158273e-05,323      "loss": 0.4014,324      "step": 450325    },326    {327      "epoch": 3.2857142857142856,328      "grad_norm": 0.11320160329341888,329      "learning_rate": 3.453237410071943e-05,330      "loss": 0.405,331      "step": 460332    },333    {334      "epoch": 3.357142857142857,335      "grad_norm": 0.10981149971485138,336      "learning_rate": 3.3093525179856116e-05,337      "loss": 0.3951,338      "step": 470339    },340    {341      "epoch": 3.4285714285714284,342      "grad_norm": 0.11303650587797165,343      "learning_rate": 3.165467625899281e-05,344      "loss": 0.4026,345      "step": 480346    },347    {348      "epoch": 3.5,349      "grad_norm": 0.1161050871014595,350      "learning_rate": 3.0215827338129498e-05,351      "loss": 0.384,352      "step": 490353    },354    {355      "epoch": 3.571428571428571,356      "grad_norm": 0.10942329466342926,357      "learning_rate": 2.8776978417266186e-05,358      "loss": 0.4008,359      "step": 500360    },361    {362      "epoch": 3.642857142857143,363      "grad_norm": 0.10819849371910095,364      "learning_rate": 2.733812949640288e-05,365      "loss": 0.3774,366      "step": 510367    },368    {369      "epoch": 3.7142857142857144,370      "grad_norm": 0.11515466868877411,371      "learning_rate": 2.589928057553957e-05,372      "loss": 0.3936,373      "step": 520374    },375    {376      "epoch": 3.7857142857142856,377      "grad_norm": 0.12771977484226227,378      "learning_rate": 2.446043165467626e-05,379      "loss": 0.4261,380      "step": 530381    },382    {383      "epoch": 3.857142857142857,384      "grad_norm": 0.20400740206241608,385      "learning_rate": 2.302158273381295e-05,386      "loss": 0.3877,387      "step": 540388    },389    {390      "epoch": 3.928571428571429,391      "grad_norm": 0.12298396229743958,392      "learning_rate": 2.1582733812949642e-05,393      "loss": 0.4114,394      "step": 550395    },396    {397      "epoch": 4.0,398      "grad_norm": 0.10772908478975296,399      "learning_rate": 2.0143884892086333e-05,400      "loss": 0.3973,401      "step": 560402    },403    {404      "epoch": 4.071428571428571,405      "grad_norm": 0.1267159879207611,406      "learning_rate": 1.8705035971223024e-05,407      "loss": 0.3852,408      "step": 570409    },410    {411      "epoch": 4.142857142857143,412      "grad_norm": 0.15349607169628143,413      "learning_rate": 1.7266187050359716e-05,414      "loss": 0.3799,415      "step": 580416    },417    {418      "epoch": 4.214285714285714,419      "grad_norm": 0.1264091581106186,420      "learning_rate": 1.5827338129496403e-05,421      "loss": 0.4209,422      "step": 590423    },424    {425      "epoch": 4.285714285714286,426      "grad_norm": 0.13532622158527374,427      "learning_rate": 1.4388489208633093e-05,428      "loss": 0.4079,429      "step": 600430    },431    {432      "epoch": 4.357142857142857,433      "grad_norm": 0.13242410123348236,434      "learning_rate": 1.2949640287769784e-05,435      "loss": 0.36,436      "step": 610437    },438    {439      "epoch": 4.428571428571429,440      "grad_norm": 0.13940675556659698,441      "learning_rate": 1.1510791366906475e-05,442      "loss": 0.3692,443      "step": 620444    },445    {446      "epoch": 4.5,447      "grad_norm": 0.12690038979053497,448      "learning_rate": 1.0071942446043167e-05,449      "loss": 0.4025,450      "step": 630451    },452    {453      "epoch": 4.571428571428571,454      "grad_norm": 0.12537573277950287,455      "learning_rate": 8.633093525179858e-06,456      "loss": 0.3709,457      "step": 640458    },459    {460      "epoch": 4.642857142857143,461      "grad_norm": 0.13673488795757294,462      "learning_rate": 7.1942446043165465e-06,463      "loss": 0.4176,464      "step": 650465    },466    {467      "epoch": 4.714285714285714,468      "grad_norm": 0.1424897164106369,469      "learning_rate": 5.755395683453238e-06,470      "loss": 0.4099,471      "step": 660472    },473    {474      "epoch": 4.785714285714286,475      "grad_norm": 0.11409413069486618,476      "learning_rate": 4.316546762589929e-06,477      "loss": 0.3672,478      "step": 670479    },480    {481      "epoch": 4.857142857142857,482      "grad_norm": 0.12917353212833405,483      "learning_rate": 2.877697841726619e-06,484      "loss": 0.3525,485      "step": 680486    },487    {488      "epoch": 4.928571428571429,489      "grad_norm": 0.1459251493215561,490      "learning_rate": 1.4388489208633094e-06,491      "loss": 0.372,492      "step": 690493    },494    {495      "epoch": 5.0,496      "grad_norm": 0.15281479060649872,497      "learning_rate": 0.0,498      "loss": 0.3442,499      "step": 700500    }501  ],502  "logging_steps": 10,503  "max_steps": 700,504  "num_input_tokens_seen": 0,505  "num_train_epochs": 5,506  "save_steps": 500,507  "stateful_callbacks": {508    "TrainerControl": {509      "args": {510        "should_epoch_stop": false,511        "should_evaluate": false,512        "should_log": false,513        "should_save": true,514        "should_training_stop": true515      },516      "attributes": {}517    }518  },519  "total_flos": 5.7068354857181184e+17,520  "train_batch_size": 10,521  "trial_name": null,522  "trial_params": null523}524