Team Ai
Modelpublic

dzungpham/graphcodebert-code-classification

sourceHugging Facemitupdated 5mo agoView on Hugging Face
0likes
trainer_state.json604 linesDownload Raw Back to checkpoint-800
1{2  "best_global_step": null,3  "best_metric": null,4  "best_model_checkpoint": null,5  "epoch": 0.0512,6  "eval_steps": 1000,7  "global_step": 800,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 0.00064,14      "grad_norm": 1.6144306659698486,15      "learning_rate": 1.1520000000000002e-08,16      "loss": 0.729,17      "step": 1018    },19    {20      "epoch": 0.00128,21      "grad_norm": 2.0952296257019043,22      "learning_rate": 2.4320000000000002e-08,23      "loss": 0.7295,24      "step": 2025    },26    {27      "epoch": 0.00192,28      "grad_norm": 1.3587689399719238,29      "learning_rate": 3.7120000000000004e-08,30      "loss": 0.73,31      "step": 3032    },33    {34      "epoch": 0.00256,35      "grad_norm": 1.2531732320785522,36      "learning_rate": 4.9920000000000006e-08,37      "loss": 0.7221,38      "step": 4039    },40    {41      "epoch": 0.0032,42      "grad_norm": 1.437932014465332,43      "learning_rate": 6.272000000000001e-08,44      "loss": 0.7209,45      "step": 5046    },47    {48      "epoch": 0.00384,49      "grad_norm": 1.418426752090454,50      "learning_rate": 7.552e-08,51      "loss": 0.729,52      "step": 6053    },54    {55      "epoch": 0.00448,56      "grad_norm": 1.9476298093795776,57      "learning_rate": 8.832e-08,58      "loss": 0.7242,59      "step": 7060    },61    {62      "epoch": 0.00512,63      "grad_norm": 1.7948051691055298,64      "learning_rate": 1.0112000000000001e-07,65      "loss": 0.7227,66      "step": 8067    },68    {69      "epoch": 0.00576,70      "grad_norm": 1.6534360647201538,71      "learning_rate": 1.1392e-07,72      "loss": 0.7234,73      "step": 9074    },75    {76      "epoch": 0.0064,77      "grad_norm": 1.0920158624649048,78      "learning_rate": 1.2672e-07,79      "loss": 0.7328,80      "step": 10081    },82    {83      "epoch": 0.00704,84      "grad_norm": 1.977837085723877,85      "learning_rate": 1.3952000000000002e-07,86      "loss": 0.7263,87      "step": 11088    },89    {90      "epoch": 0.00768,91      "grad_norm": 1.388983130455017,92      "learning_rate": 1.5232000000000003e-07,93      "loss": 0.7286,94      "step": 12095    },96    {97      "epoch": 0.00832,98      "grad_norm": 1.2956682443618774,99      "learning_rate": 1.6512e-07,100      "loss": 0.7251,101      "step": 130102    },103    {104      "epoch": 0.00896,105      "grad_norm": 1.8125052452087402,106      "learning_rate": 1.7792e-07,107      "loss": 0.7251,108      "step": 140109    },110    {111      "epoch": 0.0096,112      "grad_norm": 1.626846194267273,113      "learning_rate": 1.9072e-07,114      "loss": 0.727,115      "step": 150116    },117    {118      "epoch": 0.01024,119      "grad_norm": 2.3243086338043213,120      "learning_rate": 2.0352e-07,121      "loss": 0.726,122      "step": 160123    },124    {125      "epoch": 0.01088,126      "grad_norm": 1.4734737873077393,127      "learning_rate": 2.1632e-07,128      "loss": 0.7252,129      "step": 170130    },131    {132      "epoch": 0.01152,133      "grad_norm": 2.090498685836792,134      "learning_rate": 2.2912e-07,135      "loss": 0.7273,136      "step": 180137    },138    {139      "epoch": 0.01216,140      "grad_norm": 1.7563093900680542,141      "learning_rate": 2.4192000000000004e-07,142      "loss": 0.719,143      "step": 190144    },145    {146      "epoch": 0.0128,147      "grad_norm": 1.449843168258667,148      "learning_rate": 2.5472000000000005e-07,149      "loss": 0.7237,150      "step": 200151    },152    {153      "epoch": 0.01344,154      "grad_norm": 144219.625,155      "learning_rate": 5.350742447516642e-07,156      "loss": 0.7218,157      "step": 210158    },159    {160      "epoch": 0.01408,161      "grad_norm": 105046.0234375,162      "learning_rate": 5.606758832565284e-07,163      "loss": 0.718,164      "step": 220165    },166    {167      "epoch": 0.01472,168      "grad_norm": 126142.4296875,169      "learning_rate": 5.862775217613928e-07,170      "loss": 0.7107,171      "step": 230172    },173    {174      "epoch": 0.01536,175      "grad_norm": 92423.2265625,176      "learning_rate": 6.118791602662571e-07,177      "loss": 0.7271,178      "step": 240179    },180    {181      "epoch": 0.016,182      "grad_norm": 98091.828125,183      "learning_rate": 6.374807987711214e-07,184      "loss": 0.7123,185      "step": 250186    },187    {188      "epoch": 0.01664,189      "grad_norm": 131949.578125,190      "learning_rate": 6.630824372759858e-07,191      "loss": 0.7204,192      "step": 260193    },194    {195      "epoch": 0.01728,196      "grad_norm": 112228.5625,197      "learning_rate": 6.8868407578085e-07,198      "loss": 0.722,199      "step": 270200    },201    {202      "epoch": 0.01792,203      "grad_norm": 64587.734375,204      "learning_rate": 7.142857142857143e-07,205      "loss": 0.7263,206      "step": 280207    },208    {209      "epoch": 0.01856,210      "grad_norm": 99893.203125,211      "learning_rate": 7.398873527905787e-07,212      "loss": 0.7169,213      "step": 290214    },215    {216      "epoch": 0.0192,217      "grad_norm": 135749.875,218      "learning_rate": 7.65488991295443e-07,219      "loss": 0.7122,220      "step": 300221    },222    {223      "epoch": 0.01984,224      "grad_norm": 103292.5703125,225      "learning_rate": 7.910906298003073e-07,226      "loss": 0.7183,227      "step": 310228    },229    {230      "epoch": 0.02048,231      "grad_norm": 86927.28125,232      "learning_rate": 8.166922683051716e-07,233      "loss": 0.7192,234      "step": 320235    },236    {237      "epoch": 0.02112,238      "grad_norm": 153738.390625,239      "learning_rate": 8.422939068100359e-07,240      "loss": 0.711,241      "step": 330242    },243    {244      "epoch": 0.02176,245      "grad_norm": 69994.7734375,246      "learning_rate": 8.678955453149002e-07,247      "loss": 0.7176,248      "step": 340249    },250    {251      "epoch": 0.0224,252      "grad_norm": 141370.6875,253      "learning_rate": 8.934971838197646e-07,254      "loss": 0.7105,255      "step": 350256    },257    {258      "epoch": 0.02304,259      "grad_norm": 71139.453125,260      "learning_rate": 9.190988223246289e-07,261      "loss": 0.7126,262      "step": 360263    },264    {265      "epoch": 0.02368,266      "grad_norm": 82039.1953125,267      "learning_rate": 9.447004608294931e-07,268      "loss": 0.7078,269      "step": 370270    },271    {272      "epoch": 0.02432,273      "grad_norm": 71275.7890625,274      "learning_rate": 9.703020993343575e-07,275      "loss": 0.7145,276      "step": 380277    },278    {279      "epoch": 0.02496,280      "grad_norm": 145801.21875,281      "learning_rate": 9.959037378392218e-07,282      "loss": 0.7102,283      "step": 390284    },285    {286      "epoch": 0.0256,287      "grad_norm": 171507.0,288      "learning_rate": 1.021505376344086e-06,289      "loss": 0.7123,290      "step": 400291    },292    {293      "epoch": 0.02624,294      "grad_norm": 79134.203125,295      "learning_rate": 1.0471070148489503e-06,296      "loss": 0.7083,297      "step": 410298    },299    {300      "epoch": 0.02688,301      "grad_norm": 69231.640625,302      "learning_rate": 1.0727086533538148e-06,303      "loss": 0.7105,304      "step": 420305    },306    {307      "epoch": 0.02752,308      "grad_norm": 113099.3984375,309      "learning_rate": 1.0983102918586791e-06,310      "loss": 0.7141,311      "step": 430312    },313    {314      "epoch": 0.02816,315      "grad_norm": 121013.734375,316      "learning_rate": 1.1239119303635434e-06,317      "loss": 0.7146,318      "step": 440319    },320    {321      "epoch": 0.0288,322      "grad_norm": 89184.609375,323      "learning_rate": 1.1495135688684077e-06,324      "loss": 0.7133,325      "step": 450326    },327    {328      "epoch": 0.02944,329      "grad_norm": 176246.890625,330      "learning_rate": 1.175115207373272e-06,331      "loss": 0.7086,332      "step": 460333    },334    {335      "epoch": 0.03008,336      "grad_norm": 88161.2265625,337      "learning_rate": 1.2007168458781362e-06,338      "loss": 0.709,339      "step": 470340    },341    {342      "epoch": 0.03072,343      "grad_norm": 74441.015625,344      "learning_rate": 1.2263184843830007e-06,345      "loss": 0.7023,346      "step": 480347    },348    {349      "epoch": 0.03136,350      "grad_norm": 96409.40625,351      "learning_rate": 1.251920122887865e-06,352      "loss": 0.715,353      "step": 490354    },355    {356      "epoch": 0.032,357      "grad_norm": 81090.6484375,358      "learning_rate": 1.2775217613927293e-06,359      "loss": 0.7109,360      "step": 500361    },362    {363      "epoch": 0.03264,364      "grad_norm": 98153.8828125,365      "learning_rate": 1.3031233998975938e-06,366      "loss": 0.7092,367      "step": 510368    },369    {370      "epoch": 0.03328,371      "grad_norm": 78782.546875,372      "learning_rate": 1.3287250384024578e-06,373      "loss": 0.7048,374      "step": 520375    },376    {377      "epoch": 0.03392,378      "grad_norm": 110360.5,379      "learning_rate": 1.354326676907322e-06,380      "loss": 0.7108,381      "step": 530382    },383    {384      "epoch": 0.03456,385      "grad_norm": 88462.0703125,386      "learning_rate": 1.3799283154121864e-06,387      "loss": 0.7041,388      "step": 540389    },390    {391      "epoch": 0.0352,392      "grad_norm": 97624.7421875,393      "learning_rate": 1.4055299539170509e-06,394      "loss": 0.7114,395      "step": 550396    },397    {398      "epoch": 0.03584,399      "grad_norm": 99471.4375,400      "learning_rate": 1.4311315924219151e-06,401      "loss": 0.7191,402      "step": 560403    },404    {405      "epoch": 0.03648,406      "grad_norm": 79087.90625,407      "learning_rate": 1.4567332309267796e-06,408      "loss": 0.7022,409      "step": 570410    },411    {412      "epoch": 0.03712,413      "grad_norm": 65275.0,414      "learning_rate": 1.4823348694316437e-06,415      "loss": 0.7088,416      "step": 580417    },418    {419      "epoch": 0.03776,420      "grad_norm": 153826.28125,421      "learning_rate": 1.507936507936508e-06,422      "loss": 0.7079,423      "step": 590424    },425    {426      "epoch": 0.0384,427      "grad_norm": 64280.38671875,428      "learning_rate": 1.5335381464413722e-06,429      "loss": 0.7018,430      "step": 600431    },432    {433      "epoch": 0.03904,434      "grad_norm": 65060.80078125,435      "learning_rate": 1.5591397849462367e-06,436      "loss": 0.7027,437      "step": 610438    },439    {440      "epoch": 0.03968,441      "grad_norm": 77339.2890625,442      "learning_rate": 1.584741423451101e-06,443      "loss": 0.7038,444      "step": 620445    },446    {447      "epoch": 0.04032,448      "grad_norm": 123140.5546875,449      "learning_rate": 1.6103430619559655e-06,450      "loss": 0.7019,451      "step": 630452    },453    {454      "epoch": 0.04096,455      "grad_norm": 67502.71875,456      "learning_rate": 1.6359447004608298e-06,457      "loss": 0.7094,458      "step": 640459    },460    {461      "epoch": 0.0416,462      "grad_norm": 95452.1796875,463      "learning_rate": 1.6615463389656938e-06,464      "loss": 0.6998,465      "step": 650466    },467    {468      "epoch": 0.04224,469      "grad_norm": 68556.421875,470      "learning_rate": 1.6871479774705581e-06,471      "loss": 0.694,472      "step": 660473    },474    {475      "epoch": 0.04288,476      "grad_norm": 78265.8046875,477      "learning_rate": 1.7127496159754226e-06,478      "loss": 0.7051,479      "step": 670480    },481    {482      "epoch": 0.04352,483      "grad_norm": 93559.3359375,484      "learning_rate": 1.7383512544802869e-06,485      "loss": 0.6997,486      "step": 680487    },488    {489      "epoch": 0.04416,490      "grad_norm": 88091.9375,491      "learning_rate": 1.7639528929851512e-06,492      "loss": 0.6963,493      "step": 690494    },495    {496      "epoch": 0.0448,497      "grad_norm": 73024.359375,498      "learning_rate": 1.7895545314900157e-06,499      "loss": 0.7021,500      "step": 700501    },502    {503      "epoch": 0.04544,504      "grad_norm": 100058.2890625,505      "learning_rate": 1.8151561699948797e-06,506      "loss": 0.7022,507      "step": 710508    },509    {510      "epoch": 0.04608,511      "grad_norm": 99197.1953125,512      "learning_rate": 1.840757808499744e-06,513      "loss": 0.7017,514      "step": 720515    },516    {517      "epoch": 0.04672,518      "grad_norm": 102018.984375,519      "learning_rate": 1.8663594470046085e-06,520      "loss": 0.6985,521      "step": 730522    },523    {524      "epoch": 0.04736,525      "grad_norm": 101586.0234375,526      "learning_rate": 1.8919610855094728e-06,527      "loss": 0.6991,528      "step": 740529    },530    {531      "epoch": 0.048,532      "grad_norm": 151948.25,533      "learning_rate": 1.9175627240143373e-06,534      "loss": 0.6977,535      "step": 750536    },537    {538      "epoch": 0.04864,539      "grad_norm": 88698.7109375,540      "learning_rate": 1.9431643625192015e-06,541      "loss": 0.6961,542      "step": 760543    },544    {545      "epoch": 0.04928,546      "grad_norm": 82451.9296875,547      "learning_rate": 1.9687660010240654e-06,548      "loss": 0.6898,549      "step": 770550    },551    {552      "epoch": 0.04992,553      "grad_norm": 82236.453125,554      "learning_rate": 1.99436763952893e-06,555      "loss": 0.6886,556      "step": 780557    },558    {559      "epoch": 0.05056,560      "grad_norm": 155064.484375,561      "learning_rate": 2.0199692780337944e-06,562      "loss": 0.6921,563      "step": 790564    },565    {566      "epoch": 0.0512,567      "grad_norm": 72238.6328125,568      "learning_rate": 2.0455709165386586e-06,569      "loss": 0.6932,570      "step": 800571    }572  ],573  "logging_steps": 10,574  "max_steps": 78125,575  "num_input_tokens_seen": 0,576  "num_train_epochs": 5,577  "save_steps": 200,578  "stateful_callbacks": {579    "EarlyStoppingCallback": {580      "args": {581        "early_stopping_patience": 3,582        "early_stopping_threshold": 0.0583      },584      "attributes": {585        "early_stopping_patience_counter": 0586      }587    },588    "TrainerControl": {589      "args": {590        "should_epoch_stop": false,591        "should_evaluate": false,592        "should_log": false,593        "should_save": true,594        "should_training_stop": false595      },596      "attributes": {}597    }598  },599  "total_flos": 6733455906568320.0,600  "train_batch_size": 32,601  "trial_name": null,602  "trial_params": null603}604