Team Ai
Modelpublic

dzungpham/graphcodebert-code-classification

sourceHugging Facemitupdated 5mo agoView on Hugging Face
0likes
trainer_state.json536 linesDownload Raw Back to checkpoint-300
1{2  "best_global_step": 200,3  "best_metric": 0.5962545254252696,4  "best_model_checkpoint": "output_checkpoints/graphcodebert-vanilla/checkpoint-200",5  "epoch": 0.29354207436399216,6  "eval_steps": 50,7  "global_step": 300,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 0.004892367906066536,14      "grad_norm": 33435.953125,15      "learning_rate": 1.3071895424836603e-07,16      "loss": 0.7006,17      "step": 518    },19    {20      "epoch": 0.009784735812133072,21      "grad_norm": 34831.7421875,22      "learning_rate": 2.9411764705882356e-07,23      "loss": 0.7023,24      "step": 1025    },26    {27      "epoch": 0.014677103718199608,28      "grad_norm": 32986.62109375,29      "learning_rate": 4.5751633986928105e-07,30      "loss": 0.7019,31      "step": 1532    },33    {34      "epoch": 0.019569471624266144,35      "grad_norm": 34257.4921875,36      "learning_rate": 6.209150326797386e-07,37      "loss": 0.7025,38      "step": 2039    },40    {41      "epoch": 0.02446183953033268,42      "grad_norm": 35511.3359375,43      "learning_rate": 7.843137254901962e-07,44      "loss": 0.7032,45      "step": 2546    },47    {48      "epoch": 0.029354207436399216,49      "grad_norm": 33043.3515625,50      "learning_rate": 9.477124183006536e-07,51      "loss": 0.6968,52      "step": 3053    },54    {55      "epoch": 0.03424657534246575,56      "grad_norm": 38538.30078125,57      "learning_rate": 1.111111111111111e-06,58      "loss": 0.6992,59      "step": 3560    },61    {62      "epoch": 0.03913894324853229,63      "grad_norm": 43255.37890625,64      "learning_rate": 1.2745098039215686e-06,65      "loss": 0.6991,66      "step": 4067    },68    {69      "epoch": 0.04403131115459882,70      "grad_norm": 34170.8046875,71      "learning_rate": 1.4379084967320261e-06,72      "loss": 0.6996,73      "step": 4574    },75    {76      "epoch": 0.04892367906066536,77      "grad_norm": 35399.70703125,78      "learning_rate": 1.6013071895424837e-06,79      "loss": 0.6937,80      "step": 5081    },82    {83      "epoch": 0.04892367906066536,84      "eval_accuracy": 0.771,85      "eval_loss": 0.6569265127182007,86      "eval_macro_f1": 0.5082027063884254,87      "eval_precision": 0.6109971743687904,88      "eval_recall": 0.5281120325963375,89      "eval_runtime": 17.5156,90      "eval_samples_per_second": 57.092,91      "eval_steps_per_second": 0.057,92      "step": 5093    },94    {95      "epoch": 0.053816046966731895,96      "grad_norm": 34677.1796875,97      "learning_rate": 1.7647058823529414e-06,98      "loss": 0.6963,99      "step": 55100    },101    {102      "epoch": 0.05870841487279843,103      "grad_norm": 31789.291015625,104      "learning_rate": 1.928104575163399e-06,105      "loss": 0.6971,106      "step": 60107    },108    {109      "epoch": 0.06360078277886497,110      "grad_norm": 30762.345703125,111      "learning_rate": 2.0915032679738565e-06,112      "loss": 0.6946,113      "step": 65114    },115    {116      "epoch": 0.0684931506849315,117      "grad_norm": 29590.083984375,118      "learning_rate": 2.254901960784314e-06,119      "loss": 0.693,120      "step": 70121    },122    {123      "epoch": 0.07338551859099804,124      "grad_norm": 29346.84765625,125      "learning_rate": 2.4183006535947716e-06,126      "loss": 0.6905,127      "step": 75128    },129    {130      "epoch": 0.07827788649706457,131      "grad_norm": 37289.77734375,132      "learning_rate": 2.581699346405229e-06,133      "loss": 0.6942,134      "step": 80135    },136    {137      "epoch": 0.08317025440313111,138      "grad_norm": 33970.94140625,139      "learning_rate": 2.7450980392156867e-06,140      "loss": 0.69,141      "step": 85142    },143    {144      "epoch": 0.08806262230919765,145      "grad_norm": 28671.583984375,146      "learning_rate": 2.9084967320261443e-06,147      "loss": 0.6889,148      "step": 90149    },150    {151      "epoch": 0.09295499021526418,152      "grad_norm": 30156.005859375,153      "learning_rate": 3.071895424836602e-06,154      "loss": 0.6866,155      "step": 95156    },157    {158      "epoch": 0.09784735812133072,159      "grad_norm": 33484.71484375,160      "learning_rate": 3.2352941176470594e-06,161      "loss": 0.6888,162      "step": 100163    },164    {165      "epoch": 0.09784735812133072,166      "eval_accuracy": 0.767,167      "eval_loss": 0.6559821367263794,168      "eval_macro_f1": 0.5260673147136775,169      "eval_precision": 0.6062366452991452,170      "eval_recall": 0.5367285927824044,171      "eval_runtime": 17.3972,172      "eval_samples_per_second": 57.481,173      "eval_steps_per_second": 0.057,174      "step": 100175    },176    {177      "epoch": 0.10273972602739725,178      "grad_norm": 35390.96484375,179      "learning_rate": 3.398692810457517e-06,180      "loss": 0.6893,181      "step": 105182    },183    {184      "epoch": 0.10763209393346379,185      "grad_norm": 34452.11328125,186      "learning_rate": 3.562091503267974e-06,187      "loss": 0.6849,188      "step": 110189    },190    {191      "epoch": 0.11252446183953033,192      "grad_norm": 41847.0625,193      "learning_rate": 3.7254901960784316e-06,194      "loss": 0.6853,195      "step": 115196    },197    {198      "epoch": 0.11741682974559686,199      "grad_norm": 31951.4140625,200      "learning_rate": 3.88888888888889e-06,201      "loss": 0.6802,202      "step": 120203    },204    {205      "epoch": 0.1223091976516634,206      "grad_norm": 34176.79296875,207      "learning_rate": 4.052287581699347e-06,208      "loss": 0.6871,209      "step": 125210    },211    {212      "epoch": 0.12720156555772993,213      "grad_norm": 35482.6640625,214      "learning_rate": 4.215686274509805e-06,215      "loss": 0.6789,216      "step": 130217    },218    {219      "epoch": 0.13209393346379647,220      "grad_norm": 60289.4296875,221      "learning_rate": 4.379084967320262e-06,222      "loss": 0.6844,223      "step": 135224    },225    {226      "epoch": 0.136986301369863,227      "grad_norm": 41964.47265625,228      "learning_rate": 4.542483660130719e-06,229      "loss": 0.6808,230      "step": 140231    },232    {233      "epoch": 0.14187866927592954,234      "grad_norm": 35805.8203125,235      "learning_rate": 4.705882352941177e-06,236      "loss": 0.6748,237      "step": 145238    },239    {240      "epoch": 0.14677103718199608,241      "grad_norm": 25688.607421875,242      "learning_rate": 4.869281045751634e-06,243      "loss": 0.6769,244      "step": 150245    },246    {247      "epoch": 0.14677103718199608,248      "eval_accuracy": 0.728,249      "eval_loss": 0.6580190658569336,250      "eval_macro_f1": 0.5668100015926103,251      "eval_precision": 0.5782073308365263,252      "eval_recall": 0.5627889260176255,253      "eval_runtime": 17.3848,254      "eval_samples_per_second": 57.521,255      "eval_steps_per_second": 0.058,256      "step": 150257    },258    {259      "epoch": 0.15166340508806261,260      "grad_norm": 30171.484375,261      "learning_rate": 5.032679738562092e-06,262      "loss": 0.6706,263      "step": 155264    },265    {266      "epoch": 0.15655577299412915,267      "grad_norm": 29393.716796875,268      "learning_rate": 5.19607843137255e-06,269      "loss": 0.6764,270      "step": 160271    },272    {273      "epoch": 0.16144814090019569,274      "grad_norm": 34377.2578125,275      "learning_rate": 5.359477124183007e-06,276      "loss": 0.6688,277      "step": 165278    },279    {280      "epoch": 0.16634050880626222,281      "grad_norm": 34805.3671875,282      "learning_rate": 5.522875816993465e-06,283      "loss": 0.6673,284      "step": 170285    },286    {287      "epoch": 0.17123287671232876,288      "grad_norm": 29948.095703125,289      "learning_rate": 5.686274509803922e-06,290      "loss": 0.6652,291      "step": 175292    },293    {294      "epoch": 0.1761252446183953,295      "grad_norm": 34735.33984375,296      "learning_rate": 5.84967320261438e-06,297      "loss": 0.6709,298      "step": 180299    },300    {301      "epoch": 0.18101761252446183,302      "grad_norm": 36469.0703125,303      "learning_rate": 6.0130718954248365e-06,304      "loss": 0.6606,305      "step": 185306    },307    {308      "epoch": 0.18590998043052837,309      "grad_norm": 27843.798828125,310      "learning_rate": 6.176470588235295e-06,311      "loss": 0.6666,312      "step": 190313    },314    {315      "epoch": 0.1908023483365949,316      "grad_norm": 27965.966796875,317      "learning_rate": 6.3398692810457515e-06,318      "loss": 0.6626,319      "step": 195320    },321    {322      "epoch": 0.19569471624266144,323      "grad_norm": 28469.09375,324      "learning_rate": 6.5032679738562095e-06,325      "loss": 0.6601,326      "step": 200327    },328    {329      "epoch": 0.19569471624266144,330      "eval_accuracy": 0.698,331      "eval_loss": 0.6574791669845581,332      "eval_macro_f1": 0.5962545254252696,333      "eval_precision": 0.591974921630094,334      "eval_recall": 0.605831327804422,335      "eval_runtime": 17.3909,336      "eval_samples_per_second": 57.501,337      "eval_steps_per_second": 0.058,338      "step": 200339    },340    {341      "epoch": 0.20058708414872797,342      "grad_norm": 26626.736328125,343      "learning_rate": 6.666666666666667e-06,344      "loss": 0.6598,345      "step": 205346    },347    {348      "epoch": 0.2054794520547945,349      "grad_norm": 26082.599609375,350      "learning_rate": 6.830065359477125e-06,351      "loss": 0.6568,352      "step": 210353    },354    {355      "epoch": 0.21037181996086105,356      "grad_norm": 33339.375,357      "learning_rate": 6.993464052287582e-06,358      "loss": 0.6563,359      "step": 215360    },361    {362      "epoch": 0.21526418786692758,363      "grad_norm": 30894.603515625,364      "learning_rate": 7.15686274509804e-06,365      "loss": 0.652,366      "step": 220367    },368    {369      "epoch": 0.22015655577299412,370      "grad_norm": 29593.958984375,371      "learning_rate": 7.320261437908497e-06,372      "loss": 0.6491,373      "step": 225374    },375    {376      "epoch": 0.22504892367906065,377      "grad_norm": 39939.2890625,378      "learning_rate": 7.483660130718955e-06,379      "loss": 0.6479,380      "step": 230381    },382    {383      "epoch": 0.2299412915851272,384      "grad_norm": 32097.01953125,385      "learning_rate": 7.647058823529411e-06,386      "loss": 0.6464,387      "step": 235388    },389    {390      "epoch": 0.23483365949119372,391      "grad_norm": 31191.142578125,392      "learning_rate": 7.81045751633987e-06,393      "loss": 0.6469,394      "step": 240395    },396    {397      "epoch": 0.23972602739726026,398      "grad_norm": 30402.431640625,399      "learning_rate": 7.973856209150329e-06,400      "loss": 0.6407,401      "step": 245402    },403    {404      "epoch": 0.2446183953033268,405      "grad_norm": 30825.1328125,406      "learning_rate": 8.137254901960784e-06,407      "loss": 0.6391,408      "step": 250409    },410    {411      "epoch": 0.2446183953033268,412      "eval_accuracy": 0.623,413      "eval_loss": 0.6709860563278198,414      "eval_macro_f1": 0.5814715106436125,415      "eval_precision": 0.6025402726146221,416      "eval_recall": 0.6470932816224296,417      "eval_runtime": 17.5511,418      "eval_samples_per_second": 56.977,419      "eval_steps_per_second": 0.057,420      "step": 250421    },422    {423      "epoch": 0.24951076320939333,424      "grad_norm": 26645.732421875,425      "learning_rate": 8.300653594771243e-06,426      "loss": 0.6397,427      "step": 255428    },429    {430      "epoch": 0.25440313111545987,431      "grad_norm": 29653.92578125,432      "learning_rate": 8.4640522875817e-06,433      "loss": 0.6437,434      "step": 260435    },436    {437      "epoch": 0.25929549902152643,438      "grad_norm": 31826.6484375,439      "learning_rate": 8.627450980392157e-06,440      "loss": 0.6373,441      "step": 265442    },443    {444      "epoch": 0.26418786692759294,445      "grad_norm": 35353.4765625,446      "learning_rate": 8.790849673202614e-06,447      "loss": 0.6319,448      "step": 270449    },450    {451      "epoch": 0.2690802348336595,452      "grad_norm": 30883.482421875,453      "learning_rate": 8.954248366013073e-06,454      "loss": 0.6355,455      "step": 275456    },457    {458      "epoch": 0.273972602739726,459      "grad_norm": 26454.451171875,460      "learning_rate": 9.11764705882353e-06,461      "loss": 0.6261,462      "step": 280463    },464    {465      "epoch": 0.2788649706457926,466      "grad_norm": 27102.65234375,467      "learning_rate": 9.281045751633987e-06,468      "loss": 0.6291,469      "step": 285470    },471    {472      "epoch": 0.2837573385518591,473      "grad_norm": 26538.755859375,474      "learning_rate": 9.444444444444445e-06,475      "loss": 0.6265,476      "step": 290477    },478    {479      "epoch": 0.28864970645792565,480      "grad_norm": 27230.40625,481      "learning_rate": 9.607843137254903e-06,482      "loss": 0.617,483      "step": 295484    },485    {486      "epoch": 0.29354207436399216,487      "grad_norm": 27588.068359375,488      "learning_rate": 9.77124183006536e-06,489      "loss": 0.618,490      "step": 300491    },492    {493      "epoch": 0.29354207436399216,494      "eval_accuracy": 0.59,495      "eval_loss": 0.6805335283279419,496      "eval_macro_f1": 0.5635902261241277,497      "eval_precision": 0.6075875666060336,498      "eval_recall": 0.6546334931985156,499      "eval_runtime": 17.4391,500      "eval_samples_per_second": 57.342,501      "eval_steps_per_second": 0.057,502      "step": 300503    }504  ],505  "logging_steps": 5,506  "max_steps": 3066,507  "num_input_tokens_seen": 0,508  "num_train_epochs": 3,509  "save_steps": 100,510  "stateful_callbacks": {511    "EarlyStoppingCallback": {512      "args": {513        "early_stopping_patience": 3,514        "early_stopping_threshold": 0.0515      },516      "attributes": {517        "early_stopping_patience_counter": 2518      }519    },520    "TrainerControl": {521      "args": {522        "should_epoch_stop": false,523        "should_evaluate": false,524        "should_log": false,525        "should_save": true,526        "should_training_stop": false527      },528      "attributes": {}529    }530  },531  "total_flos": 4.0413858103296e+16,532  "train_batch_size": 512,533  "trial_name": null,534  "trial_params": null535}536