Team Ai
Modelpublic

dzungpham/graphcodebert-code-classification

sourceHugging Facemitupdated 5mo agoView on Hugging Face
0likes
trainer_state.json324 linesDownload Raw Back to checkpoint-400
1{2  "best_global_step": null,3  "best_metric": null,4  "best_model_checkpoint": null,5  "epoch": 0.05119672340970178,6  "eval_steps": 1000,7  "global_step": 400,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 0.0012799180852425445,14      "grad_norm": 1.2002202272415161,15      "learning_rate": 1.4404609475032012e-07,16      "loss": 0.714,17      "step": 1018    },19    {20      "epoch": 0.002559836170485089,21      "grad_norm": 1.0710716247558594,22      "learning_rate": 3.040973111395647e-07,23      "loss": 0.7181,24      "step": 2025    },26    {27      "epoch": 0.0038397542557276334,28      "grad_norm": 1.0631524324417114,29      "learning_rate": 4.641485275288093e-07,30      "loss": 0.7114,31      "step": 3032    },33    {34      "epoch": 0.005119672340970178,35      "grad_norm": 1.1470946073532104,36      "learning_rate": 6.241997439180538e-07,37      "loss": 0.7083,38      "step": 4039    },40    {41      "epoch": 0.006399590426212722,42      "grad_norm": 1.1680080890655518,43      "learning_rate": 7.842509603072984e-07,44      "loss": 0.7109,45      "step": 5046    },47    {48      "epoch": 0.007679508511455267,49      "grad_norm": 0.6832358241081238,50      "learning_rate": 9.44302176696543e-07,51      "loss": 0.7131,52      "step": 6053    },54    {55      "epoch": 0.008959426596697812,56      "grad_norm": 1.8029249906539917,57      "learning_rate": 1.1043533930857875e-06,58      "loss": 0.7092,59      "step": 7060    },61    {62      "epoch": 0.010239344681940356,63      "grad_norm": 1.795204758644104,64      "learning_rate": 1.264404609475032e-06,65      "loss": 0.7063,66      "step": 8067    },68    {69      "epoch": 0.011519262767182901,70      "grad_norm": 1.2713547945022583,71      "learning_rate": 1.4244558258642767e-06,72      "loss": 0.7126,73      "step": 9074    },75    {76      "epoch": 0.012799180852425445,77      "grad_norm": 1.2709708213806152,78      "learning_rate": 1.5845070422535212e-06,79      "loss": 0.7069,80      "step": 10081    },82    {83      "epoch": 0.01407909893766799,84      "grad_norm": 0.8230543732643127,85      "learning_rate": 1.7445582586427658e-06,86      "loss": 0.7036,87      "step": 11088    },89    {90      "epoch": 0.015359017022910534,91      "grad_norm": 0.7209059596061707,92      "learning_rate": 1.9046094750320101e-06,93      "loss": 0.7058,94      "step": 12095    },96    {97      "epoch": 0.016638935108153077,98      "grad_norm": 0.7314836978912354,99      "learning_rate": 2.064660691421255e-06,100      "loss": 0.7046,101      "step": 130102    },103    {104      "epoch": 0.017918853193395624,105      "grad_norm": 0.7659752368927002,106      "learning_rate": 2.2247119078104993e-06,107      "loss": 0.6989,108      "step": 140109    },110    {111      "epoch": 0.019198771278638168,112      "grad_norm": 0.9008486866950989,113      "learning_rate": 2.384763124199744e-06,114      "loss": 0.6998,115      "step": 150116    },117    {118      "epoch": 0.02047868936388071,119      "grad_norm": 1.0409601926803589,120      "learning_rate": 2.5448143405889883e-06,121      "loss": 0.7016,122      "step": 160123    },124    {125      "epoch": 0.021758607449123255,126      "grad_norm": 0.8855634927749634,127      "learning_rate": 2.704865556978233e-06,128      "loss": 0.6947,129      "step": 170130    },131    {132      "epoch": 0.023038525534365802,133      "grad_norm": 0.798701286315918,134      "learning_rate": 2.8649167733674777e-06,135      "loss": 0.6935,136      "step": 180137    },138    {139      "epoch": 0.024318443619608346,140      "grad_norm": 1.1289243698120117,141      "learning_rate": 3.024967989756722e-06,142      "loss": 0.6937,143      "step": 190144    },145    {146      "epoch": 0.02559836170485089,147      "grad_norm": 1.4480715990066528,148      "learning_rate": 3.185019206145967e-06,149      "loss": 0.6948,150      "step": 200151    },152    {153      "epoch": 0.026878279790093433,154      "grad_norm": 0.6359772682189941,155      "learning_rate": 3.3450704225352113e-06,156      "loss": 0.6904,157      "step": 210158    },159    {160      "epoch": 0.02815819787533598,161      "grad_norm": 1.1023344993591309,162      "learning_rate": 3.5051216389244556e-06,163      "loss": 0.6873,164      "step": 220165    },166    {167      "epoch": 0.029438115960578524,168      "grad_norm": 0.8251340389251709,169      "learning_rate": 3.6651728553137003e-06,170      "loss": 0.6859,171      "step": 230172    },173    {174      "epoch": 0.030718034045821067,175      "grad_norm": 0.7032744288444519,176      "learning_rate": 3.825224071702945e-06,177      "loss": 0.6804,178      "step": 240179    },180    {181      "epoch": 0.031997952131063614,182      "grad_norm": 0.7794032096862793,183      "learning_rate": 3.98527528809219e-06,184      "loss": 0.6831,185      "step": 250186    },187    {188      "epoch": 0.033277870216306155,189      "grad_norm": 0.6654011607170105,190      "learning_rate": 4.145326504481434e-06,191      "loss": 0.6813,192      "step": 260193    },194    {195      "epoch": 0.0345577883015487,196      "grad_norm": 1.7002371549606323,197      "learning_rate": 4.3053777208706795e-06,198      "loss": 0.6793,199      "step": 270200    },201    {202      "epoch": 0.03583770638679125,203      "grad_norm": 1.0438320636749268,204      "learning_rate": 4.465428937259923e-06,205      "loss": 0.6758,206      "step": 280207    },208    {209      "epoch": 0.03711762447203379,210      "grad_norm": 0.6591306924819946,211      "learning_rate": 4.625480153649168e-06,212      "loss": 0.6758,213      "step": 290214    },215    {216      "epoch": 0.038397542557276336,217      "grad_norm": 0.5876058340072632,218      "learning_rate": 4.785531370038412e-06,219      "loss": 0.6742,220      "step": 300221    },222    {223      "epoch": 0.039677460642518876,224      "grad_norm": 0.5839381814002991,225      "learning_rate": 4.9455825864276575e-06,226      "loss": 0.6706,227      "step": 310228    },229    {230      "epoch": 0.04095737872776142,231      "grad_norm": 1.3025041818618774,232      "learning_rate": 5.105633802816902e-06,233      "loss": 0.6658,234      "step": 320235    },236    {237      "epoch": 0.04223729681300397,238      "grad_norm": 0.5543903708457947,239      "learning_rate": 5.265685019206147e-06,240      "loss": 0.6722,241      "step": 330242    },243    {244      "epoch": 0.04351721489824651,245      "grad_norm": 0.5097215175628662,246      "learning_rate": 5.425736235595391e-06,247      "loss": 0.6704,248      "step": 340249    },250    {251      "epoch": 0.04479713298348906,252      "grad_norm": 0.760080873966217,253      "learning_rate": 5.585787451984635e-06,254      "loss": 0.6652,255      "step": 350256    },257    {258      "epoch": 0.046077051068731605,259      "grad_norm": 0.7467712759971619,260      "learning_rate": 5.74583866837388e-06,261      "loss": 0.668,262      "step": 360263    },264    {265      "epoch": 0.047356969153974145,266      "grad_norm": 0.9601678848266602,267      "learning_rate": 5.905889884763125e-06,268      "loss": 0.6619,269      "step": 370270    },271    {272      "epoch": 0.04863688723921669,273      "grad_norm": 0.7230914235115051,274      "learning_rate": 6.065941101152369e-06,275      "loss": 0.6585,276      "step": 380277    },278    {279      "epoch": 0.04991680532445923,280      "grad_norm": 0.8606265783309937,281      "learning_rate": 6.225992317541613e-06,282      "loss": 0.6591,283      "step": 390284    },285    {286      "epoch": 0.05119672340970178,287      "grad_norm": 0.6350621581077576,288      "learning_rate": 6.386043533930858e-06,289      "loss": 0.6575,290      "step": 400291    }292  ],293  "logging_steps": 10,294  "max_steps": 31252,295  "num_input_tokens_seen": 0,296  "num_train_epochs": 4,297  "save_steps": 100,298  "stateful_callbacks": {299    "EarlyStoppingCallback": {300      "args": {301        "early_stopping_patience": 3,302        "early_stopping_threshold": 0.0303      },304      "attributes": {305        "early_stopping_patience_counter": 0306      }307    },308    "TrainerControl": {309      "args": {310        "should_epoch_stop": false,311        "should_evaluate": false,312        "should_log": false,313        "should_save": true,314        "should_training_stop": false315      },316      "attributes": {}317    }318  },319  "total_flos": 6735643017216000.0,320  "train_batch_size": 64,321  "trial_name": null,322  "trial_params": null323}324