CoolFace
Modelpublic

JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2

sourceHugging Faceupdated 8mo agoView on Hugging Face
0likes14downloads
trainer_state.json570 linesDownload Raw Back to checkpoint-732
1{2  "best_global_step": 244,3  "best_metric": 0.241361603140831,4  "best_model_checkpoint": "lora_qwen7b_java_abdiff_v2/checkpoint-244",5  "epoch": 3.0,6  "eval_steps": 500,7  "global_step": 732,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 0.041109969167523124,14      "grad_norm": 0.17571452260017395,15      "learning_rate": 3.648648648648649e-06,16      "loss": 0.5537,17      "step": 1018    },19    {20      "epoch": 0.08221993833504625,21      "grad_norm": 0.12462153285741806,22      "learning_rate": 7.702702702702703e-06,23      "loss": 0.5427,24      "step": 2025    },26    {27      "epoch": 0.12332990750256938,28      "grad_norm": 0.13460873067378998,29      "learning_rate": 1.1756756756756757e-05,30      "loss": 0.5255,31      "step": 3032    },33    {34      "epoch": 0.1644398766700925,35      "grad_norm": 0.2371131032705307,36      "learning_rate": 1.5810810810810808e-05,37      "loss": 0.4849,38      "step": 4039    },40    {41      "epoch": 0.20554984583761562,42      "grad_norm": 0.2611907720565796,43      "learning_rate": 1.9864864864864866e-05,44      "loss": 0.3981,45      "step": 5046    },47    {48      "epoch": 0.24665981500513876,49      "grad_norm": 0.10762301832437515,50      "learning_rate": 2.3918918918918917e-05,51      "loss": 0.3275,52      "step": 6053    },54    {55      "epoch": 0.28776978417266186,56      "grad_norm": 0.06910783052444458,57      "learning_rate": 2.7972972972972975e-05,58      "loss": 0.2976,59      "step": 7060    },61    {62      "epoch": 0.328879753340185,63      "grad_norm": 0.10020674765110016,64      "learning_rate": 2.9772036474164135e-05,65      "loss": 0.2958,66      "step": 8067    },68    {69      "epoch": 0.3699897225077081,70      "grad_norm": 0.06338030099868774,71      "learning_rate": 2.9316109422492404e-05,72      "loss": 0.2775,73      "step": 9074    },75    {76      "epoch": 0.41109969167523125,77      "grad_norm": 0.06356582045555115,78      "learning_rate": 2.886018237082067e-05,79      "loss": 0.2671,80      "step": 10081    },82    {83      "epoch": 0.4522096608427544,84      "grad_norm": 0.06176166608929634,85      "learning_rate": 2.8404255319148935e-05,86      "loss": 0.273,87      "step": 11088    },89    {90      "epoch": 0.4933196300102775,91      "grad_norm": 0.0641980841755867,92      "learning_rate": 2.7948328267477204e-05,93      "loss": 0.2708,94      "step": 12095    },96    {97      "epoch": 0.5344295991778006,98      "grad_norm": 0.060578711330890656,99      "learning_rate": 2.7492401215805473e-05,100      "loss": 0.2492,101      "step": 130102    },103    {104      "epoch": 0.5755395683453237,105      "grad_norm": 0.07500634342432022,106      "learning_rate": 2.7036474164133738e-05,107      "loss": 0.2516,108      "step": 140109    },110    {111      "epoch": 0.6166495375128469,112      "grad_norm": 0.06346568465232849,113      "learning_rate": 2.6580547112462007e-05,114      "loss": 0.2423,115      "step": 150116    },117    {118      "epoch": 0.65775950668037,119      "grad_norm": 0.214496448636055,120      "learning_rate": 2.6124620060790272e-05,121      "loss": 0.245,122      "step": 160123    },124    {125      "epoch": 0.6988694758478932,126      "grad_norm": 0.07425080984830856,127      "learning_rate": 2.566869300911854e-05,128      "loss": 0.2455,129      "step": 170130    },131    {132      "epoch": 0.7399794450154162,133      "grad_norm": 0.08862721920013428,134      "learning_rate": 2.521276595744681e-05,135      "loss": 0.2377,136      "step": 180137    },138    {139      "epoch": 0.7810894141829393,140      "grad_norm": 0.09345080703496933,141      "learning_rate": 2.4756838905775076e-05,142      "loss": 0.2493,143      "step": 190144    },145    {146      "epoch": 0.8221993833504625,147      "grad_norm": 0.12085441499948502,148      "learning_rate": 2.4300911854103345e-05,149      "loss": 0.243,150      "step": 200151    },152    {153      "epoch": 0.8633093525179856,154      "grad_norm": 0.09944415092468262,155      "learning_rate": 2.3844984802431613e-05,156      "loss": 0.2276,157      "step": 210158    },159    {160      "epoch": 0.9044193216855088,161      "grad_norm": 0.11600342392921448,162      "learning_rate": 2.338905775075988e-05,163      "loss": 0.2288,164      "step": 220165    },166    {167      "epoch": 0.9455292908530318,168      "grad_norm": 0.11351948231458664,169      "learning_rate": 2.2933130699088144e-05,170      "loss": 0.2136,171      "step": 230172    },173    {174      "epoch": 0.986639260020555,175      "grad_norm": 0.12985852360725403,176      "learning_rate": 2.2477203647416413e-05,177      "loss": 0.2166,178      "step": 240179    },180    {181      "epoch": 1.0,182      "eval_loss": 0.241361603140831,183      "eval_runtime": 48.3711,184      "eval_samples_per_second": 13.479,185      "eval_steps_per_second": 3.37,186      "step": 244187    },188    {189      "epoch": 1.024665981500514,190      "grad_norm": 0.12141554057598114,191      "learning_rate": 2.2021276595744682e-05,192      "loss": 0.2116,193      "step": 250194    },195    {196      "epoch": 1.065775950668037,197      "grad_norm": 0.1510457694530487,198      "learning_rate": 2.156534954407295e-05,199      "loss": 0.2004,200      "step": 260201    },202    {203      "epoch": 1.10688591983556,204      "grad_norm": 0.18226052820682526,205      "learning_rate": 2.1109422492401216e-05,206      "loss": 0.2089,207      "step": 270208    },209    {210      "epoch": 1.1479958890030832,211      "grad_norm": 0.1632615327835083,212      "learning_rate": 2.0653495440729482e-05,213      "loss": 0.1878,214      "step": 280215    },216    {217      "epoch": 1.1891058581706064,218      "grad_norm": 0.2921697199344635,219      "learning_rate": 2.019756838905775e-05,220      "loss": 0.1798,221      "step": 290222    },223    {224      "epoch": 1.2302158273381294,225      "grad_norm": 0.19414232671260834,226      "learning_rate": 1.974164133738602e-05,227      "loss": 0.1851,228      "step": 300229    },230    {231      "epoch": 1.2713257965056526,232      "grad_norm": 0.2113204449415207,233      "learning_rate": 1.928571428571429e-05,234      "loss": 0.1884,235      "step": 310236    },237    {238      "epoch": 1.3124357656731758,239      "grad_norm": 0.25703924894332886,240      "learning_rate": 1.8829787234042554e-05,241      "loss": 0.1666,242      "step": 320243    },244    {245      "epoch": 1.353545734840699,246      "grad_norm": 0.32676252722740173,247      "learning_rate": 1.837386018237082e-05,248      "loss": 0.1673,249      "step": 330250    },251    {252      "epoch": 1.394655704008222,253      "grad_norm": 0.2629919946193695,254      "learning_rate": 1.7917933130699088e-05,255      "loss": 0.1656,256      "step": 340257    },258    {259      "epoch": 1.435765673175745,260      "grad_norm": 0.2691596448421478,261      "learning_rate": 1.7462006079027357e-05,262      "loss": 0.1513,263      "step": 350264    },265    {266      "epoch": 1.4768756423432683,267      "grad_norm": 0.2598915994167328,268      "learning_rate": 1.7006079027355622e-05,269      "loss": 0.15,270      "step": 360271    },272    {273      "epoch": 1.5179856115107913,274      "grad_norm": 0.2840367257595062,275      "learning_rate": 1.655015197568389e-05,276      "loss": 0.1393,277      "step": 370278    },279    {280      "epoch": 1.5590955806783144,281      "grad_norm": 0.27585548162460327,282      "learning_rate": 1.609422492401216e-05,283      "loss": 0.1326,284      "step": 380285    },286    {287      "epoch": 1.6002055498458376,288      "grad_norm": 0.3558744490146637,289      "learning_rate": 1.5638297872340426e-05,290      "loss": 0.1386,291      "step": 390292    },293    {294      "epoch": 1.6413155190133608,295      "grad_norm": 0.3336169719696045,296      "learning_rate": 1.5182370820668691e-05,297      "loss": 0.135,298      "step": 400299    },300    {301      "epoch": 1.682425488180884,302      "grad_norm": 0.4432605504989624,303      "learning_rate": 1.4726443768996962e-05,304      "loss": 0.1246,305      "step": 410306    },307    {308      "epoch": 1.723535457348407,309      "grad_norm": 0.3988304138183594,310      "learning_rate": 1.4270516717325229e-05,311      "loss": 0.129,312      "step": 420313    },314    {315      "epoch": 1.7646454265159301,316      "grad_norm": 0.3611379563808441,317      "learning_rate": 1.3814589665653496e-05,318      "loss": 0.1079,319      "step": 430320    },321    {322      "epoch": 1.8057553956834531,323      "grad_norm": 0.4067041277885437,324      "learning_rate": 1.3358662613981763e-05,325      "loss": 0.1275,326      "step": 440327    },328    {329      "epoch": 1.8468653648509763,330      "grad_norm": 0.36210691928863525,331      "learning_rate": 1.2902735562310032e-05,332      "loss": 0.1122,333      "step": 450334    },335    {336      "epoch": 1.8879753340184995,337      "grad_norm": 0.3510965406894684,338      "learning_rate": 1.2446808510638298e-05,339      "loss": 0.0966,340      "step": 460341    },342    {343      "epoch": 1.9290853031860227,344      "grad_norm": 0.38730406761169434,345      "learning_rate": 1.1990881458966566e-05,346      "loss": 0.1089,347      "step": 470348    },349    {350      "epoch": 1.9701952723535459,351      "grad_norm": 0.39076584577560425,352      "learning_rate": 1.1534954407294832e-05,353      "loss": 0.1038,354      "step": 480355    },356    {357      "epoch": 2.0,358      "eval_loss": 0.2861343026161194,359      "eval_runtime": 48.2041,360      "eval_samples_per_second": 13.526,361      "eval_steps_per_second": 3.381,362      "step": 488363    },364    {365      "epoch": 2.0082219938335046,366      "grad_norm": 0.4124261438846588,367      "learning_rate": 1.10790273556231e-05,368      "loss": 0.0975,369      "step": 490370    },371    {372      "epoch": 2.049331963001028,373      "grad_norm": 0.4260999262332916,374      "learning_rate": 1.0623100303951368e-05,375      "loss": 0.0973,376      "step": 500377    },378    {379      "epoch": 2.090441932168551,380      "grad_norm": 0.4411214292049408,381      "learning_rate": 1.0167173252279635e-05,382      "loss": 0.0803,383      "step": 510384    },385    {386      "epoch": 2.131551901336074,387      "grad_norm": 0.5388243794441223,388      "learning_rate": 9.711246200607902e-06,389      "loss": 0.089,390      "step": 520391    },392    {393      "epoch": 2.172661870503597,394      "grad_norm": 0.36110010743141174,395      "learning_rate": 9.255319148936171e-06,396      "loss": 0.0955,397      "step": 530398    },399    {400      "epoch": 2.21377183967112,401      "grad_norm": 0.30860260128974915,402      "learning_rate": 8.799392097264438e-06,403      "loss": 0.0824,404      "step": 540405    },406    {407      "epoch": 2.2548818088386433,408      "grad_norm": 0.42028531432151794,409      "learning_rate": 8.343465045592705e-06,410      "loss": 0.0936,411      "step": 550412    },413    {414      "epoch": 2.2959917780061665,415      "grad_norm": 0.36835429072380066,416      "learning_rate": 7.887537993920974e-06,417      "loss": 0.074,418      "step": 560419    },420    {421      "epoch": 2.3371017471736897,422      "grad_norm": 0.43269503116607666,423      "learning_rate": 7.43161094224924e-06,424      "loss": 0.0778,425      "step": 570426    },427    {428      "epoch": 2.378211716341213,429      "grad_norm": 0.4608248770236969,430      "learning_rate": 6.975683890577508e-06,431      "loss": 0.0731,432      "step": 580433    },434    {435      "epoch": 2.419321685508736,436      "grad_norm": 0.36565056443214417,437      "learning_rate": 6.519756838905775e-06,438      "loss": 0.0812,439      "step": 590440    },441    {442      "epoch": 2.460431654676259,443      "grad_norm": 0.37470170855522156,444      "learning_rate": 6.063829787234042e-06,445      "loss": 0.071,446      "step": 600447    },448    {449      "epoch": 2.501541623843782,450      "grad_norm": 0.47044429183006287,451      "learning_rate": 5.607902735562311e-06,452      "loss": 0.075,453      "step": 610454    },455    {456      "epoch": 2.542651593011305,457      "grad_norm": 0.3516956865787506,458      "learning_rate": 5.151975683890578e-06,459      "loss": 0.0684,460      "step": 620461    },462    {463      "epoch": 2.5837615621788284,464      "grad_norm": 0.4521888196468353,465      "learning_rate": 4.696048632218845e-06,466      "loss": 0.076,467      "step": 630468    },469    {470      "epoch": 2.6248715313463515,471      "grad_norm": 0.45891526341438293,472      "learning_rate": 4.240121580547112e-06,473      "loss": 0.0701,474      "step": 640475    },476    {477      "epoch": 2.6659815005138747,478      "grad_norm": 0.33456680178642273,479      "learning_rate": 3.7841945288753804e-06,480      "loss": 0.0682,481      "step": 650482    },483    {484      "epoch": 2.707091469681398,485      "grad_norm": 0.3150039613246918,486      "learning_rate": 3.3282674772036475e-06,487      "loss": 0.0785,488      "step": 660489    },490    {491      "epoch": 2.7482014388489207,492      "grad_norm": 0.3293338716030121,493      "learning_rate": 2.872340425531915e-06,494      "loss": 0.0634,495      "step": 670496    },497    {498      "epoch": 2.789311408016444,499      "grad_norm": 0.37423741817474365,500      "learning_rate": 2.4164133738601823e-06,501      "loss": 0.0715,502      "step": 680503    },504    {505      "epoch": 2.830421377183967,506      "grad_norm": 0.32468822598457336,507      "learning_rate": 1.96048632218845e-06,508      "loss": 0.0755,509      "step": 690510    },511    {512      "epoch": 2.87153134635149,513      "grad_norm": 0.388679563999176,514      "learning_rate": 1.5045592705167174e-06,515      "loss": 0.0688,516      "step": 700517    },518    {519      "epoch": 2.9126413155190134,520      "grad_norm": 0.36400821805000305,521      "learning_rate": 1.0486322188449848e-06,522      "loss": 0.0705,523      "step": 710524    },525    {526      "epoch": 2.9537512846865366,527      "grad_norm": 0.34037601947784424,528      "learning_rate": 5.927051671732523e-07,529      "loss": 0.0647,530      "step": 720531    },532    {533      "epoch": 2.9948612538540598,534      "grad_norm": 0.30876415967941284,535      "learning_rate": 1.3677811550151974e-07,536      "loss": 0.075,537      "step": 730538    },539    {540      "epoch": 3.0,541      "eval_loss": 0.3031086027622223,542      "eval_runtime": 48.1817,543      "eval_samples_per_second": 13.532,544      "eval_steps_per_second": 3.383,545      "step": 732546    }547  ],548  "logging_steps": 10,549  "max_steps": 732,550  "num_input_tokens_seen": 0,551  "num_train_epochs": 3,552  "save_steps": 500,553  "stateful_callbacks": {554    "TrainerControl": {555      "args": {556        "should_epoch_stop": false,557        "should_evaluate": false,558        "should_log": false,559        "should_save": true,560        "should_training_stop": true561      },562      "attributes": {}563    }564  },565  "total_flos": 1.0098660093853901e+18,566  "train_batch_size": 4,567  "trial_name": null,568  "trial_params": null569}570