Team Ai
Modelpublic

dzungpham/graphcodebert-code-classification

sourceHugging Facemitupdated 5mo agoView on Hugging Face
0likes
trainer_state.json1873 linesDownload Raw Back to checkpoint-1200
1{2  "best_global_step": 1200,3  "best_metric": 0.6440359919423964,4  "best_model_checkpoint": "graphcodebert-swa-from-epoch-1/checkpoint-1200",5  "epoch": 2.4539877300613497,6  "eval_steps": 100,7  "global_step": 1200,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 0.010224948875255624,14      "grad_norm": 2.4707133769989014,15      "learning_rate": 2.0512820512820512e-08,16      "loss": 0.8431,17      "step": 518    },19    {20      "epoch": 0.02044989775051125,21      "grad_norm": 3.114851951599121,22      "learning_rate": 4.615384615384615e-08,23      "loss": 0.844,24      "step": 1025    },26    {27      "epoch": 0.03067484662576687,28      "grad_norm": 2.2256007194519043,29      "learning_rate": 7.179487179487178e-08,30      "loss": 0.847,31      "step": 1532    },33    {34      "epoch": 0.0408997955010225,35      "grad_norm": 2.5343081951141357,36      "learning_rate": 9.743589743589743e-08,37      "loss": 0.8492,38      "step": 2039    },40    {41      "epoch": 0.05112474437627812,42      "grad_norm": 3.1964163780212402,43      "learning_rate": 1.2307692307692308e-07,44      "loss": 0.8475,45      "step": 2546    },47    {48      "epoch": 0.06134969325153374,49      "grad_norm": 2.0466485023498535,50      "learning_rate": 1.4871794871794872e-07,51      "loss": 0.8445,52      "step": 3053    },54    {55      "epoch": 0.07157464212678936,56      "grad_norm": 2.164569139480591,57      "learning_rate": 1.7435897435897435e-07,58      "loss": 0.8452,59      "step": 3560    },61    {62      "epoch": 0.081799591002045,63      "grad_norm": 2.56343150138855,64      "learning_rate": 2e-07,65      "loss": 0.8473,66      "step": 4067    },68    {69      "epoch": 0.09202453987730061,70      "grad_norm": 2.5742437839508057,71      "learning_rate": 2.2564102564102563e-07,72      "loss": 0.848,73      "step": 4574    },75    {76      "epoch": 0.10224948875255624,77      "grad_norm": 2.587480306625366,78      "learning_rate": 2.5128205128205126e-07,79      "loss": 0.8409,80      "step": 5081    },82    {83      "epoch": 0.11247443762781185,84      "grad_norm": 2.5737764835357666,85      "learning_rate": 2.7692307692307693e-07,86      "loss": 0.8471,87      "step": 5588    },89    {90      "epoch": 0.12269938650306748,91      "grad_norm": 3.044358730316162,92      "learning_rate": 3.0256410256410254e-07,93      "loss": 0.8448,94      "step": 6095    },96    {97      "epoch": 0.1329243353783231,98      "grad_norm": 2.326373815536499,99      "learning_rate": 3.282051282051282e-07,100      "loss": 0.8517,101      "step": 65102    },103    {104      "epoch": 0.14314928425357873,105      "grad_norm": 2.267547607421875,106      "learning_rate": 3.5384615384615386e-07,107      "loss": 0.8387,108      "step": 70109    },110    {111      "epoch": 0.15337423312883436,112      "grad_norm": 2.609232187271118,113      "learning_rate": 3.7948717948717947e-07,114      "loss": 0.841,115      "step": 75116    },117    {118      "epoch": 0.16359918200409,119      "grad_norm": 2.9532523155212402,120      "learning_rate": 4.0512820512820514e-07,121      "loss": 0.8509,122      "step": 80123    },124    {125      "epoch": 0.1738241308793456,126      "grad_norm": 3.002154588699341,127      "learning_rate": 4.307692307692308e-07,128      "loss": 0.8482,129      "step": 85130    },131    {132      "epoch": 0.18404907975460122,133      "grad_norm": 2.701613187789917,134      "learning_rate": 4.5641025641025636e-07,135      "loss": 0.8422,136      "step": 90137    },138    {139      "epoch": 0.19427402862985685,140      "grad_norm": 2.7430365085601807,141      "learning_rate": 4.82051282051282e-07,142      "loss": 0.846,143      "step": 95144    },145    {146      "epoch": 0.20449897750511248,147      "grad_norm": 2.8101418018341064,148      "learning_rate": 5.076923076923076e-07,149      "loss": 0.8444,150      "step": 100151    },152    {153      "epoch": 0.20449897750511248,154      "eval_accuracy": 0.52033,155      "eval_loss": 0.6922348141670227,156      "eval_macro_f1": 0.4427650399783254,157      "eval_precision": 0.6036606007378691,158      "eval_recall": 0.5386742448919869,159      "eval_runtime": 80.6812,160      "eval_samples_per_second": 1239.446,161      "eval_steps_per_second": 0.607,162      "step": 100163    },164    {165      "epoch": 0.2147239263803681,166      "grad_norm": 2.5835089683532715,167      "learning_rate": 5.333333333333333e-07,168      "loss": 0.8437,169      "step": 105170    },171    {172      "epoch": 0.2249488752556237,173      "grad_norm": 2.7237253189086914,174      "learning_rate": 5.58974358974359e-07,175      "loss": 0.8431,176      "step": 110177    },178    {179      "epoch": 0.23517382413087934,180      "grad_norm": 2.4648072719573975,181      "learning_rate": 5.846153846153847e-07,182      "loss": 0.8399,183      "step": 115184    },185    {186      "epoch": 0.24539877300613497,187      "grad_norm": 2.7011852264404297,188      "learning_rate": 6.102564102564103e-07,189      "loss": 0.8409,190      "step": 120191    },192    {193      "epoch": 0.2556237218813906,194      "grad_norm": 2.3170969486236572,195      "learning_rate": 6.358974358974358e-07,196      "loss": 0.8361,197      "step": 125198    },199    {200      "epoch": 0.2658486707566462,201      "grad_norm": 2.517194986343384,202      "learning_rate": 6.615384615384615e-07,203      "loss": 0.839,204      "step": 130205    },206    {207      "epoch": 0.27607361963190186,208      "grad_norm": 2.5092124938964844,209      "learning_rate": 6.871794871794871e-07,210      "loss": 0.8438,211      "step": 135212    },213    {214      "epoch": 0.28629856850715746,215      "grad_norm": 2.3993237018585205,216      "learning_rate": 7.128205128205128e-07,217      "loss": 0.8349,218      "step": 140219    },220    {221      "epoch": 0.2965235173824131,222      "grad_norm": 2.1388165950775146,223      "learning_rate": 7.384615384615384e-07,224      "loss": 0.8363,225      "step": 145226    },227    {228      "epoch": 0.3067484662576687,229      "grad_norm": 1.8425891399383545,230      "learning_rate": 7.64102564102564e-07,231      "loss": 0.8325,232      "step": 150233    },234    {235      "epoch": 0.3169734151329243,236      "grad_norm": 1.8665552139282227,237      "learning_rate": 7.897435897435897e-07,238      "loss": 0.835,239      "step": 155240    },241    {242      "epoch": 0.32719836400818,243      "grad_norm": 1.8765455484390259,244      "learning_rate": 8.153846153846154e-07,245      "loss": 0.8328,246      "step": 160247    },248    {249      "epoch": 0.3374233128834356,250      "grad_norm": 2.640779495239258,251      "learning_rate": 8.41025641025641e-07,252      "loss": 0.8388,253      "step": 165254    },255    {256      "epoch": 0.3476482617586912,257      "grad_norm": 2.174116373062134,258      "learning_rate": 8.666666666666667e-07,259      "loss": 0.8336,260      "step": 170261    },262    {263      "epoch": 0.35787321063394684,264      "grad_norm": 1.8411178588867188,265      "learning_rate": 8.923076923076923e-07,266      "loss": 0.8384,267      "step": 175268    },269    {270      "epoch": 0.36809815950920244,271      "grad_norm": 2.3652143478393555,272      "learning_rate": 9.179487179487179e-07,273      "loss": 0.8318,274      "step": 180275    },276    {277      "epoch": 0.3783231083844581,278      "grad_norm": 1.9870903491973877,279      "learning_rate": 9.435897435897435e-07,280      "loss": 0.8306,281      "step": 185282    },283    {284      "epoch": 0.3885480572597137,285      "grad_norm": 2.458887815475464,286      "learning_rate": 9.692307692307691e-07,287      "loss": 0.8342,288      "step": 190289    },290    {291      "epoch": 0.3987730061349693,292      "grad_norm": 1.9105890989303589,293      "learning_rate": 9.948717948717949e-07,294      "loss": 0.8301,295      "step": 195296    },297    {298      "epoch": 0.40899795501022496,299      "grad_norm": 2.04896879196167,300      "learning_rate": 9.999490793845076e-07,301      "loss": 0.8291,302      "step": 200303    },304    {305      "epoch": 0.40899795501022496,306      "eval_accuracy": 0.52697,307      "eval_loss": 0.6913915872573853,308      "eval_macro_f1": 0.4511625248903547,309      "eval_precision": 0.6198512746424523,310      "eval_recall": 0.5452618609595298,311      "eval_runtime": 80.6395,312      "eval_samples_per_second": 1240.088,313      "eval_steps_per_second": 0.608,314      "step": 200315    },316    {317      "epoch": 0.41922290388548056,318      "grad_norm": 2.394630193710327,319      "learning_rate": 9.997422321595486e-07,320      "loss": 0.8311,321      "step": 205322    },323    {324      "epoch": 0.4294478527607362,325      "grad_norm": 1.7013665437698364,326      "learning_rate": 9.993763415653074e-07,327      "loss": 0.8264,328      "step": 210329    },330    {331      "epoch": 0.4396728016359918,332      "grad_norm": 2.1158103942871094,333      "learning_rate": 9.988515240467613e-07,334      "loss": 0.8262,335      "step": 215336    },337    {338      "epoch": 0.4498977505112474,339      "grad_norm": 1.5985370874404907,340      "learning_rate": 9.981679466275095e-07,341      "loss": 0.8296,342      "step": 220343    },344    {345      "epoch": 0.4601226993865031,346      "grad_norm": 2.0426042079925537,347      "learning_rate": 9.973258268566182e-07,348      "loss": 0.8233,349      "step": 225350    },351    {352      "epoch": 0.4703476482617587,353      "grad_norm": 1.7411834001541138,354      "learning_rate": 9.963254327393853e-07,355      "loss": 0.8269,356      "step": 230357    },358    {359      "epoch": 0.48057259713701433,360      "grad_norm": 2.1182405948638916,361      "learning_rate": 9.95167082652047e-07,362      "loss": 0.8247,363      "step": 235364    },365    {366      "epoch": 0.49079754601226994,367      "grad_norm": 2.0239953994750977,368      "learning_rate": 9.938511452404547e-07,369      "loss": 0.8308,370      "step": 240371    },372    {373      "epoch": 0.5010224948875256,374      "grad_norm": 2.366060495376587,375      "learning_rate": 9.923780393027534e-07,376      "loss": 0.8205,377      "step": 245378    },379    {380      "epoch": 0.5112474437627812,381      "grad_norm": 1.848169207572937,382      "learning_rate": 9.907482336560982e-07,383      "loss": 0.825,384      "step": 250385    },386    {387      "epoch": 0.5214723926380368,388      "grad_norm": 1.8216668367385864,389      "learning_rate": 9.889622469874535e-07,390      "loss": 0.8271,391      "step": 255392    },393    {394      "epoch": 0.5316973415132924,395      "grad_norm": 1.507730484008789,396      "learning_rate": 9.8702064768852e-07,397      "loss": 0.8147,398      "step": 260399    },400    {401      "epoch": 0.5419222903885481,402      "grad_norm": 1.7608263492584229,403      "learning_rate": 9.849240536748438e-07,404      "loss": 0.8221,405      "step": 265406    },407    {408      "epoch": 0.5521472392638037,409      "grad_norm": 2.203326940536499,410      "learning_rate": 9.826731321891641e-07,411      "loss": 0.8292,412      "step": 270413    },414    {415      "epoch": 0.5623721881390593,416      "grad_norm": 1.9529740810394287,417      "learning_rate": 9.802685995890632e-07,418      "loss": 0.8228,419      "step": 275420    },421    {422      "epoch": 0.5725971370143149,423      "grad_norm": 1.6214399337768555,424      "learning_rate": 9.777112211189841e-07,425      "loss": 0.8149,426      "step": 280427    },428    {429      "epoch": 0.5828220858895705,430      "grad_norm": 2.07482647895813,431      "learning_rate": 9.750018106666924e-07,432      "loss": 0.8143,433      "step": 285434    },435    {436      "epoch": 0.5930470347648262,437      "grad_norm": 1.7083203792572021,438      "learning_rate": 9.721412305042538e-07,439      "loss": 0.8188,440      "step": 290441    },442    {443      "epoch": 0.6032719836400818,444      "grad_norm": 2.0022943019866943,445      "learning_rate": 9.69130391013617e-07,446      "loss": 0.8195,447      "step": 295448    },449    {450      "epoch": 0.6134969325153374,451      "grad_norm": 1.5799461603164673,452      "learning_rate": 9.659702503968834e-07,453      "loss": 0.8146,454      "step": 300455    },456    {457      "epoch": 0.6134969325153374,458      "eval_accuracy": 0.55052,459      "eval_loss": 0.6896406412124634,460      "eval_macro_f1": 0.49869783315905847,461      "eval_precision": 0.6264643684302231,462      "eval_recall": 0.5665461014402418,463      "eval_runtime": 80.6145,464      "eval_samples_per_second": 1240.472,465      "eval_steps_per_second": 0.608,466      "step": 300467    },468    {469      "epoch": 0.623721881390593,470      "grad_norm": 1.9373347759246826,471      "learning_rate": 9.626618143713586e-07,472      "loss": 0.8166,473      "step": 305474    },475    {476      "epoch": 0.6339468302658486,477      "grad_norm": 1.6276922225952148,478      "learning_rate": 9.592061358494813e-07,479      "loss": 0.8176,480      "step": 310481    },482    {483      "epoch": 0.6441717791411042,484      "grad_norm": 1.9373250007629395,485      "learning_rate": 9.556043146037337e-07,486      "loss": 0.8168,487      "step": 315488    },489    {490      "epoch": 0.65439672801636,491      "grad_norm": 1.320465087890625,492      "learning_rate": 9.518574969166391e-07,493      "loss": 0.8101,494      "step": 320495    },496    {497      "epoch": 0.6646216768916156,498      "grad_norm": 1.8596330881118774,499      "learning_rate": 9.47966875215954e-07,500      "loss": 0.8167,501      "step": 325502    },503    {504      "epoch": 0.6748466257668712,505      "grad_norm": 1.304662823677063,506      "learning_rate": 9.439336876951793e-07,507      "loss": 0.815,508      "step": 330509    },510    {511      "epoch": 0.6850715746421268,512      "grad_norm": 1.8063029050827026,513      "learning_rate": 9.397592179195033e-07,514      "loss": 0.8121,515      "step": 335516    },517    {518      "epoch": 0.6952965235173824,519      "grad_norm": 1.7432739734649658,520      "learning_rate": 9.354447944173059e-07,521      "loss": 0.8104,522      "step": 340523    },524    {525      "epoch": 0.7055214723926381,526      "grad_norm": 1.4523797035217285,527      "learning_rate": 9.309917902573533e-07,528      "loss": 0.8098,529      "step": 345530    },531    {532      "epoch": 0.7157464212678937,533      "grad_norm": 1.681409478187561,534      "learning_rate": 9.264016226118188e-07,535      "loss": 0.8107,536      "step": 350537    },538    {539      "epoch": 0.7259713701431493,540      "grad_norm": 1.5168694257736206,541      "learning_rate": 9.216757523052652e-07,542      "loss": 0.8085,543      "step": 355544    },545    {546      "epoch": 0.7361963190184049,547      "grad_norm": 1.2200194597244263,548      "learning_rate": 9.168156833497371e-07,549      "loss": 0.8109,550      "step": 360551    },552    {553      "epoch": 0.7464212678936605,554      "grad_norm": 1.2745580673217773,555      "learning_rate": 9.118229624661078e-07,556      "loss": 0.8096,557      "step": 365558    },559    {560      "epoch": 0.7566462167689162,561      "grad_norm": 1.8339142799377441,562      "learning_rate": 9.066991785918333e-07,563      "loss": 0.808,564      "step": 370565    },566    {567      "epoch": 0.7668711656441718,568      "grad_norm": 1.2315114736557007,569      "learning_rate": 9.01445962375273e-07,570      "loss": 0.805,571      "step": 375572    },573    {574      "epoch": 0.7770961145194274,575      "grad_norm": 1.3081412315368652,576      "learning_rate": 8.960649856567333e-07,577      "loss": 0.8066,578      "step": 380579    },580    {581      "epoch": 0.787321063394683,582      "grad_norm": 1.5145998001098633,583      "learning_rate": 8.90557960936404e-07,584      "loss": 0.8028,585      "step": 385586    },587    {588      "epoch": 0.7975460122699386,589      "grad_norm": 1.5990959405899048,590      "learning_rate": 8.84926640829353e-07,591      "loss": 0.8035,592      "step": 390593    },594    {595      "epoch": 0.8077709611451943,596      "grad_norm": 1.2120558023452759,597      "learning_rate": 8.79172817507756e-07,598      "loss": 0.802,599      "step": 395600    },601    {602      "epoch": 0.8179959100204499,603      "grad_norm": 1.5799622535705566,604      "learning_rate": 8.73298322130535e-07,605      "loss": 0.8037,606      "step": 400607    },608    {609      "epoch": 0.8179959100204499,610      "eval_accuracy": 0.58537,611      "eval_loss": 0.6877263784408569,612      "eval_macro_f1": 0.5630337315451738,613      "eval_precision": 0.628845494567806,614      "eval_recall": 0.5970616303474306,615      "eval_runtime": 81.293,616      "eval_samples_per_second": 1230.118,617      "eval_steps_per_second": 0.603,618      "step": 400619    },620    {621      "epoch": 0.8282208588957055,622      "grad_norm": 1.3475037813186646,623      "learning_rate": 8.673050242605921e-07,624      "loss": 0.8067,625      "step": 405626    },627    {628      "epoch": 0.8384458077709611,629      "grad_norm": 1.2836309671401978,630      "learning_rate": 8.611948312698179e-07,631      "loss": 0.7996,632      "step": 410633    },634    {635      "epoch": 0.8486707566462167,636      "grad_norm": 1.460316777229309,637      "learning_rate": 8.5496968773207e-07,638      "loss": 0.802,639      "step": 415640    },641    {642      "epoch": 0.8588957055214724,643      "grad_norm": 1.33119797706604,644      "learning_rate": 8.486315748043109e-07,645      "loss": 0.798,646      "step": 420647    },648    {649      "epoch": 0.869120654396728,650      "grad_norm": 1.9951454401016235,651      "learning_rate": 8.42182509596102e-07,652      "loss": 0.8013,653      "step": 425654    },655    {656      "epoch": 0.8793456032719836,657      "grad_norm": 1.2590746879577637,658      "learning_rate": 8.356245445276584e-07,659      "loss": 0.7963,660      "step": 430661    },662    {663      "epoch": 0.8895705521472392,664      "grad_norm": 1.1192667484283447,665      "learning_rate": 8.28959766676663e-07,666      "loss": 0.8004,667      "step": 435668    },669    {670      "epoch": 0.8997955010224948,671      "grad_norm": 1.1180275678634644,672      "learning_rate": 8.221902971140535e-07,673      "loss": 0.8041,674      "step": 440675    },676    {677      "epoch": 0.9100204498977505,678      "grad_norm": 1.1210858821868896,679      "learning_rate": 8.153182902289897e-07,680      "loss": 0.7991,681      "step": 445682    },683    {684      "epoch": 0.9202453987730062,685      "grad_norm": 1.1266220808029175,686      "learning_rate": 8.083459330432164e-07,687      "loss": 0.8002,688      "step": 450689    },690    {691      "epoch": 0.9304703476482618,692      "grad_norm": 1.0373694896697998,693      "learning_rate": 8.012754445150434e-07,694      "loss": 0.7974,695      "step": 455696    },697    {698      "epoch": 0.9406952965235174,699      "grad_norm": 1.2223235368728638,700      "learning_rate": 7.941090748331589e-07,701      "loss": 0.8001,702      "step": 460703    },704    {705      "epoch": 0.950920245398773,706      "grad_norm": 1.4549195766448975,707      "learning_rate": 7.868491047005065e-07,708      "loss": 0.7993,709      "step": 465710    },711    {712      "epoch": 0.9611451942740287,713      "grad_norm": 1.3064852952957153,714      "learning_rate": 7.794978446084483e-07,715      "loss": 0.8006,716      "step": 470717    },718    {719      "epoch": 0.9713701431492843,720      "grad_norm": 1.2408719062805176,721      "learning_rate": 7.720576341014498e-07,722      "loss": 0.7983,723      "step": 475724    },725    {726      "epoch": 0.9815950920245399,727      "grad_norm": 1.2148370742797852,728      "learning_rate": 7.645308410325187e-07,729      "loss": 0.7959,730      "step": 480731    },732    {733      "epoch": 0.9918200408997955,734      "grad_norm": 1.0927603244781494,735      "learning_rate": 7.569198608096317e-07,736      "loss": 0.7978,737      "step": 485738    },739    {740      "SWA": "started",741      "epoch": 1.0,742      "step": 489743    },744    {745      "epoch": 1.0020449897750512,746      "grad_norm": 1.245108723640442,747      "learning_rate": 7.492271156333967e-07,748      "loss": 0.7965,749      "step": 490750    },751    {752      "epoch": 1.0122699386503067,753      "grad_norm": 1.3393553495407104,754      "learning_rate": 7.414550537261828e-07,755      "loss": 0.795,756      "step": 495757    },758    {759      "epoch": 1.0224948875255624,760      "grad_norm": 1.2823072671890259,761      "learning_rate": 7.336061485529738e-07,762      "loss": 0.8014,763      "step": 500764    },765    {766      "epoch": 1.0224948875255624,767      "eval_accuracy": 0.60723,768      "eval_loss": 0.6864892244338989,769      "eval_macro_f1": 0.5966241921587988,770      "eval_precision": 0.6341761761282843,771      "eval_recall": 0.6160142746967282,772      "eval_runtime": 81.931,773      "eval_samples_per_second": 1220.539,774      "eval_steps_per_second": 0.598,775      "step": 500776    },777    {778      "epoch": 1.032719836400818,779      "grad_norm": 1.1278107166290283,780      "learning_rate": 7.256828980341846e-07,781      "loss": 0.7977,782      "step": 505783    },784    {785      "epoch": 1.0429447852760736,786      "grad_norm": 1.110093355178833,787      "learning_rate": 7.176878237506965e-07,788      "loss": 0.7954,789      "step": 510790    },791    {792      "epoch": 1.0531697341513293,793      "grad_norm": 1.2248748540878296,794      "learning_rate": 7.096234701413617e-07,795      "loss": 0.7957,796      "step": 515797    },798    {799      "epoch": 1.0633946830265848,800      "grad_norm": 1.2420642375946045,801      "learning_rate": 7.014924036932345e-07,802      "loss": 0.7935,803      "step": 520804    },805    {806      "epoch": 1.0736196319018405,807      "grad_norm": 1.0777639150619507,808      "learning_rate": 6.932972121247831e-07,809      "loss": 0.796,810      "step": 525811    },812    {813      "epoch": 1.0838445807770962,814      "grad_norm": 1.3830324411392212,815      "learning_rate": 6.850405035623481e-07,816      "loss": 0.7929,817      "step": 530818    },819    {820      "epoch": 1.0940695296523517,821      "grad_norm": 0.9407713413238525,822      "learning_rate": 6.767249057101023e-07,823      "loss": 0.7964,824      "step": 535825    },826    {827      "epoch": 1.1042944785276074,828      "grad_norm": 1.1688194274902344,829      "learning_rate": 6.683530650137832e-07,830      "loss": 0.7944,831      "step": 540832    },833    {834      "epoch": 1.114519427402863,835      "grad_norm": 0.9509923458099365,836      "learning_rate": 6.599276458184588e-07,837      "loss": 0.7912,838      "step": 545839    },840    {841      "epoch": 1.1247443762781186,842      "grad_norm": 1.0683159828186035,843      "learning_rate": 6.514513295205969e-07,844      "loss": 0.7931,845      "step": 550846    },847    {848      "epoch": 1.1349693251533743,849      "grad_norm": 0.9022642374038696,850      "learning_rate": 6.429268137147104e-07,851      "loss": 0.7945,852      "step": 555853    },854    {855      "epoch": 1.1451942740286298,856      "grad_norm": 1.1609984636306763,857      "learning_rate": 6.343568113348441e-07,858      "loss": 0.7913,859      "step": 560860    },861    {862      "epoch": 1.1554192229038855,863      "grad_norm": 1.2184994220733643,864      "learning_rate": 6.257440497911815e-07,865      "loss": 0.7919,866      "step": 565867    },868    {869      "epoch": 1.165644171779141,870      "grad_norm": 1.0256582498550415,871      "learning_rate": 6.170912701020454e-07,872      "loss": 0.7912,873      "step": 570874    },875    {876      "epoch": 1.1758691206543967,877      "grad_norm": 0.8725862503051758,878      "learning_rate": 6.084012260215645e-07,879      "loss": 0.7907,880      "step": 575881    },882    {883      "epoch": 1.1860940695296525,884      "grad_norm": 1.5192348957061768,885      "learning_rate": 5.996766831632912e-07,886      "loss": 0.7913,887      "step": 580888    },889    {890      "epoch": 1.196319018404908,891      "grad_norm": 1.109052062034607,892      "learning_rate": 5.909204181200414e-07,893      "loss": 0.795,894      "step": 585895    },896    {897      "epoch": 1.2065439672801637,898      "grad_norm": 1.0413333177566528,899      "learning_rate": 5.821352175802419e-07,900      "loss": 0.7924,901      "step": 590902    },903    {904      "epoch": 1.2167689161554192,905      "grad_norm": 0.8926281929016113,906      "learning_rate": 5.733238774410647e-07,907      "loss": 0.7921,908      "step": 595909    },910    {911      "epoch": 1.2269938650306749,912      "grad_norm": 0.9231971502304077,913      "learning_rate": 5.644892019186307e-07,914      "loss": 0.7894,915      "step": 600916    },917    {918      "epoch": 1.2269938650306749,919      "eval_accuracy": 0.62182,920      "eval_loss": 0.6853985786437988,921      "eval_macro_f1": 0.6195549574374046,922      "eval_precision": 0.6317310781859349,923      "eval_recall": 0.6267089641577176,924      "eval_runtime": 81.4512,925      "eval_samples_per_second": 1227.728,926      "eval_steps_per_second": 0.602,927      "step": 600928    },929    {930      "epoch": 1.2372188139059306,931      "grad_norm": 0.9845394492149353,932      "learning_rate": 5.556340026555653e-07,933      "loss": 0.7918,934      "step": 605935    },936    {937      "epoch": 1.247443762781186,938      "grad_norm": 1.3759487867355347,939      "learning_rate": 5.467610978261906e-07,940      "loss": 0.7904,941      "step": 610942    },943    {944      "epoch": 1.2576687116564418,945      "grad_norm": 1.1568200588226318,946      "learning_rate": 5.378733112396398e-07,947      "loss": 0.7923,948      "step": 615949    },950    {951      "epoch": 1.2678936605316973,952      "grad_norm": 1.4351176023483276,953      "learning_rate": 5.289734714411775e-07,954      "loss": 0.7905,955      "step": 620956    },957    {958      "epoch": 1.278118609406953,959      "grad_norm": 1.178076982498169,960      "learning_rate": 5.200644108120121e-07,961      "loss": 0.7947,962      "step": 625963    },964    {965      "epoch": 1.2883435582822087,966      "grad_norm": 1.2398017644882202,967      "learning_rate": 5.111489646678896e-07,968      "loss": 0.796,969      "step": 630970    },971    {972      "epoch": 1.2985685071574642,973      "grad_norm": 1.1236284971237183,974      "learning_rate": 5.022299703567508e-07,975      "loss": 0.7895,976      "step": 635977    },978    {979      "epoch": 1.30879345603272,980      "grad_norm": 1.0112528800964355,981      "learning_rate": 4.933102663557439e-07,982      "loss": 0.79,983      "step": 640984    },985    {986      "epoch": 1.3190184049079754,987      "grad_norm": 1.3201746940612793,988      "learning_rate": 4.843926913678757e-07,989      "loss": 0.7897,990      "step": 645991    },992    {993      "epoch": 1.329243353783231,994      "grad_norm": 0.969918429851532,995      "learning_rate": 4.7548008341859384e-07,996      "loss": 0.7912,997      "step": 650998    },999    {1000      "epoch": 1.3394683026584868,1001      "grad_norm": 0.8914945125579834,1002      "learning_rate": 4.665752789525812e-07,1003      "loss": 0.7964,1004      "step": 6551005    },1006    {1007      "epoch": 1.3496932515337423,1008      "grad_norm": 0.906989574432373,1009      "learning_rate": 4.576811119310563e-07,1010      "loss": 0.7924,1011      "step": 6601012    },1013    {1014      "epoch": 1.359918200408998,1015      "grad_norm": 1.2423877716064453,1016      "learning_rate": 4.488004129298618e-07,1017      "loss": 0.7904,1018      "step": 6651019    },1020    {1021      "epoch": 1.3701431492842535,1022      "grad_norm": 1.2455909252166748,1023      "learning_rate": 4.3993600823863256e-07,1024      "loss": 0.7875,1025      "step": 6701026    },1027    {1028      "epoch": 1.3803680981595092,1029      "grad_norm": 1.4931528568267822,1030      "learning_rate": 4.3109071896132574e-07,1031      "loss": 0.7947,1032      "step": 6751033    },1034    {1035      "epoch": 1.390593047034765,1036      "grad_norm": 1.0538350343704224,1037      "learning_rate": 4.222673601184029e-07,1038      "loss": 0.7886,1039      "step": 6801040    },1041    {1042      "epoch": 1.4008179959100204,1043      "grad_norm": 0.9246828556060791,1044      "learning_rate": 4.134687397509467e-07,1045      "loss": 0.7884,1046      "step": 6851047    },1048    {1049      "epoch": 1.4110429447852761,1050      "grad_norm": 1.0383715629577637,1051      "learning_rate": 4.0469765802700033e-07,1052      "loss": 0.7943,1053      "step": 6901054    },1055    {1056      "epoch": 1.4212678936605316,1057      "grad_norm": 1.0180901288986206,1058      "learning_rate": 3.9595690635041145e-07,1059      "loss": 0.7895,1060      "step": 6951061    },1062    {1063      "epoch": 1.4314928425357873,1064      "grad_norm": 0.9119181632995605,1065      "learning_rate": 3.8724926647246536e-07,1066      "loss": 0.7864,1067      "step": 7001068    },1069    {1070      "epoch": 1.4314928425357873,1071      "eval_accuracy": 0.62357,1072      "eval_loss": 0.6852650046348572,1073      "eval_macro_f1": 0.6215147432652665,1074      "eval_precision": 0.6330088346022082,1075      "eval_recall": 0.628302383508456,1076      "eval_runtime": 80.5998,1077      "eval_samples_per_second": 1240.698,1078      "eval_steps_per_second": 0.608,1079      "step": 7001080    },1081    {1082      "epoch": 1.441717791411043,1083      "grad_norm": 0.8882152438163757,1084      "learning_rate": 3.785775096065909e-07,1085      "loss": 0.7858,1086      "step": 7051087    },1088    {1089      "epoch": 1.4519427402862985,1090      "grad_norm": 1.5290203094482422,1091      "learning_rate": 3.699443955464192e-07,1092      "loss": 0.7837,1093      "step": 7101094    },1095    {1096      "epoch": 1.4621676891615543,1097      "grad_norm": 0.881521463394165,1098      "learning_rate": 3.613526717874774e-07,1099      "loss": 0.7858,1100      "step": 7151101    },1102    {1103      "epoch": 1.4723926380368098,1104      "grad_norm": 0.9955899119377136,1105      "learning_rate": 3.5280507265279555e-07,1106      "loss": 0.7907,1107      "step": 7201108    },1109    {1110      "epoch": 1.4826175869120655,1111      "grad_norm": 1.3247544765472412,1112      "learning_rate": 3.443043184227067e-07,1113      "loss": 0.79,1114      "step": 7251115    },1116    {1117      "epoch": 1.4928425357873212,1118      "grad_norm": 1.200223445892334,1119      "learning_rate": 3.358531144691148e-07,1120      "loss": 0.7874,1121      "step": 7301122    },1123    {1124      "epoch": 1.5030674846625767,1125      "grad_norm": 0.9952226281166077,1126      "learning_rate": 3.2745415039450867e-07,1127      "loss": 0.7874,1128      "step": 7351129    },1130    {1131      "epoch": 1.5132924335378322,1132      "grad_norm": 1.2515606880187988,1133      "learning_rate": 3.19110099175993e-07,1134      "loss": 0.789,1135      "step": 7401136    },1137    {1138      "epoch": 1.5235173824130879,1139      "grad_norm": 0.8901408314704895,1140      "learning_rate": 3.10823616314612e-07,1141      "loss": 0.7853,1142      "step": 7451143    },1144    {1145      "epoch": 1.5337423312883436,1146      "grad_norm": 1.0439373254776,1147      "learning_rate": 3.0259733899023345e-07,1148      "loss": 0.7899,1149      "step": 7501150    },1151    {1152      "epoch": 1.5439672801635993,1153      "grad_norm": 1.0658971071243286,1154      "learning_rate": 2.944338852222643e-07,1155      "loss": 0.7868,1156      "step": 7551157    },1158    {1159      "epoch": 1.5541922290388548,1160      "grad_norm": 0.927455484867096,1161      "learning_rate": 2.8633585303646413e-07,1162      "loss": 0.7904,1163      "step": 7601164    },1165    {1166      "epoch": 1.5644171779141103,1167      "grad_norm": 0.9637423753738403,1168      "learning_rate": 2.783058196381214e-07,1169      "loss": 0.7856,1170      "step": 7651171    },1172    {1173      "epoch": 1.574642126789366,1174      "grad_norm": 1.396472692489624,1175      "learning_rate": 2.7034634059185437e-07,1176      "loss": 0.7903,1177      "step": 7701178    },1179    {1180      "epoch": 1.5848670756646217,1181      "grad_norm": 0.7922792434692383,1182      "learning_rate": 2.6245994900830257e-07,1183      "loss": 0.7843,1184      "step": 7751185    },1186    {1187      "epoch": 1.5950920245398774,1188      "grad_norm": 0.8896881341934204,1189      "learning_rate": 2.546491547379619e-07,1190      "loss": 0.787,1191      "step": 7801192    },1193    {1194      "epoch": 1.605316973415133,1195      "grad_norm": 0.8732028007507324,1196      "learning_rate": 2.469164435724212e-07,1197      "loss": 0.7856,1198      "step": 7851199    },1200    {

Showing the first 1,200 of 1873 lines. Download the file for the rest.