CoolFace
Modelpublic

patrickvonplaten/hello_2b

sourceHugging Faceupdated 5y agoView on Hugging Face
0likes7downloads
trainer_state.json19754 linesDownload Raw Back to root
1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 29.99310344827586,5  "global_step": 3240,6  "is_hyper_param_search": false,7  "is_local_process_zero": true,8  "is_world_process_zero": true,9  "log_history": [10    {11      "epoch": 0.01,12      "learning_rate": 2e-08,13      "loss": 15.6125,14      "step": 115    },16    {17      "epoch": 0.02,18      "learning_rate": 4e-08,19      "loss": 14.3834,20      "step": 221    },22    {23      "epoch": 0.03,24      "learning_rate": 6.000000000000001e-08,25      "loss": 14.1192,26      "step": 327    },28    {29      "epoch": 0.04,30      "learning_rate": 8e-08,31      "loss": 14.6255,32      "step": 433    },34    {35      "epoch": 0.05,36      "learning_rate": 1.0000000000000001e-07,37      "loss": 13.9643,38      "step": 539    },40    {41      "epoch": 0.06,42      "learning_rate": 1.0000000000000001e-07,43      "loss": 17.6492,44      "step": 645    },46    {47      "epoch": 0.06,48      "learning_rate": 1.0000000000000001e-07,49      "loss": 16.1044,50      "step": 751    },52    {53      "epoch": 0.07,54      "learning_rate": 1.2000000000000002e-07,55      "loss": 14.9581,56      "step": 857    },58    {59      "epoch": 0.08,60      "learning_rate": 1.4e-07,61      "loss": 13.5407,62      "step": 963    },64    {65      "epoch": 0.09,66      "learning_rate": 1.6e-07,67      "loss": 14.5327,68      "step": 1069    },70    {71      "epoch": 0.1,72      "learning_rate": 1.8e-07,73      "loss": 15.2553,74      "step": 1175    },76    {77      "epoch": 0.11,78      "learning_rate": 2.0000000000000002e-07,79      "loss": 16.276,80      "step": 1281    },82    {83      "epoch": 0.12,84      "learning_rate": 2.2e-07,85      "loss": 14.025,86      "step": 1387    },88    {89      "epoch": 0.13,90      "learning_rate": 2.4000000000000003e-07,91      "loss": 14.4253,92      "step": 1493    },94    {95      "epoch": 0.14,96      "learning_rate": 2.6e-07,97      "loss": 13.596,98      "step": 1599    },100    {101      "epoch": 0.15,102      "learning_rate": 2.8e-07,103      "loss": 14.7193,104      "step": 16105    },106    {107      "epoch": 0.16,108      "learning_rate": 3.0000000000000004e-07,109      "loss": 14.0049,110      "step": 17111    },112    {113      "epoch": 0.17,114      "learning_rate": 3.2e-07,115      "loss": 12.7994,116      "step": 18117    },118    {119      "epoch": 0.17,120      "learning_rate": 3.4000000000000003e-07,121      "loss": 13.474,122      "step": 19123    },124    {125      "epoch": 0.18,126      "learning_rate": 3.6e-07,127      "loss": 14.6847,128      "step": 20129    },130    {131      "epoch": 0.19,132      "learning_rate": 3.8e-07,133      "loss": 12.7952,134      "step": 21135    },136    {137      "epoch": 0.2,138      "learning_rate": 4.0000000000000003e-07,139      "loss": 12.9517,140      "step": 22141    },142    {143      "epoch": 0.21,144      "learning_rate": 4.2000000000000006e-07,145      "loss": 15.2301,146      "step": 23147    },148    {149      "epoch": 0.22,150      "learning_rate": 4.2000000000000006e-07,151      "loss": 14.3598,152      "step": 24153    },154    {155      "epoch": 0.23,156      "learning_rate": 4.4e-07,157      "loss": 13.0184,158      "step": 25159    },160    {161      "epoch": 0.24,162      "learning_rate": 4.6000000000000004e-07,163      "loss": 13.9059,164      "step": 26165    },166    {167      "epoch": 0.25,168      "learning_rate": 4.800000000000001e-07,169      "loss": 13.244,170      "step": 27171    },172    {173      "epoch": 0.26,174      "learning_rate": 5.000000000000001e-07,175      "loss": 12.498,176      "step": 28177    },178    {179      "epoch": 0.27,180      "learning_rate": 5.2e-07,181      "loss": 12.5503,182      "step": 29183    },184    {185      "epoch": 0.28,186      "learning_rate": 5.4e-07,187      "loss": 13.2954,188      "step": 30189    },190    {191      "epoch": 0.29,192      "learning_rate": 5.6e-07,193      "loss": 10.6686,194      "step": 31195    },196    {197      "epoch": 0.29,198      "learning_rate": 5.800000000000001e-07,199      "loss": 13.5655,200      "step": 32201    },202    {203      "epoch": 0.3,204      "learning_rate": 6.000000000000001e-07,205      "loss": 13.5897,206      "step": 33207    },208    {209      "epoch": 0.31,210      "learning_rate": 6.200000000000001e-07,211      "loss": 10.7764,212      "step": 34213    },214    {215      "epoch": 0.32,216      "learning_rate": 6.4e-07,217      "loss": 11.7895,218      "step": 35219    },220    {221      "epoch": 0.33,222      "learning_rate": 6.6e-07,223      "loss": 11.029,224      "step": 36225    },226    {227      "epoch": 0.34,228      "learning_rate": 6.6e-07,229      "loss": 9.8552,230      "step": 37231    },232    {233      "epoch": 0.35,234      "learning_rate": 6.800000000000001e-07,235      "loss": 12.1996,236      "step": 38237    },238    {239      "epoch": 0.36,240      "learning_rate": 7.000000000000001e-07,241      "loss": 10.6448,242      "step": 39243    },244    {245      "epoch": 0.37,246      "learning_rate": 7.2e-07,247      "loss": 9.2266,248      "step": 40249    },250    {251      "epoch": 0.38,252      "learning_rate": 7.4e-07,253      "loss": 9.3842,254      "step": 41255    },256    {257      "epoch": 0.39,258      "learning_rate": 7.6e-07,259      "loss": 9.9854,260      "step": 42261    },262    {263      "epoch": 0.4,264      "learning_rate": 7.8e-07,265      "loss": 8.8267,266      "step": 43267    },268    {269      "epoch": 0.4,270      "learning_rate": 8.000000000000001e-07,271      "loss": 9.5824,272      "step": 44273    },274    {275      "epoch": 0.41,276      "learning_rate": 8.200000000000001e-07,277      "loss": 8.3395,278      "step": 45279    },280    {281      "epoch": 0.42,282      "learning_rate": 8.400000000000001e-07,283      "loss": 7.8379,284      "step": 46285    },286    {287      "epoch": 0.43,288      "learning_rate": 8.6e-07,289      "loss": 8.333,290      "step": 47291    },292    {293      "epoch": 0.44,294      "learning_rate": 8.8e-07,295      "loss": 7.5948,296      "step": 48297    },298    {299      "epoch": 0.45,300      "learning_rate": 9.000000000000001e-07,301      "loss": 6.6517,302      "step": 49303    },304    {305      "epoch": 0.46,306      "learning_rate": 9.200000000000001e-07,307      "loss": 6.71,308      "step": 50309    },310    {311      "epoch": 0.47,312      "learning_rate": 9.400000000000001e-07,313      "loss": 6.2793,314      "step": 51315    },316    {317      "epoch": 0.48,318      "learning_rate": 9.600000000000001e-07,319      "loss": 5.7408,320      "step": 52321    },322    {323      "epoch": 0.49,324      "learning_rate": 9.800000000000001e-07,325      "loss": 5.4254,326      "step": 53327    },328    {329      "epoch": 0.5,330      "learning_rate": 1.0000000000000002e-06,331      "loss": 5.1803,332      "step": 54333    },334    {335      "epoch": 0.51,336      "learning_rate": 1.02e-06,337      "loss": 4.5298,338      "step": 55339    },340    {341      "epoch": 0.51,342      "learning_rate": 1.04e-06,343      "loss": 4.3988,344      "step": 56345    },346    {347      "epoch": 0.52,348      "learning_rate": 1.06e-06,349      "loss": 4.29,350      "step": 57351    },352    {353      "epoch": 0.53,354      "learning_rate": 1.08e-06,355      "loss": 4.0272,356      "step": 58357    },358    {359      "epoch": 0.54,360      "learning_rate": 1.1e-06,361      "loss": 3.9508,362      "step": 59363    },364    {365      "epoch": 0.55,366      "learning_rate": 1.12e-06,367      "loss": 4.084,368      "step": 60369    },370    {371      "epoch": 0.56,372      "learning_rate": 1.14e-06,373      "loss": 3.8152,374      "step": 61375    },376    {377      "epoch": 0.57,378      "learning_rate": 1.1600000000000001e-06,379      "loss": 3.8503,380      "step": 62381    },382    {383      "epoch": 0.58,384      "learning_rate": 1.1800000000000001e-06,385      "loss": 3.8557,386      "step": 63387    },388    {389      "epoch": 0.59,390      "learning_rate": 1.2000000000000002e-06,391      "loss": 3.8566,392      "step": 64393    },394    {395      "epoch": 0.6,396      "learning_rate": 1.2200000000000002e-06,397      "loss": 3.8701,398      "step": 65399    },400    {401      "epoch": 0.61,402      "learning_rate": 1.2400000000000002e-06,403      "loss": 3.8901,404      "step": 66405    },406    {407      "epoch": 0.62,408      "learning_rate": 1.26e-06,409      "loss": 3.7997,410      "step": 67411    },412    {413      "epoch": 0.63,414      "learning_rate": 1.28e-06,415      "loss": 3.7898,416      "step": 68417    },418    {419      "epoch": 0.63,420      "learning_rate": 1.3e-06,421      "loss": 3.7657,422      "step": 69423    },424    {425      "epoch": 0.64,426      "learning_rate": 1.32e-06,427      "loss": 3.7088,428      "step": 70429    },430    {431      "epoch": 0.65,432      "learning_rate": 1.34e-06,433      "loss": 3.7135,434      "step": 71435    },436    {437      "epoch": 0.66,438      "learning_rate": 1.3600000000000001e-06,439      "loss": 3.6795,440      "step": 72441    },442    {443      "epoch": 0.67,444      "learning_rate": 1.3800000000000001e-06,445      "loss": 3.6537,446      "step": 73447    },448    {449      "epoch": 0.68,450      "learning_rate": 1.4000000000000001e-06,451      "loss": 3.5713,452      "step": 74453    },454    {455      "epoch": 0.69,456      "learning_rate": 1.42e-06,457      "loss": 3.5568,458      "step": 75459    },460    {461      "epoch": 0.7,462      "learning_rate": 1.44e-06,463      "loss": 3.4995,464      "step": 76465    },466    {467      "epoch": 0.71,468      "learning_rate": 1.46e-06,469      "loss": 3.5318,470      "step": 77471    },472    {473      "epoch": 0.72,474      "learning_rate": 1.48e-06,475      "loss": 3.5824,476      "step": 78477    },478    {479      "epoch": 0.73,480      "learning_rate": 1.5e-06,481      "loss": 3.4513,482      "step": 79483    },484    {485      "epoch": 0.74,486      "learning_rate": 1.52e-06,487      "loss": 3.435,488      "step": 80489    },490    {491      "epoch": 0.74,492      "learning_rate": 1.54e-06,493      "loss": 3.4863,494      "step": 81495    },496    {497      "epoch": 0.75,498      "learning_rate": 1.56e-06,499      "loss": 3.4667,500      "step": 82501    },502    {503      "epoch": 0.76,504      "learning_rate": 1.5800000000000001e-06,505      "loss": 3.3752,506      "step": 83507    },508    {509      "epoch": 0.77,510      "learning_rate": 1.6000000000000001e-06,511      "loss": 3.3746,512      "step": 84513    },514    {515      "epoch": 0.78,516      "learning_rate": 1.6200000000000002e-06,517      "loss": 3.6092,518      "step": 85519    },520    {521      "epoch": 0.79,522      "learning_rate": 1.6400000000000002e-06,523      "loss": 3.3079,524      "step": 86525    },526    {527      "epoch": 0.8,528      "learning_rate": 1.6600000000000002e-06,529      "loss": 3.3401,530      "step": 87531    },532    {533      "epoch": 0.81,534      "learning_rate": 1.6800000000000002e-06,535      "loss": 3.3808,536      "step": 88537    },538    {539      "epoch": 0.82,540      "learning_rate": 1.7000000000000002e-06,541      "loss": 3.3068,542      "step": 89543    },544    {545      "epoch": 0.83,546      "learning_rate": 1.72e-06,547      "loss": 3.2597,548      "step": 90549    },550    {551      "epoch": 0.84,552      "learning_rate": 1.74e-06,553      "loss": 3.2623,554      "step": 91555    },556    {557      "epoch": 0.85,558      "learning_rate": 1.76e-06,559      "loss": 3.2299,560      "step": 92561    },562    {563      "epoch": 0.86,564      "learning_rate": 1.7800000000000001e-06,565      "loss": 3.2305,566      "step": 93567    },568    {569      "epoch": 0.86,570      "learning_rate": 1.8000000000000001e-06,571      "loss": 3.3822,572      "step": 94573    },574    {575      "epoch": 0.87,576      "learning_rate": 1.8200000000000002e-06,577      "loss": 3.1923,578      "step": 95579    },580    {581      "epoch": 0.88,582      "learning_rate": 1.8400000000000002e-06,583      "loss": 3.2007,584      "step": 96585    },586    {587      "epoch": 0.89,588      "learning_rate": 1.8600000000000002e-06,589      "loss": 3.1704,590      "step": 97591    },592    {593      "epoch": 0.9,594      "learning_rate": 1.8800000000000002e-06,595      "loss": 3.1524,596      "step": 98597    },598    {599      "epoch": 0.91,600      "learning_rate": 1.9000000000000002e-06,601      "loss": 3.1479,602      "step": 99603    },604    {605      "epoch": 0.92,606      "learning_rate": 1.9200000000000003e-06,607      "loss": 3.1646,608      "step": 100609    },610    {611      "epoch": 0.92,612      "eval_loss": 3.210620641708374,613      "eval_runtime": 65.7809,614      "eval_samples_per_second": 25.038,615      "eval_steps_per_second": 1.566,616      "eval_wer": 1.0,617      "step": 100618    },619    {620      "epoch": 0.93,621      "learning_rate": 1.94e-06,622      "loss": 3.1444,623      "step": 101624    },625    {626      "epoch": 0.94,627      "learning_rate": 1.9600000000000003e-06,628      "loss": 3.1609,629      "step": 102630    },631    {632      "epoch": 0.95,633      "learning_rate": 1.98e-06,634      "loss": 3.1686,635      "step": 103636    },637    {638      "epoch": 0.96,639      "learning_rate": 2.0000000000000003e-06,640      "loss": 3.1571,641      "step": 104642    },643    {644      "epoch": 0.97,645      "learning_rate": 2.02e-06,646      "loss": 3.156,647      "step": 105648    },649    {650      "epoch": 0.97,651      "learning_rate": 2.04e-06,652      "loss": 3.1405,653      "step": 106654    },655    {656      "epoch": 0.98,657      "learning_rate": 2.06e-06,658      "loss": 3.1422,659      "step": 107660    },661    {662      "epoch": 0.99,663      "learning_rate": 2.08e-06,664      "loss": 3.1269,665      "step": 108666    },667    {668      "epoch": 1.01,669      "learning_rate": 2.1000000000000002e-06,670      "loss": 5.4893,671      "step": 109672    },673    {674      "epoch": 1.02,675      "learning_rate": 2.12e-06,676      "loss": 3.0968,677      "step": 110678    },679    {680      "epoch": 1.03,681      "learning_rate": 2.1400000000000003e-06,682      "loss": 3.0483,683      "step": 111684    },685    {686      "epoch": 1.04,687      "learning_rate": 2.16e-06,688      "loss": 3.1096,689      "step": 112690    },691    {692      "epoch": 1.05,693      "learning_rate": 2.1800000000000003e-06,694      "loss": 3.0971,695      "step": 113696    },697    {698      "epoch": 1.06,699      "learning_rate": 2.2e-06,700      "loss": 3.0985,701      "step": 114702    },703    {704      "epoch": 1.06,705      "learning_rate": 2.2200000000000003e-06,706      "loss": 3.1238,707      "step": 115708    },709    {710      "epoch": 1.07,711      "learning_rate": 2.24e-06,712      "loss": 3.0668,713      "step": 116714    },715    {716      "epoch": 1.08,717      "learning_rate": 2.2600000000000004e-06,718      "loss": 3.0742,719      "step": 117720    },721    {722      "epoch": 1.09,723      "learning_rate": 2.28e-06,724      "loss": 3.0523,725      "step": 118726    },727    {728      "epoch": 1.1,729      "learning_rate": 2.3000000000000004e-06,730      "loss": 3.0594,731      "step": 119732    },733    {734      "epoch": 1.11,735      "learning_rate": 2.3200000000000002e-06,736      "loss": 2.9866,737      "step": 120738    },739    {740      "epoch": 1.12,741      "learning_rate": 2.3400000000000005e-06,742      "loss": 2.9892,743      "step": 121744    },745    {746      "epoch": 1.13,747      "learning_rate": 2.3600000000000003e-06,748      "loss": 2.9748,749      "step": 122750    },751    {752      "epoch": 1.14,753      "learning_rate": 2.38e-06,754      "loss": 2.984,755      "step": 123756    },757    {758      "epoch": 1.15,759      "learning_rate": 2.4000000000000003e-06,760      "loss": 3.0392,761      "step": 124762    },763    {764      "epoch": 1.16,765      "learning_rate": 2.42e-06,766      "loss": 2.9758,767      "step": 125768    },769    {770      "epoch": 1.17,771      "learning_rate": 2.4400000000000004e-06,772      "loss": 2.9587,773      "step": 126774    },775    {776      "epoch": 1.17,777      "learning_rate": 2.46e-06,778      "loss": 3.0037,779      "step": 127780    },781    {782      "epoch": 1.18,783      "learning_rate": 2.4800000000000004e-06,784      "loss": 2.9908,785      "step": 128786    },787    {788      "epoch": 1.19,789      "learning_rate": 2.5e-06,790      "loss": 2.8789,791      "step": 129792    },793    {794      "epoch": 1.2,795      "learning_rate": 2.52e-06,796      "loss": 2.9244,797      "step": 130798    },799    {800      "epoch": 1.21,801      "learning_rate": 2.5400000000000002e-06,802      "loss": 2.844,803      "step": 131804    },805    {806      "epoch": 1.22,807      "learning_rate": 2.56e-06,808      "loss": 2.8837,809      "step": 132810    },811    {812      "epoch": 1.23,813      "learning_rate": 2.5800000000000003e-06,814      "loss": 2.8248,815      "step": 133816    },817    {818      "epoch": 1.24,819      "learning_rate": 2.6e-06,820      "loss": 2.8488,821      "step": 134822    },823    {824      "epoch": 1.25,825      "learning_rate": 2.6200000000000003e-06,826      "loss": 2.8064,827      "step": 135828    },829    {830      "epoch": 1.26,831      "learning_rate": 2.64e-06,832      "loss": 2.752,833      "step": 136834    },835    {836      "epoch": 1.27,837      "learning_rate": 2.6600000000000004e-06,838      "loss": 2.7703,839      "step": 137840    },841    {842      "epoch": 1.28,843      "learning_rate": 2.68e-06,844      "loss": 2.7082,845      "step": 138846    },847    {848      "epoch": 1.29,849      "learning_rate": 2.7000000000000004e-06,850      "loss": 2.632,851      "step": 139852    },853    {854      "epoch": 1.29,855      "learning_rate": 2.7200000000000002e-06,856      "loss": 2.6731,857      "step": 140858    },859    {860      "epoch": 1.3,861      "learning_rate": 2.7400000000000004e-06,862      "loss": 2.6164,863      "step": 141864    },865    {866      "epoch": 1.31,867      "learning_rate": 2.7600000000000003e-06,868      "loss": 2.5367,869      "step": 142870    },871    {872      "epoch": 1.32,873      "learning_rate": 2.7800000000000005e-06,874      "loss": 2.4815,875      "step": 143876    },877    {878      "epoch": 1.33,879      "learning_rate": 2.8000000000000003e-06,880      "loss": 2.4263,881      "step": 144882    },883    {884      "epoch": 1.34,885      "learning_rate": 2.82e-06,886      "loss": 2.3901,887      "step": 145888    },889    {890      "epoch": 1.35,891      "learning_rate": 2.84e-06,892      "loss": 2.3535,893      "step": 146894    },895    {896      "epoch": 1.36,897      "learning_rate": 2.86e-06,898      "loss": 2.2753,899      "step": 147900    },901    {902      "epoch": 1.37,903      "learning_rate": 2.88e-06,904      "loss": 2.1824,905      "step": 148906    },907    {908      "epoch": 1.38,909      "learning_rate": 2.9e-06,910      "loss": 2.1984,911      "step": 149912    },913    {914      "epoch": 1.39,915      "learning_rate": 2.92e-06,916      "loss": 2.0474,917      "step": 150918    },919    {920      "epoch": 1.4,921      "learning_rate": 2.9400000000000002e-06,922      "loss": 2.0605,923      "step": 151924    },925    {926      "epoch": 1.4,927      "learning_rate": 2.96e-06,928      "loss": 1.9639,929      "step": 152930    },931    {932      "epoch": 1.41,933      "learning_rate": 2.9800000000000003e-06,934      "loss": 1.9454,935      "step": 153936    },937    {938      "epoch": 1.42,939      "learning_rate": 3e-06,940      "loss": 1.8509,941      "step": 154942    },943    {944      "epoch": 1.43,945      "learning_rate": 3.0200000000000003e-06,946      "loss": 1.8947,947      "step": 155948    },949    {950      "epoch": 1.44,951      "learning_rate": 3.04e-06,952      "loss": 1.6702,953      "step": 156954    },955    {956      "epoch": 1.45,957      "learning_rate": 3.0600000000000003e-06,958      "loss": 1.6755,959      "step": 157960    },961    {962      "epoch": 1.46,963      "learning_rate": 3.08e-06,964      "loss": 1.6647,965      "step": 158966    },967    {968      "epoch": 1.47,969      "learning_rate": 3.1000000000000004e-06,970      "loss": 1.4576,971      "step": 159972    },973    {974      "epoch": 1.48,975      "learning_rate": 3.12e-06,976      "loss": 1.4793,977      "step": 160978    },979    {980      "epoch": 1.49,981      "learning_rate": 3.1400000000000004e-06,982      "loss": 1.3493,983      "step": 161984    },985    {986      "epoch": 1.5,987      "learning_rate": 3.1600000000000002e-06,988      "loss": 1.2696,989      "step": 162990    },991    {992      "epoch": 1.51,993      "learning_rate": 3.1800000000000005e-06,994      "loss": 1.2714,995      "step": 163996    },997    {998      "epoch": 1.51,999      "learning_rate": 3.2000000000000003e-06,1000      "loss": 1.1438,1001      "step": 1641002    },1003    {1004      "epoch": 1.52,1005      "learning_rate": 3.2200000000000005e-06,1006      "loss": 1.0983,1007      "step": 1651008    },1009    {1010      "epoch": 1.53,1011      "learning_rate": 3.2400000000000003e-06,1012      "loss": 1.1143,1013      "step": 1661014    },1015    {1016      "epoch": 1.54,1017      "learning_rate": 3.2600000000000006e-06,1018      "loss": 1.0719,1019      "step": 1671020    },1021    {1022      "epoch": 1.55,1023      "learning_rate": 3.2800000000000004e-06,1024      "loss": 0.9655,1025      "step": 1681026    },1027    {1028      "epoch": 1.56,1029      "learning_rate": 3.3000000000000006e-06,1030      "loss": 0.962,1031      "step": 1691032    },1033    {1034      "epoch": 1.57,1035      "learning_rate": 3.3200000000000004e-06,1036      "loss": 0.9304,1037      "step": 1701038    },1039    {1040      "epoch": 1.58,1041      "learning_rate": 3.3400000000000006e-06,1042      "loss": 0.8993,1043      "step": 1711044    },1045    {1046      "epoch": 1.59,1047      "learning_rate": 3.3600000000000004e-06,1048      "loss": 0.8029,1049      "step": 1721050    },1051    {1052      "epoch": 1.6,1053      "learning_rate": 3.3800000000000007e-06,1054      "loss": 0.7713,1055      "step": 1731056    },1057    {1058      "epoch": 1.61,1059      "learning_rate": 3.4000000000000005e-06,1060      "loss": 0.8287,1061      "step": 1741062    },1063    {1064      "epoch": 1.62,1065      "learning_rate": 3.4200000000000007e-06,1066      "loss": 0.7307,1067      "step": 1751068    },1069    {1070      "epoch": 1.63,1071      "learning_rate": 3.44e-06,1072      "loss": 0.7621,1073      "step": 1761074    },1075    {1076      "epoch": 1.63,1077      "learning_rate": 3.46e-06,1078      "loss": 0.7228,1079      "step": 1771080    },1081    {1082      "epoch": 1.64,1083      "learning_rate": 3.48e-06,1084      "loss": 0.5989,1085      "step": 1781086    },1087    {1088      "epoch": 1.65,1089      "learning_rate": 3.5e-06,1090      "loss": 0.6095,1091      "step": 1791092    },1093    {1094      "epoch": 1.66,1095      "learning_rate": 3.52e-06,1096      "loss": 0.6489,1097      "step": 1801098    },1099    {1100      "epoch": 1.67,1101      "learning_rate": 3.54e-06,1102      "loss": 0.6002,1103      "step": 1811104    },1105    {1106      "epoch": 1.68,1107      "learning_rate": 3.5600000000000002e-06,1108      "loss": 0.5754,1109      "step": 1821110    },1111    {1112      "epoch": 1.69,1113      "learning_rate": 3.58e-06,1114      "loss": 0.6392,1115      "step": 1831116    },1117    {1118      "epoch": 1.7,1119      "learning_rate": 3.6000000000000003e-06,1120      "loss": 0.5334,1121      "step": 1841122    },1123    {1124      "epoch": 1.71,1125      "learning_rate": 3.62e-06,1126      "loss": 0.5087,1127      "step": 1851128    },1129    {1130      "epoch": 1.72,1131      "learning_rate": 3.6400000000000003e-06,1132      "loss": 0.5398,1133      "step": 1861134    },1135    {1136      "epoch": 1.73,1137      "learning_rate": 3.66e-06,1138      "loss": 0.5603,1139      "step": 1871140    },1141    {1142      "epoch": 1.74,1143      "learning_rate": 3.6800000000000003e-06,1144      "loss": 0.4915,1145      "step": 1881146    },1147    {1148      "epoch": 1.74,1149      "learning_rate": 3.7e-06,1150      "loss": 0.6469,1151      "step": 1891152    },1153    {1154      "epoch": 1.75,1155      "learning_rate": 3.7200000000000004e-06,1156      "loss": 0.4197,1157      "step": 1901158    },1159    {1160      "epoch": 1.76,1161      "learning_rate": 3.74e-06,1162      "loss": 0.5177,1163      "step": 1911164    },1165    {1166      "epoch": 1.77,1167      "learning_rate": 3.7600000000000004e-06,1168      "loss": 0.4551,1169      "step": 1921170    },1171    {1172      "epoch": 1.78,1173      "learning_rate": 3.7800000000000002e-06,1174      "loss": 0.5005,1175      "step": 1931176    },1177    {1178      "epoch": 1.79,1179      "learning_rate": 3.8000000000000005e-06,1180      "loss": 0.4125,1181      "step": 1941182    },1183    {1184      "epoch": 1.8,1185      "learning_rate": 3.820000000000001e-06,1186      "loss": 0.443,1187      "step": 1951188    },1189    {1190      "epoch": 1.81,1191      "learning_rate": 3.8400000000000005e-06,1192      "loss": 0.4782,1193      "step": 1961194    },1195    {1196      "epoch": 1.82,1197      "learning_rate": 3.86e-06,1198      "loss": 0.3756,1199      "step": 1971200    },

Showing the first 1,200 of 19754 lines. Download the file for the rest.