CoolFace
Modelpublic

gethoney/moderation

sourceHugging Faceupdated 10mo agoView on Hugging Face
0likes4downloads
trainer_state.json610 linesDownload Raw Back to root
1{2  "best_global_step": null,3  "best_metric": null,4  "best_model_checkpoint": null,5  "epoch": 3.0,6  "eval_steps": 81,7  "global_step": 81,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 0.037037037037037035,14      "grad_norm": 27.625,15      "learning_rate": 0.0003,16      "loss": 7.5734,17      "step": 118    },19    {20      "epoch": 0.07407407407407407,21      "grad_norm": 7.78125,22      "learning_rate": 0.0002998871928756345,23      "loss": 1.8836,24      "step": 225    },26    {27      "epoch": 0.1111111111111111,28      "grad_norm": 2.34375,29      "learning_rate": 0.0002995489411751688,30      "loss": 0.4221,31      "step": 332    },33    {34      "epoch": 0.14814814814814814,35      "grad_norm": 12.375,36      "learning_rate": 0.00029898575366129145,37      "loss": 1.3091,38      "step": 439    },40    {41      "epoch": 0.18518518518518517,42      "grad_norm": 17.5,43      "learning_rate": 0.0002981984774215213,44      "loss": 3.4129,45      "step": 546    },47    {48      "epoch": 0.2222222222222222,49      "grad_norm": 2.140625,50      "learning_rate": 0.00029718829659410766,51      "loss": 0.4298,52      "step": 653    },54    {55      "epoch": 0.25925925925925924,56      "grad_norm": 3.96875,57      "learning_rate": 0.00029595673058697357,58      "loss": 0.1712,59      "step": 760    },61    {62      "epoch": 0.2962962962962963,63      "grad_norm": 0.41796875,64      "learning_rate": 0.000294505631792382,65      "loss": 0.0804,66      "step": 867    },68    {69      "epoch": 0.3333333333333333,70      "grad_norm": 4.3125,71      "learning_rate": 0.00029283718280076227,72      "loss": 0.6341,73      "step": 974    },75    {76      "epoch": 0.37037037037037035,77      "grad_norm": 9.4375,78      "learning_rate": 0.0002909538931178862,79      "loss": 1.3757,80      "step": 1081    },82    {83      "epoch": 0.4074074074074074,84      "grad_norm": 2.484375,85      "learning_rate": 0.00028885859539033357,86      "loss": 0.3671,87      "step": 1188    },89    {90      "epoch": 0.4444444444444444,91      "grad_norm": 3.046875,92      "learning_rate": 0.000286554441144922,93      "loss": 0.8087,94      "step": 1295    },96    {97      "epoch": 0.48148148148148145,98      "grad_norm": 1.6484375,99      "learning_rate": 0.0002840448960485118,100      "loss": 0.3402,101      "step": 13102    },103    {104      "epoch": 0.5185185185185185,105      "grad_norm": 2.109375,106      "learning_rate": 0.00028133373469531363,107      "loss": 0.338,108      "step": 14109    },110    {111      "epoch": 0.5555555555555556,112      "grad_norm": 50.25,113      "learning_rate": 0.00027842503492953995,114      "loss": 0.5713,115      "step": 15116    },117    {118      "epoch": 0.5925925925925926,119      "grad_norm": 1.296875,120      "learning_rate": 0.00027532317171194046,121      "loss": 0.3056,122      "step": 16123    },124    {125      "epoch": 0.6296296296296297,126      "grad_norm": 1.9296875,127      "learning_rate": 0.0002720328105394451,128      "loss": 0.3462,129      "step": 17130    },131    {132      "epoch": 0.6666666666666666,133      "grad_norm": 1.7421875,134      "learning_rate": 0.00026855890042781387,135      "loss": 0.3946,136      "step": 18137    },138    {139      "epoch": 0.7037037037037037,140      "grad_norm": 0.76171875,141      "learning_rate": 0.00026490666646784665,142      "loss": 0.2438,143      "step": 19144    },145    {146      "epoch": 0.7407407407407407,147      "grad_norm": 0.9140625,148      "learning_rate": 0.00026108160196635066,149      "loss": 0.2663,150      "step": 20151    },152    {153      "epoch": 0.7777777777777778,154      "grad_norm": 5.59375,155      "learning_rate": 0.00025708946018368484,156      "loss": 0.5623,157      "step": 21158    },159    {160      "epoch": 0.8148148148148148,161      "grad_norm": 1.796875,162      "learning_rate": 0.00025293624568031,163      "loss": 0.2297,164      "step": 22165    },166    {167      "epoch": 0.8518518518518519,168      "grad_norm": 1.375,169      "learning_rate": 0.00024862820528535954,170      "loss": 0.4665,171      "step": 23172    },173    {174      "epoch": 0.8888888888888888,175      "grad_norm": 1.1953125,176      "learning_rate": 0.0002441718187008148,177      "loss": 0.1926,178      "step": 24179    },180    {181      "epoch": 0.9259259259259259,182      "grad_norm": 3.609375,183      "learning_rate": 0.00023957378875541792,184      "loss": 0.533,185      "step": 25186    },187    {188      "epoch": 0.9629629629629629,189      "grad_norm": 15.4375,190      "learning_rate": 0.00023484103132298079,191      "loss": 0.6521,192      "step": 26193    },194    {195      "epoch": 1.0,196      "grad_norm": 19.625,197      "learning_rate": 0.0002299806649202537,198      "loss": 0.4345,199      "step": 27200    },201    {202      "epoch": 1.037037037037037,203      "grad_norm": 1.453125,204      "learning_rate": 0.000225,205      "loss": 0.28,206      "step": 28207    },208    {209      "epoch": 1.074074074074074,210      "grad_norm": 1.0859375,211      "learning_rate": 0.00021990652795538082,212      "loss": 0.2518,213      "step": 29214    },215    {216      "epoch": 1.1111111111111112,217      "grad_norm": 4.59375,218      "learning_rate": 0.00021470790985218802,219      "loss": 0.2764,220      "step": 30221    },222    {223      "epoch": 1.1481481481481481,224      "grad_norm": 1.3203125,225      "learning_rate": 0.0002094119649058735,226      "loss": 0.3554,227      "step": 31228    },229    {230      "epoch": 1.1851851851851851,231      "grad_norm": 1.4765625,232      "learning_rate": 0.00020402665872070654,233      "loss": 0.2718,234      "step": 32235    },236    {237      "epoch": 1.2222222222222223,238      "grad_norm": 1.109375,239      "learning_rate": 0.00019856009130874816,240      "loss": 0.1842,241      "step": 33242    },243    {244      "epoch": 1.2592592592592593,245      "grad_norm": 1.0390625,246      "learning_rate": 0.00019302048490666353,247      "loss": 0.1867,248      "step": 34249    },250    {251      "epoch": 1.2962962962962963,252      "grad_norm": 0.83984375,253      "learning_rate": 0.00018741617160869718,254      "loss": 0.1935,255      "step": 35256    },257    {258      "epoch": 1.3333333333333333,259      "grad_norm": 0.98828125,260      "learning_rate": 0.00018175558083441162,261      "loss": 0.1352,262      "step": 36263    },264    {265      "epoch": 1.3703703703703702,266      "grad_norm": 1.9140625,267      "learning_rate": 0.00017604722665003956,268      "loss": 0.2805,269      "step": 37270    },271    {272      "epoch": 1.4074074074074074,273      "grad_norm": 0.6640625,274      "learning_rate": 0.00017029969496251966,275      "loss": 0.1006,276      "step": 38277    },278    {279      "epoch": 1.4444444444444444,280      "grad_norm": 1.125,281      "learning_rate": 0.00016452163060547687,282      "loss": 0.1406,283      "step": 39284    },285    {286      "epoch": 1.4814814814814814,287      "grad_norm": 0.81640625,288      "learning_rate": 0.00015872172433657134,289      "loss": 0.0966,290      "step": 40291    },292    {293      "epoch": 1.5185185185185186,294      "grad_norm": 1.3984375,295      "learning_rate": 0.00015290869976577364,296      "loss": 0.2579,297      "step": 41298    },299    {300      "epoch": 1.5555555555555556,301      "grad_norm": 1.1171875,302      "learning_rate": 0.00014709130023422633,303      "loss": 0.1991,304      "step": 42305    },306    {307      "epoch": 1.5925925925925926,308      "grad_norm": 1.140625,309      "learning_rate": 0.00014127827566342863,310      "loss": 0.2034,311      "step": 43312    },313    {314      "epoch": 1.6296296296296298,315      "grad_norm": 0.62890625,316      "learning_rate": 0.00013547836939452313,317      "loss": 0.1011,318      "step": 44319    },320    {321      "epoch": 1.6666666666666665,322      "grad_norm": 1.3203125,323      "learning_rate": 0.00012970030503748036,324      "loss": 0.1216,325      "step": 45326    },327    {328      "epoch": 1.7037037037037037,329      "grad_norm": 5.0,330      "learning_rate": 0.00012395277334996044,331      "loss": 0.235,332      "step": 46333    },334    {335      "epoch": 1.7407407407407407,336      "grad_norm": 3.296875,337      "learning_rate": 0.00011824441916558842,338      "loss": 0.3172,339      "step": 47340    },341    {342      "epoch": 1.7777777777777777,343      "grad_norm": 1.265625,344      "learning_rate": 0.00011258382839130281,345      "loss": 0.1774,346      "step": 48347    },348    {349      "epoch": 1.8148148148148149,350      "grad_norm": 1.1171875,351      "learning_rate": 0.0001069795150933365,352      "loss": 0.1706,353      "step": 49354    },355    {356      "epoch": 1.8518518518518519,357      "grad_norm": 0.9609375,358      "learning_rate": 0.00010143990869125184,359      "loss": 0.2188,360      "step": 50361    },362    {363      "epoch": 1.8888888888888888,364      "grad_norm": 0.8203125,365      "learning_rate": 9.597334127929346e-05,366      "loss": 0.2991,367      "step": 51368    },369    {370      "epoch": 1.925925925925926,371      "grad_norm": 1.40625,372      "learning_rate": 9.058803509412646e-05,373      "loss": 0.2037,374      "step": 52375    },376    {377      "epoch": 1.9629629629629628,378      "grad_norm": 0.546875,379      "learning_rate": 8.529209014781201e-05,380      "loss": 0.2029,381      "step": 53382    },383    {384      "epoch": 2.0,385      "grad_norm": 0.54296875,386      "learning_rate": 8.009347204461921e-05,387      "loss": 0.1574,388      "step": 54389    },390    {391      "epoch": 2.037037037037037,392      "grad_norm": 0.796875,393      "learning_rate": 7.500000000000002e-05,394      "loss": 0.1279,395      "step": 55396    },397    {398      "epoch": 2.074074074074074,399      "grad_norm": 0.39453125,400      "learning_rate": 7.001933507974633e-05,401      "loss": 0.1127,402      "step": 56403    },404    {405      "epoch": 2.111111111111111,406      "grad_norm": 0.66796875,407      "learning_rate": 6.515896867701923e-05,408      "loss": 0.1211,409      "step": 57410    },411    {412      "epoch": 2.148148148148148,413      "grad_norm": 0.33203125,414      "learning_rate": 6.04262112445821e-05,415      "loss": 0.0949,416      "step": 58417    },418    {419      "epoch": 2.185185185185185,420      "grad_norm": 0.84765625,421      "learning_rate": 5.582818129918524e-05,422      "loss": 0.1086,423      "step": 59424    },425    {426      "epoch": 2.2222222222222223,427      "grad_norm": 0.62890625,428      "learning_rate": 5.137179471464047e-05,429      "loss": 0.1671,430      "step": 60431    },432    {433      "epoch": 2.259259259259259,434      "grad_norm": 0.64453125,435      "learning_rate": 4.706375431968997e-05,436      "loss": 0.1354,437      "step": 61438    },439    {440      "epoch": 2.2962962962962963,441      "grad_norm": 0.9453125,442      "learning_rate": 4.2910539816315164e-05,443      "loss": 0.1621,444      "step": 62445    },446    {447      "epoch": 2.3333333333333335,448      "grad_norm": 0.828125,449      "learning_rate": 3.891839803364934e-05,450      "loss": 0.069,451      "step": 63452    },453    {454      "epoch": 2.3703703703703702,455      "grad_norm": 0.734375,456      "learning_rate": 3.509333353215331e-05,457      "loss": 0.1796,458      "step": 64459    },460    {461      "epoch": 2.4074074074074074,462      "grad_norm": 0.65234375,463      "learning_rate": 3.144109957218612e-05,464      "loss": 0.1112,465      "step": 65466    },467    {468      "epoch": 2.4444444444444446,469      "grad_norm": 0.80078125,470      "learning_rate": 2.7967189460554872e-05,471      "loss": 0.1915,472      "step": 66473    },474    {475      "epoch": 2.4814814814814814,476      "grad_norm": 0.298828125,477      "learning_rate": 2.4676828288059558e-05,478      "loss": 0.0934,479      "step": 67480    },481    {482      "epoch": 2.5185185185185186,483      "grad_norm": 0.57421875,484      "learning_rate": 2.1574965070460043e-05,485      "loss": 0.0809,486      "step": 68487    },488    {489      "epoch": 2.5555555555555554,490      "grad_norm": 0.1611328125,491      "learning_rate": 1.8666265304686383e-05,492      "loss": 0.0554,493      "step": 69494    },495    {496      "epoch": 2.5925925925925926,497      "grad_norm": 0.546875,498      "learning_rate": 1.5955103951488173e-05,499      "loss": 0.2103,500      "step": 70501    },502    {503      "epoch": 2.6296296296296298,504      "grad_norm": 0.94921875,505      "learning_rate": 1.3445558855078014e-05,506      "loss": 0.21,507      "step": 71508    },509    {510      "epoch": 2.6666666666666665,511      "grad_norm": 0.353515625,512      "learning_rate": 1.1141404609666449e-05,513      "loss": 0.1128,514      "step": 72515    },516    {517      "epoch": 2.7037037037037037,518      "grad_norm": 0.361328125,519      "learning_rate": 9.046106882113751e-06,520      "loss": 0.0408,521      "step": 73522    },523    {524      "epoch": 2.7407407407407405,525      "grad_norm": 0.72265625,526      "learning_rate": 7.1628171992377025e-06,527      "loss": 0.0699,528      "step": 74529    },530    {531      "epoch": 2.7777777777777777,532      "grad_norm": 0.94140625,533      "learning_rate": 5.494368207617949e-06,534      "loss": 0.203,535      "step": 75536    },537    {538      "epoch": 2.814814814814815,539      "grad_norm": 1.6484375,540      "learning_rate": 4.043269413026429e-06,541      "loss": 0.1818,542      "step": 76543    },544    {545      "epoch": 2.851851851851852,546      "grad_norm": 0.80078125,547      "learning_rate": 2.811703405892296e-06,548      "loss": 0.1156,549      "step": 77550    },551    {552      "epoch": 2.888888888888889,553      "grad_norm": 0.484375,554      "learning_rate": 1.801522578478648e-06,555      "loss": 0.1011,556      "step": 78557    },558    {559      "epoch": 2.925925925925926,560      "grad_norm": 1.8984375,561      "learning_rate": 1.0142463387085464e-06,562      "loss": 0.1353,563      "step": 79564    },565    {566      "epoch": 2.962962962962963,567      "grad_norm": 0.59765625,568      "learning_rate": 4.510588248311964e-07,569      "loss": 0.1148,570      "step": 80571    },572    {573      "epoch": 3.0,574      "grad_norm": 0.294921875,575      "learning_rate": 1.1280712436549378e-07,576      "loss": 0.042,577      "step": 81578    },579    {580      "epoch": 3.0,581      "eval_loss": 0.20274528861045837,582      "eval_runtime": 17.1585,583      "eval_samples_per_second": 3.031,584      "eval_steps_per_second": 0.408,585      "step": 81586    }587  ],588  "logging_steps": 1.0,589  "max_steps": 81,590  "num_input_tokens_seen": 0,591  "num_train_epochs": 3,592  "save_steps": 0,593  "stateful_callbacks": {594    "TrainerControl": {595      "args": {596        "should_epoch_stop": false,597        "should_evaluate": false,598        "should_log": false,599        "should_save": true,600        "should_training_stop": true601      },602      "attributes": {}603    }604  },605  "total_flos": 2.6369079864878694e+17,606  "train_batch_size": 1,607  "trial_name": null,608  "trial_params": null609}610