| { |
| "best_global_step": 2000, |
| "best_metric": 0.9754661432777233, |
| "best_model_checkpoint": "/kaggle/working/outputs/bert_rd_keystrokes/checkpoint-2000", |
| "epoch": 1.6181229773462782, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0008090614886731392, |
| "grad_norm": 2.5394184589385986, |
| "learning_rate": 0.0, |
| "loss": 0.6913009285926819, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.020226537216828478, |
| "grad_norm": 3.3882575035095215, |
| "learning_rate": 9.716599190283402e-07, |
| "loss": 0.710881233215332, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.040453074433656956, |
| "grad_norm": 4.59527063369751, |
| "learning_rate": 1.9838056680161946e-06, |
| "loss": 0.6965625762939454, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.06067961165048544, |
| "grad_norm": 6.466946125030518, |
| "learning_rate": 2.995951417004049e-06, |
| "loss": 0.6713954925537109, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.08090614886731391, |
| "grad_norm": 5.92415714263916, |
| "learning_rate": 4.008097165991903e-06, |
| "loss": 0.6306858444213868, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1011326860841424, |
| "grad_norm": 7.790467262268066, |
| "learning_rate": 5.020242914979757e-06, |
| "loss": 0.5511775207519531, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.12135922330097088, |
| "grad_norm": 5.874857425689697, |
| "learning_rate": 6.0323886639676124e-06, |
| "loss": 0.5026376342773438, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.14158576051779936, |
| "grad_norm": 12.701870918273926, |
| "learning_rate": 7.044534412955466e-06, |
| "loss": 0.4295468521118164, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.16181229773462782, |
| "grad_norm": 5.137658596038818, |
| "learning_rate": 8.056680161943322e-06, |
| "loss": 0.3788005828857422, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1820388349514563, |
| "grad_norm": 5.249273300170898, |
| "learning_rate": 9.068825910931175e-06, |
| "loss": 0.2651861381530762, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.2022653721682848, |
| "grad_norm": 38.753013610839844, |
| "learning_rate": 1.008097165991903e-05, |
| "loss": 0.3065790557861328, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.22249190938511326, |
| "grad_norm": 13.836112022399902, |
| "learning_rate": 1.1093117408906884e-05, |
| "loss": 0.38094028472900393, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.24271844660194175, |
| "grad_norm": 6.559873580932617, |
| "learning_rate": 1.2105263157894737e-05, |
| "loss": 0.3118729019165039, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.26294498381877024, |
| "grad_norm": 7.356478214263916, |
| "learning_rate": 1.3117408906882592e-05, |
| "loss": 0.23761932373046876, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.28317152103559873, |
| "grad_norm": 4.0845184326171875, |
| "learning_rate": 1.4129554655870446e-05, |
| "loss": 0.26587358474731443, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.30339805825242716, |
| "grad_norm": 28.685104370117188, |
| "learning_rate": 1.5141700404858302e-05, |
| "loss": 0.3239314651489258, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.32362459546925565, |
| "grad_norm": 1.7896462678909302, |
| "learning_rate": 1.6153846153846154e-05, |
| "loss": 0.24046634674072265, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.34385113268608414, |
| "grad_norm": 6.960549831390381, |
| "learning_rate": 1.716599190283401e-05, |
| "loss": 0.27144105911254884, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.3640776699029126, |
| "grad_norm": 22.062820434570312, |
| "learning_rate": 1.8178137651821864e-05, |
| "loss": 0.24825719833374024, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.3843042071197411, |
| "grad_norm": 0.4285735785961151, |
| "learning_rate": 1.9190283400809718e-05, |
| "loss": 0.22249792098999024, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.4045307443365696, |
| "grad_norm": 0.26966607570648193, |
| "learning_rate": 1.999993769982229e-05, |
| "loss": 0.25503772735595703, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4045307443365696, |
| "eval_accuracy": 0.9550277918140475, |
| "eval_f1": 0.9709055246812683, |
| "eval_loss": 0.1790667176246643, |
| "eval_precision": 0.9574468085106383, |
| "eval_recall": 0.9847480106100795, |
| "eval_runtime": 34.5481, |
| "eval_samples_per_second": 57.282, |
| "eval_steps_per_second": 3.589, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.42475728155339804, |
| "grad_norm": 1.232269048690796, |
| "learning_rate": 1.9997757275108847e-05, |
| "loss": 0.2667963790893555, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.4449838187702265, |
| "grad_norm": 12.561880111694336, |
| "learning_rate": 1.9992462617728763e-05, |
| "loss": 0.2216647148132324, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.465210355987055, |
| "grad_norm": 0.4093881845474243, |
| "learning_rate": 1.9984055376931414e-05, |
| "loss": 0.23123834609985353, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.4854368932038835, |
| "grad_norm": 3.573305368423462, |
| "learning_rate": 1.9972538171514525e-05, |
| "loss": 0.2226162338256836, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5056634304207119, |
| "grad_norm": 12.511730194091797, |
| "learning_rate": 1.9957914589008405e-05, |
| "loss": 0.2451229476928711, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.5258899676375405, |
| "grad_norm": 11.676703453063965, |
| "learning_rate": 1.9940189184558487e-05, |
| "loss": 0.25127721786499024, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.5461165048543689, |
| "grad_norm": 5.444802284240723, |
| "learning_rate": 1.9919367479506413e-05, |
| "loss": 0.30009620666503906, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.5663430420711975, |
| "grad_norm": 1.9753400087356567, |
| "learning_rate": 1.989545595967018e-05, |
| "loss": 0.3415143585205078, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.5865695792880259, |
| "grad_norm": 0.7816814184188843, |
| "learning_rate": 1.986846207332384e-05, |
| "loss": 0.24259204864501954, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.6067961165048543, |
| "grad_norm": 20.42180061340332, |
| "learning_rate": 1.9838394228877443e-05, |
| "loss": 0.1343485450744629, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.6270226537216829, |
| "grad_norm": 21.677453994750977, |
| "learning_rate": 1.980526179225785e-05, |
| "loss": 0.25507625579833987, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.6472491909385113, |
| "grad_norm": 4.561895370483398, |
| "learning_rate": 1.97690750839913e-05, |
| "loss": 0.26329845428466797, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.6674757281553398, |
| "grad_norm": 0.17717082798480988, |
| "learning_rate": 1.9729845375988694e-05, |
| "loss": 0.16668357849121093, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.6877022653721683, |
| "grad_norm": 6.059898853302002, |
| "learning_rate": 1.968758488803439e-05, |
| "loss": 0.2621467399597168, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.7079288025889967, |
| "grad_norm": 5.8439130783081055, |
| "learning_rate": 1.9642306783979902e-05, |
| "loss": 0.3152758979797363, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.7281553398058253, |
| "grad_norm": 5.4012041091918945, |
| "learning_rate": 1.959402516764339e-05, |
| "loss": 0.2474656867980957, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.7483818770226537, |
| "grad_norm": 13.964224815368652, |
| "learning_rate": 1.954275507841646e-05, |
| "loss": 0.22230056762695313, |
| "step": 925 |
| }, |
| { |
| "epoch": 0.7686084142394822, |
| "grad_norm": 8.115334510803223, |
| "learning_rate": 1.948851248657947e-05, |
| "loss": 0.3234273910522461, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.7888349514563107, |
| "grad_norm": 0.23621903359889984, |
| "learning_rate": 1.9431314288326925e-05, |
| "loss": 0.1469671630859375, |
| "step": 975 |
| }, |
| { |
| "epoch": 0.8090614886731392, |
| "grad_norm": 3.0084638595581055, |
| "learning_rate": 1.9371178300504394e-05, |
| "loss": 0.24907604217529297, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8090614886731392, |
| "eval_accuracy": 0.9615967660434563, |
| "eval_f1": 0.9752604166666666, |
| "eval_loss": 0.15361516177654266, |
| "eval_precision": 0.9578005115089514, |
| "eval_recall": 0.993368700265252, |
| "eval_runtime": 34.2684, |
| "eval_samples_per_second": 57.75, |
| "eval_steps_per_second": 3.618, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8292880258899676, |
| "grad_norm": 0.658998429775238, |
| "learning_rate": 1.930812325505871e-05, |
| "loss": 0.128564510345459, |
| "step": 1025 |
| }, |
| { |
| "epoch": 0.8495145631067961, |
| "grad_norm": 14.597765922546387, |
| "learning_rate": 1.9242168793203088e-05, |
| "loss": 0.28263355255126954, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.8697411003236246, |
| "grad_norm": 10.520459175109863, |
| "learning_rate": 1.9173335459299025e-05, |
| "loss": 0.20550737380981446, |
| "step": 1075 |
| }, |
| { |
| "epoch": 0.889967637540453, |
| "grad_norm": 8.196412086486816, |
| "learning_rate": 1.9101644694456873e-05, |
| "loss": 0.21728286743164063, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.9101941747572816, |
| "grad_norm": 10.451470375061035, |
| "learning_rate": 1.902711882985708e-05, |
| "loss": 0.22805599212646485, |
| "step": 1125 |
| }, |
| { |
| "epoch": 0.93042071197411, |
| "grad_norm": 0.7729430794715881, |
| "learning_rate": 1.894978107979417e-05, |
| "loss": 0.19682933807373046, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.9506472491909385, |
| "grad_norm": 1.208465814590454, |
| "learning_rate": 1.886965553444568e-05, |
| "loss": 0.21496267318725587, |
| "step": 1175 |
| }, |
| { |
| "epoch": 0.970873786407767, |
| "grad_norm": 8.930377006530762, |
| "learning_rate": 1.8786767152368197e-05, |
| "loss": 0.2545662498474121, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.9911003236245954, |
| "grad_norm": 8.784140586853027, |
| "learning_rate": 1.8701141752722966e-05, |
| "loss": 0.15711795806884765, |
| "step": 1225 |
| }, |
| { |
| "epoch": 1.0113268608414239, |
| "grad_norm": 6.048089504241943, |
| "learning_rate": 1.8612806007233382e-05, |
| "loss": 0.18027606964111328, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.0315533980582525, |
| "grad_norm": 2.1826491355895996, |
| "learning_rate": 1.8521787431876954e-05, |
| "loss": 0.1467225170135498, |
| "step": 1275 |
| }, |
| { |
| "epoch": 1.051779935275081, |
| "grad_norm": 13.113622665405273, |
| "learning_rate": 1.8428114378314237e-05, |
| "loss": 0.21480131149291992, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.0720064724919094, |
| "grad_norm": 6.212342262268066, |
| "learning_rate": 1.8331816025057508e-05, |
| "loss": 0.22947580337524415, |
| "step": 1325 |
| }, |
| { |
| "epoch": 1.0922330097087378, |
| "grad_norm": 0.22277741134166718, |
| "learning_rate": 1.823292236838186e-05, |
| "loss": 0.10173338890075684, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.1124595469255663, |
| "grad_norm": 11.058046340942383, |
| "learning_rate": 1.813146421298154e-05, |
| "loss": 0.2582175064086914, |
| "step": 1375 |
| }, |
| { |
| "epoch": 1.132686084142395, |
| "grad_norm": 9.502155303955078, |
| "learning_rate": 1.802747316237454e-05, |
| "loss": 0.23467300415039063, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.1529126213592233, |
| "grad_norm": 5.091904640197754, |
| "learning_rate": 1.792098160905829e-05, |
| "loss": 0.18842180252075194, |
| "step": 1425 |
| }, |
| { |
| "epoch": 1.1731391585760518, |
| "grad_norm": 0.2650909721851349, |
| "learning_rate": 1.7812022724419624e-05, |
| "loss": 0.13545321464538573, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.1933656957928802, |
| "grad_norm": 3.7782185077667236, |
| "learning_rate": 1.7700630448402125e-05, |
| "loss": 0.16887168884277343, |
| "step": 1475 |
| }, |
| { |
| "epoch": 1.2135922330097086, |
| "grad_norm": 0.5704866051673889, |
| "learning_rate": 1.758683947893406e-05, |
| "loss": 0.22910015106201173, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.2135922330097086, |
| "eval_accuracy": 0.9605861546235472, |
| "eval_f1": 0.974559686888454, |
| "eval_loss": 0.14868734776973724, |
| "eval_precision": 0.9589216944801027, |
| "eval_recall": 0.9907161803713528, |
| "eval_runtime": 34.2705, |
| "eval_samples_per_second": 57.746, |
| "eval_steps_per_second": 3.618, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.2338187702265373, |
| "grad_norm": 16.6047306060791, |
| "learning_rate": 1.747068526112022e-05, |
| "loss": 0.14131352424621582, |
| "step": 1525 |
| }, |
| { |
| "epoch": 1.2540453074433657, |
| "grad_norm": 5.992398262023926, |
| "learning_rate": 1.735220397620101e-05, |
| "loss": 0.15291913986206054, |
| "step": 1550 |
| }, |
| { |
| "epoch": 1.2742718446601942, |
| "grad_norm": 0.36782047152519226, |
| "learning_rate": 1.7231432530282246e-05, |
| "loss": 0.09922373771667481, |
| "step": 1575 |
| }, |
| { |
| "epoch": 1.2944983818770226, |
| "grad_norm": 1.3172669410705566, |
| "learning_rate": 1.7108408542839146e-05, |
| "loss": 0.1941922378540039, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.3147249190938513, |
| "grad_norm": 0.693942666053772, |
| "learning_rate": 1.698317033499813e-05, |
| "loss": 0.16940629959106446, |
| "step": 1625 |
| }, |
| { |
| "epoch": 1.3349514563106797, |
| "grad_norm": 0.1476801335811615, |
| "learning_rate": 1.6855756917600057e-05, |
| "loss": 0.12692631721496583, |
| "step": 1650 |
| }, |
| { |
| "epoch": 1.3551779935275081, |
| "grad_norm": 23.20606231689453, |
| "learning_rate": 1.6726207979048604e-05, |
| "loss": 0.25180328369140625, |
| "step": 1675 |
| }, |
| { |
| "epoch": 1.3754045307443366, |
| "grad_norm": 0.3847394287586212, |
| "learning_rate": 1.6594563872947613e-05, |
| "loss": 0.13337421417236328, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.395631067961165, |
| "grad_norm": 7.629310131072998, |
| "learning_rate": 1.6460865605531214e-05, |
| "loss": 0.17984333038330078, |
| "step": 1725 |
| }, |
| { |
| "epoch": 1.4158576051779934, |
| "grad_norm": 0.40370574593544006, |
| "learning_rate": 1.6325154822890663e-05, |
| "loss": 0.15392546653747557, |
| "step": 1750 |
| }, |
| { |
| "epoch": 1.436084142394822, |
| "grad_norm": 3.1435182094573975, |
| "learning_rate": 1.618747379800188e-05, |
| "loss": 0.1560378646850586, |
| "step": 1775 |
| }, |
| { |
| "epoch": 1.4563106796116505, |
| "grad_norm": 6.557313919067383, |
| "learning_rate": 1.6047865417557695e-05, |
| "loss": 0.23071422576904296, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.476537216828479, |
| "grad_norm": 4.851151943206787, |
| "learning_rate": 1.5906373168608952e-05, |
| "loss": 0.17919015884399414, |
| "step": 1825 |
| }, |
| { |
| "epoch": 1.4967637540453074, |
| "grad_norm": 6.987358093261719, |
| "learning_rate": 1.576304112501858e-05, |
| "loss": 0.22098312377929688, |
| "step": 1850 |
| }, |
| { |
| "epoch": 1.516990291262136, |
| "grad_norm": 4.638033390045166, |
| "learning_rate": 1.5617913933732892e-05, |
| "loss": 0.1659644889831543, |
| "step": 1875 |
| }, |
| { |
| "epoch": 1.5372168284789645, |
| "grad_norm": 3.2221922874450684, |
| "learning_rate": 1.5471036800874375e-05, |
| "loss": 0.18479549407958984, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.557443365695793, |
| "grad_norm": 0.3064526617527008, |
| "learning_rate": 1.5322455477660274e-05, |
| "loss": 0.18851667404174804, |
| "step": 1925 |
| }, |
| { |
| "epoch": 1.5776699029126213, |
| "grad_norm": 15.610395431518555, |
| "learning_rate": 1.5172216246151426e-05, |
| "loss": 0.23035451889038086, |
| "step": 1950 |
| }, |
| { |
| "epoch": 1.5978964401294498, |
| "grad_norm": 8.045638084411621, |
| "learning_rate": 1.50203659048357e-05, |
| "loss": 0.05388895988464355, |
| "step": 1975 |
| }, |
| { |
| "epoch": 1.6181229773462782, |
| "grad_norm": 12.035682678222656, |
| "learning_rate": 1.4866951754050605e-05, |
| "loss": 0.2584081268310547, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.6181229773462782, |
| "eval_accuracy": 0.9621020717534108, |
| "eval_f1": 0.9754661432777233, |
| "eval_loss": 0.145921990275383, |
| "eval_precision": 0.9625564880568108, |
| "eval_recall": 0.9887267904509284, |
| "eval_runtime": 34.2514, |
| "eval_samples_per_second": 57.779, |
| "eval_steps_per_second": 3.62, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 4944, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8416396438855680.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
