| { | |
| "best_metric": 0.2396179437637329, | |
| "best_model_checkpoint": "./vit-front-page-384-top-v2/checkpoint-29800", | |
| "epoch": 63.99936874979235, | |
| "global_step": 30080, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7e-08, | |
| "loss": 1.1579, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.4e-07, | |
| "loss": 1.0878, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.47199266883765073, | |
| "eval_f1": 0.30458585117802356, | |
| "eval_loss": 1.0330626964569092, | |
| "eval_matthews_correlation": 0.06652323581980453, | |
| "eval_precision": 0.31744913205816433, | |
| "eval_recall": 0.3553557284231841, | |
| "eval_runtime": 697.3486, | |
| "eval_samples_per_second": 87.63, | |
| "eval_steps_per_second": 10.954, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.0999999999999997e-07, | |
| "loss": 0.9749, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.8e-07, | |
| "loss": 0.8564, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.6716686576445368, | |
| "eval_f1": 0.2862959733836089, | |
| "eval_loss": 0.8043246269226074, | |
| "eval_matthews_correlation": 0.02054232176534715, | |
| "eval_precision": 0.3965367638489952, | |
| "eval_recall": 0.3372454942697249, | |
| "eval_runtime": 737.791, | |
| "eval_samples_per_second": 82.827, | |
| "eval_steps_per_second": 10.354, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.5e-07, | |
| "loss": 0.7595, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.1999999999999995e-07, | |
| "loss": 0.6686, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_accuracy": 0.7726685103667218, | |
| "eval_f1": 0.5415520240343557, | |
| "eval_loss": 0.6247742176055908, | |
| "eval_matthews_correlation": 0.4840060501393934, | |
| "eval_precision": 0.675520444855411, | |
| "eval_recall": 0.549548707524528, | |
| "eval_runtime": 748.1219, | |
| "eval_samples_per_second": 81.683, | |
| "eval_steps_per_second": 10.211, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.9e-07, | |
| "loss": 0.5908, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 5.6e-07, | |
| "loss": 0.5402, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_accuracy": 0.8031877464857877, | |
| "eval_f1": 0.6064835974975745, | |
| "eval_loss": 0.5200676918029785, | |
| "eval_matthews_correlation": 0.5685671703134927, | |
| "eval_precision": 0.7346226714541242, | |
| "eval_recall": 0.623939460705213, | |
| "eval_runtime": 747.2328, | |
| "eval_samples_per_second": 81.78, | |
| "eval_steps_per_second": 10.223, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 6.3e-07, | |
| "loss": 0.5092, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 7e-07, | |
| "loss": 0.4738, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.8222847698375034, | |
| "eval_f1": 0.656503045814189, | |
| "eval_loss": 0.45921027660369873, | |
| "eval_matthews_correlation": 0.6152769290835743, | |
| "eval_precision": 0.7706297185314468, | |
| "eval_recall": 0.6613208665680587, | |
| "eval_runtime": 741.9279, | |
| "eval_samples_per_second": 82.365, | |
| "eval_steps_per_second": 10.296, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.975928473177441e-07, | |
| "loss": 0.4505, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 6.951856946354883e-07, | |
| "loss": 0.4334, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_accuracy": 0.8358997856289581, | |
| "eval_f1": 0.6933151931691204, | |
| "eval_loss": 0.42466118931770325, | |
| "eval_matthews_correlation": 0.6473298137474588, | |
| "eval_precision": 0.8018420432885766, | |
| "eval_recall": 0.6883870696562419, | |
| "eval_runtime": 739.542, | |
| "eval_samples_per_second": 82.631, | |
| "eval_steps_per_second": 10.329, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 6.927785419532324e-07, | |
| "loss": 0.421, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 6.903713892709766e-07, | |
| "loss": 0.4096, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.8459310412541524, | |
| "eval_f1": 0.7259215048690799, | |
| "eval_loss": 0.4023092985153198, | |
| "eval_matthews_correlation": 0.6694736037554148, | |
| "eval_precision": 0.817972095086389, | |
| "eval_recall": 0.7115413009532899, | |
| "eval_runtime": 742.9738, | |
| "eval_samples_per_second": 82.249, | |
| "eval_steps_per_second": 10.282, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 6.879642365887207e-07, | |
| "loss": 0.399, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 6.855570839064649e-07, | |
| "loss": 0.3911, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_accuracy": 0.8531149257883455, | |
| "eval_f1": 0.7472369760964189, | |
| "eval_loss": 0.38542693853378296, | |
| "eval_matthews_correlation": 0.6854869391821359, | |
| "eval_precision": 0.8286984473444058, | |
| "eval_recall": 0.728941183310836, | |
| "eval_runtime": 750.7098, | |
| "eval_samples_per_second": 81.402, | |
| "eval_steps_per_second": 10.176, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 6.83149931224209e-07, | |
| "loss": 0.3863, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 6.807427785419532e-07, | |
| "loss": 0.374, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_accuracy": 0.858727846961986, | |
| "eval_f1": 0.7579728569088652, | |
| "eval_loss": 0.3718436658382416, | |
| "eval_matthews_correlation": 0.6985763451826267, | |
| "eval_precision": 0.8419368842500098, | |
| "eval_recall": 0.7379464209001965, | |
| "eval_runtime": 743.1963, | |
| "eval_samples_per_second": 82.225, | |
| "eval_steps_per_second": 10.279, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 6.783356258596973e-07, | |
| "loss": 0.373, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 6.759284731774416e-07, | |
| "loss": 0.364, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_accuracy": 0.8634243728419709, | |
| "eval_f1": 0.7730246028265862, | |
| "eval_loss": 0.3604389429092407, | |
| "eval_matthews_correlation": 0.7086435730935319, | |
| "eval_precision": 0.8446686042583251, | |
| "eval_recall": 0.751376357217314, | |
| "eval_runtime": 740.92, | |
| "eval_samples_per_second": 82.477, | |
| "eval_steps_per_second": 10.31, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 6.735213204951857e-07, | |
| "loss": 0.361, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 6.711141678129298e-07, | |
| "loss": 0.3515, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "eval_accuracy": 0.8670572256132485, | |
| "eval_f1": 0.786935372106972, | |
| "eval_loss": 0.35153478384017944, | |
| "eval_matthews_correlation": 0.7164149373512902, | |
| "eval_precision": 0.8431062825642964, | |
| "eval_recall": 0.7655026420308885, | |
| "eval_runtime": 744.262, | |
| "eval_samples_per_second": 82.107, | |
| "eval_steps_per_second": 10.264, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 6.68707015130674e-07, | |
| "loss": 0.3474, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 6.662998624484181e-07, | |
| "loss": 0.3495, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "eval_accuracy": 0.8695445842674565, | |
| "eval_f1": 0.7912078713980214, | |
| "eval_loss": 0.3432447612285614, | |
| "eval_matthews_correlation": 0.722187531750913, | |
| "eval_precision": 0.8471645851807871, | |
| "eval_recall": 0.7701986078087044, | |
| "eval_runtime": 746.5629, | |
| "eval_samples_per_second": 81.854, | |
| "eval_steps_per_second": 10.232, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 6.638927097661623e-07, | |
| "loss": 0.3393, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 6.614855570839064e-07, | |
| "loss": 0.3394, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "eval_accuracy": 0.8722937701484234, | |
| "eval_f1": 0.8014358996356167, | |
| "eval_loss": 0.33667007088661194, | |
| "eval_matthews_correlation": 0.7282296966850125, | |
| "eval_precision": 0.8474604270710779, | |
| "eval_recall": 0.7808572336828936, | |
| "eval_runtime": 738.9406, | |
| "eval_samples_per_second": 82.698, | |
| "eval_steps_per_second": 10.338, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 6.590784044016506e-07, | |
| "loss": 0.3322, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 6.566712517193947e-07, | |
| "loss": 0.3292, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_accuracy": 0.8754029684661834, | |
| "eval_f1": 0.8057316783028342, | |
| "eval_loss": 0.3303240239620209, | |
| "eval_matthews_correlation": 0.7353280019112225, | |
| "eval_precision": 0.8534328687035272, | |
| "eval_recall": 0.7852621867922206, | |
| "eval_runtime": 739.5259, | |
| "eval_samples_per_second": 82.633, | |
| "eval_steps_per_second": 10.33, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 6.542640990371389e-07, | |
| "loss": 0.3279, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 6.51856946354883e-07, | |
| "loss": 0.3221, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "eval_accuracy": 0.8771048454401152, | |
| "eval_f1": 0.8118912367116238, | |
| "eval_loss": 0.325397253036499, | |
| "eval_matthews_correlation": 0.7391493356040657, | |
| "eval_precision": 0.8529734453691505, | |
| "eval_recall": 0.7922690785460985, | |
| "eval_runtime": 740.6825, | |
| "eval_samples_per_second": 82.504, | |
| "eval_steps_per_second": 10.313, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 6.494497936726272e-07, | |
| "loss": 0.3198, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 6.470426409903714e-07, | |
| "loss": 0.3193, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "eval_accuracy": 0.8786430803973229, | |
| "eval_f1": 0.8149222847393559, | |
| "eval_loss": 0.32044103741645813, | |
| "eval_matthews_correlation": 0.7425187249293684, | |
| "eval_precision": 0.8557527653691984, | |
| "eval_recall": 0.7949691401817414, | |
| "eval_runtime": 746.3851, | |
| "eval_samples_per_second": 81.873, | |
| "eval_steps_per_second": 10.235, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 6.446354883081155e-07, | |
| "loss": 0.3201, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 6.422283356258597e-07, | |
| "loss": 0.3132, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "eval_accuracy": 0.8806722414047031, | |
| "eval_f1": 0.8174184090965871, | |
| "eval_loss": 0.3158539831638336, | |
| "eval_matthews_correlation": 0.7467975049519304, | |
| "eval_precision": 0.8619184711052283, | |
| "eval_recall": 0.795602570450299, | |
| "eval_runtime": 738.2169, | |
| "eval_samples_per_second": 82.779, | |
| "eval_steps_per_second": 10.348, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 6.398211829436038e-07, | |
| "loss": 0.3073, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 6.37414030261348e-07, | |
| "loss": 0.3132, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "eval_accuracy": 0.8820795627485313, | |
| "eval_f1": 0.8206075847781881, | |
| "eval_loss": 0.31192630529403687, | |
| "eval_matthews_correlation": 0.7498734961565087, | |
| "eval_precision": 0.8633026761277282, | |
| "eval_recall": 0.7987569311521797, | |
| "eval_runtime": 740.9094, | |
| "eval_samples_per_second": 82.478, | |
| "eval_steps_per_second": 10.31, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 6.350068775790921e-07, | |
| "loss": 0.3069, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 6.326237964236588e-07, | |
| "loss": 0.3025, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "eval_accuracy": 0.8831432358572388, | |
| "eval_f1": 0.8196955655944261, | |
| "eval_loss": 0.3085801303386688, | |
| "eval_matthews_correlation": 0.7524770103029159, | |
| "eval_precision": 0.8670221506031749, | |
| "eval_recall": 0.7980346533793877, | |
| "eval_runtime": 744.5383, | |
| "eval_samples_per_second": 82.076, | |
| "eval_steps_per_second": 10.26, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 6.30216643741403e-07, | |
| "loss": 0.3045, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 6.278094910591471e-07, | |
| "loss": 0.2985, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "eval_accuracy": 0.8848451128311705, | |
| "eval_f1": 0.8224187877042858, | |
| "eval_loss": 0.3054741322994232, | |
| "eval_matthews_correlation": 0.7562553921752282, | |
| "eval_precision": 0.8707087913084752, | |
| "eval_recall": 0.8003224168402451, | |
| "eval_runtime": 744.3622, | |
| "eval_samples_per_second": 82.096, | |
| "eval_steps_per_second": 10.262, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 6.254023383768913e-07, | |
| "loss": 0.3025, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 6.229951856946355e-07, | |
| "loss": 0.2935, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "eval_accuracy": 0.8856960513181364, | |
| "eval_f1": 0.8270971016415025, | |
| "eval_loss": 0.3019094467163086, | |
| "eval_matthews_correlation": 0.7579503685116903, | |
| "eval_precision": 0.8686093007370651, | |
| "eval_recall": 0.8055890535079828, | |
| "eval_runtime": 737.7079, | |
| "eval_samples_per_second": 82.836, | |
| "eval_steps_per_second": 10.355, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 6.205880330123796e-07, | |
| "loss": 0.2922, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 6.181808803301237e-07, | |
| "loss": 0.2972, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "eval_accuracy": 0.886726996023499, | |
| "eval_f1": 0.8312888416170532, | |
| "eval_loss": 0.29910609126091003, | |
| "eval_matthews_correlation": 0.7602803738695297, | |
| "eval_precision": 0.8670983019375994, | |
| "eval_recall": 0.8110478011642049, | |
| "eval_runtime": 740.1058, | |
| "eval_samples_per_second": 82.568, | |
| "eval_steps_per_second": 10.321, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 6.15773727647868e-07, | |
| "loss": 0.291, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 6.133665749656121e-07, | |
| "loss": 0.2842, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "eval_accuracy": 0.8881834099723445, | |
| "eval_f1": 0.8288009711968476, | |
| "eval_loss": 0.2969624698162079, | |
| "eval_matthews_correlation": 0.7633162920871629, | |
| "eval_precision": 0.87764007829966, | |
| "eval_recall": 0.8043731442813558, | |
| "eval_runtime": 741.7489, | |
| "eval_samples_per_second": 82.385, | |
| "eval_steps_per_second": 10.299, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 6.109594222833563e-07, | |
| "loss": 0.2899, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 6.085522696011004e-07, | |
| "loss": 0.2817, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "eval_accuracy": 0.8889525274509483, | |
| "eval_f1": 0.8315132262764084, | |
| "eval_loss": 0.2943968176841736, | |
| "eval_matthews_correlation": 0.7651421821245511, | |
| "eval_precision": 0.8750942573381245, | |
| "eval_recall": 0.8092884505952779, | |
| "eval_runtime": 745.4507, | |
| "eval_samples_per_second": 81.976, | |
| "eval_steps_per_second": 10.247, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 6.061451169188445e-07, | |
| "loss": 0.2875, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 6.037379642365887e-07, | |
| "loss": 0.2835, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "eval_accuracy": 0.8902289351813972, | |
| "eval_f1": 0.8358968469870814, | |
| "eval_loss": 0.2914660573005676, | |
| "eval_matthews_correlation": 0.7678325605146122, | |
| "eval_precision": 0.8751855078748036, | |
| "eval_recall": 0.8140379985221483, | |
| "eval_runtime": 740.8099, | |
| "eval_samples_per_second": 82.489, | |
| "eval_steps_per_second": 10.312, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.85, | |
| "learning_rate": 6.013308115543328e-07, | |
| "loss": 0.2865, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 5.98923658872077e-07, | |
| "loss": 0.2785, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "eval_accuracy": 0.890376212996449, | |
| "eval_f1": 0.8379544187375135, | |
| "eval_loss": 0.2892487943172455, | |
| "eval_matthews_correlation": 0.7683922526616379, | |
| "eval_precision": 0.8718213134907034, | |
| "eval_recall": 0.8183367928328248, | |
| "eval_runtime": 743.5573, | |
| "eval_samples_per_second": 82.185, | |
| "eval_steps_per_second": 10.274, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 5.965165061898212e-07, | |
| "loss": 0.2806, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 5.941093535075653e-07, | |
| "loss": 0.277, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "eval_accuracy": 0.8905234908115007, | |
| "eval_f1": 0.8422741485565478, | |
| "eval_loss": 0.28853607177734375, | |
| "eval_matthews_correlation": 0.7691630289472814, | |
| "eval_precision": 0.867865425515812, | |
| "eval_recall": 0.8254618782640463, | |
| "eval_runtime": 744.2909, | |
| "eval_samples_per_second": 82.104, | |
| "eval_steps_per_second": 10.263, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 5.91726272352132e-07, | |
| "loss": 0.2756, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 5.893191196698761e-07, | |
| "loss": 0.2761, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "eval_accuracy": 0.8924708308105189, | |
| "eval_f1": 0.8407206897924651, | |
| "eval_loss": 0.2853315472602844, | |
| "eval_matthews_correlation": 0.7728119384929814, | |
| "eval_precision": 0.8769128232635235, | |
| "eval_recall": 0.8197283860690042, | |
| "eval_runtime": 745.7896, | |
| "eval_samples_per_second": 81.939, | |
| "eval_steps_per_second": 10.243, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 5.869119669876203e-07, | |
| "loss": 0.2707, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 5.845048143053646e-07, | |
| "loss": 0.2716, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "eval_accuracy": 0.8929453926590192, | |
| "eval_f1": 0.8413825933753687, | |
| "eval_loss": 0.28369224071502686, | |
| "eval_matthews_correlation": 0.7738849095862524, | |
| "eval_precision": 0.8776341480244246, | |
| "eval_recall": 0.8205318685675761, | |
| "eval_runtime": 740.9165, | |
| "eval_samples_per_second": 82.478, | |
| "eval_steps_per_second": 10.31, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 5.820976616231087e-07, | |
| "loss": 0.2712, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 5.796905089408528e-07, | |
| "loss": 0.2706, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "eval_accuracy": 0.893174491482433, | |
| "eval_f1": 0.8403426048749795, | |
| "eval_loss": 0.2822517454624176, | |
| "eval_matthews_correlation": 0.7742762977153516, | |
| "eval_precision": 0.880588737201879, | |
| "eval_recall": 0.8178958665818555, | |
| "eval_runtime": 738.4683, | |
| "eval_samples_per_second": 82.751, | |
| "eval_steps_per_second": 10.344, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 12.98, | |
| "learning_rate": 5.77283356258597e-07, | |
| "loss": 0.2694, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 5.748762035763411e-07, | |
| "loss": 0.2699, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "eval_accuracy": 0.8943363498011749, | |
| "eval_f1": 0.8443115910170147, | |
| "eval_loss": 0.28035762906074524, | |
| "eval_matthews_correlation": 0.777057401011472, | |
| "eval_precision": 0.8780772144476896, | |
| "eval_recall": 0.824585718133633, | |
| "eval_runtime": 742.9977, | |
| "eval_samples_per_second": 82.247, | |
| "eval_steps_per_second": 10.281, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 5.724690508940853e-07, | |
| "loss": 0.2678, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 5.700618982118294e-07, | |
| "loss": 0.2658, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "eval_accuracy": 0.8939763373643816, | |
| "eval_f1": 0.8482864178784256, | |
| "eval_loss": 0.279739111661911, | |
| "eval_matthews_correlation": 0.7769030493211544, | |
| "eval_precision": 0.871542005569914, | |
| "eval_recall": 0.8327322280709701, | |
| "eval_runtime": 743.5, | |
| "eval_samples_per_second": 82.191, | |
| "eval_steps_per_second": 10.274, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 5.676547455295735e-07, | |
| "loss": 0.2645, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 5.652475928473177e-07, | |
| "loss": 0.2641, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "eval_accuracy": 0.8951709240864685, | |
| "eval_f1": 0.8478363991609905, | |
| "eval_loss": 0.27740514278411865, | |
| "eval_matthews_correlation": 0.7789944627888661, | |
| "eval_precision": 0.8766918197263195, | |
| "eval_recall": 0.8294813091251183, | |
| "eval_runtime": 736.239, | |
| "eval_samples_per_second": 83.002, | |
| "eval_steps_per_second": 10.376, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 5.628404401650618e-07, | |
| "loss": 0.2613, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 5.60433287482806e-07, | |
| "loss": 0.2583, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "eval_accuracy": 0.8960054983717619, | |
| "eval_f1": 0.8484009381961903, | |
| "eval_loss": 0.2757231295108795, | |
| "eval_matthews_correlation": 0.7807710754658247, | |
| "eval_precision": 0.8788473802383798, | |
| "eval_recall": 0.8296059132709127, | |
| "eval_runtime": 737.7308, | |
| "eval_samples_per_second": 82.834, | |
| "eval_steps_per_second": 10.355, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 5.580261348005502e-07, | |
| "loss": 0.2622, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 5.556189821182944e-07, | |
| "loss": 0.2609, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "eval_accuracy": 0.8964636960185898, | |
| "eval_f1": 0.8467878889818169, | |
| "eval_loss": 0.274697482585907, | |
| "eval_matthews_correlation": 0.7816126666488368, | |
| "eval_precision": 0.8828935769496994, | |
| "eval_recall": 0.825967453708594, | |
| "eval_runtime": 745.3068, | |
| "eval_samples_per_second": 81.992, | |
| "eval_steps_per_second": 10.249, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 5.532118294360385e-07, | |
| "loss": 0.2623, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "learning_rate": 5.508046767537827e-07, | |
| "loss": 0.2552, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "eval_accuracy": 0.8972000850938487, | |
| "eval_f1": 0.8488471894918507, | |
| "eval_loss": 0.27332302927970886, | |
| "eval_matthews_correlation": 0.7831318513368358, | |
| "eval_precision": 0.8836577049278613, | |
| "eval_recall": 0.827858892352507, | |
| "eval_runtime": 744.4826, | |
| "eval_samples_per_second": 82.083, | |
| "eval_steps_per_second": 10.261, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 5.483975240715268e-07, | |
| "loss": 0.2601, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 15.74, | |
| "learning_rate": 5.45990371389271e-07, | |
| "loss": 0.2565, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 15.74, | |
| "eval_accuracy": 0.8969709862704348, | |
| "eval_f1": 0.8464355744063914, | |
| "eval_loss": 0.2729514539241791, | |
| "eval_matthews_correlation": 0.7825953061295711, | |
| "eval_precision": 0.8866637200187834, | |
| "eval_recall": 0.8237014239383851, | |
| "eval_runtime": 743.0997, | |
| "eval_samples_per_second": 82.235, | |
| "eval_steps_per_second": 10.28, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 15.96, | |
| "learning_rate": 5.435832187070151e-07, | |
| "loss": 0.2534, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 5.411760660247592e-07, | |
| "loss": 0.2542, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "eval_accuracy": 0.8977237395473662, | |
| "eval_f1": 0.8506805656096144, | |
| "eval_loss": 0.270821750164032, | |
| "eval_matthews_correlation": 0.7844297352009149, | |
| "eval_precision": 0.8822614346822268, | |
| "eval_recall": 0.8312275513546116, | |
| "eval_runtime": 741.166, | |
| "eval_samples_per_second": 82.45, | |
| "eval_steps_per_second": 10.307, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "learning_rate": 5.387689133425034e-07, | |
| "loss": 0.2509, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "learning_rate": 5.363617606602475e-07, | |
| "loss": 0.2558, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "eval_accuracy": 0.8981328445891767, | |
| "eval_f1": 0.8532626854707139, | |
| "eval_loss": 0.26965296268463135, | |
| "eval_matthews_correlation": 0.7855245919617574, | |
| "eval_precision": 0.8802239860976143, | |
| "eval_recall": 0.8356030600335531, | |
| "eval_runtime": 748.1086, | |
| "eval_samples_per_second": 81.685, | |
| "eval_steps_per_second": 10.211, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 16.81, | |
| "learning_rate": 5.339546079779917e-07, | |
| "loss": 0.2539, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 5.315474552957359e-07, | |
| "loss": 0.2477, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "eval_accuracy": 0.8987710484544011, | |
| "eval_f1": 0.8545204466402865, | |
| "eval_loss": 0.2690507769584656, | |
| "eval_matthews_correlation": 0.7868961445247914, | |
| "eval_precision": 0.8812243874345828, | |
| "eval_recall": 0.8368239812000686, | |
| "eval_runtime": 747.2219, | |
| "eval_samples_per_second": 81.782, | |
| "eval_steps_per_second": 10.223, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 17.23, | |
| "learning_rate": 5.2914030261348e-07, | |
| "loss": 0.2463, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 5.267331499312242e-07, | |
| "loss": 0.2502, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "eval_accuracy": 0.8990983324878495, | |
| "eval_f1": 0.8546462671842509, | |
| "eval_loss": 0.26760247349739075, | |
| "eval_matthews_correlation": 0.7876851465411057, | |
| "eval_precision": 0.8812407286161982, | |
| "eval_recall": 0.8373995657726027, | |
| "eval_runtime": 741.9382, | |
| "eval_samples_per_second": 82.364, | |
| "eval_steps_per_second": 10.296, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 5.243259972489684e-07, | |
| "loss": 0.251, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "learning_rate": 5.219188445667125e-07, | |
| "loss": 0.2511, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "eval_accuracy": 0.8994092523196255, | |
| "eval_f1": 0.8545339122334958, | |
| "eval_loss": 0.2665061354637146, | |
| "eval_matthews_correlation": 0.7882560569421876, | |
| "eval_precision": 0.8828087230192415, | |
| "eval_recall": 0.8365150750628026, | |
| "eval_runtime": 740.5436, | |
| "eval_samples_per_second": 82.519, | |
| "eval_steps_per_second": 10.315, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 18.09, | |
| "learning_rate": 5.195116918844567e-07, | |
| "loss": 0.2408, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 5.171045392022008e-07, | |
| "loss": 0.2462, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "eval_accuracy": 0.90004745618485, | |
| "eval_f1": 0.854345541460756, | |
| "eval_loss": 0.26559463143348694, | |
| "eval_matthews_correlation": 0.7894719027614444, | |
| "eval_precision": 0.8859884402321344, | |
| "eval_recall": 0.8347541294507611, | |
| "eval_runtime": 750.3886, | |
| "eval_samples_per_second": 81.436, | |
| "eval_steps_per_second": 10.18, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 5.146973865199449e-07, | |
| "loss": 0.2444, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 5.122902338376891e-07, | |
| "loss": 0.2436, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "eval_accuracy": 0.8999819993781604, | |
| "eval_f1": 0.8569867461994901, | |
| "eval_loss": 0.264913409948349, | |
| "eval_matthews_correlation": 0.7896869217134314, | |
| "eval_precision": 0.8816538878944042, | |
| "eval_recall": 0.8404004977379529, | |
| "eval_runtime": 744.4344, | |
| "eval_samples_per_second": 82.088, | |
| "eval_steps_per_second": 10.261, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 18.94, | |
| "learning_rate": 5.098830811554332e-07, | |
| "loss": 0.2464, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 5.074759284731774e-07, | |
| "loss": 0.2464, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "eval_accuracy": 0.9005711106383675, | |
| "eval_f1": 0.8562170006167902, | |
| "eval_loss": 0.26369336247444153, | |
| "eval_matthews_correlation": 0.7906712725947966, | |
| "eval_precision": 0.8852868622867386, | |
| "eval_recall": 0.8375004858208192, | |
| "eval_runtime": 743.3786, | |
| "eval_samples_per_second": 82.204, | |
| "eval_steps_per_second": 10.276, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 5.050687757909216e-07, | |
| "loss": 0.2381, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 5.026616231086657e-07, | |
| "loss": 0.2437, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "eval_accuracy": 0.9009147588734884, | |
| "eval_f1": 0.8571370437744039, | |
| "eval_loss": 0.26282036304473877, | |
| "eval_matthews_correlation": 0.7914882999582277, | |
| "eval_precision": 0.8851775755386426, | |
| "eval_recall": 0.8389657015963111, | |
| "eval_runtime": 740.0577, | |
| "eval_samples_per_second": 82.573, | |
| "eval_steps_per_second": 10.322, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 5.002544704264098e-07, | |
| "loss": 0.2418, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.978473177441541e-07, | |
| "loss": 0.241, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9013074997136264, | |
| "eval_f1": 0.8579732984585191, | |
| "eval_loss": 0.2618636190891266, | |
| "eval_matthews_correlation": 0.7923310665266654, | |
| "eval_precision": 0.8854615836013919, | |
| "eval_recall": 0.839858651438767, | |
| "eval_runtime": 748.2729, | |
| "eval_samples_per_second": 81.667, | |
| "eval_steps_per_second": 10.209, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 4.954401650618982e-07, | |
| "loss": 0.2406, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "learning_rate": 4.930330123796424e-07, | |
| "loss": 0.2389, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "eval_accuracy": 0.9017002405537646, | |
| "eval_f1": 0.8575329634536392, | |
| "eval_loss": 0.261372447013855, | |
| "eval_matthews_correlation": 0.7930363459247477, | |
| "eval_precision": 0.888018208273173, | |
| "eval_recall": 0.838029027266019, | |
| "eval_runtime": 745.7008, | |
| "eval_samples_per_second": 81.948, | |
| "eval_steps_per_second": 10.244, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 4.906258596973865e-07, | |
| "loss": 0.237, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 20.85, | |
| "learning_rate": 4.882427785419532e-07, | |
| "loss": 0.2391, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 20.85, | |
| "eval_accuracy": 0.9013565923186437, | |
| "eval_f1": 0.8597863431938432, | |
| "eval_loss": 0.2607530355453491, | |
| "eval_matthews_correlation": 0.7927602334646836, | |
| "eval_precision": 0.8827109469253611, | |
| "eval_recall": 0.8439017966934105, | |
| "eval_runtime": 742.1666, | |
| "eval_samples_per_second": 82.339, | |
| "eval_steps_per_second": 10.293, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 21.06, | |
| "learning_rate": 4.858356258596974e-07, | |
| "loss": 0.2357, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 4.834284731774415e-07, | |
| "loss": 0.2371, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "eval_accuracy": 0.9024039012256787, | |
| "eval_f1": 0.8585350986459802, | |
| "eval_loss": 0.25968602299690247, | |
| "eval_matthews_correlation": 0.7945932525195208, | |
| "eval_precision": 0.8889130473258957, | |
| "eval_recall": 0.8392043038337625, | |
| "eval_runtime": 741.2239, | |
| "eval_samples_per_second": 82.443, | |
| "eval_steps_per_second": 10.306, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 21.49, | |
| "learning_rate": 4.810213204951857e-07, | |
| "loss": 0.2315, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 21.7, | |
| "learning_rate": 4.786141678129298e-07, | |
| "loss": 0.235, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 21.7, | |
| "eval_accuracy": 0.9023875370240063, | |
| "eval_f1": 0.8579339604243469, | |
| "eval_loss": 0.2591555118560791, | |
| "eval_matthews_correlation": 0.7945022911900744, | |
| "eval_precision": 0.8901148253384278, | |
| "eval_recall": 0.8378479456567698, | |
| "eval_runtime": 750.7123, | |
| "eval_samples_per_second": 81.401, | |
| "eval_steps_per_second": 10.176, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 21.91, | |
| "learning_rate": 4.7620701513067397e-07, | |
| "loss": 0.236, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "learning_rate": 4.737998624484181e-07, | |
| "loss": 0.2337, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "eval_accuracy": 0.9021584382005924, | |
| "eval_f1": 0.860737037506755, | |
| "eval_loss": 0.25833263993263245, | |
| "eval_matthews_correlation": 0.7944254210179659, | |
| "eval_precision": 0.8843675846869027, | |
| "eval_recall": 0.844477056198123, | |
| "eval_runtime": 743.1068, | |
| "eval_samples_per_second": 82.234, | |
| "eval_steps_per_second": 10.28, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 22.34, | |
| "learning_rate": 4.7139270976616234e-07, | |
| "loss": 0.2375, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 4.6898555708390644e-07, | |
| "loss": 0.2281, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "eval_accuracy": 0.9028457346708341, | |
| "eval_f1": 0.8598823495950803, | |
| "eval_loss": 0.25760677456855774, | |
| "eval_matthews_correlation": 0.7955802107006815, | |
| "eval_precision": 0.8886009036729954, | |
| "eval_recall": 0.8410807443232993, | |
| "eval_runtime": 742.6712, | |
| "eval_samples_per_second": 82.283, | |
| "eval_steps_per_second": 10.286, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 22.77, | |
| "learning_rate": 4.665784044016506e-07, | |
| "loss": 0.2303, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "learning_rate": 4.6417125171939476e-07, | |
| "loss": 0.2344, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "eval_accuracy": 0.9032384755109722, | |
| "eval_f1": 0.8614877881378621, | |
| "eval_loss": 0.25682786107063293, | |
| "eval_matthews_correlation": 0.7966375034728815, | |
| "eval_precision": 0.8871158453880478, | |
| "eval_recall": 0.8443591875886006, | |
| "eval_runtime": 739.46, | |
| "eval_samples_per_second": 82.64, | |
| "eval_steps_per_second": 10.331, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 4.617881705639615e-07, | |
| "loss": 0.23, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "learning_rate": 4.5938101788170567e-07, | |
| "loss": 0.2272, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "eval_accuracy": 0.9034512101327137, | |
| "eval_f1": 0.8610570534840231, | |
| "eval_loss": 0.2564578950405121, | |
| "eval_matthews_correlation": 0.7970282021069359, | |
| "eval_precision": 0.8883674341834357, | |
| "eval_recall": 0.8432709063754382, | |
| "eval_runtime": 752.7164, | |
| "eval_samples_per_second": 81.185, | |
| "eval_steps_per_second": 10.149, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 23.62, | |
| "learning_rate": 4.569738651994498e-07, | |
| "loss": 0.2332, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "learning_rate": 4.5456671251719393e-07, | |
| "loss": 0.2293, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "eval_accuracy": 0.9036148521494379, | |
| "eval_f1": 0.8616572588260412, | |
| "eval_loss": 0.25602078437805176, | |
| "eval_matthews_correlation": 0.797432339957468, | |
| "eval_precision": 0.888044730558219, | |
| "eval_recall": 0.8443106476754284, | |
| "eval_runtime": 742.2507, | |
| "eval_samples_per_second": 82.329, | |
| "eval_steps_per_second": 10.292, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 4.521595598349381e-07, | |
| "loss": 0.2294, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "learning_rate": 4.4975240715268225e-07, | |
| "loss": 0.228, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "eval_accuracy": 0.9036803089561276, | |
| "eval_f1": 0.863877165875425, | |
| "eval_loss": 0.2554364502429962, | |
| "eval_matthews_correlation": 0.7978497276838488, | |
| "eval_precision": 0.8853713205361755, | |
| "eval_recall": 0.8485692629483124, | |
| "eval_runtime": 741.2199, | |
| "eval_samples_per_second": 82.444, | |
| "eval_steps_per_second": 10.306, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 24.47, | |
| "learning_rate": 4.4734525447042636e-07, | |
| "loss": 0.2285, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 24.68, | |
| "learning_rate": 4.449381017881705e-07, | |
| "loss": 0.2241, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 24.68, | |
| "eval_accuracy": 0.9043839696280417, | |
| "eval_f1": 0.8622166226518697, | |
| "eval_loss": 0.25478339195251465, | |
| "eval_matthews_correlation": 0.7990088010286016, | |
| "eval_precision": 0.8902756572528782, | |
| "eval_recall": 0.8440660279986302, | |
| "eval_runtime": 744.3537, | |
| "eval_samples_per_second": 82.097, | |
| "eval_steps_per_second": 10.263, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 4.425309491059147e-07, | |
| "loss": 0.2268, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "learning_rate": 4.4012379642365883e-07, | |
| "loss": 0.2245, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "eval_accuracy": 0.9046457968548004, | |
| "eval_f1": 0.8637462915746076, | |
| "eval_loss": 0.2541418671607971, | |
| "eval_matthews_correlation": 0.7996477164682352, | |
| "eval_precision": 0.8892718452758656, | |
| "eval_recall": 0.8464763772370704, | |
| "eval_runtime": 748.8427, | |
| "eval_samples_per_second": 81.605, | |
| "eval_steps_per_second": 10.201, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 4.37716643741403e-07, | |
| "loss": 0.225, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 25.53, | |
| "learning_rate": 4.353094910591472e-07, | |
| "loss": 0.2238, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 25.53, | |
| "eval_accuracy": 0.903811222569507, | |
| "eval_f1": 0.864660167207754, | |
| "eval_loss": 0.25406739115715027, | |
| "eval_matthews_correlation": 0.7983907547582928, | |
| "eval_precision": 0.8839791554106121, | |
| "eval_recall": 0.8508116086209433, | |
| "eval_runtime": 745.3712, | |
| "eval_samples_per_second": 81.985, | |
| "eval_steps_per_second": 10.249, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 25.74, | |
| "learning_rate": 4.3290233837689136e-07, | |
| "loss": 0.2247, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 25.96, | |
| "learning_rate": 4.3049518569463547e-07, | |
| "loss": 0.225, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 25.96, | |
| "eval_accuracy": 0.905054901896611, | |
| "eval_f1": 0.8641024583307882, | |
| "eval_loss": 0.25294584035873413, | |
| "eval_matthews_correlation": 0.8004878158132844, | |
| "eval_precision": 0.8903692184524515, | |
| "eval_recall": 0.84646983821535, | |
| "eval_runtime": 739.4176, | |
| "eval_samples_per_second": 82.645, | |
| "eval_steps_per_second": 10.331, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 26.17, | |
| "learning_rate": 4.2808803301237963e-07, | |
| "loss": 0.2232, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "learning_rate": 4.256808803301238e-07, | |
| "loss": 0.2208, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "eval_accuracy": 0.9049894450899213, | |
| "eval_f1": 0.8656264504704531, | |
| "eval_loss": 0.2527241110801697, | |
| "eval_matthews_correlation": 0.8005795279768213, | |
| "eval_precision": 0.8879028249152308, | |
| "eval_recall": 0.8498085009087021, | |
| "eval_runtime": 738.7805, | |
| "eval_samples_per_second": 82.716, | |
| "eval_steps_per_second": 10.34, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 26.6, | |
| "learning_rate": 4.2327372764786794e-07, | |
| "loss": 0.227, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 26.81, | |
| "learning_rate": 4.2086657496561205e-07, | |
| "loss": 0.2213, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 26.81, | |
| "eval_accuracy": 0.9055949205518009, | |
| "eval_f1": 0.8659007593747939, | |
| "eval_loss": 0.2519753873348236, | |
| "eval_matthews_correlation": 0.8018946867846759, | |
| "eval_precision": 0.8888062714711293, | |
| "eval_recall": 0.8501058257883659, | |
| "eval_runtime": 749.2751, | |
| "eval_samples_per_second": 81.557, | |
| "eval_steps_per_second": 10.195, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 4.184594222833562e-07, | |
| "loss": 0.2185, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 27.23, | |
| "learning_rate": 4.1605226960110037e-07, | |
| "loss": 0.2162, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 27.23, | |
| "eval_accuracy": 0.9055458279467836, | |
| "eval_f1": 0.8654050977825888, | |
| "eval_loss": 0.251761794090271, | |
| "eval_matthews_correlation": 0.8017166743761434, | |
| "eval_precision": 0.8894291889404059, | |
| "eval_recall": 0.8490704765886147, | |
| "eval_runtime": 736.7918, | |
| "eval_samples_per_second": 82.939, | |
| "eval_steps_per_second": 10.368, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 4.136451169188445e-07, | |
| "loss": 0.2249, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 27.66, | |
| "learning_rate": 4.112379642365887e-07, | |
| "loss": 0.2191, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 27.66, | |
| "eval_accuracy": 0.9057749267701976, | |
| "eval_f1": 0.8640115443984718, | |
| "eval_loss": 0.251422643661499, | |
| "eval_matthews_correlation": 0.8019134866391471, | |
| "eval_precision": 0.8934815340390392, | |
| "eval_recall": 0.844930576575448, | |
| "eval_runtime": 737.5683, | |
| "eval_samples_per_second": 82.852, | |
| "eval_steps_per_second": 10.357, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 27.87, | |
| "learning_rate": 4.088308115543329e-07, | |
| "loss": 0.2188, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "learning_rate": 4.0642365887207706e-07, | |
| "loss": 0.2191, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "eval_accuracy": 0.9049894450899213, | |
| "eval_f1": 0.8675464478616566, | |
| "eval_loss": 0.2514873445034027, | |
| "eval_matthews_correlation": 0.8011420603338137, | |
| "eval_precision": 0.8844914181097606, | |
| "eval_recall": 0.8548387805177459, | |
| "eval_runtime": 745.343, | |
| "eval_samples_per_second": 81.988, | |
| "eval_steps_per_second": 10.249, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 28.3, | |
| "learning_rate": 4.0401650618982116e-07, | |
| "loss": 0.219, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 28.51, | |
| "learning_rate": 4.016093535075653e-07, | |
| "loss": 0.2205, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 28.51, | |
| "eval_accuracy": 0.9057094699635079, | |
| "eval_f1": 0.8676904171040173, | |
| "eval_loss": 0.25054237246513367, | |
| "eval_matthews_correlation": 0.8024081650223417, | |
| "eval_precision": 0.8869776283900569, | |
| "eval_recall": 0.8535847409175318, | |
| "eval_runtime": 750.8946, | |
| "eval_samples_per_second": 81.382, | |
| "eval_steps_per_second": 10.173, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 28.72, | |
| "learning_rate": 3.992022008253095e-07, | |
| "loss": 0.216, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 28.94, | |
| "learning_rate": 3.9679504814305364e-07, | |
| "loss": 0.214, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 28.94, | |
| "eval_accuracy": 0.9062331244170253, | |
| "eval_f1": 0.867645791485915, | |
| "eval_loss": 0.24997290968894958, | |
| "eval_matthews_correlation": 0.8033874172790445, | |
| "eval_precision": 0.8886721526351784, | |
| "eval_recall": 0.852700998600651, | |
| "eval_runtime": 745.2233, | |
| "eval_samples_per_second": 82.001, | |
| "eval_steps_per_second": 10.251, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 29.15, | |
| "learning_rate": 3.943878954607978e-07, | |
| "loss": 0.2144, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 29.36, | |
| "learning_rate": 3.919807427785419e-07, | |
| "loss": 0.2207, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 29.36, | |
| "eval_accuracy": 0.9066913220638532, | |
| "eval_f1": 0.8675697100687536, | |
| "eval_loss": 0.2494281381368637, | |
| "eval_matthews_correlation": 0.8042043740475852, | |
| "eval_precision": 0.8908271504932497, | |
| "eval_recall": 0.851473961737513, | |
| "eval_runtime": 736.0083, | |
| "eval_samples_per_second": 83.028, | |
| "eval_steps_per_second": 10.379, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "learning_rate": 3.8957359009628606e-07, | |
| "loss": 0.2122, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 29.79, | |
| "learning_rate": 3.871664374140302e-07, | |
| "loss": 0.219, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 29.79, | |
| "eval_accuracy": 0.9062331244170253, | |
| "eval_f1": 0.8687037334671018, | |
| "eval_loss": 0.249604269862175, | |
| "eval_matthews_correlation": 0.8036021820406698, | |
| "eval_precision": 0.8873113636744671, | |
| "eval_recall": 0.8550087041944906, | |
| "eval_runtime": 741.2966, | |
| "eval_samples_per_second": 82.435, | |
| "eval_steps_per_second": 10.305, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 3.8475928473177443e-07, | |
| "loss": 0.2116, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "learning_rate": 3.823521320495186e-07, | |
| "loss": 0.2142, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "eval_accuracy": 0.906494951643784, | |
| "eval_f1": 0.8680762828304092, | |
| "eval_loss": 0.24876296520233154, | |
| "eval_matthews_correlation": 0.8038881291758961, | |
| "eval_precision": 0.8895630825937241, | |
| "eval_recall": 0.852751783692581, | |
| "eval_runtime": 754.682, | |
| "eval_samples_per_second": 80.973, | |
| "eval_steps_per_second": 10.122, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 30.43, | |
| "learning_rate": 3.7996905089408523e-07, | |
| "loss": 0.2134, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 30.64, | |
| "learning_rate": 3.775618982118294e-07, | |
| "loss": 0.2141, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 30.64, | |
| "eval_accuracy": 0.9072640691223879, | |
| "eval_f1": 0.8685185701276202, | |
| "eval_loss": 0.2483629435300827, | |
| "eval_matthews_correlation": 0.8053746864658841, | |
| "eval_precision": 0.8919558059100855, | |
| "eval_recall": 0.8520663663180831, | |
| "eval_runtime": 738.298, | |
| "eval_samples_per_second": 82.77, | |
| "eval_steps_per_second": 10.347, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 30.85, | |
| "learning_rate": 3.7515474552957355e-07, | |
| "loss": 0.2114, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 31.06, | |
| "learning_rate": 3.7274759284731776e-07, | |
| "loss": 0.2126, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 31.06, | |
| "eval_accuracy": 0.9075749889541639, | |
| "eval_f1": 0.8683508503340195, | |
| "eval_loss": 0.24826984107494354, | |
| "eval_matthews_correlation": 0.8060075540928401, | |
| "eval_precision": 0.8931309736871068, | |
| "eval_recall": 0.8514670976479711, | |
| "eval_runtime": 739.7867, | |
| "eval_samples_per_second": 82.604, | |
| "eval_steps_per_second": 10.326, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 31.28, | |
| "learning_rate": 3.703404401650619e-07, | |
| "loss": 0.2127, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 31.49, | |
| "learning_rate": 3.679332874828061e-07, | |
| "loss": 0.2109, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 31.49, | |
| "eval_accuracy": 0.90734589013075, | |
| "eval_f1": 0.8685226338776406, | |
| "eval_loss": 0.24782830476760864, | |
| "eval_matthews_correlation": 0.8055607272223679, | |
| "eval_precision": 0.8920656839237181, | |
| "eval_recall": 0.8521065453558755, | |
| "eval_runtime": 749.8464, | |
| "eval_samples_per_second": 81.495, | |
| "eval_steps_per_second": 10.187, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 31.7, | |
| "learning_rate": 3.655261348005502e-07, | |
| "loss": 0.2129, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 31.91, | |
| "learning_rate": 3.6311898211829434e-07, | |
| "loss": 0.2112, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 31.91, | |
| "eval_accuracy": 0.9076240815591812, | |
| "eval_f1": 0.8678417140935201, | |
| "eval_loss": 0.24749217927455902, | |
| "eval_matthews_correlation": 0.8060172776856861, | |
| "eval_precision": 0.894366472061838, | |
| "eval_recall": 0.8500650948722064, | |
| "eval_runtime": 752.8019, | |
| "eval_samples_per_second": 81.175, | |
| "eval_steps_per_second": 10.147, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 3.607118294360385e-07, | |
| "loss": 0.2096, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "learning_rate": 3.5830467675378266e-07, | |
| "loss": 0.2101, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "eval_accuracy": 0.9075586247524915, | |
| "eval_f1": 0.8688133561667789, | |
| "eval_loss": 0.2471538633108139, | |
| "eval_matthews_correlation": 0.8060577001402198, | |
| "eval_precision": 0.8922446411765517, | |
| "eval_recall": 0.8526258792755002, | |
| "eval_runtime": 741.9397, | |
| "eval_samples_per_second": 82.364, | |
| "eval_steps_per_second": 10.296, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 32.55, | |
| "learning_rate": 3.5589752407152677e-07, | |
| "loss": 0.2103, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 32.77, | |
| "learning_rate": 3.534903713892709e-07, | |
| "loss": 0.2118, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 32.77, | |
| "eval_accuracy": 0.9074440753407845, | |
| "eval_f1": 0.8694313427193112, | |
| "eval_loss": 0.24689117074012756, | |
| "eval_matthews_correlation": 0.8059002977899355, | |
| "eval_precision": 0.8910870495474871, | |
| "eval_recall": 0.8539698095446958, | |
| "eval_runtime": 743.6136, | |
| "eval_samples_per_second": 82.178, | |
| "eval_steps_per_second": 10.273, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 32.98, | |
| "learning_rate": 3.510832187070151e-07, | |
| "loss": 0.2063, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 3.486760660247593e-07, | |
| "loss": 0.2076, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "eval_accuracy": 0.9079350013909572, | |
| "eval_f1": 0.8697927249175175, | |
| "eval_loss": 0.24656882882118225, | |
| "eval_matthews_correlation": 0.8068707039804212, | |
| "eval_precision": 0.8925155749184236, | |
| "eval_recall": 0.8537441567974152, | |
| "eval_runtime": 742.1498, | |
| "eval_samples_per_second": 82.341, | |
| "eval_steps_per_second": 10.293, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 3.462689133425034e-07, | |
| "loss": 0.2083, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 33.62, | |
| "learning_rate": 3.4386176066024756e-07, | |
| "loss": 0.2045, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 33.62, | |
| "eval_accuracy": 0.9080004581976469, | |
| "eval_f1": 0.8675131816041591, | |
| "eval_loss": 0.246909961104393, | |
| "eval_matthews_correlation": 0.8067187118432039, | |
| "eval_precision": 0.8969134215836245, | |
| "eval_recall": 0.8483570812735763, | |
| "eval_runtime": 754.8684, | |
| "eval_samples_per_second": 80.953, | |
| "eval_steps_per_second": 10.12, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 33.83, | |
| "learning_rate": 3.4145460797799177e-07, | |
| "loss": 0.2082, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 34.04, | |
| "learning_rate": 3.390474552957359e-07, | |
| "loss": 0.2085, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 34.04, | |
| "eval_accuracy": 0.9081313718110262, | |
| "eval_f1": 0.8710620558469785, | |
| "eval_loss": 0.246111661195755, | |
| "eval_matthews_correlation": 0.8075115150125068, | |
| "eval_precision": 0.8909909483708672, | |
| "eval_recall": 0.8565113019506504, | |
| "eval_runtime": 738.1997, | |
| "eval_samples_per_second": 82.781, | |
| "eval_steps_per_second": 10.348, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 34.26, | |
| "learning_rate": 3.3664030261348004e-07, | |
| "loss": 0.2042, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 34.47, | |
| "learning_rate": 3.342331499312242e-07, | |
| "loss": 0.2058, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 34.47, | |
| "eval_accuracy": 0.9084259274411298, | |
| "eval_f1": 0.8703727106005682, | |
| "eval_loss": 0.2457207441329956, | |
| "eval_matthews_correlation": 0.8079506680918748, | |
| "eval_precision": 0.8931130297108375, | |
| "eval_recall": 0.8544519579982045, | |
| "eval_runtime": 741.949, | |
| "eval_samples_per_second": 82.363, | |
| "eval_steps_per_second": 10.296, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 34.68, | |
| "learning_rate": 3.3182599724896835e-07, | |
| "loss": 0.2072, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 34.89, | |
| "learning_rate": 3.2941884456671246e-07, | |
| "loss": 0.2058, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 34.89, | |
| "eval_accuracy": 0.9084913842478195, | |
| "eval_f1": 0.8708104266168474, | |
| "eval_loss": 0.2456207275390625, | |
| "eval_matthews_correlation": 0.8081614856249896, | |
| "eval_precision": 0.8925443643292025, | |
| "eval_recall": 0.8554175551765084, | |
| "eval_runtime": 746.0001, | |
| "eval_samples_per_second": 81.916, | |
| "eval_steps_per_second": 10.24, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 35.11, | |
| "learning_rate": 3.2701169188445667e-07, | |
| "loss": 0.2109, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 35.32, | |
| "learning_rate": 3.2460453920220083e-07, | |
| "loss": 0.207, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 35.32, | |
| "eval_accuracy": 0.9085732052561816, | |
| "eval_f1": 0.8695274706079684, | |
| "eval_loss": 0.24534425139427185, | |
| "eval_matthews_correlation": 0.80811600198511, | |
| "eval_precision": 0.8951195580549336, | |
| "eval_recall": 0.8522425039487266, | |
| "eval_runtime": 751.7816, | |
| "eval_samples_per_second": 81.286, | |
| "eval_steps_per_second": 10.161, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 35.53, | |
| "learning_rate": 3.22197386519945e-07, | |
| "loss": 0.2051, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 35.74, | |
| "learning_rate": 3.197902338376891e-07, | |
| "loss": 0.1983, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 35.74, | |
| "eval_accuracy": 0.907853180382595, | |
| "eval_f1": 0.871964648841848, | |
| "eval_loss": 0.24542571604251862, | |
| "eval_matthews_correlation": 0.8072695576967016, | |
| "eval_precision": 0.8884804951307341, | |
| "eval_recall": 0.8593824892770483, | |
| "eval_runtime": 746.5178, | |
| "eval_samples_per_second": 81.859, | |
| "eval_steps_per_second": 10.233, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 35.96, | |
| "learning_rate": 3.1738308115543325e-07, | |
| "loss": 0.2041, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 36.17, | |
| "learning_rate": 3.1497592847317746e-07, | |
| "loss": 0.2031, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 36.17, | |
| "eval_accuracy": 0.9087859398779231, | |
| "eval_f1": 0.8694601945231047, | |
| "eval_loss": 0.24508897960186005, | |
| "eval_matthews_correlation": 0.8085159705148504, | |
| "eval_precision": 0.8963359573586805, | |
| "eval_recall": 0.8515431618805932, | |
| "eval_runtime": 741.3509, | |
| "eval_samples_per_second": 82.429, | |
| "eval_steps_per_second": 10.304, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 36.38, | |
| "learning_rate": 3.1256877579092157e-07, | |
| "loss": 0.2029, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 36.6, | |
| "learning_rate": 3.1016162310866573e-07, | |
| "loss": 0.2037, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 36.6, | |
| "eval_accuracy": 0.90890048928963, | |
| "eval_f1": 0.8713599651821928, | |
| "eval_loss": 0.2446085512638092, | |
| "eval_matthews_correlation": 0.8089947448606745, | |
| "eval_precision": 0.8934233371557734, | |
| "eval_recall": 0.8556962381944763, | |
| "eval_runtime": 739.8731, | |
| "eval_samples_per_second": 82.594, | |
| "eval_steps_per_second": 10.325, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 36.81, | |
| "learning_rate": 3.077544704264099e-07, | |
| "loss": 0.2007, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 3.0534731774415405e-07, | |
| "loss": 0.2039, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "eval_accuracy": 0.9089495818946473, | |
| "eval_f1": 0.8721432834897387, | |
| "eval_loss": 0.24436742067337036, | |
| "eval_matthews_correlation": 0.8092876273116901, | |
| "eval_precision": 0.892041748943175, | |
| "eval_recall": 0.8577428291713033, | |
| "eval_runtime": 751.7628, | |
| "eval_samples_per_second": 81.288, | |
| "eval_steps_per_second": 10.161, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 37.23, | |
| "learning_rate": 3.029401650618982e-07, | |
| "loss": 0.2043, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 37.45, | |
| "learning_rate": 3.0053301237964236e-07, | |
| "loss": 0.1991, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 37.45, | |
| "eval_accuracy": 0.9091132239113715, | |
| "eval_f1": 0.8712923172635568, | |
| "eval_loss": 0.24404539167881012, | |
| "eval_matthews_correlation": 0.8093881662403425, | |
| "eval_precision": 0.8943403115909888, | |
| "eval_recall": 0.8551265425080193, | |
| "eval_runtime": 740.8242, | |
| "eval_samples_per_second": 82.488, | |
| "eval_steps_per_second": 10.311, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 37.66, | |
| "learning_rate": 2.981258596973865e-07, | |
| "loss": 0.2039, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 37.87, | |
| "learning_rate": 2.957187070151307e-07, | |
| "loss": 0.1987, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 37.87, | |
| "eval_accuracy": 0.9090804955080266, | |
| "eval_f1": 0.8719347271029217, | |
| "eval_loss": 0.24388256669044495, | |
| "eval_matthews_correlation": 0.8094381432711057, | |
| "eval_precision": 0.8931812855590735, | |
| "eval_recall": 0.8566921567493543, | |
| "eval_runtime": 744.8306, | |
| "eval_samples_per_second": 82.044, | |
| "eval_steps_per_second": 10.256, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 38.09, | |
| "learning_rate": 2.933115543328748e-07, | |
| "loss": 0.1994, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 38.3, | |
| "learning_rate": 2.9090440165061894e-07, | |
| "loss": 0.2029, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 38.3, | |
| "eval_accuracy": 0.9086059336595265, | |
| "eval_f1": 0.8729315195273094, | |
| "eval_loss": 0.2439950406551361, | |
| "eval_matthews_correlation": 0.8088593944730788, | |
| "eval_precision": 0.8896414828192207, | |
| "eval_recall": 0.8602966512277792, | |
| "eval_runtime": 743.7981, | |
| "eval_samples_per_second": 82.158, | |
| "eval_steps_per_second": 10.27, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 38.51, | |
| "learning_rate": 2.8849724896836316e-07, | |
| "loss": 0.1999, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 38.72, | |
| "learning_rate": 2.8609009628610726e-07, | |
| "loss": 0.1979, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 38.72, | |
| "eval_accuracy": 0.9096041499615442, | |
| "eval_f1": 0.8726507105657216, | |
| "eval_loss": 0.24374985694885254, | |
| "eval_matthews_correlation": 0.8105181128329951, | |
| "eval_precision": 0.8942523767849427, | |
| "eval_recall": 0.8571308075255727, | |
| "eval_runtime": 761.2563, | |
| "eval_samples_per_second": 80.274, | |
| "eval_steps_per_second": 10.035, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 38.94, | |
| "learning_rate": 2.836829436038514e-07, | |
| "loss": 0.1991, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 39.15, | |
| "learning_rate": 2.812757909215956e-07, | |
| "loss": 0.1976, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 39.15, | |
| "eval_accuracy": 0.9094077795414751, | |
| "eval_f1": 0.8727723424343431, | |
| "eval_loss": 0.24345378577709198, | |
| "eval_matthews_correlation": 0.8102216224369119, | |
| "eval_precision": 0.892994687316735, | |
| "eval_recall": 0.8580974781646172, | |
| "eval_runtime": 745.8574, | |
| "eval_samples_per_second": 81.931, | |
| "eval_steps_per_second": 10.242, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 39.36, | |
| "learning_rate": 2.7886863823933974e-07, | |
| "loss": 0.1999, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "learning_rate": 2.764614855570839e-07, | |
| "loss": 0.1998, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "eval_accuracy": 0.9093586869364578, | |
| "eval_f1": 0.8731071210160151, | |
| "eval_loss": 0.24329745769500732, | |
| "eval_matthews_correlation": 0.810291015551236, | |
| "eval_precision": 0.8918008827080101, | |
| "eval_recall": 0.8594994809403819, | |
| "eval_runtime": 743.2655, | |
| "eval_samples_per_second": 82.217, | |
| "eval_steps_per_second": 10.278, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 39.79, | |
| "learning_rate": 2.7405433287482806e-07, | |
| "loss": 0.1963, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.716471801925722e-07, | |
| "loss": 0.1991, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9097350635749235, | |
| "eval_f1": 0.8721199545387476, | |
| "eval_loss": 0.24315683543682098, | |
| "eval_matthews_correlation": 0.8106751456907673, | |
| "eval_precision": 0.8956919850283284, | |
| "eval_recall": 0.8555874788532533, | |
| "eval_runtime": 746.9224, | |
| "eval_samples_per_second": 81.814, | |
| "eval_steps_per_second": 10.227, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 40.21, | |
| "learning_rate": 2.6924002751031637e-07, | |
| "loss": 0.1975, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 40.43, | |
| "learning_rate": 2.668328748280605e-07, | |
| "loss": 0.1987, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 40.43, | |
| "eval_accuracy": 0.9090477671046818, | |
| "eval_f1": 0.8727541153629755, | |
| "eval_loss": 0.24294930696487427, | |
| "eval_matthews_correlation": 0.8095974827888198, | |
| "eval_precision": 0.8914797277254355, | |
| "eval_recall": 0.858983790728077, | |
| "eval_runtime": 749.8186, | |
| "eval_samples_per_second": 81.498, | |
| "eval_steps_per_second": 10.188, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 40.64, | |
| "learning_rate": 2.6442572214580464e-07, | |
| "loss": 0.1952, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 40.85, | |
| "learning_rate": 2.620426409903714e-07, | |
| "loss": 0.1976, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 40.85, | |
| "eval_accuracy": 0.9097841561799408, | |
| "eval_f1": 0.872683199992249, | |
| "eval_loss": 0.24285992980003357, | |
| "eval_matthews_correlation": 0.8109297645828953, | |
| "eval_precision": 0.8944717841896703, | |
| "eval_recall": 0.8572710599613864, | |
| "eval_runtime": 752.1052, | |
| "eval_samples_per_second": 81.251, | |
| "eval_steps_per_second": 10.157, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 41.06, | |
| "learning_rate": 2.5963548830811555e-07, | |
| "loss": 0.1961, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 41.28, | |
| "learning_rate": 2.5722833562585965e-07, | |
| "loss": 0.2017, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 41.28, | |
| "eval_accuracy": 0.9099314339949925, | |
| "eval_f1": 0.8730188066211935, | |
| "eval_loss": 0.24267245829105377, | |
| "eval_matthews_correlation": 0.8112522802158343, | |
| "eval_precision": 0.8945637840197834, | |
| "eval_recall": 0.8576804628217713, | |
| "eval_runtime": 746.8685, | |
| "eval_samples_per_second": 81.82, | |
| "eval_steps_per_second": 10.228, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 41.49, | |
| "learning_rate": 2.548211829436038e-07, | |
| "loss": 0.1942, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 41.7, | |
| "learning_rate": 2.52414030261348e-07, | |
| "loss": 0.1971, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 41.7, | |
| "eval_accuracy": 0.9096041499615442, | |
| "eval_f1": 0.8735390507743382, | |
| "eval_loss": 0.24244600534439087, | |
| "eval_matthews_correlation": 0.8107460289807942, | |
| "eval_precision": 0.8925036461858465, | |
| "eval_recall": 0.8595422302247533, | |
| "eval_runtime": 747.3405, | |
| "eval_samples_per_second": 81.769, | |
| "eval_steps_per_second": 10.222, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 41.91, | |
| "learning_rate": 2.500068775790922e-07, | |
| "loss": 0.1917, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 42.13, | |
| "learning_rate": 2.475997248968363e-07, | |
| "loss": 0.1946, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 42.13, | |
| "eval_accuracy": 0.9096368783648889, | |
| "eval_f1": 0.874113149714388, | |
| "eval_loss": 0.24247263371944427, | |
| "eval_matthews_correlation": 0.811004627436087, | |
| "eval_precision": 0.8913735929095795, | |
| "eval_recall": 0.861217775525328, | |
| "eval_runtime": 756.2136, | |
| "eval_samples_per_second": 80.809, | |
| "eval_steps_per_second": 10.102, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 42.34, | |
| "learning_rate": 2.4519257221458044e-07, | |
| "loss": 0.195, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 42.55, | |
| "learning_rate": 2.427854195323246e-07, | |
| "loss": 0.1924, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 42.55, | |
| "eval_accuracy": 0.9096696067682338, | |
| "eval_f1": 0.8741752540282713, | |
| "eval_loss": 0.24245992302894592, | |
| "eval_matthews_correlation": 0.8110785773139436, | |
| "eval_precision": 0.8913748490482861, | |
| "eval_recall": 0.8613116349694508, | |
| "eval_runtime": 742.7503, | |
| "eval_samples_per_second": 82.274, | |
| "eval_steps_per_second": 10.285, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 42.77, | |
| "learning_rate": 2.4037826685006876e-07, | |
| "loss": 0.197, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 42.98, | |
| "learning_rate": 2.3797111416781292e-07, | |
| "loss": 0.1941, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 42.98, | |
| "eval_accuracy": 0.9098168845832856, | |
| "eval_f1": 0.8738721398767385, | |
| "eval_loss": 0.24205400049686432, | |
| "eval_matthews_correlation": 0.8111798243968735, | |
| "eval_precision": 0.8929678894520333, | |
| "eval_recall": 0.8597504128283546, | |
| "eval_runtime": 747.1909, | |
| "eval_samples_per_second": 81.785, | |
| "eval_steps_per_second": 10.224, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 2.3556396148555708e-07, | |
| "loss": 0.1945, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 43.4, | |
| "learning_rate": 2.3315680880330124e-07, | |
| "loss": 0.1925, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 43.4, | |
| "eval_accuracy": 0.9098168845832856, | |
| "eval_f1": 0.8737181606915122, | |
| "eval_loss": 0.2419564574956894, | |
| "eval_matthews_correlation": 0.811203316782751, | |
| "eval_precision": 0.8928199742952545, | |
| "eval_recall": 0.8597244835520194, | |
| "eval_runtime": 751.5582, | |
| "eval_samples_per_second": 81.31, | |
| "eval_steps_per_second": 10.164, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 43.62, | |
| "learning_rate": 2.3074965612104537e-07, | |
| "loss": 0.1928, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 43.83, | |
| "learning_rate": 2.2834250343878953e-07, | |
| "loss": 0.193, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 43.83, | |
| "eval_accuracy": 0.9097023351715786, | |
| "eval_f1": 0.8739989567109828, | |
| "eval_loss": 0.2419792115688324, | |
| "eval_matthews_correlation": 0.811123761250777, | |
| "eval_precision": 0.8915912375928783, | |
| "eval_recall": 0.860990625992209, | |
| "eval_runtime": 755.6743, | |
| "eval_samples_per_second": 80.867, | |
| "eval_steps_per_second": 10.109, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 44.04, | |
| "learning_rate": 2.2593535075653371e-07, | |
| "loss": 0.1952, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 44.26, | |
| "learning_rate": 2.2352819807427785e-07, | |
| "loss": 0.1928, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 44.26, | |
| "eval_accuracy": 0.9099150697933202, | |
| "eval_f1": 0.8742112339895834, | |
| "eval_loss": 0.2418925017118454, | |
| "eval_matthews_correlation": 0.8115406626215701, | |
| "eval_precision": 0.8920952424009275, | |
| "eval_recall": 0.8609913743851282, | |
| "eval_runtime": 745.9913, | |
| "eval_samples_per_second": 81.917, | |
| "eval_steps_per_second": 10.24, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 44.47, | |
| "learning_rate": 2.21121045392022e-07, | |
| "loss": 0.1909, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 44.68, | |
| "learning_rate": 2.1871389270976614e-07, | |
| "loss": 0.1923, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 44.68, | |
| "eval_accuracy": 0.9105041810535273, | |
| "eval_f1": 0.874316975987767, | |
| "eval_loss": 0.2416362762451172, | |
| "eval_matthews_correlation": 0.812580262506876, | |
| "eval_precision": 0.8944898131806891, | |
| "eval_recall": 0.859724906877117, | |
| "eval_runtime": 744.1718, | |
| "eval_samples_per_second": 82.117, | |
| "eval_steps_per_second": 10.265, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 44.89, | |
| "learning_rate": 2.163067400275103e-07, | |
| "loss": 0.1934, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 45.11, | |
| "learning_rate": 2.1392365887207702e-07, | |
| "loss": 0.1895, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 45.11, | |
| "eval_accuracy": 0.9105205452551998, | |
| "eval_f1": 0.8722078400643984, | |
| "eval_loss": 0.2422172725200653, | |
| "eval_matthews_correlation": 0.8122786320101358, | |
| "eval_precision": 0.8983590023748841, | |
| "eval_recall": 0.8545989459702907, | |
| "eval_runtime": 741.2328, | |
| "eval_samples_per_second": 82.442, | |
| "eval_steps_per_second": 10.306, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 45.32, | |
| "learning_rate": 2.1151650618982118e-07, | |
| "loss": 0.191, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 45.53, | |
| "learning_rate": 2.091093535075653e-07, | |
| "loss": 0.192, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 45.53, | |
| "eval_accuracy": 0.9102423538267685, | |
| "eval_f1": 0.8743146922489909, | |
| "eval_loss": 0.24138787388801575, | |
| "eval_matthews_correlation": 0.8120982187500523, | |
| "eval_precision": 0.8935139726217215, | |
| "eval_recall": 0.8602445658645633, | |
| "eval_runtime": 752.2607, | |
| "eval_samples_per_second": 81.234, | |
| "eval_steps_per_second": 10.155, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 45.74, | |
| "learning_rate": 2.0670220082530947e-07, | |
| "loss": 0.1913, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 45.96, | |
| "learning_rate": 2.0429504814305363e-07, | |
| "loss": 0.1912, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 45.96, | |
| "eval_accuracy": 0.9101932612217513, | |
| "eval_f1": 0.8748401862258565, | |
| "eval_loss": 0.24133703112602234, | |
| "eval_matthews_correlation": 0.8121627721616604, | |
| "eval_precision": 0.8922978706813973, | |
| "eval_recall": 0.8618021442983398, | |
| "eval_runtime": 741.2809, | |
| "eval_samples_per_second": 82.437, | |
| "eval_steps_per_second": 10.305, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 46.17, | |
| "learning_rate": 2.018878954607978e-07, | |
| "loss": 0.1945, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 46.38, | |
| "learning_rate": 1.9948074277854194e-07, | |
| "loss": 0.1878, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 46.38, | |
| "eval_accuracy": 0.9099641623983374, | |
| "eval_f1": 0.8749444985348495, | |
| "eval_loss": 0.2415376454591751, | |
| "eval_matthews_correlation": 0.8117670504578143, | |
| "eval_precision": 0.891458264723633, | |
| "eval_recall": 0.8624156627299087, | |
| "eval_runtime": 743.8046, | |
| "eval_samples_per_second": 82.157, | |
| "eval_steps_per_second": 10.27, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 46.6, | |
| "learning_rate": 1.970735900962861e-07, | |
| "loss": 0.1911, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 46.81, | |
| "learning_rate": 1.9466643741403024e-07, | |
| "loss": 0.1912, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 46.81, | |
| "eval_accuracy": 0.9104387242468376, | |
| "eval_f1": 0.8741819314594247, | |
| "eval_loss": 0.24110712110996246, | |
| "eval_matthews_correlation": 0.8124326381078381, | |
| "eval_precision": 0.8944450308572095, | |
| "eval_recall": 0.8595371879888715, | |
| "eval_runtime": 742.2886, | |
| "eval_samples_per_second": 82.325, | |
| "eval_steps_per_second": 10.291, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 1.922592847317744e-07, | |
| "loss": 0.1906, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 47.23, | |
| "learning_rate": 1.8985213204951858e-07, | |
| "loss": 0.1905, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 47.23, | |
| "eval_accuracy": 0.9106187304652342, | |
| "eval_f1": 0.8742166094007501, | |
| "eval_loss": 0.24093787372112274, | |
| "eval_matthews_correlation": 0.8127323260629485, | |
| "eval_precision": 0.8954204606441226, | |
| "eval_recall": 0.8589773499636327, | |
| "eval_runtime": 748.4618, | |
| "eval_samples_per_second": 81.646, | |
| "eval_steps_per_second": 10.206, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 47.45, | |
| "learning_rate": 1.874449793672627e-07, | |
| "loss": 0.1901, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 47.66, | |
| "learning_rate": 1.8503782668500687e-07, | |
| "loss": 0.1904, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 47.66, | |
| "eval_accuracy": 0.9104059958434928, | |
| "eval_f1": 0.8742663877233575, | |
| "eval_loss": 0.24106551706790924, | |
| "eval_matthews_correlation": 0.8123897699414998, | |
| "eval_precision": 0.894213768652531, | |
| "eval_recall": 0.8598063384134425, | |
| "eval_runtime": 744.7161, | |
| "eval_samples_per_second": 82.057, | |
| "eval_steps_per_second": 10.258, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 47.87, | |
| "learning_rate": 1.8263067400275103e-07, | |
| "loss": 0.1863, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "learning_rate": 1.8022352132049516e-07, | |
| "loss": 0.1897, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "eval_accuracy": 0.9108641934903206, | |
| "eval_f1": 0.8748685488468945, | |
| "eval_loss": 0.24090926349163055, | |
| "eval_matthews_correlation": 0.8132937556039521, | |
| "eval_precision": 0.8954126640738053, | |
| "eval_recall": 0.8599276239197389, | |
| "eval_runtime": 741.0969, | |
| "eval_samples_per_second": 82.458, | |
| "eval_steps_per_second": 10.308, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 48.3, | |
| "learning_rate": 1.7781636863823935e-07, | |
| "loss": 0.1874, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 48.51, | |
| "learning_rate": 1.754092159559835e-07, | |
| "loss": 0.1904, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 48.51, | |
| "eval_accuracy": 0.9108805576919929, | |
| "eval_f1": 0.8750717050514312, | |
| "eval_loss": 0.24086318910121918, | |
| "eval_matthews_correlation": 0.8133710577922498, | |
| "eval_precision": 0.895092107684644, | |
| "eval_recall": 0.8604283159776674, | |
| "eval_runtime": 739.1681, | |
| "eval_samples_per_second": 82.673, | |
| "eval_steps_per_second": 10.335, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 48.72, | |
| "learning_rate": 1.7300206327372764e-07, | |
| "loss": 0.1902, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 48.94, | |
| "learning_rate": 1.705949105914718e-07, | |
| "loss": 0.188, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 48.94, | |
| "eval_accuracy": 0.9103732674401479, | |
| "eval_f1": 0.875369556789435, | |
| "eval_loss": 0.2407529205083847, | |
| "eval_matthews_correlation": 0.8125919221461162, | |
| "eval_precision": 0.8922872454470531, | |
| "eval_recall": 0.8625906286425353, | |
| "eval_runtime": 747.8812, | |
| "eval_samples_per_second": 81.71, | |
| "eval_steps_per_second": 10.214, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 49.15, | |
| "learning_rate": 1.6818775790921595e-07, | |
| "loss": 0.1851, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 49.36, | |
| "learning_rate": 1.657806052269601e-07, | |
| "loss": 0.1909, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 49.36, | |
| "eval_accuracy": 0.9109296502970102, | |
| "eval_f1": 0.8746313053916013, | |
| "eval_loss": 0.24063973128795624, | |
| "eval_matthews_correlation": 0.8133910501963836, | |
| "eval_precision": 0.8959133105343128, | |
| "eval_recall": 0.859337464517926, | |
| "eval_runtime": 742.5919, | |
| "eval_samples_per_second": 82.292, | |
| "eval_steps_per_second": 10.287, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "learning_rate": 1.6337345254470425e-07, | |
| "loss": 0.187, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 49.79, | |
| "learning_rate": 1.6099037138927097e-07, | |
| "loss": 0.186, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 49.79, | |
| "eval_accuracy": 0.9101768970200789, | |
| "eval_f1": 0.8753978543653685, | |
| "eval_loss": 0.24069301784038544, | |
| "eval_matthews_correlation": 0.8122564726191961, | |
| "eval_precision": 0.8915507771756968, | |
| "eval_recall": 0.8630646430312097, | |
| "eval_runtime": 744.7662, | |
| "eval_samples_per_second": 82.051, | |
| "eval_steps_per_second": 10.257, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 1.5858321870701513e-07, | |
| "loss": 0.1877, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 50.21, | |
| "learning_rate": 1.5617606602475929e-07, | |
| "loss": 0.1881, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 50.21, | |
| "eval_accuracy": 0.9105369094568722, | |
| "eval_f1": 0.8752674535162299, | |
| "eval_loss": 0.24077627062797546, | |
| "eval_matthews_correlation": 0.8128808529504822, | |
| "eval_precision": 0.8928712715800744, | |
| "eval_recall": 0.8621524011914147, | |
| "eval_runtime": 739.9032, | |
| "eval_samples_per_second": 82.591, | |
| "eval_steps_per_second": 10.324, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 50.43, | |
| "learning_rate": 1.5376891334250342e-07, | |
| "loss": 0.1856, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 50.64, | |
| "learning_rate": 1.513617606602476e-07, | |
| "loss": 0.1848, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 50.64, | |
| "eval_accuracy": 0.9103896316418204, | |
| "eval_f1": 0.875465347493809, | |
| "eval_loss": 0.2406722754240036, | |
| "eval_matthews_correlation": 0.8126619796181362, | |
| "eval_precision": 0.8921096020639947, | |
| "eval_recall": 0.862883886489782, | |
| "eval_runtime": 749.2847, | |
| "eval_samples_per_second": 81.556, | |
| "eval_steps_per_second": 10.195, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 50.85, | |
| "learning_rate": 1.4895460797799174e-07, | |
| "loss": 0.1891, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 51.06, | |
| "learning_rate": 1.465474552957359e-07, | |
| "loss": 0.1863, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 51.06, | |
| "eval_accuracy": 0.9103078106334582, | |
| "eval_f1": 0.8753293970227211, | |
| "eval_loss": 0.24059292674064636, | |
| "eval_matthews_correlation": 0.812532435225692, | |
| "eval_precision": 0.8916938221865601, | |
| "eval_recall": 0.8629992831100012, | |
| "eval_runtime": 739.941, | |
| "eval_samples_per_second": 82.586, | |
| "eval_steps_per_second": 10.324, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 1.4414030261348005e-07, | |
| "loss": 0.1844, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 51.49, | |
| "learning_rate": 1.417331499312242e-07, | |
| "loss": 0.1847, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 51.49, | |
| "eval_accuracy": 0.9108641934903206, | |
| "eval_f1": 0.8749605708498898, | |
| "eval_loss": 0.24038459360599518, | |
| "eval_matthews_correlation": 0.813382769196118, | |
| "eval_precision": 0.8947204237006231, | |
| "eval_recall": 0.8606017851044561, | |
| "eval_runtime": 739.8088, | |
| "eval_samples_per_second": 82.601, | |
| "eval_steps_per_second": 10.326, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 51.7, | |
| "learning_rate": 1.3932599724896834e-07, | |
| "loss": 0.1887, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 51.91, | |
| "learning_rate": 1.3691884456671253e-07, | |
| "loss": 0.1871, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 51.91, | |
| "eval_accuracy": 0.9113060269354759, | |
| "eval_f1": 0.8751060690982179, | |
| "eval_loss": 0.24039125442504883, | |
| "eval_matthews_correlation": 0.8141588021164547, | |
| "eval_precision": 0.8967775480498688, | |
| "eval_recall": 0.8595482173681065, | |
| "eval_runtime": 740.8776, | |
| "eval_samples_per_second": 82.482, | |
| "eval_steps_per_second": 10.311, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 52.13, | |
| "learning_rate": 1.3451169188445666e-07, | |
| "loss": 0.187, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 52.34, | |
| "learning_rate": 1.3210453920220082e-07, | |
| "loss": 0.1854, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 52.34, | |
| "eval_accuracy": 0.9106841872719239, | |
| "eval_f1": 0.8756565438291358, | |
| "eval_loss": 0.24039310216903687, | |
| "eval_matthews_correlation": 0.8132068008896376, | |
| "eval_precision": 0.8930378738634004, | |
| "eval_recall": 0.8626136626044701, | |
| "eval_runtime": 754.0793, | |
| "eval_samples_per_second": 81.038, | |
| "eval_steps_per_second": 10.13, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 52.55, | |
| "learning_rate": 1.2969738651994498e-07, | |
| "loss": 0.1855, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 52.77, | |
| "learning_rate": 1.272902338376891e-07, | |
| "loss": 0.1847, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 52.77, | |
| "eval_accuracy": 0.9111587491204242, | |
| "eval_f1": 0.8745820046811602, | |
| "eval_loss": 0.24042600393295288, | |
| "eval_matthews_correlation": 0.8138215404157054, | |
| "eval_precision": 0.8968482300783717, | |
| "eval_recall": 0.8588017339153629, | |
| "eval_runtime": 742.1234, | |
| "eval_samples_per_second": 82.343, | |
| "eval_steps_per_second": 10.293, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 52.98, | |
| "learning_rate": 1.2490715268225583e-07, | |
| "loss": 0.1876, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 53.19, | |
| "learning_rate": 1.225e-07, | |
| "loss": 0.186, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 53.19, | |
| "eval_accuracy": 0.9108478292886482, | |
| "eval_f1": 0.8756306261296279, | |
| "eval_loss": 0.24016867578029633, | |
| "eval_matthews_correlation": 0.8134681771839503, | |
| "eval_precision": 0.8938238096788703, | |
| "eval_recall": 0.8620717180480083, | |
| "eval_runtime": 738.0424, | |
| "eval_samples_per_second": 82.799, | |
| "eval_steps_per_second": 10.35, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 53.4, | |
| "learning_rate": 1.2009284731774415e-07, | |
| "loss": 0.1849, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 53.62, | |
| "learning_rate": 1.176856946354883e-07, | |
| "loss": 0.1854, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 53.62, | |
| "eval_accuracy": 0.9111914775237691, | |
| "eval_f1": 0.8749684700070617, | |
| "eval_loss": 0.24017079174518585, | |
| "eval_matthews_correlation": 0.8139472964260621, | |
| "eval_precision": 0.8963489801148983, | |
| "eval_recall": 0.8596475423732087, | |
| "eval_runtime": 739.6265, | |
| "eval_samples_per_second": 82.621, | |
| "eval_steps_per_second": 10.328, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 53.83, | |
| "learning_rate": 1.1527854195323247e-07, | |
| "loss": 0.184, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 54.04, | |
| "learning_rate": 1.1287138927097661e-07, | |
| "loss": 0.1858, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 54.04, | |
| "eval_accuracy": 0.9111423849187518, | |
| "eval_f1": 0.8750983580631472, | |
| "eval_loss": 0.24004679918289185, | |
| "eval_matthews_correlation": 0.8138717910322704, | |
| "eval_precision": 0.8959739410784087, | |
| "eval_recall": 0.8600123740955624, | |
| "eval_runtime": 747.7449, | |
| "eval_samples_per_second": 81.724, | |
| "eval_steps_per_second": 10.216, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 54.26, | |
| "learning_rate": 1.1046423658872076e-07, | |
| "loss": 0.1828, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 54.47, | |
| "learning_rate": 1.0805708390646493e-07, | |
| "loss": 0.1857, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 54.47, | |
| "eval_accuracy": 0.9108314650869758, | |
| "eval_f1": 0.8760467483571004, | |
| "eval_loss": 0.24011586606502533, | |
| "eval_matthews_correlation": 0.8135914183834242, | |
| "eval_precision": 0.8927898839248911, | |
| "eval_recall": 0.8634120046098842, | |
| "eval_runtime": 743.1897, | |
| "eval_samples_per_second": 82.225, | |
| "eval_steps_per_second": 10.279, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 54.68, | |
| "learning_rate": 1.0564993122420908e-07, | |
| "loss": 0.1846, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 54.89, | |
| "learning_rate": 1.0324277854195322e-07, | |
| "loss": 0.1834, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 54.89, | |
| "eval_accuracy": 0.9111423849187518, | |
| "eval_f1": 0.8748835890356302, | |
| "eval_loss": 0.24021214246749878, | |
| "eval_matthews_correlation": 0.8138675354624196, | |
| "eval_precision": 0.8960648924130842, | |
| "eval_recall": 0.8597271520558745, | |
| "eval_runtime": 742.673, | |
| "eval_samples_per_second": 82.283, | |
| "eval_steps_per_second": 10.286, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 55.11, | |
| "learning_rate": 1.008356258596974e-07, | |
| "loss": 0.1841, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 55.32, | |
| "learning_rate": 9.842847317744154e-08, | |
| "loss": 0.1856, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 55.32, | |
| "eval_accuracy": 0.9111751133220966, | |
| "eval_f1": 0.8759753884674994, | |
| "eval_loss": 0.2399187684059143, | |
| "eval_matthews_correlation": 0.8141158746054352, | |
| "eval_precision": 0.8946325772420679, | |
| "eval_recall": 0.8621027878175015, | |
| "eval_runtime": 741.8617, | |
| "eval_samples_per_second": 82.372, | |
| "eval_steps_per_second": 10.297, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 55.53, | |
| "learning_rate": 9.602132049518568e-08, | |
| "loss": 0.1832, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 55.74, | |
| "learning_rate": 9.361416781292984e-08, | |
| "loss": 0.1831, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 55.74, | |
| "eval_accuracy": 0.9111587491204242, | |
| "eval_f1": 0.876187515167234, | |
| "eval_loss": 0.23990817368030548, | |
| "eval_matthews_correlation": 0.8141847804240233, | |
| "eval_precision": 0.8938979116586415, | |
| "eval_recall": 0.8629504181290072, | |
| "eval_runtime": 754.7989, | |
| "eval_samples_per_second": 80.961, | |
| "eval_steps_per_second": 10.121, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 55.96, | |
| "learning_rate": 9.120701513067399e-08, | |
| "loss": 0.182, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 56.17, | |
| "learning_rate": 8.879986244841816e-08, | |
| "loss": 0.1866, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 56.17, | |
| "eval_accuracy": 0.9110278355070448, | |
| "eval_f1": 0.8761487837478463, | |
| "eval_loss": 0.23999524116516113, | |
| "eval_matthews_correlation": 0.8139186941063224, | |
| "eval_precision": 0.8936589268832552, | |
| "eval_recall": 0.8629898487738804, | |
| "eval_runtime": 741.1796, | |
| "eval_samples_per_second": 82.448, | |
| "eval_steps_per_second": 10.307, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 56.38, | |
| "learning_rate": 8.63927097661623e-08, | |
| "loss": 0.1824, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 56.6, | |
| "learning_rate": 8.398555708390646e-08, | |
| "loss": 0.1835, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 56.6, | |
| "eval_accuracy": 0.9111423849187518, | |
| "eval_f1": 0.8756141164672545, | |
| "eval_loss": 0.23985013365745544, | |
| "eval_matthews_correlation": 0.813993717251868, | |
| "eval_precision": 0.8950094790718368, | |
| "eval_recall": 0.8613866257413322, | |
| "eval_runtime": 741.0623, | |
| "eval_samples_per_second": 82.461, | |
| "eval_steps_per_second": 10.308, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 56.81, | |
| "learning_rate": 8.157840440165061e-08, | |
| "loss": 0.1809, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 57.02, | |
| "learning_rate": 7.917125171939477e-08, | |
| "loss": 0.1854, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 57.02, | |
| "eval_accuracy": 0.9113060269354759, | |
| "eval_f1": 0.875421277692427, | |
| "eval_loss": 0.23988887667655945, | |
| "eval_matthews_correlation": 0.8142691695381462, | |
| "eval_precision": 0.8958322440673258, | |
| "eval_recall": 0.8606631762505234, | |
| "eval_runtime": 743.0149, | |
| "eval_samples_per_second": 82.245, | |
| "eval_steps_per_second": 10.281, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 57.23, | |
| "learning_rate": 7.676409903713893e-08, | |
| "loss": 0.1864, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 57.45, | |
| "learning_rate": 7.435694635488309e-08, | |
| "loss": 0.1836, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 57.45, | |
| "eval_accuracy": 0.9113551195404932, | |
| "eval_f1": 0.8755706284668032, | |
| "eval_loss": 0.2398097962141037, | |
| "eval_matthews_correlation": 0.8143731570721386, | |
| "eval_precision": 0.8959067974921013, | |
| "eval_recall": 0.8608169300548751, | |
| "eval_runtime": 755.7111, | |
| "eval_samples_per_second": 80.863, | |
| "eval_steps_per_second": 10.108, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 57.66, | |
| "learning_rate": 7.194979367262723e-08, | |
| "loss": 0.1832, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 57.87, | |
| "learning_rate": 6.954264099037139e-08, | |
| "loss": 0.1803, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 57.87, | |
| "eval_accuracy": 0.9112078417254414, | |
| "eval_f1": 0.8766829819833193, | |
| "eval_loss": 0.2398734986782074, | |
| "eval_matthews_correlation": 0.8144037096432566, | |
| "eval_precision": 0.8932464422984686, | |
| "eval_recall": 0.8641154137104348, | |
| "eval_runtime": 743.4359, | |
| "eval_samples_per_second": 82.198, | |
| "eval_steps_per_second": 10.275, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 58.09, | |
| "learning_rate": 6.713548830811555e-08, | |
| "loss": 0.1835, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 58.3, | |
| "learning_rate": 6.47283356258597e-08, | |
| "loss": 0.1836, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 58.3, | |
| "eval_accuracy": 0.9112732985321311, | |
| "eval_f1": 0.8764331639044038, | |
| "eval_loss": 0.23976343870162964, | |
| "eval_matthews_correlation": 0.8144084809151402, | |
| "eval_precision": 0.8941883616324207, | |
| "eval_recall": 0.8630844566109225, | |
| "eval_runtime": 741.7654, | |
| "eval_samples_per_second": 82.383, | |
| "eval_steps_per_second": 10.298, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 58.51, | |
| "learning_rate": 6.232118294360385e-08, | |
| "loss": 0.1802, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 58.72, | |
| "learning_rate": 5.9914030261348e-08, | |
| "loss": 0.184, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 58.72, | |
| "eval_accuracy": 0.9111914775237691, | |
| "eval_f1": 0.8763957508353747, | |
| "eval_loss": 0.23981378972530365, | |
| "eval_matthews_correlation": 0.8142917281911558, | |
| "eval_precision": 0.8937138213627563, | |
| "eval_recall": 0.8633813581654887, | |
| "eval_runtime": 737.9501, | |
| "eval_samples_per_second": 82.809, | |
| "eval_steps_per_second": 10.352, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 58.94, | |
| "learning_rate": 5.753094910591472e-08, | |
| "loss": 0.181, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 59.15, | |
| "learning_rate": 5.512379642365887e-08, | |
| "loss": 0.1863, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 59.15, | |
| "eval_accuracy": 0.9112732985321311, | |
| "eval_f1": 0.8764471697031038, | |
| "eval_loss": 0.23969484865665436, | |
| "eval_matthews_correlation": 0.8144196501940248, | |
| "eval_precision": 0.894127496044295, | |
| "eval_recall": 0.8631622444399282, | |
| "eval_runtime": 753.6879, | |
| "eval_samples_per_second": 81.08, | |
| "eval_steps_per_second": 10.135, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 59.36, | |
| "learning_rate": 5.2716643741403025e-08, | |
| "loss": 0.1819, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 59.57, | |
| "learning_rate": 5.030949105914718e-08, | |
| "loss": 0.1797, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 59.57, | |
| "eval_accuracy": 0.9111423849187518, | |
| "eval_f1": 0.8757162075593086, | |
| "eval_loss": 0.2396748661994934, | |
| "eval_matthews_correlation": 0.8140161582224527, | |
| "eval_precision": 0.8947931225288825, | |
| "eval_recall": 0.8616459185046849, | |
| "eval_runtime": 740.934, | |
| "eval_samples_per_second": 82.476, | |
| "eval_steps_per_second": 10.31, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 59.79, | |
| "learning_rate": 4.7902338376891336e-08, | |
| "loss": 0.1835, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 4.549518569463548e-08, | |
| "loss": 0.1816, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.9111914775237691, | |
| "eval_f1": 0.875684259377722, | |
| "eval_loss": 0.23967032134532928, | |
| "eval_matthews_correlation": 0.8140985991678936, | |
| "eval_precision": 0.895037456074052, | |
| "eval_recall": 0.8614625917166782, | |
| "eval_runtime": 741.9954, | |
| "eval_samples_per_second": 82.358, | |
| "eval_steps_per_second": 10.295, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 60.21, | |
| "learning_rate": 4.308803301237964e-08, | |
| "loss": 0.1831, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 60.43, | |
| "learning_rate": 4.068088033012379e-08, | |
| "loss": 0.1783, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 60.43, | |
| "eval_accuracy": 0.9110932923137345, | |
| "eval_f1": 0.8756175323420491, | |
| "eval_loss": 0.23969128727912903, | |
| "eval_matthews_correlation": 0.813915664812348, | |
| "eval_precision": 0.8946951899568988, | |
| "eval_recall": 0.8615699525293389, | |
| "eval_runtime": 743.6353, | |
| "eval_samples_per_second": 82.176, | |
| "eval_steps_per_second": 10.273, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 60.64, | |
| "learning_rate": 3.827372764786795e-08, | |
| "loss": 0.1828, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 60.85, | |
| "learning_rate": 3.58665749656121e-08, | |
| "loss": 0.184, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 60.85, | |
| "eval_accuracy": 0.9113060269354759, | |
| "eval_f1": 0.8762367531132061, | |
| "eval_loss": 0.23966141045093536, | |
| "eval_matthews_correlation": 0.8144473273801464, | |
| "eval_precision": 0.8944561977906652, | |
| "eval_recall": 0.8626856598046749, | |
| "eval_runtime": 744.885, | |
| "eval_samples_per_second": 82.038, | |
| "eval_steps_per_second": 10.255, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 61.06, | |
| "learning_rate": 3.3459422283356255e-08, | |
| "loss": 0.1829, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 61.28, | |
| "learning_rate": 3.105226960110041e-08, | |
| "loss": 0.1875, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 61.28, | |
| "eval_accuracy": 0.9112242059271138, | |
| "eval_f1": 0.8758497580945278, | |
| "eval_loss": 0.23964743316173553, | |
| "eval_matthews_correlation": 0.8142105312256298, | |
| "eval_precision": 0.8948033936113107, | |
| "eval_recall": 0.8618935317531595, | |
| "eval_runtime": 748.7394, | |
| "eval_samples_per_second": 81.616, | |
| "eval_steps_per_second": 10.202, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 61.49, | |
| "learning_rate": 2.8645116918844566e-08, | |
| "loss": 0.1791, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 61.7, | |
| "learning_rate": 2.6237964236588718e-08, | |
| "loss": 0.1838, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 61.7, | |
| "eval_accuracy": 0.9111587491204242, | |
| "eval_f1": 0.8760228033495788, | |
| "eval_loss": 0.23964354395866394, | |
| "eval_matthews_correlation": 0.8141091546113298, | |
| "eval_precision": 0.8944177182411416, | |
| "eval_recall": 0.8623281154969605, | |
| "eval_runtime": 748.1941, | |
| "eval_samples_per_second": 81.675, | |
| "eval_steps_per_second": 10.21, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 61.91, | |
| "learning_rate": 2.3830811554332873e-08, | |
| "loss": 0.1785, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 62.13, | |
| "learning_rate": 2.142365887207703e-08, | |
| "loss": 0.1789, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 62.13, | |
| "eval_accuracy": 0.9111587491204242, | |
| "eval_f1": 0.8758841231334511, | |
| "eval_loss": 0.23965215682983398, | |
| "eval_matthews_correlation": 0.8141002784950974, | |
| "eval_precision": 0.8944914970092818, | |
| "eval_recall": 0.8621206812862784, | |
| "eval_runtime": 749.2476, | |
| "eval_samples_per_second": 81.56, | |
| "eval_steps_per_second": 10.196, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 62.34, | |
| "learning_rate": 1.9016506189821184e-08, | |
| "loss": 0.1796, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 62.55, | |
| "learning_rate": 1.6609353507565336e-08, | |
| "loss": 0.1867, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 62.55, | |
| "eval_accuracy": 0.9111751133220966, | |
| "eval_f1": 0.875965589962468, | |
| "eval_loss": 0.23963497579097748, | |
| "eval_matthews_correlation": 0.8141472397026508, | |
| "eval_precision": 0.8944009651598707, | |
| "eval_recall": 0.8622842927518485, | |
| "eval_runtime": 751.8905, | |
| "eval_samples_per_second": 81.274, | |
| "eval_steps_per_second": 10.16, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 62.77, | |
| "learning_rate": 1.420220082530949e-08, | |
| "loss": 0.184, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 62.98, | |
| "learning_rate": 1.1795048143053644e-08, | |
| "loss": 0.1786, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 62.98, | |
| "eval_accuracy": 0.9112896627338035, | |
| "eval_f1": 0.8760749417095012, | |
| "eval_loss": 0.2396363765001297, | |
| "eval_matthews_correlation": 0.8143793765063666, | |
| "eval_precision": 0.8946518427392349, | |
| "eval_recall": 0.8623146141284225, | |
| "eval_runtime": 751.3146, | |
| "eval_samples_per_second": 81.336, | |
| "eval_steps_per_second": 10.168, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 63.19, | |
| "learning_rate": 9.387895460797799e-09, | |
| "loss": 0.1824, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 63.4, | |
| "learning_rate": 7.004814305364511e-09, | |
| "loss": 0.1844, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 63.4, | |
| "eval_accuracy": 0.9112732985321311, | |
| "eval_f1": 0.8761606783620112, | |
| "eval_loss": 0.2396179437637329, | |
| "eval_matthews_correlation": 0.8143620838003341, | |
| "eval_precision": 0.8945106594084687, | |
| "eval_recall": 0.8625140125315464, | |
| "eval_runtime": 748.6773, | |
| "eval_samples_per_second": 81.623, | |
| "eval_steps_per_second": 10.203, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 63.62, | |
| "learning_rate": 4.597661623108666e-09, | |
| "loss": 0.18, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 63.83, | |
| "learning_rate": 2.19050894085282e-09, | |
| "loss": 0.1802, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 63.83, | |
| "eval_accuracy": 0.9112732985321311, | |
| "eval_f1": 0.8761211571982682, | |
| "eval_loss": 0.23962871730327606, | |
| "eval_matthews_correlation": 0.8143600284848606, | |
| "eval_precision": 0.8945126008533779, | |
| "eval_recall": 0.8624621539788757, | |
| "eval_runtime": 744.937, | |
| "eval_samples_per_second": 82.032, | |
| "eval_steps_per_second": 10.255, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "step": 30080, | |
| "total_flos": 3.5213331699056304e+21, | |
| "train_loss": 0.24540981396715691, | |
| "train_runtime": 455032.4128, | |
| "train_samples_per_second": 33.866, | |
| "train_steps_per_second": 0.066 | |
| } | |
| ], | |
| "max_steps": 30080, | |
| "num_train_epochs": 64, | |
| "total_flos": 3.5213331699056304e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |