| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 2913, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010298661174047374, | |
| "grad_norm": 11.615089416503906, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 0.6748, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02059732234809475, | |
| "grad_norm": 10.92617130279541, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.6647, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.030895983522142123, | |
| "grad_norm": 10.422063827514648, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.6572, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0411946446961895, | |
| "grad_norm": 11.15770149230957, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 0.6352, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05149330587023687, | |
| "grad_norm": 9.185620307922363, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.6052, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.061791967044284246, | |
| "grad_norm": 9.457632064819336, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.5875, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07209062821833162, | |
| "grad_norm": 10.167529106140137, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 0.5659, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.082389289392379, | |
| "grad_norm": 13.378604888916016, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 0.5659, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09268795056642637, | |
| "grad_norm": 17.715898513793945, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 0.5147, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.10298661174047374, | |
| "grad_norm": 16.888174057006836, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.4991, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10298661174047374, | |
| "eval_accuracy": 0.7925463439752832, | |
| "eval_accuracy_label_0": 0.9507723080342261, | |
| "eval_accuracy_label_1": 0.5747284687165366, | |
| "eval_f1": 0.7818901179048853, | |
| "eval_loss": 0.47476595640182495, | |
| "eval_precision": 0.8135697505549326, | |
| "eval_recall": 0.7925463439752832, | |
| "eval_runtime": 28.6334, | |
| "eval_samples_per_second": 542.583, | |
| "eval_steps_per_second": 16.973, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11328527291452112, | |
| "grad_norm": 12.777868270874023, | |
| "learning_rate": 4.4e-06, | |
| "loss": 0.4864, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12358393408856849, | |
| "grad_norm": 14.114547729492188, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.437, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13388259526261587, | |
| "grad_norm": 19.731557846069336, | |
| "learning_rate": 5.2e-06, | |
| "loss": 0.409, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.14418125643666324, | |
| "grad_norm": 14.552102088928223, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 0.4041, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.15447991761071062, | |
| "grad_norm": 13.959667205810547, | |
| "learning_rate": 6e-06, | |
| "loss": 0.3836, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.164778578784758, | |
| "grad_norm": 14.573174476623535, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.3685, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17507723995880536, | |
| "grad_norm": 16.22774887084961, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 0.3229, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.18537590113285274, | |
| "grad_norm": 19.044815063476562, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.3893, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1956745623069001, | |
| "grad_norm": 45.681358337402344, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 0.304, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2059732234809475, | |
| "grad_norm": 29.214599609375, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.3087, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2059732234809475, | |
| "eval_accuracy": 0.8798918640576725, | |
| "eval_accuracy_label_0": 0.9188798755417269, | |
| "eval_accuracy_label_1": 0.8262199785834481, | |
| "eval_f1": 0.8792919938020355, | |
| "eval_loss": 0.3051721453666687, | |
| "eval_precision": 0.8799368067929555, | |
| "eval_recall": 0.8798918640576725, | |
| "eval_runtime": 28.5459, | |
| "eval_samples_per_second": 544.247, | |
| "eval_steps_per_second": 17.025, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21627188465499486, | |
| "grad_norm": 15.713203430175781, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.3222, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.22657054582904224, | |
| "grad_norm": 15.416417121887207, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.3231, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2368692070030896, | |
| "grad_norm": 15.711112022399902, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.2795, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.24716786817713698, | |
| "grad_norm": 36.23487854003906, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.3044, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.25746652935118436, | |
| "grad_norm": 34.81510543823242, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2941, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.26776519052523173, | |
| "grad_norm": 27.128246307373047, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.2958, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2780638516992791, | |
| "grad_norm": 321.4391174316406, | |
| "learning_rate": 1.0800000000000002e-05, | |
| "loss": 0.3246, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.2883625128733265, | |
| "grad_norm": 19.725854873657227, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.2937, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.29866117404737386, | |
| "grad_norm": 18.257448196411133, | |
| "learning_rate": 1.16e-05, | |
| "loss": 0.2814, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.30895983522142123, | |
| "grad_norm": 13.747376441955566, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.2974, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.30895983522142123, | |
| "eval_accuracy": 0.9093074150360453, | |
| "eval_accuracy_label_0": 0.9181020113345927, | |
| "eval_accuracy_label_1": 0.8972005507113354, | |
| "eval_f1": 0.9093673855692345, | |
| "eval_loss": 0.23899167776107788, | |
| "eval_precision": 0.9094597674517649, | |
| "eval_recall": 0.9093074150360453, | |
| "eval_runtime": 28.6387, | |
| "eval_samples_per_second": 542.482, | |
| "eval_steps_per_second": 16.97, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3192584963954686, | |
| "grad_norm": 33.30331039428711, | |
| "learning_rate": 1.2400000000000002e-05, | |
| "loss": 0.2292, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.329557157569516, | |
| "grad_norm": 11.742475509643555, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 0.2624, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.33985581874356335, | |
| "grad_norm": 20.29306411743164, | |
| "learning_rate": 1.3200000000000002e-05, | |
| "loss": 0.2521, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.35015447991761073, | |
| "grad_norm": 30.528644561767578, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.2194, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3604531410916581, | |
| "grad_norm": 12.220970153808594, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.2429, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3707518022657055, | |
| "grad_norm": 24.19580841064453, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 0.2087, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.38105046343975285, | |
| "grad_norm": 23.321378707885742, | |
| "learning_rate": 1.48e-05, | |
| "loss": 0.286, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3913491246138002, | |
| "grad_norm": 32.3515625, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.2545, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4016477857878476, | |
| "grad_norm": 23.015567779541016, | |
| "learning_rate": 1.5600000000000003e-05, | |
| "loss": 0.2302, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.411946446961895, | |
| "grad_norm": 62.823158264160156, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.2644, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.411946446961895, | |
| "eval_accuracy": 0.8663105046343975, | |
| "eval_accuracy_label_0": 0.789865540615624, | |
| "eval_accuracy_label_1": 0.9715465810004589, | |
| "eval_f1": 0.8670270957842099, | |
| "eval_loss": 0.3067936897277832, | |
| "eval_precision": 0.8886912845830801, | |
| "eval_recall": 0.8663105046343975, | |
| "eval_runtime": 28.5898, | |
| "eval_samples_per_second": 543.41, | |
| "eval_steps_per_second": 16.999, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42224510813594235, | |
| "grad_norm": 17.351797103881836, | |
| "learning_rate": 1.64e-05, | |
| "loss": 0.2175, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.4325437693099897, | |
| "grad_norm": 17.912687301635742, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.2392, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4428424304840371, | |
| "grad_norm": 42.50285720825195, | |
| "learning_rate": 1.72e-05, | |
| "loss": 0.3647, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.45314109165808447, | |
| "grad_norm": 16.606185913085938, | |
| "learning_rate": 1.76e-05, | |
| "loss": 0.2354, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.46343975283213185, | |
| "grad_norm": 16.927104949951172, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.219, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4737384140061792, | |
| "grad_norm": 21.259096145629883, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.2094, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.4840370751802266, | |
| "grad_norm": 24.833669662475586, | |
| "learning_rate": 1.88e-05, | |
| "loss": 0.2152, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.49433573635427397, | |
| "grad_norm": 16.225502014160156, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.2355, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5046343975283213, | |
| "grad_norm": 22.97551918029785, | |
| "learning_rate": 1.9600000000000002e-05, | |
| "loss": 0.2245, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5149330587023687, | |
| "grad_norm": 6.800662517547607, | |
| "learning_rate": 2e-05, | |
| "loss": 0.223, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5149330587023687, | |
| "eval_accuracy": 0.9153578784757982, | |
| "eval_accuracy_label_0": 0.8905433937104122, | |
| "eval_accuracy_label_1": 0.9495181275814594, | |
| "eval_f1": 0.9157786272541746, | |
| "eval_loss": 0.2122022956609726, | |
| "eval_precision": 0.9194646287255005, | |
| "eval_recall": 0.9153578784757982, | |
| "eval_runtime": 28.5689, | |
| "eval_samples_per_second": 543.809, | |
| "eval_steps_per_second": 17.012, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.525231719876416, | |
| "grad_norm": 8.790451049804688, | |
| "learning_rate": 1.9917115623704932e-05, | |
| "loss": 0.2304, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5355303810504635, | |
| "grad_norm": 34.816078186035156, | |
| "learning_rate": 1.9834231247409866e-05, | |
| "loss": 0.1986, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5458290422245108, | |
| "grad_norm": 25.571226119995117, | |
| "learning_rate": 1.9751346871114796e-05, | |
| "loss": 0.2303, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5561277033985582, | |
| "grad_norm": 30.41813850402832, | |
| "learning_rate": 1.966846249481973e-05, | |
| "loss": 0.2466, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5664263645726055, | |
| "grad_norm": 16.801122665405273, | |
| "learning_rate": 1.958557811852466e-05, | |
| "loss": 0.2301, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.576725025746653, | |
| "grad_norm": 12.966567993164062, | |
| "learning_rate": 1.950269374222959e-05, | |
| "loss": 0.1849, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.5870236869207003, | |
| "grad_norm": 22.240522384643555, | |
| "learning_rate": 1.9419809365934525e-05, | |
| "loss": 0.2195, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5973223480947477, | |
| "grad_norm": 12.580880165100098, | |
| "learning_rate": 1.9336924989639455e-05, | |
| "loss": 0.2231, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.607621009268795, | |
| "grad_norm": 16.313684463500977, | |
| "learning_rate": 1.9254040613344385e-05, | |
| "loss": 0.1995, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6179196704428425, | |
| "grad_norm": 22.65012550354004, | |
| "learning_rate": 1.917115623704932e-05, | |
| "loss": 0.215, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6179196704428425, | |
| "eval_accuracy": 0.9228887744593203, | |
| "eval_accuracy_label_0": 0.9714412712523613, | |
| "eval_accuracy_label_1": 0.8560501759216766, | |
| "eval_f1": 0.9221719088414253, | |
| "eval_loss": 0.20105671882629395, | |
| "eval_precision": 0.9252341477386846, | |
| "eval_recall": 0.9228887744593203, | |
| "eval_runtime": 28.6849, | |
| "eval_samples_per_second": 541.608, | |
| "eval_steps_per_second": 16.943, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6282183316168898, | |
| "grad_norm": 13.182197570800781, | |
| "learning_rate": 1.908827186075425e-05, | |
| "loss": 0.2018, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6385169927909372, | |
| "grad_norm": 17.625165939331055, | |
| "learning_rate": 1.900538748445918e-05, | |
| "loss": 0.2005, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6488156539649845, | |
| "grad_norm": 31.007543563842773, | |
| "learning_rate": 1.892250310816411e-05, | |
| "loss": 0.2392, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.659114315139032, | |
| "grad_norm": 12.987165451049805, | |
| "learning_rate": 1.8839618731869044e-05, | |
| "loss": 0.2064, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6694129763130793, | |
| "grad_norm": 14.435954093933105, | |
| "learning_rate": 1.8756734355573975e-05, | |
| "loss": 0.1576, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6797116374871267, | |
| "grad_norm": 20.525474548339844, | |
| "learning_rate": 1.867384997927891e-05, | |
| "loss": 0.1876, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.690010298661174, | |
| "grad_norm": 16.95576286315918, | |
| "learning_rate": 1.859096560298384e-05, | |
| "loss": 0.2114, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.7003089598352215, | |
| "grad_norm": 36.12498092651367, | |
| "learning_rate": 1.850808122668877e-05, | |
| "loss": 0.2061, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.7106076210092688, | |
| "grad_norm": 22.316720962524414, | |
| "learning_rate": 1.8425196850393703e-05, | |
| "loss": 0.1984, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7209062821833162, | |
| "grad_norm": 7.638524532318115, | |
| "learning_rate": 1.8342312474098633e-05, | |
| "loss": 0.1419, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7209062821833162, | |
| "eval_accuracy": 0.9304840370751802, | |
| "eval_accuracy_label_0": 0.9689965551727969, | |
| "eval_accuracy_label_1": 0.877466727856815, | |
| "eval_f1": 0.9300182365736557, | |
| "eval_loss": 0.18355503678321838, | |
| "eval_precision": 0.931752271905432, | |
| "eval_recall": 0.9304840370751802, | |
| "eval_runtime": 28.6805, | |
| "eval_samples_per_second": 541.692, | |
| "eval_steps_per_second": 16.945, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7312049433573635, | |
| "grad_norm": 13.644458770751953, | |
| "learning_rate": 1.8259428097803567e-05, | |
| "loss": 0.1721, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.741503604531411, | |
| "grad_norm": 17.838420867919922, | |
| "learning_rate": 1.8176543721508498e-05, | |
| "loss": 0.1458, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.7518022657054583, | |
| "grad_norm": 27.161771774291992, | |
| "learning_rate": 1.8093659345213428e-05, | |
| "loss": 0.1231, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.7621009268795057, | |
| "grad_norm": 22.936689376831055, | |
| "learning_rate": 1.8010774968918362e-05, | |
| "loss": 0.2046, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.772399588053553, | |
| "grad_norm": 20.51582908630371, | |
| "learning_rate": 1.7927890592623292e-05, | |
| "loss": 0.1781, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7826982492276005, | |
| "grad_norm": 20.982328414916992, | |
| "learning_rate": 1.7845006216328226e-05, | |
| "loss": 0.1914, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.7929969104016478, | |
| "grad_norm": 16.1798038482666, | |
| "learning_rate": 1.7762121840033156e-05, | |
| "loss": 0.2076, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.8032955715756952, | |
| "grad_norm": 26.379657745361328, | |
| "learning_rate": 1.7679237463738087e-05, | |
| "loss": 0.1707, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.8135942327497425, | |
| "grad_norm": 7.800419807434082, | |
| "learning_rate": 1.7596353087443017e-05, | |
| "loss": 0.142, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.82389289392379, | |
| "grad_norm": 10.589848518371582, | |
| "learning_rate": 1.751346871114795e-05, | |
| "loss": 0.1511, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.82389289392379, | |
| "eval_accuracy": 0.930548403707518, | |
| "eval_accuracy_label_0": 0.9145460606734082, | |
| "eval_accuracy_label_1": 0.9525776350007649, | |
| "eval_f1": 0.9308174189927962, | |
| "eval_loss": 0.18278397619724274, | |
| "eval_precision": 0.9327234594811592, | |
| "eval_recall": 0.930548403707518, | |
| "eval_runtime": 28.6416, | |
| "eval_samples_per_second": 542.428, | |
| "eval_steps_per_second": 16.968, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8341915550978373, | |
| "grad_norm": 12.684349060058594, | |
| "learning_rate": 1.743058433485288e-05, | |
| "loss": 0.2034, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.8444902162718847, | |
| "grad_norm": 13.458330154418945, | |
| "learning_rate": 1.7347699958557812e-05, | |
| "loss": 0.1508, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.854788877445932, | |
| "grad_norm": 52.44272232055664, | |
| "learning_rate": 1.7264815582262742e-05, | |
| "loss": 0.2015, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.8650875386199794, | |
| "grad_norm": 12.620824813842773, | |
| "learning_rate": 1.7181931205967676e-05, | |
| "loss": 0.2104, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.8753861997940268, | |
| "grad_norm": 22.93926429748535, | |
| "learning_rate": 1.7099046829672606e-05, | |
| "loss": 0.1698, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8856848609680742, | |
| "grad_norm": 43.46416091918945, | |
| "learning_rate": 1.701616245337754e-05, | |
| "loss": 0.2122, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.8959835221421215, | |
| "grad_norm": 13.863987922668457, | |
| "learning_rate": 1.693327807708247e-05, | |
| "loss": 0.1794, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.9062821833161689, | |
| "grad_norm": 13.215469360351562, | |
| "learning_rate": 1.68503937007874e-05, | |
| "loss": 0.1822, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.9165808444902163, | |
| "grad_norm": 10.52542495727539, | |
| "learning_rate": 1.6767509324492335e-05, | |
| "loss": 0.1605, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.9268795056642637, | |
| "grad_norm": 15.559625625610352, | |
| "learning_rate": 1.6684624948197265e-05, | |
| "loss": 0.173, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9268795056642637, | |
| "eval_accuracy": 0.9430355303810505, | |
| "eval_accuracy_label_0": 0.9665518390932326, | |
| "eval_accuracy_label_1": 0.9106623833562797, | |
| "eval_f1": 0.942846283646341, | |
| "eval_loss": 0.15442048013210297, | |
| "eval_precision": 0.9433049100473271, | |
| "eval_recall": 0.9430355303810505, | |
| "eval_runtime": 28.6287, | |
| "eval_samples_per_second": 542.672, | |
| "eval_steps_per_second": 16.976, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.937178166838311, | |
| "grad_norm": 16.371034622192383, | |
| "learning_rate": 1.66017405719022e-05, | |
| "loss": 0.1453, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.9474768280123584, | |
| "grad_norm": 11.040371894836426, | |
| "learning_rate": 1.651885619560713e-05, | |
| "loss": 0.1388, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.9577754891864058, | |
| "grad_norm": 24.066585540771484, | |
| "learning_rate": 1.6435971819312063e-05, | |
| "loss": 0.1822, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.9680741503604532, | |
| "grad_norm": 12.861708641052246, | |
| "learning_rate": 1.6353087443016994e-05, | |
| "loss": 0.1382, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.9783728115345005, | |
| "grad_norm": 11.843149185180664, | |
| "learning_rate": 1.6270203066721924e-05, | |
| "loss": 0.1766, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.9886714727085479, | |
| "grad_norm": 37.507041931152344, | |
| "learning_rate": 1.6187318690426858e-05, | |
| "loss": 0.1511, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.9989701338825953, | |
| "grad_norm": 15.694278717041016, | |
| "learning_rate": 1.6104434314131788e-05, | |
| "loss": 0.1444, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.0092687950566426, | |
| "grad_norm": 13.906076431274414, | |
| "learning_rate": 1.602154993783672e-05, | |
| "loss": 0.1528, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.01956745623069, | |
| "grad_norm": 7.0642571449279785, | |
| "learning_rate": 1.5938665561541652e-05, | |
| "loss": 0.1619, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.0298661174047374, | |
| "grad_norm": 9.03572940826416, | |
| "learning_rate": 1.5855781185246583e-05, | |
| "loss": 0.0986, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0298661174047374, | |
| "eval_accuracy": 0.9429067971163748, | |
| "eval_accuracy_label_0": 0.9384376041782421, | |
| "eval_accuracy_label_1": 0.9490592014685636, | |
| "eval_f1": 0.9430264358268661, | |
| "eval_loss": 0.1512954831123352, | |
| "eval_precision": 0.9435332838620341, | |
| "eval_recall": 0.9429067971163748, | |
| "eval_runtime": 28.6625, | |
| "eval_samples_per_second": 542.033, | |
| "eval_steps_per_second": 16.956, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0401647785787849, | |
| "grad_norm": 14.95033073425293, | |
| "learning_rate": 1.5772896808951513e-05, | |
| "loss": 0.127, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.050463439752832, | |
| "grad_norm": 11.197813034057617, | |
| "learning_rate": 1.5690012432656444e-05, | |
| "loss": 0.1089, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.0607621009268795, | |
| "grad_norm": 29.581073760986328, | |
| "learning_rate": 1.5607128056361377e-05, | |
| "loss": 0.1313, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.071060762100927, | |
| "grad_norm": 9.089577674865723, | |
| "learning_rate": 1.5524243680066308e-05, | |
| "loss": 0.1005, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.0813594232749741, | |
| "grad_norm": 11.24911117553711, | |
| "learning_rate": 1.5441359303771238e-05, | |
| "loss": 0.1182, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.0916580844490216, | |
| "grad_norm": 12.69548511505127, | |
| "learning_rate": 1.5358474927476172e-05, | |
| "loss": 0.1086, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.101956745623069, | |
| "grad_norm": 6.551661491394043, | |
| "learning_rate": 1.5275590551181102e-05, | |
| "loss": 0.1795, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.1122554067971164, | |
| "grad_norm": 7.627679347991943, | |
| "learning_rate": 1.5192706174886036e-05, | |
| "loss": 0.1228, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.1225540679711639, | |
| "grad_norm": 9.827099800109863, | |
| "learning_rate": 1.5109821798590967e-05, | |
| "loss": 0.1744, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.132852729145211, | |
| "grad_norm": 16.760608673095703, | |
| "learning_rate": 1.5026937422295897e-05, | |
| "loss": 0.1403, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.132852729145211, | |
| "eval_accuracy": 0.9426493305870237, | |
| "eval_accuracy_label_0": 0.9277697521946883, | |
| "eval_accuracy_label_1": 0.9631329355973688, | |
| "eval_f1": 0.9428523899715144, | |
| "eval_loss": 0.15147006511688232, | |
| "eval_precision": 0.9443742901764207, | |
| "eval_recall": 0.9426493305870237, | |
| "eval_runtime": 28.672, | |
| "eval_samples_per_second": 541.852, | |
| "eval_steps_per_second": 16.95, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.1431513903192585, | |
| "grad_norm": 13.244966506958008, | |
| "learning_rate": 1.4944053046000831e-05, | |
| "loss": 0.1337, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.153450051493306, | |
| "grad_norm": 16.159469604492188, | |
| "learning_rate": 1.4861168669705761e-05, | |
| "loss": 0.1257, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.1637487126673531, | |
| "grad_norm": 8.31472396850586, | |
| "learning_rate": 1.4778284293410693e-05, | |
| "loss": 0.1138, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.1740473738414006, | |
| "grad_norm": 20.465499877929688, | |
| "learning_rate": 1.4695399917115625e-05, | |
| "loss": 0.1145, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.184346035015448, | |
| "grad_norm": 14.761605262756348, | |
| "learning_rate": 1.4612515540820556e-05, | |
| "loss": 0.1319, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.1946446961894954, | |
| "grad_norm": 14.083001136779785, | |
| "learning_rate": 1.4529631164525488e-05, | |
| "loss": 0.1596, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.2049433573635429, | |
| "grad_norm": 15.79395866394043, | |
| "learning_rate": 1.4446746788230418e-05, | |
| "loss": 0.1195, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.21524201853759, | |
| "grad_norm": 19.134933471679688, | |
| "learning_rate": 1.4363862411935352e-05, | |
| "loss": 0.1326, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.2255406797116375, | |
| "grad_norm": 8.911842346191406, | |
| "learning_rate": 1.4280978035640283e-05, | |
| "loss": 0.1658, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.235839340885685, | |
| "grad_norm": 13.809399604797363, | |
| "learning_rate": 1.4198093659345216e-05, | |
| "loss": 0.1133, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.235839340885685, | |
| "eval_accuracy": 0.9474768280123584, | |
| "eval_accuracy_label_0": 0.9531059006556284, | |
| "eval_accuracy_label_1": 0.9397277038396818, | |
| "eval_f1": 0.9474920315228875, | |
| "eval_loss": 0.1394452601671219, | |
| "eval_precision": 0.9475135239059512, | |
| "eval_recall": 0.9474768280123584, | |
| "eval_runtime": 28.6446, | |
| "eval_samples_per_second": 542.371, | |
| "eval_steps_per_second": 16.967, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.2461380020597321, | |
| "grad_norm": 6.037145137786865, | |
| "learning_rate": 1.4115209283050147e-05, | |
| "loss": 0.1181, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.2564366632337796, | |
| "grad_norm": 12.423005104064941, | |
| "learning_rate": 1.4032324906755077e-05, | |
| "loss": 0.1262, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.266735324407827, | |
| "grad_norm": 4.064807415008545, | |
| "learning_rate": 1.394944053046001e-05, | |
| "loss": 0.127, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.2770339855818744, | |
| "grad_norm": 12.577651023864746, | |
| "learning_rate": 1.3866556154164941e-05, | |
| "loss": 0.0983, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.2873326467559219, | |
| "grad_norm": 29.784053802490234, | |
| "learning_rate": 1.3783671777869873e-05, | |
| "loss": 0.1294, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.297631307929969, | |
| "grad_norm": 10.433960914611816, | |
| "learning_rate": 1.3700787401574804e-05, | |
| "loss": 0.1268, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.3079299691040165, | |
| "grad_norm": 23.706260681152344, | |
| "learning_rate": 1.3617903025279734e-05, | |
| "loss": 0.1508, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.318228630278064, | |
| "grad_norm": 8.82191276550293, | |
| "learning_rate": 1.3535018648984668e-05, | |
| "loss": 0.1419, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.3285272914521111, | |
| "grad_norm": 15.989568710327148, | |
| "learning_rate": 1.3452134272689598e-05, | |
| "loss": 0.1148, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.3388259526261586, | |
| "grad_norm": 18.397598266601562, | |
| "learning_rate": 1.3369249896394532e-05, | |
| "loss": 0.1117, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.3388259526261586, | |
| "eval_accuracy": 0.9457389289392379, | |
| "eval_accuracy_label_0": 0.9371041226802979, | |
| "eval_accuracy_label_1": 0.9576258222426189, | |
| "eval_f1": 0.9458829241092044, | |
| "eval_loss": 0.15250205993652344, | |
| "eval_precision": 0.9466897814987169, | |
| "eval_recall": 0.9457389289392379, | |
| "eval_runtime": 28.6931, | |
| "eval_samples_per_second": 541.455, | |
| "eval_steps_per_second": 16.938, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.349124613800206, | |
| "grad_norm": 8.94162368774414, | |
| "learning_rate": 1.3286365520099463e-05, | |
| "loss": 0.1298, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.3594232749742534, | |
| "grad_norm": 8.949539184570312, | |
| "learning_rate": 1.3203481143804393e-05, | |
| "loss": 0.1136, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.3697219361483008, | |
| "grad_norm": 9.650628089904785, | |
| "learning_rate": 1.3120596767509325e-05, | |
| "loss": 0.1107, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.380020597322348, | |
| "grad_norm": 20.57952308654785, | |
| "learning_rate": 1.3037712391214257e-05, | |
| "loss": 0.1305, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.3903192584963955, | |
| "grad_norm": 6.576913833618164, | |
| "learning_rate": 1.295482801491919e-05, | |
| "loss": 0.1008, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.400617919670443, | |
| "grad_norm": 8.591489791870117, | |
| "learning_rate": 1.287194363862412e-05, | |
| "loss": 0.1142, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.4109165808444901, | |
| "grad_norm": 21.97450065612793, | |
| "learning_rate": 1.2789059262329052e-05, | |
| "loss": 0.1098, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.4212152420185376, | |
| "grad_norm": 13.194725036621094, | |
| "learning_rate": 1.2706174886033984e-05, | |
| "loss": 0.115, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.431513903192585, | |
| "grad_norm": 17.651912689208984, | |
| "learning_rate": 1.2623290509738914e-05, | |
| "loss": 0.1392, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.4418125643666324, | |
| "grad_norm": 10.665314674377441, | |
| "learning_rate": 1.2540406133443848e-05, | |
| "loss": 0.1277, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.4418125643666324, | |
| "eval_accuracy": 0.9490216271884655, | |
| "eval_accuracy_label_0": 0.950105567285254, | |
| "eval_accuracy_label_1": 0.9475294477589108, | |
| "eval_f1": 0.9490756146391877, | |
| "eval_loss": 0.13106246292591095, | |
| "eval_precision": 0.9492196286028385, | |
| "eval_recall": 0.9490216271884655, | |
| "eval_runtime": 28.6067, | |
| "eval_samples_per_second": 543.09, | |
| "eval_steps_per_second": 16.989, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.4521112255406798, | |
| "grad_norm": 26.829360961914062, | |
| "learning_rate": 1.2457521757148779e-05, | |
| "loss": 0.1164, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.462409886714727, | |
| "grad_norm": 12.50798225402832, | |
| "learning_rate": 1.2374637380853709e-05, | |
| "loss": 0.1368, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.4727085478887745, | |
| "grad_norm": 10.048441886901855, | |
| "learning_rate": 1.2291753004558643e-05, | |
| "loss": 0.0953, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.483007209062822, | |
| "grad_norm": 9.52072811126709, | |
| "learning_rate": 1.2208868628263573e-05, | |
| "loss": 0.1373, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.4933058702368691, | |
| "grad_norm": 10.079704284667969, | |
| "learning_rate": 1.2125984251968505e-05, | |
| "loss": 0.0797, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.5036045314109165, | |
| "grad_norm": 16.81131935119629, | |
| "learning_rate": 1.2043099875673436e-05, | |
| "loss": 0.1407, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.513903192584964, | |
| "grad_norm": 9.030206680297852, | |
| "learning_rate": 1.196021549937837e-05, | |
| "loss": 0.1378, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.5242018537590112, | |
| "grad_norm": 25.010522842407227, | |
| "learning_rate": 1.18773311230833e-05, | |
| "loss": 0.1205, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.5345005149330588, | |
| "grad_norm": 23.806989669799805, | |
| "learning_rate": 1.179444674678823e-05, | |
| "loss": 0.1473, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.544799176107106, | |
| "grad_norm": 8.146597862243652, | |
| "learning_rate": 1.1711562370493164e-05, | |
| "loss": 0.0886, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.544799176107106, | |
| "eval_accuracy": 0.9503089598352215, | |
| "eval_accuracy_label_0": 0.962773641515724, | |
| "eval_accuracy_label_1": 0.933149762888175, | |
| "eval_f1": 0.9502536107094707, | |
| "eval_loss": 0.1374950259923935, | |
| "eval_precision": 0.9502824202007619, | |
| "eval_recall": 0.9503089598352215, | |
| "eval_runtime": 28.5942, | |
| "eval_samples_per_second": 543.328, | |
| "eval_steps_per_second": 16.996, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.5550978372811535, | |
| "grad_norm": 11.416892051696777, | |
| "learning_rate": 1.1628677994198094e-05, | |
| "loss": 0.1135, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.565396498455201, | |
| "grad_norm": 19.61497688293457, | |
| "learning_rate": 1.1545793617903027e-05, | |
| "loss": 0.1169, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.575695159629248, | |
| "grad_norm": 11.90202808380127, | |
| "learning_rate": 1.1462909241607959e-05, | |
| "loss": 0.1339, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.5859938208032955, | |
| "grad_norm": 6.188625812530518, | |
| "learning_rate": 1.1380024865312889e-05, | |
| "loss": 0.07, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.596292481977343, | |
| "grad_norm": 14.50114631652832, | |
| "learning_rate": 1.1297140489017821e-05, | |
| "loss": 0.1047, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.6065911431513902, | |
| "grad_norm": 18.257389068603516, | |
| "learning_rate": 1.1214256112722752e-05, | |
| "loss": 0.1098, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.6168898043254378, | |
| "grad_norm": 12.986026763916016, | |
| "learning_rate": 1.1131371736427685e-05, | |
| "loss": 0.1248, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.627188465499485, | |
| "grad_norm": 13.668187141418457, | |
| "learning_rate": 1.1048487360132616e-05, | |
| "loss": 0.0758, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.6374871266735325, | |
| "grad_norm": 24.57569694519043, | |
| "learning_rate": 1.0965602983837546e-05, | |
| "loss": 0.1076, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.64778578784758, | |
| "grad_norm": 8.269564628601074, | |
| "learning_rate": 1.088271860754248e-05, | |
| "loss": 0.1273, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.64778578784758, | |
| "eval_accuracy": 0.95326982492276, | |
| "eval_accuracy_label_0": 0.9535503944882765, | |
| "eval_accuracy_label_1": 0.9528835857426954, | |
| "eval_f1": 0.9533210896239291, | |
| "eval_loss": 0.12969127297401428, | |
| "eval_precision": 0.9534697447214137, | |
| "eval_recall": 0.95326982492276, | |
| "eval_runtime": 28.6188, | |
| "eval_samples_per_second": 542.861, | |
| "eval_steps_per_second": 16.982, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.658084449021627, | |
| "grad_norm": 13.074461936950684, | |
| "learning_rate": 1.079983423124741e-05, | |
| "loss": 0.134, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.6683831101956745, | |
| "grad_norm": 17.92150115966797, | |
| "learning_rate": 1.0716949854952342e-05, | |
| "loss": 0.138, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.678681771369722, | |
| "grad_norm": 6.528224468231201, | |
| "learning_rate": 1.0634065478657275e-05, | |
| "loss": 0.1281, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.6889804325437692, | |
| "grad_norm": 15.4542236328125, | |
| "learning_rate": 1.0551181102362205e-05, | |
| "loss": 0.1272, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.6992790937178168, | |
| "grad_norm": 7.588622570037842, | |
| "learning_rate": 1.0468296726067137e-05, | |
| "loss": 0.0765, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.709577754891864, | |
| "grad_norm": 14.380094528198242, | |
| "learning_rate": 1.0385412349772067e-05, | |
| "loss": 0.1326, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.7198764160659115, | |
| "grad_norm": 17.22504997253418, | |
| "learning_rate": 1.0302527973477001e-05, | |
| "loss": 0.1725, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.730175077239959, | |
| "grad_norm": 21.660451889038086, | |
| "learning_rate": 1.0219643597181932e-05, | |
| "loss": 0.1201, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.740473738414006, | |
| "grad_norm": 12.858647346496582, | |
| "learning_rate": 1.0136759220886862e-05, | |
| "loss": 0.1303, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.7507723995880535, | |
| "grad_norm": 7.619086742401123, | |
| "learning_rate": 1.0053874844591796e-05, | |
| "loss": 0.1102, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.7507723995880535, | |
| "eval_accuracy": 0.9578398558187435, | |
| "eval_accuracy_label_0": 0.9636626291810201, | |
| "eval_accuracy_label_1": 0.9498240783233899, | |
| "eval_f1": 0.9578394145096656, | |
| "eval_loss": 0.11356295645236969, | |
| "eval_precision": 0.9578389813236798, | |
| "eval_recall": 0.9578398558187435, | |
| "eval_runtime": 28.6352, | |
| "eval_samples_per_second": 542.548, | |
| "eval_steps_per_second": 16.972, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.761071060762101, | |
| "grad_norm": 11.526819229125977, | |
| "learning_rate": 9.970990468296728e-06, | |
| "loss": 0.0705, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.7713697219361482, | |
| "grad_norm": 11.57654857635498, | |
| "learning_rate": 9.888106092001658e-06, | |
| "loss": 0.1298, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.7816683831101958, | |
| "grad_norm": 11.508631706237793, | |
| "learning_rate": 9.80522171570659e-06, | |
| "loss": 0.0818, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.791967044284243, | |
| "grad_norm": 15.72537612915039, | |
| "learning_rate": 9.722337339411521e-06, | |
| "loss": 0.1334, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.8022657054582905, | |
| "grad_norm": 19.711965560913086, | |
| "learning_rate": 9.639452963116453e-06, | |
| "loss": 0.0747, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.8125643666323379, | |
| "grad_norm": 14.697903633117676, | |
| "learning_rate": 9.556568586821385e-06, | |
| "loss": 0.0819, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.822863027806385, | |
| "grad_norm": 9.13084888458252, | |
| "learning_rate": 9.473684210526315e-06, | |
| "loss": 0.076, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.8331616889804325, | |
| "grad_norm": 6.7411909103393555, | |
| "learning_rate": 9.390799834231248e-06, | |
| "loss": 0.117, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.84346035015448, | |
| "grad_norm": 9.10245132446289, | |
| "learning_rate": 9.30791545793618e-06, | |
| "loss": 0.099, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.8537590113285272, | |
| "grad_norm": 12.770278930664062, | |
| "learning_rate": 9.225031081641112e-06, | |
| "loss": 0.0793, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.8537590113285272, | |
| "eval_accuracy": 0.9562306900102987, | |
| "eval_accuracy_label_0": 0.9717746416268475, | |
| "eval_accuracy_label_1": 0.934832491968793, | |
| "eval_f1": 0.9561461033354728, | |
| "eval_loss": 0.12691599130630493, | |
| "eval_precision": 0.9563031504820825, | |
| "eval_recall": 0.9562306900102987, | |
| "eval_runtime": 28.648, | |
| "eval_samples_per_second": 542.306, | |
| "eval_steps_per_second": 16.965, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.8640576725025748, | |
| "grad_norm": 10.909438133239746, | |
| "learning_rate": 9.142146705346044e-06, | |
| "loss": 0.094, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.874356333676622, | |
| "grad_norm": 24.187469482421875, | |
| "learning_rate": 9.059262329050974e-06, | |
| "loss": 0.1057, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.8846549948506695, | |
| "grad_norm": 12.352056503295898, | |
| "learning_rate": 8.976377952755906e-06, | |
| "loss": 0.0996, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.8949536560247169, | |
| "grad_norm": 18.231224060058594, | |
| "learning_rate": 8.893493576460838e-06, | |
| "loss": 0.1419, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.905252317198764, | |
| "grad_norm": 13.484111785888672, | |
| "learning_rate": 8.810609200165769e-06, | |
| "loss": 0.0816, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.9155509783728115, | |
| "grad_norm": 7.332424640655518, | |
| "learning_rate": 8.727724823870701e-06, | |
| "loss": 0.1034, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.925849639546859, | |
| "grad_norm": 10.0885648727417, | |
| "learning_rate": 8.644840447575633e-06, | |
| "loss": 0.0846, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.9361483007209062, | |
| "grad_norm": 7.032443046569824, | |
| "learning_rate": 8.561956071280563e-06, | |
| "loss": 0.1134, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.9464469618949538, | |
| "grad_norm": 15.94394302368164, | |
| "learning_rate": 8.479071694985496e-06, | |
| "loss": 0.1097, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.956745623069001, | |
| "grad_norm": 9.909218788146973, | |
| "learning_rate": 8.396187318690428e-06, | |
| "loss": 0.0995, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.956745623069001, | |
| "eval_accuracy": 0.9590628218331617, | |
| "eval_accuracy_label_0": 0.9702189132125791, | |
| "eval_accuracy_label_1": 0.943705063484779, | |
| "eval_f1": 0.9590181542400875, | |
| "eval_loss": 0.11290641874074936, | |
| "eval_precision": 0.9590551602931409, | |
| "eval_recall": 0.9590628218331617, | |
| "eval_runtime": 28.6377, | |
| "eval_samples_per_second": 542.502, | |
| "eval_steps_per_second": 16.971, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.9670442842430484, | |
| "grad_norm": 15.3870210647583, | |
| "learning_rate": 8.31330294239536e-06, | |
| "loss": 0.1248, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.9773429454170959, | |
| "grad_norm": 8.369405746459961, | |
| "learning_rate": 8.230418566100292e-06, | |
| "loss": 0.0975, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.987641606591143, | |
| "grad_norm": 20.09193992614746, | |
| "learning_rate": 8.147534189805222e-06, | |
| "loss": 0.1065, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.9979402677651905, | |
| "grad_norm": 12.807772636413574, | |
| "learning_rate": 8.064649813510154e-06, | |
| "loss": 0.1091, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 2.008238928939238, | |
| "grad_norm": 11.321664810180664, | |
| "learning_rate": 7.981765437215085e-06, | |
| "loss": 0.0707, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.018537590113285, | |
| "grad_norm": 6.500060081481934, | |
| "learning_rate": 7.898881060920017e-06, | |
| "loss": 0.0548, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 2.028836251287333, | |
| "grad_norm": 6.183711528778076, | |
| "learning_rate": 7.815996684624949e-06, | |
| "loss": 0.0596, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 2.03913491246138, | |
| "grad_norm": 10.278242111206055, | |
| "learning_rate": 7.733112308329881e-06, | |
| "loss": 0.0768, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 2.049433573635427, | |
| "grad_norm": 36.13182067871094, | |
| "learning_rate": 7.650227932034812e-06, | |
| "loss": 0.1081, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 2.059732234809475, | |
| "grad_norm": 18.672588348388672, | |
| "learning_rate": 7.567343555739744e-06, | |
| "loss": 0.0846, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.059732234809475, | |
| "eval_accuracy": 0.95326982492276, | |
| "eval_accuracy_label_0": 0.9422158017557506, | |
| "eval_accuracy_label_1": 0.9684870735811534, | |
| "eval_f1": 0.9534029516094716, | |
| "eval_loss": 0.1361849009990692, | |
| "eval_precision": 0.9543244872259893, | |
| "eval_recall": 0.95326982492276, | |
| "eval_runtime": 28.6073, | |
| "eval_samples_per_second": 543.078, | |
| "eval_steps_per_second": 16.989, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.070030895983522, | |
| "grad_norm": 8.882670402526855, | |
| "learning_rate": 7.484459179444675e-06, | |
| "loss": 0.0747, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 2.0803295571575697, | |
| "grad_norm": 9.687372207641602, | |
| "learning_rate": 7.401574803149607e-06, | |
| "loss": 0.0447, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 2.090628218331617, | |
| "grad_norm": 10.967034339904785, | |
| "learning_rate": 7.318690426854539e-06, | |
| "loss": 0.0504, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 2.100926879505664, | |
| "grad_norm": 16.16581153869629, | |
| "learning_rate": 7.2358060505594695e-06, | |
| "loss": 0.078, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 2.111225540679712, | |
| "grad_norm": 10.206809997558594, | |
| "learning_rate": 7.1529216742644016e-06, | |
| "loss": 0.0731, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.121524201853759, | |
| "grad_norm": 3.9291794300079346, | |
| "learning_rate": 7.070037297969334e-06, | |
| "loss": 0.0573, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 2.131822863027806, | |
| "grad_norm": 3.0698776245117188, | |
| "learning_rate": 6.987152921674265e-06, | |
| "loss": 0.0734, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 2.142121524201854, | |
| "grad_norm": 23.81843376159668, | |
| "learning_rate": 6.904268545379197e-06, | |
| "loss": 0.0821, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 2.152420185375901, | |
| "grad_norm": 7.545326232910156, | |
| "learning_rate": 6.821384169084129e-06, | |
| "loss": 0.0453, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 2.1627188465499483, | |
| "grad_norm": 17.654476165771484, | |
| "learning_rate": 6.7384997927890595e-06, | |
| "loss": 0.096, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.1627188465499483, | |
| "eval_accuracy": 0.9562950566426365, | |
| "eval_accuracy_label_0": 0.9466607400822313, | |
| "eval_accuracy_label_1": 0.9695579011779104, | |
| "eval_f1": 0.9564082597816722, | |
| "eval_loss": 0.1383037120103836, | |
| "eval_precision": 0.9571555565808465, | |
| "eval_recall": 0.9562950566426365, | |
| "eval_runtime": 28.6473, | |
| "eval_samples_per_second": 542.321, | |
| "eval_steps_per_second": 16.965, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.173017507723996, | |
| "grad_norm": 9.992446899414062, | |
| "learning_rate": 6.655615416493992e-06, | |
| "loss": 0.027, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 2.183316168898043, | |
| "grad_norm": 6.128831386566162, | |
| "learning_rate": 6.572731040198923e-06, | |
| "loss": 0.0743, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 2.193614830072091, | |
| "grad_norm": 18.08496856689453, | |
| "learning_rate": 6.489846663903855e-06, | |
| "loss": 0.0483, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 2.203913491246138, | |
| "grad_norm": 20.862857818603516, | |
| "learning_rate": 6.406962287608787e-06, | |
| "loss": 0.0872, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 2.214212152420185, | |
| "grad_norm": 6.609086513519287, | |
| "learning_rate": 6.3240779113137175e-06, | |
| "loss": 0.1039, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.224510813594233, | |
| "grad_norm": 9.900079727172852, | |
| "learning_rate": 6.2411935350186496e-06, | |
| "loss": 0.08, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 2.23480947476828, | |
| "grad_norm": 6.2700700759887695, | |
| "learning_rate": 6.158309158723581e-06, | |
| "loss": 0.051, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 2.2451081359423277, | |
| "grad_norm": 12.434645652770996, | |
| "learning_rate": 6.075424782428513e-06, | |
| "loss": 0.058, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 2.255406797116375, | |
| "grad_norm": 7.681482791900635, | |
| "learning_rate": 5.992540406133445e-06, | |
| "loss": 0.0752, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 2.265705458290422, | |
| "grad_norm": 24.001230239868164, | |
| "learning_rate": 5.909656029838376e-06, | |
| "loss": 0.0797, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.265705458290422, | |
| "eval_accuracy": 0.9619593202883625, | |
| "eval_accuracy_label_0": 0.9711079008778754, | |
| "eval_accuracy_label_1": 0.9493651522104941, | |
| "eval_f1": 0.9619302021150672, | |
| "eval_loss": 0.11368735879659653, | |
| "eval_precision": 0.9619423362488065, | |
| "eval_recall": 0.9619593202883625, | |
| "eval_runtime": 28.6312, | |
| "eval_samples_per_second": 542.625, | |
| "eval_steps_per_second": 16.974, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.27600411946447, | |
| "grad_norm": 14.428683280944824, | |
| "learning_rate": 5.8267716535433075e-06, | |
| "loss": 0.0506, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 2.286302780638517, | |
| "grad_norm": 8.54249382019043, | |
| "learning_rate": 5.743887277248239e-06, | |
| "loss": 0.06, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 2.296601441812564, | |
| "grad_norm": 19.03498077392578, | |
| "learning_rate": 5.661002900953171e-06, | |
| "loss": 0.0668, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 2.306900102986612, | |
| "grad_norm": 10.844647407531738, | |
| "learning_rate": 5.578118524658103e-06, | |
| "loss": 0.0449, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 2.317198764160659, | |
| "grad_norm": 14.049932479858398, | |
| "learning_rate": 5.495234148363034e-06, | |
| "loss": 0.1016, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.3274974253347063, | |
| "grad_norm": 6.799467086791992, | |
| "learning_rate": 5.4123497720679655e-06, | |
| "loss": 0.0576, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 2.337796086508754, | |
| "grad_norm": 3.510343551635742, | |
| "learning_rate": 5.329465395772897e-06, | |
| "loss": 0.0354, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 2.348094747682801, | |
| "grad_norm": 17.81386947631836, | |
| "learning_rate": 5.246581019477829e-06, | |
| "loss": 0.1046, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 2.358393408856849, | |
| "grad_norm": 1.548386573791504, | |
| "learning_rate": 5.163696643182761e-06, | |
| "loss": 0.0688, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 2.368692070030896, | |
| "grad_norm": 19.792476654052734, | |
| "learning_rate": 5.080812266887692e-06, | |
| "loss": 0.0602, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.368692070030896, | |
| "eval_accuracy": 0.96086508753862, | |
| "eval_accuracy_label_0": 0.9664407156350706, | |
| "eval_accuracy_label_1": 0.953189536484626, | |
| "eval_f1": 0.9608634468691928, | |
| "eval_loss": 0.12112918496131897, | |
| "eval_precision": 0.9608619366174393, | |
| "eval_recall": 0.96086508753862, | |
| "eval_runtime": 28.6488, | |
| "eval_samples_per_second": 542.291, | |
| "eval_steps_per_second": 16.964, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.378990731204943, | |
| "grad_norm": 14.4805269241333, | |
| "learning_rate": 4.997927890592623e-06, | |
| "loss": 0.0683, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 2.389289392378991, | |
| "grad_norm": 23.142452239990234, | |
| "learning_rate": 4.9150435142975555e-06, | |
| "loss": 0.0669, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 2.399588053553038, | |
| "grad_norm": 17.42975616455078, | |
| "learning_rate": 4.832159138002487e-06, | |
| "loss": 0.0774, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 2.4098867147270857, | |
| "grad_norm": 20.081676483154297, | |
| "learning_rate": 4.749274761707419e-06, | |
| "loss": 0.0714, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 2.420185375901133, | |
| "grad_norm": 15.057238578796387, | |
| "learning_rate": 4.66639038541235e-06, | |
| "loss": 0.0702, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.43048403707518, | |
| "grad_norm": 15.039963722229004, | |
| "learning_rate": 4.583506009117281e-06, | |
| "loss": 0.0548, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 2.4407826982492278, | |
| "grad_norm": 10.758746147155762, | |
| "learning_rate": 4.5006216328222135e-06, | |
| "loss": 0.0444, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 2.451081359423275, | |
| "grad_norm": 18.213958740234375, | |
| "learning_rate": 4.417737256527145e-06, | |
| "loss": 0.0559, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 2.461380020597322, | |
| "grad_norm": 17.926952362060547, | |
| "learning_rate": 4.334852880232077e-06, | |
| "loss": 0.0675, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 2.47167868177137, | |
| "grad_norm": 7.6708807945251465, | |
| "learning_rate": 4.251968503937008e-06, | |
| "loss": 0.0951, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.47167868177137, | |
| "eval_accuracy": 0.9614443872296602, | |
| "eval_accuracy_label_0": 0.962773641515724, | |
| "eval_accuracy_label_1": 0.9596145020651675, | |
| "eval_f1": 0.9614721624380318, | |
| "eval_loss": 0.1193719357252121, | |
| "eval_precision": 0.9615409347691732, | |
| "eval_recall": 0.9614443872296602, | |
| "eval_runtime": 28.6329, | |
| "eval_samples_per_second": 542.592, | |
| "eval_steps_per_second": 16.973, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.481977342945417, | |
| "grad_norm": 15.066208839416504, | |
| "learning_rate": 4.169084127641939e-06, | |
| "loss": 0.0683, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 2.4922760041194643, | |
| "grad_norm": 23.18450355529785, | |
| "learning_rate": 4.086199751346871e-06, | |
| "loss": 0.0626, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 2.502574665293512, | |
| "grad_norm": 0.8303961753845215, | |
| "learning_rate": 4.003315375051803e-06, | |
| "loss": 0.0476, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 2.512873326467559, | |
| "grad_norm": 20.618289947509766, | |
| "learning_rate": 3.920430998756735e-06, | |
| "loss": 0.0582, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 2.5231719876416063, | |
| "grad_norm": 6.84626579284668, | |
| "learning_rate": 3.837546622461666e-06, | |
| "loss": 0.057, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.533470648815654, | |
| "grad_norm": 4.529855251312256, | |
| "learning_rate": 3.7546622461665977e-06, | |
| "loss": 0.0523, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 2.543769309989701, | |
| "grad_norm": 14.540194511413574, | |
| "learning_rate": 3.6717778698715294e-06, | |
| "loss": 0.0906, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 2.554067971163749, | |
| "grad_norm": 25.749385833740234, | |
| "learning_rate": 3.5888934935764615e-06, | |
| "loss": 0.0516, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 2.564366632337796, | |
| "grad_norm": 12.172739028930664, | |
| "learning_rate": 3.5060091172813927e-06, | |
| "loss": 0.0597, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 2.5746652935118437, | |
| "grad_norm": 1.8584766387939453, | |
| "learning_rate": 3.4231247409863244e-06, | |
| "loss": 0.0343, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.5746652935118437, | |
| "eval_accuracy": 0.9628604531410917, | |
| "eval_accuracy_label_0": 0.9624402711412379, | |
| "eval_accuracy_label_1": 0.9634388863392994, | |
| "eval_f1": 0.962897301831431, | |
| "eval_loss": 0.12369329482316971, | |
| "eval_precision": 0.9630139003703244, | |
| "eval_recall": 0.9628604531410917, | |
| "eval_runtime": 28.6342, | |
| "eval_samples_per_second": 542.569, | |
| "eval_steps_per_second": 16.973, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.584963954685891, | |
| "grad_norm": 15.55650520324707, | |
| "learning_rate": 3.340240364691256e-06, | |
| "loss": 0.0645, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 2.595262615859938, | |
| "grad_norm": 5.339417934417725, | |
| "learning_rate": 3.2573559883961873e-06, | |
| "loss": 0.0497, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 2.6055612770339858, | |
| "grad_norm": 18.813339233398438, | |
| "learning_rate": 3.1744716121011194e-06, | |
| "loss": 0.0856, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 2.615859938208033, | |
| "grad_norm": 18.912582397460938, | |
| "learning_rate": 3.0915872358060507e-06, | |
| "loss": 0.0684, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 2.62615859938208, | |
| "grad_norm": 29.817142486572266, | |
| "learning_rate": 3.0087028595109823e-06, | |
| "loss": 0.0742, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.636457260556128, | |
| "grad_norm": 20.53231430053711, | |
| "learning_rate": 2.925818483215914e-06, | |
| "loss": 0.0675, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 2.646755921730175, | |
| "grad_norm": 1.9606025218963623, | |
| "learning_rate": 2.8429341069208453e-06, | |
| "loss": 0.0319, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 2.6570545829042223, | |
| "grad_norm": 15.020525932312012, | |
| "learning_rate": 2.7600497306257774e-06, | |
| "loss": 0.0681, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 2.66735324407827, | |
| "grad_norm": 13.114953994750977, | |
| "learning_rate": 2.677165354330709e-06, | |
| "loss": 0.0348, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 2.677651905252317, | |
| "grad_norm": 25.307437896728516, | |
| "learning_rate": 2.5942809780356403e-06, | |
| "loss": 0.0512, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.677651905252317, | |
| "eval_accuracy": 0.9625386199794027, | |
| "eval_accuracy_label_0": 0.9737748638737638, | |
| "eval_accuracy_label_1": 0.947070521646015, | |
| "eval_f1": 0.962493472042095, | |
| "eval_loss": 0.12632428109645844, | |
| "eval_precision": 0.9625475718092084, | |
| "eval_recall": 0.9625386199794027, | |
| "eval_runtime": 28.7287, | |
| "eval_samples_per_second": 540.783, | |
| "eval_steps_per_second": 16.917, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.6879505664263643, | |
| "grad_norm": 19.501306533813477, | |
| "learning_rate": 2.5113966017405724e-06, | |
| "loss": 0.0515, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 2.698249227600412, | |
| "grad_norm": 17.550600051879883, | |
| "learning_rate": 2.4285122254455037e-06, | |
| "loss": 0.0491, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 2.708547888774459, | |
| "grad_norm": 36.03532409667969, | |
| "learning_rate": 2.3456278491504353e-06, | |
| "loss": 0.085, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 2.718846549948507, | |
| "grad_norm": 11.236651420593262, | |
| "learning_rate": 2.262743472855367e-06, | |
| "loss": 0.0656, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 2.729145211122554, | |
| "grad_norm": 12.065185546875, | |
| "learning_rate": 2.1798590965602987e-06, | |
| "loss": 0.0698, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.7394438722966017, | |
| "grad_norm": 0.8977580070495605, | |
| "learning_rate": 2.0969747202652304e-06, | |
| "loss": 0.0646, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 2.749742533470649, | |
| "grad_norm": 14.258803367614746, | |
| "learning_rate": 2.0140903439701616e-06, | |
| "loss": 0.065, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 2.760041194644696, | |
| "grad_norm": 1.7737594842910767, | |
| "learning_rate": 1.9312059676750933e-06, | |
| "loss": 0.0412, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 2.7703398558187438, | |
| "grad_norm": 5.75368595123291, | |
| "learning_rate": 1.8483215913800252e-06, | |
| "loss": 0.0681, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 2.780638516992791, | |
| "grad_norm": 44.601314544677734, | |
| "learning_rate": 1.7654372150849566e-06, | |
| "loss": 0.0532, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.780638516992791, | |
| "eval_accuracy": 0.9633110195674562, | |
| "eval_accuracy_label_0": 0.9705522835870652, | |
| "eval_accuracy_label_1": 0.9533425118555913, | |
| "eval_f1": 0.9632954018759314, | |
| "eval_loss": 0.12292636930942535, | |
| "eval_precision": 0.963292880058248, | |
| "eval_recall": 0.9633110195674562, | |
| "eval_runtime": 28.687, | |
| "eval_samples_per_second": 541.569, | |
| "eval_steps_per_second": 16.941, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.790937178166838, | |
| "grad_norm": 12.678955078125, | |
| "learning_rate": 1.682552838789888e-06, | |
| "loss": 0.0683, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 2.801235839340886, | |
| "grad_norm": 1.118263602256775, | |
| "learning_rate": 1.59966846249482e-06, | |
| "loss": 0.0303, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 2.811534500514933, | |
| "grad_norm": 14.192521095275879, | |
| "learning_rate": 1.5167840861997514e-06, | |
| "loss": 0.0681, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 2.8218331616889802, | |
| "grad_norm": 18.46016502380371, | |
| "learning_rate": 1.4338997099046831e-06, | |
| "loss": 0.0686, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 2.832131822863028, | |
| "grad_norm": 15.062724113464355, | |
| "learning_rate": 1.3510153336096146e-06, | |
| "loss": 0.0521, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.842430484037075, | |
| "grad_norm": 7.8030900955200195, | |
| "learning_rate": 1.2681309573145465e-06, | |
| "loss": 0.0923, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 2.8527291452111223, | |
| "grad_norm": 5.273398399353027, | |
| "learning_rate": 1.185246581019478e-06, | |
| "loss": 0.0471, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 2.86302780638517, | |
| "grad_norm": 10.055742263793945, | |
| "learning_rate": 1.1023622047244096e-06, | |
| "loss": 0.0517, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 2.873326467559217, | |
| "grad_norm": 22.551183700561523, | |
| "learning_rate": 1.0194778284293413e-06, | |
| "loss": 0.0497, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 2.883625128733265, | |
| "grad_norm": 10.616918563842773, | |
| "learning_rate": 9.365934521342727e-07, | |
| "loss": 0.0673, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.883625128733265, | |
| "eval_accuracy": 0.9644052523171988, | |
| "eval_accuracy_label_0": 0.9678853205911768, | |
| "eval_accuracy_label_1": 0.9596145020651675, | |
| "eval_f1": 0.9644144636556568, | |
| "eval_loss": 0.12062814831733704, | |
| "eval_precision": 0.9644287833599177, | |
| "eval_recall": 0.9644052523171988, | |
| "eval_runtime": 28.6805, | |
| "eval_samples_per_second": 541.691, | |
| "eval_steps_per_second": 16.945, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.893923789907312, | |
| "grad_norm": 12.785795211791992, | |
| "learning_rate": 8.537090758392044e-07, | |
| "loss": 0.0662, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 2.9042224510813597, | |
| "grad_norm": 8.8677396774292, | |
| "learning_rate": 7.70824699544136e-07, | |
| "loss": 0.0789, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 2.914521112255407, | |
| "grad_norm": 19.09882354736328, | |
| "learning_rate": 6.879403232490677e-07, | |
| "loss": 0.0358, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 2.924819773429454, | |
| "grad_norm": 13.237493515014648, | |
| "learning_rate": 6.050559469539992e-07, | |
| "loss": 0.069, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 2.9351184346035017, | |
| "grad_norm": 0.5621568560600281, | |
| "learning_rate": 5.221715706589308e-07, | |
| "loss": 0.0503, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.945417095777549, | |
| "grad_norm": 11.271636009216309, | |
| "learning_rate": 4.392871943638625e-07, | |
| "loss": 0.0379, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 2.955715756951596, | |
| "grad_norm": 14.567364692687988, | |
| "learning_rate": 3.564028180687941e-07, | |
| "loss": 0.0489, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 2.966014418125644, | |
| "grad_norm": 11.992318153381348, | |
| "learning_rate": 2.7351844177372567e-07, | |
| "loss": 0.0569, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 2.976313079299691, | |
| "grad_norm": 9.122631072998047, | |
| "learning_rate": 1.9063406547865727e-07, | |
| "loss": 0.0704, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 2.9866117404737382, | |
| "grad_norm": 28.3140869140625, | |
| "learning_rate": 1.077496891835889e-07, | |
| "loss": 0.0209, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.9866117404737382, | |
| "eval_accuracy": 0.9644696189495365, | |
| "eval_accuracy_label_0": 0.9708856539615512, | |
| "eval_accuracy_label_1": 0.9556371424200704, | |
| "eval_f1": 0.9644590852602763, | |
| "eval_loss": 0.11849933117628098, | |
| "eval_precision": 0.9644549735327069, | |
| "eval_recall": 0.9644696189495365, | |
| "eval_runtime": 28.6233, | |
| "eval_samples_per_second": 542.775, | |
| "eval_steps_per_second": 16.979, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.996910401647786, | |
| "grad_norm": 26.769432067871094, | |
| "learning_rate": 2.4865312888520517e-08, | |
| "loss": 0.0621, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 2913, | |
| "total_flos": 2227577912202240.0, | |
| "train_loss": 0.15083247099878697, | |
| "train_runtime": 1636.2013, | |
| "train_samples_per_second": 113.936, | |
| "train_steps_per_second": 1.78 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9645339855818743, | |
| "eval_accuracy_label_0": 0.9707745305033892, | |
| "eval_accuracy_label_1": 0.9559430931620009, | |
| "eval_f1": 0.9645246094465593, | |
| "eval_loss": 0.11850666999816895, | |
| "eval_precision": 0.9645203525935409, | |
| "eval_recall": 0.9645339855818743, | |
| "eval_runtime": 28.6606, | |
| "eval_samples_per_second": 542.068, | |
| "eval_steps_per_second": 16.957, | |
| "step": 2913 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2913, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2227577912202240.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |