| { | |
| "best_metric": 0.8601036269430051, | |
| "best_model_checkpoint": "./vit-base-skin/checkpoint-3500", | |
| "epoch": 6.0, | |
| "global_step": 3756, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001994675186368477, | |
| "loss": 1.348, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019893503727369543, | |
| "loss": 1.1281, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019840255591054313, | |
| "loss": 0.8345, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019787007454739086, | |
| "loss": 1.0349, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019733759318423856, | |
| "loss": 0.8851, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019680511182108628, | |
| "loss": 0.8551, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019627263045793398, | |
| "loss": 0.9658, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019574014909478168, | |
| "loss": 0.8991, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001952076677316294, | |
| "loss": 0.984, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001946751863684771, | |
| "loss": 0.8348, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.6632124352331606, | |
| "eval_f1": 0.5925945827584863, | |
| "eval_loss": 0.8249555826187134, | |
| "eval_precision": 0.565098555699833, | |
| "eval_recall": 0.6632124352331606, | |
| "eval_runtime": 1.2932, | |
| "eval_samples_per_second": 149.246, | |
| "eval_steps_per_second": 19.332, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019414270500532483, | |
| "loss": 0.9221, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019361022364217253, | |
| "loss": 0.8559, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019307774227902025, | |
| "loss": 0.7901, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00019254526091586795, | |
| "loss": 0.6743, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00019201277955271565, | |
| "loss": 0.8357, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019148029818956338, | |
| "loss": 0.8055, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00019094781682641108, | |
| "loss": 0.6695, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0001904153354632588, | |
| "loss": 0.8113, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001898828541001065, | |
| "loss": 0.7557, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00018935037273695422, | |
| "loss": 0.8258, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.7409326424870466, | |
| "eval_f1": 0.6882730451946492, | |
| "eval_loss": 0.6617661118507385, | |
| "eval_precision": 0.7368367158860514, | |
| "eval_recall": 0.7409326424870466, | |
| "eval_runtime": 1.3161, | |
| "eval_samples_per_second": 146.646, | |
| "eval_steps_per_second": 18.996, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00018881789137380192, | |
| "loss": 0.8002, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00018828541001064962, | |
| "loss": 0.7426, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00018775292864749735, | |
| "loss": 0.705, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00018722044728434505, | |
| "loss": 0.6996, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018668796592119277, | |
| "loss": 0.5599, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00018615548455804047, | |
| "loss": 0.6936, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001856230031948882, | |
| "loss": 0.8606, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001850905218317359, | |
| "loss": 0.744, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001845580404685836, | |
| "loss": 0.8032, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00018402555910543132, | |
| "loss": 0.6543, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.7823834196891192, | |
| "eval_f1": 0.7768475373290318, | |
| "eval_loss": 0.6106820106506348, | |
| "eval_precision": 0.792659270318004, | |
| "eval_recall": 0.7823834196891192, | |
| "eval_runtime": 1.3519, | |
| "eval_samples_per_second": 142.762, | |
| "eval_steps_per_second": 18.493, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00018349307774227902, | |
| "loss": 0.5641, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00018296059637912674, | |
| "loss": 0.6198, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018242811501597444, | |
| "loss": 0.7088, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00018189563365282217, | |
| "loss": 0.7418, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00018136315228966987, | |
| "loss": 0.7361, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00018083067092651756, | |
| "loss": 0.6418, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0001802981895633653, | |
| "loss": 0.6598, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00017976570820021302, | |
| "loss": 0.5981, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00017923322683706071, | |
| "loss": 0.5242, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001787007454739084, | |
| "loss": 0.8157, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.772020725388601, | |
| "eval_f1": 0.7647052227916401, | |
| "eval_loss": 0.5686162710189819, | |
| "eval_precision": 0.7709856834237326, | |
| "eval_recall": 0.772020725388601, | |
| "eval_runtime": 1.4024, | |
| "eval_samples_per_second": 137.624, | |
| "eval_steps_per_second": 17.827, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00017816826411075614, | |
| "loss": 0.735, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00017763578274760384, | |
| "loss": 0.6545, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00017710330138445154, | |
| "loss": 0.7224, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00017657082002129926, | |
| "loss": 0.6715, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.000176038338658147, | |
| "loss": 0.6065, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00017550585729499469, | |
| "loss": 0.582, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001749733759318424, | |
| "loss": 0.646, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0001744408945686901, | |
| "loss": 0.5761, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001739084132055378, | |
| "loss": 0.7707, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001733759318423855, | |
| "loss": 0.6783, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.8134715025906736, | |
| "eval_f1": 0.8048654809820208, | |
| "eval_loss": 0.589982271194458, | |
| "eval_precision": 0.825687248128958, | |
| "eval_recall": 0.8134715025906736, | |
| "eval_runtime": 1.4527, | |
| "eval_samples_per_second": 132.854, | |
| "eval_steps_per_second": 17.209, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00017284345047923323, | |
| "loss": 0.619, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00017231096911608096, | |
| "loss": 0.595, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00017177848775292866, | |
| "loss": 0.5368, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00017124600638977638, | |
| "loss": 0.6713, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017071352502662408, | |
| "loss": 0.6346, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00017018104366347178, | |
| "loss": 0.6452, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00016964856230031948, | |
| "loss": 0.5533, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001691160809371672, | |
| "loss": 0.4746, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00016858359957401493, | |
| "loss": 0.5641, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016805111821086263, | |
| "loss": 0.5844, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.8186528497409327, | |
| "eval_f1": 0.801376323104553, | |
| "eval_loss": 0.49070069193840027, | |
| "eval_precision": 0.8252026039590807, | |
| "eval_recall": 0.8186528497409327, | |
| "eval_runtime": 1.4456, | |
| "eval_samples_per_second": 133.509, | |
| "eval_steps_per_second": 17.294, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016751863684771035, | |
| "loss": 0.7764, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00016698615548455805, | |
| "loss": 0.5125, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00016645367412140575, | |
| "loss": 0.5497, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00016592119275825345, | |
| "loss": 0.3826, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00016538871139510118, | |
| "loss": 0.457, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0001648562300319489, | |
| "loss": 0.5431, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001643237486687966, | |
| "loss": 0.5583, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00016379126730564433, | |
| "loss": 0.5116, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00016325878594249202, | |
| "loss": 0.4291, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00016272630457933972, | |
| "loss": 0.4288, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_accuracy": 0.8134715025906736, | |
| "eval_f1": 0.7998473772947372, | |
| "eval_loss": 0.4793131649494171, | |
| "eval_precision": 0.8134138785838797, | |
| "eval_recall": 0.8134715025906736, | |
| "eval_runtime": 1.3883, | |
| "eval_samples_per_second": 139.024, | |
| "eval_steps_per_second": 18.008, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00016219382321618745, | |
| "loss": 0.5297, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00016166134185303515, | |
| "loss": 0.5115, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00016112886048988287, | |
| "loss": 0.4218, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00016059637912673057, | |
| "loss": 0.521, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0001600638977635783, | |
| "loss": 0.4867, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.000159531416400426, | |
| "loss": 0.4876, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001589989350372737, | |
| "loss": 0.4126, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00015846645367412142, | |
| "loss": 0.5093, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00015793397231096912, | |
| "loss": 0.5028, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00015740149094781684, | |
| "loss": 0.5126, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_accuracy": 0.8341968911917098, | |
| "eval_f1": 0.8339117779824388, | |
| "eval_loss": 0.48048293590545654, | |
| "eval_precision": 0.8427480658155704, | |
| "eval_recall": 0.8341968911917098, | |
| "eval_runtime": 1.4984, | |
| "eval_samples_per_second": 128.802, | |
| "eval_steps_per_second": 16.684, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00015686900958466454, | |
| "loss": 0.4947, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00015633652822151227, | |
| "loss": 0.6075, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00015580404685835997, | |
| "loss": 0.4077, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00015527156549520767, | |
| "loss": 0.5626, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001547390841320554, | |
| "loss": 0.4439, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0001542066027689031, | |
| "loss": 0.7081, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00015367412140575082, | |
| "loss": 0.6184, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00015314164004259851, | |
| "loss": 0.3523, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00015260915867944624, | |
| "loss": 0.4468, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00015207667731629394, | |
| "loss": 0.4601, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.8497409326424871, | |
| "eval_f1": 0.84074195785157, | |
| "eval_loss": 0.45874446630477905, | |
| "eval_precision": 0.851347725086476, | |
| "eval_recall": 0.8497409326424871, | |
| "eval_runtime": 1.5041, | |
| "eval_samples_per_second": 128.314, | |
| "eval_steps_per_second": 16.621, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00015154419595314164, | |
| "loss": 0.4133, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015101171458998936, | |
| "loss": 0.5022, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015047923322683706, | |
| "loss": 0.4672, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001499467518636848, | |
| "loss": 0.5649, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00014941427050053249, | |
| "loss": 0.5258, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001488817891373802, | |
| "loss": 0.4983, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0001483493077742279, | |
| "loss": 0.4717, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0001478168264110756, | |
| "loss": 0.4742, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014728434504792333, | |
| "loss": 0.4787, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014675186368477103, | |
| "loss": 0.4189, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.8134715025906736, | |
| "eval_f1": 0.8109036052621809, | |
| "eval_loss": 0.5409760475158691, | |
| "eval_precision": 0.8294618365480906, | |
| "eval_recall": 0.8134715025906736, | |
| "eval_runtime": 1.4957, | |
| "eval_samples_per_second": 129.033, | |
| "eval_steps_per_second": 16.714, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00014621938232161876, | |
| "loss": 0.4103, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00014568690095846646, | |
| "loss": 0.4355, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00014515441959531418, | |
| "loss": 0.4698, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00014462193823216188, | |
| "loss": 0.5684, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00014408945686900958, | |
| "loss": 0.4727, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0001435569755058573, | |
| "loss": 0.4739, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.000143024494142705, | |
| "loss": 0.4324, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00014249201277955273, | |
| "loss": 0.476, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00014195953141640043, | |
| "loss": 0.408, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00014142705005324815, | |
| "loss": 0.3752, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_accuracy": 0.8601036269430051, | |
| "eval_f1": 0.8551463588464094, | |
| "eval_loss": 0.4159872531890869, | |
| "eval_precision": 0.8692539301263543, | |
| "eval_recall": 0.8601036269430051, | |
| "eval_runtime": 1.4438, | |
| "eval_samples_per_second": 133.672, | |
| "eval_steps_per_second": 17.315, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00014089456869009585, | |
| "loss": 0.5864, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00014036208732694355, | |
| "loss": 0.3692, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00013982960596379128, | |
| "loss": 0.2931, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.000139297124600639, | |
| "loss": 0.396, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0001387646432374867, | |
| "loss": 0.5685, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0001382321618743344, | |
| "loss": 0.4215, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00013769968051118212, | |
| "loss": 0.3664, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00013716719914802982, | |
| "loss": 0.5569, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00013663471778487752, | |
| "loss": 0.2922, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00013610223642172525, | |
| "loss": 0.4127, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_accuracy": 0.8341968911917098, | |
| "eval_f1": 0.8420551345845699, | |
| "eval_loss": 0.44651323556900024, | |
| "eval_precision": 0.8681320466205227, | |
| "eval_recall": 0.8341968911917098, | |
| "eval_runtime": 1.4884, | |
| "eval_samples_per_second": 129.669, | |
| "eval_steps_per_second": 16.797, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00013556975505857297, | |
| "loss": 0.4459, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00013503727369542067, | |
| "loss": 0.2338, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00013450479233226837, | |
| "loss": 0.3703, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0001339723109691161, | |
| "loss": 0.4983, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001334398296059638, | |
| "loss": 0.4492, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0001329073482428115, | |
| "loss": 0.4158, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00013237486687965922, | |
| "loss": 0.2796, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00013184238551650694, | |
| "loss": 0.3179, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00013130990415335464, | |
| "loss": 0.2897, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.00013077742279020234, | |
| "loss": 0.2633, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_accuracy": 0.8238341968911918, | |
| "eval_f1": 0.8204437692572268, | |
| "eval_loss": 0.4700864851474762, | |
| "eval_precision": 0.840758032986012, | |
| "eval_recall": 0.8238341968911918, | |
| "eval_runtime": 1.4661, | |
| "eval_samples_per_second": 131.639, | |
| "eval_steps_per_second": 17.052, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.00013024494142705007, | |
| "loss": 0.2347, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00012971246006389777, | |
| "loss": 0.3424, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00012917997870074546, | |
| "loss": 0.2534, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0001286474973375932, | |
| "loss": 0.2936, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.00012811501597444092, | |
| "loss": 0.2391, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00012758253461128861, | |
| "loss": 0.2853, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0001270500532481363, | |
| "loss": 0.2031, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.00012651757188498404, | |
| "loss": 0.3192, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00012598509052183174, | |
| "loss": 0.3473, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.00012545260915867944, | |
| "loss": 0.2527, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.8497409326424871, | |
| "eval_f1": 0.8460794104429671, | |
| "eval_loss": 0.5073708891868591, | |
| "eval_precision": 0.8791117636053318, | |
| "eval_recall": 0.8497409326424871, | |
| "eval_runtime": 1.4672, | |
| "eval_samples_per_second": 131.542, | |
| "eval_steps_per_second": 17.039, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00012492012779552716, | |
| "loss": 0.2465, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0001243876464323749, | |
| "loss": 0.3593, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.00012385516506922259, | |
| "loss": 0.1774, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00012332268370607028, | |
| "loss": 0.2558, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.000122790202342918, | |
| "loss": 0.3348, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0001222577209797657, | |
| "loss": 0.1961, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.00012172523961661342, | |
| "loss": 0.1826, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00012119275825346112, | |
| "loss": 0.4577, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00012066027689030886, | |
| "loss": 0.2633, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00012012779552715656, | |
| "loss": 0.2699, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.7823834196891192, | |
| "eval_f1": 0.767840964913232, | |
| "eval_loss": 0.6482508778572083, | |
| "eval_precision": 0.781575699462611, | |
| "eval_recall": 0.7823834196891192, | |
| "eval_runtime": 1.4868, | |
| "eval_samples_per_second": 129.807, | |
| "eval_steps_per_second": 16.814, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00011959531416400427, | |
| "loss": 0.1626, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.00011906283280085198, | |
| "loss": 0.2613, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.00011853035143769968, | |
| "loss": 0.2578, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.00011799787007454739, | |
| "loss": 0.2794, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.00011746538871139509, | |
| "loss": 0.2433, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00011693290734824283, | |
| "loss": 0.2209, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.00011640042598509053, | |
| "loss": 0.253, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.00011586794462193824, | |
| "loss": 0.3002, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.00011533546325878595, | |
| "loss": 0.2315, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.00011480298189563365, | |
| "loss": 0.2916, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_accuracy": 0.8497409326424871, | |
| "eval_f1": 0.8474487520162014, | |
| "eval_loss": 0.503077507019043, | |
| "eval_precision": 0.8555723618575612, | |
| "eval_recall": 0.8497409326424871, | |
| "eval_runtime": 1.4183, | |
| "eval_samples_per_second": 136.076, | |
| "eval_steps_per_second": 17.626, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00011427050053248136, | |
| "loss": 0.1462, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.00011373801916932908, | |
| "loss": 0.3573, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0001132055378061768, | |
| "loss": 0.3686, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0001126730564430245, | |
| "loss": 0.2446, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.00011214057507987221, | |
| "loss": 0.3967, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00011160809371671992, | |
| "loss": 0.2246, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00011107561235356762, | |
| "loss": 0.3989, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.00011054313099041533, | |
| "loss": 0.2718, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.00011001064962726305, | |
| "loss": 0.4763, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.00010947816826411077, | |
| "loss": 0.1639, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.8704663212435233, | |
| "eval_f1": 0.871441633648278, | |
| "eval_loss": 0.4313341975212097, | |
| "eval_precision": 0.8772752872268529, | |
| "eval_recall": 0.8704663212435233, | |
| "eval_runtime": 1.486, | |
| "eval_samples_per_second": 129.877, | |
| "eval_steps_per_second": 16.823, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.00010894568690095847, | |
| "loss": 0.2929, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.00010841320553780618, | |
| "loss": 0.2339, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.0001078807241746539, | |
| "loss": 0.2102, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0001073482428115016, | |
| "loss": 0.1776, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0001068157614483493, | |
| "loss": 0.2266, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.00010628328008519702, | |
| "loss": 0.2611, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.00010575079872204474, | |
| "loss": 0.3267, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00010521831735889244, | |
| "loss": 0.2278, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00010468583599574015, | |
| "loss": 0.2413, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.00010415335463258787, | |
| "loss": 0.2591, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_accuracy": 0.8756476683937824, | |
| "eval_f1": 0.8720033220279861, | |
| "eval_loss": 0.4406687021255493, | |
| "eval_precision": 0.8872037651161766, | |
| "eval_recall": 0.8756476683937824, | |
| "eval_runtime": 1.4427, | |
| "eval_samples_per_second": 133.773, | |
| "eval_steps_per_second": 17.328, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.00010362087326943557, | |
| "loss": 0.3264, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.00010308839190628328, | |
| "loss": 0.2925, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.000102555910543131, | |
| "loss": 0.2325, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00010202342917997871, | |
| "loss": 0.1951, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.00010149094781682643, | |
| "loss": 0.1905, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.00010095846645367413, | |
| "loss": 0.3546, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.00010042598509052184, | |
| "loss": 0.3751, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.989350372736954e-05, | |
| "loss": 0.209, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.936102236421726e-05, | |
| "loss": 0.0976, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 9.882854100106496e-05, | |
| "loss": 0.1511, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_accuracy": 0.8238341968911918, | |
| "eval_f1": 0.818544620182296, | |
| "eval_loss": 0.5291632413864136, | |
| "eval_precision": 0.8386427341451549, | |
| "eval_recall": 0.8238341968911918, | |
| "eval_runtime": 1.4526, | |
| "eval_samples_per_second": 132.864, | |
| "eval_steps_per_second": 17.21, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 9.829605963791267e-05, | |
| "loss": 0.1853, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 9.77635782747604e-05, | |
| "loss": 0.1759, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 9.72310969116081e-05, | |
| "loss": 0.0915, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 9.669861554845581e-05, | |
| "loss": 0.0668, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 9.616613418530351e-05, | |
| "loss": 0.0958, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 9.563365282215123e-05, | |
| "loss": 0.17, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 9.510117145899895e-05, | |
| "loss": 0.1376, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 9.456869009584664e-05, | |
| "loss": 0.1937, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 9.403620873269437e-05, | |
| "loss": 0.0914, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 9.350372736954207e-05, | |
| "loss": 0.0782, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_accuracy": 0.8341968911917098, | |
| "eval_f1": 0.8283394509085317, | |
| "eval_loss": 0.599178671836853, | |
| "eval_precision": 0.8267532023603915, | |
| "eval_recall": 0.8341968911917098, | |
| "eval_runtime": 1.4237, | |
| "eval_samples_per_second": 135.563, | |
| "eval_steps_per_second": 17.56, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 9.297124600638978e-05, | |
| "loss": 0.0858, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 9.243876464323749e-05, | |
| "loss": 0.0933, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 9.19062832800852e-05, | |
| "loss": 0.1706, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 9.137380191693292e-05, | |
| "loss": 0.166, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 9.084132055378062e-05, | |
| "loss": 0.0686, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 9.030883919062834e-05, | |
| "loss": 0.0917, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 8.977635782747604e-05, | |
| "loss": 0.0949, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 8.924387646432375e-05, | |
| "loss": 0.0548, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 8.871139510117146e-05, | |
| "loss": 0.0499, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 8.817891373801918e-05, | |
| "loss": 0.0706, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_accuracy": 0.8341968911917098, | |
| "eval_f1": 0.8211052468838738, | |
| "eval_loss": 0.631217896938324, | |
| "eval_precision": 0.8211818406118925, | |
| "eval_recall": 0.8341968911917098, | |
| "eval_runtime": 1.498, | |
| "eval_samples_per_second": 128.836, | |
| "eval_steps_per_second": 16.689, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 8.764643237486689e-05, | |
| "loss": 0.1315, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 8.711395101171459e-05, | |
| "loss": 0.0844, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 8.663471778487753e-05, | |
| "loss": 0.2011, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 8.610223642172525e-05, | |
| "loss": 0.0879, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 8.556975505857295e-05, | |
| "loss": 0.2016, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 8.503727369542066e-05, | |
| "loss": 0.0913, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 8.450479233226837e-05, | |
| "loss": 0.1158, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 8.397231096911609e-05, | |
| "loss": 0.0632, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 8.34398296059638e-05, | |
| "loss": 0.0227, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 8.29073482428115e-05, | |
| "loss": 0.1729, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_accuracy": 0.8393782383419689, | |
| "eval_f1": 0.8401017184708062, | |
| "eval_loss": 0.5897563099861145, | |
| "eval_precision": 0.8427747429207628, | |
| "eval_recall": 0.8393782383419689, | |
| "eval_runtime": 1.4896, | |
| "eval_samples_per_second": 129.567, | |
| "eval_steps_per_second": 16.783, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 8.237486687965922e-05, | |
| "loss": 0.0961, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 8.184238551650692e-05, | |
| "loss": 0.0713, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 8.130990415335463e-05, | |
| "loss": 0.1107, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 8.077742279020235e-05, | |
| "loss": 0.1033, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 8.024494142705006e-05, | |
| "loss": 0.0861, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 7.971246006389777e-05, | |
| "loss": 0.2032, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 7.917997870074548e-05, | |
| "loss": 0.0854, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 7.86474973375932e-05, | |
| "loss": 0.0937, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 7.811501597444089e-05, | |
| "loss": 0.1106, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 7.75825346112886e-05, | |
| "loss": 0.1356, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_accuracy": 0.8549222797927462, | |
| "eval_f1": 0.8533967869044328, | |
| "eval_loss": 0.5565972328186035, | |
| "eval_precision": 0.8573825055232043, | |
| "eval_recall": 0.8549222797927462, | |
| "eval_runtime": 1.3852, | |
| "eval_samples_per_second": 139.325, | |
| "eval_steps_per_second": 18.047, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 7.705005324813632e-05, | |
| "loss": 0.0954, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 7.651757188498403e-05, | |
| "loss": 0.1952, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 7.598509052183174e-05, | |
| "loss": 0.0759, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 7.545260915867945e-05, | |
| "loss": 0.0471, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 7.492012779552717e-05, | |
| "loss": 0.1038, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 7.438764643237486e-05, | |
| "loss": 0.1454, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 7.385516506922258e-05, | |
| "loss": 0.1326, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 7.332268370607029e-05, | |
| "loss": 0.1068, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 7.2790202342918e-05, | |
| "loss": 0.1038, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 7.225772097976571e-05, | |
| "loss": 0.0941, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_accuracy": 0.844559585492228, | |
| "eval_f1": 0.8420695150420747, | |
| "eval_loss": 0.6472011208534241, | |
| "eval_precision": 0.8464751579543209, | |
| "eval_recall": 0.844559585492228, | |
| "eval_runtime": 1.4944, | |
| "eval_samples_per_second": 129.146, | |
| "eval_steps_per_second": 16.729, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 7.172523961661343e-05, | |
| "loss": 0.169, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 7.119275825346114e-05, | |
| "loss": 0.0707, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 7.066027689030884e-05, | |
| "loss": 0.1167, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 7.012779552715655e-05, | |
| "loss": 0.0331, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 6.959531416400426e-05, | |
| "loss": 0.0357, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 6.906283280085197e-05, | |
| "loss": 0.1012, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 6.853035143769968e-05, | |
| "loss": 0.0744, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 6.79978700745474e-05, | |
| "loss": 0.0868, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 6.746538871139511e-05, | |
| "loss": 0.0562, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 6.693290734824281e-05, | |
| "loss": 0.1733, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.844559585492228, | |
| "eval_f1": 0.8406974663942941, | |
| "eval_loss": 0.5888794660568237, | |
| "eval_precision": 0.838737123604599, | |
| "eval_recall": 0.844559585492228, | |
| "eval_runtime": 1.4926, | |
| "eval_samples_per_second": 129.306, | |
| "eval_steps_per_second": 16.749, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 6.640042598509052e-05, | |
| "loss": 0.0827, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 6.586794462193823e-05, | |
| "loss": 0.0225, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 6.533546325878594e-05, | |
| "loss": 0.0565, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 6.480298189563366e-05, | |
| "loss": 0.0324, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 6.427050053248137e-05, | |
| "loss": 0.0687, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 6.373801916932908e-05, | |
| "loss": 0.0195, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 6.320553780617678e-05, | |
| "loss": 0.0613, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 6.26730564430245e-05, | |
| "loss": 0.0284, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 6.214057507987222e-05, | |
| "loss": 0.0804, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 6.160809371671991e-05, | |
| "loss": 0.0512, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_accuracy": 0.8290155440414507, | |
| "eval_f1": 0.8376171259706224, | |
| "eval_loss": 0.6856790781021118, | |
| "eval_precision": 0.8574849271033915, | |
| "eval_recall": 0.8290155440414507, | |
| "eval_runtime": 1.5054, | |
| "eval_samples_per_second": 128.204, | |
| "eval_steps_per_second": 16.607, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 6.107561235356763e-05, | |
| "loss": 0.0761, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.054313099041534e-05, | |
| "loss": 0.0738, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 6.001064962726305e-05, | |
| "loss": 0.0177, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 5.9478168264110756e-05, | |
| "loss": 0.0106, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 5.8945686900958475e-05, | |
| "loss": 0.0174, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 5.841320553780618e-05, | |
| "loss": 0.0386, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 5.7880724174653886e-05, | |
| "loss": 0.0177, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 5.73482428115016e-05, | |
| "loss": 0.0643, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 5.681576144834932e-05, | |
| "loss": 0.0306, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 5.628328008519702e-05, | |
| "loss": 0.0329, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_accuracy": 0.8497409326424871, | |
| "eval_f1": 0.8518420405753666, | |
| "eval_loss": 0.6440693140029907, | |
| "eval_precision": 0.8592012089810018, | |
| "eval_recall": 0.8497409326424871, | |
| "eval_runtime": 1.4798, | |
| "eval_samples_per_second": 130.421, | |
| "eval_steps_per_second": 16.894, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 5.575079872204473e-05, | |
| "loss": 0.0065, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 5.521831735889245e-05, | |
| "loss": 0.0943, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 5.468583599574015e-05, | |
| "loss": 0.0091, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 5.415335463258786e-05, | |
| "loss": 0.0075, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 5.362087326943557e-05, | |
| "loss": 0.0082, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 5.308839190628329e-05, | |
| "loss": 0.0071, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 5.2555910543130994e-05, | |
| "loss": 0.0937, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 5.20234291799787e-05, | |
| "loss": 0.0663, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 5.149094781682642e-05, | |
| "loss": 0.0365, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 5.095846645367412e-05, | |
| "loss": 0.0054, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_accuracy": 0.8341968911917098, | |
| "eval_f1": 0.8377213732247963, | |
| "eval_loss": 0.6683371067047119, | |
| "eval_precision": 0.84321819228555, | |
| "eval_recall": 0.8341968911917098, | |
| "eval_runtime": 1.4882, | |
| "eval_samples_per_second": 129.683, | |
| "eval_steps_per_second": 16.798, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 5.0425985090521835e-05, | |
| "loss": 0.034, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 4.989350372736955e-05, | |
| "loss": 0.0076, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 4.936102236421725e-05, | |
| "loss": 0.0627, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 4.8828541001064965e-05, | |
| "loss": 0.0825, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 4.829605963791268e-05, | |
| "loss": 0.0054, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 4.776357827476038e-05, | |
| "loss": 0.0062, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 4.7231096911608095e-05, | |
| "loss": 0.0185, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 4.669861554845581e-05, | |
| "loss": 0.0416, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 4.616613418530352e-05, | |
| "loss": 0.0458, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 4.563365282215123e-05, | |
| "loss": 0.0252, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_accuracy": 0.8549222797927462, | |
| "eval_f1": 0.8565077323471078, | |
| "eval_loss": 0.687915563583374, | |
| "eval_precision": 0.8619031638834972, | |
| "eval_recall": 0.8549222797927462, | |
| "eval_runtime": 1.4913, | |
| "eval_samples_per_second": 129.421, | |
| "eval_steps_per_second": 16.764, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 4.5101171458998936e-05, | |
| "loss": 0.0338, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 4.456869009584665e-05, | |
| "loss": 0.0198, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 4.4036208732694354e-05, | |
| "loss": 0.008, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 4.3503727369542066e-05, | |
| "loss": 0.0667, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 4.297124600638978e-05, | |
| "loss": 0.0292, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 4.243876464323749e-05, | |
| "loss": 0.0214, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 4.19062832800852e-05, | |
| "loss": 0.0332, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 4.137380191693291e-05, | |
| "loss": 0.007, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 4.084132055378062e-05, | |
| "loss": 0.0243, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 4.0308839190628325e-05, | |
| "loss": 0.0052, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "eval_accuracy": 0.8549222797927462, | |
| "eval_f1": 0.8533510294868818, | |
| "eval_loss": 0.7231641411781311, | |
| "eval_precision": 0.8531663391594642, | |
| "eval_recall": 0.8549222797927462, | |
| "eval_runtime": 1.474, | |
| "eval_samples_per_second": 130.933, | |
| "eval_steps_per_second": 16.96, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 3.9776357827476044e-05, | |
| "loss": 0.0425, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 3.9243876464323756e-05, | |
| "loss": 0.0412, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 3.871139510117146e-05, | |
| "loss": 0.0073, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 3.8178913738019174e-05, | |
| "loss": 0.0277, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 3.764643237486688e-05, | |
| "loss": 0.0118, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 3.711395101171459e-05, | |
| "loss": 0.0211, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 3.65814696485623e-05, | |
| "loss": 0.0038, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 3.6048988285410015e-05, | |
| "loss": 0.05, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 3.551650692225773e-05, | |
| "loss": 0.0334, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 3.498402555910543e-05, | |
| "loss": 0.0245, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_accuracy": 0.8652849740932642, | |
| "eval_f1": 0.862776044489481, | |
| "eval_loss": 0.6865922808647156, | |
| "eval_precision": 0.8641787564766841, | |
| "eval_recall": 0.8652849740932642, | |
| "eval_runtime": 1.3614, | |
| "eval_samples_per_second": 141.764, | |
| "eval_steps_per_second": 18.363, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 3.4451544195953145e-05, | |
| "loss": 0.0254, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 3.391906283280085e-05, | |
| "loss": 0.0701, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.338658146964856e-05, | |
| "loss": 0.0058, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 3.2854100106496274e-05, | |
| "loss": 0.0065, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 3.2321618743343987e-05, | |
| "loss": 0.0055, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 3.17891373801917e-05, | |
| "loss": 0.0036, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 3.1256656017039404e-05, | |
| "loss": 0.0039, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 3.0724174653887116e-05, | |
| "loss": 0.0038, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 3.0191693290734825e-05, | |
| "loss": 0.0032, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 2.9659211927582537e-05, | |
| "loss": 0.0192, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "eval_accuracy": 0.8601036269430051, | |
| "eval_f1": 0.8574745639558298, | |
| "eval_loss": 0.7032139301300049, | |
| "eval_precision": 0.8586892491689417, | |
| "eval_recall": 0.8601036269430051, | |
| "eval_runtime": 1.4392, | |
| "eval_samples_per_second": 134.104, | |
| "eval_steps_per_second": 17.371, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 2.912673056443025e-05, | |
| "loss": 0.0035, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 2.8594249201277955e-05, | |
| "loss": 0.0036, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 2.806176783812567e-05, | |
| "loss": 0.0038, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 2.7529286474973375e-05, | |
| "loss": 0.0344, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 2.6996805111821088e-05, | |
| "loss": 0.0327, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 2.6464323748668796e-05, | |
| "loss": 0.0045, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 2.593184238551651e-05, | |
| "loss": 0.0047, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 2.539936102236422e-05, | |
| "loss": 0.0074, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 2.486687965921193e-05, | |
| "loss": 0.0034, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 2.4334398296059638e-05, | |
| "loss": 0.0401, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "eval_accuracy": 0.8549222797927462, | |
| "eval_f1": 0.8538788387428684, | |
| "eval_loss": 0.7521350979804993, | |
| "eval_precision": 0.8581735751295338, | |
| "eval_recall": 0.8549222797927462, | |
| "eval_runtime": 1.3915, | |
| "eval_samples_per_second": 138.702, | |
| "eval_steps_per_second": 17.967, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 2.380191693290735e-05, | |
| "loss": 0.0036, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.326943556975506e-05, | |
| "loss": 0.0039, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 2.273695420660277e-05, | |
| "loss": 0.0031, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 2.220447284345048e-05, | |
| "loss": 0.0035, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 2.167199148029819e-05, | |
| "loss": 0.0035, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 2.11395101171459e-05, | |
| "loss": 0.0031, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 2.0607028753993613e-05, | |
| "loss": 0.0032, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 2.007454739084132e-05, | |
| "loss": 0.0034, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 1.9542066027689034e-05, | |
| "loss": 0.0051, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 1.9009584664536742e-05, | |
| "loss": 0.0165, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "eval_accuracy": 0.8601036269430051, | |
| "eval_f1": 0.8613574283414414, | |
| "eval_loss": 0.7556974291801453, | |
| "eval_precision": 0.8655209188633125, | |
| "eval_recall": 0.8601036269430051, | |
| "eval_runtime": 1.5094, | |
| "eval_samples_per_second": 127.865, | |
| "eval_steps_per_second": 16.563, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 1.847710330138445e-05, | |
| "loss": 0.0032, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 1.7944621938232163e-05, | |
| "loss": 0.0031, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 1.7412140575079875e-05, | |
| "loss": 0.0313, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 1.6879659211927584e-05, | |
| "loss": 0.0033, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 1.6347177848775293e-05, | |
| "loss": 0.0306, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 1.5814696485623005e-05, | |
| "loss": 0.0032, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 1.5282215122470714e-05, | |
| "loss": 0.0033, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 1.4749733759318424e-05, | |
| "loss": 0.0067, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 1.4217252396166134e-05, | |
| "loss": 0.0319, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 1.3684771033013847e-05, | |
| "loss": 0.0283, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_accuracy": 0.8601036269430051, | |
| "eval_f1": 0.8587372232982163, | |
| "eval_loss": 0.7359268069267273, | |
| "eval_precision": 0.8619977452584695, | |
| "eval_recall": 0.8601036269430051, | |
| "eval_runtime": 1.4666, | |
| "eval_samples_per_second": 131.597, | |
| "eval_steps_per_second": 17.046, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 1.3152289669861555e-05, | |
| "loss": 0.0043, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 1.2619808306709266e-05, | |
| "loss": 0.0033, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 1.2087326943556976e-05, | |
| "loss": 0.0028, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 1.1554845580404687e-05, | |
| "loss": 0.0027, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 1.1022364217252397e-05, | |
| "loss": 0.0033, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 1.0489882854100107e-05, | |
| "loss": 0.0031, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 9.957401490947816e-06, | |
| "loss": 0.0029, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 9.424920127795528e-06, | |
| "loss": 0.0036, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 8.892438764643237e-06, | |
| "loss": 0.0031, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 8.359957401490947e-06, | |
| "loss": 0.004, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "eval_accuracy": 0.8549222797927462, | |
| "eval_f1": 0.8539219313601594, | |
| "eval_loss": 0.7251555323600769, | |
| "eval_precision": 0.8541107440307215, | |
| "eval_recall": 0.8549222797927462, | |
| "eval_runtime": 1.598, | |
| "eval_samples_per_second": 120.778, | |
| "eval_steps_per_second": 15.645, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 7.82747603833866e-06, | |
| "loss": 0.0031, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 7.294994675186369e-06, | |
| "loss": 0.0056, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 6.762513312034079e-06, | |
| "loss": 0.0027, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 6.230031948881789e-06, | |
| "loss": 0.0027, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 5.6975505857295e-06, | |
| "loss": 0.0027, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 5.16506922257721e-06, | |
| "loss": 0.0031, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 4.6325878594249205e-06, | |
| "loss": 0.0027, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 4.100106496272631e-06, | |
| "loss": 0.0333, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 3.5676251331203413e-06, | |
| "loss": 0.0029, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 3.0351437699680513e-06, | |
| "loss": 0.004, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_accuracy": 0.8549222797927462, | |
| "eval_f1": 0.852586666119307, | |
| "eval_loss": 0.7362812161445618, | |
| "eval_precision": 0.8563626123819863, | |
| "eval_recall": 0.8549222797927462, | |
| "eval_runtime": 1.4557, | |
| "eval_samples_per_second": 132.582, | |
| "eval_steps_per_second": 17.174, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 2.5026624068157617e-06, | |
| "loss": 0.0048, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 1.9701810436634718e-06, | |
| "loss": 0.0037, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 1.4376996805111822e-06, | |
| "loss": 0.0531, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 9.052183173588925e-07, | |
| "loss": 0.0029, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 3.727369542066028e-07, | |
| "loss": 0.0027, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 3756, | |
| "total_flos": 4.65670232933972e+18, | |
| "train_loss": 0.270467962446812, | |
| "train_runtime": 1312.8643, | |
| "train_samples_per_second": 45.77, | |
| "train_steps_per_second": 2.861 | |
| } | |
| ], | |
| "max_steps": 3756, | |
| "num_train_epochs": 6, | |
| "total_flos": 4.65670232933972e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |