| { | |
| "best_metric": 0.909, | |
| "best_model_checkpoint": "dinov2-base-imagenet1k-1-layer-finetuned-galaxy10-decals-head-finetuned-100-galaxy_mnist/checkpoint-1437", | |
| "epoch": 29.76, | |
| "eval_steps": 500, | |
| "global_step": 1860, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 1.4447, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 1.4069, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 1.3572, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 1.2822, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 1.1889, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 1.1235, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.622, | |
| "eval_f1": 0.624854734204189, | |
| "eval_loss": 0.9578595757484436, | |
| "eval_precision": 0.6409798855356537, | |
| "eval_recall": 0.622, | |
| "eval_runtime": 16.8298, | |
| "eval_samples_per_second": 118.837, | |
| "eval_steps_per_second": 3.743, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 1.0003, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.8665, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.8069, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.7, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 5.913978494623657e-05, | |
| "loss": 0.5919, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.5488, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.852, | |
| "eval_f1": 0.8523278401704051, | |
| "eval_loss": 0.39638885855674744, | |
| "eval_precision": 0.8534315840873946, | |
| "eval_recall": 0.852, | |
| "eval_runtime": 16.8612, | |
| "eval_samples_per_second": 118.615, | |
| "eval_steps_per_second": 3.736, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.989247311827958e-05, | |
| "loss": 0.5053, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.4556, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.064516129032258e-05, | |
| "loss": 0.4248, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.3989, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 9.13978494623656e-05, | |
| "loss": 0.4156, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.384, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.882, | |
| "eval_f1": 0.8819155512304139, | |
| "eval_loss": 0.28765082359313965, | |
| "eval_precision": 0.8820432880055151, | |
| "eval_recall": 0.882, | |
| "eval_runtime": 17.0553, | |
| "eval_samples_per_second": 117.266, | |
| "eval_steps_per_second": 3.694, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 9.97610513739546e-05, | |
| "loss": 0.3662, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.916367980884111e-05, | |
| "loss": 0.3768, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 9.85663082437276e-05, | |
| "loss": 0.3781, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.79689366786141e-05, | |
| "loss": 0.3335, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 9.73715651135006e-05, | |
| "loss": 0.3226, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.339, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.61768219832736e-05, | |
| "loss": 0.3493, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8885, | |
| "eval_f1": 0.8885042805006992, | |
| "eval_loss": 0.2621266543865204, | |
| "eval_precision": 0.8885093864504561, | |
| "eval_recall": 0.8885, | |
| "eval_runtime": 16.8935, | |
| "eval_samples_per_second": 118.389, | |
| "eval_steps_per_second": 3.729, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.55794504181601e-05, | |
| "loss": 0.3274, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 9.49820788530466e-05, | |
| "loss": 0.3158, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 9.438470728793309e-05, | |
| "loss": 0.3157, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 9.378733572281961e-05, | |
| "loss": 0.3246, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 9.31899641577061e-05, | |
| "loss": 0.3278, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 9.25925925925926e-05, | |
| "loss": 0.3184, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8945, | |
| "eval_f1": 0.894569910818708, | |
| "eval_loss": 0.257001131772995, | |
| "eval_precision": 0.8956679417211442, | |
| "eval_recall": 0.8945, | |
| "eval_runtime": 16.9245, | |
| "eval_samples_per_second": 118.172, | |
| "eval_steps_per_second": 3.722, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 9.199522102747909e-05, | |
| "loss": 0.3183, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 9.13978494623656e-05, | |
| "loss": 0.3247, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 9.080047789725208e-05, | |
| "loss": 0.2915, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 9.02031063321386e-05, | |
| "loss": 0.3194, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 8.960573476702509e-05, | |
| "loss": 0.3309, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 8.900836320191159e-05, | |
| "loss": 0.3027, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9, | |
| "eval_f1": 0.8999625553654238, | |
| "eval_loss": 0.24849317967891693, | |
| "eval_precision": 0.9013348450853103, | |
| "eval_recall": 0.9, | |
| "eval_runtime": 17.0678, | |
| "eval_samples_per_second": 117.18, | |
| "eval_steps_per_second": 3.691, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 8.84109916367981e-05, | |
| "loss": 0.3149, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 8.781362007168459e-05, | |
| "loss": 0.2934, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 8.72162485065711e-05, | |
| "loss": 0.3055, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 8.661887694145759e-05, | |
| "loss": 0.3009, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.2988, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 8.542413381123058e-05, | |
| "loss": 0.3245, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.9035, | |
| "eval_f1": 0.9034300406420113, | |
| "eval_loss": 0.23968428373336792, | |
| "eval_precision": 0.9038367786864951, | |
| "eval_recall": 0.9035, | |
| "eval_runtime": 16.9143, | |
| "eval_samples_per_second": 118.243, | |
| "eval_steps_per_second": 3.725, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 8.482676224611709e-05, | |
| "loss": 0.3201, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 8.422939068100359e-05, | |
| "loss": 0.3185, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 8.363201911589009e-05, | |
| "loss": 0.3069, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 8.30346475507766e-05, | |
| "loss": 0.3005, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 8.243727598566309e-05, | |
| "loss": 0.3241, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 8.183990442054959e-05, | |
| "loss": 0.282, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 8.124253285543608e-05, | |
| "loss": 0.2666, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9035, | |
| "eval_f1": 0.9034072593288889, | |
| "eval_loss": 0.2413206398487091, | |
| "eval_precision": 0.9050617749604192, | |
| "eval_recall": 0.9035, | |
| "eval_runtime": 17.0352, | |
| "eval_samples_per_second": 117.404, | |
| "eval_steps_per_second": 3.698, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 8.064516129032258e-05, | |
| "loss": 0.2902, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.004778972520908e-05, | |
| "loss": 0.3072, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 7.945041816009559e-05, | |
| "loss": 0.3048, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7.885304659498209e-05, | |
| "loss": 0.2844, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 7.825567502986858e-05, | |
| "loss": 0.2892, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 7.765830346475508e-05, | |
| "loss": 0.2705, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.905, | |
| "eval_f1": 0.904954557880876, | |
| "eval_loss": 0.23356491327285767, | |
| "eval_precision": 0.9057394655090609, | |
| "eval_recall": 0.905, | |
| "eval_runtime": 17.0788, | |
| "eval_samples_per_second": 117.104, | |
| "eval_steps_per_second": 3.689, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 7.706093189964157e-05, | |
| "loss": 0.2951, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 7.646356033452809e-05, | |
| "loss": 0.2894, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 7.586618876941458e-05, | |
| "loss": 0.3032, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.2939, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 7.467144563918757e-05, | |
| "loss": 0.2978, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.2524, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9065, | |
| "eval_f1": 0.9064598532587708, | |
| "eval_loss": 0.23204877972602844, | |
| "eval_precision": 0.9072005308647697, | |
| "eval_recall": 0.9065, | |
| "eval_runtime": 16.966, | |
| "eval_samples_per_second": 117.883, | |
| "eval_steps_per_second": 3.713, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 7.347670250896058e-05, | |
| "loss": 0.2997, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 7.287933094384708e-05, | |
| "loss": 0.2884, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 7.228195937873358e-05, | |
| "loss": 0.297, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 7.168458781362007e-05, | |
| "loss": 0.2942, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 7.108721624850657e-05, | |
| "loss": 0.2824, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 7.048984468339306e-05, | |
| "loss": 0.271, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.908, | |
| "eval_f1": 0.9079337551093364, | |
| "eval_loss": 0.2293005883693695, | |
| "eval_precision": 0.9084810736190014, | |
| "eval_recall": 0.908, | |
| "eval_runtime": 16.9766, | |
| "eval_samples_per_second": 117.809, | |
| "eval_steps_per_second": 3.711, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 6.989247311827958e-05, | |
| "loss": 0.2949, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 6.929510155316607e-05, | |
| "loss": 0.2698, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 6.869772998805257e-05, | |
| "loss": 0.2716, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.810035842293908e-05, | |
| "loss": 0.3006, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 6.750298685782557e-05, | |
| "loss": 0.3228, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 6.690561529271207e-05, | |
| "loss": 0.2885, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 6.630824372759857e-05, | |
| "loss": 0.2624, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9045, | |
| "eval_f1": 0.9044749638957836, | |
| "eval_loss": 0.22658687829971313, | |
| "eval_precision": 0.9047119422348452, | |
| "eval_recall": 0.9045, | |
| "eval_runtime": 16.9548, | |
| "eval_samples_per_second": 117.961, | |
| "eval_steps_per_second": 3.716, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 6.571087216248507e-05, | |
| "loss": 0.2729, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 6.511350059737156e-05, | |
| "loss": 0.3197, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.2834, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 6.391875746714456e-05, | |
| "loss": 0.2792, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 6.332138590203107e-05, | |
| "loss": 0.2601, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 6.272401433691756e-05, | |
| "loss": 0.2681, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.908, | |
| "eval_f1": 0.9079335348210644, | |
| "eval_loss": 0.22864139080047607, | |
| "eval_precision": 0.9087504256984704, | |
| "eval_recall": 0.908, | |
| "eval_runtime": 16.8831, | |
| "eval_samples_per_second": 118.462, | |
| "eval_steps_per_second": 3.732, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 6.212664277180407e-05, | |
| "loss": 0.294, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 6.152927120669057e-05, | |
| "loss": 0.2743, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 6.093189964157706e-05, | |
| "loss": 0.2793, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 6.033452807646356e-05, | |
| "loss": 0.2812, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 5.9737156511350064e-05, | |
| "loss": 0.2682, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 5.913978494623657e-05, | |
| "loss": 0.262, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9085, | |
| "eval_f1": 0.9084699038093151, | |
| "eval_loss": 0.22392599284648895, | |
| "eval_precision": 0.908913865638198, | |
| "eval_recall": 0.9085, | |
| "eval_runtime": 17.038, | |
| "eval_samples_per_second": 117.385, | |
| "eval_steps_per_second": 3.698, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 5.8542413381123063e-05, | |
| "loss": 0.2721, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 5.794504181600956e-05, | |
| "loss": 0.3093, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 5.7347670250896056e-05, | |
| "loss": 0.2713, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 5.675029868578255e-05, | |
| "loss": 0.2494, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 5.615292712066906e-05, | |
| "loss": 0.2742, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.3015, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.9075, | |
| "eval_f1": 0.9074456999803892, | |
| "eval_loss": 0.22646784782409668, | |
| "eval_precision": 0.9084528115105349, | |
| "eval_recall": 0.9075, | |
| "eval_runtime": 17.0055, | |
| "eval_samples_per_second": 117.609, | |
| "eval_steps_per_second": 3.705, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 5.495818399044206e-05, | |
| "loss": 0.2798, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 5.436081242532856e-05, | |
| "loss": 0.2823, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.2594, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 5.316606929510155e-05, | |
| "loss": 0.2795, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 5.256869772998806e-05, | |
| "loss": 0.3088, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 5.1971326164874556e-05, | |
| "loss": 0.2859, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 5.137395459976105e-05, | |
| "loss": 0.2635, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9065, | |
| "eval_f1": 0.9064090882493226, | |
| "eval_loss": 0.22558730840682983, | |
| "eval_precision": 0.9082479314947143, | |
| "eval_recall": 0.9065, | |
| "eval_runtime": 16.9967, | |
| "eval_samples_per_second": 117.67, | |
| "eval_steps_per_second": 3.707, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 5.077658303464755e-05, | |
| "loss": 0.2404, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 5.017921146953405e-05, | |
| "loss": 0.2807, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.2933, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.275, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.274, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.2708, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.9075, | |
| "eval_f1": 0.90752129626734, | |
| "eval_loss": 0.223880335688591, | |
| "eval_precision": 0.9089089641672106, | |
| "eval_recall": 0.9075, | |
| "eval_runtime": 17.0508, | |
| "eval_samples_per_second": 117.297, | |
| "eval_steps_per_second": 3.695, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.2699, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.2872, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.2914, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.2889, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.2802, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.2616, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9075, | |
| "eval_f1": 0.9074261303562965, | |
| "eval_loss": 0.22308723628520966, | |
| "eval_precision": 0.9084033935045609, | |
| "eval_recall": 0.9075, | |
| "eval_runtime": 17.0748, | |
| "eval_samples_per_second": 117.132, | |
| "eval_steps_per_second": 3.69, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.266, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.2886, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.2994, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.2669, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.2655, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.2658, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.9075, | |
| "eval_f1": 0.9074865381203052, | |
| "eval_loss": 0.22291453182697296, | |
| "eval_precision": 0.9091971779067979, | |
| "eval_recall": 0.9075, | |
| "eval_runtime": 17.0421, | |
| "eval_samples_per_second": 117.357, | |
| "eval_steps_per_second": 3.697, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.2847, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.2455, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.2814, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.264, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.2986, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2801, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.2578, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.908, | |
| "eval_f1": 0.9079724821729502, | |
| "eval_loss": 0.22162187099456787, | |
| "eval_precision": 0.9093421920417138, | |
| "eval_recall": 0.908, | |
| "eval_runtime": 16.9889, | |
| "eval_samples_per_second": 117.724, | |
| "eval_steps_per_second": 3.708, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.2719, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.2905, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.2936, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.2806, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.2814, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.2823, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.9075, | |
| "eval_f1": 0.907479981106695, | |
| "eval_loss": 0.22057318687438965, | |
| "eval_precision": 0.9084443292881205, | |
| "eval_recall": 0.9075, | |
| "eval_runtime": 16.9935, | |
| "eval_samples_per_second": 117.692, | |
| "eval_steps_per_second": 3.707, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.2616, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.2265, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.2918, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.2735, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.2659, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.2714, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9085, | |
| "eval_f1": 0.9084457033817459, | |
| "eval_loss": 0.2222590446472168, | |
| "eval_precision": 0.909974033032129, | |
| "eval_recall": 0.9085, | |
| "eval_runtime": 16.9688, | |
| "eval_samples_per_second": 117.864, | |
| "eval_steps_per_second": 3.713, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.2427, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.2608, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.2661, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.2494, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.2873, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.2631, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.909, | |
| "eval_f1": 0.9089340300469084, | |
| "eval_loss": 0.22345826029777527, | |
| "eval_precision": 0.9107619887821399, | |
| "eval_recall": 0.909, | |
| "eval_runtime": 16.996, | |
| "eval_samples_per_second": 117.675, | |
| "eval_steps_per_second": 3.707, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.2726, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.2365, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.2892, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.2642, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.2695, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.2604, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.2695, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9085, | |
| "eval_f1": 0.908437223875608, | |
| "eval_loss": 0.22136835753917694, | |
| "eval_precision": 0.9101084555841303, | |
| "eval_recall": 0.9085, | |
| "eval_runtime": 16.9876, | |
| "eval_samples_per_second": 117.733, | |
| "eval_steps_per_second": 3.709, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.2739, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.2412, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.2528, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.2847, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2692, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.2698, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.908, | |
| "eval_f1": 0.9079405672047738, | |
| "eval_loss": 0.22075149416923523, | |
| "eval_precision": 0.909536654920438, | |
| "eval_recall": 0.908, | |
| "eval_runtime": 16.9782, | |
| "eval_samples_per_second": 117.798, | |
| "eval_steps_per_second": 3.711, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.2684, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.2515, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 25.44, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.2782, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.2925, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.2728, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.2285, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9075, | |
| "eval_f1": 0.9074666467178584, | |
| "eval_loss": 0.21882151067256927, | |
| "eval_precision": 0.908281507099877, | |
| "eval_recall": 0.9075, | |
| "eval_runtime": 16.8981, | |
| "eval_samples_per_second": 118.356, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 26.08, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.261, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.2583, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.2579, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.2993, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.2618, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.2716, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.9075, | |
| "eval_f1": 0.9074524953350263, | |
| "eval_loss": 0.22022314369678497, | |
| "eval_precision": 0.90890991555233, | |
| "eval_recall": 0.9075, | |
| "eval_runtime": 16.9002, | |
| "eval_samples_per_second": 118.342, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1687 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.2556, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.2731, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.2504, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.2446, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.288, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.2904, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.2628, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9075, | |
| "eval_f1": 0.9074442116155013, | |
| "eval_loss": 0.22049841284751892, | |
| "eval_precision": 0.9090410247519826, | |
| "eval_recall": 0.9075, | |
| "eval_runtime": 17.049, | |
| "eval_samples_per_second": 117.309, | |
| "eval_steps_per_second": 3.695, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.2579, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.3021, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.2963, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.2654, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.2583, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.2619, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.907, | |
| "eval_f1": 0.9069478432720398, | |
| "eval_loss": 0.2206609547138214, | |
| "eval_precision": 0.9085473165672802, | |
| "eval_recall": 0.907, | |
| "eval_runtime": 16.9647, | |
| "eval_samples_per_second": 117.892, | |
| "eval_steps_per_second": 3.714, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.289, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.2571, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.2673, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.266, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.2568, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.907, | |
| "eval_f1": 0.9069478432720398, | |
| "eval_loss": 0.22041857242584229, | |
| "eval_precision": 0.9085473165672802, | |
| "eval_recall": 0.907, | |
| "eval_runtime": 16.9946, | |
| "eval_samples_per_second": 117.685, | |
| "eval_steps_per_second": 3.707, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 1860, | |
| "total_flos": 2.4317906065576428e+19, | |
| "train_loss": 0.3364416819746776, | |
| "train_runtime": 2765.6505, | |
| "train_samples_per_second": 86.779, | |
| "train_steps_per_second": 0.673 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 2.4317906065576428e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |