| { | |
| "best_metric": 0.93, | |
| "best_model_checkpoint": "dinov2-base-imagenet1k-1-layer-finetuned-galaxy_mnist/checkpoint-875", | |
| "epoch": 29.76, | |
| "eval_steps": 500, | |
| "global_step": 930, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 1.2963, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.6569, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.4569, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.8145, | |
| "eval_f1": 0.8062014969756545, | |
| "eval_loss": 0.4349806606769562, | |
| "eval_precision": 0.8694463934261056, | |
| "eval_recall": 0.8145, | |
| "eval_runtime": 19.0737, | |
| "eval_samples_per_second": 104.856, | |
| "eval_steps_per_second": 1.678, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.4693, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.4344, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.4173, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_accuracy": 0.871, | |
| "eval_f1": 0.8681661966927955, | |
| "eval_loss": 0.3161027431488037, | |
| "eval_precision": 0.8848178640258768, | |
| "eval_recall": 0.871, | |
| "eval_runtime": 18.7829, | |
| "eval_samples_per_second": 106.48, | |
| "eval_steps_per_second": 1.704, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.3501, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.5032, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.4318, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.8285, | |
| "eval_f1": 0.8216347905069582, | |
| "eval_loss": 0.3914068639278412, | |
| "eval_precision": 0.8800858789744227, | |
| "eval_recall": 0.8285, | |
| "eval_runtime": 19.2231, | |
| "eval_samples_per_second": 104.042, | |
| "eval_steps_per_second": 1.665, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.4468, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.4381, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.4238, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8485, | |
| "eval_f1": 0.844101752903838, | |
| "eval_loss": 0.3689117431640625, | |
| "eval_precision": 0.8684029141839681, | |
| "eval_recall": 0.8485, | |
| "eval_runtime": 19.1718, | |
| "eval_samples_per_second": 104.32, | |
| "eval_steps_per_second": 1.669, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.4272, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.3204, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.3735, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8735, | |
| "eval_f1": 0.870456579915893, | |
| "eval_loss": 0.29686883091926575, | |
| "eval_precision": 0.8929206411088424, | |
| "eval_recall": 0.8735, | |
| "eval_runtime": 19.2606, | |
| "eval_samples_per_second": 103.839, | |
| "eval_steps_per_second": 1.661, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.3527, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.3495, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.3371, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_accuracy": 0.906, | |
| "eval_f1": 0.9062924251143148, | |
| "eval_loss": 0.21738244593143463, | |
| "eval_precision": 0.9136144489096446, | |
| "eval_recall": 0.906, | |
| "eval_runtime": 19.0431, | |
| "eval_samples_per_second": 105.025, | |
| "eval_steps_per_second": 1.68, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.3082, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.2839, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.3069, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.9055, | |
| "eval_f1": 0.9049217838761544, | |
| "eval_loss": 0.2422126680612564, | |
| "eval_precision": 0.9076776650164383, | |
| "eval_recall": 0.9055, | |
| "eval_runtime": 19.1102, | |
| "eval_samples_per_second": 104.656, | |
| "eval_steps_per_second": 1.674, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.3309, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.2901, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.3296, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.2526, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8905, | |
| "eval_f1": 0.8899290547941602, | |
| "eval_loss": 0.27833855152130127, | |
| "eval_precision": 0.9072396856057143, | |
| "eval_recall": 0.8905, | |
| "eval_runtime": 19.0808, | |
| "eval_samples_per_second": 104.817, | |
| "eval_steps_per_second": 1.677, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.3102, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.2885, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.2753, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.9155, | |
| "eval_f1": 0.914969072356757, | |
| "eval_loss": 0.23728662729263306, | |
| "eval_precision": 0.9175583090538354, | |
| "eval_recall": 0.9155, | |
| "eval_runtime": 19.0448, | |
| "eval_samples_per_second": 105.015, | |
| "eval_steps_per_second": 1.68, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.2786, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.2572, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2704, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_accuracy": 0.8865, | |
| "eval_f1": 0.8863626818115898, | |
| "eval_loss": 0.2804119884967804, | |
| "eval_precision": 0.9000528290442162, | |
| "eval_recall": 0.8865, | |
| "eval_runtime": 19.0758, | |
| "eval_samples_per_second": 104.845, | |
| "eval_steps_per_second": 1.678, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.2529, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.246, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.2417, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_accuracy": 0.912, | |
| "eval_f1": 0.9121972705907047, | |
| "eval_loss": 0.20778250694274902, | |
| "eval_precision": 0.9125873163675496, | |
| "eval_recall": 0.912, | |
| "eval_runtime": 19.0898, | |
| "eval_samples_per_second": 104.768, | |
| "eval_steps_per_second": 1.676, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.2477, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.2278, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.266, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.918, | |
| "eval_f1": 0.9183010528913053, | |
| "eval_loss": 0.2004268765449524, | |
| "eval_precision": 0.9187900810311216, | |
| "eval_recall": 0.918, | |
| "eval_runtime": 19.3032, | |
| "eval_samples_per_second": 103.61, | |
| "eval_steps_per_second": 1.658, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.216, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.274, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.2387, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.9165, | |
| "eval_f1": 0.9159563215617916, | |
| "eval_loss": 0.2255440503358841, | |
| "eval_precision": 0.9196243307141442, | |
| "eval_recall": 0.9165, | |
| "eval_runtime": 19.1751, | |
| "eval_samples_per_second": 104.302, | |
| "eval_steps_per_second": 1.669, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.228, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.2203, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.2137, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "eval_accuracy": 0.9145, | |
| "eval_f1": 0.9146809990290234, | |
| "eval_loss": 0.22079433500766754, | |
| "eval_precision": 0.916937564127325, | |
| "eval_recall": 0.9145, | |
| "eval_runtime": 19.3578, | |
| "eval_samples_per_second": 103.318, | |
| "eval_steps_per_second": 1.653, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.2236, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.2423, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.2063, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_accuracy": 0.9205, | |
| "eval_f1": 0.920438049274758, | |
| "eval_loss": 0.20779238641262054, | |
| "eval_precision": 0.9209836159835532, | |
| "eval_recall": 0.9205, | |
| "eval_runtime": 18.9812, | |
| "eval_samples_per_second": 105.368, | |
| "eval_steps_per_second": 1.686, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.2152, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.1983, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.2027, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.2081, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9045, | |
| "eval_f1": 0.9036736649053552, | |
| "eval_loss": 0.26576581597328186, | |
| "eval_precision": 0.9114982051043011, | |
| "eval_recall": 0.9045, | |
| "eval_runtime": 19.0285, | |
| "eval_samples_per_second": 105.106, | |
| "eval_steps_per_second": 1.682, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.2033, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.2304, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.1862, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.914, | |
| "eval_f1": 0.914336611544218, | |
| "eval_loss": 0.24250277876853943, | |
| "eval_precision": 0.9207773863704141, | |
| "eval_recall": 0.914, | |
| "eval_runtime": 19.0054, | |
| "eval_samples_per_second": 105.233, | |
| "eval_steps_per_second": 1.684, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.2003, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.1996, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.1905, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "eval_accuracy": 0.912, | |
| "eval_f1": 0.9115715146839237, | |
| "eval_loss": 0.23983970284461975, | |
| "eval_precision": 0.9113901919601698, | |
| "eval_recall": 0.912, | |
| "eval_runtime": 19.1498, | |
| "eval_samples_per_second": 104.439, | |
| "eval_steps_per_second": 1.671, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.1786, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.1958, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.1727, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "eval_accuracy": 0.9085, | |
| "eval_f1": 0.9083837227703245, | |
| "eval_loss": 0.29992052912712097, | |
| "eval_precision": 0.910009519747882, | |
| "eval_recall": 0.9085, | |
| "eval_runtime": 19.2612, | |
| "eval_samples_per_second": 103.836, | |
| "eval_steps_per_second": 1.661, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.1687, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.1824, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1697, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9185, | |
| "eval_f1": 0.9183176260420626, | |
| "eval_loss": 0.25201329588890076, | |
| "eval_precision": 0.9196789220314392, | |
| "eval_recall": 0.9185, | |
| "eval_runtime": 19.2235, | |
| "eval_samples_per_second": 104.039, | |
| "eval_steps_per_second": 1.665, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.1742, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.1606, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.161, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.9205, | |
| "eval_f1": 0.9204648754998753, | |
| "eval_loss": 0.24709747731685638, | |
| "eval_precision": 0.9215625042030531, | |
| "eval_recall": 0.9205, | |
| "eval_runtime": 19.1672, | |
| "eval_samples_per_second": 104.345, | |
| "eval_steps_per_second": 1.67, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.1791, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.1507, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.1363, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "eval_accuracy": 0.922, | |
| "eval_f1": 0.92218826600295, | |
| "eval_loss": 0.24492745101451874, | |
| "eval_precision": 0.9224308527734407, | |
| "eval_recall": 0.922, | |
| "eval_runtime": 19.0337, | |
| "eval_samples_per_second": 105.077, | |
| "eval_steps_per_second": 1.681, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.133, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.1507, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.1533, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "eval_accuracy": 0.917, | |
| "eval_f1": 0.9173330401448656, | |
| "eval_loss": 0.27803662419319153, | |
| "eval_precision": 0.9179378176525308, | |
| "eval_recall": 0.917, | |
| "eval_runtime": 19.0927, | |
| "eval_samples_per_second": 104.752, | |
| "eval_steps_per_second": 1.676, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.139, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.1278, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.1523, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.1324, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.917, | |
| "eval_f1": 0.9169819079289377, | |
| "eval_loss": 0.2683439254760742, | |
| "eval_precision": 0.9183514160763434, | |
| "eval_recall": 0.917, | |
| "eval_runtime": 19.0455, | |
| "eval_samples_per_second": 105.012, | |
| "eval_steps_per_second": 1.68, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.1126, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.136, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.1291, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.924, | |
| "eval_f1": 0.9239691519167053, | |
| "eval_loss": 0.2650637924671173, | |
| "eval_precision": 0.924266989876481, | |
| "eval_recall": 0.924, | |
| "eval_runtime": 19.2675, | |
| "eval_samples_per_second": 103.802, | |
| "eval_steps_per_second": 1.661, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.122, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.1342, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.1112, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 25.98, | |
| "eval_accuracy": 0.924, | |
| "eval_f1": 0.9239700273294605, | |
| "eval_loss": 0.303556889295578, | |
| "eval_precision": 0.9245461595177494, | |
| "eval_recall": 0.924, | |
| "eval_runtime": 19.3639, | |
| "eval_samples_per_second": 103.285, | |
| "eval_steps_per_second": 1.653, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.1064, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.1084, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.1175, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 26.98, | |
| "eval_accuracy": 0.927, | |
| "eval_f1": 0.9269337553196025, | |
| "eval_loss": 0.28181326389312744, | |
| "eval_precision": 0.9270177422439586, | |
| "eval_recall": 0.927, | |
| "eval_runtime": 19.2493, | |
| "eval_samples_per_second": 103.9, | |
| "eval_steps_per_second": 1.662, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.1027, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.0997, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.1214, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.93, | |
| "eval_f1": 0.9300021139343475, | |
| "eval_loss": 0.2800217866897583, | |
| "eval_precision": 0.9301212864940808, | |
| "eval_recall": 0.93, | |
| "eval_runtime": 19.2287, | |
| "eval_samples_per_second": 104.011, | |
| "eval_steps_per_second": 1.664, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.0971, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.1173, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.0953, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.9245, | |
| "eval_f1": 0.924368857900811, | |
| "eval_loss": 0.31678149104118347, | |
| "eval_precision": 0.9243813880854884, | |
| "eval_recall": 0.9245, | |
| "eval_runtime": 19.1501, | |
| "eval_samples_per_second": 104.438, | |
| "eval_steps_per_second": 1.671, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.102, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.0935, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.0955, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.925, | |
| "eval_f1": 0.9248854297488431, | |
| "eval_loss": 0.32158568501472473, | |
| "eval_precision": 0.9248895458550859, | |
| "eval_recall": 0.925, | |
| "eval_runtime": 19.1026, | |
| "eval_samples_per_second": 104.698, | |
| "eval_steps_per_second": 1.675, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 930, | |
| "total_flos": 2.4317906065576428e+19, | |
| "train_loss": 0.24588879500665972, | |
| "train_runtime": 5652.2795, | |
| "train_samples_per_second": 42.461, | |
| "train_steps_per_second": 0.165 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 930, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 2.4317906065576428e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |