| { | |
| "best_metric": 0.058743953704833984, | |
| "best_model_checkpoint": "./vit-base-beans/checkpoint-1000", | |
| "epoch": 3.9130434782608696, | |
| "global_step": 1440, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001986413043478261, | |
| "loss": 0.4939, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001972826086956522, | |
| "loss": 0.0893, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019592391304347828, | |
| "loss": 0.1067, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019456521739130434, | |
| "loss": 0.1309, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.9645776566757494, | |
| "eval_loss": 0.1362440586090088, | |
| "eval_runtime": 17.6545, | |
| "eval_samples_per_second": 41.576, | |
| "eval_steps_per_second": 5.211, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019320652173913046, | |
| "loss": 0.1611, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019184782608695653, | |
| "loss": 0.1387, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019048913043478262, | |
| "loss": 0.1267, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001891304347826087, | |
| "loss": 0.1563, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.9632152588555858, | |
| "eval_loss": 0.15953560173511505, | |
| "eval_runtime": 18.8416, | |
| "eval_samples_per_second": 38.956, | |
| "eval_steps_per_second": 4.883, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001877717391304348, | |
| "loss": 0.1176, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0001864130434782609, | |
| "loss": 0.0943, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00018505434782608698, | |
| "loss": 0.1512, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00018369565217391304, | |
| "loss": 0.1858, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.946866485013624, | |
| "eval_loss": 0.20780953764915466, | |
| "eval_runtime": 17.8429, | |
| "eval_samples_per_second": 41.137, | |
| "eval_steps_per_second": 5.156, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00018233695652173913, | |
| "loss": 0.1897, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00018097826086956522, | |
| "loss": 0.1031, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001796195652173913, | |
| "loss": 0.0836, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001782608695652174, | |
| "loss": 0.072, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.9686648501362398, | |
| "eval_loss": 0.10965152829885483, | |
| "eval_runtime": 17.2333, | |
| "eval_samples_per_second": 42.592, | |
| "eval_steps_per_second": 5.338, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001769021739130435, | |
| "loss": 0.0967, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00017554347826086956, | |
| "loss": 0.0429, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00017418478260869567, | |
| "loss": 0.0393, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00017282608695652174, | |
| "loss": 0.1578, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.9673024523160763, | |
| "eval_loss": 0.11375105381011963, | |
| "eval_runtime": 17.5835, | |
| "eval_samples_per_second": 41.744, | |
| "eval_steps_per_second": 5.232, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00017146739130434783, | |
| "loss": 0.1322, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00017010869565217392, | |
| "loss": 0.0823, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00016875, | |
| "loss": 0.1165, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0001673913043478261, | |
| "loss": 0.1477, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.9673024523160763, | |
| "eval_loss": 0.10707248002290726, | |
| "eval_runtime": 18.2425, | |
| "eval_samples_per_second": 40.236, | |
| "eval_steps_per_second": 5.043, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0001660326086956522, | |
| "loss": 0.1144, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00016467391304347828, | |
| "loss": 0.1695, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00016331521739130434, | |
| "loss": 0.1258, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00016195652173913046, | |
| "loss": 0.1107, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.9700272479564033, | |
| "eval_loss": 0.08703844249248505, | |
| "eval_runtime": 17.4796, | |
| "eval_samples_per_second": 41.992, | |
| "eval_steps_per_second": 5.263, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00016059782608695652, | |
| "loss": 0.1093, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00015923913043478262, | |
| "loss": 0.0835, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0001578804347826087, | |
| "loss": 0.0558, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0001565217391304348, | |
| "loss": 0.1394, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.9673024523160763, | |
| "eval_loss": 0.11179673671722412, | |
| "eval_runtime": 17.932, | |
| "eval_samples_per_second": 40.932, | |
| "eval_steps_per_second": 5.13, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00015516304347826086, | |
| "loss": 0.1003, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00015380434782608698, | |
| "loss": 0.0771, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00015244565217391304, | |
| "loss": 0.1046, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015108695652173913, | |
| "loss": 0.0496, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_accuracy": 0.9700272479564033, | |
| "eval_loss": 0.1116204559803009, | |
| "eval_runtime": 17.3489, | |
| "eval_samples_per_second": 42.308, | |
| "eval_steps_per_second": 5.303, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00014972826086956522, | |
| "loss": 0.2176, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001483695652173913, | |
| "loss": 0.0762, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0001470108695652174, | |
| "loss": 0.0792, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0001456521739130435, | |
| "loss": 0.0501, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.09637871384620667, | |
| "eval_runtime": 17.4012, | |
| "eval_samples_per_second": 42.181, | |
| "eval_steps_per_second": 5.287, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00014429347826086956, | |
| "loss": 0.0874, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00014293478260869567, | |
| "loss": 0.075, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00014157608695652174, | |
| "loss": 0.1461, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00014021739130434783, | |
| "loss": 0.0853, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.9700272479564033, | |
| "eval_loss": 0.11846118420362473, | |
| "eval_runtime": 17.3926, | |
| "eval_samples_per_second": 42.202, | |
| "eval_steps_per_second": 5.29, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00013885869565217392, | |
| "loss": 0.1182, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001375, | |
| "loss": 0.0839, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001361413043478261, | |
| "loss": 0.0657, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0001347826086956522, | |
| "loss": 0.0362, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.0951201394200325, | |
| "eval_runtime": 17.6244, | |
| "eval_samples_per_second": 41.647, | |
| "eval_steps_per_second": 5.22, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00013342391304347828, | |
| "loss": 0.0846, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00013206521739130434, | |
| "loss": 0.1286, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00013070652173913046, | |
| "loss": 0.0269, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00012934782608695652, | |
| "loss": 0.0898, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.08077488094568253, | |
| "eval_runtime": 17.4813, | |
| "eval_samples_per_second": 41.988, | |
| "eval_steps_per_second": 5.263, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00012798913043478261, | |
| "loss": 0.1056, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0001266304347826087, | |
| "loss": 0.0592, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0001252717391304348, | |
| "loss": 0.064, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00012391304347826086, | |
| "loss": 0.04, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_accuracy": 0.9645776566757494, | |
| "eval_loss": 0.1037047803401947, | |
| "eval_runtime": 18.122, | |
| "eval_samples_per_second": 40.503, | |
| "eval_steps_per_second": 5.077, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00012255434782608698, | |
| "loss": 0.0988, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00012119565217391304, | |
| "loss": 0.0948, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00011983695652173914, | |
| "loss": 0.1029, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00011847826086956522, | |
| "loss": 0.106, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.07200556993484497, | |
| "eval_runtime": 17.4833, | |
| "eval_samples_per_second": 41.983, | |
| "eval_steps_per_second": 5.262, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00011711956521739131, | |
| "loss": 0.0976, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00011576086956521739, | |
| "loss": 0.0603, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00011440217391304349, | |
| "loss": 0.0507, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00011304347826086956, | |
| "loss": 0.0753, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.07421814650297165, | |
| "eval_runtime": 17.6534, | |
| "eval_samples_per_second": 41.578, | |
| "eval_steps_per_second": 5.211, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00011168478260869566, | |
| "loss": 0.0664, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00011032608695652174, | |
| "loss": 0.0628, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00010896739130434783, | |
| "loss": 0.1395, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0001076086956521739, | |
| "loss": 0.0774, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.07968690246343613, | |
| "eval_runtime": 17.474, | |
| "eval_samples_per_second": 42.005, | |
| "eval_steps_per_second": 5.265, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00010625000000000001, | |
| "loss": 0.0545, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0001048913043478261, | |
| "loss": 0.0493, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010353260869565218, | |
| "loss": 0.0773, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010217391304347828, | |
| "loss": 0.0628, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.06992962956428528, | |
| "eval_runtime": 17.9437, | |
| "eval_samples_per_second": 40.906, | |
| "eval_steps_per_second": 5.127, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010081521739130436, | |
| "loss": 0.068, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.945652173913043e-05, | |
| "loss": 0.0489, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.809782608695652e-05, | |
| "loss": 0.1042, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.673913043478261e-05, | |
| "loss": 0.0216, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.09693184494972229, | |
| "eval_runtime": 16.972, | |
| "eval_samples_per_second": 43.248, | |
| "eval_steps_per_second": 5.421, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.538043478260869e-05, | |
| "loss": 0.0751, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.402173913043478e-05, | |
| "loss": 0.0625, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.266304347826087e-05, | |
| "loss": 0.0581, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 9.130434782608696e-05, | |
| "loss": 0.04, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_accuracy": 0.9686648501362398, | |
| "eval_loss": 0.06984598189592361, | |
| "eval_runtime": 17.4344, | |
| "eval_samples_per_second": 42.101, | |
| "eval_steps_per_second": 5.277, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.994565217391305e-05, | |
| "loss": 0.0959, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 8.858695652173914e-05, | |
| "loss": 0.0842, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.722826086956522e-05, | |
| "loss": 0.0556, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 8.586956521739131e-05, | |
| "loss": 0.0372, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.09554506838321686, | |
| "eval_runtime": 17.2543, | |
| "eval_samples_per_second": 42.54, | |
| "eval_steps_per_second": 5.332, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 8.45108695652174e-05, | |
| "loss": 0.1344, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 8.315217391304349e-05, | |
| "loss": 0.02, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 8.179347826086957e-05, | |
| "loss": 0.0706, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 8.043478260869566e-05, | |
| "loss": 0.0609, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_accuracy": 0.9700272479564033, | |
| "eval_loss": 0.06672107428312302, | |
| "eval_runtime": 17.3439, | |
| "eval_samples_per_second": 42.32, | |
| "eval_steps_per_second": 5.304, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.907608695652175e-05, | |
| "loss": 0.0986, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 7.771739130434783e-05, | |
| "loss": 0.0523, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.635869565217392e-05, | |
| "loss": 0.0652, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0375, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.07068129628896713, | |
| "eval_runtime": 17.3031, | |
| "eval_samples_per_second": 42.42, | |
| "eval_steps_per_second": 5.317, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.364130434782608e-05, | |
| "loss": 0.0506, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.228260869565217e-05, | |
| "loss": 0.0764, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.092391304347826e-05, | |
| "loss": 0.0622, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.956521739130436e-05, | |
| "loss": 0.0532, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.06182615086436272, | |
| "eval_runtime": 17.2684, | |
| "eval_samples_per_second": 42.505, | |
| "eval_steps_per_second": 5.328, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.820652173913043e-05, | |
| "loss": 0.0462, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.684782608695652e-05, | |
| "loss": 0.0477, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 6.548913043478261e-05, | |
| "loss": 0.0526, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 6.413043478260869e-05, | |
| "loss": 0.092, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.058743953704833984, | |
| "eval_runtime": 17.0643, | |
| "eval_samples_per_second": 43.014, | |
| "eval_steps_per_second": 5.391, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 6.277173913043478e-05, | |
| "loss": 0.0704, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 6.141304347826087e-05, | |
| "loss": 0.0301, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 6.0054347826086955e-05, | |
| "loss": 0.0788, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 5.869565217391305e-05, | |
| "loss": 0.0742, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.06040079519152641, | |
| "eval_runtime": 17.6675, | |
| "eval_samples_per_second": 41.545, | |
| "eval_steps_per_second": 5.207, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.7336956521739136e-05, | |
| "loss": 0.0658, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 5.5978260869565226e-05, | |
| "loss": 0.0564, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 5.461956521739131e-05, | |
| "loss": 0.0486, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 5.32608695652174e-05, | |
| "loss": 0.0443, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.11983449757099152, | |
| "eval_runtime": 17.2197, | |
| "eval_samples_per_second": 42.626, | |
| "eval_steps_per_second": 5.343, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.1902173913043484e-05, | |
| "loss": 0.0397, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.054347826086957e-05, | |
| "loss": 0.0818, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.918478260869566e-05, | |
| "loss": 0.0492, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.782608695652174e-05, | |
| "loss": 0.062, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.06326533854007721, | |
| "eval_runtime": 17.0684, | |
| "eval_samples_per_second": 43.003, | |
| "eval_steps_per_second": 5.39, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 4.646739130434783e-05, | |
| "loss": 0.0414, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 4.5108695652173916e-05, | |
| "loss": 0.0331, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.0531, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 4.239130434782609e-05, | |
| "loss": 0.0708, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.07502922415733337, | |
| "eval_runtime": 17.6357, | |
| "eval_samples_per_second": 41.62, | |
| "eval_steps_per_second": 5.217, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 4.1032608695652174e-05, | |
| "loss": 0.0507, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.9673913043478264e-05, | |
| "loss": 0.0607, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.831521739130435e-05, | |
| "loss": 0.0374, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 3.695652173913043e-05, | |
| "loss": 0.0252, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.08786644786596298, | |
| "eval_runtime": 17.4164, | |
| "eval_samples_per_second": 42.144, | |
| "eval_steps_per_second": 5.282, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 3.559782608695653e-05, | |
| "loss": 0.0502, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.423913043478261e-05, | |
| "loss": 0.0513, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 3.2880434782608696e-05, | |
| "loss": 0.0698, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.152173913043479e-05, | |
| "loss": 0.038, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.07282000035047531, | |
| "eval_runtime": 17.6309, | |
| "eval_samples_per_second": 41.631, | |
| "eval_steps_per_second": 5.218, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 3.016304347826087e-05, | |
| "loss": 0.0707, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2.8804347826086957e-05, | |
| "loss": 0.0639, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2.7445652173913044e-05, | |
| "loss": 0.0647, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2.608695652173913e-05, | |
| "loss": 0.0348, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.07391868531703949, | |
| "eval_runtime": 17.5666, | |
| "eval_samples_per_second": 41.784, | |
| "eval_steps_per_second": 5.237, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 2.472826086956522e-05, | |
| "loss": 0.0471, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2.3369565217391306e-05, | |
| "loss": 0.0859, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 2.2010869565217393e-05, | |
| "loss": 0.0558, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 2.065217391304348e-05, | |
| "loss": 0.0348, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.09225168824195862, | |
| "eval_runtime": 17.7535, | |
| "eval_samples_per_second": 41.344, | |
| "eval_steps_per_second": 5.182, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.9293478260869567e-05, | |
| "loss": 0.0205, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.793478260869565e-05, | |
| "loss": 0.051, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.6576086956521738e-05, | |
| "loss": 0.0419, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.5217391304347828e-05, | |
| "loss": 0.019, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.08419564366340637, | |
| "eval_runtime": 17.5834, | |
| "eval_samples_per_second": 41.744, | |
| "eval_steps_per_second": 5.232, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.3858695652173914e-05, | |
| "loss": 0.0473, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.0316, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 1.1141304347826088e-05, | |
| "loss": 0.0301, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 9.782608695652175e-06, | |
| "loss": 0.0181, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.09280063211917877, | |
| "eval_runtime": 17.9174, | |
| "eval_samples_per_second": 40.966, | |
| "eval_steps_per_second": 5.135, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 8.423913043478262e-06, | |
| "loss": 0.0314, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 7.065217391304347e-06, | |
| "loss": 0.0606, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 5.706521739130435e-06, | |
| "loss": 0.0453, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 4.347826086956522e-06, | |
| "loss": 0.0496, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "eval_accuracy": 0.9713896457765667, | |
| "eval_loss": 0.08846529573202133, | |
| "eval_runtime": 17.2944, | |
| "eval_samples_per_second": 42.442, | |
| "eval_steps_per_second": 5.32, | |
| "step": 1440 | |
| } | |
| ], | |
| "max_steps": 1472, | |
| "num_train_epochs": 4, | |
| "total_flos": 1.781944272047278e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |