| { | |
| "best_metric": 0.20915627479553223, | |
| "best_model_checkpoint": "./vit-large-binary-isic-sharpened-patch-32/checkpoint-2100", | |
| "epoch": 4.0, | |
| "global_step": 4328, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019953789279112755, | |
| "loss": 0.5991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001990757855822551, | |
| "loss": 0.4327, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019861367837338263, | |
| "loss": 0.3795, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019815157116451017, | |
| "loss": 0.3665, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001976894639556377, | |
| "loss": 0.6357, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019722735674676528, | |
| "loss": 0.5116, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001967652495378928, | |
| "loss": 0.3421, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019630314232902034, | |
| "loss": 0.3856, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019584103512014788, | |
| "loss": 0.3333, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019537892791127544, | |
| "loss": 0.3437, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.8412352639671963, | |
| "eval_f1": 0.8412352639671963, | |
| "eval_loss": 0.3367173373699188, | |
| "eval_precision": 0.8412352639671963, | |
| "eval_recall": 0.8412352639671963, | |
| "eval_runtime": 82.5501, | |
| "eval_samples_per_second": 94.537, | |
| "eval_steps_per_second": 11.823, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019491682070240296, | |
| "loss": 0.321, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001944547134935305, | |
| "loss": 0.2976, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019399260628465804, | |
| "loss": 0.448, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001935304990757856, | |
| "loss": 0.3983, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019306839186691312, | |
| "loss": 0.3479, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001926524953789279, | |
| "loss": 0.3198, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019219038817005547, | |
| "loss": 0.4198, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000191728280961183, | |
| "loss": 0.2527, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019126617375231055, | |
| "loss": 0.3548, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001908040665434381, | |
| "loss": 0.3702, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.858534085084572, | |
| "eval_f1": 0.8585340850845719, | |
| "eval_loss": 0.3093763589859009, | |
| "eval_precision": 0.858534085084572, | |
| "eval_recall": 0.858534085084572, | |
| "eval_runtime": 83.0128, | |
| "eval_samples_per_second": 94.01, | |
| "eval_steps_per_second": 11.757, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019034195933456563, | |
| "loss": 0.3353, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00018987985212569317, | |
| "loss": 0.3458, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001894177449168207, | |
| "loss": 0.2603, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00018895563770794825, | |
| "loss": 0.2883, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0001884935304990758, | |
| "loss": 0.3665, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00018803142329020333, | |
| "loss": 0.2682, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00018756931608133087, | |
| "loss": 0.3169, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00018710720887245841, | |
| "loss": 0.3047, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00018664510166358596, | |
| "loss": 0.3223, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001861829944547135, | |
| "loss": 0.2693, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.8007432086109687, | |
| "eval_f1": 0.8007432086109687, | |
| "eval_loss": 0.4360676109790802, | |
| "eval_precision": 0.8007432086109687, | |
| "eval_recall": 0.8007432086109687, | |
| "eval_runtime": 83.0367, | |
| "eval_samples_per_second": 93.983, | |
| "eval_steps_per_second": 11.754, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00018572088724584104, | |
| "loss": 0.4223, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001852587800369686, | |
| "loss": 0.2914, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00018479667282809612, | |
| "loss": 0.3506, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00018433456561922366, | |
| "loss": 0.2313, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001838724584103512, | |
| "loss": 0.2737, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00018341035120147877, | |
| "loss": 0.3939, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00018294824399260628, | |
| "loss": 0.2264, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00018248613678373382, | |
| "loss": 0.2714, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001820240295748614, | |
| "loss": 0.418, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00018156192236598893, | |
| "loss": 0.3183, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.8643003587903639, | |
| "eval_f1": 0.864300358790364, | |
| "eval_loss": 0.2955211102962494, | |
| "eval_precision": 0.8643003587903639, | |
| "eval_recall": 0.8643003587903639, | |
| "eval_runtime": 82.9777, | |
| "eval_samples_per_second": 94.049, | |
| "eval_steps_per_second": 11.762, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00018109981515711647, | |
| "loss": 0.2969, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018063770794824399, | |
| "loss": 0.2474, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018017560073937155, | |
| "loss": 0.309, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001797134935304991, | |
| "loss": 0.2835, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017925138632162663, | |
| "loss": 0.2011, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017878927911275415, | |
| "loss": 0.301, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017832717190388172, | |
| "loss": 0.2318, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00017786506469500926, | |
| "loss": 0.2671, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001774029574861368, | |
| "loss": 0.2451, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00017694085027726434, | |
| "loss": 0.2688, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.8603280369041517, | |
| "eval_f1": 0.8603280369041517, | |
| "eval_loss": 0.30635467171669006, | |
| "eval_precision": 0.8603280369041517, | |
| "eval_recall": 0.8603280369041517, | |
| "eval_runtime": 82.9244, | |
| "eval_samples_per_second": 94.11, | |
| "eval_steps_per_second": 11.77, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00017647874306839188, | |
| "loss": 0.2145, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00017601663585951942, | |
| "loss": 0.4501, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00017555452865064696, | |
| "loss": 0.2039, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001750924214417745, | |
| "loss": 0.3418, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00017463031423290204, | |
| "loss": 0.2178, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00017416820702402958, | |
| "loss": 0.2159, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00017370609981515712, | |
| "loss": 0.2128, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0001732439926062847, | |
| "loss": 0.2741, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0001727818853974122, | |
| "loss": 0.2614, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00017231977818853975, | |
| "loss": 0.2507, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.8329062019477191, | |
| "eval_f1": 0.8329062019477191, | |
| "eval_loss": 0.3556201756000519, | |
| "eval_precision": 0.8329062019477191, | |
| "eval_recall": 0.8329062019477191, | |
| "eval_runtime": 83.089, | |
| "eval_samples_per_second": 93.923, | |
| "eval_steps_per_second": 11.746, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00017185767097966729, | |
| "loss": 0.3248, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00017139556377079485, | |
| "loss": 0.3201, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00017093345656192237, | |
| "loss": 0.2245, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0001704713493530499, | |
| "loss": 0.3081, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00017000924214417745, | |
| "loss": 0.1629, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00016954713493530502, | |
| "loss": 0.2981, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00016908502772643253, | |
| "loss": 0.224, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00016862292051756007, | |
| "loss": 0.2895, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00016816081330868764, | |
| "loss": 0.3021, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00016769870609981518, | |
| "loss": 0.203, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.8432854946181445, | |
| "eval_f1": 0.8432854946181444, | |
| "eval_loss": 0.31337106227874756, | |
| "eval_precision": 0.8432854946181445, | |
| "eval_recall": 0.8432854946181445, | |
| "eval_runtime": 82.6906, | |
| "eval_samples_per_second": 94.376, | |
| "eval_steps_per_second": 11.803, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0001672365988909427, | |
| "loss": 0.2444, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00016677449168207023, | |
| "loss": 0.3056, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0001663123844731978, | |
| "loss": 0.2116, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00016585027726432534, | |
| "loss": 0.2301, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00016538817005545286, | |
| "loss": 0.195, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001649260628465804, | |
| "loss": 0.4002, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00016446395563770796, | |
| "loss": 0.1884, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001640018484288355, | |
| "loss": 0.197, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00016353974121996305, | |
| "loss": 0.3021, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0001630776340110906, | |
| "loss": 0.2315, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.8855715017939518, | |
| "eval_f1": 0.8855715017939518, | |
| "eval_loss": 0.25248605012893677, | |
| "eval_precision": 0.8855715017939518, | |
| "eval_recall": 0.8855715017939518, | |
| "eval_runtime": 83.3186, | |
| "eval_samples_per_second": 93.665, | |
| "eval_steps_per_second": 11.714, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00016261552680221813, | |
| "loss": 0.223, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00016215341959334567, | |
| "loss": 0.1829, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0001616913123844732, | |
| "loss": 0.2863, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00016122920517560075, | |
| "loss": 0.2746, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001607670979667283, | |
| "loss": 0.1964, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00016030499075785583, | |
| "loss": 0.1948, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00015984288354898337, | |
| "loss": 0.2401, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0001593807763401109, | |
| "loss": 0.2701, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00015891866913123845, | |
| "loss": 0.2135, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.000158456561922366, | |
| "loss": 0.3527, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.8731419784725781, | |
| "eval_f1": 0.8731419784725781, | |
| "eval_loss": 0.2814614772796631, | |
| "eval_precision": 0.8731419784725781, | |
| "eval_recall": 0.8731419784725781, | |
| "eval_runtime": 83.0866, | |
| "eval_samples_per_second": 93.926, | |
| "eval_steps_per_second": 11.747, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00015799445471349353, | |
| "loss": 0.175, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00015753234750462108, | |
| "loss": 0.2016, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00015707024029574862, | |
| "loss": 0.2683, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00015660813308687616, | |
| "loss": 0.2227, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0001561460258780037, | |
| "loss": 0.2204, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00015568391866913127, | |
| "loss": 0.1745, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00015522181146025878, | |
| "loss": 0.1872, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00015475970425138632, | |
| "loss": 0.2944, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0001542975970425139, | |
| "loss": 0.2532, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00015383548983364143, | |
| "loss": 0.292, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.8534085084572014, | |
| "eval_f1": 0.8534085084572014, | |
| "eval_loss": 0.38787639141082764, | |
| "eval_precision": 0.8534085084572014, | |
| "eval_recall": 0.8534085084572014, | |
| "eval_runtime": 84.131, | |
| "eval_samples_per_second": 92.76, | |
| "eval_steps_per_second": 11.601, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00015337338262476894, | |
| "loss": 0.2367, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00015291127541589648, | |
| "loss": 0.1986, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00015244916820702405, | |
| "loss": 0.216, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0001519870609981516, | |
| "loss": 0.1958, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0001515249537892791, | |
| "loss": 0.1846, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015106284658040665, | |
| "loss": 0.2404, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015060073937153421, | |
| "loss": 0.2018, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00015013863216266175, | |
| "loss": 0.2524, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00014967652495378927, | |
| "loss": 0.1601, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00014921441774491684, | |
| "loss": 0.1342, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.8873654536135315, | |
| "eval_f1": 0.8873654536135316, | |
| "eval_loss": 0.2927275002002716, | |
| "eval_precision": 0.8873654536135315, | |
| "eval_recall": 0.8873654536135315, | |
| "eval_runtime": 83.3209, | |
| "eval_samples_per_second": 93.662, | |
| "eval_steps_per_second": 11.714, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00014875231053604438, | |
| "loss": 0.1838, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00014829020332717192, | |
| "loss": 0.2187, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00014782809611829943, | |
| "loss": 0.1682, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.000147365988909427, | |
| "loss": 0.1609, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00014690388170055454, | |
| "loss": 0.2879, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014644177449168208, | |
| "loss": 0.1388, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014597966728280962, | |
| "loss": 0.1733, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00014551756007393716, | |
| "loss": 0.1821, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001450554528650647, | |
| "loss": 0.1493, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00014459334565619224, | |
| "loss": 0.1571, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_accuracy": 0.8912096360840595, | |
| "eval_f1": 0.8912096360840595, | |
| "eval_loss": 0.2560170888900757, | |
| "eval_precision": 0.8912096360840595, | |
| "eval_recall": 0.8912096360840595, | |
| "eval_runtime": 84.2134, | |
| "eval_samples_per_second": 92.669, | |
| "eval_steps_per_second": 11.59, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00014413123844731978, | |
| "loss": 0.2068, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00014366913123844732, | |
| "loss": 0.1672, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00014320702402957487, | |
| "loss": 0.1269, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001427449168207024, | |
| "loss": 0.0931, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00014228280961182995, | |
| "loss": 0.1773, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001418207024029575, | |
| "loss": 0.1294, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00014135859519408503, | |
| "loss": 0.1321, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00014089648798521257, | |
| "loss": 0.1243, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00014043438077634014, | |
| "loss": 0.1342, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00013997227356746765, | |
| "loss": 0.1787, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.8789082521783701, | |
| "eval_f1": 0.8789082521783701, | |
| "eval_loss": 0.32453852891921997, | |
| "eval_precision": 0.8789082521783701, | |
| "eval_recall": 0.8789082521783701, | |
| "eval_runtime": 83.7885, | |
| "eval_samples_per_second": 93.139, | |
| "eval_steps_per_second": 11.648, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0001395101663585952, | |
| "loss": 0.2326, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00013904805914972273, | |
| "loss": 0.195, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001385859519408503, | |
| "loss": 0.0794, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00013812384473197784, | |
| "loss": 0.1913, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00013766173752310535, | |
| "loss": 0.0852, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0001371996303142329, | |
| "loss": 0.1181, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00013673752310536046, | |
| "loss": 0.1172, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.000136275415896488, | |
| "loss": 0.1908, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00013581330868761552, | |
| "loss": 0.0785, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00013535120147874308, | |
| "loss": 0.1757, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_accuracy": 0.8719887237314198, | |
| "eval_f1": 0.8719887237314198, | |
| "eval_loss": 0.3308282792568207, | |
| "eval_precision": 0.8719887237314198, | |
| "eval_recall": 0.8719887237314198, | |
| "eval_runtime": 84.0924, | |
| "eval_samples_per_second": 92.803, | |
| "eval_steps_per_second": 11.606, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00013488909426987063, | |
| "loss": 0.1575, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00013442698706099817, | |
| "loss": 0.135, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00013396487985212568, | |
| "loss": 0.2077, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00013350277264325325, | |
| "loss": 0.1352, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0001330406654343808, | |
| "loss": 0.2521, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00013257855822550833, | |
| "loss": 0.1678, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00013211645101663584, | |
| "loss": 0.1433, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0001316543438077634, | |
| "loss": 0.1419, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00013119223659889095, | |
| "loss": 0.152, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0001307301293900185, | |
| "loss": 0.1867, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_accuracy": 0.8876217324449001, | |
| "eval_f1": 0.8876217324449001, | |
| "eval_loss": 0.2715943157672882, | |
| "eval_precision": 0.8876217324449001, | |
| "eval_recall": 0.8876217324449001, | |
| "eval_runtime": 83.5575, | |
| "eval_samples_per_second": 93.397, | |
| "eval_steps_per_second": 11.681, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00013026802218114603, | |
| "loss": 0.1407, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00012980591497227357, | |
| "loss": 0.1583, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00012934380776340111, | |
| "loss": 0.1489, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00012888170055452866, | |
| "loss": 0.1227, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0001284195933456562, | |
| "loss": 0.2175, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00012795748613678374, | |
| "loss": 0.1076, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00012749537892791128, | |
| "loss": 0.0623, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00012703327171903882, | |
| "loss": 0.0974, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00012657116451016639, | |
| "loss": 0.0827, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001261090573012939, | |
| "loss": 0.124, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_accuracy": 0.8744233726294208, | |
| "eval_f1": 0.8744233726294208, | |
| "eval_loss": 0.36631861329078674, | |
| "eval_precision": 0.8744233726294208, | |
| "eval_recall": 0.8744233726294208, | |
| "eval_runtime": 83.8843, | |
| "eval_samples_per_second": 93.033, | |
| "eval_steps_per_second": 11.635, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00012564695009242144, | |
| "loss": 0.1379, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00012518484288354898, | |
| "loss": 0.1139, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00012472273567467655, | |
| "loss": 0.1972, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00012426062846580406, | |
| "loss": 0.1286, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0001237985212569316, | |
| "loss": 0.1683, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00012333641404805914, | |
| "loss": 0.1258, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0001228743068391867, | |
| "loss": 0.2343, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00012241219963031423, | |
| "loss": 0.081, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00012195009242144178, | |
| "loss": 0.1306, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00012148798521256932, | |
| "loss": 0.082, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_accuracy": 0.9033828805740646, | |
| "eval_f1": 0.9033828805740646, | |
| "eval_loss": 0.27925997972488403, | |
| "eval_precision": 0.9033828805740646, | |
| "eval_recall": 0.9033828805740646, | |
| "eval_runtime": 83.9762, | |
| "eval_samples_per_second": 92.931, | |
| "eval_steps_per_second": 11.622, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00012102587800369687, | |
| "loss": 0.0851, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00012056377079482442, | |
| "loss": 0.1024, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00012010166358595194, | |
| "loss": 0.1428, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00011963955637707948, | |
| "loss": 0.1423, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00011917744916820704, | |
| "loss": 0.1106, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00011871534195933458, | |
| "loss": 0.2542, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0001182532347504621, | |
| "loss": 0.1781, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00011779112754158965, | |
| "loss": 0.1283, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0001173290203327172, | |
| "loss": 0.1128, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00011686691312384474, | |
| "loss": 0.1365, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_accuracy": 0.9077396207073296, | |
| "eval_f1": 0.9077396207073296, | |
| "eval_loss": 0.23988166451454163, | |
| "eval_precision": 0.9077396207073296, | |
| "eval_recall": 0.9077396207073296, | |
| "eval_runtime": 83.349, | |
| "eval_samples_per_second": 93.63, | |
| "eval_steps_per_second": 11.71, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00011640480591497227, | |
| "loss": 0.103, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00011594269870609982, | |
| "loss": 0.1121, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00011548059149722736, | |
| "loss": 0.0994, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0001150184842883549, | |
| "loss": 0.0895, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00011455637707948243, | |
| "loss": 0.2364, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00011409426987060999, | |
| "loss": 0.0949, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00011363216266173753, | |
| "loss": 0.0659, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00011317005545286508, | |
| "loss": 0.1123, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00011270794824399262, | |
| "loss": 0.1497, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00011224584103512015, | |
| "loss": 0.0998, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_accuracy": 0.8900563813429011, | |
| "eval_f1": 0.8900563813429011, | |
| "eval_loss": 0.33613133430480957, | |
| "eval_precision": 0.8900563813429011, | |
| "eval_recall": 0.8900563813429011, | |
| "eval_runtime": 84.1161, | |
| "eval_samples_per_second": 92.777, | |
| "eval_steps_per_second": 11.603, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00011178373382624769, | |
| "loss": 0.1725, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00011132162661737524, | |
| "loss": 0.1393, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00011085951940850278, | |
| "loss": 0.1611, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00011039741219963031, | |
| "loss": 0.0976, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00010993530499075787, | |
| "loss": 0.1349, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0001094731977818854, | |
| "loss": 0.0715, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00010901109057301295, | |
| "loss": 0.0771, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00010854898336414047, | |
| "loss": 0.1318, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00010808687615526803, | |
| "loss": 0.0837, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00010762476894639557, | |
| "loss": 0.0748, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_accuracy": 0.8959507944643772, | |
| "eval_f1": 0.8959507944643772, | |
| "eval_loss": 0.3239482045173645, | |
| "eval_precision": 0.8959507944643772, | |
| "eval_recall": 0.8959507944643772, | |
| "eval_runtime": 83.2562, | |
| "eval_samples_per_second": 93.735, | |
| "eval_steps_per_second": 11.723, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00010716266173752312, | |
| "loss": 0.06, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00010670055452865064, | |
| "loss": 0.1431, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00010623844731977819, | |
| "loss": 0.0771, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00010577634011090573, | |
| "loss": 0.095, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00010531423290203329, | |
| "loss": 0.0845, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00010485212569316081, | |
| "loss": 0.0701, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00010439001848428835, | |
| "loss": 0.118, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0001039279112754159, | |
| "loss": 0.1539, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010346580406654345, | |
| "loss": 0.1065, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010300369685767099, | |
| "loss": 0.1163, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.9201691440287032, | |
| "eval_f1": 0.9201691440287032, | |
| "eval_loss": 0.20915627479553223, | |
| "eval_precision": 0.9201691440287032, | |
| "eval_recall": 0.9201691440287032, | |
| "eval_runtime": 84.6818, | |
| "eval_samples_per_second": 92.157, | |
| "eval_steps_per_second": 11.526, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00010254158964879852, | |
| "loss": 0.1373, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010207948243992607, | |
| "loss": 0.1621, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010161737523105361, | |
| "loss": 0.0703, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010115526802218117, | |
| "loss": 0.0391, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00010069316081330868, | |
| "loss": 0.1049, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010023105360443623, | |
| "loss": 0.0779, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.976894639556378e-05, | |
| "loss": 0.0339, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.930683918669132e-05, | |
| "loss": 0.0697, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.884473197781886e-05, | |
| "loss": 0.0602, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.83826247689464e-05, | |
| "loss": 0.0604, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.9138903126601743, | |
| "eval_f1": 0.9138903126601743, | |
| "eval_loss": 0.305562824010849, | |
| "eval_precision": 0.9138903126601743, | |
| "eval_recall": 0.9138903126601743, | |
| "eval_runtime": 83.4162, | |
| "eval_samples_per_second": 93.555, | |
| "eval_steps_per_second": 11.7, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.792051756007394e-05, | |
| "loss": 0.0743, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.745841035120148e-05, | |
| "loss": 0.0233, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.699630314232902e-05, | |
| "loss": 0.0969, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.653419593345656e-05, | |
| "loss": 0.0558, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.607208872458411e-05, | |
| "loss": 0.0515, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.560998151571166e-05, | |
| "loss": 0.028, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.51478743068392e-05, | |
| "loss": 0.0946, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 9.468576709796674e-05, | |
| "loss": 0.0633, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.422365988909428e-05, | |
| "loss": 0.0892, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.376155268022182e-05, | |
| "loss": 0.0792, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.9070989236289082, | |
| "eval_f1": 0.9070989236289082, | |
| "eval_loss": 0.2880270481109619, | |
| "eval_precision": 0.9070989236289082, | |
| "eval_recall": 0.9070989236289082, | |
| "eval_runtime": 83.916, | |
| "eval_samples_per_second": 92.998, | |
| "eval_steps_per_second": 11.631, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.329944547134936e-05, | |
| "loss": 0.0367, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.28373382624769e-05, | |
| "loss": 0.013, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.237523105360444e-05, | |
| "loss": 0.0598, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 9.195933456561923e-05, | |
| "loss": 0.0785, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 9.149722735674677e-05, | |
| "loss": 0.023, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 9.103512014787431e-05, | |
| "loss": 0.0054, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 9.057301293900185e-05, | |
| "loss": 0.052, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.01109057301294e-05, | |
| "loss": 0.0869, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.964879852125694e-05, | |
| "loss": 0.0113, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.918669131238448e-05, | |
| "loss": 0.0749, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_accuracy": 0.906970784213224, | |
| "eval_f1": 0.9069707842132241, | |
| "eval_loss": 0.30151692032814026, | |
| "eval_precision": 0.906970784213224, | |
| "eval_recall": 0.906970784213224, | |
| "eval_runtime": 84.0279, | |
| "eval_samples_per_second": 92.874, | |
| "eval_steps_per_second": 11.615, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 8.872458410351202e-05, | |
| "loss": 0.0341, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 8.826247689463956e-05, | |
| "loss": 0.0512, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 8.78003696857671e-05, | |
| "loss": 0.0713, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.733826247689464e-05, | |
| "loss": 0.0573, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.687615526802218e-05, | |
| "loss": 0.0159, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 8.641404805914972e-05, | |
| "loss": 0.0637, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 8.595194085027726e-05, | |
| "loss": 0.0437, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 8.548983364140482e-05, | |
| "loss": 0.0237, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 8.502772643253236e-05, | |
| "loss": 0.0105, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 8.45656192236599e-05, | |
| "loss": 0.0032, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_accuracy": 0.9090210148641722, | |
| "eval_f1": 0.9090210148641721, | |
| "eval_loss": 0.36854496598243713, | |
| "eval_precision": 0.9090210148641722, | |
| "eval_recall": 0.9090210148641722, | |
| "eval_runtime": 84.1598, | |
| "eval_samples_per_second": 92.728, | |
| "eval_steps_per_second": 11.597, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 8.410351201478744e-05, | |
| "loss": 0.083, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 8.364140480591498e-05, | |
| "loss": 0.0377, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 8.317929759704252e-05, | |
| "loss": 0.0618, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 8.271719038817006e-05, | |
| "loss": 0.021, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 8.22550831792976e-05, | |
| "loss": 0.0177, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 8.179297597042514e-05, | |
| "loss": 0.0029, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.133086876155268e-05, | |
| "loss": 0.011, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.086876155268022e-05, | |
| "loss": 0.0613, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 8.040665434380776e-05, | |
| "loss": 0.0252, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 7.99445471349353e-05, | |
| "loss": 0.1038, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.907483341875961, | |
| "eval_f1": 0.907483341875961, | |
| "eval_loss": 0.35386165976524353, | |
| "eval_precision": 0.907483341875961, | |
| "eval_recall": 0.907483341875961, | |
| "eval_runtime": 84.079, | |
| "eval_samples_per_second": 92.818, | |
| "eval_steps_per_second": 11.608, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 7.948243992606285e-05, | |
| "loss": 0.0483, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.902033271719039e-05, | |
| "loss": 0.0767, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 7.855822550831793e-05, | |
| "loss": 0.0037, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.809611829944548e-05, | |
| "loss": 0.0589, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 7.763401109057301e-05, | |
| "loss": 0.0144, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.717190388170056e-05, | |
| "loss": 0.0331, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.67097966728281e-05, | |
| "loss": 0.0436, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.624768946395564e-05, | |
| "loss": 0.0498, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.578558225508319e-05, | |
| "loss": 0.0932, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.532347504621073e-05, | |
| "loss": 0.0474, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.9151717068170169, | |
| "eval_f1": 0.9151717068170169, | |
| "eval_loss": 0.3220309615135193, | |
| "eval_precision": 0.9151717068170169, | |
| "eval_recall": 0.9151717068170169, | |
| "eval_runtime": 85.2146, | |
| "eval_samples_per_second": 91.581, | |
| "eval_steps_per_second": 11.453, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.486136783733827e-05, | |
| "loss": 0.1098, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 7.439926062846581e-05, | |
| "loss": 0.0917, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.393715341959335e-05, | |
| "loss": 0.0154, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.347504621072089e-05, | |
| "loss": 0.0568, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.301293900184843e-05, | |
| "loss": 0.0462, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.255083179297597e-05, | |
| "loss": 0.0224, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.208872458410351e-05, | |
| "loss": 0.0381, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.162661737523105e-05, | |
| "loss": 0.018, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.11645101663586e-05, | |
| "loss": 0.082, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.070240295748613e-05, | |
| "loss": 0.0376, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_accuracy": 0.9202972834443875, | |
| "eval_f1": 0.9202972834443875, | |
| "eval_loss": 0.2925526201725006, | |
| "eval_precision": 0.9202972834443875, | |
| "eval_recall": 0.9202972834443875, | |
| "eval_runtime": 83.7261, | |
| "eval_samples_per_second": 93.209, | |
| "eval_steps_per_second": 11.657, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.024029574861369e-05, | |
| "loss": 0.0078, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.977818853974121e-05, | |
| "loss": 0.0187, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.931608133086877e-05, | |
| "loss": 0.0055, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.885397412199631e-05, | |
| "loss": 0.0381, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.839186691312385e-05, | |
| "loss": 0.0197, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.792975970425139e-05, | |
| "loss": 0.0816, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.746765249537893e-05, | |
| "loss": 0.0145, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.700554528650647e-05, | |
| "loss": 0.0121, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.654343807763401e-05, | |
| "loss": 0.0478, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 6.608133086876155e-05, | |
| "loss": 0.0424, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_accuracy": 0.9064582265504869, | |
| "eval_f1": 0.9064582265504869, | |
| "eval_loss": 0.34626173973083496, | |
| "eval_precision": 0.9064582265504869, | |
| "eval_recall": 0.9064582265504869, | |
| "eval_runtime": 83.4217, | |
| "eval_samples_per_second": 93.549, | |
| "eval_steps_per_second": 11.7, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 6.56192236598891e-05, | |
| "loss": 0.1154, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 6.515711645101664e-05, | |
| "loss": 0.076, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 6.469500924214418e-05, | |
| "loss": 0.0109, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 6.423290203327173e-05, | |
| "loss": 0.0501, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 6.377079482439926e-05, | |
| "loss": 0.0127, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 6.330868761552681e-05, | |
| "loss": 0.0428, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 6.284658040665434e-05, | |
| "loss": 0.0197, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 6.23844731977819e-05, | |
| "loss": 0.0333, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 6.192236598890942e-05, | |
| "loss": 0.0077, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 6.146025878003697e-05, | |
| "loss": 0.0408, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_accuracy": 0.9263198359815479, | |
| "eval_f1": 0.9263198359815479, | |
| "eval_loss": 0.27719464898109436, | |
| "eval_precision": 0.9263198359815479, | |
| "eval_recall": 0.9263198359815479, | |
| "eval_runtime": 83.7232, | |
| "eval_samples_per_second": 93.212, | |
| "eval_steps_per_second": 11.657, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 6.099815157116451e-05, | |
| "loss": 0.0501, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 6.0536044362292056e-05, | |
| "loss": 0.0073, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 6.0073937153419604e-05, | |
| "loss": 0.0268, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 5.961182994454714e-05, | |
| "loss": 0.0326, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 5.9149722735674685e-05, | |
| "loss": 0.0356, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 5.868761552680222e-05, | |
| "loss": 0.0098, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 5.8225508317929767e-05, | |
| "loss": 0.0115, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.77634011090573e-05, | |
| "loss": 0.0103, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.730129390018485e-05, | |
| "loss": 0.0218, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5.683918669131238e-05, | |
| "loss": 0.0467, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_accuracy": 0.9227319323423885, | |
| "eval_f1": 0.9227319323423884, | |
| "eval_loss": 0.29630914330482483, | |
| "eval_precision": 0.9227319323423885, | |
| "eval_recall": 0.9227319323423885, | |
| "eval_runtime": 84.2619, | |
| "eval_samples_per_second": 92.616, | |
| "eval_steps_per_second": 11.583, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5.637707948243993e-05, | |
| "loss": 0.0856, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 5.591497227356747e-05, | |
| "loss": 0.059, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 5.545286506469501e-05, | |
| "loss": 0.0591, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 5.499075785582255e-05, | |
| "loss": 0.0318, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 5.45286506469501e-05, | |
| "loss": 0.0486, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.406654343807763e-05, | |
| "loss": 0.0297, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 5.360443622920518e-05, | |
| "loss": 0.0073, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5.3142329020332715e-05, | |
| "loss": 0.0165, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.268022181146026e-05, | |
| "loss": 0.0465, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.2218114602587796e-05, | |
| "loss": 0.0083, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.9202972834443875, | |
| "eval_f1": 0.9202972834443875, | |
| "eval_loss": 0.2971321642398834, | |
| "eval_precision": 0.9202972834443875, | |
| "eval_recall": 0.9202972834443875, | |
| "eval_runtime": 84.4051, | |
| "eval_samples_per_second": 92.459, | |
| "eval_steps_per_second": 11.563, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 5.1756007393715344e-05, | |
| "loss": 0.0372, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 5.129390018484289e-05, | |
| "loss": 0.0277, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.0831792975970425e-05, | |
| "loss": 0.0114, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.036968576709797e-05, | |
| "loss": 0.0349, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.9907578558225506e-05, | |
| "loss": 0.0073, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.9445471349353054e-05, | |
| "loss": 0.0186, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.8983364140480595e-05, | |
| "loss": 0.0026, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.8521256931608135e-05, | |
| "loss": 0.0018, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.8059149722735676e-05, | |
| "loss": 0.0057, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 4.759704251386322e-05, | |
| "loss": 0.0165, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_accuracy": 0.9256791389031266, | |
| "eval_f1": 0.9256791389031266, | |
| "eval_loss": 0.31615641713142395, | |
| "eval_precision": 0.9256791389031266, | |
| "eval_recall": 0.9256791389031266, | |
| "eval_runtime": 83.9772, | |
| "eval_samples_per_second": 92.93, | |
| "eval_steps_per_second": 11.622, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 4.7134935304990764e-05, | |
| "loss": 0.0016, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 4.6672828096118305e-05, | |
| "loss": 0.0016, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 4.6210720887245846e-05, | |
| "loss": 0.003, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 4.5748613678373387e-05, | |
| "loss": 0.0017, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 4.528650646950093e-05, | |
| "loss": 0.0117, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.482439926062847e-05, | |
| "loss": 0.0061, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.436229205175601e-05, | |
| "loss": 0.0011, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 4.390018484288355e-05, | |
| "loss": 0.0013, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 4.343807763401109e-05, | |
| "loss": 0.002, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 4.297597042513863e-05, | |
| "loss": 0.0023, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_accuracy": 0.9267042542286007, | |
| "eval_f1": 0.9267042542286007, | |
| "eval_loss": 0.31474342942237854, | |
| "eval_precision": 0.9267042542286007, | |
| "eval_recall": 0.9267042542286007, | |
| "eval_runtime": 84.0653, | |
| "eval_samples_per_second": 92.833, | |
| "eval_steps_per_second": 11.61, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 4.251386321626618e-05, | |
| "loss": 0.0011, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 4.205175600739372e-05, | |
| "loss": 0.001, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.158964879852126e-05, | |
| "loss": 0.0023, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 4.11275415896488e-05, | |
| "loss": 0.0009, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.066543438077634e-05, | |
| "loss": 0.0009, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.020332717190388e-05, | |
| "loss": 0.0013, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.974121996303142e-05, | |
| "loss": 0.0012, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.9279112754158964e-05, | |
| "loss": 0.0305, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.8817005545286504e-05, | |
| "loss": 0.0088, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 3.835489833641405e-05, | |
| "loss": 0.0009, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_accuracy": 0.9265761148129165, | |
| "eval_f1": 0.9265761148129165, | |
| "eval_loss": 0.3432656526565552, | |
| "eval_precision": 0.9265761148129165, | |
| "eval_recall": 0.9265761148129165, | |
| "eval_runtime": 84.6037, | |
| "eval_samples_per_second": 92.242, | |
| "eval_steps_per_second": 11.536, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 3.789279112754159e-05, | |
| "loss": 0.0057, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.743068391866913e-05, | |
| "loss": 0.001, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 3.6968576709796674e-05, | |
| "loss": 0.0011, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.6506469500924215e-05, | |
| "loss": 0.0008, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 3.6044362292051755e-05, | |
| "loss": 0.0194, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 3.55822550831793e-05, | |
| "loss": 0.0018, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 3.5120147874306844e-05, | |
| "loss": 0.0009, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 3.4658040665434384e-05, | |
| "loss": 0.0069, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.4195933456561925e-05, | |
| "loss": 0.0013, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.3733826247689466e-05, | |
| "loss": 0.0007, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_accuracy": 0.93118913377755, | |
| "eval_f1": 0.93118913377755, | |
| "eval_loss": 0.32155078649520874, | |
| "eval_precision": 0.93118913377755, | |
| "eval_recall": 0.93118913377755, | |
| "eval_runtime": 83.5468, | |
| "eval_samples_per_second": 93.409, | |
| "eval_steps_per_second": 11.682, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 3.3271719038817007e-05, | |
| "loss": 0.0123, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.280961182994455e-05, | |
| "loss": 0.0012, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.234750462107209e-05, | |
| "loss": 0.0155, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 3.188539741219963e-05, | |
| "loss": 0.0168, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.142329020332717e-05, | |
| "loss": 0.0007, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 3.096118299445471e-05, | |
| "loss": 0.0007, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 3.0499075785582254e-05, | |
| "loss": 0.0007, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 3.0036968576709802e-05, | |
| "loss": 0.0007, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 2.9574861367837343e-05, | |
| "loss": 0.0015, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2.9112754158964883e-05, | |
| "loss": 0.0011, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "eval_accuracy": 0.9346488980010251, | |
| "eval_f1": 0.9346488980010251, | |
| "eval_loss": 0.32093849778175354, | |
| "eval_precision": 0.9346488980010251, | |
| "eval_recall": 0.9346488980010251, | |
| "eval_runtime": 84.7259, | |
| "eval_samples_per_second": 92.109, | |
| "eval_steps_per_second": 11.52, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 2.8650646950092424e-05, | |
| "loss": 0.0008, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2.8188539741219965e-05, | |
| "loss": 0.0009, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2.7726432532347505e-05, | |
| "loss": 0.0006, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 2.726432532347505e-05, | |
| "loss": 0.0006, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2.680221811460259e-05, | |
| "loss": 0.0008, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2.634011090573013e-05, | |
| "loss": 0.0013, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2.5878003696857672e-05, | |
| "loss": 0.0396, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 2.5415896487985213e-05, | |
| "loss": 0.0048, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2.4953789279112753e-05, | |
| "loss": 0.0017, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 2.4491682070240297e-05, | |
| "loss": 0.0029, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_accuracy": 0.9324705279343927, | |
| "eval_f1": 0.9324705279343927, | |
| "eval_loss": 0.32358312606811523, | |
| "eval_precision": 0.9324705279343927, | |
| "eval_recall": 0.9324705279343927, | |
| "eval_runtime": 83.628, | |
| "eval_samples_per_second": 93.318, | |
| "eval_steps_per_second": 11.671, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 2.4029574861367838e-05, | |
| "loss": 0.0013, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2.3567467652495382e-05, | |
| "loss": 0.0336, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 2.3105360443622923e-05, | |
| "loss": 0.0011, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 2.2643253234750464e-05, | |
| "loss": 0.0008, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 2.2181146025878004e-05, | |
| "loss": 0.0007, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2.1719038817005545e-05, | |
| "loss": 0.0009, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 2.125693160813309e-05, | |
| "loss": 0.0007, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 2.079482439926063e-05, | |
| "loss": 0.0008, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 2.033271719038817e-05, | |
| "loss": 0.0006, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.987060998151571e-05, | |
| "loss": 0.0011, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_accuracy": 0.9301640184520759, | |
| "eval_f1": 0.9301640184520759, | |
| "eval_loss": 0.3297111690044403, | |
| "eval_precision": 0.9301640184520759, | |
| "eval_recall": 0.9301640184520759, | |
| "eval_runtime": 83.3236, | |
| "eval_samples_per_second": 93.659, | |
| "eval_steps_per_second": 11.713, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.9408502772643252e-05, | |
| "loss": 0.0369, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.8946395563770796e-05, | |
| "loss": 0.0007, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.8484288354898337e-05, | |
| "loss": 0.001, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.8022181146025878e-05, | |
| "loss": 0.0076, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.7560073937153422e-05, | |
| "loss": 0.0084, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.7097966728280963e-05, | |
| "loss": 0.0019, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.6635859519408503e-05, | |
| "loss": 0.0076, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.6173752310536044e-05, | |
| "loss": 0.0006, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.5711645101663585e-05, | |
| "loss": 0.0008, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.5249537892791127e-05, | |
| "loss": 0.0225, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_accuracy": 0.9323423885187083, | |
| "eval_f1": 0.9323423885187083, | |
| "eval_loss": 0.32631945610046387, | |
| "eval_precision": 0.9323423885187083, | |
| "eval_recall": 0.9323423885187083, | |
| "eval_runtime": 83.4276, | |
| "eval_samples_per_second": 93.542, | |
| "eval_steps_per_second": 11.699, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.4787430683918671e-05, | |
| "loss": 0.0008, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.4325323475046212e-05, | |
| "loss": 0.0043, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.3863216266173753e-05, | |
| "loss": 0.0011, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.3401109057301295e-05, | |
| "loss": 0.0029, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1.2939001848428836e-05, | |
| "loss": 0.0171, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.2476894639556377e-05, | |
| "loss": 0.0008, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.2014787430683919e-05, | |
| "loss": 0.0007, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.1552680221811461e-05, | |
| "loss": 0.0051, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 1.1090573012939002e-05, | |
| "loss": 0.0016, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.0628465804066545e-05, | |
| "loss": 0.0008, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_accuracy": 0.9310609943618657, | |
| "eval_f1": 0.9310609943618657, | |
| "eval_loss": 0.3351826071739197, | |
| "eval_precision": 0.9310609943618657, | |
| "eval_recall": 0.9310609943618657, | |
| "eval_runtime": 83.7082, | |
| "eval_samples_per_second": 93.229, | |
| "eval_steps_per_second": 11.66, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.0166358595194085e-05, | |
| "loss": 0.0095, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 9.704251386321626e-06, | |
| "loss": 0.0007, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 9.242144177449168e-06, | |
| "loss": 0.0008, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 8.780036968576711e-06, | |
| "loss": 0.0006, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 8.317929759704252e-06, | |
| "loss": 0.0006, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 7.855822550831792e-06, | |
| "loss": 0.0075, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 7.393715341959336e-06, | |
| "loss": 0.0011, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 6.931608133086876e-06, | |
| "loss": 0.0009, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 6.469500924214418e-06, | |
| "loss": 0.0346, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 6.0073937153419595e-06, | |
| "loss": 0.0391, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_accuracy": 0.9282419272168119, | |
| "eval_f1": 0.9282419272168119, | |
| "eval_loss": 0.33426162600517273, | |
| "eval_precision": 0.9282419272168119, | |
| "eval_recall": 0.9282419272168119, | |
| "eval_runtime": 83.2302, | |
| "eval_samples_per_second": 93.764, | |
| "eval_steps_per_second": 11.727, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 5.545286506469501e-06, | |
| "loss": 0.0023, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 5.083179297597043e-06, | |
| "loss": 0.0011, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 4.621072088724584e-06, | |
| "loss": 0.0007, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 4.158964879852126e-06, | |
| "loss": 0.0016, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.696857670979668e-06, | |
| "loss": 0.0009, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 3.234750462107209e-06, | |
| "loss": 0.0007, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 2.7726432532347505e-06, | |
| "loss": 0.0009, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 2.310536044362292e-06, | |
| "loss": 0.0007, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1.848428835489834e-06, | |
| "loss": 0.0011, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 1.3863216266173753e-06, | |
| "loss": 0.0019, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_accuracy": 0.9279856483854434, | |
| "eval_f1": 0.9279856483854434, | |
| "eval_loss": 0.3318524956703186, | |
| "eval_precision": 0.9279856483854434, | |
| "eval_recall": 0.9279856483854434, | |
| "eval_runtime": 83.5291, | |
| "eval_samples_per_second": 93.429, | |
| "eval_steps_per_second": 11.685, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 9.24214417744917e-07, | |
| "loss": 0.0012, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 4.621072088724585e-07, | |
| "loss": 0.0021, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 4328, | |
| "total_flos": 1.9098706401253786e+19, | |
| "train_loss": 0.11752553500730868, | |
| "train_runtime": 6124.0144, | |
| "train_samples_per_second": 11.302, | |
| "train_steps_per_second": 0.707 | |
| } | |
| ], | |
| "max_steps": 4328, | |
| "num_train_epochs": 4, | |
| "total_flos": 1.9098706401253786e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |