| { | |
| "best_metric": 0.7542949318885803, | |
| "best_model_checkpoint": "/mnt/bn/qingyi-bn-lq/llama/saved-alpaca-belle7b/checkpoint-6800", | |
| "epoch": 2.9341963322545848, | |
| "global_step": 6800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.8997, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.5651, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.1268, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.041, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0094, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.000299124215443001, | |
| "loss": 0.9948, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00029824843088600204, | |
| "loss": 0.974, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000297372646329003, | |
| "loss": 0.9594, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029649686177200406, | |
| "loss": 0.9494, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002956210772150051, | |
| "loss": 0.9473, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.9373907446861267, | |
| "eval_runtime": 9.7698, | |
| "eval_samples_per_second": 204.713, | |
| "eval_steps_per_second": 3.275, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029474529265800613, | |
| "loss": 0.9377, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002938695081010071, | |
| "loss": 0.9311, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00029299372354400815, | |
| "loss": 0.9268, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002921179389870092, | |
| "loss": 0.9145, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002912421544300102, | |
| "loss": 0.9099, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00029036636987301125, | |
| "loss": 0.9076, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00028949058531601223, | |
| "loss": 0.901, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00028861480075901327, | |
| "loss": 0.901, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002877390162020143, | |
| "loss": 0.8973, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028686323164501534, | |
| "loss": 0.8904, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.8943666815757751, | |
| "eval_runtime": 9.7563, | |
| "eval_samples_per_second": 204.995, | |
| "eval_steps_per_second": 3.28, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002859874470880163, | |
| "loss": 0.8905, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00028511166253101735, | |
| "loss": 0.8856, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002842358779740184, | |
| "loss": 0.883, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028336009341701937, | |
| "loss": 0.8846, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002824843088600204, | |
| "loss": 0.8777, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00028160852430302144, | |
| "loss": 0.883, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002807327397460225, | |
| "loss": 0.8819, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027985695518902346, | |
| "loss": 0.8761, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002789811706320245, | |
| "loss": 0.8738, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002781053860750255, | |
| "loss": 0.8636, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.8673094511032104, | |
| "eval_runtime": 9.8373, | |
| "eval_samples_per_second": 203.309, | |
| "eval_steps_per_second": 3.253, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002772296015180265, | |
| "loss": 0.8627, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00027635381696102754, | |
| "loss": 0.8615, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002754780324040286, | |
| "loss": 0.8647, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002746022478470296, | |
| "loss": 0.8635, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002737264632900306, | |
| "loss": 0.8619, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00027285067873303163, | |
| "loss": 0.8477, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00027197489417603266, | |
| "loss": 0.8564, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002710991096190337, | |
| "loss": 0.8513, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002702233250620347, | |
| "loss": 0.855, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002693475405050357, | |
| "loss": 0.8462, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.8500058650970459, | |
| "eval_runtime": 9.7922, | |
| "eval_samples_per_second": 204.244, | |
| "eval_steps_per_second": 3.268, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00026847175594803675, | |
| "loss": 0.852, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002675959713910378, | |
| "loss": 0.8455, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002667201868340388, | |
| "loss": 0.8479, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002658444022770398, | |
| "loss": 0.8423, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00026496861772004084, | |
| "loss": 0.8404, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00026409283316304187, | |
| "loss": 0.8434, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002632170486060429, | |
| "loss": 0.8371, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002623412640490439, | |
| "loss": 0.8397, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002614654794920449, | |
| "loss": 0.8394, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00026058969493504596, | |
| "loss": 0.8368, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.8375310301780701, | |
| "eval_runtime": 9.8151, | |
| "eval_samples_per_second": 203.767, | |
| "eval_steps_per_second": 3.26, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.000259713910378047, | |
| "loss": 0.8376, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00025883812582104803, | |
| "loss": 0.8307, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.000257962341264049, | |
| "loss": 0.8254, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00025708655670705005, | |
| "loss": 0.8347, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002562107721500511, | |
| "loss": 0.8273, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002553349875930521, | |
| "loss": 0.8252, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002544592030360531, | |
| "loss": 0.8245, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00025358341847905413, | |
| "loss": 0.8213, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00025270763392205517, | |
| "loss": 0.8269, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002518318493650562, | |
| "loss": 0.8218, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.8258803486824036, | |
| "eval_runtime": 9.7909, | |
| "eval_samples_per_second": 204.271, | |
| "eval_steps_per_second": 3.268, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00025095606480805724, | |
| "loss": 0.8141, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002500802802510582, | |
| "loss": 0.822, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00024920449569405925, | |
| "loss": 0.82, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002483287111370603, | |
| "loss": 0.8133, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00024745292658006127, | |
| "loss": 0.8248, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002465771420230623, | |
| "loss": 0.814, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00024570135746606334, | |
| "loss": 0.8157, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002448255729090644, | |
| "loss": 0.8109, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00024394978835206538, | |
| "loss": 0.8142, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00024307400379506642, | |
| "loss": 0.8107, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.8169026970863342, | |
| "eval_runtime": 9.8327, | |
| "eval_samples_per_second": 203.402, | |
| "eval_steps_per_second": 3.254, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002421982192380674, | |
| "loss": 0.8133, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00024132243468106843, | |
| "loss": 0.8107, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00024044665012406947, | |
| "loss": 0.8086, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002395708655670705, | |
| "loss": 0.8142, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00023869508101007149, | |
| "loss": 0.8154, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023781929645307252, | |
| "loss": 0.8088, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023694351189607356, | |
| "loss": 0.8052, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00023606772733907456, | |
| "loss": 0.8146, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0002351919427820756, | |
| "loss": 0.802, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002343161582250766, | |
| "loss": 0.8115, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.8092362284660339, | |
| "eval_runtime": 9.7925, | |
| "eval_samples_per_second": 204.237, | |
| "eval_steps_per_second": 3.268, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00023344037366807764, | |
| "loss": 0.7997, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023256458911107865, | |
| "loss": 0.807, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00023168880455407968, | |
| "loss": 0.7951, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002308130199970807, | |
| "loss": 0.8027, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002299372354400817, | |
| "loss": 0.8119, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00022906145088308274, | |
| "loss": 0.8024, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00022818566632608377, | |
| "loss": 0.8043, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0002273098817690848, | |
| "loss": 0.8005, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002264340972120858, | |
| "loss": 0.8024, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00022555831265508682, | |
| "loss": 0.7949, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.8031176924705505, | |
| "eval_runtime": 9.8716, | |
| "eval_samples_per_second": 202.602, | |
| "eval_steps_per_second": 3.242, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00022468252809808786, | |
| "loss": 0.7939, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0002238067435410889, | |
| "loss": 0.7958, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00022293095898408987, | |
| "loss": 0.8019, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002220551744270909, | |
| "loss": 0.7933, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00022117938987009194, | |
| "loss": 0.7994, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00022030360531309298, | |
| "loss": 0.7938, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.000219427820756094, | |
| "loss": 0.7914, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.000218552036199095, | |
| "loss": 0.7921, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00021767625164209603, | |
| "loss": 0.8021, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00021680046708509704, | |
| "loss": 0.7961, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 0.7977419495582581, | |
| "eval_runtime": 9.8406, | |
| "eval_samples_per_second": 203.239, | |
| "eval_steps_per_second": 3.252, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00021592468252809807, | |
| "loss": 0.7969, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00021504889797109908, | |
| "loss": 0.7942, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00021417311341410012, | |
| "loss": 0.7882, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00021329732885710112, | |
| "loss": 0.79, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00021242154430010216, | |
| "loss": 0.7903, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002115457597431032, | |
| "loss": 0.7885, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002106699751861042, | |
| "loss": 0.7925, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002097941906291052, | |
| "loss": 0.7896, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00020891840607210625, | |
| "loss": 0.7892, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00020804262151510728, | |
| "loss": 0.7901, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 0.7927260994911194, | |
| "eval_runtime": 9.9093, | |
| "eval_samples_per_second": 201.83, | |
| "eval_steps_per_second": 3.229, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00020716683695810826, | |
| "loss": 0.7937, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002062910524011093, | |
| "loss": 0.7904, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00020541526784411033, | |
| "loss": 0.7886, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00020453948328711137, | |
| "loss": 0.7837, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002036636987301124, | |
| "loss": 0.79, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00020278791417311338, | |
| "loss": 0.7886, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00020191212961611442, | |
| "loss": 0.7816, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00020103634505911545, | |
| "loss": 0.7774, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00020016056050211646, | |
| "loss": 0.7811, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00019928477594511747, | |
| "loss": 0.788, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 0.7887651920318604, | |
| "eval_runtime": 10.1462, | |
| "eval_samples_per_second": 197.119, | |
| "eval_steps_per_second": 3.154, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001984089913881185, | |
| "loss": 0.7818, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00019753320683111954, | |
| "loss": 0.7864, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00019665742227412055, | |
| "loss": 0.7745, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00019578163771712158, | |
| "loss": 0.7743, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0001949058531601226, | |
| "loss": 0.7832, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0001940300686031236, | |
| "loss": 0.7803, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00019315428404612463, | |
| "loss": 0.7817, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00019227849948912567, | |
| "loss": 0.7843, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00019140271493212668, | |
| "loss": 0.7755, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00019052693037512769, | |
| "loss": 0.7816, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.7844015955924988, | |
| "eval_runtime": 9.9343, | |
| "eval_samples_per_second": 201.323, | |
| "eval_steps_per_second": 3.221, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00018965114581812872, | |
| "loss": 0.7753, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00018877536126112976, | |
| "loss": 0.7782, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001878995767041308, | |
| "loss": 0.7776, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00018702379214713177, | |
| "loss": 0.7773, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0001861480075901328, | |
| "loss": 0.7771, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00018527222303313384, | |
| "loss": 0.7762, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018439643847613488, | |
| "loss": 0.7694, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018352065391913586, | |
| "loss": 0.7789, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0001826448693621369, | |
| "loss": 0.7808, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00018176908480513793, | |
| "loss": 0.7743, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.7819436192512512, | |
| "eval_runtime": 9.8637, | |
| "eval_samples_per_second": 202.764, | |
| "eval_steps_per_second": 3.244, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00018089330024813894, | |
| "loss": 0.7785, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00018001751569113997, | |
| "loss": 0.7737, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00017914173113414098, | |
| "loss": 0.7793, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00017826594657714202, | |
| "loss": 0.7741, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00017739016202014302, | |
| "loss": 0.7758, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00017651437746314406, | |
| "loss": 0.7742, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00017563859290614507, | |
| "loss": 0.7678, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001747628083491461, | |
| "loss": 0.7717, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0001738870237921471, | |
| "loss": 0.7752, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00017301123923514814, | |
| "loss": 0.7733, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.7789211273193359, | |
| "eval_runtime": 9.8687, | |
| "eval_samples_per_second": 202.66, | |
| "eval_steps_per_second": 3.243, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017213545467814918, | |
| "loss": 0.772, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00017125967012115016, | |
| "loss": 0.7726, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0001703838855641512, | |
| "loss": 0.7669, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00016950810100715223, | |
| "loss": 0.7716, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00016863231645015327, | |
| "loss": 0.7736, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00016775653189315425, | |
| "loss": 0.7652, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00016688074733615528, | |
| "loss": 0.7675, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00016600496277915632, | |
| "loss": 0.7729, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00016512917822215735, | |
| "loss": 0.7748, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00016425339366515836, | |
| "loss": 0.7728, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.7762572169303894, | |
| "eval_runtime": 9.9106, | |
| "eval_samples_per_second": 201.803, | |
| "eval_steps_per_second": 3.229, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00016337760910815937, | |
| "loss": 0.7644, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0001625018245511604, | |
| "loss": 0.7701, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00016162603999416144, | |
| "loss": 0.7712, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00016075025543716245, | |
| "loss": 0.7665, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00015987447088016346, | |
| "loss": 0.7649, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0001589986863231645, | |
| "loss": 0.7636, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0001581229017661655, | |
| "loss": 0.7679, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00015724711720916653, | |
| "loss": 0.7686, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00015637133265216757, | |
| "loss": 0.7723, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015549554809516858, | |
| "loss": 0.7672, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.7736611366271973, | |
| "eval_runtime": 9.8349, | |
| "eval_samples_per_second": 203.357, | |
| "eval_steps_per_second": 3.254, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00015461976353816958, | |
| "loss": 0.7633, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00015374397898117062, | |
| "loss": 0.762, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015286819442417166, | |
| "loss": 0.7647, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00015199240986717264, | |
| "loss": 0.7626, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00015111662531017367, | |
| "loss": 0.7683, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0001502408407531747, | |
| "loss": 0.7633, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00014936505619617571, | |
| "loss": 0.7641, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014848927163917675, | |
| "loss": 0.7702, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014761348708217778, | |
| "loss": 0.772, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0001467377025251788, | |
| "loss": 0.7759, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 0.7713318467140198, | |
| "eval_runtime": 9.9228, | |
| "eval_samples_per_second": 201.556, | |
| "eval_steps_per_second": 3.225, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014586191796817983, | |
| "loss": 0.7647, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00014498613341118084, | |
| "loss": 0.7597, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014411034885418187, | |
| "loss": 0.7615, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00014323456429718288, | |
| "loss": 0.7588, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014235877974018391, | |
| "loss": 0.7549, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00014148299518318492, | |
| "loss": 0.7687, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00014060721062618596, | |
| "loss": 0.7684, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00013973142606918697, | |
| "loss": 0.7664, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.000138855641512188, | |
| "loss": 0.7638, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.000137979856955189, | |
| "loss": 0.763, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.7696812748908997, | |
| "eval_runtime": 9.9103, | |
| "eval_samples_per_second": 201.81, | |
| "eval_steps_per_second": 3.229, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013710407239819002, | |
| "loss": 0.7594, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00013622828784119105, | |
| "loss": 0.7579, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013535250328419206, | |
| "loss": 0.7651, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0001344767187271931, | |
| "loss": 0.7665, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0001336009341701941, | |
| "loss": 0.7595, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00013272514961319514, | |
| "loss": 0.7635, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00013184936505619617, | |
| "loss": 0.7599, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00013097358049919718, | |
| "loss": 0.7581, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00013009779594219822, | |
| "loss": 0.7514, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00012922201138519922, | |
| "loss": 0.7597, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.7680906057357788, | |
| "eval_runtime": 10.2283, | |
| "eval_samples_per_second": 195.536, | |
| "eval_steps_per_second": 3.129, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00012834622682820026, | |
| "loss": 0.7664, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00012747044227120127, | |
| "loss": 0.7613, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0001265946577142023, | |
| "loss": 0.759, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0001257188731572033, | |
| "loss": 0.7609, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012484308860020435, | |
| "loss": 0.765, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00012396730404320538, | |
| "loss": 0.7559, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0001230915194862064, | |
| "loss": 0.7575, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0001222157349292074, | |
| "loss": 0.7596, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00012133995037220842, | |
| "loss": 0.7692, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00012046416581520945, | |
| "loss": 0.7627, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.7660259008407593, | |
| "eval_runtime": 9.861, | |
| "eval_samples_per_second": 202.82, | |
| "eval_steps_per_second": 3.245, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011958838125821046, | |
| "loss": 0.7642, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0001187125967012115, | |
| "loss": 0.7612, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0001178368121442125, | |
| "loss": 0.7576, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00011696102758721354, | |
| "loss": 0.7592, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011608524303021456, | |
| "loss": 0.7614, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011520945847321558, | |
| "loss": 0.7564, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0001143336739162166, | |
| "loss": 0.7604, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00011345788935921761, | |
| "loss": 0.7547, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011258210480221865, | |
| "loss": 0.7602, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00011170632024521966, | |
| "loss": 0.7569, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 0.764076828956604, | |
| "eval_runtime": 9.9349, | |
| "eval_samples_per_second": 201.31, | |
| "eval_steps_per_second": 3.221, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00011083053568822069, | |
| "loss": 0.7545, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0001099547511312217, | |
| "loss": 0.7552, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010907896657422273, | |
| "loss": 0.7579, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010820318201722376, | |
| "loss": 0.7547, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010732739746022478, | |
| "loss": 0.7581, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0001064516129032258, | |
| "loss": 0.7554, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010557582834622682, | |
| "loss": 0.7563, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010470004378922784, | |
| "loss": 0.7569, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010382425923222885, | |
| "loss": 0.7571, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010294847467522989, | |
| "loss": 0.7616, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.7628415822982788, | |
| "eval_runtime": 10.0234, | |
| "eval_samples_per_second": 199.534, | |
| "eval_steps_per_second": 3.193, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0001020726901182309, | |
| "loss": 0.7587, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010119690556123193, | |
| "loss": 0.7536, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.00010032112100423295, | |
| "loss": 0.7575, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.944533644723397e-05, | |
| "loss": 0.7572, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.8569551890235e-05, | |
| "loss": 0.7578, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.769376733323602e-05, | |
| "loss": 0.7545, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.681798277623704e-05, | |
| "loss": 0.7616, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.594219821923806e-05, | |
| "loss": 0.7549, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.506641366223908e-05, | |
| "loss": 0.7571, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.41906291052401e-05, | |
| "loss": 0.7528, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 0.7622065544128418, | |
| "eval_runtime": 9.9086, | |
| "eval_samples_per_second": 201.845, | |
| "eval_steps_per_second": 3.23, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.331484454824112e-05, | |
| "loss": 0.7561, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.243905999124216e-05, | |
| "loss": 0.7528, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.156327543424317e-05, | |
| "loss": 0.7496, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 9.06874908772442e-05, | |
| "loss": 0.7594, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.981170632024521e-05, | |
| "loss": 0.7539, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.893592176324623e-05, | |
| "loss": 0.7437, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.806013720624725e-05, | |
| "loss": 0.7475, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.718435264924827e-05, | |
| "loss": 0.75, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.63085680922493e-05, | |
| "loss": 0.7552, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.543278353525032e-05, | |
| "loss": 0.753, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.7612386345863342, | |
| "eval_runtime": 9.9196, | |
| "eval_samples_per_second": 201.621, | |
| "eval_steps_per_second": 3.226, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.455699897825135e-05, | |
| "loss": 0.7546, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.368121442125236e-05, | |
| "loss": 0.7562, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.28054298642534e-05, | |
| "loss": 0.7495, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.19296453072544e-05, | |
| "loss": 0.751, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.105386075025544e-05, | |
| "loss": 0.7459, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.017807619325645e-05, | |
| "loss": 0.7553, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.930229163625748e-05, | |
| "loss": 0.7504, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.842650707925849e-05, | |
| "loss": 0.7565, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.755072252225951e-05, | |
| "loss": 0.7471, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.667493796526055e-05, | |
| "loss": 0.7507, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 0.7600537538528442, | |
| "eval_runtime": 9.8816, | |
| "eval_samples_per_second": 202.397, | |
| "eval_steps_per_second": 3.238, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.579915340826155e-05, | |
| "loss": 0.7537, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.492336885126258e-05, | |
| "loss": 0.7537, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.40475842942636e-05, | |
| "loss": 0.7516, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.317179973726463e-05, | |
| "loss": 0.7459, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.229601518026565e-05, | |
| "loss": 0.7509, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.142023062326668e-05, | |
| "loss": 0.7519, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.05444460662677e-05, | |
| "loss": 0.7426, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.966866150926872e-05, | |
| "loss": 0.7451, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.879287695226974e-05, | |
| "loss": 0.7493, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.791709239527075e-05, | |
| "loss": 0.748, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 0.7588484287261963, | |
| "eval_runtime": 9.902, | |
| "eval_samples_per_second": 201.98, | |
| "eval_steps_per_second": 3.232, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.704130783827177e-05, | |
| "loss": 0.75, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.616552328127279e-05, | |
| "loss": 0.7491, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.528973872427383e-05, | |
| "loss": 0.747, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.441395416727485e-05, | |
| "loss": 0.7512, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.353816961027587e-05, | |
| "loss": 0.7557, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.266238505327689e-05, | |
| "loss": 0.7529, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.178660049627791e-05, | |
| "loss": 0.7465, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.091081593927893e-05, | |
| "loss": 0.7462, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 6.003503138227995e-05, | |
| "loss": 0.7476, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.915924682528097e-05, | |
| "loss": 0.7478, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 0.7580318450927734, | |
| "eval_runtime": 9.8692, | |
| "eval_samples_per_second": 202.65, | |
| "eval_steps_per_second": 3.242, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.8283462268281994e-05, | |
| "loss": 0.7504, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.740767771128302e-05, | |
| "loss": 0.7491, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.6531893154284043e-05, | |
| "loss": 0.7464, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.5656108597285065e-05, | |
| "loss": 0.7474, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.478032404028609e-05, | |
| "loss": 0.7488, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.390453948328711e-05, | |
| "loss": 0.7484, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.302875492628813e-05, | |
| "loss": 0.7486, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.215297036928915e-05, | |
| "loss": 0.7487, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.127718581229017e-05, | |
| "loss": 0.747, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.040140125529119e-05, | |
| "loss": 0.7511, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 0.7569240927696228, | |
| "eval_runtime": 9.868, | |
| "eval_samples_per_second": 202.676, | |
| "eval_steps_per_second": 3.243, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.952561669829222e-05, | |
| "loss": 0.7475, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.864983214129324e-05, | |
| "loss": 0.7402, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.777404758429426e-05, | |
| "loss": 0.7497, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.689826302729528e-05, | |
| "loss": 0.7481, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.60224784702963e-05, | |
| "loss": 0.7488, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.5146693913297324e-05, | |
| "loss": 0.747, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.4270909356298346e-05, | |
| "loss": 0.7538, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.339512479929937e-05, | |
| "loss": 0.7465, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.251934024230039e-05, | |
| "loss": 0.7499, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.164355568530142e-05, | |
| "loss": 0.7477, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.7565082907676697, | |
| "eval_runtime": 9.8679, | |
| "eval_samples_per_second": 202.678, | |
| "eval_steps_per_second": 3.243, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.076777112830244e-05, | |
| "loss": 0.7455, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.989198657130346e-05, | |
| "loss": 0.749, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.901620201430448e-05, | |
| "loss": 0.751, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.81404174573055e-05, | |
| "loss": 0.7471, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.726463290030652e-05, | |
| "loss": 0.7473, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.638884834330754e-05, | |
| "loss": 0.7515, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.551306378630857e-05, | |
| "loss": 0.7449, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.463727922930959e-05, | |
| "loss": 0.7433, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.376149467231061e-05, | |
| "loss": 0.7504, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.2885710115311626e-05, | |
| "loss": 0.7508, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 0.7557815909385681, | |
| "eval_runtime": 9.9145, | |
| "eval_samples_per_second": 201.725, | |
| "eval_steps_per_second": 3.228, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.200992555831265e-05, | |
| "loss": 0.7461, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.1134141001313676e-05, | |
| "loss": 0.7411, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.0258356444314698e-05, | |
| "loss": 0.7461, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.9382571887315716e-05, | |
| "loss": 0.7465, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.8506787330316738e-05, | |
| "loss": 0.7515, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.7631002773317763e-05, | |
| "loss": 0.7444, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.6755218216318784e-05, | |
| "loss": 0.7488, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.5879433659319806e-05, | |
| "loss": 0.7471, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.5003649102320828e-05, | |
| "loss": 0.7494, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.41716537731718e-05, | |
| "loss": 0.7552, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 0.7553005218505859, | |
| "eval_runtime": 9.9033, | |
| "eval_samples_per_second": 201.953, | |
| "eval_steps_per_second": 3.231, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.329586921617282e-05, | |
| "loss": 0.7425, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.242008465917384e-05, | |
| "loss": 0.744, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.1544300102174863e-05, | |
| "loss": 0.7431, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.0668515545175885e-05, | |
| "loss": 0.7421, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.9792730988176907e-05, | |
| "loss": 0.7481, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.8916946431177928e-05, | |
| "loss": 0.7332, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.804116187417895e-05, | |
| "loss": 0.7462, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.716537731717997e-05, | |
| "loss": 0.7487, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.6289592760180993e-05, | |
| "loss": 0.7493, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.5413808203182015e-05, | |
| "loss": 0.75, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 0.7546943426132202, | |
| "eval_runtime": 9.8229, | |
| "eval_samples_per_second": 203.606, | |
| "eval_steps_per_second": 3.258, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.4538023646183038e-05, | |
| "loss": 0.7489, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.366223908918406e-05, | |
| "loss": 0.7544, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.2786454532185083e-05, | |
| "loss": 0.7459, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.1910669975186103e-05, | |
| "loss": 0.7427, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.1034885418187124e-05, | |
| "loss": 0.7482, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.0159100861188148e-05, | |
| "loss": 0.7454, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.283316304189169e-06, | |
| "loss": 0.7576, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.40753174719019e-06, | |
| "loss": 0.7385, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.5317471901912114e-06, | |
| "loss": 0.742, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 6.655962633192234e-06, | |
| "loss": 0.7499, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 0.7542949318885803, | |
| "eval_runtime": 9.9073, | |
| "eval_samples_per_second": 201.871, | |
| "eval_steps_per_second": 3.23, | |
| "step": 6800 | |
| } | |
| ], | |
| "max_steps": 6951, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.767789823284111e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |