| { | |
| "best_metric": 0.7870123386383057, | |
| "best_model_checkpoint": "/mnt/bn/qingyi-bn-lq/llama/saved-alpaca-belle-cot7b/checkpoint-15600", | |
| "epoch": 2.989078367503353, | |
| "global_step": 15600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.8213, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.5494, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.179, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.1022, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0003, | |
| "loss": 1.078, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00029961432152728675, | |
| "loss": 1.0347, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002992286430545735, | |
| "loss": 1.0169, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00029884296458186025, | |
| "loss": 1.0088, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00029845728610914697, | |
| "loss": 0.9896, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00029807160763643375, | |
| "loss": 0.99, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.0032634735107422, | |
| "eval_runtime": 16.3952, | |
| "eval_samples_per_second": 121.987, | |
| "eval_steps_per_second": 1.952, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00029768592916372047, | |
| "loss": 0.9724, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00029730025069100725, | |
| "loss": 0.9719, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00029691457221829397, | |
| "loss": 0.9652, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00029652889374558075, | |
| "loss": 0.9579, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00029614321527286747, | |
| "loss": 0.9532, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00029575753680015425, | |
| "loss": 0.9613, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000295371858327441, | |
| "loss": 0.9473, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00029498617985472775, | |
| "loss": 0.9416, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002946005013820145, | |
| "loss": 0.9386, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029421482290930125, | |
| "loss": 0.9338, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.957970380783081, | |
| "eval_runtime": 16.3897, | |
| "eval_samples_per_second": 122.028, | |
| "eval_steps_per_second": 1.952, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.000293829144436588, | |
| "loss": 0.937, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029344346596387475, | |
| "loss": 0.9304, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002930577874911615, | |
| "loss": 0.9323, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029267210901844825, | |
| "loss": 0.9185, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.000292286430545735, | |
| "loss": 0.9273, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00029190075207302175, | |
| "loss": 0.922, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002915150736003085, | |
| "loss": 0.9146, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00029112939512759525, | |
| "loss": 0.9129, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.000290743716654882, | |
| "loss": 0.9146, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002903580381821688, | |
| "loss": 0.9078, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.9345074892044067, | |
| "eval_runtime": 16.4049, | |
| "eval_samples_per_second": 121.914, | |
| "eval_steps_per_second": 1.951, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002899723597094555, | |
| "loss": 0.9004, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002895866812367423, | |
| "loss": 0.9042, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000289201002764029, | |
| "loss": 0.9028, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002888153242913158, | |
| "loss": 0.8889, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002884296458186025, | |
| "loss": 0.8935, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002880439673458893, | |
| "loss": 0.9024, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.000287658288873176, | |
| "loss": 0.8922, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002872726104004628, | |
| "loss": 0.8896, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002868869319277495, | |
| "loss": 0.8907, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002865012534550363, | |
| "loss": 0.8922, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.9149895310401917, | |
| "eval_runtime": 16.4499, | |
| "eval_samples_per_second": 121.581, | |
| "eval_steps_per_second": 1.945, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002861155749823231, | |
| "loss": 0.8867, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002857298965096098, | |
| "loss": 0.891, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00028534421803689657, | |
| "loss": 0.8882, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002849585395641833, | |
| "loss": 0.8835, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028457286109147007, | |
| "loss": 0.8798, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002841871826187568, | |
| "loss": 0.8784, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00028380150414604357, | |
| "loss": 0.8841, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002834158256733303, | |
| "loss": 0.8787, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00028303014720061707, | |
| "loss": 0.8693, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002826444687279038, | |
| "loss": 0.8711, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 0.9027432799339294, | |
| "eval_runtime": 16.447, | |
| "eval_samples_per_second": 121.603, | |
| "eval_steps_per_second": 1.946, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00028225879025519057, | |
| "loss": 0.876, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002818731117824773, | |
| "loss": 0.8749, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00028148743330976407, | |
| "loss": 0.877, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028110175483705085, | |
| "loss": 0.8754, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028071607636433757, | |
| "loss": 0.8792, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028033039789162435, | |
| "loss": 0.8701, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027994471941891107, | |
| "loss": 0.8667, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027955904094619785, | |
| "loss": 0.8769, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00027917336247348457, | |
| "loss": 0.8734, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002787876840007713, | |
| "loss": 0.8708, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.8911536335945129, | |
| "eval_runtime": 16.423, | |
| "eval_samples_per_second": 121.78, | |
| "eval_steps_per_second": 1.948, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00027840200552805807, | |
| "loss": 0.8673, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027801632705534485, | |
| "loss": 0.8618, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027763064858263157, | |
| "loss": 0.8739, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00027724497010991834, | |
| "loss": 0.8608, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002768592916372051, | |
| "loss": 0.8631, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00027647361316449184, | |
| "loss": 0.8547, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002760879346917786, | |
| "loss": 0.8589, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00027570225621906534, | |
| "loss": 0.8615, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002753165777463521, | |
| "loss": 0.8644, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00027493089927363884, | |
| "loss": 0.8524, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.8813066482543945, | |
| "eval_runtime": 16.4628, | |
| "eval_samples_per_second": 121.486, | |
| "eval_steps_per_second": 1.944, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00027454522080092557, | |
| "loss": 0.8562, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00027415954232821234, | |
| "loss": 0.8547, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002737738638554991, | |
| "loss": 0.8599, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00027338818538278584, | |
| "loss": 0.8491, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002730025069100726, | |
| "loss": 0.8496, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002726168284373594, | |
| "loss": 0.8594, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002722311499646461, | |
| "loss": 0.8512, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002718454714919329, | |
| "loss": 0.8441, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002714597930192196, | |
| "loss": 0.8621, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002710741145465064, | |
| "loss": 0.8525, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.8728711009025574, | |
| "eval_runtime": 16.4389, | |
| "eval_samples_per_second": 121.663, | |
| "eval_steps_per_second": 1.947, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002706884360737931, | |
| "loss": 0.852, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00027030275760107984, | |
| "loss": 0.8553, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002699170791283666, | |
| "loss": 0.8445, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002695314006556534, | |
| "loss": 0.8518, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002691457221829401, | |
| "loss": 0.8318, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002687600437102269, | |
| "loss": 0.8492, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002683743652375136, | |
| "loss": 0.8475, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002679886867648004, | |
| "loss": 0.8437, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00026760300829208717, | |
| "loss": 0.8355, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002672173298193739, | |
| "loss": 0.8486, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.8663893938064575, | |
| "eval_runtime": 16.4511, | |
| "eval_samples_per_second": 121.572, | |
| "eval_steps_per_second": 1.945, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00026683165134666067, | |
| "loss": 0.8449, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002664459728739474, | |
| "loss": 0.853, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00026606029440123417, | |
| "loss": 0.8472, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002656746159285209, | |
| "loss": 0.83, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002652889374558076, | |
| "loss": 0.8398, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002649032589830944, | |
| "loss": 0.8337, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00026451758051038117, | |
| "loss": 0.8314, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002641319020376679, | |
| "loss": 0.8314, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00026374622356495467, | |
| "loss": 0.845, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00026336054509224144, | |
| "loss": 0.8294, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.8619188666343689, | |
| "eval_runtime": 16.4444, | |
| "eval_samples_per_second": 121.622, | |
| "eval_steps_per_second": 1.946, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00026297486661952817, | |
| "loss": 0.8404, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00026258918814681494, | |
| "loss": 0.839, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00026220350967410167, | |
| "loss": 0.84, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00026181783120138844, | |
| "loss": 0.8442, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00026143215272867517, | |
| "loss": 0.8443, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002610464742559619, | |
| "loss": 0.8301, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00026066079578324867, | |
| "loss": 0.8302, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00026027511731053544, | |
| "loss": 0.836, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00025988943883782216, | |
| "loss": 0.8277, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00025950376036510894, | |
| "loss": 0.8335, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.8562669157981873, | |
| "eval_runtime": 16.4486, | |
| "eval_samples_per_second": 121.591, | |
| "eval_steps_per_second": 1.945, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00025911808189239566, | |
| "loss": 0.8267, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00025873240341968244, | |
| "loss": 0.8267, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002583467249469692, | |
| "loss": 0.8293, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00025796104647425594, | |
| "loss": 0.836, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002575753680015427, | |
| "loss": 0.8255, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00025718968952882944, | |
| "loss": 0.8177, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00025680401105611616, | |
| "loss": 0.8272, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00025641833258340294, | |
| "loss": 0.831, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00025603265411068966, | |
| "loss": 0.819, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00025564697563797644, | |
| "loss": 0.8216, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.8516544103622437, | |
| "eval_runtime": 16.476, | |
| "eval_samples_per_second": 121.389, | |
| "eval_steps_per_second": 1.942, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002552612971652632, | |
| "loss": 0.8305, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00025487561869254994, | |
| "loss": 0.8305, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002544899402198367, | |
| "loss": 0.8302, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002541042617471235, | |
| "loss": 0.824, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002537185832744102, | |
| "loss": 0.8315, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.000253332904801697, | |
| "loss": 0.8224, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002529472263289837, | |
| "loss": 0.8229, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00025256154785627044, | |
| "loss": 0.8156, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002521758693835572, | |
| "loss": 0.8319, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00025179019091084394, | |
| "loss": 0.8222, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.8481459021568298, | |
| "eval_runtime": 16.453, | |
| "eval_samples_per_second": 121.558, | |
| "eval_steps_per_second": 1.945, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002514045124381307, | |
| "loss": 0.8205, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002510188339654175, | |
| "loss": 0.8267, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002506331554927042, | |
| "loss": 0.8116, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.000250247477019991, | |
| "loss": 0.8239, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00024986179854727777, | |
| "loss": 0.8126, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002494761200745645, | |
| "loss": 0.8226, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00024909044160185127, | |
| "loss": 0.8173, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.000248704763129138, | |
| "loss": 0.8227, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002483190846564247, | |
| "loss": 0.8129, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002479334061837115, | |
| "loss": 0.8164, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.8439643979072571, | |
| "eval_runtime": 16.4767, | |
| "eval_samples_per_second": 121.384, | |
| "eval_steps_per_second": 1.942, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002475477277109982, | |
| "loss": 0.807, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.000247162049238285, | |
| "loss": 0.8126, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00024677637076557176, | |
| "loss": 0.8193, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002463906922928585, | |
| "loss": 0.8091, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00024600501382014526, | |
| "loss": 0.8147, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.000245619335347432, | |
| "loss": 0.8207, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00024523365687471876, | |
| "loss": 0.8087, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00024484797840200554, | |
| "loss": 0.8198, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00024446229992929226, | |
| "loss": 0.8087, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.000244076621456579, | |
| "loss": 0.8182, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 0.8408891558647156, | |
| "eval_runtime": 16.4801, | |
| "eval_samples_per_second": 121.358, | |
| "eval_steps_per_second": 1.942, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002436909429838658, | |
| "loss": 0.8188, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002433052645111525, | |
| "loss": 0.8082, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024291958603843926, | |
| "loss": 0.8171, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.000242533907565726, | |
| "loss": 0.8088, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024214822909301276, | |
| "loss": 0.8148, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00024176255062029954, | |
| "loss": 0.8122, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00024137687214758626, | |
| "loss": 0.811, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00024099119367487304, | |
| "loss": 0.8179, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002406055152021598, | |
| "loss": 0.8029, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002402198367294465, | |
| "loss": 0.8143, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.837196946144104, | |
| "eval_runtime": 16.4913, | |
| "eval_samples_per_second": 121.276, | |
| "eval_steps_per_second": 1.94, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002398341582567333, | |
| "loss": 0.7969, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00023944847978402, | |
| "loss": 0.8158, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002390628013113068, | |
| "loss": 0.8019, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00023867712283859354, | |
| "loss": 0.8042, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0002382914443658803, | |
| "loss": 0.8022, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023790576589316704, | |
| "loss": 0.8043, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002375200874204538, | |
| "loss": 0.8106, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023713440894774054, | |
| "loss": 0.8146, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002367487304750273, | |
| "loss": 0.8004, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00023636305200231404, | |
| "loss": 0.8096, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.8347571492195129, | |
| "eval_runtime": 16.4822, | |
| "eval_samples_per_second": 121.343, | |
| "eval_steps_per_second": 1.941, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002359773735296008, | |
| "loss": 0.8226, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023559169505688756, | |
| "loss": 0.8083, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023520601658417428, | |
| "loss": 0.8168, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00023482033811146106, | |
| "loss": 0.8112, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002344346596387478, | |
| "loss": 0.8131, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00023404898116603456, | |
| "loss": 0.8097, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0002336633026933213, | |
| "loss": 0.804, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00023327762422060806, | |
| "loss": 0.8085, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002328919457478948, | |
| "loss": 0.7992, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002325062672751816, | |
| "loss": 0.8124, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.8324670791625977, | |
| "eval_runtime": 16.4936, | |
| "eval_samples_per_second": 121.259, | |
| "eval_steps_per_second": 1.94, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002321205888024683, | |
| "loss": 0.8024, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002317349103297551, | |
| "loss": 0.8032, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00023134923185704184, | |
| "loss": 0.8065, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023096355338432856, | |
| "loss": 0.8106, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023057787491161534, | |
| "loss": 0.8009, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023019219643890206, | |
| "loss": 0.816, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00022980651796618884, | |
| "loss": 0.8103, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00022942083949347559, | |
| "loss": 0.8099, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00022903516102076233, | |
| "loss": 0.8085, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00022864948254804908, | |
| "loss": 0.8044, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.830141544342041, | |
| "eval_runtime": 16.4845, | |
| "eval_samples_per_second": 121.326, | |
| "eval_steps_per_second": 1.941, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00022826380407533586, | |
| "loss": 0.7969, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00022787812560262258, | |
| "loss": 0.8029, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00022749244712990936, | |
| "loss": 0.7921, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002271067686571961, | |
| "loss": 0.8051, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00022672109018448283, | |
| "loss": 0.807, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002263354117117696, | |
| "loss": 0.8042, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00022594973323905633, | |
| "loss": 0.7947, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0002255640547663431, | |
| "loss": 0.7972, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00022517837629362986, | |
| "loss": 0.8038, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002247926978209166, | |
| "loss": 0.8064, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.828279435634613, | |
| "eval_runtime": 16.4904, | |
| "eval_samples_per_second": 121.283, | |
| "eval_steps_per_second": 1.941, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00022440701934820336, | |
| "loss": 0.8032, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00022402134087549014, | |
| "loss": 0.7934, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00022363566240277686, | |
| "loss": 0.7919, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00022324998393006364, | |
| "loss": 0.8011, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00022286430545735036, | |
| "loss": 0.8026, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0002224786269846371, | |
| "loss": 0.804, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00022209294851192388, | |
| "loss": 0.8122, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002217072700392106, | |
| "loss": 0.7932, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00022132159156649738, | |
| "loss": 0.7911, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00022093591309378413, | |
| "loss": 0.8012, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.8261794447898865, | |
| "eval_runtime": 16.4921, | |
| "eval_samples_per_second": 121.27, | |
| "eval_steps_per_second": 1.94, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00022055023462107088, | |
| "loss": 0.7989, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00022016455614835763, | |
| "loss": 0.8031, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00021977887767564438, | |
| "loss": 0.8066, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00021939319920293113, | |
| "loss": 0.7964, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002190075207302179, | |
| "loss": 0.7947, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00021862184225750463, | |
| "loss": 0.8035, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00021823616378479138, | |
| "loss": 0.8029, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00021785048531207816, | |
| "loss": 0.7941, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00021746480683936488, | |
| "loss": 0.7934, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00021707912836665166, | |
| "loss": 0.7946, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.823946475982666, | |
| "eval_runtime": 16.4887, | |
| "eval_samples_per_second": 121.295, | |
| "eval_steps_per_second": 1.941, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00021669344989393838, | |
| "loss": 0.7974, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00021630777142122516, | |
| "loss": 0.7962, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002159220929485119, | |
| "loss": 0.7946, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00021553641447579866, | |
| "loss": 0.7818, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002151507360030854, | |
| "loss": 0.803, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00021476505753037218, | |
| "loss": 0.7851, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002143793790576589, | |
| "loss": 0.7984, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00021399370058494568, | |
| "loss": 0.7973, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002136080221122324, | |
| "loss": 0.782, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00021322234363951916, | |
| "loss": 0.7951, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.8220962285995483, | |
| "eval_runtime": 16.5191, | |
| "eval_samples_per_second": 121.072, | |
| "eval_steps_per_second": 1.937, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00021283666516680593, | |
| "loss": 0.7947, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00021245098669409266, | |
| "loss": 0.7957, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00021206530822137943, | |
| "loss": 0.797, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00021167962974866618, | |
| "loss": 0.8097, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00021129395127595293, | |
| "loss": 0.7894, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00021090827280323968, | |
| "loss": 0.7789, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002105225943305264, | |
| "loss": 0.7949, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00021013691585781318, | |
| "loss": 0.7895, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00020975123738509996, | |
| "loss": 0.8036, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00020936555891238668, | |
| "loss": 0.7966, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.8209095597267151, | |
| "eval_runtime": 16.5035, | |
| "eval_samples_per_second": 121.187, | |
| "eval_steps_per_second": 1.939, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00020897988043967343, | |
| "loss": 0.7892, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002085942019669602, | |
| "loss": 0.7825, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00020820852349424693, | |
| "loss": 0.7937, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002078228450215337, | |
| "loss": 0.7893, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00020743716654882043, | |
| "loss": 0.7944, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002070514880761072, | |
| "loss": 0.7973, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00020666580960339396, | |
| "loss": 0.7919, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002062801311306807, | |
| "loss": 0.7918, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00020589445265796746, | |
| "loss": 0.7901, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00020550877418525423, | |
| "loss": 0.7891, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.8192855715751648, | |
| "eval_runtime": 16.5248, | |
| "eval_samples_per_second": 121.03, | |
| "eval_steps_per_second": 1.936, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00020512309571254096, | |
| "loss": 0.7813, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002047374172398277, | |
| "loss": 0.7831, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00020435173876711445, | |
| "loss": 0.7911, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002039660602944012, | |
| "loss": 0.7816, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00020358038182168798, | |
| "loss": 0.7915, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0002031947033489747, | |
| "loss": 0.791, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00020280902487626148, | |
| "loss": 0.7851, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00020242334640354823, | |
| "loss": 0.7859, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00020203766793083498, | |
| "loss": 0.7888, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00020165198945812173, | |
| "loss": 0.7854, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.8173321485519409, | |
| "eval_runtime": 16.5042, | |
| "eval_samples_per_second": 121.182, | |
| "eval_steps_per_second": 1.939, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002012663109854085, | |
| "loss": 0.7888, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00020088063251269523, | |
| "loss": 0.7893, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00020049495403998198, | |
| "loss": 0.7817, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00020010927556726873, | |
| "loss": 0.7755, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00019972359709455548, | |
| "loss": 0.7839, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00019933791862184226, | |
| "loss": 0.7911, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00019895224014912898, | |
| "loss": 0.7819, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00019856656167641576, | |
| "loss": 0.7802, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001981808832037025, | |
| "loss": 0.7847, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00019779520473098925, | |
| "loss": 0.7824, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.8163856267929077, | |
| "eval_runtime": 16.5306, | |
| "eval_samples_per_second": 120.988, | |
| "eval_steps_per_second": 1.936, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00019742881018191167, | |
| "loss": 0.7757, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001970431317091984, | |
| "loss": 0.786, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00019665745323648517, | |
| "loss": 0.7923, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00019627177476377191, | |
| "loss": 0.791, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00019588609629105866, | |
| "loss": 0.7863, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00019550041781834541, | |
| "loss": 0.7879, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0001951147393456322, | |
| "loss": 0.7924, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00019472906087291891, | |
| "loss": 0.7918, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001943433824002057, | |
| "loss": 0.792, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001939577039274924, | |
| "loss": 0.7784, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.8148436546325684, | |
| "eval_runtime": 16.5424, | |
| "eval_samples_per_second": 120.901, | |
| "eval_steps_per_second": 1.934, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0001935720254547792, | |
| "loss": 0.7903, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00019318634698206594, | |
| "loss": 0.785, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00019280066850935266, | |
| "loss": 0.7916, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00019241499003663944, | |
| "loss": 0.779, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0001920293115639262, | |
| "loss": 0.7909, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00019164363309121294, | |
| "loss": 0.7798, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001912579546184997, | |
| "loss": 0.7846, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00019087227614578647, | |
| "loss": 0.7887, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0001904865976730732, | |
| "loss": 0.7802, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00019010091920035997, | |
| "loss": 0.7891, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.8130878806114197, | |
| "eval_runtime": 16.5056, | |
| "eval_samples_per_second": 121.171, | |
| "eval_steps_per_second": 1.939, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0001897152407276467, | |
| "loss": 0.7819, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00018932956225493346, | |
| "loss": 0.7945, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00018894388378222021, | |
| "loss": 0.784, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00018855820530950694, | |
| "loss": 0.7838, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00018817252683679371, | |
| "loss": 0.7841, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001877868483640805, | |
| "loss": 0.7909, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001874011698913672, | |
| "loss": 0.7775, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00018701549141865396, | |
| "loss": 0.7827, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001866298129459407, | |
| "loss": 0.7866, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00018624413447322746, | |
| "loss": 0.7696, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.8125277757644653, | |
| "eval_runtime": 16.506, | |
| "eval_samples_per_second": 121.168, | |
| "eval_steps_per_second": 1.939, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00018585845600051424, | |
| "loss": 0.783, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00018547277752780096, | |
| "loss": 0.7792, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00018508709905508774, | |
| "loss": 0.7775, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001847014205823745, | |
| "loss": 0.7806, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0001843157421096612, | |
| "loss": 0.7801, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.000183930063636948, | |
| "loss": 0.7853, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0001835443851642347, | |
| "loss": 0.7937, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0001831587066915215, | |
| "loss": 0.7873, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018277302821880824, | |
| "loss": 0.778, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.000182387349746095, | |
| "loss": 0.781, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.8113830089569092, | |
| "eval_runtime": 16.5217, | |
| "eval_samples_per_second": 121.053, | |
| "eval_steps_per_second": 1.937, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018200167127338174, | |
| "loss": 0.7746, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00018161599280066851, | |
| "loss": 0.7752, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00018123031432795524, | |
| "loss": 0.7838, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.000180844635855242, | |
| "loss": 0.789, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00018045895738252874, | |
| "loss": 0.7882, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00018007327890981549, | |
| "loss": 0.7822, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00017968760043710226, | |
| "loss": 0.7889, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017930192196438899, | |
| "loss": 0.7891, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017891624349167576, | |
| "loss": 0.7884, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001785305650189625, | |
| "loss": 0.7733, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.810148298740387, | |
| "eval_runtime": 16.5113, | |
| "eval_samples_per_second": 121.129, | |
| "eval_steps_per_second": 1.938, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00017814488654624926, | |
| "loss": 0.7794, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.000177759208073536, | |
| "loss": 0.775, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00017737352960082276, | |
| "loss": 0.7706, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0001769878511281095, | |
| "loss": 0.7808, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001766021726553963, | |
| "loss": 0.7805, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.000176216494182683, | |
| "loss": 0.7813, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001758308157099698, | |
| "loss": 0.7789, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00017544513723725654, | |
| "loss": 0.7827, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00017505945876454326, | |
| "loss": 0.7763, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00017467378029183004, | |
| "loss": 0.7779, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 0.8090565800666809, | |
| "eval_runtime": 16.4954, | |
| "eval_samples_per_second": 121.246, | |
| "eval_steps_per_second": 1.94, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00017428810181911676, | |
| "loss": 0.7793, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00017390242334640354, | |
| "loss": 0.7778, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00017351674487369029, | |
| "loss": 0.7802, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00017313106640097704, | |
| "loss": 0.7823, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00017274538792826379, | |
| "loss": 0.7868, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00017235970945555056, | |
| "loss": 0.7824, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00017197403098283728, | |
| "loss": 0.7777, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017158835251012406, | |
| "loss": 0.7822, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017120267403741078, | |
| "loss": 0.7798, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017081699556469753, | |
| "loss": 0.7712, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 0.8080956935882568, | |
| "eval_runtime": 16.5234, | |
| "eval_samples_per_second": 121.041, | |
| "eval_steps_per_second": 1.937, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0001704313170919843, | |
| "loss": 0.7888, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00017004563861927103, | |
| "loss": 0.7769, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0001696599601465578, | |
| "loss": 0.7686, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00016927428167384456, | |
| "loss": 0.7762, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0001688886032011313, | |
| "loss": 0.7807, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00016850292472841806, | |
| "loss": 0.7831, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0001681172462557048, | |
| "loss": 0.7856, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00016773156778299156, | |
| "loss": 0.775, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00016734588931027834, | |
| "loss": 0.7835, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00016696021083756506, | |
| "loss": 0.7756, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 0.8070209622383118, | |
| "eval_runtime": 16.4997, | |
| "eval_samples_per_second": 121.214, | |
| "eval_steps_per_second": 1.939, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0001665745323648518, | |
| "loss": 0.7756, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00016618885389213859, | |
| "loss": 0.7783, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0001658031754194253, | |
| "loss": 0.7697, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00016541749694671208, | |
| "loss": 0.7889, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00016503181847399883, | |
| "loss": 0.7725, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00016464614000128558, | |
| "loss": 0.7726, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00016426046152857233, | |
| "loss": 0.7787, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00016387478305585908, | |
| "loss": 0.782, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00016348910458314583, | |
| "loss": 0.7736, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0001631034261104326, | |
| "loss": 0.7748, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.8063712120056152, | |
| "eval_runtime": 16.5096, | |
| "eval_samples_per_second": 121.142, | |
| "eval_steps_per_second": 1.938, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00016271774763771933, | |
| "loss": 0.7717, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00016233206916500608, | |
| "loss": 0.7676, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00016194639069229286, | |
| "loss": 0.7662, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00016156071221957958, | |
| "loss": 0.7809, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00016117503374686636, | |
| "loss": 0.7731, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00016078935527415308, | |
| "loss": 0.7795, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00016040367680143986, | |
| "loss": 0.78, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0001600179983287266, | |
| "loss": 0.7785, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00015963231985601336, | |
| "loss": 0.7694, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0001592466413833001, | |
| "loss": 0.781, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 0.8048364520072937, | |
| "eval_runtime": 16.5235, | |
| "eval_samples_per_second": 121.04, | |
| "eval_steps_per_second": 1.937, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00015886096291058688, | |
| "loss": 0.7681, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0001584752844378736, | |
| "loss": 0.7835, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00015808960596516038, | |
| "loss": 0.7778, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0001577039274924471, | |
| "loss": 0.775, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00015731824901973386, | |
| "loss": 0.7758, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00015693257054702063, | |
| "loss": 0.7846, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00015654689207430736, | |
| "loss": 0.7756, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00015616121360159413, | |
| "loss": 0.7764, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00015577553512888088, | |
| "loss": 0.7684, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00015538985665616763, | |
| "loss": 0.7837, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 0.8041849136352539, | |
| "eval_runtime": 16.4633, | |
| "eval_samples_per_second": 121.482, | |
| "eval_steps_per_second": 1.944, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00015500417818345438, | |
| "loss": 0.772, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0001546184997107411, | |
| "loss": 0.7759, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015423282123802788, | |
| "loss": 0.7778, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015384714276531466, | |
| "loss": 0.78, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00015346146429260138, | |
| "loss": 0.7681, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00015307578581988813, | |
| "loss": 0.7731, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001526901073471749, | |
| "loss": 0.78, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015230442887446163, | |
| "loss": 0.7719, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0001519187504017484, | |
| "loss": 0.7667, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015153307192903513, | |
| "loss": 0.7804, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 0.8034607768058777, | |
| "eval_runtime": 16.4833, | |
| "eval_samples_per_second": 121.335, | |
| "eval_steps_per_second": 1.941, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001511473934563219, | |
| "loss": 0.7813, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00015076171498360866, | |
| "loss": 0.7751, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00015037603651089538, | |
| "loss": 0.7681, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00014999035803818216, | |
| "loss": 0.7679, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0001496046795654689, | |
| "loss": 0.7723, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00014921900109275566, | |
| "loss": 0.7732, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0001488333226200424, | |
| "loss": 0.7805, | |
| "step": 7940 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00014844764414732916, | |
| "loss": 0.7666, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001480619656746159, | |
| "loss": 0.7801, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00014767628720190265, | |
| "loss": 0.7736, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.8029702305793762, | |
| "eval_runtime": 16.5088, | |
| "eval_samples_per_second": 121.147, | |
| "eval_steps_per_second": 1.938, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014729060872918943, | |
| "loss": 0.7716, | |
| "step": 8020 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014690493025647618, | |
| "loss": 0.7771, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014651925178376293, | |
| "loss": 0.7715, | |
| "step": 8060 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00014613357331104968, | |
| "loss": 0.7731, | |
| "step": 8080 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00014574789483833643, | |
| "loss": 0.7763, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014536221636562318, | |
| "loss": 0.7705, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014497653789290993, | |
| "loss": 0.7702, | |
| "step": 8140 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014459085942019668, | |
| "loss": 0.7752, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00014420518094748343, | |
| "loss": 0.7662, | |
| "step": 8180 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00014381950247477018, | |
| "loss": 0.7757, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.8025923371315002, | |
| "eval_runtime": 16.5398, | |
| "eval_samples_per_second": 120.921, | |
| "eval_steps_per_second": 1.935, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014343382400205693, | |
| "loss": 0.7638, | |
| "step": 8220 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0001430481455293437, | |
| "loss": 0.7836, | |
| "step": 8240 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014266246705663046, | |
| "loss": 0.7685, | |
| "step": 8260 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0001422767885839172, | |
| "loss": 0.7901, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00014189111011120396, | |
| "loss": 0.7729, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0001415054316384907, | |
| "loss": 0.7614, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014111975316577745, | |
| "loss": 0.7789, | |
| "step": 8340 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0001407340746930642, | |
| "loss": 0.7713, | |
| "step": 8360 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00014034839622035095, | |
| "loss": 0.7831, | |
| "step": 8380 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0001399627177476377, | |
| "loss": 0.7674, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.801445722579956, | |
| "eval_runtime": 16.5305, | |
| "eval_samples_per_second": 120.989, | |
| "eval_steps_per_second": 1.936, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00013957703927492445, | |
| "loss": 0.7698, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0001391913608022112, | |
| "loss": 0.7725, | |
| "step": 8440 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00013880568232949795, | |
| "loss": 0.771, | |
| "step": 8460 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00013842000385678473, | |
| "loss": 0.7679, | |
| "step": 8480 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00013803432538407148, | |
| "loss": 0.7788, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00013764864691135823, | |
| "loss": 0.7705, | |
| "step": 8520 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00013726296843864495, | |
| "loss": 0.7625, | |
| "step": 8540 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00013687728996593173, | |
| "loss": 0.7626, | |
| "step": 8560 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00013649161149321848, | |
| "loss": 0.7731, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013610593302050523, | |
| "loss": 0.7788, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 0.8010225296020508, | |
| "eval_runtime": 16.5075, | |
| "eval_samples_per_second": 121.157, | |
| "eval_steps_per_second": 1.939, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013572025454779198, | |
| "loss": 0.7758, | |
| "step": 8620 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00013533457607507873, | |
| "loss": 0.7738, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00013494889760236548, | |
| "loss": 0.7827, | |
| "step": 8660 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00013456321912965223, | |
| "loss": 0.779, | |
| "step": 8680 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013417754065693898, | |
| "loss": 0.771, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013379186218422575, | |
| "loss": 0.7683, | |
| "step": 8720 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0001334061837115125, | |
| "loss": 0.7728, | |
| "step": 8740 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013302050523879925, | |
| "loss": 0.7761, | |
| "step": 8760 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013263482676608598, | |
| "loss": 0.7705, | |
| "step": 8780 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00013224914829337275, | |
| "loss": 0.7624, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 0.8003928065299988, | |
| "eval_runtime": 16.5035, | |
| "eval_samples_per_second": 121.186, | |
| "eval_steps_per_second": 1.939, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0001318634698206595, | |
| "loss": 0.7669, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00013147779134794625, | |
| "loss": 0.7675, | |
| "step": 8840 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.000131092112875233, | |
| "loss": 0.7629, | |
| "step": 8860 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00013070643440251975, | |
| "loss": 0.7663, | |
| "step": 8880 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0001303207559298065, | |
| "loss": 0.7708, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00012993507745709325, | |
| "loss": 0.7734, | |
| "step": 8920 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00012954939898438, | |
| "loss": 0.7711, | |
| "step": 8940 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00012916372051166678, | |
| "loss": 0.769, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00012877804203895353, | |
| "loss": 0.7706, | |
| "step": 8980 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00012839236356624025, | |
| "loss": 0.7752, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.799389660358429, | |
| "eval_runtime": 16.516, | |
| "eval_samples_per_second": 121.094, | |
| "eval_steps_per_second": 1.938, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.000128006685093527, | |
| "loss": 0.7678, | |
| "step": 9020 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00012762100662081378, | |
| "loss": 0.7764, | |
| "step": 9040 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00012723532814810053, | |
| "loss": 0.7672, | |
| "step": 9060 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00012684964967538728, | |
| "loss": 0.7705, | |
| "step": 9080 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00012646397120267403, | |
| "loss": 0.7657, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00012607829272996078, | |
| "loss": 0.7648, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00012569261425724753, | |
| "loss": 0.7737, | |
| "step": 9140 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00012530693578453428, | |
| "loss": 0.7628, | |
| "step": 9160 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00012492125731182103, | |
| "loss": 0.767, | |
| "step": 9180 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0001245355788391078, | |
| "loss": 0.764, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.7991757988929749, | |
| "eval_runtime": 16.5416, | |
| "eval_samples_per_second": 120.907, | |
| "eval_steps_per_second": 1.935, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012414990036639455, | |
| "loss": 0.7658, | |
| "step": 9220 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012376422189368128, | |
| "loss": 0.7642, | |
| "step": 9240 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012337854342096802, | |
| "loss": 0.7611, | |
| "step": 9260 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0001229928649482548, | |
| "loss": 0.7665, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00012260718647554155, | |
| "loss": 0.7785, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0001222215080028283, | |
| "loss": 0.7673, | |
| "step": 9320 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00012183582953011504, | |
| "loss": 0.777, | |
| "step": 9340 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0001214501510574018, | |
| "loss": 0.7684, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00012106447258468855, | |
| "loss": 0.7694, | |
| "step": 9380 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0001206787941119753, | |
| "loss": 0.7634, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.7980849742889404, | |
| "eval_runtime": 16.5086, | |
| "eval_samples_per_second": 121.149, | |
| "eval_steps_per_second": 1.938, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00012031239956289772, | |
| "loss": 0.7636, | |
| "step": 9420 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00011992672109018447, | |
| "loss": 0.7629, | |
| "step": 9440 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00011954104261747122, | |
| "loss": 0.7724, | |
| "step": 9460 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011915536414475797, | |
| "loss": 0.7697, | |
| "step": 9480 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011876968567204474, | |
| "loss": 0.7574, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011838400719933149, | |
| "loss": 0.7719, | |
| "step": 9520 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00011799832872661822, | |
| "loss": 0.7761, | |
| "step": 9540 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00011761265025390497, | |
| "loss": 0.7693, | |
| "step": 9560 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00011722697178119174, | |
| "loss": 0.7687, | |
| "step": 9580 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00011684129330847849, | |
| "loss": 0.7758, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 0.7981218099594116, | |
| "eval_runtime": 16.5407, | |
| "eval_samples_per_second": 120.914, | |
| "eval_steps_per_second": 1.935, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00011645561483576524, | |
| "loss": 0.7603, | |
| "step": 9620 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00011606993636305199, | |
| "loss": 0.7579, | |
| "step": 9640 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00011568425789033875, | |
| "loss": 0.7673, | |
| "step": 9660 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0001152985794176255, | |
| "loss": 0.7745, | |
| "step": 9680 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011491290094491225, | |
| "loss": 0.758, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.000114527222472199, | |
| "loss": 0.7686, | |
| "step": 9720 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00011414154399948576, | |
| "loss": 0.7741, | |
| "step": 9740 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00011375586552677251, | |
| "loss": 0.7646, | |
| "step": 9760 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00011337018705405925, | |
| "loss": 0.7675, | |
| "step": 9780 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.000112984508581346, | |
| "loss": 0.7637, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.7970672845840454, | |
| "eval_runtime": 16.5386, | |
| "eval_samples_per_second": 120.929, | |
| "eval_steps_per_second": 1.935, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00011259883010863276, | |
| "loss": 0.7678, | |
| "step": 9820 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011221315163591951, | |
| "loss": 0.762, | |
| "step": 9840 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011182747316320626, | |
| "loss": 0.7653, | |
| "step": 9860 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011144179469049301, | |
| "loss": 0.7666, | |
| "step": 9880 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00011105611621777977, | |
| "loss": 0.7621, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00011067043774506652, | |
| "loss": 0.7715, | |
| "step": 9920 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00011028475927235327, | |
| "loss": 0.7605, | |
| "step": 9940 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00010989908079964002, | |
| "loss": 0.7618, | |
| "step": 9960 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00010951340232692679, | |
| "loss": 0.7726, | |
| "step": 9980 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010912772385421352, | |
| "loss": 0.7684, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.7967627048492432, | |
| "eval_runtime": 16.5033, | |
| "eval_samples_per_second": 121.188, | |
| "eval_steps_per_second": 1.939, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010874204538150027, | |
| "loss": 0.7666, | |
| "step": 10020 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010835636690878702, | |
| "loss": 0.7661, | |
| "step": 10040 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010797068843607378, | |
| "loss": 0.7621, | |
| "step": 10060 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010758500996336053, | |
| "loss": 0.7736, | |
| "step": 10080 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010719933149064728, | |
| "loss": 0.76, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010681365301793405, | |
| "loss": 0.764, | |
| "step": 10120 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0001064279745452208, | |
| "loss": 0.7697, | |
| "step": 10140 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00010604229607250755, | |
| "loss": 0.7602, | |
| "step": 10160 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0001056566175997943, | |
| "loss": 0.766, | |
| "step": 10180 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00010527093912708106, | |
| "loss": 0.7719, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.7964752912521362, | |
| "eval_runtime": 16.4947, | |
| "eval_samples_per_second": 121.251, | |
| "eval_steps_per_second": 1.94, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010488526065436781, | |
| "loss": 0.7653, | |
| "step": 10220 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010449958218165455, | |
| "loss": 0.7653, | |
| "step": 10240 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0001041139037089413, | |
| "loss": 0.7711, | |
| "step": 10260 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010372822523622806, | |
| "loss": 0.7729, | |
| "step": 10280 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010334254676351481, | |
| "loss": 0.7709, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010295686829080156, | |
| "loss": 0.7611, | |
| "step": 10320 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010257118981808831, | |
| "loss": 0.7607, | |
| "step": 10340 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00010218551134537507, | |
| "loss": 0.761, | |
| "step": 10360 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00010179983287266182, | |
| "loss": 0.7645, | |
| "step": 10380 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00010141415439994857, | |
| "loss": 0.7682, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.7955361008644104, | |
| "eval_runtime": 16.5066, | |
| "eval_samples_per_second": 121.164, | |
| "eval_steps_per_second": 1.939, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010102847592723531, | |
| "loss": 0.76, | |
| "step": 10420 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010064279745452208, | |
| "loss": 0.7653, | |
| "step": 10440 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010025711898180882, | |
| "loss": 0.7625, | |
| "step": 10460 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.987144050909557e-05, | |
| "loss": 0.764, | |
| "step": 10480 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.948576203638232e-05, | |
| "loss": 0.766, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.910008356366908e-05, | |
| "loss": 0.7656, | |
| "step": 10520 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.871440509095583e-05, | |
| "loss": 0.7698, | |
| "step": 10540 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.832872661824258e-05, | |
| "loss": 0.7635, | |
| "step": 10560 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.794304814552933e-05, | |
| "loss": 0.77, | |
| "step": 10580 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.75573696728161e-05, | |
| "loss": 0.7651, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.7953855395317078, | |
| "eval_runtime": 16.5084, | |
| "eval_samples_per_second": 121.15, | |
| "eval_steps_per_second": 1.938, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.717169120010285e-05, | |
| "loss": 0.7628, | |
| "step": 10620 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.67860127273896e-05, | |
| "loss": 0.7662, | |
| "step": 10640 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.640033425467633e-05, | |
| "loss": 0.7635, | |
| "step": 10660 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.60146557819631e-05, | |
| "loss": 0.7601, | |
| "step": 10680 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.562897730924984e-05, | |
| "loss": 0.7649, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.52432988365366e-05, | |
| "loss": 0.758, | |
| "step": 10720 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.485762036382334e-05, | |
| "loss": 0.767, | |
| "step": 10740 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.447194189111011e-05, | |
| "loss": 0.7559, | |
| "step": 10760 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.408626341839686e-05, | |
| "loss": 0.765, | |
| "step": 10780 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.37005849456836e-05, | |
| "loss": 0.7641, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 0.794941782951355, | |
| "eval_runtime": 16.5101, | |
| "eval_samples_per_second": 121.138, | |
| "eval_steps_per_second": 1.938, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.331490647297036e-05, | |
| "loss": 0.7691, | |
| "step": 10820 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.292922800025712e-05, | |
| "loss": 0.7611, | |
| "step": 10840 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.254354952754387e-05, | |
| "loss": 0.7609, | |
| "step": 10860 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.21578710548306e-05, | |
| "loss": 0.758, | |
| "step": 10880 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.177219258211736e-05, | |
| "loss": 0.7637, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.138651410940412e-05, | |
| "loss": 0.7645, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.100083563669087e-05, | |
| "loss": 0.7507, | |
| "step": 10940 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.061515716397762e-05, | |
| "loss": 0.7673, | |
| "step": 10960 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.022947869126437e-05, | |
| "loss": 0.7552, | |
| "step": 10980 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.984380021855113e-05, | |
| "loss": 0.7639, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 0.7940524220466614, | |
| "eval_runtime": 16.5029, | |
| "eval_samples_per_second": 121.19, | |
| "eval_steps_per_second": 1.939, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.945812174583788e-05, | |
| "loss": 0.7719, | |
| "step": 11020 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.907244327312463e-05, | |
| "loss": 0.7641, | |
| "step": 11040 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.868676480041138e-05, | |
| "loss": 0.7614, | |
| "step": 11060 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.830108632769814e-05, | |
| "loss": 0.7785, | |
| "step": 11080 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.79154078549849e-05, | |
| "loss": 0.7756, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.752972938227163e-05, | |
| "loss": 0.7645, | |
| "step": 11120 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.714405090955838e-05, | |
| "loss": 0.7621, | |
| "step": 11140 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.675837243684514e-05, | |
| "loss": 0.7662, | |
| "step": 11160 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.637269396413189e-05, | |
| "loss": 0.7617, | |
| "step": 11180 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.598701549141864e-05, | |
| "loss": 0.7683, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 0.7937352061271667, | |
| "eval_runtime": 16.5052, | |
| "eval_samples_per_second": 121.174, | |
| "eval_steps_per_second": 1.939, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.560133701870539e-05, | |
| "loss": 0.7635, | |
| "step": 11220 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.521565854599216e-05, | |
| "loss": 0.7622, | |
| "step": 11240 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.48299800732789e-05, | |
| "loss": 0.7616, | |
| "step": 11260 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.444430160056565e-05, | |
| "loss": 0.7558, | |
| "step": 11280 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.40586231278524e-05, | |
| "loss": 0.7714, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.367294465513917e-05, | |
| "loss": 0.7676, | |
| "step": 11320 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.32872661824259e-05, | |
| "loss": 0.7623, | |
| "step": 11340 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.290158770971265e-05, | |
| "loss": 0.7608, | |
| "step": 11360 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.251590923699942e-05, | |
| "loss": 0.7746, | |
| "step": 11380 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.213023076428617e-05, | |
| "loss": 0.7684, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.7929428219795227, | |
| "eval_runtime": 16.7561, | |
| "eval_samples_per_second": 119.359, | |
| "eval_steps_per_second": 1.91, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.174455229157292e-05, | |
| "loss": 0.7628, | |
| "step": 11420 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.135887381885967e-05, | |
| "loss": 0.7614, | |
| "step": 11440 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.099247926978209e-05, | |
| "loss": 0.7616, | |
| "step": 11460 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.060680079706884e-05, | |
| "loss": 0.7614, | |
| "step": 11480 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.022112232435559e-05, | |
| "loss": 0.7684, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.983544385164233e-05, | |
| "loss": 0.7663, | |
| "step": 11520 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.94497653789291e-05, | |
| "loss": 0.7621, | |
| "step": 11540 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.906408690621584e-05, | |
| "loss": 0.77, | |
| "step": 11560 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.867840843350259e-05, | |
| "loss": 0.7629, | |
| "step": 11580 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.829272996078934e-05, | |
| "loss": 0.7592, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.7931132316589355, | |
| "eval_runtime": 16.4886, | |
| "eval_samples_per_second": 121.296, | |
| "eval_steps_per_second": 1.941, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.79070514880761e-05, | |
| "loss": 0.7593, | |
| "step": 11620 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.752137301536285e-05, | |
| "loss": 0.7579, | |
| "step": 11640 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.71356945426496e-05, | |
| "loss": 0.7666, | |
| "step": 11660 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.675001606993635e-05, | |
| "loss": 0.7573, | |
| "step": 11680 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.636433759722312e-05, | |
| "loss": 0.7654, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.597865912450986e-05, | |
| "loss": 0.7637, | |
| "step": 11720 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.559298065179661e-05, | |
| "loss": 0.7638, | |
| "step": 11740 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.520730217908335e-05, | |
| "loss": 0.7538, | |
| "step": 11760 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.482162370637011e-05, | |
| "loss": 0.7598, | |
| "step": 11780 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.443594523365686e-05, | |
| "loss": 0.7577, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 0.7928204536437988, | |
| "eval_runtime": 16.5434, | |
| "eval_samples_per_second": 120.894, | |
| "eval_steps_per_second": 1.934, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.405026676094361e-05, | |
| "loss": 0.7561, | |
| "step": 11820 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.366458828823038e-05, | |
| "loss": 0.7557, | |
| "step": 11840 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.327890981551713e-05, | |
| "loss": 0.7606, | |
| "step": 11860 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.289323134280388e-05, | |
| "loss": 0.7575, | |
| "step": 11880 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.250755287009063e-05, | |
| "loss": 0.7557, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.212187439737738e-05, | |
| "loss": 0.7687, | |
| "step": 11920 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.173619592466414e-05, | |
| "loss": 0.7647, | |
| "step": 11940 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.135051745195089e-05, | |
| "loss": 0.7608, | |
| "step": 11960 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.096483897923764e-05, | |
| "loss": 0.7624, | |
| "step": 11980 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.057916050652439e-05, | |
| "loss": 0.7651, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_loss": 0.7917994856834412, | |
| "eval_runtime": 16.5312, | |
| "eval_samples_per_second": 120.983, | |
| "eval_steps_per_second": 1.936, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.019348203381114e-05, | |
| "loss": 0.7678, | |
| "step": 12020 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.980780356109789e-05, | |
| "loss": 0.7606, | |
| "step": 12040 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.942212508838465e-05, | |
| "loss": 0.7607, | |
| "step": 12060 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.90364466156714e-05, | |
| "loss": 0.763, | |
| "step": 12080 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.865076814295815e-05, | |
| "loss": 0.7669, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.82650896702449e-05, | |
| "loss": 0.755, | |
| "step": 12120 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.787941119753165e-05, | |
| "loss": 0.7611, | |
| "step": 12140 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.74937327248184e-05, | |
| "loss": 0.7576, | |
| "step": 12160 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.710805425210516e-05, | |
| "loss": 0.7581, | |
| "step": 12180 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.672237577939191e-05, | |
| "loss": 0.7647, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 0.7914180755615234, | |
| "eval_runtime": 16.5021, | |
| "eval_samples_per_second": 121.196, | |
| "eval_steps_per_second": 1.939, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.633669730667866e-05, | |
| "loss": 0.7582, | |
| "step": 12220 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.595101883396541e-05, | |
| "loss": 0.7531, | |
| "step": 12240 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.556534036125216e-05, | |
| "loss": 0.7526, | |
| "step": 12260 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.517966188853891e-05, | |
| "loss": 0.7701, | |
| "step": 12280 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.479398341582568e-05, | |
| "loss": 0.7662, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.440830494311241e-05, | |
| "loss": 0.7541, | |
| "step": 12320 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.402262647039918e-05, | |
| "loss": 0.7578, | |
| "step": 12340 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.363694799768592e-05, | |
| "loss": 0.7569, | |
| "step": 12360 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.325126952497267e-05, | |
| "loss": 0.7635, | |
| "step": 12380 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.286559105225942e-05, | |
| "loss": 0.7618, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 0.7912635207176208, | |
| "eval_runtime": 16.4984, | |
| "eval_samples_per_second": 121.224, | |
| "eval_steps_per_second": 1.94, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.247991257954619e-05, | |
| "loss": 0.7536, | |
| "step": 12420 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.209423410683292e-05, | |
| "loss": 0.7478, | |
| "step": 12440 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.170855563411969e-05, | |
| "loss": 0.745, | |
| "step": 12460 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.132287716140644e-05, | |
| "loss": 0.7611, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.0937198688693187e-05, | |
| "loss": 0.763, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.0551520215979936e-05, | |
| "loss": 0.7647, | |
| "step": 12520 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.016584174326669e-05, | |
| "loss": 0.7621, | |
| "step": 12540 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.978016327055344e-05, | |
| "loss": 0.7568, | |
| "step": 12560 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.93944847978402e-05, | |
| "loss": 0.7613, | |
| "step": 12580 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.900880632512694e-05, | |
| "loss": 0.7568, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.7910023331642151, | |
| "eval_runtime": 16.5022, | |
| "eval_samples_per_second": 121.196, | |
| "eval_steps_per_second": 1.939, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.86231278524137e-05, | |
| "loss": 0.7636, | |
| "step": 12620 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.823744937970045e-05, | |
| "loss": 0.7657, | |
| "step": 12640 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.7851770906987205e-05, | |
| "loss": 0.7703, | |
| "step": 12660 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.7466092434273955e-05, | |
| "loss": 0.7557, | |
| "step": 12680 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.708041396156071e-05, | |
| "loss": 0.7667, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.6694735488847454e-05, | |
| "loss": 0.7605, | |
| "step": 12720 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.630905701613421e-05, | |
| "loss": 0.7549, | |
| "step": 12740 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.592337854342096e-05, | |
| "loss": 0.7592, | |
| "step": 12760 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.553770007070772e-05, | |
| "loss": 0.7654, | |
| "step": 12780 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.5171305521630135e-05, | |
| "loss": 0.7636, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 0.7906058430671692, | |
| "eval_runtime": 16.5012, | |
| "eval_samples_per_second": 121.203, | |
| "eval_steps_per_second": 1.939, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.478562704891688e-05, | |
| "loss": 0.7629, | |
| "step": 12820 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.4399948576203634e-05, | |
| "loss": 0.7688, | |
| "step": 12840 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.4014270103490384e-05, | |
| "loss": 0.7534, | |
| "step": 12860 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.362859163077714e-05, | |
| "loss": 0.76, | |
| "step": 12880 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.324291315806389e-05, | |
| "loss": 0.7561, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.285723468535065e-05, | |
| "loss": 0.7562, | |
| "step": 12920 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.247155621263739e-05, | |
| "loss": 0.7607, | |
| "step": 12940 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.2085877739924146e-05, | |
| "loss": 0.7612, | |
| "step": 12960 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.1700199267210896e-05, | |
| "loss": 0.7643, | |
| "step": 12980 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.131452079449765e-05, | |
| "loss": 0.7656, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 0.790121853351593, | |
| "eval_runtime": 16.5158, | |
| "eval_samples_per_second": 121.096, | |
| "eval_steps_per_second": 1.938, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.09288423217844e-05, | |
| "loss": 0.756, | |
| "step": 13020 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.054316384907115e-05, | |
| "loss": 0.7597, | |
| "step": 13040 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.01574853763579e-05, | |
| "loss": 0.7525, | |
| "step": 13060 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.977180690364466e-05, | |
| "loss": 0.7565, | |
| "step": 13080 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.938612843093141e-05, | |
| "loss": 0.7631, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.9000449958218165e-05, | |
| "loss": 0.7514, | |
| "step": 13120 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.861477148550491e-05, | |
| "loss": 0.7576, | |
| "step": 13140 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.8229093012791664e-05, | |
| "loss": 0.7539, | |
| "step": 13160 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.7843414540078414e-05, | |
| "loss": 0.7586, | |
| "step": 13180 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.745773606736517e-05, | |
| "loss": 0.7573, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 0.7899668216705322, | |
| "eval_runtime": 16.509, | |
| "eval_samples_per_second": 121.146, | |
| "eval_steps_per_second": 1.938, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.707205759465192e-05, | |
| "loss": 0.7671, | |
| "step": 13220 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.668637912193868e-05, | |
| "loss": 0.758, | |
| "step": 13240 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.630070064922542e-05, | |
| "loss": 0.7444, | |
| "step": 13260 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.5915022176512176e-05, | |
| "loss": 0.7548, | |
| "step": 13280 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.5529343703798926e-05, | |
| "loss": 0.7681, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.514366523108568e-05, | |
| "loss": 0.7599, | |
| "step": 13320 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.475798675837243e-05, | |
| "loss": 0.7631, | |
| "step": 13340 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.437230828565919e-05, | |
| "loss": 0.7565, | |
| "step": 13360 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.398662981294593e-05, | |
| "loss": 0.7586, | |
| "step": 13380 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.360095134023269e-05, | |
| "loss": 0.7526, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 0.7896500825881958, | |
| "eval_runtime": 16.5086, | |
| "eval_samples_per_second": 121.149, | |
| "eval_steps_per_second": 1.938, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.321527286751944e-05, | |
| "loss": 0.7591, | |
| "step": 13420 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.2829594394806195e-05, | |
| "loss": 0.7645, | |
| "step": 13440 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.2443915922092944e-05, | |
| "loss": 0.7532, | |
| "step": 13460 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.2077521373015355e-05, | |
| "loss": 0.746, | |
| "step": 13480 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.169184290030211e-05, | |
| "loss": 0.7534, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.130616442758886e-05, | |
| "loss": 0.7506, | |
| "step": 13520 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.092048595487562e-05, | |
| "loss": 0.7535, | |
| "step": 13540 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.053480748216237e-05, | |
| "loss": 0.7596, | |
| "step": 13560 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.0149129009449124e-05, | |
| "loss": 0.7686, | |
| "step": 13580 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.976345053673587e-05, | |
| "loss": 0.7537, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 0.7891342639923096, | |
| "eval_runtime": 16.5163, | |
| "eval_samples_per_second": 121.092, | |
| "eval_steps_per_second": 1.937, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.9377772064022624e-05, | |
| "loss": 0.7656, | |
| "step": 13620 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.8992093591309374e-05, | |
| "loss": 0.7515, | |
| "step": 13640 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.860641511859613e-05, | |
| "loss": 0.761, | |
| "step": 13660 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.822073664588288e-05, | |
| "loss": 0.7648, | |
| "step": 13680 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.783505817316963e-05, | |
| "loss": 0.7671, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.7449379700456386e-05, | |
| "loss": 0.7653, | |
| "step": 13720 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.7063701227743136e-05, | |
| "loss": 0.7583, | |
| "step": 13740 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.6678022755029886e-05, | |
| "loss": 0.7602, | |
| "step": 13760 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.629234428231664e-05, | |
| "loss": 0.7626, | |
| "step": 13780 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.590666580960339e-05, | |
| "loss": 0.7485, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 0.7891269326210022, | |
| "eval_runtime": 16.5041, | |
| "eval_samples_per_second": 121.182, | |
| "eval_steps_per_second": 1.939, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.552098733689014e-05, | |
| "loss": 0.7564, | |
| "step": 13820 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.51353088641769e-05, | |
| "loss": 0.7603, | |
| "step": 13840 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.474963039146365e-05, | |
| "loss": 0.7584, | |
| "step": 13860 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.43639519187504e-05, | |
| "loss": 0.7608, | |
| "step": 13880 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.3978273446037154e-05, | |
| "loss": 0.7535, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.3592594973323904e-05, | |
| "loss": 0.7614, | |
| "step": 13920 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.3206916500610654e-05, | |
| "loss": 0.7654, | |
| "step": 13940 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.282123802789741e-05, | |
| "loss": 0.7656, | |
| "step": 13960 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.243555955518416e-05, | |
| "loss": 0.756, | |
| "step": 13980 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.204988108247091e-05, | |
| "loss": 0.7653, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 0.7888805866241455, | |
| "eval_runtime": 16.5275, | |
| "eval_samples_per_second": 121.01, | |
| "eval_steps_per_second": 1.936, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.1664202609757666e-05, | |
| "loss": 0.7618, | |
| "step": 14020 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.1278524137044416e-05, | |
| "loss": 0.7588, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.0892845664331166e-05, | |
| "loss": 0.7625, | |
| "step": 14060 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.050716719161792e-05, | |
| "loss": 0.7532, | |
| "step": 14080 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.0121488718904672e-05, | |
| "loss": 0.7538, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.9735810246191422e-05, | |
| "loss": 0.7531, | |
| "step": 14120 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.9350131773478175e-05, | |
| "loss": 0.7551, | |
| "step": 14140 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.8964453300764928e-05, | |
| "loss": 0.7479, | |
| "step": 14160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.8578774828051678e-05, | |
| "loss": 0.7629, | |
| "step": 14180 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.819309635533843e-05, | |
| "loss": 0.7572, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 0.7884878516197205, | |
| "eval_runtime": 16.7595, | |
| "eval_samples_per_second": 119.335, | |
| "eval_steps_per_second": 1.909, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.7807417882625184e-05, | |
| "loss": 0.758, | |
| "step": 14220 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.7421739409911934e-05, | |
| "loss": 0.7608, | |
| "step": 14240 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.7036060937198687e-05, | |
| "loss": 0.7555, | |
| "step": 14260 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.6650382464485437e-05, | |
| "loss": 0.7512, | |
| "step": 14280 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.626470399177219e-05, | |
| "loss": 0.7488, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.5879025519058943e-05, | |
| "loss": 0.7532, | |
| "step": 14320 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.5493347046345693e-05, | |
| "loss": 0.7525, | |
| "step": 14340 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.5107668573632446e-05, | |
| "loss": 0.7662, | |
| "step": 14360 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.47219901009192e-05, | |
| "loss": 0.7583, | |
| "step": 14380 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.433631162820595e-05, | |
| "loss": 0.7442, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 0.7883238196372986, | |
| "eval_runtime": 16.474, | |
| "eval_samples_per_second": 121.403, | |
| "eval_steps_per_second": 1.942, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.3950633155492702e-05, | |
| "loss": 0.7612, | |
| "step": 14420 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.3564954682779455e-05, | |
| "loss": 0.7571, | |
| "step": 14440 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.3179276210066205e-05, | |
| "loss": 0.7511, | |
| "step": 14460 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.2793597737352958e-05, | |
| "loss": 0.7567, | |
| "step": 14480 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.2407919264639708e-05, | |
| "loss": 0.7555, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.202224079192646e-05, | |
| "loss": 0.7555, | |
| "step": 14520 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.1636562319213214e-05, | |
| "loss": 0.7509, | |
| "step": 14540 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.1250883846499964e-05, | |
| "loss": 0.7585, | |
| "step": 14560 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.0865205373786717e-05, | |
| "loss": 0.7621, | |
| "step": 14580 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.047952690107347e-05, | |
| "loss": 0.7601, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.7880419492721558, | |
| "eval_runtime": 16.6163, | |
| "eval_samples_per_second": 120.364, | |
| "eval_steps_per_second": 1.926, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.009384842836022e-05, | |
| "loss": 0.7574, | |
| "step": 14620 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.9708169955646973e-05, | |
| "loss": 0.7538, | |
| "step": 14640 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.9322491482933726e-05, | |
| "loss": 0.7611, | |
| "step": 14660 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.8936813010220476e-05, | |
| "loss": 0.7519, | |
| "step": 14680 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.855113453750723e-05, | |
| "loss": 0.7559, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.8165456064793982e-05, | |
| "loss": 0.7596, | |
| "step": 14720 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.7779777592080735e-05, | |
| "loss": 0.7564, | |
| "step": 14740 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.7394099119367485e-05, | |
| "loss": 0.7526, | |
| "step": 14760 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.7008420646654238e-05, | |
| "loss": 0.7624, | |
| "step": 14780 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.662274217394099e-05, | |
| "loss": 0.7569, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 0.7879504561424255, | |
| "eval_runtime": 16.5411, | |
| "eval_samples_per_second": 120.911, | |
| "eval_steps_per_second": 1.935, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.623706370122774e-05, | |
| "loss": 0.7543, | |
| "step": 14820 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.5851385228514494e-05, | |
| "loss": 0.7533, | |
| "step": 14840 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.5465706755801247e-05, | |
| "loss": 0.7579, | |
| "step": 14860 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.5080028283087997e-05, | |
| "loss": 0.7638, | |
| "step": 14880 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.469434981037475e-05, | |
| "loss": 0.7456, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.4308671337661502e-05, | |
| "loss": 0.7561, | |
| "step": 14920 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.3922992864948253e-05, | |
| "loss": 0.7626, | |
| "step": 14940 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.3537314392235005e-05, | |
| "loss": 0.7686, | |
| "step": 14960 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.3151635919521758e-05, | |
| "loss": 0.7512, | |
| "step": 14980 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.276595744680851e-05, | |
| "loss": 0.7526, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 0.7875809073448181, | |
| "eval_runtime": 16.5086, | |
| "eval_samples_per_second": 121.149, | |
| "eval_steps_per_second": 1.938, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.238027897409526e-05, | |
| "loss": 0.7582, | |
| "step": 15020 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.1994600501382012e-05, | |
| "loss": 0.7584, | |
| "step": 15040 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.1608922028668765e-05, | |
| "loss": 0.7643, | |
| "step": 15060 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.1223243555955517e-05, | |
| "loss": 0.7693, | |
| "step": 15080 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.0837565083242268e-05, | |
| "loss": 0.7591, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.0451886610529021e-05, | |
| "loss": 0.7482, | |
| "step": 15120 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.0066208137815773e-05, | |
| "loss": 0.7553, | |
| "step": 15140 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.680529665102524e-06, | |
| "loss": 0.7563, | |
| "step": 15160 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.294851192389277e-06, | |
| "loss": 0.7639, | |
| "step": 15180 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 8.909172719676029e-06, | |
| "loss": 0.7577, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 0.7872186303138733, | |
| "eval_runtime": 16.5027, | |
| "eval_samples_per_second": 121.192, | |
| "eval_steps_per_second": 1.939, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.523494246962782e-06, | |
| "loss": 0.7566, | |
| "step": 15220 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.137815774249533e-06, | |
| "loss": 0.7594, | |
| "step": 15240 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.752137301536285e-06, | |
| "loss": 0.758, | |
| "step": 15260 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.366458828823037e-06, | |
| "loss": 0.766, | |
| "step": 15280 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 6.980780356109789e-06, | |
| "loss": 0.7542, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 6.595101883396541e-06, | |
| "loss": 0.7643, | |
| "step": 15320 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 6.209423410683292e-06, | |
| "loss": 0.7638, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5.823744937970045e-06, | |
| "loss": 0.7629, | |
| "step": 15360 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.438066465256798e-06, | |
| "loss": 0.752, | |
| "step": 15380 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.052387992543549e-06, | |
| "loss": 0.7565, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 0.787341296672821, | |
| "eval_runtime": 16.5038, | |
| "eval_samples_per_second": 121.184, | |
| "eval_steps_per_second": 1.939, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.666709519830301e-06, | |
| "loss": 0.7558, | |
| "step": 15420 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 4.281031047117053e-06, | |
| "loss": 0.7683, | |
| "step": 15440 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.895352574403805e-06, | |
| "loss": 0.7454, | |
| "step": 15460 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.509674101690557e-06, | |
| "loss": 0.7566, | |
| "step": 15480 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.123995628977309e-06, | |
| "loss": 0.7536, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.738317156264061e-06, | |
| "loss": 0.7491, | |
| "step": 15520 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 2.3526386835508128e-06, | |
| "loss": 0.7571, | |
| "step": 15540 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.9669602108375647e-06, | |
| "loss": 0.7604, | |
| "step": 15560 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.581281738124317e-06, | |
| "loss": 0.7586, | |
| "step": 15580 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.1956032654110688e-06, | |
| "loss": 0.7599, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 0.7870123386383057, | |
| "eval_runtime": 16.493, | |
| "eval_samples_per_second": 121.263, | |
| "eval_steps_per_second": 1.94, | |
| "step": 15600 | |
| } | |
| ], | |
| "max_steps": 15657, | |
| "num_train_epochs": 3, | |
| "total_flos": 4.055629659314848e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |