| { | |
| "best_metric": 0.60627281665802, | |
| "best_model_checkpoint": "lora-alpaca-trading-candles/checkpoint-18600", | |
| "epoch": 2.983084826462849, | |
| "global_step": 18600, | |
| "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": 2.1224, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.5943, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.7997, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.6494, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6283, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002996775060467616, | |
| "loss": 0.6055, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00029935501209352324, | |
| "loss": 0.6061, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002990325181402848, | |
| "loss": 0.6085, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002987100241870465, | |
| "loss": 0.6014, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002983875302338081, | |
| "loss": 0.6009, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.6189413070678711, | |
| "eval_runtime": 81.8892, | |
| "eval_samples_per_second": 24.423, | |
| "eval_steps_per_second": 3.053, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002980650362805697, | |
| "loss": 0.6046, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00029774254232733135, | |
| "loss": 0.6035, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00029742004837409293, | |
| "loss": 0.6036, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00029709755442085457, | |
| "loss": 0.6074, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002967750604676162, | |
| "loss": 0.6004, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00029645256651437784, | |
| "loss": 0.605, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00029613007256113947, | |
| "loss": 0.595, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00029580757860790105, | |
| "loss": 0.5994, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002954850846546627, | |
| "loss": 0.5957, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002951625907014243, | |
| "loss": 0.6023, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.6173219680786133, | |
| "eval_runtime": 82.3581, | |
| "eval_samples_per_second": 24.284, | |
| "eval_steps_per_second": 3.036, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00029484009674818595, | |
| "loss": 0.5934, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002945176027949476, | |
| "loss": 0.5951, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002941951088417092, | |
| "loss": 0.5996, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002938726148884708, | |
| "loss": 0.5942, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029355012093523243, | |
| "loss": 0.5938, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029322762698199406, | |
| "loss": 0.5964, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002929051330287557, | |
| "loss": 0.5925, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029258263907551733, | |
| "loss": 0.5996, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002922601451222789, | |
| "loss": 0.5976, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00029193765116904054, | |
| "loss": 0.6009, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.6116005778312683, | |
| "eval_runtime": 82.3123, | |
| "eval_samples_per_second": 24.298, | |
| "eval_steps_per_second": 3.037, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002916151572158022, | |
| "loss": 0.5986, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002912926632625638, | |
| "loss": 0.5891, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00029097016930932544, | |
| "loss": 0.5983, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.000290647675356087, | |
| "loss": 0.5919, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00029032518140284866, | |
| "loss": 0.5969, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002900026874496103, | |
| "loss": 0.5971, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002896801934963719, | |
| "loss": 0.5915, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00028935769954313356, | |
| "loss": 0.5916, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00028903520558989514, | |
| "loss": 0.5945, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002887127116366568, | |
| "loss": 0.5982, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.6110595464706421, | |
| "eval_runtime": 82.5778, | |
| "eval_samples_per_second": 24.22, | |
| "eval_steps_per_second": 3.027, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002883902176834184, | |
| "loss": 0.601, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00028806772373018004, | |
| "loss": 0.5915, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00028774522977694167, | |
| "loss": 0.5946, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00028742273582370325, | |
| "loss": 0.5971, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00028710024187046494, | |
| "loss": 0.5961, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002867777479172265, | |
| "loss": 0.6021, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00028645525396398815, | |
| "loss": 0.5983, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002861327600107498, | |
| "loss": 0.5955, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002858102660575114, | |
| "loss": 0.5899, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.000285487772104273, | |
| "loss": 0.5956, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.6105289459228516, | |
| "eval_runtime": 82.6465, | |
| "eval_samples_per_second": 24.199, | |
| "eval_steps_per_second": 3.025, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00028516527815103463, | |
| "loss": 0.5972, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028484278419779627, | |
| "loss": 0.5977, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002845202902445579, | |
| "loss": 0.5988, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028419779629131953, | |
| "loss": 0.592, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002838753023380811, | |
| "loss": 0.5935, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00028355280838484275, | |
| "loss": 0.5993, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002832303144316044, | |
| "loss": 0.5997, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.000282907820478366, | |
| "loss": 0.588, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00028258532652512765, | |
| "loss": 0.5949, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00028226283257188923, | |
| "loss": 0.5915, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 0.6102217435836792, | |
| "eval_runtime": 82.7137, | |
| "eval_samples_per_second": 24.18, | |
| "eval_steps_per_second": 3.022, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00028194033861865086, | |
| "loss": 0.5936, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002816178446654125, | |
| "loss": 0.5951, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00028129535071217413, | |
| "loss": 0.591, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028097285675893576, | |
| "loss": 0.6245, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028065036280569734, | |
| "loss": 0.5964, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028032786885245903, | |
| "loss": 0.5962, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002800053748992206, | |
| "loss": 0.5983, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027968288094598224, | |
| "loss": 0.5928, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002793603869927439, | |
| "loss": 0.5944, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027903789303950546, | |
| "loss": 0.594, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.6102790236473083, | |
| "eval_runtime": 82.6061, | |
| "eval_samples_per_second": 24.211, | |
| "eval_steps_per_second": 3.026, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00027871539908626714, | |
| "loss": 0.592, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002783929051330287, | |
| "loss": 0.5976, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00027807041117979036, | |
| "loss": 0.5925, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000277747917226552, | |
| "loss": 0.5939, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027742542327331357, | |
| "loss": 0.5891, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027710292932007526, | |
| "loss": 0.6036, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00027678043536683684, | |
| "loss": 0.5949, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00027645794141359847, | |
| "loss": 0.5862, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002761354474603601, | |
| "loss": 0.6025, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00027581295350712174, | |
| "loss": 0.5963, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.6100178360939026, | |
| "eval_runtime": 82.3733, | |
| "eval_samples_per_second": 24.28, | |
| "eval_steps_per_second": 3.035, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002754904595538833, | |
| "loss": 0.6012, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00027516796560064495, | |
| "loss": 0.5866, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002748454716474066, | |
| "loss": 0.595, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002745229776941682, | |
| "loss": 0.5929, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00027420048374092985, | |
| "loss": 0.594, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00027387798978769143, | |
| "loss": 0.5904, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00027355549583445306, | |
| "loss": 0.5878, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002732330018812147, | |
| "loss": 0.5981, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00027291050792797633, | |
| "loss": 0.5958, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00027258801397473797, | |
| "loss": 0.589, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 0.609899640083313, | |
| "eval_runtime": 83.0673, | |
| "eval_samples_per_second": 24.077, | |
| "eval_steps_per_second": 3.01, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00027226552002149954, | |
| "loss": 0.6015, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002719430260682612, | |
| "loss": 0.5978, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002716205321150228, | |
| "loss": 0.5923, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00027129803816178445, | |
| "loss": 0.5933, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002709755442085461, | |
| "loss": 0.5846, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00027065305025530766, | |
| "loss": 0.5992, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00027033055630206935, | |
| "loss": 0.5943, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002700080623488309, | |
| "loss": 0.5954, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00026968556839559256, | |
| "loss": 0.5931, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002693630744423542, | |
| "loss": 0.5925, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.6094837784767151, | |
| "eval_runtime": 82.8167, | |
| "eval_samples_per_second": 24.15, | |
| "eval_steps_per_second": 3.019, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00026904058048911577, | |
| "loss": 0.595, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00026871808653587746, | |
| "loss": 0.5933, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00026839559258263904, | |
| "loss": 0.5958, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002680730986294007, | |
| "loss": 0.5897, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002677506046761623, | |
| "loss": 0.5889, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00026742811072292394, | |
| "loss": 0.6007, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002671056167696856, | |
| "loss": 0.591, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00026678312281644715, | |
| "loss": 0.5868, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002664606288632088, | |
| "loss": 0.589, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002661381349099704, | |
| "loss": 0.5919, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.6094632148742676, | |
| "eval_runtime": 83.078, | |
| "eval_samples_per_second": 24.074, | |
| "eval_steps_per_second": 3.009, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00026581564095673205, | |
| "loss": 0.5983, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00026549314700349363, | |
| "loss": 0.5958, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00026517065305025527, | |
| "loss": 0.5902, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002648481590970169, | |
| "loss": 0.5953, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00026452566514377854, | |
| "loss": 0.5982, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00026420317119054017, | |
| "loss": 0.5902, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00026388067723730175, | |
| "loss": 0.5899, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002635581832840634, | |
| "loss": 0.5948, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.000263235689330825, | |
| "loss": 0.5896, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00026291319537758665, | |
| "loss": 0.5922, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.6090299487113953, | |
| "eval_runtime": 82.9058, | |
| "eval_samples_per_second": 24.124, | |
| "eval_steps_per_second": 3.015, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002625907014243483, | |
| "loss": 0.5976, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00026226820747110986, | |
| "loss": 0.593, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00026194571351787155, | |
| "loss": 0.5987, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00026162321956463313, | |
| "loss": 0.5886, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00026130072561139476, | |
| "loss": 0.5937, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002609782316581564, | |
| "loss": 0.5878, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.000260655737704918, | |
| "loss": 0.5932, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00026033324375167966, | |
| "loss": 0.5968, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00026001074979844124, | |
| "loss": 0.5925, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002596882558452029, | |
| "loss": 0.5882, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.609171986579895, | |
| "eval_runtime": 82.3867, | |
| "eval_samples_per_second": 24.276, | |
| "eval_steps_per_second": 3.034, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002593657618919645, | |
| "loss": 0.5948, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00025904326793872614, | |
| "loss": 0.5928, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002587207739854878, | |
| "loss": 0.6007, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00025839828003224936, | |
| "loss": 0.5954, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.000258075786079011, | |
| "loss": 0.5976, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002577532921257726, | |
| "loss": 0.5876, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00025743079817253426, | |
| "loss": 0.5906, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002571083042192959, | |
| "loss": 0.5953, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00025678581026605747, | |
| "loss": 0.5923, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002564633163128191, | |
| "loss": 0.6015, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.6090067028999329, | |
| "eval_runtime": 83.1007, | |
| "eval_samples_per_second": 24.067, | |
| "eval_steps_per_second": 3.008, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00025614082235958074, | |
| "loss": 0.5899, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00025581832840634237, | |
| "loss": 0.5953, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.000255495834453104, | |
| "loss": 0.5948, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002551733404998656, | |
| "loss": 0.5946, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002548508465466272, | |
| "loss": 0.6018, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00025452835259338885, | |
| "loss": 0.5957, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002542058586401505, | |
| "loss": 0.5934, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00025388336468691207, | |
| "loss": 0.5971, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00025356087073367375, | |
| "loss": 0.5903, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00025323837678043533, | |
| "loss": 0.594, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.6089543700218201, | |
| "eval_runtime": 83.1486, | |
| "eval_samples_per_second": 24.053, | |
| "eval_steps_per_second": 3.007, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00025291588282719697, | |
| "loss": 0.5916, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002525933888739586, | |
| "loss": 0.5914, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002522708949207202, | |
| "loss": 0.5992, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00025194840096748187, | |
| "loss": 0.6012, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00025162590701424345, | |
| "loss": 0.5863, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002513034130610051, | |
| "loss": 0.5947, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002509809191077667, | |
| "loss": 0.5998, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002506584251545283, | |
| "loss": 0.5884, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00025033593120129, | |
| "loss": 0.6021, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00025001343724805156, | |
| "loss": 0.5931, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.6089305281639099, | |
| "eval_runtime": 82.7488, | |
| "eval_samples_per_second": 24.17, | |
| "eval_steps_per_second": 3.021, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002496909432948132, | |
| "loss": 0.5944, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00024936844934157483, | |
| "loss": 0.5886, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00024904595538833646, | |
| "loss": 0.5974, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002487234614350981, | |
| "loss": 0.5928, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002484009674818597, | |
| "loss": 0.5881, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002480784735286213, | |
| "loss": 0.5999, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00024775597957538294, | |
| "loss": 0.5941, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002474334856221446, | |
| "loss": 0.5971, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002471109916689062, | |
| "loss": 0.5908, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002467884977156678, | |
| "loss": 0.6051, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.6087088584899902, | |
| "eval_runtime": 82.9672, | |
| "eval_samples_per_second": 24.106, | |
| "eval_steps_per_second": 3.013, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002464660037624294, | |
| "loss": 0.5909, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00024614350980919106, | |
| "loss": 0.5909, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002458210158559527, | |
| "loss": 0.5898, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002454985219027143, | |
| "loss": 0.5891, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002451760279494759, | |
| "loss": 0.5896, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00024485353399623754, | |
| "loss": 0.5899, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00024453104004299917, | |
| "loss": 0.5984, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002442085460897608, | |
| "loss": 0.5969, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002438860521365224, | |
| "loss": 0.5908, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00024356355818328404, | |
| "loss": 0.5929, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.6087647080421448, | |
| "eval_runtime": 82.8339, | |
| "eval_samples_per_second": 24.145, | |
| "eval_steps_per_second": 3.018, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00024324106423004565, | |
| "loss": 0.5976, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002429185702768073, | |
| "loss": 0.5862, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024259607632356892, | |
| "loss": 0.5943, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024227358237033052, | |
| "loss": 0.5852, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024195108841709216, | |
| "loss": 0.5984, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00024162859446385376, | |
| "loss": 0.5921, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00024130610051061543, | |
| "loss": 0.6005, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00024098360655737703, | |
| "loss": 0.5953, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00024066111260413864, | |
| "loss": 0.5919, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00024033861865090027, | |
| "loss": 0.5948, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.6086417436599731, | |
| "eval_runtime": 82.8938, | |
| "eval_samples_per_second": 24.127, | |
| "eval_steps_per_second": 3.016, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002400161246976619, | |
| "loss": 0.5918, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00023969363074442354, | |
| "loss": 0.5874, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00023937113679118515, | |
| "loss": 0.5918, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00023904864283794675, | |
| "loss": 0.5906, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0002387261488847084, | |
| "loss": 0.5976, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00023840365493147002, | |
| "loss": 0.5879, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00023808116097823163, | |
| "loss": 0.5982, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023775866702499326, | |
| "loss": 0.5969, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023743617307175487, | |
| "loss": 0.5832, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023711367911851653, | |
| "loss": 0.5839, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.6088613271713257, | |
| "eval_runtime": 82.8863, | |
| "eval_samples_per_second": 24.129, | |
| "eval_steps_per_second": 3.016, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023679118516527813, | |
| "loss": 0.5897, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00023646869121203974, | |
| "loss": 0.5929, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00023614619725880137, | |
| "loss": 0.5914, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.000235823703305563, | |
| "loss": 0.5909, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023550120935232464, | |
| "loss": 0.5918, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023517871539908625, | |
| "loss": 0.5917, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023485622144584785, | |
| "loss": 0.5955, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00023453372749260951, | |
| "loss": 0.5901, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00023421123353937112, | |
| "loss": 0.5876, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00023388873958613273, | |
| "loss": 0.5894, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.6085715293884277, | |
| "eval_runtime": 83.2471, | |
| "eval_samples_per_second": 24.025, | |
| "eval_steps_per_second": 3.003, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00023356624563289436, | |
| "loss": 0.5986, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00023324375167965597, | |
| "loss": 0.5943, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00023292125772641763, | |
| "loss": 0.5868, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00023259876377317924, | |
| "loss": 0.5888, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00023227626981994084, | |
| "loss": 0.5974, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00023195377586670248, | |
| "loss": 0.5879, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00023163128191346408, | |
| "loss": 0.5933, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00023130878796022574, | |
| "loss": 0.597, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00023098629400698735, | |
| "loss": 0.5946, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023066380005374896, | |
| "loss": 0.5951, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 0.6085190176963806, | |
| "eval_runtime": 83.1305, | |
| "eval_samples_per_second": 24.059, | |
| "eval_steps_per_second": 3.007, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023034130610051062, | |
| "loss": 0.5906, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023001881214727222, | |
| "loss": 0.5945, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00022969631819403386, | |
| "loss": 0.5892, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00022937382424079546, | |
| "loss": 0.594, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00022905133028755707, | |
| "loss": 0.5931, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00022872883633431873, | |
| "loss": 0.5974, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00022840634238108034, | |
| "loss": 0.5871, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00022808384842784194, | |
| "loss": 0.5919, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00022776135447460358, | |
| "loss": 0.5894, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00022743886052136518, | |
| "loss": 0.5862, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.6086148023605347, | |
| "eval_runtime": 83.5908, | |
| "eval_samples_per_second": 23.926, | |
| "eval_steps_per_second": 2.991, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00022711636656812684, | |
| "loss": 0.5912, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00022679387261488845, | |
| "loss": 0.6005, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00022647137866165006, | |
| "loss": 0.5891, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002261488847084117, | |
| "loss": 0.5963, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00022582639075517332, | |
| "loss": 0.5907, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00022550389680193496, | |
| "loss": 0.5948, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00022518140284869656, | |
| "loss": 0.5978, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00022485890889545817, | |
| "loss": 0.5975, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00022453641494221983, | |
| "loss": 0.5934, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00022421392098898144, | |
| "loss": 0.592, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.6084710359573364, | |
| "eval_runtime": 82.8821, | |
| "eval_samples_per_second": 24.131, | |
| "eval_steps_per_second": 3.016, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00022389142703574307, | |
| "loss": 0.5936, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00022356893308250468, | |
| "loss": 0.5898, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00022324643912926629, | |
| "loss": 0.5895, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00022292394517602795, | |
| "loss": 0.5885, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00022260145122278955, | |
| "loss": 0.5836, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00022227895726955116, | |
| "loss": 0.588, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0002219564633163128, | |
| "loss": 0.5933, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00022163396936307443, | |
| "loss": 0.6007, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00022131147540983606, | |
| "loss": 0.5976, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00022098898145659767, | |
| "loss": 0.5886, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.6084069609642029, | |
| "eval_runtime": 83.0728, | |
| "eval_samples_per_second": 24.075, | |
| "eval_steps_per_second": 3.009, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00022066648750335927, | |
| "loss": 0.6022, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00022034399355012093, | |
| "loss": 0.5898, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00022002149959688254, | |
| "loss": 0.5878, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00021969900564364417, | |
| "loss": 0.5958, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00021937651169040578, | |
| "loss": 0.5863, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002190540177371674, | |
| "loss": 0.5897, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00021873152378392905, | |
| "loss": 0.5893, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00021840902983069065, | |
| "loss": 0.5913, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002180865358774523, | |
| "loss": 0.5924, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002177640419242139, | |
| "loss": 0.595, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.6084703207015991, | |
| "eval_runtime": 83.4269, | |
| "eval_samples_per_second": 23.973, | |
| "eval_steps_per_second": 2.997, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00021744154797097553, | |
| "loss": 0.5887, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00021711905401773716, | |
| "loss": 0.5909, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00021679656006449877, | |
| "loss": 0.5935, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00021647406611126037, | |
| "loss": 0.602, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00021615157215802204, | |
| "loss": 0.5927, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00021582907820478364, | |
| "loss": 0.5963, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00021550658425154528, | |
| "loss": 0.5897, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00021518409029830688, | |
| "loss": 0.5902, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002148615963450685, | |
| "loss": 0.5879, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00021453910239183015, | |
| "loss": 0.5894, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.6084801554679871, | |
| "eval_runtime": 83.4424, | |
| "eval_samples_per_second": 23.969, | |
| "eval_steps_per_second": 2.996, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00021421660843859176, | |
| "loss": 0.5966, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002138941144853534, | |
| "loss": 0.5912, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.000213571620532115, | |
| "loss": 0.5895, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00021324912657887663, | |
| "loss": 0.5961, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00021292663262563826, | |
| "loss": 0.5938, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00021260413867239987, | |
| "loss": 0.5896, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00021228164471916148, | |
| "loss": 0.5999, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00021195915076592314, | |
| "loss": 0.595, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00021163665681268474, | |
| "loss": 0.5957, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00021131416285944638, | |
| "loss": 0.5816, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.6085809469223022, | |
| "eval_runtime": 82.9268, | |
| "eval_samples_per_second": 24.118, | |
| "eval_steps_per_second": 3.015, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00021099166890620798, | |
| "loss": 0.597, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002106691749529696, | |
| "loss": 0.5795, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00021034668099973125, | |
| "loss": 0.5969, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00021002418704649286, | |
| "loss": 0.592, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002097016930932545, | |
| "loss": 0.5941, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002093791991400161, | |
| "loss": 0.5919, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002090567051867777, | |
| "loss": 0.59, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00020873421123353937, | |
| "loss": 0.5915, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00020841171728030097, | |
| "loss": 0.5967, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002080892233270626, | |
| "loss": 0.5922, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.608452558517456, | |
| "eval_runtime": 83.4452, | |
| "eval_samples_per_second": 23.968, | |
| "eval_steps_per_second": 2.996, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00020776672937382424, | |
| "loss": 0.5859, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00020744423542058585, | |
| "loss": 0.5895, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00020712174146734748, | |
| "loss": 0.5848, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00020679924751410909, | |
| "loss": 0.5956, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002064767535608707, | |
| "loss": 0.5929, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00020615425960763235, | |
| "loss": 0.5888, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00020583176565439396, | |
| "loss": 0.5893, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002055092717011556, | |
| "loss": 0.5937, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002051867777479172, | |
| "loss": 0.5981, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002048642837946788, | |
| "loss": 0.5964, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.6083669066429138, | |
| "eval_runtime": 83.3491, | |
| "eval_samples_per_second": 23.995, | |
| "eval_steps_per_second": 2.999, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00020454178984144047, | |
| "loss": 0.5951, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00020421929588820207, | |
| "loss": 0.5915, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002038968019349637, | |
| "loss": 0.5914, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00020357430798172531, | |
| "loss": 0.5957, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00020325181402848695, | |
| "loss": 0.5885, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00020292932007524858, | |
| "loss": 0.5899, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0002026068261220102, | |
| "loss": 0.5978, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00020228433216877182, | |
| "loss": 0.5946, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00020196183821553345, | |
| "loss": 0.5984, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00020163934426229506, | |
| "loss": 0.5872, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.6081907749176025, | |
| "eval_runtime": 83.4032, | |
| "eval_samples_per_second": 23.98, | |
| "eval_steps_per_second": 2.997, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002013168503090567, | |
| "loss": 0.5918, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002009943563558183, | |
| "loss": 0.5899, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002006718624025799, | |
| "loss": 0.5901, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00020034936844934157, | |
| "loss": 0.5927, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00020002687449610318, | |
| "loss": 0.5996, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0001997043805428648, | |
| "loss": 0.5959, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00019938188658962642, | |
| "loss": 0.5929, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00019905939263638805, | |
| "loss": 0.5917, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00019873689868314968, | |
| "loss": 0.5935, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001984144047299113, | |
| "loss": 0.5955, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.6082538366317749, | |
| "eval_runtime": 83.3309, | |
| "eval_samples_per_second": 24.001, | |
| "eval_steps_per_second": 3.0, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00019809191077667292, | |
| "loss": 0.5849, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00019776941682343456, | |
| "loss": 0.5927, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00019744692287019616, | |
| "loss": 0.5883, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001971244289169578, | |
| "loss": 0.5921, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001968019349637194, | |
| "loss": 0.5884, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.000196479441010481, | |
| "loss": 0.5835, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00019615694705724267, | |
| "loss": 0.5918, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00019583445310400428, | |
| "loss": 0.5949, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0001955119591507659, | |
| "loss": 0.5908, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00019518946519752752, | |
| "loss": 0.5895, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 0.6080419421195984, | |
| "eval_runtime": 83.5935, | |
| "eval_samples_per_second": 23.925, | |
| "eval_steps_per_second": 2.991, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00019486697124428915, | |
| "loss": 0.5918, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00019454447729105078, | |
| "loss": 0.5891, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001942219833378124, | |
| "loss": 0.5909, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00019389948938457402, | |
| "loss": 0.5981, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00019357699543133566, | |
| "loss": 0.5905, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00019325450147809726, | |
| "loss": 0.5913, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0001929320075248589, | |
| "loss": 0.5885, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0001926095135716205, | |
| "loss": 0.5967, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00019228701961838217, | |
| "loss": 0.5907, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00019196452566514377, | |
| "loss": 0.5914, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 0.6082321405410767, | |
| "eval_runtime": 83.2497, | |
| "eval_samples_per_second": 24.024, | |
| "eval_steps_per_second": 3.003, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00019164203171190538, | |
| "loss": 0.5842, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.000191319537758667, | |
| "loss": 0.5925, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00019099704380542862, | |
| "loss": 0.5858, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00019067454985219025, | |
| "loss": 0.5875, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00019035205589895189, | |
| "loss": 0.5916, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0001900295619457135, | |
| "loss": 0.5972, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00018970706799247513, | |
| "loss": 0.5869, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00018938457403923676, | |
| "loss": 0.5937, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00018906208008599837, | |
| "loss": 0.5942, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00018873958613276, | |
| "loss": 0.5852, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.6080183386802673, | |
| "eval_runtime": 83.8653, | |
| "eval_samples_per_second": 23.848, | |
| "eval_steps_per_second": 2.981, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001884170921795216, | |
| "loss": 0.5909, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00018809459822628327, | |
| "loss": 0.5968, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00018777210427304487, | |
| "loss": 0.5896, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00018744961031980648, | |
| "loss": 0.5935, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00018712711636656811, | |
| "loss": 0.5935, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00018680462241332972, | |
| "loss": 0.5909, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00018648212846009138, | |
| "loss": 0.5914, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.000186159634506853, | |
| "loss": 0.5926, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001858371405536146, | |
| "loss": 0.5914, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00018551464660037623, | |
| "loss": 0.595, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.6081690788269043, | |
| "eval_runtime": 83.4491, | |
| "eval_samples_per_second": 23.967, | |
| "eval_steps_per_second": 2.996, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00018519215264713786, | |
| "loss": 0.587, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00018486965869389947, | |
| "loss": 0.5877, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001845471647406611, | |
| "loss": 0.5988, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0001842246707874227, | |
| "loss": 0.5959, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00018390217683418437, | |
| "loss": 0.5986, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00018357968288094598, | |
| "loss": 0.5864, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018325718892770758, | |
| "loss": 0.5915, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018293469497446922, | |
| "loss": 0.5893, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018261220102123082, | |
| "loss": 0.5926, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018228970706799248, | |
| "loss": 0.5965, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.6080557703971863, | |
| "eval_runtime": 83.3607, | |
| "eval_samples_per_second": 23.992, | |
| "eval_steps_per_second": 2.999, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0001819672131147541, | |
| "loss": 0.5909, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0001816447191615157, | |
| "loss": 0.595, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00018132222520827733, | |
| "loss": 0.5918, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00018099973125503894, | |
| "loss": 0.5898, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00018067723730180057, | |
| "loss": 0.5931, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0001803547433485622, | |
| "loss": 0.5887, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0001800322493953238, | |
| "loss": 0.5927, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00017970975544208544, | |
| "loss": 0.5911, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017938726148884708, | |
| "loss": 0.5916, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017906476753560868, | |
| "loss": 0.5931, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 0.607985258102417, | |
| "eval_runtime": 83.5156, | |
| "eval_samples_per_second": 23.948, | |
| "eval_steps_per_second": 2.993, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017874227358237032, | |
| "loss": 0.5903, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00017841977962913192, | |
| "loss": 0.5943, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00017809728567589358, | |
| "loss": 0.5976, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001777747917226552, | |
| "loss": 0.5954, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001774522977694168, | |
| "loss": 0.5919, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00017712980381617843, | |
| "loss": 0.5867, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00017680730986294004, | |
| "loss": 0.592, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0001764848159097017, | |
| "loss": 0.5919, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001761623219564633, | |
| "loss": 0.5943, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001758398280032249, | |
| "loss": 0.592, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.6081468462944031, | |
| "eval_runtime": 83.7403, | |
| "eval_samples_per_second": 23.883, | |
| "eval_steps_per_second": 2.985, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00017551733404998655, | |
| "loss": 0.595, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00017519484009674818, | |
| "loss": 0.5908, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00017487234614350979, | |
| "loss": 0.5953, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00017454985219027142, | |
| "loss": 0.5939, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00017422735823703303, | |
| "loss": 0.5949, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0001739048642837947, | |
| "loss": 0.597, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0001735823703305563, | |
| "loss": 0.5987, | |
| "step": 7940 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001732598763773179, | |
| "loss": 0.5976, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00017293738242407953, | |
| "loss": 0.5892, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00017261488847084114, | |
| "loss": 0.5919, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 0.6079828143119812, | |
| "eval_runtime": 83.5244, | |
| "eval_samples_per_second": 23.945, | |
| "eval_steps_per_second": 2.993, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0001722923945176028, | |
| "loss": 0.5977, | |
| "step": 8020 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0001719699005643644, | |
| "loss": 0.5958, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.000171647406611126, | |
| "loss": 0.5888, | |
| "step": 8060 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017132491265788765, | |
| "loss": 0.5953, | |
| "step": 8080 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017100241870464928, | |
| "loss": 0.5902, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017067992475141091, | |
| "loss": 0.5936, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00017035743079817252, | |
| "loss": 0.5918, | |
| "step": 8140 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00017003493684493413, | |
| "loss": 0.5952, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0001697124428916958, | |
| "loss": 0.588, | |
| "step": 8180 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0001693899489384574, | |
| "loss": 0.5804, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.6079012155532837, | |
| "eval_runtime": 83.6243, | |
| "eval_samples_per_second": 23.916, | |
| "eval_steps_per_second": 2.99, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.000169067454985219, | |
| "loss": 0.5991, | |
| "step": 8220 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00016874496103198063, | |
| "loss": 0.5937, | |
| "step": 8240 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00016842246707874224, | |
| "loss": 0.5914, | |
| "step": 8260 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0001680999731255039, | |
| "loss": 0.592, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0001677774791722655, | |
| "loss": 0.5897, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00016745498521902712, | |
| "loss": 0.5922, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00016713249126578875, | |
| "loss": 0.5944, | |
| "step": 8340 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00016680999731255038, | |
| "loss": 0.5925, | |
| "step": 8360 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00016648750335931202, | |
| "loss": 0.5904, | |
| "step": 8380 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00016616500940607362, | |
| "loss": 0.5908, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.6079640984535217, | |
| "eval_runtime": 83.4353, | |
| "eval_samples_per_second": 23.971, | |
| "eval_steps_per_second": 2.996, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00016584251545283523, | |
| "loss": 0.5949, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0001655200214995969, | |
| "loss": 0.5898, | |
| "step": 8440 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001651975275463585, | |
| "loss": 0.5881, | |
| "step": 8460 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001648750335931201, | |
| "loss": 0.5911, | |
| "step": 8480 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00016455253963988174, | |
| "loss": 0.5918, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00016423004568664334, | |
| "loss": 0.5928, | |
| "step": 8520 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.000163907551733405, | |
| "loss": 0.5916, | |
| "step": 8540 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0001635850577801666, | |
| "loss": 0.5903, | |
| "step": 8560 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00016326256382692822, | |
| "loss": 0.5897, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00016294006987368985, | |
| "loss": 0.5969, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.6079634428024292, | |
| "eval_runtime": 83.8122, | |
| "eval_samples_per_second": 23.863, | |
| "eval_steps_per_second": 2.983, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00016261757592045146, | |
| "loss": 0.587, | |
| "step": 8620 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00016229508196721312, | |
| "loss": 0.5929, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00016197258801397472, | |
| "loss": 0.5914, | |
| "step": 8660 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00016165009406073633, | |
| "loss": 0.5915, | |
| "step": 8680 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.000161327600107498, | |
| "loss": 0.5874, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0001610051061542596, | |
| "loss": 0.5862, | |
| "step": 8720 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00016068261220102123, | |
| "loss": 0.594, | |
| "step": 8740 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00016036011824778284, | |
| "loss": 0.5928, | |
| "step": 8760 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00016003762429454444, | |
| "loss": 0.5861, | |
| "step": 8780 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0001597151303413061, | |
| "loss": 0.5932, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 0.6077998280525208, | |
| "eval_runtime": 83.6323, | |
| "eval_samples_per_second": 23.914, | |
| "eval_steps_per_second": 2.989, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0001593926363880677, | |
| "loss": 0.5961, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00015907014243482932, | |
| "loss": 0.5913, | |
| "step": 8840 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00015874764848159095, | |
| "loss": 0.5963, | |
| "step": 8860 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00015842515452835256, | |
| "loss": 0.5927, | |
| "step": 8880 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00015810266057511422, | |
| "loss": 0.585, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00015778016662187583, | |
| "loss": 0.5898, | |
| "step": 8920 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00015745767266863743, | |
| "loss": 0.5958, | |
| "step": 8940 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00015713517871539907, | |
| "loss": 0.5832, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0001568126847621607, | |
| "loss": 0.591, | |
| "step": 8980 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00015649019080892233, | |
| "loss": 0.594, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.6079277396202087, | |
| "eval_runtime": 83.6924, | |
| "eval_samples_per_second": 23.897, | |
| "eval_steps_per_second": 2.987, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00015616769685568394, | |
| "loss": 0.5982, | |
| "step": 9020 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00015584520290244555, | |
| "loss": 0.5918, | |
| "step": 9040 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0001555227089492072, | |
| "loss": 0.5949, | |
| "step": 9060 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00015520021499596881, | |
| "loss": 0.5894, | |
| "step": 9080 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00015487772104273045, | |
| "loss": 0.5887, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00015455522708949205, | |
| "loss": 0.5896, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015423273313625366, | |
| "loss": 0.5933, | |
| "step": 9140 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015391023918301532, | |
| "loss": 0.5961, | |
| "step": 9160 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015358774522977693, | |
| "loss": 0.586, | |
| "step": 9180 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00015326525127653853, | |
| "loss": 0.5921, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.607754111289978, | |
| "eval_runtime": 83.89, | |
| "eval_samples_per_second": 23.841, | |
| "eval_steps_per_second": 2.98, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00015294275732330017, | |
| "loss": 0.5973, | |
| "step": 9220 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001526202633700618, | |
| "loss": 0.5917, | |
| "step": 9240 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015229776941682344, | |
| "loss": 0.5932, | |
| "step": 9260 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015197527546358504, | |
| "loss": 0.5966, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015165278151034665, | |
| "loss": 0.5984, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0001513302875571083, | |
| "loss": 0.5951, | |
| "step": 9320 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00015100779360386992, | |
| "loss": 0.5863, | |
| "step": 9340 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00015068529965063155, | |
| "loss": 0.593, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00015036280569739316, | |
| "loss": 0.5906, | |
| "step": 9380 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00015004031174415476, | |
| "loss": 0.5936, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 0.6078041791915894, | |
| "eval_runtime": 83.6959, | |
| "eval_samples_per_second": 23.896, | |
| "eval_steps_per_second": 2.987, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0001497178177909164, | |
| "loss": 0.5899, | |
| "step": 9420 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00014939532383767803, | |
| "loss": 0.5911, | |
| "step": 9440 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00014907282988443966, | |
| "loss": 0.5881, | |
| "step": 9460 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00014875033593120127, | |
| "loss": 0.5879, | |
| "step": 9480 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0001484278419779629, | |
| "loss": 0.5883, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001481053480247245, | |
| "loss": 0.5974, | |
| "step": 9520 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00014778285407148614, | |
| "loss": 0.5992, | |
| "step": 9540 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00014746036011824778, | |
| "loss": 0.5892, | |
| "step": 9560 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0001471378661650094, | |
| "loss": 0.5873, | |
| "step": 9580 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014681537221177102, | |
| "loss": 0.5905, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.607796847820282, | |
| "eval_runtime": 83.56, | |
| "eval_samples_per_second": 23.935, | |
| "eval_steps_per_second": 2.992, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014649287825853262, | |
| "loss": 0.589, | |
| "step": 9620 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00014617038430529426, | |
| "loss": 0.5866, | |
| "step": 9640 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0001458478903520559, | |
| "loss": 0.5895, | |
| "step": 9660 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00014552539639881752, | |
| "loss": 0.592, | |
| "step": 9680 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014520290244557913, | |
| "loss": 0.5954, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014488040849234076, | |
| "loss": 0.591, | |
| "step": 9720 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014455791453910237, | |
| "loss": 0.5925, | |
| "step": 9740 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.000144235420585864, | |
| "loss": 0.5938, | |
| "step": 9760 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0001439129266326256, | |
| "loss": 0.5928, | |
| "step": 9780 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00014359043267938725, | |
| "loss": 0.5979, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.6077319383621216, | |
| "eval_runtime": 83.3796, | |
| "eval_samples_per_second": 23.987, | |
| "eval_steps_per_second": 2.998, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00014326793872614888, | |
| "loss": 0.5922, | |
| "step": 9820 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0001429454447729105, | |
| "loss": 0.5865, | |
| "step": 9840 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014262295081967212, | |
| "loss": 0.5845, | |
| "step": 9860 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014230045686643373, | |
| "loss": 0.5896, | |
| "step": 9880 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00014197796291319536, | |
| "loss": 0.5905, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.000141655468959957, | |
| "loss": 0.5875, | |
| "step": 9920 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00014133297500671863, | |
| "loss": 0.5936, | |
| "step": 9940 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014101048105348023, | |
| "loss": 0.6014, | |
| "step": 9960 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014068798710024187, | |
| "loss": 0.5898, | |
| "step": 9980 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014036549314700347, | |
| "loss": 0.5895, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.6077406406402588, | |
| "eval_runtime": 83.5244, | |
| "eval_samples_per_second": 23.945, | |
| "eval_steps_per_second": 2.993, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0001400429991937651, | |
| "loss": 0.5883, | |
| "step": 10020 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0001397205052405267, | |
| "loss": 0.599, | |
| "step": 10040 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00013939801128728835, | |
| "loss": 0.5964, | |
| "step": 10060 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00013907551733404998, | |
| "loss": 0.5924, | |
| "step": 10080 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00013875302338081161, | |
| "loss": 0.5866, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00013843052942757322, | |
| "loss": 0.5946, | |
| "step": 10120 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00013810803547433483, | |
| "loss": 0.5953, | |
| "step": 10140 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00013778554152109646, | |
| "loss": 0.5992, | |
| "step": 10160 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0001374630475678581, | |
| "loss": 0.6, | |
| "step": 10180 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00013714055361461973, | |
| "loss": 0.596, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.607699453830719, | |
| "eval_runtime": 83.655, | |
| "eval_samples_per_second": 23.908, | |
| "eval_steps_per_second": 2.988, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00013681805966138133, | |
| "loss": 0.5904, | |
| "step": 10220 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00013649556570814297, | |
| "loss": 0.5906, | |
| "step": 10240 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013617307175490457, | |
| "loss": 0.5939, | |
| "step": 10260 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0001358505778016662, | |
| "loss": 0.5854, | |
| "step": 10280 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013552808384842784, | |
| "loss": 0.5917, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00013520558989518945, | |
| "loss": 0.5966, | |
| "step": 10320 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00013488309594195108, | |
| "loss": 0.5853, | |
| "step": 10340 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0001345606019887127, | |
| "loss": 0.5905, | |
| "step": 10360 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00013423810803547432, | |
| "loss": 0.5954, | |
| "step": 10380 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013391561408223593, | |
| "loss": 0.5992, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.6076706051826477, | |
| "eval_runtime": 83.9433, | |
| "eval_samples_per_second": 23.826, | |
| "eval_steps_per_second": 2.978, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013359312012899756, | |
| "loss": 0.5816, | |
| "step": 10420 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0001332706261757592, | |
| "loss": 0.5885, | |
| "step": 10440 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013294813222252083, | |
| "loss": 0.592, | |
| "step": 10460 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013262563826928244, | |
| "loss": 0.59, | |
| "step": 10480 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013230314431604407, | |
| "loss": 0.5903, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00013198065036280568, | |
| "loss": 0.5902, | |
| "step": 10520 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0001316581564095673, | |
| "loss": 0.5949, | |
| "step": 10540 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00013133566245632894, | |
| "loss": 0.5869, | |
| "step": 10560 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00013101316850309055, | |
| "loss": 0.5945, | |
| "step": 10580 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00013069067454985218, | |
| "loss": 0.5964, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.607550859451294, | |
| "eval_runtime": 83.5845, | |
| "eval_samples_per_second": 23.928, | |
| "eval_steps_per_second": 2.991, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0001303681805966138, | |
| "loss": 0.5986, | |
| "step": 10620 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00013004568664337542, | |
| "loss": 0.6024, | |
| "step": 10640 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00012972319269013706, | |
| "loss": 0.5901, | |
| "step": 10660 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00012940069873689866, | |
| "loss": 0.5902, | |
| "step": 10680 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0001290782047836603, | |
| "loss": 0.5921, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00012875571083042193, | |
| "loss": 0.5915, | |
| "step": 10720 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00012843321687718354, | |
| "loss": 0.5952, | |
| "step": 10740 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00012811072292394514, | |
| "loss": 0.5907, | |
| "step": 10760 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00012778822897070678, | |
| "loss": 0.5959, | |
| "step": 10780 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0001274657350174684, | |
| "loss": 0.5884, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.6075096726417542, | |
| "eval_runtime": 83.2167, | |
| "eval_samples_per_second": 24.034, | |
| "eval_steps_per_second": 3.004, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00012714324106423005, | |
| "loss": 0.5959, | |
| "step": 10820 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00012682074711099165, | |
| "loss": 0.5841, | |
| "step": 10840 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00012649825315775329, | |
| "loss": 0.5881, | |
| "step": 10860 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001261757592045149, | |
| "loss": 0.5845, | |
| "step": 10880 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00012585326525127653, | |
| "loss": 0.5918, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00012553077129803816, | |
| "loss": 0.5886, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00012520827734479977, | |
| "loss": 0.5941, | |
| "step": 10940 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0001248857833915614, | |
| "loss": 0.5949, | |
| "step": 10960 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00012456328943832303, | |
| "loss": 0.5906, | |
| "step": 10980 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00012424079548508464, | |
| "loss": 0.5963, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.6074970960617065, | |
| "eval_runtime": 83.4435, | |
| "eval_samples_per_second": 23.968, | |
| "eval_steps_per_second": 2.996, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012391830153184625, | |
| "loss": 0.5951, | |
| "step": 11020 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012359580757860788, | |
| "loss": 0.5896, | |
| "step": 11040 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012327331362536951, | |
| "loss": 0.5826, | |
| "step": 11060 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00012295081967213115, | |
| "loss": 0.5885, | |
| "step": 11080 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00012262832571889275, | |
| "loss": 0.5896, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0001223058317656544, | |
| "loss": 0.5921, | |
| "step": 11120 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00012198333781241601, | |
| "loss": 0.588, | |
| "step": 11140 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00012166084385917763, | |
| "loss": 0.5885, | |
| "step": 11160 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00012133834990593926, | |
| "loss": 0.5969, | |
| "step": 11180 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00012101585595270087, | |
| "loss": 0.5908, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.6075094938278198, | |
| "eval_runtime": 83.5597, | |
| "eval_samples_per_second": 23.935, | |
| "eval_steps_per_second": 2.992, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0001206933619994625, | |
| "loss": 0.5908, | |
| "step": 11220 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00012037086804622412, | |
| "loss": 0.5925, | |
| "step": 11240 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00012004837409298576, | |
| "loss": 0.5966, | |
| "step": 11260 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00011972588013974738, | |
| "loss": 0.5862, | |
| "step": 11280 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00011940338618650898, | |
| "loss": 0.5927, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011908089223327062, | |
| "loss": 0.598, | |
| "step": 11320 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011875839828003224, | |
| "loss": 0.582, | |
| "step": 11340 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011843590432679387, | |
| "loss": 0.5982, | |
| "step": 11360 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00011811341037355548, | |
| "loss": 0.5972, | |
| "step": 11380 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00011779091642031711, | |
| "loss": 0.5999, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 0.6074954867362976, | |
| "eval_runtime": 83.1861, | |
| "eval_samples_per_second": 24.042, | |
| "eval_steps_per_second": 3.005, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00011746842246707873, | |
| "loss": 0.5943, | |
| "step": 11420 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00011714592851384036, | |
| "loss": 0.5895, | |
| "step": 11440 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00011682343456060198, | |
| "loss": 0.5908, | |
| "step": 11460 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00011650094060736359, | |
| "loss": 0.5925, | |
| "step": 11480 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00011617844665412522, | |
| "loss": 0.5886, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00011585595270088686, | |
| "loss": 0.5832, | |
| "step": 11520 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00011553345874764848, | |
| "loss": 0.5889, | |
| "step": 11540 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00011521096479441008, | |
| "loss": 0.5895, | |
| "step": 11560 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011488847084117172, | |
| "loss": 0.5901, | |
| "step": 11580 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011456597688793334, | |
| "loss": 0.593, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 0.6075332760810852, | |
| "eval_runtime": 83.8045, | |
| "eval_samples_per_second": 23.865, | |
| "eval_steps_per_second": 2.983, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011424348293469497, | |
| "loss": 0.5991, | |
| "step": 11620 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00011392098898145659, | |
| "loss": 0.5968, | |
| "step": 11640 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00011359849502821821, | |
| "loss": 0.5929, | |
| "step": 11660 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00011327600107497983, | |
| "loss": 0.5917, | |
| "step": 11680 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00011295350712174146, | |
| "loss": 0.5948, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00011263101316850308, | |
| "loss": 0.5903, | |
| "step": 11720 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00011230851921526469, | |
| "loss": 0.5895, | |
| "step": 11740 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011198602526202633, | |
| "loss": 0.5956, | |
| "step": 11760 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011166353130878795, | |
| "loss": 0.5847, | |
| "step": 11780 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011134103735554958, | |
| "loss": 0.585, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 0.6074097156524658, | |
| "eval_runtime": 83.3467, | |
| "eval_samples_per_second": 23.996, | |
| "eval_steps_per_second": 3.0, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0001110185434023112, | |
| "loss": 0.5937, | |
| "step": 11820 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00011069604944907282, | |
| "loss": 0.5911, | |
| "step": 11840 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00011037355549583444, | |
| "loss": 0.5962, | |
| "step": 11860 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00011005106154259607, | |
| "loss": 0.5973, | |
| "step": 11880 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00010972856758935769, | |
| "loss": 0.5844, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00010940607363611931, | |
| "loss": 0.5893, | |
| "step": 11920 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00010908357968288093, | |
| "loss": 0.5852, | |
| "step": 11940 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010876108572964257, | |
| "loss": 0.5968, | |
| "step": 11960 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010843859177640419, | |
| "loss": 0.5973, | |
| "step": 11980 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010811609782316579, | |
| "loss": 0.5824, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.6074831485748291, | |
| "eval_runtime": 83.2845, | |
| "eval_samples_per_second": 24.014, | |
| "eval_steps_per_second": 3.002, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010779360386992743, | |
| "loss": 0.5889, | |
| "step": 12020 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010747110991668905, | |
| "loss": 0.5848, | |
| "step": 12040 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010714861596345068, | |
| "loss": 0.5851, | |
| "step": 12060 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0001068261220102123, | |
| "loss": 0.6018, | |
| "step": 12080 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010650362805697392, | |
| "loss": 0.5931, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010618113410373554, | |
| "loss": 0.5908, | |
| "step": 12120 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00010585864015049717, | |
| "loss": 0.5878, | |
| "step": 12140 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0001055361461972588, | |
| "loss": 0.5943, | |
| "step": 12160 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0001052136522440204, | |
| "loss": 0.589, | |
| "step": 12180 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010489115829078203, | |
| "loss": 0.5985, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.6074686646461487, | |
| "eval_runtime": 83.5238, | |
| "eval_samples_per_second": 23.945, | |
| "eval_steps_per_second": 2.993, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010456866433754367, | |
| "loss": 0.5897, | |
| "step": 12220 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010424617038430529, | |
| "loss": 0.5926, | |
| "step": 12240 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010392367643106692, | |
| "loss": 0.5931, | |
| "step": 12260 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010360118247782853, | |
| "loss": 0.5956, | |
| "step": 12280 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010327868852459015, | |
| "loss": 0.5889, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010295619457135178, | |
| "loss": 0.5945, | |
| "step": 12320 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0001026337006181134, | |
| "loss": 0.5881, | |
| "step": 12340 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010231120666487502, | |
| "loss": 0.595, | |
| "step": 12360 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00010198871271163664, | |
| "loss": 0.589, | |
| "step": 12380 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00010166621875839828, | |
| "loss": 0.5886, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.6073445081710815, | |
| "eval_runtime": 83.2878, | |
| "eval_samples_per_second": 24.013, | |
| "eval_steps_per_second": 3.002, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0001013437248051599, | |
| "loss": 0.5883, | |
| "step": 12420 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010102123085192153, | |
| "loss": 0.5972, | |
| "step": 12440 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010069873689868314, | |
| "loss": 0.5963, | |
| "step": 12460 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010037624294544476, | |
| "loss": 0.5926, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010005374899220639, | |
| "loss": 0.5919, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.973125503896801e-05, | |
| "loss": 0.5898, | |
| "step": 12520 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.940876108572963e-05, | |
| "loss": 0.5908, | |
| "step": 12540 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.908626713249125e-05, | |
| "loss": 0.5925, | |
| "step": 12560 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.876377317925288e-05, | |
| "loss": 0.5912, | |
| "step": 12580 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.84412792260145e-05, | |
| "loss": 0.59, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 0.6073500514030457, | |
| "eval_runtime": 83.3951, | |
| "eval_samples_per_second": 23.982, | |
| "eval_steps_per_second": 2.998, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.811878527277614e-05, | |
| "loss": 0.596, | |
| "step": 12620 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.779629131953774e-05, | |
| "loss": 0.5913, | |
| "step": 12640 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.747379736629938e-05, | |
| "loss": 0.5926, | |
| "step": 12660 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.7151303413061e-05, | |
| "loss": 0.591, | |
| "step": 12680 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.682880945982263e-05, | |
| "loss": 0.5871, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.650631550658424e-05, | |
| "loss": 0.5918, | |
| "step": 12720 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.618382155334586e-05, | |
| "loss": 0.5919, | |
| "step": 12740 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.586132760010749e-05, | |
| "loss": 0.5982, | |
| "step": 12760 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.553883364686911e-05, | |
| "loss": 0.5947, | |
| "step": 12780 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.521633969363075e-05, | |
| "loss": 0.5904, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 0.607369601726532, | |
| "eval_runtime": 83.4201, | |
| "eval_samples_per_second": 23.975, | |
| "eval_steps_per_second": 2.997, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.489384574039235e-05, | |
| "loss": 0.5936, | |
| "step": 12820 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.457135178715399e-05, | |
| "loss": 0.5836, | |
| "step": 12840 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.42488578339156e-05, | |
| "loss": 0.59, | |
| "step": 12860 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.392636388067724e-05, | |
| "loss": 0.5928, | |
| "step": 12880 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.360386992743885e-05, | |
| "loss": 0.5921, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.328137597420048e-05, | |
| "loss": 0.5919, | |
| "step": 12920 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.29588820209621e-05, | |
| "loss": 0.5966, | |
| "step": 12940 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.263638806772373e-05, | |
| "loss": 0.597, | |
| "step": 12960 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.231389411448534e-05, | |
| "loss": 0.5932, | |
| "step": 12980 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.199140016124696e-05, | |
| "loss": 0.5884, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.6073188185691833, | |
| "eval_runtime": 83.7205, | |
| "eval_samples_per_second": 23.889, | |
| "eval_steps_per_second": 2.986, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.16689062080086e-05, | |
| "loss": 0.588, | |
| "step": 13020 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.134641225477021e-05, | |
| "loss": 0.5908, | |
| "step": 13040 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.102391830153185e-05, | |
| "loss": 0.589, | |
| "step": 13060 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.070142434829345e-05, | |
| "loss": 0.5867, | |
| "step": 13080 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.037893039505509e-05, | |
| "loss": 0.5987, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.005643644181671e-05, | |
| "loss": 0.5874, | |
| "step": 13120 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.973394248857834e-05, | |
| "loss": 0.5894, | |
| "step": 13140 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.941144853533995e-05, | |
| "loss": 0.5939, | |
| "step": 13160 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.908895458210157e-05, | |
| "loss": 0.5887, | |
| "step": 13180 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.87664606288632e-05, | |
| "loss": 0.5861, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.607224702835083, | |
| "eval_runtime": 83.4876, | |
| "eval_samples_per_second": 23.956, | |
| "eval_steps_per_second": 2.994, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.844396667562482e-05, | |
| "loss": 0.5897, | |
| "step": 13220 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.812147272238646e-05, | |
| "loss": 0.5954, | |
| "step": 13240 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.779897876914806e-05, | |
| "loss": 0.5968, | |
| "step": 13260 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.74764848159097e-05, | |
| "loss": 0.5912, | |
| "step": 13280 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.715399086267132e-05, | |
| "loss": 0.5959, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.683149690943295e-05, | |
| "loss": 0.5905, | |
| "step": 13320 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.650900295619456e-05, | |
| "loss": 0.5954, | |
| "step": 13340 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.618650900295619e-05, | |
| "loss": 0.5889, | |
| "step": 13360 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.586401504971781e-05, | |
| "loss": 0.5895, | |
| "step": 13380 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.554152109647944e-05, | |
| "loss": 0.5852, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 0.6072360873222351, | |
| "eval_runtime": 83.3501, | |
| "eval_samples_per_second": 23.995, | |
| "eval_steps_per_second": 2.999, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.521902714324106e-05, | |
| "loss": 0.5812, | |
| "step": 13420 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.489653319000267e-05, | |
| "loss": 0.5899, | |
| "step": 13440 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.45740392367643e-05, | |
| "loss": 0.5825, | |
| "step": 13460 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.425154528352592e-05, | |
| "loss": 0.5917, | |
| "step": 13480 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.392905133028756e-05, | |
| "loss": 0.5887, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.360655737704916e-05, | |
| "loss": 0.59, | |
| "step": 13520 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.32840634238108e-05, | |
| "loss": 0.5906, | |
| "step": 13540 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.296156947057242e-05, | |
| "loss": 0.5909, | |
| "step": 13560 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.263907551733405e-05, | |
| "loss": 0.5883, | |
| "step": 13580 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.231658156409567e-05, | |
| "loss": 0.5919, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.6071310639381409, | |
| "eval_runtime": 83.4575, | |
| "eval_samples_per_second": 23.964, | |
| "eval_steps_per_second": 2.996, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.199408761085728e-05, | |
| "loss": 0.5927, | |
| "step": 13620 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.167159365761891e-05, | |
| "loss": 0.5922, | |
| "step": 13640 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.134909970438054e-05, | |
| "loss": 0.5946, | |
| "step": 13660 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.102660575114216e-05, | |
| "loss": 0.5834, | |
| "step": 13680 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.070411179790377e-05, | |
| "loss": 0.5884, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.03816178446654e-05, | |
| "loss": 0.587, | |
| "step": 13720 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.005912389142703e-05, | |
| "loss": 0.5948, | |
| "step": 13740 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.973662993818866e-05, | |
| "loss": 0.5888, | |
| "step": 13760 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.941413598495028e-05, | |
| "loss": 0.5885, | |
| "step": 13780 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.90916420317119e-05, | |
| "loss": 0.5929, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 0.6071040034294128, | |
| "eval_runtime": 83.4169, | |
| "eval_samples_per_second": 23.976, | |
| "eval_steps_per_second": 2.997, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.876914807847352e-05, | |
| "loss": 0.5989, | |
| "step": 13820 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.844665412523515e-05, | |
| "loss": 0.5933, | |
| "step": 13840 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.812416017199677e-05, | |
| "loss": 0.5899, | |
| "step": 13860 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.780166621875838e-05, | |
| "loss": 0.593, | |
| "step": 13880 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.747917226552001e-05, | |
| "loss": 0.5993, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.715667831228163e-05, | |
| "loss": 0.5907, | |
| "step": 13920 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.683418435904327e-05, | |
| "loss": 0.5895, | |
| "step": 13940 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.651169040580487e-05, | |
| "loss": 0.5946, | |
| "step": 13960 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.61891964525665e-05, | |
| "loss": 0.5914, | |
| "step": 13980 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.586670249932813e-05, | |
| "loss": 0.5874, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_loss": 0.6071457266807556, | |
| "eval_runtime": 83.3637, | |
| "eval_samples_per_second": 23.991, | |
| "eval_steps_per_second": 2.999, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.554420854608976e-05, | |
| "loss": 0.5882, | |
| "step": 14020 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.522171459285138e-05, | |
| "loss": 0.5903, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.4899220639613e-05, | |
| "loss": 0.59, | |
| "step": 14060 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.457672668637462e-05, | |
| "loss": 0.5951, | |
| "step": 14080 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.425423273313625e-05, | |
| "loss": 0.5876, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.393173877989786e-05, | |
| "loss": 0.5961, | |
| "step": 14120 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.36092448266595e-05, | |
| "loss": 0.589, | |
| "step": 14140 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.328675087342111e-05, | |
| "loss": 0.5836, | |
| "step": 14160 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.296425692018273e-05, | |
| "loss": 0.5883, | |
| "step": 14180 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.264176296694437e-05, | |
| "loss": 0.5927, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.6070078015327454, | |
| "eval_runtime": 83.5563, | |
| "eval_samples_per_second": 23.936, | |
| "eval_steps_per_second": 2.992, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.231926901370599e-05, | |
| "loss": 0.5895, | |
| "step": 14220 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.199677506046761e-05, | |
| "loss": 0.593, | |
| "step": 14240 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.167428110722923e-05, | |
| "loss": 0.5854, | |
| "step": 14260 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.135178715399086e-05, | |
| "loss": 0.5887, | |
| "step": 14280 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.102929320075248e-05, | |
| "loss": 0.5911, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.07067992475141e-05, | |
| "loss": 0.5878, | |
| "step": 14320 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.038430529427572e-05, | |
| "loss": 0.5913, | |
| "step": 14340 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.006181134103736e-05, | |
| "loss": 0.5868, | |
| "step": 14360 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.973931738779898e-05, | |
| "loss": 0.5978, | |
| "step": 14380 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.94168234345606e-05, | |
| "loss": 0.5927, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 0.6069301962852478, | |
| "eval_runtime": 83.3785, | |
| "eval_samples_per_second": 23.987, | |
| "eval_steps_per_second": 2.998, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.909432948132222e-05, | |
| "loss": 0.5838, | |
| "step": 14420 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.877183552808384e-05, | |
| "loss": 0.5929, | |
| "step": 14440 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.844934157484547e-05, | |
| "loss": 0.5853, | |
| "step": 14460 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.812684762160709e-05, | |
| "loss": 0.593, | |
| "step": 14480 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.780435366836871e-05, | |
| "loss": 0.587, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.748185971513033e-05, | |
| "loss": 0.5901, | |
| "step": 14520 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.715936576189196e-05, | |
| "loss": 0.5871, | |
| "step": 14540 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.683687180865358e-05, | |
| "loss": 0.5955, | |
| "step": 14560 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.65143778554152e-05, | |
| "loss": 0.5886, | |
| "step": 14580 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.619188390217684e-05, | |
| "loss": 0.5918, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 0.6069862842559814, | |
| "eval_runtime": 83.2688, | |
| "eval_samples_per_second": 24.019, | |
| "eval_steps_per_second": 3.002, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.586938994893844e-05, | |
| "loss": 0.5891, | |
| "step": 14620 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.554689599570008e-05, | |
| "loss": 0.5892, | |
| "step": 14640 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.52244020424617e-05, | |
| "loss": 0.5855, | |
| "step": 14660 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.490190808922332e-05, | |
| "loss": 0.5919, | |
| "step": 14680 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.457941413598494e-05, | |
| "loss": 0.5895, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.425692018274657e-05, | |
| "loss": 0.5938, | |
| "step": 14720 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.393442622950819e-05, | |
| "loss": 0.5935, | |
| "step": 14740 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.361193227626981e-05, | |
| "loss": 0.5913, | |
| "step": 14760 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.328943832303145e-05, | |
| "loss": 0.5898, | |
| "step": 14780 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.296694436979307e-05, | |
| "loss": 0.5945, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.6069702506065369, | |
| "eval_runtime": 83.2944, | |
| "eval_samples_per_second": 24.011, | |
| "eval_steps_per_second": 3.001, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.264445041655469e-05, | |
| "loss": 0.5912, | |
| "step": 14820 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.23219564633163e-05, | |
| "loss": 0.5909, | |
| "step": 14840 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.199946251007793e-05, | |
| "loss": 0.5871, | |
| "step": 14860 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.167696855683955e-05, | |
| "loss": 0.5889, | |
| "step": 14880 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.135447460360118e-05, | |
| "loss": 0.5879, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.10319806503628e-05, | |
| "loss": 0.5912, | |
| "step": 14920 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.0709486697124426e-05, | |
| "loss": 0.5874, | |
| "step": 14940 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.038699274388605e-05, | |
| "loss": 0.5885, | |
| "step": 14960 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.0080623488309586e-05, | |
| "loss": 0.5876, | |
| "step": 14980 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.975812953507121e-05, | |
| "loss": 0.5849, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.6070013046264648, | |
| "eval_runtime": 83.6124, | |
| "eval_samples_per_second": 23.92, | |
| "eval_steps_per_second": 2.99, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.943563558183283e-05, | |
| "loss": 0.5854, | |
| "step": 15020 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.911314162859446e-05, | |
| "loss": 0.588, | |
| "step": 15040 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.879064767535608e-05, | |
| "loss": 0.5884, | |
| "step": 15060 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.846815372211771e-05, | |
| "loss": 0.5893, | |
| "step": 15080 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.8145659768879334e-05, | |
| "loss": 0.5875, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.7823165815640954e-05, | |
| "loss": 0.5866, | |
| "step": 15120 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.750067186240258e-05, | |
| "loss": 0.5929, | |
| "step": 15140 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.7178177909164194e-05, | |
| "loss": 0.59, | |
| "step": 15160 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.685568395592582e-05, | |
| "loss": 0.595, | |
| "step": 15180 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.653319000268744e-05, | |
| "loss": 0.5941, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 0.6068729758262634, | |
| "eval_runtime": 83.4028, | |
| "eval_samples_per_second": 23.98, | |
| "eval_steps_per_second": 2.998, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.621069604944907e-05, | |
| "loss": 0.593, | |
| "step": 15220 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.588820209621069e-05, | |
| "loss": 0.5893, | |
| "step": 15240 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.5565708142972315e-05, | |
| "loss": 0.5835, | |
| "step": 15260 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.5243214189733935e-05, | |
| "loss": 0.5869, | |
| "step": 15280 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.492072023649556e-05, | |
| "loss": 0.5882, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.459822628325719e-05, | |
| "loss": 0.5942, | |
| "step": 15320 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.427573233001881e-05, | |
| "loss": 0.5818, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.3953238376780436e-05, | |
| "loss": 0.5974, | |
| "step": 15360 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.363074442354205e-05, | |
| "loss": 0.5935, | |
| "step": 15380 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.3308250470303676e-05, | |
| "loss": 0.5897, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 0.6068193912506104, | |
| "eval_runtime": 83.4516, | |
| "eval_samples_per_second": 23.966, | |
| "eval_steps_per_second": 2.996, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.2985756517065296e-05, | |
| "loss": 0.5887, | |
| "step": 15420 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.266326256382692e-05, | |
| "loss": 0.5904, | |
| "step": 15440 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.234076861058854e-05, | |
| "loss": 0.5887, | |
| "step": 15460 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.201827465735017e-05, | |
| "loss": 0.5854, | |
| "step": 15480 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.1695780704111797e-05, | |
| "loss": 0.5868, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.137328675087342e-05, | |
| "loss": 0.5922, | |
| "step": 15520 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.1050792797635044e-05, | |
| "loss": 0.5914, | |
| "step": 15540 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.0728298844396664e-05, | |
| "loss": 0.5973, | |
| "step": 15560 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.040580489115829e-05, | |
| "loss": 0.5882, | |
| "step": 15580 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.0083310937919904e-05, | |
| "loss": 0.5967, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 0.6067527532577515, | |
| "eval_runtime": 83.0971, | |
| "eval_samples_per_second": 24.068, | |
| "eval_steps_per_second": 3.009, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.976081698468154e-05, | |
| "loss": 0.5884, | |
| "step": 15620 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.943832303144315e-05, | |
| "loss": 0.5865, | |
| "step": 15640 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.911582907820478e-05, | |
| "loss": 0.5855, | |
| "step": 15660 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.8793335124966404e-05, | |
| "loss": 0.5926, | |
| "step": 15680 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.8470841171728025e-05, | |
| "loss": 0.5929, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.814834721848965e-05, | |
| "loss": 0.5997, | |
| "step": 15720 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.782585326525127e-05, | |
| "loss": 0.592, | |
| "step": 15740 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.75033593120129e-05, | |
| "loss": 0.5934, | |
| "step": 15760 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.718086535877452e-05, | |
| "loss": 0.5946, | |
| "step": 15780 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.6858371405536145e-05, | |
| "loss": 0.5881, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 0.6067208647727966, | |
| "eval_runtime": 83.4992, | |
| "eval_samples_per_second": 23.952, | |
| "eval_steps_per_second": 2.994, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.6535877452297765e-05, | |
| "loss": 0.5882, | |
| "step": 15820 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.621338349905939e-05, | |
| "loss": 0.5938, | |
| "step": 15840 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.5890889545821006e-05, | |
| "loss": 0.5908, | |
| "step": 15860 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.556839559258263e-05, | |
| "loss": 0.5964, | |
| "step": 15880 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.524590163934426e-05, | |
| "loss": 0.5909, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.492340768610588e-05, | |
| "loss": 0.5856, | |
| "step": 15920 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.4600913732867506e-05, | |
| "loss": 0.5856, | |
| "step": 15940 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.4278419779629126e-05, | |
| "loss": 0.5938, | |
| "step": 15960 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.395592582639075e-05, | |
| "loss": 0.5912, | |
| "step": 15980 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.363343187315237e-05, | |
| "loss": 0.5941, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 0.6066766381263733, | |
| "eval_runtime": 83.8427, | |
| "eval_samples_per_second": 23.854, | |
| "eval_steps_per_second": 2.982, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.3310937919914e-05, | |
| "loss": 0.5888, | |
| "step": 16020 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.298844396667562e-05, | |
| "loss": 0.5816, | |
| "step": 16040 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.266595001343725e-05, | |
| "loss": 0.5924, | |
| "step": 16060 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.2343456060198874e-05, | |
| "loss": 0.6001, | |
| "step": 16080 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.202096210696049e-05, | |
| "loss": 0.5897, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.1698468153722114e-05, | |
| "loss": 0.5932, | |
| "step": 16120 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.1375974200483734e-05, | |
| "loss": 0.5894, | |
| "step": 16140 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.105348024724536e-05, | |
| "loss": 0.5895, | |
| "step": 16160 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.073098629400698e-05, | |
| "loss": 0.5943, | |
| "step": 16180 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.040849234076861e-05, | |
| "loss": 0.5909, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 0.6066379547119141, | |
| "eval_runtime": 83.5749, | |
| "eval_samples_per_second": 23.931, | |
| "eval_steps_per_second": 2.991, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.008599838753023e-05, | |
| "loss": 0.5893, | |
| "step": 16220 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 3.9763504434291855e-05, | |
| "loss": 0.5891, | |
| "step": 16240 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.9441010481053475e-05, | |
| "loss": 0.5898, | |
| "step": 16260 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.91185165278151e-05, | |
| "loss": 0.5977, | |
| "step": 16280 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.879602257457673e-05, | |
| "loss": 0.5899, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.847352862133835e-05, | |
| "loss": 0.5891, | |
| "step": 16320 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.8151034668099976e-05, | |
| "loss": 0.5919, | |
| "step": 16340 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.782854071486159e-05, | |
| "loss": 0.5876, | |
| "step": 16360 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.7506046761623216e-05, | |
| "loss": 0.5874, | |
| "step": 16380 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.718355280838484e-05, | |
| "loss": 0.5914, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 0.6065989136695862, | |
| "eval_runtime": 83.5367, | |
| "eval_samples_per_second": 23.942, | |
| "eval_steps_per_second": 2.993, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.686105885514646e-05, | |
| "loss": 0.587, | |
| "step": 16420 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.653856490190809e-05, | |
| "loss": 0.5924, | |
| "step": 16440 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.621607094866971e-05, | |
| "loss": 0.5929, | |
| "step": 16460 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.589357699543133e-05, | |
| "loss": 0.5938, | |
| "step": 16480 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.5571083042192957e-05, | |
| "loss": 0.5943, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.524858908895458e-05, | |
| "loss": 0.592, | |
| "step": 16520 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.4926095135716204e-05, | |
| "loss": 0.5904, | |
| "step": 16540 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.460360118247783e-05, | |
| "loss": 0.5869, | |
| "step": 16560 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.428110722923945e-05, | |
| "loss": 0.5874, | |
| "step": 16580 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.395861327600107e-05, | |
| "loss": 0.586, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 0.6066107153892517, | |
| "eval_runtime": 83.5674, | |
| "eval_samples_per_second": 23.933, | |
| "eval_steps_per_second": 2.992, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.36361193227627e-05, | |
| "loss": 0.5901, | |
| "step": 16620 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.331362536952432e-05, | |
| "loss": 0.5897, | |
| "step": 16640 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.2991131416285944e-05, | |
| "loss": 0.5896, | |
| "step": 16660 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.2668637463047564e-05, | |
| "loss": 0.5884, | |
| "step": 16680 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.2346143509809185e-05, | |
| "loss": 0.5917, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.202364955657081e-05, | |
| "loss": 0.5888, | |
| "step": 16720 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.170115560333243e-05, | |
| "loss": 0.589, | |
| "step": 16740 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.137866165009406e-05, | |
| "loss": 0.5881, | |
| "step": 16760 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.1056167696855685e-05, | |
| "loss": 0.5909, | |
| "step": 16780 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.0733673743617305e-05, | |
| "loss": 0.587, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_loss": 0.6065407991409302, | |
| "eval_runtime": 83.5297, | |
| "eval_samples_per_second": 23.944, | |
| "eval_steps_per_second": 2.993, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.041117979037893e-05, | |
| "loss": 0.5947, | |
| "step": 16820 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.0088685837140552e-05, | |
| "loss": 0.5894, | |
| "step": 16840 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.9766191883902176e-05, | |
| "loss": 0.5938, | |
| "step": 16860 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.9443697930663796e-05, | |
| "loss": 0.5852, | |
| "step": 16880 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.912120397742542e-05, | |
| "loss": 0.5893, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.8798710024187043e-05, | |
| "loss": 0.5915, | |
| "step": 16920 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.8476216070948666e-05, | |
| "loss": 0.5958, | |
| "step": 16940 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.8153722117710293e-05, | |
| "loss": 0.5919, | |
| "step": 16960 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.7831228164471916e-05, | |
| "loss": 0.5998, | |
| "step": 16980 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.7508734211233537e-05, | |
| "loss": 0.5979, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 0.6064393520355225, | |
| "eval_runtime": 83.7117, | |
| "eval_samples_per_second": 23.892, | |
| "eval_steps_per_second": 2.986, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.718624025799516e-05, | |
| "loss": 0.5881, | |
| "step": 17020 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.6863746304756784e-05, | |
| "loss": 0.5822, | |
| "step": 17040 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.6541252351518407e-05, | |
| "loss": 0.5921, | |
| "step": 17060 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.621875839828003e-05, | |
| "loss": 0.5932, | |
| "step": 17080 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.589626444504165e-05, | |
| "loss": 0.5988, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.5573770491803274e-05, | |
| "loss": 0.5928, | |
| "step": 17120 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.5251276538564897e-05, | |
| "loss": 0.5899, | |
| "step": 17140 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.4928782585326524e-05, | |
| "loss": 0.5852, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.4606288632088148e-05, | |
| "loss": 0.5918, | |
| "step": 17180 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.428379467884977e-05, | |
| "loss": 0.5918, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 0.6064170002937317, | |
| "eval_runtime": 83.4786, | |
| "eval_samples_per_second": 23.958, | |
| "eval_steps_per_second": 2.995, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.3961300725611395e-05, | |
| "loss": 0.5917, | |
| "step": 17220 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.3638806772373015e-05, | |
| "loss": 0.5863, | |
| "step": 17240 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.3316312819134638e-05, | |
| "loss": 0.5916, | |
| "step": 17260 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.2993818865896262e-05, | |
| "loss": 0.5952, | |
| "step": 17280 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.2671324912657885e-05, | |
| "loss": 0.5958, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.234883095941951e-05, | |
| "loss": 0.5896, | |
| "step": 17320 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.2026337006181136e-05, | |
| "loss": 0.5897, | |
| "step": 17340 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.1703843052942756e-05, | |
| "loss": 0.594, | |
| "step": 17360 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.138134909970438e-05, | |
| "loss": 0.5931, | |
| "step": 17380 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.1058855146466003e-05, | |
| "loss": 0.5875, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 0.6064504384994507, | |
| "eval_runtime": 83.4439, | |
| "eval_samples_per_second": 23.968, | |
| "eval_steps_per_second": 2.996, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.0736361193227626e-05, | |
| "loss": 0.5886, | |
| "step": 17420 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.041386723998925e-05, | |
| "loss": 0.5906, | |
| "step": 17440 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.009137328675087e-05, | |
| "loss": 0.5915, | |
| "step": 17460 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.9768879333512493e-05, | |
| "loss": 0.5879, | |
| "step": 17480 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.9446385380274117e-05, | |
| "loss": 0.5863, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.912389142703574e-05, | |
| "loss": 0.5878, | |
| "step": 17520 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.8801397473797367e-05, | |
| "loss": 0.5872, | |
| "step": 17540 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.8478903520558987e-05, | |
| "loss": 0.5883, | |
| "step": 17560 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.815640956732061e-05, | |
| "loss": 0.5918, | |
| "step": 17580 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.7833915614082234e-05, | |
| "loss": 0.591, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_loss": 0.6063485145568848, | |
| "eval_runtime": 83.6891, | |
| "eval_samples_per_second": 23.898, | |
| "eval_steps_per_second": 2.987, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.7511421660843857e-05, | |
| "loss": 0.5927, | |
| "step": 17620 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.718892770760548e-05, | |
| "loss": 0.5865, | |
| "step": 17640 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.6866433754367104e-05, | |
| "loss": 0.5911, | |
| "step": 17660 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.6543939801128728e-05, | |
| "loss": 0.5873, | |
| "step": 17680 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.622144584789035e-05, | |
| "loss": 0.5907, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.5898951894651975e-05, | |
| "loss": 0.5877, | |
| "step": 17720 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.5576457941413598e-05, | |
| "loss": 0.5924, | |
| "step": 17740 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.525396398817522e-05, | |
| "loss": 0.5907, | |
| "step": 17760 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.4931470034936845e-05, | |
| "loss": 0.5935, | |
| "step": 17780 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.4608976081698467e-05, | |
| "loss": 0.5894, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 0.606357216835022, | |
| "eval_runtime": 83.4836, | |
| "eval_samples_per_second": 23.957, | |
| "eval_steps_per_second": 2.995, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.428648212846009e-05, | |
| "loss": 0.5899, | |
| "step": 17820 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.3963988175221714e-05, | |
| "loss": 0.5959, | |
| "step": 17840 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.3641494221983336e-05, | |
| "loss": 0.5887, | |
| "step": 17860 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.331900026874496e-05, | |
| "loss": 0.5888, | |
| "step": 17880 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.2996506315506584e-05, | |
| "loss": 0.5921, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.2674012362268206e-05, | |
| "loss": 0.5899, | |
| "step": 17920 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.235151840902983e-05, | |
| "loss": 0.5967, | |
| "step": 17940 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.2029024455791451e-05, | |
| "loss": 0.5932, | |
| "step": 17960 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.1706530502553076e-05, | |
| "loss": 0.5985, | |
| "step": 17980 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.13840365493147e-05, | |
| "loss": 0.5944, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 0.6062895655632019, | |
| "eval_runtime": 83.4829, | |
| "eval_samples_per_second": 23.957, | |
| "eval_steps_per_second": 2.995, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.1061542596076323e-05, | |
| "loss": 0.5942, | |
| "step": 18020 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.0739048642837945e-05, | |
| "loss": 0.5814, | |
| "step": 18040 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.0416554689599569e-05, | |
| "loss": 0.5896, | |
| "step": 18060 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.0094060736361194e-05, | |
| "loss": 0.5958, | |
| "step": 18080 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.771566783122816e-06, | |
| "loss": 0.5828, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.449072829884439e-06, | |
| "loss": 0.5978, | |
| "step": 18120 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.126578876646061e-06, | |
| "loss": 0.595, | |
| "step": 18140 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 8.804084923407686e-06, | |
| "loss": 0.5966, | |
| "step": 18160 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.481590970169308e-06, | |
| "loss": 0.5868, | |
| "step": 18180 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.159097016930933e-06, | |
| "loss": 0.5894, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 0.6062944531440735, | |
| "eval_runtime": 83.3214, | |
| "eval_samples_per_second": 24.003, | |
| "eval_steps_per_second": 3.0, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.836603063692555e-06, | |
| "loss": 0.588, | |
| "step": 18220 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.514109110454178e-06, | |
| "loss": 0.5939, | |
| "step": 18240 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.191615157215802e-06, | |
| "loss": 0.596, | |
| "step": 18260 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 6.869121203977424e-06, | |
| "loss": 0.5909, | |
| "step": 18280 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 6.546627250739049e-06, | |
| "loss": 0.5938, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 6.224133297500671e-06, | |
| "loss": 0.5887, | |
| "step": 18320 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5.901639344262295e-06, | |
| "loss": 0.586, | |
| "step": 18340 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5.579145391023918e-06, | |
| "loss": 0.5888, | |
| "step": 18360 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.256651437785541e-06, | |
| "loss": 0.5922, | |
| "step": 18380 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.934157484547164e-06, | |
| "loss": 0.5878, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 0.6062828302383423, | |
| "eval_runtime": 83.3962, | |
| "eval_samples_per_second": 23.982, | |
| "eval_steps_per_second": 2.998, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.611663531308788e-06, | |
| "loss": 0.5886, | |
| "step": 18420 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 4.28916957807041e-06, | |
| "loss": 0.5889, | |
| "step": 18440 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.966675624832034e-06, | |
| "loss": 0.5948, | |
| "step": 18460 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.6441816715936573e-06, | |
| "loss": 0.5896, | |
| "step": 18480 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.321687718355281e-06, | |
| "loss": 0.5901, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.9991937651169034e-06, | |
| "loss": 0.5917, | |
| "step": 18520 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.676699811878527e-06, | |
| "loss": 0.5878, | |
| "step": 18540 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 2.3542058586401504e-06, | |
| "loss": 0.5918, | |
| "step": 18560 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 2.031711905401774e-06, | |
| "loss": 0.5857, | |
| "step": 18580 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.7092179521633967e-06, | |
| "loss": 0.5928, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 0.60627281665802, | |
| "eval_runtime": 83.148, | |
| "eval_samples_per_second": 24.054, | |
| "eval_steps_per_second": 3.007, | |
| "step": 18600 | |
| } | |
| ], | |
| "max_steps": 18705, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.4177730269248225e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |