| { | |
| "best_metric": 0.3034871220588684, | |
| "best_model_checkpoint": "./Mistral/17-03-24-Weni-ZeroShot-3.3.35-Mistral-7b-Multilanguage-3.3.0_ZeroShot SFT Training with its best hyperparameters-2_max_steps-2344_batch_16_2024-03-17_ppid_9/checkpoint-2300", | |
| "epoch": 1.9607843137254903, | |
| "eval_steps": 50, | |
| "global_step": 2300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 5.4808268547058105, | |
| "learning_rate": 1.623931623931624e-05, | |
| "loss": 1.7023, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.232806444168091, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.1297, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.5450807809829712, | |
| "eval_runtime": 271.242, | |
| "eval_samples_per_second": 7.687, | |
| "eval_steps_per_second": 0.962, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.8864539265632629, | |
| "learning_rate": 4.9572649572649575e-05, | |
| "loss": 0.5849, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.8033413887023926, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.4593, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.6578605771064758, | |
| "learning_rate": 8.376068376068377e-05, | |
| "loss": 0.4425, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.42795854806900024, | |
| "eval_runtime": 271.0229, | |
| "eval_samples_per_second": 7.693, | |
| "eval_steps_per_second": 0.963, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.5158710479736328, | |
| "learning_rate": 0.00010085470085470086, | |
| "loss": 0.4249, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.4536530375480652, | |
| "learning_rate": 0.00011794871794871796, | |
| "loss": 0.4241, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.4137832820415497, | |
| "eval_runtime": 271.1041, | |
| "eval_samples_per_second": 7.691, | |
| "eval_steps_per_second": 0.963, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.3979959785938263, | |
| "learning_rate": 0.00013504273504273505, | |
| "loss": 0.4154, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.4166259467601776, | |
| "learning_rate": 0.00015213675213675214, | |
| "loss": 0.4107, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.40765708684921265, | |
| "learning_rate": 0.00016923076923076923, | |
| "loss": 0.4059, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.40599754452705383, | |
| "eval_runtime": 271.1072, | |
| "eval_samples_per_second": 7.691, | |
| "eval_steps_per_second": 0.963, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.39934784173965454, | |
| "learning_rate": 0.00018632478632478634, | |
| "loss": 0.3935, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.39337554574012756, | |
| "learning_rate": 0.00019999822653125876, | |
| "loss": 0.4125, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.4002617597579956, | |
| "eval_runtime": 271.1099, | |
| "eval_samples_per_second": 7.691, | |
| "eval_steps_per_second": 0.963, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.4723268449306488, | |
| "learning_rate": 0.00019993616172996704, | |
| "loss": 0.4074, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.4829658269882202, | |
| "learning_rate": 0.00019978548638541202, | |
| "loss": 0.3933, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.7815160155296326, | |
| "learning_rate": 0.00019954633409712276, | |
| "loss": 0.3948, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.3945770263671875, | |
| "eval_runtime": 271.0451, | |
| "eval_samples_per_second": 7.692, | |
| "eval_steps_per_second": 0.963, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.4525783956050873, | |
| "learning_rate": 0.00019921891691460983, | |
| "loss": 0.3777, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.3549365699291229, | |
| "learning_rate": 0.00019880352514934724, | |
| "loss": 0.3979, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.3886016309261322, | |
| "eval_runtime": 271.0939, | |
| "eval_samples_per_second": 7.691, | |
| "eval_steps_per_second": 0.963, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.38849011063575745, | |
| "learning_rate": 0.00019830052711736142, | |
| "loss": 0.3895, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.4513374865055084, | |
| "learning_rate": 0.00019771036881265598, | |
| "loss": 0.3866, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.4288094639778137, | |
| "learning_rate": 0.00019703357351176151, | |
| "loss": 0.3938, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.38462838530540466, | |
| "eval_runtime": 271.1664, | |
| "eval_samples_per_second": 7.689, | |
| "eval_steps_per_second": 0.963, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.3525382876396179, | |
| "learning_rate": 0.00019627074130976126, | |
| "loss": 0.3891, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.5788955688476562, | |
| "learning_rate": 0.0001954225485882039, | |
| "loss": 0.3739, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.3804500699043274, | |
| "eval_runtime": 271.0816, | |
| "eval_samples_per_second": 7.691, | |
| "eval_steps_per_second": 0.963, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.47232553362846375, | |
| "learning_rate": 0.00019448974741537525, | |
| "loss": 0.371, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.38733381032943726, | |
| "learning_rate": 0.0001934731648794609, | |
| "loss": 0.37, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.42200860381126404, | |
| "learning_rate": 0.00019237370235519077, | |
| "loss": 0.3726, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.3774518370628357, | |
| "eval_runtime": 271.1201, | |
| "eval_samples_per_second": 7.69, | |
| "eval_steps_per_second": 0.963, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.5560094118118286, | |
| "learning_rate": 0.00019119233470461558, | |
| "loss": 0.3754, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.3813556134700775, | |
| "learning_rate": 0.00018993010941272478, | |
| "loss": 0.363, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.37297067046165466, | |
| "eval_runtime": 271.0879, | |
| "eval_samples_per_second": 7.691, | |
| "eval_steps_per_second": 0.963, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.5384305715560913, | |
| "learning_rate": 0.0001885881456586713, | |
| "loss": 0.3656, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.4100024700164795, | |
| "learning_rate": 0.0001871676333234274, | |
| "loss": 0.3668, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.4203307628631592, | |
| "learning_rate": 0.0001856698319347513, | |
| "loss": 0.3718, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.3698495626449585, | |
| "eval_runtime": 271.0857, | |
| "eval_samples_per_second": 7.691, | |
| "eval_steps_per_second": 0.963, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.5422376990318298, | |
| "learning_rate": 0.0001840960695503995, | |
| "loss": 0.3813, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.41980084776878357, | |
| "learning_rate": 0.00018244774158057624, | |
| "loss": 0.3711, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.3666984438896179, | |
| "eval_runtime": 271.059, | |
| "eval_samples_per_second": 7.692, | |
| "eval_steps_per_second": 0.963, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.49988237023353577, | |
| "learning_rate": 0.00018072630955066288, | |
| "loss": 0.3669, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.4338107407093048, | |
| "learning_rate": 0.00017893329980532498, | |
| "loss": 0.3709, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.46425387263298035, | |
| "learning_rate": 0.0001770703021551463, | |
| "loss": 0.3665, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.36363786458969116, | |
| "eval_runtime": 271.1155, | |
| "eval_samples_per_second": 7.69, | |
| "eval_steps_per_second": 0.963, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.5348316431045532, | |
| "learning_rate": 0.00017513896846698882, | |
| "loss": 0.3574, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.4046632945537567, | |
| "learning_rate": 0.00017314101119932974, | |
| "loss": 0.3625, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.3617616891860962, | |
| "eval_runtime": 271.137, | |
| "eval_samples_per_second": 7.69, | |
| "eval_steps_per_second": 0.963, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.44371724128723145, | |
| "learning_rate": 0.00017107820188387327, | |
| "loss": 0.3752, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.4216190576553345, | |
| "learning_rate": 0.00016895236955478412, | |
| "loss": 0.3606, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.5870906114578247, | |
| "learning_rate": 0.00016676539912693501, | |
| "loss": 0.3756, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.3583546280860901, | |
| "eval_runtime": 271.1679, | |
| "eval_samples_per_second": 7.689, | |
| "eval_steps_per_second": 0.963, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.4018837511539459, | |
| "learning_rate": 0.00016451922972460643, | |
| "loss": 0.358, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.4688343107700348, | |
| "learning_rate": 0.00016221585296212054, | |
| "loss": 0.3493, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.35402199625968933, | |
| "eval_runtime": 271.1165, | |
| "eval_samples_per_second": 7.69, | |
| "eval_steps_per_second": 0.963, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.4941730797290802, | |
| "learning_rate": 0.00015985731117793353, | |
| "loss": 0.3502, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.4220365583896637, | |
| "learning_rate": 0.00015744569562375235, | |
| "loss": 0.3478, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.4305894374847412, | |
| "learning_rate": 0.00015498314461028157, | |
| "loss": 0.3585, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.3510061800479889, | |
| "eval_runtime": 271.1908, | |
| "eval_samples_per_second": 7.688, | |
| "eval_steps_per_second": 0.962, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.45022985339164734, | |
| "learning_rate": 0.00015247184161124415, | |
| "loss": 0.3558, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.4498714506626129, | |
| "learning_rate": 0.00014991401332735781, | |
| "loss": 0.3466, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.34707528352737427, | |
| "eval_runtime": 271.0841, | |
| "eval_samples_per_second": 7.691, | |
| "eval_steps_per_second": 0.963, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.49369582533836365, | |
| "learning_rate": 0.00014731192771198282, | |
| "loss": 0.3463, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.36855530738830566, | |
| "learning_rate": 0.00014466789196019257, | |
| "loss": 0.3428, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.501837968826294, | |
| "learning_rate": 0.00014198425046304942, | |
| "loss": 0.3483, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.34373167157173157, | |
| "eval_runtime": 271.0714, | |
| "eval_samples_per_second": 7.692, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.35614344477653503, | |
| "learning_rate": 0.00013926338272890026, | |
| "loss": 0.3322, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.5366308689117432, | |
| "learning_rate": 0.00013650770127353416, | |
| "loss": 0.343, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.3401084542274475, | |
| "eval_runtime": 271.1104, | |
| "eval_samples_per_second": 7.691, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.46004125475883484, | |
| "learning_rate": 0.00013371964948107344, | |
| "loss": 0.3417, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.5817845463752747, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.332, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.9298326969146729, | |
| "learning_rate": 0.00012805634973870103, | |
| "loss": 0.3373, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.3367879390716553, | |
| "eval_runtime": 271.219, | |
| "eval_samples_per_second": 7.688, | |
| "eval_steps_per_second": 0.962, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.5731242299079895, | |
| "learning_rate": 0.00012518612327508773, | |
| "loss": 0.3443, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.6886520981788635, | |
| "learning_rate": 0.00012229356499456783, | |
| "loss": 0.3388, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.3337441086769104, | |
| "eval_runtime": 271.0416, | |
| "eval_samples_per_second": 7.693, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.5007095336914062, | |
| "learning_rate": 0.00011938123964603922, | |
| "loss": 0.3375, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.49403801560401917, | |
| "learning_rate": 0.00011645172950529504, | |
| "loss": 0.3091, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.36014652252197266, | |
| "learning_rate": 0.00011350763208539337, | |
| "loss": 0.256, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 0.33549007773399353, | |
| "eval_runtime": 271.1529, | |
| "eval_samples_per_second": 7.689, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.4871821403503418, | |
| "learning_rate": 0.0001105515578335165, | |
| "loss": 0.2534, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.4773302376270294, | |
| "learning_rate": 0.00010758612781636189, | |
| "loss": 0.2485, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.3336337208747864, | |
| "eval_runtime": 270.9871, | |
| "eval_samples_per_second": 7.694, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.4584294259548187, | |
| "learning_rate": 0.00010461397139611717, | |
| "loss": 0.2621, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.45226892828941345, | |
| "learning_rate": 0.00010163772389907971, | |
| "loss": 0.244, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.5343567728996277, | |
| "learning_rate": 9.86600242789879e-05, | |
| "loss": 0.2452, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.33007845282554626, | |
| "eval_runtime": 271.0147, | |
| "eval_samples_per_second": 7.693, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.4986325800418854, | |
| "learning_rate": 9.568351277713618e-05, | |
| "loss": 0.2525, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.4909712076187134, | |
| "learning_rate": 9.271082858134854e-05, | |
| "loss": 0.2573, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.3278447985649109, | |
| "eval_runtime": 271.052, | |
| "eval_samples_per_second": 7.692, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.4675891697406769, | |
| "learning_rate": 8.974460748588577e-05, | |
| "loss": 0.2516, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.5919708013534546, | |
| "learning_rate": 8.678747955436209e-05, | |
| "loss": 0.2459, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.5164061784744263, | |
| "learning_rate": 8.384206678774267e-05, | |
| "loss": 0.245, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.3246319591999054, | |
| "eval_runtime": 270.8895, | |
| "eval_samples_per_second": 7.697, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.5498049855232239, | |
| "learning_rate": 8.091098079949022e-05, | |
| "loss": 0.244, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.40771761536598206, | |
| "learning_rate": 7.79968204999218e-05, | |
| "loss": 0.2446, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 0.32402417063713074, | |
| "eval_runtime": 270.9055, | |
| "eval_samples_per_second": 7.696, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.4820304811000824, | |
| "learning_rate": 7.510216979182932e-05, | |
| "loss": 0.2485, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.40890711545944214, | |
| "learning_rate": 7.222959527940643e-05, | |
| "loss": 0.2426, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.4243795573711395, | |
| "learning_rate": 6.93816439925141e-05, | |
| "loss": 0.2416, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 0.32116860151290894, | |
| "eval_runtime": 270.8886, | |
| "eval_samples_per_second": 7.697, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.5360056161880493, | |
| "learning_rate": 6.656084112830165e-05, | |
| "loss": 0.2454, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.5155255198478699, | |
| "learning_rate": 6.376968781218665e-05, | |
| "loss": 0.2432, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.32005202770233154, | |
| "eval_runtime": 271.08, | |
| "eval_samples_per_second": 7.691, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.564046323299408, | |
| "learning_rate": 6.101065888017833e-05, | |
| "loss": 0.2414, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.45059406757354736, | |
| "learning_rate": 5.828620068451111e-05, | |
| "loss": 0.2408, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.5122149586677551, | |
| "learning_rate": 5.559872892453375e-05, | |
| "loss": 0.242, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.316841185092926, | |
| "eval_runtime": 271.0293, | |
| "eval_samples_per_second": 7.693, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.48864319920539856, | |
| "learning_rate": 5.29506265047779e-05, | |
| "loss": 0.2432, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.603583812713623, | |
| "learning_rate": 5.034424142210443e-05, | |
| "loss": 0.231, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 0.3156278729438782, | |
| "eval_runtime": 271.0109, | |
| "eval_samples_per_second": 7.693, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.5807139873504639, | |
| "learning_rate": 4.778188468380169e-05, | |
| "loss": 0.2425, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.4968738555908203, | |
| "learning_rate": 4.526582825848131e-05, | |
| "loss": 0.2362, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.6385018825531006, | |
| "learning_rate": 4.2798303061588404e-05, | |
| "loss": 0.2369, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.3140126168727875, | |
| "eval_runtime": 270.9649, | |
| "eval_samples_per_second": 7.695, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.5020663738250732, | |
| "learning_rate": 4.038149697731247e-05, | |
| "loss": 0.2425, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.5276768207550049, | |
| "learning_rate": 3.801755291865307e-05, | |
| "loss": 0.2405, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 0.3110227882862091, | |
| "eval_runtime": 270.8888, | |
| "eval_samples_per_second": 7.697, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.5092354416847229, | |
| "learning_rate": 3.570856692735976e-05, | |
| "loss": 0.2356, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.4134100079536438, | |
| "learning_rate": 3.3456586315431874e-05, | |
| "loss": 0.2397, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.41335973143577576, | |
| "learning_rate": 3.126360784982532e-05, | |
| "loss": 0.2263, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.309181272983551, | |
| "eval_runtime": 270.9592, | |
| "eval_samples_per_second": 7.695, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.6216692924499512, | |
| "learning_rate": 2.9131575981976245e-05, | |
| "loss": 0.2371, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.6529776453971863, | |
| "learning_rate": 2.7062381123711532e-05, | |
| "loss": 0.2324, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.3087258040904999, | |
| "eval_runtime": 270.9376, | |
| "eval_samples_per_second": 7.695, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.41469648480415344, | |
| "learning_rate": 2.505785797107446e-05, | |
| "loss": 0.2148, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.5092002749443054, | |
| "learning_rate": 2.3119783877552126e-05, | |
| "loss": 0.2287, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.6236806511878967, | |
| "learning_rate": 2.1249877278146868e-05, | |
| "loss": 0.2203, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 0.30838343501091003, | |
| "eval_runtime": 270.9479, | |
| "eval_samples_per_second": 7.695, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.5142087936401367, | |
| "learning_rate": 1.944979616568885e-05, | |
| "loss": 0.2287, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.5550097227096558, | |
| "learning_rate": 1.7721136620741218e-05, | |
| "loss": 0.223, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.30595675110816956, | |
| "eval_runtime": 271.0761, | |
| "eval_samples_per_second": 7.692, | |
| "eval_steps_per_second": 0.963, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.5284961462020874, | |
| "learning_rate": 1.6065431396400986e-05, | |
| "loss": 0.2268, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.7719703912734985, | |
| "learning_rate": 1.4484148559250588e-05, | |
| "loss": 0.2406, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.5748826861381531, | |
| "learning_rate": 1.2978690187665133e-05, | |
| "loss": 0.2218, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.3054625391960144, | |
| "eval_runtime": 271.0494, | |
| "eval_samples_per_second": 7.692, | |
| "eval_steps_per_second": 0.963, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.4736625850200653, | |
| "learning_rate": 1.1550391128629501e-05, | |
| "loss": 0.2362, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.6235111951828003, | |
| "learning_rate": 1.0200517814167632e-05, | |
| "loss": 0.2278, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 0.30488070845603943, | |
| "eval_runtime": 271.0127, | |
| "eval_samples_per_second": 7.693, | |
| "eval_steps_per_second": 0.963, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.5903782248497009, | |
| "learning_rate": 8.930267138433335e-06, | |
| "loss": 0.2315, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.5188658833503723, | |
| "learning_rate": 7.740765396458482e-06, | |
| "loss": 0.2366, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.6277506351470947, | |
| "learning_rate": 6.633067285499228e-06, | |
| "loss": 0.2229, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.30428797006607056, | |
| "eval_runtime": 270.9982, | |
| "eval_samples_per_second": 7.694, | |
| "eval_steps_per_second": 0.963, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.5176372528076172, | |
| "learning_rate": 5.6081549698661305e-06, | |
| "loss": 0.2277, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.5887135863304138, | |
| "learning_rate": 4.666937210067012e-06, | |
| "loss": 0.2189, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 0.3041435480117798, | |
| "eval_runtime": 270.8969, | |
| "eval_samples_per_second": 7.697, | |
| "eval_steps_per_second": 0.963, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.5156753063201904, | |
| "learning_rate": 3.8102485570350123e-06, | |
| "loss": 0.2281, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.5229103565216064, | |
| "learning_rate": 3.0388486121560313e-06, | |
| "loss": 0.2238, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.6205452084541321, | |
| "learning_rate": 2.3534213537518832e-06, | |
| "loss": 0.23, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.3037714958190918, | |
| "eval_runtime": 270.8992, | |
| "eval_samples_per_second": 7.697, | |
| "eval_steps_per_second": 0.963, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.502139151096344, | |
| "learning_rate": 1.7545745306162487e-06, | |
| "loss": 0.2298, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.590472936630249, | |
| "learning_rate": 1.242839123141104e-06, | |
| "loss": 0.2235, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.3036145567893982, | |
| "eval_runtime": 271.0048, | |
| "eval_samples_per_second": 7.694, | |
| "eval_steps_per_second": 0.963, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.5944371223449707, | |
| "learning_rate": 8.186688725116187e-07, | |
| "loss": 0.2343, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.6346670389175415, | |
| "learning_rate": 4.824398783867423e-07, | |
| "loss": 0.2401, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.6338953375816345, | |
| "learning_rate": 2.3445026542239235e-07, | |
| "loss": 0.2368, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.3034871220588684, | |
| "eval_runtime": 271.0599, | |
| "eval_samples_per_second": 7.692, | |
| "eval_steps_per_second": 0.963, | |
| "step": 2300 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 2344, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 1.2020124951876895e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |